linux/mm/internal.h

1447 lines
44 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/* internal.h: mm/ internal definitions
*
* Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*/
#ifndef __MM_INTERNAL_H
#define __MM_INTERNAL_H
#include <linux/fs.h>
mm: move internal core VMA manipulation functions to own file This patch introduces vma.c and moves internal core VMA manipulation functions to this file from mmap.c. This allows us to isolate VMA functionality in a single place such that we can create userspace testing code that invokes this functionality in an environment where we can implement simple unit tests of core functionality. This patch ensures that core VMA functionality is explicitly marked as such by its presence in mm/vma.h. It also places the header includes required by vma.c in vma_internal.h, which is simply imported by vma.c. This makes the VMA functionality testable, as userland testing code can simply stub out functionality as required. Link: https://lkml.kernel.org/r/c77a6aafb4c42aaadb8e7271a853658cbdca2e22.1722251717.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Brendan Higgins <brendanhiggins@google.com> Cc: Christian Brauner <brauner@kernel.org> Cc: David Gow <davidgow@google.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Jan Kara <jack@suse.cz> Cc: Kees Cook <kees@kernel.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Rae Moar <rmoar@google.com> Cc: SeongJae Park <sj@kernel.org> Cc: Shuah Khan <shuah@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Pengfei Xu <pengfei.xu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-07-29 11:50:38 +00:00
#include <linux/khugepaged.h>
#include <linux/mm.h>
mm: move internal core VMA manipulation functions to own file This patch introduces vma.c and moves internal core VMA manipulation functions to this file from mmap.c. This allows us to isolate VMA functionality in a single place such that we can create userspace testing code that invokes this functionality in an environment where we can implement simple unit tests of core functionality. This patch ensures that core VMA functionality is explicitly marked as such by its presence in mm/vma.h. It also places the header includes required by vma.c in vma_internal.h, which is simply imported by vma.c. This makes the VMA functionality testable, as userland testing code can simply stub out functionality as required. Link: https://lkml.kernel.org/r/c77a6aafb4c42aaadb8e7271a853658cbdca2e22.1722251717.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Brendan Higgins <brendanhiggins@google.com> Cc: Christian Brauner <brauner@kernel.org> Cc: David Gow <davidgow@google.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Jan Kara <jack@suse.cz> Cc: Kees Cook <kees@kernel.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Rae Moar <rmoar@google.com> Cc: SeongJae Park <sj@kernel.org> Cc: Shuah Khan <shuah@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Pengfei Xu <pengfei.xu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-07-29 11:50:38 +00:00
#include <linux/mm_inline.h>
thp: reintroduce split_huge_page() This patch adds implementation of split_huge_page() for new refcountings. Unlike previous implementation, new split_huge_page() can fail if somebody holds GUP pin on the page. It also means that pin on page would prevent it from bening split under you. It makes situation in many places much cleaner. The basic scheme of split_huge_page(): - Check that sum of mapcounts of all subpage is equal to page_count() plus one (caller pin). Foll off with -EBUSY. This way we can avoid useless PMD-splits. - Freeze the page counters by splitting all PMD and setup migration PTEs. - Re-check sum of mapcounts against page_count(). Page's counts are stable now. -EBUSY if page is pinned. - Split compound page. - Unfreeze the page by removing migration entries. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Sasha Levin <sasha.levin@oracle.com> Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Jerome Marchand <jmarchan@redhat.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Steve Capper <steve.capper@linaro.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:54:10 +00:00
#include <linux/pagemap.h>
#include <linux/rmap.h>
mm: swap: free_swap_and_cache_nr() as batched free_swap_and_cache() Now that we no longer have a convenient flag in the cluster to determine if a folio is large, free_swap_and_cache() will take a reference and lock a large folio much more often, which could lead to contention and (e.g.) failure to split large folios, etc. Let's solve that problem by batch freeing swap and cache with a new function, free_swap_and_cache_nr(), to free a contiguous range of swap entries together. This allows us to first drop a reference to each swap slot before we try to release the cache folio. This means we only try to release the folio once, only taking the reference and lock once - much better than the previous 512 times for the 2M THP case. Contiguous swap entries are gathered in zap_pte_range() and madvise_free_pte_range() in a similar way to how present ptes are already gathered in zap_pte_range(). While we are at it, let's simplify by converting the return type of both functions to void. The return value was used only by zap_pte_range() to print a bad pte, and was ignored by everyone else, so the extra reporting wasn't exactly guaranteed. We will still get the warning with most of the information from get_swap_device(). With the batch version, we wouldn't know which pte was bad anyway so could print the wrong one. [ryan.roberts@arm.com: fix a build warning on parisc] Link: https://lkml.kernel.org/r/20240409111840.3173122-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20240408183946.2991168-3-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Barry Song <21cnbao@gmail.com> Cc: Barry Song <v-songbaohua@oppo.com> Cc: Chris Li <chrisl@kernel.org> Cc: Gao Xiang <xiang@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-08 18:39:41 +00:00
#include <linux/swap.h>
#include <linux/swapops.h>
mm: attempt to batch free swap entries for zap_pte_range() Zhiguo reported that swap release could be a serious bottleneck during process exits[1]. With mTHP, we have the opportunity to batch free swaps. Thanks to the work of Chris and Kairui[2], I was able to achieve this optimization with minimal code changes by building on their efforts. If swap_count is 1, which is likely true as most anon memory are private, we can free all contiguous swap slots all together. Ran the below test program for measuring the bandwidth of munmap using zRAM and 64KiB mTHP: #include <sys/mman.h> #include <sys/time.h> #include <stdlib.h> unsigned long long tv_to_ms(struct timeval tv) { return tv.tv_sec * 1000 + tv.tv_usec / 1000; } main() { struct timeval tv_b, tv_e; int i; #define SIZE 1024*1024*1024 void *p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (!p) { perror("fail to get memory"); exit(-1); } madvise(p, SIZE, MADV_HUGEPAGE); memset(p, 0x11, SIZE); /* write to get mem */ madvise(p, SIZE, MADV_PAGEOUT); gettimeofday(&tv_b, NULL); munmap(p, SIZE); gettimeofday(&tv_e, NULL); printf("munmap in bandwidth: %ld bytes/ms\n", SIZE/(tv_to_ms(tv_e) - tv_to_ms(tv_b))); } The result is as below (munmap bandwidth): mm-unstable mm-unstable-with-patch round1 21053761 63161283 round2 21053761 63161283 round3 21053761 63161283 round4 20648881 67108864 round5 20648881 67108864 munmap bandwidth becomes 3X faster. [1] https://lore.kernel.org/linux-mm/20240731133318.527-1-justinjiang@vivo.com/ [2] https://lore.kernel.org/linux-mm/20240730-swap-allocator-v5-0-cb9c148b9297@kernel.org/ [v-songbaohua@oppo.com: check all swaps belong to same swap_cgroup in swap_pte_batch()] Link: https://lkml.kernel.org/r/20240815215308.55233-1-21cnbao@gmail.com [hughd@google.com: add mem_cgroup_disabled() check] Link: https://lkml.kernel.org/r/33f34a88-0130-5444-9b84-93198eeb50e7@google.com [21cnbao@gmail.com: add missing zswap_invalidate()] Link: https://lkml.kernel.org/r/20240821054921.43468-1-21cnbao@gmail.com Link: https://lkml.kernel.org/r/20240807215859.57491-3-21cnbao@gmail.com Signed-off-by: Barry Song <v-songbaohua@oppo.com> Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Kairui Song <kasong@tencent.com> Cc: Chris Li <chrisl@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kalesh Singh <kaleshsingh@google.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Barry Song <baohua@kernel.org> Cc: Yosry Ahmed <yosryahmed@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-08-07 21:58:59 +00:00
#include <linux/swap_cgroup.h>
mm, printk: introduce new format string for flags In mm we use several kinds of flags bitfields that are sometimes printed for debugging purposes, or exported to userspace via sysfs. To make them easier to interpret independently on kernel version and config, we want to dump also the symbolic flag names. So far this has been done with repeated calls to pr_cont(), which is unreliable on SMP, and not usable for e.g. sysfs export. To get a more reliable and universal solution, this patch extends printk() format string for pointers to handle the page flags (%pGp), gfp_flags (%pGg) and vma flags (%pGv). Existing users of dump_flag_names() are converted and simplified. It would be possible to pass flags by value instead of pointer, but the %p format string for pointers already has extensions for various kernel structures, so it's a good fit, and the extra indirection in a non-critical path is negligible. [linux@rasmusvillemoes.dk: lots of good implementation suggestions] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:56 +00:00
#include <linux/tracepoint-defs.h>
mm: move internal core VMA manipulation functions to own file This patch introduces vma.c and moves internal core VMA manipulation functions to this file from mmap.c. This allows us to isolate VMA functionality in a single place such that we can create userspace testing code that invokes this functionality in an environment where we can implement simple unit tests of core functionality. This patch ensures that core VMA functionality is explicitly marked as such by its presence in mm/vma.h. It also places the header includes required by vma.c in vma_internal.h, which is simply imported by vma.c. This makes the VMA functionality testable, as userland testing code can simply stub out functionality as required. Link: https://lkml.kernel.org/r/c77a6aafb4c42aaadb8e7271a853658cbdca2e22.1722251717.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Brendan Higgins <brendanhiggins@google.com> Cc: Christian Brauner <brauner@kernel.org> Cc: David Gow <davidgow@google.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Jan Kara <jack@suse.cz> Cc: Kees Cook <kees@kernel.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Rae Moar <rmoar@google.com> Cc: SeongJae Park <sj@kernel.org> Cc: Shuah Khan <shuah@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Pengfei Xu <pengfei.xu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-07-29 11:50:38 +00:00
/* Internal core VMA manipulation functions. */
#include "vma.h"
struct folio_batch;
/*
* The set of flags that only affect watermark checking and reclaim
* behaviour. This is used by the MM to obey the caller constraints
* about IO, FS and watermark checking while ignoring placement
* hints such as HIGHMEM usage.
*/
#define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\
mm, tree wide: replace __GFP_REPEAT by __GFP_RETRY_MAYFAIL with more useful semantic __GFP_REPEAT was designed to allow retry-but-eventually-fail semantic to the page allocator. This has been true but only for allocations requests larger than PAGE_ALLOC_COSTLY_ORDER. It has been always ignored for smaller sizes. This is a bit unfortunate because there is no way to express the same semantic for those requests and they are considered too important to fail so they might end up looping in the page allocator for ever, similarly to GFP_NOFAIL requests. Now that the whole tree has been cleaned up and accidental or misled usage of __GFP_REPEAT flag has been removed for !costly requests we can give the original flag a better name and more importantly a more useful semantic. Let's rename it to __GFP_RETRY_MAYFAIL which tells the user that the allocator would try really hard but there is no promise of a success. This will work independent of the order and overrides the default allocator behavior. Page allocator users have several levels of guarantee vs. cost options (take GFP_KERNEL as an example) - GFP_KERNEL & ~__GFP_RECLAIM - optimistic allocation without _any_ attempt to free memory at all. The most light weight mode which even doesn't kick the background reclaim. Should be used carefully because it might deplete the memory and the next user might hit the more aggressive reclaim - GFP_KERNEL & ~__GFP_DIRECT_RECLAIM (or GFP_NOWAIT)- optimistic allocation without any attempt to free memory from the current context but can wake kswapd to reclaim memory if the zone is below the low watermark. Can be used from either atomic contexts or when the request is a performance optimization and there is another fallback for a slow path. - (GFP_KERNEL|__GFP_HIGH) & ~__GFP_DIRECT_RECLAIM (aka GFP_ATOMIC) - non sleeping allocation with an expensive fallback so it can access some portion of memory reserves. Usually used from interrupt/bh context with an expensive slow path fallback. - GFP_KERNEL - both background and direct reclaim are allowed and the _default_ page allocator behavior is used. That means that !costly allocation requests are basically nofail but there is no guarantee of that behavior so failures have to be checked properly by callers (e.g. OOM killer victim is allowed to fail currently). - GFP_KERNEL | __GFP_NORETRY - overrides the default allocator behavior and all allocation requests fail early rather than cause disruptive reclaim (one round of reclaim in this implementation). The OOM killer is not invoked. - GFP_KERNEL | __GFP_RETRY_MAYFAIL - overrides the default allocator behavior and all allocation requests try really hard. The request will fail if the reclaim cannot make any progress. The OOM killer won't be triggered. - GFP_KERNEL | __GFP_NOFAIL - overrides the default allocator behavior and all allocation requests will loop endlessly until they succeed. This might be really dangerous especially for larger orders. Existing users of __GFP_REPEAT are changed to __GFP_RETRY_MAYFAIL because they already had their semantic. No new users are added. __alloc_pages_slowpath is changed to bail out for __GFP_RETRY_MAYFAIL if there is no progress and we have already passed the OOM point. This means that all the reclaim opportunities have been exhausted except the most disruptive one (the OOM killer) and a user defined fallback behavior is more sensible than keep retrying in the page allocator. [akpm@linux-foundation.org: fix arch/sparc/kernel/mdesc.c] [mhocko@suse.com: semantic fix] Link: http://lkml.kernel.org/r/20170626123847.GM11534@dhcp22.suse.cz [mhocko@kernel.org: address other thing spotted by Vlastimil] Link: http://lkml.kernel.org/r/20170626124233.GN11534@dhcp22.suse.cz Link: http://lkml.kernel.org/r/20170623085345.11304-3-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Alex Belits <alex.belits@cavium.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Darrick J. Wong <darrick.wong@oracle.com> Cc: David Daney <david.daney@cavium.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: NeilBrown <neilb@suse.com> Cc: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-12 21:36:45 +00:00
__GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\
__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\
mm: discard __GFP_ATOMIC __GFP_ATOMIC serves little purpose. Its main effect is to set ALLOC_HARDER which adds a few little boosts to increase the chance of an allocation succeeding, one of which is to lower the water-mark at which it will succeed. It is *always* paired with __GFP_HIGH which sets ALLOC_HIGH which also adjusts this watermark. It is probable that other users of __GFP_HIGH should benefit from the other little bonuses that __GFP_ATOMIC gets. __GFP_ATOMIC also gives a warning if used with __GFP_DIRECT_RECLAIM. There is little point to this. We already get a might_sleep() warning if __GFP_DIRECT_RECLAIM is set. __GFP_ATOMIC allows the "watermark_boost" to be side-stepped. It is probable that testing ALLOC_HARDER is a better fit here. __GFP_ATOMIC is used by tegra-smmu.c to check if the allocation might sleep. This should test __GFP_DIRECT_RECLAIM instead. This patch: - removes __GFP_ATOMIC - allows __GFP_HIGH allocations to ignore watermark boosting as well as GFP_ATOMIC requests. - makes other adjustments as suggested by the above. The net result is not change to GFP_ATOMIC allocations. Other allocations that use __GFP_HIGH will benefit from a few different extra privileges. This affects: xen, dm, md, ntfs3 the vermillion frame buffer hibernation ksm swap all of which likely produce more benefit than cost if these selected allocation are more likely to succeed quickly. [mgorman: Minor adjustments to rework on top of a series] Link: https://lkml.kernel.org/r/163712397076.13692.4727608274002939094@noble.neil.brown.name Link: https://lkml.kernel.org/r/20230113111217.14134-7-mgorman@techsingularity.net Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thierry Reding <thierry.reding@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-01-13 11:12:17 +00:00
__GFP_NOLOCKDEP)
/* The GFP flags allowed during early boot */
#define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS))
/* Control allocation cpuset and node placement constraints */
#define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE)
/* Do not use these with a slab allocator */
#define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK)
/*
* Different from WARN_ON_ONCE(), no warning will be issued
* when we specify __GFP_NOWARN.
*/
#define WARN_ON_ONCE_GFP(cond, gfp) ({ \
static bool __section(".data.once") __warned; \
int __ret_warn_once = !!(cond); \
\
if (unlikely(!(gfp & __GFP_NOWARN) && __ret_warn_once && !__warned)) { \
__warned = true; \
WARN_ON(1); \
} \
unlikely(__ret_warn_once); \
})
2016-12-25 03:00:30 +00:00
void page_writeback_init(void);
/*
* If a 16GB hugetlb folio were mapped by PTEs of all of its 4kB pages,
* its nr_pages_mapped would be 0x400000: choose the ENTIRELY_MAPPED bit
* above that range, instead of 2*(PMD_SIZE/PAGE_SIZE). Hugetlb currently
* leaves nr_pages_mapped at 0, but avoid surprise if it participates later.
*/
#define ENTIRELY_MAPPED 0x800000
#define FOLIO_PAGES_MAPPED (ENTIRELY_MAPPED - 1)
/*
* Flags passed to __show_mem() and show_free_areas() to suppress output in
* various contexts.
*/
#define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */
/*
* How many individual pages have an elevated _mapcount. Excludes
* the folio's entire_mapcount.
mm: track mapcount of large folios in single value Let's track the mapcount of large folios in a single value. The mapcount of a large folio currently corresponds to the sum of the entire mapcount and all page mapcounts. This sum is what we actually want to know in folio_mapcount() and it is also sufficient for implementing folio_mapped(). With PTE-mapped THP becoming more important and more widely used, we want to avoid looping over all pages of a folio just to obtain the mapcount of large folios. The comment "In the common case, avoid the loop when no pages mapped by PTE" in folio_total_mapcount() does no longer hold for mTHP that are always mapped by PTE. Further, we are planning on using folio_mapcount() more frequently, and might even want to remove page mapcounts for large folios in some kernel configs. Therefore, allow for reading the mapcount of large folios efficiently and atomically without looping over any pages. Maintain the mapcount also for hugetlb pages for simplicity. Use the new mapcount to implement folio_mapcount() and folio_mapped(). Make page_mapped() simply call folio_mapped(). We can now get rid of folio_large_is_mapped(). _nr_pages_mapped is now only used in rmap code and for debugging purposes. Keep folio_nr_pages_mapped() around, but document that its use should be limited to rmap internals and debugging purposes. This change implies one additional atomic add/sub whenever mapping/unmapping (parts of) a large folio. As we now batch RMAP operations for PTE-mapped THP during fork(), during unmap/zap, and when PTE-remapping a PMD-mapped THP, and we adjust the large mapcount for a PTE batch only once, the added overhead in the common case is small. Only when unmapping individual pages of a large folio (e.g., during COW), the overhead might be bigger in comparison, but it's essentially one additional atomic operation. Note that before the new mapcount would overflow, already our refcount would overflow: each mapping requires a folio reference. Extend the focumentation of folio_mapcount(). Link: https://lkml.kernel.org/r/20240409192301.907377-5-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Reviewed-by: Yin Fengwei <fengwei.yin@intel.com> Cc: Chris Zankel <chris@zankel.net> Cc: Hugh Dickins <hughd@google.com> Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Muchun Song <muchun.song@linux.dev> Cc: Naoya Horiguchi <nao.horiguchi@gmail.com> Cc: Peter Xu <peterx@redhat.com> Cc: Richard Chang <richardycc@google.com> Cc: Rich Felker <dalias@libc.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-09 19:22:47 +00:00
*
* Don't use this function outside of debugging code.
*/
static inline int folio_nr_pages_mapped(const struct folio *folio)
{
return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED;
}
arm64: mm: swap: support THP_SWAP on hardware with MTE Commit d0637c505f8a1 ("arm64: enable THP_SWAP for arm64") brings up THP_SWAP on ARM64, but it doesn't enable THP_SWP on hardware with MTE as the MTE code works with the assumption tags save/restore is always handling a folio with only one page. The limitation should be removed as more and more ARM64 SoCs have this feature. Co-existence of MTE and THP_SWAP becomes more and more important. This patch makes MTE tags saving support large folios, then we don't need to split large folios into base pages for swapping out on ARM64 SoCs with MTE any more. arch_prepare_to_swap() should take folio rather than page as parameter because we support THP swap-out as a whole. It saves tags for all pages in a large folio. As now we are restoring tags based-on folio, in arch_swap_restore(), we may increase some extra loops and early-exitings while refaulting a large folio which is still in swapcache in do_swap_page(). In case a large folio has nr pages, do_swap_page() will only set the PTE of the particular page which is causing the page fault. Thus do_swap_page() runs nr times, and each time, arch_swap_restore() will loop nr times for those subpages in the folio. So right now the algorithmic complexity becomes O(nr^2). Once we support mapping large folios in do_swap_page(), extra loops and early-exitings will decrease while not being completely removed as a large folio might get partially tagged in corner cases such as, 1. a large folio in swapcache can be partially unmapped, thus, MTE tags for the unmapped pages will be invalidated; 2. users might use mprotect() to set MTEs on a part of a large folio. arch_thp_swp_supported() is dropped since ARM64 MTE was the only one who needed it. Link: https://lkml.kernel.org/r/20240322114136.61386-2-21cnbao@gmail.com Signed-off-by: Barry Song <v-songbaohua@oppo.com> Reviewed-by: Steven Price <steven.price@arm.com> Acked-by: Chris Li <chrisl@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: David Hildenbrand <david@redhat.com> Cc: Kemeng Shi <shikemeng@huaweicloud.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Peter Collingbourne <pcc@google.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Peter Xu <peterx@redhat.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: "Mike Rapoport (IBM)" <rppt@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> Cc: Rick Edgecombe <rick.p.edgecombe@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-03-22 11:41:36 +00:00
/*
* Retrieve the first entry of a folio based on a provided entry within the
* folio. We cannot rely on folio->swap as there is no guarantee that it has
* been initialized. Used for calling arch_swap_restore()
*/
static inline swp_entry_t folio_swap(swp_entry_t entry,
const struct folio *folio)
arm64: mm: swap: support THP_SWAP on hardware with MTE Commit d0637c505f8a1 ("arm64: enable THP_SWAP for arm64") brings up THP_SWAP on ARM64, but it doesn't enable THP_SWP on hardware with MTE as the MTE code works with the assumption tags save/restore is always handling a folio with only one page. The limitation should be removed as more and more ARM64 SoCs have this feature. Co-existence of MTE and THP_SWAP becomes more and more important. This patch makes MTE tags saving support large folios, then we don't need to split large folios into base pages for swapping out on ARM64 SoCs with MTE any more. arch_prepare_to_swap() should take folio rather than page as parameter because we support THP swap-out as a whole. It saves tags for all pages in a large folio. As now we are restoring tags based-on folio, in arch_swap_restore(), we may increase some extra loops and early-exitings while refaulting a large folio which is still in swapcache in do_swap_page(). In case a large folio has nr pages, do_swap_page() will only set the PTE of the particular page which is causing the page fault. Thus do_swap_page() runs nr times, and each time, arch_swap_restore() will loop nr times for those subpages in the folio. So right now the algorithmic complexity becomes O(nr^2). Once we support mapping large folios in do_swap_page(), extra loops and early-exitings will decrease while not being completely removed as a large folio might get partially tagged in corner cases such as, 1. a large folio in swapcache can be partially unmapped, thus, MTE tags for the unmapped pages will be invalidated; 2. users might use mprotect() to set MTEs on a part of a large folio. arch_thp_swp_supported() is dropped since ARM64 MTE was the only one who needed it. Link: https://lkml.kernel.org/r/20240322114136.61386-2-21cnbao@gmail.com Signed-off-by: Barry Song <v-songbaohua@oppo.com> Reviewed-by: Steven Price <steven.price@arm.com> Acked-by: Chris Li <chrisl@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: David Hildenbrand <david@redhat.com> Cc: Kemeng Shi <shikemeng@huaweicloud.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Peter Collingbourne <pcc@google.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Peter Xu <peterx@redhat.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: "Mike Rapoport (IBM)" <rppt@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> Cc: Rick Edgecombe <rick.p.edgecombe@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-03-22 11:41:36 +00:00
{
swp_entry_t swap = {
.val = ALIGN_DOWN(entry.val, folio_nr_pages(folio)),
};
return swap;
}
static inline void *folio_raw_mapping(const struct folio *folio)
{
unsigned long mapping = (unsigned long)folio->mapping;
return (void *)(mapping & ~PAGE_MAPPING_FLAGS);
}
#ifdef CONFIG_MMU
/* Flags for folio_pte_batch(). */
typedef int __bitwise fpb_t;
/* Compare PTEs after pte_mkclean(), ignoring the dirty bit. */
#define FPB_IGNORE_DIRTY ((__force fpb_t)BIT(0))
/* Compare PTEs after pte_clear_soft_dirty(), ignoring the soft-dirty bit. */
#define FPB_IGNORE_SOFT_DIRTY ((__force fpb_t)BIT(1))
static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags)
{
if (flags & FPB_IGNORE_DIRTY)
pte = pte_mkclean(pte);
if (likely(flags & FPB_IGNORE_SOFT_DIRTY))
pte = pte_clear_soft_dirty(pte);
return pte_wrprotect(pte_mkold(pte));
}
/**
* folio_pte_batch - detect a PTE batch for a large folio
* @folio: The large folio to detect a PTE batch for.
* @addr: The user virtual address the first page is mapped at.
* @start_ptep: Page table pointer for the first entry.
* @pte: Page table entry for the first page.
* @max_nr: The maximum number of table entries to consider.
* @flags: Flags to modify the PTE batch semantics.
* @any_writable: Optional pointer to indicate whether any entry except the
* first one is writable.
mm: madvise: avoid split during MADV_PAGEOUT and MADV_COLD Rework madvise_cold_or_pageout_pte_range() to avoid splitting any large folio that is fully and contiguously mapped in the pageout/cold vm range. This change means that large folios will be maintained all the way to swap storage. This both improves performance during swap-out, by eliding the cost of splitting the folio, and sets us up nicely for maintaining the large folio when it is swapped back in (to be covered in a separate series). Folios that are not fully mapped in the target range are still split, but note that behavior is changed so that if the split fails for any reason (folio locked, shared, etc) we now leave it as is and move to the next pte in the range and continue work on the proceeding folios. Previously any failure of this sort would cause the entire operation to give up and no folios mapped at higher addresses were paged out or made cold. Given large folios are becoming more common, this old behavior would have likely lead to wasted opportunities. While we are at it, change the code that clears young from the ptes to use ptep_test_and_clear_young(), via the new mkold_ptes() batch helper function. This is more efficent than get_and_clear/modify/set, especially for contpte mappings on arm64, where the old approach would require unfolding/refolding and the new approach can be done in place. Link: https://lkml.kernel.org/r/20240408183946.2991168-8-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Reviewed-by: Barry Song <v-songbaohua@oppo.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Barry Song <21cnbao@gmail.com> Cc: Chris Li <chrisl@kernel.org> Cc: Gao Xiang <xiang@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-08 18:39:46 +00:00
* @any_young: Optional pointer to indicate whether any entry except the
* first one is young.
* @any_dirty: Optional pointer to indicate whether any entry except the
* first one is dirty.
*
* Detect a PTE batch: consecutive (present) PTEs that map consecutive
* pages of the same large folio.
*
* All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN,
* the accessed bit, writable bit, dirty bit (with FPB_IGNORE_DIRTY) and
* soft-dirty bit (with FPB_IGNORE_SOFT_DIRTY).
*
* start_ptep must map any page of the folio. max_nr must be at least one and
* must be limited by the caller so scanning cannot exceed a single page table.
*
* Return: the number of table entries in the batch.
*/
static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags,
bool *any_writable, bool *any_young, bool *any_dirty)
{
unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio);
const pte_t *end_ptep = start_ptep + max_nr;
pte_t expected_pte, *ptep;
bool writable, young, dirty;
int nr;
if (any_writable)
*any_writable = false;
mm: madvise: avoid split during MADV_PAGEOUT and MADV_COLD Rework madvise_cold_or_pageout_pte_range() to avoid splitting any large folio that is fully and contiguously mapped in the pageout/cold vm range. This change means that large folios will be maintained all the way to swap storage. This both improves performance during swap-out, by eliding the cost of splitting the folio, and sets us up nicely for maintaining the large folio when it is swapped back in (to be covered in a separate series). Folios that are not fully mapped in the target range are still split, but note that behavior is changed so that if the split fails for any reason (folio locked, shared, etc) we now leave it as is and move to the next pte in the range and continue work on the proceeding folios. Previously any failure of this sort would cause the entire operation to give up and no folios mapped at higher addresses were paged out or made cold. Given large folios are becoming more common, this old behavior would have likely lead to wasted opportunities. While we are at it, change the code that clears young from the ptes to use ptep_test_and_clear_young(), via the new mkold_ptes() batch helper function. This is more efficent than get_and_clear/modify/set, especially for contpte mappings on arm64, where the old approach would require unfolding/refolding and the new approach can be done in place. Link: https://lkml.kernel.org/r/20240408183946.2991168-8-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Reviewed-by: Barry Song <v-songbaohua@oppo.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Barry Song <21cnbao@gmail.com> Cc: Chris Li <chrisl@kernel.org> Cc: Gao Xiang <xiang@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-08 18:39:46 +00:00
if (any_young)
*any_young = false;
if (any_dirty)
*any_dirty = false;
VM_WARN_ON_FOLIO(!pte_present(pte), folio);
VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio);
VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio);
nr = pte_batch_hint(start_ptep, pte);
expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags);
ptep = start_ptep + nr;
while (ptep < end_ptep) {
pte = ptep_get(ptep);
if (any_writable)
writable = !!pte_write(pte);
mm: madvise: avoid split during MADV_PAGEOUT and MADV_COLD Rework madvise_cold_or_pageout_pte_range() to avoid splitting any large folio that is fully and contiguously mapped in the pageout/cold vm range. This change means that large folios will be maintained all the way to swap storage. This both improves performance during swap-out, by eliding the cost of splitting the folio, and sets us up nicely for maintaining the large folio when it is swapped back in (to be covered in a separate series). Folios that are not fully mapped in the target range are still split, but note that behavior is changed so that if the split fails for any reason (folio locked, shared, etc) we now leave it as is and move to the next pte in the range and continue work on the proceeding folios. Previously any failure of this sort would cause the entire operation to give up and no folios mapped at higher addresses were paged out or made cold. Given large folios are becoming more common, this old behavior would have likely lead to wasted opportunities. While we are at it, change the code that clears young from the ptes to use ptep_test_and_clear_young(), via the new mkold_ptes() batch helper function. This is more efficent than get_and_clear/modify/set, especially for contpte mappings on arm64, where the old approach would require unfolding/refolding and the new approach can be done in place. Link: https://lkml.kernel.org/r/20240408183946.2991168-8-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Reviewed-by: Barry Song <v-songbaohua@oppo.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Barry Song <21cnbao@gmail.com> Cc: Chris Li <chrisl@kernel.org> Cc: Gao Xiang <xiang@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-08 18:39:46 +00:00
if (any_young)
young = !!pte_young(pte);
if (any_dirty)
dirty = !!pte_dirty(pte);
pte = __pte_batch_clear_ignored(pte, flags);
if (!pte_same(pte, expected_pte))
break;
/*
* Stop immediately once we reached the end of the folio. In
* corner cases the next PFN might fall into a different
* folio.
*/
if (pte_pfn(pte) >= folio_end_pfn)
break;
if (any_writable)
*any_writable |= writable;
mm: madvise: avoid split during MADV_PAGEOUT and MADV_COLD Rework madvise_cold_or_pageout_pte_range() to avoid splitting any large folio that is fully and contiguously mapped in the pageout/cold vm range. This change means that large folios will be maintained all the way to swap storage. This both improves performance during swap-out, by eliding the cost of splitting the folio, and sets us up nicely for maintaining the large folio when it is swapped back in (to be covered in a separate series). Folios that are not fully mapped in the target range are still split, but note that behavior is changed so that if the split fails for any reason (folio locked, shared, etc) we now leave it as is and move to the next pte in the range and continue work on the proceeding folios. Previously any failure of this sort would cause the entire operation to give up and no folios mapped at higher addresses were paged out or made cold. Given large folios are becoming more common, this old behavior would have likely lead to wasted opportunities. While we are at it, change the code that clears young from the ptes to use ptep_test_and_clear_young(), via the new mkold_ptes() batch helper function. This is more efficent than get_and_clear/modify/set, especially for contpte mappings on arm64, where the old approach would require unfolding/refolding and the new approach can be done in place. Link: https://lkml.kernel.org/r/20240408183946.2991168-8-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Reviewed-by: Barry Song <v-songbaohua@oppo.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Barry Song <21cnbao@gmail.com> Cc: Chris Li <chrisl@kernel.org> Cc: Gao Xiang <xiang@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-08 18:39:46 +00:00
if (any_young)
*any_young |= young;
if (any_dirty)
*any_dirty |= dirty;
nr = pte_batch_hint(ptep, pte);
expected_pte = pte_advance_pfn(expected_pte, nr);
ptep += nr;
}
return min(ptep - start_ptep, max_nr);
}
mm: swap: free_swap_and_cache_nr() as batched free_swap_and_cache() Now that we no longer have a convenient flag in the cluster to determine if a folio is large, free_swap_and_cache() will take a reference and lock a large folio much more often, which could lead to contention and (e.g.) failure to split large folios, etc. Let's solve that problem by batch freeing swap and cache with a new function, free_swap_and_cache_nr(), to free a contiguous range of swap entries together. This allows us to first drop a reference to each swap slot before we try to release the cache folio. This means we only try to release the folio once, only taking the reference and lock once - much better than the previous 512 times for the 2M THP case. Contiguous swap entries are gathered in zap_pte_range() and madvise_free_pte_range() in a similar way to how present ptes are already gathered in zap_pte_range(). While we are at it, let's simplify by converting the return type of both functions to void. The return value was used only by zap_pte_range() to print a bad pte, and was ignored by everyone else, so the extra reporting wasn't exactly guaranteed. We will still get the warning with most of the information from get_swap_device(). With the batch version, we wouldn't know which pte was bad anyway so could print the wrong one. [ryan.roberts@arm.com: fix a build warning on parisc] Link: https://lkml.kernel.org/r/20240409111840.3173122-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20240408183946.2991168-3-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Barry Song <21cnbao@gmail.com> Cc: Barry Song <v-songbaohua@oppo.com> Cc: Chris Li <chrisl@kernel.org> Cc: Gao Xiang <xiang@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-08 18:39:41 +00:00
/**
mm: introduce pte_move_swp_offset() helper which can move offset bidirectionally There could arise a necessity to obtain the first pte_t from a swap pte_t located in the middle. For instance, this may occur within the context of do_swap_page(), where a page fault can potentially occur in any PTE of a large folio. To address this, the following patch introduces pte_move_swp_offset(), a function capable of bidirectional movement by a specified delta argument. Consequently, pte_next_swp_offset() will directly invoke it with delta = 1. Link: https://lkml.kernel.org/r/20240529082824.150954-4-21cnbao@gmail.com Signed-off-by: Barry Song <v-songbaohua@oppo.com> Suggested-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Reviewed-by: "Huang, Ying" <ying.huang@intel.com> Cc: Andreas Larsson <andreas@gaisler.com> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: Chris Li <chrisl@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Cc: Chuanhua Han <hanchuanhua@oppo.com> Cc: David Hildenbrand <david@redhat.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Gao Xiang <xiang@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kairui Song <kasong@tencent.com> Cc: Khalid Aziz <khalid.aziz@oracle.com> Cc: Len Brown <len.brown@intel.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-05-29 08:28:21 +00:00
* pte_move_swp_offset - Move the swap entry offset field of a swap pte
* forward or backward by delta
mm: swap: free_swap_and_cache_nr() as batched free_swap_and_cache() Now that we no longer have a convenient flag in the cluster to determine if a folio is large, free_swap_and_cache() will take a reference and lock a large folio much more often, which could lead to contention and (e.g.) failure to split large folios, etc. Let's solve that problem by batch freeing swap and cache with a new function, free_swap_and_cache_nr(), to free a contiguous range of swap entries together. This allows us to first drop a reference to each swap slot before we try to release the cache folio. This means we only try to release the folio once, only taking the reference and lock once - much better than the previous 512 times for the 2M THP case. Contiguous swap entries are gathered in zap_pte_range() and madvise_free_pte_range() in a similar way to how present ptes are already gathered in zap_pte_range(). While we are at it, let's simplify by converting the return type of both functions to void. The return value was used only by zap_pte_range() to print a bad pte, and was ignored by everyone else, so the extra reporting wasn't exactly guaranteed. We will still get the warning with most of the information from get_swap_device(). With the batch version, we wouldn't know which pte was bad anyway so could print the wrong one. [ryan.roberts@arm.com: fix a build warning on parisc] Link: https://lkml.kernel.org/r/20240409111840.3173122-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20240408183946.2991168-3-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Barry Song <21cnbao@gmail.com> Cc: Barry Song <v-songbaohua@oppo.com> Cc: Chris Li <chrisl@kernel.org> Cc: Gao Xiang <xiang@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-08 18:39:41 +00:00
* @pte: The initial pte state; is_swap_pte(pte) must be true and
* non_swap_entry() must be false.
mm: introduce pte_move_swp_offset() helper which can move offset bidirectionally There could arise a necessity to obtain the first pte_t from a swap pte_t located in the middle. For instance, this may occur within the context of do_swap_page(), where a page fault can potentially occur in any PTE of a large folio. To address this, the following patch introduces pte_move_swp_offset(), a function capable of bidirectional movement by a specified delta argument. Consequently, pte_next_swp_offset() will directly invoke it with delta = 1. Link: https://lkml.kernel.org/r/20240529082824.150954-4-21cnbao@gmail.com Signed-off-by: Barry Song <v-songbaohua@oppo.com> Suggested-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Reviewed-by: "Huang, Ying" <ying.huang@intel.com> Cc: Andreas Larsson <andreas@gaisler.com> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: Chris Li <chrisl@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Cc: Chuanhua Han <hanchuanhua@oppo.com> Cc: David Hildenbrand <david@redhat.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Gao Xiang <xiang@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kairui Song <kasong@tencent.com> Cc: Khalid Aziz <khalid.aziz@oracle.com> Cc: Len Brown <len.brown@intel.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-05-29 08:28:21 +00:00
* @delta: The direction and the offset we are moving; forward if delta
* is positive; backward if delta is negative
mm: swap: free_swap_and_cache_nr() as batched free_swap_and_cache() Now that we no longer have a convenient flag in the cluster to determine if a folio is large, free_swap_and_cache() will take a reference and lock a large folio much more often, which could lead to contention and (e.g.) failure to split large folios, etc. Let's solve that problem by batch freeing swap and cache with a new function, free_swap_and_cache_nr(), to free a contiguous range of swap entries together. This allows us to first drop a reference to each swap slot before we try to release the cache folio. This means we only try to release the folio once, only taking the reference and lock once - much better than the previous 512 times for the 2M THP case. Contiguous swap entries are gathered in zap_pte_range() and madvise_free_pte_range() in a similar way to how present ptes are already gathered in zap_pte_range(). While we are at it, let's simplify by converting the return type of both functions to void. The return value was used only by zap_pte_range() to print a bad pte, and was ignored by everyone else, so the extra reporting wasn't exactly guaranteed. We will still get the warning with most of the information from get_swap_device(). With the batch version, we wouldn't know which pte was bad anyway so could print the wrong one. [ryan.roberts@arm.com: fix a build warning on parisc] Link: https://lkml.kernel.org/r/20240409111840.3173122-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20240408183946.2991168-3-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Barry Song <21cnbao@gmail.com> Cc: Barry Song <v-songbaohua@oppo.com> Cc: Chris Li <chrisl@kernel.org> Cc: Gao Xiang <xiang@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-08 18:39:41 +00:00
*
mm: introduce pte_move_swp_offset() helper which can move offset bidirectionally There could arise a necessity to obtain the first pte_t from a swap pte_t located in the middle. For instance, this may occur within the context of do_swap_page(), where a page fault can potentially occur in any PTE of a large folio. To address this, the following patch introduces pte_move_swp_offset(), a function capable of bidirectional movement by a specified delta argument. Consequently, pte_next_swp_offset() will directly invoke it with delta = 1. Link: https://lkml.kernel.org/r/20240529082824.150954-4-21cnbao@gmail.com Signed-off-by: Barry Song <v-songbaohua@oppo.com> Suggested-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Reviewed-by: "Huang, Ying" <ying.huang@intel.com> Cc: Andreas Larsson <andreas@gaisler.com> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: Chris Li <chrisl@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Cc: Chuanhua Han <hanchuanhua@oppo.com> Cc: David Hildenbrand <david@redhat.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Gao Xiang <xiang@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kairui Song <kasong@tencent.com> Cc: Khalid Aziz <khalid.aziz@oracle.com> Cc: Len Brown <len.brown@intel.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-05-29 08:28:21 +00:00
* Moves the swap offset, while maintaining all other fields, including
mm: swap: free_swap_and_cache_nr() as batched free_swap_and_cache() Now that we no longer have a convenient flag in the cluster to determine if a folio is large, free_swap_and_cache() will take a reference and lock a large folio much more often, which could lead to contention and (e.g.) failure to split large folios, etc. Let's solve that problem by batch freeing swap and cache with a new function, free_swap_and_cache_nr(), to free a contiguous range of swap entries together. This allows us to first drop a reference to each swap slot before we try to release the cache folio. This means we only try to release the folio once, only taking the reference and lock once - much better than the previous 512 times for the 2M THP case. Contiguous swap entries are gathered in zap_pte_range() and madvise_free_pte_range() in a similar way to how present ptes are already gathered in zap_pte_range(). While we are at it, let's simplify by converting the return type of both functions to void. The return value was used only by zap_pte_range() to print a bad pte, and was ignored by everyone else, so the extra reporting wasn't exactly guaranteed. We will still get the warning with most of the information from get_swap_device(). With the batch version, we wouldn't know which pte was bad anyway so could print the wrong one. [ryan.roberts@arm.com: fix a build warning on parisc] Link: https://lkml.kernel.org/r/20240409111840.3173122-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20240408183946.2991168-3-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Barry Song <21cnbao@gmail.com> Cc: Barry Song <v-songbaohua@oppo.com> Cc: Chris Li <chrisl@kernel.org> Cc: Gao Xiang <xiang@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-08 18:39:41 +00:00
* swap type, and any swp pte bits. The resulting pte is returned.
*/
mm: introduce pte_move_swp_offset() helper which can move offset bidirectionally There could arise a necessity to obtain the first pte_t from a swap pte_t located in the middle. For instance, this may occur within the context of do_swap_page(), where a page fault can potentially occur in any PTE of a large folio. To address this, the following patch introduces pte_move_swp_offset(), a function capable of bidirectional movement by a specified delta argument. Consequently, pte_next_swp_offset() will directly invoke it with delta = 1. Link: https://lkml.kernel.org/r/20240529082824.150954-4-21cnbao@gmail.com Signed-off-by: Barry Song <v-songbaohua@oppo.com> Suggested-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Reviewed-by: "Huang, Ying" <ying.huang@intel.com> Cc: Andreas Larsson <andreas@gaisler.com> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: Chris Li <chrisl@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Cc: Chuanhua Han <hanchuanhua@oppo.com> Cc: David Hildenbrand <david@redhat.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Gao Xiang <xiang@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kairui Song <kasong@tencent.com> Cc: Khalid Aziz <khalid.aziz@oracle.com> Cc: Len Brown <len.brown@intel.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-05-29 08:28:21 +00:00
static inline pte_t pte_move_swp_offset(pte_t pte, long delta)
mm: swap: free_swap_and_cache_nr() as batched free_swap_and_cache() Now that we no longer have a convenient flag in the cluster to determine if a folio is large, free_swap_and_cache() will take a reference and lock a large folio much more often, which could lead to contention and (e.g.) failure to split large folios, etc. Let's solve that problem by batch freeing swap and cache with a new function, free_swap_and_cache_nr(), to free a contiguous range of swap entries together. This allows us to first drop a reference to each swap slot before we try to release the cache folio. This means we only try to release the folio once, only taking the reference and lock once - much better than the previous 512 times for the 2M THP case. Contiguous swap entries are gathered in zap_pte_range() and madvise_free_pte_range() in a similar way to how present ptes are already gathered in zap_pte_range(). While we are at it, let's simplify by converting the return type of both functions to void. The return value was used only by zap_pte_range() to print a bad pte, and was ignored by everyone else, so the extra reporting wasn't exactly guaranteed. We will still get the warning with most of the information from get_swap_device(). With the batch version, we wouldn't know which pte was bad anyway so could print the wrong one. [ryan.roberts@arm.com: fix a build warning on parisc] Link: https://lkml.kernel.org/r/20240409111840.3173122-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20240408183946.2991168-3-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Barry Song <21cnbao@gmail.com> Cc: Barry Song <v-songbaohua@oppo.com> Cc: Chris Li <chrisl@kernel.org> Cc: Gao Xiang <xiang@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-08 18:39:41 +00:00
{
swp_entry_t entry = pte_to_swp_entry(pte);
pte_t new = __swp_entry_to_pte(__swp_entry(swp_type(entry),
mm: introduce pte_move_swp_offset() helper which can move offset bidirectionally There could arise a necessity to obtain the first pte_t from a swap pte_t located in the middle. For instance, this may occur within the context of do_swap_page(), where a page fault can potentially occur in any PTE of a large folio. To address this, the following patch introduces pte_move_swp_offset(), a function capable of bidirectional movement by a specified delta argument. Consequently, pte_next_swp_offset() will directly invoke it with delta = 1. Link: https://lkml.kernel.org/r/20240529082824.150954-4-21cnbao@gmail.com Signed-off-by: Barry Song <v-songbaohua@oppo.com> Suggested-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Reviewed-by: "Huang, Ying" <ying.huang@intel.com> Cc: Andreas Larsson <andreas@gaisler.com> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: Chris Li <chrisl@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Cc: Chuanhua Han <hanchuanhua@oppo.com> Cc: David Hildenbrand <david@redhat.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Gao Xiang <xiang@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kairui Song <kasong@tencent.com> Cc: Khalid Aziz <khalid.aziz@oracle.com> Cc: Len Brown <len.brown@intel.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-05-29 08:28:21 +00:00
(swp_offset(entry) + delta)));
mm: swap: free_swap_and_cache_nr() as batched free_swap_and_cache() Now that we no longer have a convenient flag in the cluster to determine if a folio is large, free_swap_and_cache() will take a reference and lock a large folio much more often, which could lead to contention and (e.g.) failure to split large folios, etc. Let's solve that problem by batch freeing swap and cache with a new function, free_swap_and_cache_nr(), to free a contiguous range of swap entries together. This allows us to first drop a reference to each swap slot before we try to release the cache folio. This means we only try to release the folio once, only taking the reference and lock once - much better than the previous 512 times for the 2M THP case. Contiguous swap entries are gathered in zap_pte_range() and madvise_free_pte_range() in a similar way to how present ptes are already gathered in zap_pte_range(). While we are at it, let's simplify by converting the return type of both functions to void. The return value was used only by zap_pte_range() to print a bad pte, and was ignored by everyone else, so the extra reporting wasn't exactly guaranteed. We will still get the warning with most of the information from get_swap_device(). With the batch version, we wouldn't know which pte was bad anyway so could print the wrong one. [ryan.roberts@arm.com: fix a build warning on parisc] Link: https://lkml.kernel.org/r/20240409111840.3173122-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20240408183946.2991168-3-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Barry Song <21cnbao@gmail.com> Cc: Barry Song <v-songbaohua@oppo.com> Cc: Chris Li <chrisl@kernel.org> Cc: Gao Xiang <xiang@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-08 18:39:41 +00:00
if (pte_swp_soft_dirty(pte))
new = pte_swp_mksoft_dirty(new);
if (pte_swp_exclusive(pte))
new = pte_swp_mkexclusive(new);
if (pte_swp_uffd_wp(pte))
new = pte_swp_mkuffd_wp(new);
return new;
}
mm: introduce pte_move_swp_offset() helper which can move offset bidirectionally There could arise a necessity to obtain the first pte_t from a swap pte_t located in the middle. For instance, this may occur within the context of do_swap_page(), where a page fault can potentially occur in any PTE of a large folio. To address this, the following patch introduces pte_move_swp_offset(), a function capable of bidirectional movement by a specified delta argument. Consequently, pte_next_swp_offset() will directly invoke it with delta = 1. Link: https://lkml.kernel.org/r/20240529082824.150954-4-21cnbao@gmail.com Signed-off-by: Barry Song <v-songbaohua@oppo.com> Suggested-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Reviewed-by: "Huang, Ying" <ying.huang@intel.com> Cc: Andreas Larsson <andreas@gaisler.com> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: Chris Li <chrisl@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Cc: Chuanhua Han <hanchuanhua@oppo.com> Cc: David Hildenbrand <david@redhat.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Gao Xiang <xiang@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kairui Song <kasong@tencent.com> Cc: Khalid Aziz <khalid.aziz@oracle.com> Cc: Len Brown <len.brown@intel.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-05-29 08:28:21 +00:00
/**
* pte_next_swp_offset - Increment the swap entry offset field of a swap pte.
* @pte: The initial pte state; is_swap_pte(pte) must be true and
* non_swap_entry() must be false.
*
* Increments the swap offset, while maintaining all other fields, including
* swap type, and any swp pte bits. The resulting pte is returned.
*/
static inline pte_t pte_next_swp_offset(pte_t pte)
{
return pte_move_swp_offset(pte, 1);
}
mm: swap: free_swap_and_cache_nr() as batched free_swap_and_cache() Now that we no longer have a convenient flag in the cluster to determine if a folio is large, free_swap_and_cache() will take a reference and lock a large folio much more often, which could lead to contention and (e.g.) failure to split large folios, etc. Let's solve that problem by batch freeing swap and cache with a new function, free_swap_and_cache_nr(), to free a contiguous range of swap entries together. This allows us to first drop a reference to each swap slot before we try to release the cache folio. This means we only try to release the folio once, only taking the reference and lock once - much better than the previous 512 times for the 2M THP case. Contiguous swap entries are gathered in zap_pte_range() and madvise_free_pte_range() in a similar way to how present ptes are already gathered in zap_pte_range(). While we are at it, let's simplify by converting the return type of both functions to void. The return value was used only by zap_pte_range() to print a bad pte, and was ignored by everyone else, so the extra reporting wasn't exactly guaranteed. We will still get the warning with most of the information from get_swap_device(). With the batch version, we wouldn't know which pte was bad anyway so could print the wrong one. [ryan.roberts@arm.com: fix a build warning on parisc] Link: https://lkml.kernel.org/r/20240409111840.3173122-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20240408183946.2991168-3-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Barry Song <21cnbao@gmail.com> Cc: Barry Song <v-songbaohua@oppo.com> Cc: Chris Li <chrisl@kernel.org> Cc: Gao Xiang <xiang@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-08 18:39:41 +00:00
/**
* swap_pte_batch - detect a PTE batch for a set of contiguous swap entries
* @start_ptep: Page table pointer for the first entry.
* @max_nr: The maximum number of table entries to consider.
* @pte: Page table entry for the first entry.
*
* Detect a batch of contiguous swap entries: consecutive (non-present) PTEs
* containing swap entries all with consecutive offsets and targeting the same
* swap type, all with matching swp pte bits.
*
* max_nr must be at least one and must be limited by the caller so scanning
* cannot exceed a single page table.
*
* Return: the number of table entries in the batch.
