From 86a66810baa87e5d1c93a51f71d36c7f71fe3113 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 13 Jul 2018 21:49:56 -0700 Subject: mm, madvise_inject_error: Disable MADV_SOFT_OFFLINE for ZONE_DEVICE pages Given that dax / device-mapped pages are never subject to page allocations remove them from consideration by the soft-offline mechanism. Reported-by: Naoya Horiguchi Signed-off-by: Dan Williams Acked-by: Naoya Horiguchi Signed-off-by: Dave Jiang --- mm/memory-failure.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 9d142b9b86dc..988f977db3d2 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1751,6 +1751,14 @@ int soft_offline_page(struct page *page, int flags) int ret; unsigned long pfn = page_to_pfn(page); + if (is_zone_device_page(page)) { + pr_debug_ratelimited("soft_offline: %#lx page is device page\n", + pfn); + if (flags & MF_COUNT_INCREASED) + put_page(page); + return -EIO; + } + if (PageHWPoison(page)) { pr_info("soft offline: %#lx page already poisoned\n", pfn); if (flags & MF_COUNT_INCREASED) -- cgit v1.2.3-55-g7522 From ae1139ece126b8eb6d0770094fbac43ea928d9d9 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 13 Jul 2018 21:50:11 -0700 Subject: mm, memory_failure: Collect mapping size in collect_procs() In preparation for supporting memory_failure() for dax mappings, teach collect_procs() to also determine the mapping size. Unlike typical mappings the dax mapping size is determined by walking page-table entries rather than using the compound-page accounting for THP pages. Acked-by: Naoya Horiguchi Signed-off-by: Dan Williams Signed-off-by: Dave Jiang --- mm/memory-failure.c | 81 ++++++++++++++++++++++++++--------------------------- 1 file changed, 40 insertions(+), 41 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 988f977db3d2..8a81680d00dd 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -173,23 +173,52 @@ int hwpoison_filter(struct page *p) EXPORT_SYMBOL_GPL(hwpoison_filter); +/* + * Kill all processes that have a poisoned page mapped and then isolate + * the page. + * + * General strategy: + * Find all processes having the page mapped and kill them. + * But we keep a page reference around so that the page is not + * actually freed yet. + * Then stash the page away + * + * There's no convenient way to get back to mapped processes + * from the VMAs. So do a brute-force search over all + * running processes. + * + * Remember that machine checks are not common (or rather + * if they are common you have other problems), so this shouldn't + * be a performance issue. + * + * Also there are some races possible while we get from the + * error detection to actually handle it. + */ + +struct to_kill { + struct list_head nd; + struct task_struct *tsk; + unsigned long addr; + short size_shift; + char addr_valid; +}; + /* * Send all the processes who have the page mapped a signal. * ``action optional'' if they are not immediately affected by the error * ``action required'' if error happened in current execution context */ -static int kill_proc(struct task_struct *t, unsigned long addr, - unsigned long pfn, struct page *page, int flags) +static int kill_proc(struct to_kill *tk, unsigned long pfn, int flags) { - short addr_lsb; + struct task_struct *t = tk->tsk; + short addr_lsb = tk->size_shift; int ret; pr_err("Memory failure: %#lx: Killing %s:%d due to hardware memory corruption\n", pfn, t->comm, t->pid); - addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT; if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) { - ret = force_sig_mceerr(BUS_MCEERR_AR, (void __user *)addr, + ret = force_sig_mceerr(BUS_MCEERR_AR, (void __user *)tk->addr, addr_lsb, current); } else { /* @@ -198,7 +227,7 @@ static int kill_proc(struct task_struct *t, unsigned long addr, * This could cause a loop when the user sets SIGBUS * to SIG_IGN, but hopefully no one will do that? */ - ret = send_sig_mceerr(BUS_MCEERR_AO, (void __user *)addr, + ret = send_sig_mceerr(BUS_MCEERR_AO, (void __user *)tk->addr, addr_lsb, t); /* synchronous? */ } if (ret < 0) @@ -234,35 +263,6 @@ void shake_page(struct page *p, int access) } EXPORT_SYMBOL_GPL(shake_page); -/* - * Kill all processes that have a poisoned page mapped and then isolate - * the page. - * - * General strategy: - * Find all processes having the page mapped and kill them. - * But we keep a page reference around so that the page is not - * actually freed yet. - * Then stash the page away - * - * There's no convenient way to get back to mapped processes - * from the VMAs. So do a brute-force search over all - * running processes. - * - * Remember that machine checks are not common (or rather - * if they are common you have other problems), so this shouldn't - * be a performance issue. - * - * Also there are some races possible while we get from the - * error detection to actually handle it. - */ - -struct to_kill { - struct list_head nd; - struct task_struct *tsk; - unsigned long addr; - char addr_valid; -}; - /* * Failure handling: if we can't find or can't kill a process there's * not much we can do. We just print a message and ignore otherwise. @@ -292,6 +292,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, } tk->addr = page_address_in_vma(p, vma); tk->addr_valid = 1; + tk->size_shift = compound_order(compound_head(p)) + PAGE_SHIFT; /* * In theory we don't have to kill when the page was @@ -317,9 +318,8 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, * Also when FAIL is set do a force kill because something went * wrong earlier. */ -static void kill_procs(struct list_head *to_kill, int forcekill, - bool fail, struct page *page, unsigned long pfn, - int flags) +static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, + unsigned long pfn, int flags) { struct to_kill *tk, *next; @@ -342,8 +342,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, * check for that, but we need to tell the * process anyways. */ - else if (kill_proc(tk->tsk, tk->addr, - pfn, page, flags) < 0) + else if (kill_proc(tk, pfn, flags) < 0) pr_err("Memory failure: %#lx: Cannot send advisory machine check signal to %s:%d\n", pfn, tk->tsk->comm, tk->tsk->pid); } @@ -1012,7 +1011,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * any accesses to the poisoned memory. */ forcekill = PageDirty(hpage) || (flags & MF_MUST_KILL); - kill_procs(&tokill, forcekill, !unmap_success, p, pfn, flags); + kill_procs(&tokill, forcekill, !unmap_success, pfn, flags); return unmap_success; } -- cgit v1.2.3-55-g7522 From 6100e34b2526e1dc3dbcc47fea2677974d6aaea5 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 13 Jul 2018 21:50:21 -0700 Subject: mm, memory_failure: Teach memory_failure() about dev_pagemap pages mce: Uncorrected hardware memory error in user-access at af34214200 {1}[Hardware Error]: It has been corrected by h/w and requires no further action mce: [Hardware Error]: Machine check events logged {1}[Hardware Error]: event severity: corrected Memory failure: 0xaf34214: reserved kernel page still referenced by 1 users [..] Memory failure: 0xaf34214: recovery action for reserved kernel page: Failed mce: Memory error not recovered In contrast to typical memory, dev_pagemap pages may be dax mapped. With dax there is no possibility to map in another page dynamically since dax establishes 1:1 physical address to file offset associations. Also dev_pagemap pages associated with NVDIMM / persistent memory devices can internal remap/repair addresses with poison. While memory_failure() assumes that it can discard typical poisoned pages and keep them unmapped indefinitely, dev_pagemap pages may be returned to service after the error is cleared. Teach memory_failure() to detect and handle MEMORY_DEVICE_HOST dev_pagemap pages that have poison consumed by userspace. Mark the memory as UC instead of unmapping it completely to allow ongoing access via the device driver (nd_pmem). Later, nd_pmem will grow support for marking the page back to WB when the error is cleared. Cc: Jan Kara Cc: Christoph Hellwig Cc: Jérôme Glisse Cc: Matthew Wilcox Cc: Naoya Horiguchi Cc: Ross Zwisler Signed-off-by: Dan Williams Signed-off-by: Dave Jiang --- include/linux/mm.h | 1 + mm/memory-failure.c | 125 +++++++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 124 insertions(+), 2 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/include/linux/mm.h b/include/linux/mm.h index a0fbb9ffe380..374e5e9284f7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2725,6 +2725,7 @@ enum mf_action_page_type { MF_MSG_TRUNCATED_LRU, MF_MSG_BUDDY, MF_MSG_BUDDY_2ND, + MF_MSG_DAX, MF_MSG_UNKNOWN, }; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 8a81680d00dd..32a644d9c2ee 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -55,6 +55,7 @@ #include #include #include +#include #include #include #include "internal.h" @@ -263,6 +264,40 @@ void shake_page(struct page *p, int