Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending

Pull SCSI target updates from Nicholas Bellinger:
 "Lots of activity again this round for I/O performance optimizations
  (per-cpu IDA pre-allocation for vhost + iscsi/target), and the
  addition of new fabric independent features to target-core
  (COMPARE_AND_WRITE + EXTENDED_COPY).

  The main highlights include:

   - Support for iscsi-target login multiplexing across individual
     network portals
   - Generic Per-cpu IDA logic (kent + akpm + clameter)
   - Conversion of vhost to use per-cpu IDA pre-allocation for
     descriptors, SGLs and userspace page pointer list
   - Conversion of iscsi-target + iser-target to use per-cpu IDA
     pre-allocation for descriptors
   - Add support for generic COMPARE_AND_WRITE (AtomicTestandSet)
     emulation for virtual backend drivers
   - Add support for generic EXTENDED_COPY (CopyOffload) emulation for
     virtual backend drivers.
   - Add support for fast memory registration mode to iser-target (Vu)

  The patches to add COMPARE_AND_WRITE and EXTENDED_COPY support are of
  particular significance, which make us the first and only open source
  target to support the full set of VAAI primitives.

  Currently Linux clients are lacking upstream support to actually
  utilize these primitives.  However, with server side support now in
  place for folks like MKP + ZAB working on the client, this logic once
  reserved for the highest end of storage arrays, can now be run in VMs
  on their laptops"

* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending: (50 commits)
  target/iscsi: Bump versions to v4.1.0
  target: Update copyright ownership/year information to 2013
  iscsi-target: Bump default TCP listen backlog to 256
  target: Fix >= v3.9+ regression in PR APTPL + ALUA metadata write-out
  iscsi-target; Bump default CmdSN Depth to 64
  iscsi-target: Remove unnecessary wait_for_completion in iscsi_get_thread_set
  iscsi-target: Add thread_set->ts_activate_sem + use common deallocate
  iscsi-target: Fix race with thread_pre_handler flush_signals + ISCSI_THREAD_SET_DIE
  target: remove unused including <linux/version.h>
  iser-target: introduce fast memory registration mode (FRWR)
  iser-target: generalize rdma memory registration and cleanup
  iser-target: move rdma wr processing to a shared function
  target: Enable global EXTENDED_COPY setup/release
  target: Add Third Party Copy (3PC) bit in INQUIRY response
  target: Enable EXTENDED_COPY setup in spc_parse_cdb
  target: Add support for EXTENDED_COPY copy offload emulation
  target: Avoid non-existent tg_pt_gp_mem in target_alua_state_check
  target: Add global device list for EXTENDED_COPY
  target: Make helpers non static for EXTENDED_COPY command setup
  target: Make spc_parse_naa_6h_vendor_specific non static
  ...

