Merge patch series "Add Multi Circular Queue Support"

Asutosh Das <quic_asutoshd@quicinc.com> says:

This patch series is an implementation of UFS Multi-Circular Queue.
Please consider this series for next merge window.  This
implementation has been verified on a Qualcomm & MediaTek platform.

UFS Multi-Circular Queue (MCQ) has been added in UFSHCI v4.0 to
improve storage performance.  The implementation uses the shared
tagging mechanism so that tags are shared among the hardware
queues. The number of hardware queues is configurable.  This series
doesn't include the ESI implementation for completion handling.

Link: https://lore.kernel.org/r/cover.1673557949.git.quic_asutoshd@quicinc.comSigned-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/ufs/core/Makefile

 # SPDX-License-Identifier: GPL-2.0
 
 obj-$(CONFIG_SCSI_UFSHCD)		+= ufshcd-core.o
-ufshcd-core-y				+= ufshcd.o ufs-sysfs.o
+ufshcd-core-y				+= ufshcd.o ufs-sysfs.o ufs-mcq.o
 ufshcd-core-$(CONFIG_DEBUG_FS)		+= ufs-debugfs.o
 ufshcd-core-$(CONFIG_SCSI_UFS_BSG)	+= ufs_bsg.o
 ufshcd-core-$(CONFIG_SCSI_UFS_CRYPTO)	+= ufshcd-crypto.o

