From ec2df7d5e0238a8f56eccc229e2cb22e2c80c944 Mon Sep 17 00:00:00 2001 From: Zhang Enpei Date: Mon, 30 Jun 2025 18:05:05 +0800 Subject: [PATCH 1/2] memory-failure: use a folio in me_huge_page() commit fe01748ca6d6ad25d31eaa61d155f5ecf80907cc upstream. [ Upstream commit b6fd410c32f1a66a52a42d6aae1ab7b011b74547 ] This function was already explicitly calling compound_head(); unfortunately the compiler can't know that and elide the redundant calls to compound_head() buried in page_mapping(), unlock_page(), etc. Switch to using a folio, which does let us elide these calls. Link: https://lkml.kernel.org/r/20231117161447.2461643-5-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Stable-dep-of: 8cf360b9d6a8 ("mm/memory-failure: fix handling of dissolved but not taken off from buddy pages") Signed-off-by: Sasha Levin Fixes: CVE-2024-39298 Signed-off-by: Enpei Zhang Signed-off-by: Wenya Zhang Reviewed-by: Xuexin Jiang --- mm/memory-failure.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index ca738ab7c787..d5792d94490f 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1182,25 +1182,25 @@ static int me_swapcache_clean(struct page_state *ps, struct page *p) */ static int me_huge_page(struct page_state *ps, struct page *p) { + struct folio *folio = page_folio(p); int res; - struct page *hpage = compound_head(p); struct address_space *mapping; bool extra_pins = false; - mapping = page_mapping(hpage); + mapping = folio_mapping(folio); if (mapping) { - res = truncate_error_page(hpage, page_to_pfn(p), mapping); + res = truncate_error_page(&folio->page, page_to_pfn(p), mapping); /* The page is kept in page cache. */ extra_pins = true; - unlock_page(hpage); + folio_unlock(folio); } else { - unlock_page(hpage); + folio_unlock(folio); /* * migration entry prevents later access on error hugepage, * so we can free and dissolve it into buddy to save healthy * subpages. */ - put_page(hpage); + folio_put(folio); if (__page_handle_poison(p) >= 0) { page_ref_inc(p); res = MF_RECOVERED; -- Gitee From 660a715021eaee4ab50ca8f8cbfcf7d4a8c5bd58 Mon Sep 17 00:00:00 2001 From: Zhang Enpei Date: Mon, 30 Jun 2025 18:05:05 +0800 Subject: [PATCH 2/2] mm/memory-failure: fix handling of dissolved but not taken off from buddy pages commit bb9bb13ce64cc7cae47f5e2ab9ce93b7bfa0117e upstream. [ Upstream commit 8cf360b9d6a840700e06864236a01a883b34bbad ] When I did memory failure tests recently, below panic occurs: page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x8cee00 flags: 0x6fffe0000000000(node=1|zone=2|lastcpupid=0x7fff) raw: 06fffe0000000000 dead000000000100 dead000000000122 0000000000000000 raw: 0000000000000000 0000000000000009 00000000ffffffff 0000000000000000 page dumped because: VM_BUG_ON_PAGE(!PageBuddy(page)) ------------[ cut here ]------------ kernel BUG at include/linux/page-flags.h:1009! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI RIP: 0010:__del_page_from_free_list+0x151/0x180 RSP: 0018:ffffa49c90437998 EFLAGS: 00000046 RAX: 0000000000000035 RBX: 0000000000000009 RCX: ffff8dd8dfd1c9c8 RDX: 0000000000000000 RSI: 0000000000000027 RDI: ffff8dd8dfd1c9c0 RBP: ffffd901233b8000 R08: ffffffffab5511f8 R09: 0000000000008c69 R10: 0000000000003c15 R11: ffffffffab5511f8 R12: ffff8dd8fffc0c80 R13: 0000000000000001 R14: ffff8dd8fffc0c80 R15: 0000000000000009 FS: 00007ff916304740(0000) GS:ffff8dd8dfd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055eae50124c8 CR3: 00000008479e0000 CR4: 00000000000006f0 Call Trace: __rmqueue_pcplist+0x23b/0x520 get_page_from_freelist+0x26b/0xe40 __alloc_pages_noprof+0x113/0x1120 __folio_alloc_noprof+0x11/0xb0 alloc_buddy_hugetlb_folio.isra.0+0x5a/0x130 __alloc_fresh_hugetlb_folio+0xe7/0x140 alloc_pool_huge_folio+0x68/0x100 set_max_huge_pages+0x13d/0x340 