6 files changed, 128 insertions, 4 deletions

diff --git a/include/linux/percpu_ida.h b/include/linux/percpu_ida.h
new file mode 100644
index 00000000000..0b23edbee30
--- /dev/null
+++ b/include/linux/percpu_ida.h
@@ -0,0 +1,60 @@
+#ifndef __PERCPU_IDA_H__
+#define __PERCPU_IDA_H__
+
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/init.h>
+#include <linux/spinlock_types.h>
+#include <linux/wait.h>
+#include <linux/cpumask.h>
+
+struct percpu_ida_cpu;
+
+struct percpu_ida {
+	/*
+	 * number of tags available to be allocated, as passed to
+	 * percpu_ida_init()
+	 */
+	unsigned			nr_tags;
+
+	struct percpu_ida_cpu __percpu	*tag_cpu;
+
+	/*
+	 * Bitmap of cpus that (may) have tags on their percpu freelists:
+	 * steal_tags() uses this to decide when to steal tags, and which cpus
+	 * to try stealing from.
+	 *
+	 * It's ok for a freelist to be empty when its bit is set - steal_tags()
+	 * will just keep looking - but the bitmap _must_ be set whenever a
+	 * percpu freelist does have tags.
+	 */
+	cpumask_t			cpus_have_tags;
+
+	struct {
+		spinlock_t		lock;
+		/*
+		 * When we go to steal tags from another cpu (see steal_tags()),
+		 * we want to pick a cpu at random. Cycling through them every
+		 * time we steal is a bit easier and more or less equivalent:
+		 */
+		unsigned		cpu_last_stolen;
+
+		/* For sleeping on allocation failure */
+		wait_queue_head_t	wait;
+
+		/*
+		 * Global freelist - it's a stack where nr_free points to the
+		 * top
+		 */
+		unsigned		nr_free;
+		unsigned		*freelist;
+	} ____cacheline_aligned_in_smp;
+};
+
+int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp);
+void percpu_ida_free(struct percpu_ida *pool, unsigned tag);
+
+void percpu_ida_destroy(struct percpu_ida *pool);
+int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags);
+
+#endif /* __PERCPU_IDA_H__ */
diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h
index d477bfb73fb..66d42edfb3f 100644
--- a/include/scsi/scsi.h
+++ b/include/scsi/scsi.h
@@ -144,6 +144,7 @@ enum scsi_timeouts {
 #define ACCESS_CONTROL_IN     0x86
 #define ACCESS_CONTROL_OUT    0x87
 #define READ_16               0x88
+#define COMPARE_AND_WRITE     0x89
 #define WRITE_16              0x8a
 #define READ_ATTRIBUTE        0x8c
 #define WRITE_ATTRIBUTE	      0x8d
diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h
index e5d09d242ba..a12589c4ee9 100644
--- a/include/target/iscsi/iscsi_transport.h
+++ b/include/target/iscsi/iscsi_transport.h
@@ -6,13 +6,13 @@ struct iscsit_transport {
 #define ISCSIT_TRANSPORT_NAME	16
 	char name[ISCSIT_TRANSPORT_NAME];
 	int transport_type;
+	int priv_size;
 	struct module *owner;
 	struct list_head t_node;
 	int (*iscsit_setup_np)(struct iscsi_np *, struct __kernel_sockaddr_storage *);
 	int (*iscsit_accept_np)(struct iscsi_np *, struct iscsi_conn *);
 	void (*iscsit_free_np)(struct iscsi_np *);
 	void (*iscsit_free_conn)(struct iscsi_conn *);
-	struct iscsi_cmd *(*iscsit_alloc_cmd)(struct iscsi_conn *, gfp_t);
 	int (*iscsit_get_login_rx)(struct iscsi_conn *, struct iscsi_login *);
 	int (*iscsit_put_login_tx)(struct iscsi_conn *, struct iscsi_login *, u32);
 	int (*iscsit_immediate_queue)(struct iscsi_conn *, struct iscsi_cmd *, int);
@@ -22,6 +22,11 @@ struct iscsit_transport {
 	int (*iscsit_queue_status)(struct iscsi_conn *, struct iscsi_cmd *);
 };
 
+static inline void *iscsit_priv_cmd(struct iscsi_cmd *cmd)
+{
+	return (void *)(cmd + 1);
+}
+
 /*
  * From iscsi_target_transport.c
  */
@@ -92,3 +97,4 @@ extern int iscsit_tmr_post_handler(struct iscsi_cmd *, struct iscsi_conn *);
 extern struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *, gfp_t);
 extern int iscsit_sequence_cmd(struct iscsi_conn *, struct iscsi_cmd *,
 			       unsigned char *, __be32);
+extern void iscsit_release_cmd(struct iscsi_cmd *);
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index ffa2696d64d..5ebe21cd5d1 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -39,7 +39,8 @@ struct se_subsystem_api {
 };
 
 struct sbc_ops {
-	sense_reason_t (*execute_rw)(struct se_cmd *cmd);
+	sense_reason_t (*execute_rw)(struct se_cmd *cmd, struct scatterlist *,
+				     u32, enum dma_data_direction);
 	sense_reason_t (*execute_sync_cache)(struct se_cmd *cmd);
 	sense_reason_t (*execute_write_same)(struct se_cmd *cmd);
 	sense_reason_t (*execute_write_same_unmap)(struct se_cmd *cmd);
@@ -73,6 +74,10 @@ int	transport_set_vpd_ident(struct t10_vpd *, unsigned char *);
 /* core helpers also used by command snooping in pscsi */
 void	*transport_kmap_data_sg(struct se_cmd *);
 void	transport_kunmap_data_sg(struct se_cmd *);
+/* core helpers also used by xcopy during internal command setup */
+int	target_alloc_sgl(struct scatterlist **, unsigned int *, u32, bool);
+sense_reason_t	transport_generic_map_mem_to_cmd(struct se_cmd *,
+		struct scatterlist *, u32, struct scatterlist *, u32);
 
 void	array_free(void *array, int n);
 
