diff options
author | Linus Torvalds | 2019-07-12 20:40:28 +0200 |
---|---|---|
committer | Linus Torvalds | 2019-07-12 20:40:28 +0200 |
commit | ef8f3d48afd6a17a0dae8c277c2f539c2f19fd16 (patch) | |
tree | 5c28f9f287a552ad1a655b9e29e5330966652e89 /mm/vmscan.c | |
parent | Merge tag 'tag-chrome-platform-for-v5.3' of git://git.kernel.org/pub/scm/linu... (diff) | |
parent | mm/oom_kill.c: remove redundant OOM score normalization in select_bad_process() (diff) | |
download | kernel-qcow2-linux-ef8f3d48afd6a17a0dae8c277c2f539c2f19fd16.tar.gz kernel-qcow2-linux-ef8f3d48afd6a17a0dae8c277c2f539c2f19fd16.tar.xz kernel-qcow2-linux-ef8f3d48afd6a17a0dae8c277c2f539c2f19fd16.zip |
Merge branch 'akpm' (patches from Andrew)
Merge updates from Andrew Morton:
"Am experimenting with splitting MM up into identifiable subsystems
perhaps with a view to gitifying it in complex ways. Also with more
verbose "incoming" emails.
Most of MM is here and a few other trees.
Subsystems affected by this patch series:
- hotfixes
- iommu
- scripts
- arch/sh
- ocfs2
- mm:slab-generic
- mm:slub
- mm:kmemleak
- mm:kasan
- mm:cleanups
- mm:debug
- mm:pagecache
- mm:swap
- mm:memcg
- mm:gup
- mm:pagemap
- mm:infrastructure
- mm:vmalloc
- mm:initialization
- mm:pagealloc
- mm:vmscan
- mm:tools
- mm:proc
- mm:ras
- mm:oom-kill
hotfixes:
mm: vmscan: scan anonymous pages on file refaults
mm/nvdimm: add is_ioremap_addr and use that to check ioremap address
mm/memcontrol: fix wrong statistics in memory.stat
mm/z3fold.c: lock z3fold page before __SetPageMovable()
nilfs2: do not use unexported cpu_to_le32()/le32_to_cpu() in uapi header
MAINTAINERS: nilfs2: update email address
iommu:
include/linux/dmar.h: replace single-char identifiers in macros
scripts:
scripts/decode_stacktrace: match basepath using shell prefix operator, not regex
scripts/decode_stacktrace: look for modules with .ko.debug extension
scripts/spelling.txt: drop "sepc" from the misspelling list
scripts/spelling.txt: add spelling fix for prohibited
scripts/decode_stacktrace: Accept dash/underscore in modules
scripts/spelling.txt: add more spellings to spelling.txt
arch/sh:
arch/sh/configs/sdk7786_defconfig: remove CONFIG_LOGFS
sh: config: remove left-over BACKLIGHT_LCD_SUPPORT
sh: prevent warnings when using iounmap
ocfs2:
fs: ocfs: fix spelling mistake "hearbeating" -> "heartbeat"
ocfs2/dlm: use struct_size() helper
ocfs2: add last unlock times in locking_state
ocfs2: add locking filter debugfs file
ocfs2: add first lock wait time in locking_state
ocfs: no need to check return value of debugfs_create functions
fs/ocfs2/dlmglue.c: unneeded variable: "status"
ocfs2: use kmemdup rather than duplicating its implementation
mm:slab-generic:
Patch series "mm/slab: Improved sanity checking":
mm/slab: validate cache membership under freelist hardening
mm/slab: sanity-check page type when looking up cache
lkdtm/heap: add tests for freelist hardening
mm:slub:
mm/slub.c: avoid double string traverse in kmem_cache_flags()
slub: don't panic for memcg kmem cache creation failure
mm:kmemleak:
mm/kmemleak.c: fix check for softirq context
mm/kmemleak.c: change error at _write when kmemleak is disabled
docs: kmemleak: add more documentation details
mm:kasan:
mm/kasan: print frame description for stack bugs
Patch series "Bitops instrumentation for KASAN", v5:
lib/test_kasan: add bitops tests
x86: use static_cpu_has in uaccess region to avoid instrumentation
asm-generic, x86: add bitops instrumentation for KASAN
Patch series "mm/kasan: Add object validation in ksize()", v3:
mm/kasan: introduce __kasan_check_{read,write}
mm/kasan: change kasan_check_{read,write} to return boolean
lib/test_kasan: Add test for double-kzfree detection
mm/slab: refactor common ksize KASAN logic into slab_common.c
mm/kasan: add object validation in ksize()
mm:cleanups:
