[PATCH] mm/vmscan: Fix hard LOCKUP in function isolate_lru_folios

[liuye <liuye@xxxxxxxxxx>]

This fixes the following hard lockup in function isolate_lru_folios
when memory reclaim.If the LRU mostly contains ineligible folios
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>

Fixes: b2e18757f2c9 ("mm, vmscan: begin reclaiming pages on a per-node basis")
Signed-off-by: liuye <liuye@xxxxxxxxxx>
---
 include/linux/swap.h | 1 +
 mm/vmscan.c          | 7 +++++--
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index ba7ea95d1c57..afb3274c90ef 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -223,6 +223,7 @@ enum {
 };
 
 #define SWAP_CLUSTER_MAX 32UL
+#define SWAP_CLUSTER_MAX_SKIPPED (SWAP_CLUSTER_MAX << 10)
 #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX
 
 /* Bit flag in swap_map */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index cfa839284b92..02a8f86d4883 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1655,6 +1655,7 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan,
 	unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
 	unsigned long skipped = 0;
 	unsigned long scan, total_scan, nr_pages;
+	unsigned long max_nr_skipped = 0;
 	LIST_HEAD(folios_skipped);
 
 	total_scan = 0;
@@ -1669,10 +1670,12 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan,
 		nr_pages = folio_nr_pages(folio);
 		total_scan += nr_pages;
 
-		if (folio_zonenum(folio) > sc->reclaim_idx ||
-				skip_cma(folio, sc)) {
+		/* Using max_nr_skipped to prevent hard LOCKUP*/
+		if ((max_nr_skipped < SWAP_CLUSTER_MAX_SKIPPED) &&
+			(folio_zonenum(folio) > sc->reclaim_idx || skip_cma(folio, sc))) {
 			nr_skipped[folio_zonenum(folio)] += nr_pages;
 			move_to = &folios_skipped;
+			max_nr_skipped++;
 			goto move;
 		}
 
-- 
2.25.1