drivers/ufs/core/ufs-mcq.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022 Qualcomm Innovation Center. All rights reserved.
+ *
+ * Authors:
+ *	Asutosh Das <quic_asutoshd@quicinc.com>
+ *	Can Guo <quic_cang@quicinc.com>
+ */
+
+#include <asm/unaligned.h>
+#include <linux/dma-mapping.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include "ufshcd-priv.h"
+
+#define MAX_QUEUE_SUP GENMASK(7, 0)
+#define UFS_MCQ_MIN_RW_QUEUES 2
+#define UFS_MCQ_MIN_READ_QUEUES 0
+#define UFS_MCQ_NUM_DEV_CMD_QUEUES 1
+#define UFS_MCQ_MIN_POLL_QUEUES 0
+#define QUEUE_EN_OFFSET 31
+#define QUEUE_ID_OFFSET 16
+
+#define MAX_DEV_CMD_ENTRIES	2
+#define MCQ_CFG_MAC_MASK	GENMASK(16, 8)
+#define MCQ_QCFG_SIZE		0x40
+#define MCQ_ENTRY_SIZE_IN_DWORD	8
+#define CQE_UCD_BA GENMASK_ULL(63, 7)
+
+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,
+				     num_possible_cpus());
+}
+
+static const struct kernel_param_ops rw_queue_count_ops = {
+	.set = rw_queue_count_set,
+	.get = param_get_uint,
+};
+
+static unsigned int rw_queues;
+module_param_cb(rw_queues, &rw_queue_count_ops, &rw_queues, 0644);
+MODULE_PARM_DESC(rw_queues,
+		 "Number of interrupt driven I/O queues used for rw. Default value is nr_cpus");
+
+static int read_queue_count_set(const char *val, const struct kernel_param *kp)
+{
+	return param_set_uint_minmax(val, kp, UFS_MCQ_MIN_READ_QUEUES,
+				     num_possible_cpus());
+}
+
+static const struct kernel_param_ops read_queue_count_ops = {
+	.set = read_queue_count_set,
+	.get = param_get_uint,
+};
+
+static unsigned int read_queues;
+module_param_cb(read_queues, &read_queue_count_ops, &read_queues, 0644);
+MODULE_PARM_DESC(read_queues,
+		 "Number of interrupt driven read queues used for read. Default value is 0");
+
+static int poll_queue_count_set(const char *val, const struct kernel_param *kp)
+{
+	return param_set_uint_minmax(val, kp, UFS_MCQ_MIN_POLL_QUEUES,
+				     num_possible_cpus());
+}
+
+static const struct kernel_param_ops poll_queue_count_ops = {
+	.set = poll_queue_count_set,
+	.get = param_get_uint,
+};
+
+static unsigned int poll_queues = 1;
+module_param_cb(poll_queues, &poll_queue_count_ops, &poll_queues, 0644);
+MODULE_PARM_DESC(poll_queues,
+		 "Number of poll queues used for r/w. Default value is 1");
+
+/**
+ * ufshcd_mcq_config_mac - Set the #Max Activ Cmds.
+ * @hba - per adapter instance
+ * @max_active_cmds - maximum # of active commands to the device at any time.
+ *
+ * The controller won't send more than the max_active_cmds to the device at
+ * any time.
+ */
+void ufshcd_mcq_config_mac(struct ufs_hba *hba, u32 max_active_cmds)
+{
+	u32 val;
+
+	val = ufshcd_readl(hba, REG_UFS_MCQ_CFG);
+	val &= ~MCQ_CFG_MAC_MASK;
+	val |= FIELD_PREP(MCQ_CFG_MAC_MASK, max_active_cmds);
+	ufshcd_writel(hba, val, REG_UFS_MCQ_CFG);
+}
+
+/**
+ * ufshcd_mcq_req_to_hwq - find the hardware queue on which the
+ * request would be issued.
+ * @hba - per adapter instance
+ * @req - pointer to the request to be issued
+ *
+ * Returns the hardware queue instance on which the request would
+ * be queued.
+ */
+struct ufs_hw_queue *ufshcd_mcq_req_to_hwq(struct ufs_hba *hba,
+					 struct request *req)
+{
+	u32 utag = blk_mq_unique_tag(req);
+	u32 hwq = blk_mq_unique_tag_to_hwq(utag);
+
+	/* uhq[0] is used to serve device commands */
+	return &hba->uhq[hwq + UFSHCD_MCQ_IO_QUEUE_OFFSET];
+}
+
+/**
+ * ufshcd_mcq_decide_queue_depth - decide the queue depth
+ * @hba - per adapter instance
+ *
+ * Returns queue-depth on success, non-zero on error
+ *
+ * MAC - Max. Active Command of the Host Controller (HC)
+ * HC wouldn't send more than this commands to the device.
+ * It is mandatory to implement get_hba_mac() to enable MCQ mode.
+ * Calculates and adjusts the queue depth based on the depth
+ * supported by the HC and ufs device.
+ */
+int ufshcd_mcq_decide_queue_depth(struct ufs_hba *hba)
+{
+	int mac;
+
+	/* Mandatory to implement get_hba_mac() */
+	mac = ufshcd_mcq_vops_get_hba_mac(hba);
+	if (mac < 0) {
+		dev_err(hba->dev, "Failed to get mac, err=%d\n", mac);
+		return mac;
+	}
+
+	WARN_ON_ONCE(!hba->dev_info.bqueuedepth);
+	/*
+	 * max. value of bqueuedepth = 256, mac is host dependent.
+	 * It is mandatory for UFS device to define bQueueDepth if
+	 * shared queuing architecture is enabled.
+	 */
+	return min_t(int, mac, hba->dev_info.bqueuedepth);
+}
+
+static int ufshcd_mcq_config_nr_queues(struct ufs_hba *hba)
+{
+	int i;
+	u32 hba_maxq, rem, tot_queues;
+	struct Scsi_Host *host = hba->host;
+
+	hba_maxq = FIELD_GET(MAX_QUEUE_SUP, hba->mcq_capabilities);
+
+	tot_queues = UFS_MCQ_NUM_DEV_CMD_QUEUES + read_queues + poll_queues +
+			rw_queues;
+
+	if (hba_maxq < tot_queues) {
+		dev_err(hba->dev, "Total queues (%d) exceeds HC capacity (%d)\n",
+			tot_queues, hba_maxq);
+		return -EOPNOTSUPP;
+	}
+
+	rem = hba_maxq - UFS_MCQ_NUM_DEV_CMD_QUEUES;
+
+	if (rw_queues) {
+		hba->nr_queues[HCTX_TYPE_DEFAULT] = rw_queues;
+		rem -= hba->nr_queues[HCTX_TYPE_DEFAULT];
+	} else {
+		rw_queues = num_possible_cpus();
+	}
+
+	if (poll_queues) {
+		hba->nr_queues[HCTX_TYPE_POLL] = poll_queues;
+		rem -= hba->nr_queues[HCTX_TYPE_POLL];
+	}
+
+	if (read_queues) {
+		hba->nr_queues[HCTX_TYPE_READ] = read_queues;
+		rem -= hba->nr_queues[HCTX_TYPE_READ];
+	}
+
+	if (!hba->nr_queues[HCTX_TYPE_DEFAULT])
+		hba->nr_queues[HCTX_TYPE_DEFAULT] = min3(rem, rw_queues,
+							 num_possible_cpus());
+
+	for (i = 0; i < HCTX_MAX_TYPES; i++)
+		host->nr_hw_queues += hba->nr_queues[i];
+
+	hba->nr_hw_queues = host->nr_hw_queues + UFS_MCQ_NUM_DEV_CMD_QUEUES;
+	return 0;
+}
+
+int ufshcd_mcq_memory_alloc(struct ufs_hba *hba)
+{
+	struct ufs_hw_queue *hwq;
+	size_t utrdl_size, cqe_size;
+	int i;
+
+	for (i = 0; i < hba->nr_hw_queues; i++) {
+		hwq = &hba->uhq[i];
+
+		utrdl_size = sizeof(struct utp_transfer_req_desc) *
+			     hwq->max_entries;
+		hwq->sqe_base_addr = dmam_alloc_coherent(hba->dev, utrdl_size,
+							 &hwq->sqe_dma_addr,
+							 GFP_KERNEL);
+		if (!hwq->sqe_dma_addr) {
+			dev_err(hba->dev, "SQE allocation failed\n");
+			return -ENOMEM;
+		}
+
+		cqe_size = sizeof(struct cq_entry) * hwq->max_entries;
+		hwq->cqe_base_addr = dmam_alloc_coherent(hba->dev, cqe_size,
+							 &hwq->cqe_dma_addr,
+							 GFP_KERNEL);
+		if (!hwq->cqe_dma_addr) {
+			dev_err(hba->dev, "CQE allocation failed\n");
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+
+/* Operation and runtime registers configuration */
+#define MCQ_CFG_n(r, i)	((r) + MCQ_QCFG_SIZE * (i))
+#define MCQ_OPR_OFFSET_n(p, i) \
+	(hba->mcq_opr[(p)].offset + hba->mcq_opr[(p)].stride * (i))
+
+static void __iomem *mcq_opr_base(struct ufs_hba *hba,
+					 enum ufshcd_mcq_opr n, int i)
+{
+	struct ufshcd_mcq_opr_info_t *opr = &hba->mcq_opr[n];
+
+	return opr->base + opr->stride * i;
+}
+
+u32 ufshcd_mcq_read_cqis(struct ufs_hba *hba, int i)
+{
+	return readl(mcq_opr_base(hba, OPR_CQIS, i) + REG_CQIS);
+}
+
+void ufshcd_mcq_write_cqis(struct ufs_hba *hba, u32 val, int i)
+{
+	writel(val, mcq_opr_base(hba, OPR_CQIS, i) + REG_CQIS);
+}
+
+/*
+ * Current MCQ specification doesn't provide a Task Tag or its equivalent in
+ * the Completion Queue Entry. Find the Task Tag using an indirect method.
+ */
+static int ufshcd_mcq_get_tag(struct ufs_hba *hba,
+				     struct ufs_hw_queue *hwq,
+				     struct cq_entry *cqe)
+{
+	u64 addr;
+
+	/* sizeof(struct utp_transfer_cmd_desc) must be a multiple of 128 */
+	BUILD_BUG_ON(sizeof(struct utp_transfer_cmd_desc) & GENMASK(6, 0));
+
+	/* Bits 63:7 UCD base address, 6:5 are reserved, 4:0 is SQ ID */
+	addr = (le64_to_cpu(cqe->command_desc_base_addr) & CQE_UCD_BA) -
+		hba->ucdl_dma_addr;
+
+	return div_u64(addr, sizeof(struct utp_transfer_cmd_desc));
+}
+
+static void ufshcd_mcq_process_cqe(struct ufs_hba *hba,
+					    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);
+}
+
+unsigned long ufshcd_mcq_poll_cqe_nolock(struct ufs_hba *hba,
+					 struct ufs_hw_queue *hwq)
+{
+	unsigned long completed_reqs = 0;
+
+	ufshcd_mcq_update_cq_tail_slot(hwq);
+	while (!ufshcd_mcq_is_cq_empty(hwq)) {
+		ufshcd_mcq_process_cqe(hba, hwq);
+		ufshcd_mcq_inc_cq_head_slot(hwq);
+		completed_reqs++;
+	}
+
+	if (completed_reqs)
+		ufshcd_mcq_update_cq_head(hwq);
+
+	return completed_reqs;
+}
+
+unsigned long ufshcd_mcq_poll_cqe_lock(struct ufs_hba *hba,
+				       struct ufs_hw_queue *hwq)
+{
+	unsigned long completed_reqs;
+
+	spin_lock(&hwq->cq_lock);
+	completed_reqs = ufshcd_mcq_poll_cqe_nolock(hba, hwq);
+	spin_unlock(&hwq->cq_lock);
+
+	return completed_reqs;
+}
+
+void ufshcd_mcq_make_queues_operational(struct ufs_hba *hba)
+{
+	struct ufs_hw_queue *hwq;
+	u16 qsize;
+	int i;
+
+	for (i = 0; i < hba->nr_hw_queues; i++) {
+		hwq = &hba->uhq[i];
+		hwq->id = i;
+		qsize = hwq->max_entries * MCQ_ENTRY_SIZE_IN_DWORD - 1;
+
+		/* Submission Queue Lower Base Address */
+		ufsmcq_writelx(hba, lower_32_bits(hwq->sqe_dma_addr),
+			      MCQ_CFG_n(REG_SQLBA, i));
+		/* Submission Queue Upper Base Address */
+		ufsmcq_writelx(hba, upper_32_bits(hwq->sqe_dma_addr),
+			      MCQ_CFG_n(REG_SQUBA, i));
+		/* Submission Queue Doorbell Address Offset */
+		ufsmcq_writelx(hba, MCQ_OPR_OFFSET_n(OPR_SQD, i),
+			      MCQ_CFG_n(REG_SQDAO, i));
+		/* Submission Queue Interrupt Status Address Offset */
+		ufsmcq_writelx(hba, MCQ_OPR_OFFSET_n(OPR_SQIS, i),
+			      MCQ_CFG_n(REG_SQISAO, i));
+
+		/* Completion Queue Lower Base Address */
+		ufsmcq_writelx(hba, lower_32_bits(hwq->cqe_dma_addr),
+			      MCQ_CFG_n(REG_CQLBA, i));
+		/* Completion Queue Upper Base Address */
+		ufsmcq_writelx(hba, upper_32_bits(hwq->cqe_dma_addr),
+			      MCQ_CFG_n(REG_CQUBA, i));
+		/* Completion Queue Doorbell Address Offset */
+		ufsmcq_writelx(hba, MCQ_OPR_OFFSET_n(OPR_CQD, i),
+			      MCQ_CFG_n(REG_CQDAO, i));
+		/* Completion Queue Interrupt Status Address Offset */
+		ufsmcq_writelx(hba, MCQ_OPR_OFFSET_n(OPR_CQIS, i),
+			      MCQ_CFG_n(REG_CQISAO, i));
+
+		/* Save the base addresses for quicker access */
+		hwq->mcq_sq_head = mcq_opr_base(hba, OPR_SQD, i) + REG_SQHP;
+		hwq->mcq_sq_tail = mcq_opr_base(hba, OPR_SQD, i) + REG_SQTP;
+		hwq->mcq_cq_head = mcq_opr_base(hba, OPR_CQD, i) + REG_CQHP;
+		hwq->mcq_cq_tail = mcq_opr_base(hba, OPR_CQD, i) + REG_CQTP;
+
+		/* Reinitializing is needed upon HC reset */
+		hwq->sq_tail_slot = hwq->cq_tail_slot = hwq->cq_head_slot = 0;
+
+		/* Enable Tail Entry Push Status interrupt only for non-poll queues */
+		if (i < hba->nr_hw_queues - hba->nr_queues[HCTX_TYPE_POLL])
+			writel(1, mcq_opr_base(hba, OPR_CQIS, i) + REG_CQIE);
+
+		/* Completion Queue Enable|Size to Completion Queue Attribute */
+		ufsmcq_writel(hba, (1 << QUEUE_EN_OFFSET) | qsize,
+			      MCQ_CFG_n(REG_CQATTR, i));
+
+		/*
+		 * Submission Qeueue Enable|Size|Completion Queue ID to
+		 * Submission Queue Attribute
+		 */
+		ufsmcq_writel(hba, (1 << QUEUE_EN_OFFSET) | qsize |
+			      (i << QUEUE_ID_OFFSET),
+			      MCQ_CFG_n(REG_SQATTR, i));
+	}
+}
+
+int ufshcd_mcq_init(struct ufs_hba *hba)
+{
+	struct Scsi_Host *host = hba->host;
+	struct ufs_hw_queue *hwq;
+	int ret, i;
+
+	ret = ufshcd_mcq_config_nr_queues(hba);
+	if (ret)
+		return ret;
+
+	ret = ufshcd_vops_mcq_config_resource(hba);
+	if (ret)
+		return ret;
+
+	ret = ufshcd_mcq_vops_op_runtime_config(hba);
+	if (ret) {
+		dev_err(hba->dev, "Operation runtime config failed, ret=%d\n",
+			ret);
+		return ret;
+	}
+	hba->uhq = devm_kzalloc(hba->dev,
+				hba->nr_hw_queues * sizeof(struct ufs_hw_queue),
+				GFP_KERNEL);
+	if (!hba->uhq) {
+		dev_err(hba->dev, "ufs hw queue memory allocation failed\n");
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < hba->nr_hw_queues; i++) {
+		hwq = &hba->uhq[i];
+		hwq->max_entries = hba->nutrs;
+		spin_lock_init(&hwq->sq_lock);
+		spin_lock_init(&hwq->cq_lock);
+	}
+
+	/* The very first HW queue serves device commands */
+	hba->dev_cmd_queue = &hba->uhq[0];
+	/* Give dev_cmd_queue the minimal number of entries */
+	hba->dev_cmd_queue->max_entries = MAX_DEV_CMD_ENTRIES;
+
+	host->host_tagset = 1;
+	return 0;
+}

