cregit-Linux how code gets into the kernel

Release 4.8 mm/memory-failure.c

Directory: mm
/*
 * Copyright (C) 2008, 2009 Intel Corporation
 * Authors: Andi Kleen, Fengguang Wu
 *
 * This software may be redistributed and/or modified under the terms of
 * the GNU General Public License ("GPL") version 2 only as published by the
 * Free Software Foundation.
 *
 * High level machine check handler. Handles pages reported by the
 * hardware as being corrupted usually due to a multi-bit ECC memory or cache
 * failure.
 * 
 * In addition there is a "soft offline" entry point that allows stop using
 * not-yet-corrupted-by-suspicious pages without killing anything.
 *
 * Handles page cache pages in various states.  The tricky part
 * here is that we can access any page asynchronously in respect to 
 * other VM users, because memory failures could happen anytime and 
 * anywhere. This could violate some of their assumptions. This is why 
 * this code has to be extremely careful. Generally it tries to use 
 * normal locking rules, as in get the standard locks, even if that means 
 * the error handling takes potentially a long time.
 *
 * It can be very tempting to add handling for obscure cases here.
 * In general any code for handling new cases should only be added iff:
 * - You know how to test it.
 * - You have a test that can be added to mce-test
 *   https://git.kernel.org/cgit/utils/cpu/mce/mce-test.git/
 * - The case actually shows up as a frequent (top 10) page state in
 *   tools/vm/page-types when running a real workload.
 * 
 * There are several operations here with exponential complexity because
 * of unsuitable VM data structures. For example the operation to map back 
 * from RMAP chains to processes has to walk the complete process list and 
 * has non linear complexity with the number. But since memory corruptions
 * are rare we hope to get away with this. This avoids impacting the core 
 * VM.
 */
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/page-flags.h>
#include <linux/kernel-page-flags.h>
#include <linux/sched.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/export.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/backing-dev.h>
#include <linux/migrate.h>
#include <linux/page-isolation.h>
#include <linux/suspend.h>
#include <linux/slab.h>
#include <linux/swapops.h>
#include <linux/hugetlb.h>
#include <linux/memory_hotplug.h>
#include <linux/mm_inline.h>
#include <linux/kfifo.h>
#include <linux/ratelimit.h>
#include "internal.h"
#include "ras/ras_event.h"


int sysctl_memory_failure_early_kill __read_mostly = 0;


int sysctl_memory_failure_recovery __read_mostly = 1;


atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);

#if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE)


u32 hwpoison_filter_enable = 0;

u32 hwpoison_filter_dev_major = ~0U;

u32 hwpoison_filter_dev_minor = ~0U;

u64 hwpoison_filter_flags_mask;

u64 hwpoison_filter_flags_value;

EXPORT_SYMBOL_GPL(hwpoison_filter_enable);

EXPORT_SYMBOL_GPL(hwpoison_filter_dev_major);

EXPORT_SYMBOL_GPL(hwpoison_filter_dev_minor);

EXPORT_SYMBOL_GPL(hwpoison_filter_flags_mask);

EXPORT_SYMBOL_GPL(hwpoison_filter_flags_value);


static int hwpoison_filter_dev(struct page *p) { struct address_space *mapping; dev_t dev; if (hwpoison_filter_dev_major == ~0U && hwpoison_filter_dev_minor == ~0U) return 0; /* * page_mapping() does not accept slab pages. */ if (PageSlab(p)) return -EINVAL; mapping = page_mapping(p); if (mapping == NULL || mapping->host == NULL) return -EINVAL; dev = mapping->host->i_sb->s_dev; if (hwpoison_filter_dev_major != ~0U && hwpoison_filter_dev_major != MAJOR(dev)) return -EINVAL; if (hwpoison_filter_dev_minor != ~0U && hwpoison_filter_dev_minor != MINOR(dev)) return -EINVAL; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
fengguang wufengguang wu11799.15%150.00%
andi kleenandi kleen10.85%150.00%
Total118100.00%2100.00%


static int hwpoison_filter_flags(struct page *p) { if (!hwpoison_filter_flags_mask) return 0; if ((stable_page_flags(p) & hwpoison_filter_flags_mask) == hwpoison_filter_flags_value) return 0; else return -EINVAL; }

