diff options
author | Jan Kara <jack@suse.cz> | 2016-08-10 17:22:44 +0200 |
---|---|---|
committer | Dan Williams <dan.j.williams@intel.com> | 2016-12-26 20:29:24 -0800 |
commit | c6dcf52c23d2d3fb5235cec42d7dd3f786b87d55 (patch) | |
tree | 7e63a6c0225a769e679b194f54b5723e4cfba385 /fs/dax.c | |
parent | e568df6b84ff05a22467503afc11bee7a6ba0700 (diff) | |
download | talos-op-linux-c6dcf52c23d2d3fb5235cec42d7dd3f786b87d55.tar.gz talos-op-linux-c6dcf52c23d2d3fb5235cec42d7dd3f786b87d55.zip |
mm: Invalidate DAX radix tree entries only if appropriate
Currently invalidate_inode_pages2_range() and invalidate_mapping_pages()
just delete all exceptional radix tree entries they find. For DAX this
is not desirable as we track cache dirtiness in these entries and when
they are evicted, we may not flush caches although it is necessary. This
can for example manifest when we write to the same block both via mmap
and via write(2) (to different offsets) and fsync(2) then does not
properly flush CPU caches when modification via write(2) was the last
one.
Create appropriate DAX functions to handle invalidation of DAX entries
for invalidate_inode_pages2_range() and invalidate_mapping_pages() and
wire them up into the corresponding mm functions.
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Diffstat (limited to 'fs/dax.c')
-rw-r--r-- | fs/dax.c | 71 |
1 files changed, 61 insertions, 10 deletions
@@ -451,16 +451,37 @@ void dax_wake_mapping_entry_waiter(struct address_space *mapping, __wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key); } +static int __dax_invalidate_mapping_entry(struct address_space *mapping, + pgoff_t index, bool trunc) +{ + int ret = 0; + void *entry; + struct radix_tree_root *page_tree = &mapping->page_tree; + + spin_lock_irq(&mapping->tree_lock); + entry = get_unlocked_mapping_entry(mapping, index, NULL); + if (!entry || !radix_tree_exceptional_entry(entry)) + goto out; + if (!trunc && + (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) || + radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))) + goto out; + radix_tree_delete(page_tree, index); + mapping->nrexceptional--; + ret = 1; +out: + put_unlocked_mapping_entry(mapping, index, entry); + spin_unlock_irq(&mapping->tree_lock); + return ret; +} /* * Delete exceptional DAX entry at @index from @mapping. Wait for radix tree * entry to get unlocked before deleting it. */ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index) { - void *entry; + int ret = __dax_invalidate_mapping_entry(mapping, index, true); - spin_lock_irq(&mapping->tree_lock); - entry = get_unlocked_mapping_entry(mapping, index, NULL); /* * This gets called from truncate / punch_hole path. As such, the caller * must hold locks protecting against concurrent modifications of the @@ -468,16 +489,46 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index) * caller has seen exceptional entry for this index, we better find it * at that index as well... */ - if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry))) { - spin_unlock_irq(&mapping->tree_lock); - return 0; - } - radix_tree_delete(&mapping->page_tree, index); + WARN_ON_ONCE(!ret); + return ret; +} + +/* + * Invalidate exceptional DAX entry if easily possible. This handles DAX + * entries for invalidate_inode_pages() so we evict the entry only if we can + * do so without blocking. + */ +int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index) +{ + int ret = 0; + void *entry, **slot; + struct radix_tree_root *page_tree = &mapping->page_tree; + + spin_lock_irq(&mapping->tree_lock); + entry = __radix_tree_lookup(page_tree, index, NULL, &slot); + if (!entry || !radix_tree_exceptional_entry(entry) || + slot_locked(mapping, slot)) + goto out; + if (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) || + radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE)) + goto out; + radix_tree_delete(page_tree, index); mapping->nrexceptional--; + ret = 1; +out: spin_unlock_irq(&mapping->tree_lock); - dax_wake_mapping_entry_waiter(mapping, index, entry, true); + if (ret) + dax_wake_mapping_entry_waiter(mapping, index, entry, true); + return ret; +} - return 1; +/* + * Invalidate exceptional DAX entry if it is clean. + */ +int dax_invalidate_mapping_entry_sync(struct address_space *mapping, + pgoff_t index) +{ + return __dax_invalidate_mapping_entry(mapping, index, false); } /* |