drivers/ufs/core/ufshcd-priv.h

@@ -61,7 +61,24 @@ int ufshcd_query_attr(struct ufs_hba *hba, enum query_opcode opcode,
 int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode,
 	enum flag_idn idn, u8 index, bool *flag_res);
 void ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit);
-
+void ufshcd_compl_one_cqe(struct ufs_hba *hba, int task_tag,
+			  struct cq_entry *cqe);
+int ufshcd_mcq_init(struct ufs_hba *hba);
+int ufshcd_mcq_decide_queue_depth(struct ufs_hba *hba);
+int ufshcd_mcq_memory_alloc(struct ufs_hba *hba);
+void ufshcd_mcq_make_queues_operational(struct ufs_hba *hba);
+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);
+
+#define UFSHCD_MCQ_IO_QUEUE_OFFSET	1
 #define SD_ASCII_STD true
 #define SD_RAW false
 int ufshcd_read_string_desc(struct ufs_hba *hba, u8 desc_index,
@@ -229,6 +246,39 @@ static inline void ufshcd_vops_reinit_notify(struct ufs_hba *hba)
 		hba->vops->reinit_notify(hba);
 }
 
+static inline int ufshcd_vops_mcq_config_resource(struct ufs_hba *hba)
+{
+	if (hba->vops && hba->vops->mcq_config_resource)
+		return hba->vops->mcq_config_resource(hba);
+
+	return -EOPNOTSUPP;
+}
+
+static inline int ufshcd_mcq_vops_get_hba_mac(struct ufs_hba *hba)
+{
+	if (hba->vops && hba->vops->get_hba_mac)
+		return hba->vops->get_hba_mac(hba);
+
+	return -EOPNOTSUPP;
+}
+
+static inline int ufshcd_mcq_vops_op_runtime_config(struct ufs_hba *hba)
+{
+	if (hba->vops && hba->vops->op_runtime_config)
+		return hba->vops->op_runtime_config(hba);
+
+	return -EOPNOTSUPP;
+}
+
+static inline int ufshcd_vops_get_outstanding_cqs(struct ufs_hba *hba,
+						  unsigned long *ocqs)
+{
+	if (hba->vops && hba->vops->get_outstanding_cqs)
+		return hba->vops->get_outstanding_cqs(hba, ocqs);
+
+	return -EOPNOTSUPP;
+}
+
 extern const struct ufs_pm_lvl_states ufs_pm_lvl_states[];
 
 /**
@@ -305,4 +355,44 @@ 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);
 }
 
+static inline void ufshcd_inc_sq_tail(struct ufs_hw_queue *q)
+{
+	u32 mask = q->max_entries - 1;
+	u32 val;
+
+	q->sq_tail_slot = (q->sq_tail_slot + 1) & mask;
+	val = q->sq_tail_slot * sizeof(struct utp_transfer_req_desc);
+	writel(val, q->mcq_sq_tail);
+}
+
+static inline void ufshcd_mcq_update_cq_tail_slot(struct ufs_hw_queue *q)
+{
+	u32 val = readl(q->mcq_cq_tail);
+
+	q->cq_tail_slot = val / sizeof(struct cq_entry);
+}
+
+static inline bool ufshcd_mcq_is_cq_empty(struct ufs_hw_queue *q)
+{
+	return q->cq_head_slot == q->cq_tail_slot;
+}
+
+static inline void ufshcd_mcq_inc_cq_head_slot(struct ufs_hw_queue *q)
+{
+	q->cq_head_slot++;
+	if (q->cq_head_slot == q->max_entries)
+		q->cq_head_slot = 0;
+}
+
+static inline void ufshcd_mcq_update_cq_head(struct ufs_hw_queue *q)
+{
+	writel(q->cq_head_slot * sizeof(struct cq_entry), q->mcq_cq_head);
+}
+
+static inline struct cq_entry *ufshcd_mcq_cur_cqe(struct ufs_hw_queue *q)
+{
+	struct cq_entry *cqe = q->cqe_base_addr;
+
+	return cqe + q->cq_head_slot;
+}
 #endif /* _UFSHCD_PRIV_H_ */

drivers/ufs/core/ufshcd.c

@@ -43,6 +43,12 @@
 #define UFSHCD_ENABLE_INTRS	(UTP_TRANSFER_REQ_COMPL |\
 				 UTP_TASK_REQ_COMPL |\
 				 UFSHCD_ERROR_MASK)
+
+#define UFSHCD_ENABLE_MCQ_INTRS	(UTP_TASK_REQ_COMPL |\
+				 UFSHCD_ERROR_MASK |\
+				 MCQ_CQ_EVENT_STATUS)
+
+
 /* UIC command timeout, unit: ms */
 #define UIC_CMD_TIMEOUT	500
 
@@ -92,6 +98,33 @@
 /* Polling time to wait for fDeviceInit */
 #define FDEVICEINIT_COMPL_TIMEOUT 1500 /* millisecs */
 
+/* UFSHC 4.0 compliant HC support this mode, refer param_set_mcq_mode() */
+static bool use_mcq_mode = true;
+
+static bool is_mcq_supported(struct ufs_hba *hba)
+{
+	return hba->mcq_sup && use_mcq_mode;
+}
+
+static int param_set_mcq_mode(const char *val, const struct kernel_param *kp)
+{
+	int ret;
+
+	ret = param_set_bool(val, kp);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static const struct kernel_param_ops mcq_mode_ops = {
+	.set = param_set_mcq_mode,
+	.get = param_get_bool,
+};
+
+module_param_cb(use_mcq_mode, &mcq_mode_ops, &use_mcq_mode, 0644);
+MODULE_PARM_DESC(use_mcq_mode, "Control MCQ mode for controllers starting from UFSHCI 4.0. 1 - enable MCQ, 0 - disable MCQ. MCQ is enabled by default");
+
 #define ufshcd_toggle_vreg(_dev, _vreg, _on)				\
 	({                                                              \
 		int _ret;                                               \
@@ -743,12 +776,17 @@ static inline bool ufshcd_is_device_present(struct ufs_hba *hba)
 /**
  * ufshcd_get_tr_ocs - Get the UTRD Overall Command Status
  * @lrbp: pointer to local command reference block
+ * @cqe: pointer to the completion queue entry
  *
  * This function is used to get the OCS field from UTRD
  * Returns the OCS field in the UTRD
  */
-static enum utp_ocs ufshcd_get_tr_ocs(struct ufshcd_lrb *lrbp)
+static enum utp_ocs ufshcd_get_tr_ocs(struct ufshcd_lrb *lrbp,
+				      struct cq_entry *cqe)
 {
+	if (cqe)
+		return le32_to_cpu(cqe->status) & MASK_OCS;
+
 	return le32_to_cpu(lrbp->utr_descriptor_ptr->header.dword_2) & MASK_OCS;
 }
 
@@ -2152,9 +2190,11 @@ static void ufshcd_update_monitor(struct ufs_hba *hba, const struct ufshcd_lrb *
  * ufshcd_send_command - Send SCSI or device management commands
  * @hba: per adapter instance
  * @task_tag: Task tag of the command
+ * @hwq: pointer to hardware queue instance
  */
 static inline
-void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag)
+void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag,
+			 struct ufs_hw_queue *hwq)
 {
 	struct ufshcd_lrb *lrbp = &hba->lrb[task_tag];
 	unsigned long flags;
@@ -2168,12 +2208,24 @@ void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag)
 	if (unlikely(ufshcd_should_inform_monitor(hba, lrbp)))
 		ufshcd_start_monitor(hba, lrbp);
 