*/
static inline int swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte)
{
pte_t expected_pte = pte_next_swp_offset(pte);
const pte_t *end_ptep = start_ptep + max_nr;
mm: attempt to batch free swap entries for zap_pte_range() Zhiguo reported that swap release could be a serious bottleneck during process exits[1]. With mTHP, we have the opportunity to batch free swaps. Thanks to the work of Chris and Kairui[2], I was able to achieve this optimization with minimal code changes by building on their efforts. If swap_count is 1, which is likely true as most anon memory are private, we can free all contiguous swap slots all together. Ran the below test program for measuring the bandwidth of munmap using zRAM and 64KiB mTHP: #include <sys/mman.h> #include <sys/time.h> #include <stdlib.h> unsigned long long tv_to_ms(struct timeval tv) { return tv.tv_sec * 1000 + tv.tv_usec / 1000; } main() { struct timeval tv_b, tv_e; int i; #define SIZE 1024*1024*1024 void *p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (!p) { perror("fail to get memory"); exit(-1); } madvise(p, SIZE, MADV_HUGEPAGE); memset(p, 0x11, SIZE); /* write to get mem */ madvise(p, SIZE, MADV_PAGEOUT); gettimeofday(&tv_b, NULL); munmap(p, SIZE); gettimeofday(&tv_e, NULL); printf("munmap in bandwidth: %ld bytes/ms\n", SIZE/(tv_to_ms(tv_e) - tv_to_ms(tv_b))); } The result is as below (munmap bandwidth): mm-unstable mm-unstable-with-patch round1 21053761 63161283 round2 21053761 63161283 round3 21053761 63161283 round4 20648881 67108864 round5 20648881 67108864 munmap bandwidth becomes 3X faster. [1] https://lore.kernel.org/linux-mm/20240731133318.527-1-justinjiang@vivo.com/ [2] https://lore.kernel.org/linux-mm/20240730-swap-allocator-v5-0-cb9c148b9297@kernel.org/ [v-songbaohua@oppo.com: check all swaps belong to same swap_cgroup in swap_pte_batch()] Link: https://lkml.kernel.org/r/20240815215308.55233-1-21cnbao@gmail.com [hughd@google.com: add mem_cgroup_disabled() check] Link: https://lkml.kernel.org/r/33f34a88-0130-5444-9b84-93198eeb50e7@google.com [21cnbao@gmail.com: add missing zswap_invalidate()] Link: https://lkml.kernel.org/r/20240821054921.43468-1-21cnbao@gmail.com Link: https://lkml.kernel.org/r/20240807215859.57491-3-21cnbao@gmail.com Signed-off-by: Barry Song <v-songbaohua@oppo.com> Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Kairui Song <kasong@tencent.com> Cc: Chris Li <chrisl@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kalesh Singh <kaleshsingh@google.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Barry Song <baohua@kernel.org> Cc: Yosry Ahmed <yosryahmed@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-08-07 21:58:59 +00:00
swp_entry_t entry = pte_to_swp_entry(pte);
mm: swap: free_swap_and_cache_nr() as batched free_swap_and_cache() Now that we no longer have a convenient flag in the cluster to determine if a folio is large, free_swap_and_cache() will take a reference and lock a large folio much more often, which could lead to contention and (e.g.) failure to split large folios, etc. Let's solve that problem by batch freeing swap and cache with a new function, free_swap_and_cache_nr(), to free a contiguous range of swap entries together. This allows us to first drop a reference to each swap slot before we try to release the cache folio. This means we only try to release the folio once, only taking the reference and lock once - much better than the previous 512 times for the 2M THP case. Contiguous swap entries are gathered in zap_pte_range() and madvise_free_pte_range() in a similar way to how present ptes are already gathered in zap_pte_range(). While we are at it, let's simplify by converting the return type of both functions to void. The return value was used only by zap_pte_range() to print a bad pte, and was ignored by everyone else, so the extra reporting wasn't exactly guaranteed. We will still get the warning with most of the information from get_swap_device(). With the batch version, we wouldn't know which pte was bad anyway so could print the wrong one. [ryan.roberts@arm.com: fix a build warning on parisc] Link: https://lkml.kernel.org/r/20240409111840.3173122-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20240408183946.2991168-3-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Barry Song <21cnbao@gmail.com> Cc: Barry Song <v-songbaohua@oppo.com> Cc: Chris Li <chrisl@kernel.org> Cc: Gao Xiang <xiang@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-08 18:39:41 +00:00
pte_t *ptep = start_ptep + 1;
mm: attempt to batch free swap entries for zap_pte_range() Zhiguo reported that swap release could be a serious bottleneck during process exits[1]. With mTHP, we have the opportunity to batch free swaps. Thanks to the work of Chris and Kairui[2], I was able to achieve this optimization with minimal code changes by building on their efforts. If swap_count is 1, which is likely true as most anon memory are private, we can free all contiguous swap slots all together. Ran the below test program for measuring the bandwidth of munmap using zRAM and 64KiB mTHP: #include <sys/mman.h> #include <sys/time.h> #include <stdlib.h> unsigned long long tv_to_ms(struct timeval tv) { return tv.tv_sec * 1000 + tv.tv_usec / 1000; } main() { struct timeval tv_b, tv_e; int i; #define SIZE 1024*1024*1024 void *p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (!p) { perror("fail to get memory"); exit(-1); } madvise(p, SIZE, MADV_HUGEPAGE); memset(p, 0x11, SIZE); /* write to get mem */ madvise(p, SIZE, MADV_PAGEOUT); gettimeofday(&tv_b, NULL); munmap(p, SIZE); gettimeofday(&tv_e, NULL); printf("munmap in bandwidth: %ld bytes/ms\n", SIZE/(tv_to_ms(tv_e) - tv_to_ms(tv_b))); } The result is as below (munmap bandwidth): mm-unstable mm-unstable-with-patch round1 21053761 63161283 round2 21053761 63161283 round3 21053761 63161283 round4 20648881 67108864 round5 20648881 67108864 munmap bandwidth becomes 3X faster. [1] https://lore.kernel.org/linux-mm/20240731133318.527-1-justinjiang@vivo.com/ [2] https://lore.kernel.org/linux-mm/20240730-swap-allocator-v5-0-cb9c148b9297@kernel.org/ [v-songbaohua@oppo.com: check all swaps belong to same swap_cgroup in swap_pte_batch()] Link: https://lkml.kernel.org/r/20240815215308.55233-1-21cnbao@gmail.com [hughd@google.com: add mem_cgroup_disabled() check] Link: https://lkml.kernel.org/r/33f34a88-0130-5444-9b84-93198eeb50e7@google.com [21cnbao@gmail.com: add missing zswap_invalidate()] Link: https://lkml.kernel.org/r/20240821054921.43468-1-21cnbao@gmail.com Link: https://lkml.kernel.org/r/20240807215859.57491-3-21cnbao@gmail.com Signed-off-by: Barry Song <v-songbaohua@oppo.com> Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Kairui Song <kasong@tencent.com> Cc: Chris Li <chrisl@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kalesh Singh <kaleshsingh@google.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Barry Song <baohua@kernel.org> Cc: Yosry Ahmed <yosryahmed@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-08-07 21:58:59 +00:00
unsigned short cgroup_id;
mm: swap: free_swap_and_cache_nr() as batched free_swap_and_cache() Now that we no longer have a convenient flag in the cluster to determine if a folio is large, free_swap_and_cache() will take a reference and lock a large folio much more often, which could lead to contention and (e.g.) failure to split large folios, etc. Let's solve that problem by batch freeing swap and cache with a new function, free_swap_and_cache_nr(), to free a contiguous range of swap entries together. This allows us to first drop a reference to each swap slot before we try to release the cache folio. This means we only try to release the folio once, only taking the reference and lock once - much better than the previous 512 times for the 2M THP case. Contiguous swap entries are gathered in zap_pte_range() and madvise_free_pte_range() in a similar way to how present ptes are already gathered in zap_pte_range(). While we are at it, let's simplify by converting the return type of both functions to void. The return value was used only by zap_pte_range() to print a bad pte, and was ignored by everyone else, so the extra reporting wasn't exactly guaranteed. We will still get the warning with most of the information from get_swap_device(). With the batch version, we wouldn't know which pte was bad anyway so could print the wrong one. [ryan.roberts@arm.com: fix a build warning on parisc] Link: https://lkml.kernel.org/r/20240409111840.3173122-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20240408183946.2991168-3-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Barry Song <21cnbao@gmail.com> Cc: Barry Song <v-songbaohua@oppo.com> Cc: Chris Li <chrisl@kernel.org> Cc: Gao Xiang <xiang@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-08 18:39:41 +00:00
VM_WARN_ON(max_nr < 1);
VM_WARN_ON(!is_swap_pte(pte));
mm: attempt to batch free swap entries for zap_pte_range() Zhiguo reported that swap release could be a serious bottleneck during process exits[1]. With mTHP, we have the opportunity to batch free swaps. Thanks to the work of Chris and Kairui[2], I was able to achieve this optimization with minimal code changes by building on their efforts. If swap_count is 1, which is likely true as most anon memory are private, we can free all contiguous swap slots all together. Ran the below test program for measuring the bandwidth of munmap using zRAM and 64KiB mTHP: #include <sys/mman.h> #include <sys/time.h> #include <stdlib.h> unsigned long long tv_to_ms(struct timeval tv) { return tv.tv_sec * 1000 + tv.tv_usec / 1000; } main() { struct timeval tv_b, tv_e; int i; #define SIZE 1024*1024*1024 void *p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (!p) { perror("fail to get memory"); exit(-1); } madvise(p, SIZE, MADV_HUGEPAGE); memset(p, 0x11, SIZE); /* write to get mem */ madvise(p, SIZE, MADV_PAGEOUT); gettimeofday(&tv_b, NULL); munmap(p, SIZE); gettimeofday(&tv_e, NULL); printf("munmap in bandwidth: %ld bytes/ms\n", SIZE/(tv_to_ms(tv_e) - tv_to_ms(tv_b))); } The result is as below (munmap bandwidth): mm-unstable mm-unstable-with-patch round1 21053761 63161283 round2 21053761 63161283 round3 21053761 63161283 round4 20648881 67108864 round5 20648881 67108864 munmap bandwidth becomes 3X faster. [1] https://lore.kernel.org/linux-mm/20240731133318.527-1-justinjiang@vivo.com/ [2] https://lore.kernel.org/linux-mm/20240730-swap-allocator-v5-0-cb9c148b9297@kernel.org/ [v-songbaohua@oppo.com: check all swaps belong to same swap_cgroup in swap_pte_batch()] Link: https://lkml.kernel.org/r/20240815215308.55233-1-21cnbao@gmail.com [hughd@google.com: add mem_cgroup_disabled() check] Link: https://lkml.kernel.org/r/33f34a88-0130-5444-9b84-93198eeb50e7@google.com [21cnbao@gmail.com: add missing zswap_invalidate()] Link: https://lkml.kernel.org/r/20240821054921.43468-1-21cnbao@gmail.com Link: https://lkml.kernel.org/r/20240807215859.57491-3-21cnbao@gmail.com Signed-off-by: Barry Song <v-songbaohua@oppo.com> Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Kairui Song <kasong@tencent.com> Cc: Chris Li <chrisl@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kalesh Singh <kaleshsingh@google.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Barry Song <baohua@kernel.org> Cc: Yosry Ahmed <yosryahmed@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-08-07 21:58:59 +00:00
VM_WARN_ON(non_swap_entry(entry));
mm: swap: free_swap_and_cache_nr() as batched free_swap_and_cache() Now that we no longer have a convenient flag in the cluster to determine if a folio is large, free_swap_and_cache() will take a reference and lock a large folio much more often, which could lead to contention and (e.g.) failure to split large folios, etc. Let's solve that problem by batch freeing swap and cache with a new function, free_swap_and_cache_nr(), to free a contiguous range of swap entries together. This allows us to first drop a reference to each swap slot before we try to release the cache folio. This means we only try to release the folio once, only taking the reference and lock once - much better than the previous 512 times for the 2M THP case. Contiguous swap entries are gathered in zap_pte_range() and madvise_free_pte_range() in a similar way to how present ptes are already gathered in zap_pte_range(). While we are at it, let's simplify by converting the return type of both functions to void. The return value was used only by zap_pte_range() to print a bad pte, and was ignored by everyone else, so the extra reporting wasn't exactly guaranteed. We will still get the warning with most of the information from get_swap_device(). With the batch version, we wouldn't know which pte was bad anyway so could print the wrong one. [ryan.roberts@arm.com: fix a build warning on parisc] Link: https://lkml.kernel.org/r/20240409111840.3173122-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20240408183946.2991168-3-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Barry Song <21cnbao@gmail.com> Cc: Barry Song <v-songbaohua@oppo.com> Cc: Chris Li <chrisl@kernel.org> Cc: Gao Xiang <xiang@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-08 18:39:41 +00:00
mm: attempt to batch free swap entries for zap_pte_range() Zhiguo reported that swap release could be a serious bottleneck during process exits[1]. With mTHP, we have the opportunity to batch free swaps. Thanks to the work of Chris and Kairui[2], I was able to achieve this optimization with minimal code changes by building on their efforts. If swap_count is 1, which is likely true as most anon memory are private, we can free all contiguous swap slots all together. Ran the below test program for measuring the bandwidth of munmap using zRAM and 64KiB mTHP: #include <sys/mman.h> #include <sys/time.h> #include <stdlib.h> unsigned long long tv_to_ms(struct timeval tv) { return tv.tv_sec * 1000 + tv.tv_usec / 1000; } main() { struct timeval tv_b, tv_e; int i; #define SIZE 1024*1024*1024 void *p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (!p) { perror("fail to get memory"); exit(-1); } madvise(p, SIZE, MADV_HUGEPAGE); memset(p, 0x11, SIZE); /* write to get mem */ madvise(p, SIZE, MADV_PAGEOUT); gettimeofday(&tv_b, NULL); munmap(p, SIZE); gettimeofday(&tv_e, NULL); printf("munmap in bandwidth: %ld bytes/ms\n", SIZE/(tv_to_ms(tv_e) - tv_to_ms(tv_b))); } The result is as below (munmap bandwidth): mm-unstable mm-unstable-with-patch round1 21053761 63161283 round2 21053761 63161283 round3 21053761 63161283 round4 20648881 67108864 round5 20648881 67108864 munmap bandwidth becomes 3X faster. [1] https://lore.kernel.org/linux-mm/20240731133318.527-1-justinjiang@vivo.com/ [2] https://lore.kernel.org/linux-mm/20240730-swap-allocator-v5-0-cb9c148b9297@kernel.org/ [v-songbaohua@oppo.com: check all swaps belong to same swap_cgroup in swap_pte_batch()] Link: https://lkml.kernel.org/r/20240815215308.55233-1-21cnbao@gmail.com [hughd@google.com: add mem_cgroup_disabled() check] Link: https://lkml.kernel.org/r/33f34a88-0130-5444-9b84-93198eeb50e7@google.com [21cnbao@gmail.com: add missing zswap_invalidate()] Link: https://lkml.kernel.org/r/20240821054921.43468-1-21cnbao@gmail.com Link: https://lkml.kernel.org/r/20240807215859.57491-3-21cnbao@gmail.com Signed-off-by: Barry Song <v-songbaohua@oppo.com> Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Kairui Song <kasong@tencent.com> Cc: Chris Li <chrisl@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kalesh Singh <kaleshsingh@google.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Barry Song <baohua@kernel.org> Cc: Yosry Ahmed <yosryahmed@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-08-07 21:58:59 +00:00
cgroup_id = lookup_swap_cgroup_id(entry);
mm: swap: free_swap_and_cache_nr() as batched free_swap_and_cache() Now that we no longer have a convenient flag in the cluster to determine if a folio is large, free_swap_and_cache() will take a reference and lock a large folio much more often, which could lead to contention and (e.g.) failure to split large folios, etc. Let's solve that problem by batch freeing swap and cache with a new function, free_swap_and_cache_nr(), to free a contiguous range of swap entries together. This allows us to first drop a reference to each swap slot before we try to release the cache folio. This means we only try to release the folio once, only taking the reference and lock once - much better than the previous 512 times for the 2M THP case. Contiguous swap entries are gathered in zap_pte_range() and madvise_free_pte_range() in a similar way to how present ptes are already gathered in zap_pte_range(). While we are at it, let's simplify by converting the return type of both functions to void. The return value was used only by zap_pte_range() to print a bad pte, and was ignored by everyone else, so the extra reporting wasn't exactly guaranteed. We will still get the warning with most of the information from get_swap_device(). With the batch version, we wouldn't know which pte was bad anyway so could print the wrong one. [ryan.roberts@arm.com: fix a build warning on parisc] Link: https://lkml.kernel.org/r/20240409111840.3173122-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20240408183946.2991168-3-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Barry Song <21cnbao@gmail.com> Cc: Barry Song <v-songbaohua@oppo.com> Cc: Chris Li <chrisl@kernel.org> Cc: Gao Xiang <xiang@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-08 18:39:41 +00:00
while (ptep < end_ptep) {
pte = ptep_get(ptep);
if (!pte_same(pte, expected_pte))
break;
mm: attempt to batch free swap entries for zap_pte_range() Zhiguo reported that swap release could be a serious bottleneck during process exits[1]. With mTHP, we have the opportunity to batch free swaps. Thanks to the work of Chris and Kairui[2], I was able to achieve this optimization with minimal code changes by building on their efforts. If swap_count is 1, which is likely true as most anon memory are private, we can free all contiguous swap slots all together. Ran the below test program for measuring the bandwidth of munmap using zRAM and 64KiB mTHP: #include <sys/mman.h> #include <sys/time.h> #include <stdlib.h> unsigned long long tv_to_ms(struct timeval tv) { return tv.tv_sec * 1000 + tv.tv_usec / 1000; } main() { struct timeval tv_b, tv_e; int i; #define SIZE 1024*1024*1024 void *p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (!p) { perror("fail to get memory"); exit(-1); } madvise(p, SIZE, MADV_HUGEPAGE); memset(p, 0x11, SIZE); /* write to get mem */ madvise(p, SIZE, MADV_PAGEOUT); gettimeofday(&tv_b, NULL); munmap(p, SIZE); gettimeofday(&tv_e, NULL); printf("munmap in bandwidth: %ld bytes/ms\n", SIZE/(tv_to_ms(tv_e) - tv_to_ms(tv_b))); } The result is as below (munmap bandwidth): mm-unstable mm-unstable-with-patch round1 21053761 63161283 round2 21053761 63161283 round3 21053761 63161283 round4 20648881 67108864 round5 20648881 67108864 munmap bandwidth becomes 3X faster. [1] https://lore.kernel.org/linux-mm/20240731133318.527-1-justinjiang@vivo.com/ [2] https://lore.kernel.org/linux-mm/20240730-swap-allocator-v5-0-cb9c148b9297@kernel.org/ [v-songbaohua@oppo.com: check all swaps belong to same swap_cgroup in swap_pte_batch()] Link: https://lkml.kernel.org/r/20240815215308.55233-1-21cnbao@gmail.com [hughd@google.com: add mem_cgroup_disabled() check] Link: https://lkml.kernel.org/r/33f34a88-0130-5444-9b84-93198eeb50e7@google.com [21cnbao@gmail.com: add missing zswap_invalidate()] Link: https://lkml.kernel.org/r/20240821054921.43468-1-21cnbao@gmail.com Link: https://lkml.kernel.org/r/20240807215859.57491-3-21cnbao@gmail.com Signed-off-by: Barry Song <v-songbaohua@oppo.com> Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Kairui Song <kasong@tencent.com> Cc: Chris Li <chrisl@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kalesh Singh <kaleshsingh@google.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Barry Song <baohua@kernel.org> Cc: Yosry Ahmed <yosryahmed@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-08-07 21:58:59 +00:00
if (lookup_swap_cgroup_id(pte_to_swp_entry(pte)) != cgroup_id)
break;
mm: swap: free_swap_and_cache_nr() as batched free_swap_and_cache() Now that we no longer have a convenient flag in the cluster to determine if a folio is large, free_swap_and_cache() will take a reference and lock a large folio much more often, which could lead to contention and (e.g.) failure to split large folios, etc. Let's solve that problem by batch freeing swap and cache with a new function, free_swap_and_cache_nr(), to free a contiguous range of swap entries together. This allows us to first drop a reference to each swap slot before we try to release the cache folio. This means we only try to release the folio once, only taking the reference and lock once - much better than the previous 512 times for the 2M THP case. Contiguous swap entries are gathered in zap_pte_range() and madvise_free_pte_range() in a similar way to how present ptes are already gathered in zap_pte_range(). While we are at it, let's simplify by converting the return type of both functions to void. The return value was used only by zap_pte_range() to print a bad pte, and was ignored by everyone else, so the extra reporting wasn't exactly guaranteed. We will still get the warning with most of the information from get_swap_device(). With the batch version, we wouldn't know which pte was bad anyway so could print the wrong one. [ryan.roberts@arm.com: fix a build warning on parisc] Link: https://lkml.kernel.org/r/20240409111840.3173122-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20240408183946.2991168-3-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Barry Song <21cnbao@gmail.com> Cc: Barry Song <v-songbaohua@oppo.com> Cc: Chris Li <chrisl@kernel.org> Cc: Gao Xiang <xiang@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Lance Yang <ioworker0@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-08 18:39:41 +00:00
expected_pte = pte_next_swp_offset(expected_pte);
ptep++;
}
return ptep - start_ptep;
}
#endif /* CONFIG_MMU */
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
void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio,
mm/vmscan: throttle reclaim until some writeback completes if congested Patch series "Remove dependency on congestion_wait in mm/", v5. This series that removes all calls to congestion_wait in mm/ and deletes wait_iff_congested. It's not a clever implementation but congestion_wait has been broken for a long time [1]. Even if congestion throttling worked, it was never a great idea. While excessive dirty/writeback pages at the tail of the LRU is one possibility that reclaim may be slow, there is also the problem of too many pages being isolated and reclaim failing for other reasons (elevated references, too many pages isolated, excessive LRU contention etc). This series replaces the "congestion" throttling with 3 different types. - If there are too many dirty/writeback pages, sleep until a timeout or enough pages get cleaned - If too many pages are isolated, sleep until enough isolated pages are either reclaimed or put back on the LRU - If no progress is being made, direct reclaim tasks sleep until another task makes progress with acceptable efficiency. This was initially tested with a mix of workloads that used to trigger corner cases that no longer work. A new test case was created called "stutterp" (pagereclaim-stutterp-noreaders in mmtests) using a freshly created XFS filesystem. Note that it may be necessary to increase the timeout of ssh if executing remotely as ssh itself can get throttled and the connection may timeout. stutterp varies the number of "worker" processes from 4 up to NR_CPUS*4 to check the impact as the number of direct reclaimers increase. It has four types of worker. - One "anon latency" worker creates small mappings with mmap() and times how long it takes to fault the mapping reading it 4K at a time - X file writers which is fio randomly writing X files where the total size of the files add up to the allowed dirty_ratio. fio is allowed to run for a warmup period to allow some file-backed pages to accumulate. The duration of the warmup is based on the best-case linear write speed of the storage. - Y file readers which is fio randomly reading small files - Z anon memory hogs which continually map (100-dirty_ratio)% of memory - Total estimated WSS = (100+dirty_ration) percentage of memory X+Y+Z+1 == NR_WORKERS varying from 4 up to NR_CPUS*4 The intent is to maximise the total WSS with a mix of file and anon memory where some anonymous memory must be swapped and there is a high likelihood of dirty/writeback pages reaching the end of the LRU. The test can be configured to have no background readers to stress dirty/writeback pages. The results below are based on having zero readers. The short summary of the results is that the series works and stalls until some event occurs but the timeouts may need adjustment. The test results are not broken down by patch as the series should be treated as one block that replaces a broken throttling mechanism with a working one. Finally, three machines were tested but I'm reporting the worst set of results. The other two machines had much better latencies for example. First the results of the "anon latency" latency stutterp 5.15.0-rc1 5.15.0-rc1 vanilla mm-reclaimcongest-v5r4 Amean mmap-4 31.4003 ( 0.00%) 2661.0198 (-8374.52%) Amean mmap-7 38.1641 ( 0.00%) 149.2891 (-291.18%) Amean mmap-12 60.0981 ( 0.00%) 187.8105 (-212.51%) Amean mmap-21 161.2699 ( 0.00%) 213.9107 ( -32.64%) Amean mmap-30 174.5589 ( 0.00%) 377.7548 (-116.41%) Amean mmap-48 8106.8160 ( 0.00%) 1070.5616 ( 86.79%) Stddev mmap-4 41.3455 ( 0.00%) 27573.9676 (-66591.66%) Stddev mmap-7 53.5556 ( 0.00%) 4608.5860 (-8505.23%) Stddev mmap-12 171.3897 ( 0.00%) 5559.4542 (-3143.75%) Stddev mmap-21 1506.6752 ( 0.00%) 5746.2507 (-281.39%) Stddev mmap-30 557.5806 ( 0.00%) 7678.1624 (-1277.05%) Stddev mmap-48 61681.5718 ( 0.00%) 14507.2830 ( 76.48%) Max-90 mmap-4 31.4243 ( 0.00%) 83.1457 (-164.59%) Max-90 mmap-7 41.0410 ( 0.00%) 41.0720 ( -0.08%) Max-90 mmap-12 66.5255 ( 0.00%) 53.9073 ( 18.97%) Max-90 mmap-21 146.7479 ( 0.00%) 105.9540 ( 27.80%) Max-90 mmap-30 193.9513 ( 0.00%) 64.3067 ( 66.84%) Max-90 mmap-48 277.9137 ( 0.00%) 591.0594 (-112.68%) Max mmap-4 1913.8009 ( 0.00%) 299623.9695 (-15555.96%) Max mmap-7 2423.9665 ( 0.00%) 204453.1708 (-8334.65%) Max mmap-12 6845.6573 ( 0.00%) 221090.3366 (-3129.64%) Max mmap-21 56278.6508 ( 0.00%) 213877.3496 (-280.03%) Max mmap-30 19716.2990 ( 0.00%) 216287.6229 (-997.00%) Max mmap-48 477923.9400 ( 0.00%) 245414.8238 ( 48.65%) For most thread counts, the time to mmap() is unfortunately increased. In earlier versions of the series, this was lower but a large number of throttling events were reaching their timeout increasing the amount of inefficient scanning of the LRU. There is no prioritisation of reclaim tasks making progress based on each tasks rate of page allocation versus progress of reclaim. The variance is also impacted for high worker counts but in all cases, the differences in latency are not statistically significant due to very large maximum outliers. Max-90 shows that 90% of the stalls are comparable but the Max results show the massive outliers which are increased to to stalling. It is expected that this will be very machine dependant. Due to the test design, reclaim is difficult so allocations stall and there are variances depending on whether THPs can be allocated or not. The amount of memory will affect exactly how bad the corner cases are and how often they trigger. The warmup period calculation is not ideal as it's based on linear writes where as fio is randomly writing multiple files from multiple tasks so the start state of the test is variable. For example, these are the latencies on a single-socket machine that had more memory Amean mmap-4 42.2287 ( 0.00%) 49.6838 * -17.65%* Amean mmap-7 216.4326 ( 0.00%) 47.4451 * 78.08%* Amean mmap-12 2412.0588 ( 0.00%) 51.7497 ( 97.85%) Amean mmap-21 5546.2548 ( 0.00%) 51.8862 ( 99.06%) Amean mmap-30 1085.3121 ( 0.00%) 72.1004 ( 93.36%) The overall system CPU usage and elapsed time is as follows 5.15.0-rc3 5.15.0-rc3 vanilla mm-reclaimcongest-v5r4 Duration User 6989.03 983.42 Duration System 7308.12 799.68 Duration Elapsed 2277.67 2092.98 The patches reduce system CPU usage by 89% as the vanilla kernel is rarely stalling. The high-level /proc/vmstats show 5.15.0-rc1 5.15.0-rc1 vanilla mm-reclaimcongest-v5r2 Ops Direct pages scanned 1056608451.00 503594991.00 Ops Kswapd pages scanned 109795048.00 147289810.00 Ops Kswapd pages reclaimed 63269243.00 31036005.00 Ops Direct pages reclaimed 10803973.00 6328887.00 Ops Kswapd efficiency % 57.62 21.07 Ops Kswapd velocity 48204.98 57572.86 Ops Direct efficiency % 1.02 1.26 Ops Direct velocity 463898.83 196845.97 Kswapd scanned less pages but the detailed pattern is different. The vanilla kernel scans slowly over time where as the patches exhibits burst patterns of scan activity. Direct reclaim scanning is reduced by 52% due to stalling. The pattern for stealing pages is also slightly different. Both kernels exhibit spikes but the vanilla kernel when reclaiming shows pages being reclaimed over a period of time where as the patches tend to reclaim in spikes. The difference is that vanilla is not throttling and instead scanning constantly finding some pages over time where as the patched kernel throttles and reclaims in spikes. Ops Percentage direct scans 90.59 77.37 For direct reclaim, vanilla scanned 90.59% of pages where as with the patches, 77.37% were direct reclaim due to throttling Ops Page writes by reclaim 2613590.00 1687131.00 Page writes from reclaim context are reduced. Ops Page writes anon 2932752.00 1917048.00 And there is less swapping. Ops Page reclaim immediate 996248528.00 107664764.00 The number of pages encountered at the tail of the LRU tagged for immediate reclaim but still dirty/writeback is reduced by 89%. Ops Slabs scanned 164284.00 153608.00 Slab scan activity is similar. ftrace was used to gather stall activity Vanilla ------- 1 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=16000 2 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=12000 8 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=8000 29 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=4000 82394 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=0 The fast majority of wait_iff_congested calls do not stall at all. What is likely happening is that cond_resched() reschedules the task for a short period when the BDI is not registering congestion (which it never will in this test setup). 1 writeback_congestion_wait: usec_timeout=100000 usec_delayed=120000 2 writeback_congestion_wait: usec_timeout=100000 usec_delayed=132000 4 writeback_congestion_wait: usec_timeout=100000 usec_delayed=112000 380 writeback_congestion_wait: usec_timeout=100000 usec_delayed=108000 778 writeback_congestion_wait: usec_timeout=100000 usec_delayed=104000 congestion_wait if called always exceeds the timeout as there is no trigger to wake it up. Bottom line: Vanilla will throttle but it's not effective. Patch series ------------ Kswapd throttle activity was always due to scanning pages tagged for immediate reclaim at the tail of the LRU 1 usec_timeout=100000 usect_delayed=72000 reason=VMSCAN_THROTTLE_WRITEBACK 4 usec_timeout=100000 usect_delayed=20000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=12000 reason=VMSCAN_THROTTLE_WRITEBACK 6 usec_timeout=100000 usect_delayed=16000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=100000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=8000 reason=VMSCAN_THROTTLE_WRITEBACK 94 usec_timeout=100000 usect_delayed=0 reason=VMSCAN_THROTTLE_WRITEBACK 112 usec_timeout=100000 usect_delayed=4000 reason=VMSCAN_THROTTLE_WRITEBACK The majority of events did not stall or stalled for a short period. Roughly 16% of stalls reached the timeout before expiry. For direct reclaim, the number of times stalled for each reason were 6624 reason=VMSCAN_THROTTLE_ISOLATED 93246 reason=VMSCAN_THROTTLE_NOPROGRESS 96934 reason=VMSCAN_THROTTLE_WRITEBACK The most common reason to stall was due to excessive pages tagged for immediate reclaim at the tail of the LRU followed by a failure to make forward. A relatively small number were due to too many pages isolated from the LRU by parallel threads For VMSCAN_THROTTLE_ISOLATED, the breakdown of delays was 9 usec_timeout=20000 usect_delayed=4000 reason=VMSCAN_THROTTLE_ISOLATED 12 usec_timeout=20000 usect_delayed=16000 reason=VMSCAN_THROTTLE_ISOLATED 83 usec_timeout=20000 usect_delayed=20000 reason=VMSCAN_THROTTLE_ISOLATED 6520 usec_timeout=20000 usect_delayed=0 reason=VMSCAN_THROTTLE_ISOLATED Most did not stall at all. A small number reached the timeout. For VMSCAN_THROTTLE_NOPROGRESS, the breakdown of stalls were all over the map 1 usec_timeout=500000 usect_delayed=324000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=332000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=348000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=360000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=228000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=260000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=340000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=364000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=372000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=428000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=460000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=464000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=244000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=252000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=272000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=188000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=268000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=328000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=380000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=392000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=432000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=204000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=220000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=412000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=436000 reason=VMSCAN_THROTTLE_NOPROGRESS 6 usec_timeout=500000 usect_delayed=488000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=212000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=300000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=316000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=472000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=248000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=356000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=456000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=124000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=376000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=484000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=172000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=420000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=452000 reason=VMSCAN_THROTTLE_NOPROGRESS 11 usec_timeout=500000 usect_delayed=256000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=112000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=116000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=144000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=152000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=264000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=384000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=424000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=492000 reason=VMSCAN_THROTTLE_NOPROGRESS 13 usec_timeout=500000 usect_delayed=184000 reason=VMSCAN_THROTTLE_NOPROGRESS 13 usec_timeout=500000 usect_delayed=444000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=308000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=440000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=476000 reason=VMSCAN_THROTTLE_NOPROGRESS 16 usec_timeout=500000 usect_delayed=140000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=232000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=240000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=280000 reason=VMSCAN_THROTTLE_NOPROGRESS 18 usec_timeout=500000 usect_delayed=404000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=148000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=216000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=468000 reason=VMSCAN_THROTTLE_NOPROGRESS 21 usec_timeout=500000 usect_delayed=448000 reason=VMSCAN_THROTTLE_NOPROGRESS 23 usec_timeout=500000 usect_delayed=168000 reason=VMSCAN_THROTTLE_NOPROGRESS 23 usec_timeout=500000 usect_delayed=296000 reason=VMSCAN_THROTTLE_NOPROGRESS 25 usec_timeout=500000 usect_delayed=132000 reason=VMSCAN_THROTTLE_NOPROGRESS 25 usec_timeout=500000 usect_delayed=352000 reason=VMSCAN_THROTTLE_NOPROGRESS 26 usec_timeout=500000 usect_delayed=180000 reason=VMSCAN_THROTTLE_NOPROGRESS 27 usec_timeout=500000 usect_delayed=284000 reason=VMSCAN_THROTTLE_NOPROGRESS 28 usec_timeout=500000 usect_delayed=164000 reason=VMSCAN_THROTTLE_NOPROGRESS 29 usec_timeout=500000 usect_delayed=136000 reason=VMSCAN_THROTTLE_NOPROGRESS 30 usec_timeout=500000 usect_delayed=200000 reason=VMSCAN_THROTTLE_NOPROGRESS 30 usec_timeout=500000 usect_delayed=400000 reason=VMSCAN_THROTTLE_NOPROGRESS 31 usec_timeout=500000 usect_delayed=196000 reason=VMSCAN_THROTTLE_NOPROGRESS 32 usec_timeout=500000 usect_delayed=156000 reason=VMSCAN_THROTTLE_NOPROGRESS 33 usec_timeout=500000 usect_delayed=224000 reason=VMSCAN_THROTTLE_NOPROGRESS 35 usec_timeout=500000 usect_delayed=128000 reason=VMSCAN_THROTTLE_NOPROGRESS 35 usec_timeout=500000 usect_delayed=176000 reason=VMSCAN_THROTTLE_NOPROGRESS 36 usec_timeout=500000 usect_delayed=368000 reason=VMSCAN_THROTTLE_NOPROGRESS 36 usec_timeout=500000 usect_delayed=496000 reason=VMSCAN_THROTTLE_NOPROGRESS 37 usec_timeout=500000 usect_delayed=312000 reason=VMSCAN_THROTTLE_NOPROGRESS 38 usec_timeout=500000 usect_delayed=304000 reason=VMSCAN_THROTTLE_NOPROGRESS 40 usec_timeout=500000 usect_delayed=288000 reason=VMSCAN_THROTTLE_NOPROGRESS 43 usec_timeout=500000 usect_delayed=408000 reason=VMSCAN_THROTTLE_NOPROGRESS 55 usec_timeout=500000 usect_delayed=416000 reason=VMSCAN_THROTTLE_NOPROGRESS 56 usec_timeout=500000 usect_delayed=76000 reason=VMSCAN_THROTTLE_NOPROGRESS 58 usec_timeout=500000 usect_delayed=120000 reason=VMSCAN_THROTTLE_NOPROGRESS 59 usec_timeout=500000 usect_delayed=208000 reason=VMSCAN_THROTTLE_NOPROGRESS 61 usec_timeout=500000 usect_delayed=68000 reason=VMSCAN_THROTTLE_NOPROGRESS 71 usec_timeout=500000 usect_delayed=192000 reason=VMSCAN_THROTTLE_NOPROGRESS 71 usec_timeout=500000 usect_delayed=480000 reason=VMSCAN_THROTTLE_NOPROGRESS 79 usec_timeout=500000 usect_delayed=60000 reason=VMSCAN_THROTTLE_NOPROGRESS 82 usec_timeout=500000 usect_delayed=320000 reason=VMSCAN_THROTTLE_NOPROGRESS 82 usec_timeout=500000 usect_delayed=92000 reason=VMSCAN_THROTTLE_NOPROGRESS 85 usec_timeout=500000 usect_delayed=64000 reason=VMSCAN_THROTTLE_NOPROGRESS 85 usec_timeout=500000 usect_delayed=80000 reason=VMSCAN_THROTTLE_NOPROGRESS 88 usec_timeout=500000 usect_delayed=84000 reason=VMSCAN_THROTTLE_NOPROGRESS 90 usec_timeout=500000 usect_delayed=160000 reason=VMSCAN_THROTTLE_NOPROGRESS 90 usec_timeout=500000 usect_delayed=292000 reason=VMSCAN_THROTTLE_NOPROGRESS 94 usec_timeout=500000 usect_delayed=56000 reason=VMSCAN_THROTTLE_NOPROGRESS 118 usec_timeout=500000 usect_delayed=88000 reason=VMSCAN_THROTTLE_NOPROGRESS 119 usec_timeout=500000 usect_delayed=72000 reason=VMSCAN_THROTTLE_NOPROGRESS 126 usec_timeout=500000 usect_delayed=108000 reason=VMSCAN_THROTTLE_NOPROGRESS 146 usec_timeout=500000 usect_delayed=52000 reason=VMSCAN_THROTTLE_NOPROGRESS 148 usec_timeout=500000 usect_delayed=36000 reason=VMSCAN_THROTTLE_NOPROGRESS 148 usec_timeout=500000 usect_delayed=48000 reason=VMSCAN_THROTTLE_NOPROGRESS 159 usec_timeout=500000 usect_delayed=28000 reason=VMSCAN_THROTTLE_NOPROGRESS 178 usec_timeout=500000 usect_delayed=44000 reason=VMSCAN_THROTTLE_NOPROGRESS 183 usec_timeout=500000 usect_delayed=40000 reason=VMSCAN_THROTTLE_NOPROGRESS 237 usec_timeout=500000 usect_delayed=100000 reason=VMSCAN_THROTTLE_NOPROGRESS 266 usec_timeout=500000 usect_delayed=32000 reason=VMSCAN_THROTTLE_NOPROGRESS 313 usec_timeout=500000 usect_delayed=24000 reason=VMSCAN_THROTTLE_NOPROGRESS 347 usec_timeout=500000 usect_delayed=96000 reason=VMSCAN_THROTTLE_NOPROGRESS 470 usec_timeout=500000 usect_delayed=20000 reason=VMSCAN_THROTTLE_NOPROGRESS 559 usec_timeout=500000 usect_delayed=16000 reason=VMSCAN_THROTTLE_NOPROGRESS 964 usec_timeout=500000 usect_delayed=12000 reason=VMSCAN_THROTTLE_NOPROGRESS 2001 usec_timeout=500000 usect_delayed=104000 reason=VMSCAN_THROTTLE_NOPROGRESS 2447 usec_timeout=500000 usect_delayed=8000 reason=VMSCAN_THROTTLE_NOPROGRESS 7888 usec_timeout=500000 usect_delayed=4000 reason=VMSCAN_THROTTLE_NOPROGRESS 22727 usec_timeout=500000 usect_delayed=0 reason=VMSCAN_THROTTLE_NOPROGRESS 51305 usec_timeout=500000 usect_delayed=500000 reason=VMSCAN_THROTTLE_NOPROGRESS The full timeout is often hit but a large number also do not stall at all. The remainder slept a little allowing other reclaim tasks to make progress. While this timeout could be further increased, it could also negatively impact worst-case behaviour when there is no prioritisation of what task should make progress. For VMSCAN_THROTTLE_WRITEBACK, the breakdown was 1 usec_timeout=100000 usect_delayed=44000 reason=VMSCAN_THROTTLE_WRITEBACK 2 usec_timeout=100000 usect_delayed=76000 reason=VMSCAN_THROTTLE_WRITEBACK 3 usec_timeout=100000 usect_delayed=80000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=48000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=84000 reason=VMSCAN_THROTTLE_WRITEBACK 6 usec_timeout=100000 usect_delayed=72000 reason=VMSCAN_THROTTLE_WRITEBACK 7 usec_timeout=100000 usect_delayed=88000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=56000 reason=VMSCAN_THROTTLE_WRITEBACK 12 usec_timeout=100000 usect_delayed=64000 reason=VMSCAN_THROTTLE_WRITEBACK 16 usec_timeout=100000 usect_delayed=92000 reason=VMSCAN_THROTTLE_WRITEBACK 24 usec_timeout=100000 usect_delayed=68000 reason=VMSCAN_THROTTLE_WRITEBACK 28 usec_timeout=100000 usect_delayed=32000 reason=VMSCAN_THROTTLE_WRITEBACK 30 usec_timeout=100000 usect_delayed=60000 reason=VMSCAN_THROTTLE_WRITEBACK 30 usec_timeout=100000 usect_delayed=96000 reason=VMSCAN_THROTTLE_WRITEBACK 32 usec_timeout=100000 usect_delayed=52000 reason=VMSCAN_THROTTLE_WRITEBACK 42 usec_timeout=100000 usect_delayed=40000 reason=VMSCAN_THROTTLE_WRITEBACK 77 usec_timeout=100000 usect_delayed=28000 reason=VMSCAN_THROTTLE_WRITEBACK 99 usec_timeout=100000 usect_delayed=36000 reason=VMSCAN_THROTTLE_WRITEBACK 137 usec_timeout=100000 usect_delayed=24000 reason=VMSCAN_THROTTLE_WRITEBACK 190 usec_timeout=100000 usect_delayed=20000 reason=VMSCAN_THROTTLE_WRITEBACK 339 usec_timeout=100000 usect_delayed=16000 reason=VMSCAN_THROTTLE_WRITEBACK 518 usec_timeout=100000 usect_delayed=12000 reason=VMSCAN_THROTTLE_WRITEBACK 852 usec_timeout=100000 usect_delayed=8000 reason=VMSCAN_THROTTLE_WRITEBACK 3359 usec_timeout=100000 usect_delayed=4000 reason=VMSCAN_THROTTLE_WRITEBACK 7147 usec_timeout=100000 usect_delayed=0 reason=VMSCAN_THROTTLE_WRITEBACK 83962 usec_timeout=100000 usect_delayed=100000 reason=VMSCAN_THROTTLE_WRITEBACK The majority hit the timeout in direct reclaim context although a sizable number did not stall at all. This is very different to kswapd where only a tiny percentage of stalls due to writeback reached the timeout. Bottom line, the throttling appears to work and the wakeup events may limit worst case stalls. There might be some grounds for adjusting timeouts but it's likely futile as the worst-case scenarios depend on the workload, memory size and the speed of the storage. A better approach to improve the series further would be to prioritise tasks based on their rate of allocation with the caveat that it may be very expensive to track. This patch (of 5): Page reclaim throttles on wait_iff_congested under the following conditions: - kswapd is encountering pages under writeback and marked for immediate reclaim implying that pages are cycling through the LRU faster than pages can be cleaned. - Direct reclaim will stall if all dirty pages are backed by congested inodes. wait_iff_congested is almost completely broken with few exceptions. This patch adds a new node-based workqueue and tracks the number of throttled tasks and pages written back since throttling started. If enough pages belonging to the node are written back then the throttled tasks will wake early. If not, the throttled tasks sleeps until the timeout expires. [neilb@suse.de: Uninterruptible sleep and simpler wakeups] [hdanton@sina.com: Avoid race when reclaim starts] [vbabka@suse.cz: vmstat irq-safe api, clarifications] Link: https://lore.kernel.org/linux-mm/45d8b7a6-8548-65f5-cccf-9f451d4ae3d4@kernel.dk/ [1] Link: https://lkml.kernel.org/r/20211022144651.19914-1-mgorman@techsingularity.net Link: https://lkml.kernel.org/r/20211022144651.19914-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: NeilBrown <neilb@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: "Darrick J . Wong" <djwong@kernel.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@surriel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Corbet <corbet@lwn.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 20:42:25 +00:00
int nr_throttled);
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
static inline void acct_reclaim_writeback(struct folio *folio)
mm/vmscan: throttle reclaim until some writeback completes if congested Patch series "Remove dependency on congestion_wait in mm/", v5. This series that removes all calls to congestion_wait in mm/ and deletes wait_iff_congested. It's not a clever implementation but congestion_wait has been broken for a long time [1]. Even if congestion throttling worked, it was never a great idea. While excessive dirty/writeback pages at the tail of the LRU is one possibility that reclaim may be slow, there is also the problem of too many pages being isolated and reclaim failing for other reasons (elevated references, too many pages isolated, excessive LRU contention etc). This series replaces the "congestion" throttling with 3 different types. - If there are too many dirty/writeback pages, sleep until a timeout or enough pages get cleaned - If too many pages are isolated, sleep until enough isolated pages are either reclaimed or put back on the LRU - If no progress is being made, direct reclaim tasks sleep until another task makes progress with acceptable efficiency. This was initially tested with a mix of workloads that used to trigger corner cases that no longer work. A new test case was created called "stutterp" (pagereclaim-stutterp-noreaders in mmtests) using a freshly created XFS filesystem. Note that it may be necessary to increase the timeout of ssh if executing remotely as ssh itself can get throttled and the connection may timeout. stutterp varies the number of "worker" processes from 4 up to NR_CPUS*4 to check the impact as the number of direct reclaimers increase. It has four types of worker. - One "anon latency" worker creates small mappings with mmap() and times how long it takes to fault the mapping reading it 4K at a time - X file writers which is fio randomly writing X files where the total size of the files add up to the allowed dirty_ratio. fio is allowed to run for a warmup period to allow some file-backed pages to accumulate. The duration of the warmup is based on the best-case linear write speed of the storage. - Y file readers which is fio randomly reading small files - Z anon memory hogs which continually map (100-dirty_ratio)% of memory - Total estimated WSS = (100+dirty_ration) percentage of memory X+Y+Z+1 == NR_WORKERS varying from 4 up to NR_CPUS*4 The intent is to maximise the total WSS with a mix of file and anon memory where some anonymous memory must be swapped and there is a high likelihood of dirty/writeback pages reaching the end of the LRU. The test can be configured to have no background readers to stress dirty/writeback pages. The results below are based on having zero readers. The short summary of the results is that the series works and stalls until some event occurs but the timeouts may need adjustment. The test results are not broken down by patch as the series should be treated as one block that replaces a broken throttling mechanism with a working one. Finally, three machines were tested but I'm reporting the worst set of results. The other two machines had much better latencies for example. First the results of the "anon latency" latency stutterp 5.15.0-rc1 5.15.0-rc1 vanilla mm-reclaimcongest-v5r4 Amean mmap-4 31.4003 ( 0.00%) 2661.0198 (-8374.52%) Amean mmap-7 38.1641 ( 0.00%) 149.2891 (-291.18%) Amean mmap-12 60.0981 ( 0.00%) 187.8105 (-212.51%) Amean mmap-21 161.2699 ( 0.00%) 213.9107 ( -32.64%) Amean mmap-30 174.5589 ( 0.00%) 377.7548 (-116.41%) Amean mmap-48 8106.8160 ( 0.00%) 1070.5616 ( 86.79%) Stddev mmap-4 41.3455 ( 0.00%) 27573.9676 (-66591.66%) Stddev mmap-7 53.5556 ( 0.00%) 4608.5860 (-8505.23%) Stddev mmap-12 171.3897 ( 0.00%) 5559.4542 (-3143.75%) Stddev mmap-21 1506.6752 ( 0.00%) 5746.2507 (-281.39%) Stddev mmap-30 557.5806 ( 0.00%) 7678.1624 (-1277.05%) Stddev mmap-48 61681.5718 ( 0.00%) 14507.2830 ( 76.48%) Max-90 mmap-4 31.4243 ( 0.00%) 83.1457 (-164.59%) Max-90 mmap-7 41.0410 ( 0.00%) 41.0720 ( -0.08%) Max-90 mmap-12 66.5255 ( 0.00%) 53.9073 ( 18.97%) Max-90 mmap-21 146.7479 ( 0.00%) 105.9540 ( 27.80%) Max-90 mmap-30 193.9513 ( 0.00%) 64.3067 ( 66.84%) Max-90 mmap-48 277.9137 ( 0.00%) 591.0594 (-112.68%) Max mmap-4 1913.8009 ( 0.00%) 299623.9695 (-15555.96%) Max mmap-7 2423.9665 ( 0.00%) 204453.1708 (-8334.65%) Max mmap-12 6845.6573 ( 0.00%) 221090.3366 (-3129.64%) Max mmap-21 56278.6508 ( 0.00%) 213877.3496 (-280.03%) Max mmap-30 19716.2990 ( 0.00%) 216287.6229 (-997.00%) Max mmap-48 477923.9400 ( 0.00%) 245414.8238 ( 48.65%) For most thread counts, the time to mmap() is unfortunately increased. In earlier versions of the series, this was lower but a large number of throttling events were reaching their timeout increasing the amount of inefficient scanning of the LRU. There is no prioritisation of reclaim tasks making progress based on each tasks rate of page allocation versus progress of reclaim. The variance is also impacted for high worker counts but in all cases, the differences in latency are not statistically significant due to very large maximum outliers. Max-90 shows that 90% of the stalls are comparable but the Max results show the massive outliers which are increased to to stalling. It is expected that this will be very machine dependant. Due to the test design, reclaim is difficult so allocations stall and there are variances depending on whether THPs can be allocated or not. The amount of memory will affect exactly how bad the corner cases are and how often they trigger. The warmup period calculation is not ideal as it's based on linear writes where as fio is randomly writing multiple files from multiple tasks so the start state of the test is variable. For example, these are the latencies on a single-socket machine that had more memory Amean mmap-4 42.2287 ( 0.00%) 49.6838 * -17.65%* Amean mmap-7 216.4326 ( 0.00%) 47.4451 * 78.08%* Amean mmap-12 2412.0588 ( 0.00%) 51.7497 ( 97.85%) Amean mmap-21 5546.2548 ( 0.00%) 51.8862 ( 99.06%) Amean mmap-30 1085.3121 ( 0.00%) 72.1004 ( 93.36%) The overall system CPU usage and elapsed time is as follows 5.15.0-rc3 5.15.0-rc3 vanilla mm-reclaimcongest-v5r4 Duration User 6989.03 983.42 Duration System 7308.12 799.68 Duration Elapsed 2277.67 2092.98 The patches reduce system CPU usage by 89% as the vanilla kernel is rarely stalling. The high-level /proc/vmstats show 5.15.0-rc1 5.15.0-rc1 vanilla mm-reclaimcongest-v5r2 Ops Direct pages scanned 1056608451.00 503594991.00 Ops Kswapd pages scanned 109795048.00 147289810.00 Ops Kswapd pages reclaimed 63269243.00 31036005.00 Ops Direct pages reclaimed 10803973.00 6328887.00 Ops Kswapd efficiency % 57.62 21.07 Ops Kswapd velocity 48204.98 57572.86 Ops Direct efficiency % 1.02 1.26 Ops Direct velocity 463898.83 196845.97 Kswapd scanned less pages but the detailed pattern is different. The vanilla kernel scans slowly over time where as the patches exhibits burst patterns of scan activity. Direct reclaim scanning is reduced by 52% due to stalling. The pattern for stealing pages is also slightly different. Both kernels exhibit spikes but the vanilla kernel when reclaiming shows pages being reclaimed over a period of time where as the patches tend to reclaim in spikes. The difference is that vanilla is not throttling and instead scanning constantly finding some pages over time where as the patched kernel throttles and reclaims in spikes. Ops Percentage direct scans 90.59 77.37 For direct reclaim, vanilla scanned 90.59% of pages where as with the patches, 77.37% were direct reclaim due to throttling Ops Page writes by reclaim 2613590.00 1687131.00 Page writes from reclaim context are reduced. Ops Page writes anon 2932752.00 1917048.00 And there is less swapping. Ops Page reclaim immediate 996248528.00 107664764.00 The number of pages encountered at the tail of the LRU tagged for immediate reclaim but still dirty/writeback is reduced by 89%. Ops Slabs scanned 164284.00 153608.00 Slab scan activity is similar. ftrace was used to gather stall activity Vanilla ------- 1 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=16000 2 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=12000 8 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=8000 29 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=4000 82394 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=0 The fast majority of wait_iff_congested calls do not stall at all. What is likely happening is that cond_resched() reschedules the task for a short period when the BDI is not registering congestion (which it never will in this test setup). 1 writeback_congestion_wait: usec_timeout=100000 usec_delayed=120000 2 writeback_congestion_wait: usec_timeout=100000 usec_delayed=132000 4 writeback_congestion_wait: usec_timeout=100000 usec_delayed=112000 380 writeback_congestion_wait: usec_timeout=100000 usec_delayed=108000 778 writeback_congestion_wait: usec_timeout=100000 usec_delayed=104000 congestion_wait if called always exceeds the timeout as there is no trigger to wake it up. Bottom line: Vanilla will throttle but it's not effective. Patch series ------------ Kswapd throttle activity was always due to scanning pages tagged for immediate reclaim at the tail of the LRU 1 usec_timeout=100000 usect_delayed=72000 reason=VMSCAN_THROTTLE_WRITEBACK 4 usec_timeout=100000 usect_delayed=20000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=12000 reason=VMSCAN_THROTTLE_WRITEBACK 6 usec_timeout=100000 usect_delayed=16000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=100000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=8000 reason=VMSCAN_THROTTLE_WRITEBACK 94 usec_timeout=100000 usect_delayed=0 reason=VMSCAN_THROTTLE_WRITEBACK 112 usec_timeout=100000 usect_delayed=4000 reason=VMSCAN_THROTTLE_WRITEBACK The majority of events did not stall or stalled for a short period. Roughly 16% of stalls reached the timeout before expiry. For direct reclaim, the number of times stalled for each reason were 6624 reason=VMSCAN_THROTTLE_ISOLATED 93246 reason=VMSCAN_THROTTLE_NOPROGRESS 96934 reason=VMSCAN_THROTTLE_WRITEBACK The most common reason to stall was due to excessive pages tagged for immediate reclaim at the tail of the LRU followed by a failure to make forward. A relatively small number were due to too many pages isolated from the LRU by parallel threads For VMSCAN_THROTTLE_ISOLATED, the breakdown of delays was 9 usec_timeout=20000 usect_delayed=4000 reason=VMSCAN_THROTTLE_ISOLATED 12 usec_timeout=20000 usect_delayed=16000 reason=VMSCAN_THROTTLE_ISOLATED 83 usec_timeout=20000 usect_delayed=20000 reason=VMSCAN_THROTTLE_ISOLATED 6520 usec_timeout=20000 usect_delayed=0 reason=VMSCAN_THROTTLE_ISOLATED Most did not stall at all. A small number reached the timeout. For VMSCAN_THROTTLE_NOPROGRESS, the breakdown of stalls were all over the map 1 usec_timeout=500000 usect_delayed=324000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=332000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=348000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=360000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=228000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=260000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=340000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=364000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=372000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=428000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=460000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=464000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=244000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=252000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=272000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=188000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=268000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=328000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=380000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=392000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=432000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=204000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=220000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=412000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=436000 reason=VMSCAN_THROTTLE_NOPROGRESS 6 usec_timeout=500000 usect_delayed=488000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=212000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=300000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=316000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=472000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=248000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=356000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=456000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=124000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=376000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=484000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=172000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=420000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=452000 reason=VMSCAN_THROTTLE_NOPROGRESS 11 usec_timeout=500000 usect_delayed=256000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=112000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=116000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=144000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=152000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=264000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=384000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=424000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=492000 reason=VMSCAN_THROTTLE_NOPROGRESS 13 usec_timeout=500000 usect_delayed=184000 reason=VMSCAN_THROTTLE_NOPROGRESS 13 usec_timeout=500000 usect_delayed=444000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=308000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=440000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=476000 reason=VMSCAN_THROTTLE_NOPROGRESS 16 usec_timeout=500000 usect_delayed=140000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=232000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=240000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=280000 reason=VMSCAN_THROTTLE_NOPROGRESS 18 usec_timeout=500000 usect_delayed=404000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=148000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=216000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=468000 reason=VMSCAN_THROTTLE_NOPROGRESS 21 usec_timeout=500000 usect_delayed=448000 reason=VMSCAN_THROTTLE_NOPROGRESS 23 usec_timeout=500000 usect_delayed=168000 reason=VMSCAN_THROTTLE_NOPROGRESS 23 usec_timeout=500000 usect_delayed=296000 reason=VMSCAN_THROTTLE_NOPROGRESS 25 usec_timeout=500000 usect_delayed=132000 reason=VMSCAN_THROTTLE_NOPROGRESS 25 usec_timeout=500000 usect_delayed=352000 reason=VMSCAN_THROTTLE_NOPROGRESS 26 usec_timeout=500000 usect_delayed=180000 reason=VMSCAN_THROTTLE_NOPROGRESS 27 usec_timeout=500000 usect_delayed=284000 reason=VMSCAN_THROTTLE_NOPROGRESS 28 usec_timeout=500000 usect_delayed=164000 reason=VMSCAN_THROTTLE_NOPROGRESS 29 usec_timeout=500000 usect_delayed=136000 reason=VMSCAN_THROTTLE_NOPROGRESS 30 usec_timeout=500000 usect_delayed=200000 reason=VMSCAN_THROTTLE_NOPROGRESS 30 usec_timeout=500000 usect_delayed=400000 reason=VMSCAN_THROTTLE_NOPROGRESS 31 usec_timeout=500000 usect_delayed=196000 reason=VMSCAN_THROTTLE_NOPROGRESS 32 usec_timeout=500000 usect_delayed=156000 reason=VMSCAN_THROTTLE_NOPROGRESS 33 usec_timeout=500000 usect_delayed=224000 reason=VMSCAN_THROTTLE_NOPROGRESS 35 usec_timeout=500000 usect_delayed=128000 reason=VMSCAN_THROTTLE_NOPROGRESS 35 usec_timeout=500000 usect_delayed=176000 reason=VMSCAN_THROTTLE_NOPROGRESS 36 usec_timeout=500000 usect_delayed=368000 reason=VMSCAN_THROTTLE_NOPROGRESS 36 usec_timeout=500000 usect_delayed=496000 reason=VMSCAN_THROTTLE_NOPROGRESS 37 usec_timeout=500000 usect_delayed=312000 reason=VMSCAN_THROTTLE_NOPROGRESS 38 usec_timeout=500000 usect_delayed=304000 reason=VMSCAN_THROTTLE_NOPROGRESS 40 usec_timeout=500000 usect_delayed=288000 reason=VMSCAN_THROTTLE_NOPROGRESS 43 usec_timeout=500000 usect_delayed=408000 reason=VMSCAN_THROTTLE_NOPROGRESS 55 usec_timeout=500000 usect_delayed=416000 reason=VMSCAN_THROTTLE_NOPROGRESS 56 usec_timeout=500000 usect_delayed=76000 reason=VMSCAN_THROTTLE_NOPROGRESS 58 usec_timeout=500000 usect_delayed=120000 reason=VMSCAN_THROTTLE_NOPROGRESS 59 usec_timeout=500000 usect_delayed=208000 reason=VMSCAN_THROTTLE_NOPROGRESS 61 usec_timeout=500000 usect_delayed=68000 reason=VMSCAN_THROTTLE_NOPROGRESS 71 usec_timeout=500000 usect_delayed=192000 reason=VMSCAN_THROTTLE_NOPROGRESS 71 usec_timeout=500000 usect_delayed=480000 reason=VMSCAN_THROTTLE_NOPROGRESS 79 usec_timeout=500000 usect_delayed=60000 reason=VMSCAN_THROTTLE_NOPROGRESS 82 usec_timeout=500000 usect_delayed=320000 reason=VMSCAN_THROTTLE_NOPROGRESS 82 usec_timeout=500000 usect_delayed=92000 reason=VMSCAN_THROTTLE_NOPROGRESS 85 usec_timeout=500000 usect_delayed=64000 reason=VMSCAN_THROTTLE_NOPROGRESS 85 usec_timeout=500000 usect_delayed=80000 reason=VMSCAN_THROTTLE_NOPROGRESS 88 usec_timeout=500000 usect_delayed=84000 reason=VMSCAN_THROTTLE_NOPROGRESS 90 usec_timeout=500000 usect_delayed=160000 reason=VMSCAN_THROTTLE_NOPROGRESS 90 usec_timeout=500000 usect_delayed=292000 reason=VMSCAN_THROTTLE_NOPROGRESS 94 usec_timeout=500000 usect_delayed=56000 reason=VMSCAN_THROTTLE_NOPROGRESS 118 usec_timeout=500000 usect_delayed=88000 reason=VMSCAN_THROTTLE_NOPROGRESS 119 usec_timeout=500000 usect_delayed=72000 reason=VMSCAN_THROTTLE_NOPROGRESS 126 usec_timeout=500000 usect_delayed=108000 reason=VMSCAN_THROTTLE_NOPROGRESS 146 usec_timeout=500000 usect_delayed=52000 reason=VMSCAN_THROTTLE_NOPROGRESS 148 usec_timeout=500000 usect_delayed=36000 reason=VMSCAN_THROTTLE_NOPROGRESS 148 usec_timeout=500000 usect_delayed=48000 reason=VMSCAN_THROTTLE_NOPROGRESS 159 usec_timeout=500000 usect_delayed=28000 reason=VMSCAN_THROTTLE_NOPROGRESS 178 usec_timeout=500000 usect_delayed=44000 reason=VMSCAN_THROTTLE_NOPROGRESS 183 usec_timeout=500000 usect_delayed=40000 reason=VMSCAN_THROTTLE_NOPROGRESS 237 usec_timeout=500000 usect_delayed=100000 reason=VMSCAN_THROTTLE_NOPROGRESS 266 usec_timeout=500000 usect_delayed=32000 reason=VMSCAN_THROTTLE_NOPROGRESS 313 usec_timeout=500000 usect_delayed=24000 reason=VMSCAN_THROTTLE_NOPROGRESS 347 usec_timeout=500000 usect_delayed=96000 reason=VMSCAN_THROTTLE_NOPROGRESS 470 usec_timeout=500000 usect_delayed=20000 reason=VMSCAN_THROTTLE_NOPROGRESS 559 usec_timeout=500000 usect_delayed=16000 reason=VMSCAN_THROTTLE_NOPROGRESS 964 usec_timeout=500000 usect_delayed=12000 reason=VMSCAN_THROTTLE_NOPROGRESS 2001 usec_timeout=500000 usect_delayed=104000 reason=VMSCAN_THROTTLE_NOPROGRESS 2447 usec_timeout=500000 usect_delayed=8000 reason=VMSCAN_THROTTLE_NOPROGRESS 7888 usec_timeout=500000 usect_delayed=4000 reason=VMSCAN_THROTTLE_NOPROGRESS 22727 usec_timeout=500000 usect_delayed=0 reason=VMSCAN_THROTTLE_NOPROGRESS 51305 usec_timeout=500000 usect_delayed=500000 reason=VMSCAN_THROTTLE_NOPROGRESS The full timeout is often hit but a large number also do not stall at all. The remainder slept a little allowing other reclaim tasks to make progress. While this timeout could be further increased, it could also negatively impact worst-case behaviour when there is no prioritisation of what task should make progress. For VMSCAN_THROTTLE_WRITEBACK, the breakdown was 1 usec_timeout=100000 usect_delayed=44000 reason=VMSCAN_THROTTLE_WRITEBACK 2 usec_timeout=100000 usect_delayed=76000 reason=VMSCAN_THROTTLE_WRITEBACK 3 usec_timeout=100000 usect_delayed=80000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=48000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=84000 reason=VMSCAN_THROTTLE_WRITEBACK 6 usec_timeout=100000 usect_delayed=72000 reason=VMSCAN_THROTTLE_WRITEBACK 7 usec_timeout=100000 usect_delayed=88000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=56000 reason=VMSCAN_THROTTLE_WRITEBACK 12 usec_timeout=100000 usect_delayed=64000 reason=VMSCAN_THROTTLE_WRITEBACK 16 usec_timeout=100000 usect_delayed=92000 reason=VMSCAN_THROTTLE_WRITEBACK 24 usec_timeout=100000 usect_delayed=68000 reason=VMSCAN_THROTTLE_WRITEBACK 28 usec_timeout=100000 usect_delayed=32000 reason=VMSCAN_THROTTLE_WRITEBACK 30 usec_timeout=100000 usect_delayed=60000 reason=VMSCAN_THROTTLE_WRITEBACK 30 usec_timeout=100000 usect_delayed=96000 reason=VMSCAN_THROTTLE_WRITEBACK 32 usec_timeout=100000 usect_delayed=52000 reason=VMSCAN_THROTTLE_WRITEBACK 42 usec_timeout=100000 usect_delayed=40000 reason=VMSCAN_THROTTLE_WRITEBACK 77 usec_timeout=100000 usect_delayed=28000 reason=VMSCAN_THROTTLE_WRITEBACK 99 usec_timeout=100000 usect_delayed=36000 reason=VMSCAN_THROTTLE_WRITEBACK 137 usec_timeout=100000 usect_delayed=24000 reason=VMSCAN_THROTTLE_WRITEBACK 190 usec_timeout=100000 usect_delayed=20000 reason=VMSCAN_THROTTLE_WRITEBACK 339 usec_timeout=100000 usect_delayed=16000 reason=VMSCAN_THROTTLE_WRITEBACK 518 usec_timeout=100000 usect_delayed=12000 reason=VMSCAN_THROTTLE_WRITEBACK 852 usec_timeout=100000 usect_delayed=8000 reason=VMSCAN_THROTTLE_WRITEBACK 3359 usec_timeout=100000 usect_delayed=4000 reason=VMSCAN_THROTTLE_WRITEBACK 7147 usec_timeout=100000 usect_delayed=0 reason=VMSCAN_THROTTLE_WRITEBACK 83962 usec_timeout=100000 usect_delayed=100000 reason=VMSCAN_THROTTLE_WRITEBACK The majority hit the timeout in direct reclaim context although a sizable number did not stall at all. This is very different to kswapd where only a tiny percentage of stalls due to writeback reached the timeout. Bottom line, the throttling appears to work and the wakeup events may limit worst case stalls. There might be some grounds for adjusting timeouts but it's likely futile as the worst-case scenarios depend on the workload, memory size and the speed of the storage. A better approach to improve the series further would be to prioritise tasks based on their rate of allocation with the caveat that it may be very expensive to track. This patch (of 5): Page reclaim throttles on wait_iff_congested under the following conditions: - kswapd is encountering pages under writeback and marked for immediate reclaim implying that pages are cycling through the LRU faster than pages can be cleaned. - Direct reclaim will stall if all dirty pages are backed by congested inodes. wait_iff_congested is almost completely broken with few exceptions. This patch adds a new node-based workqueue and tracks the number of throttled tasks and pages written back since throttling started. If enough pages belonging to the node are written back then the throttled tasks will wake early. If not, the throttled tasks sleeps until the timeout expires. [neilb@suse.de: Uninterruptible sleep and simpler wakeups] [hdanton@sina.com: Avoid race when reclaim starts] [vbabka@suse.cz: vmstat irq-safe api, clarifications] Link: https://lore.kernel.org/linux-mm/45d8b7a6-8548-65f5-cccf-9f451d4ae3d4@kernel.dk/ [1] Link: https://lkml.kernel.org/r/20211022144651.19914-1-mgorman@techsingularity.net Link: https://lkml.kernel.org/r/20211022144651.19914-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: NeilBrown <neilb@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: "Darrick J . Wong" <djwong@kernel.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@surriel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Corbet <corbet@lwn.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 20:42:25 +00:00
