summaryrefslogtreecommitdiff
path: root/mm/memory-failure.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-09-03 20:08:28 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2021-09-03 20:08:28 +0300
commit14726903c835101cd8d0a703b609305094350d61 (patch)
tree5cdcf5d2f06ca14be76efd33a4de0e3b28a70de0 /mm/memory-failure.c
parenta9c9a6f741cdaa2fa9ba24a790db8d07295761e3 (diff)
parentd5fffc5aff269717a035baa087630adca612a6c4 (diff)
downloadlinux-14726903c835101cd8d0a703b609305094350d61.tar.xz
Merge branch 'akpm' (patches from Andrew)
Merge misc updates from Andrew Morton: "173 patches. Subsystems affected by this series: ia64, ocfs2, block, and mm (debug, pagecache, gup, swap, shmem, memcg, selftests, pagemap, mremap, bootmem, sparsemem, vmalloc, kasan, pagealloc, memory-failure, hugetlb, userfaultfd, vmscan, compaction, mempolicy, memblock, oom-kill, migration, ksm, percpu, vmstat, and madvise)" * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (173 commits) mm/madvise: add MADV_WILLNEED to process_madvise() mm/vmstat: remove unneeded return value mm/vmstat: simplify the array size calculation mm/vmstat: correct some wrong comments mm/percpu,c: remove obsolete comments of pcpu_chunk_populated() selftests: vm: add COW time test for KSM pages selftests: vm: add KSM merging time test mm: KSM: fix data type selftests: vm: add KSM merging across nodes test selftests: vm: add KSM zero page merging test selftests: vm: add KSM unmerge test selftests: vm: add KSM merge test mm/migrate: correct kernel-doc notation mm: wire up syscall process_mrelease mm: introduce process_mrelease system call memblock: make memblock_find_in_range method private mm/mempolicy.c: use in_task() in mempolicy_slab_node() mm/mempolicy: unify the create() func for bind/interleave/prefer-many policies mm/mempolicy: advertise new MPOL_PREFERRED_MANY mm/hugetlb: add support for mempolicy MPOL_PREFERRED_MANY ...
Diffstat (limited to 'mm/memory-failure.c')
-rw-r--r--mm/memory-failure.c51
1 files changed, 24 insertions, 27 deletions
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index e1f87cf13235..54879c339024 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -68,7 +68,7 @@ atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
static bool __page_handle_poison(struct page *page)
{
- bool ret;
+ int ret;
zone_pcp_disable(page_zone(page));
ret = dissolve_free_huge_page(page);
@@ -76,7 +76,7 @@ static bool __page_handle_poison(struct page *page)
ret = take_page_off_buddy(page);
zone_pcp_enable(page_zone(page));
- return ret;
+ return ret > 0;
}
static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, bool release)
@@ -282,9 +282,9 @@ static int kill_proc(struct to_kill *tk, unsigned long pfn, int flags)
/*
* Unknown page type encountered. Try to check whether it can turn PageLRU by
- * lru_add_drain_all, or a free page by reclaiming slabs when possible.
+ * lru_add_drain_all.
*/
-void shake_page(struct page *p, int access)
+void shake_page(struct page *p)
{
if (PageHuge(p))
return;
@@ -296,11 +296,9 @@ void shake_page(struct page *p, int access)
}
/*
- * 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);
@@ -391,8 +389,8 @@ 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.
*/
@@ -632,7 +630,7 @@ static int hwpoison_pte_range(pmd_t *pmdp, unsigned long addr,
{
struct hwp_walk *hwp = (struct hwp_walk *)walk->private;
int ret = 0;
- pte_t *ptep;
+ pte_t *ptep, *mapped_pte;
spinlock_t *ptl;
ptl = pmd_trans_huge_lock(pmdp, walk->vma);
@@ -645,14 +643,15 @@ static int hwpoison_pte_range(pmd_t *pmdp, unsigned long addr,
if (pmd_trans_unstable(pmdp))
goto out;
- ptep = pte_offset_map_lock(walk->vma->vm_mm, pmdp, addr, &ptl);
+ 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(ptep - 1, ptl);
+ pte_unmap_unlock(mapped_pte, ptl);
out:
cond_resched();
return ret;
@@ -1204,7 +1203,7 @@ try_again:
* page, retry.
*/
if (pass++ < 3) {
- shake_page(p, 1);
+ shake_page(p);
goto try_again;
}
ret = -EIO;
@@ -1221,7 +1220,7 @@ try_again:
*/
if (pass++ < 3) {
put_page(p);
- shake_page(p, 1);
+ shake_page(p);
count_increased = false;
goto try_again;
}
@@ -1229,6 +1228,9 @@ try_again:
ret = -EIO;
}
out:
+ if (ret == -EIO)
+ dump_page(p, "hwpoison: unhandlable page");
+
return ret;
}
@@ -1270,14 +1272,13 @@ static int get_hwpoison_page(struct page *p, unsigned long flags)
* 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_SYNC;
struct address_space *mapping;
LIST_HEAD(tokill);
bool unmap_success;
int kill = 1, forcekill;
- struct page *hpage = *hpagep;
bool mlocked = PageMlocked(hpage);
/*
@@ -1369,7 +1370,7 @@ 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
@@ -1502,7 +1503,7 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags)
goto out;
}
- if (!hwpoison_user_mappings(p, pfn, flags, &head)) {
+ if (!hwpoison_user_mappings(p, pfn, flags, head)) {
action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
res = -EBUSY;
goto out;
@@ -1518,7 +1519,6 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
struct dev_pagemap *pgmap)
{
struct page *page = pfn_to_page(pfn);
- const bool unmap_success = true;
unsigned long size = 0;
struct to_kill *tk;
LIST_HEAD(tokill);
@@ -1590,7 +1590,7 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
start = (page->index << PAGE_SHIFT) & ~(size - 1);
unmap_mapping_range(page->mapping, start, size, 0);
}
- kill_procs(&tokill, flags & MF_MUST_KILL, !unmap_success, pfn, flags);
+ kill_procs(&tokill, flags & MF_MUST_KILL, false, pfn, flags);
rc = 0;
unlock:
dax_unlock_page(page, cookie);
@@ -1724,7 +1724,7 @@ try_again:
* 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(p);
lock_page(p);
@@ -1783,7 +1783,7 @@ try_again:
* Now take care of user space mappings.
* Abort on fail: __delete_from_page_cache() assumes unmapped page.
*/
- if (!hwpoison_user_mappings(p, pfn, flags, &p)) {
+ if (!hwpoison_user_mappings(p, pfn, flags, p)) {
action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
res = -EBUSY;
goto unlock_page;
@@ -2099,7 +2099,7 @@ static int __soft_offline_page(struct page *page)
if (isolate_page(hpage, &pagelist)) {
ret = migrate_pages(&pagelist, alloc_migration_target, NULL,
- (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE);
+ (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE, NULL);
if (!ret) {
bool release = !huge;
@@ -2208,9 +2208,6 @@ retry:
try_again = false;
goto retry;
}
- } else if (ret == -EIO) {
- pr_info("%s: %#lx: unknown page type: %lx (%pGp)\n",
- __func__, pfn, page->flags, &page->flags);
}
return ret;