diff options
Diffstat (limited to 'mm/memory-failure.c')
| -rw-r--r-- | mm/memory-failure.c | 2931 |
1 files changed, 1974 insertions, 957 deletions
diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 7c72f2a95785..fbc5a01260c8 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1,24 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * 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 + * 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. @@ -27,21 +24,25 @@ * - 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. - * + * tools/mm/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 + * 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 + * are rare we hope to get away with this. This avoids impacting the core * VM. */ + +#define pr_fmt(fmt) "Memory failure: " fmt + #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/memory-failure.h> #include <linux/page-flags.h> -#include <linux/kernel-page-flags.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> +#include <linux/dax.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/export.h> @@ -49,131 +50,204 @@ #include <linux/swap.h> #include <linux/backing-dev.h> #include <linux/migrate.h> -#include <linux/suspend.h> #include <linux/slab.h> -#include <linux/swapops.h> +#include <linux/leafops.h> #include <linux/hugetlb.h> #include <linux/memory_hotplug.h> #include <linux/mm_inline.h> #include <linux/memremap.h> #include <linux/kfifo.h> #include <linux/ratelimit.h> -#include <linux/page-isolation.h> +#include <linux/pagewalk.h> +#include <linux/shmem_fs.h> +#include <linux/sysctl.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/memory-failure.h> + +#include "swap.h" #include "internal.h" -#include "ras/ras_event.h" -int sysctl_memory_failure_early_kill __read_mostly = 0; +static int sysctl_memory_failure_early_kill __read_mostly; + +static int sysctl_memory_failure_recovery __read_mostly = 1; -int sysctl_memory_failure_recovery __read_mostly = 1; +static int sysctl_enable_soft_offline __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) +static bool hw_memory_failure __read_mostly = false; -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 DEFINE_MUTEX(mf_mutex); -static int hwpoison_filter_dev(struct page *p) +void num_poisoned_pages_inc(unsigned long pfn) { - struct address_space *mapping; - dev_t dev; - - if (hwpoison_filter_dev_major == ~0U && - hwpoison_filter_dev_minor == ~0U) - return 0; + atomic_long_inc(&num_poisoned_pages); + memblk_nr_poison_inc(pfn); +} - /* - * page_mapping() does not accept slab pages. - */ - if (PageSlab(p)) - return -EINVAL; +void num_poisoned_pages_sub(unsigned long pfn, long i) +{ + atomic_long_sub(i, &num_poisoned_pages); + if (pfn != -1UL) + memblk_nr_poison_sub(pfn, i); +} - mapping = page_mapping(p); - if (mapping == NULL || mapping->host == NULL) - return -EINVAL; +/** + * MF_ATTR_RO - Create sysfs entry for each memory failure statistics. + * @_name: name of the file in the per NUMA sysfs directory. + */ +#define MF_ATTR_RO(_name) \ +static ssize_t _name##_show(struct device *dev, \ + struct device_attribute *attr, \ + char *buf) \ +{ \ + struct memory_failure_stats *mf_stats = \ + &NODE_DATA(dev->id)->mf_stats; \ + return sysfs_emit(buf, "%lu\n", mf_stats->_name); \ +} \ +static DEVICE_ATTR_RO(_name) + +MF_ATTR_RO(total); +MF_ATTR_RO(ignored); +MF_ATTR_RO(failed); +MF_ATTR_RO(delayed); +MF_ATTR_RO(recovered); + +static struct attribute *memory_failure_attr[] = { + &dev_attr_total.attr, + &dev_attr_ignored.attr, + &dev_attr_failed.attr, + &dev_attr_delayed.attr, + &dev_attr_recovered.attr, + NULL, +}; - 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; +const struct attribute_group memory_failure_attr_group = { + .name = "memory_failure", + .attrs = memory_failure_attr, +}; - return 0; -} +static const struct ctl_table memory_failure_table[] = { + { + .procname = "memory_failure_early_kill", + .data = &sysctl_memory_failure_early_kill, + .maxlen = sizeof(sysctl_memory_failure_early_kill), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "memory_failure_recovery", + .data = &sysctl_memory_failure_recovery, + .maxlen = sizeof(sysctl_memory_failure_recovery), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "enable_soft_offline", + .data = &sysctl_enable_soft_offline, + .maxlen = sizeof(sysctl_enable_soft_offline), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + } +}; -static int hwpoison_filter_flags(struct page *p) -{ - if (!hwpoison_filter_flags_mask) - return 0; +static struct rb_root_cached pfn_space_itree = RB_ROOT_CACHED; - if ((stable_page_flags(p) & hwpoison_filter_flags_mask) == - hwpoison_filter_flags_value) - return 0; - else - return -EINVAL; -} +static DEFINE_MUTEX(pfn_space_lock); /* - * 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. + * Return values: + * 1: the page is dissolved (if needed) and taken off from buddy, + * 0: the page is dissolved (if needed) and not taken off from buddy, + * < 0: failed to dissolve. */ -#ifdef CONFIG_MEMCG -u64 hwpoison_filter_memcg; -EXPORT_SYMBOL_GPL(hwpoison_filter_memcg); -static int hwpoison_filter_task(struct page *p) +static int __page_handle_poison(struct page *page) { - if (!hwpoison_filter_memcg) - return 0; + int ret; - if (page_cgroup_ino(p) != hwpoison_filter_memcg) - return -EINVAL; + /* + * zone_pcp_disable() can't be used here. It will + * hold pcp_batch_high_lock and dissolve_free_hugetlb_folio() might hold + * cpu_hotplug_lock via static_key_slow_dec() when hugetlb vmemmap + * optimization is enabled. This will break current lock dependency + * chain and leads to deadlock. + * Disabling pcp before dissolving the page was a deterministic + * approach because we made sure that those pages cannot end up in any + * PCP list. Draining PCP lists expels those pages to the buddy system, + * but nothing guarantees that those pages do not get back to a PCP + * queue if we need to refill those. + */ + ret = dissolve_free_hugetlb_folio(page_folio(page)); + if (!ret) { + drain_all_pages(page_zone(page)); + ret = take_page_off_buddy(page); + } - return 0; + return ret; } -#else -static int hwpoison_filter_task(struct page *p) { return 0; } -#endif -int hwpoison_filter(struct page *p) +static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, bool release) { - if (!hwpoison_filter_enable) - return 0; + if (hugepage_or_freepage) { + /* + * Doing this check for free pages is also fine since + * dissolve_free_hugetlb_folio() returns 0 for non-hugetlb folios as well. + */ + if (__page_handle_poison(page) <= 0) + /* + * We could fail to take off the target page from buddy + * for example due to racy page allocation, but that's + * acceptable because soft-offlined page is not broken + * and if someone really want to use it, they should + * take it. + */ + return false; + } - if (hwpoison_filter_dev(p)) - return -EINVAL; + SetPageHWPoison(page); + if (release) + put_page(page); + page_ref_inc(page); + num_poisoned_pages_inc(page_to_pfn(page)); - if (hwpoison_filter_flags(p)) - return -EINVAL; + return true; +} - if (hwpoison_filter_task(p)) - return -EINVAL; +static hwpoison_filter_func_t __rcu *hwpoison_filter_func __read_mostly; - return 0; +void hwpoison_filter_register(hwpoison_filter_func_t *filter) +{ + rcu_assign_pointer(hwpoison_filter_func, filter); } -#else -int hwpoison_filter(struct page *p) +EXPORT_SYMBOL_GPL(hwpoison_filter_register); + +void hwpoison_filter_unregister(void) { - return 0; + RCU_INIT_POINTER(hwpoison_filter_func, NULL); + synchronize_rcu(); } -#endif +EXPORT_SYMBOL_GPL(hwpoison_filter_unregister); + +static int hwpoison_filter(struct page *p) +{ + int ret = 0; + hwpoison_filter_func_t *filter; -EXPORT_SYMBOL_GPL(hwpoison_filter); + rcu_read_lock(); + filter = rcu_dereference(hwpoison_filter_func); + if (filter) + ret = filter(p); + rcu_read_unlock(); + + return ret; +} /* * Kill all processes that have a poisoned page mapped and then isolate @@ -202,7 +276,6 @@ struct to_kill { struct task_struct *tsk; unsigned long addr; short size_shift; - char addr_valid; }; /* @@ -214,67 +287,65 @@ static int kill_proc(struct to_kill *tk, unsigned long pfn, int flags) { struct task_struct *t = tk->tsk; short addr_lsb = tk->size_shift; - int ret; + int ret = 0; - pr_err("Memory failure: %#lx: Killing %s:%d due to hardware memory corruption\n", - pfn, t->comm, t->pid); + pr_err("%#lx: Sending SIGBUS to %s:%d due to hardware memory corruption\n", + pfn, t->comm, task_pid_nr(t)); - if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) { - ret = force_sig_mceerr(BUS_MCEERR_AR, (void __user *)tk->addr, - addr_lsb, current); - } else { + if ((flags & MF_ACTION_REQUIRED) && (t == current)) + ret = force_sig_mceerr(BUS_MCEERR_AR, + (void __user *)tk->addr, addr_lsb); + else /* + * Signal other processes sharing the page if they have + * PF_MCE_EARLY set. * 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? */ ret = send_sig_mceerr(BUS_MCEERR_AO, (void __user *)tk->addr, - addr_lsb, t); /* synchronous? */ - } + addr_lsb, t); if (ret < 0) - pr_info("Memory failure: Error sending signal to %s:%d: %d\n", - t->comm, t->pid, ret); + pr_info("Error sending signal to %s:%d: %d\n", + t->comm, task_pid_nr(t), ret); return ret; } /* - * 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. + * Unknown page type encountered. Try to check whether it can turn PageLRU by + * lru_add_drain_all. */ -void shake_page(struct page *p, int access) +void shake_folio(struct folio *folio) { - if (PageHuge(p)) + if (folio_test_hugetlb(folio)) return; - - 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. + * TODO: Could shrink slab caches here if a lightweight range-based + * shrinker will be available. */ - if (access) - drop_slab_node(page_to_nid(p)); + if (folio_test_slab(folio)) + return; + + lru_add_drain_all(); +} +EXPORT_SYMBOL_GPL(shake_folio); + +static void shake_page(struct page *page) +{ + shake_folio(page_folio(page)); } -EXPORT_SYMBOL_GPL(shake_page); -static unsigned long dev_pagemap_mapping_shift(struct page *page, - struct vm_area_struct *vma) +static unsigned long dev_pagemap_mapping_shift(struct vm_area_struct *vma, + unsigned long address) { - unsigned long address = vma_address(page, vma); + unsigned long ret = 0; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; + pte_t ptent; + VM_BUG_ON_VMA(address == -EFAULT, vma); pgd = pgd_offset(vma->vm_mm, address); if (!pgd_present(*pgd)) return 0; @@ -284,19 +355,21 @@ static unsigned long dev_pagemap_mapping_shift(struct page *page, pud = pud_offset(p4d, address); if (!pud_present(*pud)) return 0; - if (pud_devmap(*pud)) + if (pud_trans_huge(*pud)) return PUD_SHIFT; pmd = pmd_offset(pud, address); if (!pmd_present(*pmd)) return 0; - if (pmd_devmap(*pmd)) + if (pmd_trans_huge(*pmd)) return PMD_SHIFT; pte = pte_offset_map(pmd, address); - if (!pte_present(*pte)) + if (!pte) return 0; - if (pte_devmap(*pte)) - return PAGE_SHIFT; - return 0; + ptent = ptep_get(pte); + if (pte_present(ptent)) + ret = PAGE_SHIFT; + pte_unmap(pte); + return ret; } /* @@ -307,72 +380,97 @@ static unsigned long dev_pagemap_mapping_shift(struct page *page, /* * 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) +static void __add_to_kill(struct task_struct *tsk, const struct page *p, + struct vm_area_struct *vma, struct list_head *to_kill, + unsigned long addr) { 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 = kmalloc(sizeof(struct to_kill), GFP_ATOMIC); + if (!tk) { + pr_err("Out of memory while machine check handling\n"); + return; } - tk->addr = page_address_in_vma(p, vma); - tk->addr_valid = 1; + + tk->addr = addr; if (is_zone_device_page(p)) - tk->size_shift = dev_pagemap_mapping_shift(p, vma); + tk->size_shift = dev_pagemap_mapping_shift(vma, tk->addr); else - tk->size_shift = compound_order(compound_head(p)) + PAGE_SHIFT; + tk->size_shift = folio_shift(page_folio(p)); /* - * 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) { - pr_info("Memory failure: Unable to find user space address %lx in %s\n", + if (tk->addr == -EFAULT) { + pr_info("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; list_add_tail(&tk->nd, to_kill); } +static void add_to_kill_anon_file(struct task_struct *tsk, const struct page *p, + struct vm_area_struct *vma, struct list_head *to_kill, + unsigned long addr) +{ + if (addr == -EFAULT) + return; + __add_to_kill(tsk, p, vma, to_kill, addr); +} + +#ifdef CONFIG_KSM +static bool task_in_to_kill_list(struct list_head *to_kill, + struct task_struct *tsk) +{ + struct to_kill *tk, *next; + + list_for_each_entry_safe(tk, next, to_kill, nd) { + if (tk->tsk == tsk) + return true; + } + + return false; +} + +void add_to_kill_ksm(struct task_struct *tsk, const struct page *p, + struct vm_area_struct *vma, struct list_head *to_kill, + unsigned long addr) +{ + if (!task_in_to_kill_list(to_kill, tsk)) + __add_to_kill(tsk, p, vma, to_kill, addr); +} +#endif /* * 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. + * Only do anything when FORCEKILL is set, otherwise just free the + * list (this is used for clean pages which do not need killing) */ -static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, +static void kill_procs(struct list_head *to_kill, int forcekill, unsigned long pfn, int flags) { struct to_kill *tk, *next; - list_for_each_entry_safe (tk, next, to_kill, nd) { + 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); + if (tk->addr == -EFAULT) { + pr_err("%#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", + pfn, tk->tsk->comm, task_pid_nr(tk->tsk)); + do_send_sig_info(SIGKILL, SEND_SIG_PRIV, + tk->tsk, PIDTYPE_PID); } /* @@ -382,9 +480,10 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, * process anyways. */ 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); + pr_err("%#lx: Cannot send advisory machine check signal to %s:%d\n", + pfn, tk->tsk->comm, task_pid_nr(tk->tsk)); } + list_del(&tk->nd); put_task_struct(tk->tsk); kfree(tk); } @@ -395,16 +494,22 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, * 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. + * We already hold rcu 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; + for_each_thread(tsk, t) { + if (t->flags & PF_MCE_PROCESS) { + if (t->flags & PF_MCE_EARLY) + return t; + } else { + if (sysctl_memory_failure_early_kill) + return t; + } + } return NULL; } @@ -412,75 +517,84 @@ static struct task_struct *find_early_kill_thread(struct task_struct *tsk) * 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. + * specified) if the process is "early kill" and otherwise returns NULL. + * + * Note that the above is true for Action Optional case. For Action Required + * case, it's only meaningful to the current thread which need to be signaled + * with SIGBUS, this error is Action Optional for other non current + * processes sharing the same error page,if the process is "early kill", the + * task_struct of the dedicated thread will also be returned. */ -static struct task_struct *task_early_kill(struct task_struct *tsk, - int force_early) +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; + /* + * Comparing ->mm here because current task might represent + * a subthread, while tsk always points to the main thread. + */ + if (force_early && tsk->mm == current->mm) + return current; + + return find_early_kill_thread(tsk); } /* * 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) +static void collect_procs_anon(const struct folio *folio, + const struct page *page, struct list_head *to_kill, + 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); + av = folio_lock_anon_vma_read(folio, NULL); if (av == NULL) /* Not actually mapped anymore */ return; - pgoff = page_to_pgoff(page); - read_lock(&tasklist_lock); - for_each_process (tsk) { + pgoff = page_pgoff(folio, page); + rcu_read_lock(); + for_each_process(tsk) { + struct vm_area_struct *vma; struct anon_vma_chain *vmac; struct task_struct *t = task_early_kill(tsk, force_early); + unsigned long addr; if (!t) continue; anon_vma_interval_tree_foreach(vmac, &av->rb_root, pgoff, pgoff) { vma = vmac->vma; - if (!page_mapped_in_vma(page, vma)) + if (vma->vm_mm != t->mm) continue; - if (vma->vm_mm == t->mm) - add_to_kill(t, page, vma, to_kill, tkc); + addr = page_mapped_in_vma(page, vma); + add_to_kill_anon_file(t, page, vma, to_kill, addr); } } - read_unlock(&tasklist_lock); - page_unlock_anon_vma_read(av); + rcu_read_unlock(); + anon_vma_unlock_read(av); } /* * 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) +static void collect_procs_file(const struct folio *folio, + const struct page *page, struct list_head *to_kill, + int force_early) { struct vm_area_struct *vma; struct task_struct *tsk; - struct address_space *mapping = page->mapping; + struct address_space *mapping = folio->mapping; + pgoff_t pgoff; i_mmap_lock_read(mapping); - read_lock(&tasklist_lock); + rcu_read_lock(); + pgoff = page_pgoff(folio, page); for_each_process(tsk) { - pgoff_t pgoff = page_to_pgoff(page); struct task_struct *t = task_early_kill(tsk, force_early); + unsigned long addr; if (!t) continue; @@ -489,42 +603,269 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, /* * Send early kill signal to tasks where a vma covers * the page but the corrupted page is not necessarily - * mapped it in its pte. + * mapped 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); + if (vma->vm_mm != t->mm) + continue; + addr = page_address_in_vma(folio, page, vma); + add_to_kill_anon_file(t, page, vma, to_kill, addr); } } - read_unlock(&tasklist_lock); + rcu_read_unlock(); i_mmap_unlock_read(mapping); } +#ifdef CONFIG_FS_DAX +static void add_to_kill_fsdax(struct task_struct *tsk, const struct page *p, + struct vm_area_struct *vma, + struct list_head *to_kill, pgoff_t pgoff) +{ + unsigned long addr = vma_address(vma, pgoff, 1); + __add_to_kill(tsk, p, vma, to_kill, addr); +} + /* - * 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. + * Collect processes when the error hit a fsdax page. */ -static void collect_procs(struct page *page, struct list_head *tokill, - int force_early) +static void collect_procs_fsdax(const struct page *page, + struct address_space *mapping, pgoff_t pgoff, + struct list_head *to_kill, bool pre_remove) { - struct to_kill *tk; + struct vm_area_struct *vma; + struct task_struct *tsk; - if (!page->mapping) - return; + i_mmap_lock_read(mapping); + rcu_read_lock(); + for_each_process(tsk) { + struct task_struct *t = tsk; - tk = kmalloc(sizeof(struct to_kill), GFP_NOIO); - if (!tk) + /* + * Search for all tasks while MF_MEM_PRE_REMOVE is set, because + * the current may not be the one accessing the fsdax page. + * Otherwise, search for the current task. + */ + if (!pre_remove) + t = task_early_kill(tsk, true); + if (!t) + continue; + vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { + if (vma->vm_mm == t->mm) + add_to_kill_fsdax(t, page, vma, to_kill, pgoff); + } + } + rcu_read_unlock(); + i_mmap_unlock_read(mapping); +} +#endif /* CONFIG_FS_DAX */ + +/* + * Collect the processes who have the corrupted page mapped to kill. + */ +static void collect_procs(const struct folio *folio, const struct page *page, + struct list_head *tokill, int force_early) +{ + if (!folio->mapping) return; - if (PageAnon(page)) - collect_procs_anon(page, tokill, &tk, force_early); + if (unlikely(folio_test_ksm(folio))) + collect_procs_ksm(folio, page, tokill, force_early); + else if (folio_test_anon(folio)) + collect_procs_anon(folio, page, tokill, force_early); else - collect_procs_file(page, tokill, &tk, force_early); - kfree(tk); + collect_procs_file(folio, page, tokill, force_early); +} + +struct hwpoison_walk { + struct to_kill tk; + unsigned long pfn; + int flags; +}; + +static void set_to_kill(struct to_kill *tk, unsigned long addr, short shift) +{ + tk->addr = addr; + tk->size_shift = shift; +} + +static int check_hwpoisoned_entry(pte_t pte, unsigned long addr, short shift, + unsigned long poisoned_pfn, struct to_kill *tk) +{ + unsigned long pfn = 0; + + if (pte_present(pte)) { + pfn = pte_pfn(pte); + } else { + const softleaf_t entry = softleaf_from_pte(pte); + + if (softleaf_is_hwpoison(entry)) + pfn = softleaf_to_pfn(entry); + } + + if (!pfn || pfn != poisoned_pfn) + return 0; + + set_to_kill(tk, addr, shift); + return 1; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static int check_hwpoisoned_pmd_entry(pmd_t *pmdp, unsigned long addr, + struct hwpoison_walk *hwp) +{ + pmd_t pmd = *pmdp; + unsigned long pfn; + unsigned long hwpoison_vaddr; + + if (!pmd_present(pmd)) + return 0; + pfn = pmd_pfn(pmd); + if (pfn <= hwp->pfn && hwp->pfn < pfn + HPAGE_PMD_NR) { + hwpoison_vaddr = addr + ((hwp->pfn - pfn) << PAGE_SHIFT); + set_to_kill(&hwp->tk, hwpoison_vaddr, PAGE_SHIFT); + return 1; + } + return 0; +} +#else +static int check_hwpoisoned_pmd_entry(pmd_t *pmdp, unsigned long addr, + struct hwpoison_walk *hwp) +{ + return 0; +} +#endif + +static int hwpoison_pte_range(pmd_t *pmdp, unsigned long addr, + unsigned long end, struct mm_walk *walk) +{ + struct hwpoison_walk *hwp = walk->private; + int ret = 0; + pte_t *ptep, *mapped_pte; + spinlock_t *ptl; + + ptl = pmd_trans_huge_lock(pmdp, walk->vma); + if (ptl) { + ret = check_hwpoisoned_pmd_entry(pmdp, addr, hwp); + spin_unlock(ptl); + goto out; + } + + mapped_pte = ptep = pte_offset_map_lock(walk->vma->vm_mm, pmdp, + addr, &ptl); + if (!ptep) + goto out; + + for (; addr != end; ptep++, addr += PAGE_SIZE) { + ret = check_hwpoisoned_entry(ptep_get(ptep), addr, PAGE_SHIFT, + hwp->pfn, &hwp->tk); + if (ret == 1) + break; + } + pte_unmap_unlock(mapped_pte, ptl); +out: + cond_resched(); + return ret; +} + +#ifdef CONFIG_HUGETLB_PAGE +static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask, + unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct hwpoison_walk *hwp = walk->private; + struct hstate *h = hstate_vma(walk->vma); + spinlock_t *ptl; + pte_t pte; + int ret; + + ptl = huge_pte_lock(h, walk->mm, ptep); + pte = huge_ptep_get(walk->mm, addr, ptep); + ret = check_hwpoisoned_entry(pte, addr, huge_page_shift(h), + hwp->pfn, &hwp->tk); + spin_unlock(ptl); + return ret; +} +#else +#define hwpoison_hugetlb_range NULL +#endif + +static int hwpoison_test_walk(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + /* We also want to consider pages mapped into VM_PFNMAP. */ + return 0; +} + +static const struct mm_walk_ops hwpoison_walk_ops = { + .pmd_entry = hwpoison_pte_range, + .hugetlb_entry = hwpoison_hugetlb_range, + .test_walk = hwpoison_test_walk, + .walk_lock = PGWALK_RDLOCK, +}; + +/* + * Sends SIGBUS to the current process with error info. + * + * This function is intended to handle "Action Required" MCEs on already + * hardware poisoned pages. They could happen, for example, when + * memory_failure() failed to unmap the error page at the first call, or + * when multiple local machine checks happened on different CPUs. + * + * MCE handler currently has no easy access to the error virtual address, + * so this function walks page table to find it. The returned virtual address + * is proper in most cases, but it could be wrong when the application + * process has multiple entries mapping the error page. + */ +static int kill_accessing_process(struct task_struct *p, unsigned long pfn, + int flags) +{ + int ret; + struct hwpoison_walk priv = { + .pfn = pfn, + }; + priv.tk.tsk = p; + + if (!p->mm) + return -EFAULT; + + mmap_read_lock(p->mm); + ret = walk_page_range(p->mm, 0, TASK_SIZE, &hwpoison_walk_ops, + (void *)&priv); + /* + * ret = 1 when CMCI wins, regardless of whether try_to_unmap() + * succeeds or fails, then kill the process with SIGBUS. + * ret = 0 when poison page is a clean page and it's dropped, no + * SIGBUS is needed. + */ + if (ret == 1 && priv.tk.addr) + kill_proc(&priv.tk, pfn, flags); + mmap_read_unlock(p->mm); + + return ret > 0 ? -EHWPOISON : 0; +} + +/* + * MF_IGNORED - The m-f() handler marks the page as PG_hwpoisoned'ed. + * But it could not do more to isolate the page from being accessed again, + * nor does it kill the process. This is extremely rare and one of the + * potential causes is that the page state has been changed due to + * underlying race condition. This is the most severe outcomes. + * + * MF_FAILED - The m-f() handler marks the page as PG_hwpoisoned'ed. + * It should have killed the process, but it can't isolate the page, + * due to conditions such as extra pin, unmap failure, etc. Accessing + * the page again may trigger another MCE and the process will be killed + * by the m-f() handler immediately. + * + * MF_DELAYED - The m-f() handler marks the page as PG_hwpoisoned'ed. + * The page is unmapped, and is removed from the LRU or file mapping. + * An attempt to access the page again will trigger page fault and the + * PF handler will kill the process. + * + * MF_RECOVERED - The m-f() handler marks the page as PG_hwpoisoned'ed. + * The page has been completely isolated, that is, unmapped, taken out of + * the buddy system, or hole-punnched out of the file mapping. + */ static const char *action_name[] = { [MF_IGNORED] = "Ignored", [MF_FAILED] = "Failed", @@ -535,12 +876,9 @@ static const char *action_name[] = { 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_NON_PMD_HUGE] = "non-pmd-sized huge page", + [MF_MSG_GET_HWPOISON] = "get hwpoison page", [MF_MSG_UNMAP_FAILED] = "unmapping failed page", [MF_MSG_DIRTY_SWAPCACHE] = "dirty swapcache page", [MF_MSG_CLEAN_SWAPCACHE] = "clean swapcache page", @@ -552,8 +890,10 @@ static const char * const action_page_types[] = { [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_DAX] = "dax page", + [MF_MSG_UNSPLIT_THP] = "unsplit thp", + [MF_MSG_ALREADY_POISONED] = "already poisoned page", + [MF_MSG_PFN_MAP] = "non struct page pfn", [MF_MSG_UNKNOWN] = "unknown page", }; @@ -563,98 +903,133 @@ static const char * const action_page_types[] = { * 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) +static int delete_from_lru_cache(struct folio *folio) { - if (!isolate_lru_page(p)) { + if (folio_isolate_lru(folio)) { /* * Clear sensible page flags, so that the buddy system won't - * complain when the page is unpoison-and-freed. + * complain when the folio is unpoison-and-freed. */ - ClearPageActive(p); - ClearPageUnevictable(p); + folio_clear_active(folio); + folio_clear_unevictable(folio); /* * Poisoned page might never drop its ref count to 0 so we have * to uncharge it manually from its memcg. */ - mem_cgroup_uncharge(p); + mem_cgroup_uncharge(folio); /* - * drop the page count elevated by isolate_lru_page() + * drop the refcount elevated by folio_isolate_lru() */ - put_page(p); + folio_put(folio); return 0; } return -EIO; } -static int truncate_error_page(struct page *p, unsigned long pfn, +static int truncate_error_folio(struct folio *folio, unsigned long pfn, struct address_space *mapping) { int ret = MF_FAILED; - if (mapping->a_ops->error_remove_page) { - int err = mapping->a_ops->error_remove_page(mapping, p); + if (mapping->a_ops->error_remove_folio) { + int err = mapping->a_ops->error_remove_folio(mapping, folio); - 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 { + if (err != 0) + pr_info("%#lx: Failed to punch page: %d\n", pfn, err); + else if (!filemap_release_folio(folio, GFP_NOIO)) + pr_info("%#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)) + if (mapping_evict_folio(mapping, folio)) ret = MF_RECOVERED; else - pr_info("Memory failure: %#lx: Failed to invalidate\n", - pfn); + pr_info("%#lx: Failed to invalidate\n", pfn); } return ret; } +struct page_state { + unsigned long mask; + unsigned long res; + enum mf_action_page_type type; + + /* Callback ->action() has to unlock the relevant page inside it. */ + int (*action)(struct page_state *ps, struct page *p); +}; + +/* + * Return true if page is still referenced by others, otherwise return + * false. + * + * The extra_pins is true when one extra refcount is expected. + */ +static bool has_extra_refcount(struct page_state *ps, struct page *p, + bool extra_pins) +{ + int count = page_count(p) - 1; + + if (extra_pins) + count -= folio_nr_pages(page_folio(p)); + + if (count > 0) { + pr_err("%#lx: %s still referenced by %d users\n", + page_to_pfn(p), action_page_types[ps->type], count); + return true; + } + + return false; +} + /* * 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) +static int me_kernel(struct page_state *ps, struct page *p) { + unlock_page(p); return MF_IGNORED; } /* * Page in unknown state. Do nothing. + * This is a catch-all in case we fail to make sense of the page state. */ -static int me_unknown(struct page *p, unsigned long pfn) +static int me_unknown(struct page_state *ps, struct page *p) { - pr_err("Memory failure: %#lx: Unknown page state\n", pfn); - return MF_FAILED; + pr_err("%#lx: Unknown page state\n", page_to_pfn(p)); + unlock_page(p); + return MF_IGNORED; } /* * Clean (or cleaned) page cache page. */ -static int me_pagecache_clean(struct page *p, unsigned long pfn) +static int me_pagecache_clean(struct page_state *ps, struct page *p) { + struct folio *folio = page_folio(p); + int ret; struct address_space *mapping; + bool extra_pins; - delete_from_lru_cache(p); + delete_from_lru_cache(folio); /* - * For anonymous pages we're done the only reference left + * For anonymous folios the only reference left * should be the one m_f() holds. */ - if (PageAnon(p)) - return MF_RECOVERED; + if (folio_test_anon(folio)) { + ret = MF_RECOVERED; + goto out; + } /* * Now truncate the page in the page cache. This is really @@ -663,20 +1038,32 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) * has a reference, because it could be file system metadata * and that's not safe to truncate. */ - mapping = page_mapping(p); + mapping = folio_mapping(folio); if (!mapping) { - /* - * Page has been teared down in the meanwhile - */ - return MF_FAILED; + /* Folio has been torn down in the meantime */ + ret = MF_FAILED; + goto out; } /* + * The shmem page is kept in page cache instead of truncating + * so is expected to have an extra refcount after error-handling. + */ + extra_pins = shmem_mapping(mapping); + + /* * 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. + * Open: to take i_rwsem or not for this? Right now we don't. */ - return truncate_error_page(p, pfn, mapping); + ret = truncate_error_folio(folio, page_to_pfn(p), mapping); + if (has_extra_refcount(ps, p, extra_pins)) + ret = MF_FAILED; + +out: + folio_unlock(folio); + + return ret; } /* @@ -684,11 +1071,11 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) * 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) +static int me_pagecache_dirty(struct page_state *ps, struct page *p) { - struct address_space *mapping = page_mapping(p); + struct folio *folio = page_folio(p); + struct address_space *mapping = folio_mapping(folio); - SetPageError(p); /* TBD: print more information about the file. */ if (mapping) { /* @@ -696,49 +1083,21 @@ static int me_pagecache_dirty(struct page *p, unsigned long pfn) * 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); + return me_pagecache_clean(ps, p); } /* * 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 + * table 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, + * try_to_unmap(!TTU_HWPOISON) to convert the normal PTEs to swap PTEs, * and then * - clear dirty bit to prevent IO * - remove from LRU @@ -750,26 +1109,42 @@ static int me_pagecache_dirty(struct page *p, unsigned long pfn) * 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) +static int me_swapcache_dirty(struct page_state *ps, struct page *p) { - ClearPageDirty(p); + struct folio *folio = page_folio(p); + int ret; + bool extra_pins = false; + + folio_clear_dirty(folio); /* Trigger EIO in shmem: */ - ClearPageUptodate(p); + folio_clear_uptodate(folio); - if (!delete_from_lru_cache(p)) - return MF_DELAYED; - else - return MF_FAILED; + ret = delete_from_lru_cache(folio) ? MF_FAILED : MF_DELAYED; + folio_unlock(folio); + + if (ret == MF_DELAYED) + extra_pins = true; + + if (has_extra_refcount(ps, p, extra_pins)) + ret = MF_FAILED; + + return ret; } -static int me_swapcache_clean(struct page *p, unsigned long pfn) +static int me_swapcache_clean(struct page_state *ps, struct page *p) { - delete_from_swap_cache(p); + struct folio *folio = page_folio(p); + int ret; - if (!delete_from_lru_cache(p)) - return MF_RECOVERED; - else - return MF_FAILED; + swap_cache_del_folio(folio); + + ret = delete_from_lru_cache(folio) ? MF_FAILED : MF_RECOVERED; + folio_unlock(folio); + + if (has_extra_refcount(ps, p, false)) + ret = MF_FAILED; + + return ret; } /* @@ -778,32 +1153,38 @@ static int me_swapcache_clean(struct page *p, unsigned long pfn) * - 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) +static int me_huge_page(struct page_state *ps, struct page *p) { - int res = 0; - struct page *hpage = compound_head(p); + struct folio *folio = page_folio(p); + int res; struct address_space *mapping; + bool extra_pins = false; - if (!PageHuge(hpage)) - return MF_DELAYED; - - mapping = page_mapping(hpage); + mapping = folio_mapping(folio); if (mapping) { - res = truncate_error_page(hpage, pfn, mapping); + res = truncate_error_folio(folio, page_to_pfn(p), mapping); + /* The page is kept in page cache. */ + extra_pins = true; + folio_unlock(folio); } else { - unlock_page(hpage); + folio_unlock(folio); /* - * migration entry prevents later access on error anonymous - * hugepage, so we can free and dissolve it into buddy to - * save healthy subpages. + * migration entry prevents later access on error hugepage, + * so we can free and dissolve it into buddy to save healthy + * subpages. */ - if (PageAnon(hpage)) - put_page(hpage); - dissolve_free_huge_page(p); - res = MF_RECOVERED; - lock_page(hpage); + folio_put(folio); + if (__page_handle_poison(p) > 0) { + page_ref_inc(p); + res = MF_RECOVERED; + } else { + res = MF_FAILED; + } } + if (has_extra_refcount(ps, p, extra_pins)) + res = MF_FAILED; + return res; } @@ -824,31 +1205,17 @@ static int me_huge_page(struct page *p, unsigned long pfn) #define sc ((1UL << PG_swapcache) | (1UL << PG_swapbacked)) #define unevict (1UL << PG_unevictable) #define mlock (1UL << PG_mlocked) -#define writeback (1UL << PG_writeback) #define lru (1UL << PG_lru) #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[] = { +static struct page_state 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 }, @@ -873,172 +1240,382 @@ static struct page_state { #undef sc #undef unevict #undef mlock -#undef writeback #undef lru #undef head -#undef slab #undef reserved +static void update_per_node_mf_stats(unsigned long pfn, + enum mf_result result) +{ + int nid = MAX_NUMNODES; + struct memory_failure_stats *mf_stats = NULL; + + nid = pfn_to_nid(pfn); + if (unlikely(nid < 0 || nid >= MAX_NUMNODES)) { + WARN_ONCE(1, "Memory failure: pfn=%#lx, invalid nid=%d", pfn, nid); + return; + } + + mf_stats = &NODE_DATA(nid)->mf_stats; + switch (result) { + case MF_IGNORED: + ++mf_stats->ignored; + break; + case MF_FAILED: + ++mf_stats->failed; + break; + case MF_DELAYED: + ++mf_stats->delayed; + break; + case MF_RECOVERED: + ++mf_stats->recovered; + break; + default: + WARN_ONCE(1, "Memory failure: mf_result=%d is not properly handled", result); + break; + } + ++mf_stats->total; +} + /* * "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) +static int 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", + if (type != MF_MSG_ALREADY_POISONED && type != MF_MSG_PFN_MAP) { + num_poisoned_pages_inc(pfn); + update_per_node_mf_stats(pfn, result); + } + + pr_err("%#lx: recovery action for %s: %s\n", pfn, action_page_types[type], action_name[result]); + + return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY; } 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); + /* page p should be unlocked after returning from ps->action(). */ + result = ps->action(ps, p); /* 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; + return action_result(pfn, ps->type, result); } -/** - * 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.) +static inline bool PageHWPoisonTakenOff(struct page *page) +{ + return PageHWPoison(page) && page_private(page) == MAGIC_HWPOISON; +} + +void SetPageHWPoisonTakenOff(struct page *page) +{ + set_page_private(page, MAGIC_HWPOISON); +} + +void ClearPageHWPoisonTakenOff(struct page *page) +{ + if (PageHWPoison(page)) + set_page_private(page, 0); +} + +/* + * Return true if a page type of a given page is supported by hwpoison + * mechanism (while handling could fail), otherwise false. This function + * does not return true for hugetlb or device memory pages, so it's assumed + * to be called only in the context where we never have such pages. */ -int get_hwpoison_page(struct page *page) +static inline bool HWPoisonHandlable(struct page *page, unsigned long flags) { - struct page *head = compound_head(page); + if (PageSlab(page)) + return false; - 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; + /* Soft offline could migrate movable_ops pages */ + if ((flags & MF_SOFT_OFFLINE) && page_has_movable_ops(page)) + return true; + + return PageLRU(page) || is_free_buddy_page(page); +} + +static int __get_hwpoison_page(struct page *page, unsigned long flags) +{ + struct folio *folio = page_folio(page); + int ret = 0; + bool hugetlb = false; + + ret = get_hwpoison_hugetlb_folio(folio, &hugetlb, false); + if (hugetlb) { + /* Make sure hugetlb demotion did not happen from under us. */ + if (folio == page_folio(page)) + return ret; + if (ret > 0) { + folio_put(folio); + folio = page_folio(page); } } - if (get_page_unless_zero(head)) { - if (head == compound_head(page)) + /* + * This check prevents from calling folio_try_get() for any + * unsupported type of folio in order to reduce the risk of unexpected + * races caused by taking a folio refcount. + */ + if (!HWPoisonHandlable(&folio->page, flags)) + return -EBUSY; + + if (folio_try_get(folio)) { + if (folio == page_folio(page)) return 1; - pr_info("Memory failure: %#lx cannot catch tail\n", - page_to_pfn(page)); - put_page(head); + pr_info("%#lx cannot catch tail\n", page_to_pfn(page)); + folio_put(folio); } return 0; } -EXPORT_SYMBOL_GPL(get_hwpoison_page); + +#define GET_PAGE_MAX_RETRY_NUM 3 + +static int get_any_page(struct page *p, unsigned long flags) +{ + int ret = 0, pass = 0; + bool count_increased = false; + + if (flags & MF_COUNT_INCREASED) + count_increased = true; + +try_again: + if (!count_increased) { + ret = __get_hwpoison_page(p, flags); + if (!ret) { + if (page_count(p)) { + /* We raced with an allocation, retry. */ + if (pass++ < GET_PAGE_MAX_RETRY_NUM) + goto try_again; + ret = -EBUSY; + } else if (!PageHuge(p) && !is_free_buddy_page(p)) { + /* We raced with put_page, retry. */ + if (pass++ < GET_PAGE_MAX_RETRY_NUM) + goto try_again; + ret = -EIO; + } + goto out; + } else if (ret == -EBUSY) { + /* + * We raced with (possibly temporary) unhandlable + * page, retry. + */ + if (pass++ < 3) { + shake_page(p); + goto try_again; + } + ret = -EIO; + goto out; + } + } + + if (PageHuge(p) || HWPoisonHandlable(p, flags)) { + ret = 1; + } else { + /* + * A page we cannot handle. Check whether we can turn + * it into something we can handle. + */ + if (pass++ < GET_PAGE_MAX_RETRY_NUM) { + put_page(p); + shake_page(p); + count_increased = false; + goto try_again; + } + put_page(p); + ret = -EIO; + } +out: + if (ret == -EIO) + pr_err("%#lx: unhandlable page.\n", page_to_pfn(p)); + + return ret; +} + +static int __get_unpoison_page(struct page *page) +{ + struct folio *folio = page_folio(page); + int ret = 0; + bool hugetlb = false; + + ret = get_hwpoison_hugetlb_folio(folio, &hugetlb, true); + if (hugetlb) { + /* Make sure hugetlb demotion did not happen from under us. */ + if (folio == page_folio(page)) + return ret; + if (ret > 0) + folio_put(folio); + } + + /* + * PageHWPoisonTakenOff pages are not only marked as PG_hwpoison, + * but also isolated from buddy freelist, so need to identify the + * state and have to cancel both operations to unpoison. + */ + if (PageHWPoisonTakenOff(page)) + return -EHWPOISON; + + return get_page_unless_zero(page) ? 1 : 0; +} + +/** + * get_hwpoison_page() - Get refcount for memory error handling + * @p: Raw error page (hit by memory error) + * @flags: Flags controlling behavior of error handling + * + * get_hwpoison_page() takes a page refcount of an error page to handle memory + * error on it, after checking that the error page is in a well-defined state + * (defined as a page-type we can successfully handle the memory error on it, + * such as LRU page and hugetlb page). + * + * Memory error handling could be triggered at any time on any type of page, + * so it's prone to race with typical memory management lifecycle (like + * allocation and free). So to avoid such races, get_hwpoison_page() takes + * extra care for the error page's state (as done in __get_hwpoison_page()), + * and has some retry logic in get_any_page(). + * + * When called from unpoison_memory(), the caller should already ensure that + * the given page has PG_hwpoison. So it's never reused for other page + * allocations, and __get_unpoison_page() never races with them. + * + * Return: 0 on failure or free buddy (hugetlb) page, + * 1 on success for in-use pages in a well-defined state, + * -EIO for pages on which we can not handle memory errors, + * -EBUSY when get_hwpoison_page() has raced with page lifecycle + * operations like allocation and free, + * -EHWPOISON when the page is hwpoisoned and taken off from buddy. + */ +static int get_hwpoison_page(struct page *p, unsigned long flags) +{ + int ret; + + zone_pcp_disable(page_zone(p)); + if (flags & MF_UNPOISON) + ret = __get_unpoison_page(p); + else + ret = get_any_page(p, flags); + zone_pcp_enable(page_zone(p)); + + return ret; +} + +/* + * The caller must guarantee the folio isn't large folio, except hugetlb. + * try_to_unmap() can't handle it. + */ +int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill) +{ + enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON; + struct address_space *mapping; + + if (folio_test_swapcache(folio)) { + pr_err("%#lx: keeping poisoned page in swap cache\n", pfn); + ttu &= ~TTU_HWPOISON; + } + + /* + * Propagate the dirty bit from PTEs to struct page first, because we + * need this to decide if we should kill or just drop the page. + * XXX: the dirty test could be racy: set_page_dirty() may not always + * be called inside page lock (it's recommended but not enforced). + */ + mapping = folio_mapping(folio); + if (!must_kill && !folio_test_dirty(folio) && mapping && + mapping_can_writeback(mapping)) { + if (folio_mkclean(folio)) { + folio_set_dirty(folio); + } else { + ttu &= ~TTU_HWPOISON; + pr_info("%#lx: corrupted page was clean: dropped without side effects\n", + pfn); + } + } + + if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) { + /* + * For hugetlb folios in shared mappings, try_to_unmap + * could potentially call huge_pmd_unshare. Because of + * this, take semaphore in write mode here and set + * TTU_RMAP_LOCKED to indicate we have taken the lock + * at this higher level. + */ + mapping = hugetlb_folio_mapping_lock_write(folio); + if (!mapping) { + pr_info("%#lx: could not lock mapping for mapped hugetlb folio\n", + folio_pfn(folio)); + return -EBUSY; + } + + try_to_unmap(folio, ttu|TTU_RMAP_LOCKED); + i_mmap_unlock_write(mapping); + } else { + try_to_unmap(folio, ttu); + } + + return folio_mapped(folio) ? -EBUSY : 0; +} /* * 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 bool hwpoison_user_mappings(struct page *p, unsigned long pfn, - int flags, struct page **hpagep) +static bool hwpoison_user_mappings(struct folio *folio, struct page *p, + unsigned long pfn, int flags) { - enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS; - struct address_space *mapping; LIST_HEAD(tokill); bool unmap_success; - int kill = 1, forcekill; - struct page *hpage = *hpagep; - bool mlocked = PageMlocked(hpage); + int forcekill; + bool mlocked = folio_test_mlocked(folio); /* * Here we are interested only in user-mapped pages, so skip any * other types of pages. */ - if (PageReserved(p) || PageSlab(p)) + if (folio_test_reserved(folio) || folio_test_slab(folio) || + folio_test_pgtable(folio) || folio_test_offline(folio)) return true; - if (!(PageLRU(hpage) || PageHuge(p))) + if (!(folio_test_lru(folio) || folio_test_hugetlb(folio))) return true; /* * This check implies we don't kill processes if their pages * are in the swap cache early. Those are always late kills. */ - if (!page_mapped(hpage)) + if (!folio_mapped(folio)) return true; - if (PageKsm(p)) { - pr_err("Memory failure: %#lx: can't handle KSM pages.\n", pfn); - return false; - } - - if (PageSwapCache(p)) { - pr_err("Memory failure: %#lx: keeping poisoned page in swap cache\n", - pfn); - ttu |= TTU_IGNORE_HWPOISON; - } - - /* - * Propagate the dirty bit from PTEs to struct page first, because we - * need this to decide if we should kill or just drop the page. - * XXX: the dirty test could be racy: set_page_dirty() may not always - * be called inside page lock (it's recommended but not enforced). - */ - mapping = page_mapping(hpage); - if (!