include/linux/pfn_t.h: remove pfn_t_to_virt()
Patch series "remove ARCH_SELECT_MEMORY_MODEL where it has no effect":
arm: remove ARCH_SELECT_MEMORY_MODEL
s390: remove ARCH_SELECT_MEMORY_MODEL
sparc: remove ARCH_SELECT_MEMORY_MODEL
mm/gup.c: make follow_page_mask() static
mm/memory.c: trivial clean up in insert_page()
mm: make !CONFIG_HUGE_PAGE wrappers into static inlines
include/linux/mm_types.h: ifdef struct vm_area_struct::swap_readahead_info
mm: remove the account_page_dirtied export
mm/page_isolation.c: change the prototype of undo_isolate_page_range()
include/linux/vmpressure.h: use spinlock_t instead of struct spinlock
mm: remove the exporting of totalram_pages
include/linux/pagemap.h: document trylock_page() return value
mm:debug:
mm/failslab.c: by default, do not fail allocations with direct reclaim only
Patch series "debug_pagealloc improvements":
mm, debug_pagelloc: use static keys to enable debugging
mm, page_alloc: more extensive free page checking with debug_pagealloc
mm, debug_pagealloc: use a page type instead of page_ext flag
mm:pagecache:
Patch series "fix filler_t callback type mismatches", v2:
mm/filemap.c: fix an overly long line in read_cache_page
mm/filemap: don't cast ->readpage to filler_t for do_read_cache_page
jffs2: pass the correct prototype to read_cache_page
9p: pass the correct prototype to read_cache_page
mm/filemap.c: correct the comment about VM_FAULT_RETRY
mm:swap:
mm, swap: fix race between swapoff and some swap operations
mm/swap_state.c: simplify total_swapcache_pages() with get_swap_device()
mm, swap: use rbtree for swap_extent
mm/mincore.c: fix race between swapoff and mincore
mm:memcg:
memcg, oom: no oom-kill for __GFP_RETRY_MAYFAIL
memcg, fsnotify: no oom-kill for remote memcg charging
mm, memcg: introduce memory.events.local
mm: memcontrol: dump memory.stat during cgroup OOM
Patch series "mm: reparent slab memory on cgroup removal", v7:
mm: memcg/slab: postpone kmem_cache memcg pointer initialization to memcg_link_cache()
mm: memcg/slab: rename slab delayed deactivation functions and fields
mm: memcg/slab: generalize postponed non-root kmem_cache deactivation
mm: memcg/slab: introduce __memcg_kmem_uncharge_memcg()
mm: memcg/slab: unify SLAB and SLUB page accounting
mm: memcg/slab: don't check the dying flag on kmem_cache creation
mm: memcg/slab: synchronize access to kmem_cache dying flag using a spinlock
mm: memcg/slab: rework non-root kmem_cache lifecycle management
mm: memcg/slab: stop setting page->mem_cgroup pointer for slab pages
mm: memcg/slab: reparent memcg kmem_caches on cgroup removal
mm, memcg: add a memcg_slabinfo debugfs file
mm:gup:
Patch series "switch the remaining architectures to use generic GUP", v4:
mm: use untagged_addr() for get_user_pages_fast addresses
mm: simplify gup_fast_permitted
mm: lift the x86_32 PAE version of gup_get_pte to common code
MIPS: use the generic get_user_pages_fast code
sh: add the missing pud_page definition
sh: use the generic get_user_pages_fast code
sparc64: add the missing pgd_page definition
sparc64: define untagged_addr()
sparc64: use the generic get_user_pages_fast code
mm: rename CONFIG_HAVE_GENERIC_GUP to CONFIG_HAVE_FAST_GUP
mm: reorder code blocks in gup.c
mm: consolidate the get_user_pages* implementations
mm: validate get_user_pages_fast flags
mm: move the powerpc hugepd code to mm/gup.c
mm: switch gup_hugepte to use try_get_compound_head
mm: mark the page referenced in gup_hugepte
mm/gup: speed up check_and_migrate_cma_pages() on huge page
mm/gup.c: remove some BUG_ONs from get_gate_page()
mm/gup.c: mark undo_dev_pagemap as __maybe_unused
mm:pagemap:
asm-generic, x86: introduce generic pte_{alloc,free}_one[_kernel]
alpha: switch to generic version of pte allocation
arm: switch to generic version of pte allocation
