diff options
Diffstat (limited to '')
| -rw-r--r-- | mm/memory-failure.c | 1930 |
1 files changed, 1324 insertions, 606 deletions
diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 41c634f45d45..bead6bccc7f2 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -33,12 +33,16 @@ * 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/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> @@ -56,6 +60,9 @@ #include <linux/kfifo.h> #include <linux/ratelimit.h> #include <linux/page-isolation.h> +#include <linux/pagewalk.h> +#include <linux/shmem_fs.h> +#include "swap.h" #include "internal.h" #include "ras/ras_event.h" @@ -65,6 +72,54 @@ int sysctl_memory_failure_recovery __read_mostly = 1; atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0); +static bool hw_memory_failure __read_mostly = false; + +/* + * 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. + */ +static int __page_handle_poison(struct page *page) +{ + int ret; + + zone_pcp_disable(page_zone(page)); + ret = dissolve_free_huge_page(page); + if (!ret) + ret = take_page_off_buddy(page); + zone_pcp_enable(page_zone(page)); + + return ret; +} + +static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, bool release) +{ + if (hugepage_or_freepage) { + /* + * Doing this check for free pages is also fine since dissolve_free_huge_page + * returns 0 for non-hugetlb pages 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; + } + + SetPageHWPoison(page); + if (release) + put_page(page); + page_ref_inc(page); + num_poisoned_pages_inc(); + + return true; +} + #if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE) u32 hwpoison_filter_enable = 0; @@ -87,12 +142,6 @@ static int hwpoison_filter_dev(struct page *p) hwpoison_filter_dev_minor == ~0U) return 0; - /* - * page_mapping() does not accept slab pages. - */ - if (PageSlab(p)) - return -EINVAL; - mapping = page_mapping(p); if (mapping == NULL || mapping->host == NULL) return -EINVAL; @@ -210,67 +259,64 @@ 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: Sending SIGBUS to %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, t->pid); - if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) { - ret = force_sig_mceerr(BUS_MCEERR_AR, (void __user *)tk->addr, - addr_lsb); - } 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", + pr_info("Error sending signal to %s:%d: %d\n", t->comm, t->pid, 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_page(struct page *p) { if (PageHuge(p)) 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)); } 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; + VM_BUG_ON_VMA(address == -EFAULT, vma); pgd = pgd_offset(vma->vm_mm, address); if (!pgd_present(*pgd)) return 0; @@ -288,11 +334,10 @@ static unsigned long dev_pagemap_mapping_shift(struct page *page, if (pmd_devmap(*pmd)) return PMD_SHIFT; pte = pte_offset_map(pmd, address); - if (!pte_present(*pte)) - return 0; - if (pte_devmap(*pte)) - return PAGE_SHIFT; - return 0; + if (pte_present(*pte) && pte_devmap(*pte)) + ret = PAGE_SHIFT; + pte_unmap(pte); + return ret; } /* @@ -300,26 +345,36 @@ static unsigned long dev_pagemap_mapping_shift(struct page *page, * not much we can do. We just print a message and ignore otherwise. */ +#define FSDAX_INVALID_PGOFF ULONG_MAX + /* * Schedule a process for later kill. * Uses GFP_ATOMIC allocations to avoid potential recursions in the VM. + * + * Note: @fsdax_pgoff is used only when @p is a fsdax page and a + * filesystem with a memory failure handler has claimed the + * memory_failure event. In all other cases, page->index and + * page->mapping are sufficient for mapping the page back to its + * corresponding user virtual address. */ static void add_to_kill(struct task_struct *tsk, struct page *p, - struct vm_area_struct *vma, - struct list_head *to_kill) + pgoff_t fsdax_pgoff, struct vm_area_struct *vma, + struct list_head *to_kill) { struct to_kill *tk; tk = kmalloc(sizeof(struct to_kill), GFP_ATOMIC); if (!tk) { - pr_err("Memory failure: Out of memory while machine check handling\n"); + pr_err("Out of memory while machine check handling\n"); return; } tk->addr = page_address_in_vma(p, vma); - if (is_zone_device_page(p)) - tk->size_shift = dev_pagemap_mapping_shift(p, vma); - else + if (is_zone_device_page(p)) { + if (fsdax_pgoff != FSDAX_INVALID_PGOFF) + tk->addr = vma_pgoff_address(fsdax_pgoff, 1, vma); + tk->size_shift = dev_pagemap_mapping_shift(vma, tk->addr); + } else tk->size_shift = page_shift(compound_head(p)); /* @@ -333,7 +388,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, * has a mapping for the page. */ if (tk->addr == -EFAULT) { - pr_info("Memory failure: Unable to find user space address %lx in %s\n", + pr_info("Unable to find user space address %lx in %s\n", page_to_pfn(p), tsk->comm); } else if (tk->size_shift == 0) { kfree(tk); @@ -348,8 +403,8 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, /* * 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) + * Only do anything when FORCEKILL 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. */ @@ -358,7 +413,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, { 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 @@ -366,7 +421,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, * signal and then access the memory. Just kill it. */ if (fail || tk->addr == -EFAULT) { - pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", + pr_err("%#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", pfn, tk->tsk->comm, tk->tsk->pid); do_send_sig_info(SIGKILL, SEND_SIG_PRIV, tk->tsk, PIDTYPE_PID); @@ -379,9 +434,10 @@ 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", + pr_err("%#lx: Cannot send advisory machine check signal to %s:%d\n", pfn, tk->tsk->comm, tk->tsk->pid); } + list_del(&tk->nd); put_task_struct(tk->tsk); kfree(tk); } @@ -399,9 +455,15 @@ 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; } @@ -409,22 +471,27 @@ 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 *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); } /* @@ -433,12 +500,13 @@ static struct task_struct *task_early_kill(struct task_struct *tsk, static void collect_procs_anon(struct page *page, struct list_head *to_kill, int force_early) { + struct folio *folio = page_folio(page); 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; @@ -453,14 +521,15 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, anon_vma_interval_tree_foreach(vmac, &av->rb_root, pgoff, pgoff) { vma = vmac->vma; + if (vma->vm_mm != t->mm) + continue; if (!page_mapped_in_vma(page, vma)) continue; - if (vma->vm_mm == t->mm) - add_to_kill(t, page, vma, to_kill); + add_to_kill(t, page, FSDAX_INVALID_PGOFF, vma, to_kill); } } read_unlock(&tasklist_lock); - page_unlock_anon_vma_read(av); + anon_vma_unlock_read(av); } /* @@ -472,11 +541,12 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, struct vm_area_struct *vma; struct task_struct *tsk; struct address_space *mapping = page->mapping; + pgoff_t pgoff; i_mmap_lock_read(mapping); read_lock(&tasklist_lock); + pgoff = page_to_pgoff(page); for_each_process(tsk) { - pgoff_t pgoff = page_to_pgoff(page); struct task_struct *t = task_early_kill(tsk, force_early); if (!t) @@ -491,12 +561,41 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, * to be informed of all such data corruptions. */ if (vma->vm_mm == t->mm) - add_to_kill(t, page, vma, to_kill); + add_to_kill(t, page, FSDAX_INVALID_PGOFF, vma, + to_kill); + } + } + read_unlock(&tasklist_lock); + i_mmap_unlock_read(mapping); +} + +#ifdef CONFIG_FS_DAX +/* + * Collect processes when the error hit a fsdax page. + */ +static void collect_procs_fsdax(struct page *page, + struct address_space *mapping, pgoff_t pgoff, + struct list_head *to_kill) +{ + struct vm_area_struct *vma; + struct task_struct *tsk; + + i_mmap_lock_read(mapping); + read_lock(&tasklist_lock); + for_each_process(tsk) { + struct task_struct *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(t, page, pgoff, vma, to_kill); } } read_unlock(&tasklist_lock); i_mmap_unlock_read(mapping); } +#endif /* CONFIG_FS_DAX */ /* * Collect the processes who have the corrupted page mapped to kill. @@ -513,6 +612,154 @@ static void collect_procs(struct page *page, struct list_head *tokill, collect_procs_file(page, tokill, force_early); } +struct hwp_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 { + swp_entry_t swp = pte_to_swp_entry(pte); + + if (is_hwpoison_entry(swp)) + pfn = swp_offset_pfn(swp); + } + + 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 hwp_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 hwp_walk *hwp) +{ + return 0; +} +#endif + +static int hwpoison_pte_range(pmd_t *pmdp, unsigned long addr, + unsigned long end, struct mm_walk *walk) +{ + struct hwp_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; + } + + if (pmd_trans_unstable(pmdp)) + goto out; + + mapped_pte = ptep = pte_offset_map_lock(walk->vma->vm_mm, pmdp, + addr, &ptl); + for (; addr != end; ptep++, addr += PAGE_SIZE) { + ret = check_hwpoisoned_entry(*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 hwp_walk *hwp = walk->private; + pte_t pte = huge_ptep_get(ptep); + struct hstate *h = hstate_vma(walk->vma); + + return check_hwpoisoned_entry(pte, addr, huge_page_shift(h), + hwp->pfn, &hwp->tk); +} +#else +#define hwpoison_hugetlb_range NULL +#endif + +static const struct mm_walk_ops hwp_walk_ops = { + .pmd_entry = hwpoison_pte_range, + .hugetlb_entry = hwpoison_hugetlb_range, +}; + +/* + * 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 hwp_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, &hwp_walk_ops, + (void *)&priv); + if (ret == 1 && priv.tk.addr) + kill_proc(&priv.tk, pfn, flags); + else + ret = 0; + mmap_read_unlock(p->mm); + return ret > 0 ? -EHWPOISON : -EFAULT; +} + static const char *action_name[] = { [MF_IGNORED] = "Ignored", [MF_FAILED] = "Failed", @@ -525,10 +772,8 @@ static const char * const action_page_types[] = { [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_UNMAP_FAILED] = "unmapping failed page", [MF_MSG_DIRTY_SWAPCACHE] = "dirty swapcache page", [MF_MSG_CLEAN_SWAPCACHE] = "clean swapcache page", @@ -540,8 +785,8 @@ 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_UNKNOWN] = "unknown page", }; @@ -565,7 +810,7 @@ static int delete_from_lru_cache(struct page *p) * 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(page_folio(p)); /* * drop