(flags & MF_MUST_KILL) && !PageDirty(hpage) && mapping && - mapping_cap_writeback_dirty(mapping)) { - if (page_mkclean(hpage)) { - SetPageDirty(hpage); - } else { - kill = 0; - ttu |= TTU_IGNORE_HWPOISON; - pr_info("Memory failure: %#lx: corrupted page was clean: dropped without side effects\n", - pfn); - } - } - /* * First collect all the processes that have the page * mapped in dirty form. This has to be done before try_to_unmap, * because ttu takes the rmap data structures down. - * - * Error handling: We ignore errors here because - * there's nothing that can be done. */ - if (kill) - collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED); + collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED); - unmap_success = try_to_unmap(hpage, ttu); + unmap_success = !unmap_poisoned_folio(folio, pfn, flags & MF_MUST_KILL); if (!unmap_success) - pr_err("Memory failure: %#lx: failed to unmap page (mapcount=%d)\n", - pfn, page_mapcount(hpage)); + pr_err("%#lx: failed to unmap page (folio mapcount=%d)\n", + pfn, folio_mapcount(folio)); /* * try_to_unmap() might put mlocked page in lru cache, so call * shake_page() again to ensure that it's flushed. */ if (mlocked) - shake_page(hpage, 0); + shake_folio(folio); /* * Now that the dirty bit has been propagated to the @@ -1050,8 +1627,9 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * use a more force-full uncatchable kill to prevent * any accesses to the poisoned memory. */ - forcekill = PageDirty(hpage) || (flags & MF_MUST_KILL); - kill_procs(&tokill, forcekill, !unmap_success, pfn, flags); + forcekill = folio_test_dirty(folio) || (flags & MF_MUST_KILL) || + !unmap_success; + kill_procs(&tokill, forcekill, pfn, flags); return unmap_success; } @@ -1067,10 +1645,10 @@ static int identify_page_state(unsigned long pfn, struct page *p, * carried out only if the first check can't determine the page status. */ for (ps = error_states;; ps++) - if ((p->flags & ps->mask) == ps->res) + if ((p->flags.f & ps->mask) == ps->res) break; - page_flags |= (p->flags & (1UL << PG_dirty)); + page_flags |= (p->flags.f & (1UL << PG_dirty)); if (!ps->mask) for (ps = error_states;; ps++) @@ -1079,89 +1657,67 @@ static int identify_page_state(unsigned long pfn, struct page *p, return page_action(ps, p, pfn); } -static int memory_failure_hugetlb(unsigned long pfn, int flags) +/* + * When 'release' is 'false', it means that if thp split has failed, + * there is still more to do, hence the page refcount we took earlier + * is still needed. + */ +static int try_to_split_thp_page(struct page *page, unsigned int new_order, + bool release) { - struct page *p = pfn_to_page(pfn); - struct page *head = compound_head(p); - int res; - unsigned long page_flags; + int ret; - if (TestSetPageHWPoison(head)) { - pr_err("Memory failure: %#lx: already hardware poisoned\n", - pfn); - return 0; - } + lock_page(page); + ret = split_huge_page_to_order(page, new_order); + unlock_page(page); - num_poisoned_pages_inc(); + if (ret && release) + put_page(page); - if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p)) { - /* - * Check "filter hit" and "race with other subpage." - */ - lock_page(head); - if (PageHWPoison(head)) { - if ((hwpoison_filter(p) && TestClearPageHWPoison(p)) - || (p != head && TestSetPageHWPoison(head))) { - num_poisoned_pages_dec(); - unlock_page(head); - return 0; - } - } - unlock_page(head); - dissolve_free_huge_page(p); - action_result(pfn, MF_MSG_FREE_HUGE, MF_DELAYED); - return 0; - } + return ret; +} - lock_page(head); - page_flags = head->flags; +static void unmap_and_kill(struct list_head *to_kill, unsigned long pfn, + struct address_space *mapping, pgoff_t index, int flags) +{ + struct to_kill *tk; + unsigned long size = 0; - if (!PageHWPoison(head)) { - pr_err("Memory failure: %#lx: just unpoisoned\n", pfn); - num_poisoned_pages_dec(); - unlock_page(head); - put_hwpoison_page(head); - return 0; - } + list_for_each_entry(tk, to_kill, nd) + if (tk->size_shift) + size = max(size, 1UL << tk->size_shift); - /* - * TODO: hwpoison for pud-sized hugetlb doesn't work right now, so - * simply disable it. In order to make it work properly, we need - * make sure that: - * - conversion of a pud that maps an error hugetlb into hwpoison - * entry properly works, and - * - other mm code walking over page table is aware of pud-aligned - * hwpoison entries. - */ - if (huge_page_size(page_hstate(head)) > PMD_SIZE) { - action_result(pfn, MF_MSG_NON_PMD_HUGE, MF_IGNORED); - res = -EBUSY; - goto out; - } + 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() + */ + loff_t start = ((loff_t)index << PAGE_SHIFT) & ~(size - 1); - if (!hwpoison_user_mappings(p, pfn, flags, &head)) { - action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED); - res = -EBUSY; - goto out; + unmap_mapping_range(mapping, start, size, 0); } - res = identify_page_state(pfn, p, page_flags); -out: - unlock_page(head); - return res; + kill_procs(to_kill, flags & MF_MUST_KILL, pfn, flags); } -static int memory_failure_dev_pagemap(unsigned long pfn, int flags, +/* + * Only dev_pagemap pages get here, such as fsdax when the filesystem + * either do not claim or fails to claim a hwpoison event, or devdax. + * The fsdax pages are initialized per base page, and the devdax pages + * could be initialized either as base pages, or as compound pages with + * vmemmap optimization enabled. Devdax is simplistic in its dealing with + * hwpoison, such that, if a subpage of a compound page is poisoned, + * simply mark the compound head page is by far sufficient. + */ +static int mf_generic_kill_procs(unsigned long 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; + struct folio *folio = pfn_folio(pfn); + LIST_HEAD(to_kill); dax_entry_t cookie; + int rc = 0; /* * Prevent the inode from being freed while we are interrogating @@ -1170,22 +1726,23 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags, * also prevents changes to the mapping of this pfn until * poison signaling is complete. */ - cookie = dax_lock_page(page); + cookie = dax_lock_folio(folio); if (!cookie) - goto out; + return -EBUSY; - if (hwpoison_filter(page)) { - rc = 0; + if (hwpoison_filter(&folio->page)) { + rc = -EOPNOTSUPP; goto unlock; } switch (pgmap->type) { case MEMORY_DEVICE_PRIVATE: - case MEMORY_DEVICE_PUBLIC: + case MEMORY_DEVICE_COHERENT: /* - * TODO: Handle HMM pages which may need coordination + * TODO: Handle device pages which may need coordination * with device-side memory. */ + rc = -ENXIO; goto unlock; default: break; @@ -1195,7 +1752,7 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags, * Use this flag as an indication that the dax page has been * remapped UC to prevent speculative consumption of poison. */ - SetPageHWPoison(page); + SetPageHWPoison(&folio->page); /* * Unlike System-RAM there is no possibility to swap in a @@ -1204,32 +1761,531 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags, * SIGBUS (i.e. MF_MUST_KILL) */ flags |= MF_ACTION_REQUIRED | MF_MUST_KILL; - collect_procs(page, &tokill, flags & MF_ACTION_REQUIRED); + collect_procs(folio, &folio->page, &to_kill, true); + + unmap_and_kill(&to_kill, pfn, folio->mapping, folio->index, flags); +unlock: + dax_unlock_folio(folio, cookie); + return rc; +} + +#ifdef CONFIG_FS_DAX +/** + * mf_dax_kill_procs - Collect and kill processes who are using this file range + * @mapping: address_space of the file in use + * @index: start pgoff of the range within the file + * @count: length of the range, in unit of PAGE_SIZE + * @mf_flags: memory failure flags + */ +int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, + unsigned long count, int mf_flags) +{ + LIST_HEAD(to_kill); + dax_entry_t cookie; + struct page *page; + size_t end = index + count; + bool pre_remove = mf_flags & MF_MEM_PRE_REMOVE; + + mf_flags |= MF_ACTION_REQUIRED | MF_MUST_KILL; + + for (; index < end; index++) { + page = NULL; + cookie = dax_lock_mapping_entry(mapping, index, &page); + if (!cookie) + return -EBUSY; + if (!page) + goto unlock; + + if (!pre_remove) + SetPageHWPoison(page); - 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() + * The pre_remove case is revoking access, the memory is still + * good and could theoretically be put back into service. */ - 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; + collect_procs_fsdax(page, mapping, index, &to_kill, pre_remove); + unmap_and_kill(&to_kill, page_to_pfn(page), mapping, + index, mf_flags); unlock: - dax_unlock_page(page, cookie); + dax_unlock_mapping_entry(mapping, index, cookie); + } + return 0; +} +EXPORT_SYMBOL_GPL(mf_dax_kill_procs); +#endif /* CONFIG_FS_DAX */ + +#ifdef CONFIG_HUGETLB_PAGE + +/* + * Struct raw_hwp_page represents information about "raw error page", + * constructing singly linked list from ->_hugetlb_hwpoison field of folio. + */ +struct raw_hwp_page { + struct llist_node node; + struct page *page; +}; + +static inline struct llist_head *raw_hwp_list_head(struct folio *folio) +{ + return (struct llist_head *)&folio->_hugetlb_hwpoison; +} + +bool is_raw_hwpoison_page_in_hugepage(struct page *page) +{ + struct llist_head *raw_hwp_head; + struct raw_hwp_page *p; + struct folio *folio = page_folio(page); + bool ret = false; + + if (!folio_test_hwpoison(folio)) + return false; + + if (!folio_test_hugetlb(folio)) + return PageHWPoison(page); + + /* + * When RawHwpUnreliable is set, kernel lost track of which subpages + * are HWPOISON. So return as if ALL subpages are HWPOISONed. + */ + if (folio_test_hugetlb_raw_hwp_unreliable(folio)) + return true; + + mutex_lock(&mf_mutex); + + raw_hwp_head = raw_hwp_list_head(folio); + llist_for_each_entry(p, raw_hwp_head->first, node) { + if (page == p->page) { + ret = true; + break; + } + } + + mutex_unlock(&mf_mutex); + + return ret; +} + +static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag) +{ + struct llist_node *head; + struct raw_hwp_page *p, *next; + unsigned long count = 0; + + head = llist_del_all(raw_hwp_list_head(folio)); + llist_for_each_entry_safe(p, next, head, node) { + if (move_flag) + SetPageHWPoison(p->page); + else + num_poisoned_pages_sub(page_to_pfn(p->page), 1); + kfree(p); + count++; + } + return count; +} + +static int folio_set_hugetlb_hwpoison(struct folio *folio, struct page *page) +{ + struct llist_head *head; + struct raw_hwp_page *raw_hwp; + struct raw_hwp_page *p; + int ret = folio_test_set_hwpoison(folio) ? -EHWPOISON : 0; + + /* + * Once the hwpoison hugepage has lost reliable raw error info, + * there is little meaning to keep additional error info precisely, + * so skip to add additional raw error info. + */ + if (folio_test_hugetlb_raw_hwp_unreliable(folio)) + return -EHWPOISON; + head = raw_hwp_list_head(folio); + llist_for_each_entry(p, head->first, node) { + if (p->page == page) + return -EHWPOISON; + } + + raw_hwp = kmalloc(sizeof(struct raw_hwp_page), GFP_ATOMIC); + if (raw_hwp) { + raw_hwp->page = page; + llist_add(&raw_hwp->node, head); + /* the first error event will be counted in action_result(). */ + if (ret) + num_poisoned_pages_inc(page_to_pfn(page)); + } else { + /* + * Failed to save raw error info. We no longer trace all + * hwpoisoned subpages, and we need refuse to free/dissolve + * this hwpoisoned hugepage. + */ + folio_set_hugetlb_raw_hwp_unreliable(folio); + /* + * Once hugetlb_raw_hwp_unreliable is set, raw_hwp_page is not + * used any more, so free it. + */ + __folio_free_raw_hwp(folio, false); + } + return ret; +} + +static unsigned long folio_free_raw_hwp(struct folio *folio, bool move_flag) +{ + /* + * hugetlb_vmemmap_optimized hugepages can't be freed because struct + * pages for tail pages are required but they don't exist. + */ + if (move_flag && folio_test_hugetlb_vmemmap_optimized(folio)) + return 0; + + /* + * hugetlb_raw_hwp_unreliable hugepages shouldn't be unpoisoned by + * definition. + */ + if (folio_test_hugetlb_raw_hwp_unreliable(folio)) + return 0; + + return __folio_free_raw_hwp(folio, move_flag); +} + +void folio_clear_hugetlb_hwpoison(struct folio *folio) +{ + if (folio_test_hugetlb_raw_hwp_unreliable(folio)) + return; + if (folio_test_hugetlb_vmemmap_optimized(folio)) + return; + folio_clear_hwpoison(folio); + folio_free_raw_hwp(folio, true); +} + +/* + * Called from hugetlb code with hugetlb_lock held. + * + * Return values: + * 0 - free hugepage + * 1 - in-use hugepage + * 2 - not a hugepage + * -EBUSY - the hugepage is busy (try to retry) + * -EHWPOISON - the hugepage is already hwpoisoned + */ +int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, + bool *migratable_cleared) +{ + struct page *page = pfn_to_page(pfn); + struct folio *folio = page_folio(page); + int ret = 2; /* fallback to normal page handling */ + bool count_increased = false; + + if (!folio_test_hugetlb(folio)) + goto out; + + if (flags & MF_COUNT_INCREASED) { + ret = 1; + count_increased = true; + } else if (folio_test_hugetlb_freed(folio)) { + ret = 0; + } else if (folio_test_hugetlb_migratable(folio)) { + ret = folio_try_get(folio); + if (ret) + count_increased = true; + } else { + ret = -EBUSY; + if (!