arm64: switch to generic version of pte allocation
csky: switch to generic version of pte allocation
m68k: sun3: switch to generic version of pte allocation
mips: switch to generic version of pte allocation
nds32: switch to generic version of pte allocation
nios2: switch to generic version of pte allocation
parisc: switch to generic version of pte allocation
riscv: switch to generic version of pte allocation
um: switch to generic version of pte allocation
unicore32: switch to generic version of pte allocation
mm/pgtable: drop pgtable_t variable from pte_fn_t functions
mm/memory.c: fail when offset == num in first check of __vm_map_pages()
mm:infrastructure:
mm/mmu_notifier: use hlist_add_head_rcu()
mm:vmalloc:
Patch series "Some cleanups for the KVA/vmalloc", v5:
mm/vmalloc.c: remove "node" argument
mm/vmalloc.c: preload a CPU with one object for split purpose
mm/vmalloc.c: get rid of one single unlink_va() when merge
mm/vmalloc.c: switch to WARN_ON() and move it under unlink_va()
mm/vmalloc.c: spelling> s/informaion/information/
mm:initialization:
mm/large system hash: use vmalloc for size > MAX_ORDER when !hashdist
mm/large system hash: clear hashdist when only one node with memory is booted
mm:pagealloc:
arm64: move jump_label_init() before parse_early_param()
Patch series "add init_on_alloc/init_on_free boot options", v10:
mm: security: introduce init_on_alloc=1 and init_on_free=1 boot options
mm: init: report memory auto-initialization features at boot time
mm:vmscan:
mm: vmscan: remove double slab pressure by inc'ing sc->nr_scanned
mm: vmscan: correct some vmscan counters for THP swapout
mm:tools:
tools/vm/slabinfo: order command line options
tools/vm/slabinfo: add partial slab listing to -X
tools/vm/slabinfo: add option to sort by partial slabs
tools/vm/slabinfo: add sorting info to help menu
mm:proc:
proc: use down_read_killable mmap_sem for /proc/pid/maps
proc: use down_read_killable mmap_sem for /proc/pid/smaps_rollup
proc: use down_read_killable mmap_sem for /proc/pid/pagemap
proc: use down_read_killable mmap_sem for /proc/pid/clear_refs
proc: use down_read_killable mmap_sem for /proc/pid/map_files
mm: use down_read_killable for locking mmap_sem in access_remote_vm
mm: smaps: split PSS into components
mm: vmalloc: show number of vmalloc pages in /proc/meminfo
mm:ras:
mm/memory-failure.c: clarify error message
mm:oom-kill:
mm: memcontrol: use CSS_TASK_ITER_PROCS at mem_cgroup_scan_tasks()
mm, oom: refactor dump_tasks for memcg OOMs
mm, oom: remove redundant task_in_mem_cgroup() check
oom: decouple mems_allowed from oom_unkillable_task
mm/oom_kill.c: remove redundant OOM score normalization in select_bad_process()"
* akpm: (147 commits)
mm/oom_kill.c: remove redundant OOM score normalization in select_bad_process()
oom: decouple mems_allowed from oom_unkillable_task
mm, oom: remove redundant task_in_mem_cgroup() check
mm, oom: refactor dump_tasks for memcg OOMs
mm: memcontrol: use CSS_TASK_ITER_PROCS at mem_cgroup_scan_tasks()
mm/memory-failure.c: clarify error message
mm: vmalloc: show number of vmalloc pages in /proc/meminfo
mm: smaps: split PSS into components
mm: use down_read_killable for locking mmap_sem in access_remote_vm
proc: use down_read_killable mmap_sem for /proc/pid/map_files
proc: use down_read_killable mmap_sem for /proc/pid/clear_refs
proc: use down_read_killable mmap_sem for /proc/pid/pagemap
proc: use down_read_killable mmap_sem for /proc/pid/smaps_rollup
proc: use down_read_killable mmap_sem for /proc/pid/maps
tools/vm/slabinfo: add sorting info to help menu
tools/vm/slabinfo: add option to sort by partial slabs
tools/vm/slabinfo: add partial slab listing to -X
tools/vm/slabinfo: order command line options
mm: vmscan: correct some vmscan counters for THP swapout
mm: vmscan: remove double slab pressure by inc'ing sc->nr_scanned
...