the page count elevated by isolate_lru_page() @@ -585,12 +830,10 @@ static int truncate_error_page(struct page *p, unsigned long pfn, int err = mapping->a_ops->error_remove_page(mapping, p); if (err != 0) { - pr_info("Memory failure: %#lx: Failed to punch page: %d\n", - pfn, err); + pr_info("%#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); + pr_info("%#lx: failed to release buffers\n", pfn); } else { ret = MF_RECOVERED; } @@ -602,38 +845,73 @@ static int truncate_error_page(struct page *p, unsigned long pfn, if (invalidate_inode_page(p)) 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 -= 1; + + 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. */ -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); + pr_err("%#lx: Unknown page state\n", page_to_pfn(p)); + unlock_page(p); return MF_FAILED; } /* * 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) { + int ret; struct address_space *mapping; + bool extra_pins; delete_from_lru_cache(p); @@ -641,8 +919,10 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) * For anonymous pages we're done the only reference left * should be the one m_f() holds. */ - if (PageAnon(p)) - return MF_RECOVERED; + if (PageAnon(p)) { + ret = MF_RECOVERED; + goto out; + } /* * Now truncate the page in the page cache. This is really @@ -656,15 +936,29 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) /* * Page has been teared down in the meanwhile */ - return MF_FAILED; + 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_page(p, page_to_pfn(p), mapping); + if (has_extra_refcount(ps, p, extra_pins)) + ret = MF_FAILED; + +out: + unlock_page(p); + + return ret; } /* @@ -672,7 +966,7 @@ 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); @@ -716,7 +1010,7 @@ static int me_pagecache_dirty(struct page *p, unsigned long pfn) mapping_set_error(mapping, -EIO); } - return me_pagecache_clean(p, pfn); + return me_pagecache_clean(ps, p); } /* @@ -738,26 +1032,41 @@ 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) { + int ret; + bool extra_pins = false; + ClearPageDirty(p); /* Trigger EIO in shmem: */ ClearPageUptodate(p); - if (!delete_from_lru_cache(p)) - return MF_DELAYED; - else - return MF_FAILED; + ret = delete_from_lru_cache(p) ? MF_FAILED : MF_DELAYED; + unlock_page(p); + + 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; + delete_from_swap_cache(folio); + + ret = delete_from_lru_cache(p) ? MF_FAILED : MF_RECOVERED; + folio_unlock(folio); + + if (has_extra_refcount(ps, p, false)) + ret = MF_FAILED; + + return ret; } /* @@ -766,32 +1075,41 @@ 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; + int res; struct page *hpage = compound_head(p); struct address_space *mapping; + bool extra_pins = false; if (!PageHuge(hpage)) return MF_DELAYED; mapping = page_mapping(hpage); if (mapping) { - res = truncate_error_page(hpage, pfn, mapping); + res = truncate_error_page(hpage, page_to_pfn(p), mapping); + /* The page is kept in page cache. */ + extra_pins = true; + unlock_page(hpage); } else { unlock_page(hpage); /* - * 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); + put_page(hpage); + 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; } @@ -812,18 +1130,12 @@ 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: @@ -861,7 +1173,6 @@ static struct page_state { #undef sc #undef unevict #undef mlock -#undef writeback #undef lru #undef head #undef slab @@ -876,7 +1187,8 @@ static void action_result(unsigned long pfn, enum mf_action_page_type type, { trace_memory_failure_event(pfn, type, result); - pr_err("Memory failure: %#lx: recovery action for %s: %s\n", + num_poisoned_pages_inc(); + pr_err("%#lx: recovery action for %s: %s\n", pfn, action_page_types[type], action_name[result]); } @@ -884,18 +1196,10 @@ static int page_action(struct page_state *ps, struct page *p, unsigned long pfn) { int result; - int count; - result = ps->action(p, pfn); + /* page p should be unlocked after returning from ps->action(). */ + result = ps->action(ps, p); - count = page_count(p) - 1; - if (ps->action == me_swapcache_dirty && result == MF_DELAYED) - count--; - if (count > 0) { - pr_err("Memory failure: %#lx: %s still referenced by %d users\n", - pfn, action_page_types[ps->type], count); - result = MF_FAILED; - } action_result(pfn, ps->type, result); /* Could do more checks here if page looks ok */ @@ -906,64 +1210,209 @@ static int page_action(struct page_state *ps, struct page *p, return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY; } -/** - * 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) +{ + /* Soft offline could migrate non-LRU movable pages */ + if ((flags & MF_SOFT_OFFLINE) && __PageMovable(page)) + return true; + + return PageLRU(page) || is_free_buddy_page(page); +} + +static int __get_hwpoison_page(struct page *page, unsigned long flags) { struct page *head = compound_head(page); + int ret = 0; + bool hugetlb = 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; - } - } + ret = get_hwpoison_huge_page(head, &hugetlb); + if (hugetlb) + return ret; + + /* + * This check prevents from calling get_page_unless_zero() for any + * unsupported type of page in order to reduce the risk of unexpected + * races caused by taking a page refcount. + */ + if (!HWPoisonHandlable(head, flags)) + return -EBUSY; if (get_page_unless_zero(head)) { if (head == compound_head(page)) return 1; - pr_info("Memory failure: %#lx cannot catch tail\n", - page_to_pfn(page)); + pr_info("%#lx cannot catch tail\n", page_to_pfn(page)); put_page(head); } return 0; } -EXPORT_SYMBOL_GPL(get_hwpoison_page); + +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++ < 3) + goto try_again; + ret = -EBUSY; + } else if (!PageHuge(p) && !is_free_buddy_page(p)) { + /* We raced with put_page, retry. */ + if (pass++ < 3) + 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++ < 3) { + 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 page *head = compound_head(page); + int ret = 0; + bool hugetlb = false; + + ret = get_hwpoison_huge_page(head, &hugetlb); + if (hugetlb) + return ret; + + /* + * 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, + * 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; +} /* * 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) + int flags, struct page *hpage) { - enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS; + struct folio *folio = page_folio(hpage); + enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC; struct address_space *mapping; LIST_HEAD(tokill); bool unmap_success; - int kill = 1, forcekill; - struct page *hpage = *hpagep; + int forcekill; bool mlocked = PageMlocked(hpage); /* * Here we are interested only in user-mapped pages, so skip any * other types of pages. */ - if (PageReserved(p) || PageSlab(p)) + if (PageReserved(p) || PageSlab(p) || PageTable(p)) return true; if (!(PageLRU(hpage) || PageHuge(p))) return true; @@ -976,13 +1425,12 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, return true; if (PageKsm(p)) { - pr_err("Memory failure: %#lx: can't handle KSM pages.\n", pfn); + pr_err("%#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); + pr_err("%#lx: keeping poisoned page in swap cache\n", pfn); ttu |= TTU_IGNORE_HWPOISON; } @@ -994,13 +1442,12 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, */ mapping = page_mapping(hpage); if (!(flags & MF_MUST_KILL) && !PageDirty(hpage) && mapping && - mapping_cap_writeback_dirty(mapping)) { + mapping_can_writeback(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", + pr_info("%#lx: corrupted page was clean: dropped without side effects\n", pfn); } } @@ -1009,16 +1456,30 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long 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(hpage, &tokill, flags & MF_ACTION_REQUIRED); + + if (PageHuge(hpage) && !PageAnon(hpage)) { + /* + * For hugetlb pages 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_page_mapping_lock_write(hpage); + if (mapping) { + try_to_unmap(folio, ttu|TTU_RMAP_LOCKED); + i_mmap_unlock_write(mapping); + } else + pr_info("%#lx: could not lock mapping for mapped huge page\n", pfn); + } else { + try_to_unmap(folio, ttu); + } - unmap_success = try_to_unmap(hpage, ttu); + unmap_success = !page_mapped(hpage); if (!unmap_success) - pr_err("Memory failure: %#lx: failed to unmap page (mapcount=%d)\n", + pr_err("%#lx: failed to unmap page (mapcount=%d)\n", pfn, page_mapcount(hpage)); /* @@ -1026,7 +1487,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * shake_page() again to ensure that it's flushed. */ if (mlocked) - shake_page(hpage, 0); + shake_page(hpage); /* * Now that the dirty bit has been propagated to the @@ -1038,7 +1499,8 @@ 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); + forcekill = PageDirty(hpage) || (flags & MF_MUST_KILL) || + !unmap_success; kill_procs(&tokill, forcekill, !unmap_success, pfn, flags); return unmap_success; @@ -1067,89 +1529,58 @@ 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) +static int try_to_split_thp_page(struct page *page) { - 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(page); + unlock_page(page); - num_poisoned_pages_inc(); + if (unlikely(ret)) + 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 = (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, false, pfn, flags); } -static int memory_failure_dev_pagemap(unsigned long pfn, int flags, +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; + LIST_HEAD(to_kill); dax_entry_t cookie; + int rc = 0; + + /* + * Pages instantiated by device-dax (not filesystem-dax) + * may be compound pages. + */ + page = compound_head(page); /* * Prevent the inode from being freed while we are interrogating @@ -1160,19 +1591,24 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags, */ cookie = dax_lock_page(page); if (!cookie) - goto out; + return -EBUSY; if (hwpoison_filter(page)) { - rc = 0; + rc = -EOPNOTSUPP; goto unlock; } - if (pgmap->type == MEMORY_DEVICE_PRIVATE) { + switch (pgmap->type) { + case MEMORY_DEVICE_PRIVATE: + 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; } /* @@ -1188,25 +1624,326 @@ 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(page, &to_kill, true); - list_for_each_entry(tk, &tokill, nd) - if (tk->size_shift) - size = max(size, 1UL << tk->size_shift); - if (size) { + unmap_and_kill(&to_kill, pfn, page->mapping, page->index, flags); +unlock: + dax_unlock_page(page, 