* this code has to be extremely careful. Generally it tries to use
* normal locking rules, as in get the standard locks, even if that means
* the error handling takes potentially a long time.
+ *
+ * It can be very tempting to add handling for obscure cases here.
+ * In general any code for handling new cases should only be added iff:
+ * - You know how to test it.
+ * - You have a test that can be added to mce-test
+ * https://git.kernel.org/cgit/utils/cpu/mce/mce-test.git/
+ * - The case actually shows up as a frequent (top 10) page state in
+ * tools/vm/page-types when running a real workload.
*
* There are several operations here with exponential complexity because
* of unsuitable VM data structures. For example the operation to map back
* are rare we hope to get away with this. This avoids impacting the core
* VM.
*/
-
-/*
- * Notebook:
- * - hugetlb needs more code
- * - kcore/oldmem/vmcore/mem/kmem check for hwpoison pages
- * - pass bad pages to kdump next kernel
- */
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/page-flags.h>
#include <linux/memory_hotplug.h>
#include <linux/mm_inline.h>
#include <linux/kfifo.h>
+#include <linux/ratelimit.h>
#include "internal.h"
+#include "ras/ras_event.h"
int sysctl_memory_failure_early_kill __read_mostly = 0;
* can only guarantee that the page either belongs to the memcg tasks, or is
* a freed page.
*/
-#ifdef CONFIG_MEMCG_SWAP
+#ifdef CONFIG_MEMCG
u64 hwpoison_filter_memcg;
EXPORT_SYMBOL_GPL(hwpoison_filter_memcg);
static int hwpoison_filter_task(struct page *p)
{
- struct mem_cgroup *mem;
- struct cgroup_subsys_state *css;
- unsigned long ino;
-
if (!hwpoison_filter_memcg)
return 0;
- mem = try_get_mem_cgroup_from_page(p);
- if (!mem)
- return -EINVAL;
-
- css = mem_cgroup_css(mem);
- /* root_mem_cgroup has NULL dentries */
- if (!css->cgroup->dentry)
- return -EINVAL;
-
- ino = css->cgroup->dentry->d_inode->i_ino;
- css_put(css);
-
- if (ino != hwpoison_filter_memcg)
+ if (page_cgroup_ino(p) != hwpoison_filter_memcg)
return -EINVAL;
return 0;
#ifdef __ARCH_SI_TRAPNO
si.si_trapno = trapno;
#endif
- si.si_addr_lsb = compound_trans_order(compound_head(page)) + PAGE_SHIFT;
+ si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT;
- if ((flags & MF_ACTION_REQUIRED) && t == current) {
+ if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) {
si.si_code = BUS_MCEERR_AR;
- ret = force_sig_info(SIGBUS, &si, t);
+ ret = force_sig_info(SIGBUS, &si, current);
} else {
/*
* Don't use force here, it's convenient if the signal
lru_add_drain_all();
if (PageLRU(p))
return;
- drain_all_pages();
+ drain_all_pages(page_zone(p));
if (PageLRU(p) || is_free_buddy_page(p))
return;
}
/*
- * Only call shrink_slab here (which would also shrink other caches) if
- * access is not potentially fatal.
+ * Only call shrink_node_slabs here (which would also shrink
+ * other caches) if access is not potentially fatal.
*/
- if (access) {
- int nr;
- do {
- struct shrink_control shrink = {
- .gfp_mask = GFP_KERNEL,
- };
-
- nr = shrink_slab(&shrink, 1000, 1000);
- if (page_count(p) == 1)
- break;
- } while (nr > 10);
- }
+ if (access)
+ drop_slab_node(page_to_nid(p));
}
EXPORT_SYMBOL_GPL(shake_page);
}
}
-static int task_early_kill(struct task_struct *tsk)
+/*
+ * Find a dedicated thread which is supposed to handle SIGBUS(BUS_MCEERR_AO)
+ * on behalf of the thread group. Return task_struct of the (first found)
+ * dedicated thread if found, and return NULL otherwise.
+ *
+ * We already hold read_lock(&tasklist_lock) in the caller, so we don't
+ * have to call rcu_read_lock/unlock() in this function.
+ */
+static struct task_struct *find_early_kill_thread(struct task_struct *tsk)
{
+ struct task_struct *t;
+
+ for_each_thread(tsk, t)
+ if ((t->flags & PF_MCE_PROCESS) && (t->flags & PF_MCE_EARLY))
+ return t;
+ return NULL;
+}
+
+/*
+ * Determine whether a given process is "early kill" process which expects
+ * to be signaled when some page under the process is hwpoisoned.
+ * Return task_struct of the dedicated thread (main thread unless explicitly
+ * specified) if the process is "early kill," and otherwise returns NULL.
