tcm_vhost.c 44.2 KB
Newer Older
1 2 3 4 5 6 7 8 9 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 49
/*******************************************************************************
 * Vhost kernel TCM fabric driver for virtio SCSI initiators
 *
 * (C) Copyright 2010-2012 RisingTide Systems LLC.
 * (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>
 *          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_net.h> /* TODO vhost.h currently depends on this */
#include <linux/virtio_scsi.h>
50
#include <linux/llist.h>
A
Asias He 已提交
51
#include <linux/bitmap.h>
52 53 54 55 56

#include "vhost.c"
#include "vhost.h"
#include "tcm_vhost.h"

57 58 59 60 61 62
enum {
	VHOST_SCSI_VQ_CTL = 0,
	VHOST_SCSI_VQ_EVT = 1,
	VHOST_SCSI_VQ_IO = 2,
};

63 64 65 66 67 68 69 70 71
/*
 * VIRTIO_RING_F_EVENT_IDX seems broken. Not sure the bug is in
 * kernel but disabling it helps.
 * TODO: debug and remove the workaround.
 */
enum {
	VHOST_SCSI_FEATURES = VHOST_FEATURES & (~VIRTIO_RING_F_EVENT_IDX)
};

A
Asias He 已提交
72 73
#define VHOST_SCSI_MAX_TARGET	256
#define VHOST_SCSI_MAX_VQ	128
A
Asias He 已提交
74

75
struct vhost_scsi {
A
Asias He 已提交
76
	/* Protected by vhost_scsi->dev.mutex */
77
	struct tcm_vhost_tpg **vs_tpg;
A
Asias He 已提交
78 79
	char vs_vhost_wwpn[TRANSPORT_IQN_LEN];

80
	struct vhost_dev dev;
A
Asias He 已提交
81
	struct vhost_virtqueue vqs[VHOST_SCSI_MAX_VQ];
82 83

	struct vhost_work vs_completion_work; /* cmd completion work item */
84
	struct llist_head vs_completion_list; /* cmd completion queue */
85 86 87 88 89 90 91 92 93 94 95
};

/* 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
96 97 98 99 100 101
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;
}

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
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;
}

160
static u32 tcm_vhost_get_pr_transport_id(struct se_portal_group *se_tpg,
161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189
	struct se_node_acl *se_nacl,
	struct t10_pr_registration *pr_reg,
	int *format_code,
	unsigned char *buf)
{
	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);
}

190
static u32 tcm_vhost_get_pr_transport_id_len(struct se_portal_group *se_tpg,
191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218
	struct se_node_acl *se_nacl,
	struct t10_pr_registration *pr_reg,
	int *format_code)
{
	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);
}

219
static char *tcm_vhost_parse_pr_out_transport_id(struct se_portal_group *se_tpg,
220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254
	const char *buf,
	u32 *out_tid_len,
	char **port_nexus_ptr)
{
	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);
}

static struct se_node_acl *tcm_vhost_alloc_fabric_acl(
	struct se_portal_group *se_tpg)
{
	struct tcm_vhost_nacl *nacl;

	nacl = kzalloc(sizeof(struct tcm_vhost_nacl), GFP_KERNEL);
	if (!nacl) {
255
		pr_err("Unable to allocate struct tcm_vhost_nacl\n");
256 257 258 259 260 261
		return NULL;
	}

	return &nacl->se_node_acl;
}

262
static void tcm_vhost_release_fabric_acl(struct se_portal_group *se_tpg,
263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321
	struct se_node_acl *se_nacl)
{
	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)
{
	return;
}

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;
}

322 323 324 325
static void vhost_scsi_complete_cmd(struct tcm_vhost_cmd *tv_cmd)
{
	struct vhost_scsi *vs = tv_cmd->tvc_vhost;