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; + + 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; + + SetPageHWPoison(page); + + collect_procs_fsdax(page, mapping, index, &to_kill); + unmap_and_kill(&to_kill, page_to_pfn(page), mapping, + index, mf_flags); +unlock: + 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 originated from ->private field of + * SUBPAGE_INDEX_HWPOISON-th tail page. + */ +struct raw_hwp_page { + struct llist_node node; + struct page *page; +}; + +static inline struct llist_head *raw_hwp_list_head(struct page *hpage) +{ + return (struct llist_head *)&page_private(hpage + SUBPAGE_INDEX_HWPOISON); +} + +static unsigned long __free_raw_hwp_pages(struct page *hpage, bool move_flag) +{ + struct llist_head *head; + struct llist_node *t, *tnode; + unsigned long count = 0; + + head = raw_hwp_list_head(hpage); + llist_for_each_safe(tnode, t, head->first) { + struct raw_hwp_page *p = container_of(tnode, struct raw_hwp_page, node); + + if (move_flag) + SetPageHWPoison(p->page); + kfree(p); + count++; + } + llist_del_all(head); + return count; +} + +static int hugetlb_set_page_hwpoison(struct page *hpage, struct page *page) +{ + struct llist_head *head; + struct raw_hwp_page *raw_hwp; + struct llist_node *t, *tnode; + int ret = TestSetPageHWPoison(hpage) ? -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 (HPageRawHwpUnreliable(hpage)) + return -EHWPOISON; + head = raw_hwp_list_head(hpage); + llist_for_each_safe(tnode, t, head->first) { + struct raw_hwp_page *p = container_of(tnode, struct raw_hwp_page, 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(); + } else { /* - * 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() + * Failed to save raw error info. We no longer trace all + * hwpoisoned subpages, and we need refuse to free/dissolve + * this hwpoisoned hugepage. */ - start = (page->index << PAGE_SHIFT) & ~(size - 1); - unmap_mapping_range(page->mapping, start, start + size, 0); + SetHPageRawHwpUnreliable(hpage); + /* + * Once HPageRawHwpUnreliable is set, raw_hwp_page is not + * used any more, so free it. + */ + __free_raw_hwp_pages(hpage, false); } - kill_procs(&tokill, flags & MF_MUST_KILL, !unmap_success, pfn, flags); - rc = 0; -unlock: - dax_unlock_page(page, cookie); + return ret; +} + +static unsigned long free_raw_hwp_pages(struct page *hpage, bool move_flag) +{ + /* + * HPageVmemmapOptimized hugepages can't be freed because struct + * pages for tail pages are required but they don't exist. + */ + if (move_flag && HPageVmemmapOptimized(hpage)) + return 0; + + /* + * HPageRawHwpUnreliable hugepages shouldn't be unpoisoned by + * definition. + */ + if (HPageRawHwpUnreliable(hpage)) + return 0; + + return __free_raw_hwp_pages(hpage, move_flag); +} + +void hugetlb_clear_page_hwpoison(struct page *hpage) +{ + if (HPageRawHwpUnreliable(hpage)) + return; + ClearPageHWPoison(hpage); + free_raw_hwp_pages(hpage, 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) +{ + struct page *page = pfn_to_page(pfn); + struct page *head = compound_head(page); + int ret = 2; /* fallback to normal page handling */ + bool count_increased = false; + + if (!PageHeadHuge(head)) + goto out; + + if (flags & MF_COUNT_INCREASED) { + ret = 1; + count_increased = true; + } else if (HPageFreed(head)) { + ret = 0; + } else if (HPageMigratable(head)) { + ret = get_page_unless_zero(head); + if (ret) + count_increased = true; + } else { + ret = -EBUSY; + if (!(flags & MF_NO_RETRY)) + goto out; + } + + if (hugetlb_set_page_hwpoison(head, page)) { + ret = -EHWPOISON; + goto out; + } + + return ret; +out: + if (count_increased) + put_page(head); + 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 page *head; + unsigned long page_flags; + + *hugetlb = 1; +retry: + res = get_huge_page_for_hwpoison(pfn, flags); + if (res == 2) { /* fallback to normal page handling */ + *hugetlb = 0; + return 0; + } else if (res == -EHWPOISON) { + pr_err("%#lx: already hardware poisoned\n", pfn); + if (flags & MF_ACTION_REQUIRED) { + head = compound_head(p); + res = kill_accessing_process(current, page_to_pfn(head), flags); + } + return res; + } else if (res == -EBUSY) { + if (!(flags & MF_NO_RETRY)) { + flags |= MF_NO_RETRY; + goto retry; + } + action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED); + return res; + } + + head = compound_head(p); + lock_page(head); + + if (hwpoison_filter(p)) { + hugetlb_clear_page_hwpoison(head); + unlock_page(head); + if (res == 1) + put_page(head); + return -EOPNOTSUPP; + } + + /* + * Handling free hugepage. The possible race with hugepage allocation + * or demotion can be prevented by PageHWPoison flag. + */ + if (res == 0) { + unlock_page(head); + if (__page_handle_poison(p) >= 0) { + page_ref_inc(p); + res = MF_RECOVERED; + } else { + res = MF_FAILED; + } + action_result(pfn, MF_MSG_FREE_HUGE, res); + return res == MF_RECOVERED ? 