Contributors

PersonTokensPropCommitsCommitProp
fengguang wufengguang wu40100.00%1100.00%
Total40100.00%1100.00%

/* * This allows stress tests to limit test scope to a collection of tasks * by putting them under some memcg. This prevents killing unrelated/important * processes such as /sbin/init. Note that the target task may share clean * pages with init (eg. libc text), which is harmless. If the target task * share _dirty_ pages with another task B, the test scheme must make sure B * is also included in the memcg. At last, due to race conditions this filter * can only guarantee that the page either belongs to the memcg tasks, or is * a freed page. */ #ifdef CONFIG_MEMCG u64 hwpoison_filter_memcg; EXPORT_SYMBOL_GPL(hwpoison_filter_memcg);
static int hwpoison_filter_task(struct page *p) { if (!hwpoison_filter_memcg) return 0; if (page_cgroup_ino(p) != hwpoison_filter_memcg) return -EINVAL; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen3291.43%133.33%
vladimir davydovvladimir davydov25.71%133.33%
tejun heotejun heo12.86%133.33%
Total35100.00%3100.00%

#else
static int hwpoison_filter_task(struct page *p) { return 0; }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen14100.00%1100.00%
Total14100.00%1100.00%

#endif
int hwpoison_filter(struct page *p) { if (!hwpoison_filter_enable) return 0; if (hwpoison_filter_dev(p)) return -EINVAL; if (hwpoison_filter_flags(p)) return -EINVAL; if (hwpoison_filter_task(p)) return -EINVAL; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
fengguang wufengguang wu3564.81%250.00%
andi kleenandi kleen1120.37%125.00%
haicheng lihaicheng li814.81%125.00%
Total54100.00%4100.00%

#else
int hwpoison_filter(struct page *p) { return 0; }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen13100.00%1100.00%
Total13100.00%1100.00%

#endif EXPORT_SYMBOL_GPL(hwpoison_filter); /* * 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, int trapno, unsigned long pfn, struct page *page, int flags) { struct siginfo si; int ret; pr_err("Memory failure: %#lx: Killing %s:%d due to hardware memory corruption\n", pfn, t->comm, t->pid); si.si_signo = SIGBUS; si.si_errno = 0; si.si_addr = (void *)addr; #ifdef __ARCH_SI_TRAPNO si.si_trapno = trapno; #endif si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT; if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) { si.si_code = BUS_MCEERR_AR; ret = force_sig_info(SIGBUS, &si, current); } else { /* * Don't use force here, it's convenient if the signal * can be temporarily blocked. * This could cause a loop when the user sets SIGBUS * to SIG_IGN, but hopefully no one will do that? */ si.si_code = BUS_MCEERR_AO; ret = send_sig_info(SIGBUS, &si, t); /* synchronous? */ } if (ret < 0) pr_info("Memory failure: Error sending signal to %s:%d: %d\n", t->comm, t->pid, ret); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen12769.78%228.57%
tony lucktony luck5027.47%228.57%
chen yucongchen yucong21.10%114.29%
joe perchesjoe perches21.10%114.29%
wanpeng liwanpeng li10.55%114.29%
Total182100.00%7100.00%

/* * When a unknown page type is encountered drain as many buffers as possible * in the hope to turn the page into a LRU or free page, which we can handle. */
void shake_page(struct page *p, int access) { if (!PageSlab(p)) { lru_add_drain_all(); if (PageLRU(p)) return; drain_all_pages(page_zone(p)); if (PageLRU(p) || is_free_buddy_page(p)) return; } /* * Only call shrink_node_slabs here (which would also shrink * other caches) if access is not potentially fatal. */ if (access) drop_slab_node(page_to_nid(p)); }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen5580.88%228.57%
vlastimil babkavlastimil babka68.82%228.57%
dave chinnerdave chinner45.88%114.29%
vladimir davydovvladimir davydov22.94%114.29%
johannes weinerjohannes weiner11.47%114.29%
Total68100.00%7100.00%