326
	llist_add(&tv_cmd->tvc_completion_list, &vs->vs_completion_list);
327 328 329

	vhost_work_queue(&vs->dev, &vs->vs_completion_work);
}
330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378

static int tcm_vhost_queue_data_in(struct se_cmd *se_cmd)
{
	struct tcm_vhost_cmd *tv_cmd = container_of(se_cmd,
				struct tcm_vhost_cmd, tvc_se_cmd);
	vhost_scsi_complete_cmd(tv_cmd);
	return 0;
}

static int tcm_vhost_queue_status(struct se_cmd *se_cmd)
{
	struct tcm_vhost_cmd *tv_cmd = container_of(se_cmd,
				struct tcm_vhost_cmd, tvc_se_cmd);
	vhost_scsi_complete_cmd(tv_cmd);
	return 0;
}

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

static void vhost_scsi_free_cmd(struct tcm_vhost_cmd *tv_cmd)
{
	struct se_cmd *se_cmd = &tv_cmd->tvc_se_cmd;

	/* TODO locking against target/backend threads? */
	transport_generic_free_cmd(se_cmd, 1);

	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);
	}

	kfree(tv_cmd);
}

/* 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
379
	DECLARE_BITMAP(signal, VHOST_SCSI_MAX_VQ);
380
	struct virtio_scsi_cmd_resp v_rsp;
381
	struct tcm_vhost_cmd *tv_cmd;
382 383
	struct llist_node *llnode;
	struct se_cmd *se_cmd;
A
Asias He 已提交
384
	int ret, vq;
385

A
Asias He 已提交
386
	bitmap_zero(signal, VHOST_SCSI_MAX_VQ);
387 388 389 390 391 392
	llnode = llist_del_all(&vs->vs_completion_list);
	while (llnode) {
		tv_cmd = llist_entry(llnode, struct tcm_vhost_cmd,
				     tvc_completion_list);
		llnode = llist_next(llnode);
		se_cmd = &tv_cmd->tvc_se_cmd;
393 394 395 396 397 398 399 400 401 402 403 404

		pr_debug("%s tv_cmd %p resid %u status %#02x\n", __func__,
			tv_cmd, se_cmd->residual_count, se_cmd->scsi_status);

		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;
		memcpy(v_rsp.sense, tv_cmd->tvc_sense_buf,
		       v_rsp.sense_len);
		ret = copy_to_user(tv_cmd->tvc_resp, &v_rsp, sizeof(v_rsp));
A
Asias He 已提交
405 406 407 408 409
		if (likely(ret == 0)) {
			vhost_add_used(tv_cmd->tvc_vq, tv_cmd->tvc_vq_desc, 0);
			vq = tv_cmd->tvc_vq - vs->vqs;
			__set_bit(vq, signal);
		} else
410 411 412 413 414
			pr_err("Faulted on virtio_scsi_cmd_resp\n");

		vhost_scsi_free_cmd(tv_cmd);
	}

A
Asias He 已提交
415 416 417 418
	vq = -1;
	while ((vq = find_next_bit(signal, VHOST_SCSI_MAX_VQ, vq + 1))
		< VHOST_SCSI_MAX_VQ)
		vhost_signal(&vs->dev, &vs->vqs[vq]);
419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441
}

static struct tcm_vhost_cmd *vhost_scsi_allocate_cmd(
	struct tcm_vhost_tpg *tv_tpg,
	struct virtio_scsi_cmd_req *v_req,
	u32 exp_data_len,
	int data_direction)
{
	struct tcm_vhost_cmd *tv_cmd;
	struct tcm_vhost_nexus *tv_nexus;

	tv_nexus = tv_tpg->tpg_nexus;
	if (!tv_nexus) {
		pr_err("Unable to locate active struct tcm_vhost_nexus\n");
		return ERR_PTR(-EIO);
	}

