scsi.c 58.0 KB
Newer Older
1 2 3
/*******************************************************************************
 * Vhost kernel TCM fabric driver for virtio SCSI initiators
 *
4
 * (C) Copyright 2010-2013 Datera, Inc.
5 6 7 8
 * (C) Copyright 2010-2012 IBM Corp.
 *
 * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
 *
9
 * Authors: Nicholas A. Bellinger <nab@daterainc.com>
10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48
 *          Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 ****************************************************************************/

#include <linux/module.h>
#include <linux/moduleparam.h>
#include <generated/utsrelease.h>
#include <linux/utsname.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/kthread.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/configfs.h>
#include <linux/ctype.h>
#include <linux/compat.h>
#include <linux/eventfd.h>
#include <linux/fs.h>
#include <linux/miscdevice.h>
#include <asm/unaligned.h>
#include <scsi/scsi.h>
#include <scsi/scsi_tcq.h>
#include <target/target_core_base.h>
#include <target/target_core_fabric.h>
#include <target/target_core_fabric_configfs.h>
#include <target/target_core_configfs.h>
#include <target/configfs_macros.h>
#include <linux/vhost.h>
#include <linux/virtio_scsi.h>
49
#include <linux/llist.h>
A
Asias He 已提交
50
#include <linux/bitmap.h>
51
#include <linux/percpu_ida.h>
52 53

#include "vhost.h"
M
Michael S. Tsirkin 已提交
54 55 56 57

#define TCM_VHOST_VERSION  "v0.1"
#define TCM_VHOST_NAMELEN 256
#define TCM_VHOST_MAX_CDB_SIZE 32
58
#define TCM_VHOST_DEFAULT_TAGS 256
59 60
#define TCM_VHOST_PREALLOC_SGLS 2048
#define TCM_VHOST_PREALLOC_PAGES 2048
M
Michael S. Tsirkin 已提交
61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85

struct vhost_scsi_inflight {
	/* Wait for the flush operation to finish */
	struct completion comp;
	/* Refcount for the inflight reqs */
	struct kref kref;
};

struct tcm_vhost_cmd {
	/* Descriptor from vhost_get_vq_desc() for virt_queue segment */
	int tvc_vq_desc;
	/* virtio-scsi initiator task attribute */
	int tvc_task_attr;
	/* virtio-scsi initiator data direction */
	enum dma_data_direction tvc_data_direction;
	/* Expected data transfer length from virtio-scsi header */
	u32 tvc_exp_data_len;
	/* The Tag from include/linux/virtio_scsi.h:struct virtio_scsi_cmd_req */
	u64 tvc_tag;
	/* The number of scatterlists associated with this cmd */
	u32 tvc_sgl_count;
	/* Saved unpacked SCSI LUN for tcm_vhost_submission_work() */
	u32 tvc_lun;
	/* Pointer to the SGL formatted memory from virtio-scsi */
	struct scatterlist *tvc_sgl;
86
	struct page **tvc_upages;
M
Michael S. Tsirkin 已提交
87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160
	/* Pointer to response */
	struct virtio_scsi_cmd_resp __user *tvc_resp;
	/* Pointer to vhost_scsi for our device */
	struct vhost_scsi *tvc_vhost;
	/* Pointer to vhost_virtqueue for the cmd */
	struct vhost_virtqueue *tvc_vq;
	/* Pointer to vhost nexus memory */
	struct tcm_vhost_nexus *tvc_nexus;
	/* The TCM I/O descriptor that is accessed via container_of() */
	struct se_cmd tvc_se_cmd;
	/* work item used for cmwq dispatch to tcm_vhost_submission_work() */
	struct work_struct work;
	/* Copy of the incoming SCSI command descriptor block (CDB) */
	unsigned char tvc_cdb[TCM_VHOST_MAX_CDB_SIZE];
	/* Sense buffer that will be mapped into outgoing status */
	unsigned char tvc_sense_buf[TRANSPORT_SENSE_BUFFER];
	/* Completed commands list, serviced from vhost worker thread */
	struct llist_node tvc_completion_list;
	/* Used to track inflight cmd */
	struct vhost_scsi_inflight *inflight;
};

struct tcm_vhost_nexus {
	/* Pointer to TCM session for I_T Nexus */
	struct se_session *tvn_se_sess;
};

struct tcm_vhost_nacl {
	/* Binary World Wide unique Port Name for Vhost Initiator port */
	u64 iport_wwpn;
	/* ASCII formatted WWPN for Sas Initiator port */
	char iport_name[TCM_VHOST_NAMELEN];
	/* Returned by tcm_vhost_make_nodeacl() */
	struct se_node_acl se_node_acl;
};

struct tcm_vhost_tpg {
	/* Vhost port target portal group tag for TCM */
	u16 tport_tpgt;
	/* Used to track number of TPG Port/Lun Links wrt to explict I_T Nexus shutdown */
	int tv_tpg_port_count;
	/* Used for vhost_scsi device reference to tpg_nexus, protected by tv_tpg_mutex */
	int tv_tpg_vhost_count;
	/* list for tcm_vhost_list */
	struct list_head tv_tpg_list;
	/* Used to protect access for tpg_nexus */
	struct mutex tv_tpg_mutex;
	/* Pointer to the TCM VHost I_T Nexus for this TPG endpoint */
	struct tcm_vhost_nexus *tpg_nexus;
	/* Pointer back to tcm_vhost_tport */
	struct tcm_vhost_tport *tport;
	/* Returned by tcm_vhost_make_tpg() */
	struct se_portal_group se_tpg;
	/* Pointer back to vhost_scsi, protected by tv_tpg_mutex */
	struct vhost_scsi *vhost_scsi;
};

struct tcm_vhost_tport {
	/* SCSI protocol the tport is providing */
	u8 tport_proto_id;
	/* Binary World Wide unique Port Name for Vhost Target port */
	u64 tport_wwpn;
	/* ASCII formatted WWPN for Vhost Target port */
	char tport_name[TCM_VHOST_NAMELEN];
	/* Returned by tcm_vhost_make_tport() */
	struct se_wwn tport_wwn;
};

struct tcm_vhost_evt {
	/* event to be sent to guest */
	struct virtio_scsi_event event;
	/* event list, serviced from vhost worker thread */
	struct llist_node list;
};
161

162 163 164 165 166 167
enum {
	VHOST_SCSI_VQ_CTL = 0,
	VHOST_SCSI_VQ_EVT = 1,
	VHOST_SCSI_VQ_IO = 2,
};

168
enum {
169
	VHOST_SCSI_FEATURES = VHOST_FEATURES | (1ULL << VIRTIO_SCSI_F_HOTPLUG)
170 171
};

A
Asias He 已提交
172 173
#define VHOST_SCSI_MAX_TARGET	256
#define VHOST_SCSI_MAX_VQ	128
174
#define VHOST_SCSI_MAX_EVENT	128
A
Asias He 已提交
175

176 177
struct vhost_scsi_virtqueue {
	struct vhost_virtqueue vq;
178 179 180 181 182
	/*
	 * Reference counting for inflight reqs, used for flush operation. At
	 * each time, one reference tracks new commands submitted, while we
	 * wait for another one to reach 0.
	 */
183
	struct vhost_scsi_inflight inflights[2];
184 185 186 187
	/*
	 * Indicate current inflight in use, protected by vq->mutex.
	 * Writers must also take dev mutex and flush under it.
	 */
188
	int inflight_idx;
189 190
};

191
struct vhost_scsi {
A
Asias He 已提交
192
	/* Protected by vhost_scsi->dev.mutex */
193
	struct tcm_vhost_tpg **vs_tpg;
A
Asias He 已提交
194 195
	char vs_vhost_wwpn[TRANSPORT_IQN_LEN];

196
	struct vhost_dev dev;
197
	struct vhost_scsi_virtqueue vqs[VHOST_SCSI_MAX_VQ];
198 199

	struct vhost_work vs_completion_work; /* cmd completion work item */
200
	struct llist_head vs_completion_list; /* cmd completion queue */
201 202 203 204 205 206

	struct vhost_work vs_event_work; /* evt injection work item */
	struct llist_head vs_event_list; /* evt injection queue */

	bool vs_events_missed; /* any missed events, protected by vq->mutex */
	int vs_events_nr; /* num of pending events, protected by vq->mutex */
207 208 209 210 211 212 213 214 215 216 217
};

/* Local pointer to allocated TCM configfs fabric module */
static struct target_fabric_configfs *tcm_vhost_fabric_configfs;

static struct workqueue_struct *tcm_vhost_workqueue;

/* Global spinlock to protect tcm_vhost TPG list for vhost IOCTL access */
static DEFINE_MUTEX(tcm_vhost_mutex);
static LIST_HEAD(tcm_vhost_list);

A
Asias He 已提交
218 219 220 221 222 223
static int iov_num_pages(struct iovec *iov)
{
	return (PAGE_ALIGN((unsigned long)iov->iov_base + iov->iov_len) -
	       ((unsigned long)iov->iov_base & PAGE_MASK)) >> PAGE_SHIFT;
}

A
Asias He 已提交
224
static void tcm_vhost_done_inflight(struct kref *kref)
225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276
{
	struct vhost_scsi_inflight *inflight;

	inflight = container_of(kref, struct vhost_scsi_inflight, kref);
	complete(&inflight->comp);
}

static void tcm_vhost_init_inflight(struct vhost_scsi *vs,
				    struct vhost_scsi_inflight *old_inflight[])
{
	struct vhost_scsi_inflight *new_inflight;
	struct vhost_virtqueue *vq;
	int idx, i;

	for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
		vq = &vs->vqs[i].vq;

		mutex_lock(&vq->mutex);

		/* store old infight */
		idx = vs->vqs[i].inflight_idx;
		if (old_inflight)
			old_inflight[i] = &vs->vqs[i].inflights[idx];

		/* setup new infight */
		vs->vqs[i].inflight_idx = idx ^ 1;
		new_inflight = &vs->vqs[i].inflights[idx ^ 1];
		kref_init(&new_inflight->kref);
		init_completion(&new_inflight->comp);

		mutex_unlock(&vq->mutex);
	}
}

static struct vhost_scsi_inflight *
tcm_vhost_get_inflight(struct vhost_virtqueue *vq)
{
	struct vhost_scsi_inflight *inflight;
	struct vhost_scsi_virtqueue *svq;

	svq = container_of(vq, struct vhost_scsi_virtqueue, vq);
	inflight = &svq->inflights[svq->inflight_idx];
	kref_get(&inflight->kref);

	return inflight;
}

static void tcm_vhost_put_inflight(struct vhost_scsi_inflight *inflight)
{
	kref_put(&inflight->kref, tcm_vhost_done_inflight);
}