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. */ /* * Schedule a process for later kill. * Uses GFP_ATOMIC allocations to avoid potential recursions in the VM. * TBD would GFP_NOIO be enough? */
static void add_to_kill(struct task_struct *tsk, struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, struct to_kill **tkc) { struct to_kill *tk; if (*tkc) { tk = *tkc; *tkc = NULL; } else { tk = kmalloc(sizeof(struct to_kill), GFP_ATOMIC); if (!tk) { pr_err("Memory failure: Out of memory while machine check handling\n"); return; } } tk->addr = page_address_in_vma(p, vma); tk->addr_valid = 1; /* * 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. */ 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; } get_task_struct(tsk); tk->tsk = tsk; list_add_tail(&tk->nd, to_kill); }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen15098.04%250.00%
chen yucongchen yucong21.31%125.00%
joe perchesjoe perches10.65%125.00%
Total153100.00%4100.00%

/* * Kill the processes that have been collected earlier. * * Only do anything when DOIT is set, otherwise just free the list * (this is used for clean pages which do not need killing) * 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, int trapno, int fail, struct page *page, unsigned long pfn, int flags) { struct to_kill *tk, *next; list_for_each_entry_safe (tk, next, to_kill, nd) { if (forcekill) { /* * In case something went wrong with munmapping * make sure the process doesn't catch the * signal and then access the memory. Just kill it. */ if (fail || tk->addr_valid == 0) { pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", pfn, tk->tsk->comm, tk->tsk->pid); force_sig(SIGKILL, tk->tsk); } /* * In theory the process could have mapped * something else on the address in-between. We could * check for that, but we need to tell the * process anyways. */ else if (kill_proc(tk->tsk, tk->addr, trapno, pfn, page, flags) < 0) pr_err("Memory failure: %#lx: Cannot send advisory machine check signal to %s:%d\n", pfn, tk->tsk->comm, tk->tsk->pid); } put_task_struct(tk->tsk); kfree(tk); } }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen14291.61%342.86%
tony lucktony luck95.81%228.57%
chen yucongchen yucong21.29%114.29%
joe perchesjoe perches21.29%114.29%
Total155100.00%7100.00%

/* * Find a dedicated thread which is supposed to handle SIGBUS(BUS_MCEERR_AO) * on behalf of the thread group. Return task_struct of the (first found) * dedicated thread if found, and return NULL otherwise. * * We already hold read_lock(&tasklist_lock) in the caller, so we don't * have to call rcu_read_lock/unlock() in this function. */
static struct task_struct *find_early_kill_thread(struct task_struct *tsk) { struct task_struct *t; for_each_thread(tsk, t) if ((t->flags & PF_MCE_PROCESS) && (t->flags & PF_MCE_EARLY)) return t; return NULL; }

Contributors

PersonTokensPropCommitsCommitProp
naoya horiguchinaoya horiguchi48100.00%1100.00%
Total48100.00%1100.00%

/* * Determine whether a given process is "early kill" process which expects * to be signaled when some page under the process is hwpoisoned. * Return task_struct of the dedicated thread (main thread unless explicitly * specified) if the process is "early kill," and otherwise returns NULL. */
static struct task_struct *task_early_kill(struct task_struct *tsk, int force_early) { struct task_struct *t; if (!tsk->mm) return NULL; if (force_early) return tsk; t = find_early_kill_thread(tsk); if (t) return t; if (sysctl_memory_failure_early_kill) return tsk; return NULL; }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen2743.55%133.33%
naoya horiguchinaoya horiguchi2641.94%133.33%
tony lucktony luck914.52%133.33%
Total62100.00%3100.00%

/* * Collect processes when the error hit an anonymous page. */
static void collect_procs_anon(struct page *page, struct list_head *to_kill, struct to_kill **tkc, int force_early) { struct vm_area_struct *vma; struct task_struct *tsk; struct anon_vma *av; pgoff_t pgoff; av = page_lock_anon_vma_read(page); if (av == NULL) /* Not actually mapped anymore */ return; pgoff = page_to_pgoff(page); read_lock(&tasklist_lock); for_each_process (tsk) { struct anon_vma_chain *vmac; struct task_struct *t = task_early_kill(tsk, force_early); if (!t) continue; anon_vma_interval_tree_foreach(vmac, &av->rb_root, pgoff, pgoff) { vma = vmac->vma; if (!page_mapped_in_vma(page, vma)) continue; if (vma->vm_mm == t->mm) add_to_kill(t, page, vma, to_kill, tkc); } } read_unlock(&tasklist_lock); page_unlock_anon_vma_read(av); }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen10665.03%112.50%
naoya horiguchinaoya horiguchi159.20%225.00%
michel lespinassemichel lespinasse127.36%112.50%
rik van rielrik van riel127.36%112.50%
peter zijlstrapeter zijlstra116.75%112.50%
tony lucktony luck53.07%112.50%
ingo molnaringo molnar21.23%112.50%
Total163100.00%8100.00%

