summaryrefslogtreecommitdiffstats
path: root/drivers/scsi/scsi_scan.c
diff options
context:
space:
mode:
authorMing Lei2019-02-15 12:13:23 +0100
committerJens Axboe2019-02-15 16:40:12 +0100
commit2705c93742e91730d335838025d75d8043861174 (patch)
tree16e379f17a745cbb3a1f8d7ba5ffe7e2b8ddee86 /drivers/scsi/scsi_scan.c
parentblock: document usage of bio iterator helpers (diff)
downloadkernel-qcow2-linux-2705c93742e91730d335838025d75d8043861174.tar.gz
kernel-qcow2-linux-2705c93742e91730d335838025d75d8043861174.tar.xz
kernel-qcow2-linux-2705c93742e91730d335838025d75d8043861174.zip
block: kill QUEUE_FLAG_NO_SG_MERGE
Since bdced438acd83ad83a6c ("block: setup bi_phys_segments after splitting"), physical segment number is mainly figured out in blk_queue_split() for fast path, and the flag of BIO_SEG_VALID is set there too. Now only blk_recount_segments() and blk_recalc_rq_segments() use this flag. Basically blk_recount_segments() is bypassed in fast path given BIO_SEG_VALID is set in blk_queue_split(). For another user of blk_recalc_rq_segments(): - run in partial completion branch of blk_update_request, which is an unusual case - run in blk_cloned_rq_check_limits(), still not a big problem if the flag is killed since dm-rq is the only user. Multi-page bvec is enabled now, not doing S/G merging is rather pointless with the current setup of the I/O path, as it isn't going to save you a significant amount of cycles. Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Omar Sandoval <osandov@fb.com> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'drivers/scsi/scsi_scan.c')
0 files changed, 0 insertions, 0 deletions