277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334
static int tcm_vhost_check_true(struct se_portal_group *se_tpg)
{
	return 1;
}

static int tcm_vhost_check_false(struct se_portal_group *se_tpg)
{
	return 0;
}

static char *tcm_vhost_get_fabric_name(void)
{
	return "vhost";
}

static u8 tcm_vhost_get_fabric_proto_ident(struct se_portal_group *se_tpg)
{
	struct tcm_vhost_tpg *tpg = container_of(se_tpg,
				struct tcm_vhost_tpg, se_tpg);
	struct tcm_vhost_tport *tport = tpg->tport;

	switch (tport->tport_proto_id) {
	case SCSI_PROTOCOL_SAS:
		return sas_get_fabric_proto_ident(se_tpg);
	case SCSI_PROTOCOL_FCP:
		return fc_get_fabric_proto_ident(se_tpg);
	case SCSI_PROTOCOL_ISCSI:
		return iscsi_get_fabric_proto_ident(se_tpg);
	default:
		pr_err("Unknown tport_proto_id: 0x%02x, using"
			" SAS emulation\n", tport->tport_proto_id);
		break;
	}

	return sas_get_fabric_proto_ident(se_tpg);
}

static char *tcm_vhost_get_fabric_wwn(struct se_portal_group *se_tpg)
{
	struct tcm_vhost_tpg *tpg = container_of(se_tpg,
				struct tcm_vhost_tpg, se_tpg);
	struct tcm_vhost_tport *tport = tpg->tport;

	return &tport->tport_name[0];
}

static u16 tcm_vhost_get_tag(struct se_portal_group *se_tpg)
{
	struct tcm_vhost_tpg *tpg = container_of(se_tpg,
				struct tcm_vhost_tpg, se_tpg);
	return tpg->tport_tpgt;
}

static u32 tcm_vhost_get_default_depth(struct se_portal_group *se_tpg)
{
	return 1;
}

335 336 337 338 339 340
static u32
tcm_vhost_get_pr_transport_id(struct se_portal_group *se_tpg,
			      struct se_node_acl *se_nacl,
			      struct t10_pr_registration *pr_reg,
			      int *format_code,
			      unsigned char *buf)
341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365
{
	struct tcm_vhost_tpg *tpg = container_of(se_tpg,
				struct tcm_vhost_tpg, se_tpg);
	struct tcm_vhost_tport *tport = tpg->tport;

	switch (tport->tport_proto_id) {
	case SCSI_PROTOCOL_SAS:
		return sas_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
					format_code, buf);
	case SCSI_PROTOCOL_FCP:
		return fc_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
					format_code, buf);
	case SCSI_PROTOCOL_ISCSI:
		return iscsi_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
					format_code, buf);
	default:
		pr_err("Unknown tport_proto_id: 0x%02x, using"
			" SAS emulation\n", tport->tport_proto_id);
		break;
	}

	return sas_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
			format_code, buf);
}

366 367 368 369 370
static u32
tcm_vhost_get_pr_transport_id_len(struct se_portal_group *se_tpg,
				  struct se_node_acl *se_nacl,
				  struct t10_pr_registration *pr_reg,
				  int *format_code)
371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395
{
	struct tcm_vhost_tpg *tpg = container_of(se_tpg,
				struct tcm_vhost_tpg, se_tpg);
	struct tcm_vhost_tport *tport = tpg->tport;

	switch (tport->tport_proto_id) {
	case SCSI_PROTOCOL_SAS:
		return sas_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
					format_code);
	case SCSI_PROTOCOL_FCP:
		return fc_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
					format_code);
	case SCSI_PROTOCOL_ISCSI:
		return iscsi_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
					format_code);
	default:
		pr_err("Unknown tport_proto_id: 0x%02x, using"
			" SAS emulation\n", tport->tport_proto_id);
		break;
	}

	return sas_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
			format_code);
}

396 397 398 399 400
static char *
tcm_vhost_parse_pr_out_transport_id(struct se_portal_group *se_tpg,
				    const char *buf,
				    u32 *out_tid_len,
				    char **port_nexus_ptr)
401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425
{
	struct tcm_vhost_tpg *tpg = container_of(se_tpg,
				struct tcm_vhost_tpg, se_tpg);
	struct tcm_vhost_tport *tport = tpg->tport;

	switch (tport->tport_proto_id) {
	case SCSI_PROTOCOL_SAS:
		return sas_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
					port_nexus_ptr);
	case SCSI_PROTOCOL_FCP:
		return fc_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
					port_nexus_ptr);
	case SCSI_PROTOCOL_ISCSI:
		return iscsi_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
					port_nexus_ptr);
	default:
		pr_err("Unknown tport_proto_id: 0x%02x, using"
			" SAS emulation\n", tport->tport_proto_id);
		break;
	}

	return sas_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
			port_nexus_ptr);
}

426 427
static struct se_node_acl *
tcm_vhost_alloc_fabric_acl(struct se_portal_group *se_tpg)
428 429 430 431 432
{
	struct tcm_vhost_nacl *nacl;

	nacl = kzalloc(sizeof(struct tcm_vhost_nacl), GFP_KERNEL);
	if (!nacl) {
433
		pr_err("Unable to allocate struct tcm_vhost_nacl\n");
434 435 436 437 438 439
		return NULL;
	}

	return &nacl->se_node_acl;
}

440 441 442
static void
tcm_vhost_release_fabric_acl(struct se_portal_group *se_tpg,
			     struct se_node_acl *se_nacl)
443 444 445 446 447 448 449 450 451 452 453 454 455
{
	struct tcm_vhost_nacl *nacl = container_of(se_nacl,
			struct tcm_vhost_nacl, se_node_acl);
	kfree(nacl);
}

static u32 tcm_vhost_tpg_get_inst_index(struct se_portal_group *se_tpg)
{
	return 1;
}

static void tcm_vhost_release_cmd(struct se_cmd *se_cmd)
{
456 457
	struct tcm_vhost_cmd *tv_cmd = container_of(se_cmd,
				struct tcm_vhost_cmd, tvc_se_cmd);
458
	struct se_session *se_sess = se_cmd->se_sess;
459 460 461 462 463

	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]));
464
	}
465 466

	tcm_vhost_put_inflight(tv_cmd->inflight);
467
	percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag);
468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511
}

static int tcm_vhost_shutdown_session(struct se_session *se_sess)
{
	return 0;
}

static void tcm_vhost_close_session(struct se_session *se_sess)
{
	return;
}

static u32 tcm_vhost_sess_get_index(struct se_session *se_sess)
{
	return 0;
}

static int tcm_vhost_write_pending(struct se_cmd *se_cmd)
{
	/* Go ahead and process the write immediately */
	target_execute_cmd(se_cmd);
	return 0;
}

static int tcm_vhost_write_pending_status(struct se_cmd *se_cmd)
{
	return 0;
}

static void tcm_vhost_set_default_node_attrs(struct se_node_acl *nacl)
{
	return;
}

static u32 tcm_vhost_get_task_tag(struct se_cmd *se_cmd)
{
	return 0;
}

static int tcm_vhost_get_cmd_state(struct se_cmd *se_cmd)
{
	return 0;
}

512
static void vhost_scsi_complete_cmd(struct tcm_vhost_cmd *cmd)
513
{
514
	struct vhost_scsi *vs = cmd->tvc_vhost;
515

516
	llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list);
517 518 519

	vhost_work_queue(&vs->dev, &vs->vs_completion_work);
}
520 521 522

static int tcm_vhost_queue_data_in(struct se_cmd *se_cmd)
{
523
	struct tcm_vhost_cmd *cmd = container_of(se_cmd,
524
				struct tcm_vhost_cmd, tvc_se_cmd);
525
	vhost_scsi_complete_cmd(cmd);
526 527 528 529 530
	return 0;
}

static int tcm_vhost_queue_status(struct se_cmd *se_cmd)
{
531
	struct tcm_vhost_cmd *cmd = container_of(se_cmd,
532
				struct tcm_vhost_cmd, tvc_se_cmd);
533
	vhost_scsi_complete_cmd(cmd);
534 535 536
	return 0;
}

537
static void tcm_vhost_queue_tm_rsp(struct se_cmd *se_cmd)
538
{
539
	return;
540 541
}

542 543 544 545 546 547
static void tcm_vhost_free_evt(struct vhost_scsi *vs, struct tcm_vhost_evt *evt)
{
	vs->vs_events_nr--;
	kfree(evt);
}

548 549 550
static struct tcm_vhost_evt *
tcm_vhost_allocate_evt(struct vhost_scsi *vs,
		       u32 event, u32 reason)
551
{
552
	struct vhost_virtqueue *vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573
	struct tcm_vhost_evt *evt;

	if (vs->vs_events_nr > VHOST_SCSI_MAX_EVENT) {
		vs->vs_events_missed = true;
		return NULL;
	}

	evt = kzalloc(sizeof(*evt), GFP_KERNEL);
	if (!evt) {
		vq_err(vq, "Failed to allocate tcm_vhost_evt\n");
		vs->vs_events_missed = true;
		return NULL;
	}

	evt->event.event = event;
	evt->event.reason = reason;
	vs->vs_events_nr++;

	return evt;
}

574
static void vhost_scsi_free_cmd(struct tcm_vhost_cmd *cmd)
575
{
576
	struct se_cmd *se_cmd = &cmd->tvc_se_cmd;
577 578

	/* TODO locking against target/backend threads? */
579
	transport_generic_free_cmd(se_cmd, 0);
580

581
}
582

583 584 585
static int vhost_scsi_check_stop_free(struct se_cmd *se_cmd)
{
	return target_put_sess_cmd(se_cmd->se_sess, se_cmd);
586 587
}

588 589
static void
tcm_vhost_do_evt_work(struct vhost_scsi *vs, struct tcm_vhost_evt *evt)
590
{
591
	struct vhost_virtqueue *vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641
	struct virtio_scsi_event *event = &evt->event;
	struct virtio_scsi_event __user *eventp;
	unsigned out, in;
	int head, ret;

	if (!vq->private_data) {
		vs->vs_events_missed = true;
		return;
	}

again:
	vhost_disable_notify(&vs->dev, vq);
	head = vhost_get_vq_desc(&vs->dev, vq, vq->iov,
			ARRAY_SIZE(vq->iov), &out, &in,
			NULL, NULL);
	if (head < 0) {
		vs->vs_events_missed = true;
		return;
	}
	if (head == vq->num) {
		if (vhost_enable_notify(&vs->dev, vq))
			goto again;
		vs->vs_events_missed = true;
		return;
	}

	if ((vq->iov[out].iov_len != sizeof(struct virtio_scsi_event))) {
		vq_err(vq, "Expecting virtio_scsi_event, got %zu bytes\n",
				vq->iov[out].iov_len);
		vs->vs_events_missed = true;
		return;
	}

	if (vs->vs_events_missed) {
		event->event |= VIRTIO_SCSI_T_EVENTS_MISSED;
		vs->vs_events_missed = false;
	}

	eventp = vq->iov[out].iov_base;
	ret = __copy_to_user(eventp, event, sizeof(*event));
	if (!ret)
		vhost_add_used_and_signal(&vs->dev, vq, head, 0);
	else
		vq_err(vq, "Faulted on tcm_vhost_send_event\n");
}

static void tcm_vhost_evt_work(struct vhost_work *work)
{
	struct vhost_scsi *vs = container_of(work, struct vhost_scsi,
					vs_event_work);
642
	struct vhost_virtqueue *vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
643 644 645 646 647 648 649 650 651 652 653 654 655 656
	struct tcm_vhost_evt *evt;
	struct llist_node *llnode;

	mutex_lock(&vq->mutex);
	llnode = llist_del_all(&vs->vs_event_list);
	while (llnode) {
		evt = llist_entry(llnode, struct tcm_vhost_evt, list);
		llnode = llist_next(llnode);
		tcm_vhost_do_evt_work(vs, evt);
		tcm_vhost_free_evt(vs, evt);
	}
	mutex_unlock(&vq->mutex);
}

