| commit | c43a5082a61f351248c5f015ee5d4641309bd96e | |
| author | Jens Axboe <jens.axboe@oracle.com> | |
| Fri, 12 Jan 2007 11:20:26 +0000 (12 12:20 +0100) | ||
| committer | Linus Torvalds <torvalds@woody.osdl.org> | |
| Fri, 12 Jan 2007 18:46:49 +0000 (12 10:46 -0800) | ||
| tree | 1a01acbf9d606c392f85449fe6d6af06154a9346 | treesnapshot (tar.gz zip) |
| parent | d39c9400ae0d60aaaf534b1ad860a9bc1413d8af | commitdiff |
[PATCH] blktrace: only add a bounce trace when we really bounce
Currently we issue a bounce trace when __blk_queue_bounce() is called,
but that merely means that the device has a lower dma mask than the
higher pages in the system. The bio itself may still be lower pages. So
move the bounce trace into __blk_queue_bounce(), when we know there will
actually be page bouncing.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Currently we issue a bounce trace when __blk_queue_bounce() is called,
but that merely means that the device has a lower dma mask than the
higher pages in the system. The bio itself may still be lower pages. So
move the bounce trace into __blk_queue_bounce(), when we know there will
actually be page bouncing.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
| mm/bounce.c | diffblobblamehistory |