{
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
pg_data_t *pgdat = folio_pgdat(folio);
mm/vmscan: throttle reclaim until some writeback completes if congested Patch series "Remove dependency on congestion_wait in mm/", v5. This series that removes all calls to congestion_wait in mm/ and deletes wait_iff_congested. It's not a clever implementation but congestion_wait has been broken for a long time [1]. Even if congestion throttling worked, it was never a great idea. While excessive dirty/writeback pages at the tail of the LRU is one possibility that reclaim may be slow, there is also the problem of too many pages being isolated and reclaim failing for other reasons (elevated references, too many pages isolated, excessive LRU contention etc). This series replaces the "congestion" throttling with 3 different types. - If there are too many dirty/writeback pages, sleep until a timeout or enough pages get cleaned - If too many pages are isolated, sleep until enough isolated pages are either reclaimed or put back on the LRU - If no progress is being made, direct reclaim tasks sleep until another task makes progress with acceptable efficiency. This was initially tested with a mix of workloads that used to trigger corner cases that no longer work. A new test case was created called "stutterp" (pagereclaim-stutterp-noreaders in mmtests) using a freshly created XFS filesystem. Note that it may be necessary to increase the timeout of ssh if executing remotely as ssh itself can get throttled and the connection may timeout. stutterp varies the number of "worker" processes from 4 up to NR_CPUS*4 to check the impact as the number of direct reclaimers increase. It has four types of worker. - One "anon latency" worker creates small mappings with mmap() and times how long it takes to fault the mapping reading it 4K at a time - X file writers which is fio randomly writing X files where the total size of the files add up to the allowed dirty_ratio. fio is allowed to run for a warmup period to allow some file-backed pages to accumulate. The duration of the warmup is based on the best-case linear write speed of the storage. - Y file readers which is fio randomly reading small files - Z anon memory hogs which continually map (100-dirty_ratio)% of memory - Total estimated WSS = (100+dirty_ration) percentage of memory X+Y+Z+1 == NR_WORKERS varying from 4 up to NR_CPUS*4 The intent is to maximise the total WSS with a mix of file and anon memory where some anonymous memory must be swapped and there is a high likelihood of dirty/writeback pages reaching the end of the LRU. The test can be configured to have no background readers to stress dirty/writeback pages. The results below are based on having zero readers. The short summary of the results is that the series works and stalls until some event occurs but the timeouts may need adjustment. The test results are not broken down by patch as the series should be treated as one block that replaces a broken throttling mechanism with a working one. Finally, three machines were tested but I'm reporting the worst set of results. The other two machines had much better latencies for example. First the results of the "anon latency" latency stutterp 5.15.0-rc1 5.15.0-rc1 vanilla mm-reclaimcongest-v5r4 Amean mmap-4 31.4003 ( 0.00%) 2661.0198 (-8374.52%) Amean mmap-7 38.1641 ( 0.00%) 149.2891 (-291.18%) Amean mmap-12 60.0981 ( 0.00%) 187.8105 (-212.51%) Amean mmap-21 161.2699 ( 0.00%) 213.9107 ( -32.64%) Amean mmap-30 174.5589 ( 0.00%) 377.7548 (-116.41%) Amean mmap-48 8106.8160 ( 0.00%) 1070.5616 ( 86.79%) Stddev mmap-4 41.3455 ( 0.00%) 27573.9676 (-66591.66%) Stddev mmap-7 53.5556 ( 0.00%) 4608.5860 (-8505.23%) Stddev mmap-12 171.3897 ( 0.00%) 5559.4542 (-3143.75%) Stddev mmap-21 1506.6752 ( 0.00%) 5746.2507 (-281.39%) Stddev mmap-30 557.5806 ( 0.00%) 7678.1624 (-1277.05%) Stddev mmap-48 61681.5718 ( 0.00%) 14507.2830 ( 76.48%) Max-90 mmap-4 31.4243 ( 0.00%) 83.1457 (-164.59%) Max-90 mmap-7 41.0410 ( 0.00%) 41.0720 ( -0.08%) Max-90 mmap-12 66.5255 ( 0.00%) 53.9073 ( 18.97%) Max-90 mmap-21 146.7479 ( 0.00%) 105.9540 ( 27.80%) Max-90 mmap-30 193.9513 ( 0.00%) 64.3067 ( 66.84%) Max-90 mmap-48 277.9137 ( 0.00%) 591.0594 (-112.68%) Max mmap-4 1913.8009 ( 0.00%) 299623.9695 (-15555.96%) Max mmap-7 2423.9665 ( 0.00%) 204453.1708 (-8334.65%) Max mmap-12 6845.6573 ( 0.00%) 221090.3366 (-3129.64%) Max mmap-21 56278.6508 ( 0.00%) 213877.3496 (-280.03%) Max mmap-30 19716.2990 ( 0.00%) 216287.6229 (-997.00%) Max mmap-48 477923.9400 ( 0.00%) 245414.8238 ( 48.65%) For most thread counts, the time to mmap() is unfortunately increased. In earlier versions of the series, this was lower but a large number of throttling events were reaching their timeout increasing the amount of inefficient scanning of the LRU. There is no prioritisation of reclaim tasks making progress based on each tasks rate of page allocation versus progress of reclaim. The variance is also impacted for high worker counts but in all cases, the differences in latency are not statistically significant due to very large maximum outliers. Max-90 shows that 90% of the stalls are comparable but the Max results show the massive outliers which are increased to to stalling. It is expected that this will be very machine dependant. Due to the test design, reclaim is difficult so allocations stall and there are variances depending on whether THPs can be allocated or not. The amount of memory will affect exactly how bad the corner cases are and how often they trigger. The warmup period calculation is not ideal as it's based on linear writes where as fio is randomly writing multiple files from multiple tasks so the start state of the test is variable. For example, these are the latencies on a single-socket machine that had more memory Amean mmap-4 42.2287 ( 0.00%) 49.6838 * -17.65%* Amean mmap-7 216.4326 ( 0.00%) 47.4451 * 78.08%* Amean mmap-12 2412.0588 ( 0.00%) 51.7497 ( 97.85%) Amean mmap-21 5546.2548 ( 0.00%) 51.8862 ( 99.06%) Amean mmap-30 1085.3121 ( 0.00%) 72.1004 ( 93.36%) The overall system CPU usage and elapsed time is as follows 5.15.0-rc3 5.15.0-rc3 vanilla mm-reclaimcongest-v5r4 Duration User 6989.03 983.42 Duration System 7308.12 799.68 Duration Elapsed 2277.67 2092.98 The patches reduce system CPU usage by 89% as the vanilla kernel is rarely stalling. The high-level /proc/vmstats show 5.15.0-rc1 5.15.0-rc1 vanilla mm-reclaimcongest-v5r2 Ops Direct pages scanned 1056608451.00 503594991.00 Ops Kswapd pages scanned 109795048.00 147289810.00 Ops Kswapd pages reclaimed 63269243.00 31036005.00 Ops Direct pages reclaimed 10803973.00 6328887.00 Ops Kswapd efficiency % 57.62 21.07 Ops Kswapd velocity 48204.98 57572.86 Ops Direct efficiency % 1.02 1.26 Ops Direct velocity 463898.83 196845.97 Kswapd scanned less pages but the detailed pattern is different. The vanilla kernel scans slowly over time where as the patches exhibits burst patterns of scan activity. Direct reclaim scanning is reduced by 52% due to stalling. The pattern for stealing pages is also slightly different. Both kernels exhibit spikes but the vanilla kernel when reclaiming shows pages being reclaimed over a period of time where as the patches tend to reclaim in spikes. The difference is that vanilla is not throttling and instead scanning constantly finding some pages over time where as the patched kernel throttles and reclaims in spikes. Ops Percentage direct scans 90.59 77.37 For direct reclaim, vanilla scanned 90.59% of pages where as with the patches, 77.37% were direct reclaim due to throttling Ops Page writes by reclaim 2613590.00 1687131.00 Page writes from reclaim context are reduced. Ops Page writes anon 2932752.00 1917048.00 And there is less swapping. Ops Page reclaim immediate 996248528.00 107664764.00 The number of pages encountered at the tail of the LRU tagged for immediate reclaim but still dirty/writeback is reduced by 89%. Ops Slabs scanned 164284.00 153608.00 Slab scan activity is similar. ftrace was used to gather stall activity Vanilla ------- 1 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=16000 2 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=12000 8 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=8000 29 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=4000 82394 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=0 The fast majority of wait_iff_congested calls do not stall at all. What is likely happening is that cond_resched() reschedules the task for a short period when the BDI is not registering congestion (which it never will in this test setup). 1 writeback_congestion_wait: usec_timeout=100000 usec_delayed=120000 2 writeback_congestion_wait: usec_timeout=100000 usec_delayed=132000 4 writeback_congestion_wait: usec_timeout=100000 usec_delayed=112000 380 writeback_congestion_wait: usec_timeout=100000 usec_delayed=108000 778 writeback_congestion_wait: usec_timeout=100000 usec_delayed=104000 congestion_wait if called always exceeds the timeout as there is no trigger to wake it up. Bottom line: Vanilla will throttle but it's not effective. Patch series ------------ Kswapd throttle activity was always due to scanning pages tagged for immediate reclaim at the tail of the LRU 1 usec_timeout=100000 usect_delayed=72000 reason=VMSCAN_THROTTLE_WRITEBACK 4 usec_timeout=100000 usect_delayed=20000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=12000 reason=VMSCAN_THROTTLE_WRITEBACK 6 usec_timeout=100000 usect_delayed=16000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=100000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=8000 reason=VMSCAN_THROTTLE_WRITEBACK 94 usec_timeout=100000 usect_delayed=0 reason=VMSCAN_THROTTLE_WRITEBACK 112 usec_timeout=100000 usect_delayed=4000 reason=VMSCAN_THROTTLE_WRITEBACK The majority of events did not stall or stalled for a short period. Roughly 16% of stalls reached the timeout before expiry. For direct reclaim, the number of times stalled for each reason were 6624 reason=VMSCAN_THROTTLE_ISOLATED 93246 reason=VMSCAN_THROTTLE_NOPROGRESS 96934 reason=VMSCAN_THROTTLE_WRITEBACK The most common reason to stall was due to excessive pages tagged for immediate reclaim at the tail of the LRU followed by a failure to make forward. A relatively small number were due to too many pages isolated from the LRU by parallel threads For VMSCAN_THROTTLE_ISOLATED, the breakdown of delays was 9 usec_timeout=20000 usect_delayed=4000 reason=VMSCAN_THROTTLE_ISOLATED 12 usec_timeout=20000 usect_delayed=16000 reason=VMSCAN_THROTTLE_ISOLATED 83 usec_timeout=20000 usect_delayed=20000 reason=VMSCAN_THROTTLE_ISOLATED 6520 usec_timeout=20000 usect_delayed=0 reason=VMSCAN_THROTTLE_ISOLATED Most did not stall at all. A small number reached the timeout. For VMSCAN_THROTTLE_NOPROGRESS, the breakdown of stalls were all over the map 1 usec_timeout=500000 usect_delayed=324000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=332000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=348000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=360000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=228000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=260000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=340000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=364000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=372000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=428000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=460000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=464000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=244000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=252000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=272000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=188000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=268000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=328000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=380000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=392000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=432000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=204000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=220000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=412000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=436000 reason=VMSCAN_THROTTLE_NOPROGRESS 6 usec_timeout=500000 usect_delayed=488000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=212000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=300000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=316000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=472000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=248000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=356000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=456000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=124000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=376000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=484000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=172000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=420000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=452000 reason=VMSCAN_THROTTLE_NOPROGRESS 11 usec_timeout=500000 usect_delayed=256000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=112000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=116000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=144000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=152000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=264000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=384000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=424000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=492000 reason=VMSCAN_THROTTLE_NOPROGRESS 13 usec_timeout=500000 usect_delayed=184000 reason=VMSCAN_THROTTLE_NOPROGRESS 13 usec_timeout=500000 usect_delayed=444000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=308000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=440000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=476000 reason=VMSCAN_THROTTLE_NOPROGRESS 16 usec_timeout=500000 usect_delayed=140000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=232000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=240000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=280000 reason=VMSCAN_THROTTLE_NOPROGRESS 18 usec_timeout=500000 usect_delayed=404000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=148000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=216000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=468000 reason=VMSCAN_THROTTLE_NOPROGRESS 21 usec_timeout=500000 usect_delayed=448000 reason=VMSCAN_THROTTLE_NOPROGRESS 23 usec_timeout=500000 usect_delayed=168000 reason=VMSCAN_THROTTLE_NOPROGRESS 23 usec_timeout=500000 usect_delayed=296000 reason=VMSCAN_THROTTLE_NOPROGRESS 25 usec_timeout=500000 usect_delayed=132000 reason=VMSCAN_THROTTLE_NOPROGRESS 25 usec_timeout=500000 usect_delayed=352000 reason=VMSCAN_THROTTLE_NOPROGRESS 26 usec_timeout=500000 usect_delayed=180000 reason=VMSCAN_THROTTLE_NOPROGRESS 27 usec_timeout=500000 usect_delayed=284000 reason=VMSCAN_THROTTLE_NOPROGRESS 28 usec_timeout=500000 usect_delayed=164000 reason=VMSCAN_THROTTLE_NOPROGRESS 29 usec_timeout=500000 usect_delayed=136000 reason=VMSCAN_THROTTLE_NOPROGRESS 30 usec_timeout=500000 usect_delayed=200000 reason=VMSCAN_THROTTLE_NOPROGRESS 30 usec_timeout=500000 usect_delayed=400000 reason=VMSCAN_THROTTLE_NOPROGRESS 31 usec_timeout=500000 usect_delayed=196000 reason=VMSCAN_THROTTLE_NOPROGRESS 32 usec_timeout=500000 usect_delayed=156000 reason=VMSCAN_THROTTLE_NOPROGRESS 33 usec_timeout=500000 usect_delayed=224000 reason=VMSCAN_THROTTLE_NOPROGRESS 35 usec_timeout=500000 usect_delayed=128000 reason=VMSCAN_THROTTLE_NOPROGRESS 35 usec_timeout=500000 usect_delayed=176000 reason=VMSCAN_THROTTLE_NOPROGRESS 36 usec_timeout=500000 usect_delayed=368000 reason=VMSCAN_THROTTLE_NOPROGRESS 36 usec_timeout=500000 usect_delayed=496000 reason=VMSCAN_THROTTLE_NOPROGRESS 37 usec_timeout=500000 usect_delayed=312000 reason=VMSCAN_THROTTLE_NOPROGRESS 38 usec_timeout=500000 usect_delayed=304000 reason=VMSCAN_THROTTLE_NOPROGRESS 40 usec_timeout=500000 usect_delayed=288000 reason=VMSCAN_THROTTLE_NOPROGRESS 43 usec_timeout=500000 usect_delayed=408000 reason=VMSCAN_THROTTLE_NOPROGRESS 55 usec_timeout=500000 usect_delayed=416000 reason=VMSCAN_THROTTLE_NOPROGRESS 56 usec_timeout=500000 usect_delayed=76000 reason=VMSCAN_THROTTLE_NOPROGRESS 58 usec_timeout=500000 usect_delayed=120000 reason=VMSCAN_THROTTLE_NOPROGRESS 59 usec_timeout=500000 usect_delayed=208000 reason=VMSCAN_THROTTLE_NOPROGRESS 61 usec_timeout=500000 usect_delayed=68000 reason=VMSCAN_THROTTLE_NOPROGRESS 71 usec_timeout=500000 usect_delayed=192000 reason=VMSCAN_THROTTLE_NOPROGRESS 71 usec_timeout=500000 usect_delayed=480000 reason=VMSCAN_THROTTLE_NOPROGRESS 79 usec_timeout=500000 usect_delayed=60000 reason=VMSCAN_THROTTLE_NOPROGRESS 82 usec_timeout=500000 usect_delayed=320000 reason=VMSCAN_THROTTLE_NOPROGRESS 82 usec_timeout=500000 usect_delayed=92000 reason=VMSCAN_THROTTLE_NOPROGRESS 85 usec_timeout=500000 usect_delayed=64000 reason=VMSCAN_THROTTLE_NOPROGRESS 85 usec_timeout=500000 usect_delayed=80000 reason=VMSCAN_THROTTLE_NOPROGRESS 88 usec_timeout=500000 usect_delayed=84000 reason=VMSCAN_THROTTLE_NOPROGRESS 90 usec_timeout=500000 usect_delayed=160000 reason=VMSCAN_THROTTLE_NOPROGRESS 90 usec_timeout=500000 usect_delayed=292000 reason=VMSCAN_THROTTLE_NOPROGRESS 94 usec_timeout=500000 usect_delayed=56000 reason=VMSCAN_THROTTLE_NOPROGRESS 118 usec_timeout=500000 usect_delayed=88000 reason=VMSCAN_THROTTLE_NOPROGRESS 119 usec_timeout=500000 usect_delayed=72000 reason=VMSCAN_THROTTLE_NOPROGRESS 126 usec_timeout=500000 usect_delayed=108000 reason=VMSCAN_THROTTLE_NOPROGRESS 146 usec_timeout=500000 usect_delayed=52000 reason=VMSCAN_THROTTLE_NOPROGRESS 148 usec_timeout=500000 usect_delayed=36000 reason=VMSCAN_THROTTLE_NOPROGRESS 148 usec_timeout=500000 usect_delayed=48000 reason=VMSCAN_THROTTLE_NOPROGRESS 159 usec_timeout=500000 usect_delayed=28000 reason=VMSCAN_THROTTLE_NOPROGRESS 178 usec_timeout=500000 usect_delayed=44000 reason=VMSCAN_THROTTLE_NOPROGRESS 183 usec_timeout=500000 usect_delayed=40000 reason=VMSCAN_THROTTLE_NOPROGRESS 237 usec_timeout=500000 usect_delayed=100000 reason=VMSCAN_THROTTLE_NOPROGRESS 266 usec_timeout=500000 usect_delayed=32000 reason=VMSCAN_THROTTLE_NOPROGRESS 313 usec_timeout=500000 usect_delayed=24000 reason=VMSCAN_THROTTLE_NOPROGRESS 347 usec_timeout=500000 usect_delayed=96000 reason=VMSCAN_THROTTLE_NOPROGRESS 470 usec_timeout=500000 usect_delayed=20000 reason=VMSCAN_THROTTLE_NOPROGRESS 559 usec_timeout=500000 usect_delayed=16000 reason=VMSCAN_THROTTLE_NOPROGRESS 964 usec_timeout=500000 usect_delayed=12000 reason=VMSCAN_THROTTLE_NOPROGRESS 2001 usec_timeout=500000 usect_delayed=104000 reason=VMSCAN_THROTTLE_NOPROGRESS 2447 usec_timeout=500000 usect_delayed=8000 reason=VMSCAN_THROTTLE_NOPROGRESS 7888 usec_timeout=500000 usect_delayed=4000 reason=VMSCAN_THROTTLE_NOPROGRESS 22727 usec_timeout=500000 usect_delayed=0 reason=VMSCAN_THROTTLE_NOPROGRESS 51305 usec_timeout=500000 usect_delayed=500000 reason=VMSCAN_THROTTLE_NOPROGRESS The full timeout is often hit but a large number also do not stall at all. The remainder slept a little allowing other reclaim tasks to make progress. While this timeout could be further increased, it could also negatively impact worst-case behaviour when there is no prioritisation of what task should make progress. For VMSCAN_THROTTLE_WRITEBACK, the breakdown was 1 usec_timeout=100000 usect_delayed=44000 reason=VMSCAN_THROTTLE_WRITEBACK 2 usec_timeout=100000 usect_delayed=76000 reason=VMSCAN_THROTTLE_WRITEBACK 3 usec_timeout=100000 usect_delayed=80000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=48000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=84000 reason=VMSCAN_THROTTLE_WRITEBACK 6 usec_timeout=100000 usect_delayed=72000 reason=VMSCAN_THROTTLE_WRITEBACK 7 usec_timeout=100000 usect_delayed=88000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=56000 reason=VMSCAN_THROTTLE_WRITEBACK 12 usec_timeout=100000 usect_delayed=64000 reason=VMSCAN_THROTTLE_WRITEBACK 16 usec_timeout=100000 usect_delayed=92000 reason=VMSCAN_THROTTLE_WRITEBACK 24 usec_timeout=100000 usect_delayed=68000 reason=VMSCAN_THROTTLE_WRITEBACK 28 usec_timeout=100000 usect_delayed=32000 reason=VMSCAN_THROTTLE_WRITEBACK 30 usec_timeout=100000 usect_delayed=60000 reason=VMSCAN_THROTTLE_WRITEBACK 30 usec_timeout=100000 usect_delayed=96000 reason=VMSCAN_THROTTLE_WRITEBACK 32 usec_timeout=100000 usect_delayed=52000 reason=VMSCAN_THROTTLE_WRITEBACK 42 usec_timeout=100000 usect_delayed=40000 reason=VMSCAN_THROTTLE_WRITEBACK 77 usec_timeout=100000 usect_delayed=28000 reason=VMSCAN_THROTTLE_WRITEBACK 99 usec_timeout=100000 usect_delayed=36000 reason=VMSCAN_THROTTLE_WRITEBACK 137 usec_timeout=100000 usect_delayed=24000 reason=VMSCAN_THROTTLE_WRITEBACK 190 usec_timeout=100000 usect_delayed=20000 reason=VMSCAN_THROTTLE_WRITEBACK 339 usec_timeout=100000 usect_delayed=16000 reason=VMSCAN_THROTTLE_WRITEBACK 518 usec_timeout=100000 usect_delayed=12000 reason=VMSCAN_THROTTLE_WRITEBACK 852 usec_timeout=100000 usect_delayed=8000 reason=VMSCAN_THROTTLE_WRITEBACK 3359 usec_timeout=100000 usect_delayed=4000 reason=VMSCAN_THROTTLE_WRITEBACK 7147 usec_timeout=100000 usect_delayed=0 reason=VMSCAN_THROTTLE_WRITEBACK 83962 usec_timeout=100000 usect_delayed=100000 reason=VMSCAN_THROTTLE_WRITEBACK The majority hit the timeout in direct reclaim context although a sizable number did not stall at all. This is very different to kswapd where only a tiny percentage of stalls due to writeback reached the timeout. Bottom line, the throttling appears to work and the wakeup events may limit worst case stalls. There might be some grounds for adjusting timeouts but it's likely futile as the worst-case scenarios depend on the workload, memory size and the speed of the storage. A better approach to improve the series further would be to prioritise tasks based on their rate of allocation with the caveat that it may be very expensive to track. This patch (of 5): Page reclaim throttles on wait_iff_congested under the following conditions: - kswapd is encountering pages under writeback and marked for immediate reclaim implying that pages are cycling through the LRU faster than pages can be cleaned. - Direct reclaim will stall if all dirty pages are backed by congested inodes. wait_iff_congested is almost completely broken with few exceptions. This patch adds a new node-based workqueue and tracks the number of throttled tasks and pages written back since throttling started. If enough pages belonging to the node are written back then the throttled tasks will wake early. If not, the throttled tasks sleeps until the timeout expires. [neilb@suse.de: Uninterruptible sleep and simpler wakeups] [hdanton@sina.com: Avoid race when reclaim starts] [vbabka@suse.cz: vmstat irq-safe api, clarifications] Link: https://lore.kernel.org/linux-mm/45d8b7a6-8548-65f5-cccf-9f451d4ae3d4@kernel.dk/ [1] Link: https://lkml.kernel.org/r/20211022144651.19914-1-mgorman@techsingularity.net Link: https://lkml.kernel.org/r/20211022144651.19914-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: NeilBrown <neilb@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: "Darrick J . Wong" <djwong@kernel.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@surriel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Corbet <corbet@lwn.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 20:42:25 +00:00
int nr_throttled = atomic_read(&pgdat->nr_writeback_throttled);
if (nr_throttled)
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(pgdat, folio, nr_throttled);
mm/vmscan: throttle reclaim until some writeback completes if congested Patch series "Remove dependency on congestion_wait in mm/", v5. This series that removes all calls to congestion_wait in mm/ and deletes wait_iff_congested. It's not a clever implementation but congestion_wait has been broken for a long time [1]. Even if congestion throttling worked, it was never a great idea. While excessive dirty/writeback pages at the tail of the LRU is one possibility that reclaim may be slow, there is also the problem of too many pages being isolated and reclaim failing for other reasons (elevated references, too many pages isolated, excessive LRU contention etc). This series replaces the "congestion" throttling with 3 different types. - If there are too many dirty/writeback pages, sleep until a timeout or enough pages get cleaned - If too many pages are isolated, sleep until enough isolated pages are either reclaimed or put back on the LRU - If no progress is being made, direct reclaim tasks sleep until another task makes progress with acceptable efficiency. This was initially tested with a mix of workloads that used to trigger corner cases that no longer work. A new test case was created called "stutterp" (pagereclaim-stutterp-noreaders in mmtests) using a freshly created XFS filesystem. Note that it may be necessary to increase the timeout of ssh if executing remotely as ssh itself can get throttled and the connection may timeout. stutterp varies the number of "worker" processes from 4 up to NR_CPUS*4 to check the impact as the number of direct reclaimers increase. It has four types of worker. - One "anon latency" worker creates small mappings with mmap() and times how long it takes to fault the mapping reading it 4K at a time - X file writers which is fio randomly writing X files where the total size of the files add up to the allowed dirty_ratio. fio is allowed to run for a warmup period to allow some file-backed pages to accumulate. The duration of the warmup is based on the best-case linear write speed of the storage. - Y file readers which is fio randomly reading small files - Z anon memory hogs which continually map (100-dirty_ratio)% of memory - Total estimated WSS = (100+dirty_ration) percentage of memory X+Y+Z+1 == NR_WORKERS varying from 4 up to NR_CPUS*4 The intent is to maximise the total WSS with a mix of file and anon memory where some anonymous memory must be swapped and there is a high likelihood of dirty/writeback pages reaching the end of the LRU. The test can be configured to have no background readers to stress dirty/writeback pages. The results below are based on having zero readers. The short summary of the results is that the series works and stalls until some event occurs but the timeouts may need adjustment. The test results are not broken down by patch as the series should be treated as one block that replaces a broken throttling mechanism with a working one. Finally, three machines were tested but I'm reporting the worst set of results. The other two machines had much better latencies for example. First the results of the "anon latency" latency stutterp 5.15.0-rc1 5.15.0-rc1 vanilla mm-reclaimcongest-v5r4 Amean mmap-4 31.4003 ( 0.00%) 2661.0198 (-8374.52%) Amean mmap-7 38.1641 ( 0.00%) 149.2891 (-291.18%) Amean mmap-12 60.0981 ( 0.00%) 187.8105 (-212.51%) Amean mmap-21 161.2699 ( 0.00%) 213.9107 ( -32.64%) Amean mmap-30 174.5589 ( 0.00%) 377.7548 (-116.41%) Amean mmap-48 8106.8160 ( 0.00%) 1070.5616 ( 86.79%) Stddev mmap-4 41.3455 ( 0.00%) 27573.9676 (-66591.66%) Stddev mmap-7 53.5556 ( 0.00%) 4608.5860 (-8505.23%) Stddev mmap-12 171.3897 ( 0.00%) 5559.4542 (-3143.75%) Stddev mmap-21 1506.6752 ( 0.00%) 5746.2507 (-281.39%) Stddev mmap-30 557.5806 ( 0.00%) 7678.1624 (-1277.05%) Stddev mmap-48 61681.5718 ( 0.00%) 14507.2830 ( 76.48%) Max-90 mmap-4 31.4243 ( 0.00%) 83.1457 (-164.59%) Max-90 mmap-7 41.0410 ( 0.00%) 41.0720 ( -0.08%) Max-90 mmap-12 66.5255 ( 0.00%) 53.9073 ( 18.97%) Max-90 mmap-21 146.7479 ( 0.00%) 105.9540 ( 27.80%) Max-90 mmap-30 193.9513 ( 0.00%) 64.3067 ( 66.84%) Max-90 mmap-48 277.9137 ( 0.00%) 591.0594 (-112.68%) Max mmap-4 1913.8009 ( 0.00%) 299623.9695 (-15555.96%) Max mmap-7 2423.9665 ( 0.00%) 204453.1708 (-8334.65%) Max mmap-12 6845.6573 ( 0.00%) 221090.3366 (-3129.64%) Max mmap-21 56278.6508 ( 0.00%) 213877.3496 (-280.03%) Max mmap-30 19716.2990 ( 0.00%) 216287.6229 (-997.00%) Max mmap-48 477923.9400 ( 0.00%) 245414.8238 ( 48.65%) For most thread counts, the time to mmap() is unfortunately increased. In earlier versions of the series, this was lower but a large number of throttling events were reaching their timeout increasing the amount of inefficient scanning of the LRU. There is no prioritisation of reclaim tasks making progress based on each tasks rate of page allocation versus progress of reclaim. The variance is also impacted for high worker counts but in all cases, the differences in latency are not statistically significant due to very large maximum outliers. Max-90 shows that 90% of the stalls are comparable but the Max results show the massive outliers which are increased to to stalling. It is expected that this will be very machine dependant. Due to the test design, reclaim is difficult so allocations stall and there are variances depending on whether THPs can be allocated or not. The amount of memory will affect exactly how bad the corner cases are and how often they trigger. The warmup period calculation is not ideal as it's based on linear writes where as fio is randomly writing multiple files from multiple tasks so the start state of the test is variable. For example, these are the latencies on a single-socket machine that had more memory Amean mmap-4 42.2287 ( 0.00%) 49.6838 * -17.65%* Amean mmap-7 216.4326 ( 0.00%) 47.4451 * 78.08%* Amean mmap-12 2412.0588 ( 0.00%) 51.7497 ( 97.85%) Amean mmap-21 5546.2548 ( 0.00%) 51.8862 ( 99.06%) Amean mmap-30 1085.3121 ( 0.00%) 72.1004 ( 93.36%) The overall system CPU usage and elapsed time is as follows 5.15.0-rc3 5.15.0-rc3 vanilla mm-reclaimcongest-v5r4 Duration User 6989.03 983.42 Duration System 7308.12 799.68 Duration Elapsed 2277.67 2092.98 The patches reduce system CPU usage by 89% as the vanilla kernel is rarely stalling. The high-level /proc/vmstats show 5.15.0-rc1 5.15.0-rc1 vanilla mm-reclaimcongest-v5r2 Ops Direct pages scanned 1056608451.00 503594991.00 Ops Kswapd pages scanned 109795048.00 147289810.00 Ops Kswapd pages reclaimed 63269243.00 31036005.00 Ops Direct pages reclaimed 10803973.00 6328887.00 Ops Kswapd efficiency % 57.62 21.07 Ops Kswapd velocity 48204.98 57572.86 Ops Direct efficiency % 1.02 1.26 Ops Direct velocity 463898.83 196845.97 Kswapd scanned less pages but the detailed pattern is different. The vanilla kernel scans slowly over time where as the patches exhibits burst patterns of scan activity. Direct reclaim scanning is reduced by 52% due to stalling. The pattern for stealing pages is also slightly different. Both kernels exhibit spikes but the vanilla kernel when reclaiming shows pages being reclaimed over a period of time where as the patches tend to reclaim in spikes. The difference is that vanilla is not throttling and instead scanning constantly finding some pages over time where as the patched kernel throttles and reclaims in spikes. Ops Percentage direct scans 90.59 77.37 For direct reclaim, vanilla scanned 90.59% of pages where as with the patches, 77.37% were direct reclaim due to throttling Ops Page writes by reclaim 2613590.00 1687131.00 Page writes from reclaim context are reduced. Ops Page writes anon 2932752.00 1917048.00 And there is less swapping. Ops Page reclaim immediate 996248528.00 107664764.00 The number of pages encountered at the tail of the LRU tagged for immediate reclaim but still dirty/writeback is reduced by 89%. Ops Slabs scanned 164284.00 153608.00 Slab scan activity is similar. ftrace was used to gather stall activity Vanilla ------- 1 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=16000 2 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=12000 8 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=8000 29 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=4000 82394 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=0 The fast majority of wait_iff_congested calls do not stall at all. What is likely happening is that cond_resched() reschedules the task for a short period when the BDI is not registering congestion (which it never will in this test setup). 1 writeback_congestion_wait: usec_timeout=100000 usec_delayed=120000 2 writeback_congestion_wait: usec_timeout=100000 usec_delayed=132000 4 writeback_congestion_wait: usec_timeout=100000 usec_delayed=112000 380 writeback_congestion_wait: usec_timeout=100000 usec_delayed=108000 778 writeback_congestion_wait: usec_timeout=100000 usec_delayed=104000 congestion_wait if called always exceeds the timeout as there is no trigger to wake it up. Bottom line: Vanilla will throttle but it's not effective. Patch series ------------ Kswapd throttle activity was always due to scanning pages tagged for immediate reclaim at the tail of the LRU 1 usec_timeout=100000 usect_delayed=72000 reason=VMSCAN_THROTTLE_WRITEBACK 4 usec_timeout=100000 usect_delayed=20000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=12000 reason=VMSCAN_THROTTLE_WRITEBACK 6 usec_timeout=100000 usect_delayed=16000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=100000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=8000 reason=VMSCAN_THROTTLE_WRITEBACK 94 usec_timeout=100000 usect_delayed=0 reason=VMSCAN_THROTTLE_WRITEBACK 112 usec_timeout=100000 usect_delayed=4000 reason=VMSCAN_THROTTLE_WRITEBACK The majority of events did not stall or stalled for a short period. Roughly 16% of stalls reached the timeout before expiry. For direct reclaim, the number of times stalled for each reason were 6624 reason=VMSCAN_THROTTLE_ISOLATED 93246 reason=VMSCAN_THROTTLE_NOPROGRESS 96934 reason=VMSCAN_THROTTLE_WRITEBACK The most common reason to stall was due to excessive pages tagged for immediate reclaim at the tail of the LRU followed by a failure to make forward. A relatively small number were due to too many pages isolated from the LRU by parallel threads For VMSCAN_THROTTLE_ISOLATED, the breakdown of delays was 9 usec_timeout=20000 usect_delayed=4000 reason=VMSCAN_THROTTLE_ISOLATED 12 usec_timeout=20000 usect_delayed=16000 reason=VMSCAN_THROTTLE_ISOLATED 83 usec_timeout=20000 usect_delayed=20000 reason=VMSCAN_THROTTLE_ISOLATED 6520 usec_timeout=20000 usect_delayed=0 reason=VMSCAN_THROTTLE_ISOLATED Most did not stall at all. A small number reached the timeout. For VMSCAN_THROTTLE_NOPROGRESS, the breakdown of stalls were all over the map 1 usec_timeout=500000 usect_delayed=324000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=332000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=348000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=360000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=228000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=260000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=340000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=364000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=372000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=428000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=460000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=464000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=244000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=252000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=272000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=188000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=268000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=328000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=380000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=392000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=432000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=204000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=220000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=412000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=436000 reason=VMSCAN_THROTTLE_NOPROGRESS 6 usec_timeout=500000 usect_delayed=488000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=212000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=300000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=316000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=472000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=248000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=356000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=456000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=124000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=376000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=484000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=172000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=420000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=452000 reason=VMSCAN_THROTTLE_NOPROGRESS 11 usec_timeout=500000 usect_delayed=256000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=112000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=116000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=144000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=152000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=264000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=384000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=424000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=492000 reason=VMSCAN_THROTTLE_NOPROGRESS 13 usec_timeout=500000 usect_delayed=184000 reason=VMSCAN_THROTTLE_NOPROGRESS 13 usec_timeout=500000 usect_delayed=444000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=308000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=440000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=476000 reason=VMSCAN_THROTTLE_NOPROGRESS 16 usec_timeout=500000 usect_delayed=140000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=232000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=240000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=280000 reason=VMSCAN_THROTTLE_NOPROGRESS 18 usec_timeout=500000 usect_delayed=404000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=148000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=216000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=468000 reason=VMSCAN_THROTTLE_NOPROGRESS 21 usec_timeout=500000 usect_delayed=448000 reason=VMSCAN_THROTTLE_NOPROGRESS 23 usec_timeout=500000 usect_delayed=168000 reason=VMSCAN_THROTTLE_NOPROGRESS 23 usec_timeout=500000 usect_delayed=296000 reason=VMSCAN_THROTTLE_NOPROGRESS 25 usec_timeout=500000 usect_delayed=132000 reason=VMSCAN_THROTTLE_NOPROGRESS 25 usec_timeout=500000 usect_delayed=352000 reason=VMSCAN_THROTTLE_NOPROGRESS 26 usec_timeout=500000 usect_delayed=180000 reason=VMSCAN_THROTTLE_NOPROGRESS 27 usec_timeout=500000 usect_delayed=284000 reason=VMSCAN_THROTTLE_NOPROGRESS 28 usec_timeout=500000 usect_delayed=164000 reason=VMSCAN_THROTTLE_NOPROGRESS 29 usec_timeout=500000 usect_delayed=136000 reason=VMSCAN_THROTTLE_NOPROGRESS 30 usec_timeout=500000 usect_delayed=200000 reason=VMSCAN_THROTTLE_NOPROGRESS 30 usec_timeout=500000 usect_delayed=400000 reason=VMSCAN_THROTTLE_NOPROGRESS 31 usec_timeout=500000 usect_delayed=196000 reason=VMSCAN_THROTTLE_NOPROGRESS 32 usec_timeout=500000 usect_delayed=156000 reason=VMSCAN_THROTTLE_NOPROGRESS 33 usec_timeout=500000 usect_delayed=224000 reason=VMSCAN_THROTTLE_NOPROGRESS 35 usec_timeout=500000 usect_delayed=128000 reason=VMSCAN_THROTTLE_NOPROGRESS 35 usec_timeout=500000 usect_delayed=176000 reason=VMSCAN_THROTTLE_NOPROGRESS 36 usec_timeout=500000 usect_delayed=368000 reason=VMSCAN_THROTTLE_NOPROGRESS 36 usec_timeout=500000 usect_delayed=496000 reason=VMSCAN_THROTTLE_NOPROGRESS 37 usec_timeout=500000 usect_delayed=312000 reason=VMSCAN_THROTTLE_NOPROGRESS 38 usec_timeout=500000 usect_delayed=304000 reason=VMSCAN_THROTTLE_NOPROGRESS 40 usec_timeout=500000 usect_delayed=288000 reason=VMSCAN_THROTTLE_NOPROGRESS 43 usec_timeout=500000 usect_delayed=408000 reason=VMSCAN_THROTTLE_NOPROGRESS 55 usec_timeout=500000 usect_delayed=416000 reason=VMSCAN_THROTTLE_NOPROGRESS 56 usec_timeout=500000 usect_delayed=76000 reason=VMSCAN_THROTTLE_NOPROGRESS 58 usec_timeout=500000 usect_delayed=120000 reason=VMSCAN_THROTTLE_NOPROGRESS 59 usec_timeout=500000 usect_delayed=208000 reason=VMSCAN_THROTTLE_NOPROGRESS 61 usec_timeout=500000 usect_delayed=68000 reason=VMSCAN_THROTTLE_NOPROGRESS 71 usec_timeout=500000 usect_delayed=192000 reason=VMSCAN_THROTTLE_NOPROGRESS 71 usec_timeout=500000 usect_delayed=480000 reason=VMSCAN_THROTTLE_NOPROGRESS 79 usec_timeout=500000 usect_delayed=60000 reason=VMSCAN_THROTTLE_NOPROGRESS 82 usec_timeout=500000 usect_delayed=320000 reason=VMSCAN_THROTTLE_NOPROGRESS 82 usec_timeout=500000 usect_delayed=92000 reason=VMSCAN_THROTTLE_NOPROGRESS 85 usec_timeout=500000 usect_delayed=64000 reason=VMSCAN_THROTTLE_NOPROGRESS 85 usec_timeout=500000 usect_delayed=80000 reason=VMSCAN_THROTTLE_NOPROGRESS 88 usec_timeout=500000 usect_delayed=84000 reason=VMSCAN_THROTTLE_NOPROGRESS 90 usec_timeout=500000 usect_delayed=160000 reason=VMSCAN_THROTTLE_NOPROGRESS 90 usec_timeout=500000 usect_delayed=292000 reason=VMSCAN_THROTTLE_NOPROGRESS 94 usec_timeout=500000 usect_delayed=56000 reason=VMSCAN_THROTTLE_NOPROGRESS 118 usec_timeout=500000 usect_delayed=88000 reason=VMSCAN_THROTTLE_NOPROGRESS 119 usec_timeout=500000 usect_delayed=72000 reason=VMSCAN_THROTTLE_NOPROGRESS 126 usec_timeout=500000 usect_delayed=108000 reason=VMSCAN_THROTTLE_NOPROGRESS 146 usec_timeout=500000 usect_delayed=52000 reason=VMSCAN_THROTTLE_NOPROGRESS 148 usec_timeout=500000 usect_delayed=36000 reason=VMSCAN_THROTTLE_NOPROGRESS 148 usec_timeout=500000 usect_delayed=48000 reason=VMSCAN_THROTTLE_NOPROGRESS 159 usec_timeout=500000 usect_delayed=28000 reason=VMSCAN_THROTTLE_NOPROGRESS 178 usec_timeout=500000 usect_delayed=44000 reason=VMSCAN_THROTTLE_NOPROGRESS 183 usec_timeout=500000 usect_delayed=40000 reason=VMSCAN_THROTTLE_NOPROGRESS 237 usec_timeout=500000 usect_delayed=100000 reason=VMSCAN_THROTTLE_NOPROGRESS 266 usec_timeout=500000 usect_delayed=32000 reason=VMSCAN_THROTTLE_NOPROGRESS 313 usec_timeout=500000 usect_delayed=24000 reason=VMSCAN_THROTTLE_NOPROGRESS 347 usec_timeout=500000 usect_delayed=96000 reason=VMSCAN_THROTTLE_NOPROGRESS 470 usec_timeout=500000 usect_delayed=20000 reason=VMSCAN_THROTTLE_NOPROGRESS 559 usec_timeout=500000 usect_delayed=16000 reason=VMSCAN_THROTTLE_NOPROGRESS 964 usec_timeout=500000 usect_delayed=12000 reason=VMSCAN_THROTTLE_NOPROGRESS 2001 usec_timeout=500000 usect_delayed=104000 reason=VMSCAN_THROTTLE_NOPROGRESS 2447 usec_timeout=500000 usect_delayed=8000 reason=VMSCAN_THROTTLE_NOPROGRESS 7888 usec_timeout=500000 usect_delayed=4000 reason=VMSCAN_THROTTLE_NOPROGRESS 22727 usec_timeout=500000 usect_delayed=0 reason=VMSCAN_THROTTLE_NOPROGRESS 51305 usec_timeout=500000 usect_delayed=500000 reason=VMSCAN_THROTTLE_NOPROGRESS The full timeout is often hit but a large number also do not stall at all. The remainder slept a little allowing other reclaim tasks to make progress. While this timeout could be further increased, it could also negatively impact worst-case behaviour when there is no prioritisation of what task should make progress. For VMSCAN_THROTTLE_WRITEBACK, the breakdown was 1 usec_timeout=100000 usect_delayed=44000 reason=VMSCAN_THROTTLE_WRITEBACK 2 usec_timeout=100000 usect_delayed=76000 reason=VMSCAN_THROTTLE_WRITEBACK 3 usec_timeout=100000 usect_delayed=80000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=48000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=84000 reason=VMSCAN_THROTTLE_WRITEBACK 6 usec_timeout=100000 usect_delayed=72000 reason=VMSCAN_THROTTLE_WRITEBACK 7 usec_timeout=100000 usect_delayed=88000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=56000 reason=VMSCAN_THROTTLE_WRITEBACK 12 usec_timeout=100000 usect_delayed=64000 reason=VMSCAN_THROTTLE_WRITEBACK 16 usec_timeout=100000 usect_delayed=92000 reason=VMSCAN_THROTTLE_WRITEBACK 24 usec_timeout=100000 usect_delayed=68000 reason=VMSCAN_THROTTLE_WRITEBACK 28 usec_timeout=100000 usect_delayed=32000 reason=VMSCAN_THROTTLE_WRITEBACK 30 usec_timeout=100000 usect_delayed=60000 reason=VMSCAN_THROTTLE_WRITEBACK 30 usec_timeout=100000 usect_delayed=96000 reason=VMSCAN_THROTTLE_WRITEBACK 32 usec_timeout=100000 usect_delayed=52000 reason=VMSCAN_THROTTLE_WRITEBACK 42 usec_timeout=100000 usect_delayed=40000 reason=VMSCAN_THROTTLE_WRITEBACK 77 usec_timeout=100000 usect_delayed=28000 reason=VMSCAN_THROTTLE_WRITEBACK 99 usec_timeout=100000 usect_delayed=36000 reason=VMSCAN_THROTTLE_WRITEBACK 137 usec_timeout=100000 usect_delayed=24000 reason=VMSCAN_THROTTLE_WRITEBACK 190 usec_timeout=100000 usect_delayed=20000 reason=VMSCAN_THROTTLE_WRITEBACK 339 usec_timeout=100000 usect_delayed=16000 reason=VMSCAN_THROTTLE_WRITEBACK 518 usec_timeout=100000 usect_delayed=12000 reason=VMSCAN_THROTTLE_WRITEBACK 852 usec_timeout=100000 usect_delayed=8000 reason=VMSCAN_THROTTLE_WRITEBACK 3359 usec_timeout=100000 usect_delayed=4000 reason=VMSCAN_THROTTLE_WRITEBACK 7147 usec_timeout=100000 usect_delayed=0 reason=VMSCAN_THROTTLE_WRITEBACK 83962 usec_timeout=100000 usect_delayed=100000 reason=VMSCAN_THROTTLE_WRITEBACK The majority hit the timeout in direct reclaim context although a sizable number did not stall at all. This is very different to kswapd where only a tiny percentage of stalls due to writeback reached the timeout. Bottom line, the throttling appears to work and the wakeup events may limit worst case stalls. There might be some grounds for adjusting timeouts but it's likely futile as the worst-case scenarios depend on the workload, memory size and the speed of the storage. A better approach to improve the series further would be to prioritise tasks based on their rate of allocation with the caveat that it may be very expensive to track. This patch (of 5): Page reclaim throttles on wait_iff_congested under the following conditions: - kswapd is encountering pages under writeback and marked for immediate reclaim implying that pages are cycling through the LRU faster than pages can be cleaned. - Direct reclaim will stall if all dirty pages are backed by congested inodes. wait_iff_congested is almost completely broken with few exceptions. This patch adds a new node-based workqueue and tracks the number of throttled tasks and pages written back since throttling started. If enough pages belonging to the node are written back then the throttled tasks will wake early. If not, the throttled tasks sleeps until the timeout expires. [neilb@suse.de: Uninterruptible sleep and simpler wakeups] [hdanton@sina.com: Avoid race when reclaim starts] [vbabka@suse.cz: vmstat irq-safe api, clarifications] Link: https://lore.kernel.org/linux-mm/45d8b7a6-8548-65f5-cccf-9f451d4ae3d4@kernel.dk/ [1] Link: https://lkml.kernel.org/r/20211022144651.19914-1-mgorman@techsingularity.net Link: https://lkml.kernel.org/r/20211022144651.19914-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: NeilBrown <neilb@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: "Darrick J . Wong" <djwong@kernel.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@surriel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Corbet <corbet@lwn.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 20:42:25 +00:00
}
static inline void wake_throttle_isolated(pg_data_t *pgdat)
{
wait_queue_head_t *wqh;
wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_ISOLATED];
if (waitqueue_active(wqh))
wake_up(wqh);
}
vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf);
static inline vm_fault_t vmf_anon_prepare(struct vm_fault *vmf)
{
vm_fault_t ret = __vmf_anon_prepare(vmf);
if (unlikely(ret & VM_FAULT_RETRY))
vma_end_read(vmf->vma);
return ret;
}
vm_fault_t do_swap_page(struct vm_fault *vmf);
void folio_rotate_reclaimable(struct folio *folio);
bool __folio_end_writeback(struct folio *folio);
void deactivate_file_folio(struct folio *folio);
mm: multi-gen LRU: exploit locality in rmap Searching the rmap for PTEs mapping each page on an LRU list (to test and clear the accessed bit) can be expensive because pages from different VMAs (PA space) are not cache friendly to the rmap (VA space). For workloads mostly using mapped pages, searching the rmap can incur the highest CPU cost in the reclaim path. This patch exploits spatial locality to reduce the trips into the rmap. When shrink_page_list() walks the rmap and finds a young PTE, a new function lru_gen_look_around() scans at most BITS_PER_LONG-1 adjacent PTEs. On finding another young PTE, it clears the accessed bit and updates the gen counter of the page mapped by this PTE to (max_seq%MAX_NR_GENS)+1. Server benchmark results: Single workload: fio (buffered I/O): no change Single workload: memcached (anon): +[3, 5]% Ops/sec KB/sec patch1-6: 1106168.46 43025.04 patch1-7: 1147696.57 44640.29 Configurations: no change Client benchmark results: kswapd profiles: patch1-6 39.03% lzo1x_1_do_compress (real work) 18.47% page_vma_mapped_walk (overhead) 6.74% _raw_spin_unlock_irq 3.97% do_raw_spin_lock 2.49% ptep_clear_flush 2.48% anon_vma_interval_tree_iter_first 1.92% folio_referenced_one 1.88% __zram_bvec_write 1.48% memmove 1.31% vma_interval_tree_iter_next patch1-7 48.16% lzo1x_1_do_compress (real work) 8.20% page_vma_mapped_walk (overhead) 7.06% _raw_spin_unlock_irq 2.92% ptep_clear_flush 2.53% __zram_bvec_write 2.11% do_raw_spin_lock 2.02% memmove 1.93% lru_gen_look_around 1.56% free_unref_page_list 1.40% memset Configurations: no change Link: https://lkml.kernel.org/r/20220918080010.2920238-8-yuzhao@google.com Signed-off-by: Yu Zhao <yuzhao@google.com> Acked-by: Barry Song <baohua@kernel.org> Acked-by: Brian Geffon <bgeffon@google.com> Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org> Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name> Acked-by: Steven Barrett <steven@liquorix.net> Acked-by: Suleiman Souhlal <suleiman@google.com> Tested-by: Daniel Byrne <djbyrne@mtu.edu> Tested-by: Donald Carr <d@chaos-reins.com> Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com> Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru> Tested-by: Shuang Zhai <szhai2@cs.rochester.edu> Tested-by: Sofia Trinh <sofia.trinh@edi.works> Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michael Larabel <Michael@MichaelLarabel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Rapoport <rppt@kernel.org> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-09-18 08:00:04 +00:00
void folio_activate(struct folio *folio);
mm: make swapin readahead to improve thp collapse rate This patch makes swapin readahead to improve thp collapse rate. When khugepaged scanned pages, there can be a few of the pages in swap area. With the patch THP can collapse 4kB pages into a THP when there are up to max_ptes_swap swap ptes in a 2MB range. The patch was tested with a test program that allocates 400B of memory, writes to it, and then sleeps. I force the system to swap out all. Afterwards, the test program touches the area by writing, it skips a page in each 20 pages of the area. Without the patch, system did not swap in readahead. THP rate was %65 of the program of the memory, it did not change over time. With this patch, after 10 minutes of waiting khugepaged had collapsed %99 of the program's memory. [kirill.shutemov@linux.intel.com: trivial cleanup of exit path of the function] [kirill.shutemov@linux.intel.com: __collapse_huge_page_swapin(): drop unused 'pte' parameter] [kirill.shutemov@linux.intel.com: do not hold anon_vma lock during swap in] Signed-off-by: Ebru Akagunduz <ebru.akagunduz@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Xie XiuQi <xiexiuqi@huawei.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Rientjes <rientjes@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-07-26 22:25:03 +00:00
void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
mm: remove the vma linked list Replace any vm_next use with vma_find(). Update free_pgtables(), unmap_vmas(), and zap_page_range() to use the maple tree. Use the new free_pgtables() and unmap_vmas() in do_mas_align_munmap(). At the same time, alter the loop to be more compact. Now that free_pgtables() and unmap_vmas() take a maple tree as an argument, rearrange do_mas_align_munmap() to use the new tree to hold the vmas to remove. Remove __vma_link_list() and __vma_unlink_list() as they are exclusively used to update the linked list. Drop linked list update from __insert_vm_struct(). Rework validation of tree as it was depending on the linked list. [yang.lee@linux.alibaba.com: fix one kernel-doc comment] Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=1949 Link: https://lkml.kernel.org/r/20220824021918.94116-1-yang.lee@linux.alibaba.comLink: https://lkml.kernel.org/r/20220906194824.2110408-69-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com> Signed-off-by: Yang Li <yang.lee@linux.alibaba.com> Tested-by: Yu Zhao <yuzhao@google.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: SeongJae Park <sj@kernel.org> Cc: Sven Schnelle <svens@linux.ibm.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-09-06 19:49:06 +00:00
struct vm_area_struct *start_vma, unsigned long floor,
unsigned long ceiling, bool mm_wr_locked);
void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte);
struct zap_details;
mm, oom: introduce oom reaper This patch (of 5): This is based on the idea from Mel Gorman discussed during LSFMM 2015 and independently brought up by Oleg Nesterov. The OOM killer currently allows to kill only a single task in a good hope that the task will terminate in a reasonable time and frees up its memory. Such a task (oom victim) will get an access to memory reserves via mark_oom_victim to allow a forward progress should there be a need for additional memory during exit path. It has been shown (e.g. by Tetsuo Handa) that it is not that hard to construct workloads which break the core assumption mentioned above and the OOM victim might take unbounded amount of time to exit because it might be blocked in the uninterruptible state waiting for an event (e.g. lock) which is blocked by another task looping in the page allocator. This patch reduces the probability of such a lockup by introducing a specialized kernel thread (oom_reaper) which tries to reclaim additional memory by preemptively reaping the anonymous or swapped out memory owned by the oom victim under an assumption that such a memory won't be needed when its owner is killed and kicked from the userspace anyway. There is one notable exception to this, though, if the OOM victim was in the process of coredumping the result would be incomplete. This is considered a reasonable constrain because the overall system health is more important than debugability of a particular application. A kernel thread has been chosen because we need a reliable way of invocation so workqueue context is not appropriate because all the workers might be busy (e.g. allocating memory). Kswapd which sounds like another good fit is not appropriate as well because it might get blocked on locks during reclaim as well. oom_reaper has to take mmap_sem on the target task for reading so the solution is not 100% because the semaphore might be held or blocked for write but the probability is reduced considerably wrt. basically any lock blocking forward progress as described above. In order to prevent from blocking on the lock without any forward progress we are using only a trylock and retry 10 times with a short sleep in between. Users of mmap_sem which need it for write should be carefully reviewed to use _killable waiting as much as possible and reduce allocations requests done with the lock held to absolute minimum to reduce the risk even further. The API between oom killer and oom reaper is quite trivial. wake_oom_reaper updates mm_to_reap with cmpxchg to guarantee only NULL->mm transition and oom_reaper clear this atomically once it is done with the work. This means that only a single mm_struct can be reaped at the time. As the operation is potentially disruptive we are trying to limit it to the ncessary minimum and the reaper blocks any updates while it operates on an mm. mm_struct is pinned by mm_count to allow parallel exit_mmap and a race is detected by atomic_inc_not_zero(mm_users). Signed-off-by: Michal Hocko <mhocko@suse.com> Suggested-by: Oleg Nesterov <oleg@redhat.com> Suggested-by: Mel Gorman <mgorman@suse.de> Acked-by: Mel Gorman <mgorman@suse.de> Acked-by: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Andrea Argangeli <andrea@kernel.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-25 21:20:24 +00:00
void unmap_page_range(struct mmu_gather *tlb,
struct vm_area_struct *vma,
unsigned long addr, unsigned long end,
struct zap_details *details);
void page_cache_ra_order(struct readahead_control *, struct file_ra_state *,
unsigned int order);
void force_page_cache_ra(struct readahead_control *, unsigned long nr);
static inline void force_page_cache_readahead(struct address_space *mapping,
struct file *file, pgoff_t index, unsigned long nr_to_read)
{
DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, index);
force_page_cache_ra(&ractl, nr_to_read);
}
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);
unsigned find_get_entries(struct address_space *mapping, pgoff_t *start,
pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices);
void filemap_free_folio(struct address_space *mapping, struct folio *folio);
int truncate_inode_folio(struct address_space *mapping, struct folio *folio);
bool truncate_inode_partial_folio(struct folio *folio, loff_t start,
loff_t end);
long mapping_evict_folio(struct address_space *mapping, struct folio *folio);
unsigned long mapping_try_invalidate(struct address_space *mapping,
pgoff_t start, pgoff_t end, unsigned long *nr_failed);
mm: swap: make page_evictable() inline When backporting commit 9c4e6b1a7027 ("mm, mlock, vmscan: no more skipping pagevecs") to our 4.9 kernel, our test bench noticed around 10% down with a couple of vm-scalability's test cases (lru-file-readonce, lru-file-readtwice and lru-file-mmap-read). I didn't see that much down on my VM (32c-64g-2nodes). It might be caused by the test configuration, which is 32c-256g with NUMA disabled and the tests were run in root memcg, so the tests actually stress only one inactive and active lru. It sounds not very usual in mordern production environment. That commit did two major changes: 1. Call page_evictable() 2. Use smp_mb to force the PG_lru set visible It looks they contribute the most overhead. The page_evictable() is a function which does function prologue and epilogue, and that was used by page reclaim path only. However, lru add is a very hot path, so it sounds better to make it inline. However, it calls page_mapping() which is not inlined either, but the disassemble shows it doesn't do push and pop operations and it sounds not very straightforward to inline it. Other than this, it sounds smp_mb() is not necessary for x86 since SetPageLRU is atomic which enforces memory barrier already, replace it with smp_mb__after_atomic() in the following patch. With the two fixes applied, the tests can get back around 5% on that test bench and get back normal on my VM. Since the test bench configuration is not that usual and I also saw around 6% up on the latest upstream, so it sounds good enough IMHO. The below is test data (lru-file-readtwice throughput) against the v5.6-rc4: mainline w/ inline fix 150MB 154MB With this patch the throughput gets 2.67% up. The data with using smp_mb__after_atomic() is showed in the following patch. Shakeel Butt did the below test: On a real machine with limiting the 'dd' on a single node and reading 100 GiB sparse file (less than a single node). Just ran a single instance to not cause the lru lock contention. The cmdline used is "dd if=file-100GiB of=/dev/null bs=4k". Ran the cmd 10 times with drop_caches in between and measured the time it took. Without patch: 56.64143 +- 0.672 sec With patches: 56.10 +- 0.21 sec [akpm@linux-foundation.org: move page_evictable() to internal.h] Fixes: 9c4e6b1a7027 ("mm, mlock, vmscan: no more skipping pagevecs") Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Shakeel Butt <shakeelb@google.com> Reviewed-by: Shakeel Butt <shakeelb@google.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Link: http://lkml.kernel.org/r/1584500541-46817-1-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-02 04:06:20 +00:00
/**
* folio_evictable - Test whether a folio is evictable.