	tv_cmd = kzalloc(sizeof(struct tcm_vhost_cmd), GFP_ATOMIC);
	if (!tv_cmd) {
		pr_err("Unable to allocate struct tcm_vhost_cmd\n");
		return ERR_PTR(-ENOMEM);
	}
	tv_cmd->tvc_tag = v_req->tag;
442 443 444 445
	tv_cmd->tvc_task_attr = v_req->task_attr;
	tv_cmd->tvc_exp_data_len = exp_data_len;
	tv_cmd->tvc_data_direction = data_direction;
	tv_cmd->tvc_nexus = tv_nexus;
446 447 448 449 450 451 452 453 454 455

	return tv_cmd;
}

/*
 * Map a user memory range into a scatterlist
 *
 * Returns the number of scatterlist entries used or -errno on error.
 */
static int vhost_scsi_map_to_sgl(struct scatterlist *sgl,
456
	unsigned int sgl_count, struct iovec *iov, int write)
457
{
458
	unsigned int npages = 0, pages_nr, offset, nbytes;
459
	struct scatterlist *sg = sgl;
460 461 462 463
	void __user *ptr = iov->iov_base;
	size_t len = iov->iov_len;
	struct page **pages;
	int ret, i;
464

465 466 467
	pages_nr = iov_num_pages(iov);
	if (pages_nr > sgl_count)
		return -ENOBUFS;
468

469 470 471
	pages = kmalloc(pages_nr * sizeof(struct page *), GFP_KERNEL);
	if (!pages)
		return -ENOMEM;
472

473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488
	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);
489 490 491 492 493 494
		ptr += nbytes;
		len -= nbytes;
		sg++;
		npages++;
	}

495 496
out:
	kfree(pages);
497 498 499 500 501 502 503 504 505 506 507 508 509 510 511
	return ret;
}

static int vhost_scsi_map_iov_to_sgl(struct tcm_vhost_cmd *tv_cmd,
	struct iovec *iov, unsigned int niov, int write)
{
	int ret;
	unsigned int i;
	u32 sgl_count;
	struct scatterlist *sg;

	/*
	 * Find out how long sglist needs to be
	 */
	sgl_count = 0;
512 513 514
	for (i = 0; i < niov; i++)
		sgl_count += iov_num_pages(&iov[i]);

515 516 517 518 519
	/* TODO overflow checking */

	sg = kmalloc(sizeof(tv_cmd->tvc_sgl[0]) * sgl_count, GFP_ATOMIC);
	if (!sg)
		return -ENOMEM;
520 521
	pr_debug("%s sg %p sgl_count %u is_err %d\n", __func__,
	       sg, sgl_count, !sg);
522 523 524 525 526 527 528
	sg_init_table(sg, sgl_count);

	tv_cmd->tvc_sgl = sg;
	tv_cmd->tvc_sgl_count = sgl_count;

	pr_debug("Mapping %u iovecs for %u pages\n", niov, sgl_count);
	for (i = 0; i < niov; i++) {
529
		ret = vhost_scsi_map_to_sgl(sg, sgl_count, &iov[i], write);
530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548
		if (ret < 0) {
			for (i = 0; i < tv_cmd->tvc_sgl_count; i++)
				put_page(sg_page(&tv_cmd->tvc_sgl[i]));
			kfree(tv_cmd->tvc_sgl);
			tv_cmd->tvc_sgl = NULL;
			tv_cmd->tvc_sgl_count = 0;
			return ret;
		}

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

static void tcm_vhost_submission_work(struct work_struct *work)
{
	struct tcm_vhost_cmd *tv_cmd =
		container_of(work, struct tcm_vhost_cmd, work);
549
	struct tcm_vhost_nexus *tv_nexus;
550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565
	struct se_cmd *se_cmd = &tv_cmd->tvc_se_cmd;
	struct scatterlist *sg_ptr, *sg_bidi_ptr = NULL;
	int rc, sg_no_bidi = 0;

	if (tv_cmd->tvc_sgl_count) {
		sg_ptr = tv_cmd->tvc_sgl;
/* 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;
	}
566 567 568 569 570 571 572 573
	tv_nexus = tv_cmd->tvc_nexus;