+ */
+static struct task_struct *task_early_kill(struct task_struct *tsk,
+ int force_early)
+{
+ struct task_struct *t;
if (!tsk->mm)
- return 0;
- if (tsk->flags & PF_MCE_PROCESS)
- return !!(tsk->flags & PF_MCE_EARLY);
- return sysctl_memory_failure_early_kill;
+ 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;
}
/*
* 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)
+ struct to_kill **tkc, int force_early)
{
struct vm_area_struct *vma;
struct task_struct *tsk;
if (av == NULL) /* Not actually mapped anymore */
return;
- pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+ pgoff = page_to_pgoff(page);
read_lock(&tasklist_lock);
for_each_process (tsk) {
struct anon_vma_chain *vmac;
+ struct task_struct *t = task_early_kill(tsk, force_early);
- if (!task_early_kill(tsk))
+ if (!t)
continue;
anon_vma_interval_tree_foreach(vmac, &av->rb_root,
pgoff, pgoff) {
vma = vmac->vma;
if (!page_mapped_in_vma(page, vma))
continue;
- if (vma->vm_mm == tsk->mm)
- add_to_kill(tsk, page, vma, to_kill, tkc);
+ if (vma->vm_mm == t->mm)
+ add_to_kill(t, page, vma, to_kill, tkc);
}
}
read_unlock(&tasklist_lock);
* 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)
+ struct to_kill **tkc, int force_early)
{
struct vm_area_struct *vma;
struct task_struct *tsk;
struct address_space *mapping = page->mapping;
- mutex_lock(&mapping->i_mmap_mutex);
+ i_mmap_lock_read(mapping);
read_lock(&tasklist_lock);
for_each_process(tsk) {
- pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+ pgoff_t pgoff = page_to_pgoff(page);
+ struct task_struct *t = task_early_kill(tsk, force_early);
- if (!task_early_kill(tsk))
+ if (!t)
continue;
-
vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff,
pgoff) {
/*
* Assume applications who requested early kill want
* to be informed of all such data corruptions.
*/
- if (vma->vm_mm == tsk->mm)
- add_to_kill(tsk, page, vma, to_kill, tkc);
+ if (vma->vm_mm == t->mm)
+ add_to_kill(t, page, vma, to_kill, tkc);
}
}
read_unlock(&tasklist_lock);
- mutex_unlock(&mapping->i_mmap_mutex);
+ i_mmap_unlock_read(mapping);
}
/*
* First preallocate one tokill structure outside the spin locks,
* so that we can kill at least one process reasonably reliable.
*/
-static void collect_procs(struct page *page, struct list_head *tokill)
+static void collect_procs(struct page *page, struct list_head *tokill,
+ int force_early)
{
struct to_kill *tk;
if (!tk)
return;
if (PageAnon(page))
- collect_procs_anon(page, tokill, &tk);
+ collect_procs_anon(page, tokill, &tk, force_early);
else
- collect_procs_file(page, tokill, &tk);
+ collect_procs_file(page, tokill, &tk, force_early);
kfree(tk);
}
-/*
- * Error handlers for various types of pages.
- */
-
-enum outcome {
- IGNORED, /* Error: cannot be handled */
- FAILED, /* Error: handling failed */
- DELAYED, /* Will be handled later */
- RECOVERED, /* Successfully recovered */
+static const char *action_name[] = {
+ [MF_IGNORED] = "Ignored",
+ [MF_FAILED] = "Failed",
+ [MF_DELAYED] = "Delayed",
+ [MF_RECOVERED] = "Recovered",
};
-static const char *action_name[] = {
- [IGNORED] = "Ignored",
- [FAILED] = "Failed",
- [DELAYED] = "Delayed",
- [RECOVERED] = "Recovered",
+static const char * const action_page_types[] = {
+ [MF_MSG_KERNEL] = "reserved kernel page",
+ [MF_MSG_KERNEL_HIGH_ORDER] = "high-order kernel page",
+ [MF_MSG_SLAB] = "kernel slab page",
+ [MF_MSG_DIFFERENT_COMPOUND] = "different compound page after locking",
+ [MF_MSG_POISONED_HUGE] = "huge page already hardware poisoned",
+ [MF_MSG_HUGE] = "huge page",
+ [MF_MSG_FREE_HUGE] = "free huge page",
+ [MF_MSG_UNMAP_FAILED] = "unmapping failed page",
+ [MF_MSG_DIRTY_SWAPCACHE] = "dirty swapcache page",
+ [MF_MSG_CLEAN_SWAPCACHE] = "clean swapcache page",
+ [MF_MSG_DIRTY_MLOCKED_LRU] = "dirty mlocked LRU page",
+ [MF_MSG_CLEAN_MLOCKED_LRU] = "clean mlocked LRU page",
+ [MF_MSG_DIRTY_UNEVICTABLE_LRU] = "dirty unevictable LRU page",
+ [MF_MSG_CLEAN_UNEVICTABLE_LRU] = "clean unevictable LRU page",
+ [MF_MSG_DIRTY_LRU] = "dirty LRU page",
+ [MF_MSG_CLEAN_LRU] = "clean LRU page",
+ [MF_MSG_TRUNCATED_LRU] = "already truncated LRU page",
+ [MF_MSG_BUDDY] = "free buddy page",
+ [MF_MSG_BUDDY_2ND] = "free buddy page (2nd try)",
+ [MF_MSG_UNKNOWN] = "unknown page",
};
/*
*/
static int me_kernel(struct page *p, unsigned long pfn)
{
- return IGNORED;
+ return MF_IGNORED;
}
/*
static int me_unknown(struct page *p, unsigned long pfn)
{
printk(KERN_ERR "MCE %#lx: Unknown page state\n", pfn);
- return FAILED;
+ return MF_FAILED;
}
/*
static int me_pagecache_clean(struct page *p, unsigned long pfn)
{
int err;
- int ret = FAILED;
+ int ret = MF_FAILED;
struct address_space *mapping;
delete_from_lru_cache(p);
* should be the one m_f() holds.