/* * Collect processes when the error hit a file mapped page. */
static void collect_procs_file(struct page *page, struct list_head *to_kill, struct to_kill **tkc, int force_early) { struct vm_area_struct *vma; struct task_struct *tsk; struct address_space *mapping = page->mapping; i_mmap_lock_read(mapping); read_lock(&tasklist_lock); for_each_process(tsk) { pgoff_t pgoff = page_to_pgoff(page); struct task_struct *t = task_early_kill(tsk, force_early); if (!t) continue; vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { /* * Send early kill signal to tasks where a vma covers * the page but the corrupted page is not necessarily * mapped it in its pte. * Assume applications who requested early kill want * to be informed of all such data corruptions. */ if (vma->vm_mm == t->mm) add_to_kill(t, page, vma, to_kill, tkc); } } read_unlock(&tasklist_lock); i_mmap_unlock_read(mapping); }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen10276.12%114.29%
naoya horiguchinaoya horiguchi1511.19%228.57%
peter zijlstrapeter zijlstra96.72%114.29%
tony lucktony luck53.73%114.29%
davidlohr buesodavidlohr bueso21.49%114.29%
michel lespinassemichel lespinasse10.75%114.29%
Total134100.00%7100.00%

/* * Collect the processes who have the corrupted page mapped to kill. * This is done in two steps for locking reasons. * First preallocate one tokill structure outside the spin locks, * so that we can kill at least one process reasonably reliable. */
static void collect_procs(struct page *page, struct list_head *tokill, int force_early) { struct to_kill *tk; if (!page->mapping) return; tk = kmalloc(sizeof(struct to_kill), GFP_NOIO); if (!tk) return; if (PageAnon(page)) collect_procs_anon(page, tokill, &tk, force_early); else collect_procs_file(page, tokill, &tk, force_early); kfree(tk); }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen8192.05%150.00%
tony lucktony luck77.95%150.00%
Total88100.00%2100.00%

static const char *action_name[] = { [MF_IGNORED] = "Ignored", [MF_FAILED] = "Failed", [MF_DELAYED] = "Delayed", [MF_RECOVERED] = "Recovered", }; static const char * const action_page_types[] = { [MF_MSG_KERNEL] = "reserved kernel page", [MF_MSG_KERNEL_HIGH_ORDER] = "high-order kernel page", [MF_MSG_SLAB] = "kernel slab page", [MF_MSG_DIFFERENT_COMPOUND] = "different compound page after locking", [MF_MSG_POISONED_HUGE] = "huge page already hardware poisoned", [MF_MSG_HUGE] = "huge page", [MF_MSG_FREE_HUGE] = "free huge page", [MF_MSG_UNMAP_FAILED] = "unmapping failed page", [MF_MSG_DIRTY_SWAPCACHE] = "dirty swapcache page", [MF_MSG_CLEAN_SWAPCACHE] = "clean swapcache page", [MF_MSG_DIRTY_MLOCKED_LRU] = "dirty mlocked LRU page", [MF_MSG_CLEAN_MLOCKED_LRU] = "clean mlocked LRU page", [MF_MSG_DIRTY_UNEVICTABLE_LRU] = "dirty unevictable LRU page", [MF_MSG_CLEAN_UNEVICTABLE_LRU] = "clean unevictable LRU page", [MF_MSG_DIRTY_LRU] = "dirty LRU page", [MF_MSG_CLEAN_LRU] = "clean LRU page", [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_UNKNOWN] = "unknown page", }; /* * XXX: It is possible that a page is isolated from LRU cache, * and then kept in swap cache or failed to remove from page cache. * The page count will stop it from being freed by unpoison. * Stress tests should be aware of this memory leak problem. */
static int delete_from_lru_cache(struct page *p) { if (!isolate_lru_page(p)) { /* * Clear sensible page flags, so that the buddy system won't * complain when the page is unpoison-and-freed. */ ClearPageActive(p); ClearPageUnevictable(p); /* * drop the page count elevated by isolate_lru_page() */ put_page(p); return 0; } return -EIO; }