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index e34fc904f2e..5bdb8b7d2a6 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -5,11 +5,12 @@
 #include <linux/configfs.h>
 #include <linux/dma-mapping.h>
 #include <linux/blkdev.h>
+#include <linux/percpu_ida.h>
 #include <scsi/scsi_cmnd.h>
 #include <net/sock.h>
 #include <net/tcp.h>
 
-#define TARGET_CORE_MOD_VERSION		"v4.1.0-rc2-ml"
+#define TARGET_CORE_MOD_VERSION		"v4.1.0"
 #define TARGET_CORE_VERSION		TARGET_CORE_MOD_VERSION
 
 /* Maximum Number of LUNs per Target Portal Group */
@@ -96,6 +97,10 @@
  * block/blk-lib.c:blkdev_issue_discard()
  */
 #define DA_EMULATE_TPWS				0
+/* Emulation for CompareAndWrite (AtomicTestandSet) by default */
+#define DA_EMULATE_CAW				1
+/* Emulation for 3rd Party Copy (ExtendedCopy) by default */
+#define DA_EMULATE_3PC				1
 /* No Emulation for PSCSI by default */
 #define DA_EMULATE_ALUA				0
 /* Enforce SCSI Initiator Port TransportID with 'ISID' for PR */
@@ -158,6 +163,9 @@ enum se_cmd_flags_table {
 	SCF_ALUA_NON_OPTIMIZED		= 0x00008000,
 	SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC = 0x00020000,
 	SCF_ACK_KREF			= 0x00040000,
+	SCF_COMPARE_AND_WRITE		= 0x00080000,
+	SCF_COMPARE_AND_WRITE_POST	= 0x00100000,
+	SCF_CMD_XCOPY_PASSTHROUGH	= 0x00200000,
 };
 
 /* struct se_dev_entry->lun_flags and struct se_lun->lun_access */
@@ -196,6 +204,7 @@ enum tcm_sense_reason_table {
 	TCM_ADDRESS_OUT_OF_RANGE		= R(0x11),
 	TCM_OUT_OF_RESOURCES			= R(0x12),
 	TCM_PARAMETER_LIST_LENGTH_ERROR		= R(0x13),
+	TCM_MISCOMPARE_VERIFY			= R(0x14),
 #undef R
 };
 
@@ -415,6 +424,8 @@ struct se_cmd {
 	enum dma_data_direction	data_direction;
 	/* For SAM Task Attribute */
 	int			sam_task_attr;
+	/* Used for se_sess->sess_tag_pool */
+	unsigned int		map_tag;
 	/* Transport protocol dependent state, see transport_state_table */
 	enum transport_state_table t_state;
 	unsigned		cmd_wait_set:1;
@@ -444,11 +455,14 @@ struct se_cmd {
 	struct kref		cmd_kref;
 	struct target_core_fabric_ops *se_tfo;
 	sense_reason_t		(*execute_cmd)(struct se_cmd *);
-	void (*transport_complete_callback)(struct se_cmd *);
+	sense_reason_t		(*execute_rw)(struct se_cmd *, struct scatterlist *,
+					      u32, enum dma_data_direction);
+	sense_reason_t (*transport_complete_callback)(struct se_cmd *);
 
 	unsigned char		*t_task_cdb;
 	unsigned char		__t_task_cdb[TCM_MAX_COMMAND_SIZE];
 	unsigned long long	t_task_lba;
+	unsigned int		t_task_nolb;
 	unsigned int		transport_state;
 #define CMD_T_ABORTED		(1 << 0)
 #define CMD_T_ACTIVE		(1 << 1)
@@ -469,7 +483,9 @@ struct se_cmd {
 	struct work_struct	work;
 