*/
if (PageAnon(p))
- return RECOVERED;
+ return MF_RECOVERED;
/*
* Now truncate the page in the page cache. This is really
/*
* Page has been teared down in the meanwhile
*/
- return FAILED;
+ return MF_FAILED;
}
/*
!try_to_release_page(p, GFP_NOIO)) {
pr_info("MCE %#lx: failed to release buffers\n", pfn);
} else {
- ret = RECOVERED;
+ ret = MF_RECOVERED;
}
} else {
/*
* This fails on dirty or anything with private pages
*/
if (invalidate_inode_page(p))
- ret = RECOVERED;
+ ret = MF_RECOVERED;
else
printk(KERN_INFO "MCE %#lx: Failed to invalidate\n",
pfn);
}
/*
- * Dirty cache page page
+ * Dirty pagecache page
* Issues: when the error hit a hole page the error is not properly
* propagated.
*/
ClearPageUptodate(p);
if (!delete_from_lru_cache(p))
- return DELAYED;
+ return MF_DELAYED;
else
- return FAILED;
+ return MF_FAILED;
}
static int me_swapcache_clean(struct page *p, unsigned long pfn)
delete_from_swap_cache(p);
if (!delete_from_lru_cache(p))
- return RECOVERED;
+ return MF_RECOVERED;
else
- return FAILED;
+ return MF_FAILED;
}
/*
{
int res = 0;
struct page *hpage = compound_head(p);
+
+ if (!PageHuge(hpage))
+ return MF_DELAYED;
+
/*
* We can safely recover from error on free or reserved (i.e.
* not in-use) hugepage by dequeuing it from freelist.
if (!(page_mapping(hpage) || PageAnon(hpage))) {
res = dequeue_hwpoisoned_huge_page(hpage);
if (!res)
- return RECOVERED;
+ return MF_RECOVERED;
}
- return DELAYED;
+ return MF_DELAYED;
}
/*
#define lru (1UL << PG_lru)
#define swapbacked (1UL << PG_swapbacked)
#define head (1UL << PG_head)
-#define tail (1UL << PG_tail)
-#define compound (1UL << PG_compound)
#define slab (1UL << PG_slab)
#define reserved (1UL << PG_reserved)
static struct page_state {
unsigned long mask;
unsigned long res;
- char *msg;
+ enum mf_action_page_type type;
int (*action)(struct page *p, unsigned long pfn);
} error_states[] = {
- { reserved, reserved, "reserved kernel", me_kernel },
+ { 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.
* currently unused objects without touching them. But just
* treat it as standard kernel for now.
*/
- { slab, slab, "kernel slab", me_kernel },
+ { slab, slab, MF_MSG_SLAB, me_kernel },
-#ifdef CONFIG_PAGEFLAGS_EXTENDED
- { head, head, "huge", me_huge_page },
- { tail, tail, "huge", me_huge_page },
-#else
- { compound, compound, "huge", me_huge_page },
-#endif
+ { head, head, MF_MSG_HUGE, me_huge_page },
- { sc|dirty, sc|dirty, "dirty swapcache", me_swapcache_dirty },
- { sc|dirty, sc, "clean swapcache", me_swapcache_clean },
+ { sc|dirty, sc|dirty, MF_MSG_DIRTY_SWAPCACHE, me_swapcache_dirty },
+ { sc|dirty, sc, MF_MSG_CLEAN_SWAPCACHE, me_swapcache_clean },
- { mlock|dirty, mlock|dirty, "dirty mlocked LRU", me_pagecache_dirty },
- { mlock|dirty, mlock, "clean mlocked LRU", me_pagecache_clean },
+ { mlock|dirty, mlock|dirty, MF_MSG_DIRTY_MLOCKED_LRU, me_pagecache_dirty },
+ { mlock|dirty, mlock, MF_MSG_CLEAN_MLOCKED_LRU, me_pagecache_clean },
- { unevict|dirty, unevict|dirty, "dirty unevictable LRU", me_pagecache_dirty },
- { unevict|dirty, unevict, "clean unevictable LRU", me_pagecache_clean },
+ { unevict|dirty, unevict|dirty, MF_MSG_DIRTY_UNEVICTABLE_LRU, me_pagecache_dirty },
+ { unevict|dirty, unevict, MF_MSG_CLEAN_UNEVICTABLE_LRU, me_pagecache_clean },
- { lru|dirty, lru|dirty, "dirty LRU", me_pagecache_dirty },
- { lru|dirty, lru, "clean LRU", me_pagecache_clean },
+ { lru|dirty, lru|dirty, MF_MSG_DIRTY_LRU, me_pagecache_dirty },
+ { lru|dirty, lru, MF_MSG_CLEAN_LRU, me_pagecache_clean },
/*
* Catchall entry: must be at end.