Contributors

PersonTokensPropCommitsCommitProp
fengguang wufengguang wu4497.78%150.00%
kirill a. shutemovkirill a. shutemov12.22%150.00%
Total45100.00%2100.00%

/* * Error hit kernel page. * Do nothing, try to be lucky and not touch this instead. For a few cases we * could be more sophisticated. */
static int me_kernel(struct page *p, unsigned long pfn) { return MF_IGNORED; }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen1794.44%150.00%
xie xiuqixie xiuqi15.56%150.00%
Total18100.00%2100.00%

/* * Page in unknown state. Do nothing. */
static int me_unknown(struct page *p, unsigned long pfn) { pr_err("Memory failure: %#lx: Unknown page state\n", pfn); return MF_FAILED; }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen2288.00%125.00%
joe perchesjoe perches14.00%125.00%
chen yucongchen yucong14.00%125.00%
xie xiuqixie xiuqi14.00%125.00%
Total25100.00%4100.00%

/* * Clean (or cleaned) page cache page. */
static int me_pagecache_clean(struct page *p, unsigned long pfn) { int err; int ret = MF_FAILED; struct address_space *mapping; delete_from_lru_cache(p); /* * For anonymous pages we're done the only reference left * should be the one m_f() holds. */ if (PageAnon(p)) return MF_RECOVERED; /* * Now truncate the page in the page cache. This is really * more like a "temporary hole punch" * Don't do this for block devices when someone else * has a reference, because it could be file system metadata * and that's not safe to truncate. */ mapping = page_mapping(p); if (!mapping) { /* * Page has been teared down in the meanwhile */ return MF_FAILED; } /* * Truncation is a bit tricky. Enable it per file system for now. * * Open: to take i_mutex or not for this? Right now we don't. */ if (mapping->a_ops->error_remove_page) { err = mapping->a_ops->error_remove_page(mapping, p); if (err != 0) { pr_info("Memory failure: %#lx: Failed to punch page: %d\n", pfn, err); } else if (page_has_private(p) && !try_to_release_page(p, GFP_NOIO)) { pr_info("Memory failure: %#lx: failed to release buffers\n", pfn); } else { ret = MF_RECOVERED; } } else { /* * If the file system doesn't support it just invalidate * This fails on dirty or anything with private pages */ if (invalidate_inode_page(p)) ret = MF_RECOVERED; else pr_info("Memory failure: %#lx: Failed to invalidate\n", pfn); } return ret; }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen14790.74%233.33%
xie xiuqixie xiuqi53.09%116.67%
fengguang wufengguang wu53.09%116.67%
chen yucongchen yucong31.85%116.67%
joe perchesjoe perches21.23%116.67%
Total162100.00%6100.00%

/* * Dirty pagecache page * Issues: when the error hit a hole page the error is not properly * propagated. */
static int me_pagecache_dirty(struct page *p, unsigned long pfn) { struct address_space *mapping = page_mapping(p); SetPageError(p); /* TBD: print more information about the file. */ if (mapping) { /* * IO error will be reported by write(), fsync(), etc. * who check the mapping. * This way the application knows that something went * wrong with its dirty file data. * * There's one open issue: * * The EIO will be only reported on the next IO * operation and then cleared through the IO map. * Normally Linux has two mechanisms to pass IO error * first through the AS_EIO flag in the address space * and then through the PageError flag in the page. * Since we drop pages on memory failure handling the * only mechanism open to use is through AS_AIO. * * This has the disadvantage that it gets cleared on * the first operation that returns an error, while * the PageError bit is more sticky and only cleared * when the page is reread or dropped. If an * application assumes it will always get error on * fsync, but does other operations on the fd before * and the page is dropped between then the error * will not be properly reported. * * This can already happen even without hwpoisoned * pages: first on metadata IO errors (which only * report through AS_EIO) or when the page is dropped * at the wrong time. * * So right now we assume that the application DTRT on * the first EIO, but we're not worse than other parts * of the kernel. */ mapping_set_error(mapping, EIO); } return me_pagecache_clean(p, pfn); }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen5298.11%150.00%
lucas de marchilucas de marchi11.89%150.00%
Total53100.00%2100.00%

