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, 103 insertions, 33 deletions

diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 0c27c7df1b0..4b79a1f2f90 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1,12 +1,12 @@
 /*******************************************************************************
  * Vhost kernel TCM fabric driver for virtio SCSI initiators
  *
- * (C) Copyright 2010-2012 RisingTide Systems LLC.
+ * (C) Copyright 2010-2013 Datera, Inc.
  * (C) Copyright 2010-2012 IBM Corp.
  *
  * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
  *
- * Authors: Nicholas A. Bellinger <nab@risingtidesystems.com>
+ * Authors: Nicholas A. Bellinger <nab@daterainc.com>
  *          Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
  *
  * This program is free software; you can redistribute it and/or modify
@@ -48,12 +48,16 @@
 #include <linux/virtio_scsi.h>
 #include <linux/llist.h>
 #include <linux/bitmap.h>
+#include <linux/percpu_ida.h>
 
 #include "vhost.h"
 
 #define TCM_VHOST_VERSION  "v0.1"
 #define TCM_VHOST_NAMELEN 256
 #define TCM_VHOST_MAX_CDB_SIZE 32
+#define TCM_VHOST_DEFAULT_TAGS 256
+#define TCM_VHOST_PREALLOC_SGLS 2048
+#define TCM_VHOST_PREALLOC_PAGES 2048
 
 struct vhost_scsi_inflight {
 	/* Wait for the flush operation to finish */
@@ -79,6 +83,7 @@ struct tcm_vhost_cmd {
 	u32 tvc_lun;
 	/* Pointer to the SGL formatted memory from virtio-scsi */
 	struct scatterlist *tvc_sgl;
+	struct page **tvc_upages;
 	/* Pointer to response */
 	struct virtio_scsi_cmd_resp __user *tvc_resp;
 	/* Pointer to vhost_scsi for our device */
@@ -450,17 +455,16 @@ static void tcm_vhost_release_cmd(struct se_cmd *se_cmd)
 {
 	struct tcm_vhost_cmd *tv_cmd = container_of(se_cmd,
 				struct tcm_vhost_cmd, tvc_se_cmd);
+	struct se_session *se_sess = se_cmd->se_sess;
 
 	if (tv_cmd->tvc_sgl_count) {
 		u32 i;
 		for (i = 0; i < tv_cmd->tvc_sgl_count; i++)
 			put_page(sg_page(&tv_cmd->tvc_sgl[i]));
-
-		kfree(tv_cmd->tvc_sgl);
         }
 
 	tcm_vhost_put_inflight(tv_cmd->inflight);
-	kfree(tv_cmd);
+	percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag);
 }
 
 static int tcm_vhost_shutdown_session(struct se_session *se_sess)
@@ -704,7 +708,7 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
 }
 
 static struct tcm_vhost_cmd *
-vhost_scsi_allocate_cmd(struct vhost_virtqueue *vq,
+vhost_scsi_get_tag(struct vhost_virtqueue *vq,
 			struct tcm_vhost_tpg *tpg,
 			struct virtio_scsi_cmd_req *v_req,
 			u32 exp_data_len,
@@ -712,18 +716,27 @@ vhost_scsi_allocate_cmd(struct vhost_virtqueue *vq,
 {
 	struct tcm_vhost_cmd *cmd;
 	struct tcm_vhost_nexus *tv_nexus;
+	struct se_session *se_sess;
+	struct scatterlist *sg;
+	struct page **pages;
+	int tag;
 
 	tv_nexus = tpg->tpg_nexus;
 	if (!tv_nexus) {
 		pr_err("Unable to locate active struct tcm_vhost_nexus\n");
 		return ERR_PTR(-EIO);
 	}
+	se_sess = tv_nexus->tvn_se_sess;
 
-	cmd = kzalloc(sizeof(struct tcm_vhost_cmd), GFP_ATOMIC);
-	if (!cmd) {
-		pr_err("Unable to allocate struct tcm_vhost_cmd\n");
-		return ERR_PTR(-ENOMEM);
-	}
+	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, GFP_KERNEL);
+	cmd = &((struct tcm_vhost_cmd *)se_sess->sess_cmd_map)[tag];
+	sg = cmd->tvc_sgl;
+	pages = cmd->tvc_upages;
+	memset(cmd, 0, sizeof(struct tcm_vhost_cmd));
+
+	cmd->tvc_sgl = sg;
+	cmd->tvc_upages = pages;
+	cmd->tvc_se_cmd.map_tag = tag;
 	cmd->tvc_tag = v_req->tag;
 	cmd->tvc_task_attr = v_req->task_attr;
 	cmd->tvc_exp_data_len = exp_data_len;
@@ -740,7 +753,8 @@ vhost_scsi_allocate_cmd(struct vhost_virtqueue *vq,
  * Returns the number of scatterlist entries used or -errno on error.
  */
 static int
-vhost_scsi_map_to_sgl(struct scatterlist *sgl,
+vhost_scsi_map_to_sgl(struct tcm_vhost_cmd *tv_cmd,
+		      struct scatterlist *sgl,
 		      unsigned int sgl_count,
 		      struct iovec *iov,
 		      int write)
@@ -752,13 +766,25 @@ vhost_scsi_map_to_sgl(struct scatterlist *sgl,
 	struct page **pages;
 	int ret, i;
 