(flags & MF_NO_RETRY)) + goto out; + } + + if (folio_set_hugetlb_hwpoison(folio, page)) { + ret = -EHWPOISON; + goto out; + } + + /* + * Clearing hugetlb_migratable for hwpoisoned hugepages to prevent them + * from being migrated by memory hotremove. + */ + if (count_increased && folio_test_hugetlb_migratable(folio)) { + folio_clear_hugetlb_migratable(folio); + *migratable_cleared = true; + } + + return ret; +out: + if (count_increased) + folio_put(folio); + return ret; +} + +/* + * Taking refcount of hugetlb pages needs extra care about race conditions + * with basic operations like hugepage allocation/free/demotion. + * So some of prechecks for hwpoison (pinning, and testing/setting + * PageHWPoison) should be done in single hugetlb_lock range. + */ +static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb) +{ + int res; + struct page *p = pfn_to_page(pfn); + struct folio *folio; + unsigned long page_flags; + bool migratable_cleared = false; + + *hugetlb = 1; +retry: + res = get_huge_page_for_hwpoison(pfn, flags, &migratable_cleared); + if (res == 2) { /* fallback to normal page handling */ + *hugetlb = 0; + return 0; + } else if (res == -EHWPOISON) { + if (flags & MF_ACTION_REQUIRED) { + folio = page_folio(p); + res = kill_accessing_process(current, folio_pfn(folio), flags); + } + action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED); + return res; + } else if (res == -EBUSY) { + if (!(flags & MF_NO_RETRY)) { + flags |= MF_NO_RETRY; + goto retry; + } + return action_result(pfn, MF_MSG_GET_HWPOISON, MF_IGNORED); + } + + folio = page_folio(p); + folio_lock(folio); + + if (hwpoison_filter(p)) { + folio_clear_hugetlb_hwpoison(folio); + if (migratable_cleared) + folio_set_hugetlb_migratable(folio); + folio_unlock(folio); + if (res == 1) + folio_put(folio); + return -EOPNOTSUPP; + } + + /* + * Handling free hugepage. The possible race with hugepage allocation + * or demotion can be prevented by PageHWPoison flag. + */ + if (res == 0) { + folio_unlock(folio); + if (__page_handle_poison(p) > 0) { + page_ref_inc(p); + res = MF_RECOVERED; + } else { + res = MF_FAILED; + } + return action_result(pfn, MF_MSG_FREE_HUGE, res); + } + + page_flags = folio->flags.f; + + if (!hwpoison_user_mappings(folio, p, pfn, flags)) { + folio_unlock(folio); + return action_result(pfn, MF_MSG_UNMAP_FAILED, MF_FAILED); + } + + return identify_page_state(pfn, p, page_flags); +} + +#else +static inline int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb) +{ + return 0; +} + +static inline unsigned long folio_free_raw_hwp(struct folio *folio, bool flag) +{ + return 0; +} +#endif /* CONFIG_HUGETLB_PAGE */ + +/* Drop the extra refcount in case we come from madvise() */ +static void put_ref_page(unsigned long pfn, int flags) +{ + if (!(flags & MF_COUNT_INCREASED)) + return; + + put_page(pfn_to_page(pfn)); +} + +static int memory_failure_dev_pagemap(unsigned long pfn, int flags, + struct dev_pagemap *pgmap) +{ + int rc = -ENXIO; + + /* device metadata space is not recoverable */ + if (!pgmap_pfn_valid(pgmap, pfn)) + goto out; + + /* + * Call driver's implementation to handle the memory failure, otherwise + * fall back to generic handler. + */ + if (pgmap_has_memory_failure(pgmap)) { + rc = pgmap->ops->memory_failure(pgmap, pfn, 1, flags); + /* + * Fall back to generic handler too if operation is not + * supported inside the driver/device/filesystem. + */ + if (rc != -EOPNOTSUPP) + goto out; + } + + rc = mf_generic_kill_procs(pfn, flags, pgmap); out: /* drop pgmap ref acquired in caller */ put_dev_pagemap(pgmap); - action_result(pfn, MF_MSG_DAX, rc ? MF_FAILED : MF_RECOVERED); + if (rc != -EOPNOTSUPP) + action_result(pfn, MF_MSG_DAX, rc ? MF_FAILED : MF_RECOVERED); return rc; } +/* + * The calling condition is as such: thp split failed, page might have + * been RDMA pinned, not much can be done for recovery. + * But a SIGBUS should be delivered with vaddr provided so that the user + * application has a chance to recover. Also, application processes' + * election for MCE early killed will be honored. + */ +static void kill_procs_now(struct page *p, unsigned long pfn, int flags, + struct folio *folio) +{ + LIST_HEAD(tokill); + + folio_lock(folio); + collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED); + folio_unlock(folio); + + kill_procs(&tokill, true, pfn, flags); +} + +int register_pfn_address_space(struct pfn_address_space *pfn_space) +{ + guard(mutex)(&pfn_space_lock); + + if (interval_tree_iter_first(&pfn_space_itree, + pfn_space->node.start, + pfn_space->node.last)) + return -EBUSY; + + interval_tree_insert(&pfn_space->node, &pfn_space_itree); + + return 0; +} +EXPORT_SYMBOL_GPL(register_pfn_address_space); + +void unregister_pfn_address_space(struct pfn_address_space *pfn_space) +{ + guard(mutex)(&pfn_space_lock); + + if (interval_tree_iter_first(&pfn_space_itree, + pfn_space->node.start, + pfn_space->node.last)) + interval_tree_remove(&pfn_space->node, &pfn_space_itree); +} +EXPORT_SYMBOL_GPL(unregister_pfn_address_space); + +static void add_to_kill_pfn(struct task_struct *tsk, + struct vm_area_struct *vma, + struct list_head *to_kill, + unsigned long pfn) +{ + struct to_kill *tk; + + tk = kmalloc(sizeof(*tk), GFP_ATOMIC); + if (!tk) { + pr_info("Unable to kill proc %d\n", tsk->pid); + return; + } + + /* Check for pgoff not backed by struct page */ + tk->addr = vma_address(vma, pfn, 1); + tk->size_shift = PAGE_SHIFT; + + if (tk->addr == -EFAULT) + pr_info("Unable to find address %lx in %s\n", + pfn, tsk->comm); + + get_task_struct(tsk); + tk->tsk = tsk; + list_add_tail(&tk->nd, to_kill); +} + +/* + * Collect processes when the error hit a PFN not backed by struct page. + */ +static void collect_procs_pfn(struct address_space *mapping, + unsigned long pfn, struct list_head *to_kill) +{ + struct vm_area_struct *vma; + struct task_struct *tsk; + + i_mmap_lock_read(mapping); + rcu_read_lock(); + for_each_process(tsk) { + struct task_struct *t = tsk; + + t = task_early_kill(tsk, true); + if (!t) + continue; + vma_interval_tree_foreach(vma, &mapping->i_mmap, pfn, pfn) { + if (vma->vm_mm == t->mm) + add_to_kill_pfn(t, vma, to_kill, pfn); + } + } + rcu_read_unlock(); + i_mmap_unlock_read(mapping); +} + +/** + * memory_failure_pfn - Handle memory failure on a page not backed by + * struct page. + * @pfn: Page Number of the corrupted page + * @flags: fine tune action taken + * + * Return: + * 0 - success, + * -EBUSY - Page PFN does not belong to any address space mapping. + */ +static int memory_failure_pfn(unsigned long pfn, int flags) +{ + struct interval_tree_node *node; + LIST_HEAD(tokill); + + scoped_guard(mutex, &pfn_space_lock) { + bool mf_handled = false; + + /* + * Modules registers with MM the address space mapping to + * the device memory they manage. Iterate to identify + * exactly which address space has mapped to this failing + * PFN. + */ + for (node = interval_tree_iter_first(&pfn_space_itree, pfn, pfn); node; + node = interval_tree_iter_next(node, pfn, pfn)) { + struct pfn_address_space *pfn_space = + container_of(node, struct pfn_address_space, node); + + collect_procs_pfn(pfn_space->mapping, pfn, &tokill); + + mf_handled = true; + } + + if (!mf_handled) + return action_result(pfn, MF_MSG_PFN_MAP, MF_IGNORED); + } + + /* + * Unlike System-RAM there is no possibility to swap in a different + * physical page at a given virtual address, so all userspace + * consumption of direct PFN memory necessitates SIGBUS (i.e. + * MF_MUST_KILL) + */ + flags |= MF_ACTION_REQUIRED | MF_MUST_KILL; + + kill_procs(&tokill, true, pfn, flags); + + return action_result(pfn, MF_MSG_PFN_MAP, MF_RECOVERED); +} + /** * memory_failure - Handle memory failure of a page. * @pfn: Page Number of the corrupted page @@ -1245,46 +2301,81 @@ out: * detected by a background scrubber) * * Must run in process context (e.g. a work queue) with interrupts - * enabled and no spinlocks hold. + * enabled and no spinlocks held. + * + * Return: + * 0 - success, + * -ENXIO - memory not managed by the kernel + * -EOPNOTSUPP - hwpoison_filter() filtered the error event, + * -EHWPOISON - the page was already poisoned, potentially + * kill process, + * other negative values - failure. */ int memory_failure(unsigned long pfn, int flags) { struct page *p; - struct page *hpage; - struct page *orig_head; + struct folio *folio; struct dev_pagemap *pgmap; - int res; + int res = 0; unsigned long page_flags; + bool retry = true; + int hugetlb = 0; if (!sysctl_memory_failure_recovery) panic("Memory failure on page %lx", pfn); - if (!pfn_valid(pfn)) { - pr_err("Memory failure: %#lx: memory outside kernel control\n", - pfn); - return -ENXIO; + mutex_lock(&mf_mutex); + + if (!(flags & MF_SW_SIMULATED)) + hw_memory_failure = true; + + p = pfn_to_online_page(pfn); + if (!p) { + res = arch_memory_failure(pfn, flags); + if (res == 0) + goto unlock_mutex; + + if (!pfn_valid(pfn) && !arch_is_platform_page(PFN_PHYS(pfn))) { + /* + * The PFN is not backed by struct page. + */ + res = memory_failure_pfn(pfn, flags); + goto unlock_mutex; + } + + if (pfn_valid(pfn)) { + pgmap = get_dev_pagemap(pfn); + put_ref_page(pfn, flags); + if (pgmap) { + res = memory_failure_dev_pagemap(pfn, flags, + pgmap); + goto unlock_mutex; + } + } + pr_err("%#lx: memory outside kernel control\n", pfn); + res = -ENXIO; + goto unlock_mutex; } - pgmap = get_dev_pagemap(pfn, NULL); - if (pgmap) - return memory_failure_dev_pagemap(pfn, flags, pgmap); +try_again: + res = try_memory_failure_hugetlb(pfn, flags, &hugetlb); + if (hugetlb) + goto unlock_mutex; - p = pfn_to_page(pfn); - if (PageHuge(p)) - return memory_failure_hugetlb(pfn, flags); if (TestSetPageHWPoison(p)) { - pr_err("Memory failure: %#lx: already hardware poisoned\n", - pfn); - return 0; + res = -EHWPOISON; + if (flags & MF_ACTION_REQUIRED) + res = kill_accessing_process(current, pfn, flags); + if (flags & MF_COUNT_INCREASED) + put_page(p); + action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED); + goto unlock_mutex; } - orig_head = hpage = compound_head(p); - num_poisoned_pages_inc(); - /* * We need/can do nothing about count=0 pages. * 1) it's a free page, and therefore in safe hand: - * prep_new_page() will be the gate keeper. + * check_new_page() will be the gate keeper. * 2) it's part of a non-compound high order page. * Implies some kernel user: cannot stop them from * R/W the page; let's pray that the page has been @@ -1292,34 +2383,82 @@ int memory_failure(unsigned long pfn, int flags) * In fact it's dangerous to directly bump up page count from 0, * that may make page_ref_freeze()/page_ref_unfreeze() mismatch. */ - 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; + if (!