[PATCH v1 0/2] fix MCQ abort defect

[PATCH v1 0/2] fix MCQ abort defect

[peter.wang]

From: Peter Wang <peter.wang@mediatek.com>

This series fixes MCQ abort defect.

Peter Wang (2):
  ufs: core: fix the issue of ICU failure
  ufs: core: requeue MCQ abort request

 drivers/ufs/core/ufs-mcq.c | 10 ++++++----
 drivers/ufs/core/ufshcd.c  | 21 ++++++++-------------
 include/ufs/ufshcd.h       |  2 ++
 3 files changed, 16 insertions(+), 17 deletions(-)

-- 
2.45.2

[PATCH v1 1/2] ufs: core: fix the issue of ICU failure

[peter.wang]

From: Peter Wang <peter.wang@mediatek.com>

When setting the ICU bit without using read-modify-write,
SQRTCy will restart SQ again and receive an RTC return
error code 2 (Failure - SQ not stopped).

Additionally, the error log has been modified so that
this type of error can be observed.

Fixes: ab248643d3d6 ("scsi: ufs: core: Add error handling for MCQ mode")
Cc: stable@vger.kernel.org
Signed-off-by: Peter Wang <peter.wang@mediatek.com>
---
 drivers/ufs/core/ufs-mcq.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c
index 5891cdacd0b3..afd9541f4bd8 100644
--- a/drivers/ufs/core/ufs-mcq.c
+++ b/drivers/ufs/core/ufs-mcq.c
@@ -570,15 +570,16 @@ int ufshcd_mcq_sq_cleanup(struct ufs_hba *hba, int task_tag)
 	writel(nexus, opr_sqd_base + REG_SQCTI);
 
 	/* SQRTCy.ICU = 1 */
-	writel(SQ_ICU, opr_sqd_base + REG_SQRTC);
+	writel(readl(opr_sqd_base + REG_SQRTC) | SQ_ICU,
+		opr_sqd_base + REG_SQRTC);
 
 	/* Poll SQRTSy.CUS = 1. Return result from SQRTSy.RTC */
 	reg = opr_sqd_base + REG_SQRTS;
 	err = read_poll_timeout(readl, val, val & SQ_CUS, 20,
 				MCQ_POLL_US, false, reg);
-	if (err)
-		dev_err(hba->dev, "%s: failed. hwq=%d, tag=%d err=%ld\n",
-			__func__, id, task_tag,
+	if (err || FIELD_GET(SQ_ICU_ERR_CODE_MASK, readl(reg)))
+		dev_err(hba->dev, "%s: failed. hwq=%d, tag=%d err=%d RTC=%ld\n",
+			__func__, id, task_tag, err,
 			FIELD_GET(SQ_ICU_ERR_CODE_MASK, readl(reg)));
 
 	if (ufshcd_mcq_sq_start(hba, hwq))
-- 
2.45.2

Re: [PATCH v1 1/2] ufs: core: fix the issue of ICU failure

[Bart Van Assche]

On 8/30/24 3:44 AM, peter.wang@mediatek.com wrote:
> Fixes: ab248643d3d6 ("scsi: ufs: core: Add error handling for MCQ mode")

Bao, please help with reviewing this patch series.

Thanks,

Bart.

[PATCH v1 2/2] ufs: core: requeue MCQ abort request

[peter.wang]

From: Peter Wang <peter.wang@mediatek.com>

MCQ aborts a command using two methods below:
1. Nullified UTRD, Host controller skips this transfer request,
   reply Completion Queue entry to Host SW with OCS=ABORTED
2. SQ cleanup, The host controller will post to the Completion Queue
   to update the OCS field with ABORTED.

For these two cases, set a flag to notify SCSI to requeue the
command after receiving OCS_ABORTED.