0 : -EBUSY; + } + + page_flags = head->flags; + + if (!hwpoison_user_mappings(p, pfn, flags, head)) { + action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED); + res = -EBUSY; + goto out; + } + + return identify_page_state(pfn, p, page_flags); +out: + unlock_page(head); + return res; +} + +#else +static inline int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb) +{ + return 0; +} + +static inline unsigned long free_raw_hwp_pages(struct page *hpage, bool flag) +{ + return 0; +} +#endif /* CONFIG_HUGETLB_PAGE */ + +static int memory_failure_dev_pagemap(unsigned long pfn, int flags, + struct dev_pagemap *pgmap) +{ + struct page *page = pfn_to_page(pfn); + int rc = -ENXIO; + + if (flags & MF_COUNT_INCREASED) + /* + * Drop the extra refcount in case we come from madvise(). + */ + put_page(page); + + /* 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); @@ -1214,6 +1951,8 @@ out: return rc; } +static DEFINE_MUTEX(mf_mutex); + /** * memory_failure - Handle memory failure of a page. * @pfn: Page Number of the corrupted page @@ -1230,47 +1969,69 @@ out: * * Must run in process context (e.g. a work queue) with interrupts * enabled and no spinlocks hold. + * + * Return: 0 for successfully handled the memory error, + * -EOPNOTSUPP for hwpoison_filter() filtered the error event, + * < 0(except -EOPNOTSUPP) on failure. */ int memory_failure(unsigned long pfn, int flags) { struct page *p; struct page *hpage; - struct page *orig_head; 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); + 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)) { pgmap = get_dev_pagemap(pfn, NULL); - if (pgmap) - return memory_failure_dev_pagemap(pfn, flags, - pgmap); + if (pgmap) { + res = memory_failure_dev_pagemap(pfn, flags, + pgmap); + goto unlock_mutex; + } } - pr_err("Memory failure: %#lx: memory outside kernel control\n", - pfn); - return -ENXIO; + pr_err("%#lx: memory outside kernel control\n", pfn); + res = -ENXIO; + goto unlock_mutex; } - if (PageHuge(p)) - return memory_failure_hugetlb(pfn, flags); +try_again: + res = try_memory_failure_hugetlb(pfn, flags, &hugetlb); + if (hugetlb) + goto unlock_mutex; + if (TestSetPageHWPoison(p)) { - pr_err("Memory failure: %#lx: already hardware poisoned\n", - pfn); - return 0; + pr_err("%#lx: already hardware poisoned\n", pfn); + res = -EHWPOISON; + if (flags & MF_ACTION_REQUIRED) + res = kill_accessing_process(current, pfn, flags); + if (flags & MF_COUNT_INCREASED) + put_page(p); + goto unlock_mutex; } - orig_head = hpage = compound_head(p); - num_poisoned_pages_inc(); + hpage = compound_head(p); /* * 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 @@ -1278,34 +2039,57 @@ 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; + } + action_result(pfn, MF_MSG_BUDDY, res); + res = res == MF_RECOVERED ? 0 : -EBUSY; + } else { + action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED); + res = -EBUSY; + } + goto unlock_mutex; + } else if (res < 0) { + action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED); + res = -EBUSY; + 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; + /* + * 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_INCREASE. 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. + */ + SetPageHasHWPoisoned(hpage); + if (try_to_split_thp_page(p) < 0) { + action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED); + res = -EBUSY; + goto unlock_mutex; } - unlock_page(p); VM_BUG_ON_PAGE(!page_count(p), p); - hpage = compound_head(p); } /* @@ -1316,26 +2100,28 @@ 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_page(p); lock_page(p); /* - * 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. + * However, the page could have changed compound pages due to + * race window. If this happens, we could try again to hopefully + * handle the page next round. */ - if (PageCompound(p) && compound_head(p) != orig_head) { + if (PageCompound(p)) { + if (retry) { + ClearPageHWPoison(p); + unlock_page(p); + put_page(p); + flags &= ~MF_COUNT_INCREASED; + retry = false; + goto try_again; + } action_result(pfn, MF_MSG_DIFFERENT_COMPOUND, MF_IGNORED); res = -EBUSY; - goto out; + goto unlock_page; } /* @@ -1345,30 +2131,22 @@ int memory_failure(unsigned long pfn, int flags) * 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. */ - if (PageHuge(p)) - page_flags = hpage->flags; - else - page_flags = p->flags; + page_flags = p->flags; - /* - * unpoison always clear PG_hwpoison inside page lock - */ - 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(); + ClearPageHWPoison(p); unlock_page(p); - put_hwpoison_page(p); - return 0; + put_page(p); + res = -EOPNOTSUPP; + goto unlock_mutex; } - if (!PageTransTail(p) && !PageLRU(p)) + /* + * __munlock_pagevec may clear a writeback page's LRU flag without + * page_lock. We need wait writeback completion for this page or it + * may trigger vfs BUG while evict inode. + */ + if (!PageLRU(p) && !PageWriteback(p)) goto identify_page_state; /* @@ -1379,15 +2157,12 @@ int memory_failure(unsigned long pfn, int flags) /* * 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)) { + if (!hwpoison_user_mappings(p, pfn, flags, p)) { action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED); res = -EBUSY; - goto out; + goto unlock_page; } /* @@ -1396,13 +2171,17 @@ int memory_failure(unsigned long pfn, int flags) if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) { action_result(pfn, MF_MSG_TRUNCATED_LRU, MF_IGNORED); res = -EBUSY; - goto out; + goto