From: James Smart <jsmart2021@gmail.com>
Date: Wed, 14 Aug 2019 16:56:54 -0700
Subject: scsi: lpfc: Fix too many sg segments spamming in kernel log
Patch-mainline: v5.4-rc1
Git-commit: 5e0e2318aa2a6fb8c2c693fb7ff995650e452054
References: jsc#SLE-8284 jsc#SLE-8654
This issue is specific to SLI-3 adapters, specifically when DIF is used.
Once seen, this message floods the logs:
9064 BLKGRD: lpfc_scsi_prep_dma_buf_s3: Too many sg segments from
dma_map_sg
The driver, upon detecting an error such as too many elements in an sglist,
misrepresents the error by treating it as a temporary resource issue by
returning MLQUEUE_HOST_BUSY. In these cases, no retry will fix it and it
should have been a hard error. The repeated retry was causing the spamming
of the log.
As for the initial reason of why an I/O encountered this issue at all is
not clear as parameters set by the driver should have avoided this. The
dm multipath maintainer has been notified of the issue.
Fix by changing the return code for the dma mapping routines to indicate
cases that are not retryable and return DID_ERROR on those cases.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: Daniel Wagner <dwagner@suse.de>
---
drivers/scsi/lpfc/lpfc_scsi.c | 79 +++++++++++++++++++++++++++++++-----------
1 file changed, 60 insertions(+), 19 deletions(-)
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -918,9 +918,10 @@ lpfc_scsi_prep_dma_buf_s3(struct lpfc_hb
"dma_map_sg. Config %d, seg_cnt %d\n",
__func__, phba->cfg_sg_seg_cnt,
lpfc_cmd->seg_cnt);
+ WARN_ON_ONCE(lpfc_cmd->seg_cnt > phba->cfg_sg_seg_cnt);
lpfc_cmd->seg_cnt = 0;
scsi_dma_unmap(scsi_cmnd);
- return 1;
+ return 2;
}
/*
@@ -2430,7 +2431,10 @@ lpfc_bg_scsi_adjust_dl(struct lpfc_hba *
*
* This is the protection/DIF aware version of
* lpfc_scsi_prep_dma_buf(). It may be a good idea to combine the
- * two functions eventually, but for now, it's here
+ * two functions eventually, but for now, it's here.
+ * RETURNS 0 - SUCCESS,
+ * 1 - Failed DMA map, retry.
+ * 2 - Invalid scsi cmd or prot-type. Do not rety.
**/
static int
lpfc_bg_scsi_prep_dma_buf_s3(struct lpfc_hba *phba,
@@ -2444,6 +2448,7 @@ lpfc_bg_scsi_prep_dma_buf_s3(struct lpfc
int datasegcnt, protsegcnt, datadir = scsi_cmnd->sc_data_direction;
int prot_group_type = 0;
int fcpdl;
+ int ret = 1;
struct lpfc_vport *vport = phba->pport;
/*
@@ -2467,8 +2472,11 @@ lpfc_bg_scsi_prep_dma_buf_s3(struct lpfc
lpfc_cmd->seg_cnt = datasegcnt;
/* First check if data segment count from SCSI Layer is good */
- if (lpfc_cmd->seg_cnt > phba->cfg_sg_seg_cnt)
+ if (lpfc_cmd->seg_cnt > phba->cfg_sg_seg_cnt) {
+ WARN_ON_ONCE(lpfc_cmd->seg_cnt > phba->cfg_sg_seg_cnt);
+ ret = 2;
goto err;
+ }
prot_group_type = lpfc_prot_group_type(phba, scsi_cmnd);
@@ -2476,14 +2484,18 @@ lpfc_bg_scsi_prep_dma_buf_s3(struct lpfc
case LPFC_PG_TYPE_NO_DIF:
/* Here we need to add a PDE5 and PDE6 to the count */
- if ((lpfc_cmd->seg_cnt + 2) > phba->cfg_total_seg_cnt)
+ if ((lpfc_cmd->seg_cnt + 2) > phba->cfg_total_seg_cnt) {
+ ret = 2;
goto err;
+ }
num_bde = lpfc_bg_setup_bpl(phba, scsi_cmnd, bpl,
datasegcnt);
/* we should have 2 or more entries in buffer list */
- if (num_bde < 2)
+ if (num_bde < 2) {
+ ret = 2;
goto err;
+ }
break;
case LPFC_PG_TYPE_DIF_BUF:
@@ -2507,15 +2519,19 @@ lpfc_bg_scsi_prep_dma_buf_s3(struct lpfc
* protection data segment.
*/
if ((lpfc_cmd->prot_seg_cnt * 4) >
- (phba->cfg_total_seg_cnt - 2))
+ (phba->cfg_total_seg_cnt - 2)) {
+ ret = 2;
goto err;
+ }
num_bde = lpfc_bg_setup_bpl_prot(phba, scsi_cmnd, bpl,
datasegcnt, protsegcnt);
/* we should have 3 or more entries in buffer list */
if ((num_bde < 3) ||
- (num_bde > phba->cfg_total_seg_cnt))
+ (num_bde > phba->cfg_total_seg_cnt)) {
+ ret = 2;
goto err;
+ }
break;
case LPFC_PG_TYPE_INVALID:
@@ -2526,7 +2542,7 @@ lpfc_bg_scsi_prep_dma_buf_s3(struct lpfc
lpfc_printf_log(phba, KERN_ERR, LOG_FCP,
"9022 Unexpected protection group %i\n",
prot_group_type);
- return 1;
+ return 2;
}
}
@@ -2576,7 +2592,7 @@ err:
lpfc_cmd->seg_cnt = 0;
lpfc_cmd->prot_seg_cnt = 0;
- return 1;
+ return ret;
}
/*
@@ -2962,7 +2978,8 @@ out:
* field of @lpfc_cmd for device with SLI-4 interface spec.