*/
- { 0, 0, "unknown page state", me_unknown },
+ { 0, 0, MF_MSG_UNKNOWN, me_unknown },
};
#undef dirty
* "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, char *msg, int result)
+static void action_result(unsigned long pfn, enum mf_action_page_type type,
+ enum mf_result result)
{
- pr_err("MCE %#lx: %s page recovery: %s\n",
- pfn, msg, action_name[result]);
+ trace_memory_failure_event(pfn, type, result);
+
+ pr_err("MCE %#lx: recovery action for %s: %s\n",
+ pfn, action_page_types[type], action_name[result]);
}
static int page_action(struct page_state *ps, struct page *p,
int count;
result = ps->action(p, pfn);
- action_result(pfn, ps->msg, result);
count = page_count(p) - 1;
- if (ps->action == me_swapcache_dirty && result == DELAYED)
+ if (ps->action == me_swapcache_dirty && result == MF_DELAYED)
count--;
if (count != 0) {
printk(KERN_ERR
- "MCE %#lx: %s page still referenced by %d users\n",
- pfn, ps->msg, count);
- result = FAILED;
+ "MCE %#lx: %s still referenced by %d users\n",
+ pfn, action_page_types[ps->type], count);
+ result = MF_FAILED;
}
+ action_result(pfn, ps->type, result);
/* Could do more checks here if page looks ok */
/*
* Could adjust zone counters here to correct for the missing page.
*/
- return (result == RECOVERED || result == DELAYED) ? 0 : -EBUSY;
+ 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.)
+ */
+int get_hwpoison_page(struct page *page)
+{
+ struct page *head = compound_head(page);
+
+ if (PageHuge(head))
+ return get_page_unless_zero(head);
+
+ /*
+ * Thp tail page has special refcounting rule (refcount of tail pages
+ * is stored in ->_mapcount,) so we can't call get_page_unless_zero()
+ * directly for tail pages.
+ */
+ if (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("MCE: %#lx: non anonymous thp\n",
+ page_to_pfn(page));
+ return 0;
+ }
+
+ if (get_page_unless_zero(head)) {
+ if (PageTail(page))
+ get_page(page);
+ return 1;
+ } else {
+ return 0;
+ }
+ }
+
+ return get_page_unless_zero(page);
+}
+EXPORT_SYMBOL_GPL(get_hwpoison_page);
+
+/**
+ * put_hwpoison_page() - Put refcount for memory error handling:
+ * @page: raw error page (hit by memory error)
+ */
+void put_hwpoison_page(struct page *page)
+{
+ struct page *head = compound_head(page);
+
+ if (PageHuge(head)) {
+ put_page(head);
+ return;
+ }
+
+ if (PageTransHuge(head))
+ if (page != head)
+ put_page(head);
+
+ put_page(page);
+}
+EXPORT_SYMBOL_GPL(put_hwpoison_page);
+
/*
* Do all that is necessary to remove user space mappings. Unmap
* the pages and send SIGBUS to the processes if the data was dirty.
*/
static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
- int trapno, int flags)
+ int trapno, int flags, struct page **hpagep)
{
enum ttu_flags ttu = TTU_UNMAP | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS;
struct address_space *mapping;
LIST_HEAD(tokill);
int ret;
int kill = 1, forcekill;
- struct page *hpage = compound_head(p);
- struct page *ppage;
+ struct page *hpage = *hpagep;
+ /*
+ * Here we are interested only in user-mapped pages, so skip any
+ * other types of pages.
+ */
if (PageReserved(p) || PageSlab(p))
return SWAP_SUCCESS;
+ if (!(PageLRU(hpage) || PageHuge(p)))
+ return SWAP_SUCCESS;
/*
* This check implies we don't kill processes if their pages
if (!page_mapped(hpage))
return SWAP_SUCCESS;
- if (PageKsm(p))
+ if (PageKsm(p)) {
+ pr_err("MCE %#lx: can't handle KSM pages.\n", pfn);
return SWAP_FAIL;
+ }
if (PageSwapCache(p)) {
printk(KERN_ERR
}
}
- /*
- * ppage: poisoned page
- * if p is regular page(4k page)
- * ppage == real poisoned page;
- * else p is hugetlb or THP, ppage == head page.
- */
- ppage = hpage;
-
- if (PageTransHuge(hpage)) {
- /*
- * Verify that this isn't a hugetlbfs head page, the check for
- * PageAnon is just for avoid tripping a split_huge_page
- * internal debug check, as split_huge_page refuses to deal with
- * anything that isn't an anon page. PageAnon can't go away fro
- * under us because we hold a refcount on the hpage, without a
- * refcount on the hpage. split_huge_page can't be safely called
- * in the first place, having a refcount on the tail isn't
- * enough * to be safe.
- */
- if (!PageHuge(hpage) && PageAnon(hpage)) {
- if (unlikely(split_huge_page(hpage))) {
- /*
- * FIXME: if splitting THP is failed, it is
- * better to stop the following operation rather
- * than causing panic by unmapping. System might
- * survive if the page is freed later.
- */
- printk(KERN_INFO
- "MCE %#lx: failed to split THP\n", pfn);
-
- BUG_ON(!PageHWPoison(p));
- return SWAP_FAIL;
- }
- /* THP is split, so ppage should be the real poisoned page. */
- ppage = p;
- }
- }
-
/*
* First collect all the processes that have the page
* mapped in dirty form. This has to be done before try_to_unmap,
* there's nothing that can be done.
