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, 143 insertions, 27 deletions

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index d8e49d79f8cc..84747cc1aac0 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -3,7 +3,7 @@
  *
  * This file contains the Generic Target Engine Core.
  *
- * (c) Copyright 2002-2012 RisingTide Systems LLC.
+ * (c) Copyright 2002-2013 Datera, Inc.
  *
  * Nicholas A. Bellinger <nab@kernel.org>
  *
@@ -67,7 +67,6 @@ struct kmem_cache *t10_alua_tg_pt_gp_mem_cache;
 static void transport_complete_task_attr(struct se_cmd *cmd);
 static void transport_handle_queue_full(struct se_cmd *cmd,
 		struct se_device *dev);
-static int transport_generic_get_mem(struct se_cmd *cmd);
 static int transport_put_cmd(struct se_cmd *cmd);
 static void target_complete_ok_work(struct work_struct *work);
 
@@ -232,6 +231,50 @@ struct se_session *transport_init_session(void)
 }
 EXPORT_SYMBOL(transport_init_session);
 
+int transport_alloc_session_tags(struct se_session *se_sess,
+			         unsigned int tag_num, unsigned int tag_size)
+{
+	int rc;
+
+	se_sess->sess_cmd_map = kzalloc(tag_num * tag_size, GFP_KERNEL);
+	if (!se_sess->sess_cmd_map) {
+		pr_err("Unable to allocate se_sess->sess_cmd_map\n");
+		return -ENOMEM;
+	}
+
+	rc = percpu_ida_init(&se_sess->sess_tag_pool, tag_num);
+	if (rc < 0) {
+		pr_err("Unable to init se_sess->sess_tag_pool,"
+			" tag_num: %u\n", tag_num);
+		kfree(se_sess->sess_cmd_map);
+		se_sess->sess_cmd_map = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(transport_alloc_session_tags);
+
+struct se_session *transport_init_session_tags(unsigned int tag_num,
+					       unsigned int tag_size)
+{
+	struct se_session *se_sess;
+	int rc;
+
+	se_sess = transport_init_session();
+	if (IS_ERR(se_sess))
+		return se_sess;
+
+	rc = transport_alloc_session_tags(se_sess, tag_num, tag_size);
+	if (rc < 0) {
+		transport_free_session(se_sess);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return se_sess;
+}
+EXPORT_SYMBOL(transport_init_session_tags);
+
 /*
  * Called with spin_lock_irqsave(&struct se_portal_group->session_lock called.
  */
@@ -367,6 +410,10 @@ EXPORT_SYMBOL(transport_deregister_session_configfs);
 
 void transport_free_session(struct se_session *se_sess)
 {
+	if (se_sess->sess_cmd_map) {
+		percpu_ida_destroy(&se_sess->sess_tag_pool);
+		kfree(se_sess->sess_cmd_map);
+	}
 	kmem_cache_free(se_sess_cache, se_sess);
 }
 EXPORT_SYMBOL(transport_free_session);
@@ -1206,7 +1253,7 @@ int transport_handle_cdb_direct(
 }
 EXPORT_SYMBOL(transport_handle_cdb_direct);
 
-static sense_reason_t
+sense_reason_t
 transport_generic_map_mem_to_cmd(struct se_cmd *cmd, struct scatterlist *sgl,
 		u32 sgl_count, struct scatterlist *sgl_bidi, u32 sgl_bidi_count)
 {
@@ -1512,6 +1559,13 @@ void transport_generic_request_failure(struct se_cmd *cmd,
 	 * For SAM Task Attribute emulation for failed struct se_cmd
 	 */
 	transport_complete_task_attr(cmd);
+	/*
+	 * Handle special case for COMPARE_AND_WRITE failure, where the
+	 * callback is expected to drop the per device ->caw_mutex.
+	 */
+	if ((cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) &&
+	     cmd->transport_complete_callback)
+		cmd->transport_complete_callback(cmd);
 
 	switch (sense_reason) {
 	case TCM_NON_EXISTENT_LUN:
@@ -1579,7 +1633,7 @@ queue_full:
 }
 EXPORT_SYMBOL(transport_generic_request_failure);
 