657 658 659 660 661 662 663 664 665
/* Fill in status and signal that we are done processing this command
 *
 * This is scheduled in the vhost work queue so we are called with the owner
 * process mm and can access the vring.
 */
static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
{
	struct vhost_scsi *vs = container_of(work, struct vhost_scsi,
					vs_completion_work);
A
Asias He 已提交
666
	DECLARE_BITMAP(signal, VHOST_SCSI_MAX_VQ);
667
	struct virtio_scsi_cmd_resp v_rsp;
668
	struct tcm_vhost_cmd *cmd;
669 670
	struct llist_node *llnode;
	struct se_cmd *se_cmd;
A
Asias He 已提交
671
	int ret, vq;
672

A
Asias He 已提交
673
	bitmap_zero(signal, VHOST_SCSI_MAX_VQ);
674 675
	llnode = llist_del_all(&vs->vs_completion_list);
	while (llnode) {
676
		cmd = llist_entry(llnode, struct tcm_vhost_cmd,
677 678
				     tvc_completion_list);
		llnode = llist_next(llnode);
679
		se_cmd = &cmd->tvc_se_cmd;
680 681

		pr_debug("%s tv_cmd %p resid %u status %#02x\n", __func__,
682
			cmd, se_cmd->residual_count, se_cmd->scsi_status);
683 684 685 686 687 688

		memset(&v_rsp, 0, sizeof(v_rsp));
		v_rsp.resid = se_cmd->residual_count;
		/* TODO is status_qualifier field needed? */
		v_rsp.status = se_cmd->scsi_status;
		v_rsp.sense_len = se_cmd->scsi_sense_length;
689
		memcpy(v_rsp.sense, cmd->tvc_sense_buf,
690
		       v_rsp.sense_len);
691
		ret = copy_to_user(cmd->tvc_resp, &v_rsp, sizeof(v_rsp));
A
Asias He 已提交
692
		if (likely(ret == 0)) {
693
			struct vhost_scsi_virtqueue *q;
694 695
			vhost_add_used(cmd->tvc_vq, cmd->tvc_vq_desc, 0);
			q = container_of(cmd->tvc_vq, struct vhost_scsi_virtqueue, vq);
696
			vq = q - vs->vqs;
A
Asias He 已提交
697 698
			__set_bit(vq, signal);
		} else
699 700
			pr_err("Faulted on virtio_scsi_cmd_resp\n");

701
		vhost_scsi_free_cmd(cmd);
702 703
	}

A
Asias He 已提交
704 705 706
	vq = -1;
	while ((vq = find_next_bit(signal, VHOST_SCSI_MAX_VQ, vq + 1))
		< VHOST_SCSI_MAX_VQ)
707
		vhost_signal(&vs->dev, &vs->vqs[vq].vq);
708 709
}

710
static struct tcm_vhost_cmd *
711
vhost_scsi_get_tag(struct vhost_virtqueue *vq,
712
			struct tcm_vhost_tpg *tpg,
713 714 715
			struct virtio_scsi_cmd_req *v_req,
			u32 exp_data_len,
			int data_direction)
716
{
717
	struct tcm_vhost_cmd *cmd;
718
	struct tcm_vhost_nexus *tv_nexus;
719
	struct se_session *se_sess;
720 721
	struct scatterlist *sg;
	struct page **pages;
722
	int tag;
723

724
	tv_nexus = tpg->tpg_nexus;
725 726 727 728
	if (!tv_nexus) {
		pr_err("Unable to locate active struct tcm_vhost_nexus\n");
		return ERR_PTR(-EIO);
	}
729
	se_sess = tv_nexus->tvn_se_sess;
730

731 732 733 734 735 736
	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, GFP_ATOMIC);
	if (tag < 0) {
		pr_err("Unable to obtain tag for tcm_vhost_cmd\n");
		return ERR_PTR(-ENOMEM);
	}

737
	cmd = &((struct tcm_vhost_cmd *)se_sess->sess_cmd_map)[tag];
738 739
	sg = cmd->tvc_sgl;
	pages = cmd->tvc_upages;
740 741
	memset(cmd, 0, sizeof(struct tcm_vhost_cmd));

742 743
	cmd->tvc_sgl = sg;
	cmd->tvc_upages = pages;
744
	cmd->tvc_se_cmd.map_tag = tag;
745 746 747 748 749 750 751 752
	cmd->tvc_tag = v_req->tag;
	cmd->tvc_task_attr = v_req->task_attr;
	cmd->tvc_exp_data_len = exp_data_len;
	cmd->tvc_data_direction = data_direction;
	cmd->tvc_nexus = tv_nexus;
	cmd->inflight = tcm_vhost_get_inflight(vq);

	return cmd;
753 754 755 756 757 758 759
}

/*
 * Map a user memory range into a scatterlist
 *
 * Returns the number of scatterlist entries used or -errno on error.
 */
760
static int
761 762
vhost_scsi_map_to_sgl(struct tcm_vhost_cmd *tv_cmd,
		      struct scatterlist *sgl,
763 764 765
		      unsigned int sgl_count,
		      struct iovec *iov,
		      int write)
766
{
767
	unsigned int npages = 0, pages_nr, offset, nbytes;
768
	struct scatterlist *sg = sgl;
769 770 771 772
	void __user *ptr = iov->iov_base;
	size_t len = iov->iov_len;
	struct page **pages;
	int ret, i;
773

774 775 776 777 778 779 780
	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;
	}

781 782 783
	pages_nr = iov_num_pages(iov);
	if (pages_nr > sgl_count)
		return -ENOBUFS;
784

785 786 787 788 789 790 791 792
	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;
793

794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809
	ret = get_user_pages_fast((unsigned long)ptr, pages_nr, write, pages);
	/* No pages were pinned */
	if (ret < 0)
		goto out;
	/* Less pages pinned than wanted */
	if (ret != pages_nr) {
		for (i = 0; i < ret; i++)
			put_page(pages[i]);
		ret = -EFAULT;
		goto out;
	}

	while (len > 0) {
		offset = (uintptr_t)ptr & ~PAGE_MASK;
		nbytes = min_t(unsigned int, PAGE_SIZE - offset, len);
		sg_set_page(sg, pages[npages], nbytes, offset);
810 811 812 813 814 815
		ptr += nbytes;
		len -= nbytes;
		sg++;
		npages++;
	}

816
out:
817 818 819
	return ret;
}

820
static int
821
vhost_scsi_map_iov_to_sgl(struct tcm_vhost_cmd *cmd,
822 823 824
			  struct iovec *iov,
			  unsigned int niov,
			  int write)
825 826 827 828 829 830 831 832 833 834
{
	int ret;
	unsigned int i;
	u32 sgl_count;
	struct scatterlist *sg;

	/*
	 * Find out how long sglist needs to be
	 */
	sgl_count = 0;
835 836 837
	for (i = 0; i < niov; i++)
		sgl_count += iov_num_pages(&iov[i]);

838 839
	/* TODO overflow checking */

840 841
	sg = cmd->tvc_sgl;
	pr_debug("%s sg %p sgl_count %u\n", __func__, sg, sgl_count);
842 843
	sg_init_table(sg, sgl_count);

844
	cmd->tvc_sgl_count = sgl_count;
845 846 847

	pr_debug("Mapping %u iovecs for %u pages\n", niov, sgl_count);
	for (i = 0; i < niov; i++) {
848 849
		ret = vhost_scsi_map_to_sgl(cmd, sg, sgl_count, &iov[i],
					    write);
850
		if (ret < 0) {
851 852
			for (i = 0; i < cmd->tvc_sgl_count; i++)
				put_page(sg_page(&cmd->tvc_sgl[i]));
853

854
			cmd->tvc_sgl_count = 0;
855 856 857 858 859 860 861 862 863 864 865
			return ret;
		}

		sg += ret;
		sgl_count -= ret;
	}
	return 0;
}

static void tcm_vhost_submission_work(struct work_struct *work)
{
866
	struct tcm_vhost_cmd *cmd =
867
		container_of(work, struct tcm_vhost_cmd, work);
868
	struct tcm_vhost_nexus *tv_nexus;
869
	struct se_cmd *se_cmd = &cmd->tvc_se_cmd;
870 871 872
	struct scatterlist *sg_ptr, *sg_bidi_ptr = NULL;
	int rc, sg_no_bidi = 0;

873 874
	if (cmd->tvc_sgl_count) {
		sg_ptr = cmd->tvc_sgl;
875 876 877 878 879 880 881 882 883 884
/* FIXME: Fix BIDI operation in tcm_vhost_submission_work() */
#if 0
		if (se_cmd->se_cmd_flags & SCF_BIDI) {
			sg_bidi_ptr = NULL;
			sg_no_bidi = 0;
		}
#endif
	} else {
		sg_ptr = NULL;
	}
885
	tv_nexus = cmd->tvc_nexus;
886 887

	rc = target_submit_cmd_map_sgls(se_cmd, tv_nexus->tvn_se_sess,
888 889 890
			cmd->tvc_cdb, &cmd->tvc_sense_buf[0],
			cmd->tvc_lun, cmd->tvc_exp_data_len,
			cmd->tvc_task_attr, cmd->tvc_data_direction,
891
			TARGET_SCF_ACK_KREF, sg_ptr, cmd->tvc_sgl_count,
892
			sg_bidi_ptr, sg_no_bidi);
893 894
	if (rc < 0) {
		transport_send_check_condition_and_sense(se_cmd,
895
				TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE, 0);
896 897 898 899
		transport_generic_free_cmd(se_cmd, 0);
	}
}