-	spin_lock_irqsave(&hba->outstanding_lock, flags);
-	if (hba->vops && hba->vops->setup_xfer_req)
-		hba->vops->setup_xfer_req(hba, task_tag, !!lrbp->cmd);
-	__set_bit(task_tag, &hba->outstanding_reqs);
-	ufshcd_writel(hba, 1 << task_tag, REG_UTP_TRANSFER_REQ_DOOR_BELL);
-	spin_unlock_irqrestore(&hba->outstanding_lock, flags);
+	if (is_mcq_enabled(hba)) {
+		int utrd_size = sizeof(struct utp_transfer_req_desc);
+
+		spin_lock(&hwq->sq_lock);
+		memcpy(hwq->sqe_base_addr + (hwq->sq_tail_slot * utrd_size),
+		       lrbp->utr_descriptor_ptr, utrd_size);
+		ufshcd_inc_sq_tail(hwq);
+		spin_unlock(&hwq->sq_lock);
+	} else {
+		spin_lock_irqsave(&hba->outstanding_lock, flags);
+		if (hba->vops && hba->vops->setup_xfer_req)
+			hba->vops->setup_xfer_req(hba, lrbp->task_tag,
+						  !!lrbp->cmd);
+		__set_bit(lrbp->task_tag, &hba->outstanding_reqs);
+		ufshcd_writel(hba, 1 << lrbp->task_tag,
+			      REG_UTP_TRANSFER_REQ_DOOR_BELL);
+		spin_unlock_irqrestore(&hba->outstanding_lock, flags);
+	}
 }
 
 /**
@@ -2261,6 +2313,14 @@ static inline int ufshcd_hba_capabilities(struct ufs_hba *hba)
 	if (err)
 		dev_err(hba->dev, "crypto setup failed\n");
 
+	hba->mcq_sup = FIELD_GET(MASK_MCQ_SUPPORT, hba->capabilities);
+	if (!hba->mcq_sup)
+		return err;
+
+	hba->mcq_capabilities = ufshcd_readl(hba, REG_MCQCAP);
+	hba->ext_iid_sup = FIELD_GET(MASK_EXT_IID_SUPPORT,
+				     hba->mcq_capabilities);
+
 	return err;
 }
 
@@ -2735,24 +2795,28 @@ static inline bool is_device_wlun(struct scsi_device *sdev)
  */
 static void ufshcd_map_queues(struct Scsi_Host *shost)
 {
-	int i;
+	struct ufs_hba *hba = shost_priv(shost);
+	int i, queue_offset = 0;
+
+	if (!is_mcq_supported(hba)) {
+		hba->nr_queues[HCTX_TYPE_DEFAULT] = 1;
+		hba->nr_queues[HCTX_TYPE_READ] = 0;
+		hba->nr_queues[HCTX_TYPE_POLL] = 1;
+		hba->nr_hw_queues = 1;
+	}
 
 	for (i = 0; i < shost->nr_maps; i++) {
 		struct blk_mq_queue_map *map = &shost->tag_set.map[i];
 
-		switch (i) {
-		case HCTX_TYPE_DEFAULT:
-		case HCTX_TYPE_POLL:
-			map->nr_queues = 1;
-			break;
-		case HCTX_TYPE_READ:
-			map->nr_queues = 0;
+		map->nr_queues = hba->nr_queues[i];
+		if (!map->nr_queues)
 			continue;
-		default:
-			WARN_ON_ONCE(true);
-		}
-		map->queue_offset = 0;
+		map->queue_offset = queue_offset;
+		if (i == HCTX_TYPE_POLL && !is_mcq_supported(hba))
+			map->queue_offset = 0;
+
 		blk_mq_map_queues(map);
+		queue_offset += map->nr_queues;
 	}
 }
 
@@ -2791,6 +2855,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	int tag = scsi_cmd_to_rq(cmd)->tag;
 	struct ufshcd_lrb *lrbp;
 	int err = 0;
+	struct ufs_hw_queue *hwq = NULL;
 
 	WARN_ONCE(tag < 0 || tag >= hba->nutrs, "Invalid tag %d\n", tag);
 
@@ -2875,7 +2940,10 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 		goto out;
 	}
 
-	ufshcd_send_command(hba, tag);
+	if (is_mcq_enabled(hba))
+		hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd));
+
+	ufshcd_send_command(hba, tag, hwq);
 
 out:
 	rcu_read_unlock();
@@ -3005,7 +3073,7 @@ static int ufshcd_wait_for_dev_cmd(struct ufs_hba *hba,
 		 * not trigger any race conditions.
 		 */
 		hba->dev_cmd.complete = NULL;
-		err = ufshcd_get_tr_ocs(lrbp);
+		err = ufshcd_get_tr_ocs(lrbp, hba->dev_cmd.cqe);
 		if (!err)
 			err = ufshcd_dev_cmd_completion(hba, lrbp);
 	} else {
@@ -3076,10 +3144,11 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba,
 		goto out;
 
 	hba->dev_cmd.complete = &wait;
+	hba->dev_cmd.cqe = NULL;
 
 	ufshcd_add_query_upiu_trace(hba, UFS_QUERY_SEND, lrbp->ucd_req_ptr);
 
-	ufshcd_send_command(hba, tag);
+	ufshcd_send_command(hba, tag, hba->dev_cmd_queue);
 	err = ufshcd_wait_for_dev_cmd(hba, lrbp, timeout);
 	ufshcd_add_query_upiu_trace(hba, err ? UFS_QUERY_ERR : UFS_QUERY_COMP,
 				    (struct utp_upiu_req *)lrbp->ucd_rsp_ptr);
@@ -3684,6 +3753,14 @@ static int ufshcd_memory_alloc(struct ufs_hba *hba)
 		goto out;
 	}
 
+	/*
+	 * Skip utmrdl allocation; it may have been
+	 * allocated during first pass and not released during
+	 * MCQ memory allocation.
+	 * See ufshcd_release_sdb_queue() and ufshcd_config_mcq()
+	 */
+	if (hba->utmrdl_base_addr)
+		goto skip_utmrdl;
 	/*
 	 * Allocate memory for UTP Task Management descriptors
 	 * UFSHCI requires 1024 byte alignment of UTMRD
@@ -3700,6 +3777,7 @@ static int ufshcd_memory_alloc(struct ufs_hba *hba)
 		goto out;
 	}
 
+skip_utmrdl:
 	/* Allocate memory for local reference block */
 	hba->lrb = devm_kcalloc(hba->dev,
 				hba->nutrs, sizeof(struct ufshcd_lrb),
@@ -5129,18 +5207,20 @@ ufshcd_scsi_cmd_status(struct ufshcd_lrb *lrbp, int scsi_status)
  * ufshcd_transfer_rsp_status - Get overall status of the response
  * @hba: per adapter instance
  * @lrbp: pointer to local reference block of completed command
+ * @cqe: pointer to the completion queue entry
  *
  * Returns result of the command to notify SCSI midlayer
  */
 static inline int
-ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
+ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp,
+			   struct cq_entry *cqe)
 {
 	int result = 0;
 	int scsi_status;
 	enum utp_ocs ocs;
 
 	/* overall command status of utrd */
-	ocs = ufshcd_get_tr_ocs(lrbp);
+	ocs = ufshcd_get_tr_ocs(lrbp, cqe);
 
 	if (hba->quirks & UFSHCD_QUIRK_BROKEN_OCS_FATAL_ERROR) {
 		if (be32_to_cpu(lrbp->ucd_rsp_ptr->header.dword_1) &
@@ -5305,42 +5385,53 @@ static void ufshcd_release_scsi_cmd(struct ufs_hba *hba,
 }
 