unlock_page; } identify_page_state: res = identify_page_state(pfn, p, page_flags); -out: + mutex_unlock(&mf_mutex); + return res; +unlock_page: unlock_page(p); +unlock_mutex: + mutex_unlock(&mf_mutex); return res; } EXPORT_SYMBOL_GPL(memory_failure); @@ -1454,7 +2233,7 @@ void memory_failure_queue(unsigned long pfn, int flags) if (kfifo_put(&mf_cpu->fifo, entry)) schedule_work_on(smp_processor_id(), &mf_cpu->work); else - pr_err("Memory failure: buffer overflow when queuing memory failure at %#lx\n", + pr_err("buffer overflow when queuing memory failure at %#lx\n", pfn); spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); put_cpu_var(memory_failure_cpu); @@ -1468,7 +2247,7 @@ 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); gotten = kfifo_get(&mf_cpu->fifo, &entry); @@ -1482,6 +2261,19 @@ static void memory_failure_work_func(struct work_struct *work) } } +/* + * Process memory_failure work queued on the specified CPU. + * Used to avoid return-to-userspace racing with the memory_failure workqueue. + */ +void memory_failure_queue_kick(int cpu) +{ + struct memory_failure_cpu *mf_cpu; + + mf_cpu = &per_cpu(memory_failure_cpu, cpu); + cancel_work_sync(&mf_cpu->work); + memory_failure_work_func(&mf_cpu->work); +} + static int __init memory_failure_init(void) { struct memory_failure_cpu *mf_cpu; @@ -1498,6 +2290,8 @@ static int __init memory_failure_init(void) } core_initcall(memory_failure_init); +#undef pr_fmt +#define pr_fmt(fmt) "" fmt #define unpoison_pr_info(fmt, pfn, rs) \ ({ \ if (__ratelimit(rs)) \ @@ -1520,7 +2314,9 @@ int unpoison_memory(unsigned long pfn) { struct page *page; struct page *p; + int ret = -EBUSY; int freeit = 0; + unsigned long count = 1; static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); @@ -1530,329 +2326,200 @@ int unpoison_memory(unsigned long pfn) p = pfn_to_page(pfn); page = compound_head(p); + mutex_lock(&mf_mutex); + + if (hw_memory_failure) { + unpoison_pr_info("Unpoison: Disabled after HW memory failure %#lx\n", + pfn, &unpoison_rs); + ret = -EOPNOTSUPP; + goto unlock_mutex; + } + if (!PageHWPoison(p)) { unpoison_pr_info("Unpoison: Page was already unpoisoned %#lx\n", pfn, &unpoison_rs); - return 0; + goto unlock_mutex; } if (page_count(page) > 1) { unpoison_pr_info("Unpoison: Someone grabs the hwpoison page %#lx\n", pfn, &unpoison_rs); - return 0; + goto unlock_mutex; } if (page_mapped(page)) { unpoison_pr_info("Unpoison: Someone maps the hwpoison page %#lx\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", 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 (PageSlab(page) || PageTable(page) || PageReserved(page)) + 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", - pfn, &unpoison_rs); - return 0; + ret = get_hwpoison_page(p, MF_UNPOISON); + if (!ret) { + if (PageHuge(p)) { + count = free_raw_hwp_pages(page, false); + if (count == 0) { + ret = -EBUSY; + goto unlock_mutex; + } + } + ret = TestClearPageHWPoison(page) ? 0 : -EBUSY; + } else if (ret < 0) { + if (ret == -EHWPOISON) { + ret = put_page_back_buddy(p) ? 0 : -EBUSY; + } else + unpoison_pr_info("Unpoison: failed to grab page %#lx\n", + pfn, &unpoison_rs); + } else { + if (PageHuge(p)) { + count = free_raw_hwp_pages(page, false); + if (count == 0) { + ret = -EBUSY; + put_page(page); + goto unlock_mutex; + } + } + freeit = !!TestClearPageHWPoison(p); + + put_page(page); + if (freeit) { + put_page(page); + ret = 0; + } } - 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)) { +unlock_mutex: + mutex_unlock(&mf_mutex); + if (!ret || freeit) { + num_poisoned_pages_sub(count); unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n", - pfn, &unpoison_rs); - num_poisoned_pages_dec(); - freeit = 1; + page_to_pfn(p), &unpoison_rs); } - unlock_page(page); - - put_hwpoison_page(page); - if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1)) - put_hwpoison_page(page); - - return 0; + return ret; } EXPORT_SYMBOL(unpoison_memory); -static struct page *new_page(struct page *p, unsigned long private) +static bool isolate_page(struct page *page, struct list_head *pagelist) { - int nid = page_to_nid(p); + bool isolated = false; - 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; - } else { - pr_info("%s: %#lx: unknown zero refcount page type %lx\n", - __func__, pfn, p->flags); - ret = -EIO; - } + if (PageHuge(page)) { + isolated = !isolate_hugetlb(page, pagelist); } else { - /* Not a free page */ - ret = 1; - } - return ret; -} + bool lru = !__PageMovable(page); -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); - - /* - * 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; + if (lru) + isolated = !isolate_lru_page(page); + else + isolated = !isolate_movable_page(page, + ISOLATE_UNEVICTABLE); + + if (isolated) { + list_add(&page->lru, pagelist); + if (lru) + inc_node_page_state(page, NR_ISOLATED_ANON + + page_is_file_lru(page)); } } - return ret; + + /* + * If we succeed to isolate the page, we grabbed another refcount on + * the page, so we can safely drop the one we got from get_any_pages(). + * If we failed to isolate the page, it means that we cannot go further + * and we will return an error, so drop the reference we got from + * get_any_pages() as well. + */ + put_page(page); + return isolated; } -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); + char const *msg_page[] = {"page", "hugepage"}; + bool huge = PageHuge(page); LIST_HEAD(pagelist); + struct migration_target_control mtc = { + .nid = NUMA_NO_NODE, + .