	rc = target_submit_cmd_map_sgls(se_cmd, tv_nexus->tvn_se_sess,
			tv_cmd->tvc_cdb, &tv_cmd->tvc_sense_buf[0],
			tv_cmd->tvc_lun, tv_cmd->tvc_exp_data_len,
			tv_cmd->tvc_task_attr, tv_cmd->tvc_data_direction,
			0, sg_ptr, tv_cmd->tvc_sgl_count,
			sg_bidi_ptr, sg_no_bidi);
574 575
	if (rc < 0) {
		transport_send_check_condition_and_sense(se_cmd,
576
				TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE, 0);
577 578 579 580
		transport_generic_free_cmd(se_cmd, 0);
	}
}

581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597
static void vhost_scsi_send_bad_target(struct vhost_scsi *vs,
	struct vhost_virtqueue *vq, int head, unsigned out)
{
	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");
}

A
Asias He 已提交
598 599
static void vhost_scsi_handle_vq(struct vhost_scsi *vs,
	struct vhost_virtqueue *vq)
600
{
601
	struct tcm_vhost_tpg **vs_tpg;
602 603 604 605 606 607
	struct virtio_scsi_cmd_req v_req;
	struct tcm_vhost_tpg *tv_tpg;
	struct tcm_vhost_cmd *tv_cmd;
	u32 exp_data_len, data_first, data_num, data_direction;
	unsigned out, in, i;
	int head, ret;
A
Asias He 已提交
608
	u8 target;
609

610 611 612 613 614 615 616 617 618 619
	/*
	 * We can handle the vq only after the endpoint is setup by calling the
	 * VHOST_SCSI_SET_ENDPOINT ioctl.
	 *
	 * TODO: Check that we are running from vhost_worker which acts
	 * as read-side critical section for vhost kind of RCU.
	 * See the comments in struct vhost_virtqueue in drivers/vhost/vhost.h
	 */
	vs_tpg = rcu_dereference_check(vq->private_data, 1);
	if (!vs_tpg)
620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686
		return;

	mutex_lock(&vq->mutex);
	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
687 688
		/* Extract the tpgt */
		target = v_req.lun[1];
689
		tv_tpg = ACCESS_ONCE(vs_tpg[target]);
A
Asias He 已提交
690 691 692

		/* Target does not exist, fail the request */
		if (unlikely(!tv_tpg)) {
693
			vhost_scsi_send_bad_target(vs, vq, head, out);
A
Asias He 已提交
694 695 696
			continue;
		}

697 698 699 700 701 702 703 704 705
		exp_data_len = 0;
		for (i = 0; i < data_num; i++)
			exp_data_len += vq->iov[data_first + i].iov_len;

		tv_cmd = vhost_scsi_allocate_cmd(tv_tpg, &v_req,
					exp_data_len, data_direction);
		if (IS_ERR(tv_cmd)) {
			vq_err(vq, "vhost_scsi_allocate_cmd failed %ld\n",
					PTR_ERR(tv_cmd));
706
			goto err_cmd;
707 708 709 710 711
		}
		pr_debug("Allocated tv_cmd: %p exp_data_len: %d, data_direction"
			": %d\n", tv_cmd, exp_data_len, data_direction);

		tv_cmd->tvc_vhost = vs;
A
Asias He 已提交
712
		tv_cmd->tvc_vq = vq;
713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731
		tv_cmd->tvc_resp = vq->iov[out].iov_base;

		/*
		 * Copy in the recieved CDB descriptor into tv_cmd->tvc_cdb
		 * that will be used by tcm_vhost_new_cmd_map() and down into
		 * target_setup_cmd_from_cdb()
		 */
		memcpy(tv_cmd->tvc_cdb, v_req.cdb, TCM_VHOST_MAX_CDB_SIZE);
		/*
		 * 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? */
		if (unlikely(scsi_command_size(tv_cmd->tvc_cdb) >
					TCM_VHOST_MAX_CDB_SIZE)) {
			vq_err(vq, "Received SCSI CDB with command_size: %d that"
				" exceeds SCSI_MAX_VARLEN_CDB_SIZE: %d\n",
				scsi_command_size(tv_cmd->tvc_cdb),
				TCM_VHOST_MAX_CDB_SIZE);
732
			goto err_free;
733 734 735 736 737 738 739 740 741 742 743 744
		}
		tv_cmd->tvc_lun = ((v_req.lun[2] << 8) | v_req.lun[3]) & 0x3FFF;