* @folio: The folio to test.
mm: swap: make page_evictable() inline When backporting commit 9c4e6b1a7027 ("mm, mlock, vmscan: no more skipping pagevecs") to our 4.9 kernel, our test bench noticed around 10% down with a couple of vm-scalability's test cases (lru-file-readonce, lru-file-readtwice and lru-file-mmap-read). I didn't see that much down on my VM (32c-64g-2nodes). It might be caused by the test configuration, which is 32c-256g with NUMA disabled and the tests were run in root memcg, so the tests actually stress only one inactive and active lru. It sounds not very usual in mordern production environment. That commit did two major changes: 1. Call page_evictable() 2. Use smp_mb to force the PG_lru set visible It looks they contribute the most overhead. The page_evictable() is a function which does function prologue and epilogue, and that was used by page reclaim path only. However, lru add is a very hot path, so it sounds better to make it inline. However, it calls page_mapping() which is not inlined either, but the disassemble shows it doesn't do push and pop operations and it sounds not very straightforward to inline it. Other than this, it sounds smp_mb() is not necessary for x86 since SetPageLRU is atomic which enforces memory barrier already, replace it with smp_mb__after_atomic() in the following patch. With the two fixes applied, the tests can get back around 5% on that test bench and get back normal on my VM. Since the test bench configuration is not that usual and I also saw around 6% up on the latest upstream, so it sounds good enough IMHO. The below is test data (lru-file-readtwice throughput) against the v5.6-rc4: mainline w/ inline fix 150MB 154MB With this patch the throughput gets 2.67% up. The data with using smp_mb__after_atomic() is showed in the following patch. Shakeel Butt did the below test: On a real machine with limiting the 'dd' on a single node and reading 100 GiB sparse file (less than a single node). Just ran a single instance to not cause the lru lock contention. The cmdline used is "dd if=file-100GiB of=/dev/null bs=4k". Ran the cmd 10 times with drop_caches in between and measured the time it took. Without patch: 56.64143 +- 0.672 sec With patches: 56.10 +- 0.21 sec [akpm@linux-foundation.org: move page_evictable() to internal.h] Fixes: 9c4e6b1a7027 ("mm, mlock, vmscan: no more skipping pagevecs") Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Shakeel Butt <shakeelb@google.com> Reviewed-by: Shakeel Butt <shakeelb@google.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Link: http://lkml.kernel.org/r/1584500541-46817-1-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-02 04:06:20 +00:00
*
* Test whether @folio is evictable -- i.e., should be placed on
* active/inactive lists vs unevictable list.
mm: swap: make page_evictable() inline When backporting commit 9c4e6b1a7027 ("mm, mlock, vmscan: no more skipping pagevecs") to our 4.9 kernel, our test bench noticed around 10% down with a couple of vm-scalability's test cases (lru-file-readonce, lru-file-readtwice and lru-file-mmap-read). I didn't see that much down on my VM (32c-64g-2nodes). It might be caused by the test configuration, which is 32c-256g with NUMA disabled and the tests were run in root memcg, so the tests actually stress only one inactive and active lru. It sounds not very usual in mordern production environment. That commit did two major changes: 1. Call page_evictable() 2. Use smp_mb to force the PG_lru set visible It looks they contribute the most overhead. The page_evictable() is a function which does function prologue and epilogue, and that was used by page reclaim path only. However, lru add is a very hot path, so it sounds better to make it inline. However, it calls page_mapping() which is not inlined either, but the disassemble shows it doesn't do push and pop operations and it sounds not very straightforward to inline it. Other than this, it sounds smp_mb() is not necessary for x86 since SetPageLRU is atomic which enforces memory barrier already, replace it with smp_mb__after_atomic() in the following patch. With the two fixes applied, the tests can get back around 5% on that test bench and get back normal on my VM. Since the test bench configuration is not that usual and I also saw around 6% up on the latest upstream, so it sounds good enough IMHO. The below is test data (lru-file-readtwice throughput) against the v5.6-rc4: mainline w/ inline fix 150MB 154MB With this patch the throughput gets 2.67% up. The data with using smp_mb__after_atomic() is showed in the following patch. Shakeel Butt did the below test: On a real machine with limiting the 'dd' on a single node and reading 100 GiB sparse file (less than a single node). Just ran a single instance to not cause the lru lock contention. The cmdline used is "dd if=file-100GiB of=/dev/null bs=4k". Ran the cmd 10 times with drop_caches in between and measured the time it took. Without patch: 56.64143 +- 0.672 sec With patches: 56.10 +- 0.21 sec [akpm@linux-foundation.org: move page_evictable() to internal.h] Fixes: 9c4e6b1a7027 ("mm, mlock, vmscan: no more skipping pagevecs") Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Shakeel Butt <shakeelb@google.com> Reviewed-by: Shakeel Butt <shakeelb@google.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Link: http://lkml.kernel.org/r/1584500541-46817-1-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-02 04:06:20 +00:00
*
* Reasons folio might not be evictable:
* 1. folio's mapping marked unevictable
* 2. One of the pages in the folio is part of an mlocked VMA
mm: swap: make page_evictable() inline When backporting commit 9c4e6b1a7027 ("mm, mlock, vmscan: no more skipping pagevecs") to our 4.9 kernel, our test bench noticed around 10% down with a couple of vm-scalability's test cases (lru-file-readonce, lru-file-readtwice and lru-file-mmap-read). I didn't see that much down on my VM (32c-64g-2nodes). It might be caused by the test configuration, which is 32c-256g with NUMA disabled and the tests were run in root memcg, so the tests actually stress only one inactive and active lru. It sounds not very usual in mordern production environment. That commit did two major changes: 1. Call page_evictable() 2. Use smp_mb to force the PG_lru set visible It looks they contribute the most overhead. The page_evictable() is a function which does function prologue and epilogue, and that was used by page reclaim path only. However, lru add is a very hot path, so it sounds better to make it inline. However, it calls page_mapping() which is not inlined either, but the disassemble shows it doesn't do push and pop operations and it sounds not very straightforward to inline it. Other than this, it sounds smp_mb() is not necessary for x86 since SetPageLRU is atomic which enforces memory barrier already, replace it with smp_mb__after_atomic() in the following patch. With the two fixes applied, the tests can get back around 5% on that test bench and get back normal on my VM. Since the test bench configuration is not that usual and I also saw around 6% up on the latest upstream, so it sounds good enough IMHO. The below is test data (lru-file-readtwice throughput) against the v5.6-rc4: mainline w/ inline fix 150MB 154MB With this patch the throughput gets 2.67% up. The data with using smp_mb__after_atomic() is showed in the following patch. Shakeel Butt did the below test: On a real machine with limiting the 'dd' on a single node and reading 100 GiB sparse file (less than a single node). Just ran a single instance to not cause the lru lock contention. The cmdline used is "dd if=file-100GiB of=/dev/null bs=4k". Ran the cmd 10 times with drop_caches in between and measured the time it took. Without patch: 56.64143 +- 0.672 sec With patches: 56.10 +- 0.21 sec [akpm@linux-foundation.org: move page_evictable() to internal.h] Fixes: 9c4e6b1a7027 ("mm, mlock, vmscan: no more skipping pagevecs") Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Shakeel Butt <shakeelb@google.com> Reviewed-by: Shakeel Butt <shakeelb@google.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Link: http://lkml.kernel.org/r/1584500541-46817-1-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-02 04:06:20 +00:00
*/
static inline bool folio_evictable(struct folio *folio)
{
bool ret;
/* Prevent address_space of inode and swap cache from being freed */
rcu_read_lock();
ret = !mapping_unevictable(folio_mapping(folio)) &&
!folio_test_mlocked(folio);
rcu_read_unlock();
return ret;
}
/*
* Turn a non-refcounted page (->_refcount == 0) into refcounted with
* a count of one.
*/
static inline void set_page_refcounted(struct page *page)
{
VM_BUG_ON_PAGE(PageTail(page), page);
2016-03-17 21:19:26 +00:00
VM_BUG_ON_PAGE(page_ref_count(page), page);
set_page_count(page, 1);
}
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
/*
* Return true if a folio needs ->release_folio() calling upon it.
*/
static inline bool folio_needs_release(struct folio *folio)
{
mm, netfs, fscache: stop read optimisation when folio removed from pagecache Fscache has an optimisation by which reads from the cache are skipped until we know that (a) there's data there to be read and (b) that data isn't entirely covered by pages resident in the netfs pagecache. This is done with two flags manipulated by fscache_note_page_release(): if (... test_bit(FSCACHE_COOKIE_HAVE_DATA, &cookie->flags) && test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags)) clear_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); where the NO_DATA_TO_READ flag causes cachefiles_prepare_read() to indicate that netfslib should download from the server or clear the page instead. The fscache_note_page_release() function is intended to be called from ->releasepage() - but that only gets called if PG_private or PG_private_2 is set - and currently the former is at the discretion of the network filesystem and the latter is only set whilst a page is being written to the cache, so sometimes we miss clearing the optimisation. Fix this by following Willy's suggestion[1] and adding an address_space flag, AS_RELEASE_ALWAYS, that causes filemap_release_folio() to always call ->release_folio() if it's set, even if PG_private or PG_private_2 aren't set. Note that this would require folio_test_private() and page_has_private() to become more complicated. To avoid that, in the places[*] where these are used to conditionalise calls to filemap_release_folio() and try_to_release_page(), the tests are removed the those functions just jumped to unconditionally and the test is performed there. [*] There are some exceptions in vmscan.c where the check guards more than just a call to the releaser. I've added a function, folio_needs_release() to wrap all the checks for that. AS_RELEASE_ALWAYS should be set if a non-NULL cookie is obtained from fscache and cleared in ->evict_inode() before truncate_inode_pages_final() is called. Additionally, the FSCACHE_COOKIE_NO_DATA_TO_READ flag needs to be cleared and the optimisation cancelled if a cachefiles object already contains data when we open it. [dwysocha@redhat.com: call folio_mapping() inside folio_needs_release()] Link: https://github.com/DaveWysochanskiRH/kernel/commit/902c990e311120179fa5de99d68364b2947b79ec Link: https://lkml.kernel.org/r/20230628104852.3391651-3-dhowells@redhat.com Fixes: 1f67e6d0b188 ("fscache: Provide a function to note the release of a page") Fixes: 047487c947e8 ("cachefiles: Implement the I/O routines") Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Dave Wysochanski <dwysocha@redhat.com> Reported-by: Rohith Surabattula <rohiths.msft@gmail.com> Suggested-by: Matthew Wilcox <willy@infradead.org> Tested-by: SeongJae Park <sj@kernel.org> Cc: Daire Byrne <daire.byrne@gmail.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: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jingbo Xu <jefflexu@linux.alibaba.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Xiubo Li <xiubli@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-28 10:48:52 +00:00
struct address_space *mapping = folio_mapping(folio);
return folio_has_private(folio) ||
(mapping && mapping_release_always(mapping));
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
}
extern unsigned long highest_memmap_pfn;
mm: fix 100% CPU kswapd busyloop on unreclaimable nodes Patch series "mm: kswapd spinning on unreclaimable nodes - fixes and cleanups". Jia reported a scenario in which the kswapd of a node indefinitely spins at 100% CPU usage. We have seen similar cases at Facebook. The kernel's current method of judging its ability to reclaim a node (or whether to back off and sleep) is based on the amount of scanned pages in proportion to the amount of reclaimable pages. In Jia's and our scenarios, there are no reclaimable pages in the node, however, and the condition for backing off is never met. Kswapd busyloops in an attempt to restore the watermarks while having nothing to work with. This series reworks the definition of an unreclaimable node based not on scanning but on whether kswapd is able to actually reclaim pages in MAX_RECLAIM_RETRIES (16) consecutive runs. This is the same criteria the page allocator uses for giving up on direct reclaim and invoking the OOM killer. If it cannot free any pages, kswapd will go to sleep and leave further attempts to direct reclaim invocations, which will either make progress and re-enable kswapd, or invoke the OOM killer. Patch #1 fixes the immediate problem Jia reported, the remainder are smaller fixlets, cleanups, and overall phasing out of the old method. Patch #6 is the odd one out. It's a nice cleanup to get_scan_count(), and directly related to #5, but in itself not relevant to the series. If the whole series is too ambitious for 4.11, I would consider the first three patches fixes, the rest cleanups. This patch (of 9): Jia He reports a problem with kswapd spinning at 100% CPU when requesting more hugepages than memory available in the system: $ echo 4000 >/proc/sys/vm/nr_hugepages top - 13:42:59 up 3:37, 1 user, load average: 1.09, 1.03, 1.01 Tasks: 1 total, 1 running, 0 sleeping, 0 stopped, 0 zombie %Cpu(s): 0.0 us, 12.5 sy, 0.0 ni, 85.5 id, 2.0 wa, 0.0 hi, 0.0 si, 0.0 st KiB Mem: 31371520 total, 30915136 used, 456384 free, 320 buffers KiB Swap: 6284224 total, 115712 used, 6168512 free. 48192 cached Mem PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 76 root 20 0 0 0 0 R 100.0 0.000 217:17.29 kswapd3 At that time, there are no reclaimable pages left in the node, but as kswapd fails to restore the high watermarks it refuses to go to sleep. Kswapd needs to back away from nodes that fail to balance. Up until commit 1d82de618ddd ("mm, vmscan: make kswapd reclaim in terms of nodes") kswapd had such a mechanism. It considered zones whose theoretically reclaimable pages it had reclaimed six times over as unreclaimable and backed away from them. This guard was erroneously removed as the patch changed the definition of a balanced node. However, simply restoring this code wouldn't help in the case reported here: there *are* no reclaimable pages that could be scanned until the threshold is met. Kswapd would stay awake anyway. Introduce a new and much simpler way of backing off. If kswapd runs through MAX_RECLAIM_RETRIES (16) cycles without reclaiming a single page, make it back off from the node. This is the same number of shots direct reclaim takes before declaring OOM. Kswapd will go to sleep on that node until a direct reclaimer manages to reclaim some pages, thus proving the node reclaimable again. [hannes@cmpxchg.org: check kswapd failure against the cumulative nr_reclaimed count] Link: http://lkml.kernel.org/r/20170306162410.GB2090@cmpxchg.org [shakeelb@google.com: fix condition for throttle_direct_reclaim] Link: http://lkml.kernel.org/r/20170314183228.20152-1-shakeelb@google.com Link: http://lkml.kernel.org/r/20170228214007.5621-2-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Shakeel Butt <shakeelb@google.com> Reported-by: Jia He <hejianet@gmail.com> Tested-by: Jia He <hejianet@gmail.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Acked-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-03 21:51:51 +00:00
/*
* Maximum number of reclaim retries without progress before the OOM
* killer is consider the only way forward.
*/
#define MAX_RECLAIM_RETRIES 16
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:39 +00:00
/*
* in mm/vmscan.c:
*/
mm: change to return bool for folio_isolate_lru() Patch series "Change the return value for page isolation functions", v3. Now the page isolation functions did not return a boolean to indicate success or not, instead it will return a negative error when failed to isolate a page. So below code used in most places seem a boolean success/failure thing, which can confuse people whether the isolation is successful. if (folio_isolate_lru(folio)) continue; Moreover the page isolation functions only return 0 or -EBUSY, and most users did not care about the negative error except for few users, thus we can convert all page isolation functions to return a boolean value, which can remove the confusion to make code more clear. No functional changes intended in this patch series. This patch (of 4): Now the folio_isolate_lru() did not return a boolean value to indicate isolation success or not, however below code checking the return value can make people think that it was a boolean success/failure thing, which makes people easy to make mistakes (see the fix patch[1]). if (folio_isolate_lru(folio)) continue; Thus it's better to check the negative error value expilictly returned by folio_isolate_lru(), which makes code more clear per Linus's suggestion[2]. Moreover Matthew suggested we can convert the isolation functions to return a boolean[3], since most users did not care about the negative error value, and can also remove the confusing of checking return value. So this patch converts the folio_isolate_lru() to return a boolean value, which means return 'true' to indicate the folio isolation is successful, and 'false' means a failure to isolation. Meanwhile changing all users' logic of checking the isolation state. No functional changes intended. [1] https://lore.kernel.org/all/20230131063206.28820-1-Kuan-Ying.Lee@mediatek.com/T/#u [2] https://lore.kernel.org/all/CAHk-=wiBrY+O-4=2mrbVyxR+hOqfdJ=Do6xoucfJ9_5az01L4Q@mail.gmail.com/ [3] https://lore.kernel.org/all/Y+sTFqwMNAjDvxw3@casper.infradead.org/ Link: https://lkml.kernel.org/r/cover.1676424378.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/8a4e3679ed4196168efadf7ea36c038f2f7d5aa9.1676424378.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com> Reviewed-by: SeongJae Park <sj@kernel.org> Acked-by: David Hildenbrand <david@redhat.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Muchun Song <muchun.song@linux.dev> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Shakeel Butt <shakeelb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-02-15 10:39:34 +00:00
bool folio_isolate_lru(struct folio *folio);
void folio_putback_lru(struct folio *folio);
mm/vmscan: centralise timeout values for reclaim_throttle Neil Brown raised concerns about callers of reclaim_throttle specifying a timeout value. The original timeout values to congestion_wait() were probably pulled out of thin air or copy&pasted from somewhere else. This patch centralises the timeout values and selects a timeout based on the reason for reclaim throttling. These figures are also pulled out of the same thin air but better values may be derived Running a workload that is throttling for inappropriate periods and tracing mm_vmscan_throttled can be used to pick a more appropriate value. Excessive throttling would pick a lower timeout where as excessive CPU usage in reclaim context would select a larger timeout. Ideally a large value would always be used and the wakeups would occur before a timeout but that requires careful testing. Link: https://lkml.kernel.org/r/20211022144651.19914-7-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: "Darrick J . Wong" <djwong@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: NeilBrown <neilb@suse.de> Cc: Rik van Riel <riel@surriel.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 20:42:42 +00:00
extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason);
vmscan: move isolate_lru_page() to vmscan.c On large memory systems, the VM can spend way too much time scanning through pages that it cannot (or should not) evict from memory. Not only does it use up CPU time, but it also provokes lock contention and can leave large systems under memory presure in a catatonic state. This patch series improves VM scalability by: 1) putting filesystem backed, swap backed and unevictable pages onto their own LRUs, so the system only scans the pages that it can/should evict from memory 2) switching to two handed clock replacement for the anonymous LRUs, so the number of pages that need to be scanned when the system starts swapping is bound to a reasonable number 3) keeping unevictable pages off the LRU completely, so the VM does not waste CPU time scanning them. ramfs, ramdisk, SHM_LOCKED shared memory segments and mlock()ed VMA pages are keept on the unevictable list. This patch: isolate_lru_page logically belongs to be in vmscan.c than migrate.c. It is tough, because we don't need that function without memory migration so there is a valid argument to have it in migrate.c. However a subsequent patch needs to make use of it in the core mm, so we can happily move it to vmscan.c. Also, make the function a little more generic by not requiring that it adds an isolated page to a given list. Callers can do that. Note that we now have '__isolate_lru_page()', that does something quite different, visible outside of vmscan.c for use with memory controller. Methinks we need to rationalize these names/purposes. --lts [akpm@linux-foundation.org: fix mm/memory_hotplug.c build] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:09 +00:00
/*
* in mm/rmap.c:
*/
mm/khugepaged: record SCAN_PMD_MAPPED when scan_pmd() finds hugepage When scanning an anon pmd to see if it's eligible for collapse, return SCAN_PMD_MAPPED if the pmd already maps a hugepage. Note that SCAN_PMD_MAPPED is different from SCAN_PAGE_COMPOUND used in the file-collapse path, since the latter might identify pte-mapped compound pages. This is required by MADV_COLLAPSE which necessarily needs to know what hugepage-aligned/sized regions are already pmd-mapped. In order to determine if a pmd already maps a hugepage, refactor mm_find_pmd(): Return mm_find_pmd() to it's pre-commit f72e7dcdd252 ("mm: let mm_find_pmd fix buggy race with THP fault") behavior. ksm was the only caller that explicitly wanted a pte-mapping pmd, so open code the pte-mapping logic there (pmd_present() and pmd_trans_huge() checks). Undo revert change in commit f72e7dcdd252 ("mm: let mm_find_pmd fix buggy race with THP fault") that open-coded split_huge_pmd_address() pmd lookup and use mm_find_pmd() instead. Link: https://lkml.kernel.org/r/20220706235936.2197195-9-zokeefe@google.com Signed-off-by: Zach O'Keefe <zokeefe@google.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Cc: Alex Shi <alex.shi@linux.alibaba.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Chris Kennelly <ckennelly@google.com> Cc: Chris Zankel <chris@zankel.net> Cc: David Hildenbrand <david@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: Helge Deller <deller@gmx.de> Cc: Hugh Dickins <hughd@google.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Pasha Tatashin <pasha.tatashin@soleen.com> Cc: Pavel Begunkov <asml.silence@gmail.com> Cc: Peter Xu <peterx@redhat.com> Cc: Rongwei Wang <rongwei.wang@linux.alibaba.com> Cc: SeongJae Park <sj@kernel.org> Cc: Song Liu <songliubraving@fb.com> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Zi Yan <ziy@nvidia.com> Cc: Dan Carpenter <dan.carpenter@oracle.com> Cc: "Souptick Joarder (HPE)" <jrdr.linux@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-06 23:59:26 +00:00
pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address);
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:39 +00:00
/*
* in mm/page_alloc.c
*/
#define K(x) ((x) << (PAGE_SHIFT-10))
mm/page_alloc: restrict max order of merging on isolated pageblock Current pageblock isolation logic could isolate each pageblock individually. This causes freepage accounting problem if freepage with pageblock order on isolate pageblock is merged with other freepage on normal pageblock. We can prevent merging by restricting max order of merging to pageblock order if freepage is on isolate pageblock. A side-effect of this change is that there could be non-merged buddy freepage even if finishing pageblock isolation, because undoing pageblock isolation is just to move freepage from isolate buddy list to normal buddy list rather than to consider merging. So, the patch also makes undoing pageblock isolation consider freepage merge. When un-isolation, freepage with more than pageblock order and it's buddy are checked. If they are on normal pageblock, instead of just moving, we isolate the freepage and free it in order to get merged. Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Laura Abbott <lauraa@codeaurora.org> Cc: Heesub Shin <heesub.shin@samsung.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Cc: Ritesh Harjani <ritesh.list@gmail.com> Cc: Gioh Kim <gioh.kim@lge.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-11-13 23:19:21 +00:00
extern char * const zone_names[MAX_NR_ZONES];
/* perform sanity checks on struct pages being allocated or freed */
DECLARE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled);
extern int min_free_kbytes;
void setup_per_zone_wmarks(void);
void calculate_min_free_kbytes(void);
int __meminit init_per_zone_wmark_min(void);
void page_alloc_sysctl_init(void);
/*
* Structure for holding the mostly immutable allocation parameters passed
* between functions involved in allocations, including the alloc_pages*
* family of functions.
*
* nodemask, migratetype and highest_zoneidx are initialized only once in
* __alloc_pages() and then never change.
*
* zonelist, preferred_zone and highest_zoneidx are set first in
* __alloc_pages() for the fast path, and might be later changed
* in __alloc_pages_slowpath(). All other functions pass the whole structure
* by a const pointer.
*/
struct alloc_context {
struct zonelist *zonelist;
nodemask_t *nodemask;
struct zoneref *preferred_zoneref;
int migratetype;
/*
* highest_zoneidx represents highest usable zone index of
* the allocation request. Due to the nature of the zone,
* memory on lower zone than the highest_zoneidx will be
* protected by lowmem_reserve[highest_zoneidx].
*
* highest_zoneidx is also used by reclaim/compaction to limit
* the target zone since higher zone than this index cannot be
* usable for this allocation request.
*/
enum zone_type highest_zoneidx;
bool spread_dirty_pages;
};
/*
* This function returns the order of a free page in the buddy system. In
* general, page_zone(page)->lock must be held by the caller to prevent the
* page from being allocated in parallel and returning garbage as the order.
* If a caller does not hold page_zone(page)->lock, it must guarantee that the
* page cannot be allocated or merged in parallel. Alternatively, it must
* handle invalid values gracefully, and use buddy_order_unsafe() below.
*/
static inline unsigned int buddy_order(struct page *page)
{
/* PageBuddy() must be checked by the caller */
return page_private(page);
}
/*
* Like buddy_order(), but for callers who cannot afford to hold the zone lock.
* PageBuddy() should be checked first by the caller to minimize race window,
* and invalid values must be handled gracefully.
*
* READ_ONCE is used so that if the caller assigns the result into a local
* variable and e.g. tests it for valid range before using, the compiler cannot
* decide to remove the variable and inline the page_private(page) multiple
* times, potentially observing different values in the tests and the actual
* use of the result.
*/
#define buddy_order_unsafe(page) READ_ONCE(page_private(page))
/*
* This function checks whether a page is free && is the buddy
* we can coalesce a page and its buddy if
* (a) the buddy is not in a hole (check before calling!) &&
* (b) the buddy is in the buddy system &&
* (c) a page and its buddy have the same order &&
* (d) a page and its buddy are in the same zone.
*
* For recording whether a page is in the buddy system, we set PageBuddy.
* Setting, clearing, and testing PageBuddy is serialized by zone->lock.
*
* For recording page's order, we use page_private(page).
*/
static inline bool page_is_buddy(struct page *page, struct page *buddy,
unsigned int order)
{
if (!page_is_guard(buddy) && !PageBuddy(buddy))
return false;
if (buddy_order(buddy) != order)
return false;
/*
* zone check is done late to avoid uselessly calculating
* zone/node ids for pages that could never merge.
*/
if (page_zone_id(page) != page_zone_id(buddy))
return false;
VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);
return true;
}
mm/page_alloc: restrict max order of merging on isolated pageblock Current pageblock isolation logic could isolate each pageblock individually. This causes freepage accounting problem if freepage with pageblock order on isolate pageblock is merged with other freepage on normal pageblock. We can prevent merging by restricting max order of merging to pageblock order if freepage is on isolate pageblock. A side-effect of this change is that there could be non-merged buddy freepage even if finishing pageblock isolation, because undoing pageblock isolation is just to move freepage from isolate buddy list to normal buddy list rather than to consider merging. So, the patch also makes undoing pageblock isolation consider freepage merge. When un-isolation, freepage with more than pageblock order and it's buddy are checked. If they are on normal pageblock, instead of just moving, we isolate the freepage and free it in order to get merged. Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Laura Abbott <lauraa@codeaurora.org> Cc: Heesub Shin <heesub.shin@samsung.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Cc: Ritesh Harjani <ritesh.list@gmail.com> Cc: Gioh Kim <gioh.kim@lge.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-11-13 23:19:21 +00:00
/*
* Locate the struct page for both the matching buddy in our
* pair (buddy1) and the combined O(n+1) page they form (page).
*
* 1) Any buddy B1 will have an order O twin B2 which satisfies
* the following equation:
* B2 = B1 ^ (1 << O)
* For example, if the starting buddy (buddy2) is #8 its order
* 1 buddy is #10:
* B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10
*
* 2) Any buddy B will have an order O+1 parent P which
* satisfies the following equation:
* P = B & ~(1 << O)
*
* Assumption: *_mem_map is contiguous at least up to MAX_PAGE_ORDER
mm/page_alloc: restrict max order of merging on isolated pageblock Current pageblock isolation logic could isolate each pageblock individually. This causes freepage accounting problem if freepage with pageblock order on isolate pageblock is merged with other freepage on normal pageblock. We can prevent merging by restricting max order of merging to pageblock order if freepage is on isolate pageblock. A side-effect of this change is that there could be non-merged buddy freepage even if finishing pageblock isolation, because undoing pageblock isolation is just to move freepage from isolate buddy list to normal buddy list rather than to consider merging. So, the patch also makes undoing pageblock isolation consider freepage merge. When un-isolation, freepage with more than pageblock order and it's buddy are checked. If they are on normal pageblock, instead of just moving, we isolate the freepage and free it in order to get merged. Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Laura Abbott <lauraa@codeaurora.org> Cc: Heesub Shin <heesub.shin@samsung.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Cc: Ritesh Harjani <ritesh.list@gmail.com> Cc: Gioh Kim <gioh.kim@lge.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-11-13 23:19:21 +00:00
*/
static inline unsigned long
__find_buddy_pfn(unsigned long page_pfn, unsigned int order)
mm/page_alloc: restrict max order of merging on isolated pageblock Current pageblock isolation logic could isolate each pageblock individually. This causes freepage accounting problem if freepage with pageblock order on isolate pageblock is merged with other freepage on normal pageblock. We can prevent merging by restricting max order of merging to pageblock order if freepage is on isolate pageblock. A side-effect of this change is that there could be non-merged buddy freepage even if finishing pageblock isolation, because undoing pageblock isolation is just to move freepage from isolate buddy list to normal buddy list rather than to consider merging. So, the patch also makes undoing pageblock isolation consider freepage merge. When un-isolation, freepage with more than pageblock order and it's buddy are checked. If they are on normal pageblock, instead of just moving, we isolate the freepage and free it in order to get merged. Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Laura Abbott <lauraa@codeaurora.org> Cc: Heesub Shin <heesub.shin@samsung.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Cc: Ritesh Harjani <ritesh.list@gmail.com> Cc: Gioh Kim <gioh.kim@lge.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-11-13 23:19:21 +00:00
{
return page_pfn ^ (1 << order);
mm/page_alloc: restrict max order of merging on isolated pageblock Current pageblock isolation logic could isolate each pageblock individually. This causes freepage accounting problem if freepage with pageblock order on isolate pageblock is merged with other freepage on normal pageblock. We can prevent merging by restricting max order of merging to pageblock order if freepage is on isolate pageblock. A side-effect of this change is that there could be non-merged buddy freepage even if finishing pageblock isolation, because undoing pageblock isolation is just to move freepage from isolate buddy list to normal buddy list rather than to consider merging. So, the patch also makes undoing pageblock isolation consider freepage merge. When un-isolation, freepage with more than pageblock order and it's buddy are checked. If they are on normal pageblock, instead of just moving, we isolate the freepage and free it in order to get merged. Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Laura Abbott <lauraa@codeaurora.org> Cc: Heesub Shin <heesub.shin@samsung.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Cc: Ritesh Harjani <ritesh.list@gmail.com> Cc: Gioh Kim <gioh.kim@lge.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-11-13 23:19:21 +00:00
}
/*
* Find the buddy of @page and validate it.
* @page: The input page
* @pfn: The pfn of the page, it saves a call to page_to_pfn() when the
* function is used in the performance-critical __free_one_page().
* @order: The order of the page
* @buddy_pfn: The output pointer to the buddy pfn, it also saves a call to
* page_to_pfn().
*
* The found buddy can be a non PageBuddy, out of @page's zone, or its order is
* not the same as @page. The validation is necessary before use it.
*
* Return: the found buddy page or NULL if not found.
*/
static inline struct page *find_buddy_page_pfn(struct page *page,
unsigned long pfn, unsigned int order, unsigned long *buddy_pfn)
{
unsigned long __buddy_pfn = __find_buddy_pfn(pfn, order);
struct page *buddy;
buddy = page + (__buddy_pfn - pfn);
if (buddy_pfn)
*buddy_pfn = __buddy_pfn;
if (page_is_buddy(page, buddy, order))
return buddy;
return NULL;
}
mm/compaction: speed up pageblock_pfn_to_page() when zone is contiguous There is a performance drop report due to hugepage allocation and in there half of cpu time are spent on pageblock_pfn_to_page() in compaction [1]. In that workload, compaction is triggered to make hugepage but most of pageblocks are un-available for compaction due to pageblock type and skip bit so compaction usually fails. Most costly operations in this case is to find valid pageblock while scanning whole zone range. To check if pageblock is valid to compact, valid pfn within pageblock is required and we can obtain it by calling pageblock_pfn_to_page(). This function checks whether pageblock is in a single zone and return valid pfn if possible. Problem is that we need to check it every time before scanning pageblock even if we re-visit it and this turns out to be very expensive in this workload. Although we have no way to skip this pageblock check in the system where hole exists at arbitrary position, we can use cached value for zone continuity and just do pfn_to_page() in the system where hole doesn't exist. This optimization considerably speeds up in above workload. Before vs After Max: 1096 MB/s vs 1325 MB/s Min: 635 MB/s 1015 MB/s Avg: 899 MB/s 1194 MB/s Avg is improved by roughly 30% [2]. [1]: http://www.spinics.net/lists/linux-mm/msg97378.html [2]: https://lkml.org/lkml/2015/12/9/23 [akpm@linux-foundation.org: don't forget to restore zone->contiguous on error path, per Vlastimil] Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Reported-by: Aaron Lu <aaron.lu@intel.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Tested-by: Aaron Lu <aaron.lu@intel.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:57:51 +00:00
extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn,
unsigned long end_pfn, struct zone *zone);
static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn,
unsigned long end_pfn, struct zone *zone)
{
if (zone->contiguous)
return pfn_to_page(start_pfn);
return __pageblock_pfn_to_page(start_pfn, end_pfn, zone);
}
void set_zone_contiguous(struct zone *zone);
static inline void clear_zone_contiguous(struct zone *zone)
{
zone->contiguous = false;
}
mm/page_alloc: restrict max order of merging on isolated pageblock Current pageblock isolation logic could isolate each pageblock individually. This causes freepage accounting problem if freepage with pageblock order on isolate pageblock is merged with other freepage on normal pageblock. We can prevent merging by restricting max order of merging to pageblock order if freepage is on isolate pageblock. A side-effect of this change is that there could be non-merged buddy freepage even if finishing pageblock isolation, because undoing pageblock isolation is just to move freepage from isolate buddy list to normal buddy list rather than to consider merging. So, the patch also makes undoing pageblock isolation consider freepage merge. When un-isolation, freepage with more than pageblock order and it's buddy are checked. If they are on normal pageblock, instead of just moving, we isolate the freepage and free it in order to get merged. Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Laura Abbott <lauraa@codeaurora.org> Cc: Heesub Shin <heesub.shin@samsung.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Cc: Ritesh Harjani <ritesh.list@gmail.com> Cc: Gioh Kim <gioh.kim@lge.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-11-13 23:19:21 +00:00
extern int __isolate_free_page(struct page *page, unsigned int order);
mm: add function __putback_isolated_page There are cases where we would benefit from avoiding having to go through the allocation and free cycle to return an isolated page. Examples for this might include page poisoning in which we isolate a page and then put it back in the free list without ever having actually allocated it. This will enable us to also avoid notifiers for the future free page reporting which will need to avoid retriggering page reporting when returning pages that have been reported on. Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: David Hildenbrand <david@redhat.com> Acked-by: Mel Gorman <mgorman@techsingularity.net> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Nitesh Narayan Lal <nitesh@redhat.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Pankaj Gupta <pagupta@redhat.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Rik van Riel <riel@surriel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Wei Wang <wei.w.wang@intel.com> Cc: Yang Zhang <yang.zhang.wz@gmail.com> Cc: wei qi <weiqi4@huawei.com> Link: http://lkml.kernel.org/r/20200211224624.29318.89287.stgit@localhost.localdomain Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-07 03:04:53 +00:00
extern void __putback_isolated_page(struct page *page, unsigned int order,
int mt);
memblock: rename __free_pages_bootmem to memblock_free_pages The conversion is done using sed -i 's@__free_pages_bootmem@memblock_free_pages@' \ $(git grep -l __free_pages_bootmem) Link: http://lkml.kernel.org/r/1536927045-23536-27-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: "David S. Miller" <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Ingo Molnar <mingo@redhat.com> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Jonas Bonn <jonas@southpole.se> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Ley Foon Tan <lftan@altera.com> Cc: Mark Salter <msalter@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Palmer Dabbelt <palmer@sifive.com> Cc: Paul Burton <paul.burton@mips.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Serge Semin <fancer.lancer@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-30 22:09:36 +00:00
extern void memblock_free_pages(struct page *page, unsigned long pfn,
unsigned int order);
mm: pass meminit_context to __free_pages_core() Patch series "mm/memory_hotplug: use PageOffline() instead of PageReserved() for !ZONE_DEVICE". This can be a considered a long-overdue follow-up to some parts of [1]. The patches are based on [2], but they are not strictly required -- just makes it clearer why we can use adjust_managed_page_count() for memory hotplug without going into details about highmem. We stop initializing pages with PageReserved() in memory hotplug code -- except when dealing with ZONE_DEVICE for now. Instead, we use PageOffline(): all pages are initialized to PageOffline() when onlining a memory section, and only the ones actually getting exposed to the system/page allocator will get PageOffline cleared. This way, we enlighten memory hotplug more about PageOffline() pages and can cleanup some hacks we have in virtio-mem code. What about ZONE_DEVICE? PageOffline() is wrong, but we might just stop using PageReserved() for them later by simply checking for is_zone_device_page() at suitable places. That will be a separate patch set / proposal. This primarily affects virtio-mem, HV-balloon and XEN balloon. I only briefly tested with virtio-mem, which benefits most from these cleanups. [1] https://lore.kernel.org/all/20191024120938.11237-1-david@redhat.com/ [2] https://lkml.kernel.org/r/20240607083711.62833-1-david@redhat.com This patch (of 3): In preparation for further changes, let's teach __free_pages_core() about the differences of memory hotplug handling. Move the memory hotplug specific handling from generic_online_page() to __free_pages_core(), use adjust_managed_page_count() on the memory hotplug path, and spell out why memory freed via memblock cannot currently use adjust_managed_page_count(). [david@redhat.com: add missed CONFIG_DEFERRED_STRUCT_PAGE_INIT] Link: https://lkml.kernel.org/r/b72e6efd-fb0a-459c-b1a0-88a98e5b19e2@redhat.com [david@redhat.com: fix up the memblock comment, per Oscar] Link: https://lkml.kernel.org/r/2ed64218-7f3b-4302-a5dc-27f060654fe2@redhat.com [david@redhat.com: add the parameter name also in the declaration] Link: https://lkml.kernel.org/r/ca575956-f0dd-4fb9-a307-6b7621681ed9@redhat.com Link: https://lkml.kernel.org/r/20240607090939.89524-1-david@redhat.com Link: https://lkml.kernel.org/r/20240607090939.89524-2-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Cc: Alexander Potapenko <glider@google.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Eugenio Pérez <eperezma@redhat.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Juergen Gross <jgross@suse.com> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Marco Elver <elver@google.com> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: Wei Liu <wei.liu@kernel.org> Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-06-07 09:09:36 +00:00
extern void __free_pages_core(struct page *page, unsigned int order,
enum meminit_context context);
/*
* This will have no effect, other than possibly generating a warning, if the
* caller passes in a non-large folio.
*/
static inline void folio_set_order(struct folio *folio, unsigned int order)
{
if (WARN_ON_ONCE(!order || !folio_test_large(folio)))
return;
folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order;
#ifdef CONFIG_64BIT
folio->_folio_nr_pages = 1U << order;
#endif
}
void __folio_undo_large_rmappable(struct folio *folio);
static inline void folio_undo_large_rmappable(struct folio *folio)
{
if (folio_order(folio) <= 1 || !folio_test_large_rmappable(folio))
return;
/*
* At this point, there is no one trying to add the folio to
* deferred_list. If folio is not in deferred_list, it's safe
* to check without acquiring the split_queue_lock.
*/
if (data_race(list_empty(&folio->_deferred_list)))
return;
__folio_undo_large_rmappable(folio);
}
static inline struct folio *page_rmappable_folio(struct page *page)
{
struct folio *folio = (struct folio *)page;
if (folio && folio_test_large(folio))
folio_set_large_rmappable(folio);
return folio;
}
static inline void prep_compound_head(struct page *page, unsigned int order)
{
struct folio *folio = (struct folio *)page;
folio_set_order(folio, order);
mm: track mapcount of large folios in single value Let's track the mapcount of large folios in a single value. The mapcount of a large folio currently corresponds to the sum of the entire mapcount and all page mapcounts. This sum is what we actually want to know in folio_mapcount() and it is also sufficient for implementing folio_mapped(). With PTE-mapped THP becoming more important and more widely used, we want to avoid looping over all pages of a folio just to obtain the mapcount of large folios. The comment "In the common case, avoid the loop when no pages mapped by PTE" in folio_total_mapcount() does no longer hold for mTHP that are always mapped by PTE. Further, we are planning on using folio_mapcount() more frequently, and might even want to remove page mapcounts for large folios in some kernel configs. Therefore, allow for reading the mapcount of large folios efficiently and atomically without looping over any pages. Maintain the mapcount also for hugetlb pages for simplicity. Use the new mapcount to implement folio_mapcount() and folio_mapped(). Make page_mapped() simply call folio_mapped(). We can now get rid of folio_large_is_mapped(). _nr_pages_mapped is now only used in rmap code and for debugging purposes. Keep folio_nr_pages_mapped() around, but document that its use should be limited to rmap internals and debugging purposes. This change implies one additional atomic add/sub whenever mapping/unmapping (parts of) a large folio. As we now batch RMAP operations for PTE-mapped THP during fork(), during unmap/zap, and when PTE-remapping a PMD-mapped THP, and we adjust the large mapcount for a PTE batch only once, the added overhead in the common case is small. Only when unmapping individual pages of a large folio (e.g., during COW), the overhead might be bigger in comparison, but it's essentially one additional atomic operation. Note that before the new mapcount would overflow, already our refcount would overflow: each mapping requires a folio reference. Extend the focumentation of folio_mapcount(). Link: https://lkml.kernel.org/r/20240409192301.907377-5-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Reviewed-by: Yin Fengwei <fengwei.yin@intel.com> Cc: Chris Zankel <chris@zankel.net> Cc: Hugh Dickins <hughd@google.com> Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Muchun Song <muchun.song@linux.dev> Cc: Naoya Horiguchi <nao.horiguchi@gmail.com> Cc: Peter Xu <peterx@redhat.com> Cc: Richard Chang <richardycc@google.com> Cc: Rich Felker <dalias@libc.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-09 19:22:47 +00:00
atomic_set(&folio->_large_mapcount, -1);
atomic_set(&folio->_entire_mapcount, -1);
atomic_set(&folio->_nr_pages_mapped, 0);
atomic_set(&folio->_pincount, 0);
if (order > 1)
INIT_LIST_HEAD(&folio->_deferred_list);
}
static inline void prep_compound_tail(struct page *head, int tail_idx)
{
struct page *p = head + tail_idx;
p->mapping = TAIL_MAPPING;
set_compound_head(p, head);
set_page_private(p, 0);
}
extern void prep_compound_page(struct page *page, unsigned int order);
mm/page_alloc: introduce post allocation processing on page allocator This patch is motivated from Hugh and Vlastimil's concern [1]. There are two ways to get freepage from the allocator. One is using normal memory allocation API and the other is __isolate_free_page() which is internally used for compaction and pageblock isolation. Later usage is rather tricky since it doesn't do whole post allocation processing done by normal API. One problematic thing I already know is that poisoned page would not be checked if it is allocated by __isolate_free_page(). Perhaps, there would be more. We could add more debug logic for allocated page in the future and this separation would cause more problem. I'd like to fix this situation at this time. Solution is simple. This patch commonize some logic for newly allocated page and uses it on all sites. This will solve the problem. [1] http://marc.info/?i=alpine.LSU.2.11.1604270029350.7066%40eggly.anvils%3E [iamjoonsoo.kim@lge.com: mm-page_alloc-introduce-post-allocation-processing-on-page-allocator-v3] Link: http://lkml.kernel.org/r/1464230275-25791-7-git-send-email-iamjoonsoo.kim@lge.com Link: http://lkml.kernel.org/r/1466150259-27727-9-git-send-email-iamjoonsoo.kim@lge.com Link: http://lkml.kernel.org/r/1464230275-25791-7-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Minchan Kim <minchan@kernel.org> Cc: Alexander Potapenko <glider@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Michal Hocko <mhocko@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-07-26 22:23:58 +00:00
extern void post_alloc_hook(struct page *page, unsigned int order,
gfp_t gfp_flags);
mm/compaction: add support for >0 order folio memory compaction. Before last commit, memory compaction only migrates order-0 folios and skips >0 order folios. Last commit splits all >0 order folios during compaction. This commit migrates >0 order folios during compaction by keeping isolated free pages at their original size without splitting them into order-0 pages and using them directly during migration process. What is different from the prior implementation: 1. All isolated free pages are kept in a NR_PAGE_ORDERS array of page lists, where each page list stores free pages in the same order. 2. All free pages are not post_alloc_hook() processed nor buddy pages, although their orders are stored in first page's private like buddy pages. 3. During migration, in new page allocation time (i.e., in compaction_alloc()), free pages are then processed by post_alloc_hook(). When migration fails and a new page is returned (i.e., in compaction_free()), free pages are restored by reversing the post_alloc_hook() operations using newly added free_pages_prepare_fpi_none(). Step 3 is done for a latter optimization that splitting and/or merging free pages during compaction becomes easier. Note: without splitting free pages, compaction can end prematurely due to migration will return -ENOMEM even if there is free pages. This happens when no order-0 free page exist and compaction_alloc() return NULL. Link: https://lkml.kernel.org/r/20240220183220.1451315-4-zi.yan@sent.com Signed-off-by: Zi Yan <ziy@nvidia.com> Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Tested-by: Baolin Wang <baolin.wang@linux.alibaba.com> Tested-by: Yu Zhao <yuzhao@google.com> Cc: Adam Manzanares <a.manzanares@samsung.com> Cc: David Hildenbrand <david@redhat.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kemeng Shi <shikemeng@huaweicloud.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Vishal Moola (Oracle) <vishal.moola@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yin Fengwei <fengwei.yin@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-02-20 18:32:19 +00:00
extern bool free_pages_prepare(struct page *page, unsigned int order);
extern int user_min_free_kbytes;
mm: introduce PageHuge() for testing huge/gigantic pages A series of patches to enhance the /proc/pagemap interface and to add a userspace executable which can be used to present the pagemap data. Export 10 more flags to end users (and more for kernel developers): 11. KPF_MMAP (pseudo flag) memory mapped page 12. KPF_ANON (pseudo flag) memory mapped page (anonymous) 13. KPF_SWAPCACHE page is in swap cache 14. KPF_SWAPBACKED page is swap/RAM backed 15. KPF_COMPOUND_HEAD (*) 16. KPF_COMPOUND_TAIL (*) 17. KPF_HUGE hugeTLB pages 18. KPF_UNEVICTABLE page is in the unevictable LRU list 19. KPF_HWPOISON hardware detected corruption 20. KPF_NOPAGE (pseudo flag) no page frame at the address (*) For compound pages, exporting _both_ head/tail info enables users to tell where a compound page starts/ends, and its order. a simple demo of the page-types tool # ./page-types -h page-types [options] -r|--raw Raw mode, for kernel developers -a|--addr addr-spec Walk a range of pages -b|--bits bits-spec Walk pages with specified bits -l|--list Show page details in ranges -L|--list-each Show page details one by one -N|--no-summary Don't show summay info -h|--help Show this usage message addr-spec: N one page at offset N (unit: pages) N+M pages range from N to N+M-1 N,M pages range from N to M-1 N, pages range from N to end ,M pages range from 0 to M bits-spec: bit1,bit2 (flags & (bit1|bit2)) != 0 bit1,bit2=bit1 (flags & (bit1|bit2)) == bit1 bit1,~bit2 (flags & (bit1|bit2)) == bit1 =bit1,bit2 flags == (bit1|bit2) bit-names: locked error referenced uptodate dirty lru active slab writeback reclaim buddy mmap anonymous swapcache swapbacked compound_head compound_tail huge unevictable hwpoison nopage reserved(r) mlocked(r) mappedtodisk(r) private(r) private_2(r) owner_private(r) arch(r) uncached(r) readahead(o) slob_free(o) slub_frozen(o) slub_debug(o) (r) raw mode bits (o) overloaded bits # ./page-types flags page-count MB symbolic-flags long-symbolic-flags 0x0000000000000000 487369 1903 _________________________________ 0x0000000000000014 5 0 __R_D____________________________ referenced,dirty 0x0000000000000020 1 0 _____l___________________________ lru 0x0000000000000024 34 0 __R__l___________________________ referenced,lru 0x0000000000000028 3838 14 ___U_l___________________________ uptodate,lru 0x0001000000000028 48 0 ___U_l_______________________I___ uptodate,lru,readahead 0x000000000000002c 6478 25 __RU_l___________________________ referenced,uptodate,lru 0x000100000000002c 47 0 __RU_l_______________________I___ referenced,uptodate,lru,readahead 0x0000000000000040 8344 32 ______A__________________________ active 0x0000000000000060 1 0 _____lA__________________________ lru,active 0x0000000000000068 348 1 ___U_lA__________________________ uptodate,lru,active 0x0001000000000068 12 0 ___U_lA______________________I___ uptodate,lru,active,readahead 0x000000000000006c 988 3 __RU_lA__________________________ referenced,uptodate,lru,active 0x000100000000006c 48 0 __RU_lA______________________I___ referenced,uptodate,lru,active,readahead 0x0000000000004078 1 0 ___UDlA_______b__________________ uptodate,dirty,lru,active,swapbacked 0x000000000000407c 34 0 __RUDlA_______b__________________ referenced,uptodate,dirty,lru,active,swapbacked 0x0000000000000400 503 1 __________B______________________ buddy 0x0000000000000804 1 0 __R________M_____________________ referenced,mmap 0x0000000000000828 1029 4 ___U_l_____M_____________________ uptodate,lru,mmap 0x0001000000000828 43 0 ___U_l_____M_________________I___ uptodate,lru,mmap,readahead 0x000000000000082c 382 1 __RU_l_____M_____________________ referenced,uptodate,lru,mmap 0x000100000000082c 12 0 __RU_l_____M_________________I___ referenced,uptodate,lru,mmap,readahead 0x0000000000000868 192 0 ___U_lA____M_____________________ uptodate,lru,active,mmap 0x0001000000000868 12 0 ___U_lA____M_________________I___ uptodate,lru,active,mmap,readahead 0x000000000000086c 800 3 __RU_lA____M_____________________ referenced,uptodate,lru,active,mmap 0x000100000000086c 31 0 __RU_lA____M_________________I___ referenced,uptodate,lru,active,mmap,readahead 0x0000000000004878 2 0 ___UDlA____M__b__________________ uptodate,dirty,lru,active,mmap,swapbacked 0x0000000000001000 492 1 ____________a____________________ anonymous 0x0000000000005808 4 0 ___U_______Ma_b__________________ uptodate,mmap,anonymous,swapbacked 0x0000000000005868 2839 11 ___U_lA____Ma_b__________________ uptodate,lru,active,mmap,anonymous,swapbacked 0x000000000000586c 30 0 __RU_lA____Ma_b__________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked total 513968 2007 # ./page-types -r flags page-count MB symbolic-flags long-symbolic-flags 0x0000000000000000 468002 1828 _________________________________ 0x0000000100000000 19102 74 _____________________r___________ reserved 0x0000000000008000 41 0 _______________H_________________ compound_head 0x0000000000010000 188 0 ________________T________________ compound_tail 0x0000000000008014 1 0 __R_D__________H_________________ referenced,dirty,compound_head 0x0000000000010014 4 0 __R_D___________T________________ referenced,dirty,compound_tail 0x0000000000000020 1 0 _____l___________________________ lru 0x0000000800000024 34 0 __R__l__________________P________ referenced,lru,private 0x0000000000000028 3794 14 ___U_l___________________________ uptodate,lru 0x0001000000000028 46 0 ___U_l_______________________I___ uptodate,lru,readahead 0x0000000400000028 44 0 ___U_l_________________d_________ uptodate,lru,mappedtodisk 0x0001000400000028 2 0 ___U_l_________________d_____I___ uptodate,lru,mappedtodisk,readahead 0x000000000000002c 6434 25 __RU_l___________________________ referenced,uptodate,lru 0x000100000000002c 47 0 __RU_l_______________________I___ referenced,uptodate,lru,readahead 0x000000040000002c 14 0 __RU_l_________________d_________ referenced,uptodate,lru,mappedtodisk 0x000000080000002c 30 0 __RU_l__________________P________ referenced,uptodate,lru,private 0x0000000800000040 8124 31 ______A_________________P________ active,private 0x0000000000000040 219 0 ______A__________________________ active 0x0000000800000060 1 0 _____lA_________________P________ lru,active,private 0x0000000000000068 322 1 ___U_lA__________________________ uptodate,lru,active 0x0001000000000068 12 0 ___U_lA______________________I___ uptodate,lru,active,readahead 0x0000000400000068 13 0 ___U_lA________________d_________ uptodate,lru,active,mappedtodisk 0x0000000800000068 12 0 ___U_lA_________________P________ uptodate,lru,active,private 0x000000000000006c 977 3 __RU_lA__________________________ referenced,uptodate,lru,active 0x000100000000006c 48 0 __RU_lA______________________I___ referenced,uptodate,lru,active,readahead 0x000000040000006c 5 0 __RU_lA________________d_________ referenced,uptodate,lru,active,mappedtodisk 0x000000080000006c 3 0 __RU_lA_________________P________ referenced,uptodate,lru,active,private 0x0000000c0000006c 3 0 __RU_lA________________dP________ referenced,uptodate,lru,active,mappedtodisk,private 0x0000000c00000068 1 0 ___U_lA________________dP________ uptodate,lru,active,mappedtodisk,private 0x0000000000004078 1 0 ___UDlA_______b__________________ uptodate,dirty,lru,active,swapbacked 0x000000000000407c 34 0 __RUDlA_______b__________________ referenced,uptodate,dirty,lru,active,swapbacked 0x0000000000000400 538 2 __________B______________________ buddy 0x0000000000000804 1 0 __R________M_____________________ referenced,mmap 0x0000000000000828 1029 4 ___U_l_____M_____________________ uptodate,lru,mmap 0x0001000000000828 43 0 ___U_l_____M_________________I___ uptodate,lru,mmap,readahead 0x000000000000082c 382 1 __RU_l_____M_____________________ referenced,uptodate,lru,mmap 0x000100000000082c 12 0 __RU_l_____M_________________I___ referenced,uptodate,lru,mmap,readahead 0x0000000000000868 192 0 ___U_lA____M_____________________ uptodate,lru,active,mmap 0x0001000000000868 12 0 ___U_lA____M_________________I___ uptodate,lru,active,mmap,readahead 0x000000000000086c 800 3 __RU_lA____M_____________________ referenced,uptodate,lru,active,mmap 0x000100000000086c 31 0 __RU_lA____M_________________I___ referenced,uptodate,lru,active,mmap,readahead 0x0000000000004878 2 0 ___UDlA____M__b__________________ uptodate,dirty,lru,active,mmap,swapbacked 0x0000000000001000 492 1 ____________a____________________ anonymous 0x0000000000005008 2 0 ___U________a_b__________________ uptodate,anonymous,swapbacked 0x0000000000005808 4 0 ___U_______Ma_b__________________ uptodate,mmap,anonymous,swapbacked 0x000000000000580c 1 0 __RU_______Ma_b__________________ referenced,uptodate,mmap,anonymous,swapbacked 0x0000000000005868 2839 11 ___U_lA____Ma_b__________________ uptodate,lru,active,mmap,anonymous,swapbacked 0x000000000000586c 29 0 __RU_lA____Ma_b__________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked total 513968 2007 # ./page-types --raw --list --no-summary --bits reserved offset count flags 0 15 _____________________r___________ 31 4 _____________________r___________ 159 97 _____________________r___________ 4096 2067 _____________________r___________ 6752 2390 _____________________r___________ 9355 3 _____________________r___________ 9728 14526 _____________________r___________ This patch: Introduce PageHuge(), which identifies huge/gigantic pages by their dedicated compound destructor functions. Also move prep_compound_gigantic_page() to hugetlb.c and make __free_pages_ok() non-static. Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Matt Mackall <mpm@selenic.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-16 22:32:22 +00:00
void free_unref_page(struct page *page, unsigned int order);
void free_unref_folios(struct folio_batch *fbatch);
extern void zone_pcp_reset(struct zone *zone);
mm, page_alloc: disable pcplists during memory offline Memory offlining relies on page isolation to guarantee a forward progress because pages cannot be reused while they are isolated. But the page isolation itself doesn't prevent from races while freed pages are stored on pcp lists and thus can be reused. This can be worked around by repeated draining of pcplists, as done by commit 968318261221 ("mm/memory_hotplug: drain per-cpu pages again during memory offline"). David and Michal would prefer that this race was closed in a way that callers of page isolation who need stronger guarantees don't need to repeatedly drain. David suggested disabling pcplists usage completely during page isolation, instead of repeatedly draining them. To achieve this without adding special cases in alloc/free fastpath, we can use the same approach as boot pagesets - when pcp->high is 0, any pcplist addition will be immediately flushed. The race can thus be closed by setting pcp->high to 0 and draining pcplists once, before calling start_isolate_page_range(). The draining will serialize after processes that already disabled interrupts and read the old value of pcp->high in free_unref_page_commit(), and processes that have not yet disabled interrupts, will observe pcp->high == 0 when they are rescheduled, and skip pcplists. This guarantees no stray pages on pcplists in zones where isolation happens. This patch thus adds zone_pcp_disable() and zone_pcp_enable() functions that page isolation users can call before start_isolate_page_range() and after unisolating (or offlining) the isolated pages. Also, drain_all_pages() is optimized to only execute on cpus where pcplists are not empty. The check can however race with a free to pcplist that has not yet increased the pcp->count from 0 to 1. Thus make the drain optionally skip the racy check and drain on all cpus, and use this option in zone_pcp_disable(). As we have to avoid external updates to high and batch while pcplists are disabled, we take pcp_batch_high_lock in zone_pcp_disable() and release it in zone_pcp_enable(). This also synchronizes multiple users of zone_pcp_disable()/enable(). Currently the only user of this functionality is offline_pages(). [vbabka@suse.cz: add comment, per David] Link: https://lkml.kernel.org/r/527480ef-ed72-e1c1-52a0-1c5b0113df45@suse.cz Link: https://lkml.kernel.org/r/20201111092812.11329-8-vbabka@suse.cz Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Suggested-by: David Hildenbrand <david@redhat.com> Suggested-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Reviewed-by: David Hildenbrand <david@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-12-15 03:10:59 +00:00
extern void zone_pcp_disable(struct zone *zone);
extern void zone_pcp_enable(struct zone *zone);
extern void zone_pcp_init(struct zone *zone);
extern void *memmap_alloc(phys_addr_t size, phys_addr_t align,
phys_addr_t min_addr,
int nid, bool exact_nid);
void memmap_init_range(unsigned long, int, unsigned long, unsigned long,
unsigned long, enum meminit_context, struct vmem_altmap *, int);
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/*
* in mm/compaction.c
*/
/*
* compact_control is used to track pages being migrated and the free pages
* they are being migrated to during memory compaction. The free_pfn starts
* at the end of a zone and migrate_pfn begins at the start. Movable pages
* are moved to the end of a zone during a compaction run and the run
* completes when free_pfn <= migrate_pfn
*/
struct compact_control {
mm/compaction: add support for >0 order folio memory compaction. Before last commit, memory compaction only migrates order-0 folios and skips >0 order folios. Last commit splits all >0 order folios during compaction. This commit migrates >0 order folios during compaction by keeping isolated free pages at their original size without splitting them into order-0 pages and using them directly during migration process. What is different from the prior implementation: 1. All isolated free pages are kept in a NR_PAGE_ORDERS array of page lists, where each page list stores free pages in the same order. 2. All free pages are not post_alloc_hook() processed nor buddy pages, although their orders are stored in first page's private like buddy pages. 3. During migration, in new page allocation time (i.e., in compaction_alloc()), free pages are then processed by post_alloc_hook(). When migration fails and a new page is returned (i.e., in compaction_free()), free pages are restored by reversing the post_alloc_hook() operations using newly added free_pages_prepare_fpi_none(). Step 3 is done for a latter optimization that splitting and/or merging free pages during compaction becomes easier. Note: without splitting free pages, compaction can end prematurely due to migration will return -ENOMEM even if there is free pages. This happens when no order-0 free page exist and compaction_alloc() return NULL. Link: https://lkml.kernel.org/r/20240220183220.1451315-4-zi.yan@sent.com Signed-off-by: Zi Yan <ziy@nvidia.com> Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Tested-by: Baolin Wang <baolin.wang@linux.alibaba.com> Tested-by: Yu Zhao <yuzhao@google.com> Cc: Adam Manzanares <a.manzanares@samsung.com> Cc: David Hildenbrand <david@redhat.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kemeng Shi <shikemeng@huaweicloud.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Vishal Moola (Oracle) <vishal.moola@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yin Fengwei <fengwei.yin@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-02-20 18:32:19 +00:00
struct list_head freepages[NR_PAGE_ORDERS]; /* List of free pages to migrate to */
struct list_head migratepages; /* List of pages being migrated */
mm, compaction: shrink compact_control Patch series "Increase success rates and reduce latency of compaction", v3. This series reduces scan rates and success rates of compaction, primarily by using the free lists to shorten scans, better controlling of skip information and whether multiple scanners can target the same block and capturing pageblocks before being stolen by parallel requests. The series is based on mmotm from January 9th, 2019 with the previous compaction series reverted. I'm mostly using thpscale to measure the impact of the series. The benchmark creates a large file, maps it, faults it, punches holes in the mapping so that the virtual address space is fragmented and then tries to allocate THP. It re-executes for different numbers of threads. From a fragmentation perspective, the workload is relatively benign but it does stress compaction. The overall impact on latencies for a 1-socket machine is baseline patches Amean fault-both-3 3832.09 ( 0.00%) 2748.56 * 28.28%* Amean fault-both-5 4933.06 ( 0.00%) 4255.52 ( 13.73%) Amean fault-both-7 7017.75 ( 0.00%) 6586.93 ( 6.14%) Amean fault-both-12 11610.51 ( 0.00%) 9162.34 * 21.09%* Amean fault-both-18 17055.85 ( 0.00%) 11530.06 * 32.40%* Amean fault-both-24 19306.27 ( 0.00%) 17956.13 ( 6.99%) Amean fault-both-30 22516.49 ( 0.00%) 15686.47 * 30.33%* Amean fault-both-32 23442.93 ( 0.00%) 16564.83 * 29.34%* The allocation success rates are much improved baseline patches Percentage huge-3 85.99 ( 0.00%) 97.96 ( 13.92%) Percentage huge-5 88.27 ( 0.00%) 96.87 ( 9.74%) Percentage huge-7 85.87 ( 0.00%) 94.53 ( 10.09%) Percentage huge-12 82.38 ( 0.00%) 98.44 ( 19.49%) Percentage huge-18 83.29 ( 0.00%) 99.14 ( 19.04%) Percentage huge-24 81.41 ( 0.00%) 97.35 ( 19.57%) Percentage huge-30 80.98 ( 0.00%) 98.05 ( 21.08%) Percentage huge-32 80.53 ( 0.00%) 97.06 ( 20.53%) That's a nearly perfect allocation success rate. The biggest impact is on the scan rates Compaction migrate scanned 55893379 19341254 Compaction free scanned 474739990 11903963 The number of pages scanned for migration was reduced by 65% and the free scanner was reduced by 97.5%. So much less work in exchange for lower latency and better success rates. The series was also evaluated using a workload that heavily fragments memory but the benefits there are also significant, albeit not presented. It was commented that we should be rethinking scanning entirely and to a large extent I agree. However, to achieve that you need a lot of this series in place first so it's best to make the linear scanners as best as possible before ripping them out. This patch (of 22): The isolate and migrate scanners should never isolate more than a pageblock of pages so unsigned int is sufficient saving 8 bytes on a 64-bit build. Link: http://lkml.kernel.org/r/20190118175136.31341-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: David Rientjes <rientjes@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Dan Carpenter <dan.carpenter@oracle.com> Cc: YueHaibing <yuehaibing@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-05 23:44:25 +00:00
unsigned int nr_freepages; /* Number of isolated free pages */
unsigned int nr_migratepages; /* Number of pages to migrate */
unsigned long free_pfn; /* isolate_freepages search base */
/*
* Acts as an in/out parameter to page isolation for migration.
