Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi

Pull SCSI updates from James Bottomley:
 "This is mostly update of the usual drivers: arcmsr, qla2xxx, lpfc,
  hisi_sas, target/iscsi and target/core.

  Additionally Christoph refactored gdth as part of the dma changes. The
  major mid-layer change this time is the removal of bidi commands and
  with them the whole of the osd/exofs driver and filesystem. This is a
  major simplification for block and mq in particular"

* tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (240 commits)
  scsi: cxgb4i: validate tcp sequence number only if chip version <= T5
  scsi: cxgb4i: get pf number from lldi->pf
  scsi: core: replace GFP_ATOMIC with GFP_KERNEL in scsi_scan.c
  scsi: mpt3sas: Add missing breaks in switch statements
  scsi: aacraid: Fix missing break in switch statement
  scsi: kill command serial number
  scsi: csiostor: drop serial_number usage
  scsi: mvumi: use request tag instead of serial_number
  scsi: dpt_i2o: remove serial number usage
  scsi: st: osst: Remove negative constant left-shifts
  scsi: ufs-bsg: Allow reading descriptors
  scsi: ufs: Allow reading descriptor via raw upiu
  scsi: ufs-bsg: Change the calling convention for write descriptor
  scsi: ufs: Remove unused device quirks
  Revert "scsi: ufs: disable vccq if it's not needed by UFS device"
  scsi: megaraid_sas: Remove a bunch of set but not used variables
  scsi: clean obsolete return values of eh_timed_out
  scsi: sd: Optimal I/O size should be a multiple of physical block size
  scsi: MAINTAINERS: SCSI initiator and target tweaks
  scsi: fcoe: make use of fip_mode enum complete
  ...

5 files changed, 1233 insertions, 125 deletions

diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index af291947a54d..6c87bd34509a 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -14,6 +14,7 @@
 
 #include <linux/acpi.h>
 #include <linux/clk.h>
+#include <linux/debugfs.h>
 #include <linux/dmapool.h>
 #include <linux/iopoll.h>
 #include <linux/lcm.h>
@@ -29,7 +30,7 @@
 
 #define HISI_SAS_MAX_PHYS	9
 #define HISI_SAS_MAX_QUEUES	32
-#define HISI_SAS_QUEUE_SLOTS 512
+#define HISI_SAS_QUEUE_SLOTS	4096
 #define HISI_SAS_MAX_ITCT_ENTRIES 1024
 #define HISI_SAS_MAX_DEVICES HISI_SAS_MAX_ITCT_ENTRIES
 #define HISI_SAS_RESET_BIT	0
@@ -40,20 +41,25 @@
 #define HISI_SAS_COMMAND_TABLE_SZ (sizeof(union hisi_sas_command_table))
 
 #define hisi_sas_status_buf_addr(buf) \
-	(buf + offsetof(struct hisi_sas_slot_buf_table, status_buffer))
-#define hisi_sas_status_buf_addr_mem(slot) hisi_sas_status_buf_addr(slot->buf)
+	((buf) + offsetof(struct hisi_sas_slot_buf_table, status_buffer))
+#define hisi_sas_status_buf_addr_mem(slot) hisi_sas_status_buf_addr((slot)->buf)
 #define hisi_sas_status_buf_addr_dma(slot) \
-	hisi_sas_status_buf_addr(slot->buf_dma)
+	hisi_sas_status_buf_addr((slot)->buf_dma)
 
 #define hisi_sas_cmd_hdr_addr(buf) \
-	(buf + offsetof(struct hisi_sas_slot_buf_table, command_header))
-#define hisi_sas_cmd_hdr_addr_mem(slot) hisi_sas_cmd_hdr_addr(slot->buf)
-#define hisi_sas_cmd_hdr_addr_dma(slot) hisi_sas_cmd_hdr_addr(slot->buf_dma)
+	((buf) + offsetof(struct hisi_sas_slot_buf_table, command_header))
+#define hisi_sas_cmd_hdr_addr_mem(slot) hisi_sas_cmd_hdr_addr((slot)->buf)
+#define hisi_sas_cmd_hdr_addr_dma(slot) hisi_sas_cmd_hdr_addr((slot)->buf_dma)
 
 #define hisi_sas_sge_addr(buf) \
-	(buf + offsetof(struct hisi_sas_slot_buf_table, sge_page))
-#define hisi_sas_sge_addr_mem(slot) hisi_sas_sge_addr(slot->buf)
-#define hisi_sas_sge_addr_dma(slot) hisi_sas_sge_addr(slot->buf_dma)
+	((buf) + offsetof(struct hisi_sas_slot_buf_table, sge_page))
+#define hisi_sas_sge_addr_mem(slot) hisi_sas_sge_addr((slot)->buf)
+#define hisi_sas_sge_addr_dma(slot) hisi_sas_sge_addr((slot)->buf_dma)
+
+#define hisi_sas_sge_dif_addr(buf) \
+	((buf) + offsetof(struct hisi_sas_slot_dif_buf_table, sge_dif_page))
+#define hisi_sas_sge_dif_addr_mem(slot) hisi_sas_sge_dif_addr((slot)->buf)
+#define hisi_sas_sge_dif_addr_dma(slot) hisi_sas_sge_dif_addr((slot)->buf_dma)
 
 #define HISI_SAS_MAX_SSP_RESP_SZ (sizeof(struct ssp_frame_hdr) + 1024)
 #define HISI_SAS_MAX_SMP_RESP_SZ 1028
@@ -73,7 +79,13 @@
 				SHOST_DIF_TYPE2_PROTECTION | \
 				SHOST_DIF_TYPE3_PROTECTION)
 
-#define HISI_SAS_PROT_MASK (HISI_SAS_DIF_PROT_MASK)
+#define HISI_SAS_DIX_PROT_MASK (SHOST_DIX_TYPE1_PROTECTION | \
+				SHOST_DIX_TYPE2_PROTECTION | \
+				SHOST_DIX_TYPE3_PROTECTION)
+
+#define HISI_SAS_PROT_MASK (HISI_SAS_DIF_PROT_MASK | HISI_SAS_DIX_PROT_MASK)
+
+#define HISI_SAS_WAIT_PHYUP_TIMEOUT 20
 
 struct hisi_hba;
 