hugetlb_sysctl_handler_common+0xe8/0x110 proc_sys_call_handler+0x194/0x280 vfs_write+0x387/0x550 ksys_write+0x64/0xe0 do_syscall_64+0xc2/0x1d0 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7ff916114887 RSP: 002b:00007ffec8a2fd78 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 000055eae500e350 RCX: 00007ff916114887 RDX: 0000000000000004 RSI: 000055eae500e390 RDI: 0000000000000003 RBP: 000055eae50104c0 R08: 0000000000000000 R09: 000055eae50104c0 R10: 0000000000000077 R11: 0000000000000246 R12: 0000000000000004 R13: 0000000000000004 R14: 00007ff916216b80 R15: 00007ff916216a00 Modules linked in: mce_inject hwpoison_inject ---[ end trace 0000000000000000 ]--- And before the panic, there had an warning about bad page state: BUG: Bad page state in process page-types pfn:8cee00 page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x8cee00 flags: 0x6fffe0000000000(node=1|zone=2|lastcpupid=0x7fff) page_type: 0xffffff7f(buddy) raw: 06fffe0000000000 ffffd901241c0008 ffffd901240f8008 0000000000000000 raw: 0000000000000000 0000000000000009 00000000ffffff7f 0000000000000000 page dumped because: nonzero mapcount Modules linked in: mce_inject hwpoison_inject CPU: 8 PID: 154211 Comm: page-types Not tainted 6.9.0-rc4-00499-g5544ec3178e2-dirty #22 Call Trace: dump_stack_lvl+0x83/0xa0 bad_page+0x63/0xf0 free_unref_page+0x36e/0x5c0 unpoison_memory+0x50b/0x630 simple_attr_write_xsigned.constprop.0.isra.0+0xb3/0x110 debugfs_attr_write+0x42/0x60 full_proxy_write+0x5b/0x80 vfs_write+0xcd/0x550 ksys_write+0x64/0xe0 do_syscall_64+0xc2/0x1d0 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f189a514887 RSP: 002b:00007ffdcd899718 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f189a514887 RDX: 0000000000000009 RSI: 00007ffdcd899730 RDI: 0000000000000003 RBP: 00007ffdcd8997a0 R08: 0000000000000000 R09: 00007ffdcd8994b2 R10: 0000000000000000 R11: 0000000000000246 R12: 00007ffdcda199a8 R13: 0000000000404af1 R14: 000000000040ad78 R15: 00007f189a7a5040 The root cause should be the below race: memory_failure try_memory_failure_hugetlb me_huge_page __page_handle_poison dissolve_free_hugetlb_folio drain_all_pages -- Buddy page can be isolated e.g. for compaction. take_page_off_buddy -- Failed as page is not in the buddy list. -- Page can be putback into buddy after compaction. page_ref_inc -- Leads to buddy page with refcnt = 1. Then unpoison_memory() can unpoison the page and send the buddy page back into buddy list again leading to the above bad page state warning. And bad_page() will call page_mapcount_reset() to remove PageBuddy from buddy page leading to later VM_BUG_ON_PAGE(!PageBuddy(page)) when trying to allocate this page. Fix this issue by only treating __page_handle_poison() as successful when it returns 1. Link: https://lkml.kernel.org/r/20240523071217.1696196-1-linmiaohe@huawei.com Fixes: ceaf8fbea79a ("mm, hwpoison: skip raw hwpoison page in freeing 1GB hugepage") Signed-off-by: Miaohe Lin Cc: Naoya Horiguchi Cc: Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin Fixes: CVE-2024-39298 Signed-off-by: Enpei Zhang Signed-off-by: Wenya Zhang Reviewed-by: Xuexin Jiang --- mm/memory-failure.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index d5792d94490f..b535a9da37cd 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1201,7 +1201,7 @@ static int me_huge_page(struct page_state *ps, struct page *p) * subpages. */ folio_put(folio); - if (__page_handle_poison(p) >= 0) { + if (__page_handle_poison(p) > 0) { page_ref_inc(p); res = MF_RECOVERED; } else { @@ -2071,7 +2071,7 @@ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb */ if (res == 0) { folio_unlock(folio); - if (__page_handle_poison(p) >= 0) { + if (__page_handle_poison(p) > 0) { page_ref_inc(p); res = MF_RECOVERED; } else { -- Gitee