* isolate_migratepages uses it as a search base.
* isolate_migratepages_block will update the value to the next pfn
* after the last isolated one.
*/
unsigned long migrate_pfn;
mm, compaction: use free lists to quickly locate a migration source The migration scanner is a linear scan of a zone with a potentiall large search space. Furthermore, many pageblocks are unusable such as those filled with reserved pages or partially filled with pages that cannot migrate. These still get scanned in the common case of allocating a THP and the cost accumulates. The patch uses a partial search of the free lists to locate a migration source candidate that is marked as MOVABLE when allocating a THP. It prefers picking a block with a larger number of free pages already on the basis that there are fewer pages to migrate to free the entire block. The lowest PFN found during searches is tracked as the basis of the start for the linear search after the first search of the free list fails. After the search, the free list is shuffled so that the next search will not encounter the same page. If the search fails then the subsequent searches will be shorter and the linear scanner is used. If this search fails, or if the request is for a small or unmovable/reclaimable allocation then the linear scanner is still used. It is somewhat pointless to use the list search in those cases. Small free pages must be used for the search and there is no guarantee that movable pages are located within that block that are contiguous. 5.0.0-rc1 5.0.0-rc1 noboost-v3r10 findmig-v3r15 Amean fault-both-3 3771.41 ( 0.00%) 3390.40 ( 10.10%) Amean fault-both-5 5409.05 ( 0.00%) 5082.28 ( 6.04%) Amean fault-both-7 7040.74 ( 0.00%) 7012.51 ( 0.40%) Amean fault-both-12 11887.35 ( 0.00%) 11346.63 ( 4.55%) Amean fault-both-18 16718.19 ( 0.00%) 15324.19 ( 8.34%) Amean fault-both-24 21157.19 ( 0.00%) 16088.50 * 23.96%* Amean fault-both-30 21175.92 ( 0.00%) 18723.42 * 11.58%* Amean fault-both-32 21339.03 ( 0.00%) 18612.01 * 12.78%* 5.0.0-rc1 5.0.0-rc1 noboost-v3r10 findmig-v3r15 Percentage huge-3 86.50 ( 0.00%) 89.83 ( 3.85%) Percentage huge-5 92.52 ( 0.00%) 91.96 ( -0.61%) Percentage huge-7 92.44 ( 0.00%) 92.85 ( 0.44%) Percentage huge-12 92.98 ( 0.00%) 92.74 ( -0.25%) Percentage huge-18 91.70 ( 0.00%) 91.71 ( 0.02%) Percentage huge-24 91.59 ( 0.00%) 92.13 ( 0.60%) Percentage huge-30 90.14 ( 0.00%) 93.79 ( 4.04%) Percentage huge-32 90.03 ( 0.00%) 91.27 ( 1.37%) This shows an improvement in allocation latencies with similar allocation success rates. While not presented, there was a 31% reduction in migration scanning and a 8% reduction on system CPU usage. A 2-socket machine showed similar benefits. [mgorman@techsingularity.net: several fixes] Link: http://lkml.kernel.org/r/20190204120111.GL9565@techsingularity.net [vbabka@suse.cz: migrate block that was found-fast, some optimisations] Link: http://lkml.kernel.org/r/20190118175136.31341-10-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <Vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Dan Carpenter <dan.carpenter@oracle.com> Cc: David Rientjes <rientjes@google.com> Cc: YueHaibing <yuehaibing@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-05 23:44:54 +00:00
unsigned long fast_start_pfn; /* a pfn to start linear scan from */
struct zone *zone;
unsigned long total_migrate_scanned;
unsigned long total_free_scanned;
unsigned short fast_search_fail;/* failures to use free list searches */
short search_order; /* order to start a fast search at */
mm, compaction: reorder fields in struct compact_control Patch series "try to reduce fragmenting fallbacks", v3. Last year, Johannes Weiner has reported a regression in page mobility grouping [1] and while the exact cause was not found, I've come up with some ways to improve it by reducing the number of allocations falling back to different migratetype and causing permanent fragmentation. The series was tested with mmtests stress-highalloc modified to do GFP_KERNEL order-4 allocations, on 4.9 with "mm, vmscan: fix zone balance check in prepare_kswapd_sleep" (without that, kcompactd indeed wasn't woken up) on UMA machine with 4GB memory. There were 5 repeats of each run, as the extfrag stats are quite volatile (note the stats below are sums, not averages, as it was less perl hacking for me). Success rate are the same, already high due to the low allocation order used, so I'm not including them. Compaction stats: (the patches are stacked, and I haven't measured the non-functional-changes patches separately) patch 1 patch 2 patch 3 patch 4 patch 7 patch 8 Compaction stalls 22449 24680 24846 19765 22059 17480 Compaction success 12971 14836 14608 10475 11632 8757 Compaction failures 9477 9843 10238 9290 10426 8722 Page migrate success 3109022 3370438 3312164 1695105 1608435 2111379 Page migrate failure 911588 1149065 1028264 1112675 1077251 1026367 Compaction pages isolated 7242983 8015530 7782467 4629063 4402787 5377665 Compaction migrate scanned 980838938 987367943 957690188 917647238 947155598 1018922197 Compaction free scanned 557926893 598946443 602236894 594024490 541169699 763651731 Compaction cost 10243 10578 10304 8286 8398 9440 Compaction stats are mostly within noise until patch 4, which decreases the number of compactions, and migrations. Part of that could be due to more pageblocks marked as unmovable, and async compaction skipping those. This changes a bit with patch 7, but not so much. Patch 8 increases free scanner stats and migrations, which comes from the changed termination criteria. Interestingly number of compactions decreases - probably the fully compacted pageblock satisfies multiple subsequent allocations, so it amortizes. Next comes the extfrag tracepoint, where "fragmenting" means that an allocation had to fallback to a pageblock of another migratetype which wasn't fully free (which is almost all of the fallbacks). I have locally added another tracepoint for "Page steal" into steal_suitable_fallback() which triggers in situations where we are allowed to do move_freepages_block(). If we decide to also do set_pageblock_migratetype(), it's "Pages steal with pageblock" with break down for which allocation migratetype we are stealing and from which fallback migratetype. The last part "due to counting" comes from patch 4 and counts the events where the counting of movable pages allowed us to change pageblock's migratetype, while the number of free pages alone wouldn't be enough to cross the threshold. patch 1 patch 2 patch 3 patch 4 patch 7 patch 8 Page alloc extfrag event 10155066 8522968 10164959 15622080 13727068 13140319 Extfrag fragmenting 10149231 8517025 10159040 15616925 13721391 13134792 Extfrag fragmenting for unmovable 159504 168500 184177 97835 70625 56948 Extfrag fragmenting unmovable placed with movable 153613 163549 172693 91740 64099 50917 Extfrag fragmenting unmovable placed with reclaim. 5891 4951 11484 6095 6526 6031 Extfrag fragmenting for reclaimable 4738 4829 6345 4822 5640 5378 Extfrag fragmenting reclaimable placed with movable 1836 1902 1851 1579 1739 1760 Extfrag fragmenting reclaimable placed with unmov. 2902 2927 4494 3243 3901 3618 Extfrag fragmenting for movable 9984989 8343696 9968518 15514268 13645126 13072466 Pages steal 179954 192291 210880 123254 94545 81486 Pages steal with pageblock 22153 18943 20154 33562 29969 33444 Pages steal with pageblock for unmovable 14350 12858 13256 20660 19003 20852 Pages steal with pageblock for unmovable from mov. 12812 11402 11683 19072 17467 19298 Pages steal with pageblock for unmovable from recl. 1538 1456 1573 1588 1536 1554 Pages steal with pageblock for movable 7114 5489 5965 11787 10012 11493 Pages steal with pageblock for movable from unmov. 6885 5291 5541 11179 9525 10885 Pages steal with pageblock for movable from recl. 229 198 424 608 487 608 Pages steal with pageblock for reclaimable 689 596 933 1115 954 1099 Pages steal with pageblock for reclaimable from unmov. 273 219 537 658 547 667 Pages steal with pageblock for reclaimable from mov. 416 377 396 457 407 432 Pages steal with pageblock due to counting 11834 10075 7530 ... for unmovable 8993 7381 4616 ... for movable 2792 2653 2851 ... for reclaimable 49 41 63 What we can see is that "Extfrag fragmenting for unmovable" and "... placed with movable" drops with almost each patch, which is good as we are polluting less movable pageblocks with unmovable pages. The most significant change is patch 4 with movable page counting. On the other hand it increases "Extfrag fragmenting for movable" by 50%. "Pages steal" drops though, so these movable allocation fallbacks find only small free pages and are not allowed to steal whole pageblocks back. "Pages steal with pageblock" raises, because the patch increases the chances of pageblock migratetype changes to happen. This affects all migratetypes. The summary is that patch 4 is not a clear win wrt these stats, but I believe that the tradeoff it makes is a good one. There's less pollution of movable pageblocks by unmovable allocations. There's less stealing between pageblock, and those that remain have higher chance of changing migratetype also the pageblock itself, so it should more faithfully reflect the migratetype of the pages within the pageblock. The increase of movable allocations falling back to unmovable pageblock might look dramatic, but those allocations can be migrated by compaction when needed, and other patches in the series (7-9) improve that aspect. Patches 7 and 8 continue the trend of reduced unmovable fallbacks and also reduce the impact on movable fallbacks from patch 4. [1] https://www.spinics.net/lists/linux-mm/msg114237.html This patch (of 8): While currently there are (mostly by accident) no holes in struct compact_control (on x86_64), but we are going to add more bool flags, so place them all together to the end of the structure. While at it, just order all fields from largest to smallest. Link: http://lkml.kernel.org/r/20170307131545.28577-2-vbabka@suse.cz Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-08 22:54:30 +00:00
const gfp_t gfp_mask; /* gfp mask of a direct compactor */
int order; /* order a direct compactor needs */
int migratetype; /* migratetype of direct compactor */
mm, compaction: reorder fields in struct compact_control Patch series "try to reduce fragmenting fallbacks", v3. Last year, Johannes Weiner has reported a regression in page mobility grouping [1] and while the exact cause was not found, I've come up with some ways to improve it by reducing the number of allocations falling back to different migratetype and causing permanent fragmentation. The series was tested with mmtests stress-highalloc modified to do GFP_KERNEL order-4 allocations, on 4.9 with "mm, vmscan: fix zone balance check in prepare_kswapd_sleep" (without that, kcompactd indeed wasn't woken up) on UMA machine with 4GB memory. There were 5 repeats of each run, as the extfrag stats are quite volatile (note the stats below are sums, not averages, as it was less perl hacking for me). Success rate are the same, already high due to the low allocation order used, so I'm not including them. Compaction stats: (the patches are stacked, and I haven't measured the non-functional-changes patches separately) patch 1 patch 2 patch 3 patch 4 patch 7 patch 8 Compaction stalls 22449 24680 24846 19765 22059 17480 Compaction success 12971 14836 14608 10475 11632 8757 Compaction failures 9477 9843 10238 9290 10426 8722 Page migrate success 3109022 3370438 3312164 1695105 1608435 2111379 Page migrate failure 911588 1149065 1028264 1112675 1077251 1026367 Compaction pages isolated 7242983 8015530 7782467 4629063 4402787 5377665 Compaction migrate scanned 980838938 987367943 957690188 917647238 947155598 1018922197 Compaction free scanned 557926893 598946443 602236894 594024490 541169699 763651731 Compaction cost 10243 10578 10304 8286 8398 9440 Compaction stats are mostly within noise until patch 4, which decreases the number of compactions, and migrations. Part of that could be due to more pageblocks marked as unmovable, and async compaction skipping those. This changes a bit with patch 7, but not so much. Patch 8 increases free scanner stats and migrations, which comes from the changed termination criteria. Interestingly number of compactions decreases - probably the fully compacted pageblock satisfies multiple subsequent allocations, so it amortizes. Next comes the extfrag tracepoint, where "fragmenting" means that an allocation had to fallback to a pageblock of another migratetype which wasn't fully free (which is almost all of the fallbacks). I have locally added another tracepoint for "Page steal" into steal_suitable_fallback() which triggers in situations where we are allowed to do move_freepages_block(). If we decide to also do set_pageblock_migratetype(), it's "Pages steal with pageblock" with break down for which allocation migratetype we are stealing and from which fallback migratetype. The last part "due to counting" comes from patch 4 and counts the events where the counting of movable pages allowed us to change pageblock's migratetype, while the number of free pages alone wouldn't be enough to cross the threshold. patch 1 patch 2 patch 3 patch 4 patch 7 patch 8 Page alloc extfrag event 10155066 8522968 10164959 15622080 13727068 13140319 Extfrag fragmenting 10149231 8517025 10159040 15616925 13721391 13134792 Extfrag fragmenting for unmovable 159504 168500 184177 97835 70625 56948 Extfrag fragmenting unmovable placed with movable 153613 163549 172693 91740 64099 50917 Extfrag fragmenting unmovable placed with reclaim. 5891 4951 11484 6095 6526 6031 Extfrag fragmenting for reclaimable 4738 4829 6345 4822 5640 5378 Extfrag fragmenting reclaimable placed with movable 1836 1902 1851 1579 1739 1760 Extfrag fragmenting reclaimable placed with unmov. 2902 2927 4494 3243 3901 3618 Extfrag fragmenting for movable 9984989 8343696 9968518 15514268 13645126 13072466 Pages steal 179954 192291 210880 123254 94545 81486 Pages steal with pageblock 22153 18943 20154 33562 29969 33444 Pages steal with pageblock for unmovable 14350 12858 13256 20660 19003 20852 Pages steal with pageblock for unmovable from mov. 12812 11402 11683 19072 17467 19298 Pages steal with pageblock for unmovable from recl. 1538 1456 1573 1588 1536 1554 Pages steal with pageblock for movable 7114 5489 5965 11787 10012 11493 Pages steal with pageblock for movable from unmov. 6885 5291 5541 11179 9525 10885 Pages steal with pageblock for movable from recl. 229 198 424 608 487 608 Pages steal with pageblock for reclaimable 689 596 933 1115 954 1099 Pages steal with pageblock for reclaimable from unmov. 273 219 537 658 547 667 Pages steal with pageblock for reclaimable from mov. 416 377 396 457 407 432 Pages steal with pageblock due to counting 11834 10075 7530 ... for unmovable 8993 7381 4616 ... for movable 2792 2653 2851 ... for reclaimable 49 41 63 What we can see is that "Extfrag fragmenting for unmovable" and "... placed with movable" drops with almost each patch, which is good as we are polluting less movable pageblocks with unmovable pages. The most significant change is patch 4 with movable page counting. On the other hand it increases "Extfrag fragmenting for movable" by 50%. "Pages steal" drops though, so these movable allocation fallbacks find only small free pages and are not allowed to steal whole pageblocks back. "Pages steal with pageblock" raises, because the patch increases the chances of pageblock migratetype changes to happen. This affects all migratetypes. The summary is that patch 4 is not a clear win wrt these stats, but I believe that the tradeoff it makes is a good one. There's less pollution of movable pageblocks by unmovable allocations. There's less stealing between pageblock, and those that remain have higher chance of changing migratetype also the pageblock itself, so it should more faithfully reflect the migratetype of the pages within the pageblock. The increase of movable allocations falling back to unmovable pageblock might look dramatic, but those allocations can be migrated by compaction when needed, and other patches in the series (7-9) improve that aspect. Patches 7 and 8 continue the trend of reduced unmovable fallbacks and also reduce the impact on movable fallbacks from patch 4. [1] https://www.spinics.net/lists/linux-mm/msg114237.html This patch (of 8): While currently there are (mostly by accident) no holes in struct compact_control (on x86_64), but we are going to add more bool flags, so place them all together to the end of the structure. While at it, just order all fields from largest to smallest. Link: http://lkml.kernel.org/r/20170307131545.28577-2-vbabka@suse.cz Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-08 22:54:30 +00:00
const unsigned int alloc_flags; /* alloc flags of a direct compactor */
const int highest_zoneidx; /* zone index of a direct compactor */
enum migrate_mode mode; /* Async or sync migration mode */
mm: compaction: cache if a pageblock was scanned and no pages were isolated When compaction was implemented it was known that scanning could potentially be excessive. The ideal was that a counter be maintained for each pageblock but maintaining this information would incur a severe penalty due to a shared writable cache line. It has reached the point where the scanning costs are a serious problem, particularly on long-lived systems where a large process starts and allocates a large number of THPs at the same time. Instead of using a shared counter, this patch adds another bit to the pageblock flags called PG_migrate_skip. If a pageblock is scanned by either migrate or free scanner and 0 pages were isolated, the pageblock is marked to be skipped in the future. When scanning, this bit is checked before any scanning takes place and the block skipped if set. The main difficulty with a patch like this is "when to ignore the cached information?" If it's ignored too often, the scanning rates will still be excessive. If the information is too stale then allocations will fail that might have otherwise succeeded. In this patch o CMA always ignores the information o If the migrate and free scanner meet then the cached information will be discarded if it's at least 5 seconds since the last time the cache was discarded o If there are a large number of allocation failures, discard the cache. The time-based heuristic is very clumsy but there are few choices for a better event. Depending solely on multiple allocation failures still allows excessive scanning when THP allocations are failing in quick succession due to memory pressure. Waiting until memory pressure is relieved would cause compaction to continually fail instead of using reclaim/compaction to try allocate the page. The time-based mechanism is clumsy but a better option is not obvious. Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Rik van Riel <riel@redhat.com> Cc: Richard Davies <richard@arachsys.com> Cc: Shaohua Li <shli@kernel.org> Cc: Avi Kivity <avi@redhat.com> Acked-by: Rafael Aquini <aquini@redhat.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Cc: Kyungmin Park <kyungmin.park@samsung.com> Cc: Mark Brown <broonie@opensource.wolfsonmicro.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-08 23:32:41 +00:00
bool ignore_skip_hint; /* Scan blocks even if marked skip */
bool no_set_skip_hint; /* Don't mark blocks for skipping */
2016-10-08 00:00:37 +00:00
bool ignore_block_suitable; /* Scan blocks considered unsuitable */
mm, kswapd: replace kswapd compaction with waking up kcompactd Similarly to direct reclaim/compaction, kswapd attempts to combine reclaim and compaction to attempt making memory allocation of given order available. The details differ from direct reclaim e.g. in having high watermark as a goal. The code involved in kswapd's reclaim/compaction decisions has evolved to be quite complex. Testing reveals that it doesn't actually work in at least one scenario, and closer inspection suggests that it could be greatly simplified without compromising on the goal (make high-order page available) or efficiency (don't reclaim too much). The simplification relieas of doing all compaction in kcompactd, which is simply woken up when high watermarks are reached by kswapd's reclaim. The scenario where kswapd compaction doesn't work was found with mmtests test stress-highalloc configured to attempt order-9 allocations without direct reclaim, just waking up kswapd. There was no compaction attempt from kswapd during the whole test. Some added instrumentation shows what happens: - balance_pgdat() sets end_zone to Normal, as it's not balanced - reclaim is attempted on DMA zone, which sets nr_attempted to 99, but it cannot reclaim anything, so sc.nr_reclaimed is 0 - for zones DMA32 and Normal, kswapd_shrink_zone uses testorder=0, so it merely checks if high watermarks were reached for base pages. This is true, so no reclaim is attempted. For DMA, testorder=0 wasn't used, as compaction_suitable() returned COMPACT_SKIPPED - even though the pgdat_needs_compaction flag wasn't set to false, no compaction happens due to the condition sc.nr_reclaimed > nr_attempted being false (as 0 < 99) - priority-- due to nr_reclaimed being 0, repeat until priority reaches 0 pgdat_balanced() is false as only the small zone DMA appears balanced (curiously in that check, watermark appears OK and compaction_suitable() returns COMPACT_PARTIAL, because a lower classzone_idx is used there) Now, even if it was decided that reclaim shouldn't be attempted on the DMA zone, the scenario would be the same, as (sc.nr_reclaimed=0 > nr_attempted=0) is also false. The condition really should use >= as the comment suggests. Then there is a mismatch in the check for setting pgdat_needs_compaction to false using low watermark, while the rest uses high watermark, and who knows what other subtlety. Hopefully this demonstrates that this is unsustainable. Luckily we can simplify this a lot. The reclaim/compaction decisions make sense for direct reclaim scenario, but in kswapd, our primary goal is to reach high watermark in order-0 pages. Afterwards we can attempt compaction just once. Unlike direct reclaim, we don't reclaim extra pages (over the high watermark), the current code already disallows it for good reasons. After this patch, we simply wake up kcompactd to process the pgdat, after we have either succeeded or failed to reach the high watermarks in kswapd, which goes to sleep. We pass kswapd's order and classzone_idx, so kcompactd can apply the same criteria to determine which zones are worth compacting. Note that we use the classzone_idx from wakeup_kswapd(), not balanced_classzone_idx which can include higher zones that kswapd tried to balance too, but didn't consider them in pgdat_balanced(). Since kswapd now cannot create high-order pages itself, we need to adjust how it determines the zones to be balanced. The key element here is adding a "highorder" parameter to zone_balanced, which, when set to false, makes it consider only order-0 watermark instead of the desired higher order (this was done previously by kswapd_shrink_zone(), but not elsewhere). This false is passed for example in pgdat_balanced(). Importantly, wakeup_kswapd() uses true to make sure kswapd and thus kcompactd are woken up for a high-order allocation failure. The last thing is to decide what to do with pageblock_skip bitmap handling. Compaction maintains a pageblock_skip bitmap to record pageblocks where isolation recently failed. This bitmap can be reset by three ways: 1) direct compaction is restarting after going through the full deferred cycle 2) kswapd goes to sleep, and some other direct compaction has previously finished scanning the whole zone and set zone->compact_blockskip_flush. Note that a successful direct compaction clears this flag. 3) compaction was invoked manually via trigger in /proc The case 2) is somewhat fuzzy to begin with, but after introducing kcompactd we should update it. The check for direct compaction in 1), and to set the flush flag in 2) use current_is_kswapd(), which doesn't work for kcompactd. Thus, this patch adds bool direct_compaction to compact_control to use in 2). For the case 1) we remove the check completely - unlike the former kswapd compaction, kcompactd does use the deferred compaction functionality, so flushing tied to restarting from deferred compaction makes sense here. Note that when kswapd goes to sleep, kcompactd is woken up, so it will see the flushed pageblock_skip bits. This is different from when the former kswapd compaction observed the bits and I believe it makes more sense. Kcompactd can afford to be more thorough than a direct compaction trying to limit allocation latency, or kswapd whose primary goal is to reclaim. For testing, I used stress-highalloc configured to do order-9 allocations with GFP_NOWAIT|__GFP_HIGH|__GFP_COMP, so they relied just on kswapd/kcompactd reclaim/compaction (the interfering kernel builds in phases 1 and 2 work as usual): stress-highalloc 4.5-rc1+before 4.5-rc1+after -nodirect -nodirect Success 1 Min 1.00 ( 0.00%) 5.00 (-66.67%) Success 1 Mean 1.40 ( 0.00%) 6.20 (-55.00%) Success 1 Max 2.00 ( 0.00%) 7.00 (-16.67%) Success 2 Min 1.00 ( 0.00%) 5.00 (-66.67%) Success 2 Mean 1.80 ( 0.00%) 6.40 (-52.38%) Success 2 Max 3.00 ( 0.00%) 7.00 (-16.67%) Success 3 Min 34.00 ( 0.00%) 62.00 ( 1.59%) Success 3 Mean 41.80 ( 0.00%) 63.80 ( 1.24%) Success 3 Max 53.00 ( 0.00%) 65.00 ( 2.99%) User 3166.67 3181.09 System 1153.37 1158.25 Elapsed 1768.53 1799.37 4.5-rc1+before 4.5-rc1+after -nodirect -nodirect Direct pages scanned 32938 32797 Kswapd pages scanned 2183166 2202613 Kswapd pages reclaimed 2152359 2143524 Direct pages reclaimed 32735 32545 Percentage direct scans 1% 1% THP fault alloc 579 612 THP collapse alloc 304 316 THP splits 0 0 THP fault fallback 793 778 THP collapse fail 11 16 Compaction stalls 1013 1007 Compaction success 92 67 Compaction failures 920 939 Page migrate success 238457 721374 Page migrate failure 23021 23469 Compaction pages isolated 504695 1479924 Compaction migrate scanned 661390 8812554 Compaction free scanned 13476658 84327916 Compaction cost 262 838 After this patch we see improvements in allocation success rate (especially for phase 3) along with increased compaction activity. The compaction stalls (direct compaction) in the interfering kernel builds (probably THP's) also decreased somewhat thanks to kcompactd activity, yet THP alloc successes improved a bit. Note that elapsed and user time isn't so useful for this benchmark, because of the background interference being unpredictable. It's just to quickly spot some major unexpected differences. System time is somewhat more useful and that didn't increase. Also (after adjusting mmtests' ftrace monitor): Time kswapd awake 2547781 2269241 Time kcompactd awake 0 119253 Time direct compacting 939937 557649 Time kswapd compacting 0 0 Time kcompactd compacting 0 119099 The decrease of overal time spent compacting appears to not match the increased compaction stats. I suspect the tasks get rescheduled and since the ftrace monitor doesn't see that, the reported time is wall time, not CPU time. But arguably direct compactors care about overall latency anyway, whether busy compacting or waiting for CPU doesn't matter. And that latency seems to almost halved. It's also interesting how much time kswapd spent awake just going through all the priorities and failing to even try compacting, over and over. We can also configure stress-highalloc to perform both direct reclaim/compaction and wakeup kswapd/kcompactd, by using GFP_KERNEL|__GFP_HIGH|__GFP_COMP: stress-highalloc 4.5-rc1+before 4.5-rc1+after -direct -direct Success 1 Min 4.00 ( 0.00%) 9.00 (-50.00%) Success 1 Mean 8.00 ( 0.00%) 10.00 (-19.05%) Success 1 Max 12.00 ( 0.00%) 11.00 ( 15.38%) Success 2 Min 4.00 ( 0.00%) 9.00 (-50.00%) Success 2 Mean 8.20 ( 0.00%) 10.00 (-16.28%) Success 2 Max 13.00 ( 0.00%) 11.00 ( 8.33%) Success 3 Min 75.00 ( 0.00%) 74.00 ( 1.33%) Success 3 Mean 75.60 ( 0.00%) 75.20 ( 0.53%) Success 3 Max 77.00 ( 0.00%) 76.00 ( 0.00%) User 3344.73 3246.04 System 1194.24 1172.29 Elapsed 1838.04 1836.76 4.5-rc1+before 4.5-rc1+after -direct -direct Direct pages scanned 125146 120966 Kswapd pages scanned 2119757 2135012 Kswapd pages reclaimed 2073183 2108388 Direct pages reclaimed 124909 120577 Percentage direct scans 5% 5% THP fault alloc 599 652 THP collapse alloc 323 354 THP splits 0 0 THP fault fallback 806 793 THP collapse fail 17 16 Compaction stalls 2457 2025 Compaction success 906 518 Compaction failures 1551 1507 Page migrate success 2031423 2360608 Page migrate failure 32845 40852 Compaction pages isolated 4129761 4802025 Compaction migrate scanned 11996712 21750613 Compaction free scanned 214970969 344372001 Compaction cost 2271 2694 In this scenario, this patch doesn't change the overall success rate as direct compaction already tries all it can. There's however significant reduction in direct compaction stalls (that is, the number of allocations that went into direct compaction). The number of successes (i.e. direct compaction stalls that ended up with successful allocation) is reduced by the same number. This means the offload to kcompactd is working as expected, and direct compaction is reduced either due to detecting contention, or compaction deferred by kcompactd. In the previous version of this patchset there was some apparent reduction of success rate, but the changes in this version (such as using sync compaction only), new baseline kernel, and/or averaging results from 5 executions (my bet), made this go away. Ftrace-based stats seem to roughly agree: Time kswapd awake 2532984 2326824 Time kcompactd awake 0 257916 Time direct compacting 864839 735130 Time kswapd compacting 0 0 Time kcompactd compacting 0 257585 Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Rik van Riel <riel@redhat.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Rientjes <rientjes@google.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-17 21:18:15 +00:00
bool direct_compaction; /* False from kcompactd or /proc/... */
mm: proactive compaction For some applications, we need to allocate almost all memory as hugepages. However, on a running system, higher-order allocations can fail if the memory is fragmented. Linux kernel currently does on-demand compaction as we request more hugepages, but this style of compaction incurs very high latency. Experiments with one-time full memory compaction (followed by hugepage allocations) show that kernel is able to restore a highly fragmented memory state to a fairly compacted memory state within <1 sec for a 32G system. Such data suggests that a more proactive compaction can help us allocate a large fraction of memory as hugepages keeping allocation latencies low. For a more proactive compaction, the approach taken here is to define a new sysctl called 'vm.compaction_proactiveness' which dictates bounds for external fragmentation which kcompactd tries to maintain. The tunable takes a value in range [0, 100], with a default of 20. Note that a previous version of this patch [1] was found to introduce too many tunables (per-order extfrag{low, high}), but this one reduces them to just one sysctl. Also, the new tunable is an opaque value instead of asking for specific bounds of "external fragmentation", which would have been difficult to estimate. The internal interpretation of this opaque value allows for future fine-tuning. Currently, we use a simple translation from this tunable to [low, high] "fragmentation score" thresholds (low=100-proactiveness, high=low+10%). The score for a node is defined as weighted mean of per-zone external fragmentation. A zone's present_pages determines its weight. To periodically check per-node score, we reuse per-node kcompactd threads, which are woken up every 500 milliseconds to check the same. If a node's score exceeds its high threshold (as derived from user-provided proactiveness value), proactive compaction is started until its score reaches its low threshold value. By default, proactiveness is set to 20, which implies threshold values of low=80 and high=90. This patch is largely based on ideas from Michal Hocko [2]. See also the LWN article [3]. Performance data ================ System: x64_64, 1T RAM, 80 CPU threads. Kernel: 5.6.0-rc3 + this patch echo madvise | sudo tee /sys/kernel/mm/transparent_hugepage/enabled echo madvise | sudo tee /sys/kernel/mm/transparent_hugepage/defrag Before starting the driver, the system was fragmented from a userspace program that allocates all memory and then for each 2M aligned section, frees 3/4 of base pages using munmap. The workload is mainly anonymous userspace pages, which are easy to move around. I intentionally avoided unmovable pages in this test to see how much latency we incur when hugepage allocations hit direct compaction. 1. Kernel hugepage allocation latencies With the system in such a fragmented state, a kernel driver then allocates as many hugepages as possible and measures allocation latency: (all latency values are in microseconds) - With vanilla 5.6.0-rc3 percentile latency –––––––––– ––––––– 5 7894 10 9496 25 12561 30 15295 40 18244 50 21229 60 27556 75 30147 80 31047 90 32859 95 33799 Total 2M hugepages allocated = 383859 (749G worth of hugepages out of 762G total free => 98% of free memory could be allocated as hugepages) - With 5.6.0-rc3 + this patch, with proactiveness=20 sysctl -w vm.compaction_proactiveness=20 percentile latency –––––––––– ––––––– 5 2 10 2 25 3 30 3 40 3 50 4 60 4 75 4 80 4 90 5 95 429 Total 2M hugepages allocated = 384105 (750G worth of hugepages out of 762G total free => 98% of free memory could be allocated as hugepages) 2. JAVA heap allocation In this test, we first fragment memory using the same method as for (1). Then, we start a Java process with a heap size set to 700G and request the heap to be allocated with THP hugepages. We also set THP to madvise to allow hugepage backing of this heap. /usr/bin/time java -Xms700G -Xmx700G -XX:+UseTransparentHugePages -XX:+AlwaysPreTouch The above command allocates 700G of Java heap using hugepages. - With vanilla 5.6.0-rc3 17.39user 1666.48system 27:37.89elapsed - With 5.6.0-rc3 + this patch, with proactiveness=20 8.35user 194.58system 3:19.62elapsed Elapsed time remains around 3:15, as proactiveness is further increased. Note that proactive compaction happens throughout the runtime of these workloads. The situation of one-time compaction, sufficient to supply hugepages for following allocation stream, can probably happen for more extreme proactiveness values, like 80 or 90. In the above Java workload, proactiveness is set to 20. The test starts with a node's score of 80 or higher, depending on the delay between the fragmentation step and starting the benchmark, which gives more-or-less time for the initial round of compaction. As t he benchmark consumes hugepages, node's score quickly rises above the high threshold (90) and proactive compaction starts again, which brings down the score to the low threshold level (80). Repeat. bpftrace also confirms proactive compaction running 20+ times during the runtime of this Java benchmark. kcompactd threads consume 100% of one of the CPUs while it tries to bring a node's score within thresholds. Backoff behavior ================ Above workloads produce a memory state which is easy to compact. However, if memory is filled with unmovable pages, proactive compaction should essentially back off. To test this aspect: - Created a kernel driver that allocates almost all memory as hugepages followed by freeing first 3/4 of each hugepage. - Set proactiveness=40 - Note that proactive_compact_node() is deferred maximum number of times with HPAGE_FRAG_CHECK_INTERVAL_MSEC of wait between each check (=> ~30 seconds between retries). [1] https://patchwork.kernel.org/patch/11098289/ [2] https://lore.kernel.org/linux-mm/20161230131412.GI13301@dhcp22.suse.cz/ [3] https://lwn.net/Articles/817905/ Signed-off-by: Nitin Gupta <nigupta@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Oleksandr Natalenko <oleksandr@redhat.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Khalid Aziz <khalid.aziz@oracle.com> Reviewed-by: Oleksandr Natalenko <oleksandr@redhat.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Khalid Aziz <khalid.aziz@oracle.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: David Rientjes <rientjes@google.com> Cc: Nitin Gupta <ngupta@nitingupta.dev> Cc: Oleksandr Natalenko <oleksandr@redhat.com> Link: http://lkml.kernel.org/r/20200616204527.19185-1-nigupta@nvidia.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 01:31:00 +00:00
bool proactive_compaction; /* kcompactd proactive compaction */
mm, compaction: make whole_zone flag ignore cached scanner positions Patch series "make direct compaction more deterministic") This is mostly a followup to Michal's oom detection rework, which highlighted the need for direct compaction to provide better feedback in reclaim/compaction loop, so that it can reliably recognize when compaction cannot make further progress, and allocation should invoke OOM killer or fail. We've discussed this at LSF/MM [1] where I proposed expanding the async/sync migration mode used in compaction to more general "priorities". This patchset adds one new priority that just overrides all the heuristics and makes compaction fully scan all zones. I don't currently think that we need more fine-grained priorities, but we'll see. Other than that there's some smaller fixes and cleanups, mainly related to the THP-specific hacks. I've tested this with stress-highalloc in GFP_KERNEL order-4 and THP-like order-9 scenarios. There's some improvement for compaction stats for the order-4, which is likely due to the better watermarks handling. In the previous version I reported mostly noise wrt compaction stats, and decreased direct reclaim - now the reclaim is without difference. I believe this is due to the less aggressive compaction priority increase in patch 6. "before" is a mmotm tree prior to 4.7 release plus the first part of the series that was sent and merged separately before after order-4: Compaction stalls 27216 30759 Compaction success 19598 25475 Compaction failures 7617 5283 Page migrate success 370510 464919 Page migrate failure 25712 27987 Compaction pages isolated 849601 1041581 Compaction migrate scanned 143146541 101084990 Compaction free scanned 208355124 144863510 Compaction cost 1403 1210 order-9: Compaction stalls 7311 7401 Compaction success 1634 1683 Compaction failures 5677 5718 Page migrate success 194657 183988 Page migrate failure 4753 4170 Compaction pages isolated 498790 456130 Compaction migrate scanned 565371 524174 Compaction free scanned 4230296 4250744 Compaction cost 215 203 [1] https://lwn.net/Articles/684611/ This patch (of 11): A recent patch has added whole_zone flag that compaction sets when scanning starts from the zone boundary, in order to report that zone has been fully scanned in one attempt. For allocations that want to try really hard or cannot fail, we will want to introduce a mode where scanning whole zone is guaranteed regardless of the cached positions. This patch reuses the whole_zone flag in a way that if it's already passed true to compaction, the cached scanner positions are ignored. Employing this flag during reclaim/compaction loop will be done in the next patch. This patch however converts compaction invoked from userspace via procfs to use this flag. Before this patch, the cached positions were first reset to zone boundaries and then read back from struct zone, so there was a window where a parallel compaction could replace the reset values, making the manual compaction less effective. Using the flag instead of performing reset is more robust. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/20160810091226.6709-2-vbabka@suse.cz Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Tested-by: Lorenzo Stoakes <lstoakes@gmail.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: David Rientjes <rientjes@google.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-07 23:57:35 +00:00
bool whole_zone; /* Whole zone should/has been scanned */
bool contended; /* Signal lock contention */
mm, compaction: rename compact_control->rescan to finish_pageblock Patch series "Fix excessive CPU usage during compaction". Commit 7efc3b726103 ("mm/compaction: fix set skip in fast_find_migrateblock") fixed a problem where pageblocks found by fast_find_migrateblock() were ignored. Unfortunately there were numerous bug reports complaining about high CPU usage and massive stalls once 6.1 was released. Due to the severity, the patch was reverted by Vlastimil as a short-term fix[1] to -stable. The underlying problem for each of the bugs is suspected to be the repeated scanning of the same pageblocks. This series should guarantee forward progress even with commit 7efc3b726103. More information is in the changelog for patch 4. [1] http://lore.kernel.org/r/20230113173345.9692-1-vbabka@suse.cz This patch (of 4): The rescan field was not well named albeit accurate at the time. Rename the field to finish_pageblock to indicate that the remainder of the pageblock should be scanned regardless of COMPACT_CLUSTER_MAX. The intent is that pageblocks with transient failures get marked for skipping to avoid revisiting the same pageblock. Link: https://lkml.kernel.org/r/20230125134434.18017-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Cc: Chuyi Zhou <zhouchuyi@bytedance.com> Cc: Jiri Slaby <jirislaby@kernel.org> Cc: Maxim Levitsky <mlevitsk@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Pedro Falcato <pedro.falcato@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-01-25 13:44:31 +00:00
bool finish_pageblock; /* Scan the remainder of a pageblock. Used
* when there are potentially transient
* isolation or migration failures to
* ensure forward progress.
*/
bool alloc_contig; /* alloc_contig_range allocation */
};
mm, compaction: capture a page under direct compaction Compaction is inherently race-prone as a suitable page freed during compaction can be allocated by any parallel task. This patch uses a capture_control structure to isolate a page immediately when it is freed by a direct compactor in the slow path of the page allocator. The intent is to avoid redundant scanning. 5.0.0-rc1 5.0.0-rc1 selective-v3r17 capture-v3r19 Amean fault-both-1 0.00 ( 0.00%) 0.00 * 0.00%* Amean fault-both-3 2582.11 ( 0.00%) 2563.68 ( 0.71%) Amean fault-both-5 4500.26 ( 0.00%) 4233.52 ( 5.93%) Amean fault-both-7 5819.53 ( 0.00%) 6333.65 ( -8.83%) Amean fault-both-12 9321.18 ( 0.00%) 9759.38 ( -4.70%) Amean fault-both-18 9782.76 ( 0.00%) 10338.76 ( -5.68%) Amean fault-both-24 15272.81 ( 0.00%) 13379.55 * 12.40%* Amean fault-both-30 15121.34 ( 0.00%) 16158.25 ( -6.86%) Amean fault-both-32 18466.67 ( 0.00%) 18971.21 ( -2.73%) Latency is only moderately affected but the devil is in the details. A closer examination indicates that base page fault latency is reduced but latency of huge pages is increased as it takes creater care to succeed. Part of the "problem" is that allocation success rates are close to 100% even when under pressure and compaction gets harder 5.0.0-rc1 5.0.0-rc1 selective-v3r17 capture-v3r19 Percentage huge-3 96.70 ( 0.00%) 98.23 ( 1.58%) Percentage huge-5 96.99 ( 0.00%) 95.30 ( -1.75%) Percentage huge-7 94.19 ( 0.00%) 97.24 ( 3.24%) Percentage huge-12 94.95 ( 0.00%) 97.35 ( 2.53%) Percentage huge-18 96.74 ( 0.00%) 97.30 ( 0.58%) Percentage huge-24 97.07 ( 0.00%) 97.55 ( 0.50%) Percentage huge-30 95.69 ( 0.00%) 98.50 ( 2.95%) Percentage huge-32 96.70 ( 0.00%) 99.27 ( 2.65%) And scan rates are reduced as expected by 6% for the migration scanner and 29% for the free scanner indicating that there is less redundant work. Compaction migrate scanned 20815362 19573286 Compaction free scanned 16352612 11510663 [mgorman@techsingularity.net: remove redundant check] Link: http://lkml.kernel.org/r/20190201143853.GH9565@techsingularity.net Link: http://lkml.kernel.org/r/20190118175136.31341-23-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Dan Carpenter <dan.carpenter@oracle.com> Cc: David Rientjes <rientjes@google.com> Cc: YueHaibing <yuehaibing@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-05 23:45:41 +00:00
/*
* Used in direct compaction when a page should be taken from the freelists
* immediately when one is created during the free path.
*/
struct capture_control {
struct compact_control *cc;
struct page *page;
};
unsigned long
mm: compaction: cache if a pageblock was scanned and no pages were isolated When compaction was implemented it was known that scanning could potentially be excessive. The ideal was that a counter be maintained for each pageblock but maintaining this information would incur a severe penalty due to a shared writable cache line. It has reached the point where the scanning costs are a serious problem, particularly on long-lived systems where a large process starts and allocates a large number of THPs at the same time. Instead of using a shared counter, this patch adds another bit to the pageblock flags called PG_migrate_skip. If a pageblock is scanned by either migrate or free scanner and 0 pages were isolated, the pageblock is marked to be skipped in the future. When scanning, this bit is checked before any scanning takes place and the block skipped if set. The main difficulty with a patch like this is "when to ignore the cached information?" If it's ignored too often, the scanning rates will still be excessive. If the information is too stale then allocations will fail that might have otherwise succeeded. In this patch o CMA always ignores the information o If the migrate and free scanner meet then the cached information will be discarded if it's at least 5 seconds since the last time the cache was discarded o If there are a large number of allocation failures, discard the cache. The time-based heuristic is very clumsy but there are few choices for a better event. Depending solely on multiple allocation failures still allows excessive scanning when THP allocations are failing in quick succession due to memory pressure. Waiting until memory pressure is relieved would cause compaction to continually fail instead of using reclaim/compaction to try allocate the page. The time-based mechanism is clumsy but a better option is not obvious. Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Rik van Riel <riel@redhat.com> Cc: Richard Davies <richard@arachsys.com> Cc: Shaohua Li <shli@kernel.org> Cc: Avi Kivity <avi@redhat.com> Acked-by: Rafael Aquini <aquini@redhat.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Cc: Kyungmin Park <kyungmin.park@samsung.com> Cc: Mark Brown <broonie@opensource.wolfsonmicro.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-08 23:32:41 +00:00
isolate_freepages_range(struct compact_control *cc,
unsigned long start_pfn, unsigned long end_pfn);
int
mm, compaction: move pageblock checks up from isolate_migratepages_range() isolate_migratepages_range() is the main function of the compaction scanner, called either on a single pageblock by isolate_migratepages() during regular compaction, or on an arbitrary range by CMA's __alloc_contig_migrate_range(). It currently perfoms two pageblock-wide compaction suitability checks, and because of the CMA callpath, it tracks if it crossed a pageblock boundary in order to repeat those checks. However, closer inspection shows that those checks are always true for CMA: - isolation_suitable() is true because CMA sets cc->ignore_skip_hint to true - migrate_async_suitable() check is skipped because CMA uses sync compaction We can therefore move the compaction-specific checks to isolate_migratepages() and simplify isolate_migratepages_range(). Furthermore, we can mimic the freepage scanner family of functions, which has isolate_freepages_block() function called both by compaction from isolate_freepages() and by CMA from isolate_freepages_range(), where each use-case adds own specific glue code. This allows further code simplification. Thus, we rename isolate_migratepages_range() to isolate_migratepages_block() and limit its functionality to a single pageblock (or its subset). For CMA, a new different isolate_migratepages_range() is created as a CMA-specific wrapper for the _block() function. The checks specific to compaction are moved to isolate_migratepages(). As part of the unification of these two families of functions, we remove the redundant zone parameter where applicable, since zone pointer is already passed in cc->zone. Furthermore, going back to compact_zone() and compact_finished() when pageblock is found unsuitable (now by isolate_migratepages()) is wasteful - the checks are meant to skip pageblocks quickly. The patch therefore also introduces a simple loop into isolate_migratepages() so that it does not return immediately on failed pageblock checks, but keeps going until isolate_migratepages_range() gets called once. Similarily to isolate_freepages(), the function periodically checks if it needs to reschedule or abort async compaction. [iamjoonsoo.kim@lge.com: fix isolated page counting bug in compaction] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Cc: Minchan Kim <minchan@kernel.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Christoph Lameter <cl@linux.com> Cc: Rik van Riel <riel@redhat.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-09 22:27:09 +00:00
isolate_migratepages_range(struct compact_control *cc,
unsigned long low_pfn, unsigned long end_pfn);
int __alloc_contig_migrate_range(struct compact_control *cc,
unsigned long start, unsigned long end,
int migratetype);
/* Free whole pageblock and set its migration type to MIGRATE_CMA. */
void init_cma_reserved_pageblock(struct page *page);
#endif /* CONFIG_COMPACTION || CONFIG_CMA */
mm/compaction: enhance compaction finish condition Compaction has anti fragmentation algorithm. It is that freepage should be more than pageblock order to finish the compaction if we don't find any freepage in requested migratetype buddy list. This is for mitigating fragmentation, but, there is a lack of migratetype consideration and it is too excessive compared to page allocator's anti fragmentation algorithm. Not considering migratetype would cause premature finish of compaction. For example, if allocation request is for unmovable migratetype, freepage with CMA migratetype doesn't help that allocation and compaction should not be stopped. But, current logic regards this situation as compaction is no longer needed, so finish the compaction. Secondly, condition is too excessive compared to page allocator's logic. We can steal freepage from other migratetype and change pageblock migratetype on more relaxed conditions in page allocator. This is designed to prevent fragmentation and we can use it here. Imposing hard constraint only to the compaction doesn't help much in this case since page allocator would cause fragmentation again. To solve these problems, this patch borrows anti fragmentation logic from page allocator. It will reduce premature compaction finish in some cases and reduce excessive compaction work. stress-highalloc test in mmtests with non movable order 7 allocation shows considerable increase of compaction success rate. Compaction success rate (Compaction success * 100 / Compaction stalls, %) 31.82 : 42.20 I tested it on non-reboot 5 runs stress-highalloc benchmark and found that there is no more degradation on allocation success rate than before. That roughly means that this patch doesn't result in more fragmentations. Vlastimil suggests additional idea that we only test for fallbacks when migration scanner has scanned a whole pageblock. It looked good for fragmentation because chance of stealing increase due to making more free pages in certain pageblock. So, I tested it, but, it results in decreased compaction success rate, roughly 38.00. I guess the reason that if system is low memory condition, watermark check could be failed due to not enough order 0 free page and so, sometimes, we can't reach a fallback check although migrate_pfn is aligned to pageblock_nr_pages. I can insert code to cope with this situation but it makes code more complicated so I don't include his idea at this patch. [akpm@linux-foundation.org: fix CONFIG_CMA=n build] Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Mel Gorman <mgorman@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-14 22:45:21 +00:00
int find_suitable_fallback(struct free_area *area, unsigned int order,
int migratetype, bool only_stealable, bool *can_steal);
static inline bool free_area_empty(struct free_area *area, int migratetype)
{
return list_empty(&area->free_list[migratetype]);
}
mm: nommu: sort mm->mmap list properly When I was reading nommu code, I found that it handles the vma list/tree in an unusual way. IIUC, because there can be more than one identical/overrapped vmas in the list/tree, it sorts the tree more strictly and does a linear search on the tree. But it doesn't applied to the list (i.e. the list could be constructed in a different order than the tree so that we can't use the list when finding the first vma in that order). Since inserting/sorting a vma in the tree and link is done at the same time, we can easily construct both of them in the same order. And linear searching on the tree could be more costly than doing it on the list, it can be converted to use the list. Also, after the commit 297c5eee3724 ("mm: make the vma list be doubly linked") made the list be doubly linked, there were a couple of code need to be fixed to construct the list properly. Patch 1/6 is a preparation. It maintains the list sorted same as the tree and construct doubly-linked list properly. Patch 2/6 is a simple optimization for the vma deletion. Patch 3/6 and 4/6 convert tree traversal to list traversal and the rest are simple fixes and cleanups. This patch: @vma added into @mm should be sorted by start addr, end addr and VMA struct addr in that order because we may get identical VMAs in the @mm. However this was true only for the rbtree, not for the list. This patch fixes this by remembering 'rb_prev' during the tree traversal like find_vma_prepare() does and linking the @vma via __vma_link_list(). After this patch, we can iterate the whole VMAs in correct order simply by using @mm->mmap list. [akpm@linux-foundation.org: avoid duplicating __vma_link_list()] Signed-off-by: Namhyung Kim <namhyung@gmail.com> Acked-by: Greg Ungerer <gerg@uclinux.org> Cc: David Howells <dhowells@redhat.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 00:11:22 +00:00
/* mm/util.c */
struct anon_vma *folio_anon_vma(struct folio *folio);
mm: nommu: sort mm->mmap list properly When I was reading nommu code, I found that it handles the vma list/tree in an unusual way. IIUC, because there can be more than one identical/overrapped vmas in the list/tree, it sorts the tree more strictly and does a linear search on the tree. But it doesn't applied to the list (i.e. the list could be constructed in a different order than the tree so that we can't use the list when finding the first vma in that order). Since inserting/sorting a vma in the tree and link is done at the same time, we can easily construct both of them in the same order. And linear searching on the tree could be more costly than doing it on the list, it can be converted to use the list. Also, after the commit 297c5eee3724 ("mm: make the vma list be doubly linked") made the list be doubly linked, there were a couple of code need to be fixed to construct the list properly. Patch 1/6 is a preparation. It maintains the list sorted same as the tree and construct doubly-linked list properly. Patch 2/6 is a simple optimization for the vma deletion. Patch 3/6 and 4/6 convert tree traversal to list traversal and the rest are simple fixes and cleanups. This patch: @vma added into @mm should be sorted by start addr, end addr and VMA struct addr in that order because we may get identical VMAs in the @mm. However this was true only for the rbtree, not for the list. This patch fixes this by remembering 'rb_prev' during the tree traversal like find_vma_prepare() does and linking the @vma via __vma_link_list(). After this patch, we can iterate the whole VMAs in correct order simply by using @mm->mmap list. [akpm@linux-foundation.org: avoid duplicating __vma_link_list()] Signed-off-by: Namhyung Kim <namhyung@gmail.com> Acked-by: Greg Ungerer <gerg@uclinux.org> Cc: David Howells <dhowells@redhat.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 00:11:22 +00:00
#ifdef CONFIG_MMU
void unmap_mapping_folio(struct folio *folio);
extern long populate_vma_page_range(struct vm_area_struct *vma,
mm: make variable names for populate_vma_page_range() consistent Patch series "mm/madvise: introduce MADV_POPULATE_(READ|WRITE) to prefault page tables", v2. Excessive details on MADV_POPULATE_(READ|WRITE) can be found in patch #2. This patch (of 5): Let's make the variable names in the function declaration match the variable names used in the definition. Link: https://lkml.kernel.org/r/20210419135443.12822-1-david@redhat.com Link: https://lkml.kernel.org/r/20210419135443.12822-2-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Michal Hocko <mhocko@suse.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Peter Xu <peterx@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Chris Zankel <chris@zankel.net> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Helge Deller <deller@gmx.de> Cc: Hugh Dickins <hughd@google.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> Cc: Jann Horn <jannh@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Ram Pai <linuxram@us.ibm.com> Cc: Richard Henderson <rth@twiddle.net> Cc: Rik van Riel <riel@surriel.com> Cc: Rolf Eike Beer <eike-kernel@sf-tec.de> Cc: Shuah Khan <shuah@kernel.org> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 01:52:23 +00:00
unsigned long start, unsigned long end, int *locked);
mm/madvise: make MADV_POPULATE_(READ|WRITE) handle VM_FAULT_RETRY properly Darrick reports that in some cases where pread() would fail with -EIO and mmap()+access would generate a SIGBUS signal, MADV_POPULATE_READ / MADV_POPULATE_WRITE will keep retrying forever and not fail with -EFAULT. While the madvise() call can be interrupted by a signal, this is not the desired behavior. MADV_POPULATE_READ / MADV_POPULATE_WRITE should behave like page faults in that case: fail and not retry forever. A reproducer can be found at [1]. The reason is that __get_user_pages(), as called by faultin_vma_page_range(), will not handle VM_FAULT_RETRY in a proper way: it will simply return 0 when VM_FAULT_RETRY happened, making madvise_populate()->faultin_vma_page_range() retry again and again, never setting FOLL_TRIED->FAULT_FLAG_TRIED for __get_user_pages(). __get_user_pages_locked() does what we want, but duplicating that logic in faultin_vma_page_range() feels wrong. So let's use __get_user_pages_locked() instead, that will detect VM_FAULT_RETRY and set FOLL_TRIED when retrying, making the fault handler return VM_FAULT_SIGBUS (VM_FAULT_ERROR) at some point, propagating -EFAULT from faultin_page() to __get_user_pages(), all the way to madvise_populate(). But, there is an issue: __get_user_pages_locked() will end up re-taking the MM lock and then __get_user_pages() will do another VMA lookup. In the meantime, the VMA layout could have changed and we'd fail with different error codes than we'd want to. As __get_user_pages() will currently do a new VMA lookup either way, let it do the VMA handling in a different way, controlled by a new FOLL_MADV_POPULATE flag, effectively moving these checks from madvise_populate() + faultin_page_range() in there. With this change, Darricks reproducer properly fails with -EFAULT, as documented for MADV_POPULATE_READ / MADV_POPULATE_WRITE. [1] https://lore.kernel.org/all/20240313171936.GN1927156@frogsfrogsfrogs/ Link: https://lkml.kernel.org/r/20240314161300.382526-1-david@redhat.com Link: https://lkml.kernel.org/r/20240314161300.382526-2-david@redhat.com Fixes: 4ca9b3859dac ("mm/madvise: introduce MADV_POPULATE_(READ|WRITE) to prefault page tables") Signed-off-by: David Hildenbrand <david@redhat.com> Reported-by: Darrick J. Wong <djwong@kernel.org> Closes: https://lore.kernel.org/all/20240311223815.GW1927156@frogsfrogsfrogs/ Cc: Darrick J. Wong <djwong@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-03-14 16:12:59 +00:00
extern long faultin_page_range(struct mm_struct *mm, unsigned long start,
unsigned long end, bool write, int *locked);
extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags,
unsigned long bytes);
mm: add functions folio_in_range() and folio_within_vma() Patch series "support large folio for mlock", v3. Yu mentioned at [1] about the mlock() can't be applied to large folio. I leant the related code and here is my understanding: - For RLIMIT_MEMLOCK related, there is no problem. Because the RLIMIT_MEMLOCK statistics is not related underneath page. That means underneath page mlock or munlock doesn't impact the RLIMIT_MEMLOCK statistics collection which is always correct. - For keeping the page in RAM, there is no problem either. At least, during try_to_unmap_one(), once detect the VMA has VM_LOCKED bit set in vm_flags, the folio will be kept whatever the folio is mlocked or not. So the function of mlock for large folio works. But it's not optimized because the page reclaim needs scan these large folio and may split them. This series identified the large folio for mlock to four types: - The large folio is in VM_LOCKED range and fully mapped to the range - The large folio is in the VM_LOCKED range but not fully mapped to the range - The large folio cross VM_LOCKED VMA boundary - The large folio cross last level page table boundary For the first type, we mlock large folio so page reclaim will skip it. For the second/third type, we don't mlock large folio. As the pages not mapped to VM_LOACKED range are mapped to none VM_LOCKED range, if system is in memory pressure situation, the large folio can be picked by page reclaim and split. Then the pages not mapped to VM_LOCKED range can be reclaimed. For the fourth type, we don't mlock large folio because locking one page table lock can't prevent the part in another last level page table being unmapped. Thanks to Ryan for pointing this out. To check whether the folio is fully mapped to the range, PTEs needs be checked to see whether the page of folio is associated. Which needs take page table lock and is heavy operation. So far, the only place needs this check is madvise and page reclaim. These functions already have their own PTE iterator. patch1 introduce API to check whether large folio is in VMA range. patch2 make page reclaim/mlock_vma_folio/munlock_vma_folio support large folio mlock/munlock. patch3 make mlock/munlock syscall support large folio. Yu also mentioned a race which can make folio unevictable after munlock during RFC v2 discussion [3]: We decided that race issue didn't block this series based on: - That race issue was not introduced by this series - We had a looks-ok fix for that race issue. Need to wait for mlock_count fixing patch as Yosry Ahmed suggested [4] [1] https://lore.kernel.org/linux-mm/CAOUHufbtNPkdktjt_5qM45GegVO-rCFOMkSh0HQminQ12zsV8Q@mail.gmail.com/ [2] https://lore.kernel.org/linux-mm/20230809061105.3369958-1-fengwei.yin@intel.com/ [3] https://lore.kernel.org/linux-mm/CAOUHufZ6=9P_=CAOQyw0xw-3q707q-1FVV09dBNDC-hpcpj2Pg@mail.gmail.com/ This patch (of 3): folio_in_range() will be used to check whether the folio is mapped to specific VMA and whether the mapping address of folio is in the range. Also a helper function folio_within_vma() to check whether folio is in the range of vma based on folio_in_range(). Link: https://lkml.kernel.org/r/20230918073318.1181104-1-fengwei.yin@intel.com Link: https://lkml.kernel.org/r/20230918073318.1181104-2-fengwei.yin@intel.com Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-18 07:33:16 +00:00
/*
* NOTE: This function can't tell whether the folio is "fully mapped" in the
* range.
