When I did memory failure tests recently, below panic occurs:
kernel BUG at include/linux/mm.h:1135!
invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
CPU: 9 PID: 137 Comm: kswapd1 Not tainted 6.9.0-rc4-00491-gd5ce28f156fe-dirty #14
RIP: 0010:shrink_huge_zero_page_scan+0x168/0x1a0
RSP: 0018:ffff9933c6c57bd0 EFLAGS: 00000246
RAX: 000000000000003e RBX: 0000000000000000 RCX: ffff88f61fc5c9c8
RDX: 0000000000000000 RSI: 0000000000000027 RDI: ffff88f61fc5c9c0
RBP: ffffcd7c446b0000 R08: ffffffff9a9405f0 R09: 0000000000005492
R10: 00000000000030ea R11: ffffffff9a9405f0 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: ffff88e703c4ac00
FS: 0000000000000000(0000) GS:ffff88f61fc40000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000055f4da6e9878 CR3: 0000000c71048000 CR4: 00000000000006f0
Call Trace:
<TASK>
do_shrink_slab+0x14f/0x6a0
shrink_slab+0xca/0x8c0
shrink_node+0x2d0/0x7d0
balance_pgdat+0x33a/0x720
kswapd+0x1f3/0x410
kthread+0xd5/0x100
ret_from_fork+0x2f/0x50
ret_from_fork_asm+0x1a/0x30
</TASK>
Modules linked in: mce_inject hwpoison_inject
---[ end trace 0000000000000000 ]---
RIP: 0010:shrink_huge_zero_page_scan+0x168/0x1a0
RSP: 0018:ffff9933c6c57bd0 EFLAGS: 00000246
RAX: 000000000000003e RBX: 0000000000000000 RCX: ffff88f61fc5c9c8
RDX: 0000000000000000 RSI: 0000000000000027 RDI: ffff88f61fc5c9c0
RBP: ffffcd7c446b0000 R08: ffffffff9a9405f0 R09: 0000000000005492
R10: 00000000000030ea R11: ffffffff9a9405f0 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: ffff88e703c4ac00
FS: 0000000000000000(0000) GS:ffff88f61fc40000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000055f4da6e9878 CR3: 0000000c71048000 CR4: 00000000000006f0
The root cause is that HWPoison flag will be set for huge_zero_page
without increasing the page refcnt. But then unpoison_memory() will
decrease the page refcnt unexpectly as it appears like a successfully
hwpoisoned page leading to VM_BUG_ON_PAGE(page_ref_count(page) == 0)
when releasing huge_zero_page.
Fix this issue by marking huge_zero_page reserved. So unpoison_memory()
will skip this page. This will make it consistent with ZERO_PAGE case too.
Fixes: 478d134e9506 ("mm/huge_memory: do not overkill when splitting huge_zero_page")
Signed-off-by: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
---
mm/huge_memory.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 89f58c7603b2..a605bc0437cd 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -208,6 +208,7 @@ static bool get_huge_zero_page(void)
__free_pages(zero_page, compound_order(zero_page));
goto retry;
}
+ __SetPageReserved(zero_page);
WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page));
/* We take additional reference here. It will be put back by shrinker */
@@ -260,6 +261,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
struct page *zero_page = xchg(&huge_zero_page, NULL);
BUG_ON(zero_page == NULL);
WRITE_ONCE(huge_zero_pfn, ~0UL);
+ __ClearPageReserved(zero_page);
__free_pages(zero_page, compound_order(zero_page));
return HPAGE_PMD_NR;
}
--
2.33.0