+	if (sgl_count > TCM_VHOST_PREALLOC_SGLS) {
+		pr_err("vhost_scsi_map_to_sgl() psgl_count: %u greater than"
+		       " preallocated TCM_VHOST_PREALLOC_SGLS: %u\n",
+			sgl_count, TCM_VHOST_PREALLOC_SGLS);
+		return -ENOBUFS;
+	}
+
 	pages_nr = iov_num_pages(iov);
 	if (pages_nr > sgl_count)
 		return -ENOBUFS;
 
-	pages = kmalloc(pages_nr * sizeof(struct page *), GFP_KERNEL);
-	if (!pages)
-		return -ENOMEM;
+	if (pages_nr > TCM_VHOST_PREALLOC_PAGES) {
+		pr_err("vhost_scsi_map_to_sgl() pages_nr: %u greater than"
+		       " preallocated TCM_VHOST_PREALLOC_PAGES: %u\n",
+			pages_nr, TCM_VHOST_PREALLOC_PAGES);
+		return -ENOBUFS;
+	}
+
+	pages = tv_cmd->tvc_upages;
 
 	ret = get_user_pages_fast((unsigned long)ptr, pages_nr, write, pages);
 	/* No pages were pinned */
@@ -783,7 +809,6 @@ vhost_scsi_map_to_sgl(struct scatterlist *sgl,
 	}
 
 out:
-	kfree(pages);
 	return ret;
 }
 
@@ -807,24 +832,20 @@ vhost_scsi_map_iov_to_sgl(struct tcm_vhost_cmd *cmd,
 
 	/* TODO overflow checking */
 
-	sg = kmalloc(sizeof(cmd->tvc_sgl[0]) * sgl_count, GFP_ATOMIC);
-	if (!sg)
-		return -ENOMEM;
-	pr_debug("%s sg %p sgl_count %u is_err %d\n", __func__,
-	       sg, sgl_count, !sg);
+	sg = cmd->tvc_sgl;
+	pr_debug("%s sg %p sgl_count %u\n", __func__, sg, sgl_count);
 	sg_init_table(sg, sgl_count);
 
-	cmd->tvc_sgl = sg;
 	cmd->tvc_sgl_count = sgl_count;
 
 	pr_debug("Mapping %u iovecs for %u pages\n", niov, sgl_count);
 	for (i = 0; i < niov; i++) {
-		ret = vhost_scsi_map_to_sgl(sg, sgl_count, &iov[i], write);
+		ret = vhost_scsi_map_to_sgl(cmd, sg, sgl_count, &iov[i],
+					    write);
 		if (ret < 0) {
 			for (i = 0; i < cmd->tvc_sgl_count; i++)
 				put_page(sg_page(&cmd->tvc_sgl[i]));
-			kfree(cmd->tvc_sgl);
-			cmd->tvc_sgl = NULL;
+
 			cmd->tvc_sgl_count = 0;
 			return ret;
 		}
@@ -989,10 +1010,10 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 		for (i = 0; i < data_num; i++)
 			exp_data_len += vq->iov[data_first + i].iov_len;
 
-		cmd = vhost_scsi_allocate_cmd(vq, tpg, &v_req,
-					exp_data_len, data_direction);
+		cmd = vhost_scsi_get_tag(vq, tpg, &v_req,
+					 exp_data_len, data_direction);
 		if (IS_ERR(cmd)) {
-			vq_err(vq, "vhost_scsi_allocate_cmd failed %ld\n",
+			vq_err(vq, "vhost_scsi_get_tag failed %ld\n",
 					PTR_ERR(cmd));
 			goto err_cmd;
 		}
@@ -1654,11 +1675,31 @@ static void tcm_vhost_drop_nodeacl(struct se_node_acl *se_acl)
 	kfree(nacl);
 }
 