 /**
- * __ufshcd_transfer_req_compl - handle SCSI and query command completion
+ * ufshcd_compl_one_cqe - handle a completion queue entry
  * @hba: per adapter instance
- * @completed_reqs: bitmask that indicates which requests to complete
+ * @task_tag: the task tag of the request to be completed
+ * @cqe: pointer to the completion queue entry
  */
-static void __ufshcd_transfer_req_compl(struct ufs_hba *hba,
-					unsigned long completed_reqs)
+void ufshcd_compl_one_cqe(struct ufs_hba *hba, int task_tag,
+			  struct cq_entry *cqe)
 {
 	struct ufshcd_lrb *lrbp;
 	struct scsi_cmnd *cmd;
-	int index;
-
-	for_each_set_bit(index, &completed_reqs, hba->nutrs) {
-		lrbp = &hba->lrb[index];
-		lrbp->compl_time_stamp = ktime_get();
-		lrbp->compl_time_stamp_local_clock = local_clock();
-		cmd = lrbp->cmd;
-		if (cmd) {
-			if (unlikely(ufshcd_should_inform_monitor(hba, lrbp)))
-				ufshcd_update_monitor(hba, lrbp);
-			ufshcd_add_command_trace(hba, index, UFS_CMD_COMP);
-			cmd->result = ufshcd_transfer_rsp_status(hba, lrbp);
-			ufshcd_release_scsi_cmd(hba, lrbp);
-			/* Do not touch lrbp after scsi done */
-			scsi_done(cmd);
-		} else if (lrbp->command_type == UTP_CMD_TYPE_DEV_MANAGE ||
-			lrbp->command_type == UTP_CMD_TYPE_UFS_STORAGE) {
-			if (hba->dev_cmd.complete) {
-				ufshcd_add_command_trace(hba, index,
-							 UFS_DEV_COMP);
-				complete(hba->dev_cmd.complete);
-				ufshcd_clk_scaling_update_busy(hba);
-			}
+
+	lrbp = &hba->lrb[task_tag];
+	lrbp->compl_time_stamp = ktime_get();
+	cmd = lrbp->cmd;
+	if (cmd) {
+		if (unlikely(ufshcd_should_inform_monitor(hba, lrbp)))
+			ufshcd_update_monitor(hba, lrbp);
+		ufshcd_add_command_trace(hba, task_tag, UFS_CMD_COMP);
+		cmd->result = ufshcd_transfer_rsp_status(hba, lrbp, cqe);
+		ufshcd_release_scsi_cmd(hba, lrbp);
+		/* Do not touch lrbp after scsi done */
+		scsi_done(cmd);
+	} else if (lrbp->command_type == UTP_CMD_TYPE_DEV_MANAGE ||
+		   lrbp->command_type == UTP_CMD_TYPE_UFS_STORAGE) {
+		if (hba->dev_cmd.complete) {
+			hba->dev_cmd.cqe = cqe;
+			ufshcd_add_command_trace(hba, task_tag, UFS_DEV_COMP);
+			complete(hba->dev_cmd.complete);
+			ufshcd_clk_scaling_update_busy(hba);
 		}
 	}
 }
 
+/**
+ * __ufshcd_transfer_req_compl - handle SCSI and query command completion
+ * @hba: per adapter instance
+ * @completed_reqs: bitmask that indicates which requests to complete
+ */
+static void __ufshcd_transfer_req_compl(struct ufs_hba *hba,
+					unsigned long completed_reqs)
+{
+	int tag;
+
+	for_each_set_bit(tag, &completed_reqs, hba->nutrs)
+		ufshcd_compl_one_cqe(hba, tag, NULL);
+}
+
 /* Any value that is not an existing queue number is fine for this constant. */
 enum {
 	UFSHCD_POLL_FROM_INTERRUPT_CONTEXT = -1
@@ -5370,6 +5461,13 @@ static int ufshcd_poll(struct Scsi_Host *shost, unsigned int queue_num)
 	struct ufs_hba *hba = shost_priv(shost);
 	unsigned long completed_reqs, flags;
 	u32 tr_doorbell;
+	struct ufs_hw_queue *hwq;
+
+	if (is_mcq_enabled(hba)) {
+		hwq = &hba->uhq[queue_num + UFSHCD_MCQ_IO_QUEUE_OFFSET];
+
+		return ufshcd_mcq_poll_cqe_lock(hba, hwq);
+	}
 
 	spin_lock_irqsave(&hba->outstanding_lock, flags);
 	tr_doorbell = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
@@ -6592,6 +6690,40 @@ static irqreturn_t ufshcd_tmc_handler(struct ufs_hba *hba)
 	return ret;
 }
 
+/**
+ * ufshcd_handle_mcq_cq_events - handle MCQ completion queue events
+ * @hba: per adapter instance
+ *
+ * Returns IRQ_HANDLED if interrupt is handled
+ */
+static irqreturn_t ufshcd_handle_mcq_cq_events(struct ufs_hba *hba)
+{
+	struct ufs_hw_queue *hwq;
+	unsigned long outstanding_cqs;
+	unsigned int nr_queues;
+	int i, ret;
+	u32 events;
+
+	ret = ufshcd_vops_get_outstanding_cqs(hba, &outstanding_cqs);
+	if (ret)
+		outstanding_cqs = (1U << hba->nr_hw_queues) - 1;
+
+	/* Exclude the poll queues */
+	nr_queues = hba->nr_hw_queues - hba->nr_queues[HCTX_TYPE_POLL];
+	for_each_set_bit(i, &outstanding_cqs, nr_queues) {
+		hwq = &hba->uhq[i];
+
+		events = ufshcd_mcq_read_cqis(hba, i);
+		if (events)
+			ufshcd_mcq_write_cqis(hba, events, i);
+
+		if (events & UFSHCD_MCQ_CQIS_TAIL_ENT_PUSH_STS)
+			ufshcd_mcq_poll_cqe_nolock(hba, hwq);
+	}
+
+	return IRQ_HANDLED;
+}
+
 /**
  * ufshcd_sl_intr - Interrupt service routine
  * @hba: per adapter instance
@@ -6617,6 +6749,9 @@ static irqreturn_t ufshcd_sl_intr(struct ufs_hba *hba, u32 intr_status)
 	if (intr_status & UTP_TRANSFER_REQ_COMPL)
 		retval |= ufshcd_transfer_req_compl(hba);
 
+	if (intr_status & MCQ_CQ_EVENT_STATUS)
+		retval |= ufshcd_handle_mcq_cq_events(hba);
+
 	return retval;
 }
 
@@ -6884,7 +7019,7 @@ static int ufshcd_issue_devman_upiu_cmd(struct ufs_hba *hba,
 
 	ufshcd_add_query_upiu_trace(hba, UFS_QUERY_SEND, lrbp->ucd_req_ptr);
 
-	ufshcd_send_command(hba, tag);
+	ufshcd_send_command(hba, tag, hba->dev_cmd_queue);
 	/*
 	 * ignore the returning value here - ufshcd_check_query_response is
 	 * bound to fail since dev_cmd.query and dev_cmd.type were left empty.
@@ -7050,7 +7185,7 @@ int ufshcd_advanced_rpmb_req_handler(struct ufs_hba *hba, struct utp_upiu_req *r
 
 	hba->dev_cmd.complete = &wait;
 
-	ufshcd_send_command(hba, tag);
+	ufshcd_send_command(hba, tag, hba->dev_cmd_queue);
 
 	err = ufshcd_wait_for_dev_cmd(hba, lrbp, ADVANCED_RPMB_REQ_TIMEOUT);
 
@@ -7766,6 +7901,31 @@ static void ufshcd_temp_notif_probe(struct ufs_hba *hba, const u8 *desc_buf)
 	}
 }
 
+static void ufshcd_ext_iid_probe(struct ufs_hba *hba, u8 *desc_buf)
+{
+	struct ufs_dev_info *dev_info = &hba->dev_info;
+	u32 ext_ufs_feature;
+	u32 ext_iid_en = 0;
+	int err;
+
+	/* Only UFS-4.0 and above may support EXT_IID */
+	if (dev_info->wspecversion < 0x400)
+		goto out;
+
+	ext_ufs_feature = get_unaligned_be32(desc_buf +
+				     DEVICE_DESC_PARAM_EXT_UFS_FEATURE_SUP);
+	if (!(ext_ufs_feature & UFS_DEV_EXT_IID_SUP))
+		goto out;
+
+	err = ufshcd_query_attr_retry(hba, UPIU_QUERY_OPCODE_READ_ATTR,
+				      QUERY_ATTR_IDN_EXT_IID_EN, 0, 0, &ext_iid_en);
+	if (err)
+		dev_err(hba->dev, "failed reading bEXTIIDEn. err = %d\n", err);
+
+out:
+	dev_info->b_ext_iid_en = ext_iid_en;
+}
+
 void ufshcd_fixup_dev_quirks(struct ufs_hba *hba,
 			     const struct ufs_dev_quirk *fixups)
 {
@@ -7827,6 +7987,7 @@ static int ufs_get_device_desc(struct ufs_hba *hba)
 	/* getting Specification Version in big endian format */
 	dev_info->wspecversion = desc_buf[DEVICE_DESC_PARAM_SPEC_VER] << 8 |
 				      desc_buf[DEVICE_DESC_PARAM_SPEC_VER + 1];
+	dev_info->bqueuedepth = desc_buf[DEVICE_DESC_PARAM_Q_DPTH];
 	b_ufs_feature_sup = desc_buf[DEVICE_DESC_PARAM_UFS_FEAT];
 
 	model_index = desc_buf[DEVICE_DESC_PARAM_PRDCT_NAME];
@@ -7864,6 +8025,9 @@ static int ufs_get_device_desc(struct ufs_hba *hba)
 
 	ufshcd_temp_notif_probe(hba, desc_buf);
 
+	if (hba->ext_iid_sup)
+		ufshcd_ext_iid_probe(hba, desc_buf);
+
 	/*
 	 * ufshcd_read_string_desc returns size of the string
 	 * reset the error value
@@ -8231,9 +8395,82 @@ static int ufshcd_add_lus(struct ufs_hba *hba)
 	return ret;
 }
 
