summaryrefslogtreecommitdiffstats
path: root/fs/ext4
diff options
context:
space:
mode:
authorDave Chinner <dchinner@redhat.com>2015-06-04 09:18:18 +1000
committerDave Chinner <david@fromorbit.com>2015-06-04 09:18:18 +1000
commite842f2903908934187af7232fb5b21da527d1757 (patch)
tree5fe6e2da05d58519d0f9360cf5116662a766906a /fs/ext4
parentec56b1f1fdc69599963574ce94cc5693d535dd64 (diff)
downloadlinux-stable-e842f2903908934187af7232fb5b21da527d1757.tar.gz
linux-stable-e842f2903908934187af7232fb5b21da527d1757.tar.bz2
linux-stable-e842f2903908934187af7232fb5b21da527d1757.zip
dax: don't abuse get_block mapping for endio callbacks
dax_fault() currently relies on the get_block callback to attach an io completion callback to the mapping buffer head so that it can run unwritten extent conversion after zeroing allocated blocks. Instead of this hack, pass the conversion callback directly into dax_fault() similar to the get_block callback. When the filesystem allocates unwritten extents, it will set the buffer_unwritten() flag, and hence the dax_fault code can call the completion function in the contexts where it is necessary without overloading the mapping buffer head. Note: The changes to ext4 to use this interface are suspect at best. In fact, the way ext4 did this end_io assignment in the first place looks suspect because it only set a completion callback when there wasn't already some other write() call taking place on the same inode. The ext4 end_io code looks rather intricate and fragile with all it's reference counting and passing to different contexts for modification via inode private pointers that aren't protected by locks... Signed-off-by: Dave Chinner <dchinner@redhat.com> Acked-by: Jan Kara <jack@suse.cz> Signed-off-by: Dave Chinner <david@fromorbit.com>
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/file.c16
-rw-r--r--fs/ext4/inode.c21
2 files changed, 21 insertions, 16 deletions
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 0613c256c344..f713cfcc43a2 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -192,15 +192,27 @@ out:
}
#ifdef CONFIG_FS_DAX
+static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate)
+{
+ struct inode *inode = bh->b_assoc_map->host;
+ /* XXX: breaks on 32-bit > 16GB. Is that even supported? */
+ loff_t offset = (loff_t)(uintptr_t)bh->b_private << inode->i_blkbits;
+ int err;
+ if (!uptodate)
+ return;
+ WARN_ON(!buffer_unwritten(bh));
+ err = ext4_convert_unwritten_extents(NULL, inode, offset, bh->b_size);
+}
+
static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
- return dax_fault(vma, vmf, ext4_get_block);
+ return dax_fault(vma, vmf, ext4_get_block, ext4_end_io_unwritten);
/* Is this the right get_block? */
}
static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
- return dax_mkwrite(vma, vmf, ext4_get_block);
+ return dax_mkwrite(vma, vmf, ext4_get_block, ext4_end_io_unwritten);
}
static const struct vm_operations_struct ext4_dax_vm_ops = {
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 55b187c3bac1..7c38ed3494cb 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -656,18 +656,6 @@ has_zeroout:
return retval;
}
-static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate)
-{
- struct inode *inode = bh->b_assoc_map->host;
- /* XXX: breaks on 32-bit > 16GB. Is that even supported? */
- loff_t offset = (loff_t)(uintptr_t)bh->b_private << inode->i_blkbits;
- int err;
- if (!uptodate)
- return;
- WARN_ON(!buffer_unwritten(bh));
- err = ext4_convert_unwritten_extents(NULL, inode, offset, bh->b_size);
-}
-
/* Maximum number of blocks we map for direct IO at once. */
#define DIO_MAX_BLOCKS 4096
@@ -705,10 +693,15 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
map_bh(bh, inode->i_sb, map.m_pblk);
bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
- if (IS_DAX(inode) && buffer_unwritten(bh) && !io_end) {
+ if (IS_DAX(inode) && buffer_unwritten(bh)) {
+ /*
+ * dgc: I suspect unwritten conversion on ext4+DAX is
+ * fundamentally broken here when there are concurrent
+ * read/write in progress on this inode.
+ */
+ WARN_ON_ONCE(io_end);
bh->b_assoc_map = inode->i_mapping;
bh->b_private = (void *)(unsigned long)iblock;
- bh->b_end_io = ext4_end_io_unwritten;
}
if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN)
set_buffer_defer_completion(bh);