@@ -82,11 +94,6 @@ enum {
 	PORT_TYPE_SATA = (1U << 0),
 };
 
-enum dev_status {
-	HISI_SAS_DEV_NORMAL,
-	HISI_SAS_DEV_EH,
-};
-
 enum {
 	HISI_SAS_INT_ABT_CMD = 0,
 	HISI_SAS_INT_ABT_DEV = 1,
@@ -145,6 +152,7 @@ struct hisi_sas_phy {
 	struct asd_sas_phy	sas_phy;
 	struct sas_identify	identify;
 	struct completion *reset_completion;
+	struct timer_list timer;
 	spinlock_t lock;
 	u64		port_id; /* from hw */
 	u64		frame_rcvd_size;
@@ -165,6 +173,7 @@ struct hisi_sas_port {
 
 struct hisi_sas_cq {
 	struct hisi_hba *hisi_hba;
+	const struct cpumask *pci_irq_mask;
 	struct tasklet_struct tasklet;
 	int	rd_point;
 	int	id;
@@ -187,7 +196,7 @@ struct hisi_sas_device {
 	enum sas_device_type	dev_type;
 	int device_id;
 	int sata_idx;
-	u8 dev_status;
+	spinlock_t lock; /* For protecting slots */
 };
 
 struct hisi_sas_tmf_task {
@@ -203,12 +212,14 @@ struct hisi_sas_slot {
 	struct sas_task *task;
 	struct hisi_sas_port	*port;
 	u64	n_elem;
+	u64	n_elem_dif;
 	int	dlvry_queue;
 	int	dlvry_queue_slot;
 	int	cmplt_queue;
 	int	cmplt_queue_slot;
 	int	abort;
 	int	ready;
+	int	device_id;
 	void	*cmd_hdr;
 	dma_addr_t cmd_hdr_dma;
 	struct timer_list internal_abort_timer;
@@ -220,6 +231,24 @@ struct hisi_sas_slot {
 	u16	idx;
 };
 
+#define HISI_SAS_DEBUGFS_REG(x) {#x, x}
+
+struct hisi_sas_debugfs_reg_lu {
+	char *name;
+	int off;
+};
+
+struct hisi_sas_debugfs_reg {
+	const struct hisi_sas_debugfs_reg_lu *lu;
+	int count;
+	int base_off;
+	union {
+		u32 (*read_global_reg)(struct hisi_hba *hisi_hba, u32 off);
+		u32 (*read_port_reg)(struct hisi_hba *hisi_hba, int port,
+				     u32 off);
+	};
+};
+
 struct hisi_sas_hw {
 	int (*hw_init)(struct hisi_hba *hisi_hba);
 	void (*setup_itct)(struct hisi_hba *hisi_hba,
@@ -227,7 +256,7 @@ struct hisi_sas_hw {
 	int (*slot_index_alloc)(struct hisi_hba *hisi_hba,
 				struct domain_device *device);
 	struct hisi_sas_device *(*alloc_dev)(struct domain_device *device);
-	void (*sl_notify)(struct hisi_hba *hisi_hba, int phy_no);
+	void (*sl_notify_ssp)(struct hisi_hba *hisi_hba, int phy_no);
 	int (*get_free_slot)(struct hisi_hba *hisi_hba, struct hisi_sas_dq *dq);
 	void (*start_delivery)(struct hisi_sas_dq *dq);
 	void (*prep_ssp)(struct hisi_hba *hisi_hba,
@@ -259,11 +288,16 @@ struct hisi_sas_hw {
 	u32 (*get_phys_state)(struct hisi_hba *hisi_hba);
 	int (*write_gpio)(struct hisi_hba *hisi_hba, u8 reg_type,
 				u8 reg_index, u8 reg_count, u8 *write_data);
-	void (*wait_cmds_complete_timeout)(struct hisi_hba *hisi_hba,
-					   int delay_ms, int timeout_ms);
+	int (*wait_cmds_complete_timeout)(struct hisi_hba *hisi_hba,
+					  int delay_ms, int timeout_ms);
+	void (*snapshot_prepare)(struct hisi_hba *hisi_hba);
+	void (*snapshot_restore)(struct hisi_hba *hisi_hba);
 	int max_command_entries;
 	int complete_hdr_size;
 	struct scsi_host_template *sht;
+
+	const struct hisi_sas_debugfs_reg *debugfs_reg_global;
+	const struct hisi_sas_debugfs_reg *debugfs_reg_port;
 };
 
 struct hisi_hba {
@@ -329,9 +363,25 @@ struct hisi_hba {
 	const struct hisi_sas_hw *hw;	/* Low level hw interface */
 	unsigned long sata_dev_bitmap[BITS_TO_LONGS(HISI_SAS_MAX_DEVICES)];
 	struct work_struct rst_work;
+	struct work_struct debugfs_work;
 	u32 phy_state;
 	u32 intr_coal_ticks;	/* Time of interrupt coalesce in us */
 	u32 intr_coal_count;	/* Interrupt count to coalesce */
+
+	int cq_nvecs;
+	unsigned int *reply_map;
+
+	/* debugfs memories */
+	u32 *debugfs_global_reg;
+	u32 *debugfs_port_reg[HISI_SAS_MAX_PHYS];
+	void *debugfs_complete_hdr[HISI_SAS_MAX_QUEUES];
+	struct hisi_sas_cmd_hdr	*debugfs_cmd_hdr[HISI_SAS_MAX_QUEUES];
+	struct hisi_sas_iost *debugfs_iost;
+	struct hisi_sas_itct *debugfs_itct;
+
+	struct dentry *debugfs_dir;
+	struct dentry *debugfs_dump_dentry;
+	bool debugfs_snapshot;
 };
 
