mirror of
git://git.yoctoproject.org/linux-yocto.git
synced 2025-10-22 23:13:01 +02:00
commit d613f53c83ec47089c4e25859d5e8e0359f6f8da upstream.
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:
<TASK>
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
</TASK>
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 <pfn> > /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:
|
||
|---|---|---|
| .. | ||
| damon | ||
| kasan | ||
| kfence | ||
| kmsan | ||
| backing-dev.c | ||
| balloon_compaction.c | ||
| bootmem_info.c | ||
| cma_debug.c | ||
| cma_sysfs.c | ||
| cma.c | ||
| cma.h | ||
| compaction.c | ||
| debug_page_ref.c | ||
| debug_vm_pgtable.c | ||
| debug.c | ||
| dmapool.c | ||
| early_ioremap.c | ||
| fadvise.c | ||
| failslab.c | ||
| filemap.c | ||
| folio-compat.c | ||
| frontswap.c | ||
| gup_test.c | ||
| gup_test.h | ||
| gup.c | ||
| highmem.c | ||
| hmm.c | ||
| huge_memory.c | ||
| hugetlb_cgroup.c | ||
| hugetlb_vmemmap.c | ||
| hugetlb_vmemmap.h | ||
| hugetlb.c | ||
| hwpoison-inject.c | ||
| init-mm.c | ||
| internal.h | ||
| interval_tree.c | ||
| io-mapping.c | ||
| ioremap.c | ||
| Kconfig | ||
| Kconfig.debug | ||
| khugepaged.c | ||
| kmemleak.c | ||
| ksm.c | ||
| list_lru.c | ||
| maccess.c | ||
| madvise.c | ||
| Makefile | ||
| mapping_dirty_helpers.c | ||
| memblock.c | ||
| memcontrol.c | ||
| memfd.c | ||
| memory_hotplug.c | ||
| memory-failure.c | ||
| memory-tiers.c | ||
| memory.c | ||
| mempolicy.c | ||
| mempool.c | ||
| memremap.c | ||
| memtest.c | ||
| migrate_device.c | ||
| migrate.c | ||
| mincore.c | ||
| mlock.c | ||
| mm_init.c | ||
| mm_slot.h | ||
| mmap_lock.c | ||
| mmap.c | ||
| mmu_gather.c | ||
| mmu_notifier.c | ||
| mmzone.c | ||
| mprotect.c | ||
| mremap.c | ||
| msync.c | ||
| nommu.c | ||
| oom_kill.c | ||
| page_alloc.c | ||
| page_counter.c | ||
| page_ext.c | ||
| page_idle.c | ||
| page_io.c | ||
| page_isolation.c | ||
| page_owner.c | ||
| page_poison.c | ||
| page_reporting.c | ||
| page_reporting.h | ||
| page_table_check.c | ||
| page_vma_mapped.c | ||
| page-writeback.c | ||
| pagewalk.c | ||
| percpu-internal.h | ||
| percpu-km.c | ||
| percpu-stats.c | ||
| percpu-vm.c | ||
| percpu.c | ||
| pgalloc-track.h | ||
| pgtable-generic.c | ||
| process_vm_access.c | ||
| ptdump.c | ||
| readahead.c | ||
| rmap.c | ||
| rodata_test.c | ||
| secretmem.c | ||
| shmem.c | ||
| shrinker_debug.c | ||
| shuffle.c | ||
| shuffle.h | ||
| slab_common.c | ||
| slab.c | ||
| slab.h | ||
| slob.c | ||
| slub.c | ||
| sparse-vmemmap.c | ||
| sparse.c | ||
| swap_cgroup.c | ||
| swap_slots.c | ||
| swap_state.c | ||
| swap.c | ||
| swap.h | ||
| swapfile.c | ||
| truncate.c | ||
| usercopy.c | ||
| userfaultfd.c | ||
| util.c | ||
| vmalloc.c | ||
| vmpressure.c | ||
| vmscan.c | ||
| vmstat.c | ||
| workingset.c | ||
| z3fold.c | ||
| zbud.c | ||
| zpool.c | ||
| zsmalloc.c | ||
| zswap.c | ||