+/* SDB - Single Doorbell */
+static void ufshcd_release_sdb_queue(struct ufs_hba *hba, int nutrs)
+{
+	size_t ucdl_size, utrdl_size;
+
+	ucdl_size = sizeof(struct utp_transfer_cmd_desc) * nutrs;
+	dmam_free_coherent(hba->dev, ucdl_size, hba->ucdl_base_addr,
+			   hba->ucdl_dma_addr);
+
+	utrdl_size = sizeof(struct utp_transfer_req_desc) * nutrs;
+	dmam_free_coherent(hba->dev, utrdl_size, hba->utrdl_base_addr,
+			   hba->utrdl_dma_addr);
+
+	devm_kfree(hba->dev, hba->lrb);
+}
+
+static int ufshcd_alloc_mcq(struct ufs_hba *hba)
+{
+	int ret;
+	int old_nutrs = hba->nutrs;
+
+	ret = ufshcd_mcq_decide_queue_depth(hba);
+	if (ret < 0)
+		return ret;
+
+	hba->nutrs = ret;
+	ret = ufshcd_mcq_init(hba);
+	if (ret)
+		goto err;
+
+	/*
+	 * Previously allocated memory for nutrs may not be enough in MCQ mode.
+	 * Number of supported tags in MCQ mode may be larger than SDB mode.
+	 */
+	if (hba->nutrs != old_nutrs) {
+		ufshcd_release_sdb_queue(hba, old_nutrs);
+		ret = ufshcd_memory_alloc(hba);
+		if (ret)
+			goto err;
+		ufshcd_host_memory_configure(hba);
+	}
+
+	ret = ufshcd_mcq_memory_alloc(hba);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	hba->nutrs = old_nutrs;
+	return ret;
+}
+
+static void ufshcd_config_mcq(struct ufs_hba *hba)
+{
+	ufshcd_enable_intr(hba, UFSHCD_ENABLE_MCQ_INTRS);
+	ufshcd_mcq_make_queues_operational(hba);
+	ufshcd_mcq_config_mac(hba, hba->nutrs);
+
+	hba->host->can_queue = hba->nutrs - UFSHCD_NUM_RESERVED;
+	hba->reserved_slot = hba->nutrs - UFSHCD_NUM_RESERVED;
+
+	/* Select MCQ mode */
+	ufshcd_writel(hba, ufshcd_readl(hba, REG_UFS_MEM_CFG) | 0x1,
+		      REG_UFS_MEM_CFG);
+	hba->mcq_enabled = true;
+
+	dev_info(hba->dev, "MCQ configured, nr_queues=%d, io_queues=%d, read_queue=%d, poll_queues=%d, queue_depth=%d\n",
+		 hba->nr_hw_queues, hba->nr_queues[HCTX_TYPE_DEFAULT],
+		 hba->nr_queues[HCTX_TYPE_READ], hba->nr_queues[HCTX_TYPE_POLL],
+		 hba->nutrs);
+}
+
 static int ufshcd_device_init(struct ufs_hba *hba, bool init_dev_params)
 {
 	int ret;
+	struct Scsi_Host *host = hba->host;
 
 	hba->ufshcd_state = UFSHCD_STATE_RESET;
 
@@ -8250,6 +8487,10 @@ static int ufshcd_device_init(struct ufs_hba *hba, bool init_dev_params)
 	/* UniPro link is active now */
 	ufshcd_set_link_active(hba);
 
+	/* Reconfigure MCQ upon reset */
+	if (is_mcq_enabled(hba) && !init_dev_params)
+		ufshcd_config_mcq(hba);
+
 	/* Verify device initialization by sending NOP OUT UPIU */
 	ret = ufshcd_verify_dev_init(hba);
 	if (ret)
@@ -8268,6 +8509,24 @@ static int ufshcd_device_init(struct ufs_hba *hba, bool init_dev_params)
 		ret = ufshcd_device_params_init(hba);
 		if (ret)
 			return ret;
+		if (is_mcq_supported(hba) && !hba->scsi_host_added) {
+			ret = ufshcd_alloc_mcq(hba);
+			if (ret) {
+				/* Continue with SDB mode */
+				use_mcq_mode = false;
+				dev_err(hba->dev, "MCQ mode is disabled, err=%d\n",
+					 ret);
+			}
+			ret = scsi_add_host(host, hba->dev);
+			if (ret) {
+				dev_err(hba->dev, "scsi_add_host failed\n");
+				return ret;
+			}
+			hba->scsi_host_added = true;
+		}
+		/* MCQ may be disabled if ufshcd_alloc_mcq() fails */
+		if (is_mcq_supported(hba) && use_mcq_mode)
+			ufshcd_config_mcq(hba);
 	}
 
 	ufshcd_tune_unipro_params(hba);
@@ -9906,10 +10165,12 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 		hba->is_irq_enabled = true;
 	}
 
-	err = scsi_add_host(host, hba->dev);
-	if (err) {
-		dev_err(hba->dev, "scsi_add_host failed\n");
-		goto out_disable;
+	if (!is_mcq_supported(hba)) {
+		err = scsi_add_host(host, hba->dev);
+		if (err) {
+			dev_err(hba->dev, "scsi_add_host failed\n");
+			goto out_disable;
+		}
 	}
 
 	hba->tmf_tag_set = (struct blk_mq_tag_set) {

drivers/ufs/host/ufs-qcom.c

@@ -22,6 +22,12 @@
 #include <ufs/ufshci.h>
 #include <ufs/ufs_quirks.h>
 
+#define MCQ_QCFGPTR_MASK	GENMASK(7, 0)
+#define MCQ_QCFGPTR_UNIT	0x200
+#define MCQ_SQATTR_OFFSET(c) \
+	((((c) >> 16) & MCQ_QCFGPTR_MASK) * MCQ_QCFGPTR_UNIT)
+#define MCQ_QCFG_SIZE	0x40
+
 enum {
 	TSTBUS_UAWM,
 	TSTBUS_UARM,
@@ -1396,6 +1402,142 @@ static void ufs_qcom_reinit_notify(struct ufs_hba *hba)
 	phy_power_off(host->generic_phy);
 }
 
