scsi: ufs: core: Optimize the hot path

Set .cmd_size in the SCSI host template such that the SCSI core makes
struct scsi_cmnd and struct ufshcd_lrb adjacent. Convert the cmd->lrbp
and lrbp->cmd memory loads into pointer offset calculations. Remove the
data structure members that became superfluous, namely ufshcd_lrb.cmd
and ufs_hba.lrb. Since ufshcd_lrb.cmd is removed, this pointer cannot be
used anymore to test whether or not a command is a SCSI command.
Introduce a new function for this purpose, namely ufshcd_is_scsi_cmd().

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20251031204029.2883185-24-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

Author: bvanassche

drivers/ufs/core/ufs-mcq.c

@@ -534,8 +534,8 @@ static int ufshcd_mcq_sq_start(struct ufs_hba *hba, struct ufs_hw_queue *hwq)
  */
 int ufshcd_mcq_sq_cleanup(struct ufs_hba *hba, int task_tag)
 {
-	struct ufshcd_lrb *lrbp = &hba->lrb[task_tag];
-	struct scsi_cmnd *cmd = lrbp->cmd;
+	struct scsi_cmnd *cmd = ufshcd_tag_to_cmd(hba, task_tag);
+	struct ufshcd_lrb *lrbp = scsi_cmd_priv(cmd);
 	struct ufs_hw_queue *hwq;
 	void __iomem *reg, *opr_sqd_base;
 	u32 nexus, id, val;
@@ -618,7 +618,8 @@ static void ufshcd_mcq_nullify_sqe(struct utp_transfer_req_desc *utrd)
 static bool ufshcd_mcq_sqe_search(struct ufs_hba *hba,
 				  struct ufs_hw_queue *hwq, int task_tag)
 {
-	struct ufshcd_lrb *lrbp = &hba->lrb[task_tag];
+	struct scsi_cmnd *cmd = ufshcd_tag_to_cmd(hba, task_tag);
+	struct ufshcd_lrb *lrbp = scsi_cmd_priv(cmd);
 	struct utp_transfer_req_desc *utrd;
 	__le64  cmd_desc_base_addr;
 	bool ret = false;
@@ -669,7 +670,7 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd)
 	struct Scsi_Host *host = cmd->device->host;
 	struct ufs_hba *hba = shost_priv(host);
 	int tag = scsi_cmd_to_rq(cmd)->tag;
-	struct ufshcd_lrb *lrbp = &hba->lrb[tag];
+	struct ufshcd_lrb *lrbp = scsi_cmd_priv(cmd);
 	struct ufs_hw_queue *hwq;
 	int err;
 

drivers/ufs/core/ufshcd-crypto.h

@@ -38,10 +38,10 @@ ufshcd_prepare_req_desc_hdr_crypto(struct ufshcd_lrb *lrbp,
 }
 
 static inline int ufshcd_crypto_fill_prdt(struct ufs_hba *hba,
-					  struct ufshcd_lrb *lrbp)
+					  struct scsi_cmnd *cmd)
 {
-	struct scsi_cmnd *cmd = lrbp->cmd;
 	const struct bio_crypt_ctx *crypt_ctx = scsi_cmd_to_rq(cmd)->crypt_ctx;
+	struct ufshcd_lrb *lrbp = scsi_cmd_priv(cmd);
 
 	if (crypt_ctx && hba->vops && hba->vops->fill_crypto_prdt)
 		return hba->vops->fill_crypto_prdt(hba, crypt_ctx,
@@ -51,17 +51,19 @@ static inline int ufshcd_crypto_fill_prdt(struct ufs_hba *hba,
 }
 
 static inline void ufshcd_crypto_clear_prdt(struct ufs_hba *hba,
-					    struct ufshcd_lrb *lrbp)
+					    struct scsi_cmnd *cmd)
 {
+	struct ufshcd_lrb *lrbp = scsi_cmd_priv(cmd);
+
 	if (!(hba->quirks & UFSHCD_QUIRK_KEYS_IN_PRDT))
 		return;
 
-	if (!(scsi_cmd_to_rq(lrbp->cmd)->crypt_ctx))
+	if (!(scsi_cmd_to_rq(cmd)->crypt_ctx))
 		return;
 
