From 3be306cccdccede13e3cefd0c14e430cc2b7c9c7 Mon Sep 17 00:00:00 2001 From: Kyle Meyer Date: Thu, 28 Aug 2025 13:38:20 -0500 Subject: mm/memory-failure: fix redundant updates for already poisoned pages Duplicate memory errors can be reported by multiple sources. Passing an already poisoned page to action_result() causes issues: * The amount of hardware corrupted memory is incorrectly updated. * Per NUMA node MF stats are incorrectly updated. * Redundant "already poisoned" messages are printed. Avoid those issues by: * Skipping hardware corrupted memory updates for already poisoned pages. * Skipping per NUMA node MF stats updates for already poisoned pages. * Dropping redundant "already poisoned" messages. Make MF_MSG_ALREADY_POISONED consistent with other action_page_types and make calls to action_result() consistent for already poisoned normal pages and huge pages. Link: https://lkml.kernel.org/r/aLCiHMy12Ck3ouwC@hpe.com Fixes: b8b9488d50b7 ("mm/memory-failure: improve memory failure action_result messages") Signed-off-by: Kyle Meyer Reviewed-by: Jiaqi Yan Acked-by: David Hildenbrand Reviewed-by: Jane Chu Acked-by: Miaohe Lin Cc: Borislav Betkov Cc: Kyle Meyer Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: "Luck, Tony" Cc: Michal Hocko Cc: Mike Rapoport Cc: Naoya Horiguchi Cc: Oscar Salvador Cc: Russ Anderson Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton --- mm/memory-failure.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index fc30ca4804bf..10b3c281c2ae 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -956,7 +956,7 @@ static const char * const action_page_types[] = { [MF_MSG_BUDDY] = "free buddy page", [MF_MSG_DAX] = "dax page", [MF_MSG_UNSPLIT_THP] = "unsplit thp", - [MF_MSG_ALREADY_POISONED] = "already poisoned", + [MF_MSG_ALREADY_POISONED] = "already poisoned page", [MF_MSG_UNKNOWN] = "unknown page", }; @@ -1349,9 +1349,10 @@ static int action_result(unsigned long pfn, enum mf_action_page_type type, { trace_memory_failure_event(pfn, type, result); - num_poisoned_pages_inc(pfn); - - update_per_node_mf_stats(pfn, result); + if (type != MF_MSG_ALREADY_POISONED) { + num_poisoned_pages_inc(pfn); + update_per_node_mf_stats(pfn, result); + } pr_err("%#lx: recovery action for %s: %s\n", pfn, action_page_types[type], action_name[result]); @@ -2094,12 +2095,11 @@ retry: *hugetlb = 0; return 0; } else if (res == -EHWPOISON) { - pr_err("%#lx: already hardware poisoned\n", pfn); if (flags & MF_ACTION_REQUIRED) { folio = page_folio(p); res = kill_accessing_process(current, folio_pfn(folio), flags); - action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED); } + action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED); return res; } else if (res == -EBUSY) { if (!(flags & MF_NO_RETRY)) { @@ -2285,7 +2285,6 @@ try_again: goto unlock_mutex; if (TestSetPageHWPoison(p)) { - pr_err("%#lx: already hardware poisoned\n", pfn); res = -EHWPOISON; if (flags & MF_ACTION_REQUIRED) res = kill_accessing_process(current, pfn, flags); -- cgit v1.2.3 From d613f53c83ec47089c4e25859d5e8e0359f6f8da Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 28 Aug 2025 10:46:18 +0800 Subject: mm/memory-failure: fix VM_BUG_ON_PAGE(PagePoisoned(page)) when unpoison memory When I did memory failure tests, below panic occurs: page dumped because: VM_BUG_ON_PAGE(PagePoisoned(page)) kernel BUG at include/linux/page-flags.h:616! Oops: invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 3 PID: 