+/* Resources */
+static const struct ufshcd_res_info ufs_res_info[RES_MAX] = {
+	{.name = "ufs_mem",},
+	{.name = "mcq",},
+	/* Submission Queue DAO */
+	{.name = "mcq_sqd",},
+	/* Submission Queue Interrupt Status */
+	{.name = "mcq_sqis",},
+	/* Completion Queue DAO */
+	{.name = "mcq_cqd",},
+	/* Completion Queue Interrupt Status */
+	{.name = "mcq_cqis",},
+	/* MCQ vendor specific */
+	{.name = "mcq_vs",},
+};
+
+static int ufs_qcom_mcq_config_resource(struct ufs_hba *hba)
+{
+	struct platform_device *pdev = to_platform_device(hba->dev);
+	struct ufshcd_res_info *res;
+	struct resource *res_mem, *res_mcq;
+	int i, ret = 0;
+
+	memcpy(hba->res, ufs_res_info, sizeof(ufs_res_info));
+
+	for (i = 0; i < RES_MAX; i++) {
+		res = &hba->res[i];
+		res->resource = platform_get_resource_byname(pdev,
+							     IORESOURCE_MEM,
+							     res->name);
+		if (!res->resource) {
+			dev_info(hba->dev, "Resource %s not provided\n", res->name);
+			if (i == RES_UFS)
+				return -ENOMEM;
+			continue;
+		} else if (i == RES_UFS) {
+			res_mem = res->resource;
+			res->base = hba->mmio_base;
+			continue;
+		}
+
+		res->base = devm_ioremap_resource(hba->dev, res->resource);
+		if (IS_ERR(res->base)) {
+			dev_err(hba->dev, "Failed to map res %s, err=%d\n",
+					 res->name, (int)PTR_ERR(res->base));
+			res->base = NULL;
+			ret = PTR_ERR(res->base);
+			return ret;
+		}
+	}
+
+	/* MCQ resource provided in DT */
+	res = &hba->res[RES_MCQ];
+	/* Bail if MCQ resource is provided */
+	if (res->base)
+		goto out;
+
+	/* Explicitly allocate MCQ resource from ufs_mem */
+	res_mcq = devm_kzalloc(hba->dev, sizeof(*res_mcq), GFP_KERNEL);
+	if (!res_mcq)
+		return ret;
+
+	res_mcq->start = res_mem->start +
+			 MCQ_SQATTR_OFFSET(hba->mcq_capabilities);
+	res_mcq->end = res_mcq->start + hba->nr_hw_queues * MCQ_QCFG_SIZE - 1;
+	res_mcq->flags = res_mem->flags;
+	res_mcq->name = "mcq";
+
+	ret = insert_resource(&iomem_resource, res_mcq);
+	if (ret) {
+		dev_err(hba->dev, "Failed to insert MCQ resource, err=%d\n",
+			ret);
+		goto insert_res_err;
+	}
+
+	res->base = devm_ioremap_resource(hba->dev, res_mcq);
+	if (IS_ERR(res->base)) {
+		dev_err(hba->dev, "MCQ registers mapping failed, err=%d\n",
+			(int)PTR_ERR(res->base));
+		ret = PTR_ERR(res->base);
+		goto ioremap_err;
+	}
+
+out:
+	hba->mcq_base = res->base;
+	return 0;
+ioremap_err:
+	res->base = NULL;
+	remove_resource(res_mcq);
+insert_res_err:
+	devm_kfree(hba->dev, res_mcq);
+	return ret;
+}
+
+static int ufs_qcom_op_runtime_config(struct ufs_hba *hba)
+{
+	struct ufshcd_res_info *mem_res, *sqdao_res;
+	struct ufshcd_mcq_opr_info_t *opr;
+	int i;
+
+	mem_res = &hba->res[RES_UFS];
+	sqdao_res = &hba->res[RES_MCQ_SQD];
+
+	if (!mem_res->base || !sqdao_res->base)
+		return -EINVAL;
+
+	for (i = 0; i < OPR_MAX; i++) {
+		opr = &hba->mcq_opr[i];
+		opr->offset = sqdao_res->resource->start -
+			      mem_res->resource->start + 0x40 * i;
+		opr->stride = 0x100;
+		opr->base = sqdao_res->base + 0x40 * i;
+	}
+
+	return 0;
+}
+
+static int ufs_qcom_get_hba_mac(struct ufs_hba *hba)
+{
+	/* Qualcomm HC supports up to 64 */
+	return MAX_SUPP_MAC;
+}
+
+static int ufs_qcom_get_outstanding_cqs(struct ufs_hba *hba,
+					unsigned long *ocqs)
+{
+	struct ufshcd_res_info *mcq_vs_res = &hba->res[RES_MCQ_VS];
+
+	if (!mcq_vs_res->base)
+		return -EINVAL;
+
+	*ocqs = readl(mcq_vs_res->base + UFS_MEM_CQIS_VS);
+
+	return 0;
+}
+
 /*
  * struct ufs_hba_qcom_vops - UFS QCOM specific variant operations
  *
@@ -1420,6 +1562,10 @@ static const struct ufs_hba_variant_ops ufs_hba_qcom_vops = {
 	.config_scaling_param = ufs_qcom_config_scaling_param,
 	.program_key		= ufs_qcom_ice_program_key,
 	.reinit_notify		= ufs_qcom_reinit_notify,
+	.mcq_config_resource	= ufs_qcom_mcq_config_resource,
+	.get_hba_mac		= ufs_qcom_get_hba_mac,
+	.op_runtime_config	= ufs_qcom_op_runtime_config,
+	.get_outstanding_cqs	= ufs_qcom_get_outstanding_cqs,
 };
 
 /**

drivers/ufs/host/ufs-qcom.h

@@ -16,6 +16,7 @@
 #define HBRN8_POLL_TOUT_MS      100
 #define DEFAULT_CLK_RATE_HZ     1000000
 #define BUS_VECTOR_NAME_LEN     32
+#define MAX_SUPP_MAC		64
 
 #define UFS_HW_VER_MAJOR_MASK	GENMASK(31, 28)
 #define UFS_HW_VER_MINOR_MASK	GENMASK(27, 16)
@@ -70,6 +71,10 @@ enum {
 	UFS_UFS_DBG_RD_EDTL_RAM			= 0x1900,
 };
 
+enum {
+	UFS_MEM_CQIS_VS		= 0x8,
+};
+
 #define UFS_CNTLR_2_x_x_VEN_REGS_OFFSET(x)	(0x000 + x)
 #define UFS_CNTLR_3_x_x_VEN_REGS_OFFSET(x)	(0x400 + x)
 

include/ufs/ufs.h

@@ -169,6 +169,7 @@ enum attr_idn {
 	QUERY_ATTR_IDN_AVAIL_WB_BUFF_SIZE       = 0x1D,
 	QUERY_ATTR_IDN_WB_BUFF_LIFE_TIME_EST    = 0x1E,
 	QUERY_ATTR_IDN_CURR_WB_BUFF_SIZE        = 0x1F,
+	QUERY_ATTR_IDN_EXT_IID_EN		= 0x2A,
 };
 
 /* Descriptor idn for Query requests */
@@ -378,6 +379,7 @@ enum {
 	UFS_DEV_EXT_TEMP_NOTIF		= BIT(6),
 	UFS_DEV_HPB_SUPPORT		= BIT(7),
 	UFS_DEV_WRITE_BOOSTER_SUP	= BIT(8),
+	UFS_DEV_EXT_IID_SUP		= BIT(16),
 };
 #define UFS_DEV_HPB_SUPPORT_VERSION		0x310
 
@@ -615,6 +617,8 @@ struct ufs_dev_info {
 	u8	*model;
 	u16	wspecversion;
 	u32	clk_gating_wait_us;
+	/* Stores the depth of queue in UFS device */
+	u8	bqueuedepth;
 
 	/* UFS HPB related flag */
 	bool	hpb_enabled;
@@ -629,6 +633,9 @@ struct ufs_dev_info {
 	u8	b_presrv_uspc_en;
 
 	bool    b_advanced_rpmb_en;
+
+	/* UFS EXT_IID Enable */
+	bool	b_ext_iid_en;
 };
 
 /*

include/ufs/ufshcd.h

@@ -224,6 +224,7 @@ struct ufs_dev_cmd {
 	struct mutex lock;
 	struct completion *complete;
 	struct ufs_query query;
+	struct cq_entry *cqe;
 };
 
 /**
@@ -300,6 +301,10 @@ struct ufs_pwr_mode_info {
  * @program_key: program or evict an inline encryption key
  * @event_notify: called to notify important events
  * @reinit_notify: called to notify reinit of UFSHCD during max gear switch
+ * @mcq_config_resource: called to configure MCQ platform resources
+ * @get_hba_mac: called to get vendor specific mac value, mandatory for mcq mode
+ * @op_runtime_config: called to config Operation and runtime regs Pointers
+ * @get_outstanding_cqs: called to get outstanding completion queues
  */
 struct ufs_hba_variant_ops {
 	const char *name;
@@ -339,6 +344,11 @@ struct ufs_hba_variant_ops {
 	void	(*event_notify)(struct ufs_hba *hba,
 				enum ufs_event_type evt, void *data);
 	void	(*reinit_notify)(struct ufs_hba *);
+	int	(*mcq_config_resource)(struct ufs_hba *hba);
+	int	(*get_hba_mac)(struct ufs_hba *hba);
+	int	(*op_runtime_config)(struct ufs_hba *hba);
+	int	(*get_outstanding_cqs)(struct ufs_hba *hba,
+				       unsigned long *ocqs);
 };
 
 /* clock gating state  */
@@ -733,6 +743,51 @@ struct ufs_hba_monitor {
 	bool enabled;
 };
 
+/**
+ * struct ufshcd_res_info_t - MCQ related resource regions
+ *
+ * @name: resource name
+ * @resource: pointer to resource region
+ * @base: register base address
+ */
+struct ufshcd_res_info {
+	const char *name;
+	struct resource *resource;
+	void __iomem *base;
+};
+
+enum ufshcd_res {
+	RES_UFS,
+	RES_MCQ,
+	RES_MCQ_SQD,
+	RES_MCQ_SQIS,
+	RES_MCQ_CQD,
+	RES_MCQ_CQIS,
+	RES_MCQ_VS,
+	RES_MAX,
+};
+
+/**
+ * struct ufshcd_mcq_opr_info_t - Operation and Runtime registers
+ *
+ * @offset: Doorbell Address Offset
+ * @stride: Steps proportional to queue [0...31]
+ * @base: base address
+ */
+struct ufshcd_mcq_opr_info_t {
+	unsigned long offset;
+	unsigned long stride;
+	void __iomem *base;
+};
+
+enum ufshcd_mcq_opr {
+	OPR_SQD,
+	OPR_SQIS,
+	OPR_CQD,
+	OPR_CQIS,
+	OPR_MAX,
+};
+
 /**
  * struct ufs_hba - per adapter private structure
  * @mmio_base: UFSHCI base register address
@@ -757,6 +812,7 @@ struct ufs_hba_monitor {
  * @outstanding_lock: Protects @outstanding_reqs.
  * @outstanding_reqs: Bits representing outstanding transfer requests
  * @capabilities: UFS Controller Capabilities
+ * @mcq_capabilities: UFS Multi Circular Queue capabilities
  * @nutrs: Transfer Request Queue depth supported by controller
  * @nutmrs: Task Management Queue depth supported by controller
  * @reserved_slot: Used to submit device commands. Protected by @dev_cmd.lock.
@@ -839,8 +895,17 @@ struct ufs_hba_monitor {
  *	ee_ctrl_mask
  * @luns_avail: number of regular and well known LUNs supported by the UFS
  *	device
+ * @nr_hw_queues: number of hardware queues configured
+ * @nr_queues: number of Queues of different queue types
  * @complete_put: whether or not to call ufshcd_rpm_put() from inside
  *	ufshcd_resume_complete()
+ * @ext_iid_sup: is EXT_IID is supported by UFSHC
+ * @mcq_sup: is mcq supported by UFSHC
+ * @mcq_enabled: is mcq ready to accept requests
+ * @res: array of resource info of MCQ registers
+ * @mcq_base: Multi circular queue registers base address
+ * @uhq: array of supported hardware queues
+ * @dev_cmd_queue: Queue for issuing device management commands
  */
 struct ufs_hba {
 	void __iomem *mmio_base;
@@ -882,6 +947,7 @@ struct ufs_hba {
 