900 901 902 903
static void
vhost_scsi_send_bad_target(struct vhost_scsi *vs,
			   struct vhost_virtqueue *vq,
			   int head, unsigned out)
904 905 906 907 908 909 910 911 912 913 914 915 916 917 918
{
	struct virtio_scsi_cmd_resp __user *resp;
	struct virtio_scsi_cmd_resp rsp;
	int ret;

	memset(&rsp, 0, sizeof(rsp));
	rsp.response = VIRTIO_SCSI_S_BAD_TARGET;
	resp = vq->iov[out].iov_base;
	ret = __copy_to_user(resp, &rsp, sizeof(rsp));
	if (!ret)
		vhost_add_used_and_signal(&vs->dev, vq, head, 0);
	else
		pr_err("Faulted on virtio_scsi_cmd_resp\n");
}

919 920
static void
vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
921
{
922
	struct tcm_vhost_tpg **vs_tpg;
923
	struct virtio_scsi_cmd_req v_req;
924
	struct tcm_vhost_tpg *tpg;
925
	struct tcm_vhost_cmd *cmd;
926 927 928
	u32 exp_data_len, data_first, data_num, data_direction;
	unsigned out, in, i;
	int head, ret;
A
Asias He 已提交
929
	u8 target;
930

931
	mutex_lock(&vq->mutex);
932 933 934 935
	/*
	 * We can handle the vq only after the endpoint is setup by calling the
	 * VHOST_SCSI_SET_ENDPOINT ioctl.
	 */
936
	vs_tpg = vq->private_data;
937
	if (!vs_tpg)
938
		goto out;
939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003

	vhost_disable_notify(&vs->dev, vq);

	for (;;) {
		head = vhost_get_vq_desc(&vs->dev, vq, vq->iov,
					ARRAY_SIZE(vq->iov), &out, &in,
					NULL, NULL);
		pr_debug("vhost_get_vq_desc: head: %d, out: %u in: %u\n",
					head, out, in);
		/* On error, stop handling until the next kick. */
		if (unlikely(head < 0))
			break;
		/* Nothing new?  Wait for eventfd to tell us they refilled. */
		if (head == vq->num) {
			if (unlikely(vhost_enable_notify(&vs->dev, vq))) {
				vhost_disable_notify(&vs->dev, vq);
				continue;
			}
			break;
		}

/* FIXME: BIDI operation */
		if (out == 1 && in == 1) {
			data_direction = DMA_NONE;
			data_first = 0;
			data_num = 0;
		} else if (out == 1 && in > 1) {
			data_direction = DMA_FROM_DEVICE;
			data_first = out + 1;
			data_num = in - 1;
		} else if (out > 1 && in == 1) {
			data_direction = DMA_TO_DEVICE;
			data_first = 1;
			data_num = out - 1;
		} else {
			vq_err(vq, "Invalid buffer layout out: %u in: %u\n",
					out, in);
			break;
		}

		/*
		 * Check for a sane resp buffer so we can report errors to
		 * the guest.
		 */
		if (unlikely(vq->iov[out].iov_len !=
					sizeof(struct virtio_scsi_cmd_resp))) {
			vq_err(vq, "Expecting virtio_scsi_cmd_resp, got %zu"
				" bytes\n", vq->iov[out].iov_len);
			break;
		}

		if (unlikely(vq->iov[0].iov_len != sizeof(v_req))) {
			vq_err(vq, "Expecting virtio_scsi_cmd_req, got %zu"
				" bytes\n", vq->iov[0].iov_len);
			break;
		}
		pr_debug("Calling __copy_from_user: vq->iov[0].iov_base: %p,"
			" len: %zu\n", vq->iov[0].iov_base, sizeof(v_req));
		ret = __copy_from_user(&v_req, vq->iov[0].iov_base,
				sizeof(v_req));
		if (unlikely(ret)) {
			vq_err(vq, "Faulted on virtio_scsi_cmd_req\n");
			break;
		}

A
Asias He 已提交
1004 1005
		/* Extract the tpgt */
		target = v_req.lun[1];
1006
		tpg = ACCESS_ONCE(vs_tpg[target]);
A
Asias He 已提交
1007 1008

		/* Target does not exist, fail the request */
1009
		if (unlikely(!tpg)) {
1010
			vhost_scsi_send_bad_target(vs, vq, head, out);
A
Asias He 已提交
1011 1012 1013
			continue;
		}

1014 1015 1016 1017
		exp_data_len = 0;
		for (i = 0; i < data_num; i++)
			exp_data_len += vq->iov[data_first + i].iov_len;

1018 1019
		cmd = vhost_scsi_get_tag(vq, tpg, &v_req,
					 exp_data_len, data_direction);
1020
		if (IS_ERR(cmd)) {
1021
			vq_err(vq, "vhost_scsi_get_tag failed %ld\n",
1022
					PTR_ERR(cmd));
1023
			goto err_cmd;
1024 1025
		}
		pr_debug("Allocated tv_cmd: %p exp_data_len: %d, data_direction"
1026
			": %d\n", cmd, exp_data_len, data_direction);
1027

1028 1029 1030
		cmd->tvc_vhost = vs;
		cmd->tvc_vq = vq;
		cmd->tvc_resp = vq->iov[out].iov_base;
1031 1032

		/*
1033
		 * Copy in the recieved CDB descriptor into cmd->tvc_cdb
1034 1035 1036
		 * that will be used by tcm_vhost_new_cmd_map() and down into
		 * target_setup_cmd_from_cdb()
		 */
1037
		memcpy(cmd->tvc_cdb, v_req.cdb, TCM_VHOST_MAX_CDB_SIZE);
1038 1039 1040 1041 1042
		/*
		 * Check that the recieved CDB size does not exceeded our
		 * hardcoded max for tcm_vhost
		 */
		/* TODO what if cdb was too small for varlen cdb header? */
1043
		if (unlikely(scsi_command_size(cmd->tvc_cdb) >
1044 1045 1046
					TCM_VHOST_MAX_CDB_SIZE)) {
			vq_err(vq, "Received SCSI CDB with command_size: %d that"
				" exceeds SCSI_MAX_VARLEN_CDB_SIZE: %d\n",
1047
				scsi_command_size(cmd->tvc_cdb),
1048
				TCM_VHOST_MAX_CDB_SIZE);
1049
			goto err_free;
1050
		}
1051
		cmd->tvc_lun = ((v_req.lun[2] << 8) | v_req.lun[3]) & 0x3FFF;
1052 1053

		pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n",
1054
			cmd->tvc_cdb[0], cmd->tvc_lun);
1055 1056

		if (data_direction != DMA_NONE) {
1057
			ret = vhost_scsi_map_iov_to_sgl(cmd,
1058 1059 1060 1061
					&vq->iov[data_first], data_num,
					data_direction == DMA_TO_DEVICE);
			if (unlikely(ret)) {
				vq_err(vq, "Failed to map iov to sgl\n");
1062
				goto err_free;
1063 1064 1065 1066 1067 1068 1069 1070
			}
		}

		/*
		 * Save the descriptor from vhost_get_vq_desc() to be used to
		 * complete the virtio-scsi request in TCM callback context via
		 * tcm_vhost_queue_data_in() and tcm_vhost_queue_status()
		 */
1071
		cmd->tvc_vq_desc = head;
1072 1073 1074 1075 1076 1077
		/*
		 * Dispatch tv_cmd descriptor for cmwq execution in process
		 * context provided by tcm_vhost_workqueue.  This also ensures
		 * tv_cmd is executed on the same kworker CPU as this vhost
		 * thread to gain positive L2 cache locality effects..
		 */
1078 1079
		INIT_WORK(&cmd->work, tcm_vhost_submission_work);
		queue_work(tcm_vhost_workqueue, &cmd->work);
1080 1081 1082
	}

	mutex_unlock(&vq->mutex);
1083 1084
	return;

1085
err_free:
1086
	vhost_scsi_free_cmd(cmd);
1087 1088
err_cmd:
	vhost_scsi_send_bad_target(vs, vq, head, out);
1089
out:
1090
	mutex_unlock(&vq->mutex);
1091 1092 1093 1094
}

static void vhost_scsi_ctl_handle_kick(struct vhost_work *work)
{
1095
	pr_debug("%s: The handling func for control queue.\n", __func__);
1096 1097
}

1098 1099 1100 1101 1102 1103
static void
tcm_vhost_send_evt(struct vhost_scsi *vs,
		   struct tcm_vhost_tpg *tpg,
		   struct se_lun *lun,
		   u32 event,
		   u32 reason)
1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127
{
	struct tcm_vhost_evt *evt;

	evt = tcm_vhost_allocate_evt(vs, event, reason);
	if (!evt)
		return;

	if (tpg && lun) {
		/* TODO: share lun setup code with virtio-scsi.ko */
		/*
		 * Note: evt->event is zeroed when we allocate it and
		 * lun[4-7] need to be zero according to virtio-scsi spec.
		 */
		evt->event.lun[0] = 0x01;
		evt->event.lun[1] = tpg->tport_tpgt & 0xFF;
		if (lun->unpacked_lun >= 256)
			evt->event.lun[2] = lun->unpacked_lun >> 8 | 0x40 ;
		evt->event.lun[3] = lun->unpacked_lun & 0xFF;
	}

	llist_add(&evt->list, &vs->vs_event_list);
	vhost_work_queue(&vs->dev, &vs->vs_event_work);
}

1128 1129
static void vhost_scsi_evt_handle_kick(struct vhost_work *work)
{
1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141
	struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
						poll.work);
	struct vhost_scsi *vs = container_of(vq->dev, struct vhost_scsi, dev);

	mutex_lock(&vq->mutex);
	if (!vq->private_data)
		goto out;

	if (vs->vs_events_missed)
		tcm_vhost_send_evt(vs, NULL, NULL, VIRTIO_SCSI_T_NO_EVENT, 0);
out:
	mutex_unlock(&vq->mutex);
1142 1143 1144 1145 1146 1147 1148 1149
}

static void vhost_scsi_handle_kick(struct vhost_work *work)
{
	struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
						poll.work);
	struct vhost_scsi *vs = container_of(vq->dev, struct vhost_scsi, dev);

A
Asias He 已提交
1150
	vhost_scsi_handle_vq(vs, vq);
1151 1152
}

1153 1154
static void vhost_scsi_flush_vq(struct vhost_scsi *vs, int index)
{
1155
	vhost_poll_flush(&vs->vqs[index].vq.poll);
1156 1157
}

1158
/* Callers must hold dev mutex */
1159 1160
static void vhost_scsi_flush(struct vhost_scsi *vs)
{
1161
	struct vhost_scsi_inflight *old_inflight[VHOST_SCSI_MAX_VQ];
1162 1163
	int i;

1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175
	/* Init new inflight and remember the old inflight */
	tcm_vhost_init_inflight(vs, old_inflight);

	/*
	 * The inflight->kref was initialized to 1. We decrement it here to
	 * indicate the start of the flush operation so that it will reach 0
	 * when all the reqs are finished.
	 */
	for (i = 0; i < VHOST_SCSI_MAX_VQ; i++)
		kref_put(&old_inflight[i]->kref, tcm_vhost_done_inflight);