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

		if (data_direction != DMA_NONE) {
			ret = vhost_scsi_map_iov_to_sgl(tv_cmd,
					&vq->iov[data_first], data_num,
					data_direction == DMA_TO_DEVICE);
			if (unlikely(ret)) {
				vq_err(vq, "Failed to map iov to sgl\n");
745
				goto err_free;
746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765
			}
		}

		/*
		 * 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()
		 */
		tv_cmd->tvc_vq_desc = head;
		/*
		 * 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..
		 */
		INIT_WORK(&tv_cmd->work, tcm_vhost_submission_work);
		queue_work(tcm_vhost_workqueue, &tv_cmd->work);
	}

	mutex_unlock(&vq->mutex);
766 767
	return;

768
err_free:
769
	vhost_scsi_free_cmd(tv_cmd);
770 771
err_cmd:
	vhost_scsi_send_bad_target(vs, vq, head, out);
772
	mutex_unlock(&vq->mutex);
773 774 775 776
}

static void vhost_scsi_ctl_handle_kick(struct vhost_work *work)
{
777
	pr_debug("%s: The handling func for control queue.\n", __func__);
778 779 780 781
}

static void vhost_scsi_evt_handle_kick(struct vhost_work *work)
{
782
	pr_debug("%s: The handling func for event queue.\n", __func__);
783 784 785 786 787 788 789 790
}

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
791
	vhost_scsi_handle_vq(vs, vq);
792 793
}

794 795 796 797 798 799 800 801 802 803 804 805 806 807
static void vhost_scsi_flush_vq(struct vhost_scsi *vs, int index)
{
	vhost_poll_flush(&vs->dev.vqs[index].poll);
}

static void vhost_scsi_flush(struct vhost_scsi *vs)
{
	int i;

	for (i = 0; i < VHOST_SCSI_MAX_VQ; i++)
		vhost_scsi_flush_vq(vs, i);
	vhost_work_flush(&vs->dev, &vs->vs_completion_work);
}

808 809 810 811 812 813 814 815 816 817
/*
 * Called from vhost_scsi_ioctl() context to walk the list of available
 * tcm_vhost_tpg with an active struct tcm_vhost_nexus
 */
static int vhost_scsi_set_endpoint(
	struct vhost_scsi *vs,
	struct vhost_scsi_target *t)
{
	struct tcm_vhost_tport *tv_tport;
	struct tcm_vhost_tpg *tv_tpg;
818 819 820
	struct tcm_vhost_tpg **vs_tpg;
	struct vhost_virtqueue *vq;
	int index, ret, i, len;
A
Asias He 已提交
821
	bool match = false;
822 823 824 825 826 827 828 829 830 831 832

	mutex_lock(&vs->dev.mutex);
	/* Verify that ring has been setup correctly. */
	for (index = 0; index < vs->dev.nvqs; ++index) {
		/* Verify that ring has been setup correctly. */
		if (!vhost_vq_access_ok(&vs->vqs[index])) {
			mutex_unlock(&vs->dev.mutex);
			return -EFAULT;
		}
	}

833 834 835 836 837 838 839 840 841
	len = sizeof(vs_tpg[0]) * VHOST_SCSI_MAX_TARGET;
	vs_tpg = kzalloc(len, GFP_KERNEL);
	if (!vs_tpg) {
		mutex_unlock(&vs->dev.mutex);
		return -ENOMEM;
	}
	if (vs->vs_tpg)
		memcpy(vs_tpg, vs->vs_tpg, len);

