qiurui/Centos-kernel-stream-9
1
0
Fork 0
mirror of https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9.git synced 2026-09-09 00:08:12 +08:00
Code Issues Packages Projects Releases Wiki Activity

mm/vmscan: fix hard LOCKUP in function isolate_lru_folios

Browse Source 
JIRA: https://issues.redhat.com/browse/RHEL-153668
Tested: sanity

commit 1c7b17cf0594f33c898004ac1b5576c032f266e2
Author: liuye <liuye@kylinos.cn>
Date:   Tue Nov 19 14:08:42 2024 +0800

    mm/vmscan: fix hard LOCKUP in function isolate_lru_folios

    This fixes the following hard lockup in isolate_lru_folios() during memory
    reclaim.  If the LRU mostly contains ineligible folios this may trigger
    watchdog.

    watchdog: Watchdog detected hard LOCKUP on cpu 173
    RIP: 0010:native_queued_spin_lock_slowpath+0x255/0x2a0
    Call Trace:
            _raw_spin_lock_irqsave+0x31/0x40
            folio_lruvec_lock_irqsave+0x5f/0x90
            folio_batch_move_lru+0x91/0x150
            lru_add_drain_per_cpu+0x1c/0x40
            process_one_work+0x17d/0x350
            worker_thread+0x27b/0x3a0
            kthread+0xe8/0x120
            ret_from_fork+0x34/0x50
            ret_from_fork_asm+0x1b/0x30

    lruvec->lru_lock owner：

    PID: 2865     TASK: ffff888139214d40  CPU: 40   COMMAND: "kswapd0"
     #0 [fffffe0000945e60] crash_nmi_callback at ffffffffa567a555
     #1 [fffffe0000945e68] nmi_handle at ffffffffa563b171
     #2 [fffffe0000945eb0] default_do_nmi at ffffffffa6575920
     #3 [fffffe0000945ed0] exc_nmi at ffffffffa6575af4
     #4 [fffffe0000945ef0] end_repeat_nmi at ffffffffa6601dde
        [exception RIP: isolate_lru_folios+403]
        RIP: ffffffffa597df53  RSP: ffffc90006fb7c28  RFLAGS: 00000002
        RAX: 0000000000000001  RBX: ffffc90006fb7c60  RCX: ffffea04a2196f88
        RDX: ffffc90006fb7c60  RSI: ffffc90006fb7c60  RDI: ffffea04a2197048
        RBP: ffff88812cbd3010   R8: ffffea04a2197008   R9: 0000000000000001
        R10: 0000000000000000  R11: 0000000000000001  R12: ffffea04a2197008
        R13: ffffea04a2197048  R14: ffffc90006fb7de8  R15: 0000000003e3e937
        ORIG_RAX: ffffffffffffffff  CS: 0010  SS: 0018
        <NMI exception stack>
     #5 [ffffc90006fb7c28] isolate_lru_folios at ffffffffa597df53
     #6 [ffffc90006fb7cf8] shrink_active_list at ffffffffa597f788
     #7 [ffffc90006fb7da8] balance_pgdat at ffffffffa5986db0
     #8 [ffffc90006fb7ec0] kswapd at ffffffffa5987354
     #9 [ffffc90006fb7ef8] kthread at ffffffffa5748238
    crash>

    Scenario:
    User processe are requesting a large amount of memory and keep page active.
    Then a module continuously requests memory from ZONE_DMA32 area.
    Memory reclaim will be triggered due to ZONE_DMA32 watermark alarm reached.
    However pages in the LRU(active_anon) list are mostly from
    the ZONE_NORMAL area.

    Reproduce:
    Terminal 1: Construct to continuously increase pages active(anon).
    mkdir /tmp/memory
    mount -t tmpfs -o size=1024000M tmpfs /tmp/memory
    dd if=/dev/zero of=/tmp/memory/block bs=4M
    tail /tmp/memory/block

    Terminal 2:
    vmstat -a 1
    active will increase.
    procs ---memory--- ---swap-- ---io---- -system-- ---cpu--- ...
     r  b   swpd   free  inact active   si   so    bi    bo
     1  0   0 1445623076 45898836 83646008    0    0     0
     1  0   0 1445623076 43450228 86094616    0    0     0
     1  0   0 1445623076 41003480 88541364    0    0     0
     1  0   0 1445623076 38557088 90987756    0    0     0
     1  0   0 1445623076 36109688 93435156    0    0     0
     1  0   0 1445619552 33663256 95881632    0    0     0
     1  0   0 1445619804 31217140 98327792    0    0     0
     1  0   0 1445619804 28769988 100774944    0    0     0
     1  0   0 1445619804 26322348 103222584    0    0     0
     1  0   0 1445619804 23875592 105669340    0    0     0

    cat /proc/meminfo | head
    Active(anon) increase.
    MemTotal:       1579941036 kB
    MemFree:        1445618500 kB
    MemAvailable:   1453013224 kB
    Buffers:            6516 kB
    Cached:         128653956 kB
    SwapCached:            0 kB
    Active:         118110812 kB
    Inactive:       11436620 kB
    Active(anon):   115345744 kB
    Inactive(anon):   945292 kB

    When the Active(anon) is 115345744 kB, insmod module triggers
    the ZONE_DMA32 watermark.

