lkml.org 
[lkml]   [2015]   [Apr]   [15]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    Patch in this message
    /
    From
    Subject[PATCH 3/3] ext4: pass in DIO_SKIP_DIO_COUNT to do_blockdev_direct_IO()
    Date
    For writes, ext4_ext_direct_IO() already holds the inode i_dio_count
    elevated, so we don't need the extra inc/dec that is done in
    do_blockdev_direct_IO(). Pass in DIO_SKIP_DIO_COUNT to tell it that.

    Cc: Theodore Ts'o <tytso@mit.edu>
    Signed-off-by: Jens Axboe <axboe@fb.com>
    ---
    fs/ext4/inode.c | 6 ++++--
    1 file changed, 4 insertions(+), 2 deletions(-)

    diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
    index 62d4615aa9b0..2605355791a3 100644
    --- a/fs/ext4/inode.c
    +++ b/fs/ext4/inode.c
    @@ -2977,8 +2977,10 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
    * conversion. This also disallows race between truncate() and
    * overwrite DIO as i_dio_count needs to be incremented under i_mutex.
    */
    - if (rw == WRITE)
    + if (rw == WRITE) {
    inode_dio_inc(inode);
    + dio_flags |= DIO_SKIP_DIO_COUNT;
    + }

    /* If we do a overwrite dio, i_mutex locking can be released */
    overwrite = *((int *)iocb->private);
    @@ -3032,7 +3034,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
    get_block_func = ext4_get_block_write_nolock;
    } else {
    get_block_func = ext4_get_block_write;
    - dio_flags = DIO_LOCKING;
    + dio_flags |= DIO_LOCKING;
    }
    if (IS_DAX(inode))
    ret = dax_do_io(rw, iocb, inode, iter, offset, get_block_func,
    --
    1.9.1


    \
     
     \ /
      Last update: 2015-04-16 00:41    [W:3.814 / U:0.048 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site