842 843 844 845 846 847 848
	mutex_lock(&tcm_vhost_mutex);
	list_for_each_entry(tv_tpg, &tcm_vhost_list, tv_tpg_list) {
		mutex_lock(&tv_tpg->tv_tpg_mutex);
		if (!tv_tpg->tpg_nexus) {
			mutex_unlock(&tv_tpg->tv_tpg_mutex);
			continue;
		}
849
		if (tv_tpg->tv_tpg_vhost_count != 0) {
850 851 852 853 854
			mutex_unlock(&tv_tpg->tv_tpg_mutex);
			continue;
		}
		tv_tport = tv_tpg->tport;

A
Asias He 已提交
855
		if (!strcmp(tv_tport->tport_name, t->vhost_wwpn)) {
856
			if (vs->vs_tpg && vs->vs_tpg[tv_tpg->tport_tpgt]) {
857
				mutex_unlock(&tv_tpg->tv_tpg_mutex);
A
Asias He 已提交
858 859
				mutex_unlock(&tcm_vhost_mutex);
				mutex_unlock(&vs->dev.mutex);
860
				kfree(vs_tpg);
861 862
				return -EEXIST;
			}
A
Asias He 已提交
863
			tv_tpg->tv_tpg_vhost_count++;
864
			vs_tpg[tv_tpg->tport_tpgt] = tv_tpg;
865
			smp_mb__after_atomic_inc();
A
Asias He 已提交
866
			match = true;
867 868 869 870
		}
		mutex_unlock(&tv_tpg->tv_tpg_mutex);
	}
	mutex_unlock(&tcm_vhost_mutex);
A
Asias He 已提交
871 872 873 874

	if (match) {
		memcpy(vs->vs_vhost_wwpn, t->vhost_wwpn,
		       sizeof(vs->vs_vhost_wwpn));
875 876 877 878 879
		for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
			vq = &vs->vqs[i];
			/* Flushing the vhost_work acts as synchronize_rcu */
			mutex_lock(&vq->mutex);
			rcu_assign_pointer(vq->private_data, vs_tpg);
880
			vhost_init_used(vq);
881 882
			mutex_unlock(&vq->mutex);
		}
A
Asias He 已提交
883 884 885 886 887
		ret = 0;
	} else {
		ret = -EEXIST;
	}

888 889 890 891 892 893 894 895
	/*
	 * 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;

A
Asias He 已提交
896 897
	mutex_unlock(&vs->dev.mutex);
	return ret;
898 899 900 901 902 903 904 905
}

static int vhost_scsi_clear_endpoint(
	struct vhost_scsi *vs,
	struct vhost_scsi_target *t)
{
	struct tcm_vhost_tport *tv_tport;
	struct tcm_vhost_tpg *tv_tpg;
906 907
	struct vhost_virtqueue *vq;
	bool match = false;
A
Asias He 已提交
908 909
	int index, ret, i;
	u8 target;
910 911 912 913 914

	mutex_lock(&vs->dev.mutex);
	/* Verify that ring has been setup correctly. */
	for (index = 0; index < vs->dev.nvqs; ++index) {
		if (!vhost_vq_access_ok(&vs->vqs[index])) {
915
			ret = -EFAULT;
916
			goto err_dev;
917 918
		}
	}
919 920 921 922 923 924

	if (!vs->vs_tpg) {
		mutex_unlock(&vs->dev.mutex);
		return 0;
	}

A
Asias He 已提交
925 926 927 928 929 930
	for (i = 0; i < VHOST_SCSI_MAX_TARGET; i++) {
		target = i;
		tv_tpg = vs->vs_tpg[target];
		if (!tv_tpg)
			continue;