	/* Flush both the vhost poll and vhost work */
1176 1177 1178
	for (i = 0; i < VHOST_SCSI_MAX_VQ; i++)
		vhost_scsi_flush_vq(vs, i);
	vhost_work_flush(&vs->dev, &vs->vs_completion_work);
1179
	vhost_work_flush(&vs->dev, &vs->vs_event_work);
1180 1181 1182 1183

	/* Wait for all reqs issued before the flush to be finished */
	for (i = 0; i < VHOST_SCSI_MAX_VQ; i++)
		wait_for_completion(&old_inflight[i]->comp);
1184 1185
}

1186 1187 1188
/*
 * Called from vhost_scsi_ioctl() context to walk the list of available
 * tcm_vhost_tpg with an active struct tcm_vhost_nexus
1189 1190 1191
 *
 *  The lock nesting rule is:
 *    tcm_vhost_mutex -> vs->dev.mutex -> tpg->tv_tpg_mutex -> vq->mutex
1192
 */
1193 1194 1195
static int
vhost_scsi_set_endpoint(struct vhost_scsi *vs,
			struct vhost_scsi_target *t)
1196 1197
{
	struct tcm_vhost_tport *tv_tport;
1198
	struct tcm_vhost_tpg *tpg;
1199 1200 1201
	struct tcm_vhost_tpg **vs_tpg;
	struct vhost_virtqueue *vq;
	int index, ret, i, len;
A
Asias He 已提交
1202
	bool match = false;
1203

1204
	mutex_lock(&tcm_vhost_mutex);
1205
	mutex_lock(&vs->dev.mutex);
1206

1207 1208 1209
	/* Verify that ring has been setup correctly. */
	for (index = 0; index < vs->dev.nvqs; ++index) {
		/* Verify that ring has been setup correctly. */
1210
		if (!vhost_vq_access_ok(&vs->vqs[index].vq)) {
1211 1212
			ret = -EFAULT;
			goto out;
1213 1214 1215
		}
	}

1216 1217 1218
	len = sizeof(vs_tpg[0]) * VHOST_SCSI_MAX_TARGET;
	vs_tpg = kzalloc(len, GFP_KERNEL);
	if (!vs_tpg) {
1219 1220
		ret = -ENOMEM;
		goto out;
1221 1222 1223 1224
	}
	if (vs->vs_tpg)
		memcpy(vs_tpg, vs->vs_tpg, len);

1225 1226 1227 1228
	list_for_each_entry(tpg, &tcm_vhost_list, tv_tpg_list) {
		mutex_lock(&tpg->tv_tpg_mutex);
		if (!tpg->tpg_nexus) {
			mutex_unlock(&tpg->tv_tpg_mutex);
1229 1230
			continue;
		}
1231 1232
		if (tpg->tv_tpg_vhost_count != 0) {
			mutex_unlock(&tpg->tv_tpg_mutex);
1233 1234
			continue;
		}
1235
		tv_tport = tpg->tport;
1236

A
Asias He 已提交
1237
		if (!strcmp(tv_tport->tport_name, t->vhost_wwpn)) {
1238
			if (vs->vs_tpg && vs->vs_tpg[tpg->tport_tpgt]) {
1239
				kfree(vs_tpg);
1240
				mutex_unlock(&tpg->tv_tpg_mutex);
1241 1242
				ret = -EEXIST;
				goto out;
1243
			}
1244 1245 1246
			tpg->tv_tpg_vhost_count++;
			tpg->vhost_scsi = vs;
			vs_tpg[tpg->tport_tpgt] = tpg;
1247
			smp_mb__after_atomic_inc();
A
Asias He 已提交
1248
			match = true;
1249
		}
1250
		mutex_unlock(&tpg->tv_tpg_mutex);
1251
	}
A
Asias He 已提交
1252 1253 1254 1255

	if (match) {
		memcpy(vs->vs_vhost_wwpn, t->vhost_wwpn,
		       sizeof(vs->vs_vhost_wwpn));
1256
		for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
1257
			vq = &vs->vqs[i].vq;
1258
			mutex_lock(&vq->mutex);
A
Asias He 已提交
1259
			vq->private_data = vs_tpg;
1260
			vhost_init_used(vq);
1261 1262
			mutex_unlock(&vq->mutex);
		}
A
Asias He 已提交
1263 1264 1265 1266 1267
		ret = 0;
	} else {
		ret = -EEXIST;
	}

1268 1269 1270 1271 1272 1273 1274 1275
	/*
	 * Act as synchronize_rcu to make sure access to
	 * old vs->vs_tpg is finished.
	 */
	vhost_scsi_flush(vs);
	kfree(vs->vs_tpg);
	vs->vs_tpg = vs_tpg;

1276
out:
A
Asias He 已提交
1277
	mutex_unlock(&vs->dev.mutex);
1278
	mutex_unlock(&tcm_vhost_mutex);
A
Asias He 已提交
1279
	return ret;
1280 1281
}

1282 1283 1284
static int
vhost_scsi_clear_endpoint(struct vhost_scsi *vs,
			  struct vhost_scsi_target *t)
1285 1286
{
	struct tcm_vhost_tport *tv_tport;
1287
	struct tcm_vhost_tpg *tpg;
1288 1289
	struct vhost_virtqueue *vq;
	bool match = false;
A
Asias He 已提交
1290 1291
	int index, ret, i;
	u8 target;
1292

1293
	mutex_lock(&tcm_vhost_mutex);
1294 1295 1296
	mutex_lock(&vs->dev.mutex);
	/* Verify that ring has been setup correctly. */
	for (index = 0; index < vs->dev.nvqs; ++index) {
1297
		if (!vhost_vq_access_ok(&vs->vqs[index].vq)) {
1298
			ret = -EFAULT;
1299
			goto err_dev;
1300 1301
		}
	}
1302 1303

	if (!vs->vs_tpg) {
1304 1305
		ret = 0;
		goto err_dev;
1306 1307
	}

A
Asias He 已提交
1308 1309
	for (i = 0; i < VHOST_SCSI_MAX_TARGET; i++) {
		target = i;
1310 1311
		tpg = vs->vs_tpg[target];
		if (!tpg)
A
Asias He 已提交
1312 1313
			continue;

1314 1315
		mutex_lock(&tpg->tv_tpg_mutex);
		tv_tport = tpg->tport;
A
Asias He 已提交
1316 1317
		if (!tv_tport) {
			ret = -ENODEV;
1318
			goto err_tpg;
A
Asias He 已提交
1319 1320 1321
		}

		if (strcmp(tv_tport->tport_name, t->vhost_wwpn)) {
1322
			pr_warn("tv_tport->tport_name: %s, tpg->tport_tpgt: %hu"
A
Asias He 已提交
1323
				" does not match t->vhost_wwpn: %s, t->vhost_tpgt: %hu\n",
1324
				tv_tport->tport_name, tpg->tport_tpgt,
A
Asias He 已提交
1325 1326
				t->vhost_wwpn, t->vhost_tpgt);
			ret = -EINVAL;
1327
			goto err_tpg;
A
Asias He 已提交
1328
		}
1329 1330
		tpg->tv_tpg_vhost_count--;
		tpg->vhost_scsi = NULL;
A
Asias He 已提交
1331
		vs->vs_tpg[target] = NULL;
1332
		match = true;
1333
		mutex_unlock(&tpg->tv_tpg_mutex);
1334
	}
1335 1336
	if (match) {
		for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
1337
			vq = &vs->vqs[i].vq;
1338
			mutex_lock(&vq->mutex);
A
Asias He 已提交
1339
			vq->private_data = NULL;
1340 1341 1342 1343 1344 1345 1346 1347 1348 1349
			mutex_unlock(&vq->mutex);
		}
	}
	/*
	 * Act as synchronize_rcu to make sure access to
	 * old vs->vs_tpg is finished.
	 */
	vhost_scsi_flush(vs);
	kfree(vs->vs_tpg);
	vs->vs_tpg = NULL;
1350
	WARN_ON(vs->vs_events_nr);
1351
	mutex_unlock(&vs->dev.mutex);
1352
	mutex_unlock(&tcm_vhost_mutex);
1353
	return 0;
1354

1355
err_tpg:
1356
	mutex_unlock(&tpg->tv_tpg_mutex);
1357
err_dev:
1358
	mutex_unlock(&vs->dev.mutex);
1359
	mutex_unlock(&tcm_vhost_mutex);
1360
	return ret;
1361 1362
}

1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380
static int vhost_scsi_set_features(struct vhost_scsi *vs, u64 features)
{
	if (features & ~VHOST_SCSI_FEATURES)
		return -EOPNOTSUPP;

	mutex_lock(&vs->dev.mutex);
	if ((features & (1 << VHOST_F_LOG_ALL)) &&
	    !vhost_log_access_ok(&vs->dev)) {
		mutex_unlock(&vs->dev.mutex);
		return -EFAULT;
	}
	vs->dev.acked_features = features;
	smp_wmb();
	vhost_scsi_flush(vs);
	mutex_unlock(&vs->dev.mutex);
	return 0;
}

1381 1382 1383 1384 1385 1386 1387 1388
static void vhost_scsi_free(struct vhost_scsi *vs)
{
	if (is_vmalloc_addr(vs))
		vfree(vs);
	else
		kfree(vs);
}

1389 1390
static int vhost_scsi_open(struct inode *inode, struct file *f)
{
1391
	struct vhost_scsi *vs;
1392
	struct vhost_virtqueue **vqs;
1393
	int r = -ENOMEM, i;
1394

1395 1396 1397 1398 1399 1400
	vs = kzalloc(sizeof(*vs), GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
	if (!vs) {
		vs = vzalloc(sizeof(*vs));
		if (!vs)
			goto err_vs;
	}
1401

1402
	vqs = kmalloc(VHOST_SCSI_MAX_VQ * sizeof(*vqs), GFP_KERNEL);
1403 1404
	if (!vqs)
		goto err_vqs;
1405

1406 1407
	vhost_work_init(&vs->vs_completion_work, vhost_scsi_complete_cmd_work);
	vhost_work_init(&vs->vs_event_work, tcm_vhost_evt_work);
1408

1409 1410
	vs->vs_events_nr = 0;
	vs->vs_events_missed = false;
1411

1412 1413 1414 1415
	vqs[VHOST_SCSI_VQ_CTL] = &vs->vqs[VHOST_SCSI_VQ_CTL].vq;
	vqs[VHOST_SCSI_VQ_EVT] = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
	vs->vqs[VHOST_SCSI_VQ_CTL].vq.handle_kick = vhost_scsi_ctl_handle_kick;
	vs->vqs[VHOST_SCSI_VQ_EVT].vq.handle_kick = vhost_scsi_evt_handle_kick;
1416
	for (i = VHOST_SCSI_VQ_IO; i < VHOST_SCSI_MAX_VQ; i++) {
1417 1418
		vqs[i] = &vs->vqs[i].vq;
		vs->vqs[i].vq.handle_kick = vhost_scsi_handle_kick;
1419
	}
1420
	r = vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ);
1421

