The patch titled
Subject: mm: protect set_page_dirty() from ongoing truncation
has been removed from the -mm tree. Its filename was
mm-protect-set_page_dirty-from-ongoing-truncation.patch
This patch was dropped because it was merged into mainline or a subsystem tree
------------------------------------------------------
From: Johannes Weiner <[email protected]>
Subject: mm: protect set_page_dirty() from ongoing truncation
Tejun, while reviewing the code, spotted the following race condition
between the dirtying and truncation of a page:
__set_page_dirty_nobuffers() __delete_from_page_cache()
if (TestSetPageDirty(page))
page->mapping = NULL
if (PageDirty())
dec_zone_page_state(page, NR_FILE_DIRTY);
dec_bdi_stat(mapping->backing_dev_info,
BDI_RECLAIMABLE);
if (page->mapping)
account_page_dirtied(page)
__inc_zone_page_state(page, NR_FILE_DIRTY);
__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
which results in an imbalance of NR_FILE_DIRTY and BDI_RECLAIMABLE.
Dirtiers usually lock out truncation, either by holding the page lock
directly, or in case of zap_pte_range(), by pinning the mapcount with the
page table lock held. The notable exception to this rule, though, is
do_wp_page(), for which this race exists. However, do_wp_page() already
waits for a locked page to unlock before setting the dirty bit, in order
to prevent a race where clear_page_dirty() misses the page bit in the
presence of dirty ptes. Upgrade that wait to a fully locked
set_page_dirty() to also cover the situation explained above.
Afterwards, the code in set_page_dirty() dealing with a truncation race is
no longer needed. Remove it.
Reported-by: Tejun Heo <[email protected]>
Signed-off-by: Johannes Weiner <[email protected]>
Acked-by: Kirill A. Shutemov <[email protected]>
Reviewed-by: Jan Kara <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
---
include/linux/writeback.h | 1
mm/memory.c | 27 ++++++++++++++--------
mm/page-writeback.c | 43 ++++++++++--------------------------
3 files changed, 29 insertions(+), 42 deletions(-)
diff -puN
include/linux/writeback.h~mm-protect-set_page_dirty-from-ongoing-truncation
include/linux/writeback.h
---
a/include/linux/writeback.h~mm-protect-set_page_dirty-from-ongoing-truncation
+++ a/include/linux/writeback.h
@@ -177,7 +177,6 @@ int write_cache_pages(struct address_spa
struct writeback_control *wbc, writepage_t writepage,
void *data);
int do_writepages(struct address_space *mapping, struct writeback_control
*wbc);
-void set_page_dirty_balance(struct page *page);
void writeback_set_ratelimit(void);
void tag_pages_for_writeback(struct address_space *mapping,
pgoff_t start, pgoff_t end);
diff -puN mm/memory.c~mm-protect-set_page_dirty-from-ongoing-truncation
mm/memory.c
--- a/mm/memory.c~mm-protect-set_page_dirty-from-ongoing-truncation
+++ a/mm/memory.c
@@ -2137,17 +2137,24 @@ reuse:
if (!dirty_page)
return ret;
- /*
- * Yes, Virginia, this is actually required to prevent a race
- * with clear_page_dirty_for_io() from clearing the page dirty
- * bit after it clear all dirty ptes, but before a racing
- * do_wp_page installs a dirty pte.
- *
- * do_shared_fault is protected similarly.
- */
if (!page_mkwrite) {
- wait_on_page_locked(dirty_page);
- set_page_dirty_balance(dirty_page);
+ struct address_space *mapping;
+ int dirtied;
+
+ lock_page(dirty_page);
+ dirtied = set_page_dirty(dirty_page);
+ VM_BUG_ON_PAGE(PageAnon(dirty_page), dirty_page);
+ mapping = dirty_page->mapping;
+ unlock_page(dirty_page);
+
+ if (dirtied && mapping) {
+ /*
+ * Some device drivers do not set page.mapping
+ * but still dirty their pages
+ */
+ balance_dirty_pages_ratelimited(mapping);
+ }
+
/* file_update_time outside page_lock */
if (vma->vm_file)
file_update_time(vma->vm_file);
diff -puN mm/page-writeback.c~mm-protect-set_page_dirty-from-ongoing-truncation
mm/page-writeback.c
--- a/mm/page-writeback.c~mm-protect-set_page_dirty-from-ongoing-truncation
+++ a/mm/page-writeback.c
@@ -1541,16 +1541,6 @@ pause:
bdi_start_background_writeback(bdi);
}
-void set_page_dirty_balance(struct page *page)
-{
- if (set_page_dirty(page)) {
- struct address_space *mapping = page_mapping(page);
-
- if (mapping)
- balance_dirty_pages_ratelimited(mapping);
- }
-}
-
static DEFINE_PER_CPU(int, bdp_ratelimits);
/*
@@ -2123,32 +2113,25 @@ EXPORT_SYMBOL(account_page_dirtied);
* page dirty in that case, but not all the buffers. This is a "bottom-up"
* dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying.
*
- * Most callers have locked the page, which pins the address_space in memory.