931
		mutex_lock(&tv_tpg->tv_tpg_mutex);
A
Asias He 已提交
932 933 934
		tv_tport = tv_tpg->tport;
		if (!tv_tport) {
			ret = -ENODEV;
935
			goto err_tpg;
A
Asias He 已提交
936 937 938 939 940 941 942 943
		}

		if (strcmp(tv_tport->tport_name, t->vhost_wwpn)) {
			pr_warn("tv_tport->tport_name: %s, tv_tpg->tport_tpgt: %hu"
				" does not match t->vhost_wwpn: %s, t->vhost_tpgt: %hu\n",
				tv_tport->tport_name, tv_tpg->tport_tpgt,
				t->vhost_wwpn, t->vhost_tpgt);
			ret = -EINVAL;
944
			goto err_tpg;
A
Asias He 已提交
945 946 947
		}
		tv_tpg->tv_tpg_vhost_count--;
		vs->vs_tpg[target] = NULL;
948
		match = true;
949
		mutex_unlock(&tv_tpg->tv_tpg_mutex);
950
	}
951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966
	if (match) {
		for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
			vq = &vs->vqs[i];
			/* Flushing the vhost_work acts as synchronize_rcu */
			mutex_lock(&vq->mutex);
			rcu_assign_pointer(vq->private_data, NULL);
			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;
967
	mutex_unlock(&vs->dev.mutex);
968

969
	return 0;
970

971 972 973
err_tpg:
	mutex_unlock(&tv_tpg->tv_tpg_mutex);
err_dev:
974 975
	mutex_unlock(&vs->dev.mutex);
	return ret;
976 977
}

978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995
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;
}

996 997 998
static int vhost_scsi_open(struct inode *inode, struct file *f)
{
	struct vhost_scsi *s;
A
Asias He 已提交
999
	int r, i;
1000 1001 1002 1003 1004 1005 1006

	s = kzalloc(sizeof(*s), GFP_KERNEL);
	if (!s)
		return -ENOMEM;

	vhost_work_init(&s->vs_completion_work, vhost_scsi_complete_cmd_work);

1007 1008
	s->vqs[VHOST_SCSI_VQ_CTL].handle_kick = vhost_scsi_ctl_handle_kick;
	s->vqs[VHOST_SCSI_VQ_EVT].handle_kick = vhost_scsi_evt_handle_kick;
A
Asias He 已提交
1009 1010 1011
	for (i = VHOST_SCSI_VQ_IO; i < VHOST_SCSI_MAX_VQ; i++)
		s->vqs[i].handle_kick = vhost_scsi_handle_kick;
	r = vhost_dev_init(&s->dev, s->vqs, VHOST_SCSI_MAX_VQ);
1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023
	if (r < 0) {
		kfree(s);
		return r;
	}

	f->private_data = s;
	return 0;
}

static int vhost_scsi_release(struct inode *inode, struct file *f)
{
	struct vhost_scsi *s = f->private_data;
A
Asias He 已提交
1024
	struct vhost_scsi_target t;
1025

A
Asias He 已提交
1026 1027 1028 1029
	mutex_lock(&s->dev.mutex);
	memcpy(t.vhost_wwpn, s->vs_vhost_wwpn, sizeof(t.vhost_wwpn));
	mutex_unlock(&s->dev.mutex);
	vhost_scsi_clear_endpoint(s, &t);
1030
	vhost_dev_stop(&s->dev);
1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043
	vhost_dev_cleanup(&s->dev, false);
	kfree(s);
	return 0;
}

static long vhost_scsi_ioctl(struct file *f, unsigned int ioctl,
				unsigned long arg)
{
	struct vhost_scsi *vs = f->private_data;
	struct vhost_scsi_target backend;
	void __user *argp = (void __user *)arg;
	u64 __user *featurep = argp;
	u64 features;
1044
	int r, abi_version = VHOST_SCSI_ABI_VERSION;
1045 1046 1047 1048 1049

	switch (ioctl) {
	case VHOST_SCSI_SET_ENDPOINT:
		if (copy_from_user(&backend, argp, sizeof backend))
			return -EFAULT;
1050 1051
		if (backend.reserved != 0)
			return -EOPNOTSUPP;
1052 1053 1054 1055 1056