* "fully mapped" means all the pages of folio is associated with the page
* table of range while this function just check whether the folio range is
* within the range [start, end). Function caller needs to do page table
mm: add functions folio_in_range() and folio_within_vma() Patch series "support large folio for mlock", v3. Yu mentioned at [1] about the mlock() can't be applied to large folio. I leant the related code and here is my understanding: - For RLIMIT_MEMLOCK related, there is no problem. Because the RLIMIT_MEMLOCK statistics is not related underneath page. That means underneath page mlock or munlock doesn't impact the RLIMIT_MEMLOCK statistics collection which is always correct. - For keeping the page in RAM, there is no problem either. At least, during try_to_unmap_one(), once detect the VMA has VM_LOCKED bit set in vm_flags, the folio will be kept whatever the folio is mlocked or not. So the function of mlock for large folio works. But it's not optimized because the page reclaim needs scan these large folio and may split them. This series identified the large folio for mlock to four types: - The large folio is in VM_LOCKED range and fully mapped to the range - The large folio is in the VM_LOCKED range but not fully mapped to the range - The large folio cross VM_LOCKED VMA boundary - The large folio cross last level page table boundary For the first type, we mlock large folio so page reclaim will skip it. For the second/third type, we don't mlock large folio. As the pages not mapped to VM_LOACKED range are mapped to none VM_LOCKED range, if system is in memory pressure situation, the large folio can be picked by page reclaim and split. Then the pages not mapped to VM_LOCKED range can be reclaimed. For the fourth type, we don't mlock large folio because locking one page table lock can't prevent the part in another last level page table being unmapped. Thanks to Ryan for pointing this out. To check whether the folio is fully mapped to the range, PTEs needs be checked to see whether the page of folio is associated. Which needs take page table lock and is heavy operation. So far, the only place needs this check is madvise and page reclaim. These functions already have their own PTE iterator. patch1 introduce API to check whether large folio is in VMA range. patch2 make page reclaim/mlock_vma_folio/munlock_vma_folio support large folio mlock/munlock. patch3 make mlock/munlock syscall support large folio. Yu also mentioned a race which can make folio unevictable after munlock during RFC v2 discussion [3]: We decided that race issue didn't block this series based on: - That race issue was not introduced by this series - We had a looks-ok fix for that race issue. Need to wait for mlock_count fixing patch as Yosry Ahmed suggested [4] [1] https://lore.kernel.org/linux-mm/CAOUHufbtNPkdktjt_5qM45GegVO-rCFOMkSh0HQminQ12zsV8Q@mail.gmail.com/ [2] https://lore.kernel.org/linux-mm/20230809061105.3369958-1-fengwei.yin@intel.com/ [3] https://lore.kernel.org/linux-mm/CAOUHufZ6=9P_=CAOQyw0xw-3q707q-1FVV09dBNDC-hpcpj2Pg@mail.gmail.com/ This patch (of 3): folio_in_range() will be used to check whether the folio is mapped to specific VMA and whether the mapping address of folio is in the range. Also a helper function folio_within_vma() to check whether folio is in the range of vma based on folio_in_range(). Link: https://lkml.kernel.org/r/20230918073318.1181104-1-fengwei.yin@intel.com Link: https://lkml.kernel.org/r/20230918073318.1181104-2-fengwei.yin@intel.com Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-18 07:33:16 +00:00
* check if it cares about the page table association.
*
* Typical usage (like mlock or madvise) is:
* Caller knows at least 1 page of folio is associated with page table of VMA
* and the range [start, end) is intersect with the VMA range. Caller wants
* to know whether the folio is fully associated with the range. It calls
* this function to check whether the folio is in the range first. Then checks
* the page table to know whether the folio is fully mapped to the range.
*/
static inline bool
folio_within_range(struct folio *folio, struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
pgoff_t pgoff, addr;
unsigned long vma_pglen = vma_pages(vma);
mm: add functions folio_in_range() and folio_within_vma() Patch series "support large folio for mlock", v3. Yu mentioned at [1] about the mlock() can't be applied to large folio. I leant the related code and here is my understanding: - For RLIMIT_MEMLOCK related, there is no problem. Because the RLIMIT_MEMLOCK statistics is not related underneath page. That means underneath page mlock or munlock doesn't impact the RLIMIT_MEMLOCK statistics collection which is always correct. - For keeping the page in RAM, there is no problem either. At least, during try_to_unmap_one(), once detect the VMA has VM_LOCKED bit set in vm_flags, the folio will be kept whatever the folio is mlocked or not. So the function of mlock for large folio works. But it's not optimized because the page reclaim needs scan these large folio and may split them. This series identified the large folio for mlock to four types: - The large folio is in VM_LOCKED range and fully mapped to the range - The large folio is in the VM_LOCKED range but not fully mapped to the range - The large folio cross VM_LOCKED VMA boundary - The large folio cross last level page table boundary For the first type, we mlock large folio so page reclaim will skip it. For the second/third type, we don't mlock large folio. As the pages not mapped to VM_LOACKED range are mapped to none VM_LOCKED range, if system is in memory pressure situation, the large folio can be picked by page reclaim and split. Then the pages not mapped to VM_LOCKED range can be reclaimed. For the fourth type, we don't mlock large folio because locking one page table lock can't prevent the part in another last level page table being unmapped. Thanks to Ryan for pointing this out. To check whether the folio is fully mapped to the range, PTEs needs be checked to see whether the page of folio is associated. Which needs take page table lock and is heavy operation. So far, the only place needs this check is madvise and page reclaim. These functions already have their own PTE iterator. patch1 introduce API to check whether large folio is in VMA range. patch2 make page reclaim/mlock_vma_folio/munlock_vma_folio support large folio mlock/munlock. patch3 make mlock/munlock syscall support large folio. Yu also mentioned a race which can make folio unevictable after munlock during RFC v2 discussion [3]: We decided that race issue didn't block this series based on: - That race issue was not introduced by this series - We had a looks-ok fix for that race issue. Need to wait for mlock_count fixing patch as Yosry Ahmed suggested [4] [1] https://lore.kernel.org/linux-mm/CAOUHufbtNPkdktjt_5qM45GegVO-rCFOMkSh0HQminQ12zsV8Q@mail.gmail.com/ [2] https://lore.kernel.org/linux-mm/20230809061105.3369958-1-fengwei.yin@intel.com/ [3] https://lore.kernel.org/linux-mm/CAOUHufZ6=9P_=CAOQyw0xw-3q707q-1FVV09dBNDC-hpcpj2Pg@mail.gmail.com/ This patch (of 3): folio_in_range() will be used to check whether the folio is mapped to specific VMA and whether the mapping address of folio is in the range. Also a helper function folio_within_vma() to check whether folio is in the range of vma based on folio_in_range(). Link: https://lkml.kernel.org/r/20230918073318.1181104-1-fengwei.yin@intel.com Link: https://lkml.kernel.org/r/20230918073318.1181104-2-fengwei.yin@intel.com Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-18 07:33:16 +00:00
VM_WARN_ON_FOLIO(folio_test_ksm(folio), folio);
if (start > end)
return false;
if (start < vma->vm_start)
start = vma->vm_start;
if (end > vma->vm_end)
end = vma->vm_end;
pgoff = folio_pgoff(folio);
/* if folio start address is not in vma range */
if (!in_range(pgoff, vma->vm_pgoff, vma_pglen))
return false;
addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
return !(addr < start || end - addr < folio_size(folio));
}
static inline bool
folio_within_vma(struct folio *folio, struct vm_area_struct *vma)
{
return folio_within_range(folio, vma, vma->vm_start, vma->vm_end);
}
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:44 +00:00
/*
* mlock_vma_folio() and munlock_vma_folio():
mm/munlock: rmap call mlock_vma_page() munlock_vma_page() Add vma argument to mlock_vma_page() and munlock_vma_page(), make them inline functions which check (vma->vm_flags & VM_LOCKED) before calling mlock_page() and munlock_page() in mm/mlock.c. Add bool compound to mlock_vma_page() and munlock_vma_page(): this is because we have understandable difficulty in accounting pte maps of THPs, and if passed a PageHead page, mlock_page() and munlock_page() cannot tell whether it's a pmd map to be counted or a pte map to be ignored. Add vma arg to page_add_file_rmap() and page_remove_rmap(), like the others, and use that to call mlock_vma_page() at the end of the page adds, and munlock_vma_page() at the end of page_remove_rmap() (end or beginning? unimportant, but end was easier for assertions in testing). No page lock is required (although almost all adds happen to hold it): delete the "Serialize with page migration" BUG_ON(!PageLocked(page))s. Certainly page lock did serialize with page migration, but I'm having difficulty explaining why that was ever important. Mlock accounting on THPs has been hard to define, differed between anon and file, involved PageDoubleMap in some places and not others, required clear_page_mlock() at some points. Keep it simple now: just count the pmds and ignore the ptes, there is no reason for ptes to undo pmd mlocks. page_add_new_anon_rmap() callers unchanged: they have long been calling lru_cache_add_inactive_or_unevictable(), which does its own VM_LOCKED handling (it also checks for not VM_SPECIAL: I think that's overcautious, and inconsistent with other checks, that mmap_region() already prevents VM_LOCKED on VM_SPECIAL; but haven't quite convinced myself to change it). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2022-02-15 02:26:39 +00:00
* should be called with vma's mmap_lock held for read or write,
* under page table lock for the pte/pmd being added or removed.
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:44 +00:00
*
* mlock is usually called at the end of folio_add_*_rmap_*(), munlock at
* the end of folio_remove_rmap_*(); but new anon folios are managed by
* folio_add_lru_vma() calling mlock_new_folio().
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:44 +00:00
*/
void mlock_folio(struct folio *folio);
static inline void mlock_vma_folio(struct folio *folio,
mm: handle large folio when large folio in VM_LOCKED VMA range If large folio is in the range of VM_LOCKED VMA, it should be mlocked to avoid being picked by page reclaim. Which may split the large folio and then mlock each pages again. Mlock this kind of large folio to prevent them being picked by page reclaim. For the large folio which cross the boundary of VM_LOCKED VMA or not fully mapped to VM_LOCKED VMA, we'd better not to mlock it. So if the system is under memory pressure, this kind of large folio will be split and the pages ouf of VM_LOCKED VMA can be reclaimed. Ideally, for large folio, we should mlock it when the large folio is fully mapped to VMA and munlock it if any page are unmampped from VMA. But it's not easy to detect whether the large folio is fully mapped to VMA in some cases (like add/remove rmap). So we update mlock_vma_folio() and munlock_vma_folio() to mlock/munlock the folio according to vma->vm_flags. Let caller to decide whether they should call these two functions. For add rmap, only mlock normal 4K folio and postpone large folio handling to page reclaim phase. It is possible to reuse page table iterator to detect whether folio is fully mapped or not during page reclaim phase. For remove rmap, invoke munlock_vma_folio() to munlock folio unconditionly because rmap makes folio not fully mapped to VMA. Link: https://lkml.kernel.org/r/20230918073318.1181104-3-fengwei.yin@intel.com Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-18 07:33:17 +00:00
struct vm_area_struct *vma)
mm/munlock: rmap call mlock_vma_page() munlock_vma_page() Add vma argument to mlock_vma_page() and munlock_vma_page(), make them inline functions which check (vma->vm_flags & VM_LOCKED) before calling mlock_page() and munlock_page() in mm/mlock.c. Add bool compound to mlock_vma_page() and munlock_vma_page(): this is because we have understandable difficulty in accounting pte maps of THPs, and if passed a PageHead page, mlock_page() and munlock_page() cannot tell whether it's a pmd map to be counted or a pte map to be ignored. Add vma arg to page_add_file_rmap() and page_remove_rmap(), like the others, and use that to call mlock_vma_page() at the end of the page adds, and munlock_vma_page() at the end of page_remove_rmap() (end or beginning? unimportant, but end was easier for assertions in testing). No page lock is required (although almost all adds happen to hold it): delete the "Serialize with page migration" BUG_ON(!PageLocked(page))s. Certainly page lock did serialize with page migration, but I'm having difficulty explaining why that was ever important. Mlock accounting on THPs has been hard to define, differed between anon and file, involved PageDoubleMap in some places and not others, required clear_page_mlock() at some points. Keep it simple now: just count the pmds and ignore the ptes, there is no reason for ptes to undo pmd mlocks. page_add_new_anon_rmap() callers unchanged: they have long been calling lru_cache_add_inactive_or_unevictable(), which does its own VM_LOCKED handling (it also checks for not VM_SPECIAL: I think that's overcautious, and inconsistent with other checks, that mmap_region() already prevents VM_LOCKED on VM_SPECIAL; but haven't quite convinced myself to change it). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2022-02-15 02:26:39 +00:00
{
/*
* The VM_SPECIAL check here serves two purposes.
* 1) VM_IO check prevents migration from double-counting during mlock.
* 2) Although mmap_region() and mlock_fixup() take care that VM_LOCKED
* is never left set on a VM_SPECIAL vma, there is an interval while
* file->f_op->mmap() is using vm_insert_page(s), when VM_LOCKED may
* still be set while VM_SPECIAL bits are added: so ignore it then.
*/
mm: handle large folio when large folio in VM_LOCKED VMA range If large folio is in the range of VM_LOCKED VMA, it should be mlocked to avoid being picked by page reclaim. Which may split the large folio and then mlock each pages again. Mlock this kind of large folio to prevent them being picked by page reclaim. For the large folio which cross the boundary of VM_LOCKED VMA or not fully mapped to VM_LOCKED VMA, we'd better not to mlock it. So if the system is under memory pressure, this kind of large folio will be split and the pages ouf of VM_LOCKED VMA can be reclaimed. Ideally, for large folio, we should mlock it when the large folio is fully mapped to VMA and munlock it if any page are unmampped from VMA. But it's not easy to detect whether the large folio is fully mapped to VMA in some cases (like add/remove rmap). So we update mlock_vma_folio() and munlock_vma_folio() to mlock/munlock the folio according to vma->vm_flags. Let caller to decide whether they should call these two functions. For add rmap, only mlock normal 4K folio and postpone large folio handling to page reclaim phase. It is possible to reuse page table iterator to detect whether folio is fully mapped or not during page reclaim phase. For remove rmap, invoke munlock_vma_folio() to munlock folio unconditionly because rmap makes folio not fully mapped to VMA. Link: https://lkml.kernel.org/r/20230918073318.1181104-3-fengwei.yin@intel.com Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-18 07:33:17 +00:00
if (unlikely((vma->vm_flags & (VM_LOCKED|VM_SPECIAL)) == VM_LOCKED))
mlock_folio(folio);
}
void munlock_folio(struct folio *folio);
static inline void munlock_vma_folio(struct folio *folio,
mm: handle large folio when large folio in VM_LOCKED VMA range If large folio is in the range of VM_LOCKED VMA, it should be mlocked to avoid being picked by page reclaim. Which may split the large folio and then mlock each pages again. Mlock this kind of large folio to prevent them being picked by page reclaim. For the large folio which cross the boundary of VM_LOCKED VMA or not fully mapped to VM_LOCKED VMA, we'd better not to mlock it. So if the system is under memory pressure, this kind of large folio will be split and the pages ouf of VM_LOCKED VMA can be reclaimed. Ideally, for large folio, we should mlock it when the large folio is fully mapped to VMA and munlock it if any page are unmampped from VMA. But it's not easy to detect whether the large folio is fully mapped to VMA in some cases (like add/remove rmap). So we update mlock_vma_folio() and munlock_vma_folio() to mlock/munlock the folio according to vma->vm_flags. Let caller to decide whether they should call these two functions. For add rmap, only mlock normal 4K folio and postpone large folio handling to page reclaim phase. It is possible to reuse page table iterator to detect whether folio is fully mapped or not during page reclaim phase. For remove rmap, invoke munlock_vma_folio() to munlock folio unconditionly because rmap makes folio not fully mapped to VMA. Link: https://lkml.kernel.org/r/20230918073318.1181104-3-fengwei.yin@intel.com Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-18 07:33:17 +00:00
struct vm_area_struct *vma)
mm/munlock: rmap call mlock_vma_page() munlock_vma_page() Add vma argument to mlock_vma_page() and munlock_vma_page(), make them inline functions which check (vma->vm_flags & VM_LOCKED) before calling mlock_page() and munlock_page() in mm/mlock.c. Add bool compound to mlock_vma_page() and munlock_vma_page(): this is because we have understandable difficulty in accounting pte maps of THPs, and if passed a PageHead page, mlock_page() and munlock_page() cannot tell whether it's a pmd map to be counted or a pte map to be ignored. Add vma arg to page_add_file_rmap() and page_remove_rmap(), like the others, and use that to call mlock_vma_page() at the end of the page adds, and munlock_vma_page() at the end of page_remove_rmap() (end or beginning? unimportant, but end was easier for assertions in testing). No page lock is required (although almost all adds happen to hold it): delete the "Serialize with page migration" BUG_ON(!PageLocked(page))s. Certainly page lock did serialize with page migration, but I'm having difficulty explaining why that was ever important. Mlock accounting on THPs has been hard to define, differed between anon and file, involved PageDoubleMap in some places and not others, required clear_page_mlock() at some points. Keep it simple now: just count the pmds and ignore the ptes, there is no reason for ptes to undo pmd mlocks. page_add_new_anon_rmap() callers unchanged: they have long been calling lru_cache_add_inactive_or_unevictable(), which does its own VM_LOCKED handling (it also checks for not VM_SPECIAL: I think that's overcautious, and inconsistent with other checks, that mmap_region() already prevents VM_LOCKED on VM_SPECIAL; but haven't quite convinced myself to change it). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2022-02-15 02:26:39 +00:00
{
mm: handle large folio when large folio in VM_LOCKED VMA range If large folio is in the range of VM_LOCKED VMA, it should be mlocked to avoid being picked by page reclaim. Which may split the large folio and then mlock each pages again. Mlock this kind of large folio to prevent them being picked by page reclaim. For the large folio which cross the boundary of VM_LOCKED VMA or not fully mapped to VM_LOCKED VMA, we'd better not to mlock it. So if the system is under memory pressure, this kind of large folio will be split and the pages ouf of VM_LOCKED VMA can be reclaimed. Ideally, for large folio, we should mlock it when the large folio is fully mapped to VMA and munlock it if any page are unmampped from VMA. But it's not easy to detect whether the large folio is fully mapped to VMA in some cases (like add/remove rmap). So we update mlock_vma_folio() and munlock_vma_folio() to mlock/munlock the folio according to vma->vm_flags. Let caller to decide whether they should call these two functions. For add rmap, only mlock normal 4K folio and postpone large folio handling to page reclaim phase. It is possible to reuse page table iterator to detect whether folio is fully mapped or not during page reclaim phase. For remove rmap, invoke munlock_vma_folio() to munlock folio unconditionly because rmap makes folio not fully mapped to VMA. Link: https://lkml.kernel.org/r/20230918073318.1181104-3-fengwei.yin@intel.com Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-18 07:33:17 +00:00
/*
* munlock if the function is called. Ideally, we should only
* do munlock if any page of folio is unmapped from VMA and
* cause folio not fully mapped to VMA.
*
* But it's not easy to confirm that's the situation. So we
* always munlock the folio and page reclaim will correct it
* if it's wrong.
*/
if (unlikely(vma->vm_flags & VM_LOCKED))
munlock_folio(folio);
mm/munlock: rmap call mlock_vma_page() munlock_vma_page() Add vma argument to mlock_vma_page() and munlock_vma_page(), make them inline functions which check (vma->vm_flags & VM_LOCKED) before calling mlock_page() and munlock_page() in mm/mlock.c. Add bool compound to mlock_vma_page() and munlock_vma_page(): this is because we have understandable difficulty in accounting pte maps of THPs, and if passed a PageHead page, mlock_page() and munlock_page() cannot tell whether it's a pmd map to be counted or a pte map to be ignored. Add vma arg to page_add_file_rmap() and page_remove_rmap(), like the others, and use that to call mlock_vma_page() at the end of the page adds, and munlock_vma_page() at the end of page_remove_rmap() (end or beginning? unimportant, but end was easier for assertions in testing). No page lock is required (although almost all adds happen to hold it): delete the "Serialize with page migration" BUG_ON(!PageLocked(page))s. Certainly page lock did serialize with page migration, but I'm having difficulty explaining why that was ever important. Mlock accounting on THPs has been hard to define, differed between anon and file, involved PageDoubleMap in some places and not others, required clear_page_mlock() at some points. Keep it simple now: just count the pmds and ignore the ptes, there is no reason for ptes to undo pmd mlocks. page_add_new_anon_rmap() callers unchanged: they have long been calling lru_cache_add_inactive_or_unevictable(), which does its own VM_LOCKED handling (it also checks for not VM_SPECIAL: I think that's overcautious, and inconsistent with other checks, that mmap_region() already prevents VM_LOCKED on VM_SPECIAL; but haven't quite convinced myself to change it). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2022-02-15 02:26:39 +00:00
}
void mlock_new_folio(struct folio *folio);
bool need_mlock_drain(int cpu);
void mlock_drain_local(void);
void mlock_drain_remote(int cpu);
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:44 +00:00
extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
/**
* vma_address - Find the virtual address a page range is mapped at
* @vma: The vma which maps this object.
* @pgoff: The page offset within its object.
* @nr_pages: The number of pages to consider.
*
* If any page in this range is mapped by this VMA, return the first address
* where any of these pages appear. Otherwise, return -EFAULT.
thp: reintroduce split_huge_page() This patch adds implementation of split_huge_page() for new refcountings. Unlike previous implementation, new split_huge_page() can fail if somebody holds GUP pin on the page. It also means that pin on page would prevent it from bening split under you. It makes situation in many places much cleaner. The basic scheme of split_huge_page(): - Check that sum of mapcounts of all subpage is equal to page_count() plus one (caller pin). Foll off with -EBUSY. This way we can avoid useless PMD-splits. - Freeze the page counters by splitting all PMD and setup migration PTEs. - Re-check sum of mapcounts against page_count(). Page's counts are stable now. -EBUSY if page is pinned. - Split compound page. - Unfreeze the page by removing migration entries. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Sasha Levin <sasha.levin@oracle.com> Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Jerome Marchand <jmarchan@redhat.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Steve Capper <steve.capper@linaro.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:54:10 +00:00
*/
static inline unsigned long vma_address(struct vm_area_struct *vma,
pgoff_t pgoff, unsigned long nr_pages)
thp: reintroduce split_huge_page() This patch adds implementation of split_huge_page() for new refcountings. Unlike previous implementation, new split_huge_page() can fail if somebody holds GUP pin on the page. It also means that pin on page would prevent it from bening split under you. It makes situation in many places much cleaner. The basic scheme of split_huge_page(): - Check that sum of mapcounts of all subpage is equal to page_count() plus one (caller pin). Foll off with -EBUSY. This way we can avoid useless PMD-splits. - Freeze the page counters by splitting all PMD and setup migration PTEs. - Re-check sum of mapcounts against page_count(). Page's counts are stable now. -EBUSY if page is pinned. - Split compound page. - Unfreeze the page by removing migration entries. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Sasha Levin <sasha.levin@oracle.com> Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Jerome Marchand <jmarchan@redhat.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Steve Capper <steve.capper@linaro.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:54:10 +00:00
{
mm/thp: fix vma_address() if virtual address below file offset Running certain tests with a DEBUG_VM kernel would crash within hours, on the total_mapcount BUG() in split_huge_page_to_list(), while trying to free up some memory by punching a hole in a shmem huge page: split's try_to_unmap() was unable to find all the mappings of the page (which, on a !DEBUG_VM kernel, would then keep the huge page pinned in memory). When that BUG() was changed to a WARN(), it would later crash on the VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma) in mm/internal.h:vma_address(), used by rmap_walk_file() for try_to_unmap(). vma_address() is usually correct, but there's a wraparound case when the vm_start address is unusually low, but vm_pgoff not so low: vma_address() chooses max(start, vma->vm_start), but that decides on the wrong address, because start has become almost ULONG_MAX. Rewrite vma_address() to be more careful about vm_pgoff; move the VM_BUG_ON_VMA() out of it, returning -EFAULT for errors, so that it can be safely used from page_mapped_in_vma() and page_address_in_vma() too. Add vma_address_end() to apply similar care to end address calculation, in page_vma_mapped_walk() and page_mkclean_one() and try_to_unmap_one(); though it raises a question of whether callers would do better to supply pvmw->end to page_vma_mapped_walk() - I chose not, for a smaller patch. An irritation is that their apparent generality breaks down on KSM pages, which cannot be located by the page->index that page_to_pgoff() uses: as commit 4b0ece6fa016 ("mm: migrate: fix remove_migration_pte() for ksm pages") once discovered. I dithered over the best thing to do about that, and have ended up with a VM_BUG_ON_PAGE(PageKsm) in both vma_address() and vma_address_end(); though the only place in danger of using it on them was try_to_unmap_one(). Sidenote: vma_address() and vma_address_end() now use compound_nr() on a head page, instead of thp_size(): to make the right calculation on a hugetlbfs page, whether or not THPs are configured. try_to_unmap() is used on hugetlbfs pages, but perhaps the wrong calculation never mattered. Link: https://lkml.kernel.org/r/caf1c1a3-7cfb-7f8f-1beb-ba816e932825@google.com Fixes: a8fa41ad2f6f ("mm, rmap: check all VMAs that PTE-mapped THP can be part of") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-16 01:23:56 +00:00
unsigned long address;
if (pgoff >= vma->vm_pgoff) {
address = vma->vm_start +
((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
/* Check for address beyond vma (or wrapped through 0?) */
if (address < vma->vm_start || address >= vma->vm_end)
address = -EFAULT;
} else if (pgoff + nr_pages - 1 >= vma->vm_pgoff) {
mm/thp: fix vma_address() if virtual address below file offset Running certain tests with a DEBUG_VM kernel would crash within hours, on the total_mapcount BUG() in split_huge_page_to_list(), while trying to free up some memory by punching a hole in a shmem huge page: split's try_to_unmap() was unable to find all the mappings of the page (which, on a !DEBUG_VM kernel, would then keep the huge page pinned in memory). When that BUG() was changed to a WARN(), it would later crash on the VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma) in mm/internal.h:vma_address(), used by rmap_walk_file() for try_to_unmap(). vma_address() is usually correct, but there's a wraparound case when the vm_start address is unusually low, but vm_pgoff not so low: vma_address() chooses max(start, vma->vm_start), but that decides on the wrong address, because start has become almost ULONG_MAX. Rewrite vma_address() to be more careful about vm_pgoff; move the VM_BUG_ON_VMA() out of it, returning -EFAULT for errors, so that it can be safely used from page_mapped_in_vma() and page_address_in_vma() too. Add vma_address_end() to apply similar care to end address calculation, in page_vma_mapped_walk() and page_mkclean_one() and try_to_unmap_one(); though it raises a question of whether callers would do better to supply pvmw->end to page_vma_mapped_walk() - I chose not, for a smaller patch. An irritation is that their apparent generality breaks down on KSM pages, which cannot be located by the page->index that page_to_pgoff() uses: as commit 4b0ece6fa016 ("mm: migrate: fix remove_migration_pte() for ksm pages") once discovered. I dithered over the best thing to do about that, and have ended up with a VM_BUG_ON_PAGE(PageKsm) in both vma_address() and vma_address_end(); though the only place in danger of using it on them was try_to_unmap_one(). Sidenote: vma_address() and vma_address_end() now use compound_nr() on a head page, instead of thp_size(): to make the right calculation on a hugetlbfs page, whether or not THPs are configured. try_to_unmap() is used on hugetlbfs pages, but perhaps the wrong calculation never mattered. Link: https://lkml.kernel.org/r/caf1c1a3-7cfb-7f8f-1beb-ba816e932825@google.com Fixes: a8fa41ad2f6f ("mm, rmap: check all VMAs that PTE-mapped THP can be part of") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-16 01:23:56 +00:00
/* Test above avoids possibility of wrap to 0 on 32-bit */
address = vma->vm_start;
} else {
address = -EFAULT;
}
return address;
}
mm/thp: fix vma_address() if virtual address below file offset Running certain tests with a DEBUG_VM kernel would crash within hours, on the total_mapcount BUG() in split_huge_page_to_list(), while trying to free up some memory by punching a hole in a shmem huge page: split's try_to_unmap() was unable to find all the mappings of the page (which, on a !DEBUG_VM kernel, would then keep the huge page pinned in memory). When that BUG() was changed to a WARN(), it would later crash on the VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma) in mm/internal.h:vma_address(), used by rmap_walk_file() for try_to_unmap(). vma_address() is usually correct, but there's a wraparound case when the vm_start address is unusually low, but vm_pgoff not so low: vma_address() chooses max(start, vma->vm_start), but that decides on the wrong address, because start has become almost ULONG_MAX. Rewrite vma_address() to be more careful about vm_pgoff; move the VM_BUG_ON_VMA() out of it, returning -EFAULT for errors, so that it can be safely used from page_mapped_in_vma() and page_address_in_vma() too. Add vma_address_end() to apply similar care to end address calculation, in page_vma_mapped_walk() and page_mkclean_one() and try_to_unmap_one(); though it raises a question of whether callers would do better to supply pvmw->end to page_vma_mapped_walk() - I chose not, for a smaller patch. An irritation is that their apparent generality breaks down on KSM pages, which cannot be located by the page->index that page_to_pgoff() uses: as commit 4b0ece6fa016 ("mm: migrate: fix remove_migration_pte() for ksm pages") once discovered. I dithered over the best thing to do about that, and have ended up with a VM_BUG_ON_PAGE(PageKsm) in both vma_address() and vma_address_end(); though the only place in danger of using it on them was try_to_unmap_one(). Sidenote: vma_address() and vma_address_end() now use compound_nr() on a head page, instead of thp_size(): to make the right calculation on a hugetlbfs page, whether or not THPs are configured. try_to_unmap() is used on hugetlbfs pages, but perhaps the wrong calculation never mattered. Link: https://lkml.kernel.org/r/caf1c1a3-7cfb-7f8f-1beb-ba816e932825@google.com Fixes: a8fa41ad2f6f ("mm, rmap: check all VMAs that PTE-mapped THP can be part of") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-16 01:23:56 +00:00
/*
* Then at what user virtual address will none of the range be found in vma?
mm/thp: fix vma_address() if virtual address below file offset Running certain tests with a DEBUG_VM kernel would crash within hours, on the total_mapcount BUG() in split_huge_page_to_list(), while trying to free up some memory by punching a hole in a shmem huge page: split's try_to_unmap() was unable to find all the mappings of the page (which, on a !DEBUG_VM kernel, would then keep the huge page pinned in memory). When that BUG() was changed to a WARN(), it would later crash on the VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma) in mm/internal.h:vma_address(), used by rmap_walk_file() for try_to_unmap(). vma_address() is usually correct, but there's a wraparound case when the vm_start address is unusually low, but vm_pgoff not so low: vma_address() chooses max(start, vma->vm_start), but that decides on the wrong address, because start has become almost ULONG_MAX. Rewrite vma_address() to be more careful about vm_pgoff; move the VM_BUG_ON_VMA() out of it, returning -EFAULT for errors, so that it can be safely used from page_mapped_in_vma() and page_address_in_vma() too. Add vma_address_end() to apply similar care to end address calculation, in page_vma_mapped_walk() and page_mkclean_one() and try_to_unmap_one(); though it raises a question of whether callers would do better to supply pvmw->end to page_vma_mapped_walk() - I chose not, for a smaller patch. An irritation is that their apparent generality breaks down on KSM pages, which cannot be located by the page->index that page_to_pgoff() uses: as commit 4b0ece6fa016 ("mm: migrate: fix remove_migration_pte() for ksm pages") once discovered. I dithered over the best thing to do about that, and have ended up with a VM_BUG_ON_PAGE(PageKsm) in both vma_address() and vma_address_end(); though the only place in danger of using it on them was try_to_unmap_one(). Sidenote: vma_address() and vma_address_end() now use compound_nr() on a head page, instead of thp_size(): to make the right calculation on a hugetlbfs page, whether or not THPs are configured. try_to_unmap() is used on hugetlbfs pages, but perhaps the wrong calculation never mattered. Link: https://lkml.kernel.org/r/caf1c1a3-7cfb-7f8f-1beb-ba816e932825@google.com Fixes: a8fa41ad2f6f ("mm, rmap: check all VMAs that PTE-mapped THP can be part of") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-16 01:23:56 +00:00
* Assumes that vma_address() already returned a good starting address.
*/
static inline unsigned long vma_address_end(struct page_vma_mapped_walk *pvmw)
thp: reintroduce split_huge_page() This patch adds implementation of split_huge_page() for new refcountings. Unlike previous implementation, new split_huge_page() can fail if somebody holds GUP pin on the page. It also means that pin on page would prevent it from bening split under you. It makes situation in many places much cleaner. The basic scheme of split_huge_page(): - Check that sum of mapcounts of all subpage is equal to page_count() plus one (caller pin). Foll off with -EBUSY. This way we can avoid useless PMD-splits. - Freeze the page counters by splitting all PMD and setup migration PTEs. - Re-check sum of mapcounts against page_count(). Page's counts are stable now. -EBUSY if page is pinned. - Split compound page. - Unfreeze the page by removing migration entries. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Sasha Levin <sasha.levin@oracle.com> Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Jerome Marchand <jmarchan@redhat.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Steve Capper <steve.capper@linaro.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:54:10 +00:00
{
struct vm_area_struct *vma = pvmw->vma;
mm/thp: fix vma_address() if virtual address below file offset Running certain tests with a DEBUG_VM kernel would crash within hours, on the total_mapcount BUG() in split_huge_page_to_list(), while trying to free up some memory by punching a hole in a shmem huge page: split's try_to_unmap() was unable to find all the mappings of the page (which, on a !DEBUG_VM kernel, would then keep the huge page pinned in memory). When that BUG() was changed to a WARN(), it would later crash on the VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma) in mm/internal.h:vma_address(), used by rmap_walk_file() for try_to_unmap(). vma_address() is usually correct, but there's a wraparound case when the vm_start address is unusually low, but vm_pgoff not so low: vma_address() chooses max(start, vma->vm_start), but that decides on the wrong address, because start has become almost ULONG_MAX. Rewrite vma_address() to be more careful about vm_pgoff; move the VM_BUG_ON_VMA() out of it, returning -EFAULT for errors, so that it can be safely used from page_mapped_in_vma() and page_address_in_vma() too. Add vma_address_end() to apply similar care to end address calculation, in page_vma_mapped_walk() and page_mkclean_one() and try_to_unmap_one(); though it raises a question of whether callers would do better to supply pvmw->end to page_vma_mapped_walk() - I chose not, for a smaller patch. An irritation is that their apparent generality breaks down on KSM pages, which cannot be located by the page->index that page_to_pgoff() uses: as commit 4b0ece6fa016 ("mm: migrate: fix remove_migration_pte() for ksm pages") once discovered. I dithered over the best thing to do about that, and have ended up with a VM_BUG_ON_PAGE(PageKsm) in both vma_address() and vma_address_end(); though the only place in danger of using it on them was try_to_unmap_one(). Sidenote: vma_address() and vma_address_end() now use compound_nr() on a head page, instead of thp_size(): to make the right calculation on a hugetlbfs page, whether or not THPs are configured. try_to_unmap() is used on hugetlbfs pages, but perhaps the wrong calculation never mattered. Link: https://lkml.kernel.org/r/caf1c1a3-7cfb-7f8f-1beb-ba816e932825@google.com Fixes: a8fa41ad2f6f ("mm, rmap: check all VMAs that PTE-mapped THP can be part of") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-16 01:23:56 +00:00
pgoff_t pgoff;
unsigned long address;
/* Common case, plus ->pgoff is invalid for KSM */
if (pvmw->nr_pages == 1)
return pvmw->address + PAGE_SIZE;
pgoff = pvmw->pgoff + pvmw->nr_pages;
mm/thp: fix vma_address() if virtual address below file offset Running certain tests with a DEBUG_VM kernel would crash within hours, on the total_mapcount BUG() in split_huge_page_to_list(), while trying to free up some memory by punching a hole in a shmem huge page: split's try_to_unmap() was unable to find all the mappings of the page (which, on a !DEBUG_VM kernel, would then keep the huge page pinned in memory). When that BUG() was changed to a WARN(), it would later crash on the VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma) in mm/internal.h:vma_address(), used by rmap_walk_file() for try_to_unmap(). vma_address() is usually correct, but there's a wraparound case when the vm_start address is unusually low, but vm_pgoff not so low: vma_address() chooses max(start, vma->vm_start), but that decides on the wrong address, because start has become almost ULONG_MAX. Rewrite vma_address() to be more careful about vm_pgoff; move the VM_BUG_ON_VMA() out of it, returning -EFAULT for errors, so that it can be safely used from page_mapped_in_vma() and page_address_in_vma() too. Add vma_address_end() to apply similar care to end address calculation, in page_vma_mapped_walk() and page_mkclean_one() and try_to_unmap_one(); though it raises a question of whether callers would do better to supply pvmw->end to page_vma_mapped_walk() - I chose not, for a smaller patch. An irritation is that their apparent generality breaks down on KSM pages, which cannot be located by the page->index that page_to_pgoff() uses: as commit 4b0ece6fa016 ("mm: migrate: fix remove_migration_pte() for ksm pages") once discovered. I dithered over the best thing to do about that, and have ended up with a VM_BUG_ON_PAGE(PageKsm) in both vma_address() and vma_address_end(); though the only place in danger of using it on them was try_to_unmap_one(). Sidenote: vma_address() and vma_address_end() now use compound_nr() on a head page, instead of thp_size(): to make the right calculation on a hugetlbfs page, whether or not THPs are configured. try_to_unmap() is used on hugetlbfs pages, but perhaps the wrong calculation never mattered. Link: https://lkml.kernel.org/r/caf1c1a3-7cfb-7f8f-1beb-ba816e932825@google.com Fixes: a8fa41ad2f6f ("mm, rmap: check all VMAs that PTE-mapped THP can be part of") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-16 01:23:56 +00:00
address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
/* Check for address beyond vma (or wrapped through 0?) */
if (address < vma->vm_start || address > vma->vm_end)
address = vma->vm_end;
return address;
thp: reintroduce split_huge_page() This patch adds implementation of split_huge_page() for new refcountings. Unlike previous implementation, new split_huge_page() can fail if somebody holds GUP pin on the page. It also means that pin on page would prevent it from bening split under you. It makes situation in many places much cleaner. The basic scheme of split_huge_page(): - Check that sum of mapcounts of all subpage is equal to page_count() plus one (caller pin). Foll off with -EBUSY. This way we can avoid useless PMD-splits. - Freeze the page counters by splitting all PMD and setup migration PTEs. - Re-check sum of mapcounts against page_count(). Page's counts are stable now. -EBUSY if page is pinned. - Split compound page. - Unfreeze the page by removing migration entries. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Sasha Levin <sasha.levin@oracle.com> Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Jerome Marchand <jmarchan@redhat.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Steve Capper <steve.capper@linaro.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:54:10 +00:00
}
mm: drop mmap_sem before calling balance_dirty_pages() in write fault One of our services is observing hanging ps/top/etc under heavy write IO, and the task states show this is an mmap_sem priority inversion: A write fault is holding the mmap_sem in read-mode and waiting for (heavily cgroup-limited) IO in balance_dirty_pages(): balance_dirty_pages+0x724/0x905 balance_dirty_pages_ratelimited+0x254/0x390 fault_dirty_shared_page.isra.96+0x4a/0x90 do_wp_page+0x33e/0x400 __handle_mm_fault+0x6f0/0xfa0 handle_mm_fault+0xe4/0x200 __do_page_fault+0x22b/0x4a0 page_fault+0x45/0x50 Somebody tries to change the address space, contending for the mmap_sem in write-mode: call_rwsem_down_write_failed_killable+0x13/0x20 do_mprotect_pkey+0xa8/0x330 SyS_mprotect+0xf/0x20 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 The waiting writer locks out all subsequent readers to avoid lock starvation, and several threads can be seen hanging like this: call_rwsem_down_read_failed+0x14/0x30 proc_pid_cmdline_read+0xa0/0x480 __vfs_read+0x23/0x140 vfs_read+0x87/0x130 SyS_read+0x42/0x90 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 To fix this, do what we do for cache read faults already: drop the mmap_sem before calling into anything IO bound, in this case the balance_dirty_pages() function, and return VM_FAULT_RETRY. Link: http://lkml.kernel.org/r/20190924194238.GA29030@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Hillf Danton <hdanton@sina.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>
2019-12-01 01:50:22 +00:00
static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
struct file *fpin)
{
int flags = vmf->flags;
if (fpin)
return fpin;
/*
* FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or
* anything, so we only pin the file and drop the mmap_lock if only
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
* FAULT_FLAG_ALLOW_RETRY is set, while this is the first attempt.
mm: drop mmap_sem before calling balance_dirty_pages() in write fault One of our services is observing hanging ps/top/etc under heavy write IO, and the task states show this is an mmap_sem priority inversion: A write fault is holding the mmap_sem in read-mode and waiting for (heavily cgroup-limited) IO in balance_dirty_pages(): balance_dirty_pages+0x724/0x905 balance_dirty_pages_ratelimited+0x254/0x390 fault_dirty_shared_page.isra.96+0x4a/0x90 do_wp_page+0x33e/0x400 __handle_mm_fault+0x6f0/0xfa0 handle_mm_fault+0xe4/0x200 __do_page_fault+0x22b/0x4a0 page_fault+0x45/0x50 Somebody tries to change the address space, contending for the mmap_sem in write-mode: call_rwsem_down_write_failed_killable+0x13/0x20 do_mprotect_pkey+0xa8/0x330 SyS_mprotect+0xf/0x20 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 The waiting writer locks out all subsequent readers to avoid lock starvation, and several threads can be seen hanging like this: call_rwsem_down_read_failed+0x14/0x30 proc_pid_cmdline_read+0xa0/0x480 __vfs_read+0x23/0x140 vfs_read+0x87/0x130 SyS_read+0x42/0x90 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 To fix this, do what we do for cache read faults already: drop the mmap_sem before calling into anything IO bound, in this case the balance_dirty_pages() function, and return VM_FAULT_RETRY. Link: http://lkml.kernel.org/r/20190924194238.GA29030@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Hillf Danton <hdanton@sina.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>
2019-12-01 01:50:22 +00:00
*/
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) &&
!(flags & FAULT_FLAG_RETRY_NOWAIT)) {
mm: drop mmap_sem before calling balance_dirty_pages() in write fault One of our services is observing hanging ps/top/etc under heavy write IO, and the task states show this is an mmap_sem priority inversion: A write fault is holding the mmap_sem in read-mode and waiting for (heavily cgroup-limited) IO in balance_dirty_pages(): balance_dirty_pages+0x724/0x905 balance_dirty_pages_ratelimited+0x254/0x390 fault_dirty_shared_page.isra.96+0x4a/0x90 do_wp_page+0x33e/0x400 __handle_mm_fault+0x6f0/0xfa0 handle_mm_fault+0xe4/0x200 __do_page_fault+0x22b/0x4a0 page_fault+0x45/0x50 Somebody tries to change the address space, contending for the mmap_sem in write-mode: call_rwsem_down_write_failed_killable+0x13/0x20 do_mprotect_pkey+0xa8/0x330 SyS_mprotect+0xf/0x20 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 The waiting writer locks out all subsequent readers to avoid lock starvation, and several threads can be seen hanging like this: call_rwsem_down_read_failed+0x14/0x30 proc_pid_cmdline_read+0xa0/0x480 __vfs_read+0x23/0x140 vfs_read+0x87/0x130 SyS_read+0x42/0x90 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 To fix this, do what we do for cache read faults already: drop the mmap_sem before calling into anything IO bound, in this case the balance_dirty_pages() function, and return VM_FAULT_RETRY. Link: http://lkml.kernel.org/r/20190924194238.GA29030@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Hillf Danton <hdanton@sina.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>
2019-12-01 01:50:22 +00:00
fpin = get_file(vmf->vma->vm_file);
release_fault_lock(vmf);
mm: drop mmap_sem before calling balance_dirty_pages() in write fault One of our services is observing hanging ps/top/etc under heavy write IO, and the task states show this is an mmap_sem priority inversion: A write fault is holding the mmap_sem in read-mode and waiting for (heavily cgroup-limited) IO in balance_dirty_pages(): balance_dirty_pages+0x724/0x905 balance_dirty_pages_ratelimited+0x254/0x390 fault_dirty_shared_page.isra.96+0x4a/0x90 do_wp_page+0x33e/0x400 __handle_mm_fault+0x6f0/0xfa0 handle_mm_fault+0xe4/0x200 __do_page_fault+0x22b/0x4a0 page_fault+0x45/0x50 Somebody tries to change the address space, contending for the mmap_sem in write-mode: call_rwsem_down_write_failed_killable+0x13/0x20 do_mprotect_pkey+0xa8/0x330 SyS_mprotect+0xf/0x20 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 The waiting writer locks out all subsequent readers to avoid lock starvation, and several threads can be seen hanging like this: call_rwsem_down_read_failed+0x14/0x30 proc_pid_cmdline_read+0xa0/0x480 __vfs_read+0x23/0x140 vfs_read+0x87/0x130 SyS_read+0x42/0x90 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 To fix this, do what we do for cache read faults already: drop the mmap_sem before calling into anything IO bound, in this case the balance_dirty_pages() function, and return VM_FAULT_RETRY. Link: http://lkml.kernel.org/r/20190924194238.GA29030@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Hillf Danton <hdanton@sina.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>
2019-12-01 01:50:22 +00:00
}
return fpin;
}
#else /* !CONFIG_MMU */
static inline void unmap_mapping_folio(struct folio *folio) { }
static inline void mlock_new_folio(struct folio *folio) { }
static inline bool need_mlock_drain(int cpu) { return false; }
static inline void mlock_drain_local(void) { }
static inline void mlock_drain_remote(int cpu) { }
static inline void vunmap_range_noflush(unsigned long start, unsigned long end)
{
}
#endif /* !CONFIG_MMU */
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:39 +00:00
/* Memory initialisation debug and verification */
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
DECLARE_STATIC_KEY_TRUE(deferred_pages);
bool __init deferred_grow_zone(struct zone *zone, unsigned int order);
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
enum mminit_level {
MMINIT_WARNING,
MMINIT_VERIFY,
MMINIT_TRACE
};
#ifdef CONFIG_DEBUG_MEMORY_INIT
extern int mminit_loglevel;
#define mminit_dprintk(level, prefix, fmt, arg...) \
do { \
if (level < mminit_loglevel) { \
if (level <= MMINIT_WARNING) \
pr_warn("mminit::" prefix " " fmt, ##arg); \
else \
printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \
} \
} while (0)
extern void mminit_verify_pageflags_layout(void);
extern void mminit_verify_zonelist(void);
#else
static inline void mminit_dprintk(enum mminit_level level,
const char *prefix, const char *fmt, ...)
