summaryrefslogtreecommitdiffstats
path: root/fs/direct-io.c
diff options
context:
space:
mode:
authorChristoph Hellwig <hch@lst.de>2009-12-15 16:47:50 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2009-12-16 07:20:13 -0800
commit5fe878ae7f82fbf0830dbfaee4c5ca18f3aee442 (patch)
tree7e7ad290cfb30705948d8ebeb46b013afa913f42 /fs/direct-io.c
parent23aee091d804efa8cc732a31c1ae5d625e1ec886 (diff)
downloadlinux-stable-5fe878ae7f82fbf0830dbfaee4c5ca18f3aee442.tar.gz
linux-stable-5fe878ae7f82fbf0830dbfaee4c5ca18f3aee442.tar.bz2
linux-stable-5fe878ae7f82fbf0830dbfaee4c5ca18f3aee442.zip
direct-io: cleanup blockdev_direct_IO locking
Currently the locking in blockdev_direct_IO is a mess, we have three different locking types and very confusing checks for some of them. The most complicated one is DIO_OWN_LOCKING for reads, which happens to not actually be used. This patch gets rid of the DIO_OWN_LOCKING - as mentioned above the read case is unused anyway, and the write side is almost identical to DIO_NO_LOCKING. The difference is that DIO_NO_LOCKING always sets the create argument for the get_blocks callback to zero, but we can easily move that to the actual get_blocks callbacks. There are four users of the DIO_NO_LOCKING mode: gfs already ignores the create argument and thus is fine with the new version, ocfs2 only errors out if create were ever set, and we can remove this dead code now, the block device code only ever uses create for an error message if we are fully beyond the device which can never happen, and last but not least XFS will need the new behavour for writes. Now we can replace the lock_type variable with a flags one, where no flag means the DIO_NO_LOCKING behaviour and DIO_LOCKING is kept as the first flag. Separate out the check for not allowing to fill holes into a separate flag, although for now both flags always get set at the same time. Also revamp the documentation of the locking scheme to actually make sense. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Christoph Hellwig <hch@lst.de> Cc: Dave Chinner <david@fromorbit.com> Cc: Badari Pulavarty <pbadari@us.ibm.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Zach Brown <zach.brown@oracle.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Alex Elder <aelder@sgi.com> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <joel.becker@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/direct-io.c')
-rw-r--r--fs/direct-io.c129
1 files changed, 52 insertions, 77 deletions
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 9f34bb9b1ecb..4012885d027f 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -53,13 +53,6 @@
*
* If blkfactor is zero then the user's request was aligned to the filesystem's
* blocksize.
- *
- * lock_type is DIO_LOCKING for regular files on direct-IO-naive filesystems.
- * This determines whether we need to do the fancy locking which prevents
- * direct-IO from being able to read uninitialised disk blocks. If its zero
- * (blockdev) this locking is not done, and if it is DIO_OWN_LOCKING i_mutex is
- * not held for the entire direct write (taken briefly, initially, during a
- * direct read though, but its never held for the duration of a direct-IO).
*/
struct dio {
@@ -68,7 +61,7 @@ struct dio {
struct inode *inode;
int rw;
loff_t i_size; /* i_size when submitted */
- int lock_type; /* doesn't change */
+ int flags; /* doesn't change */
unsigned blkbits; /* doesn't change */
unsigned blkfactor; /* When we're using an alignment which
is finer than the filesystem's soft
@@ -246,7 +239,8 @@ static int dio_complete(struct dio *dio, loff_t offset, int ret)
if (dio->end_io && dio->result)
dio->end_io(dio->iocb, offset, transferred,
dio->map_bh.b_private);
- if (dio->lock_type == DIO_LOCKING)
+
+ if (dio->flags & DIO_LOCKING)
/* lockdep: non-owner release */
up_read_non_owner(&dio->inode->i_alloc_sem);
@@ -521,21 +515,24 @@ static int get_more_blocks(struct dio *dio)
map_bh->b_state = 0;
map_bh->b_size = fs_count << dio->inode->i_blkbits;
+ /*
+ * For writes inside i_size on a DIO_SKIP_HOLES filesystem we
+ * forbid block creations: only overwrites are permitted.
+ * We will return early to the caller once we see an
+ * unmapped buffer head returned, and the caller will fall
+ * back to buffered I/O.
+ *
+ * Otherwise the decision is left to the get_blocks method,
+ * which may decide to handle it or also return an unmapped
+ * buffer head.
+ */
create = dio->rw & WRITE;
- if (dio->lock_type == DIO_LOCKING) {
+ if (dio->flags & DIO_SKIP_HOLES) {
if (dio->block_in_file < (i_size_read(dio->inode) >>
dio->blkbits))
create = 0;
- } else if (dio->lock_type == DIO_NO_LOCKING) {
- create = 0;
}
- /*
- * For writes inside i_size we forbid block creations: only
- * overwrites are permitted. We fall back to buffered writes
- * at a higher level for inside-i_size block-instantiating
- * writes.
- */
ret = (*dio->get_block)(dio->inode, fs_startblk,
map_bh, create);
}
@@ -1045,7 +1042,7 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode,
* we can let i_mutex go now that its achieved its purpose
* of protecting us from looking up uninitialized blocks.