(flags & MF_COUNT_INCREASED)) { + res = get_hwpoison_page(p, flags); + if (!res) { + if (is_free_buddy_page(p)) { + if (take_page_off_buddy(p)) { + page_ref_inc(p); + res = MF_RECOVERED; + } else { + /* We lost the race, try again */ + if (retry) { + ClearPageHWPoison(p); + retry = false; + goto try_again; + } + res = MF_FAILED; + } + res = action_result(pfn, MF_MSG_BUDDY, res); + } else { + res = action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED); + } + goto unlock_mutex; + } else if (res < 0) { + res = action_result(pfn, MF_MSG_GET_HWPOISON, MF_IGNORED); + goto unlock_mutex; } } - if (PageTransHuge(hpage)) { - lock_page(p); - if (!PageAnon(p) || unlikely(split_huge_page(p))) { - unlock_page(p); - if (!PageAnon(p)) - pr_err("Memory failure: %#lx: non anonymous thp\n", - pfn); - else - pr_err("Memory failure: %#lx: thp split failed\n", - pfn); - if (TestClearPageHWPoison(p)) - num_poisoned_pages_dec(); - put_hwpoison_page(p); - return -EBUSY; + folio = page_folio(p); + + /* filter pages that are protected from hwpoison test by users */ + folio_lock(folio); + if (hwpoison_filter(p)) { + ClearPageHWPoison(p); + folio_unlock(folio); + folio_put(folio); + res = -EOPNOTSUPP; + goto unlock_mutex; + } + folio_unlock(folio); + + if (folio_test_large(folio)) { + const int new_order = min_order_for_split(folio); + int err; + + /* + * The flag must be set after the refcount is bumped + * otherwise it may race with THP split. + * And the flag can't be set in get_hwpoison_page() since + * it is called by soft offline too and it is just called + * for !MF_COUNT_INCREASED. So here seems to be the best + * place. + * + * Don't need care about the above error handling paths for + * get_hwpoison_page() since they handle either free page + * or unhandlable page. The refcount is bumped iff the + * page is a valid handlable page. + */ + folio_set_has_hwpoisoned(folio); + err = try_to_split_thp_page(p, new_order, /* release= */ false); + /* + * If splitting a folio to order-0 fails, kill the process. + * Split the folio regardless to minimize unusable pages. + * Because the memory failure code cannot handle large + * folios, this split is always treated as if it failed. + */ + if (err || new_order) { + /* get folio again in case the original one is split */ + folio = page_folio(p); + res = -EHWPOISON; + kill_procs_now(p, pfn, flags, folio); + put_page(p); + action_result(pfn, MF_MSG_UNSPLIT_THP, MF_FAILED); + goto unlock_mutex; } - unlock_page(p); VM_BUG_ON_PAGE(!page_count(p), p); - hpage = compound_head(p); + folio = page_folio(p); } /* @@ -1330,93 +2469,66 @@ int memory_failure(unsigned long pfn, int flags) * The check (unnecessarily) ignores LRU pages being isolated and * walked by the page reclaim code, however that's not a big loss. */ - shake_page(p, 0); - /* shake_page could have turned it free. */ - if (!PageLRU(p) && is_free_buddy_page(p)) { - if (flags & MF_COUNT_INCREASED) - action_result(pfn, MF_MSG_BUDDY, MF_DELAYED); - else - action_result(pfn, MF_MSG_BUDDY_2ND, MF_DELAYED); - return 0; - } + shake_folio(folio); - lock_page(p); + folio_lock(folio); /* - * The page could have changed compound pages during the locking. - * If this happens just bail out. + * We're only intended to deal with the non-Compound page here. + * The page cannot become compound pages again as folio has been + * splited and extra refcnt is held. */ - if (PageCompound(p) && compound_head(p) != orig_head) { - action_result(pfn, MF_MSG_DIFFERENT_COMPOUND, MF_IGNORED); - res = -EBUSY; - goto out; - } + WARN_ON(folio_test_large(folio)); /* * We use page flags to determine what action should be taken, but * the flags can be modified by the error containment action. One * example is an mlocked page, where PG_mlocked is cleared by - * page_remove_rmap() in try_to_unmap_one(). So to determine page status - * correctly, we save a copy of the page flags at this time. + * folio_remove_rmap_*() in try_to_unmap_one(). So to determine page + * status correctly, we save a copy of the page flags at this time. */ - if (PageHuge(p)) - page_flags = hpage->flags; - else - page_flags = p->flags; + page_flags = folio->flags.f; /* - * unpoison always clear PG_hwpoison inside page lock + * __munlock_folio() may clear a writeback folio's LRU flag without + * the folio lock. We need to wait for writeback completion for this + * folio or it may trigger a vfs BUG while evicting inode. */ - if (!PageHWPoison(p)) { - pr_err("Memory failure: %#lx: just unpoisoned\n", pfn); - num_poisoned_pages_dec(); - unlock_page(p); - put_hwpoison_page(p); - return 0; - } - if (hwpoison_filter(p)) { - if (TestClearPageHWPoison(p)) - num_poisoned_pages_dec(); - unlock_page(p); - put_hwpoison_page(p); - return 0; - } - - if (!PageTransTail(p) && !PageLRU(p)) + if (!folio_test_lru(folio) && !folio_test_writeback(folio)) goto identify_page_state; /* * It's very difficult to mess with pages currently under IO * and in many cases impossible, so we just avoid it here. */ - wait_on_page_writeback(p); + folio_wait_writeback(folio); /* * Now take care of user space mappings. - * Abort on fail: __delete_from_page_cache() assumes unmapped page. - * - * When the raw error page is thp tail page, hpage points to the raw - * page after thp split. + * Abort on fail: __filemap_remove_folio() assumes unmapped page. */ - if (!hwpoison_user_mappings(p, pfn, flags, &hpage)) { - action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED); - res = -EBUSY; - goto out; + if (!hwpoison_user_mappings(folio, p, pfn, flags)) { + res = action_result(pfn, MF_MSG_UNMAP_FAILED, MF_FAILED); + goto unlock_page; } /* * Torn down by someone else? */ - if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) { - action_result(pfn, MF_MSG_TRUNCATED_LRU, MF_IGNORED); - res = -EBUSY; - goto out; + if (folio_test_lru(folio) && !folio_test_swapcache(folio) && + folio->mapping == NULL) { + res = action_result(pfn, MF_MSG_TRUNCATED_LRU, MF_IGNORED); + goto unlock_page; } identify_page_state: res = identify_page_state(pfn, p, page_flags); -out: - unlock_page(p); + mutex_unlock(&mf_mutex); + return res; +unlock_page: + folio_unlock(folio); +unlock_mutex: + mutex_unlock(&mf_mutex); return res; } EXPORT_SYMBOL_GPL(memory_failure); @@ -1432,7 +2544,7 @@ struct memory_failure_entry { struct memory_failure_cpu { DECLARE_KFIFO(fifo, struct memory_failure_entry, MEMORY_FAILURE_FIFO_SIZE); - spinlock_t lock; + raw_spinlock_t lock; struct work_struct work; }; @@ -1458,20 +2570,22 @@ void memory_failure_queue(unsigned long pfn, int flags) { struct memory_failure_cpu *mf_cpu; unsigned long proc_flags; + bool buffer_overflow; struct memory_failure_entry entry = { .pfn = pfn, .flags = flags, }; mf_cpu = &get_cpu_var(memory_failure_cpu); - spin_lock_irqsave(&mf_cpu->lock, proc_flags); - if (kfifo_put(&mf_cpu->fifo, entry)) + raw_spin_lock_irqsave(&mf_cpu->lock, proc_flags); + buffer_overflow = !kfifo_put(&mf_cpu->fifo, entry); + if (!buffer_overflow) schedule_work_on(smp_processor_id(), &mf_cpu->work); - else - pr_err("Memory failure: buffer overflow when queuing memory failure at %#lx\n", - pfn); - spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + raw_spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); put_cpu_var(memory_failure_cpu); + if (buffer_overflow) + pr_err("buffer overflow when queuing memory failure at %#lx\n", + pfn); } EXPORT_SYMBOL_GPL(memory_failure_queue); @@ -1482,15 +2596,15 @@ static void memory_failure_work_func(struct work_struct *work) unsigned long proc_flags; int gotten; - mf_cpu = this_cpu_ptr(&memory_failure_cpu); + mf_cpu = container_of(work, struct memory_failure_cpu, work); for (;;) { - spin_lock_irqsave(&mf_cpu->lock, proc_flags); + raw_spin_lock_irqsave(&mf_cpu->lock, proc_flags); gotten = kfifo_get(&mf_cpu->fifo, &entry); - spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + raw_spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); if (!gotten) break; if (entry.flags & MF_SOFT_OFFLINE) - soft_offline_page(pfn_to_page(entry.pfn), entry.flags); + soft_offline_page(entry.pfn, entry.flags); else memory_failure(entry.pfn, entry.flags); } @@ -1503,15 +2617,19 @@ static int __init memory_failure_init(void) for_each_possible_cpu(cpu) { mf_cpu = &per_cpu(memory_failure_cpu, cpu); - spin_lock_init(&mf_cpu->lock); + raw_spin_lock_init(&mf_cpu->lock); INIT_KFIFO(mf_cpu->fifo); INIT_WORK(&mf_cpu->work, memory_failure_work_func); } + register_sysctl_init("vm", memory_failure_table); + return 0; } core_initcall(memory_failure_init); +#undef pr_fmt +#define pr_fmt(fmt) "Unpoison: " fmt #define unpoison_pr_info(fmt, pfn, rs) \ ({ \ if (__ratelimit(rs)) \ @@ -1532,352 +2650,219 @@ core_initcall(memory_failure_init); */ int unpoison_memory(unsigned long pfn) { - struct page *page; + struct folio *folio; struct page *p; - int freeit = 0; + int ret = -EBUSY, ghp; + unsigned long count; + bool huge = false; static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); - if (!pfn_valid(pfn)) - return -ENXIO; + p = pfn_to_online_page(pfn); + if (!p) + return -EIO; + folio = page_folio(p); - p = pfn_to_page(pfn); - page = compound_head(p); + mutex_lock(&mf_mutex); - if (!PageHWPoison(p)) { - unpoison_pr_info("Unpoison: Page was already unpoisoned %#lx\n", + if (hw_memory_failure) { + unpoison_pr_info("%#lx: disabled after HW memory failure\n", pfn, &unpoison_rs); - return 0; + ret = -EOPNOTSUPP; + goto unlock_mutex; } - if (page_count(page) > 1) { - unpoison_pr_info("Unpoison: Someone grabs the hwpoison page %#lx\n", + if (is_huge_zero_folio(folio)) { + unpoison_pr_info("%#lx: huge zero page is not supported\n", pfn, &unpoison_rs); - return 0; + ret = -EOPNOTSUPP; + goto unlock_mutex; } - if (page_mapped(page)) { - unpoison_pr_info("Unpoison: Someone maps the hwpoison page %#lx\n", + if (!PageHWPoison(p)) { + unpoison_pr_info("%#lx: page was already unpoisoned\n", pfn, &unpoison_rs); - return 0; + goto unlock_mutex; } - if (page_mapping(page)) { - unpoison_pr_info("Unpoison: the hwpoison page has non-NULL mapping %#lx\n", + if (folio_ref_count(folio) > 1) { + unpoison_pr_info("%#lx: someone grabs the hwpoison page\n", pfn, &unpoison_rs); - return 0; + goto unlock_mutex; } - /* - * unpoison_memory() can encounter thp only when the thp is being - * worked by memory_failure() and the page lock is not held yet. - * In such case, we yield to memory_failure() and make unpoison fail. - */ - if (!PageHuge(page) && PageTransHuge(page)) { - unpoison_pr_info("Unpoison: Memory failure is now running on %#lx\n", - pfn, &unpoison_rs); - return 0; - } + if (folio_test_slab(folio) || folio_test_pgtable(folio) || + folio_test_reserved(folio) || folio_test_offline(folio)) + goto unlock_mutex; - if (!get_hwpoison_page(p)) { - if (TestClearPageHWPoison(p)) - num_poisoned_pages_dec(); - unpoison_pr_info("Unpoison: Software-unpoisoned free page %#lx\n", + if (folio_mapped(folio)) { + unpoison_pr_info("%#lx: someone maps the hwpoison page\n", pfn, &unpoison_rs); - return 0; + goto unlock_mutex; } - lock_page(page); - /* - * This test is racy because PG_hwpoison is set outside of page lock. - * That's acceptable because that won't trigger kernel panic. Instead, - * the PG_hwpoison page will be caught and isolated on the entrance to - * the free buddy page pool. - */ - if (TestClearPageHWPoison(page)) { - unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n", + if (folio_mapping(folio)) { + unpoison_pr_info("%#lx: the hwpoison page has non-NULL mapping\n", pfn, &unpoison_rs); - num_poisoned_pages_dec(); - freeit = 1; + goto unlock_mutex; } - unlock_page(page); - - put_hwpoison_page(page); - if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1)) - put_hwpoison_page(page); - - return 0; -} -EXPORT_SYMBOL(unpoison_memory); - -static struct page *new_page(struct page *p, unsigned long private) -{ - int nid = page_to_nid(p); - - return new_page_nodemask(p, nid, &node_states[N_MEMORY]); -} - -/* - * Safely get reference count of an arbitrary page. - * Returns 0 for a free page, -EIO for a zero refcount page - * that is not free, and 1 for any other page type. - * For 1 the page is returned with increased page count, otherwise not. - */ -static int __get_any_page(struct page *p, unsigned long pfn, int flags) -{ - int ret; - if (flags & MF_COUNT_INCREASED) - return 1; - - /* - * When the target page is a free hugepage, just remove it - * from free hugepage list. - */ - if (!get_hwpoison_page(p)) { - if (PageHuge(p)) { - pr_info("%s: %#lx free huge page\n", __func__, pfn); - ret = 0; - } else if (is_free_buddy_page(p)) { - pr_info("%s: %#lx free buddy page\n", __func__, pfn); - ret = 0; + ghp = get_hwpoison_page(p, MF_UNPOISON); + if (!ghp) { + if (folio_test_hugetlb(folio)) { + huge = true; + count = folio_free_raw_hwp(folio, false); + if (count == 0) + goto unlock_mutex; + } + ret = folio_test_clear_hwpoison(folio) ? 0 : -EBUSY; + } else if (ghp < 0) { + if (ghp == -EHWPOISON) { + ret = put_page_back_buddy(p) ? 