-static void __target_execute_cmd(struct se_cmd *cmd)
+void __target_execute_cmd(struct se_cmd *cmd)
 {
 	sense_reason_t ret;
 
@@ -1784,7 +1838,7 @@ static void transport_complete_qf(struct se_cmd *cmd)
 		ret = cmd->se_tfo->queue_data_in(cmd);
 		break;
 	case DMA_TO_DEVICE:
-		if (cmd->t_bidi_data_sg) {
+		if (cmd->se_cmd_flags & SCF_BIDI) {
 			ret = cmd->se_tfo->queue_data_in(cmd);
 			if (ret < 0)
 				break;
@@ -1856,10 +1910,25 @@ static void target_complete_ok_work(struct work_struct *work)
 	}
 	/*
 	 * Check for a callback, used by amongst other things
-	 * XDWRITE_READ_10 emulation.
+	 * XDWRITE_READ_10 and COMPARE_AND_WRITE emulation.
 	 */
-	if (cmd->transport_complete_callback)
-		cmd->transport_complete_callback(cmd);
+	if (cmd->transport_complete_callback) {
+		sense_reason_t rc;
+
+		rc = cmd->transport_complete_callback(cmd);
+		if (!rc && !(cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE_POST)) {
+			return;
+		} else if (rc) {
+			ret = transport_send_check_condition_and_sense(cmd,
+						rc, 0);
+			if (ret == -EAGAIN || ret == -ENOMEM)
+				goto queue_full;
+
+			transport_lun_remove_cmd(cmd);
+			transport_cmd_check_stop_to_fabric(cmd);
+			return;
+		}
+	}
 
 	switch (cmd->data_direction) {
 	case DMA_FROM_DEVICE:
@@ -1885,7 +1954,7 @@ static void target_complete_ok_work(struct work_struct *work)
 		/*
 		 * Check if we need to send READ payload for BIDI-COMMAND
 		 */
-		if (cmd->t_bidi_data_sg) {
+		if (cmd->se_cmd_flags & SCF_BIDI) {
 			spin_lock(&cmd->se_lun->lun_sep_lock);
 			if (cmd->se_lun->lun_sep) {
 				cmd->se_lun->lun_sep->sep_stats.tx_data_octets +=
@@ -1930,10 +1999,29 @@ static inline void transport_free_sgl(struct scatterlist *sgl, int nents)
 	kfree(sgl);
 }
 
+static inline void transport_reset_sgl_orig(struct se_cmd *cmd)
+{
+	/*
+	 * Check for saved t_data_sg that may be used for COMPARE_AND_WRITE
+	 * emulation, and free + reset pointers if necessary..
+	 */
+	if (!cmd->t_data_sg_orig)
+		return;
+
+	kfree(cmd->t_data_sg);
+	cmd->t_data_sg = cmd->t_data_sg_orig;
+	cmd->t_data_sg_orig = NULL;
+	cmd->t_data_nents = cmd->t_data_nents_orig;
+	cmd->t_data_nents_orig = 0;
+}
+
 static inline void transport_free_pages(struct se_cmd *cmd)
 {
-	if (cmd->se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC)
+	if (cmd->se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC) {
+		transport_reset_sgl_orig(cmd);
 		return;
+	}
+	transport_reset_sgl_orig(cmd);
 
 	transport_free_sgl(cmd->t_data_sg, cmd->t_data_nents);
 	cmd->t_data_sg = NULL;
@@ -2029,24 +2117,22 @@ void transport_kunmap_data_sg(struct se_cmd *cmd)
 }
 EXPORT_SYMBOL(transport_kunmap_data_sg);
 
