From b57c4db5d23b9df0118a25e2441c9288edd73710 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 29 Nov 2023 17:58:30 +0100 Subject: [PATCH 1/3] scsi: libfc: Don't schedule abort twice The current FC error recovery is sending up to three REC (recovery) frames in 10 second intervals, and as a final step sending an ABTS after 30 seconds for the command itself. Unfortunately sending an ABTS is also the action for the SCSI abort handler, and the default timeout for SCSI commands is also 30 seconds. This causes two ABTS to be scheduled, with the libfc one slightly earlier. The ABTS scheduled by SCSI EH then sees the command to be already aborted, and will always return with a 'GOOD' status irrespective on the actual result from the first ABTS. This causes the SCSI EH abort handler to always succeed, and SCSI EH never to be engaged. Fix this by not issuing an ABTS when a SCSI command is present for the exchange, but rather wait for the abort scheduled from SCSI EH. And warn if an abort is already scheduled to avoid similar errors in the future. Signed-off-by: Hannes Reinecke Link: https://lore.kernel.org/r/20231129165832.224100-2-hare@kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- drivers/scsi/libfc/fc_fcp.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c index 945adca5e72f..3f189cedf6db 100644 --- a/drivers/scsi/libfc/fc_fcp.c +++ b/drivers/scsi/libfc/fc_fcp.c @@ -265,6 +265,11 @@ static int fc_fcp_send_abort(struct fc_fcp_pkt *fsp) if (!fsp->seq_ptr) return -EINVAL; + if (fsp->state & FC_SRB_ABORT_PENDING) { + FC_FCP_DBG(fsp, "abort already pending\n"); + return -EBUSY; + } + this_cpu_inc(fsp->lp->stats->FcpPktAborts); fsp->state |= FC_SRB_ABORT_PENDING; @@ -1690,11 +1695,12 @@ static void fc_fcp_recovery(struct fc_fcp_pkt *fsp, u8 code) fsp->status_code = code; fsp->cdb_status = 0; fsp->io_status = 0; - /* - * if this fails then we let the scsi command timer fire and - * scsi-ml escalate. - */ - fc_fcp_send_abort(fsp); + if (!fsp->cmd) + /* + * Only abort non-scsi commands; otherwise let the + * scsi command timer fire and scsi-ml escalate. + */ + fc_fcp_send_abort(fsp); } /** From 53122a49f49796beb2c4a1bb702303b66347e29f Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 29 Nov 2023 17:58:31 +0100 Subject: [PATCH 2/3] scsi: libfc: Fix up timeout error in fc_fcp_rec_error() We should set the status to FC_TIMED_OUT when a timeout error is passed to fc_fcp_rec_error(). Signed-off-by: Hannes Reinecke Link: https://lore.kernel.org/r/20231129165832.224100-3-hare@kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- drivers/scsi/libfc/fc_fcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c index 3f189cedf6db..05be0810b5e3 100644 --- a/drivers/scsi/libfc/fc_fcp.c +++ b/drivers/scsi/libfc/fc_fcp.c @@ -1676,7 +1676,7 @@ static void fc_fcp_rec_error(struct fc_fcp_pkt *fsp, struct fc_frame *fp) if (fsp->recov_retry++ < FC_MAX_RECOV_RETRY) fc_fcp_rec(fsp); else - fc_fcp_recovery(fsp, FC_ERROR); + fc_fcp_recovery(fsp, FC_TIMED_OUT); break; } fc_fcp_unlock_pkt(fsp); From be40572c22cc734f5836b4faec8a60340dc7ab67 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 29 Nov 2023 17:58:32 +0100 Subject: [PATCH 3/3] scsi: libfc: Map FC_TIMED_OUT to DID_TIME_OUT When an exchange is completed with FC_TIMED_OUT we should map it to DID_TIME_OUT to inform the SCSI midlayer that this was a command timeout; DID_BUS_BUSY implies that the command was never sent which is not the case here. Signed-off-by: Hannes Reinecke Link: https://lore.kernel.org/r/20231129165832.224100-4-hare@kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- drivers/scsi/libfc/fc_fcp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c index 05be0810b5e3..80be3a936d92 100644 --- a/drivers/scsi/libfc/fc_fcp.c +++ b/drivers/scsi/libfc/fc_fcp.c @@ -2062,9 +2062,9 @@ static void fc_io_compl(struct fc_fcp_pkt *fsp) sc_cmd->result = (DID_PARITY << 16); break; case FC_TIMED_OUT: - FC_FCP_DBG(fsp, "Returning DID_BUS_BUSY to scsi-ml " + FC_FCP_DBG(fsp, "Returning DID_TIME_OUT to scsi-ml " "due to FC_TIMED_OUT\n"); - sc_cmd->result = (DID_BUS_BUSY << 16) | fsp->io_status; + sc_cmd->result = (DID_TIME_OUT << 16); break; default: FC_FCP_DBG(fsp, "Returning DID_ERROR to scsi-ml "