1422
	tcm_vhost_init_inflight(vs, NULL);
1423

1424 1425
	if (r < 0)
		goto err_init;
1426

1427
	f->private_data = vs;
1428
	return 0;
1429 1430 1431 1432 1433 1434 1435

err_init:
	kfree(vqs);
err_vqs:
	vhost_scsi_free(vs);
err_vs:
	return r;
1436 1437 1438 1439
}

static int vhost_scsi_release(struct inode *inode, struct file *f)
{
1440
	struct vhost_scsi *vs = f->private_data;
A
Asias He 已提交
1441
	struct vhost_scsi_target t;
1442

1443 1444 1445 1446 1447 1448
	mutex_lock(&vs->dev.mutex);
	memcpy(t.vhost_wwpn, vs->vs_vhost_wwpn, sizeof(t.vhost_wwpn));
	mutex_unlock(&vs->dev.mutex);
	vhost_scsi_clear_endpoint(vs, &t);
	vhost_dev_stop(&vs->dev);
	vhost_dev_cleanup(&vs->dev, false);
1449
	/* Jobs can re-queue themselves in evt kick handler. Do extra flush. */
1450 1451
	vhost_scsi_flush(vs);
	kfree(vs->dev.vqs);
1452
	vhost_scsi_free(vs);
1453 1454 1455
	return 0;
}

1456 1457 1458 1459
static long
vhost_scsi_ioctl(struct file *f,
		 unsigned int ioctl,
		 unsigned long arg)
1460 1461 1462 1463 1464
{
	struct vhost_scsi *vs = f->private_data;
	struct vhost_scsi_target backend;
	void __user *argp = (void __user *)arg;
	u64 __user *featurep = argp;
1465 1466
	u32 __user *eventsp = argp;
	u32 events_missed;
1467
	u64 features;
1468
	int r, abi_version = VHOST_SCSI_ABI_VERSION;
1469
	struct vhost_virtqueue *vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
1470 1471 1472 1473 1474

	switch (ioctl) {
	case VHOST_SCSI_SET_ENDPOINT:
		if (copy_from_user(&backend, argp, sizeof backend))
			return -EFAULT;
1475 1476
		if (backend.reserved != 0)
			return -EOPNOTSUPP;
1477 1478 1479 1480 1481

		return vhost_scsi_set_endpoint(vs, &backend);
	case VHOST_SCSI_CLEAR_ENDPOINT:
		if (copy_from_user(&backend, argp, sizeof backend))
			return -EFAULT;
1482 1483
		if (backend.reserved != 0)
			return -EOPNOTSUPP;
1484 1485 1486

		return vhost_scsi_clear_endpoint(vs, &backend);
	case VHOST_SCSI_GET_ABI_VERSION:
1487
		if (copy_to_user(argp, &abi_version, sizeof abi_version))
1488 1489
			return -EFAULT;
		return 0;
1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503
	case VHOST_SCSI_SET_EVENTS_MISSED:
		if (get_user(events_missed, eventsp))
			return -EFAULT;
		mutex_lock(&vq->mutex);
		vs->vs_events_missed = events_missed;
		mutex_unlock(&vq->mutex);
		return 0;
	case VHOST_SCSI_GET_EVENTS_MISSED:
		mutex_lock(&vq->mutex);
		events_missed = vs->vs_events_missed;
		mutex_unlock(&vq->mutex);
		if (put_user(events_missed, eventsp))
			return -EFAULT;
		return 0;
1504
	case VHOST_GET_FEATURES:
1505
		features = VHOST_SCSI_FEATURES;
1506 1507 1508 1509 1510 1511 1512 1513 1514
		if (copy_to_user(featurep, &features, sizeof features))
			return -EFAULT;
		return 0;
	case VHOST_SET_FEATURES:
		if (copy_from_user(&features, featurep, sizeof features))
			return -EFAULT;
		return vhost_scsi_set_features(vs, features);
	default:
		mutex_lock(&vs->dev.mutex);
1515 1516 1517 1518
		r = vhost_dev_ioctl(&vs->dev, ioctl, argp);
		/* TODO: flush backend after dev ioctl. */
		if (r == -ENOIOCTLCMD)
			r = vhost_vring_ioctl(&vs->dev, ioctl, argp);
1519 1520 1521 1522 1523
		mutex_unlock(&vs->dev.mutex);
		return r;
	}
}

1524 1525 1526 1527 1528 1529 1530 1531
#ifdef CONFIG_COMPAT
static long vhost_scsi_compat_ioctl(struct file *f, unsigned int ioctl,
				unsigned long arg)
{
	return vhost_scsi_ioctl(f, ioctl, (unsigned long)compat_ptr(arg));
}
#endif

1532 1533 1534 1535
static const struct file_operations vhost_scsi_fops = {
	.owner          = THIS_MODULE,
	.release        = vhost_scsi_release,
	.unlocked_ioctl = vhost_scsi_ioctl,
1536 1537 1538
#ifdef CONFIG_COMPAT
	.compat_ioctl	= vhost_scsi_compat_ioctl,
#endif
1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574
	.open           = vhost_scsi_open,
	.llseek		= noop_llseek,
};

static struct miscdevice vhost_scsi_misc = {
	MISC_DYNAMIC_MINOR,
	"vhost-scsi",
	&vhost_scsi_fops,
};

static int __init vhost_scsi_register(void)
{
	return misc_register(&vhost_scsi_misc);
}

static int vhost_scsi_deregister(void)
{
	return misc_deregister(&vhost_scsi_misc);
}

static char *tcm_vhost_dump_proto_id(struct tcm_vhost_tport *tport)
{
	switch (tport->tport_proto_id) {
	case SCSI_PROTOCOL_SAS:
		return "SAS";
	case SCSI_PROTOCOL_FCP:
		return "FCP";
	case SCSI_PROTOCOL_ISCSI:
		return "iSCSI";
	default:
		break;
	}

	return "Unknown";
}

1575 1576 1577
static void
tcm_vhost_do_plug(struct tcm_vhost_tpg *tpg,
		  struct se_lun *lun, bool plug)
1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597
{

	struct vhost_scsi *vs = tpg->vhost_scsi;
	struct vhost_virtqueue *vq;
	u32 reason;

	if (!vs)
		return;

	mutex_lock(&vs->dev.mutex);
	if (!vhost_has_feature(&vs->dev, VIRTIO_SCSI_F_HOTPLUG)) {
		mutex_unlock(&vs->dev.mutex);
		return;
	}

	if (plug)
		reason = VIRTIO_SCSI_EVT_RESET_RESCAN;
	else
		reason = VIRTIO_SCSI_EVT_RESET_REMOVED;

1598
	vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615
	mutex_lock(&vq->mutex);
	tcm_vhost_send_evt(vs, tpg, lun,
			VIRTIO_SCSI_T_TRANSPORT_RESET, reason);
	mutex_unlock(&vq->mutex);
	mutex_unlock(&vs->dev.mutex);
}

static void tcm_vhost_hotplug(struct tcm_vhost_tpg *tpg, struct se_lun *lun)
{
	tcm_vhost_do_plug(tpg, lun, true);
}

static void tcm_vhost_hotunplug(struct tcm_vhost_tpg *tpg, struct se_lun *lun)
{
	tcm_vhost_do_plug(tpg, lun, false);
}

1616
static int tcm_vhost_port_link(struct se_portal_group *se_tpg,
1617
			       struct se_lun *lun)
1618
{
1619
	struct tcm_vhost_tpg *tpg = container_of(se_tpg,
1620 1621
				struct tcm_vhost_tpg, se_tpg);

1622 1623
	mutex_lock(&tcm_vhost_mutex);

1624 1625 1626
	mutex_lock(&tpg->tv_tpg_mutex);
	tpg->tv_tpg_port_count++;
	mutex_unlock(&tpg->tv_tpg_mutex);
1627

1628
	tcm_vhost_hotplug(tpg, lun);
1629 1630 1631

	mutex_unlock(&tcm_vhost_mutex);

1632 1633 1634
	return 0;
}

1635
static void tcm_vhost_port_unlink(struct se_portal_group *se_tpg,
1636
				  struct se_lun *lun)
1637
{
1638
	struct tcm_vhost_tpg *tpg = container_of(se_tpg,
1639 1640
				struct tcm_vhost_tpg, se_tpg);

1641 1642
	mutex_lock(&tcm_vhost_mutex);

1643 1644 1645
	mutex_lock(&tpg->tv_tpg_mutex);
	tpg->tv_tpg_port_count--;
	mutex_unlock(&tpg->tv_tpg_mutex);
1646

1647
	tcm_vhost_hotunplug(tpg, lun);
1648 1649

	mutex_unlock(&tcm_vhost_mutex);
1650 1651
}

1652 1653 1654 1655
static struct se_node_acl *
tcm_vhost_make_nodeacl(struct se_portal_group *se_tpg,
		       struct config_group *group,
		       const char *name)
1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695
{
	struct se_node_acl *se_nacl, *se_nacl_new;
	struct tcm_vhost_nacl *nacl;
	u64 wwpn = 0;
	u32 nexus_depth;

	/* tcm_vhost_parse_wwn(name, &wwpn, 1) < 0)
		return ERR_PTR(-EINVAL); */
	se_nacl_new = tcm_vhost_alloc_fabric_acl(se_tpg);
	if (!se_nacl_new)
		return ERR_PTR(-ENOMEM);

	nexus_depth = 1;
	/*
	 * se_nacl_new may be released by core_tpg_add_initiator_node_acl()
	 * when converting a NodeACL from demo mode -> explict
	 */
	se_nacl = core_tpg_add_initiator_node_acl(se_tpg, se_nacl_new,
				name, nexus_depth);
	if (IS_ERR(se_nacl)) {
		tcm_vhost_release_fabric_acl(se_tpg, se_nacl_new);
		return se_nacl;
	}
	/*
	 * Locate our struct tcm_vhost_nacl and set the FC Nport WWPN
	 */
	nacl = container_of(se_nacl, struct tcm_vhost_nacl, se_node_acl);
	nacl->iport_wwpn = wwpn;

	return se_nacl;
}

static void tcm_vhost_drop_nodeacl(struct se_node_acl *se_acl)
{
	struct tcm_vhost_nacl *nacl = container_of(se_acl,
				struct tcm_vhost_nacl, se_node_acl);
	core_tpg_del_initiator_node_acl(se_acl->se_tpg, se_acl, 1);
	kfree(nacl);
}

1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712
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);
	}
}