720 Comm: bash Not tainted 6.10.0-rc1-00195-g148743902568 #40 RIP: 0010:unpoison_memory+0x2f3/0x590 RSP: 0018:ffffa57fc8787d60 EFLAGS: 00000246 RAX: 0000000000000037 RBX: 0000000000000009 RCX: ffff9be25fcdc9c8 RDX: 0000000000000000 RSI: 0000000000000027 RDI: ffff9be25fcdc9c0 RBP: 0000000000300000 R08: ffffffffb4956f88 R09: 0000000000009ffb R10: 0000000000000284 R11: ffffffffb4926fa0 R12: ffffe6b00c000000 R13: ffff9bdb453dfd00 R14: 0000000000000000 R15: fffffffffffffffe FS: 00007f08f04e4740(0000) GS:ffff9be25fcc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000564787a30410 CR3: 000000010d4e2000 CR4: 00000000000006f0 Call Trace: unpoison_memory+0x2f3/0x590 simple_attr_write_xsigned.constprop.0.isra.0+0xb3/0x110 debugfs_attr_write+0x42/0x60 full_proxy_write+0x5b/0x80 vfs_write+0xd5/0x540 ksys_write+0x64/0xe0 do_syscall_64+0xb9/0x1d0 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f08f0314887 RSP: 002b:00007ffece710078 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000009 RCX: 00007f08f0314887 RDX: 0000000000000009 RSI: 0000564787a30410 RDI: 0000000000000001 RBP: 0000564787a30410 R08: 000000000000fefe R09: 000000007fffffff R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000009 R13: 00007f08f041b780 R14: 00007f08f0417600 R15: 00007f08f0416a00 Modules linked in: hwpoison_inject ---[ end trace 0000000000000000 ]--- RIP: 0010:unpoison_memory+0x2f3/0x590 RSP: 0018:ffffa57fc8787d60 EFLAGS: 00000246 RAX: 0000000000000037 RBX: 0000000000000009 RCX: ffff9be25fcdc9c8 RDX: 0000000000000000 RSI: 0000000000000027 RDI: ffff9be25fcdc9c0 RBP: 0000000000300000 R08: ffffffffb4956f88 R09: 0000000000009ffb R10: 0000000000000284 R11: ffffffffb4926fa0 R12: ffffe6b00c000000 R13: ffff9bdb453dfd00 R14: 0000000000000000 R15: fffffffffffffffe FS: 00007f08f04e4740(0000) GS:ffff9be25fcc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000564787a30410 CR3: 000000010d4e2000 CR4: 00000000000006f0 Kernel panic - not syncing: Fatal exception Kernel Offset: 0x31c00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) ---[ end Kernel panic - not syncing: Fatal exception ]--- The root cause is that unpoison_memory() tries to check the PG_HWPoison flags of an uninitialized page. So VM_BUG_ON_PAGE(PagePoisoned(page)) is triggered. This can be reproduced by below steps: 1.Offline memory block: echo offline > /sys/devices/system/memory/memory12/state 2.Get offlined memory pfn: page-types -b n -rlN 3.Write pfn to unpoison-pfn echo > /sys/kernel/debug/hwpoison/unpoison-pfn This scenario can be identified by pfn_to_online_page() returning NULL. And ZONE_DEVICE pages are never expected, so we can simply fail if pfn_to_online_page() == NULL to fix the bug. Link: https://lkml.kernel.org/r/20250828024618.1744895-1-linmiaohe@huawei.com Fixes: f1dd2cd13c4b ("mm, memory_hotplug: do not associate hotadded memory to zones until online") Signed-off-by: Miaohe Lin Suggested-by: David Hildenbrand Acked-by: David Hildenbrand Cc: Naoya Horiguchi Cc: Signed-off-by: Andrew Morton --- mm/memory-failure.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 10b3c281c2ae..df6ee59527dd 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -2568,10 +2568,9 @@ int unpoison_memory(unsigned long pfn) static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); - if (!pfn_valid(pfn)) - return -ENXIO; - - p = pfn_to_page(pfn); + p = pfn_to_online_page(pfn); + if (!p) + return -EIO; folio = page_folio(p); mutex_lock(&mf_mutex); -- cgit v1.2.3