linux-stable/include/linux/vm_event_item.h
Barry Song e7ac4daeed mm: count zeromap read and set for swapout and swapin
When the proportion of folios from the zeromap is small, missing their
accounting may not significantly impact profiling.  However, it's easy to
construct a scenario where this becomes an issue—for example, allocating
1 GB of memory, writing zeros from userspace, followed by MADV_PAGEOUT,
and then swapping it back in.  In this case, the swap-out and swap-in
counts seem to vanish into a black hole, potentially causing semantic
ambiguity.

On the other hand, Usama reported that zero-filled pages can exceed 10% in
workloads utilizing zswap, while Hailong noted that some app in Android
have more than 6% zero-filled pages.  Before commit 0ca0c24e32 ("mm:
store zero pages to be swapped out in a bitmap"), both zswap and zRAM
implemented similar optimizations, leading to these optimized-out pages
being counted in either zswap or zRAM counters (with pswpin/pswpout also
increasing for zRAM).  With zeromap functioning prior to both zswap and
zRAM, userspace will no longer detect these swap-out and swap-in actions.

We have three ways to address this:

1. Introduce a dedicated counter specifically for the zeromap.

2. Use pswpin/pswpout accounting, treating the zero map as a standard
   backend.  This approach aligns with zRAM's current handling of
   same-page fills at the device level.  However, it would mean losing the
   optimized-out page counters previously available in zRAM and would not
   align with systems using zswap.  Additionally, as noted by Nhat Pham,
   pswpin/pswpout counters apply only to I/O done directly to the backend
   device.

3. Count zeromap pages under zswap, aligning with system behavior when
   zswap is enabled.  However, this would not be consistent with zRAM, nor
   would it align with systems lacking both zswap and zRAM.

Given the complications with options 2 and 3, this patch selects
option 1.

We can find these counters from /proc/vmstat (counters for the whole
system) and memcg's memory.stat (counters for the interested memcg).

For example:

$ grep -E 'swpin_zero|swpout_zero' /proc/vmstat
swpin_zero 1648
swpout_zero 33536

$ grep -E 'swpin_zero|swpout_zero' /sys/fs/cgroup/system.slice/memory.stat
swpin_zero 3905
swpout_zero 3985

This patch does not address any specific zeromap bug, but the missing
swpout and swpin counts for zero-filled pages can be highly confusing and
may mislead user-space agents that rely on changes in these counters as
indicators.  Therefore, we add a Fixes tag to encourage the inclusion of
this counter in any kernel versions with zeromap.

Many thanks to Kanchana for the contribution of changing
count_objcg_event() to count_objcg_events() to support large folios[1],
which has now been incorporated into this patch.

[1] https://lkml.kernel.org/r/20241001053222.6944-5-kanchana.p.sridhar@intel.com

Link: https://lkml.kernel.org/r/20241107011246.59137-1-21cnbao@gmail.com
Fixes: 0ca0c24e32 ("mm: store zero pages to be swapped out in a bitmap")
Co-developed-by: Kanchana P Sridhar <kanchana.p.sridhar@intel.com>
Signed-off-by: Barry Song <v-songbaohua@oppo.com>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Usama Arif <usamaarif642@gmail.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Cc: Hailong Liu <hailong.liu@oppo.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Kairui Song <kasong@tencent.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-11-11 00:00:37 -08:00