 	struct scatterlist	*t_data_sg;
+	struct scatterlist	*t_data_sg_orig;
 	unsigned int		t_data_nents;
+	unsigned int		t_data_nents_orig;
 	void			*t_data_vmap;
 	struct scatterlist	*t_bidi_data_sg;
 	unsigned int		t_bidi_data_nents;
@@ -536,6 +552,8 @@ struct se_session {
 	struct list_head	sess_wait_list;
 	spinlock_t		sess_cmd_lock;
 	struct kref		sess_kref;
+	void			*sess_cmd_map;
+	struct percpu_ida	sess_tag_pool;
 };
 
 struct se_device;
@@ -589,6 +607,8 @@ struct se_dev_attrib {
 	int		emulate_tas;
 	int		emulate_tpu;
 	int		emulate_tpws;
+	int		emulate_caw;
+	int		emulate_3pc;
 	int		enforce_pr_isids;
 	int		is_nonrot;
 	int		emulate_rest_reord;
@@ -656,6 +676,7 @@ struct se_device {
 	spinlock_t		se_port_lock;
 	spinlock_t		se_tmr_lock;
 	spinlock_t		qf_cmd_lock;
+	struct semaphore	caw_sem;
 	/* Used for legacy SPC-2 reservationsa */
 	struct se_node_acl	*dev_reserved_node_acl;
 	/* Used for ALUA Logical Unit Group membership */
@@ -669,6 +690,7 @@ struct se_device {
 	struct list_head	delayed_cmd_list;
 	struct list_head	state_list;
 	struct list_head	qf_cmd_list;
+	struct list_head	g_dev_node;
 	/* Pointer to associated SE HBA */
 	struct se_hba		*se_hba;
 	/* T10 Inquiry and VPD WWN Information */
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index 7a16178424f..882b650e32b 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -84,6 +84,9 @@ struct target_core_fabric_ops {
 };
 
 struct se_session *transport_init_session(void);
+int transport_alloc_session_tags(struct se_session *, unsigned int,
+		unsigned int);
+struct se_session *transport_init_session_tags(unsigned int, unsigned int);
 void	__transport_register_session(struct se_portal_group *,
 		struct se_node_acl *, struct se_session *, void *);
 void	transport_register_session(struct se_portal_group *,
@@ -131,6 +134,7 @@ int	core_tmr_alloc_req(struct se_cmd *, void *, u8, gfp_t);
 void	core_tmr_release_req(struct se_tmr_req *);
 int	transport_generic_handle_tmr(struct se_cmd *);
 void	transport_generic_request_failure(struct se_cmd *, sense_reason_t);
+void	__target_execute_cmd(struct se_cmd *);
 int	transport_lookup_tmr_lun(struct se_cmd *, u32);
 
 struct se_node_acl *core_tpg_check_initiator_node_acl(struct se_portal_group *,
@@ -175,4 +179,30 @@ u32	iscsi_get_pr_transport_id_len(struct se_portal_group *, struct se_node_acl *
 char	*iscsi_parse_pr_out_transport_id(struct se_portal_group *, const char *,
 		u32 *, char **);
 
+/*
+ * The LIO target core uses DMA_TO_DEVICE to mean that data is going
+ * to the target (eg handling a WRITE) and DMA_FROM_DEVICE to mean
+ * that data is coming from the target (eg handling a READ).  However,
+ * this is just the opposite of what we have to tell the DMA mapping
+ * layer -- eg when handling a READ, the HBA will have to DMA the data
+ * out of memory so it can send it to the initiator, which means we
+ * need to use DMA_TO_DEVICE when we map the data.
+ */
+static inline enum dma_data_direction
+target_reverse_dma_direction(struct se_cmd *se_cmd)
+{
+	if (se_cmd->se_cmd_flags & SCF_BIDI)
+		return DMA_BIDIRECTIONAL;
+
+	switch (se_cmd->data_direction) {
+	case DMA_TO_DEVICE:
+		return DMA_FROM_DEVICE;
+	case DMA_FROM_DEVICE:
+		return DMA_TO_DEVICE;
+	case DMA_NONE:
+	default:
+		return DMA_NONE;
+	}
+}
+
 #endif /* TARGET_CORE_FABRICH */