1713
static int tcm_vhost_make_nexus(struct tcm_vhost_tpg *tpg,
1714
				const char *name)
1715 1716
{
	struct se_portal_group *se_tpg;
1717
	struct se_session *se_sess;
1718
	struct tcm_vhost_nexus *tv_nexus;
1719 1720
	struct tcm_vhost_cmd *tv_cmd;
	unsigned int i;
1721

1722 1723 1724 1725
	mutex_lock(&tpg->tv_tpg_mutex);
	if (tpg->tpg_nexus) {
		mutex_unlock(&tpg->tv_tpg_mutex);
		pr_debug("tpg->tpg_nexus already exists\n");
1726 1727
		return -EEXIST;
	}
1728
	se_tpg = &tpg->se_tpg;
1729 1730 1731

	tv_nexus = kzalloc(sizeof(struct tcm_vhost_nexus), GFP_KERNEL);
	if (!tv_nexus) {
1732
		mutex_unlock(&tpg->tv_tpg_mutex);
1733 1734 1735 1736
		pr_err("Unable to allocate struct tcm_vhost_nexus\n");
		return -ENOMEM;
	}
	/*
1737 1738
	 *  Initialize the struct se_session pointer and setup tagpool
	 *  for struct tcm_vhost_cmd descriptors
1739
	 */
1740 1741 1742
	tv_nexus->tvn_se_sess = transport_init_session_tags(
					TCM_VHOST_DEFAULT_TAGS,
					sizeof(struct tcm_vhost_cmd));
1743
	if (IS_ERR(tv_nexus->tvn_se_sess)) {
1744
		mutex_unlock(&tpg->tv_tpg_mutex);
1745 1746 1747
		kfree(tv_nexus);
		return -ENOMEM;
	}
1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767
	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;
		}
	}
1768 1769 1770 1771 1772 1773 1774 1775
	/*
	 * 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
	 * the SCSI Initiator port name of the passed configfs group 'name'.
	 */
	tv_nexus->tvn_se_sess->se_node_acl = core_tpg_check_initiator_node_acl(
				se_tpg, (unsigned char *)name);
	if (!tv_nexus->tvn_se_sess->se_node_acl) {
1776
		mutex_unlock(&tpg->tv_tpg_mutex);
1777 1778
		pr_debug("core_tpg_check_initiator_node_acl() failed"
				" for %s\n", name);
1779
		goto out;
1780 1781
	}
	/*
1782
	 * Now register the TCM vhost virtual I_T Nexus as active with the
1783 1784 1785 1786
	 * call to __transport_register_session()
	 */
	__transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl,
			tv_nexus->tvn_se_sess, tv_nexus);
1787
	tpg->tpg_nexus = tv_nexus;
1788

1789
	mutex_unlock(&tpg->tv_tpg_mutex);
1790
	return 0;
1791 1792 1793 1794 1795 1796

out:
	tcm_vhost_free_cmd_map_res(tv_nexus, se_sess);
	transport_free_session(se_sess);
	kfree(tv_nexus);
	return -ENOMEM;
1797 1798
}

1799
static int tcm_vhost_drop_nexus(struct tcm_vhost_tpg *tpg)
1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816
{
	struct se_session *se_sess;
	struct tcm_vhost_nexus *tv_nexus;

	mutex_lock(&tpg->tv_tpg_mutex);
	tv_nexus = tpg->tpg_nexus;
	if (!tv_nexus) {
		mutex_unlock(&tpg->tv_tpg_mutex);
		return -ENODEV;
	}

	se_sess = tv_nexus->tvn_se_sess;
	if (!se_sess) {
		mutex_unlock(&tpg->tv_tpg_mutex);
		return -ENODEV;
	}

1817
	if (tpg->tv_tpg_port_count != 0) {
1818
		mutex_unlock(&tpg->tv_tpg_mutex);
1819
		pr_err("Unable to remove TCM_vhost I_T Nexus with"
1820
			" active TPG port count: %d\n",
1821 1822
			tpg->tv_tpg_port_count);
		return -EBUSY;
1823 1824
	}

1825
	if (tpg->tv_tpg_vhost_count != 0) {
1826
		mutex_unlock(&tpg->tv_tpg_mutex);
1827
		pr_err("Unable to remove TCM_vhost I_T Nexus with"
1828
			" active TPG vhost count: %d\n",
1829 1830
			tpg->tv_tpg_vhost_count);
		return -EBUSY;
1831 1832
	}

1833
	pr_debug("TCM_vhost_ConfigFS: Removing I_T Nexus to emulated"
1834 1835
		" %s Initiator Port: %s\n", tcm_vhost_dump_proto_id(tpg->tport),
		tv_nexus->tvn_se_sess->se_node_acl->initiatorname);
1836 1837

	tcm_vhost_free_cmd_map_res(tv_nexus, se_sess);
1838
	/*
1839
	 * Release the SCSI I_T Nexus to the emulated vhost Target Port
1840 1841 1842 1843 1844 1845 1846 1847 1848
	 */
	transport_deregister_session(tv_nexus->tvn_se_sess);
	tpg->tpg_nexus = NULL;
	mutex_unlock(&tpg->tv_tpg_mutex);

	kfree(tv_nexus);
	return 0;
}

1849
static ssize_t tcm_vhost_tpg_show_nexus(struct se_portal_group *se_tpg,
1850
					char *page)
1851
{
1852
	struct tcm_vhost_tpg *tpg = container_of(se_tpg,
1853 1854 1855 1856
				struct tcm_vhost_tpg, se_tpg);
	struct tcm_vhost_nexus *tv_nexus;
	ssize_t ret;

1857 1858
	mutex_lock(&tpg->tv_tpg_mutex);
	tv_nexus = tpg->tpg_nexus;
1859
	if (!tv_nexus) {
1860
		mutex_unlock(&tpg->tv_tpg_mutex);
1861 1862 1863 1864
		return -ENODEV;
	}
	ret = snprintf(page, PAGE_SIZE, "%s\n",
			tv_nexus->tvn_se_sess->se_node_acl->initiatorname);
1865
	mutex_unlock(&tpg->tv_tpg_mutex);
1866 1867 1868 1869

	return ret;
}

1870
static ssize_t tcm_vhost_tpg_store_nexus(struct se_portal_group *se_tpg,
1871 1872
					 const char *page,
					 size_t count)
1873
{
1874
	struct tcm_vhost_tpg *tpg = container_of(se_tpg,
1875
				struct tcm_vhost_tpg, se_tpg);
1876
	struct tcm_vhost_tport *tport_wwn = tpg->tport;
1877 1878 1879 1880 1881 1882
	unsigned char i_port[TCM_VHOST_NAMELEN], *ptr, *port_ptr;
	int ret;
	/*
	 * Shutdown the active I_T nexus if 'NULL' is passed..
	 */
	if (!strncmp(page, "NULL", 4)) {
1883
		ret = tcm_vhost_drop_nexus(tpg);
1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940
		return (!ret) ? count : ret;
	}
	/*
	 * Otherwise make sure the passed virtual Initiator port WWN matches
	 * the fabric protocol_id set in tcm_vhost_make_tport(), and call
	 * tcm_vhost_make_nexus().
	 */
	if (strlen(page) >= TCM_VHOST_NAMELEN) {
		pr_err("Emulated NAA Sas Address: %s, exceeds"
				" max: %d\n", page, TCM_VHOST_NAMELEN);
		return -EINVAL;
	}
	snprintf(&i_port[0], TCM_VHOST_NAMELEN, "%s", page);

	ptr = strstr(i_port, "naa.");
	if (ptr) {
		if (tport_wwn->tport_proto_id != SCSI_PROTOCOL_SAS) {
			pr_err("Passed SAS Initiator Port %s does not"
				" match target port protoid: %s\n", i_port,
				tcm_vhost_dump_proto_id(tport_wwn));
			return -EINVAL;
		}
		port_ptr = &i_port[0];
		goto check_newline;
	}
	ptr = strstr(i_port, "fc.");
	if (ptr) {
		if (tport_wwn->tport_proto_id != SCSI_PROTOCOL_FCP) {
			pr_err("Passed FCP Initiator Port %s does not"
				" match target port protoid: %s\n", i_port,
				tcm_vhost_dump_proto_id(tport_wwn));
			return -EINVAL;
		}
		port_ptr = &i_port[3]; /* Skip over "fc." */
		goto check_newline;
	}
	ptr = strstr(i_port, "iqn.");
	if (ptr) {
		if (tport_wwn->tport_proto_id != SCSI_PROTOCOL_ISCSI) {
			pr_err("Passed iSCSI Initiator Port %s does not"
				" match target port protoid: %s\n", i_port,
				tcm_vhost_dump_proto_id(tport_wwn));
			return -EINVAL;
		}
		port_ptr = &i_port[0];
		goto check_newline;
	}
	pr_err("Unable to locate prefix for emulated Initiator Port:"
			" %s\n", i_port);
	return -EINVAL;
	/*
	 * Clear any trailing newline for the NAA WWN
	 */
check_newline:
	if (i_port[strlen(i_port)-1] == '\n')
		i_port[strlen(i_port)-1] = '\0';

1941
	ret = tcm_vhost_make_nexus(tpg, port_ptr);
1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954
	if (ret < 0)
		return ret;

	return count;
}

TF_TPG_BASE_ATTR(tcm_vhost, nexus, S_IRUGO | S_IWUSR);

static struct configfs_attribute *tcm_vhost_tpg_attrs[] = {
	&tcm_vhost_tpg_nexus.attr,
	NULL,
};

1955 1956 1957 1958
static struct se_portal_group *
tcm_vhost_make_tpg(struct se_wwn *wwn,
		   struct config_group *group,
		   const char *name)
1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003
{
	struct tcm_vhost_tport *tport = container_of(wwn,
			struct tcm_vhost_tport, tport_wwn);

	struct tcm_vhost_tpg *tpg;
	unsigned long tpgt;
	int ret;

	if (strstr(name, "tpgt_") != name)
		return ERR_PTR(-EINVAL);
	if (kstrtoul(name + 5, 10, &tpgt) || tpgt > UINT_MAX)
		return ERR_PTR(-EINVAL);

	tpg = kzalloc(sizeof(struct tcm_vhost_tpg), GFP_KERNEL);
	if (!tpg) {
		pr_err("Unable to allocate struct tcm_vhost_tpg");
		return ERR_PTR(-ENOMEM);
	}
	mutex_init(&tpg->tv_tpg_mutex);
	INIT_LIST_HEAD(&tpg->tv_tpg_list);
	tpg->tport = tport;
	tpg->tport_tpgt = tpgt;

	ret = core_tpg_register(&tcm_vhost_fabric_configfs->tf_ops, wwn,
				&tpg->se_tpg, tpg, TRANSPORT_TPG_TYPE_NORMAL);
	if (ret < 0) {
		kfree(tpg);
		return NULL;
	}
	mutex_lock(&tcm_vhost_mutex);
	list_add_tail(&tpg->tv_tpg_list, &tcm_vhost_list);
	mutex_unlock(&tcm_vhost_mutex);

	return &tpg->se_tpg;
}

static void tcm_vhost_drop_tpg(struct se_portal_group *se_tpg)
{
	struct tcm_vhost_tpg *tpg = container_of(se_tpg,
				struct tcm_vhost_tpg, se_tpg);

	mutex_lock(&tcm_vhost_mutex);
	list_del(&tpg->tv_tpg_list);
	mutex_unlock(&tcm_vhost_mutex);
	/*
2004
	 * Release the virtual I_T Nexus for this vhost TPG
2005 2006 2007 2008 2009 2010 2011 2012 2013
	 */
	tcm_vhost_drop_nexus(tpg);
	/*
	 * Deregister the se_tpg from TCM..
	 */
	core_tpg_deregister(se_tpg);
	kfree(tpg);
}