+static void tcm_vhost_free_cmd_map_res(struct tcm_vhost_nexus *nexus,
+				       struct se_session *se_sess)
+{
+	struct tcm_vhost_cmd *tv_cmd;
+	unsigned int i;
+
+	if (!se_sess->sess_cmd_map)
+		return;
+
+	for (i = 0; i < TCM_VHOST_DEFAULT_TAGS; i++) {
+		tv_cmd = &((struct tcm_vhost_cmd *)se_sess->sess_cmd_map)[i];
+
+		kfree(tv_cmd->tvc_sgl);
+		kfree(tv_cmd->tvc_upages);
+	}
+}
+
 static int tcm_vhost_make_nexus(struct tcm_vhost_tpg *tpg,
 				const char *name)
 {
 	struct se_portal_group *se_tpg;
+	struct se_session *se_sess;
 	struct tcm_vhost_nexus *tv_nexus;
+	struct tcm_vhost_cmd *tv_cmd;
+	unsigned int i;
 
 	mutex_lock(&tpg->tv_tpg_mutex);
 	if (tpg->tpg_nexus) {
@@ -1675,14 +1716,37 @@ static int tcm_vhost_make_nexus(struct tcm_vhost_tpg *tpg,
 		return -ENOMEM;
 	}
 	/*
-	 *  Initialize the struct se_session pointer
+	 *  Initialize the struct se_session pointer and setup tagpool
+	 *  for struct tcm_vhost_cmd descriptors
 	 */
-	tv_nexus->tvn_se_sess = transport_init_session();
+	tv_nexus->tvn_se_sess = transport_init_session_tags(
+					TCM_VHOST_DEFAULT_TAGS,
+					sizeof(struct tcm_vhost_cmd));
 	if (IS_ERR(tv_nexus->tvn_se_sess)) {
 		mutex_unlock(&tpg->tv_tpg_mutex);
 		kfree(tv_nexus);
 		return -ENOMEM;
 	}
+	se_sess = tv_nexus->tvn_se_sess;
+	for (i = 0; i < TCM_VHOST_DEFAULT_TAGS; i++) {
+		tv_cmd = &((struct tcm_vhost_cmd *)se_sess->sess_cmd_map)[i];
+
+		tv_cmd->tvc_sgl = kzalloc(sizeof(struct scatterlist) *
+					TCM_VHOST_PREALLOC_SGLS, GFP_KERNEL);
+		if (!tv_cmd->tvc_sgl) {
+			mutex_unlock(&tpg->tv_tpg_mutex);
+			pr_err("Unable to allocate tv_cmd->tvc_sgl\n");
+			goto out;
+		}
+
+		tv_cmd->tvc_upages = kzalloc(sizeof(struct page *) *
+					TCM_VHOST_PREALLOC_PAGES, GFP_KERNEL);
+		if (!tv_cmd->tvc_upages) {
+			mutex_unlock(&tpg->tv_tpg_mutex);
+			pr_err("Unable to allocate tv_cmd->tvc_upages\n");
+			goto out;
+		}
+	}
 	/*
 	 * Since we are running in 'demo mode' this call with generate a
 	 * struct se_node_acl for the tcm_vhost struct se_portal_group with
@@ -1694,9 +1758,7 @@ static int tcm_vhost_make_nexus(struct tcm_vhost_tpg *tpg,
 		mutex_unlock(&tpg->tv_tpg_mutex);
 		pr_debug("core_tpg_check_initiator_node_acl() failed"
 				" for %s\n", name);
-		transport_free_session(tv_nexus->tvn_se_sess);
-		kfree(tv_nexus);
-		return -ENOMEM;
+		goto out;
 	}
 	/*
 	 * Now register the TCM vhost virtual I_T Nexus as active with the
@@ -1708,6 +1770,12 @@ static int tcm_vhost_make_nexus(struct tcm_vhost_tpg *tpg,
 
 	mutex_unlock(&tpg->tv_tpg_mutex);
 	return 0;
+
+out:
+	tcm_vhost_free_cmd_map_res(tv_nexus, se_sess);
+	transport_free_session(se_sess);
+	kfree(tv_nexus);
+	return -ENOMEM;
 }
 
 static int tcm_vhost_drop_nexus(struct tcm_vhost_tpg *tpg)
@@ -1747,6 +1815,8 @@ static int tcm_vhost_drop_nexus(struct tcm_vhost_tpg *tpg)
 	pr_debug("TCM_vhost_ConfigFS: Removing I_T Nexus to emulated"
 		" %s Initiator Port: %s\n", tcm_vhost_dump_proto_id(tpg->tport),
 		tv_nexus->tvn_se_sess->se_node_acl->initiatorname);
+
+	tcm_vhost_free_cmd_map_res(tv_nexus, se_sess);
 	/*
 	 * Release the SCSI I_T Nexus to the emulated vhost Target Port
 	 */