| Message ID | 20220201210954.570896-2-sebastian@breakpoint.cc |
|---|---|
| State | New |
| Headers | show |
| Series | Add scsi_done_direct() to complete request directly. | expand |
On 2/1/22 13:09, Sebastian Andrzej Siewior wrote: > -void scsi_done(struct scsi_cmnd *cmd) > +static bool scsi_done_need_blk_compl(struct scsi_cmnd *cmd) I'm not happy about the name of this function. The word "need" in the function name suggests that this function does not modify any state. However, the body of the function shows that it may complete a SCSI command. How about renaming the existing scsi_done() function into scsi_done_internal() or so and adding a "bool complete_directly" argument to that function? BTW, I only received patch 1/2 but not patch 2/2. Please Cc the linux-scsi mailing list for the entire patch series when reposting the patch series. Thanks, Bart.
On 2022-02-02 12:49:16 [-0800], Bart Van Assche wrote: > On 2/1/22 13:09, Sebastian Andrzej Siewior wrote: > > -void scsi_done(struct scsi_cmnd *cmd) > > +static bool scsi_done_need_blk_compl(struct scsi_cmnd *cmd) > > I'm not happy about the name of this function. The word "need" in the > function name suggests that this function does not modify any state. > However, the body of the function shows that it may complete a SCSI command. > How about renaming the existing scsi_done() function into > scsi_done_internal() or so and adding a "bool complete_directly" argument to > that function? Let me see what I can do. > BTW, I only received patch 1/2 but not patch 2/2. Please Cc the linux-scsi > mailing list for the entire patch series when reposting the patch series. I did and based on lore's archive it made it to the list: https://lore.kernel.org/linux-scsi/20220201210954.570896-1-sebastian@breakpoint.cc/ > Thanks, > > Bart. Sebastian
On 2/3/22 11:46, Sebastian Andrzej Siewior wrote: > On 2022-02-02 12:49:16 [-0800], Bart Van Assche wrote: >> On 2/1/22 13:09, Sebastian Andrzej Siewior wrote: >>> -void scsi_done(struct scsi_cmnd *cmd) >>> +static bool scsi_done_need_blk_compl(struct scsi_cmnd *cmd) >> >> I'm not happy about the name of this function. The word "need" in the >> function name suggests that this function does not modify any state. >> However, the body of the function shows that it may complete a SCSI command. >> How about renaming the existing scsi_done() function into >> scsi_done_internal() or so and adding a "bool complete_directly" argument to >> that function? > > Let me see what I can do. > >> BTW, I only received patch 1/2 but not patch 2/2. Please Cc the linux-scsi >> mailing list for the entire patch series when reposting the patch series. > > I did and based on lore's archive it made it to the list: > https://lore.kernel.org/linux-scsi/20220201210954.570896-1-sebastian@breakpoint.cc/ I agree that patch 2/2 seems to have made it to the linux-scsi list. However, I can't find that patch in my mailbox nor in my spam folder. I think this is the first time that I did not receive a patch sent to the linux-scsi mailing list. Weird ... Bart.
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 0a70aa763a961..778ef6d09616f 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1625,26 +1625,45 @@ static blk_status_t scsi_prepare_cmd(struct request *req) return scsi_cmd_to_driver(cmd)->init_command(cmd); } -void scsi_done(struct scsi_cmnd *cmd) +static bool scsi_done_need_blk_compl(struct scsi_cmnd *cmd) { switch (cmd->submitter) { case SUBMITTED_BY_BLOCK_LAYER: break; case SUBMITTED_BY_SCSI_ERROR_HANDLER: - return scsi_eh_done(cmd); + scsi_eh_done(cmd); + return false; case SUBMITTED_BY_SCSI_RESET_IOCTL: - return; + return false; } if (unlikely(blk_should_fake_timeout(scsi_cmd_to_rq(cmd)->q))) - return; + return false; if (unlikely(test_and_set_bit(SCMD_STATE_COMPLETE, &cmd->state))) + return false; + return true; +} + +void scsi_done(struct scsi_cmnd *cmd) +{ + if (!scsi_done_need_blk_compl(cmd)) return; + trace_scsi_dispatch_cmd_done(cmd); blk_mq_complete_request(scsi_cmd_to_rq(cmd)); } EXPORT_SYMBOL(scsi_done); +void scsi_done_direct(struct scsi_cmnd *cmd) +{ + if (!scsi_done_need_blk_compl(cmd)) + return; + + trace_scsi_dispatch_cmd_done(cmd); + blk_mq_complete_request_direct(scsi_cmd_to_rq(cmd), scsi_complete); +} +EXPORT_SYMBOL(scsi_done_direct); + static void scsi_mq_put_budget(struct request_queue *q, int budget_token) { struct scsi_device *sdev = q->queuedata; diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 6794d7322cbde..ff1c4b51f7aef 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -168,6 +168,7 @@ static inline struct scsi_driver *scsi_cmd_to_driver(struct scsi_cmnd *cmd) } void scsi_done(struct scsi_cmnd *cmd); +void scsi_done_direct(struct scsi_cmnd *cmd); extern void scsi_finish_command(struct scsi_cmnd *cmd);
Add scsi_done_direct() which behaves like scsi_done() except that it invokes blk_mq_complete_request_direct() in order to complete the request. Callers from process context can complete the request directly instead waking ksoftirqd. Signed-off-by: Sebastian Andrzej Siewior <sebastian@breakpoint.cc> --- drivers/scsi/scsi_lib.c | 27 +++++++++++++++++++++++---- include/scsi/scsi_cmnd.h | 1 + 2 files changed, 24 insertions(+), 4 deletions(-)