*
* Return codes:
- * 1 - Error
+ * 2 - Error - Do not retry
+ * 1 - Error - Retry
* 0 - Success
**/
static int
@@ -3012,9 +3029,10 @@ lpfc_scsi_prep_dma_buf_s4(struct lpfc_hb
"dma_map_sg. Config %d, seg_cnt %d\n",
__func__, phba->cfg_sg_seg_cnt,
lpfc_cmd->seg_cnt);
+ WARN_ON_ONCE(lpfc_cmd->seg_cnt > phba->cfg_sg_seg_cnt);
lpfc_cmd->seg_cnt = 0;
scsi_dma_unmap(scsi_cmnd);
- return 1;
+ return 2;
}
/*
@@ -3110,6 +3128,10 @@ lpfc_scsi_prep_dma_buf_s4(struct lpfc_hb
* This is the protection/DIF aware version of
* lpfc_scsi_prep_dma_buf(). It may be a good idea to combine the
* two functions eventually, but for now, it's here
+ * Return codes:
+ * 2 - Error - Do not retry
+ * 1 - Error - Retry
+ * 0 - Success
**/
static int
lpfc_bg_scsi_prep_dma_buf_s4(struct lpfc_hba *phba,
@@ -3123,6 +3145,7 @@ lpfc_bg_scsi_prep_dma_buf_s4(struct lpfc
int datasegcnt, protsegcnt, datadir = scsi_cmnd->sc_data_direction;
int prot_group_type = 0;
int fcpdl;
+ int ret = 1;
struct lpfc_vport *vport = phba->pport;
/*
@@ -3152,23 +3175,30 @@ lpfc_bg_scsi_prep_dma_buf_s4(struct lpfc
lpfc_cmd->seg_cnt = datasegcnt;
/* First check if data segment count from SCSI Layer is good */
- if (lpfc_cmd->seg_cnt > phba->cfg_sg_seg_cnt)
+ if (lpfc_cmd->seg_cnt > phba->cfg_sg_seg_cnt) {
+ WARN_ON_ONCE(lpfc_cmd->seg_cnt > phba->cfg_sg_seg_cnt);
+ ret = 2;
goto err;
+ }
prot_group_type = lpfc_prot_group_type(phba, scsi_cmnd);
switch (prot_group_type) {
case LPFC_PG_TYPE_NO_DIF:
/* Here we need to add a DISEED to the count */
- if ((lpfc_cmd->seg_cnt + 1) > phba->cfg_total_seg_cnt)
+ if ((lpfc_cmd->seg_cnt + 1) > phba->cfg_total_seg_cnt) {
+ ret = 2;
goto err;
+ }
num_sge = lpfc_bg_setup_sgl(phba, scsi_cmnd, sgl,
datasegcnt);
/* we should have 2 or more entries in buffer list */
- if (num_sge < 2)
+ if (num_sge < 2) {
+ ret = 2;
goto err;
+ }
break;
case LPFC_PG_TYPE_DIF_BUF:
@@ -3191,16 +3221,20 @@ lpfc_bg_scsi_prep_dma_buf_s4(struct lpfc
* protection data segment.
*/
if ((lpfc_cmd->prot_seg_cnt * 3) >
- (phba->cfg_total_seg_cnt - 2))
+ (phba->cfg_total_seg_cnt - 2)) {
+ ret = 2;
goto err;
+ }
num_sge = lpfc_bg_setup_sgl_prot(phba, scsi_cmnd, sgl,
datasegcnt, protsegcnt);
/* we should have 3 or more entries in buffer list */
if ((num_sge < 3) ||
- (num_sge > phba->cfg_total_seg_cnt))
+ (num_sge > phba->cfg_total_seg_cnt)) {
+ ret = 2;
goto err;
+ }
break;
case LPFC_PG_TYPE_INVALID:
@@ -3211,7 +3245,7 @@ lpfc_bg_scsi_prep_dma_buf_s4(struct lpfc
lpfc_printf_log(phba, KERN_ERR, LOG_FCP,
"9083 Unexpected protection group %i\n",
prot_group_type);
- return 1;
+ return 2;
}
}
@@ -3273,7 +3307,7 @@ err:
lpfc_cmd->seg_cnt = 0;
lpfc_cmd->prot_seg_cnt = 0;
- return 1;
+ return ret;
}
/**
@@ -4454,8 +4488,12 @@ lpfc_queuecommand(struct Scsi_Host *shos
err = lpfc_scsi_prep_dma_buf(phba, lpfc_cmd);
}
- if (err)
+ if (err == 2) {
+ cmnd->result = DID_ERROR << 16;
+ goto out_fail_command_release_buf;
+ } else if (err) {
goto out_host_busy_free_buf;
+ }
lpfc_scsi_prep_cmnd(vport, lpfc_cmd, ndlp);
@@ -4526,6 +4564,9 @@ lpfc_queuecommand(struct Scsi_Host *shos
out_tgt_busy:
return SCSI_MLQUEUE_TARGET_BUSY;
+ out_fail_command_release_buf:
+ lpfc_release_scsi_buf(phba, lpfc_cmd);
+
out_fail_command:
cmnd->scsi_done(cmnd);
return 0;