diff options
| author | Stephen M. Cameron <scameron@beardog.cce.hp.com> | 2014-02-18 20:55:22 +0100 |
|---|---|---|
| committer | James Bottomley <JBottomley@Parallels.com> | 2014-03-15 18:19:03 +0100 |
| commit | 2f6ae5cd24491647a011aead90d47523d875e443 (patch) | |
| tree | 161ee78d7bf59d5411acc93603f23251e0dde626 | |
| parent | [SCSI] hpsa: add support for 'fastpath' i/o (diff) | |
| download | linux-2f6ae5cd24491647a011aead90d47523d875e443.tar.xz linux-2f6ae5cd24491647a011aead90d47523d875e443.zip | |
[SCSI] hpsa: only allow REQ_TYPE_FS to use fast path
When commands sent down the "fast path" fail, they must be re-tried down the
normal RAID path. We do this by kicking i/o's back to the scsi mid layer with
a DID_SOFT_ERROR status, which causes them to be retried. This won't work for
SG_IO's and other non REQ_TYPE_FS i/o's which could get kicked all the way back
to the application, which may have no idea that the command needs resubmitting
and likely no way to resubmit it in such a way the that driver can recognize it
as a resubmit and send it down the normal RAID path. So we just always send
non REQ_TYPE_FS i/o's down the normal RAID path, never down the "fast path".
Signed-off-by: Stephen M. Cameron <scameron@beardog.cce.hp.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
| -rw-r--r-- | drivers/scsi/hpsa.c | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 4047c37aa4f8..6e97f05bd493 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -2330,7 +2330,8 @@ static int hpsa_scsi_queue_command_lck(struct scsi_cmnd *cmd, if ((likely(h->transMethod & CFGTBL_Trans_io_accel1)) && (dev->ioaccel_handle) && ((cmd->cmnd[0] == READ_10) || (cmd->cmnd[0] == WRITE_10)) && - (scsi_sg_count(cmd) <= IOACCEL1_MAXSGENTRIES)) + (scsi_sg_count(cmd) <= IOACCEL1_MAXSGENTRIES) && + likely(cmd->request->cmd_type == REQ_TYPE_FS)) return hpsa_scsi_ioaccel_queue_command(h, c); c->Header.ReplyQueue = 0; /* unused in simple mode */ |