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + }; - /* - * 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; - } - - 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. - */ - ret = dissolve_free_huge_page(page); - if (!ret) { - if (set_hwpoison_free_buddy_page(page)) - num_poisoned_pages_inc(); - else - ret = -EBUSY; + if (!huge && PageTransHuge(hpage)) { + if (try_to_split_thp_page(page)) { + pr_info("soft offline: %#lx: thp split failed\n", pfn); + return -EBUSY; } + hpage = 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); + if (!PageHuge(page)) + wait_on_page_writeback(page); if (PageHWPoison(page)) { unlock_page(page); - put_hwpoison_page(page); + put_page(page); pr_info("soft offline: %#lx page already poisoned\n", pfn); - return -EBUSY; + return 0; } - /* - * Try to invalidate first. This should work for - * non dirty unmapped page cache pages. - */ - ret = invalidate_inode_page(page); + + if (!PageHuge(page) && PageLRU(page) && !PageSwapCache(page)) + /* + * 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); + + if (ret) { pr_info("soft_offline: %#lx: invalidated\n", pfn); - SetPageHWPoison(page); - num_poisoned_pages_inc(); + page_handle_poison(page, false, true); 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); - /* - * After isolated lru page, the PageLRU will be cleared, - * so use !__PageMovable instead for LRU page's mapping - * cannot have PAGE_MAPPING_MOVABLE. - */ - 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 (isolate_page(hpage, &pagelist)) { + ret = migrate_pages(&pagelist, alloc_migration_target, NULL, + (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE, NULL); + if (!ret) { + bool release = !huge; + + if (!page_handle_poison(page, huge, release)) + ret = -EBUSY; + } else { if (!list_empty(&pagelist)) putback_movable_pages(&pagelist); - pr_info("soft offline: %#lx: migration failed %d, type %lx (%pGp)\n", - pfn, ret, page->flags, &page->flags); + pr_info("soft offline: %#lx: %s migration failed %ld, type %pGp\n", + pfn, msg_page[huge], ret, &page->flags); if (ret > 0) - ret = -EIO; + ret = -EBUSY; } } 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); + pr_info("soft offline: %#lx: %s isolation failed, page count %d, type %pGp\n", + pfn, msg_page[huge], page_count(page), &page->flags); + ret = -EBUSY; } return ret; } -static int soft_offline_in_use_page(struct page *page, int flags) +static void put_ref_page(struct page *page) { - int ret; - int mt; - struct page *hpage = compound_head(page); - - if (!PageHuge(page) && PageTransHuge(hpage)) { - lock_page(page); - if (!PageAnon(page) || unlikely(split_huge_page(page))) { - unlock_page(page); - if (!PageAnon(page)) - 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(page); - return -EBUSY; - } - unlock_page(page); - } - - /* - * 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. - */ - 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; -} - -static int soft_offline_free_page(struct page *page) -{ - int rc = dissolve_free_huge_page(page); - - if (!rc) { - if (set_hwpoison_free_buddy_page(page)) - num_poisoned_pages_inc(); - else - rc = -EBUSY; - } - return rc; + if (page) + put_page(page); } /** @@ -1860,7 +2527,9 @@ static int soft_offline_free_page(struct page *page) * @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 + * < 0 otherwise negated errno. * * Soft offline a page, by migration or invalidation, * without killing anything. This is for the case when @@ -1880,30 +2549,79 @@ static int soft_offline_free_page(struct page *page) int soft_offline_page(unsigned long pfn, int flags) { int ret; - struct page *page; + bool try_again = true; + struct page *page, *ref_page = NULL; + + WARN_ON_ONCE(!pfn_valid(pfn) && (flags & MF_COUNT_INCREASED)); if (!pfn_valid(pfn)) return -ENXIO; + if (flags & MF_COUNT_INCREASED) + ref_page = pfn_to_page(pfn); + /* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */ page = pfn_to_online_page(pfn); - if (!page) + if (!page) { + put_ref_page(ref_page); return -EIO; + } + + 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("%s: %#lx page already poisoned\n", __func__, pfn); + put_ref_page(ref_page); + 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) && try_again) { + try_again = false; + flags &= ~MF_COUNT_INCREASED; + goto retry; + } + } + + mutex_unlock(&mf_mutex); return ret; } + +void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) +{ + int i, total = 0; + + /* + * A further optimization is to have per section refcounted + * num_poisoned_pages. But that would need more space per memmap, so + * for now just do a quick global check to speed up this routine in the + * absence of bad pages. + */ + if (atomic_long_read(&num_poisoned_pages) == 0) + return; + + for (i = 0; i < nr_pages; i++) { + if (PageHWPoison(&memmap[i])) { + total++; + ClearPageHWPoison(&memmap[i]); + } + } + if (total) + num_poisoned_pages_sub(total); +} |