*/
- if ((rw == READ) && (dio->lock_type == DIO_LOCKING))
+ if (rw == READ && (dio->flags & DIO_LOCKING))
mutex_unlock(&dio->inode->i_mutex);
/*
@@ -1092,30 +1089,28 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode,
/*
* This is a library function for use by filesystem drivers.
- * The locking rules are governed by the dio_lock_type parameter.
*
- * DIO_NO_LOCKING (no locking, for raw block device access)
- * For writes, i_mutex is not held on entry; it is never taken.
+ * The locking rules are governed by the flags parameter:
+ * - if the flags value contains DIO_LOCKING we use a fancy locking
+ * scheme for dumb filesystems.
+ * For writes this function is called under i_mutex and returns with
+ * i_mutex held, for reads, i_mutex is not held on entry, but it is
+ * taken and dropped again before returning.
+ * For reads and writes i_alloc_sem is taken in shared mode and released
+ * on I/O completion (which may happen asynchronously after returning to
+ * the caller).
*
- * DIO_LOCKING (simple locking for regular files)
- * For writes we are called under i_mutex and return with i_mutex held, even
- * though it is internally dropped.
- * For reads, i_mutex is not held on entry, but it is taken and dropped before
- * returning.
- *
- * DIO_OWN_LOCKING (filesystem provides synchronisation and handling of
- * uninitialised data, allowing parallel direct readers and writers)
- * For writes we are called without i_mutex, return without it, never touch it.
- * For reads we are called under i_mutex and return with i_mutex held, even
- * though it may be internally dropped.
- *
- * Additional i_alloc_sem locking requirements described inline below.
+ * - if the flags value does NOT contain DIO_LOCKING we don't use any
+ * internal locking but rather rely on the filesystem to synchronize
+ * direct I/O reads/writes versus each other and truncate.
+ * For reads and writes both i_mutex and i_alloc_sem are not held on
+ * entry and are never taken.
*/
ssize_t
__blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
struct block_device *bdev, const struct iovec *iov, loff_t offset,
unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
- int dio_lock_type)
+ int flags)
{
int seg;
size_t size;
@@ -1126,8 +1121,6 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
ssize_t retval = -EINVAL;
loff_t end = offset;
struct dio *dio;
- int release_i_mutex = 0;
- int acquire_i_mutex = 0;
if (rw & WRITE)
rw = WRITE_ODIRECT_PLUG;
@@ -1168,43 +1161,30 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
*/
memset(dio, 0, offsetof(struct dio, pages));
- /*
- * For block device access DIO_NO_LOCKING is used,
- * neither readers nor writers do any locking at all
- * For regular files using DIO_LOCKING,
- * readers need to grab i_mutex and i_alloc_sem
- * writers need to grab i_alloc_sem only (i_mutex is already held)
- * For regular files using DIO_OWN_LOCKING,
- * neither readers nor writers take any locks here
- */
- dio->lock_type = dio_lock_type;
- if (dio_lock_type != DIO_NO_LOCKING) {
+ dio->flags = flags;
+ if (dio->flags & DIO_LOCKING) {
/* watch out for a 0 len io from a tricksy fs */
if (rw == READ && end > offset) {
- struct address_space *mapping;
+ struct address_space *mapping =
+ iocb->ki_filp->f_mapping;
- mapping = iocb->ki_filp->f_mapping;
- if (dio_lock_type != DIO_OWN_LOCKING) {
- mutex_lock(&inode->i_mutex);
- release_i_mutex = 1;
- }
+ /* will be released by direct_io_worker */
+ mutex_lock(&inode->i_mutex);
retval = filemap_write_and_wait_range(mapping, offset,
end - 1);
if (retval) {
+ mutex_unlock(&inode->i_mutex);
kfree(dio);
goto out;
}
-
- if (dio_lock_type == DIO_OWN_LOCKING) {
- mutex_unlock(&inode->i_mutex);
- acquire_i_mutex = 1;
- }
}
- if (dio_lock_type == DIO_LOCKING)
- /* lockdep: not the owner will release it */
- down_read_non_owner(&inode->i_alloc_sem);
+ /*
+ * Will be released at I/O completion, possibly in a
+ * different thread.
+ */
+ down_read_non_owner(&inode->i_alloc_sem);
}
/*
@@ -1222,24 +1202,19 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
/*
* In case of error extending write may have instantiated a few
* blocks outside i_size. Trim these off again for DIO_LOCKING.
- * NOTE: DIO_NO_LOCK/DIO_OWN_LOCK callers have to handle this by
- * it's own meaner.
+ *
+ * NOTE: filesystems with their own locking have to handle this
+ * on their own.
*/
- if (unlikely(retval < 0 && (rw & WRITE))) {
- loff_t isize = i_size_read(inode);
-
- if (end > isize && dio_lock_type == DIO_LOCKING)
- vmtruncate(inode, isize);
+ if (dio->flags & DIO_LOCKING) {
+ if (unlikely((rw & WRITE) && retval < 0)) {
+ loff_t isize = i_size_read(inode);
+ if (end > isize)
+ vmtruncate(inode, isize);
+ }
}
- if (rw == READ && dio_lock_type == DIO_LOCKING)
- release_i_mutex = 0;
-
out:
- if (release_i_mutex)
- mutex_unlock(&inode->i_mutex);
- else if (acquire_i_mutex)
- mutex_lock(&inode->i_mutex);
return retval;
}
EXPORT_SYMBOL(__blockdev_direct_IO);