Merge patch series "ufs: core: mcq: Add ufshcd_abort() and error handler support in MCQ mode"

Bao D. Nguyen <quic_nguyenb@quicinc.com> says:

This patch series enables support for ufshcd_abort() and error handler
in MCQ mode.

Link: https://lore.kernel.org/r/cover.1685396241.git.quic_nguyenb@quicinc.comSigned-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/ufs/core/ufs-mcq.c

@@ -12,6 +12,10 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include "ufshcd-priv.h"
+#include <linux/delay.h>
+#include <scsi/scsi_cmnd.h>
+#include <linux/bitfield.h>
+#include <linux/iopoll.h>
 
 #define MAX_QUEUE_SUP GENMASK(7, 0)
 #define UFS_MCQ_MIN_RW_QUEUES 2
@@ -27,6 +31,9 @@
 #define MCQ_ENTRY_SIZE_IN_DWORD	8
 #define CQE_UCD_BA GENMASK_ULL(63, 7)
 
+/* Max mcq register polling time in microseconds */
+#define MCQ_POLL_US 500000
+
 static int rw_queue_count_set(const char *val, const struct kernel_param *kp)
 {
 	return param_set_uint_minmax(val, kp, UFS_MCQ_MIN_RW_QUEUES,
@@ -269,16 +276,38 @@ static int ufshcd_mcq_get_tag(struct ufs_hba *hba,
 }
 
 static void ufshcd_mcq_process_cqe(struct ufs_hba *hba,
-					    struct ufs_hw_queue *hwq)
+				   struct ufs_hw_queue *hwq)
 {
 	struct cq_entry *cqe = ufshcd_mcq_cur_cqe(hwq);
 	int tag = ufshcd_mcq_get_tag(hba, hwq, cqe);
 
-	ufshcd_compl_one_cqe(hba, tag, cqe);
+	if (cqe->command_desc_base_addr) {
+		ufshcd_compl_one_cqe(hba, tag, cqe);
+		/* After processed the cqe, mark it empty (invalid) entry */
+		cqe->command_desc_base_addr = 0;
+	}
 }
 
-unsigned long ufshcd_mcq_poll_cqe_nolock(struct ufs_hba *hba,
-					 struct ufs_hw_queue *hwq)
+void ufshcd_mcq_compl_all_cqes_lock(struct ufs_hba *hba,
+				    struct ufs_hw_queue *hwq)
+{
+	unsigned long flags;
+	u32 entries = hwq->max_entries;
+
+	spin_lock_irqsave(&hwq->cq_lock, flags);
+	while (entries > 0) {
+		ufshcd_mcq_process_cqe(hba, hwq);
+		ufshcd_mcq_inc_cq_head_slot(hwq);
+		entries--;
+	}
+
+	ufshcd_mcq_update_cq_tail_slot(hwq);
+	hwq->cq_head_slot = hwq->cq_tail_slot;
+	spin_unlock_irqrestore(&hwq->cq_lock, flags);
+}
+
+static unsigned long ufshcd_mcq_poll_cqe_nolock(struct ufs_hba *hba,
+						struct ufs_hw_queue *hwq)
 {
 	unsigned long completed_reqs = 0;
 
@@ -294,7 +323,6 @@ unsigned long ufshcd_mcq_poll_cqe_nolock(struct ufs_hba *hba,
 
 	return completed_reqs;
 }
-EXPORT_SYMBOL_GPL(ufshcd_mcq_poll_cqe_nolock);
 
 unsigned long ufshcd_mcq_poll_cqe_lock(struct ufs_hba *hba,
 				       struct ufs_hw_queue *hwq)
@@ -307,6 +335,7 @@ unsigned long ufshcd_mcq_poll_cqe_lock(struct ufs_hba *hba,
 
 	return completed_reqs;
 }
+EXPORT_SYMBOL_GPL(ufshcd_mcq_poll_cqe_lock);
 
 void ufshcd_mcq_make_queues_operational(struct ufs_hba *hba)
 {
@@ -419,6 +448,7 @@ int ufshcd_mcq_init(struct ufs_hba *hba)
 		hwq->max_entries = hba->nutrs;
 		spin_lock_init(&hwq->sq_lock);
 		spin_lock_init(&hwq->cq_lock);
+		mutex_init(&hwq->sq_mutex);
 	}
 