 /* Generic HW DMA host memory structures */
@@ -430,6 +480,11 @@ struct hisi_sas_sge_page {
 	struct hisi_sas_sge sge[HISI_SAS_SGE_PAGE_CNT];
 }  __aligned(16);
 
+#define HISI_SAS_SGE_DIF_PAGE_CNT   SG_CHUNK_SIZE
+struct hisi_sas_sge_dif_page {
+	struct hisi_sas_sge sge[HISI_SAS_SGE_DIF_PAGE_CNT];
+}  __aligned(16);
+
 struct hisi_sas_command_table_ssp {
 	struct ssp_frame_hdr hdr;
 	union {
@@ -460,9 +515,18 @@ struct hisi_sas_slot_buf_table {
 	struct hisi_sas_sge_page sge_page;
 };
 
+struct hisi_sas_slot_dif_buf_table {
+	struct hisi_sas_slot_buf_table slot_buf;
+	struct hisi_sas_sge_dif_page sge_dif_page;
+};
+
 extern struct scsi_transport_template *hisi_sas_stt;
+
+extern bool hisi_sas_debugfs_enable;
+extern struct dentry *hisi_sas_debugfs_dir;
+
 extern void hisi_sas_stop_phys(struct hisi_hba *hisi_hba);
-extern int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost);
+extern int hisi_sas_alloc(struct hisi_hba *hisi_hba);
 extern void hisi_sas_free(struct hisi_hba *hisi_hba);
 extern u8 hisi_sas_get_ata_protocol(struct host_to_dev_fis *fis,
 				int direction);
@@ -487,10 +551,14 @@ extern void hisi_sas_init_mem(struct hisi_hba *hisi_hba);
 extern void hisi_sas_rst_work_handler(struct work_struct *work);
 extern void hisi_sas_sync_rst_work_handler(struct work_struct *work);
 extern void hisi_sas_kill_tasklets(struct hisi_hba *hisi_hba);
+extern void hisi_sas_phy_oob_ready(struct hisi_hba *hisi_hba, int phy_no);
 extern bool hisi_sas_notify_phy_event(struct hisi_sas_phy *phy,
 				enum hisi_sas_phy_event event);
 extern void hisi_sas_release_tasks(struct hisi_hba *hisi_hba);
 extern u8 hisi_sas_get_prog_phy_linkrate_mask(enum sas_linkrate max);
 extern void hisi_sas_controller_reset_prepare(struct hisi_hba *hisi_hba);
 extern void hisi_sas_controller_reset_done(struct hisi_hba *hisi_hba);
+extern void hisi_sas_debugfs_init(struct hisi_hba *hisi_hba);
+extern void hisi_sas_debugfs_exit(struct hisi_hba *hisi_hba);
+extern void hisi_sas_debugfs_work_handler(struct work_struct *work);
 #endif
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index bc17fa0d8375..13ca5a0bdf6b 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -144,7 +144,7 @@ EXPORT_SYMBOL_GPL(hisi_sas_get_ncq_tag);
  */
 u8 hisi_sas_get_prog_phy_linkrate_mask(enum sas_linkrate max)
 {
-	u16 rate = 0;
+	u8 rate = 0;
 	int i;
 
 	max -= SAS_LINK_RATE_1_5_GBPS;
@@ -241,8 +241,9 @@ static void hisi_sas_slot_index_init(struct hisi_hba *hisi_hba)
 void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task,
 			     struct hisi_sas_slot *slot)
 {
-	struct hisi_sas_dq *dq = &hisi_hba->dq[slot->dlvry_queue];
 	unsigned long flags;
+	int device_id = slot->device_id;
+	struct hisi_sas_device *sas_dev = &hisi_hba->devices[device_id];
 
 	if (task) {
 		struct device *dev = hisi_hba->dev;
@@ -252,17 +253,24 @@ void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task,
 
 		task->lldd_task = NULL;
 
-		if (!sas_protocol_ata(task->task_proto))
+		if (!sas_protocol_ata(task->task_proto)) {
+			struct sas_ssp_task *ssp_task = &task->ssp_task;
+			struct scsi_cmnd *scsi_cmnd = ssp_task->cmd;
+
 			if (slot->n_elem)
 				dma_unmap_sg(dev, task->scatter,
 					     task->num_scatter,
 					     task->data_dir);
+			if (slot->n_elem_dif)
+				dma_unmap_sg(dev, scsi_prot_sglist(scsi_cmnd),
+					     scsi_prot_sg_count(scsi_cmnd),
+					     task->data_dir);
+		}
 	}
 
-
-	spin_lock_irqsave(&dq->lock, flags);
+	spin_lock_irqsave(&sas_dev->lock, flags);
 	list_del_init(&slot->entry);
-	spin_unlock_irqrestore(&dq->lock, flags);
+	spin_unlock_irqrestore(&sas_dev->lock, flags);
 
 	memset(slot, 0, offsetof(struct hisi_sas_slot, buf));
 