- * But zap_pte_range() does not lock the page, however in that case the
- * mapping is pinned by the vma's ->vm_file reference.
- *
- * We take care to handle the case where the page was truncated from the
- * mapping by re-checking page_mapping() inside tree_lock.
+ * The caller must ensure this doesn't race with truncation. Most will simply
+ * hold the page lock, but e.g. zap_pte_range() calls with the page mapped and
+ * the pte lock held, which also locks out truncation.
*/
int __set_page_dirty_nobuffers(struct page *page)
{
if (!TestSetPageDirty(page)) {
struct address_space *mapping = page_mapping(page);
- struct address_space *mapping2;
unsigned long flags;
if (!mapping)
return 1;
spin_lock_irqsave(&mapping->tree_lock, flags);
- mapping2 = page_mapping(page);
- if (mapping2) { /* Race with truncate? */
- BUG_ON(mapping2 != mapping);
- WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
- account_page_dirtied(page, mapping);
- radix_tree_tag_set(&mapping->page_tree,
- page_index(page), PAGECACHE_TAG_DIRTY);
- }
+ BUG_ON(page_mapping(page) != mapping);
+ WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
+ account_page_dirtied(page, mapping);
+ radix_tree_tag_set(&mapping->page_tree, page_index(page),
+ PAGECACHE_TAG_DIRTY);
spin_unlock_irqrestore(&mapping->tree_lock, flags);
if (mapping->host) {
/* !PageAnon && !swapper_space */
@@ -2305,12 +2288,10 @@ int clear_page_dirty_for_io(struct page
/*
* We carefully synchronise fault handlers against
* installing a dirty pte and marking the page dirty
- * at this point. We do this by having them hold the
- * page lock at some point after installing their
- * pte, but before marking the page dirty.
- * Pages are always locked coming in here, so we get
- * the desired exclusion. See mm/memory.c:do_wp_page()
- * for more comments.
+ * at this point. We do this by having them hold the
+ * page lock while dirtying the page, and pages are
+ * always locked coming in here, so we get the desired
+ * exclusion.
*/
if (TestClearPageDirty(page)) {
dec_zone_page_state(page, NR_FILE_DIRTY);
_
Patches currently in -mm which might be from [email protected] are
mm-page_alloc-embed-oom-killing-naturally-into-allocation-slowpath.patch
mm-memory-remove-vm_file-check-on-shared-writable-vmas.patch
mm-memory-merge-shared-writable-dirtying-branches-in-do_wp_page.patch
mm-page_alloc-place-zone_id-check-before-vm_bug_on_page-check.patch
memcg-zap-__memcg_chargeuncharge_slab.patch
memcg-zap-memcg_name-argument-of-memcg_create_kmem_cache.patch
memcg-zap-memcg_slab_caches-and-memcg_slab_mutex.patch
mm-add-fields-for-compound-destructor-and-order-into-struct-page.patch
swap-remove-unused-mem_cgroup_uncharge_swapcache-declaration.patch
mm-memcontrol-track-move_lock-state-internally.patch
mm-memcontrol-track-move_lock-state-internally-fix.patch
mm-page_allocc-__alloc_pages_nodemask-dont-alter-arg-gfp_mask.patch
mm-vmscan-wake-up-all-pfmemalloc-throttled-processes-at-once.patch
mm-hugetlb-reduce-arch-dependent-code-around-follow_huge_.patch
mm-hugetlb-pmd_huge-returns-true-for-non-present-hugepage.patch
mm-hugetlb-take-page-table-lock-in-follow_huge_pmd.patch
mm-hugetlb-fix-getting-refcount-0-page-in-hugetlb_fault.patch
mm-hugetlb-add-migration-hwpoisoned-entry-check-in-hugetlb_change_protection.patch
mm-hugetlb-add-migration-entry-check-in-__unmap_hugepage_range.patch
mm-hugetlb-fix-suboptimal-migration-hwpoisoned-entry-check.patch
mm-hugetlb-cleanup-and-rename-is_hugetlb_entry_migrationhwpoisoned.patch
mm-set-page-pfmemalloc-in-prep_new_page.patch
mm-page_alloc-reduce-number-of-alloc_pages-functions-parameters.patch
mm-reduce-try_to_compact_pages-parameters.patch
mm-microoptimize-zonelist-operations.patch
list_lru-introduce-list_lru_shrink_countwalk.patch
fs-consolidate-nrfree_cached_objects-args-in-shrink_control.patch
vmscan-per-memory-cgroup-slab-shrinkers.patch
memcg-rename-some-cache-id-related-variables.patch
memcg-add-rwsem-to-synchronize-against-memcg_caches-arrays-relocation.patch
list_lru-get-rid-of-active_nodes.patch
list_lru-organize-all-list_lrus-to-list.patch
list_lru-introduce-per-memcg-lists.patch
fs-make-shrinker-memcg-aware.patch
vmscan-force-scan-offline-memory-cgroups.patch
fs-proc-task_mmu-show-page-size-in-proc-pid-numa_maps.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