/* * Clean and dirty swap cache. * * Dirty swap cache page is tricky to handle. The page could live both in page * cache and swap cache(ie. page is freshly swapped in). So it could be * referenced concurrently by 2 types of PTEs: * normal PTEs and swap PTEs. We try to handle them consistently by calling * try_to_unmap(TTU_IGNORE_HWPOISON) to convert the normal PTEs to swap PTEs, * and then * - clear dirty bit to prevent IO * - remove from LRU * - but keep in the swap cache, so that when we return to it on * a later page fault, we know the application is accessing * corrupted data and shall be killed (we installed simple * interception code in do_swap_page to catch it). * * Clean swap cache pages can be directly isolated. A later page fault will * bring in the known good data from disk. */
static int me_swapcache_dirty(struct page *p, unsigned long pfn) { ClearPageDirty(p); /* Trigger EIO in shmem: */ ClearPageUptodate(p); if (!delete_from_lru_cache(p)) return MF_DELAYED; else return MF_FAILED; }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen2868.29%133.33%
fengguang wufengguang wu1126.83%133.33%
xie xiuqixie xiuqi24.88%133.33%
Total41100.00%3100.00%


static int me_swapcache_clean(struct page *p, unsigned long pfn) { delete_from_swap_cache(p); if (!delete_from_lru_cache(p)) return MF_RECOVERED; else return MF_FAILED; }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen2262.86%133.33%
fengguang wufengguang wu1131.43%133.33%
xie xiuqixie xiuqi25.71%133.33%
Total35100.00%3100.00%

/* * Huge pages. Needs work. * Issues: * - Error on hugepage is contained in hugepage unit (not in raw page unit.) * To narrow down kill region to one page, we need to break up pmd. */
static int me_huge_page(struct page *p, unsigned long pfn) { int res = 0; struct page *hpage = compound_head(p); if (!PageHuge(hpage)) return MF_DELAYED; /* * We can safely recover from error on free or reserved (i.e. * not in-use) hugepage by dequeuing it from freelist. * To check whether a hugepage is in-use or not, we can't use * page->lru because it can be used in other hugepage operations, * such as __unmap_hugepage_range() and gather_surplus_pages(). * So instead we use page_mapping() and PageAnon(). */ if (!(page_mapping(hpage) || PageAnon(hpage))) { res = dequeue_hwpoisoned_huge_page(hpage); if (!res) return MF_RECOVERED; } return MF_DELAYED; }

Contributors

PersonTokensPropCommitsCommitProp
naoya horiguchinaoya horiguchi5875.32%466.67%
andi kleenandi kleen1722.08%116.67%
xie xiuqixie xiuqi22.60%116.67%
Total77100.00%6100.00%