{
}
static inline void mminit_verify_pageflags_layout(void)
{
}
static inline void mminit_verify_zonelist(void)
{
}
#endif /* CONFIG_DEBUG_MEMORY_INIT */
#define NODE_RECLAIM_NOSCAN -2
#define NODE_RECLAIM_FULL -1
#define NODE_RECLAIM_SOME 0
#define NODE_RECLAIM_SUCCESS 1
#ifdef CONFIG_NUMA
extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int);
mm/numa: automatically generate node migration order Patch series "Migrate Pages in lieu of discard", v11. We're starting to see systems with more and more kinds of memory such as Intel's implementation of persistent memory. Let's say you have a system with some DRAM and some persistent memory. Today, once DRAM fills up, reclaim will start and some of the DRAM contents will be thrown out. Allocations will, at some point, start falling over to the slower persistent memory. That has two nasty properties. First, the newer allocations can end up in the slower persistent memory. Second, reclaimed data in DRAM are just discarded even if there are gobs of space in persistent memory that could be used. This patchset implements a solution to these problems. At the end of the reclaim process in shrink_page_list() just before the last page refcount is dropped, the page is migrated to persistent memory instead of being dropped. While I've talked about a DRAM/PMEM pairing, this approach would function in any environment where memory tiers exist. This is not perfect. It "strands" pages in slower memory and never brings them back to fast DRAM. Huang Ying has follow-on work which repurposes NUMA balancing to promote hot pages back to DRAM. This is also all based on an upstream mechanism that allows persistent memory to be onlined and used as if it were volatile: http://lkml.kernel.org/r/20190124231441.37A4A305@viggo.jf.intel.com With that, the DRAM and PMEM in each socket will be represented as 2 separate NUMA nodes, with the CPUs sit in the DRAM node. So the general inter-NUMA demotion mechanism introduced in the patchset can migrate the cold DRAM pages to the PMEM node. We have tested the patchset with the postgresql and pgbench. On a 2-socket server machine with DRAM and PMEM, the kernel with the patchset can improve the score of pgbench up to 22.1% compared with that of the DRAM only + disk case. This comes from the reduced disk read throughput (which reduces up to 70.8%). == Open Issues == * Memory policies and cpusets that, for instance, restrict allocations to DRAM can be demoted to PMEM whenever they opt in to this new mechanism. A cgroup-level API to opt-in or opt-out of these migrations will likely be required as a follow-on. * Could be more aggressive about where anon LRU scanning occurs since it no longer necessarily involves I/O. get_scan_count() for instance says: "If we have no swap space, do not bother scanning anon pages" This patch (of 9): Prepare for the kernel to auto-migrate pages to other memory nodes with a node migration table. This allows creating single migration target for each NUMA node to enable the kernel to do NUMA page migrations instead of simply discarding colder pages. A node with no target is a "terminal node", so reclaim acts normally there. The migration target does not fundamentally _need_ to be a single node, but this implementation starts there to limit complexity. When memory fills up on a node, memory contents can be automatically migrated to another node. The biggest problems are knowing when to migrate and to where the migration should be targeted. The most straightforward way to generate the "to where" list would be to follow the page allocator fallback lists. Those lists already tell us if memory is full where to look next. It would also be logical to move memory in that order. But, the allocator fallback lists have a fatal flaw: most nodes appear in all the lists. This would potentially lead to migration cycles (A->B, B->A, A->B, ...). Instead of using the allocator fallback lists directly, keep a separate node migration ordering. But, reuse the same data used to generate page allocator fallback in the first place: find_next_best_node(). This means that the firmware data used to populate node distances essentially dictates the ordering for now. It should also be architecture-neutral since all NUMA architectures have a working find_next_best_node(). RCU is used to allow lock-less read of node_demotion[] and prevent demotion cycles been observed. If multiple reads of node_demotion[] are performed, a single rcu_read_lock() must be held over all reads to ensure no cycles are observed. Details are as follows. === What does RCU provide? === Imagine a simple loop which walks down the demotion path looking for the last node: terminal_node = start_node; while (node_demotion[terminal_node] != NUMA_NO_NODE) { terminal_node = node_demotion[terminal_node]; } The initial values are: node_demotion[0] = 1; node_demotion[1] = NUMA_NO_NODE; and are updated to: node_demotion[0] = NUMA_NO_NODE; node_demotion[1] = 0; What guarantees that the cycle is not observed: node_demotion[0] = 1; node_demotion[1] = 0; and would loop forever? With RCU, a rcu_read_lock/unlock() can be placed around the loop. Since the write side does a synchronize_rcu(), the loop that observed the old contents is known to be complete before the synchronize_rcu() has completed. RCU, combined with disable_all_migrate_targets(), ensures that the old migration state is not visible by the time __set_migration_target_nodes() is called. === What does READ_ONCE() provide? === READ_ONCE() forbids the compiler from merging or reordering successive reads of node_demotion[]. This ensures that any updates are *eventually* observed. Consider the above loop again. The compiler could theoretically read the entirety of node_demotion[] into local storage (registers) and never go back to memory, and *permanently* observe bad values for node_demotion[]. Note: RCU does not provide any universal compiler-ordering guarantees: https://lore.kernel.org/lkml/20150921204327.GH4029@linux.vnet.ibm.com/ This code is unused for now. It will be called later in the series. Link: https://lkml.kernel.org/r/20210721063926.3024591-1-ying.huang@intel.com Link: https://lkml.kernel.org/r/20210715055145.195411-1-ying.huang@intel.com Link: https://lkml.kernel.org/r/20210715055145.195411-2-ying.huang@intel.com Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Reviewed-by: Zi Yan <ziy@nvidia.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Michal Hocko <mhocko@suse.com> Cc: Wei Xu <weixugc@google.com> Cc: David Rientjes <rientjes@google.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: Keith Busch <kbusch@kernel.org> 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>
2021-09-02 21:59:06 +00:00
extern int find_next_best_node(int node, nodemask_t *used_node_mask);
#else
static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask,
unsigned int order)
{
return NODE_RECLAIM_NOSCAN;
}
mm/numa: automatically generate node migration order Patch series "Migrate Pages in lieu of discard", v11. We're starting to see systems with more and more kinds of memory such as Intel's implementation of persistent memory. Let's say you have a system with some DRAM and some persistent memory. Today, once DRAM fills up, reclaim will start and some of the DRAM contents will be thrown out. Allocations will, at some point, start falling over to the slower persistent memory. That has two nasty properties. First, the newer allocations can end up in the slower persistent memory. Second, reclaimed data in DRAM are just discarded even if there are gobs of space in persistent memory that could be used. This patchset implements a solution to these problems. At the end of the reclaim process in shrink_page_list() just before the last page refcount is dropped, the page is migrated to persistent memory instead of being dropped. While I've talked about a DRAM/PMEM pairing, this approach would function in any environment where memory tiers exist. This is not perfect. It "strands" pages in slower memory and never brings them back to fast DRAM. Huang Ying has follow-on work which repurposes NUMA balancing to promote hot pages back to DRAM. This is also all based on an upstream mechanism that allows persistent memory to be onlined and used as if it were volatile: http://lkml.kernel.org/r/20190124231441.37A4A305@viggo.jf.intel.com With that, the DRAM and PMEM in each socket will be represented as 2 separate NUMA nodes, with the CPUs sit in the DRAM node. So the general inter-NUMA demotion mechanism introduced in the patchset can migrate the cold DRAM pages to the PMEM node. We have tested the patchset with the postgresql and pgbench. On a 2-socket server machine with DRAM and PMEM, the kernel with the patchset can improve the score of pgbench up to 22.1% compared with that of the DRAM only + disk case. This comes from the reduced disk read throughput (which reduces up to 70.8%). == Open Issues == * Memory policies and cpusets that, for instance, restrict allocations to DRAM can be demoted to PMEM whenever they opt in to this new mechanism. A cgroup-level API to opt-in or opt-out of these migrations will likely be required as a follow-on. * Could be more aggressive about where anon LRU scanning occurs since it no longer necessarily involves I/O. get_scan_count() for instance says: "If we have no swap space, do not bother scanning anon pages" This patch (of 9): Prepare for the kernel to auto-migrate pages to other memory nodes with a node migration table. This allows creating single migration target for each NUMA node to enable the kernel to do NUMA page migrations instead of simply discarding colder pages. A node with no target is a "terminal node", so reclaim acts normally there. The migration target does not fundamentally _need_ to be a single node, but this implementation starts there to limit complexity. When memory fills up on a node, memory contents can be automatically migrated to another node. The biggest problems are knowing when to migrate and to where the migration should be targeted. The most straightforward way to generate the "to where" list would be to follow the page allocator fallback lists. Those lists already tell us if memory is full where to look next. It would also be logical to move memory in that order. But, the allocator fallback lists have a fatal flaw: most nodes appear in all the lists. This would potentially lead to migration cycles (A->B, B->A, A->B, ...). Instead of using the allocator fallback lists directly, keep a separate node migration ordering. But, reuse the same data used to generate page allocator fallback in the first place: find_next_best_node(). This means that the firmware data used to populate node distances essentially dictates the ordering for now. It should also be architecture-neutral since all NUMA architectures have a working find_next_best_node(). RCU is used to allow lock-less read of node_demotion[] and prevent demotion cycles been observed. If multiple reads of node_demotion[] are performed, a single rcu_read_lock() must be held over all reads to ensure no cycles are observed. Details are as follows. === What does RCU provide? === Imagine a simple loop which walks down the demotion path looking for the last node: terminal_node = start_node; while (node_demotion[terminal_node] != NUMA_NO_NODE) { terminal_node = node_demotion[terminal_node]; } The initial values are: node_demotion[0] = 1; node_demotion[1] = NUMA_NO_NODE; and are updated to: node_demotion[0] = NUMA_NO_NODE; node_demotion[1] = 0; What guarantees that the cycle is not observed: node_demotion[0] = 1; node_demotion[1] = 0; and would loop forever? With RCU, a rcu_read_lock/unlock() can be placed around the loop. Since the write side does a synchronize_rcu(), the loop that observed the old contents is known to be complete before the synchronize_rcu() has completed. RCU, combined with disable_all_migrate_targets(), ensures that the old migration state is not visible by the time __set_migration_target_nodes() is called. === What does READ_ONCE() provide? === READ_ONCE() forbids the compiler from merging or reordering successive reads of node_demotion[]. This ensures that any updates are *eventually* observed. Consider the above loop again. The compiler could theoretically read the entirety of node_demotion[] into local storage (registers) and never go back to memory, and *permanently* observe bad values for node_demotion[]. Note: RCU does not provide any universal compiler-ordering guarantees: https://lore.kernel.org/lkml/20150921204327.GH4029@linux.vnet.ibm.com/ This code is unused for now. It will be called later in the series. Link: https://lkml.kernel.org/r/20210721063926.3024591-1-ying.huang@intel.com Link: https://lkml.kernel.org/r/20210715055145.195411-1-ying.huang@intel.com Link: https://lkml.kernel.org/r/20210715055145.195411-2-ying.huang@intel.com Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Reviewed-by: Zi Yan <ziy@nvidia.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Michal Hocko <mhocko@suse.com> Cc: Wei Xu <weixugc@google.com> Cc: David Rientjes <rientjes@google.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: Keith Busch <kbusch@kernel.org> 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>
2021-09-02 21:59:06 +00:00
static inline int find_next_best_node(int node, nodemask_t *used_node_mask)
{
return NUMA_NO_NODE;
}
#endif
mm/memory-failure.c: move clear_hwpoisoned_pages Patch series "memory-failure: fix hwpoison_filter", v2. As well known, the memory failure mechanism handles memory corrupted event, and try to send SIGBUS to the user process which uses this corrupted page. For the virtualization case, QEMU catches SIGBUS and tries to inject MCE into the guest, and the guest handles memory failure again. Thus the guest gets the minimal effect from hardware memory corruption. The further step I'm working on: 1, try to modify code to decrease poisoned pages in a single place (mm/memofy-failure.c: simplify num_poisoned_pages_dec in this series). 2, try to use page_handle_poison() to handle SetPageHWPoison() and num_poisoned_pages_inc() together. It would be best to call num_poisoned_pages_inc() in a single place too. 3, introduce memory failure notifier list in memory-failure.c: notify the corrupted PFN to someone who registers this list. If I can complete [1] and [2] part, [3] will be quite easy(just call notifier list after increasing poisoned page). 4, introduce memory recover VQ for memory balloon device, and registers memory failure notifier list. During the guest kernel handles memory failure, balloon device gets notified by memory failure notifier list, and tells the host to recover the corrupted PFN(GPA) by the new VQ. 5, host side remaps the corrupted page(HVA), and tells the guest side to unpoison the PFN(GPA). Then the guest fixes the corrupted page(GPA) dynamically. This patch (of 5): clear_hwpoisoned_pages() clears HWPoison flag and decreases the number of poisoned pages, this actually works as part of memory failure. Move this function from sparse.c to memory-failure.c, finally there is no CONFIG_MEMORY_FAILURE in sparse.c. Link: https://lkml.kernel.org/r/20220509105641.491313-1-pizhenwei@bytedance.com Link: https://lkml.kernel.org/r/20220509105641.491313-2-pizhenwei@bytedance.com Signed-off-by: zhenwei pi <pizhenwei@bytedance.com> Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-05-13 03:23:09 +00:00
/*
* mm/memory-failure.c
*/
#ifdef CONFIG_MEMORY_FAILURE
void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu);
void shake_folio(struct folio *folio);
extern int hwpoison_filter(struct page *p);
extern u32 hwpoison_filter_dev_major;
extern u32 hwpoison_filter_dev_minor;
extern u64 hwpoison_filter_flags_mask;
extern u64 hwpoison_filter_flags_value;
HWPOISON: add memory cgroup filter The hwpoison test suite need to inject hwpoison to a collection of selected task pages, and must not touch pages not owned by them and thus kill important system processes such as init. (But it's OK to mis-hwpoison free/unowned pages as well as shared clean pages. Mis-hwpoison of shared dirty pages will kill all tasks, so the test suite will target all or non of such tasks in the first place.) The memory cgroup serves this purpose well. We can put the target processes under the control of a memory cgroup, and tell the hwpoison injection code to only kill pages associated with some active memory cgroup. The prerequisite for doing hwpoison stress tests with mem_cgroup is, the mem_cgroup code tracks task pages _accurately_ (unless page is locked). Which we believe is/should be true. The benefits are simplification of hwpoison injector code. Also the mem_cgroup code will automatically be tested by hwpoison test cases. The alternative interfaces pin-pfn/unpin-pfn can also delegate the (process and page flags) filtering functions reliably to user space. However prototype implementation shows that this scheme adds more complexity than we wanted. Example test case: mkdir /cgroup/hwpoison usemem -m 100 -s 1000 & echo `jobs -p` > /cgroup/hwpoison/tasks memcg_ino=$(ls -id /cgroup/hwpoison | cut -f1 -d' ') echo $memcg_ino > /debug/hwpoison/corrupt-filter-memcg page-types -p `pidof init` --hwpoison # shall do nothing page-types -p `pidof usemem` --hwpoison # poison its pages [AK: Fix documentation] [Add fix for problem noticed by Li Zefan <lizf@cn.fujitsu.com>; dentry in the css could be NULL] CC: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> CC: Hugh Dickins <hugh.dickins@tiscali.co.uk> CC: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> CC: Balbir Singh <balbir@linux.vnet.ibm.com> CC: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> CC: Li Zefan <lizf@cn.fujitsu.com> CC: Paul Menage <menage@google.com> CC: Nick Piggin <npiggin@suse.de> CC: Andi Kleen <andi@firstfloor.org> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andi Kleen <ak@linux.intel.com>
2009-12-16 11:19:59 +00:00
extern u64 hwpoison_filter_memcg;
extern u32 hwpoison_filter_enable;
#define MAGIC_HWPOISON 0x48575053U /* HWPS */
void SetPageHWPoisonTakenOff(struct page *page);
void ClearPageHWPoisonTakenOff(struct page *page);
bool take_page_off_buddy(struct page *page);
bool put_page_back_buddy(struct page *page);
struct task_struct *task_early_kill(struct task_struct *tsk, int force_early);
void add_to_kill_ksm(struct task_struct *tsk, struct page *p,
struct vm_area_struct *vma, struct list_head *to_kill,
unsigned long ksm_addr);
unsigned long page_mapped_in_vma(struct page *page, struct vm_area_struct *vma);
#else
static inline void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
{
}
#endif
mm: make mmap_sem for write waits killable for mm syscalls This is a follow up work for oom_reaper [1]. As the async OOM killing depends on oom_sem for read we would really appreciate if a holder for write didn't stood in the way. This patchset is changing many of down_write calls to be killable to help those cases when the writer is blocked and waiting for readers to release the lock and so help __oom_reap_task to process the oom victim. Most of the patches are really trivial because the lock is help from a shallow syscall paths where we can return EINTR trivially and allow the current task to die (note that EINTR will never get to the userspace as the task has fatal signal pending). Others seem to be easy as well as the callers are already handling fatal errors and bail and return to userspace which should be sufficient to handle the failure gracefully. I am not familiar with all those code paths so a deeper review is really appreciated. As this work is touching more areas which are not directly connected I have tried to keep the CC list as small as possible and people who I believed would be familiar are CCed only to the specific patches (all should have received the cover though). This patchset is based on linux-next and it depends on down_write_killable for rw_semaphores which got merged into tip locking/rwsem branch and it is merged into this next tree. I guess it would be easiest to route these patches via mmotm because of the dependency on the tip tree but if respective maintainers prefer other way I have no objections. I haven't covered all the mmap_write(mm->mmap_sem) instances here $ git grep "down_write(.*\<mmap_sem\>)" next/master | wc -l 98 $ git grep "down_write(.*\<mmap_sem\>)" | wc -l 62 I have tried to cover those which should be relatively easy to review in this series because this alone should be a nice improvement. Other places can be changed on top. [0] http://lkml.kernel.org/r/1456752417-9626-1-git-send-email-mhocko@kernel.org [1] http://lkml.kernel.org/r/1452094975-551-1-git-send-email-mhocko@kernel.org [2] http://lkml.kernel.org/r/1456750705-7141-1-git-send-email-mhocko@kernel.org This patch (of 18): This is the first step in making mmap_sem write waiters killable. It focuses on the trivial ones which are taking the lock early after entering the syscall and they are not changing state before. Therefore it is very easy to change them to use down_write_killable and immediately return with -EINTR. This will allow the waiter to pass away without blocking the mmap_sem which might be required to make a forward progress. E.g. the oom reaper will need the lock for reading to dismantle the OOM victim address space. The only tricky function in this patch is vm_mmap_pgoff which has many call sites via vm_mmap. To reduce the risk keep vm_mmap with the original non-killable semantic for now. vm_munmap callers do not bother checking the return value so open code it into the munmap syscall path for now for simplicity. Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Mel Gorman <mgorman@suse.de> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Hugh Dickins <hughd@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-23 23:25:27 +00:00
extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long,
unsigned long, unsigned long,
unsigned long, unsigned long);
mm: setup pageblock_order before it's used by sparsemem On architectures with CONFIG_HUGETLB_PAGE_SIZE_VARIABLE set, such as Itanium, pageblock_order is a variable with default value of 0. It's set to the right value by set_pageblock_order() in function free_area_init_core(). But pageblock_order may be used by sparse_init() before free_area_init_core() is called along path: sparse_init() ->sparse_early_usemaps_alloc_node() ->usemap_size() ->SECTION_BLOCKFLAGS_BITS ->((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS) The uninitialized pageblock_size will cause memory wasting because usemap_size() returns a much bigger value then it's really needed. For example, on an Itanium platform, sparse_init() pageblock_order=0 usemap_size=24576 free_area_init_core() before pageblock_order=0, usemap_size=24576 free_area_init_core() after pageblock_order=12, usemap_size=8 That means 24K memory has been wasted for each section, so fix it by calling set_pageblock_order() from sparse_init(). Signed-off-by: Xishi Qiu <qiuxishi@huawei.com> Signed-off-by: Jiang Liu <liuj97@gmail.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Keping Chen <chenkeping@huawei.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 23:43:19 +00:00
extern void set_pageblock_order(void);
struct folio *alloc_migrate_folio(struct folio *src, unsigned long private);
unsigned long reclaim_pages(struct list_head *folio_list);
unsigned int reclaim_clean_pages_from_list(struct zone *zone,
struct list_head *folio_list);
/* The ALLOC_WMARK bits are used as an index to zone->watermark */
#define ALLOC_WMARK_MIN WMARK_MIN
#define ALLOC_WMARK_LOW WMARK_LOW
#define ALLOC_WMARK_HIGH WMARK_HIGH
#define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */
/* Mask to get the watermark bits */
#define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1)
mm, oom: do not rely on TIF_MEMDIE for memory reserves access For ages we have been relying on TIF_MEMDIE thread flag to mark OOM victims and then, among other things, to give these threads full access to memory reserves. There are few shortcomings of this implementation, though. First of all and the most serious one is that the full access to memory reserves is quite dangerous because we leave no safety room for the system to operate and potentially do last emergency steps to move on. Secondly this flag is per task_struct while the OOM killer operates on mm_struct granularity so all processes sharing the given mm are killed. Giving the full access to all these task_structs could lead to a quick memory reserves depletion. We have tried to reduce this risk by giving TIF_MEMDIE only to the main thread and the currently allocating task but that doesn't really solve this problem while it surely opens up a room for corner cases - e.g. GFP_NO{FS,IO} requests might loop inside the allocator without access to memory reserves because a particular thread was not the group leader. Now that we have the oom reaper and that all oom victims are reapable after 1b51e65eab64 ("oom, oom_reaper: allow to reap mm shared by the kthreads") we can be more conservative and grant only partial access to memory reserves because there are reasonable chances of the parallel memory freeing. We still want some access to reserves because we do not want other consumers to eat up the victim's freed memory. oom victims will still contend with __GFP_HIGH users but those shouldn't be so aggressive to starve oom victims completely. Introduce ALLOC_OOM flag and give all tsk_is_oom_victim tasks access to the half of the reserves. This makes the access to reserves independent on which task has passed through mark_oom_victim. Also drop any usage of TIF_MEMDIE from the page allocator proper and replace it by tsk_is_oom_victim as well which will make page_alloc.c completely TIF_MEMDIE free finally. CONFIG_MMU=n doesn't have oom reaper so let's stick to the original ALLOC_NO_WATERMARKS approach. There is a demand to make the oom killer memcg aware which will imply many tasks killed at once. This change will allow such a usecase without worrying about complete memory reserves depletion. Link: http://lkml.kernel.org/r/20170810075019.28998-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Mel Gorman <mgorman@techsingularity.net> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: David Rientjes <rientjes@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Roman Gushchin <guro@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-06 23:24:50 +00:00
/*
* Only MMU archs have async oom victim reclaim - aka oom_reaper so we
* cannot assume a reduced access to memory reserves is sufficient for
* !MMU
*/
#ifdef CONFIG_MMU
#define ALLOC_OOM 0x08
#else
#define ALLOC_OOM ALLOC_NO_WATERMARKS
#endif
#define ALLOC_NON_BLOCK 0x10 /* Caller cannot block. Allow access
* to 25% of the min watermark or
* 62.5% if __GFP_HIGH is set.
*/
mm/page_alloc: rename ALLOC_HIGH to ALLOC_MIN_RESERVE Patch series "Discard __GFP_ATOMIC", v3. Neil's patch has been residing in mm-unstable as commit 2fafb4fe8f7a ("mm: discard __GFP_ATOMIC") for a long time and recently brought up again. Most recently, I was worried that __GFP_HIGH allocations could use high-order atomic reserves which is unintentional but there was no response so lets revisit -- this series reworks how min reserves are used, protects highorder reserves and then finishes with Neil's patch with very minor modifications so it fits on top. There was a review discussion on renaming __GFP_DIRECT_RECLAIM to __GFP_ALLOW_BLOCKING but I didn't think it was that big an issue and is orthogonal to the removal of __GFP_ATOMIC. There were some concerns about how the gfp flags affect the min reserves but it never reached a solid conclusion so I made my own attempt. The series tries to iron out some of the details on how reserves are used. ALLOC_HIGH becomes ALLOC_MIN_RESERVE and ALLOC_HARDER becomes ALLOC_NON_BLOCK and documents how the reserves are affected. For example, ALLOC_NON_BLOCK (no direct reclaim) on its own allows 25% of the min reserve. ALLOC_MIN_RESERVE (__GFP_HIGH) allows 50% and both combined allows deeper access again. ALLOC_OOM allows access to 75%. High-order atomic allocations are explicitly handled with the caveat that no __GFP_ATOMIC flag means that any high-order allocation that specifies GFP_HIGH and cannot enter direct reclaim will be treated as if it was GFP_ATOMIC. This patch (of 6): __GFP_HIGH aliases to ALLOC_HIGH but the name does not really hint what it means. As ALLOC_HIGH is internal to the allocator, rename it to ALLOC_MIN_RESERVE to document that the min reserves can be depleted. Link: https://lkml.kernel.org/r/20230113111217.14134-1-mgorman@techsingularity.net Link: https://lkml.kernel.org/r/20230113111217.14134-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: NeilBrown <neilb@suse.de> Cc: Thierry Reding <thierry.reding@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-01-13 11:12:12 +00:00
#define ALLOC_MIN_RESERVE 0x20 /* __GFP_HIGH set. Allow access to 50%
* of the min watermark.
*/
mm, page_alloc: spread allocations across zones before introducing fragmentation Patch series "Fragmentation avoidance improvements", v5. It has been noted before that fragmentation avoidance (aka anti-fragmentation) is not perfect. Given sufficient time or an adverse workload, memory gets fragmented and the long-term success of high-order allocations degrades. This series defines an adverse workload, a definition of external fragmentation events (including serious) ones and a series that reduces the level of those fragmentation events. The details of the workload and the consequences are described in more detail in the changelogs. However, from patch 1, this is a high-level summary of the adverse workload. The exact details are found in the mmtests implementation. The broad details of the workload are as follows; 1. Create an XFS filesystem (not specified in the configuration but done as part of the testing for this patch) 2. Start 4 fio threads that write a number of 64K files inefficiently. Inefficiently means that files are created on first access and not created in advance (fio parameterr create_on_open=1) and fallocate is not used (fallocate=none). With multiple IO issuers this creates a mix of slab and page cache allocations over time. The total size of the files is 150% physical memory so that the slabs and page cache pages get mixed 3. Warm up a number of fio read-only threads accessing the same files created in step 2. This part runs for the same length of time it took to create the files. It'll fault back in old data and further interleave slab and page cache allocations. As it's now low on memory due to step 2, fragmentation occurs as pageblocks get stolen. 4. While step 3 is still running, start a process that tries to allocate 75% of memory as huge pages with a number of threads. The number of threads is based on a (NR_CPUS_SOCKET - NR_FIO_THREADS)/4 to avoid THP threads contending with fio, any other threads or forcing cross-NUMA scheduling. Note that the test has not been used on a machine with less than 8 cores. The benchmark records whether huge pages were allocated and what the fault latency was in microseconds 5. Measure the number of events potentially causing external fragmentation, the fault latency and the huge page allocation success rate. 6. Cleanup Overall the series reduces external fragmentation causing events by over 94% on 1 and 2 socket machines, which in turn impacts high-order allocation success rates over the long term. There are differences in latencies and high-order allocation success rates. Latencies are a mixed bag as they are vulnerable to exact system state and whether allocations succeeded so they are treated as a secondary metric. Patch 1 uses lower zones if they are populated and have free memory instead of fragmenting a higher zone. It's special cased to handle a Normal->DMA32 fallback with the reasons explained in the changelog. Patch 2-4 boosts watermarks temporarily when an external fragmentation event occurs. kswapd wakes to reclaim a small amount of old memory and then wakes kcompactd on completion to recover the system slightly. This introduces some overhead in the slowpath. The level of boosting can be tuned or disabled depending on the tolerance for fragmentation vs allocation latency. Patch 5 stalls some movable allocation requests to let kswapd from patch 4 make some progress. The duration of the stalls is very low but it is possible to tune the system to avoid fragmentation events if larger stalls can be tolerated. The bulk of the improvement in fragmentation avoidance is from patches 1-4 but patch 5 can deal with a rare corner case and provides the option of tuning a system for THP allocation success rates in exchange for some stalls to control fragmentation. This patch (of 5): The page allocator zone lists are iterated based on the watermarks of each zone which does not take anti-fragmentation into account. On x86, node 0 may have multiple zones while other nodes have one zone. A consequence is that tasks running on node 0 may fragment ZONE_NORMAL even though ZONE_DMA32 has plenty of free memory. This patch special cases the allocator fast path such that it'll try an allocation from a lower local zone before fragmenting a higher zone. In this case, stealing of pageblocks or orders larger than a pageblock are still allowed in the fast path as they are uninteresting from a fragmentation point of view. This was evaluated using a benchmark designed to fragment memory before attempting THP allocations. It's implemented in mmtests as the following configurations configs/config-global-dhp__workload_thpfioscale configs/config-global-dhp__workload_thpfioscale-defrag configs/config-global-dhp__workload_thpfioscale-madvhugepage e.g. from mmtests ./run-mmtests.sh --run-monitor --config configs/config-global-dhp__workload_thpfioscale test-run-1 The broad details of the workload are as follows; 1. Create an XFS filesystem (not specified in the configuration but done as part of the testing for this patch). 2. Start 4 fio threads that write a number of 64K files inefficiently. Inefficiently means that files are created on first access and not created in advance (fio parameter create_on_open=1) and fallocate is not used (fallocate=none). With multiple IO issuers this creates a mix of slab and page cache allocations over time. The total size of the files is 150% physical memory so that the slabs and page cache pages get mixed. 3. Warm up a number of fio read-only processes accessing the same files created in step 2. This part runs for the same length of time it took to create the files. It'll refault old data and further interleave slab and page cache allocations. As it's now low on memory due to step 2, fragmentation occurs as pageblocks get stolen. 4. While step 3 is still running, start a process that tries to allocate 75% of memory as huge pages with a number of threads. The number of threads is based on a (NR_CPUS_SOCKET - NR_FIO_THREADS)/4 to avoid THP threads contending with fio, any other threads or forcing cross-NUMA scheduling. Note that the test has not been used on a machine with less than 8 cores. The benchmark records whether huge pages were allocated and what the fault latency was in microseconds. 5. Measure the number of events potentially causing external fragmentation, the fault latency and the huge page allocation success rate. 6. Cleanup the test files. Note that due to the use of IO and page cache that this benchmark is not suitable for running on large machines where the time to fragment memory may be excessive. Also note that while this is one mix that generates fragmentation that it's not the only mix that generates fragmentation. Differences in workload that are more slab-intensive or whether SLUB is used with high-order pages may yield different results. When the page allocator fragments memory, it records the event using the mm_page_alloc_extfrag ftrace event. If the fallback_order is smaller than a pageblock order (order-9 on 64-bit x86) then it's considered to be an "external fragmentation event" that may cause issues in the future. Hence, the primary metric here is the number of external fragmentation events that occur with order < 9. The secondary metric is allocation latency and huge page allocation success rates but note that differences in latencies and what the success rate also can affect the number of external fragmentation event which is why it's a secondary metric. 1-socket Skylake machine config-global-dhp__workload_thpfioscale XFS (no special madvise) 4 fio threads, 1 THP allocating thread -------------------------------------- 4.20-rc3 extfrag events < order 9: 804694 4.20-rc3+patch: 408912 (49% reduction) thpfioscale Fault Latencies 4.20.0-rc3 4.20.0-rc3 vanilla lowzone-v5r8 Amean fault-base-1 662.92 ( 0.00%) 653.58 * 1.41%* Amean fault-huge-1 0.00 ( 0.00%) 0.00 ( 0.00%) 4.20.0-rc3 4.20.0-rc3 vanilla lowzone-v5r8 Percentage huge-1 0.00 ( 0.00%) 0.00 ( 0.00%) Fault latencies are slightly reduced while allocation success rates remain at zero as this configuration does not make any special effort to allocate THP and fio is heavily active at the time and either filling memory or keeping pages resident. However, a 49% reduction of serious fragmentation events reduces the changes of external fragmentation being a problem in the future. Vlastimil asked during review for a breakdown of the allocation types that are falling back. vanilla 3816 MIGRATE_UNMOVABLE 800845 MIGRATE_MOVABLE 33 MIGRATE_UNRECLAIMABLE patch 735 MIGRATE_UNMOVABLE 408135 MIGRATE_MOVABLE 42 MIGRATE_UNRECLAIMABLE The majority of the fallbacks are due to movable allocations and this is consistent for the workload throughout the series so will not be presented again as the primary source of fallbacks are movable allocations. Movable fallbacks are sometimes considered "ok" to fallback because they can be migrated. The problem is that they can fill an unmovable/reclaimable pageblock causing those allocations to fallback later and polluting pageblocks with pages that cannot move. If there is a movable fallback, it is pretty much guaranteed to affect an unmovable/reclaimable pageblock and while it might not be enough to actually cause a unmovable/reclaimable fallback in the future, we cannot know that in advance so the patch takes the only option available to it. Hence, it's important to control them. This point is also consistent throughout the series and will not be repeated. 1-socket Skylake machine global-dhp__workload_thpfioscale-madvhugepage-xfs (MADV_HUGEPAGE) ----------------------------------------------------------------- 4.20-rc3 extfrag events < order 9: 291392 4.20-rc3+patch: 191187 (34% reduction) thpfioscale Fault Latencies 4.20.0-rc3 4.20.0-rc3 vanilla lowzone-v5r8 Amean fault-base-1 1495.14 ( 0.00%) 1467.55 ( 1.85%) Amean fault-huge-1 1098.48 ( 0.00%) 1127.11 ( -2.61%) thpfioscale Percentage Faults Huge 4.20.0-rc3 4.20.0-rc3 vanilla lowzone-v5r8 Percentage huge-1 78.57 ( 0.00%) 77.64 ( -1.18%) Fragmentation events were reduced quite a bit although this is known to be a little variable. The latencies and allocation success rates are similar but they were already quite high. 2-socket Haswell machine config-global-dhp__workload_thpfioscale XFS (no special madvise) 4 fio threads, 5 THP allocating threads ---------------------------------------------------------------- 4.20-rc3 extfrag events < order 9: 215698 4.20-rc3+patch: 200210 (7% reduction) thpfioscale Fault Latencies 4.20.0-rc3 4.20.0-rc3 vanilla lowzone-v5r8 Amean fault-base-5 1350.05 ( 0.00%) 1346.45 ( 0.27%) Amean fault-huge-5 4181.01 ( 0.00%) 3418.60 ( 18.24%) 4.20.0-rc3 4.20.0-rc3 vanilla lowzone-v5r8 Percentage huge-5 1.15 ( 0.00%) 0.78 ( -31.88%) The reduction of external fragmentation events is slight and this is partially due to the removal of __GFP_THISNODE in commit ac5b2c18911f ("mm: thp: relax __GFP_THISNODE for MADV_HUGEPAGE mappings") as THP allocations can now spill over to remote nodes instead of fragmenting local memory. 2-socket Haswell machine global-dhp__workload_thpfioscale-madvhugepage-xfs (MADV_HUGEPAGE) ----------------------------------------------------------------- 4.20-rc3 extfrag events < order 9: 166352 4.20-rc3+patch: 147463 (11% reduction) thpfioscale Fault Latencies 4.20.0-rc3 4.20.0-rc3 vanilla lowzone-v5r8 Amean fault-base-5 6138.97 ( 0.00%) 6217.43 ( -1.28%) Amean fault-huge-5 2294.28 ( 0.00%) 3163.33 * -37.88%* thpfioscale Percentage Faults Huge 4.20.0-rc3 4.20.0-rc3 vanilla lowzone-v5r8 Percentage huge-5 96.82 ( 0.00%) 95.14 ( -1.74%) There was a slight reduction in external fragmentation events although the latencies were higher. The allocation success rate is high enough that the system is struggling and there is quite a lot of parallel reclaim and compaction activity. There is also a certain degree of luck on whether processes start on node 0 or not for this patch but the relevance is reduced later in the series. Overall, the patch reduces the number of external fragmentation causing events so the success of THP over long periods of time would be improved for this adverse workload. Link: http://lkml.kernel.org/r/20181123114528.28802-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: David Rientjes <rientjes@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Zi Yan <zi.yan@cs.rutgers.edu> Cc: Michal Hocko <mhocko@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:35:41 +00:00
#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
#define ALLOC_CMA 0x80 /* allow allocations from CMA areas */
#ifdef CONFIG_ZONE_DMA32
#define ALLOC_NOFRAGMENT 0x100 /* avoid mixing pageblock types */
#else
#define ALLOC_NOFRAGMENT 0x0
#endif
#define ALLOC_HIGHATOMIC 0x200 /* Allows access to MIGRATE_HIGHATOMIC */
#define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */
/* Flags that allow allocations below the min watermark. */
#define ALLOC_RESERVES (ALLOC_NON_BLOCK|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM)
mm: send one IPI per CPU to TLB flush all entries after unmapping pages An IPI is sent to flush remote TLBs when a page is unmapped that was potentially accesssed by other CPUs. There are many circumstances where this happens but the obvious one is kswapd reclaiming pages belonging to a running process as kswapd and the task are likely running on separate CPUs. On small machines, this is not a significant problem but as machine gets larger with more cores and more memory, the cost of these IPIs can be high. This patch uses a simple structure that tracks CPUs that potentially have TLB entries for pages being unmapped. When the unmapping is complete, the full TLB is flushed on the assumption that a refill cost is lower than flushing individual entries. Architectures wishing to do this must give the following guarantee. If a clean page is unmapped and not immediately flushed, the architecture must guarantee that a write to that linear address from a CPU with a cached TLB entry will trap a page fault. This is essentially what the kernel already depends on but the window is much larger with this patch applied and is worth highlighting. The architecture should consider whether the cost of the full TLB flush is higher than sending an IPI to flush each individual entry. An additional architecture helper called flush_tlb_local is required. It's a trivial wrapper with some accounting in the x86 case. The impact of this patch depends on the workload as measuring any benefit requires both mapped pages co-located on the LRU and memory pressure. The case with the biggest impact is multiple processes reading mapped pages taken from the vm-scalability test suite. The test case uses NR_CPU readers of mapped files that consume 10*RAM. Linear mapped reader on a 4-node machine with 64G RAM and 48 CPUs 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 Ops lru-file-mmap-read-elapsed 159.62 ( 0.00%) 120.68 ( 24.40%) Ops lru-file-mmap-read-time_range 30.59 ( 0.00%) 2.80 ( 90.85%) Ops lru-file-mmap-read-time_stddv 6.70 ( 0.00%) 0.64 ( 90.38%) 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 User 581.00 611.43 System 5804.93 4111.76 Elapsed 161.03 122.12 This is showing that the readers completed 24.40% faster with 29% less system CPU time. From vmstats, it is known that the vanilla kernel was interrupted roughly 900K times per second during the steady phase of the test and the patched kernel was interrupts 180K times per second. The impact is lower on a single socket machine. 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 Ops lru-file-mmap-read-elapsed 25.33 ( 0.00%) 20.38 ( 19.54%) Ops lru-file-mmap-read-time_range 0.91 ( 0.00%) 1.44 (-58.24%) Ops lru-file-mmap-read-time_stddv 0.28 ( 0.00%) 0.47 (-65.34%) 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 User 58.09 57.64 System 111.82 76.56 Elapsed 27.29 22.55 It's still a noticeable improvement with vmstat showing interrupts went from roughly 500K per second to 45K per second. The patch will have no impact on workloads with no memory pressure or have relatively few mapped pages. It will have an unpredictable impact on the workload running on the CPU being flushed as it'll depend on how many TLB entries need to be refilled and how long that takes. Worst case, the TLB will be completely cleared of active entries when the target PFNs were not resident at all. [sasha.levin@oracle.com: trace tlb flush after disabling preemption in try_to_unmap_flush] Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Dave Hansen <dave.hansen@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Michal Hocko <mhocko@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 22:47:32 +00:00
enum ttu_flags;
struct tlbflush_unmap_batch;
mm: move pcp and lru-pcp draining into single wq We currently have 2 specific WQ_RECLAIM workqueues in the mm code. vmstat_wq for updating pcp stats and lru_add_drain_wq dedicated to drain per cpu lru caches. This seems more than necessary because both can run on a single WQ. Both do not block on locks requiring a memory allocation nor perform any allocations themselves. We will save one rescuer thread this way. On the other hand drain_all_pages() queues work on the system wq which doesn't have rescuer and so this depend on memory allocation (when all workers are stuck allocating and new ones cannot be created). Initially we thought this would be more of a theoretical problem but Hugh Dickins has reported: : 4.11-rc has been giving me hangs after hours of swapping load. At : first they looked like memory leaks ("fork: Cannot allocate memory"); : but for no good reason I happened to do "cat /proc/sys/vm/stat_refresh" : before looking at /proc/meminfo one time, and the stat_refresh stuck : in D state, waiting for completion of flush_work like many kworkers. : kthreadd waiting for completion of flush_work in drain_all_pages(). This worker should be using WQ_RECLAIM as well in order to guarantee a forward progress. We can reuse the same one as for lru draining and vmstat. Link: http://lkml.kernel.org/r/20170307131751.24936-1-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Suggested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Mel Gorman <mgorman@suse.de> Tested-by: Yang Li <pku.leo@gmail.com> Tested-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-04-07 23:05:05 +00:00
/*
* only for MM internal work items which do not depend on
* any allocations or locks which might depend on allocations
*/
extern struct workqueue_struct *mm_percpu_wq;
mm: send one IPI per CPU to TLB flush all entries after unmapping pages An IPI is sent to flush remote TLBs when a page is unmapped that was potentially accesssed by other CPUs. There are many circumstances where this happens but the obvious one is kswapd reclaiming pages belonging to a running process as kswapd and the task are likely running on separate CPUs. On small machines, this is not a significant problem but as machine gets larger with more cores and more memory, the cost of these IPIs can be high. This patch uses a simple structure that tracks CPUs that potentially have TLB entries for pages being unmapped. When the unmapping is complete, the full TLB is flushed on the assumption that a refill cost is lower than flushing individual entries. Architectures wishing to do this must give the following guarantee. If a clean page is unmapped and not immediately flushed, the architecture must guarantee that a write to that linear address from a CPU with a cached TLB entry will trap a page fault. This is essentially what the kernel already depends on but the window is much larger with this patch applied and is worth highlighting. The architecture should consider whether the cost of the full TLB flush is higher than sending an IPI to flush each individual entry. An additional architecture helper called flush_tlb_local is required. It's a trivial wrapper with some accounting in the x86 case. The impact of this patch depends on the workload as measuring any benefit requires both mapped pages co-located on the LRU and memory pressure. The case with the biggest impact is multiple processes reading mapped pages taken from the vm-scalability test suite. The test case uses NR_CPU readers of mapped files that consume 10*RAM. Linear mapped reader on a 4-node machine with 64G RAM and 48 CPUs 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 Ops lru-file-mmap-read-elapsed 159.62 ( 0.00%) 120.68 ( 24.40%) Ops lru-file-mmap-read-time_range 30.59 ( 0.00%) 2.80 ( 90.85%) Ops lru-file-mmap-read-time_stddv 6.70 ( 0.00%) 0.64 ( 90.38%) 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 User 581.00 611.43 System 5804.93 4111.76 Elapsed 161.03 122.12 This is showing that the readers completed 24.40% faster with 29% less system CPU time. From vmstats, it is known that the vanilla kernel was interrupted roughly 900K times per second during the steady phase of the test and the patched kernel was interrupts 180K times per second. The impact is lower on a single socket machine. 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 Ops lru-file-mmap-read-elapsed 25.33 ( 0.00%) 20.38 ( 19.54%) Ops lru-file-mmap-read-time_range 0.91 ( 0.00%) 1.44 (-58.24%) Ops lru-file-mmap-read-time_stddv 0.28 ( 0.00%) 0.47 (-65.34%) 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 User 58.09 57.64 System 111.82 76.56 Elapsed 27.29 22.55 It's still a noticeable improvement with vmstat showing interrupts went from roughly 500K per second to 45K per second. The patch will have no impact on workloads with no memory pressure or have relatively few mapped pages. It will have an unpredictable impact on the workload running on the CPU being flushed as it'll depend on how many TLB entries need to be refilled and how long that takes. Worst case, the TLB will be completely cleared of active entries when the target PFNs were not resident at all. [sasha.levin@oracle.com: trace tlb flush after disabling preemption in try_to_unmap_flush] Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Dave Hansen <dave.hansen@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Michal Hocko <mhocko@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 22:47:32 +00:00
#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
void try_to_unmap_flush(void);
void try_to_unmap_flush_dirty(void);
mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries Nadav Amit identified a theoritical race between page reclaim and mprotect due to TLB flushes being batched outside of the PTL being held. He described the race as follows: CPU0 CPU1 ---- ---- user accesses memory using RW PTE [PTE now cached in TLB] try_to_unmap_one() ==> ptep_get_and_clear() ==> set_tlb_ubc_flush_pending() mprotect(addr, PROT_READ) ==> change_pte_range() ==> [ PTE non-present - no flush ] user writes using cached RW PTE ... try_to_unmap_flush() The same type of race exists for reads when protecting for PROT_NONE and also exists for operations that can leave an old TLB entry behind such as munmap, mremap and madvise. For some operations like mprotect, it's not necessarily a data integrity issue but it is a correctness issue as there is a window where an mprotect that limits access still allows access. For munmap, it's potentially a data integrity issue although the race is massive as an munmap, mmap and return to userspace must all complete between the window when reclaim drops the PTL and flushes the TLB. However, it's theoritically possible so handle this issue by flushing the mm if reclaim is potentially currently batching TLB flushes. Other instances where a flush is required for a present pte should be ok as either the page lock is held preventing parallel reclaim or a page reference count is elevated preventing a parallel free leading to corruption. In the case of page_mkclean there isn't an obvious path that userspace could take advantage of without using the operations that are guarded by this patch. Other users such as gup as a race with reclaim looks just at PTEs. huge page variants should be ok as they don't race with reclaim. mincore only looks at PTEs. userfault also should be ok as if a parallel reclaim takes place, it will either fault the page back in or read some of the data before the flush occurs triggering a fault. Note that a variant of this patch was acked by Andy Lutomirski but this was for the x86 parts on top of his PCID work which didn't make the 4.13 merge window as expected. His ack is dropped from this version and there will be a follow-on patch on top of PCID that will include his ack. [akpm@linux-foundation.org: tweak comments] [akpm@linux-foundation.org: fix spello] Link: http://lkml.kernel.org/r/20170717155523.emckq2esjro6hf3z@suse.de Reported-by: Nadav Amit <nadav.amit@gmail.com> Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@kernel.org> Cc: <stable@vger.kernel.org> [v4.4+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-02 20:31:52 +00:00
void flush_tlb_batched_pending(struct mm_struct *mm);
mm: send one IPI per CPU to TLB flush all entries after unmapping pages An IPI is sent to flush remote TLBs when a page is unmapped that was potentially accesssed by other CPUs. There are many circumstances where this happens but the obvious one is kswapd reclaiming pages belonging to a running process as kswapd and the task are likely running on separate CPUs. On small machines, this is not a significant problem but as machine gets larger with more cores and more memory, the cost of these IPIs can be high. This patch uses a simple structure that tracks CPUs that potentially have TLB entries for pages being unmapped. When the unmapping is complete, the full TLB is flushed on the assumption that a refill cost is lower than flushing individual entries. Architectures wishing to do this must give the following guarantee. If a clean page is unmapped and not immediately flushed, the architecture must guarantee that a write to that linear address from a CPU with a cached TLB entry will trap a page fault. This is essentially what the kernel already depends on but the window is much larger with this patch applied and is worth highlighting. The architecture should consider whether the cost of the full TLB flush is higher than sending an IPI to flush each individual entry. An additional architecture helper called flush_tlb_local is required. It's a trivial wrapper with some accounting in the x86 case. The impact of this patch depends on the workload as measuring any benefit requires both mapped pages co-located on the LRU and memory pressure. The case with the biggest impact is multiple processes reading mapped pages taken from the vm-scalability test suite. The test case uses NR_CPU readers of mapped files that consume 10*RAM. Linear mapped reader on a 4-node machine with 64G RAM and 48 CPUs 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 Ops lru-file-mmap-read-elapsed 159.62 ( 0.00%) 120.68 ( 24.40%) Ops lru-file-mmap-read-time_range 30.59 ( 0.00%) 2.80 ( 90.85%) Ops lru-file-mmap-read-time_stddv 6.70 ( 0.00%) 0.64 ( 90.38%) 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 User 581.00 611.43 System 5804.93 4111.76 Elapsed 161.03 122.12 This is showing that the readers completed 24.40% faster with 29% less system CPU time. From vmstats, it is known that the vanilla kernel was interrupted roughly 900K times per second during the steady phase of the test and the patched kernel was interrupts 180K times per second. The impact is lower on a single socket machine. 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 Ops lru-file-mmap-read-elapsed 25.33 ( 0.00%) 20.38 ( 19.54%) Ops lru-file-mmap-read-time_range 0.91 ( 0.00%) 1.44 (-58.24%) Ops lru-file-mmap-read-time_stddv 0.28 ( 0.00%) 0.47 (-65.34%) 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 User 58.09 57.64 System 111.82 76.56 Elapsed 27.29 22.55 It's still a noticeable improvement with vmstat showing interrupts went from roughly 500K per second to 45K per second. The patch will have no impact on workloads with no memory pressure or have relatively few mapped pages. It will have an unpredictable impact on the workload running on the CPU being flushed as it'll depend on how many TLB entries need to be refilled and how long that takes. Worst case, the TLB will be completely cleared of active entries when the target PFNs were not resident at all. [sasha.levin@oracle.com: trace tlb flush after disabling preemption in try_to_unmap_flush] Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Dave Hansen <dave.hansen@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Michal Hocko <mhocko@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 22:47:32 +00:00
#else
static inline void try_to_unmap_flush(void)
{
}
static inline void try_to_unmap_flush_dirty(void)
{
}
mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries Nadav Amit identified a theoritical race between page reclaim and mprotect due to TLB flushes being batched outside of the PTL being held. He described the race as follows: CPU0 CPU1 ---- ---- user accesses memory using RW PTE [PTE now cached in TLB] try_to_unmap_one() ==> ptep_get_and_clear() ==> set_tlb_ubc_flush_pending() mprotect(addr, PROT_READ) ==> change_pte_range() ==> [ PTE non-present - no flush ] user writes using cached RW PTE ... try_to_unmap_flush() The same type of race exists for reads when protecting for PROT_NONE and also exists for operations that can leave an old TLB entry behind such as munmap, mremap and madvise. For some operations like mprotect, it's not necessarily a data integrity issue but it is a correctness issue as there is a window where an mprotect that limits access still allows access. For munmap, it's potentially a data integrity issue although the race is massive as an munmap, mmap and return to userspace must all complete between the window when reclaim drops the PTL and flushes the TLB. However, it's theoritically possible so handle this issue by flushing the mm if reclaim is potentially currently batching TLB flushes. Other instances where a flush is required for a present pte should be ok as either the page lock is held preventing parallel reclaim or a page reference count is elevated preventing a parallel free leading to corruption. In the case of page_mkclean there isn't an obvious path that userspace could take advantage of without using the operations that are guarded by this patch. Other users such as gup as a race with reclaim looks just at PTEs. huge page variants should be ok as they don't race with reclaim. mincore only looks at PTEs. userfault also should be ok as if a parallel reclaim takes place, it will either fault the page back in or read some of the data before the flush occurs triggering a fault. Note that a variant of this patch was acked by Andy Lutomirski but this was for the x86 parts on top of his PCID work which didn't make the 4.13 merge window as expected. His ack is dropped from this version and there will be a follow-on patch on top of PCID that will include his ack. [akpm@linux-foundation.org: tweak comments] [akpm@linux-foundation.org: fix spello] Link: http://lkml.kernel.org/r/20170717155523.emckq2esjro6hf3z@suse.de Reported-by: Nadav Amit <nadav.amit@gmail.com> Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@kernel.org> Cc: <stable@vger.kernel.org> [v4.4+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-02 20:31:52 +00:00
static inline void flush_tlb_batched_pending(struct mm_struct *mm)
{
}
mm: send one IPI per CPU to TLB flush all entries after unmapping pages An IPI is sent to flush remote TLBs when a page is unmapped that was potentially accesssed by other CPUs. There are many circumstances where this happens but the obvious one is kswapd reclaiming pages belonging to a running process as kswapd and the task are likely running on separate CPUs. On small machines, this is not a significant problem but as machine gets larger with more cores and more memory, the cost of these IPIs can be high. This patch uses a simple structure that tracks CPUs that potentially have TLB entries for pages being unmapped. When the unmapping is complete, the full TLB is flushed on the assumption that a refill cost is lower than flushing individual entries. Architectures wishing to do this must give the following guarantee. If a clean page is unmapped and not immediately flushed, the architecture must guarantee that a write to that linear address from a CPU with a cached TLB entry will trap a page fault. This is essentially what the kernel already depends on but the window is much larger with this patch applied and is worth highlighting. The architecture should consider whether the cost of the full TLB flush is higher than sending an IPI to flush each individual entry. An additional architecture helper called flush_tlb_local is required. It's a trivial wrapper with some accounting in the x86 case. The impact of this patch depends on the workload as measuring any benefit requires both mapped pages co-located on the LRU and memory pressure. The case with the biggest impact is multiple processes reading mapped pages taken from the vm-scalability test suite. The test case uses NR_CPU readers of mapped files that consume 10*RAM. Linear mapped reader on a 4-node machine with 64G RAM and 48 CPUs 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 Ops lru-file-mmap-read-elapsed 159.62 ( 0.00%) 120.68 ( 24.40%) Ops lru-file-mmap-read-time_range 30.59 ( 0.00%) 2.80 ( 90.85%) Ops lru-file-mmap-read-time_stddv 6.70 ( 0.00%) 0.64 ( 90.38%) 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 User 581.00 611.43 System 5804.93 4111.76 Elapsed 161.03 122.12 This is showing that the readers completed 24.40% faster with 29% less system CPU time. From vmstats, it is known that the vanilla kernel was interrupted roughly 900K times per second during the steady phase of the test and the patched kernel was interrupts 180K times per second. The impact is lower on a single socket machine. 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 Ops lru-file-mmap-read-elapsed 25.33 ( 0.00%) 20.38 ( 19.54%) Ops lru-file-mmap-read-time_range 0.91 ( 0.00%) 1.44 (-58.24%) Ops lru-file-mmap-read-time_stddv 0.28 ( 0.00%) 0.47 (-65.34%) 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 User 58.09 57.64 System 111.82 76.56 Elapsed 27.29 22.55 It's still a noticeable improvement with vmstat showing interrupts went from roughly 500K per second to 45K per second. The patch will have no impact on workloads with no memory pressure or have relatively few mapped pages. It will have an unpredictable impact on the workload running on the CPU being flushed as it'll depend on how many TLB entries need to be refilled and how long that takes. Worst case, the TLB will be completely cleared of active entries when the target PFNs were not resident at all. [sasha.levin@oracle.com: trace tlb flush after disabling preemption in try_to_unmap_flush] Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Dave Hansen <dave.hansen@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Michal Hocko <mhocko@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 22:47:32 +00:00
#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */
mm, printk: introduce new format string for flags In mm we use several kinds of flags bitfields that are sometimes printed for debugging purposes, or exported to userspace via sysfs. To make them easier to interpret independently on kernel version and config, we want to dump also the symbolic flag names. So far this has been done with repeated calls to pr_cont(), which is unreliable on SMP, and not usable for e.g. sysfs export. To get a more reliable and universal solution, this patch extends printk() format string for pointers to handle the page flags (%pGp), gfp_flags (%pGg) and vma flags (%pGv). Existing users of dump_flag_names() are converted and simplified. It would be possible to pass flags by value instead of pointer, but the %p format string for pointers already has extensions for various kernel structures, so it's a good fit, and the extra indirection in a non-critical path is negligible. [linux@rasmusvillemoes.dk: lots of good implementation suggestions] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:56 +00:00
extern const struct trace_print_flags pageflag_names[];
extern const struct trace_print_flags vmaflag_names[];
extern const struct trace_print_flags gfpflag_names[];
static inline bool is_migrate_highatomic(enum migratetype migratetype)
{
return migratetype == MIGRATE_HIGHATOMIC;
}
void setup_zone_pageset(struct zone *zone);
mm/migrate: introduce a standard migration target allocation function There are some similar functions for migration target allocation. Since there is no fundamental difference, it's better to keep just one rather than keeping all variants. This patch implements base migration target allocation function. In the following patches, variants will be converted to use this function. Changes should be mechanical, but, unfortunately, there are some differences. First, some callers' nodemask is assgined to NULL since NULL nodemask will be considered as all available nodes, that is, &node_states[N_MEMORY]. Second, for hugetlb page allocation, gfp_mask is redefined as regular hugetlb allocation gfp_mask plus __GFP_THISNODE if user provided gfp_mask has it. This is because future caller of this function requires to set this node constaint. Lastly, if provided nodeid is NUMA_NO_NODE, nodeid is set up to the node where migration source lives. It helps to remove simple wrappers for setting up the nodeid. Note that PageHighmem() call in previous function is changed to open-code "is_highmem_idx()" since it provides more readability. [akpm@linux-foundation.org: tweak patch title, per Vlastimil] [akpm@linux-foundation.org: fix typo in comment] Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Roman Gushchin <guro@fb.com> Link: http://lkml.kernel.org/r/1594622517-20681-6-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 01:37:25 +00:00
struct migration_target_control {
int nid; /* preferred node id */
nodemask_t *nmask;
gfp_t gfp_mask;
mm: record the migration reason for struct migration_target_control Patch series "make the hugetlb migration strategy consistent", v2. As discussed in previous thread [1], there is an inconsistency when handling hugetlb migration. When handling the migration of freed hugetlb, it prevents fallback to other NUMA nodes in alloc_and_dissolve_hugetlb_folio(). However, when dealing with in-use hugetlb, it allows fallback to other NUMA nodes in alloc_hugetlb_folio_nodemask(), which can break the per-node hugetlb pool and might result in unexpected failures when node bound workloads doesn't get what is asssumed available. This patchset tries to make the hugetlb migration strategy more clear and consistent. Please find details in each patch. [1] https://lore.kernel.org/all/6f26ce22d2fcd523418a085f2c588fe0776d46e7.1706794035.git.baolin.wang@linux.alibaba.com/ This patch (of 2): To support different hugetlb allocation strategies during hugetlb migration based on various migration reasons, record the migration reason in the migration_target_control structure as a preparation. Link: https://lkml.kernel.org/r/cover.1709719720.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/7b95d4981e07211f57139fc5b1f7ce91b920cee4.1709719720.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: David Hildenbrand <david@redhat.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Naoya Horiguchi <nao.horiguchi@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-03-06 10:13:26 +00:00
enum migrate_reason reason;
mm/migrate: introduce a standard migration target allocation function There are some similar functions for migration target allocation. Since there is no fundamental difference, it's better to keep just one rather than keeping all variants. This patch implements base migration target allocation function. In the following patches, variants will be converted to use this function. Changes should be mechanical, but, unfortunately, there are some differences. First, some callers' nodemask is assgined to NULL since NULL nodemask will be considered as all available nodes, that is, &node_states[N_MEMORY]. Second, for hugetlb page allocation, gfp_mask is redefined as regular hugetlb allocation gfp_mask plus __GFP_THISNODE if user provided gfp_mask has it. This is because future caller of this function requires to set this node constaint. Lastly, if provided nodeid is NUMA_NO_NODE, nodeid is set up to the node where migration source lives. It helps to remove simple wrappers for setting up the nodeid. Note that PageHighmem() call in previous function is changed to open-code "is_highmem_idx()" since it provides more readability. [akpm@linux-foundation.org: tweak patch title, per Vlastimil] [akpm@linux-foundation.org: fix typo in comment] Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Roman Gushchin <guro@fb.com> Link: http://lkml.kernel.org/r/1594622517-20681-6-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 01:37:25 +00:00
};
/*
* mm/filemap.c
*/
size_t splice_folio_into_pipe(struct pipe_inode_info *pipe,
struct folio *folio, loff_t fpos, size_t size);
/*
* mm/vmalloc.c
*/
#ifdef CONFIG_MMU
void __init vmalloc_init(void);
int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end,
pgprot_t prot, struct page **pages, unsigned int page_shift);
#else
static inline void vmalloc_init(void)
{
}
static inline
int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end,
pgprot_t prot, struct page **pages, unsigned int page_shift)
{
return -EINVAL;
}
#endif
int __must_check __vmap_pages_range_noflush(unsigned long addr,
unsigned long end, pgprot_t prot,
struct page **pages, unsigned int page_shift);
mm: kmsan: maintain KMSAN metadata for page operations Insert KMSAN hooks that make the necessary bookkeeping changes: - poison page shadow and origins in alloc_pages()/free_page(); - clear page shadow and origins in clear_page(), copy_user_highpage(); - copy page metadata in copy_highpage(), wp_page_copy(); - handle vmap()/vunmap()/iounmap(); Link: https://lkml.kernel.org/r/20220915150417.722975-15-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 15:03:48 +00:00
void vunmap_range_noflush(unsigned long start, unsigned long end);
mm: kmsan: maintain KMSAN metadata for page operations Insert KMSAN hooks that make the necessary bookkeeping changes: - poison page shadow and origins in alloc_pages()/free_page(); - clear page shadow and origins in clear_page(), copy_user_highpage(); - copy page metadata in copy_highpage(), wp_page_copy(); - handle vmap()/vunmap()/iounmap(); Link: https://lkml.kernel.org/r/20220915150417.722975-15-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 15:03:48 +00:00
void __vunmap_range_noflush(unsigned long start, unsigned long end);
int numa_migrate_check(struct folio *folio, struct vm_fault *vmf,
unsigned long addr, int *flags, bool writable,
int *last_cpupid);
void free_zone_device_folio(struct folio *folio);
int migrate_device_coherent_folio(struct folio *folio);
mm: remove the extra ZONE_DEVICE struct page refcount ZONE_DEVICE struct pages have an extra reference count that complicates the code for put_page() and several places in the kernel that need to check the reference count to see that a page is not being used (gup, compaction, migration, etc.). Clean up the code so the reference count doesn't need to be treated specially for ZONE_DEVICE pages. Note that this excludes the special idle page wakeup for fsdax pages, which still happens at refcount 1. This is a separate issue and will be sorted out later. Given that only fsdax pages require the notifiacation when the refcount hits 1 now, the PAGEMAP_OPS Kconfig symbol can go away and be replaced with a FS_DAX check for this hook in the put_page fastpath. Based on an earlier patch from Ralph Campbell <rcampbell@nvidia.com>. Link: https://lkml.kernel.org/r/20220210072828.2930359-8-hch@lst.de Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Logan Gunthorpe <logang@deltatee.com> Reviewed-by: Ralph Campbell <rcampbell@nvidia.com> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Reviewed-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Tested-by: "Sierra Guiza, Alejandro (Alex)" <alex.sierra@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Chaitanya Kulkarni <kch@nvidia.com> Cc: Christian Knig <christian.koenig@amd.com> Cc: Karol Herbst <kherbst@redhat.com> Cc: Lyude Paul <lyude@redhat.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Muchun Song <songmuchun@bytedance.com> Cc: "Pan, Xinhui" <Xinhui.Pan@amd.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2022-02-16 04:31:36 +00:00
/*
* mm/gup.c
*/
mm: gup: stop abusing try_grab_folio A kernel warning was reported when pinning folio in CMA memory when launching SEV virtual machine. The splat looks like: [ 464.325306] WARNING: CPU: 13 PID: 6734 at mm/gup.c:1313 __get_user_pages+0x423/0x520 [ 464.325464] CPU: 13 PID: 6734 Comm: qemu-kvm Kdump: loaded Not tainted 6.6.33+ #6 [ 464.325477] RIP: 0010:__get_user_pages+0x423/0x520 [ 464.325515] Call Trace: [ 464.325520] <TASK> [ 464.325523] ? __get_user_pages+0x423/0x520 [ 464.325528] ? __warn+0x81/0x130 [ 464.325536] ? __get_user_pages+0x423/0x520 [ 464.325541] ? report_bug+0x171/0x1a0 [ 464.325549] ? handle_bug+0x3c/0x70 [ 464.325554] ? exc_invalid_op+0x17/0x70 [ 464.325558] ? asm_exc_invalid_op+0x1a/0x20 [ 464.325567] ? __get_user_pages+0x423/0x520 [ 464.325575] __gup_longterm_locked+0x212/0x7a0 [ 464.325583] internal_get_user_pages_fast+0xfb/0x190 [ 464.325590] pin_user_pages_fast+0x47/0x60 [ 464.325598] sev_pin_memory+0xca/0x170 [kvm_amd] [ 464.325616] sev_mem_enc_register_region+0x81/0x130 [kvm_amd] Per the analysis done by yangge, when starting the SEV virtual machine, it will call pin_user_pages_fast(..., FOLL_LONGTERM, ...) to pin the memory. But the page is in CMA area, so fast GUP will fail then fallback to the slow path due to the longterm pinnalbe check in try_grab_folio(). The slow path will try to pin the pages then migrate them out of CMA area. But the slow path also uses try_grab_folio() to pin the page, it will also fail due to the same check then the above warning is triggered. In addition, the try_grab_folio() is supposed to be used in fast path and it elevates folio refcount by using add ref unless zero. We are guaranteed to have at least one stable reference in slow path, so the simple atomic add could be used. The performance difference should be trivial, but the misuse may be confusing and misleading. Redefined try_grab_folio() to try_grab_folio_fast(), and try_grab_page() to try_grab_folio(), and use them in the proper paths. This solves both the abuse and the kernel warning. The proper naming makes their usecase more clear and should prevent from abusing in the future. peterx said: : The user will see the pin fails, for gpu-slow it further triggers the WARN : right below that failure (as in the original report): : : folio = try_grab_folio(page, page_increm - 1, : foll_flags); : if (WARN_ON_ONCE(!folio)) { <------------------------ here : /* : * Release the 1st page ref if the : * folio is problematic, fail hard. : */ : gup_put_folio(page_folio(page), 1, : foll_flags); : ret = -EFAULT; : goto out; : } [1] https://lore.kernel.org/linux-mm/1719478388-31917-1-git-send-email-yangge1116@126.com/ [shy828301@gmail.com: fix implicit declaration of function try_grab_folio_fast] Link: https://lkml.kernel.org/r/CAHbLzkowMSso-4Nufc9hcMehQsK9PNz3OSu-+eniU-2Mm-xjhA@mail.gmail.com Link: https://lkml.kernel.org/r/20240628191458.2605553-1-yang@os.amperecomputing.com Fixes: 57edfcfd3419 ("mm/gup: accelerate thp gup even for "pages != NULL"") Signed-off-by: Yang Shi <yang@os.amperecomputing.com> Reported-by: yangge <yangge1116@126.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: David Hildenbrand <david@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: <stable@vger.kernel.org> [6.6+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-06-28 19:14:58 +00:00
int __must_check try_grab_folio(struct folio *folio, int refs,
unsigned int flags);
smaps: use vm_normal_page_pmd() instead of follow_trans_huge_pmd() We shouldn't be using a GUP-internal helper if it can be avoided. Similar to smaps_pte_entry() that uses vm_normal_page(), let's use vm_normal_page_pmd() that similarly refuses to return the huge zeropage. In contrast to follow_trans_huge_pmd(), vm_normal_page_pmd(): (1) Will always return the head page, not a tail page of a THP. If we'd ever call smaps_account with a tail page while setting "compound = true", we could be in trouble, because smaps_account() would look at the memmap of unrelated pages. If we're unlucky, that memmap does not exist at all. Before we removed PG_doublemap, we could have triggered something similar as in commit 24d7275ce279 ("fs/proc: task_mmu.c: don't read mapcount for migration entry"). This can theoretically happen ever since commit ff9f47f6f00c ("mm: proc: smaps_rollup: do not stall write attempts on mmap_lock"): (a) We're in show_smaps_rollup() and processed a VMA (b) We release the mmap lock in show_smaps_rollup() because it is contended (c) We merged that VMA with another VMA (d) We collapsed a THP in that merged VMA at that position If the end address of the original VMA falls into the middle of a THP area, we would call smap_gather_stats() with a start address that falls into a PMD-mapped THP. It's probably very rare to trigger when not really forced. (2) Will succeed on a is_pci_p2pdma_page(), like vm_normal_page() Treat such PMDs here just like smaps_pte_entry() would treat such PTEs. If such pages would be anonymous, we most certainly would want to account them. (3) Will skip over pmd_devmap(), like vm_normal_page() for pte_devmap() As noted in vm_normal_page(), that is only for handling legacy ZONE_DEVICE pages. So just like smaps_pte_entry(), we'll now also ignore such PMD entries. Especially, follow_pmd_mask() never ends up calling follow_trans_huge_pmd() on pmd_devmap(). Instead it calls follow_devmap_pmd() -- which will fail if neither FOLL_GET nor FOLL_PIN is set. So skipping pmd_devmap() pages seems to be the right thing to do. (4) Will properly handle VM_MIXEDMAP/VM_PFNMAP, like vm_normal_page() We won't be returning a memmap that should be ignored by core-mm, or worse, a memmap that does not even exist. Note that while walk_page_range() will skip VM_PFNMAP mappings, walk_page_vma() won't. Most probably this case doesn't currently really happen on the PMD level, otherwise we'd already be able to trigger kernel crashes when reading smaps / smaps_rollup. So most probably only (1) is relevant in practice as of now, but could only cause trouble in extreme corner cases. Let's move follow_trans_huge_pmd() to mm/internal.h to discourage future reuse in wrong context. Link: https://lkml.kernel.org/r/20230803143208.383663-3-david@redhat.com Fixes: ff9f47f6f00c ("mm: proc: smaps_rollup: do not stall write attempts on mmap_lock") Signed-off-by: David Hildenbrand <david@redhat.com> Acked-by: Mel Gorman <mgorman@techsingularity.net> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: liubo <liubo254@huawei.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-08-03 14:32:03 +00:00
/*
* mm/huge_memory.c
*/
mm/gup: handle huge pud for follow_pud_mask() Teach follow_pud_mask() to be able to handle normal PUD pages like hugetlb. Rename follow_devmap_pud() to follow_huge_pud() so that it can process either huge devmap or hugetlb. Move it out of TRANSPARENT_HUGEPAGE_PUD and and huge_memory.c (which relies on CONFIG_THP). Switch to pud_leaf() to detect both cases in the slow gup. In the new follow_huge_pud(), taking care of possible CoR for hugetlb if necessary. touch_pud() needs to be moved out of huge_memory.c to be accessable from gup.c even if !THP. Since at it, optimize the non-present check by adding a pud_present() early check before taking the pgtable lock, failing the follow_page() early if PUD is not present: that is required by both devmap or hugetlb. Use pud_huge() to also cover the pud_devmap() case. One more trivial thing to mention is, introduce "pud_t pud" in the code paths along the way, so the code doesn't dereference *pudp multiple time. Not only because that looks less straightforward, but also because if the dereference really happened, it's not clear whether there can be race to see different *pudp values when it's being modified at the same time. Setting ctx->page_mask properly for a PUD entry. As a side effect, this patch should also be able to optimize devmap GUP on PUD to be able to jump over the whole PUD range, but not yet verified. Hugetlb already can do so prior to this patch. Link: https://lkml.kernel.org/r/20240327152332.950956-11-peterx@redhat.com Signed-off-by: Peter Xu <peterx@redhat.com> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Tested-by: Ryan Roberts <ryan.roberts@arm.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Andrew Jones <andrew.jones@linux.dev> Cc: Aneesh Kumar K.V (IBM) <aneesh.kumar@kernel.org> 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: James Houghton <jthoughton@google.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: "Mike Rapoport (IBM)" <rppt@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Rik van Riel <riel@surriel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-03-27 15:23:29 +00:00
void touch_pud(struct vm_area_struct *vma, unsigned long addr,
pud_t *pud, bool write);
mm/gup: handle huge pmd for follow_pmd_mask() Replace pmd_trans_huge() with pmd_leaf() to also cover pmd_huge() as long as enabled. FOLL_TOUCH and FOLL_SPLIT_PMD only apply to THP, not yet huge. Since now follow_trans_huge_pmd() can process hugetlb pages, renaming it into follow_huge_pmd() to match what it does. Move it into gup.c so not depend on CONFIG_THP. When at it, move the ctx->page_mask setup into follow_huge_pmd(), only set it when the page is valid. It was not a bug to set it before even if GUP failed (page==NULL), because follow_page_mask() callers always ignores page_mask if so. But doing so makes the code cleaner. [peterx@redhat.com: allow follow_pmd_mask() to take hugetlb tail pages] Link: https://lkml.kernel.org/r/20240403013249.1418299-3-peterx@redhat.com Link: https://lkml.kernel.org/r/20240327152332.950956-12-peterx@redhat.com Signed-off-by: Peter Xu <peterx@redhat.com> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Tested-by: Ryan Roberts <ryan.roberts@arm.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Andrew Jones <andrew.jones@linux.dev> Cc: Aneesh Kumar K.V (IBM) <aneesh.kumar@kernel.org> 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: James Houghton <jthoughton@google.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: "Mike Rapoport (IBM)" <rppt@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Rik van Riel <riel@surriel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-03-27 15:23:30 +00:00
void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd, bool write);
smaps: use vm_normal_page_pmd() instead of follow_trans_huge_pmd() We shouldn't be using a GUP-internal helper if it can be avoided. Similar to smaps_pte_entry() that uses vm_normal_page(), let's use vm_normal_page_pmd() that similarly refuses to return the huge zeropage. In contrast to follow_trans_huge_pmd(), vm_normal_page_pmd(): (1) Will always return the head page, not a tail page of a THP. If we'd ever call smaps_account with a tail page while setting "compound = true", we could be in trouble, because smaps_account() would look at the memmap of unrelated pages. If we're unlucky, that memmap does not exist at all. Before we removed PG_doublemap, we could have triggered something similar as in commit 24d7275ce279 ("fs/proc: task_mmu.c: don't read mapcount for migration entry"). This can theoretically happen ever since commit ff9f47f6f00c ("mm: proc: smaps_rollup: do not stall write attempts on mmap_lock"): (a) We're in show_smaps_rollup() and processed a VMA (b) We release the mmap lock in show_smaps_rollup() because it is contended (c) We merged that VMA with another VMA (d) We collapsed a THP in that merged VMA at that position If the end address of the original VMA falls into the middle of a THP area, we would call smap_gather_stats() with a start address that falls into a PMD-mapped THP. It's probably very rare to trigger when not really forced. (2) Will succeed on a is_pci_p2pdma_page(), like vm_normal_page() Treat such PMDs here just like smaps_pte_entry() would treat such PTEs. If such pages would be anonymous, we most certainly would want to account them. (3) Will skip over pmd_devmap(), like vm_normal_page() for pte_devmap() As noted in vm_normal_page(), that is only for handling legacy ZONE_DEVICE pages. So just like smaps_pte_entry(), we'll now also ignore such PMD entries. Especially, follow_pmd_mask() never ends up calling follow_trans_huge_pmd() on pmd_devmap(). Instead it calls follow_devmap_pmd() -- which will fail if neither FOLL_GET nor FOLL_PIN is set. So skipping pmd_devmap() pages seems to be the right thing to do. (4) Will properly handle VM_MIXEDMAP/VM_PFNMAP, like vm_normal_page() We won't be returning a memmap that should be ignored by core-mm, or worse, a memmap that does not even exist. Note that while walk_page_range() will skip VM_PFNMAP mappings, walk_page_vma() won't. Most probably this case doesn't currently really happen on the PMD level, otherwise we'd already be able to trigger kernel crashes when reading smaps / smaps_rollup. So most probably only (1) is relevant in practice as of now, but could only cause trouble in extreme corner cases. Let's move follow_trans_huge_pmd() to mm/internal.h to discourage future reuse in wrong context. Link: https://lkml.kernel.org/r/20230803143208.383663-3-david@redhat.com Fixes: ff9f47f6f00c ("mm: proc: smaps_rollup: do not stall write attempts on mmap_lock") Signed-off-by: David Hildenbrand <david@redhat.com> Acked-by: Mel Gorman <mgorman@techsingularity.net> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: liubo <liubo254@huawei.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-08-03 14:32:03 +00:00
enum {
/* mark page accessed */
FOLL_TOUCH = 1 << 16,
/* a retry, previous pass started an IO */
FOLL_TRIED = 1 << 17,
/* we are working on non-current tsk/mm */
FOLL_REMOTE = 1 << 18,
/* pages must be released via unpin_user_page */
FOLL_PIN = 1 << 19,
/* gup_fast: prevent fall-back to slow gup */
FOLL_FAST_ONLY = 1 << 20,
/* allow unlocking the mmap lock */
FOLL_UNLOCKABLE = 1 << 21,
mm/madvise: make MADV_POPULATE_(READ|WRITE) handle VM_FAULT_RETRY properly Darrick reports that in some cases where pread() would fail with -EIO and mmap()+access would generate a SIGBUS signal, MADV_POPULATE_READ / MADV_POPULATE_WRITE will keep retrying forever and not fail with -EFAULT. While the madvise() call can be interrupted by a signal, this is not the desired behavior. MADV_POPULATE_READ / MADV_POPULATE_WRITE should behave like page faults in that case: fail and not retry forever. A reproducer can be found at [1]. The reason is that __get_user_pages(), as called by faultin_vma_page_range(), will not handle VM_FAULT_RETRY in a proper way: it will simply return 0 when VM_FAULT_RETRY happened, making madvise_populate()->faultin_vma_page_range() retry again and again, never setting FOLL_TRIED->FAULT_FLAG_TRIED for __get_user_pages(). __get_user_pages_locked() does what we want, but duplicating that logic in faultin_vma_page_range() feels wrong. So let's use __get_user_pages_locked() instead, that will detect VM_FAULT_RETRY and set FOLL_TRIED when retrying, making the fault handler return VM_FAULT_SIGBUS (VM_FAULT_ERROR) at some point, propagating -EFAULT from faultin_page() to __get_user_pages(), all the way to madvise_populate(). But, there is an issue: __get_user_pages_locked() will end up re-taking the MM lock and then __get_user_pages() will do another VMA lookup. In the meantime, the VMA layout could have changed and we'd fail with different error codes than we'd want to. As __get_user_pages() will currently do a new VMA lookup either way, let it do the VMA handling in a different way, controlled by a new FOLL_MADV_POPULATE flag, effectively moving these checks from madvise_populate() + faultin_page_range() in there. With this change, Darricks reproducer properly fails with -EFAULT, as documented for MADV_POPULATE_READ / MADV_POPULATE_WRITE. [1] https://lore.kernel.org/all/20240313171936.GN1927156@frogsfrogsfrogs/ Link: https://lkml.kernel.org/r/20240314161300.382526-1-david@redhat.com Link: https://lkml.kernel.org/r/20240314161300.382526-2-david@redhat.com Fixes: 4ca9b3859dac ("mm/madvise: introduce MADV_POPULATE_(READ|WRITE) to prefault page tables") Signed-off-by: David Hildenbrand <david@redhat.com> Reported-by: Darrick J. Wong <djwong@kernel.org> Closes: https://lore.kernel.org/all/20240311223815.GW1927156@frogsfrogsfrogs/ Cc: Darrick J. Wong <djwong@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-03-14 16:12:59 +00:00
/* VMA lookup+checks compatible with MADV_POPULATE_(READ|WRITE) */
FOLL_MADV_POPULATE = 1 << 22,
};
#define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \
mm/madvise: make MADV_POPULATE_(READ|WRITE) handle VM_FAULT_RETRY properly Darrick reports that in some cases where pread() would fail with -EIO and mmap()+access would generate a SIGBUS signal, MADV_POPULATE_READ / MADV_POPULATE_WRITE will keep retrying forever and not fail with -EFAULT. While the madvise() call can be interrupted by a signal, this is not the desired behavior. MADV_POPULATE_READ / MADV_POPULATE_WRITE should behave like page faults in that case: fail and not retry forever. A reproducer can be found at [1]. The reason is that __get_user_pages(), as called by faultin_vma_page_range(), will not handle VM_FAULT_RETRY in a proper way: it will simply return 0 when VM_FAULT_RETRY happened, making madvise_populate()->faultin_vma_page_range() retry again and again, never setting FOLL_TRIED->FAULT_FLAG_TRIED for __get_user_pages(). __get_user_pages_locked() does what we want, but duplicating that logic in faultin_vma_page_range() feels wrong. So let's use __get_user_pages_locked() instead, that will detect VM_FAULT_RETRY and set FOLL_TRIED when retrying, making the fault handler return VM_FAULT_SIGBUS (VM_FAULT_ERROR) at some point, propagating -EFAULT from faultin_page() to __get_user_pages(), all the way to madvise_populate(). But, there is an issue: __get_user_pages_locked() will end up re-taking the MM lock and then __get_user_pages() will do another VMA lookup. In the meantime, the VMA layout could have changed and we'd fail with different error codes than we'd want to. As __get_user_pages() will currently do a new VMA lookup either way, let it do the VMA handling in a different way, controlled by a new FOLL_MADV_POPULATE flag, effectively moving these checks from madvise_populate() + faultin_page_range() in there. With this change, Darricks reproducer properly fails with -EFAULT, as documented for MADV_POPULATE_READ / MADV_POPULATE_WRITE. [1] https://lore.kernel.org/all/20240313171936.GN1927156@frogsfrogsfrogs/ Link: https://lkml.kernel.org/r/20240314161300.382526-1-david@redhat.com Link: https://lkml.kernel.org/r/20240314161300.382526-2-david@redhat.com Fixes: 4ca9b3859dac ("mm/madvise: introduce MADV_POPULATE_(READ|WRITE) to prefault page tables") Signed-off-by: David Hildenbrand <david@redhat.com> Reported-by: Darrick J. Wong <djwong@kernel.org> Closes: https://lore.kernel.org/all/20240311223815.GW1927156@frogsfrogsfrogs/ Cc: Darrick J. Wong <djwong@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-03-14 16:12:59 +00:00
FOLL_FAST_ONLY | FOLL_UNLOCKABLE | \
FOLL_MADV_POPULATE)
/*
* Indicates for which pages that are write-protected in the page table,
* whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the
* GUP pin will remain consistent with the pages mapped into the page tables
* of the MM.
