return -EIO;
}
+static int truncate_error_page(struct page *p, unsigned long pfn,
+ struct address_space *mapping)
+{
+ int ret = MF_FAILED;
+
+ if (mapping->a_ops->error_remove_page) {
+ int err = mapping->a_ops->error_remove_page(mapping, p);
+
+ if (err != 0) {
+ pr_info("Memory failure: %#lx: Failed to punch page: %d\n",
+ pfn, err);
+ } else if (page_has_private(p) &&
+ !try_to_release_page(p, GFP_NOIO)) {
+ pr_info("Memory failure: %#lx: failed to release buffers\n",
+ pfn);
+ } else {
+ ret = MF_RECOVERED;
+ }
+ } else {
+ /*
+ * If the file system doesn't support it just invalidate
+ * This fails on dirty or anything with private pages
+ */
+ if (invalidate_inode_page(p))
+ ret = MF_RECOVERED;
+ else
+ pr_info("Memory failure: %#lx: Failed to invalidate\n",
+ pfn);
+ }
+
+ return ret;
+}
+
/*
* Error hit kernel page.
* Do nothing, try to be lucky and not touch this instead. For a few cases we
*/
static int me_pagecache_clean(struct page *p, unsigned long pfn)
{
- int err;
- int ret = MF_FAILED;
struct address_space *mapping;
delete_from_lru_cache(p);
*
* Open: to take i_mutex or not for this? Right now we don't.
*/
- if (mapping->a_ops->error_remove_page) {
- err = mapping->a_ops->error_remove_page(mapping, p);
- if (err != 0) {
- pr_info("Memory failure: %#lx: Failed to punch page: %d\n",
- pfn, err);
- } else if (page_has_private(p) &&
- !try_to_release_page(p, GFP_NOIO)) {
- pr_info("Memory failure: %#lx: failed to release buffers\n",
- pfn);
- } else {
- ret = MF_RECOVERED;
- }
- } else {
- /*
- * If the file system doesn't support it just invalidate
- * This fails on dirty or anything with private pages
- */
- if (invalidate_inode_page(p))
- ret = MF_RECOVERED;
- else
- pr_info("Memory failure: %#lx: Failed to invalidate\n",
- pfn);
- }
- return ret;
+ return truncate_error_page(p, pfn, mapping);
}
/*
{
int res = 0;
struct page *hpage = compound_head(p);
+ struct address_space *mapping;
if (!PageHuge(hpage))
return MF_DELAYED;
- /*
- * We can safely recover from error on free or reserved (i.e.
- * not in-use) hugepage by dequeuing it from freelist.
- * To check whether a hugepage is in-use or not, we can't use
- * page->lru because it can be used in other hugepage operations,
- * such as __unmap_hugepage_range() and gather_surplus_pages().
- * So instead we use page_mapping() and PageAnon().
- */
- if (!(page_mapping(hpage) || PageAnon(hpage))) {
- res = dequeue_hwpoisoned_huge_page(hpage);
- if (!res)
- return MF_RECOVERED;
+ mapping = page_mapping(hpage);
+ if (mapping) {
+ res = truncate_error_page(hpage, pfn, mapping);
+ } 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.
+ */
+ if (PageAnon(hpage))
+ put_page(hpage);
+ dissolve_free_huge_page(p);
+ res = MF_RECOVERED;
+ lock_page(hpage);
}
- return MF_DELAYED;
+
+ return res;
}
/*
count = page_count(p) - 1;
if (ps->action == me_swapcache_dirty && result == MF_DELAYED)
count--;
- if (count != 0) {
+ 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;
return unmap_success;
}
+static int identify_page_state(unsigned long pfn, struct page *p,
+ unsigned long page_flags)
+{
+ struct page_state *ps;
+
+ /*
+ * The first check uses the current page flags which may not have any
+ * relevant information. The second check with the saved page flags is
+ * carried out only if the first check can't determine the page status.
+ */
+ for (ps = error_states;; ps++)
+ if ((p->flags & ps->mask) == ps->res)
+ break;
+
+ page_flags |= (p->flags & (1UL << PG_dirty));
+
+ if (!ps->mask)
+ for (ps = error_states;; ps++)
+ if ((page_flags & ps->mask) == ps->res)
+ break;
+ return page_action(ps, p, pfn);
+}
+
+static int memory_failure_hugetlb(unsigned long pfn, int trapno, int flags)
+{
+ struct page *p = pfn_to_page(pfn);
+ struct page *head = compound_head(p);
+ int res;
+ unsigned long page_flags;
+
+ if (TestSetPageHWPoison(head)) {
+ pr_err("Memory failure: %#lx: already hardware poisoned\n",
+ pfn);
+ return 0;
+ }
+
+ num_poisoned_pages_inc();
+
+ 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;
+ }
+
+ lock_page(head);
+ page_flags = head->flags;
+
+ 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;
+ }
+
+ if (!hwpoison_user_mappings(p, pfn, trapno, flags, &head)) {
+ action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
+ res = -EBUSY;
+ goto out;
+ }
+
+ res = identify_page_state(pfn, p, page_flags);
+out:
+ unlock_page(head);
+ return res;
+}
+
/**
* memory_failure - Handle memory failure of a page.