-static int
-transport_generic_get_mem(struct se_cmd *cmd)
+int
+target_alloc_sgl(struct scatterlist **sgl, unsigned int *nents, u32 length,
+		 bool zero_page)
 {
-	u32 length = cmd->data_length;
-	unsigned int nents;
+	struct scatterlist *sg;
 	struct page *page;
-	gfp_t zero_flag;
+	gfp_t zero_flag = (zero_page) ? __GFP_ZERO : 0;
+	unsigned int nent;
 	int i = 0;
 
-	nents = DIV_ROUND_UP(length, PAGE_SIZE);
-	cmd->t_data_sg = kmalloc(sizeof(struct scatterlist) * nents, GFP_KERNEL);
-	if (!cmd->t_data_sg)
+	nent = DIV_ROUND_UP(length, PAGE_SIZE);
+	sg = kmalloc(sizeof(struct scatterlist) * nent, GFP_KERNEL);
+	if (!sg)
 		return -ENOMEM;
 
-	cmd->t_data_nents = nents;
-	sg_init_table(cmd->t_data_sg, nents);
-
-	zero_flag = cmd->se_cmd_flags & SCF_SCSI_DATA_CDB ? 0 : __GFP_ZERO;
+	sg_init_table(sg, nent);
 
 	while (length) {
 		u32 page_len = min_t(u32, length, PAGE_SIZE);
@@ -2054,19 +2140,20 @@ transport_generic_get_mem(struct se_cmd *cmd)
 		if (!page)
 			goto out;
 
-		sg_set_page(&cmd->t_data_sg[i], page, page_len, 0);
+		sg_set_page(&sg[i], page, page_len, 0);
 		length -= page_len;
 		i++;
 	}
+	*sgl = sg;
+	*nents = nent;
 	return 0;
 
 out:
 	while (i > 0) {
 		i--;
-		__free_page(sg_page(&cmd->t_data_sg[i]));
+		__free_page(sg_page(&sg[i]));
 	}
-	kfree(cmd->t_data_sg);
-	cmd->t_data_sg = NULL;
+	kfree(sg);
 	return -ENOMEM;
 }
 
@@ -2087,7 +2174,27 @@ transport_generic_new_cmd(struct se_cmd *cmd)
 	 */
 	if (!(cmd->se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC) &&
 	    cmd->data_length) {
-		ret = transport_generic_get_mem(cmd);
+		bool zero_flag = !(cmd->se_cmd_flags & SCF_SCSI_DATA_CDB);
+
+		if ((cmd->se_cmd_flags & SCF_BIDI) ||
+		    (cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE)) {
+			u32 bidi_length;
+
+			if (cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE)
+				bidi_length = cmd->t_task_nolb *
+					      cmd->se_dev->dev_attrib.block_size;
+			else
+				bidi_length = cmd->data_length;
+
+			ret = target_alloc_sgl(&cmd->t_bidi_data_sg,
+					       &cmd->t_bidi_data_nents,
+					       bidi_length, zero_flag);
+			if (ret < 0)
+				return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+		}
+
+		ret = target_alloc_sgl(&cmd->t_data_sg, &cmd->t_data_nents,
+				       cmd->data_length, zero_flag);
 		if (ret < 0)
 			return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
@@ -2740,6 +2847,15 @@ transport_send_check_condition_and_sense(struct se_cmd *cmd,
 		buffer[SPC_ASC_KEY_OFFSET] = asc;
 		buffer[SPC_ASCQ_KEY_OFFSET] = ascq;
 		break;
+	case TCM_MISCOMPARE_VERIFY:
+		/* CURRENT ERROR */
+		buffer[0] = 0x70;
+		buffer[SPC_ADD_SENSE_LEN_OFFSET] = 10;
+		buffer[SPC_SENSE_KEY_OFFSET] = MISCOMPARE;
+		/* MISCOMPARE DURING VERIFY OPERATION */
+		buffer[SPC_ASC_KEY_OFFSET] = 0x1d;
+		buffer[SPC_ASCQ_KEY_OFFSET] = 0x00;
+		break;
 	case TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE:
 	default:
 		/* CURRENT ERROR */