From: Tony Luck <tony.luck@intel.com> mainline inclusion from mainline-v5.13 commit 171936ddaf97e6f4e1264f4128bb5cf15691339c category: bugfix bugzilla: 167325 https://gitee.com/openeuler/kernel/issues/I4DDEL Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- Patch series "mm,hwpoison: fix sending SIGBUS for Action Required MCE", v5. I wrote this patchset to materialize what I think is the current allowable solution mentioned by the previous discussion [1]. I simply borrowed Tony's mutex patch and Aili's return code patch, then I queued another one to find error virtual address in the best effort manner. I know that this is not a perfect solution, but should work for some typical case. [1]: https://lore.kernel.org/linux-mm/20210331192540.2141052f@alex-virtual-machin... This patch (of 2): There can be races when multiple CPUs consume poison from the same page. The first into memory_failure() atomically sets the HWPoison page flag and begins hunting for tasks that map this page. Eventually it invalidates those mappings and may send a SIGBUS to the affected tasks. But while all that work is going on, other CPUs see a "success" return code from memory_failure() and so they believe the error has been handled and continue executing. Fix by wrapping most of the internal parts of memory_failure() in a mutex. [akpm@linux-foundation.org: make mf_mutex local to memory_failure()] Link: https://lkml.kernel.org/r/20210521030156.2612074-1-nao.horiguchi@gmail.com Link: https://lkml.kernel.org/r/20210521030156.2612074-2-nao.horiguchi@gmail.com Signed-off-by: Tony Luck <tony.luck@intel.com> Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com> Reviewed-by: Borislav Petkov <bp@suse.de> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Aili Yao <yaoaili@kingsoft.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: David Hildenbrand <david@redhat.com> Cc: Jue Wang <juew@google.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Conflicts: mm/memory-failure.c Signed-off-by: Nanyong Sun <sunnanyong@huawei.com> Reviewed-by: Chen Wandun <chenwandun@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> --- mm/memory-failure.c | 37 +++++++++++++++++++++++-------------- 1 file changed, 23 insertions(+), 14 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index d00d1b2e97da..8df59bb777a7 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1329,8 +1329,9 @@ int memory_failure(unsigned long pfn, int flags) struct page *hpage; struct page *orig_head; struct dev_pagemap *pgmap; - int res; + int res = 0; unsigned long page_flags; + static DEFINE_MUTEX(mf_mutex); if (!sysctl_memory_failure_recovery) panic("Memory failure on page %lx", pfn); @@ -1348,12 +1349,17 @@ int memory_failure(unsigned long pfn, int flags) return -ENXIO; } - if (PageHuge(p)) - return memory_failure_hugetlb(pfn, flags); + mutex_lock(&mf_mutex); + + if (PageHuge(p)) { + res = memory_failure_hugetlb(pfn, flags); + goto unlock_mutex; + } + if (TestSetPageHWPoison(p)) { pr_err("Memory failure: %#lx: already hardware poisoned\n", pfn); - return 0; + goto unlock_mutex; } orig_head = hpage = compound_head(p); @@ -1373,17 +1379,18 @@ int memory_failure(unsigned long pfn, int flags) if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p)) { if (is_free_buddy_page(p)) { action_result(pfn, MF_MSG_BUDDY, MF_DELAYED); - return 0; } else { action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED); - return -EBUSY; + res = -EBUSY; } + goto unlock_mutex; } if (PageTransHuge(hpage)) { if (try_to_split_thp_page(p, "Memory Failure") < 0) { action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED); - return -EBUSY; + res = -EBUSY; + goto unlock_mutex; } VM_BUG_ON_PAGE(!page_count(p), p); } @@ -1403,7 +1410,7 @@ int memory_failure(unsigned long pfn, int flags) action_result(pfn, MF_MSG_BUDDY, MF_DELAYED); else action_result(pfn, MF_MSG_BUDDY_2ND, MF_DELAYED); - return 0; + goto unlock_mutex; } lock_page(p); @@ -1415,7 +1422,7 @@ int memory_failure(unsigned long pfn, int flags) if (PageCompound(p) && compound_head(p) != orig_head) { action_result(pfn, MF_MSG_DIFFERENT_COMPOUND, MF_IGNORED); res = -EBUSY; - goto out; + goto unlock_page; } /* @@ -1435,14 +1442,14 @@ int memory_failure(unsigned long pfn, int flags) num_poisoned_pages_dec(); unlock_page(p); put_page(p); - return 0; + goto unlock_mutex; } if (hwpoison_filter(p)) { if (TestClearPageHWPoison(p)) num_poisoned_pages_dec(); unlock_page(p); put_page(p); - return 0; + goto unlock_mutex; } /* @@ -1466,7 +1473,7 @@ int memory_failure(unsigned long pfn, int flags) if (!hwpoison_user_mappings(p, pfn, flags, &p)) { action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED); res = -EBUSY; - goto out; + goto unlock_page; } /* @@ -1475,13 +1482,15 @@ int memory_failure(unsigned long pfn, int flags) if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) { action_result(pfn, MF_MSG_TRUNCATED_LRU, MF_IGNORED); res = -EBUSY; - goto out; + goto unlock_page; } identify_page_state: res = identify_page_state(pfn, p, page_flags); -out: +unlock_page: unlock_page(p); +unlock_mutex: + mutex_unlock(&mf_mutex); return res; } EXPORT_SYMBOL_GPL(memory_failure); -- 2.20.1