Fixes: ab248643d3d6 ("scsi: ufs: core: Add error handling for MCQ mode")
Cc: stable@vger.kernel.org
Signed-off-by: Peter Wang <peter.wang@mediatek.com>
---
 drivers/ufs/core/ufs-mcq.c |  1 +
 drivers/ufs/core/ufshcd.c  | 21 ++++++++-------------
 include/ufs/ufshcd.h       |  2 ++
 3 files changed, 11 insertions(+), 13 deletions(-)

diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c
index afd9541f4bd8..abdc55a8b960 100644
--- a/drivers/ufs/core/ufs-mcq.c
+++ b/drivers/ufs/core/ufs-mcq.c
@@ -642,6 +642,7 @@ static bool ufshcd_mcq_sqe_search(struct ufs_hba *hba,
 		match = le64_to_cpu(utrd->command_desc_base_addr) & CQE_UCD_BA;
 		if (addr == match) {
 			ufshcd_mcq_nullify_sqe(utrd);
+			lrbp->host_initiate_abort = true;
 			ret = true;
 			goto out;
 		}
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index a6f818cdef0e..18418e9d7549 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -3006,6 +3006,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	ufshcd_prepare_lrbp_crypto(scsi_cmd_to_rq(cmd), lrbp);
 
 	lrbp->req_abort_skip = false;
+	lrbp->host_initiate_abort = false;
 
 	ufshcd_comp_scsi_upiu(hba, lrbp);
 
@@ -5404,7 +5405,10 @@ ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp,
 		}
 		break;
 	case OCS_ABORTED:
-		result |= DID_ABORT << 16;
+		if (lrbp->host_initiate_abort)
+			result |= DID_REQUEUE << 16;
+		else
+			result |= DID_ABORT << 16;
 		break;
 	case OCS_INVALID_COMMAND_STATUS:
 		result |= DID_REQUEUE << 16;
@@ -6472,24 +6476,15 @@ static bool ufshcd_abort_one(struct request *rq, void *priv)
 	struct Scsi_Host *shost = sdev->host;
 	struct ufs_hba *hba = shost_priv(shost);
 	struct ufshcd_lrb *lrbp = &hba->lrb[tag];
-	struct ufs_hw_queue *hwq;
-	unsigned long flags;
 
 	*ret = ufshcd_try_to_abort_task(hba, tag);
 	dev_err(hba->dev, "Aborting tag %d / CDB %#02x %s\n", tag,
 		hba->lrb[tag].cmd ? hba->lrb[tag].cmd->cmnd[0] : -1,
 		*ret ? "failed" : "succeeded");
 
-	/* Release cmd in MCQ mode if abort succeeds */
-	if (hba->mcq_enabled && (*ret == 0)) {
-		hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(lrbp->cmd));
-		if (!hwq)
-			return 0;
-		spin_lock_irqsave(&hwq->cq_lock, flags);
-		if (ufshcd_cmd_inflight(lrbp->cmd))
-			ufshcd_release_scsi_cmd(hba, lrbp);
-		spin_unlock_irqrestore(&hwq->cq_lock, flags);
-	}
+	/* Host will post to CQ with OCS_ABORTED after SQ clean up */
+	if (is_mcq_enabled(hba) && (*ret == 0))
+		lrbp->host_initiate_abort = true;
 
 	return *ret == 0;
 }
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index 0fd2aebac728..49dd5ca8a4e7 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -173,6 +173,7 @@ struct ufs_pm_lvl_states {
  * @crypto_key_slot: the key slot to use for inline crypto (-1 if none)
  * @data_unit_num: the data unit number for the first block for inline crypto
  * @req_abort_skip: skip request abort task flag
+ * @host_initiate_abort: Abort flag initiated by host
  */
 struct ufshcd_lrb {
 	struct utp_transfer_req_desc *utr_descriptor_ptr;
@@ -202,6 +203,7 @@ struct ufshcd_lrb {
 #endif
 
 	bool req_abort_skip;
+	bool host_initiate_abort;
 };
 
 /**
-- 
2.45.2

Re: [PATCH v1 2/2] ufs: core: requeue MCQ abort request

[kernel test robot]

Hi,

kernel test robot noticed the following build errors:

[auto build test ERROR on jejb-scsi/for-next]
[also build test ERROR on mkp-scsi/for-next linus/master v6.11-rc5 next-20240830]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/peter-wang-mediatek-com/ufs-core-fix-the-issue-of-ICU-failure/20240830-154808
base:   https://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi.git for-next
patch link:    https://lore.kernel.org/r/20240830074426.21968-3-peter.wang%40mediatek.com
patch subject: [PATCH v1 2/2] ufs: core: requeue MCQ abort request
config: arm-randconfig-002-20240831 (https://download.01.org/0day-ci/archive/20240901/202409010054.kNsXraZk-lkp@intel.com/config)
compiler: clang version 15.0.7 (https://github.com/llvm/llvm-project 8dfdcc7b7bf66834a761bd8de445840ef68e4d1a)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240901/202409010054.kNsXraZk-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202409010054.kNsXraZk-lkp@intel.com/