 	u32 capabilities;
 	int nutrs;
+	u32 mcq_capabilities;
 	int nutmrs;
 	u32 reserved_slot;
 	u32 ufs_version;
@@ -990,9 +1056,62 @@ struct ufs_hba {
 	u32 debugfs_ee_rate_limit_ms;
 #endif
 	u32 luns_avail;
+	unsigned int nr_hw_queues;
+	unsigned int nr_queues[HCTX_MAX_TYPES];
 	bool complete_put;
+	bool ext_iid_sup;
+	bool scsi_host_added;
+	bool mcq_sup;
+	bool mcq_enabled;
+	struct ufshcd_res_info res[RES_MAX];
+	void __iomem *mcq_base;
+	struct ufs_hw_queue *uhq;
+	struct ufs_hw_queue *dev_cmd_queue;
+	struct ufshcd_mcq_opr_info_t mcq_opr[OPR_MAX];
+};
+
+/**
+ * struct ufs_hw_queue - per hardware queue structure
+ * @mcq_sq_head: base address of submission queue head pointer
+ * @mcq_sq_tail: base address of submission queue tail pointer
+ * @mcq_cq_head: base address of completion queue head pointer
+ * @mcq_cq_tail: base address of completion queue tail pointer
+ * @sqe_base_addr: submission queue entry base address
+ * @sqe_dma_addr: submission queue dma address
+ * @cqe_base_addr: completion queue base address
+ * @cqe_dma_addr: completion queue dma address
+ * @max_entries: max number of slots in this hardware queue
+ * @id: hardware queue ID
+ * @sq_tp_slot: current slot to which SQ tail pointer is pointing
+ * @sq_lock: serialize submission queue access
+ * @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
+ */
+struct ufs_hw_queue {
+	void __iomem *mcq_sq_head;
+	void __iomem *mcq_sq_tail;
+	void __iomem *mcq_cq_head;
+	void __iomem *mcq_cq_tail;
+
+	void *sqe_base_addr;
+	dma_addr_t sqe_dma_addr;
+	struct cq_entry *cqe_base_addr;
+	dma_addr_t cqe_dma_addr;
+	u32 max_entries;
+	u32 id;
+	u32 sq_tail_slot;
+	spinlock_t sq_lock;
+	u32 cq_tail_slot;
+	u32 cq_head_slot;
+	spinlock_t cq_lock;
 };
 
+static inline bool is_mcq_enabled(struct ufs_hba *hba)
+{
+	return hba->mcq_enabled;
+}
+
 #ifdef CONFIG_SCSI_UFS_VARIABLE_SG_ENTRY_SIZE
 static inline size_t ufshcd_sg_entry_size(const struct ufs_hba *hba)
 {
@@ -1074,6 +1193,16 @@ static inline bool ufshcd_enable_wb_if_scaling_up(struct ufs_hba *hba)
 	return hba->caps & UFSHCD_CAP_WB_WITH_CLK_SCALING;
 }
 
+#define ufsmcq_writel(hba, val, reg)	\
+	writel((val), (hba)->mcq_base + (reg))
+#define ufsmcq_readl(hba, reg)	\
+	readl((hba)->mcq_base + (reg))
+
+#define ufsmcq_writelx(hba, val, reg)	\
+	writel_relaxed((val), (hba)->mcq_base + (reg))
+#define ufsmcq_readlx(hba, reg)	\
+	readl_relaxed((hba)->mcq_base + (reg))
+
 #define ufshcd_writel(hba, val, reg)	\
 	writel((val), (hba)->mmio_base + (reg))
 #define ufshcd_readl(hba, reg)	\

include/ufs/ufshci.h

@@ -22,6 +22,7 @@ enum {
 /* UFSHCI Registers */
 enum {
 	REG_CONTROLLER_CAPABILITIES		= 0x00,
+	REG_MCQCAP				= 0x04,
 	REG_UFS_VERSION				= 0x08,
 	REG_CONTROLLER_DEV_ID			= 0x10,
 	REG_CONTROLLER_PROD_ID			= 0x14,
@@ -56,6 +57,8 @@ enum {
 	REG_UFS_CCAP				= 0x100,
 	REG_UFS_CRYPTOCAP			= 0x104,
 
+	REG_UFS_MEM_CFG				= 0x300,
+	REG_UFS_MCQ_CFG				= 0x380,
 	UFSHCI_CRYPTO_REG_SPACE_SIZE		= 0x400,
 };
 
@@ -69,6 +72,41 @@ enum {
 	MASK_OUT_OF_ORDER_DATA_DELIVERY_SUPPORT	= 0x02000000,
 	MASK_UIC_DME_TEST_MODE_SUPPORT		= 0x04000000,
 	MASK_CRYPTO_SUPPORT			= 0x10000000,
+	MASK_MCQ_SUPPORT			= 0x40000000,
+};
+
+/* MCQ capability mask */
+enum {
+	MASK_EXT_IID_SUPPORT = 0x00000400,
+};
+
+enum {
+	REG_SQATTR		= 0x0,
+	REG_SQLBA		= 0x4,
+	REG_SQUBA		= 0x8,
+	REG_SQDAO		= 0xC,
+	REG_SQISAO		= 0x10,
+
+	REG_CQATTR		= 0x20,
+	REG_CQLBA		= 0x24,
+	REG_CQUBA		= 0x28,
+	REG_CQDAO		= 0x2C,
+	REG_CQISAO		= 0x30,
+};
+
+enum {
+	REG_SQHP		= 0x0,
+	REG_SQTP		= 0x4,
+};
+
+enum {
+	REG_CQHP		= 0x0,
+	REG_CQTP		= 0x4,
+};
+
+enum {
+	REG_CQIS		= 0x0,
+	REG_CQIE		= 0x4,
 };
 
 #define UFS_MASK(mask, offset)		((mask) << (offset))
@@ -127,6 +165,7 @@ static inline u32 ufshci_version(u32 major, u32 minor)
 #define CONTROLLER_FATAL_ERROR			0x10000
 #define SYSTEM_BUS_FATAL_ERROR			0x20000
 #define CRYPTO_ENGINE_FATAL_ERROR		0x40000
+#define MCQ_CQ_EVENT_STATUS			0x100000
 
 #define UFSHCD_UIC_HIBERN8_MASK	(UIC_HIBERNATE_ENTER |\
 				UIC_HIBERNATE_EXIT)
@@ -224,6 +263,9 @@ enum {
 /* UTMRLRSR - UTP Task Management Request Run-Stop Register 80h */
 #define UTP_TASK_REQ_LIST_RUN_STOP_BIT		0x1
 
+/* CQISy - CQ y Interrupt Status Register  */
+#define UFSHCD_MCQ_CQIS_TAIL_ENT_PUSH_STS	0x1
+
 /* UICCMD - UIC Command */
 #define COMMAND_OPCODE_MASK		0xFF
 #define GEN_SELECTOR_INDEX_MASK		0xFFFF
@@ -484,6 +526,28 @@ struct utp_transfer_req_desc {
 	__le16  prd_table_offset;
 };
 
+/* MCQ Completion Queue Entry */
+struct cq_entry {
+	/* DW 0-1 */
+	__le64 command_desc_base_addr;
+
+	/* DW 2 */
+	__le16  response_upiu_length;
+	__le16  response_upiu_offset;
+
+	/* DW 3 */
+	__le16  prd_table_length;
+	__le16  prd_table_offset;
+
+	/* DW 4 */
+	__le32 status;
+
+	/* DW 5-7 */
+	__le32 reserved[3];
+};
+
+static_assert(sizeof(struct cq_entry) == 32);
+
 /*
  * UTMRD structure.
  */