* @pfn: Page Number of the corrupted page
*/
int memory_failure(unsigned long pfn, int trapno, int flags)
{
- struct page_state *ps;
struct page *p;
struct page *hpage;
struct page *orig_head;
}
p = pfn_to_page(pfn);
- orig_head = hpage = compound_head(p);
-
- /* tmporary check code, to be updated in later patches */
- if (PageHuge(p)) {
- if (TestSetPageHWPoison(hpage)) {
- pr_err("Memory failure: %#lx: already hardware poisoned\n", pfn);
- return 0;
- }
- goto tmp;
- }
+ if (PageHuge(p))
+ return memory_failure_hugetlb(pfn, trapno, flags);
if (TestSetPageHWPoison(p)) {
pr_err("Memory failure: %#lx: already hardware poisoned\n",
pfn);
return 0;
}
-tmp:
+ orig_head = hpage = compound_head(p);
num_poisoned_pages_inc();
/*
* We need/can do nothing about count=0 pages.
* 1) it's a free page, and therefore in safe hand:
* prep_new_page() will be the gate keeper.
- * 2) it's a free hugepage, which is also safe:
- * an affected hugepage will be dequeued from hugepage freelist,
- * so there's no concern about reusing it ever after.
- * 3) it's part of a non-compound high order page.
+ * 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
* used and will be freed some time later.
if (is_free_buddy_page(p)) {
action_result(pfn, MF_MSG_BUDDY, MF_DELAYED);
return 0;
- } else if (PageHuge(hpage)) {
- /*
- * Check "filter hit" and "race with other subpage."
- */
- lock_page(hpage);
- if (PageHWPoison(hpage)) {
- if ((hwpoison_filter(p) && TestClearPageHWPoison(p))
- || (p != hpage && TestSetPageHWPoison(hpage))) {
- num_poisoned_pages_dec();
- unlock_page(hpage);
- return 0;
- }
- }
- res = dequeue_hwpoisoned_huge_page(hpage);
- action_result(pfn, MF_MSG_FREE_HUGE,
- res ? MF_IGNORED : MF_DELAYED);
- unlock_page(hpage);
- return res;
} else {
action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED);
return -EBUSY;
}
}
- if (!PageHuge(p) && PageTransHuge(hpage)) {
+ if (PageTransHuge(hpage)) {
lock_page(p);
if (!PageAnon(p) || unlikely(split_huge_page(p))) {
unlock_page(p);
return 0;
}
- lock_page(hpage);
+ lock_page(p);
/*
* The page could have changed compound pages during the locking.
if (!PageHWPoison(p)) {
pr_err("Memory failure: %#lx: just unpoisoned\n", pfn);
num_poisoned_pages_dec();
- unlock_page(hpage);
- put_hwpoison_page(hpage);
+ unlock_page(p);
+ put_hwpoison_page(p);
return 0;
}
if (hwpoison_filter(p)) {
if (TestClearPageHWPoison(p))
num_poisoned_pages_dec();
- unlock_page(hpage);
- put_hwpoison_page(hpage);
+ unlock_page(p);
+ put_hwpoison_page(p);
return 0;
}
- if (!PageHuge(p) && !PageTransTail(p) && !PageLRU(p))
+ if (!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, MF_MSG_POISONED_HUGE, MF_IGNORED);
- unlock_page(hpage);
- put_hwpoison_page(hpage);
- return 0;
- }
-
/*
* It's very difficult to mess with pages currently under IO
* and in many cases impossible, so we just avoid it here.
}
identify_page_state:
- res = -EBUSY;
- /*
- * The first check uses the current page flags which may not have any
- * relevant information. The second check with the saved page flagss is
- * carried out only if the first check can't determine the page status.
- */
- for (ps = error_states;; ps++)
- if ((p->flags & ps->mask) == ps->res)
- break;
-
- page_flags |= (p->flags & (1UL << PG_dirty));
-
- if (!ps->mask)
- for (ps = error_states;; ps++)
- if ((page_flags & ps->mask) == ps->res)
- break;
- res = page_action(ps, p, pfn);
+ res = identify_page_state(pfn, p, page_flags);
out:
- unlock_page(hpage);
+ unlock_page(p);
return res;
}
EXPORT_SYMBOL_GPL(memory_failure);
}
if (!get_hwpoison_page(p)) {
- /*
- * Since HWPoisoned hugepage should have non-zero refcount,
- * race between memory failure and unpoison seems to happen.
- * In such case unpoison fails and memory failure runs
- * to the end.
- */
- if (PageHuge(page)) {
- unpoison_pr_info("Unpoison: Memory failure is now running on free hugepage %#lx\n",
- pfn, &unpoison_rs);
- return 0;
- }
if (TestClearPageHWPoison(p))
num_poisoned_pages_dec();
unpoison_pr_info("Unpoison: Software-unpoisoned free page %#lx\n",
static struct page *new_page(struct page *p, unsigned long private, int **x)
{
int nid = page_to_nid(p);
- if (PageHuge(p)) {
- struct hstate *hstate = page_hstate(compound_head(p));
-
- if (hstate_is_gigantic(hstate))
- return alloc_huge_page_node(hstate, NUMA_NO_NODE);
- return alloc_huge_page_node(hstate, nid);
- } else {
- return __alloc_pages_node(nid, GFP_HIGHUSER_MOVABLE, 0);
- }
+ return new_page_nodemask(p, nid, &node_states[N_MEMORY]);
}
/*
if (!TestSetPageHWPoison(head)) {
num_poisoned_pages_inc();
if (PageHuge(head))
- dequeue_hwpoisoned_huge_page(head);
+ dissolve_free_huge_page(page);
}
}
projects / mirror_ubuntu-bionic-kernel.git / blobdiff