*/
if (kill)
- collect_procs(ppage, &tokill);
+ collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED);
- if (hpage != ppage)
- lock_page(ppage);
-
- ret = try_to_unmap(ppage, ttu);
+ ret = try_to_unmap(hpage, ttu);
if (ret != SWAP_SUCCESS)
printk(KERN_ERR "MCE %#lx: failed to unmap page (mapcount=%d)\n",
- pfn, page_mapcount(ppage));
-
- if (hpage != ppage)
- unlock_page(ppage);
+ pfn, page_mapcount(hpage));
/*
* Now that the dirty bit has been propagated to the
* use a more force-full uncatchable kill to prevent
* any accesses to the poisoned memory.
*/
- forcekill = PageDirty(ppage) || (flags & MF_MUST_KILL);
+ forcekill = PageDirty(hpage) || (flags & MF_MUST_KILL);
kill_procs(&tokill, forcekill, trapno,
ret != SWAP_SUCCESS, p, pfn, flags);
static void set_page_hwpoison_huge_page(struct page *hpage)
{
int i;
- int nr_pages = 1 << compound_trans_order(hpage);
+ int nr_pages = 1 << compound_order(hpage);
for (i = 0; i < nr_pages; i++)
SetPageHWPoison(hpage + i);
}
static void clear_page_hwpoison_huge_page(struct page *hpage)
{
int i;
- int nr_pages = 1 << compound_trans_order(hpage);
+ int nr_pages = 1 << compound_order(hpage);
for (i = 0; i < nr_pages; i++)
ClearPageHWPoison(hpage + i);
}
struct page_state *ps;
struct page *p;
struct page *hpage;
+ struct page *orig_head;
int res;
unsigned int nr_pages;
unsigned long page_flags;
}
p = pfn_to_page(pfn);
- hpage = compound_head(p);
+ orig_head = hpage = compound_head(p);
if (TestSetPageHWPoison(p)) {
printk(KERN_ERR "MCE %#lx: already hardware poisoned\n", pfn);
return 0;
nr_pages = 1 << compound_order(hpage);
else /* normal page or thp */
nr_pages = 1;
- atomic_long_add(nr_pages, &num_poisoned_pages);
+ num_poisoned_pages_add(nr_pages);
/*
* We need/can do nothing about count=0 pages.
* In fact it's dangerous to directly bump up page count from 0,
* that may make page_freeze_refs()/page_unfreeze_refs() mismatch.
*/
- if (!(flags & MF_COUNT_INCREASED) &&
- !get_page_unless_zero(hpage)) {
+ if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p)) {
if (is_free_buddy_page(p)) {
- action_result(pfn, "free buddy", DELAYED);
+ action_result(pfn, MF_MSG_BUDDY, MF_DELAYED);
return 0;
} else if (PageHuge(hpage)) {
/*
- * Check "just unpoisoned", "filter hit", and
- * "race with other subpage."
+ * Check "filter hit" and "race with other subpage."
*/
lock_page(hpage);
- if (!PageHWPoison(hpage)
- || (hwpoison_filter(p) && TestClearPageHWPoison(p))
- || (p != hpage && TestSetPageHWPoison(hpage))) {
- atomic_long_sub(nr_pages, &num_poisoned_pages);
- return 0;
+ if (PageHWPoison(hpage)) {
+ if ((hwpoison_filter(p) && TestClearPageHWPoison(p))
+ || (p != hpage && TestSetPageHWPoison(hpage))) {
+ num_poisoned_pages_sub(nr_pages);
+ unlock_page(hpage);
+ return 0;
+ }
}
set_page_hwpoison_huge_page(hpage);
res = dequeue_hwpoisoned_huge_page(hpage);
- action_result(pfn, "free huge",
- res ? IGNORED : DELAYED);
+ action_result(pfn, MF_MSG_FREE_HUGE,
+ res ? MF_IGNORED : MF_DELAYED);
unlock_page(hpage);
return res;
} else {
- action_result(pfn, "high order kernel", IGNORED);
+ action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED);
+ return -EBUSY;
+ }
+ }
+
+ if (!PageHuge(p) && PageTransHuge(hpage)) {
+ if (!PageAnon(hpage) || unlikely(split_huge_page(hpage))) {
+ if (!PageAnon(hpage))
+ pr_err("MCE: %#lx: non anonymous thp\n", pfn);
+ else
+ pr_err("MCE: %#lx: thp split failed\n", pfn);
+ if (TestClearPageHWPoison(p))
+ num_poisoned_pages_sub(nr_pages);
+ put_hwpoison_page(p);
return -EBUSY;
}
+ VM_BUG_ON_PAGE(!page_count(p), p);
+ hpage = compound_head(p);
}
/*
* The check (unnecessarily) ignores LRU pages being isolated and
* walked by the page reclaim code, however that's not a big loss.
*/
- if (!PageHuge(p) && !PageTransTail(p)) {
+ if (!PageHuge(p)) {
if (!PageLRU(p))
shake_page(p, 0);
if (!PageLRU(p)) {
* shake_page could have turned it free.
*/
if (is_free_buddy_page(p)) {
- action_result(pfn, "free buddy, 2nd try",
- DELAYED);
+ 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;
}
- action_result(pfn, "non LRU", IGNORED);
- put_page(p);
- return -EBUSY;
}
}
+ lock_page(hpage);
+
/*
- * Lock the page and wait for writeback to finish.
- * It's very difficult to mess with pages currently under IO
- * and in many cases impossible, so we just avoid it here.
+ * The page could have changed compound pages during the locking.
+ * If this happens just bail out.
*/
- lock_page(hpage);
+ if (PageCompound(p) && compound_head(p) != orig_head) {
+ action_result(pfn, MF_MSG_DIFFERENT_COMPOUND, MF_IGNORED);
+ res = -EBUSY;
+ goto out;
+ }
/*
* We use page flags to determine what action should be taken, but
*/
if (!PageHWPoison(p)) {
printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn);
- res = 0;
- goto out;
+ num_poisoned_pages_sub(nr_pages);
+ unlock_page(hpage);
+ put_hwpoison_page(hpage);
+ return 0;
}
if (hwpoison_filter(p)) {
if (TestClearPageHWPoison(p))
- atomic_long_sub(nr_pages, &num_poisoned_pages);
+ num_poisoned_pages_sub(nr_pages);
unlock_page(hpage);
- put_page(hpage);
+ put_hwpoison_page(hpage);
return 0;
}
+ if (!PageHuge(p) && !PageTransTail(p) && !PageLRU(p))
+ goto identify_page_state;
+
/*
* For error on the tail page, we should set PG_hwpoison
* on the head page to show that the hugepage is hwpoisoned
*/
if (PageHuge(p) && PageTail(p) && TestSetPageHWPoison(hpage)) {
- action_result(pfn, "hugepage already hardware poisoned",
- IGNORED);
+ action_result(pfn, MF_MSG_POISONED_HUGE, MF_IGNORED);
unlock_page(hpage);
- put_page(hpage);
+ put_hwpoison_page(hpage);
return 0;
}
/*
if (PageHuge(p))
set_page_hwpoison_huge_page(hpage);
+ /*
+ * 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);
/*
* 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.
*/
- if (hwpoison_user_mappings(p, pfn, trapno, flags) != SWAP_SUCCESS) {
- printk(KERN_ERR "MCE %#lx: cannot unmap page, give up\n", pfn);
+ if (hwpoison_user_mappings(p, pfn, trapno, flags, &hpage)
+ != SWAP_SUCCESS) {
+ action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
res = -EBUSY;
goto out;
}
* Torn down by someone else?
*/
if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) {
- action_result(pfn, "already truncated LRU", IGNORED);
+ action_result(pfn, MF_MSG_TRUNCATED_LRU, MF_IGNORED);
res = -EBUSY;
goto out;
}
+identify_page_state:
res = -EBUSY;
/*
* The first check uses the current page flags which may not have any
for (ps = error_states;; ps++)
if ((p->flags & ps->mask) == ps->res)
break;
+
+ page_flags |= (p->flags & (1UL << PG_dirty));
+
if (!ps->mask)
for (ps = error_states;; ps++)
if ((page_flags & ps->mask) == ps->res)
mf_cpu = &get_cpu_var(memory_failure_cpu);
spin_lock_irqsave(&mf_cpu->lock, proc_flags);
- if (kfifo_put(&mf_cpu->fifo, &entry))
+ 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 0x%#lx\n",
+ pr_err("Memory failure: buffer overflow when queuing memory failure at %#lx\n",
pfn);
spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
put_cpu_var(memory_failure_cpu);
unsigned long proc_flags;
int gotten;
- mf_cpu = &__get_cpu_var(memory_failure_cpu);
+ mf_cpu = this_cpu_ptr(&memory_failure_cpu);
for (;;) {
spin_lock_irqsave(&mf_cpu->lock, proc_flags);
gotten = kfifo_get(&mf_cpu->fifo, &entry);
spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
if (!gotten)
break;
- memory_failure(entry.pfn, entry.trapno, entry.flags);
+ if (entry.flags & MF_SOFT_OFFLINE)
+ soft_offline_page(pfn_to_page(entry.pfn), entry.flags);
+ else
+ memory_failure(entry.pfn, entry.trapno, entry.flags);
}
}
}
core_initcall(memory_failure_init);
+#define unpoison_pr_info(fmt, pfn, rs) \
+({ \
+ if (__ratelimit(rs)) \
+ pr_info(fmt, pfn); \
+})
+
/**
* unpoison_memory - Unpoison a previously poisoned page
* @pfn: Page number of the to be unpoisoned page
struct page *p;
int freeit = 0;
unsigned int nr_pages;
+ static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
+ DEFAULT_RATELIMIT_BURST);
if (!pfn_valid(pfn))
return -ENXIO;
page = compound_head(p);
if (!PageHWPoison(p)) {
- pr_info("MCE: Page was already unpoisoned %#lx\n", pfn);
+ unpoison_pr_info("MCE: Page was already unpoisoned %#lx\n",
+ pfn, &unpoison_rs);
+ return 0;
+ }
+
+ if (page_count(page) > 1) {
+ unpoison_pr_info("MCE: Someone grabs the hwpoison page %#lx\n",
+ pfn, &unpoison_rs);
+ return 0;
+ }
+
+ if (page_mapped(page)) {
+ unpoison_pr_info("MCE: Someone maps the hwpoison page %#lx\n",
+ pfn, &unpoison_rs);
return 0;
}
- nr_pages = 1 << compound_trans_order(page);
+ if (page_mapping(page)) {
+ unpoison_pr_info("MCE: the hwpoison page has non-NULL mapping %#lx\n",
+ pfn, &unpoison_rs);
+ return 0;
+ }
- if (!get_page_unless_zero(page)) {
+ /*
+ * 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("MCE: Memory failure is now running on %#lx\n",
+ pfn, &unpoison_rs);
+ return 0;
+ }
+
+ nr_pages = 1 << compound_order(page);
+
+ if (!get_hwpoison_page(p)) {
/*
* Since HWPoisoned hugepage should have non-zero refcount,
* race between memory failure and unpoison seems to happen.