*
* Temporary unmapping of PageAnonExclusive() pages or clearing of
* PageAnonExclusive() has to protect against concurrent GUP:
* * Ordinary GUP: Using the PT lock
* * GUP-fast and fork(): mm->write_protect_seq
* * GUP-fast and KSM or temporary unmapping (swap, migration): see
* folio_try_share_anon_rmap_*()
*
* Must be called with the (sub)page that's actually referenced via the
* page table entry, which might not necessarily be the head page for a
* PTE-mapped THP.
*
* If the vma is NULL, we're coming from the GUP-fast path and might have
* to fallback to the slow path just to lookup the vma.
*/
static inline bool gup_must_unshare(struct vm_area_struct *vma,
unsigned int flags, struct page *page)
{
/*
* FOLL_WRITE is implicitly handled correctly as the page table entry
* has to be writable -- and if it references (part of) an anonymous
* folio, that part is required to be marked exclusive.
*/
if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN)
return false;
/*
* Note: PageAnon(page) is stable until the page is actually getting
* freed.
*/
if (!PageAnon(page)) {
/*
* We only care about R/O long-term pining: R/O short-term
* pinning does not have the semantics to observe successive
* changes through the process page tables.
*/
if (!(flags & FOLL_LONGTERM))
return false;
/* We really need the vma ... */
if (!vma)
return true;
/*
* ... because we only care about writable private ("COW")
* mappings where we have to break COW early.
*/
return is_cow_mapping(vma->vm_flags);
}
/* Paired with a memory barrier in folio_try_share_anon_rmap_*(). */
if (IS_ENABLED(CONFIG_HAVE_GUP_FAST))
smp_rmb();
/*
* Note that PageKsm() pages cannot be exclusive, and consequently,
* cannot get pinned.
*/
return !PageAnonExclusive(page);
}
extern bool mirrored_kernelcore;
extern bool memblock_has_mirror(void);
static __always_inline void vma_set_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
pgoff_t pgoff)
{
vma->vm_start = start;
vma->vm_end = end;
vma->vm_pgoff = pgoff;
}
mm/mprotect: fix soft-dirty check in can_change_pte_writable() Patch series "mm/mprotect: Fix soft-dirty checks", v4. This patch (of 3): The check wanted to make sure when soft-dirty tracking is enabled we won't grant write bit by accident, as a page fault is needed for dirty tracking. The intention is correct but we didn't check it right because VM_SOFTDIRTY set actually means soft-dirty tracking disabled. Fix it. There's another thing tricky about soft-dirty is that, we can't check the vma flag !(vma_flags & VM_SOFTDIRTY) directly but only check it after we checked CONFIG_MEM_SOFT_DIRTY because otherwise VM_SOFTDIRTY will be defined as zero, and !(vma_flags & VM_SOFTDIRTY) will constantly return true. To avoid misuse, introduce a helper for checking whether vma has soft-dirty tracking enabled. We can easily verify this with any exclusive anonymous page, like program below: =======8<====== #include <stdio.h> #include <unistd.h> #include <stdlib.h> #include <assert.h> #include <inttypes.h> #include <stdint.h> #include <sys/types.h> #include <sys/mman.h> #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> #include <fcntl.h> #include <stdbool.h> #define BIT_ULL(nr) (1ULL << (nr)) #define PM_SOFT_DIRTY BIT_ULL(55) unsigned int psize; char *page; uint64_t pagemap_read_vaddr(int fd, void *vaddr) { uint64_t value; int ret; ret = pread(fd, &value, sizeof(uint64_t), ((uint64_t)vaddr >> 12) * sizeof(uint64_t)); assert(ret == sizeof(uint64_t)); return value; } void clear_refs_write(void) { int fd = open("/proc/self/clear_refs", O_RDWR); assert(fd >= 0); write(fd, "4", 2); close(fd); } #define check_soft_dirty(str, expect) do { \ bool dirty = pagemap_read_vaddr(fd, page) & PM_SOFT_DIRTY; \ if (dirty != expect) { \ printf("ERROR: %s, soft-dirty=%d (expect: %d) ", str, dirty, expect); \ exit(-1); \ } \ } while (0) int main(void) { int fd = open("/proc/self/pagemap", O_RDONLY); assert(fd >= 0); psize = getpagesize(); page = mmap(NULL, psize, PROT_READ|PROT_WRITE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); assert(page != MAP_FAILED); *page = 1; check_soft_dirty("Just faulted in page", 1); clear_refs_write(); check_soft_dirty("Clear_refs written", 0); mprotect(page, psize, PROT_READ); check_soft_dirty("Marked RO", 0); mprotect(page, psize, PROT_READ|PROT_WRITE); check_soft_dirty("Marked RW", 0); *page = 2; check_soft_dirty("Wrote page again", 1); munmap(page, psize); close(fd); printf("Test passed. "); return 0; } =======8<====== Here we attach a Fixes to commit 64fe24a3e05e only for easy tracking, as this patch won't apply to a tree before that point. However the commit wasn't the source of problem, but instead 64e455079e1b. It's just that after 64fe24a3e05e anonymous memory will also suffer from this problem with mprotect(). Link: https://lkml.kernel.org/r/20220725142048.30450-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220725142048.30450-2-peterx@redhat.com Fixes: 64e455079e1b ("mm: softdirty: enable write notifications on VMAs after VM_SOFTDIRTY cleared") Fixes: 64fe24a3e05e ("mm/mprotect: try avoiding write faults for exclusive anonymous pages when changing protection") Signed-off-by: Peter Xu <peterx@redhat.com> Reviewed-by: David Hildenbrand <david@redhat.com> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-07-25 14:20:46 +00:00
static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma)
{
/*
* NOTE: we must check this before VM_SOFTDIRTY on soft-dirty
* enablements, because when without soft-dirty being compiled in,
* VM_SOFTDIRTY is defined as 0x0, then !(vm_flags & VM_SOFTDIRTY)
* will be constantly true.
*/
if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY))
return false;
/*
* Soft-dirty is kind of special: its tracking is enabled when the
* vma flags not set.
*/
return !(vma->vm_flags & VM_SOFTDIRTY);
}
static inline bool pmd_needs_soft_dirty_wp(struct vm_area_struct *vma, pmd_t pmd)
{
return vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd);
}
static inline bool pte_needs_soft_dirty_wp(struct vm_area_struct *vma, pte_t pte)
{
return vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte);
}
mm: hugetlb: skip initialization of gigantic tail struct pages if freed by HVO The new boot flow when it comes to initialization of gigantic pages is as follows: - At boot time, for a gigantic page during __alloc_bootmem_hugepage, the region after the first struct page is marked as noinit. - This results in only the first struct page to be initialized in reserve_bootmem_region. As the tail struct pages are not initialized at this point, there can be a significant saving in boot time if HVO succeeds later on. - Later on in the boot, the head page is prepped and the first HUGETLB_VMEMMAP_RESERVE_SIZE / sizeof(struct page) - 1 tail struct pages are initialized. - HVO is attempted. If it is not successful, then the rest of the tail struct pages are initialized. If it is successful, no more tail struct pages need to be initialized saving significant boot time. The WARN_ON for increased ref count in gather_bootmem_prealloc was changed to a VM_BUG_ON. This is OK as there should be no speculative references this early in boot process. The VM_BUG_ON's are there just in case such code is introduced. [akpm@linux-foundation.org: make it nicer for 80 cols] Link: https://lkml.kernel.org/r/20230913105401.519709-5-usama.arif@bytedance.com Signed-off-by: Usama Arif <usama.arif@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Fam Zheng <fam.zheng@bytedance.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Punit Agrawal <punit.agrawal@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-13 10:54:01 +00:00
void __meminit __init_single_page(struct page *page, unsigned long pfn,
unsigned long zone, int nid);
mm: move some shrinker-related function declarations to mm/internal.h Patch series "cleanups for lockless slab shrink", v4. This series is some cleanups for lockless slab shrink. This patch (of 4): The following functions are only used inside the mm subsystem, so it's better to move their declarations to the mm/internal.h file. 1. shrinker_debugfs_add() 2. shrinker_debugfs_detach() 3. shrinker_debugfs_remove() Link: https://lkml.kernel.org/r/20230911092517.64141-1-zhengqi.arch@bytedance.com Link: https://lkml.kernel.org/r/20230911092517.64141-2-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christian König <christian.koenig@amd.com> Cc: Chuck Lever <cel@kernel.org> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Darrick J. Wong <djwong@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Joel Fernandes <joel@joelfernandes.org> Cc: Kirill Tkhai <tkhai@ya.ru> Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Steven Price <steven.price@arm.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Abhinav Kumar <quic_abhinavk@quicinc.com> Cc: Alasdair Kergon <agk@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Andreas Gruenbacher <agruenba@redhat.com> Cc: Anna Schumaker <anna@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Bob Peterson <rpeterso@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Carlos Llamas <cmllamas@google.com> Cc: Chandan Babu R <chandan.babu@oracle.com> Cc: Chao Yu <chao@kernel.org> Cc: Chris Mason <clm@fb.com> Cc: Coly Li <colyli@suse.de> Cc: Dai Ngo <Dai.Ngo@oracle.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Airlie <airlied@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Sterba <dsterba@suse.com> Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Cc: Gao Xiang <hsiangkao@linux.alibaba.com> Cc: Huang Rui <ray.huang@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Jason Wang <jasowang@redhat.com> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jeffle Xu <jefflexu@linux.alibaba.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Juergen Gross <jgross@suse.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Marijn Suijten <marijn.suijten@somainline.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Mike Snitzer <snitzer@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Nadav Amit <namit@vmware.com> Cc: Neil Brown <neilb@suse.de> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Olga Kornievskaia <kolga@netapp.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rob Clark <robdclark@gmail.com> Cc: Rob Herring <robh@kernel.org> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Sean Paul <sean@poorly.run> Cc: Song Liu <song@kernel.org> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com> Cc: Tom Talpey <tom@talpey.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Cc: Yue Hu <huyue2@coolpad.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-11 09:25:14 +00:00
/* shrinker related functions */
mm: vmscan: move shrinker-related code into a separate file The mm/vmscan.c file is too large, so separate the shrinker-related code from it into a separate file. No functional changes. Link: https://lkml.kernel.org/r/20230911092517.64141-3-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christian König <christian.koenig@amd.com> Cc: Chuck Lever <cel@kernel.org> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Darrick J. Wong <djwong@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Joel Fernandes <joel@joelfernandes.org> Cc: Kirill Tkhai <tkhai@ya.ru> Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Steven Price <steven.price@arm.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Abhinav Kumar <quic_abhinavk@quicinc.com> Cc: Alasdair Kergon <agk@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Andreas Gruenbacher <agruenba@redhat.com> Cc: Anna Schumaker <anna@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Bob Peterson <rpeterso@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Carlos Llamas <cmllamas@google.com> Cc: Chandan Babu R <chandan.babu@oracle.com> Cc: Chao Yu <chao@kernel.org> Cc: Chris Mason <clm@fb.com> Cc: Coly Li <colyli@suse.de> Cc: Dai Ngo <Dai.Ngo@oracle.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Airlie <airlied@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Sterba <dsterba@suse.com> Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Cc: Gao Xiang <hsiangkao@linux.alibaba.com> Cc: Huang Rui <ray.huang@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Jason Wang <jasowang@redhat.com> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jeffle Xu <jefflexu@linux.alibaba.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Juergen Gross <jgross@suse.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Marijn Suijten <marijn.suijten@somainline.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Mike Snitzer <snitzer@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Nadav Amit <namit@vmware.com> Cc: Neil Brown <neilb@suse.de> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Olga Kornievskaia <kolga@netapp.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rob Clark <robdclark@gmail.com> Cc: Rob Herring <robh@kernel.org> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Sean Paul <sean@poorly.run> Cc: Song Liu <song@kernel.org> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com> Cc: Tom Talpey <tom@talpey.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Cc: Yue Hu <huyue2@coolpad.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-11 09:25:15 +00:00
unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg,
int priority);
mm: move some shrinker-related function declarations to mm/internal.h Patch series "cleanups for lockless slab shrink", v4. This series is some cleanups for lockless slab shrink. This patch (of 4): The following functions are only used inside the mm subsystem, so it's better to move their declarations to the mm/internal.h file. 1. shrinker_debugfs_add() 2. shrinker_debugfs_detach() 3. shrinker_debugfs_remove() Link: https://lkml.kernel.org/r/20230911092517.64141-1-zhengqi.arch@bytedance.com Link: https://lkml.kernel.org/r/20230911092517.64141-2-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christian König <christian.koenig@amd.com> Cc: Chuck Lever <cel@kernel.org> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Darrick J. Wong <djwong@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Joel Fernandes <joel@joelfernandes.org> Cc: Kirill Tkhai <tkhai@ya.ru> Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Steven Price <steven.price@arm.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Abhinav Kumar <quic_abhinavk@quicinc.com> Cc: Alasdair Kergon <agk@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Andreas Gruenbacher <agruenba@redhat.com> Cc: Anna Schumaker <anna@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Bob Peterson <rpeterso@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Carlos Llamas <cmllamas@google.com> Cc: Chandan Babu R <chandan.babu@oracle.com> Cc: Chao Yu <chao@kernel.org> Cc: Chris Mason <clm@fb.com> Cc: Coly Li <colyli@suse.de> Cc: Dai Ngo <Dai.Ngo@oracle.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Airlie <airlied@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Sterba <dsterba@suse.com> Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Cc: Gao Xiang <hsiangkao@linux.alibaba.com> Cc: Huang Rui <ray.huang@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Jason Wang <jasowang@redhat.com> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jeffle Xu <jefflexu@linux.alibaba.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Juergen Gross <jgross@suse.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Marijn Suijten <marijn.suijten@somainline.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Mike Snitzer <snitzer@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Nadav Amit <namit@vmware.com> Cc: Neil Brown <neilb@suse.de> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Olga Kornievskaia <kolga@netapp.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rob Clark <robdclark@gmail.com> Cc: Rob Herring <robh@kernel.org> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Sean Paul <sean@poorly.run> Cc: Song Liu <song@kernel.org> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com> Cc: Tom Talpey <tom@talpey.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Cc: Yue Hu <huyue2@coolpad.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-11 09:25:14 +00:00
mseal: add mseal syscall The new mseal() is an syscall on 64 bit CPU, and with following signature: int mseal(void addr, size_t len, unsigned long flags) addr/len: memory range. flags: reserved. mseal() blocks following operations for the given memory range. 1> Unmapping, moving to another location, and shrinking the size, via munmap() and mremap(), can leave an empty space, therefore can be replaced with a VMA with a new set of attributes. 2> Moving or expanding a different VMA into the current location, via mremap(). 3> Modifying a VMA via mmap(MAP_FIXED). 4> Size expansion, via mremap(), does not appear to pose any specific risks to sealed VMAs. It is included anyway because the use case is unclear. In any case, users can rely on merging to expand a sealed VMA. 5> mprotect() and pkey_mprotect(). 6> Some destructive madvice() behaviors (e.g. MADV_DONTNEED) for anonymous memory, when users don't have write permission to the memory. Those behaviors can alter region contents by discarding pages, effectively a memset(0) for anonymous memory. Following input during RFC are incooperated into this patch: Jann Horn: raising awareness and providing valuable insights on the destructive madvise operations. Linus Torvalds: assisting in defining system call signature and scope. Liam R. Howlett: perf optimization. Theo de Raadt: sharing the experiences and insight gained from implementing mimmutable() in OpenBSD. Finally, the idea that inspired this patch comes from Stephen Röttger's work in Chrome V8 CFI. [jeffxu@chromium.org: add branch prediction hint, per Pedro] Link: https://lkml.kernel.org/r/20240423192825.1273679-2-jeffxu@chromium.org Link: https://lkml.kernel.org/r/20240415163527.626541-3-jeffxu@chromium.org Signed-off-by: Jeff Xu <jeffxu@chromium.org> Reviewed-by: Kees Cook <keescook@chromium.org> Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com> Cc: Pedro Falcato <pedro.falcato@gmail.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Guenter Roeck <groeck@chromium.org> Cc: Jann Horn <jannh@google.com> Cc: Jeff Xu <jeffxu@google.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Jorge Lucangeli Obes <jorgelo@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Muhammad Usama Anjum <usama.anjum@collabora.com> Cc: Pedro Falcato <pedro.falcato@gmail.com> Cc: Stephen Röttger <sroettger@google.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Amer Al Shanawany <amer.shanawany@gmail.com> Cc: Javier Carrasco <javier.carrasco.cruz@gmail.com> Cc: Shuah Khan <shuah@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-15 16:35:21 +00:00
#ifdef CONFIG_64BIT
static inline int can_do_mseal(unsigned long flags)
{
if (flags)
return -EINVAL;
return 0;
}
#else
static inline int can_do_mseal(unsigned long flags)
{
return -EPERM;
}
#endif
mm: move some shrinker-related function declarations to mm/internal.h Patch series "cleanups for lockless slab shrink", v4. This series is some cleanups for lockless slab shrink. This patch (of 4): The following functions are only used inside the mm subsystem, so it's better to move their declarations to the mm/internal.h file. 1. shrinker_debugfs_add() 2. shrinker_debugfs_detach() 3. shrinker_debugfs_remove() Link: https://lkml.kernel.org/r/20230911092517.64141-1-zhengqi.arch@bytedance.com Link: https://lkml.kernel.org/r/20230911092517.64141-2-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christian König <christian.koenig@amd.com> Cc: Chuck Lever <cel@kernel.org> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Darrick J. Wong <djwong@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Joel Fernandes <joel@joelfernandes.org> Cc: Kirill Tkhai <tkhai@ya.ru> Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Steven Price <steven.price@arm.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Abhinav Kumar <quic_abhinavk@quicinc.com> Cc: Alasdair Kergon <agk@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Andreas Gruenbacher <agruenba@redhat.com> Cc: Anna Schumaker <anna@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Bob Peterson <rpeterso@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Carlos Llamas <cmllamas@google.com> Cc: Chandan Babu R <chandan.babu@oracle.com> Cc: Chao Yu <chao@kernel.org> Cc: Chris Mason <clm@fb.com> Cc: Coly Li <colyli@suse.de> Cc: Dai Ngo <Dai.Ngo@oracle.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Airlie <airlied@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Sterba <dsterba@suse.com> Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Cc: Gao Xiang <hsiangkao@linux.alibaba.com> Cc: Huang Rui <ray.huang@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Jason Wang <jasowang@redhat.com> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jeffle Xu <jefflexu@linux.alibaba.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Juergen Gross <jgross@suse.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Marijn Suijten <marijn.suijten@somainline.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Mike Snitzer <snitzer@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Nadav Amit <namit@vmware.com> Cc: Neil Brown <neilb@suse.de> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Olga Kornievskaia <kolga@netapp.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rob Clark <robdclark@gmail.com> Cc: Rob Herring <robh@kernel.org> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Sean Paul <sean@poorly.run> Cc: Song Liu <song@kernel.org> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com> Cc: Tom Talpey <tom@talpey.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Cc: Yue Hu <huyue2@coolpad.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-11 09:25:14 +00:00
#ifdef CONFIG_SHRINKER_DEBUG
static inline __printf(2, 0) int shrinker_debugfs_name_alloc(
struct shrinker *shrinker, const char *fmt, va_list ap)
mm: shrinker: add infrastructure for dynamically allocating shrinker Patch series "use refcount+RCU method to implement lockless slab shrink", v6. 1. Background ============= We used to implement the lockless slab shrink with SRCU [1], but then kernel test robot reported -88.8% regression in stress-ng.ramfs.ops_per_sec test case [2], so we reverted it [3]. This patch series aims to re-implement the lockless slab shrink using the refcount+RCU method proposed by Dave Chinner [4]. [1]. https://lore.kernel.org/lkml/20230313112819.38938-1-zhengqi.arch@bytedance.com/ [2]. https://lore.kernel.org/lkml/202305230837.db2c233f-yujie.liu@intel.com/ [3]. https://lore.kernel.org/all/20230609081518.3039120-1-qi.zheng@linux.dev/ [4]. https://lore.kernel.org/lkml/ZIJhou1d55d4H1s0@dread.disaster.area/ 2. Implementation ================= Currently, the shrinker instances can be divided into the following three types: a) global shrinker instance statically defined in the kernel, such as workingset_shadow_shrinker. b) global shrinker instance statically defined in the kernel modules, such as mmu_shrinker in x86. c) shrinker instance embedded in other structures. For case a, the memory of shrinker instance is never freed. For case b, the memory of shrinker instance will be freed after synchronize_rcu() when the module is unloaded. For case c, the memory of shrinker instance will be freed along with the structure it is embedded in. In preparation for implementing lockless slab shrink, we need to dynamically allocate those shrinker instances in case c, then the memory can be dynamically freed alone by calling kfree_rcu(). This patchset adds the following new APIs for dynamically allocating shrinker, and add a private_data field to struct shrinker to record and get the original embedded structure. 1. shrinker_alloc() 2. shrinker_register() 3. shrinker_free() In order to simplify shrinker-related APIs and make shrinker more independent of other kernel mechanisms, this patchset uses the above APIs to convert all shrinkers (including case a and b) to dynamically allocated, and then remove all existing APIs. This will also have another advantage mentioned by Dave Chinner: ``` The other advantage of this is that it will break all the existing out of tree code and third party modules using the old API and will no longer work with a kernel using lockless slab shrinkers. They need to break (both at the source and binary levels) to stop bad things from happening due to using uncoverted shrinkers in the new setup. ``` Then we free the shrinker by calling call_rcu(), and use rcu_read_{lock,unlock}() to ensure that the shrinker instance is valid. And the shrinker::refcount mechanism ensures that the shrinker instance will not be run again after unregistration. So the structure that records the pointer of shrinker instance can be safely freed without waiting for the RCU read-side critical section. In this way, while we implement the lockless slab shrink, we don't need to be blocked in unregister_shrinker() to wait RCU read-side critical section. PATCH 1: introduce new APIs PATCH 2~38: convert all shrinnkers to use new APIs PATCH 39: remove old APIs PATCH 40~41: some cleanups and preparations PATCH 42-43: implement the lockless slab shrink PATCH 44~45: convert shrinker_rwsem to mutex 3. Testing ========== 3.1 slab shrink stress test --------------------------- We can reproduce the down_read_trylock() hotspot through the following script: ``` DIR="/root/shrinker/memcg/mnt" do_create() { mkdir -p /sys/fs/cgroup/memory/test echo 4G > /sys/fs/cgroup/memory/test/memory.limit_in_bytes for i in `seq 0 $1`; do mkdir -p /sys/fs/cgroup/memory/test/$i; echo $$ > /sys/fs/cgroup/memory/test/$i/cgroup.procs; mkdir -p $DIR/$i; done } do_mount() { for i in `seq $1 $2`; do mount -t tmpfs $i $DIR/$i; done } do_touch() { for i in `seq $1 $2`; do echo $$ > /sys/fs/cgroup/memory/test/$i/cgroup.procs; dd if=/dev/zero of=$DIR/$i/file$i bs=1M count=1 & done } case "$1" in touch) do_touch $2 $3 ;; test) do_create 4000 do_mount 0 4000 do_touch 0 3000 ;; *) exit 1 ;; esac ``` Save the above script, then run test and touch commands. Then we can use the following perf command to view hotspots: perf top -U -F 999 1) Before applying this patchset: 33.15% [kernel] [k] down_read_trylock 25.38% [kernel] [k] shrink_slab 21.75% [kernel] [k] up_read 4.45% [kernel] [k] _find_next_bit 2.27% [kernel] [k] do_shrink_slab 1.80% [kernel] [k] intel_idle_irq 1.79% [kernel] [k] shrink_lruvec 0.67% [kernel] [k] xas_descend 0.41% [kernel] [k] mem_cgroup_iter 0.40% [kernel] [k] shrink_node 0.38% [kernel] [k] list_lru_count_one 2) After applying this patchset: 64.56% [kernel] [k] shrink_slab 12.18% [kernel] [k] do_shrink_slab 3.30% [kernel] [k] __rcu_read_unlock 2.61% [kernel] [k] shrink_lruvec 2.49% [kernel] [k] __rcu_read_lock 1.93% [kernel] [k] intel_idle_irq 0.89% [kernel] [k] shrink_node 0.81% [kernel] [k] mem_cgroup_iter 0.77% [kernel] [k] mem_cgroup_calculate_protection 0.66% [kernel] [k] list_lru_count_one We can see that the first perf hotspot becomes shrink_slab, which is what we expect. 3.2 registration and unregistration stress test ----------------------------------------------- Run the command below to test: stress-ng --timeout 60 --times --verify --metrics-brief --ramfs 9 & 1) Before applying this patchset: setting to a 60 second run per stressor dispatching hogs: 9 ramfs stressor bogo ops real time usr time sys time bogo ops/s bogo ops/s (secs) (secs) (secs) (real time) (usr+sys time) ramfs 473062 60.00 8.00 279.13 7884.12 1647.59 for a 60.01s run time: 1440.34s available CPU time 7.99s user time ( 0.55%) 279.13s system time ( 19.38%) 287.12s total time ( 19.93%) load average: 7.12 2.99 1.15 successful run completed in 60.01s (1 min, 0.01 secs) 2) After applying this patchset: setting to a 60 second run per stressor dispatching hogs: 9 ramfs stressor bogo ops real time usr time sys time bogo ops/s bogo ops/s (secs) (secs) (secs) (real time) (usr+sys time) ramfs 477165 60.00 8.13 281.34 7952.55 1648.40 for a 60.01s run time: 1440.33s available CPU time 8.12s user time ( 0.56%) 281.34s system time ( 19.53%) 289.46s total time ( 20.10%) load average: 6.98 3.03 1.19 successful run completed in 60.01s (1 min, 0.01 secs) We can see that the ops/s has hardly changed. This patch (of 45): Currently, the shrinker instances can be divided into the following three types: a) global shrinker instance statically defined in the kernel, such as workingset_shadow_shrinker. b) global shrinker instance statically defined in the kernel modules, such as mmu_shrinker in x86. c) shrinker instance embedded in other structures. For case a, the memory of shrinker instance is never freed. For case b, the memory of shrinker instance will be freed after synchronize_rcu() when the module is unloaded. For case c, the memory of shrinker instance will be freed along with the structure it is embedded in. In preparation for implementing lockless slab shrink, we need to dynamically allocate those shrinker instances in case c, then the memory can be dynamically freed alone by calling kfree_rcu(). So this commit adds the following new APIs for dynamically allocating shrinker, and add a private_data field to struct shrinker to record and get the original embedded structure. 1. shrinker_alloc() Used to allocate shrinker instance itself and related memory, it will return a pointer to the shrinker instance on success and NULL on failure. 2. shrinker_register() Used to register the shrinker instance, which is same as the current register_shrinker_prepared(). 3. shrinker_free() Used to unregister (if needed) and free the shrinker instance. In order to simplify shrinker-related APIs and make shrinker more independent of other kernel mechanisms, subsequent submissions will use the above API to convert all shrinkers (including case a and b) to dynamically allocated, and then remove all existing APIs. This will also have another advantage mentioned by Dave Chinner: ``` The other advantage of this is that it will break all the existing out of tree code and third party modules using the old API and will no longer work with a kernel using lockless slab shrinkers. They need to break (both at the source and binary levels) to stop bad things from happening due to using unconverted shrinkers in the new setup. ``` [zhengqi.arch@bytedance.com: mm: shrinker: some cleanup] Link: https://lkml.kernel.org/r/20230919024607.65463-1-zhengqi.arch@bytedance.com Link: https://lkml.kernel.org/r/20230911094444.68966-1-zhengqi.arch@bytedance.com Link: https://lkml.kernel.org/r/20230911094444.68966-2-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Chuck Lever <cel@kernel.org> Cc: Darrick J. Wong <djwong@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Kirill Tkhai <tkhai@ya.ru> Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Steven Price <steven.price@arm.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Abhinav Kumar <quic_abhinavk@quicinc.com> Cc: Alasdair Kergon <agk@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Andreas Gruenbacher <agruenba@redhat.com> Cc: Anna Schumaker <anna@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Bob Peterson <rpeterso@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Carlos Llamas <cmllamas@google.com> Cc: Chandan Babu R <chandan.babu@oracle.com> Cc: Chao Yu <chao@kernel.org> Cc: Chris Mason <clm@fb.com> Cc: Christian Koenig <christian.koenig@amd.com> Cc: Coly Li <colyli@suse.de> Cc: Dai Ngo <Dai.Ngo@oracle.com> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Airlie <airlied@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Sterba <dsterba@suse.com> Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Cc: Gao Xiang <hsiangkao@linux.alibaba.com> Cc: Huang Rui <ray.huang@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Jason Wang <jasowang@redhat.com> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jeffle Xu <jefflexu@linux.alibaba.com> Cc: Joel Fernandes (Google) <joel@joelfernandes.org> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Juergen Gross <jgross@suse.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Marijn Suijten <marijn.suijten@somainline.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Mike Snitzer <snitzer@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Nadav Amit <namit@vmware.com> Cc: Neil Brown <neilb@suse.de> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Olga Kornievskaia <kolga@netapp.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rob Clark <robdclark@gmail.com> Cc: Rob Herring <robh@kernel.org> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Sean Paul <sean@poorly.run> Cc: Song Liu <song@kernel.org> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com> Cc: Tom Talpey <tom@talpey.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Cc: Yue Hu <huyue2@coolpad.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-11 09:44:00 +00:00
{
shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap);
return shrinker->name ? 0 : -ENOMEM;
}
static inline void shrinker_debugfs_name_free(struct shrinker *shrinker)
{
kfree_const(shrinker->name);
shrinker->name = NULL;
}
mm: move some shrinker-related function declarations to mm/internal.h Patch series "cleanups for lockless slab shrink", v4. This series is some cleanups for lockless slab shrink. This patch (of 4): The following functions are only used inside the mm subsystem, so it's better to move their declarations to the mm/internal.h file. 1. shrinker_debugfs_add() 2. shrinker_debugfs_detach() 3. shrinker_debugfs_remove() Link: https://lkml.kernel.org/r/20230911092517.64141-1-zhengqi.arch@bytedance.com Link: https://lkml.kernel.org/r/20230911092517.64141-2-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christian König <christian.koenig@amd.com> Cc: Chuck Lever <cel@kernel.org> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Darrick J. Wong <djwong@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Joel Fernandes <joel@joelfernandes.org> Cc: Kirill Tkhai <tkhai@ya.ru> Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Steven Price <steven.price@arm.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Abhinav Kumar <quic_abhinavk@quicinc.com> Cc: Alasdair Kergon <agk@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Andreas Gruenbacher <agruenba@redhat.com> Cc: Anna Schumaker <anna@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Bob Peterson <rpeterso@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Carlos Llamas <cmllamas@google.com> Cc: Chandan Babu R <chandan.babu@oracle.com> Cc: Chao Yu <chao@kernel.org> Cc: Chris Mason <clm@fb.com> Cc: Coly Li <colyli@suse.de> Cc: Dai Ngo <Dai.Ngo@oracle.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Airlie <airlied@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Sterba <dsterba@suse.com> Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Cc: Gao Xiang <hsiangkao@linux.alibaba.com> Cc: Huang Rui <ray.huang@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Jason Wang <jasowang@redhat.com> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jeffle Xu <jefflexu@linux.alibaba.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Juergen Gross <jgross@suse.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Marijn Suijten <marijn.suijten@somainline.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Mike Snitzer <snitzer@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Nadav Amit <namit@vmware.com> Cc: Neil Brown <neilb@suse.de> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Olga Kornievskaia <kolga@netapp.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rob Clark <robdclark@gmail.com> Cc: Rob Herring <robh@kernel.org> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Sean Paul <sean@poorly.run> Cc: Song Liu <song@kernel.org> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com> Cc: Tom Talpey <tom@talpey.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Cc: Yue Hu <huyue2@coolpad.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-11 09:25:14 +00:00
extern int shrinker_debugfs_add(struct shrinker *shrinker);
extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker,
int *debugfs_id);
extern void shrinker_debugfs_remove(struct dentry *debugfs_entry,
int debugfs_id);
#else /* CONFIG_SHRINKER_DEBUG */
static inline int shrinker_debugfs_add(struct shrinker *shrinker)
{
return 0;
}
mm: shrinker: add infrastructure for dynamically allocating shrinker Patch series "use refcount+RCU method to implement lockless slab shrink", v6. 1. Background ============= We used to implement the lockless slab shrink with SRCU [1], but then kernel test robot reported -88.8% regression in stress-ng.ramfs.ops_per_sec test case [2], so we reverted it [3]. This patch series aims to re-implement the lockless slab shrink using the refcount+RCU method proposed by Dave Chinner [4]. [1]. https://lore.kernel.org/lkml/20230313112819.38938-1-zhengqi.arch@bytedance.com/ [2]. https://lore.kernel.org/lkml/202305230837.db2c233f-yujie.liu@intel.com/ [3]. https://lore.kernel.org/all/20230609081518.3039120-1-qi.zheng@linux.dev/ [4]. https://lore.kernel.org/lkml/ZIJhou1d55d4H1s0@dread.disaster.area/ 2. Implementation ================= Currently, the shrinker instances can be divided into the following three types: a) global shrinker instance statically defined in the kernel, such as workingset_shadow_shrinker. b) global shrinker instance statically defined in the kernel modules, such as mmu_shrinker in x86. c) shrinker instance embedded in other structures. For case a, the memory of shrinker instance is never freed. For case b, the memory of shrinker instance will be freed after synchronize_rcu() when the module is unloaded. For case c, the memory of shrinker instance will be freed along with the structure it is embedded in. In preparation for implementing lockless slab shrink, we need to dynamically allocate those shrinker instances in case c, then the memory can be dynamically freed alone by calling kfree_rcu(). This patchset adds the following new APIs for dynamically allocating shrinker, and add a private_data field to struct shrinker to record and get the original embedded structure. 1. shrinker_alloc() 2. shrinker_register() 3. shrinker_free() In order to simplify shrinker-related APIs and make shrinker more independent of other kernel mechanisms, this patchset uses the above APIs to convert all shrinkers (including case a and b) to dynamically allocated, and then remove all existing APIs. This will also have another advantage mentioned by Dave Chinner: ``` The other advantage of this is that it will break all the existing out of tree code and third party modules using the old API and will no longer work with a kernel using lockless slab shrinkers. They need to break (both at the source and binary levels) to stop bad things from happening due to using uncoverted shrinkers in the new setup. ``` Then we free the shrinker by calling call_rcu(), and use rcu_read_{lock,unlock}() to ensure that the shrinker instance is valid. And the shrinker::refcount mechanism ensures that the shrinker instance will not be run again after unregistration. So the structure that records the pointer of shrinker instance can be safely freed without waiting for the RCU read-side critical section. In this way, while we implement the lockless slab shrink, we don't need to be blocked in unregister_shrinker() to wait RCU read-side critical section. PATCH 1: introduce new APIs PATCH 2~38: convert all shrinnkers to use new APIs PATCH 39: remove old APIs PATCH 40~41: some cleanups and preparations PATCH 42-43: implement the lockless slab shrink PATCH 44~45: convert shrinker_rwsem to mutex 3. Testing ========== 3.1 slab shrink stress test --------------------------- We can reproduce the down_read_trylock() hotspot through the following script: ``` DIR="/root/shrinker/memcg/mnt" do_create() { mkdir -p /sys/fs/cgroup/memory/test echo 4G > /sys/fs/cgroup/memory/test/memory.limit_in_bytes for i in `seq 0 $1`; do mkdir -p /sys/fs/cgroup/memory/test/$i; echo $$ > /sys/fs/cgroup/memory/test/$i/cgroup.procs; mkdir -p $DIR/$i; done } do_mount() { for i in `seq $1 $2`; do mount -t tmpfs $i $DIR/$i; done } do_touch() { for i in `seq $1 $2`; do echo $$ > /sys/fs/cgroup/memory/test/$i/cgroup.procs; dd if=/dev/zero of=$DIR/$i/file$i bs=1M count=1 & done } case "$1" in touch) do_touch $2 $3 ;; test) do_create 4000 do_mount 0 4000 do_touch 0 3000 ;; *) exit 1 ;; esac ``` Save the above script, then run test and touch commands. Then we can use the following perf command to view hotspots: perf top -U -F 999 1) Before applying this patchset: 33.15% [kernel] [k] down_read_trylock 25.38% [kernel] [k] shrink_slab 21.75% [kernel] [k] up_read 4.45% [kernel] [k] _find_next_bit 2.27% [kernel] [k] do_shrink_slab 1.80% [kernel] [k] intel_idle_irq 1.79% [kernel] [k] shrink_lruvec 0.67% [kernel] [k] xas_descend 0.41% [kernel] [k] mem_cgroup_iter 0.40% [kernel] [k] shrink_node 0.38% [kernel] [k] list_lru_count_one 2) After applying this patchset: 64.56% [kernel] [k] shrink_slab 12.18% [kernel] [k] do_shrink_slab 3.30% [kernel] [k] __rcu_read_unlock 2.61% [kernel] [k] shrink_lruvec 2.49% [kernel] [k] __rcu_read_lock 1.93% [kernel] [k] intel_idle_irq 0.89% [kernel] [k] shrink_node 0.81% [kernel] [k] mem_cgroup_iter 0.77% [kernel] [k] mem_cgroup_calculate_protection 0.66% [kernel] [k] list_lru_count_one We can see that the first perf hotspot becomes shrink_slab, which is what we expect. 3.2 registration and unregistration stress test ----------------------------------------------- Run the command below to test: stress-ng --timeout 60 --times --verify --metrics-brief --ramfs 9 & 1) Before applying this patchset: setting to a 60 second run per stressor dispatching hogs: 9 ramfs stressor bogo ops real time usr time sys time bogo ops/s bogo ops/s (secs) (secs) (secs) (real time) (usr+sys time) ramfs 473062 60.00 8.00 279.13 7884.12 1647.59 for a 60.01s run time: 1440.34s available CPU time 7.99s user time ( 0.55%) 279.13s system time ( 19.38%) 287.12s total time ( 19.93%) load average: 7.12 2.99 1.15 successful run completed in 60.01s (1 min, 0.01 secs) 2) After applying this patchset: setting to a 60 second run per stressor dispatching hogs: 9 ramfs stressor bogo ops real time usr time sys time bogo ops/s bogo ops/s (secs) (secs) (secs) (real time) (usr+sys time) ramfs 477165 60.00 8.13 281.34 7952.55 1648.40 for a 60.01s run time: 1440.33s available CPU time 8.12s user time ( 0.56%) 281.34s system time ( 19.53%) 289.46s total time ( 20.10%) load average: 6.98 3.03 1.19 successful run completed in 60.01s (1 min, 0.01 secs) We can see that the ops/s has hardly changed. This patch (of 45): Currently, the shrinker instances can be divided into the following three types: a) global shrinker instance statically defined in the kernel, such as workingset_shadow_shrinker. b) global shrinker instance statically defined in the kernel modules, such as mmu_shrinker in x86. c) shrinker instance embedded in other structures. For case a, the memory of shrinker instance is never freed. For case b, the memory of shrinker instance will be freed after synchronize_rcu() when the module is unloaded. For case c, the memory of shrinker instance will be freed along with the structure it is embedded in. In preparation for implementing lockless slab shrink, we need to dynamically allocate those shrinker instances in case c, then the memory can be dynamically freed alone by calling kfree_rcu(). So this commit adds the following new APIs for dynamically allocating shrinker, and add a private_data field to struct shrinker to record and get the original embedded structure. 1. shrinker_alloc() Used to allocate shrinker instance itself and related memory, it will return a pointer to the shrinker instance on success and NULL on failure. 2. shrinker_register() Used to register the shrinker instance, which is same as the current register_shrinker_prepared(). 3. shrinker_free() Used to unregister (if needed) and free the shrinker instance. In order to simplify shrinker-related APIs and make shrinker more independent of other kernel mechanisms, subsequent submissions will use the above API to convert all shrinkers (including case a and b) to dynamically allocated, and then remove all existing APIs. This will also have another advantage mentioned by Dave Chinner: ``` The other advantage of this is that it will break all the existing out of tree code and third party modules using the old API and will no longer work with a kernel using lockless slab shrinkers. They need to break (both at the source and binary levels) to stop bad things from happening due to using unconverted shrinkers in the new setup. ``` [zhengqi.arch@bytedance.com: mm: shrinker: some cleanup] Link: https://lkml.kernel.org/r/20230919024607.65463-1-zhengqi.arch@bytedance.com Link: https://lkml.kernel.org/r/20230911094444.68966-1-zhengqi.arch@bytedance.com Link: https://lkml.kernel.org/r/20230911094444.68966-2-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Chuck Lever <cel@kernel.org> Cc: Darrick J. Wong <djwong@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Kirill Tkhai <tkhai@ya.ru> Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Steven Price <steven.price@arm.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Abhinav Kumar <quic_abhinavk@quicinc.com> Cc: Alasdair Kergon <agk@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Andreas Gruenbacher <agruenba@redhat.com> Cc: Anna Schumaker <anna@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Bob Peterson <rpeterso@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Carlos Llamas <cmllamas@google.com> Cc: Chandan Babu R <chandan.babu@oracle.com> Cc: Chao Yu <chao@kernel.org> Cc: Chris Mason <clm@fb.com> Cc: Christian Koenig <christian.koenig@amd.com> Cc: Coly Li <colyli@suse.de> Cc: Dai Ngo <Dai.Ngo@oracle.com> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Airlie <airlied@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Sterba <dsterba@suse.com> Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Cc: Gao Xiang <hsiangkao@linux.alibaba.com> Cc: Huang Rui <ray.huang@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Jason Wang <jasowang@redhat.com> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jeffle Xu <jefflexu@linux.alibaba.com> Cc: Joel Fernandes (Google) <joel@joelfernandes.org> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Juergen Gross <jgross@suse.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Marijn Suijten <marijn.suijten@somainline.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Mike Snitzer <snitzer@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Nadav Amit <namit@vmware.com> Cc: Neil Brown <neilb@suse.de> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Olga Kornievskaia <kolga@netapp.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rob Clark <robdclark@gmail.com> Cc: Rob Herring <robh@kernel.org> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Sean Paul <sean@poorly.run> Cc: Song Liu <song@kernel.org> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com> Cc: Tom Talpey <tom@talpey.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Cc: Yue Hu <huyue2@coolpad.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-11 09:44:00 +00:00
static inline int shrinker_debugfs_name_alloc(struct shrinker *shrinker,
const char *fmt, va_list ap)
{
return 0;
}
static inline void shrinker_debugfs_name_free(struct shrinker *shrinker)
{
}
mm: move some shrinker-related function declarations to mm/internal.h Patch series "cleanups for lockless slab shrink", v4. This series is some cleanups for lockless slab shrink. This patch (of 4): The following functions are only used inside the mm subsystem, so it's better to move their declarations to the mm/internal.h file. 1. shrinker_debugfs_add() 2. shrinker_debugfs_detach() 3. shrinker_debugfs_remove() Link: https://lkml.kernel.org/r/20230911092517.64141-1-zhengqi.arch@bytedance.com Link: https://lkml.kernel.org/r/20230911092517.64141-2-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christian König <christian.koenig@amd.com> Cc: Chuck Lever <cel@kernel.org> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Darrick J. Wong <djwong@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Joel Fernandes <joel@joelfernandes.org> Cc: Kirill Tkhai <tkhai@ya.ru> Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Steven Price <steven.price@arm.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Abhinav Kumar <quic_abhinavk@quicinc.com> Cc: Alasdair Kergon <agk@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Andreas Gruenbacher <agruenba@redhat.com> Cc: Anna Schumaker <anna@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Bob Peterson <rpeterso@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Carlos Llamas <cmllamas@google.com> Cc: Chandan Babu R <chandan.babu@oracle.com> Cc: Chao Yu <chao@kernel.org> Cc: Chris Mason <clm@fb.com> Cc: Coly Li <colyli@suse.de> Cc: Dai Ngo <Dai.Ngo@oracle.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Airlie <airlied@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Sterba <dsterba@suse.com> Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Cc: Gao Xiang <hsiangkao@linux.alibaba.com> Cc: Huang Rui <ray.huang@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Jason Wang <jasowang@redhat.com> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jeffle Xu <jefflexu@linux.alibaba.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Juergen Gross <jgross@suse.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Marijn Suijten <marijn.suijten@somainline.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Mike Snitzer <snitzer@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Nadav Amit <namit@vmware.com> Cc: Neil Brown <neilb@suse.de> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Olga Kornievskaia <kolga@netapp.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rob Clark <robdclark@gmail.com> Cc: Rob Herring <robh@kernel.org> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Sean Paul <sean@poorly.run> Cc: Song Liu <song@kernel.org> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com> Cc: Tom Talpey <tom@talpey.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Cc: Yue Hu <huyue2@coolpad.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-11 09:25:14 +00:00
static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker,
int *debugfs_id)
{
*debugfs_id = -1;
return NULL;
}
static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry,
int debugfs_id)
{
}
#endif /* CONFIG_SHRINKER_DEBUG */
/* Only track the nodes of mappings with shadow entries */
void workingset_update_node(struct xa_node *node);
extern struct list_lru shadow_nodes;
/* mremap.c */
unsigned long move_page_tables(struct vm_area_struct *vma,
unsigned long old_addr, struct vm_area_struct *new_vma,
unsigned long new_addr, unsigned long len,
bool need_rmap_locks, bool for_stack);
2024-05-21 23:43:21 +00:00
#ifdef CONFIG_UNACCEPTED_MEMORY
void accept_page(struct page *page);
#else /* CONFIG_UNACCEPTED_MEMORY */
static inline void accept_page(struct page *page)
{
}
#endif /* CONFIG_UNACCEPTED_MEMORY */
2024-05-21 23:43:21 +00:00
#endif /* __MM_INTERNAL_H */