Diffstat (limited to 'mm/vmscan.c')
-rw-r--r-- | mm/vmscan.c | 74 |
1 files changed, 52 insertions, 22 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c index 910e02c793ff..f8e3dcd527b8 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1118,6 +1118,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, int may_enter_fs; enum page_references references = PAGEREF_RECLAIM_CLEAN; bool dirty, writeback; + unsigned int nr_pages; cond_resched(); @@ -1129,7 +1130,10 @@ static unsigned long shrink_page_list(struct list_head *page_list, VM_BUG_ON_PAGE(PageActive(page), page); - sc->nr_scanned++; + nr_pages = 1 << compound_order(page); + + /* Account the number of base pages even though THP */ + sc->nr_scanned += nr_pages; if (unlikely(!page_evictable(page))) goto activate_locked; @@ -1137,11 +1141,6 @@ static unsigned long shrink_page_list(struct list_head *page_list, if (!sc->may_unmap && page_mapped(page)) goto keep_locked; - /* Double the slab pressure for mapped and swapcache pages */ - if ((page_mapped(page) || PageSwapCache(page)) && - !(PageAnon(page) && !PageSwapBacked(page))) - sc->nr_scanned++; - may_enter_fs = (sc->gfp_mask & __GFP_FS) || (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO)); @@ -1255,7 +1254,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, case PAGEREF_ACTIVATE: goto activate_locked; case PAGEREF_KEEP: - stat->nr_ref_keep++; + stat->nr_ref_keep += nr_pages; goto keep_locked; case PAGEREF_RECLAIM: case PAGEREF_RECLAIM_CLEAN: @@ -1287,7 +1286,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, } if (!add_to_swap(page)) { if (!PageTransHuge(page)) - goto activate_locked; + goto activate_locked_split; /* Fallback to swap normal pages */ if (split_huge_page_to_list(page, page_list)) @@ -1296,7 +1295,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, count_vm_event(THP_SWPOUT_FALLBACK); #endif if (!add_to_swap(page)) - goto activate_locked; + goto activate_locked_split; } may_enter_fs = 1; @@ -1311,6 +1310,18 @@ static unsigned long shrink_page_list(struct list_head *page_list, } /* + * THP may get split above, need minus tail pages and update + * nr_pages to avoid accounting tail pages twice. + * + * The tail pages that are added into swap cache successfully + * reach here. + */ + if ((nr_pages > 1) && !PageTransHuge(page)) { + sc->nr_scanned -= (nr_pages - 1); + nr_pages = 1; + } + + /* * The page is mapped into the page tables of one or more * processes. Try to unmap it here. */ @@ -1320,7 +1331,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, if (unlikely(PageTransHuge(page))) flags |= TTU_SPLIT_HUGE_PMD; if (!try_to_unmap(page, flags)) { - stat->nr_unmap_fail++; + stat->nr_unmap_fail += nr_pages; goto activate_locked; } } @@ -1447,7 +1458,11 @@ static unsigned long shrink_page_list(struct list_head *page_list, unlock_page(page); free_it: - nr_reclaimed++; + /* + * THP may get swapped out in a whole, need account + * all base pages. + */ + nr_reclaimed += nr_pages; /* * Is there need to periodically free_page_list? It would @@ -1460,6 +1475,15 @@ free_it: list_add(&page->lru, &free_pages); continue; +activate_locked_split: + /* + * The tail pages that are failed to add into swap cache + * reach here. Fixup nr_scanned and nr_pages. + */ + if (nr_pages > 1) { + sc->nr_scanned -= (nr_pages - 1); + nr_pages = 1; + } activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ if (PageSwapCache(page) && (mem_cgroup_swap_full(page) || @@ -1469,8 +1493,7 @@ activate_locked: if (!PageMlocked(page)) { int type = page_is_file_cache(page); SetPageActive(page); - pgactivate++; - stat->nr_activate[type] += hpage_nr_pages(page); + stat->nr_activate[type] += nr_pages; count_memcg_page_event(page, PGACTIVATE); } keep_locked: @@ -1480,6 +1503,8 @@ keep: VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page); } + pgactivate = stat->nr_activate[0] + stat->nr_activate[1]; + mem_cgroup_uncharge_list(&free_pages); try_to_unmap_flush(); free_unref_page_list(&free_pages); @@ -1651,10 +1676,9 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, LIST_HEAD(pages_skipped); isolate_mode_t mode = (sc->may_unmap ? 0 : ISOLATE_UNMAPPED); + total_scan = 0; scan = 0; - for (total_scan = 0; - scan < nr_to_scan && nr_taken < nr_to_scan && !list_empty(src); - total_scan++) { + while (scan < nr_to_scan && !list_empty(src)) { struct page *page; page = lru_to_page(src); @@ -1662,9 +1686,12 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, VM_BUG_ON_PAGE(!PageLRU(page), page); + nr_pages = 1 << compound_order(page); + total_scan += nr_pages; + if (page_zonenum(page) > sc->reclaim_idx) { list_move(&page->lru, &pages_skipped); - nr_skipped[page_zonenum(page)]++; + nr_skipped[page_zonenum(page)] += nr_pages; continue; } @@ -1673,11 +1700,14 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, * return with no isolated pages if the LRU mostly contains * ineligible pages. This causes the VM to not reclaim any * pages, triggering a premature OOM. + * + * Account all tail pages of THP. This would not cause + * premature OOM since __isolate_lru_page() returns -EBUSY + * only when the page is being freed somewhere else. */ - scan++; + scan += nr_pages; switch (__isolate_lru_page(page, mode)) { case 0: - nr_pages = hpage_nr_pages(page); nr_taken += nr_pages; nr_zone_taken[page_zonenum(page)] += nr_pages; list_move(&page->lru, dst); @@ -2125,7 +2155,7 @@ static void shrink_active_list(unsigned long nr_to_scan, * 10TB 320 32GB */ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, - struct scan_control *sc, bool actual_reclaim) + struct scan_control *sc, bool trace) { enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE; struct pglist_data *pgdat = lruvec_pgdat(lruvec); @@ -2151,7 +2181,7 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, * rid of the stale workingset quickly. */ refaults = lruvec_page_state_local(lruvec, WORKINGSET_ACTIVATE); - if (file && actual_reclaim && lruvec->refaults != refaults) { + if (file && lruvec->refaults != refaults) { inactive_ratio = 0; } else { gb = (inactive + active) >> (30 - PAGE_SHIFT); @@ -2161,7 +2191,7 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, inactive_ratio = 1; } - if (actual_reclaim) + if (trace) trace_mm_vmscan_inactive_list_is_low(pgdat->node_id, sc->reclaim_idx, lruvec_lru_size(lruvec, inactive_lru, MAX_NR_ZONES), inactive, lruvec_lru_size(lruvec, active_lru, MAX_NR_ZONES), active, |