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 /mm | |
parent | e568df6b84ff05a22467503afc11bee7a6ba0700 (diff) | |
download | op-kernel-dev-c6dcf52c23d2d3fb5235cec42d7dd3f786b87d55.zip op-kernel-dev-c6dcf52c23d2d3fb5235cec42d7dd3f786b87d55.tar.gz |
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 'mm')
-rw-r--r-- | mm/truncate.c | 75 |
1 files changed, 61 insertions, 14 deletions
diff --git a/mm/truncate.c b/mm/truncate.c index fd97f1d..dd7b24e 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -24,20 +24,12 @@ #include <linux/rmap.h> #include "internal.h" -static void clear_exceptional_entry(struct address_space *mapping, - pgoff_t index, void *entry) +static void clear_shadow_entry(struct address_space *mapping, pgoff_t index, + void *entry) { struct radix_tree_node *node; void **slot; - /* Handled by shmem itself */ - if (shmem_mapping(mapping)) - return; - - if (dax_mapping(mapping)) { - dax_delete_mapping_entry(mapping, index); - return; - } spin_lock_irq(&mapping->tree_lock); /* * Regular page slots are stabilized by the page lock even @@ -55,6 +47,56 @@ unlock: spin_unlock_irq(&mapping->tree_lock); } +/* + * Unconditionally remove exceptional entry. Usually called from truncate path. + */ +static void truncate_exceptional_entry(struct address_space *mapping, + pgoff_t index, void *entry) +{ + /* Handled by shmem itself */ + if (shmem_mapping(mapping)) + return; + + if (dax_mapping(mapping)) { + dax_delete_mapping_entry(mapping, index); + return; + } + clear_shadow_entry(mapping, index, entry); +} + +/* + * Invalidate exceptional entry if easily possible. This handles exceptional + * entries for invalidate_inode_pages() so for DAX it evicts only unlocked and + * clean entries. + */ +static int invalidate_exceptional_entry(struct address_space *mapping, + pgoff_t index, void *entry) +{ + /* Handled by shmem itself */ + if (shmem_mapping(mapping)) + return 1; + if (dax_mapping(mapping)) + return dax_invalidate_mapping_entry(mapping, index); + clear_shadow_entry(mapping, index, entry); + return 1; +} + +/* + * Invalidate exceptional entry if clean. This handles exceptional entries for + * invalidate_inode_pages2() so for DAX it evicts only clean entries. + */ +static int invalidate_exceptional_entry2(struct address_space *mapping, + pgoff_t index, void *entry) +{ + /* Handled by shmem itself */ + if (shmem_mapping(mapping)) + return 1; + if (dax_mapping(mapping)) + return dax_invalidate_mapping_entry_sync(mapping, index); + clear_shadow_entry(mapping, index, entry); + return 1; +} + /** * do_invalidatepage - invalidate part or all of a page * @page: the page which is affected @@ -262,7 +304,8 @@ void truncate_inode_pages_range(struct address_space *mapping, break; if (radix_tree_exceptional_entry(page)) { - clear_exceptional_entry(mapping, index, page); + truncate_exceptional_entry(mapping, index, + page); continue; } @@ -351,7 +394,8 @@ void truncate_inode_pages_range(struct address_space *mapping, } if (radix_tree_exceptional_entry(page)) { - clear_exceptional_entry(mapping, index, page); + truncate_exceptional_entry(mapping, index, + page); continue; } @@ -470,7 +514,8 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, break; if (radix_tree_exceptional_entry(page)) { - clear_exceptional_entry(mapping, index, page); + invalidate_exceptional_entry(mapping, index, + page); continue; } @@ -592,7 +637,9 @@ int invalidate_inode_pages2_range(struct address_space *mapping, break; if (radix_tree_exceptional_entry(page)) { - clear_exceptional_entry(mapping, index, page); + if (!invalidate_exceptional_entry2(mapping, + index, page)) + ret = -EBUSY; continue; } |