/* * Various page states we can handle. * * A page state is defined by its current page->flags bits. * The table matches them in order and calls the right handler. * * This is quite tricky because we can access page at any time * in its live cycle, so all accesses have to be extremely careful. * * This is not complete. More states could be added. * For any missing state don't attempt recovery. */ #define dirty (1UL << PG_dirty) #define sc (1UL << PG_swapcache) #define unevict (1UL << PG_unevictable) #define mlock (1UL << PG_mlocked) #define writeback (1UL << PG_writeback) #define lru (1UL << PG_lru) #define swapbacked (1UL << PG_swapbacked) #define head (1UL << PG_head) #define slab (1UL << PG_slab) #define reserved (1UL << PG_reserved) static struct page_state { unsigned long mask; unsigned long res; enum mf_action_page_type type; int (*action)(struct page *p, unsigned long pfn); } error_states[] = { { reserved, reserved, MF_MSG_KERNEL, me_kernel }, /* * free pages are specially detected outside this table: * PG_buddy pages only make a small fraction of all free pages. */ /* * Could in theory check if slab page is free or if we can drop * currently unused objects without touching them. But just * treat it as standard kernel for now. */ { slab, slab, MF_MSG_SLAB, me_kernel }, { head, head, MF_MSG_HUGE, me_huge_page }, { sc|dirty, sc|dirty, MF_MSG_DIRTY_SWAPCACHE, me_swapcache_dirty }, { sc|dirty, sc, MF_MSG_CLEAN_SWAPCACHE, me_swapcache_clean }, { mlock|dirty, mlock|dirty, MF_MSG_DIRTY_MLOCKED_LRU, me_pagecache_dirty }, { mlock|dirty, mlock, MF_MSG_CLEAN_MLOCKED_LRU, me_pagecache_clean }, { unevict|dirty, unevict|dirty, MF_MSG_DIRTY_UNEVICTABLE_LRU, me_pagecache_dirty }, { unevict|dirty, unevict, MF_MSG_CLEAN_UNEVICTABLE_LRU, me_pagecache_clean }, { lru|dirty, lru|dirty, MF_MSG_DIRTY_LRU, me_pagecache_dirty }, { lru|dirty, lru, MF_MSG_CLEAN_LRU, me_pagecache_clean }, /* * Catchall entry: must be at end. */ { 0, 0, MF_MSG_UNKNOWN, me_unknown }, }; #undef dirty #undef sc #undef unevict #undef mlock #undef writeback #undef lru #undef swapbacked #undef head #undef slab #undef reserved /* * "Dirty/Clean" indication is not 100% accurate due to the possibility of * setting PG_dirty outside page lock. See also comment above set_page_dirty(). */
static void action_result(unsigned long pfn, enum mf_action_page_type type, enum mf_result result) { trace_memory_failure_event(pfn, type, result); pr_err("Memory failure: %#lx: recovery action for %s: %s\n", pfn, action_page_types[type], action_name[result]); }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen2454.55%114.29%
xie xiuqixie xiuqi1227.27%342.86%
naoya horiguchinaoya horiguchi715.91%228.57%
chen yucongchen yucong12.27%114.29%
Total44100.00%7100.00%


static int page_action(struct page_state *ps, struct page *p, unsigned long pfn) { int result; int count; result = ps->action(p, pfn); count = page_count(p) - 1; if (ps->action == me_swapcache_dirty && result == MF_DELAYED) count--; if (count != 0) { pr_err("Memory failure: %#lx: %s still referenced by %d users\n", pfn, action_page_types[ps->type], count); result = MF_FAILED; } action_result(pfn, ps->type, result); /* Could do more checks here if page looks ok */ /* * Could adjust zone counters here to correct for the missing page. */ return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY; }

Contributors

PersonTokensPropCommitsCommitProp
andi kleenandi kleen6050.85%112.50%
fengguang wufengguang wu3731.36%225.00%
gong chengong chen108.47%112.50%
naoya horiguchinaoya horiguchi54.24%112.50%
xie xiuqixie xiuqi43.39%112.50%
chen yucongchen yucong10.85%112.50%
joe perchesjoe perches10.85%112.50%
Total118100.00%8100.00%

/** * get_hwpoison_page() - Get refcount for memory error handling: * @page: raw error page (hit by memory error) * * Return: return 0 if failed to grab the refcount, otherwise true (some * non-zero value.) */
int get_hwpoison_page(struct page *page) { struct page *head = compound_head(page); if (!PageHuge(head) && PageTransHuge(head)) { /* * Non anonymous thp exists only in allocation/free time. We * can't handle such a case correctly, so let's give it up. * This should be better than triggering BUG_ON when kernel * tries to touch the "partially handled" page. */ if (!PageAnon(head)) { pr_err("Memory failure: %#lx: non anonymous thp\n", page_to_pfn(page)); return 0; } } if (get_page_unless_zero(head)) { if (head == compound_head(page)) return 1; pr_info("Memory failure: %#lx cannot catch tail\n", page_to_pfn(page)); put_page(head); } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
naoya horiguchinaoya horiguchi6364.29%360.00%
konstantin khlebnikovkonstantin khlebnikov3333.67%120.00%
chen yucongchen yucong22.04%120.00%
Total98100.00%5100.00%

EXPORT_SYMBOL_GPL(get_hwpoison_page); /* * Do all that is necessary to remove user space mappings. Unmap * the pages and send SIGBUS to the processes if the data was dirty. */
static int hwpoison_user_mappings(struct page *p, unsigned long pfn, int trapno, int flags, struct page **hpagep) { enum ttu_flags ttu = TTU_UNMAP | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS; struct address_space *mapping; LIST_HEAD(tokill); int ret; int kill = 1, forcekill; struct