196 lines
4.3 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef VM_EVENT_ITEM_H_INCLUDED
#define VM_EVENT_ITEM_H_INCLUDED
#ifdef CONFIG_ZONE_DMA
#define DMA_ZONE(xx) xx##_DMA,
#else
#define DMA_ZONE(xx)
#endif
#ifdef CONFIG_ZONE_DMA32
#define DMA32_ZONE(xx) xx##_DMA32,
#else
#define DMA32_ZONE(xx)
#endif
#ifdef CONFIG_HIGHMEM
#define HIGHMEM_ZONE(xx) xx##_HIGH,
#else
#define HIGHMEM_ZONE(xx)
#endif
#ifdef CONFIG_ZONE_DEVICE
#define DEVICE_ZONE(xx) xx##_DEVICE,
#else
#define DEVICE_ZONE(xx)
#endif
#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL, \
HIGHMEM_ZONE(xx) xx##_MOVABLE, DEVICE_ZONE(xx)
enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
FOR_ALL_ZONES(PGALLOC)
FOR_ALL_ZONES(ALLOCSTALL)
FOR_ALL_ZONES(PGSCAN_SKIP)
PGFREE, PGACTIVATE, PGDEACTIVATE, PGLAZYFREE,
PGFAULT, PGMAJFAULT,
PGLAZYFREED,
PGREFILL,
PGREUSE,
PGSTEAL_KSWAPD,
PGSTEAL_DIRECT,
PGSTEAL_KHUGEPAGED,
PGSCAN_KSWAPD,
PGSCAN_DIRECT,
PGSCAN_KHUGEPAGED,
PGSCAN_DIRECT_THROTTLE,
PGSCAN_ANON,
PGSCAN_FILE,
PGSTEAL_ANON,
PGSTEAL_FILE,
#ifdef CONFIG_NUMA
PGSCAN_ZONE_RECLAIM_SUCCESS,
PGSCAN_ZONE_RECLAIM_FAILED,
#endif
PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL,
KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
PAGEOUTRUN, PGROTATED,
DROP_PAGECACHE, DROP_SLAB,
OOM_KILL,
#ifdef CONFIG_NUMA_BALANCING
NUMA_PTE_UPDATES,
NUMA_HUGE_PTE_UPDATES,
NUMA_HINT_FAULTS,
NUMA_HINT_FAULTS_LOCAL,
NUMA_PAGE_MIGRATE,
#endif
#ifdef CONFIG_MIGRATION
PGMIGRATE_SUCCESS, PGMIGRATE_FAIL,
THP_MIGRATION_SUCCESS,
THP_MIGRATION_FAIL,
THP_MIGRATION_SPLIT,
#endif
#ifdef CONFIG_COMPACTION
COMPACTMIGRATE_SCANNED, COMPACTFREE_SCANNED,
COMPACTISOLATED,
COMPACTSTALL, COMPACTFAIL, COMPACTSUCCESS,
KCOMPACTD_WAKE,
KCOMPACTD_MIGRATE_SCANNED, KCOMPACTD_FREE_SCANNED,
#endif
#ifdef CONFIG_HUGETLB_PAGE
HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL,
#endif
#ifdef CONFIG_CMA
CMA_ALLOC_SUCCESS,
CMA_ALLOC_FAIL,
#endif
UNEVICTABLE_PGCULLED, /* culled to noreclaim list */
UNEVICTABLE_PGSCANNED, /* scanned for reclaimability */
UNEVICTABLE_PGRESCUED, /* rescued from noreclaim list */
UNEVICTABLE_PGMLOCKED,
UNEVICTABLE_PGMUNLOCKED,
UNEVICTABLE_PGCLEARED, /* on COW, page truncate */
UNEVICTABLE_PGSTRANDED, /* unable to isolate on unlock */
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
THP_FAULT_ALLOC,
THP_FAULT_FALLBACK,
THP_FAULT_FALLBACK_CHARGE,
THP_COLLAPSE_ALLOC,
THP_COLLAPSE_ALLOC_FAILED,
THP_FILE_ALLOC,
THP_FILE_FALLBACK,
THP_FILE_FALLBACK_CHARGE,
THP_FILE_MAPPED,
THP_SPLIT_PAGE,
THP_SPLIT_PAGE_FAILED,
THP_DEFERRED_SPLIT_PAGE,
THP_UNDERUSED_SPLIT_PAGE,
THP_SPLIT_PMD,
THP_SCAN_EXCEED_NONE_PTE,
THP_SCAN_EXCEED_SWAP_PTE,
THP_SCAN_EXCEED_SHARED_PTE,
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
THP_SPLIT_PUD,
#endif
THP_ZERO_PAGE_ALLOC,
THP_ZERO_PAGE_ALLOC_FAILED,
THP_SWPOUT,
THP_SWPOUT_FALLBACK,
#endif
#ifdef CONFIG_MEMORY_BALLOON
BALLOON_INFLATE,
BALLOON_DEFLATE,
#ifdef CONFIG_BALLOON_COMPACTION
BALLOON_MIGRATE,
#endif
#endif
#ifdef CONFIG_DEBUG_TLBFLUSH
NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */
NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */
NR_TLB_LOCAL_FLUSH_ALL,
NR_TLB_LOCAL_FLUSH_ONE,
#endif /* CONFIG_DEBUG_TLBFLUSH */
#ifdef CONFIG_SWAP
SWAP_RA,
SWAP_RA_HIT,
SWPIN_ZERO,
SWPOUT_ZERO,
#ifdef CONFIG_KSM
KSM_SWPIN_COPY,
#endif
#endif
#ifdef CONFIG_KSM
COW_KSM,
#endif
#ifdef CONFIG_ZSWAP
ZSWPIN,
ZSWPOUT,
ZSWPWB,
#endif
#ifdef CONFIG_X86
DIRECT_MAP_LEVEL2_SPLIT,
DIRECT_MAP_LEVEL3_SPLIT,
#endif
#ifdef CONFIG_PER_VMA_LOCK_STATS
VMA_LOCK_SUCCESS,
VMA_LOCK_ABORT,
VMA_LOCK_RETRY,
VMA_LOCK_MISS,
#endif
#ifdef CONFIG_DEBUG_STACK_USAGE
KSTACK_1K,
#if THREAD_SIZE > 1024
KSTACK_2K,
#endif
#if THREAD_SIZE > 2048
KSTACK_4K,
#endif
#if THREAD_SIZE > 4096
KSTACK_8K,
#endif
#if THREAD_SIZE > 8192
KSTACK_16K,
#endif
#if THREAD_SIZE > 16384
KSTACK_32K,
#endif
#if THREAD_SIZE > 32768
KSTACK_64K,
#endif
#if THREAD_SIZE > 65536
KSTACK_REST,
#endif
#endif /* CONFIG_DEBUG_STACK_USAGE */
NR_VM_EVENT_ITEMS
};
#ifndef CONFIG_TRANSPARENT_HUGEPAGE
#define THP_FILE_ALLOC ({ BUILD_BUG(); 0; })
#define THP_FILE_FALLBACK ({ BUILD_BUG(); 0; })
#define THP_FILE_FALLBACK_CHARGE ({ BUILD_BUG(); 0; })
#define THP_FILE_MAPPED ({ BUILD_BUG(); 0; })
#endif
#endif /* VM_EVENT_ITEM_H_INCLUDED */