 	/* Zeroize the PRDT because it can contain cryptographic keys. */
 	memzero_explicit(lrbp->ucd_prdt_ptr,
-			 ufshcd_sg_entry_size(hba) * scsi_sg_count(lrbp->cmd));
+			 ufshcd_sg_entry_size(hba) * scsi_sg_count(cmd));
 }
 
 bool ufshcd_crypto_enable(struct ufs_hba *hba);
@@ -82,13 +84,15 @@ ufshcd_prepare_req_desc_hdr_crypto(struct ufshcd_lrb *lrbp,
 				   struct request_desc_header *h) { }
 
 static inline int ufshcd_crypto_fill_prdt(struct ufs_hba *hba,
-					  struct ufshcd_lrb *lrbp)
+					  struct scsi_cmnd *cmd)
 {
 	return 0;
 }
 
 static inline void ufshcd_crypto_clear_prdt(struct ufs_hba *hba,
-					    struct ufshcd_lrb *lrbp) { }
+					    struct scsi_cmnd *cmd)
+{
+}
 
 static inline bool ufshcd_crypto_enable(struct ufs_hba *hba)
 {

drivers/ufs/core/ufshcd-priv.h

@@ -77,8 +77,7 @@ bool ufshcd_cmd_inflight(struct scsi_cmnd *cmd);
 int ufshcd_mcq_sq_cleanup(struct ufs_hba *hba, int task_tag);
 int ufshcd_mcq_abort(struct scsi_cmnd *cmd);
 int ufshcd_try_to_abort_task(struct ufs_hba *hba, int tag);
-void ufshcd_release_scsi_cmd(struct ufs_hba *hba,
-			     struct ufshcd_lrb *lrbp);
+void ufshcd_release_scsi_cmd(struct ufs_hba *hba, struct scsi_cmnd *cmd);
 
 #define SD_ASCII_STD true
 #define SD_RAW false
@@ -363,6 +362,44 @@ static inline bool ufs_is_valid_unit_desc_lun(struct ufs_dev_info *dev_info, u8
 	return lun == UFS_UPIU_RPMB_WLUN || (lun < dev_info->max_lu_supported);
 }
 
+/*
+ * Convert a block layer tag into a SCSI command pointer. This function is
+ * called once per I/O completion path and is also called from error paths.
+ */
+static inline struct scsi_cmnd *ufshcd_tag_to_cmd(struct ufs_hba *hba, u32 tag)
+{
+	struct blk_mq_tags *tags = hba->host->tag_set.shared_tags;
+	struct request *rq;
+
+	/*
+	 * Handle reserved tags differently because the UFS driver does not
+	 * call blk_mq_alloc_request() for allocating reserved requests.
+	 * Allocating reserved tags with blk_mq_alloc_request() would require
+	 * the following:
+	 * - Allocate an additional request queue from &hba->host->tag_set for
+	 *   allocating reserved requests from.
+	 * - For that request queue, allocate a SCSI device.
+	 * - Calling blk_mq_alloc_request(hba->dev_mgmt_queue, REQ_OP_DRV_OUT,
+	 *   BLK_MQ_REQ_RESERVED) for allocating a reserved request and
+	 *   blk_mq_free_request() for freeing reserved requests.
+	 * - Set the .device pointer for these reserved requests.
+	 * - Submit reserved requests with blk_execute_rq().
+	 * - Modify ufshcd_queuecommand() such that it handles reserved requests
+	 *   in another way than SCSI requests.
+	 * - Modify ufshcd_compl_one_cqe() such that it calls scsi_done() for
+	 *   device management commands.
+	 * - Modify all callback functions called by blk_mq_tagset_busy_iter()
+	 *   calls in the UFS driver and skip device management commands.
+	 */
+	rq = tag < UFSHCD_NUM_RESERVED ? tags->static_rqs[tag] :
+					 blk_mq_tag_to_rq(tags, tag);
+
+	if (WARN_ON_ONCE(!rq))
+		return NULL;
+
+	return blk_mq_rq_to_pdu(rq);
+}
+
 static inline void ufshcd_inc_sq_tail(struct ufs_hw_queue *q)
 	__must_hold(&q->sq_lock)
 {