* to the end.
*/
if (PageHuge(page)) {
- pr_info("MCE: Memory failure is now running on free hugepage %#lx\n", pfn);
+ unpoison_pr_info("MCE: Memory failure is now running on free hugepage %#lx\n",
+ pfn, &unpoison_rs);
return 0;
}
if (TestClearPageHWPoison(p))
- atomic_long_sub(nr_pages, &num_poisoned_pages);
- pr_info("MCE: Software-unpoisoned free page %#lx\n", pfn);
+ num_poisoned_pages_dec();
+ unpoison_pr_info("MCE: Software-unpoisoned free page %#lx\n",
+ pfn, &unpoison_rs);
return 0;
}
* the free buddy page pool.
*/
if (TestClearPageHWPoison(page)) {
- pr_info("MCE: Software-unpoisoned page %#lx\n", pfn);
- atomic_long_sub(nr_pages, &num_poisoned_pages);
+ unpoison_pr_info("MCE: Software-unpoisoned page %#lx\n",
+ pfn, &unpoison_rs);
+ num_poisoned_pages_sub(nr_pages);
freeit = 1;
if (PageHuge(page))
clear_page_hwpoison_huge_page(page);
}
unlock_page(page);
- put_page(page);
- if (freeit)
- put_page(page);
+ put_hwpoison_page(page);
+ if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1))
+ put_hwpoison_page(page);
return 0;
}
return alloc_huge_page_node(page_hstate(compound_head(p)),
nid);
else
- return alloc_pages_exact_node(nid, GFP_HIGHUSER_MOVABLE, 0);
+ return __alloc_pages_node(nid, GFP_HIGHUSER_MOVABLE, 0);
}
/*
if (flags & MF_COUNT_INCREASED)
return 1;
- /*
- * The lock_memory_hotplug prevents a race with memory hotplug.
- * This is a big hammer, a better would be nicer.
- */
- lock_memory_hotplug();
-
- /*
- * Isolate the page, so that it doesn't get reallocated if it
- * was free.
- */
- set_migratetype_isolate(p, true);
/*
* When the target page is a free hugepage, just remove it
* from free hugepage list.
*/
- if (!get_page_unless_zero(compound_head(p))) {
+ if (!get_hwpoison_page(p)) {
if (PageHuge(p)) {
pr_info("%s: %#lx free huge page\n", __func__, pfn);
ret = 0;
/* Not a free page */
ret = 1;
}
- unset_migratetype_isolate(p, MIGRATE_MOVABLE);
- unlock_memory_hotplug();
return ret;
}
/*
* Try to free it.
*/
- put_page(page);
+ put_hwpoison_page(page);
shake_page(page, 1);
/*
* Did it turn free?
*/
ret = __get_any_page(page, pfn, 0);
- if (!PageLRU(page)) {
+ 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\n",
pfn, page->flags);
return -EIO;
int ret;
unsigned long pfn = page_to_pfn(page);
struct page *hpage = compound_head(page);
+ LIST_HEAD(pagelist);
/*
* This double-check of PageHWPoison is to avoid the race with
lock_page(hpage);
if (PageHWPoison(hpage)) {
unlock_page(hpage);
- put_page(hpage);
+ put_hwpoison_page(hpage);
pr_info("soft offline: %#lx hugepage already poisoned\n", pfn);
return -EBUSY;
}
unlock_page(hpage);
- /* Keep page count to indicate a given hugepage is isolated. */
- ret = migrate_huge_page(hpage, new_page, MPOL_MF_MOVE_ALL,
- MIGRATE_SYNC);
- put_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: migration failed %d, type %lx\n",
pfn, ret, page->flags);
+ /*
+ * We know that soft_offline_huge_page() tries to migrate
+ * only one hugepage pointed to by hpage, so we need not
+ * run through the pagelist here.
+ */
+ putback_active_hugepage(hpage);
+ if (ret > 0)
+ ret = -EIO;
} else {
- set_page_hwpoison_huge_page(hpage);
- dequeue_hwpoisoned_huge_page(hpage);
- atomic_long_add(1 << compound_trans_order(hpage),
- &num_poisoned_pages);
- }
- /* keep elevated page count for bad page */
- return ret;
-}
-
-static int __soft_offline_page(struct page *page, int flags);
-
-/**
- * soft_offline_page - Soft offline a page.
- * @page: page to offline
- * @flags: flags. Same as memory_failure().
- *
- * Returns 0 on success, otherwise negated errno.