0 : -EBUSY; } else { - pr_info("%s: %#lx: unknown zero refcount page type %lx\n", - __func__, pfn, p->flags); - ret = -EIO; + ret = ghp; + unpoison_pr_info("%#lx: failed to grab page\n", + pfn, &unpoison_rs); } } else { - /* Not a free page */ - ret = 1; - } - return ret; -} - -static int get_any_page(struct page *page, unsigned long pfn, int flags) -{ - int ret = __get_any_page(page, pfn, flags); - - if (ret == 1 && !PageHuge(page) && - !PageLRU(page) && !__PageMovable(page)) { - /* - * Try to free it. - */ - put_hwpoison_page(page); - shake_page(page, 1); + if (folio_test_hugetlb(folio)) { + huge = true; + count = folio_free_raw_hwp(folio, false); + if (count == 0) { + folio_put(folio); + goto unlock_mutex; + } + } - /* - * Did it turn free? - */ - ret = __get_any_page(page, pfn, 0); - if (ret == 1 && !PageLRU(page)) { - /* Drop page reference which is from __get_any_page() */ - put_hwpoison_page(page); - pr_info("soft_offline: %#lx: unknown non LRU page type %lx (%pGp)\n", - pfn, page->flags, &page->flags); - return -EIO; + folio_put(folio); + if (TestClearPageHWPoison(p)) { + folio_put(folio); + ret = 0; } } + +unlock_mutex: + mutex_unlock(&mf_mutex); + if (!ret) { + if (!huge) + num_poisoned_pages_sub(pfn, 1); + unpoison_pr_info("%#lx: software-unpoisoned page\n", + page_to_pfn(p), &unpoison_rs); + } return ret; } +EXPORT_SYMBOL(unpoison_memory); + +#undef pr_fmt +#define pr_fmt(fmt) "Soft offline: " fmt -static int soft_offline_huge_page(struct page *page, int flags) +/* + * soft_offline_in_use_page handles hugetlb-pages and non-hugetlb pages. + * If the page is a non-dirty unmapped page-cache page, it simply invalidates. + * If the page is mapped, it migrates the contents over. + */ +static int soft_offline_in_use_page(struct page *page) { - int ret; + long ret = 0; unsigned long pfn = page_to_pfn(page); - struct page *hpage = compound_head(page); + struct folio *folio = page_folio(page); + char const *msg_page[] = {"page", "hugepage"}; + bool huge = folio_test_hugetlb(folio); + bool isolated; LIST_HEAD(pagelist); + struct migration_target_control mtc = { + .nid = NUMA_NO_NODE, + .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + .reason = MR_MEMORY_FAILURE, + }; - /* - * This double-check of PageHWPoison is to avoid the race with - * memory_failure(). See also comment in __soft_offline_page(). - */ - lock_page(hpage); - if (PageHWPoison(hpage)) { - unlock_page(hpage); - put_hwpoison_page(hpage); - pr_info("soft offline: %#lx hugepage already poisoned\n", pfn); - return -EBUSY; - } - unlock_page(hpage); - - ret = isolate_huge_page(hpage, &pagelist); - /* - * get_any_page() and isolate_huge_page() takes a refcount each, - * so need to drop one here. - */ - put_hwpoison_page(hpage); - if (!ret) { - pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn); - return -EBUSY; - } + if (!huge && folio_test_large(folio)) { + const int new_order = min_order_for_split(folio); - ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, - MIGRATE_SYNC, MR_MEMORY_FAILURE); - if (ret) { - pr_info("soft offline: %#lx: hugepage migration failed %d, type %lx (%pGp)\n", - pfn, ret, page->flags, &page->flags); - if (!list_empty(&pagelist)) - putback_movable_pages(&pagelist); - if (ret > 0) - ret = -EIO; - } else { /* - * We set PG_hwpoison only when the migration source hugepage - * was successfully dissolved, because otherwise hwpoisoned - * hugepage remains on free hugepage list, then userspace will - * find it as SIGBUS by allocation failure. That's not expected - * in soft-offlining. + * If new_order (target split order) is not 0, do not split the + * folio at all to retain the still accessible large folio. + * NOTE: if minimizing the number of soft offline pages is + * preferred, split it to non-zero new_order like it is done in + * memory_failure(). */ - ret = dissolve_free_huge_page(page); - if (!ret) { - if (set_hwpoison_free_buddy_page(page)) - num_poisoned_pages_inc(); + if (new_order || try_to_split_thp_page(page, /* new_order= */ 0, + /* release= */ true)) { + pr_info("%#lx: thp split failed\n", pfn); + return -EBUSY; } + folio = page_folio(page); } - return ret; -} -static int __soft_offline_page(struct page *page, int flags) -{ - int ret; - unsigned long pfn = page_to_pfn(page); - - /* - * Check PageHWPoison again inside page lock because PageHWPoison - * is set by memory_failure() outside page lock. Note that - * memory_failure() also double-checks PageHWPoison inside page lock, - * so there's no race between soft_offline_page() and memory_failure(). - */ - lock_page(page); - wait_on_page_writeback(page); + folio_lock(folio); + if (!huge) + folio_wait_writeback(folio); if (PageHWPoison(page)) { - unlock_page(page); - put_hwpoison_page(page); - pr_info("soft offline: %#lx page already poisoned\n", pfn); - return -EBUSY; - } - /* - * Try to invalidate first. This should work for - * non dirty unmapped page cache pages. - */ - ret = invalidate_inode_page(page); - unlock_page(page); - /* - * RED-PEN would be better to keep it isolated here, but we - * would need to fix isolation locking first. - */ - if (ret == 1) { - put_hwpoison_page(page); - pr_info("soft_offline: %#lx: invalidated\n", pfn); - SetPageHWPoison(page); - num_poisoned_pages_inc(); + folio_unlock(folio); + folio_put(folio); + pr_info("%#lx: page already poisoned\n", pfn); return 0; } - /* - * Simple invalidation didn't work. - * Try to migrate to a new page instead. migrate.c - * handles a large number of cases for us. - */ - if (PageLRU(page)) - ret = isolate_lru_page(page); - else - ret = isolate_movable_page(page, ISOLATE_UNEVICTABLE); - /* - * Drop page reference which is came from get_any_page() - * successful isolate_lru_page() already took another one. - */ - put_hwpoison_page(page); - if (!ret) { - LIST_HEAD(pagelist); + if (!huge && folio_test_lru(folio) && !folio_test_swapcache(folio)) /* - * After isolated lru page, the PageLRU will be cleared, - * so use !__PageMovable instead for LRU page's mapping - * cannot have PAGE_MAPPING_MOVABLE. + * Try to invalidate first. This should work for + * non dirty unmapped page cache pages. */ - if (!__PageMovable(page)) - inc_node_page_state(page, NR_ISOLATED_ANON + - page_is_file_cache(page)); - list_add(&page->lru, &pagelist); - ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, - MIGRATE_SYNC, MR_MEMORY_FAILURE); - if (ret) { - if (!list_empty(&pagelist)) - putback_movable_pages(&pagelist); + ret = mapping_evict_folio(folio_mapping(folio), folio); + folio_unlock(folio); - pr_info("soft offline: %#lx: migration failed %d, type %lx (%pGp)\n", - pfn, ret, page->flags, &page->flags); - if (ret > 0) - ret = -EIO; - } - } else { - pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx (%pGp)\n", - pfn, ret, page_count(page), page->flags, &page->flags); + if (ret) { + pr_info("%#lx: invalidated\n", pfn); + page_handle_poison(page, false, true); + return 0; } - return ret; -} -static int soft_offline_in_use_page(struct page *page, int flags) -{ - int ret; - int mt; - struct page *hpage = compound_head(page); - - if (!PageHuge(page) && PageTransHuge(hpage)) { - lock_page(hpage); - if (!PageAnon(hpage) || unlikely(split_huge_page(hpage))) { - unlock_page(hpage); - if (!PageAnon(hpage)) - pr_info("soft offline: %#lx: non anonymous thp\n", page_to_pfn(page)); - else - pr_info("soft offline: %#lx: thp split failed\n", page_to_pfn(page)); - put_hwpoison_page(hpage); - return -EBUSY; - } - unlock_page(hpage); - get_hwpoison_page(page); - put_hwpoison_page(hpage); - } + isolated = isolate_folio_to_list(folio, &pagelist); /* - * Setting MIGRATE_ISOLATE here ensures that the page will be linked - * to free list immediately (not via pcplist) when released after - * successful page migration. Otherwise we can't guarantee that the - * page is really free after put_page() returns, so - * set_hwpoison_free_buddy_page() highly likely fails. + * If we succeed to isolate the folio, we grabbed another refcount on + * the folio, so we can safely drop the one we got from get_any_page(). + * If we failed to isolate the folio, it means that we cannot go further + * and we will return an error, so drop the reference we got from + * get_any_page() as well. */ - mt = get_pageblock_migratetype(page); - set_pageblock_migratetype(page, MIGRATE_ISOLATE); - if (PageHuge(page)) - ret = soft_offline_huge_page(page, flags); - else - ret = __soft_offline_page(page, flags); - set_pageblock_migratetype(page, mt); - return ret; -} + folio_put(folio); -static int soft_offline_free_page(struct page *page) -{ - int rc = 0; - struct page *head = compound_head(page); + if (isolated) { + ret = migrate_pages(&pagelist, alloc_migration_target, NULL, + (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE, NULL); + if (!ret) { + bool release = !huge; - if (PageHuge(head)) - rc = dissolve_free_huge_page(page); - if (!rc) { - if (set_hwpoison_free_buddy_page(page)) - num_poisoned_pages_inc(); - else - rc = -EBUSY; + if (!page_handle_poison(page, huge, release)) + ret = -EBUSY; + } else { + if (!list_empty(&pagelist)) + putback_movable_pages(&pagelist); + + pr_info("%#lx: %s migration failed %ld, type %pGp\n", + pfn, msg_page[huge], ret, &page->flags.f); + if (ret > 0) + ret = -EBUSY; + } + } else { + pr_info("%#lx: %s isolation failed, page count %d, type %pGp\n", + pfn, msg_page[huge], page_count(page), &page->flags.f); + ret = -EBUSY; } - return rc; + return ret; } /** * soft_offline_page - Soft offline a page. - * @page: page to offline + * @pfn: pfn to soft-offline * @flags: flags. Same as memory_failure(). * - * Returns 0 on success, otherwise negated errno. + * Returns 0 on success, + * -EOPNOTSUPP for hwpoison_filter() filtered the error event, or + * disabled by /proc/sys/vm/enable_soft_offline, + * < 0 otherwise negated errno. * * Soft offline a page, by migration or invalidation, * without killing anything. This is for the case when @@ -1894,34 +2879,66 @@ static int soft_offline_free_page(struct page *page) * This is not a 100% solution for all memory, but tries to be * ``good enough'' for the majority of memory. */ -int soft_offline_page(struct page *page, int flags) +int soft_offline_page(unsigned long pfn, int flags) { int ret; - unsigned long pfn = page_to_pfn(page); + bool try_again = true; + struct page *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); + if (!pfn_valid(pfn)) { + WARN_ON_ONCE(flags & MF_COUNT_INCREASED); + return -ENXIO; + } + + /* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */ + page = pfn_to_online_page(pfn); + if (!page) { + put_ref_page(pfn, flags); return -EIO; } + if (!sysctl_enable_soft_offline) { + pr_info_once("disabled by /proc/sys/vm/enable_soft_offline\n"); + put_ref_page(pfn, flags); + return -EOPNOTSUPP; + } + + mutex_lock(&mf_mutex); + if (PageHWPoison(page)) { - pr_info("soft offline: %#lx page already poisoned\n", pfn); - if (flags & MF_COUNT_INCREASED) - put_hwpoison_page(page); - return -EBUSY; + pr_info("%#lx: page already poisoned\n", pfn); + put_ref_page(pfn, flags); + mutex_unlock(&mf_mutex); + return 0; } +retry: get_online_mems(); - ret = get_any_page(page, pfn, flags); + ret = get_hwpoison_page(page, flags | MF_SOFT_OFFLINE); put_online_mems(); - if (ret > 0) - ret = soft_offline_in_use_page(page, flags); - else if (ret == 0) - ret = soft_offline_free_page(page); + if (hwpoison_filter(page)) { + if (ret > 0) + put_page(page); + + mutex_unlock(&mf_mutex); + return -EOPNOTSUPP; + } + + if (ret > 0) { + ret = soft_offline_in_use_page(page); + } else if (ret == 0) { + if (!page_handle_poison(page, true, false)) { + if (try_again) { + try_again = false; + flags &= ~MF_COUNT_INCREASED; + goto retry; + } + ret = -EBUSY; + } + } + + mutex_unlock(&mf_mutex); return ret; } |