2014 2015 2016 2017
static struct se_wwn *
tcm_vhost_make_tport(struct target_fabric_configfs *tf,
		     struct config_group *group,
		     const char *name)
2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086
{
	struct tcm_vhost_tport *tport;
	char *ptr;
	u64 wwpn = 0;
	int off = 0;

	/* if (tcm_vhost_parse_wwn(name, &wwpn, 1) < 0)
		return ERR_PTR(-EINVAL); */

	tport = kzalloc(sizeof(struct tcm_vhost_tport), GFP_KERNEL);
	if (!tport) {
		pr_err("Unable to allocate struct tcm_vhost_tport");
		return ERR_PTR(-ENOMEM);
	}
	tport->tport_wwpn = wwpn;
	/*
	 * Determine the emulated Protocol Identifier and Target Port Name
	 * based on the incoming configfs directory name.
	 */
	ptr = strstr(name, "naa.");
	if (ptr) {
		tport->tport_proto_id = SCSI_PROTOCOL_SAS;
		goto check_len;
	}
	ptr = strstr(name, "fc.");
	if (ptr) {
		tport->tport_proto_id = SCSI_PROTOCOL_FCP;
		off = 3; /* Skip over "fc." */
		goto check_len;
	}
	ptr = strstr(name, "iqn.");
	if (ptr) {
		tport->tport_proto_id = SCSI_PROTOCOL_ISCSI;
		goto check_len;
	}

	pr_err("Unable to locate prefix for emulated Target Port:"
			" %s\n", name);
	kfree(tport);
	return ERR_PTR(-EINVAL);

check_len:
	if (strlen(name) >= TCM_VHOST_NAMELEN) {
		pr_err("Emulated %s Address: %s, exceeds"
			" max: %d\n", name, tcm_vhost_dump_proto_id(tport),
			TCM_VHOST_NAMELEN);
		kfree(tport);
		return ERR_PTR(-EINVAL);
	}
	snprintf(&tport->tport_name[0], TCM_VHOST_NAMELEN, "%s", &name[off]);

	pr_debug("TCM_VHost_ConfigFS: Allocated emulated Target"
		" %s Address: %s\n", tcm_vhost_dump_proto_id(tport), name);

	return &tport->tport_wwn;
}

static void tcm_vhost_drop_tport(struct se_wwn *wwn)
{
	struct tcm_vhost_tport *tport = container_of(wwn,
				struct tcm_vhost_tport, tport_wwn);

	pr_debug("TCM_VHost_ConfigFS: Deallocating emulated Target"
		" %s Address: %s\n", tcm_vhost_dump_proto_id(tport),
		tport->tport_name);

	kfree(tport);
}

2087 2088 2089
static ssize_t
tcm_vhost_wwn_show_attr_version(struct target_fabric_configfs *tf,
				char *page)
2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119
{
	return sprintf(page, "TCM_VHOST fabric module %s on %s/%s"
		"on "UTS_RELEASE"\n", TCM_VHOST_VERSION, utsname()->sysname,
		utsname()->machine);
}

TF_WWN_ATTR_RO(tcm_vhost, version);

static struct configfs_attribute *tcm_vhost_wwn_attrs[] = {
	&tcm_vhost_wwn_version.attr,
	NULL,
};

static struct target_core_fabric_ops tcm_vhost_ops = {
	.get_fabric_name		= tcm_vhost_get_fabric_name,
	.get_fabric_proto_ident		= tcm_vhost_get_fabric_proto_ident,
	.tpg_get_wwn			= tcm_vhost_get_fabric_wwn,
	.tpg_get_tag			= tcm_vhost_get_tag,
	.tpg_get_default_depth		= tcm_vhost_get_default_depth,
	.tpg_get_pr_transport_id	= tcm_vhost_get_pr_transport_id,
	.tpg_get_pr_transport_id_len	= tcm_vhost_get_pr_transport_id_len,
	.tpg_parse_pr_out_transport_id	= tcm_vhost_parse_pr_out_transport_id,
	.tpg_check_demo_mode		= tcm_vhost_check_true,
	.tpg_check_demo_mode_cache	= tcm_vhost_check_true,
	.tpg_check_demo_mode_write_protect = tcm_vhost_check_false,
	.tpg_check_prod_mode_write_protect = tcm_vhost_check_false,
	.tpg_alloc_fabric_acl		= tcm_vhost_alloc_fabric_acl,
	.tpg_release_fabric_acl		= tcm_vhost_release_fabric_acl,
	.tpg_get_inst_index		= tcm_vhost_tpg_get_inst_index,
	.release_cmd			= tcm_vhost_release_cmd,
2120
	.check_stop_free		= vhost_scsi_check_stop_free,
2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209
	.shutdown_session		= tcm_vhost_shutdown_session,
	.close_session			= tcm_vhost_close_session,
	.sess_get_index			= tcm_vhost_sess_get_index,
	.sess_get_initiator_sid		= NULL,
	.write_pending			= tcm_vhost_write_pending,
	.write_pending_status		= tcm_vhost_write_pending_status,
	.set_default_node_attributes	= tcm_vhost_set_default_node_attrs,
	.get_task_tag			= tcm_vhost_get_task_tag,
	.get_cmd_state			= tcm_vhost_get_cmd_state,
	.queue_data_in			= tcm_vhost_queue_data_in,
	.queue_status			= tcm_vhost_queue_status,
	.queue_tm_rsp			= tcm_vhost_queue_tm_rsp,
	/*
	 * Setup callers for generic logic in target_core_fabric_configfs.c
	 */
	.fabric_make_wwn		= tcm_vhost_make_tport,
	.fabric_drop_wwn		= tcm_vhost_drop_tport,
	.fabric_make_tpg		= tcm_vhost_make_tpg,
	.fabric_drop_tpg		= tcm_vhost_drop_tpg,
	.fabric_post_link		= tcm_vhost_port_link,
	.fabric_pre_unlink		= tcm_vhost_port_unlink,
	.fabric_make_np			= NULL,
	.fabric_drop_np			= NULL,
	.fabric_make_nodeacl		= tcm_vhost_make_nodeacl,
	.fabric_drop_nodeacl		= tcm_vhost_drop_nodeacl,
};

static int tcm_vhost_register_configfs(void)
{
	struct target_fabric_configfs *fabric;
	int ret;

	pr_debug("TCM_VHOST fabric module %s on %s/%s"
		" on "UTS_RELEASE"\n", TCM_VHOST_VERSION, utsname()->sysname,
		utsname()->machine);
	/*
	 * Register the top level struct config_item_type with TCM core
	 */
	fabric = target_fabric_configfs_init(THIS_MODULE, "vhost");
	if (IS_ERR(fabric)) {
		pr_err("target_fabric_configfs_init() failed\n");
		return PTR_ERR(fabric);
	}
	/*
	 * Setup fabric->tf_ops from our local tcm_vhost_ops
	 */
	fabric->tf_ops = tcm_vhost_ops;
	/*
	 * Setup default attribute lists for various fabric->tf_cit_tmpl
	 */
	TF_CIT_TMPL(fabric)->tfc_wwn_cit.ct_attrs = tcm_vhost_wwn_attrs;
	TF_CIT_TMPL(fabric)->tfc_tpg_base_cit.ct_attrs = tcm_vhost_tpg_attrs;
	TF_CIT_TMPL(fabric)->tfc_tpg_attrib_cit.ct_attrs = NULL;
	TF_CIT_TMPL(fabric)->tfc_tpg_param_cit.ct_attrs = NULL;
	TF_CIT_TMPL(fabric)->tfc_tpg_np_base_cit.ct_attrs = NULL;
	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_base_cit.ct_attrs = NULL;
	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_param_cit.ct_attrs = NULL;
	/*
	 * Register the fabric for use within TCM
	 */
	ret = target_fabric_configfs_register(fabric);
	if (ret < 0) {
		pr_err("target_fabric_configfs_register() failed"
				" for TCM_VHOST\n");
		return ret;
	}
	/*
	 * Setup our local pointer to *fabric
	 */
	tcm_vhost_fabric_configfs = fabric;
	pr_debug("TCM_VHOST[0] - Set fabric -> tcm_vhost_fabric_configfs\n");
	return 0;
};

static void tcm_vhost_deregister_configfs(void)
{
	if (!tcm_vhost_fabric_configfs)
		return;

	target_fabric_configfs_deregister(tcm_vhost_fabric_configfs);
	tcm_vhost_fabric_configfs = NULL;
	pr_debug("TCM_VHOST[0] - Cleared tcm_vhost_fabric_configfs\n");
};

static int __init tcm_vhost_init(void)
{
	int ret = -ENOMEM;
2210 2211 2212 2213
	/*
	 * Use our own dedicated workqueue for submitting I/O into
	 * target core to avoid contention within system_wq.
	 */
2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242
	tcm_vhost_workqueue = alloc_workqueue("tcm_vhost", 0, 0);
	if (!tcm_vhost_workqueue)
		goto out;

	ret = vhost_scsi_register();
	if (ret < 0)
		goto out_destroy_workqueue;

	ret = tcm_vhost_register_configfs();
	if (ret < 0)
		goto out_vhost_scsi_deregister;

	return 0;

out_vhost_scsi_deregister:
	vhost_scsi_deregister();
out_destroy_workqueue:
	destroy_workqueue(tcm_vhost_workqueue);
out:
	return ret;
};

static void tcm_vhost_exit(void)
{
	tcm_vhost_deregister_configfs();
	vhost_scsi_deregister();
	destroy_workqueue(tcm_vhost_workqueue);
};

M
Michael S. Tsirkin 已提交
2243 2244
MODULE_DESCRIPTION("VHOST_SCSI series fabric driver");
MODULE_ALIAS("tcm_vhost");
2245 2246 2247
MODULE_LICENSE("GPL");
module_init(tcm_vhost_init);
module_exit(tcm_vhost_exit);