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
  ...

1 files changed, 24 insertions, 2 deletions

diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index e34fc904f2e1..5bdb8b7d2a69 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 */