@@ -380,6 +388,59 @@ prep_out:
 	return rc;
 }
 
+static void hisi_sas_dif_dma_unmap(struct hisi_hba *hisi_hba,
+				   struct sas_task *task, int n_elem_dif)
+{
+	struct device *dev = hisi_hba->dev;
+
+	if (n_elem_dif) {
+		struct sas_ssp_task *ssp_task = &task->ssp_task;
+		struct scsi_cmnd *scsi_cmnd = ssp_task->cmd;
+
+		dma_unmap_sg(dev, scsi_prot_sglist(scsi_cmnd),
+			     scsi_prot_sg_count(scsi_cmnd),
+			     task->data_dir);
+	}
+}
+
+static int hisi_sas_dif_dma_map(struct hisi_hba *hisi_hba,
+				int *n_elem_dif, struct sas_task *task)
+{
+	struct device *dev = hisi_hba->dev;
+	struct sas_ssp_task *ssp_task;
+	struct scsi_cmnd *scsi_cmnd;
+	int rc;
+
+	if (task->num_scatter) {
+		ssp_task = &task->ssp_task;
+		scsi_cmnd = ssp_task->cmd;
+
+		if (scsi_prot_sg_count(scsi_cmnd)) {
+			*n_elem_dif = dma_map_sg(dev,
+						 scsi_prot_sglist(scsi_cmnd),
+						 scsi_prot_sg_count(scsi_cmnd),
+						 task->data_dir);
+
+			if (!*n_elem_dif)
+				return -ENOMEM;
+
+			if (*n_elem_dif > HISI_SAS_SGE_DIF_PAGE_CNT) {
+				dev_err(dev, "task prep: n_elem_dif(%d) too large\n",
+					*n_elem_dif);
+				rc = -EINVAL;
+				goto err_out_dif_dma_unmap;
+			}
+		}
+	}
+
+	return 0;
+
+err_out_dif_dma_unmap:
+	dma_unmap_sg(dev, scsi_prot_sglist(scsi_cmnd),
+		     scsi_prot_sg_count(scsi_cmnd), task->data_dir);
+	return rc;
+}
+
 static int hisi_sas_task_prep(struct sas_task *task,
 			      struct hisi_sas_dq **dq_pointer,
 			      bool is_tmf, struct hisi_sas_tmf_task *tmf,
@@ -394,7 +455,7 @@ static int hisi_sas_task_prep(struct sas_task *task,
 	struct asd_sas_port *sas_port = device->port;
 	struct device *dev = hisi_hba->dev;
 	int dlvry_queue_slot, dlvry_queue, rc, slot_idx;
-	int n_elem = 0, n_elem_req = 0, n_elem_resp = 0;
+	int n_elem = 0, n_elem_dif = 0, n_elem_req = 0, n_elem_resp = 0;
 	struct hisi_sas_dq *dq;
 	unsigned long flags;
 	int wr_q_index;
@@ -410,7 +471,14 @@ static int hisi_sas_task_prep(struct sas_task *task,
 		return -ECOMM;
 	}
 
-	*dq_pointer = dq = sas_dev->dq;
+	if (hisi_hba->reply_map) {
+		int cpu = raw_smp_processor_id();
+		unsigned int dq_index = hisi_hba->reply_map[cpu];
+
+		*dq_pointer = dq = &hisi_hba->dq[dq_index];
+	} else {
+		*dq_pointer = dq = sas_dev->dq;
+	}
 
 	port = to_hisi_sas_port(sas_port);
 	if (port && !port->port_attached) {
@@ -427,6 +495,12 @@ static int hisi_sas_task_prep(struct sas_task *task,
 	if (rc < 0)
 		goto prep_out;
 
+	if (!sas_protocol_ata(task->task_proto)) {
+		rc = hisi_sas_dif_dma_map(hisi_hba, &n_elem_dif, task);
+		if (rc < 0)
+			goto err_out_dma_unmap;
+	}
+
 	if (hisi_hba->hw->slot_index_alloc)
 		rc = hisi_hba->hw->slot_index_alloc(hisi_hba, device);
 	else {
@@ -445,7 +519,7 @@ static int hisi_sas_task_prep(struct sas_task *task,
 		rc  = hisi_sas_slot_index_alloc(hisi_hba, scsi_cmnd);
 	}
 	if (rc < 0)
-		goto err_out_dma_unmap;
+		goto err_out_dif_dma_unmap;
 
 	slot_idx = rc;
 	slot = &hisi_hba->slot_info[slot_idx];
@@ -459,13 +533,17 @@ static int hisi_sas_task_prep(struct sas_task *task,
 	}
 
 	list_add_tail(&slot->delivery, &dq->list);
-	list_add_tail(&slot->entry, &sas_dev->list);
 	spin_unlock_irqrestore(&dq->lock, flags);
+	spin_lock_irqsave(&sas_dev->lock, flags);
+	list_add_tail(&slot->entry, &sas_dev->list);
+	spin_unlock_irqrestore(&sas_dev->lock, flags);
 
 	dlvry_queue = dq->id;
 	dlvry_queue_slot = wr_q_index;
 
+	slot->device_id = sas_dev->device_id;
 	slot->n_elem = n_elem;
+	slot->n_elem_dif = n_elem_dif;
 	slot->dlvry_queue = dlvry_queue;
 	slot->dlvry_queue_slot = dlvry_queue_slot;
 	cmd_hdr_base = hisi_hba->cmd_hdr[dlvry_queue];
@@ -509,6 +587,9 @@ static int hisi_sas_task_prep(struct sas_task *task,
 
 err_out_tag:
 	hisi_sas_slot_index_free(hisi_hba, slot_idx);
+err_out_dif_dma_unmap:
+	if (!sas_protocol_ata(task->task_proto))
+		hisi_sas_dif_dma_unmap(hisi_hba, task, n_elem_dif);
 err_out_dma_unmap:
 	hisi_sas_dma_unmap(hisi_hba, task, n_elem,
 			   n_elem_req, n_elem_resp);
@@ -626,11 +707,11 @@ static struct hisi_sas_device *hisi_sas_alloc_dev(struct domain_device *device)
 
 			hisi_hba->devices[i].device_id = i;
 			sas_dev = &hisi_hba->devices[i];
-			sas_dev->dev_status = HISI_SAS_DEV_NORMAL;
 			sas_dev->dev_type = device->dev_type;
 			sas_dev->hisi_hba = hisi_hba;
 			sas_dev->sas_device = device;
 			sas_dev->dq = dq;
+			spin_lock_init(&sas_dev->lock);
 			INIT_LIST_HEAD(&hisi_hba->devices[i].list);
 			break;
 		}
@@ -778,7 +859,8 @@ static void hisi_sas_phyup_work(struct work_struct *work)
 	struct asd_sas_phy *sas_phy = &phy->sas_phy;
 	int phy_no = sas_phy->id;
 
-	hisi_hba->hw->sl_notify(hisi_hba, phy_no); /* This requires a sleep */
+	if (phy->identify.target_port_protocols == SAS_PROTOCOL_SSP)
+		hisi_hba->hw->sl_notify_ssp(hisi_hba, phy_no);
 	hisi_sas_bytes_dmaed(hisi_hba, phy_no);
 }
 
@@ -808,6 +890,30 @@ bool hisi_sas_notify_phy_event(struct hisi_sas_phy *phy,
 }
 EXPORT_SYMBOL_GPL(hisi_sas_notify_phy_event);
 
+static void hisi_sas_wait_phyup_timedout(struct timer_list *t)
+{
+	struct hisi_sas_phy *phy = from_timer(phy, t, timer);
+	struct hisi_hba *hisi_hba = phy->hisi_hba;
+	struct device *dev = hisi_hba->dev;
+	int phy_no = phy->sas_phy.id;
+
+	dev_warn(dev, "phy%d wait phyup timeout, issuing link reset\n", phy_no);
+	hisi_sas_notify_phy_event(phy, HISI_PHYE_LINK_RESET);
+}
+
+void hisi_sas_phy_oob_ready(struct hisi_hba *hisi_hba, int phy_no)
+{
+	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
+	struct device *dev = hisi_hba->dev;
+
+	if (!timer_pending(&phy->timer)) {
+		dev_dbg(dev, "phy%d OOB ready\n", phy_no);
+		phy->timer.expires = jiffies + HISI_SAS_WAIT_PHYUP_TIMEOUT * HZ;
+		add_timer(&phy->timer);
+	}
+}
+EXPORT_SYMBOL_GPL(hisi_sas_phy_oob_ready);
+
 static void hisi_sas_phy_init(struct hisi_hba *hisi_hba, int phy_no)
 {
 	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
@@ -836,6 +942,8 @@ static void hisi_sas_phy_init(struct hisi_hba *hisi_hba, int phy_no)
 		INIT_WORK(&phy->works[i], hisi_sas_phye_fns[i]);
 
 	spin_lock_init(&phy->lock);
+
+	timer_setup(&phy->timer, hisi_sas_wait_phyup_timedout, 0);
 }
 
 static void hisi_sas_port_notify_formed(struct asd_sas_phy *sas_phy)
@@ -926,7 +1034,7 @@ static void hisi_sas_dev_gone(struct domain_device *device)
 
 	if (!test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags)) {
 		hisi_sas_internal_task_abort(hisi_hba, device,
-				     HISI_SAS_INT_ABT_DEV, 0);
+					     HISI_SAS_INT_ABT_DEV, 0);
 
 		hisi_sas_dereg_device(hisi_hba, device);
 
@@ -946,7 +1054,7 @@ static int hisi_sas_queue_command(struct sas_task *task, gfp_t gfp_flags)
 	return hisi_sas_task_exec(task, gfp_flags, 0, NULL);
 }
 
-static void hisi_sas_phy_set_linkrate(struct hisi_hba *hisi_hba, int phy_no,
+static int hisi_sas_phy_set_linkrate(struct hisi_hba *hisi_hba, int phy_no,
 			struct sas_phy_linkrates *r)
 {
 	struct sas_phy_linkrates _r;
@@ -955,6 +1063,9 @@ static void hisi_sas_phy_set_linkrate(struct hisi_hba *hisi_hba, int phy_no,
 	struct asd_sas_phy *sas_phy = &phy->sas_phy;
 	enum sas_linkrate min, max;
 
+	if (r->minimum_linkrate > SAS_LINK_RATE_1_5_GBPS)
+		return -EINVAL;
+
 	if (r->maximum_linkrate == SAS_LINK_RATE_UNKNOWN) {
 		max = sas_phy->phy->maximum_linkrate;
 		min = r->minimum_linkrate;
@@ -962,7 +1073,7 @@ static void hisi_sas_phy_set_linkrate(struct hisi_hba *hisi_hba, int phy_no,
 		max = r->maximum_linkrate;
 		min = sas_phy->phy->minimum_linkrate;
 	} else
-		return;
+		return -EINVAL;
 
 	_r.maximum_linkrate = max;
 	_r.minimum_linkrate = min;
@@ -974,6 +1085,8 @@ static void hisi_sas_phy_set_linkrate(struct hisi_hba *hisi_hba, int phy_no,
 	msleep(100);
 	hisi_hba->hw->phy_set_linkrate(hisi_hba, phy_no, &_r);
 	hisi_hba->hw->phy_start(hisi_hba, phy_no);
+
+	return 0;
 }
 
 static int hisi_sas_control_phy(struct asd_sas_phy *sas_phy, enum phy_func func,
@@ -999,8 +1112,7 @@ static int hisi_sas_control_phy(struct asd_sas_phy *sas_phy, enum phy_func func,
 		break;
 
 	case PHY_FUNC_SET_LINK_RATE:
-		hisi_sas_phy_set_linkrate(hisi_hba, phy_no, funcdata);
-		break;
+		return hisi_sas_phy_set_linkrate(hisi_hba, phy_no, funcdata);
 	case PHY_FUNC_GET_EVENTS:
 		if (hisi_hba->hw->get_events) {
 			hisi_hba->hw->get_events(hisi_hba, phy_no);
@@ -1068,7 +1180,7 @@ static int hisi_sas_exec_internal_tmf_task(struct domain_device *device,
 		task->task_done = hisi_sas_task_done;
 
 		task->slow_task->timer.function = hisi_sas_tmf_timedout;
-		task->slow_task->timer.expires = jiffies + TASK_TIMEOUT*HZ;
+		task->slow_task->timer.expires = jiffies + TASK_TIMEOUT * HZ;
 		add_timer(&task->slow_task->timer);
 
 		res = hisi_sas_task_exec(task, GFP_KERNEL, 1, tmf);
@@ -1429,6 +1541,9 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
 	struct Scsi_Host *shost = hisi_hba->shost;
 	int rc;
 
+	if (hisi_sas_debugfs_enable && hisi_hba->debugfs_itct)
+		queue_work(hisi_hba->wq, &hisi_hba->debugfs_work);
+
 	if (!hisi_hba->hw->soft_reset)
 		return -1;
 
@@ -1491,7 +1606,6 @@ static int hisi_sas_abort_task(struct sas_task *task)
 	task->task_state_flags |= SAS_TASK_STATE_ABORTED;
 	spin_unlock_irqrestore(&task->task_state_lock, flags);
 
-	sas_dev->dev_status = HISI_SAS_DEV_EH;
 	if (task->lldd_task && task->task_proto & SAS_PROTOCOL_SSP) {
 		struct scsi_cmnd *cmnd = task->uldd_task;
 		struct hisi_sas_slot *slot = task->lldd_task;
@@ -1527,7 +1641,8 @@ static int hisi_sas_abort_task(struct sas_task *task)
 		task->task_proto & SAS_PROTOCOL_STP) {
 		if (task->dev->dev_type == SAS_SATA_DEV) {
 			rc = hisi_sas_internal_task_abort(hisi_hba, device,
-						HISI_SAS_INT_ABT_DEV, 0);
+							  HISI_SAS_INT_ABT_DEV,
+							  0);
 			if (rc < 0) {
 				dev_err(dev, "abort task: internal abort failed\n");
 				goto out;
@@ -1542,7 +1657,7 @@ static int hisi_sas_abort_task(struct sas_task *task)
 		struct hisi_sas_cq *cq = &hisi_hba->cq[slot->dlvry_queue];
 
 		rc = hisi_sas_internal_task_abort(hisi_hba, device,
-			     HISI_SAS_INT_ABT_CMD, tag);
+						  HISI_SAS_INT_ABT_CMD, tag);
 		if (((rc < 0) || (rc == TMF_RESP_FUNC_FAILED)) &&
 					task->lldd_task) {
 			/*
@@ -1568,7 +1683,7 @@ static int hisi_sas_abort_task_set(struct domain_device *device, u8 *lun)
 	int rc = TMF_RESP_FUNC_FAILED;
 
 	rc = hisi_sas_internal_task_abort(hisi_hba, device,
-					HISI_SAS_INT_ABT_DEV, 0);
+					  HISI_SAS_INT_ABT_DEV, 0);
 	if (rc < 0) {
 		dev_err(dev, "abort task set: internal abort rc=%d\n", rc);
 		return TMF_RESP_FUNC_FAILED;
@@ -1586,8 +1701,8 @@ static int hisi_sas_abort_task_set(struct domain_device *device, u8 *lun)
 
 static int hisi_sas_clear_aca(struct domain_device *device, u8 *lun)
 {
-	int rc = TMF_RESP_FUNC_FAILED;
 	struct hisi_sas_tmf_task tmf_task;
+	int rc;
 
 	tmf_task.tmf = TMF_CLEAR_ACA;
 	rc = hisi_sas_debug_issue_ssp_tmf(device, lun, &tmf_task);
@@ -1635,17 +1750,12 @@ static int hisi_sas_debug_I_T_nexus_reset(struct domain_device *device)
 
 static int hisi_sas_I_T_nexus_reset(struct domain_device *device)
 {
-	struct hisi_sas_device *sas_dev = device->lldd_dev;
 	struct hisi_hba *hisi_hba = dev_to_hisi_hba(device);
 	struct device *dev = hisi_hba->dev;
-	int rc = TMF_RESP_FUNC_FAILED;
-
-	if (sas_dev->dev_status != HISI_SAS_DEV_EH)
-		return TMF_RESP_FUNC_FAILED;
-	sas_dev->dev_status = HISI_SAS_DEV_NORMAL;
+	int rc;
 
 	rc = hisi_sas_internal_task_abort(hisi_hba, device,
-					HISI_SAS_INT_ABT_DEV, 0);
+					  HISI_SAS_INT_ABT_DEV, 0);
 	if (rc < 0) {
 		dev_err(dev, "I_T nexus reset: internal abort (%d)\n", rc);
 		return TMF_RESP_FUNC_FAILED;
@@ -1667,7 +1777,6 @@ static int hisi_sas_lu_reset(struct domain_device *device, u8 *lun)
 	struct device *dev = hisi_hba->dev;
 	int rc = TMF_RESP_FUNC_FAILED;
 
-	sas_dev->dev_status = HISI_SAS_DEV_EH;
 	if (dev_is_sata(device)) {
 		struct sas_phy *phy;
 
@@ -1691,7 +1800,7 @@ static int hisi_sas_lu_reset(struct domain_device *device, u8 *lun)
 		struct hisi_sas_tmf_task tmf_task = { .tmf =  TMF_LU_RESET };
 
 		rc = hisi_sas_internal_task_abort(hisi_hba, device,
-						HISI_SAS_INT_ABT_DEV, 0);
+						  HISI_SAS_INT_ABT_DEV, 0);
 		if (rc < 0) {
 			dev_err(dev, "lu_reset: internal abort failed\n");
 			goto out;
@@ -1777,7 +1886,7 @@ static int hisi_sas_query_task(struct sas_task *task)
 static int
 hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, int device_id,
 				  struct sas_task *task, int abort_flag,
-				  int task_tag)
+				  int task_tag, struct hisi_sas_dq *dq)
 {
 	struct domain_device *device = task->dev;
 	struct hisi_sas_device *sas_dev = device->lldd_dev;
@@ -1786,7 +1895,6 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, int device_id,
 	struct hisi_sas_slot *slot;
 	struct asd_sas_port *sas_port = device->port;
 	struct hisi_sas_cmd_hdr *cmd_hdr_base;
-	struct hisi_sas_dq *dq = sas_dev->dq;
 	int dlvry_queue_slot, dlvry_queue, n_elem = 0, rc, slot_idx;
 	unsigned long flags, flags_dq = 0;
 	int wr_q_index;
@@ -1816,10 +1924,14 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, int device_id,
 	}
 	list_add_tail(&slot->delivery, &dq->list);
 	spin_unlock_irqrestore(&dq->lock, flags_dq);
+	spin_lock_irqsave(&sas_dev->lock, flags);
+	list_add_tail(&slot->entry, &sas_dev->list);
+	spin_unlock_irqrestore(&sas_dev->lock, flags);
 
 	dlvry_queue = dq->id;
 	dlvry_queue_slot = wr_q_index;
 
+	slot->device_id = sas_dev->device_id;
 	slot->n_elem = n_elem;
 	slot->dlvry_queue = dlvry_queue;
 	slot->dlvry_queue_slot = dlvry_queue_slot;
@@ -1843,7 +1955,6 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, int device_id,
 	WRITE_ONCE(slot->ready, 1);
 	/* send abort command to the chip */
 	spin_lock_irqsave(&dq->lock, flags);
-	list_add_tail(&slot->entry, &sas_dev->list);
 	hisi_hba->hw->start_delivery(dq);
 	spin_unlock_irqrestore(&dq->lock, flags);
 
@@ -1858,18 +1969,19 @@ err_out:
 }
 
 /**
- * hisi_sas_internal_task_abort -- execute an internal
+ * _hisi_sas_internal_task_abort -- execute an internal
  * abort command for single IO command or a device
  * @hisi_hba: host controller struct
  * @device: domain device
  * @abort_flag: mode of operation, device or single IO
  * @tag: tag of IO to be aborted (only relevant to single
  *       IO mode)
+ * @dq: delivery queue for this internal abort command
  */
 static int
-hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba,
-			     struct domain_device *device,
-			     int abort_flag, int tag)
+_hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba,
+			      struct domain_device *device, int abort_flag,
+			      int tag, struct hisi_sas_dq *dq)
 {
 	struct sas_task *task;
 	struct hisi_sas_device *sas_dev = device->lldd_dev;
@@ -1893,11 +2005,11 @@ hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba,
 	task->task_proto = device->tproto;
 	task->task_done = hisi_sas_task_done;
 	task->slow_task->timer.function = hisi_sas_tmf_timedout;
-	task->slow_task->timer.expires = jiffies + INTERNAL_ABORT_TIMEOUT*HZ;
+	task->slow_task->timer.expires = jiffies + INTERNAL_ABORT_TIMEOUT * HZ;
 	add_timer(&task->slow_task->timer);
 
 	res = hisi_sas_internal_abort_task_exec(hisi_hba, sas_dev->device_id,
-						task, abort_flag, tag);
+						task, abort_flag, tag, dq);
 	if (res) {
 		del_timer(&task->slow_task->timer);
 		dev_err(dev, "internal task abort: executing internal task failed: %d\n",
@@ -1923,6 +2035,7 @@ hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba,
 				slot->task = NULL;
 			}
 			dev_err(dev, "internal task abort: timeout and not done.\n");
+
 			res = -EIO;
 			goto exit;
 		} else
@@ -1953,6 +2066,46 @@ exit:
 	return res;
 }
 
+static int
+hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba,
+			     struct domain_device *device,
+			     int abort_flag, int tag)
+{
+	struct hisi_sas_slot *slot;
+	struct device *dev = hisi_hba->dev;
+	struct hisi_sas_dq *dq;
+	int i, rc;
+
+	switch (abort_flag) {
+	case HISI_SAS_INT_ABT_CMD:
+		slot = &hisi_hba->slot_info[tag];
+		dq = &hisi_hba->dq[slot->dlvry_queue];
+		return _hisi_sas_internal_task_abort(hisi_hba, device,
+						     abort_flag, tag, dq);
+	case HISI_SAS_INT_ABT_DEV:
+		for (i = 0; i < hisi_hba->cq_nvecs; i++) {
+			struct hisi_sas_cq *cq = &hisi_hba->cq[i];
+			const struct cpumask *mask = cq->pci_irq_mask;
+
+			if (mask && !cpumask_intersects(cpu_online_mask, mask))
+				continue;
+			dq = &hisi_hba->dq[i];
+			rc = _hisi_sas_internal_task_abort(hisi_hba, device,
+							   abort_flag, tag,
+							   dq);
+			if (rc)
+				return rc;
+		}
+		break;
+	default:
+		dev_err(dev, "Unrecognised internal abort flag (%d)\n",
+			abort_flag);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static void hisi_sas_port_formed(struct asd_sas_phy *sas_phy)
 {
 	hisi_sas_port_notify_formed(sas_phy);
@@ -2019,7 +2172,7 @@ void hisi_sas_kill_tasklets(struct hisi_hba *hisi_hba)
 {
 	int i;
 
-	for (i = 0; i < hisi_hba->queue_count; i++) {
+	for (i = 0; i < hisi_hba->cq_nvecs; i++) {
 		struct hisi_sas_cq *cq = &hisi_hba->cq[i];
 
 		tasklet_kill(&cq->tasklet);
@@ -2048,14 +2201,18 @@ static struct sas_domain_function_template hisi_sas_transport_ops = {
 
 void hisi_sas_init_mem(struct hisi_hba *hisi_hba)
 {
-	int i, s, max_command_entries = hisi_hba->hw->max_command_entries;
+	int i, s, j, max_command_entries = hisi_hba->hw->max_command_entries;
+	struct hisi_sas_breakpoint *sata_breakpoint = hisi_hba->sata_breakpoint;
 
 	for (i = 0; i < hisi_hba->queue_count; i++) {
 		struct hisi_sas_cq *cq = &hisi_hba->cq[i];
 		struct hisi_sas_dq *dq = &hisi_hba->dq[i];
+		struct hisi_sas_cmd_hdr *cmd_hdr = hisi_hba->cmd_hdr[i];
+
+		s = sizeof(struct hisi_sas_cmd_hdr);
+		for (j = 0; j < HISI_SAS_QUEUE_SLOTS; j++)
+			memset(&cmd_hdr[j], 0, s);
 
-		s = sizeof(struct hisi_sas_cmd_hdr) * HISI_SAS_QUEUE_SLOTS;
-		memset(hisi_hba->cmd_hdr[i], 0, s);
 		dq->wr_point = 0;
 
 		s = hisi_hba->hw->complete_hdr_size * HISI_SAS_QUEUE_SLOTS;
@@ -2072,12 +2229,13 @@ void hisi_sas_init_mem(struct hisi_hba *hisi_hba)
 	s = max_command_entries * sizeof(struct hisi_sas_breakpoint);
 	memset(hisi_hba->breakpoint, 0, s);
 
