search for: dio_lock

Displaying 4 results from an estimated 4 matches for "dio_lock".

Did you mean: dpio_lock
2013 Jan 31
4
[RFC][PATCH 2/2] Btrfs: implement unlocked dio write
...rw, iocb, iov, offset, nr_segs)) return 0; - if (rw == READ) { - atomic_inc(&inode->i_dio_count); - smp_mb__after_atomic_inc(); - if (unlikely(test_bit(BTRFS_INODE_READDIO_NEED_LOCK, - &BTRFS_I(inode)->runtime_flags))) { - inode_dio_done(inode); - flags = DIO_LOCKING | DIO_SKIP_HOLES; - } else { - wakeup = true; - } + atomic_inc(&inode->i_dio_count); + smp_mb__after_atomic_inc(); + if (rw == WRITE) { + mutex_unlock(&inode->i_mutex); + } else if (unlikely(test_bit(BTRFS_INODE_READDIO_NEED_LOCK, + &BTRFS_I(inode)->runtime_flag...
2011 Jun 24
10
[PATCH 0/9] remove i_alloc_sem V2
i_alloc_sem has always been a bit of an odd "lock". It''s the only remaining rw_semaphore that can be released by a different thread than the one that locked it, and it''s use case in the core direct I/O code is more like a counter given that the writers already have external serialization. This series removes it in favour of a simpler counter scheme, thus getting rid
2010 May 12
0
[PATCH 2/4] direct-io: add a hook for the fs to provide its own submit_bio function V3
...ffered and direct access */ @@ -2269,7 +2274,7 @@ static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb, dio_iodone_t end_io) { return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, - nr_segs, get_block, end_io, + nr_segs, get_block, end_io, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } @@ -2279,7 +2284,7 @@ static inline ssize_t blockdev_direct_IO_no_locking(int rw, struct kiocb *iocb, dio_iodone_t end_io) { return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, - nr_segs, get_block, end_io, 0); + nr_segs, get_block, end_io, NULL...
2010 May 07
6
[PATCH 1/5] fs: allow short direct-io reads to be completed via buffered IO V2
V1->V2: Check to see if our current ppos is >= i_size after a short DIO read, just in case it was actually a short read and we need to just return. This is similar to what already happens in the write case. If we have a short read while doing O_DIRECT, instead of just returning, fallthrough and try to read the rest via buffered IO. BTRFS needs this because if we encounter a compressed or