access) } EXPORT_SYMBOL_GPL(shake_page); +static unsigned long dev_pagemap_mapping_shift(struct page *page, + struct vm_area_struct *vma) +{ + unsigned long address = vma_address(page, vma); + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + pgd = pgd_offset(vma->vm_mm, address); + if (!pgd_present(*pgd)) + return 0; + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + return 0; + pud = pud_offset(p4d, address); + if (!pud_present(*pud)) + return 0; + if (pud_devmap(*pud)) + return PUD_SHIFT; + pmd = pmd_offset(pud, address); + if (!pmd_present(*pmd)) + return 0; + if (pmd_devmap(*pmd)) + return PMD_SHIFT; + pte = pte_offset_map(pmd, address); + if (!pte_present(*pte)) + return 0; + if (pte_devmap(*pte)) + return PAGE_SHIFT; + return 0; +} + /* * Failure handling: if we can't find or can't kill a process there's * not much we can do. We just print a message and ignore otherwise. @@ -292,7 +327,10 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, } tk->addr = page_address_in_vma(p, vma); tk->addr_valid = 1; - tk->size_shift = compound_order(compound_head(p)) + PAGE_SHIFT; + 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 @@ -300,7 +338,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, * likely very rare kill anyways just out of paranoia, but use * a SIGKILL because the error is not contained anymore. */ - if (tk->addr == -EFAULT) { + if (tk->addr == -EFAULT || tk->size_shift == 0) { pr_info("Memory failure: Unable to find user space address %lx in %s\n", page_to_pfn(p), tsk->comm); tk->addr_valid = 0; @@ -514,6 +552,7 @@ static const char * const action_page_types[] = { [MF_MSG_TRUNCATED_LRU] = "already truncated LRU page", [MF_MSG_BUDDY] = "free buddy page", [MF_MSG_BUDDY_2ND] = "free buddy page (2nd try)", + [MF_MSG_DAX] = "dax page", [MF_MSG_UNKNOWN] = "unknown page", }; @@ -1111,6 +1150,83 @@ out: return res; } +static int memory_failure_dev_pagemap(unsigned long pfn, int flags, + struct dev_pagemap *pgmap) +{ + struct page *page = pfn_to_page(pfn); + const bool unmap_success = true; + unsigned long size = 0; + struct to_kill *tk; + LIST_HEAD(tokill); + int rc = -EBUSY; + loff_t start; + + /* + * Prevent the inode from being freed while we are interrogating + * the address_space, typically this would be handled by + * lock_page(), but dax pages do not use the page lock. This + * also prevents changes to the mapping of this pfn until + * poison signaling is complete. + */ + if (!dax_lock_mapping_entry(page)) + goto out; + + if (hwpoison_filter(page)) { + rc = 0; + goto unlock; + } + + switch (pgmap->type) { + case MEMORY_DEVICE_PRIVATE: + case MEMORY_DEVICE_PUBLIC: + /* + * TODO: Handle HMM pages which may need coordination + * with device-side memory. + */ + goto unlock; + default: + break; + } + + /* + * Use this flag as an indication that the dax page has been + * remapped UC to prevent speculative consumption of poison. + */ + SetPageHWPoison(page); + + /* + * Unlike System-RAM there is no possibility to swap in a + * different physical page at a given virtual address, so all + * userspace consumption of ZONE_DEVICE memory necessitates + * SIGBUS (i.e. MF_MUST_KILL) + */ + flags |= MF_ACTION_REQUIRED | MF_MUST_KILL; + collect_procs(page, &tokill, flags & MF_ACTION_REQUIRED); + + list_for_each_entry(tk, &tokill, nd) + if (tk->size_shift) + size = max(size, 1UL << tk->size_shift); + if (size) { + /* + * Unmap the largest mapping to avoid breaking up + * device-dax mappings which are constant size. The + * actual size of the mapping being torn down is + * communicated in siginfo, see kill_proc() + */ + start = (page->index << PAGE_SHIFT) & ~(size - 1); + unmap_mapping_range(page->mapping, start, start + size, 0); + } + kill_procs(&tokill, flags & MF_MUST_KILL, !unmap_success, pfn, flags); + rc = 0; +unlock: + dax_unlock_mapping_entry(page); +out: + /* drop pgmap ref acquired in caller */ + put_dev_pagemap(pgmap); + action_result(pfn, MF_MSG_DAX, rc ? MF_FAILED : MF_RECOVERED); + return rc; +} + /** * memory_failure - Handle memory failure of a page. * @pfn: Page Number of the corrupted page @@ -1133,6 +1249,7 @@ int memory_failure(unsigned long pfn, int flags) struct page *p; struct page *hpage; struct page *orig_head; + struct dev_pagemap *pgmap; int res; unsigned long page_flags; @@ -1145,6 +1262,10 @@ int memory_failure(unsigned long pfn, int flags) 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); -- cgit v1.2.3-55-g7522