    perf record -e vmscan:mm_vmscan_lru_isolate -aR
    perf script
    isolate_mode=0 classzone=1 order=1 nr_requested=32 nr_scanned=2
    nr_skipped=2 nr_taken=0 lru=active_anon
    isolate_mode=0 classzone=1 order=1 nr_requested=32 nr_scanned=0
    nr_skipped=0 nr_taken=0 lru=active_anon
    isolate_mode=0 classzone=1 order=0 nr_requested=32 nr_scanned=28835844
    nr_skipped=28835844 nr_taken=0 lru=active_anon
    isolate_mode=0 classzone=1 order=1 nr_requested=32 nr_scanned=28835844
    nr_skipped=28835844 nr_taken=0 lru=active_anon
    isolate_mode=0 classzone=1 order=0 nr_requested=32 nr_scanned=29
    nr_skipped=29 nr_taken=0 lru=active_anon
    isolate_mode=0 classzone=1 order=0 nr_requested=32 nr_scanned=0
    nr_skipped=0 nr_taken=0 lru=active_anon

    See nr_scanned=28835844.
    28835844 * 4k = 115343376KB approximately equal to 115345744 kB.

    If increase Active(anon) to 1000G then insmod module triggers
    the ZONE_DMA32 watermark. hard lockup will occur.

    In my device nr_scanned = 0000000003e3e937 when hard lockup.
    Convert to memory size 0x0000000003e3e937 * 4KB = 261072092 KB.

       [ffffc90006fb7c28] isolate_lru_folios at ffffffffa597df53
        ffffc90006fb7c30: 0000000000000020 0000000000000000
        ffffc90006fb7c40: ffffc90006fb7d40 ffff88812cbd3000
        ffffc90006fb7c50: ffffc90006fb7d30 0000000106fb7de8
        ffffc90006fb7c60: ffffea04a2197008 ffffea0006ed4a48
        ffffc90006fb7c70: 0000000000000000 0000000000000000
        ffffc90006fb7c80: 0000000000000000 0000000000000000
        ffffc90006fb7c90: 0000000000000000 0000000000000000
        ffffc90006fb7ca0: 0000000000000000 0000000003e3e937
        ffffc90006fb7cb0: 0000000000000000 0000000000000000
        ffffc90006fb7cc0: 8d7c0b56b7874b00 ffff88812cbd3000

    About the Fixes:
    Why did it take eight years to be discovered?

    The problem requires the following conditions to occur:
    1. The device memory should be large enough.
    2. Pages in the LRU(active_anon) list are mostly from the ZONE_NORMAL area.
    3. The memory in ZONE_DMA32 needs to reach the watermark.

    If the memory is not large enough, or if the usage design of ZONE_DMA32
    area memory is reasonable, this problem is difficult to detect.

    notes:
    The problem is most likely to occur in ZONE_DMA32 and ZONE_NORMAL,
    but other suitable scenarios may also trigger the problem.

    Link: https://lkml.kernel.org/r/20241119060842.274072-1-liuye@kylinos.cn
    Fixes: b2e18757f2 ("mm, vmscan: begin reclaiming pages on a per-node basis")
    Signed-off-by: liuye <liuye@kylinos.cn>
    Cc: Hugh Dickins <hughd@google.com>
    Cc: Mel Gorman <mgorman@techsingularity.net>
    Cc: Yang Shi <yang@os.amperecomputing.com>
    Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Signed-off-by: Aristeu Rozanski <arozansk@redhat.com>
This commit is contained in:
Aristeu Rozanski
2026-08-13 10:05:04 -04:00
parent e05a2338f5
commit 5662b11d0a
2 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/linux/swap.h
+1
View File
@@ -223,6 +223,7 @@ enum {
}; };
#define SWAP_CLUSTER_MAX 32UL #define SWAP_CLUSTER_MAX 32UL
#define SWAP_CLUSTER_MAX_SKIPPED (SWAP_CLUSTER_MAX << 10)
#define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX
/* Bit flag in swap_map */ /* Bit flag in swap_map */
mm/vmscan.c
+5 -1
View File
@@ -1605,6 +1605,7 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan,
unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
unsigned long skipped = 0; unsigned long skipped = 0;
unsigned long scan, total_scan, nr_pages; unsigned long scan, total_scan, nr_pages;
unsigned long max_nr_skipped = 0;
LIST_HEAD(folios_skipped); LIST_HEAD(folios_skipped);
total_scan = 0; total_scan = 0;
@@ -1619,9 +1620,12 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan,
nr_pages = folio_nr_pages(folio); nr_pages = folio_nr_pages(folio);
total_scan += nr_pages; total_scan += nr_pages;
if (folio_zonenum(folio) > sc->reclaim_idx) { /* Using max_nr_skipped to prevent hard LOCKUP*/
if (max_nr_skipped < SWAP_CLUSTER_MAX_SKIPPED &&
(folio_zonenum(folio) > sc->reclaim_idx)) {
nr_skipped[folio_zonenum(folio)] += nr_pages; nr_skipped[folio_zonenum(folio)] += nr_pages;
move_to = &folios_skipped; move_to = &folios_skipped;
max_nr_skipped++;
goto move; goto move;
} }