- *
- * Soft offline a page, by migration or invalidation,
- * without killing anything. This is for the case when
- * a page is not corrupted yet (so it's still valid to access),
- * but has had a number of corrected errors and is better taken
- * out.
- *
- * The actual policy on when to do that is maintained by
- * user space.
- *
- * This should never impact any application or cause data loss,
- * however it might take some time.
- *
- * 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 ret;
- unsigned long pfn = page_to_pfn(page);
- struct page *hpage = compound_trans_head(page);
-
- if (PageHWPoison(page)) {
- pr_info("soft offline: %#lx page already poisoned\n", pfn);
- return -EBUSY;
- }
- if (!PageHuge(page) && PageTransHuge(hpage)) {
- if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) {
- pr_info("soft offline: %#lx: failed to split THP\n",
- pfn);
- return -EBUSY;
- }
- }
-
- ret = get_any_page(page, pfn, flags);
- if (ret < 0)
- return ret;
- if (ret) { /* for in-use pages */
- if (PageHuge(page))
- ret = soft_offline_huge_page(page, flags);
- else
- ret = __soft_offline_page(page, flags);
- } else { /* for free pages */
+ /* overcommit hugetlb page will be freed to buddy */
if (PageHuge(page)) {
set_page_hwpoison_huge_page(hpage);
dequeue_hwpoisoned_huge_page(hpage);
- atomic_long_add(1 << compound_trans_order(hpage),
- &num_poisoned_pages);
+ num_poisoned_pages_add(1 << compound_order(hpage));
} else {
SetPageHWPoison(page);
- atomic_long_inc(&num_poisoned_pages);
+ num_poisoned_pages_inc();
}
}
- /* keep elevated page count for bad page */
return ret;
}
wait_on_page_writeback(page);
if (PageHWPoison(page)) {
unlock_page(page);
- put_page(page);
+ put_hwpoison_page(page);
pr_info("soft offline: %#lx page already poisoned\n", pfn);
return -EBUSY;
}
* would need to fix isolation locking first.
*/
if (ret == 1) {
- put_page(page);
+ put_hwpoison_page(page);
pr_info("soft_offline: %#lx: invalidated\n", pfn);
SetPageHWPoison(page);
- atomic_long_inc(&num_poisoned_pages);
+ num_poisoned_pages_inc();
return 0;
}
* Drop page reference which is came from get_any_page()
* successful isolate_lru_page() already took another one.
*/
- put_page(page);
+ put_hwpoison_page(page);
if (!ret) {
LIST_HEAD(pagelist);
inc_zone_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
list_add(&page->lru, &pagelist);
- ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
+ ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
MIGRATE_SYNC, MR_MEMORY_FAILURE);
if (ret) {
- putback_lru_pages(&pagelist);
+ if (!list_empty(&pagelist)) {
+ list_del(&page->lru);
+ dec_zone_page_state(page, NR_ISOLATED_ANON +
+ page_is_file_cache(page));
+ putback_lru_page(page);
+ }
+
pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
pfn, ret, page->flags);
if (ret > 0)
ret = -EIO;
- } else {
- SetPageHWPoison(page);
- atomic_long_inc(&num_poisoned_pages);
}
} else {
pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n",
}
return ret;
}
+
+/**
+ * soft_offline_page - Soft offline a page.
+ * @page: page to offline
+ * @flags: flags. Same as memory_failure().
+ *
+ * Returns 0 on success, otherwise negated errno.
+ *
+ * Soft offline a page, by migration or invalidation,
+ * without killing anything. This is for the case when
+ * a page is not corrupted yet (so it's still valid to access),
+ * but has had a number of corrected errors and is better taken
+ * out.
+ *
+ * The actual policy on when to do that is maintained by
+ * user space.
+ *
+ * This should never impact any application or cause data loss,
+ * however it might take some time.
+ *
+ * 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 ret;
+ unsigned long pfn = page_to_pfn(page);
+ struct page *hpage = compound_head(page);
+
+ if (PageHWPoison(page)) {
+ pr_info("soft offline: %#lx page already poisoned\n", pfn);
+ if (flags & MF_COUNT_INCREASED)
+ put_hwpoison_page(page);
+ return -EBUSY;
+ }
+ if (!PageHuge(page) && PageTransHuge(hpage)) {
+ if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) {
+ pr_info("soft offline: %#lx: failed to split THP\n",
+ pfn);
+ if (flags & MF_COUNT_INCREASED)
+ put_hwpoison_page(page);
+ return -EBUSY;
+ }
+ }
+
+ get_online_mems();
+
+ ret = get_any_page(page, pfn, flags);
+ put_online_mems();
+ if (ret > 0) { /* for in-use pages */
+ if (PageHuge(page))
+ ret = soft_offline_huge_page(page, flags);
+ else
+ ret = __soft_offline_page(page, flags);
+ } else if (ret == 0) { /* for free pages */
+ if (PageHuge(page)) {
+ set_page_hwpoison_huge_page(hpage);
+ if (!dequeue_hwpoisoned_huge_page(hpage))
+ num_poisoned_pages_add(1 << compound_order(hpage));
+ } else {
+ if (!TestSetPageHWPoison(page))
+ num_poisoned_pages_inc();
+ }
+ }
+ return ret;
+}