All errors (new ones prefixed by >>):

>> drivers/ufs/core/ufshcd.c:6505:6: error: call to undeclared function 'is_mcq_enabled'; ISO C99 and later do not support implicit function declarations [-Werror,-Wimplicit-function-declaration]
           if (is_mcq_enabled(hba) && (*ret == 0))
               ^
   1 error generated.


vim +/is_mcq_enabled +6505 drivers/ufs/core/ufshcd.c

  6488	
  6489	static bool ufshcd_abort_one(struct request *rq, void *priv)
  6490	{
  6491		int *ret = priv;
  6492		u32 tag = rq->tag;
  6493		struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
  6494		struct scsi_device *sdev = cmd->device;
  6495		struct Scsi_Host *shost = sdev->host;
  6496		struct ufs_hba *hba = shost_priv(shost);
  6497		struct ufshcd_lrb *lrbp = &hba->lrb[tag];
  6498	
  6499		*ret = ufshcd_try_to_abort_task(hba, tag);
  6500		dev_err(hba->dev, "Aborting tag %d / CDB %#02x %s\n", tag,
  6501			hba->lrb[tag].cmd ? hba->lrb[tag].cmd->cmnd[0] : -1,
  6502			*ret ? "failed" : "succeeded");
  6503	
  6504		/* Host will post to CQ with OCS_ABORTED after SQ clean up */
> 6505		if (is_mcq_enabled(hba) && (*ret == 0))
  6506			lrbp->host_initiate_abort = true;
  6507	
  6508		return *ret == 0;
  6509	}
  6510	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH v1 2/2] ufs: core: requeue MCQ abort request

[kernel test robot]

Hi,

kernel test robot noticed the following build errors:

[auto build test ERROR on jejb-scsi/for-next]
[also build test ERROR on mkp-scsi/for-next linus/master v6.11-rc5 next-20240830]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/peter-wang-mediatek-com/ufs-core-fix-the-issue-of-ICU-failure/20240830-154808
base:   https://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi.git for-next
patch link:    https://lore.kernel.org/r/20240830074426.21968-3-peter.wang%40mediatek.com
patch subject: [PATCH v1 2/2] ufs: core: requeue MCQ abort request
config: arm64-randconfig-r132-20240831 (https://download.01.org/0day-ci/archive/20240901/202409010304.Ivj4eQN6-lkp@intel.com/config)
compiler: clang version 14.0.6 (https://github.com/llvm/llvm-project f28c006a5895fc0e329fe15fead81e37457cb1d1)
reproduce: (https://download.01.org/0day-ci/archive/20240901/202409010304.Ivj4eQN6-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202409010304.Ivj4eQN6-lkp@intel.com/

All errors (new ones prefixed by >>):

>> drivers/ufs/core/ufshcd.c:6505:6: error: implicit declaration of function 'is_mcq_enabled' is invalid in C99 [-Werror,-Wimplicit-function-declaration]
           if (is_mcq_enabled(hba) && (*ret == 0))
               ^
   1 error generated.


vim +/is_mcq_enabled +6505 drivers/ufs/core/ufshcd.c

  6488	
  6489	static bool ufshcd_abort_one(struct request *rq, void *priv)
  6490	{
  6491		int *ret = priv;
  6492		u32 tag = rq->tag;
  6493		struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
  6494		struct scsi_device *sdev = cmd->device;
  6495		struct Scsi_Host *shost = sdev->host;
  6496		struct ufs_hba *hba = shost_priv(shost);
  6497		struct ufshcd_lrb *lrbp = &hba->lrb[tag];
  6498	
  6499		*ret = ufshcd_try_to_abort_task(hba, tag);
  6500		dev_err(hba->dev, "Aborting tag %d / CDB %#02x %s\n", tag,
  6501			hba->lrb[tag].cmd ? hba->lrb[tag].cmd->cmnd[0] : -1,
  6502			*ret ? "failed" : "succeeded");
  6503	
  6504		/* Host will post to CQ with OCS_ABORTED after SQ clean up */
> 6505		if (is_mcq_enabled(hba) && (*ret == 0))
  6506			lrbp->host_initiate_abort = true;
  6507	
  6508		return *ret == 0;
  6509	}
  6510	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki