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

Pull SCSI updates from James Bottomley:
 "This consists of the usual driver updates (ufs, target, tcmu,
  smartpqi, lpfc, zfcp, qla2xxx, mpt3sas, pm80xx).

  The major core change is using a sbitmap instead of an atomic for
  queue tracking"

* tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (412 commits)
  scsi: target: tcm_fc: Fix a kernel-doc header
  scsi: target: Shorten ALUA error messages
  scsi: target: Fix two format specifiers
  scsi: target: Compare explicitly with SAM_STAT_GOOD
  scsi: sd: Introduce a new local variable in sd_check_events()
  scsi: dc395x: Open-code status_byte(u8) calls
  scsi: 53c700: Open-code status_byte(u8) calls
  scsi: smartpqi: Remove unused functions
  scsi: qla4xxx: Remove an unused function
  scsi: myrs: Remove unused functions
  scsi: myrb: Remove unused functions
  scsi: mpt3sas: Fix two kernel-doc headers
  scsi: fcoe: Suppress a compiler warning
  scsi: libfc: Fix a format specifier
  scsi: aacraid: Remove an unused function
  scsi: core: Introduce enum scsi_disposition
  scsi: core: Modify the scsi_send_eh_cmnd() return value for the SDEV_BLOCK case
  scsi: core: Rename scsi_softirq_done() into scsi_complete()
  scsi: core: Remove an incorrect comment
  scsi: core: Make the scsi_alloc_sgtables() documentation more accurate
  ...

13 files changed, 223 insertions, 104 deletions

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 2c473c9b8990..3bd3ee651143 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -306,12 +306,21 @@ struct blk_mq_ops {
 	 * reserved budget. Also we have to handle failure case
 	 * of .get_budget for avoiding I/O deadlock.
 	 */
-	bool (*get_budget)(struct request_queue *);
+	int (*get_budget)(struct request_queue *);
 
 	/**
 	 * @put_budget: Release the reserved budget.
 	 */
-	void (*put_budget)(struct request_queue *);
+	void (*put_budget)(struct request_queue *, int);
+
+	/*
+	 * @set_rq_budget_toekn: store rq's budget token
+	 */
+	void (*set_rq_budget_token)(struct request *, int);
+	/*
+	 * @get_rq_budget_toekn: retrieve rq's budget token
+	 */
+	int (*get_rq_budget_token)(struct request *);
 
 	/**
 	 * @timeout: Called on request timeout.
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 9c2373a1cb2d..d1e59dbef1dd 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1737,6 +1737,7 @@ static inline unsigned long virt_to_hvpfn(void *addr)
 #define NR_HV_HYP_PAGES_IN_PAGE	(PAGE_SIZE / HV_HYP_PAGE_SIZE)
 #define offset_in_hvpage(ptr)	((unsigned long)(ptr) & ~HV_HYP_PAGE_MASK)
 #define HVPFN_UP(x)	(((x) + HV_HYP_PAGE_SIZE-1) >> HV_HYP_PAGE_SHIFT)
+#define HVPFN_DOWN(x)	((x) >> HV_HYP_PAGE_SHIFT)
 #define page_to_hvpfn(page)	(page_to_pfn(page) * NR_HV_HYP_PAGES_IN_PAGE)
 
 #endif /* _HYPERV_H */
diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index 74cc6384715e..2713e689ad66 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -57,9 +57,22 @@ struct sbitmap {
 	unsigned int map_nr;
 
 	/**
+	 * @round_robin: Allocate bits in strict round-robin order.
+	 */
+	bool round_robin;
+
+	/**
 	 * @map: Allocated bitmap.
 	 */
 	struct sbitmap_word *map;
+
+	/*
+	 * @alloc_hint: Cache of last successfully allocated or freed bit.
+	 *
+	 * This is per-cpu, which allows multiple users to stick to different
+	 * cachelines until the map is exhausted.
+	 */
+	unsigned int __percpu *alloc_hint;
 };
 
 #define SBQ_WAIT_QUEUES 8
@@ -95,14 +108,6 @@ struct sbitmap_queue {
 	 */
 	struct sbitmap sb;
 
-	/*
-	 * @alloc_hint: Cache of last successfully allocated or freed bit.
-	 *
-	 * This is per-cpu, which allows multiple users to stick to different
-	 * cachelines until the map is exhausted.
-	 */
-	unsigned int __percpu *alloc_hint;
-
 	/**
 	 * @wake_batch: Number of bits which must be freed before we wake up any
 	 * waiters.
@@ -125,11 +130,6 @@ struct sbitmap_queue {
 	atomic_t ws_active;
 
 	/**
-	 * @round_robin: Allocate bits in strict round-robin order.
-	 */
-	bool round_robin;
-
-	/**
 	 * @min_shallow_depth: The minimum shallow depth which may be passed to
 	 * sbitmap_queue_get_shallow() or __sbitmap_queue_get_shallow().
 	 */
@@ -144,11 +144,16 @@ struct sbitmap_queue {
  *         given, a good default is chosen.
  * @flags: Allocation flags.
  * @node: Memory node to allocate on.
+ * @round_robin: If true, be stricter about allocation order; always allocate
+ *               starting from the last allocated bit. This is less efficient
+ *               than the default behavior (false).
+ * @alloc_hint: If true, apply percpu hint for where to start searching for
+ *              a free bit.
  *
  * Return: Zero on success or negative errno on failure.
  */
 int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
-		      gfp_t flags, int node);
+		      gfp_t flags, int node, bool round_robin, bool alloc_hint);
 
 /**
  * sbitmap_free() - Free memory used by a &struct sbitmap.
@@ -156,6 +161,7 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
  */
 static inline void sbitmap_free(struct sbitmap *sb)
 {
+	free_percpu(sb->alloc_hint);
 	kfree(sb->map);
 	sb->map = NULL;
 }
@@ -173,22 +179,17 @@ void sbitmap_resize(struct sbitmap *sb, unsigned int depth);
 /**
  * sbitmap_get() - Try to allocate a free bit from a &struct sbitmap.
  * @sb: Bitmap to allocate from.
- * @alloc_hint: Hint for where to start searching for a free bit.
- * @round_robin: If true, be stricter about allocation order; always allocate
- *               starting from the last allocated bit. This is less efficient
- *               than the default behavior (false).
  *
  * This operation provides acquire barrier semantics if it succeeds.
  *
  * Return: Non-negative allocated bit number if successful, -1 otherwise.
  */
-int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint, bool round_robin);
+int sbitmap_get(struct sbitmap *sb);
 
 /**
  * sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap,
  * limiting the depth used from each word.
  * @sb: Bitmap to allocate from.
- * @alloc_hint: Hint for where to start searching for a free bit.
  * @shallow_depth: The maximum number of bits to allocate from a single word.
  *
  * This rather specific operation allows for having multiple users with
@@ -200,8 +201,7 @@ int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint, bool round_robin);
  *
  * Return: Non-negative allocated bit number if successful, -1 otherwise.
  */
-int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint,
-			unsigned long shallow_depth);
+int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth);
 
 /**
  * sbitmap_any_bit_set() - Check for a set bit in a &struct sbitmap.
@@ -315,10 +315,16 @@ static inline void sbitmap_deferred_clear_bit(struct sbitmap *sb, unsigned int b
 	set_bit(SB_NR_TO_BIT(sb, bitnr), addr);
 }
 
-static inline void sbitmap_clear_bit_unlock(struct sbitmap *sb,
-					    unsigned int bitnr)
+/*
+ * Pair of sbitmap_get, and this one applies both cleared bit and
+ * allocation hint.
+ */
+static inline void sbitmap_put(struct sbitmap *sb, unsigned int bitnr)
 {
-	clear_bit_unlock(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr));
+	sbitmap_deferred_clear_bit(sb, bitnr);
+
+	if (likely(sb->alloc_hint && !sb->round_robin && bitnr < sb->depth))
+		*raw_cpu_ptr(sb->alloc_hint) = bitnr;
 }
 
 static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr)
@@ -326,6 +332,24 @@ static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr)
 	return test_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr));
 }
 
+static inline int sbitmap_calculate_shift(unsigned int depth)
+{
+	int	shift = ilog2(BITS_PER_LONG);
+
+	/*
+	 * If the bitmap is small, shrink the number of bits per word so
+	 * we spread over a few cachelines, at least. If less than 4
+	 * bits, just forget about it, it's not going to work optimally
+	 * anyway.
+	 */
+	if (depth >= 4) {
+		while ((4U << shift) > depth)
+			shift--;
+	}
+
+	return shift;
+}
+
 /**
  * sbitmap_show() - Dump &struct sbitmap information to a &struct seq_file.
  * @sb: Bitmap to show.
@@ -335,6 +359,16 @@ static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr)
  */
 void sbitmap_show(struct sbitmap *sb, struct seq_file *m);
 
+
+/**
+ * sbitmap_weight() - Return how many set and not cleared bits in a &struct
+ * sbitmap.
+ * @sb: Bitmap to check.
+ *
+ * Return: How many set and not cleared bits set
+ */
+unsigned int sbitmap_weight(const struct sbitmap *sb);
+
 /**
  * sbitmap_bitmap_show() - Write a hex dump of a &struct sbitmap to a &struct
  * seq_file.
@@ -369,7 +403,6 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
 static inline void sbitmap_queue_free(struct sbitmap_queue *sbq)
 {
 	kfree(sbq->ws);
-	free_percpu(sbq->alloc_hint);
 	sbitmap_free(&sbq->sb);
 }
 
diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h
index e75cca25338a..246ced401683 100644
--- a/include/scsi/scsi.h
+++ b/include/scsi/scsi.h
@@ -180,16 +180,17 @@ static inline int scsi_is_wlun(u64 lun)
 /*
  * Internal return values.
  */
-
-#define NEEDS_RETRY     0x2001
-#define SUCCESS         0x2002
-#define FAILED          0x2003
-#define QUEUED          0x2004
-#define SOFT_ERROR      0x2005
-#define ADD_TO_MLQUEUE  0x2006
-#define TIMEOUT_ERROR   0x2007
-#define SCSI_RETURN_NOT_HANDLED   0x2008
-#define FAST_IO_FAIL	0x2009
+enum scsi_disposition {
+	NEEDS_RETRY		= 0x2001,
+	SUCCESS			= 0x2002,
+	FAILED			= 0x2003,
+	QUEUED			= 0x2004,
+	SOFT_ERROR		= 0x2005,
+	ADD_TO_MLQUEUE		= 0x2006,
+	TIMEOUT_ERROR		= 0x2007,
+	SCSI_RETURN_NOT_HANDLED	= 0x2008,
+	FAST_IO_FAIL		= 0x2009,
+};
 
 /*
  * Midlevel queue return values.
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index 0fd17a5344bd..fed024f4c02a 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -10,6 +10,7 @@
 #include <linux/timer.h>
 #include <linux/scatterlist.h>
 #include <scsi/scsi_device.h>
+#include <scsi/scsi_host.h>
 #include <scsi/scsi_request.h>
 
 struct Scsi_Host;
@@ -74,6 +75,8 @@ struct scsi_cmnd {
 
 	int eh_eflags;		/* Used by error handlr */
 
+	int budget_token;
+
 	/*
 	 * This is set to jiffies as it was when the command was first
 	 * allocated.  It is used to time how long the command has
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 1a5c9a3df6d6..ac6ab16abee7 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -8,6 +8,7 @@
 #include <linux/blkdev.h>
 #include <scsi/scsi.h>
 #include <linux/atomic.h>
+#include <linux/sbitmap.h>
 
 struct device;
 struct request_queue;
@@ -106,7 +107,7 @@ struct scsi_device {
 	struct list_head    siblings;   /* list of all devices on this host */
 	struct list_head    same_target_siblings; /* just the devices sharing same target id */
 
-	atomic_t device_busy;		/* commands actually active on LLDD */
+	struct sbitmap budget_map;
 	atomic_t device_blocked;	/* Device returned QUEUE_FULL. */
 
 	atomic_t restarts;
@@ -145,7 +146,7 @@ struct scsi_device {
 	struct scsi_vpd __rcu *vpd_pg80;
 	struct scsi_vpd __rcu *vpd_pg89;
 	unsigned char current_tag;	/* current tag */
-	struct scsi_target      *sdev_target;   /* used only for single_lun */
+	struct scsi_target      *sdev_target;
 
 	blist_flags_t		sdev_bflags; /* black/white flags as also found in
 				 * scsi_devinfo.[hc]. For now used only to
@@ -590,6 +591,11 @@ static inline int scsi_device_supports_vpd(struct scsi_device *sdev)
 	return 0;
 }
 
+static inline int scsi_device_busy(struct scsi_device *sdev)
+{
+	return sbitmap_weight(&sdev->budget_map);
+}
+
 #define MODULE_ALIAS_SCSI_DEVICE(type) \
 	MODULE_ALIAS("scsi:t-" __stringify(type) "*")
 #define SCSI_DEVICE_MODALIAS_FMT "scsi:t-0x%02x"
diff --git a/include/scsi/scsi_dh.h b/include/scsi/scsi_dh.h
index 2852e470a8ed..4df943c1b90b 100644
--- a/include/scsi/scsi_dh.h
+++ b/include/scsi/scsi_dh.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * Header file for SCSI device handler infrastruture.
+ * Header file for SCSI device handler infrastructure.
  *
  * Modified version of patches posted by Mike Christie <michaelc@cs.wisc.edu>
  *
@@ -52,7 +52,8 @@ struct scsi_device_handler {
 	/* Filled by the hardware handler */
 	struct module *module;
 	const char *name;
-	int (*check_sense)(struct scsi_device *, struct scsi_sense_hdr *);
+	enum scsi_disposition (*check_sense)(struct scsi_device *,
+					     struct scsi_sense_hdr *);
 	int (*attach)(struct scsi_device *);
 	void (*detach)(struct scsi_device *);
 	int (*activate)(struct scsi_device *, activate_complete, void *);
diff --git a/include/scsi/scsi_eh.h b/include/scsi/scsi_eh.h
index 6bd5ed695a5e..468094254b3c 100644
--- a/include/scsi/scsi_eh.h
+++ b/include/scsi/scsi_eh.h
@@ -17,7 +17,7 @@ extern void scsi_report_device_reset(struct Scsi_Host *, int, int);
 extern int scsi_block_when_processing_errors(struct scsi_device *);
 extern bool scsi_command_normalize_sense(const struct scsi_cmnd *cmd,
 					 struct scsi_sense_hdr *sshdr);
-extern int scsi_check_sense(struct scsi_cmnd *);
+extern enum scsi_disposition scsi_check_sense(struct scsi_cmnd *);
 
 static inline bool scsi_sense_is_deferred(const struct scsi_sense_hdr *sshdr)
 {
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 8343c6f9fec1..d0bf88d77f02 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -19,7 +19,6 @@ struct scsi_device;
 struct scsi_host_cmd_pool;
 struct scsi_target;
 struct Scsi_Host;
-struct scsi_host_cmd_pool;
 struct scsi_transport_template;
 
 
@@ -30,40 +29,15 @@ struct scsi_transport_template;
 #define MODE_TARGET 0x02
 
 struct scsi_host_template {
-	struct module *module;
-	const char *name;
-
 	/*
-	 * The info function will return whatever useful information the
-	 * developer sees fit.  If not provided, then the name field will
-	 * be used instead.
-	 *
-	 * Status: OPTIONAL
+	 * Put fields referenced in IO submission path together in
+	 * same cacheline
 	 */
-	const char *(* info)(struct Scsi_Host *);
 
 	/*
-	 * Ioctl interface
-	 *
-	 * Status: OPTIONAL
-	 */
-	int (*ioctl)(struct scsi_device *dev, unsigned int cmd,
-		     void __user *arg);
-
-
-#ifdef CONFIG_COMPAT
-	/* 
-	 * Compat handler. Handle 32bit ABI.
-	 * When unknown ioctl is passed return -ENOIOCTLCMD.
-	 *
-	 * Status: OPTIONAL
+	 * Additional per-command data allocated for the driver.
 	 */
-	int (*compat_ioctl)(struct scsi_device *dev, unsigned int cmd,
-			    void __user *arg);
-#endif
-
-	int (*init_cmd_priv)(struct Scsi_Host *shost, struct scsi_cmnd *cmd);
-	int (*exit_cmd_priv)(struct Scsi_Host *shost, struct scsi_cmnd *cmd);
+	unsigned int cmd_size;
 
 	/*
 	 * The queuecommand function is used to queue up a scsi
@@ -111,6 +85,41 @@ struct scsi_host_template {
 	 */
 	void (*commit_rqs)(struct Scsi_Host *, u16);
 
+	struct module *module;
+	const char *name;
+
+	/*
+	 * The info function will return whatever useful information the
+	 * developer sees fit.  If not provided, then the name field will
+	 * be used instead.
+	 *
+	 * Status: OPTIONAL
+	 */
+	const char *(*info)(struct Scsi_Host *);
+
+	/*
+	 * Ioctl interface
+	 *
+	 * Status: OPTIONAL
+	 */
+	int (*ioctl)(struct scsi_device *dev, unsigned int cmd,
+		     void __user *arg);
+
+
+#ifdef CONFIG_COMPAT
+	/*
+	 * Compat handler. Handle 32bit ABI.
+	 * When unknown ioctl is passed return -ENOIOCTLCMD.
+	 *
+	 * Status: OPTIONAL
+	 */
+	int (*compat_ioctl)(struct scsi_device *dev, unsigned int cmd,
+			    void __user *arg);
+#endif
+
+	int (*init_cmd_priv)(struct Scsi_Host *shost, struct scsi_cmnd *cmd);
+	int (*exit_cmd_priv)(struct Scsi_Host *shost, struct scsi_cmnd *cmd);
+
 	/*
 	 * This is an error handling strategy routine.  You don't need to
 	 * define one of these if you don't want to - there is a default
@@ -271,6 +280,16 @@ struct scsi_host_template {
 	int (* map_queues)(struct Scsi_Host *shost);
 
 	/*
+	 * SCSI interface of blk_poll - poll for IO completions.
+	 * Only applicable if SCSI LLD exposes multiple h/w queues.
+	 *
+	 * Return value: Number of completed entries found.
+	 *
+	 * Status: OPTIONAL
+	 */
+	int (* mq_poll)(struct Scsi_Host *shost, unsigned int queue_num);
+
+	/*
 	 * Check if scatterlists need to be padded for DMA draining.
 	 *
 	 * Status: OPTIONAL
@@ -479,10 +498,6 @@ struct scsi_host_template {
 	 */
 	u64 vendor_id;
 
-	/*
-	 * Additional per-command data allocated for the driver.
-	 */
-	unsigned int cmd_size;
 	struct scsi_host_cmd_pool *cmd_pool;
 
 	/* Delay for runtime autosuspend */
@@ -611,6 +626,7 @@ struct Scsi_Host {
 	 * the total queue depth is can_queue.
 	 */
 	unsigned nr_hw_queues;
+	unsigned nr_maps;
 	unsigned active_mode:2;
 
 	/*
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index ce2fba49c95d..1f78b09bba55 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -34,6 +34,8 @@ struct target_backend_ops {
 	int (*configure_device)(struct se_device *);
 	void (*destroy_device)(struct se_device *);
 	void (*free_device)(struct se_device *device);
+	struct se_dev_plug *(*plug_device)(struct se_device *se_dev);
+	void (*unplug_device)(struct se_dev_plug *se_plug);
 
 	ssize_t (*set_configfs_dev_params)(struct se_device *,
 					   const char *, ssize_t);
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 54dcc0eb25fa..d1f7d2a45354 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -127,25 +127,25 @@ enum transport_state_table {
 
 /* Used for struct se_cmd->se_cmd_flags */
 enum se_cmd_flags_table {
-	SCF_SUPPORTED_SAM_OPCODE	= 0x00000001,
-	SCF_TRANSPORT_TASK_SENSE	= 0x00000002,
-	SCF_EMULATED_TASK_SENSE		= 0x00000004,
-	SCF_SCSI_DATA_CDB		= 0x00000008,
-	SCF_SCSI_TMR_CDB		= 0x00000010,
-	SCF_FUA				= 0x00000080,
-	SCF_SE_LUN_CMD			= 0x00000100,
-	SCF_BIDI			= 0x00000400,
-	SCF_SENT_CHECK_CONDITION	= 0x00000800,
-	SCF_OVERFLOW_BIT		= 0x00001000,
-	SCF_UNDERFLOW_BIT		= 0x00002000,
-	SCF_ALUA_NON_OPTIMIZED		= 0x00008000,
-	SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC = 0x00020000,
-	SCF_COMPARE_AND_WRITE		= 0x00080000,
-	SCF_PASSTHROUGH_PROT_SG_TO_MEM_NOALLOC = 0x00200000,
-	SCF_ACK_KREF			= 0x00400000,
-	SCF_USE_CPUID			= 0x00800000,
-	SCF_TASK_ATTR_SET		= 0x01000000,
-	SCF_TREAT_READ_AS_NORMAL	= 0x02000000,
+	SCF_SUPPORTED_SAM_OPCODE		= (1 << 0),
+	SCF_TRANSPORT_TASK_SENSE		= (1 << 1),
+	SCF_EMULATED_TASK_SENSE			= (1 << 2),
+	SCF_SCSI_DATA_CDB			= (1 << 3),
+	SCF_SCSI_TMR_CDB			= (1 << 4),
+	SCF_FUA					= (1 << 5),
+	SCF_SE_LUN_CMD				= (1 << 6),
+	SCF_BIDI				= (1 << 7),
+	SCF_SENT_CHECK_CONDITION		= (1 << 8),
+	SCF_OVERFLOW_BIT			= (1 << 9),
+	SCF_UNDERFLOW_BIT			= (1 << 10),
+	SCF_ALUA_NON_OPTIMIZED			= (1 << 11),
+	SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC	= (1 << 12),
+	SCF_COMPARE_AND_WRITE			= (1 << 13),
+	SCF_PASSTHROUGH_PROT_SG_TO_MEM_NOALLOC	= (1 << 14),
+	SCF_ACK_KREF				= (1 << 15),
+	SCF_USE_CPUID				= (1 << 16),
+	SCF_TASK_ATTR_SET			= (1 << 17),
+	SCF_TREAT_READ_AS_NORMAL		= (1 << 18),
 };
 
 /*
@@ -488,7 +488,7 @@ struct se_cmd {
 	/* Only used for internal passthrough and legacy TCM fabric modules */
 	struct se_session	*se_sess;
 	struct se_tmr_req	*se_tmr_req;
-	struct list_head	se_cmd_list;
+	struct llist_node	se_cmd_list;
 	struct completion	*free_compl;
 	struct completion	*abrt_compl;
 	const struct target_core_fabric_ops *se_tfo;
@@ -765,9 +765,19 @@ struct se_dev_stat_grps {
 	struct config_group scsi_lu_group;
 };
 
+struct se_cmd_queue {
+	struct llist_head	cmd_list;
+	struct work_struct	work;
+};
+
+struct se_dev_plug {
+	struct se_device	*se_dev;
+};
+
 struct se_device_queue {
 	struct list_head	state_list;
 	spinlock_t		lock;
+	struct se_cmd_queue	sq;
 };
 
 struct se_device {
@@ -934,11 +944,20 @@ static inline struct se_portal_group *param_to_tpg(struct config_item *item)
 			tpg_param_group);
 }
 
+enum {
+	/* Use se_cmd's cpuid for completion */
+	SE_COMPL_AFFINITY_CPUID		= -1,
+	/* Complete on current CPU */
+	SE_COMPL_AFFINITY_CURR_CPU	= -2,
+};
+
 struct se_wwn {
 	struct target_fabric_configfs *wwn_tf;
 	void			*priv;
 	struct config_group	wwn_group;
 	struct config_group	fabric_stat_group;
+	struct config_group	param_group;
+	int			cmd_compl_affinity;
 };
 
 static inline void atomic_inc_mb(atomic_t *v)
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index d60a3eb7517a..3c5ade7a04a6 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -148,18 +148,25 @@ void	transport_deregister_session_configfs(struct se_session *);
 void	transport_deregister_session(struct se_session *);
 
 
-void	transport_init_se_cmd(struct se_cmd *,
+void	__target_init_cmd(struct se_cmd *,
 		const struct target_core_fabric_ops *,
 		struct se_session *, u32, int, int, unsigned char *, u64);
+int	target_init_cmd(struct se_cmd *se_cmd, struct se_session *se_sess,
+		unsigned char *sense, u64 unpacked_lun, u32 data_length,
+		int task_attr, int data_dir, int flags);
+int	target_submit_prep(struct se_cmd *se_cmd, unsigned char *cdb,
+		struct scatterlist *sgl, u32 sgl_count,
+		struct scatterlist *sgl_bidi, u32 sgl_bidi_count,
+		struct scatterlist *sgl_prot, u32 sgl_prot_count, gfp_t gfp);
+void	target_submit(struct se_cmd *se_cmd);
 sense_reason_t transport_lookup_cmd_lun(struct se_cmd *);
-sense_reason_t target_cmd_init_cdb(struct se_cmd *, unsigned char *);
+sense_reason_t target_cmd_init_cdb(struct se_cmd *se_cmd, unsigned char *cdb,
+				   gfp_t gfp);
 sense_reason_t target_cmd_parse_cdb(struct se_cmd *);
-int	target_submit_cmd_map_sgls(struct se_cmd *, struct se_session *,
-		unsigned char *, unsigned char *, u64, u32, int, int, int,
-		struct scatterlist *, u32, struct scatterlist *, u32,
-		struct scatterlist *, u32);
-int	target_submit_cmd(struct se_cmd *, struct se_session *, unsigned char *,
+void	target_submit_cmd(struct se_cmd *, struct se_session *, unsigned char *,
 		unsigned char *, u64, u32, int, int, int);
+void	target_queue_submission(struct se_cmd *se_cmd);
+
 int	target_submit_tmr(struct se_cmd *se_cmd, struct se_session *se_sess,
 		unsigned char *sense, u64 unpacked_lun,
 		void *fabric_tmr_ptr, unsigned char tm_type,
diff --git a/include/trace/events/ufs.h b/include/trace/events/ufs.h
index e151477d645c..1cb6f1afba0e 100644
--- a/include/trace/events/ufs.h
+++ b/include/trace/events/ufs.h
@@ -349,6 +349,27 @@ TRACE_EVENT(ufshcd_upiu,
 	)
 );
 
+TRACE_EVENT(ufshcd_exception_event,
+
+	TP_PROTO(const char *dev_name, u16 status),
+
+	TP_ARGS(dev_name, status),
+
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name)
+		__field(u16, status)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name, dev_name);
+		__entry->status = status;
+	),
+
+	TP_printk("%s: status 0x%x",
+		__get_str(dev_name), __entry->status
+	)
+);
+
 #endif /* if !defined(_TRACE_UFS_H) || defined(TRACE_HEADER_MULTI_READ) */
 
 /* This part must be outside protection */