-	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_sata_breakpoint);
-	memset(hisi_hba->sata_breakpoint, 0, s);
+	s = sizeof(struct hisi_sas_sata_breakpoint);
+	for (j = 0; j < HISI_SAS_MAX_ITCT_ENTRIES; j++)
+		memset(&sata_breakpoint[j], 0, s);
 }
 EXPORT_SYMBOL_GPL(hisi_sas_init_mem);
 
-int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
+int hisi_sas_alloc(struct hisi_hba *hisi_hba)
 {
 	struct device *dev = hisi_hba->dev;
 	int i, j, s, max_command_entries = hisi_hba->hw->max_command_entries;
@@ -2095,7 +2253,6 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 	for (i = 0; i < HISI_SAS_MAX_DEVICES; i++) {
 		hisi_hba->devices[i].dev_type = SAS_PHY_UNUSED;
 		hisi_hba->devices[i].device_id = i;
-		hisi_hba->devices[i].dev_status = HISI_SAS_DEV_NORMAL;
 	}
 
 	for (i = 0; i < hisi_hba->queue_count; i++) {
@@ -2131,10 +2288,9 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 
 	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_itct);
 	hisi_hba->itct = dmam_alloc_coherent(dev, s, &hisi_hba->itct_dma,
-					     GFP_KERNEL);
+					     GFP_KERNEL | __GFP_ZERO);
 	if (!hisi_hba->itct)
 		goto err_out;
-	memset(hisi_hba->itct, 0, s);
 
 	hisi_hba->slot_info = devm_kcalloc(dev, max_command_entries,
 					   sizeof(struct hisi_sas_slot),
@@ -2144,19 +2300,24 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 
 	/* roundup to avoid overly large block size */
 	max_command_entries_ru = roundup(max_command_entries, 64);
-	sz_slot_buf_ru = roundup(sizeof(struct hisi_sas_slot_buf_table), 64);
+	if (hisi_hba->prot_mask & HISI_SAS_DIX_PROT_MASK)
+		sz_slot_buf_ru = sizeof(struct hisi_sas_slot_dif_buf_table);
+	else
+		sz_slot_buf_ru = sizeof(struct hisi_sas_slot_buf_table);
+	sz_slot_buf_ru = roundup(sz_slot_buf_ru, 64);
 	s = lcm(max_command_entries_ru, sz_slot_buf_ru);
 	blk_cnt = (max_command_entries_ru * sz_slot_buf_ru) / s;
 	slots_per_blk = s / sz_slot_buf_ru;
+
 	for (i = 0; i < blk_cnt; i++) {
-		struct hisi_sas_slot_buf_table *buf;
-		dma_addr_t buf_dma;
 		int slot_index = i * slots_per_blk;
+		dma_addr_t buf_dma;
+		void *buf;
 
-		buf = dmam_alloc_coherent(dev, s, &buf_dma, GFP_KERNEL);
+		buf = dmam_alloc_coherent(dev, s, &buf_dma,
+					  GFP_KERNEL | __GFP_ZERO);
 		if (!buf)
 			goto err_out;
-		memset(buf, 0, s);
 
 		for (j = 0; j < slots_per_blk; j++, slot_index++) {
 			struct hisi_sas_slot *slot;
@@ -2166,8 +2327,8 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 			slot->buf_dma = buf_dma;
 			slot->idx = slot_index;
 
-			buf++;
-			buf_dma += sizeof(*buf);
+			buf += sz_slot_buf_ru;
+			buf_dma += sz_slot_buf_ru;
 		}
 	}
 
@@ -2365,7 +2526,7 @@ static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
 			goto err_out;
 	}
 
-	if (hisi_sas_alloc(hisi_hba, shost)) {
+	if (hisi_sas_alloc(hisi_hba)) {
 		hisi_sas_free(hisi_hba);
 		goto err_out;
 	}
@@ -2461,6 +2622,555 @@ err_out_ha:
 }
 EXPORT_SYMBOL_GPL(hisi_sas_probe);
 
+struct dentry *hisi_sas_debugfs_dir;
+
+static void hisi_sas_debugfs_snapshot_cq_reg(struct hisi_hba *hisi_hba)
+{
+	int queue_entry_size = hisi_hba->hw->complete_hdr_size;
+	int i;
+
+	for (i = 0; i < hisi_hba->queue_count; i++)
+		memcpy(hisi_hba->debugfs_complete_hdr[i],
+		       hisi_hba->complete_hdr[i],
+		       HISI_SAS_QUEUE_SLOTS * queue_entry_size);
+}
+
+static void hisi_sas_debugfs_snapshot_dq_reg(struct hisi_hba *hisi_hba)
+{
+	int queue_entry_size = sizeof(struct hisi_sas_cmd_hdr);
+	int i;
+
+	for (i = 0; i < hisi_hba->queue_count; i++) {
+		struct hisi_sas_cmd_hdr	*debugfs_cmd_hdr, *cmd_hdr;
+		int j;
+
+		debugfs_cmd_hdr = hisi_hba->debugfs_cmd_hdr[i];
+		cmd_hdr = hisi_hba->cmd_hdr[i];
+
+		for (j = 0; j < HISI_SAS_QUEUE_SLOTS; j++)
+			memcpy(&debugfs_cmd_hdr[j], &cmd_hdr[j],
+			       queue_entry_size);
+	}
+}
+
+static void hisi_sas_debugfs_snapshot_port_reg(struct hisi_hba *hisi_hba)
+{
+	const struct hisi_sas_debugfs_reg *port =
+		hisi_hba->hw->debugfs_reg_port;
+	int i, phy_cnt;
+	u32 offset;
+	u32 *databuf;
+
+	for (phy_cnt = 0; phy_cnt < hisi_hba->n_phy; phy_cnt++) {
+		databuf = (u32 *)hisi_hba->debugfs_p