From 3d7fed4ad8ccb691d217efbb0f934e6a4df5ef91 Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Mon, 14 Oct 2019 14:12:29 -0700 Subject: mm/memory-failure: poison read receives SIGKILL instead of SIGBUS if mmaped more than once Mmap /dev/dax more than once, then read the poison location using address from one of the mappings. The other mappings due to not having the page mapped in will cause SIGKILLs delivered to the process. SIGKILL succeeds over SIGBUS, so user process loses the opportunity to handle the UE. Although one may add MAP_POPULATE to mmap(2) to work around the issue, MAP_POPULATE makes mapping 128GB of pmem several magnitudes slower, so isn't always an option. Details - ndctl inject-error --block=10 --count=1 namespace6.0 ./read_poison -x dax6.0 -o 5120 -m 2 mmaped address 0x7f5bb6600000 mmaped address 0x7f3cf3600000 doing local read at address 0x7f3cf3601400 Killed Console messages in instrumented kernel - mce: Uncorrected hardware memory error in user-access at edbe201400 Memory failure: tk->addr = 7f5bb6601000 Memory failure: address edbe201: call dev_pagemap_mapping_shift dev_pagemap_mapping_shift: page edbe201: no PUD Memory failure: tk->size_shift == 0 Memory failure: Unable to find user space address edbe201 in read_poison Memory failure: tk->addr = 7f3cf3601000 Memory failure: address edbe201: call dev_pagemap_mapping_shift Memory failure: tk->size_shift = 21 Memory failure: 0xedbe201: forcibly killing read_poison:22434 because of failure to unmap corrupted page => to deliver SIGKILL Memory failure: 0xedbe201: Killing read_poison:22434 due to hardware memory corruption => to deliver SIGBUS Link: http://lkml.kernel.org/r/1565112345-28754-3-git-send-email-jane.chu@oracle.com Signed-off-by: Jane Chu Suggested-by: Naoya Horiguchi Reviewed-by: Dan Williams Acked-by: Naoya Horiguchi Cc: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 7ef849da8278..0ae72b6acee7 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -199,7 +199,6 @@ struct to_kill { struct task_struct *tsk; unsigned long addr; short size_shift; - char addr_valid; }; /* @@ -324,22 +323,27 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, } } tk->addr = page_address_in_vma(p, vma); - tk->addr_valid = 1; if (is_zone_device_page(p)) tk->size_shift = dev_pagemap_mapping_shift(p, vma); else tk->size_shift = compound_order(compound_head(p)) + PAGE_SHIFT; /* - * In theory we don't have to kill when the page was - * munmaped. But it could be also a mremap. Since that's - * likely very rare kill anyways just out of paranoia, but use - * a SIGKILL because the error is not contained anymore. + * Send SIGKILL if "tk->addr == -EFAULT". Also, as + * "tk->size_shift" is always non-zero for !is_zone_device_page(), + * so "tk->size_shift == 0" effectively checks no mapping on + * ZONE_DEVICE. Indeed, when a devdax page is mmapped N times + * to a process' address space, it's possible not all N VMAs + * contain mappings for the page, but at least one VMA does. + * Only deliver SIGBUS with payload derived from the VMA that + * has a mapping for the page. */ - if (tk->addr == -EFAULT || tk->size_shift == 0) { + if (tk->addr == -EFAULT) { pr_info("Memory failure: Unable to find user space address %lx in %s\n", page_to_pfn(p), tsk->comm); - tk->addr_valid = 0; + } else if (tk->size_shift == 0) { + kfree(tk); + return; } get_task_struct(tsk); tk->tsk = tsk; @@ -366,7 +370,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, * make sure the process doesn't catch the * signal and then access the memory. Just kill it. */ - if (fail || tk->addr_valid == 0) { + if (fail || tk->addr == -EFAULT) { pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", pfn, tk->tsk->comm, tk->tsk->pid); do_send_sig_info(SIGKILL, SEND_SIG_PRIV, -- cgit v1.2.3 From 96c804a6ae8c59a9092b3d5dd581198472063184 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 18 Oct 2019 20:19:23 -0700 Subject: mm/memory-failure.c: don't access uninitialized memmaps in memory_failure() We should check for pfn_to_online_page() to not access uninitialized memmaps. Reshuffle the code so we don't have to duplicate the error message. Link: http://lkml.kernel.org/r/20191009142435.3975-3-david@redhat.com Signed-off-by: David Hildenbrand Fixes: f1dd2cd13c4b ("mm, memory_hotplug: do not associate hotadded memory to zones until online") [visible after d0dc12e86b319] Acked-by: Naoya Horiguchi Cc: Michal Hocko Cc: [4.13+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 0ae72b6acee7..3151c87dff73 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1257,17 +1257,19 @@ int memory_failure(unsigned long pfn, int flags) if (!sysctl_memory_failure_recovery) panic("Memory failure on page %lx", pfn); - if (!pfn_valid(pfn)) { + p = pfn_to_online_page(pfn); + if (!p) { + if (pfn_valid(pfn)) { + pgmap = get_dev_pagemap(pfn, NULL); + if (pgmap) + return memory_failure_dev_pagemap(pfn, flags, + pgmap); + } pr_err("Memory failure: %#lx: memory outside kernel control\n", pfn); return -ENXIO; } - pgmap = get_dev_pagemap(pfn, NULL); - if (pgmap) - return memory_failure_dev_pagemap(pfn, flags, pgmap); - - p = pfn_to_page(pfn); if (PageHuge(p)) return memory_failure_hugetlb(pfn, flags); if (TestSetPageHWPoison(p)) { -- cgit v1.2.3