 	/* The very first HW queue serves device commands */
@@ -429,3 +459,222 @@ int ufshcd_mcq_init(struct ufs_hba *hba)
 	host->host_tagset = 1;
 	return 0;
 }
+
+static int ufshcd_mcq_sq_stop(struct ufs_hba *hba, struct ufs_hw_queue *hwq)
+{
+	void __iomem *reg;
+	u32 id = hwq->id, val;
+	int err;
+
+	writel(SQ_STOP, mcq_opr_base(hba, OPR_SQD, id) + REG_SQRTC);
+	reg = mcq_opr_base(hba, OPR_SQD, id) + REG_SQRTS;
+	err = read_poll_timeout(readl, val, val & SQ_STS, 20,
+				MCQ_POLL_US, false, reg);
+	if (err)
+		dev_err(hba->dev, "%s: failed. hwq-id=%d, err=%d\n",
+			__func__, id, err);
+	return err;
+}
+
+static int ufshcd_mcq_sq_start(struct ufs_hba *hba, struct ufs_hw_queue *hwq)
+{
+	void __iomem *reg;
+	u32 id = hwq->id, val;
+	int err;
+
+	writel(SQ_START, mcq_opr_base(hba, OPR_SQD, id) + REG_SQRTC);
+	reg = mcq_opr_base(hba, OPR_SQD, id) + REG_SQRTS;
+	err = read_poll_timeout(readl, val, !(val & SQ_STS), 20,
+				MCQ_POLL_US, false, reg);
+	if (err)
+		dev_err(hba->dev, "%s: failed. hwq-id=%d, err=%d\n",
+			__func__, id, err);
+	return err;
+}
+
+/**
+ * ufshcd_mcq_sq_cleanup - Clean up submission queue resources
+ * associated with the pending command.
+ * @hba - per adapter instance.
+ * @task_tag - The command's task tag.
+ *
+ * Returns 0 for success; error code otherwise.
+ */
+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 ufs_hw_queue *hwq;
+	void __iomem *reg, *opr_sqd_base;
+	u32 nexus, id, val;
+	int err;
+
+	if (task_tag != hba->nutrs - UFSHCD_NUM_RESERVED) {
+		if (!cmd)
+			return -EINVAL;
+		hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd));
+	} else {
+		hwq = hba->dev_cmd_queue;
+	}
+
+	id = hwq->id;
+
+	mutex_lock(&hwq->sq_mutex);
+
+	/* stop the SQ fetching before working on it */
+	err = ufshcd_mcq_sq_stop(hba, hwq);
+	if (err)
+		goto unlock;
+
+	/* SQCTI = EXT_IID, IID, LUN, Task Tag */
+	nexus = lrbp->lun << 8 | task_tag;
+	opr_sqd_base = mcq_opr_base(hba, OPR_SQD, id);
+	writel(nexus, opr_sqd_base + REG_SQCTI);
+
+	/* SQRTCy.ICU = 1 */
+	writel(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,
+			FIELD_GET(SQ_ICU_ERR_CODE_MASK, readl(reg)));
+
+	if (ufshcd_mcq_sq_start(hba, hwq))
+		err = -ETIMEDOUT;
+
+unlock:
+	mutex_unlock(&hwq->sq_mutex);
+	return err;
+}
+
+/**
+ * ufshcd_mcq_nullify_sqe - Nullify the submission queue entry.
+ * Write the sqe's Command Type to 0xF. The host controller will not
+ * fetch any sqe with Command Type = 0xF.
+ *
+ * @utrd - UTP Transfer Request Descriptor to be nullified.
+ */
+static void ufshcd_mcq_nullify_sqe(struct utp_transfer_req_desc *utrd)
+{
+	u32 dword_0;
+
+	dword_0 = le32_to_cpu(utrd->header.dword_0);
+	dword_0 &= ~UPIU_COMMAND_TYPE_MASK;
+	dword_0 |= FIELD_PREP(UPIU_COMMAND_TYPE_MASK, 0xF);
+	utrd->header.dword_0 = cpu_to_le32(dword_0);
+}
+
+/**
+ * ufshcd_mcq_sqe_search - Search for the command in the submission queue
+ * If the command is in the submission queue and not issued to the device yet,
+ * nullify the sqe so the host controller will skip fetching the sqe.
+ *
+ * @hba - per adapter instance.
+ * @hwq - Hardware Queue to be searched.
+ * @task_tag - The command's task tag.
+ *
+ * Returns true if the SQE containing the command is present in the SQ
+ * (not fetched by the controller); returns false if the SQE is not in the SQ.
+ */
+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 utp_transfer_req_desc *utrd;
+	u32 mask = hwq->max_entries - 1;
+	__le64  cmd_desc_base_addr;
+	bool ret = false;
+	u64 addr, match;
+	u32 sq_head_slot;
+
+	mutex_lock(&hwq->sq_mutex);
+
+	ufshcd_mcq_sq_stop(hba, hwq);
+	sq_head_slot = ufshcd_mcq_get_sq_head_slot(hwq);
+	if (sq_head_slot == hwq->sq_tail_slot)
+		goto out;
+
+	cmd_desc_base_addr = lrbp->utr_descriptor_ptr->command_desc_base_addr;
+	addr = le64_to_cpu(cmd_desc_base_addr) & CQE_UCD_BA;
+
+	while (sq_head_slot != hwq->sq_tail_slot) {
+		utrd = hwq->sqe_base_addr +
+				sq_head_slot * sizeof(struct utp_transfer_req_desc);
+		match = le64_to_cpu(utrd->command_desc_base_addr) & CQE_UCD_BA;
+		if (addr == match) {
+			ufshcd_mcq_nullify_sqe(utrd);
+			ret = true;
+			goto out;
+		}
+		sq_head_slot = (sq_head_slot + 1) & mask;
+	}
+
+out:
+	ufshcd_mcq_sq_start(hba, hwq);
+	mutex_unlock(&hwq->sq_mutex);
+	return ret;
+}
+
+/**
+ * ufshcd_mcq_abort - Abort the command in MCQ.
+ * @cmd - The command to be aborted.
+ *
+ * Returns SUCCESS or FAILED error codes
+ */
+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 ufs_hw_queue *hwq;
+	int err = FAILED;
+
+	if (!ufshcd_cmd_inflight(lrbp->cmd)) {
+		dev_err(hba->dev,
+			"%s: skip abort. cmd at tag %d already completed.\n",
+			__func__, tag);
+		goto out;
+	}
+
+	/* Skip task abort in case previous aborts failed and report failure */
+	if (lrbp->req_abort_skip) {
+		dev_err(hba->dev, "%s: skip abort. tag %d failed earlier\n",
+			__func__, tag);
+		goto out;
+	}
+
+	hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd));
+
+	if (ufshcd_mcq_sqe_search(hba, hwq, tag)) {
+		/*
+		 * Failure. The command should not be "stuck" in SQ for
+		 * a long time which resulted in command being aborted.
+		 */
+		dev_err(hba->dev, "%s: cmd found in sq. hwq=%d, tag=%d\n",
+			__func__, hwq->id, tag);
+		goto out;
+	}
+
+	/*
+	 * The command is not in the submission queue, and it is not
+	 * in the completion queue either. Query the device to see if
+	 * the command is being processed in the device.
+	 */
+	if (ufshcd_try_to_abort_task(hba, tag)) {
+		dev_err(hba->dev, "%s: device abort failed %d\n", __func__, err);
+		lrbp->req_abort_skip = true;
+		goto out;
+	}
+
+	err = SUCCESS;
+	if (ufshcd_cmd_inflight(lrbp->cmd))
+		ufshcd_release_scsi_cmd(hba, lrbp);
+
+out:
+	return err;
+}

drivers/ufs/core/ufshcd-priv.h

@@ -71,12 +71,18 @@ void ufshcd_mcq_config_mac(struct ufs_hba *hba, u32 max_active_cmds);
 void ufshcd_mcq_select_mcq_mode(struct ufs_hba *hba);
 u32 ufshcd_mcq_read_cqis(struct ufs_hba *hba, int i);
 void ufshcd_mcq_write_cqis(struct ufs_hba *hba, u32 val, int i);
-unsigned long ufshcd_mcq_poll_cqe_nolock(struct ufs_hba *hba,
-					 struct ufs_hw_queue *hwq);
 struct ufs_hw_queue *ufshcd_mcq_req_to_hwq(struct ufs_hba *hba,
 					   struct request *req);
 unsigned long ufshcd_mcq_poll_cqe_lock(struct ufs_hba *hba,
 				       struct ufs_hw_queue *hwq);
+void ufshcd_mcq_compl_all_cqes_lock(struct ufs_hba *hba,
+				    struct ufs_hw_queue *hwq);
+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);
 
 #define UFSHCD_MCQ_IO_QUEUE_OFFSET	1
 #define SD_ASCII_STD true
@@ -401,4 +407,12 @@ static inline struct cq_entry *ufshcd_mcq_cur_cqe(struct ufs_hw_queue *q)
 
 	return cqe + q->cq_head_slot;
 }
+
+static inline u32 ufshcd_mcq_get_sq_head_slot(struct ufs_hw_queue *q)
+{
+	u32 val = readl(q->mcq_sq_head);
+
+	return val / sizeof(struct utp_transfer_req_desc);
+}
+
 #endif /* _UFSHCD_PRIV_H_ */

drivers/ufs/host/ufs-qcom.c

@@ -1556,7 +1556,7 @@ static irqreturn_t ufs_qcom_mcq_esi_handler(int irq, void *__hba)
 	struct ufs_hw_queue *hwq = &hba->uhq[id];
 
 	ufshcd_mcq_write_cqis(hba, 0x1, id);
-	ufshcd_mcq_poll_cqe_nolock(hba, hwq);
+	ufshcd_mcq_poll_cqe_lock(hba, hwq);
 
 	return IRQ_HANDLED;
 }

include/ufs/ufshcd.h

@@ -1087,6 +1087,7 @@ struct ufs_hba {
  * @cq_tail_slot: current slot to which CQ tail pointer is pointing
  * @cq_head_slot: current slot to which CQ head pointer is pointing
  * @cq_lock: Synchronize between multiple polling instances
+ * @sq_mutex: prevent submission queue concurrent access
  */
 struct ufs_hw_queue {
 	void __iomem *mcq_sq_head;
@@ -1105,6 +1106,8 @@ struct ufs_hw_queue {
 	u32 cq_tail_slot;
 	u32 cq_head_slot;
 	spinlock_t cq_lock;
+	/* prevent concurrent access to submission queue */
+	struct mutex sq_mutex;
 };
 
 static inline bool is_mcq_enabled(struct ufs_hba *hba)
@@ -1240,7 +1243,7 @@ void ufshcd_update_evt_hist(struct ufs_hba *hba, u32 id, u32 val);
 void ufshcd_hba_stop(struct ufs_hba *hba);
 void ufshcd_schedule_eh_work(struct ufs_hba *hba);
 void ufshcd_mcq_write_cqis(struct ufs_hba *hba, u32 val, int i);
-unsigned long ufshcd_mcq_poll_cqe_nolock(struct ufs_hba *hba,
+unsigned long ufshcd_mcq_poll_cqe_lock(struct ufs_hba *hba,
 					 struct ufs_hw_queue *hwq);
 void ufshcd_mcq_enable_esi(struct ufs_hba *hba);
 void ufshcd_mcq_config_esi(struct ufs_hba *hba, struct msi_msg *msg);

include/ufs/ufshci.h

@@ -99,6 +99,9 @@ enum {
 enum {
 	REG_SQHP		= 0x0,
 	REG_SQTP		= 0x4,
+	REG_SQRTC		= 0x8,
+	REG_SQCTI		= 0xC,
+	REG_SQRTS		= 0x10,
 };
 
 enum {
@@ -111,12 +114,26 @@ enum {
 	REG_CQIE		= 0x4,
 };
 
+enum {
+	SQ_START		= 0x0,
+	SQ_STOP			= 0x1,
+	SQ_ICU			= 0x2,
+};
+
+enum {
+	SQ_STS			= 0x1,
+	SQ_CUS			= 0x2,
+};
+
+#define SQ_ICU_ERR_CODE_MASK		GENMASK(7, 4)
+#define UPIU_COMMAND_TYPE_MASK		GENMASK(31, 28)
 #define UFS_MASK(mask, offset)		((mask) << (offset))
 
 /* UFS Version 08h */
 #define MINOR_VERSION_NUM_MASK		UFS_MASK(0xFFFF, 0)
 #define MAJOR_VERSION_NUM_MASK		UFS_MASK(0xFFFF, 16)
 
+#define UFSHCD_NUM_RESERVED	1
 /*
  * Controller UFSHCI version
  * - 2.x and newer use the following scheme:
@@ -503,8 +520,7 @@ struct request_desc_header {
 /**
  * struct utp_transfer_req_desc - UTP Transfer Request Descriptor (UTRD)
  * @header: UTRD header DW-0 to DW-3
- * @command_desc_base_addr_lo: UCD base address low DW-4
- * @command_desc_base_addr_hi: UCD base address high DW-5
+ * @command_desc_base_addr: UCD base address DW 4-5
  * @response_upiu_length: response UPIU length DW-6
  * @response_upiu_offset: response UPIU offset DW-6
  * @prd_table_length: Physical region descriptor length DW-7
@@ -516,8 +532,7 @@ struct utp_transfer_req_desc {
 	struct request_desc_header header;
 
 	/* DW 4-5*/
-	__le32  command_desc_base_addr_lo;
-	__le32  command_desc_base_addr_hi;
+	__le64  command_desc_base_addr;
 
 	/* DW 6 */
 	__le16  response_upiu_length;