		return vhost_scsi_set_endpoint(vs, &backend);
	case VHOST_SCSI_CLEAR_ENDPOINT:
		if (copy_from_user(&backend, argp, sizeof backend))
			return -EFAULT;
1057 1058
		if (backend.reserved != 0)
			return -EOPNOTSUPP;
1059 1060 1061

		return vhost_scsi_clear_endpoint(vs, &backend);
	case VHOST_SCSI_GET_ABI_VERSION:
1062
		if (copy_to_user(argp, &abi_version, sizeof abi_version))
1063 1064 1065
			return -EFAULT;
		return 0;
	case VHOST_GET_FEATURES:
1066
		features = VHOST_SCSI_FEATURES;
1067 1068 1069 1070 1071 1072 1073 1074 1075
		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);
1076 1077 1078 1079
		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);
1080 1081 1082 1083 1084
		mutex_unlock(&vs->dev.mutex);
		return r;
	}
}

1085 1086 1087 1088 1089 1090 1091 1092
#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

1093 1094 1095 1096
static const struct file_operations vhost_scsi_fops = {
	.owner          = THIS_MODULE,
	.release        = vhost_scsi_release,
	.unlocked_ioctl = vhost_scsi_ioctl,
1097 1098 1099
#ifdef CONFIG_COMPAT
	.compat_ioctl	= vhost_scsi_compat_ioctl,
#endif
1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135
	.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";
}

1136
static int tcm_vhost_port_link(struct se_portal_group *se_tpg,
1137 1138 1139 1140 1141
	struct se_lun *lun)
{
	struct tcm_vhost_tpg *tv_tpg = container_of(se_tpg,
				struct tcm_vhost_tpg, se_tpg);

1142 1143 1144
	mutex_lock(&tv_tpg->tv_tpg_mutex);
	tv_tpg->tv_tpg_port_count++;
	mutex_unlock(&tv_tpg->tv_tpg_mutex);
1145 1146 1147 1148

	return 0;
}

1149
static void tcm_vhost_port_unlink(struct se_portal_group *se_tpg,
1150 1151 1152 1153 1154
	struct se_lun *se_lun)
{
	struct tcm_vhost_tpg *tv_tpg = container_of(se_tpg,
				struct tcm_vhost_tpg, se_tpg);

1155 1156 1157
	mutex_lock(&tv_tpg->tv_tpg_mutex);
	tv_tpg->tv_tpg_port_count--;
	mutex_unlock(&tv_tpg->tv_tpg_mutex);
1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203
}

static struct se_node_acl *tcm_vhost_make_nodeacl(
	struct se_portal_group *se_tpg,
	struct config_group *group,
	const char *name)
{
	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);
}

1204
static int tcm_vhost_make_nexus(struct tcm_vhost_tpg *tv_tpg,
1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248
	const char *name)
{
	struct se_portal_group *se_tpg;
	struct tcm_vhost_nexus *tv_nexus;

	mutex_lock(&tv_tpg->tv_tpg_mutex);
	if (tv_tpg->tpg_nexus) {
		mutex_unlock(&tv_tpg->tv_tpg_mutex);
		pr_debug("tv_tpg->tpg_nexus already exists\n");
		return -EEXIST;
	}
	se_tpg = &tv_tpg->se_tpg;

	tv_nexus = kzalloc(sizeof(struct tcm_vhost_nexus), GFP_KERNEL);
	if (!tv_nexus) {
		mutex_unlock(&tv_tpg->tv_tpg_mutex);
		pr_err("Unable to allocate struct tcm_vhost_nexus\n");
		return -ENOMEM;
	}
	/*
	 *  Initialize the struct se_session pointer
	 */
	tv_nexus->tvn_se_sess = transport_init_session();
	if (IS_ERR(tv_nexus->tvn_se_sess)) {
		mutex_unlock(&tv_tpg->tv_tpg_mutex);
		kfree(tv_nexus);
		return -ENOMEM;
	}
	/*
	 * 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) {
		mutex_unlock(&tv_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;
	}
	/*
1249
	 * Now register the TCM vhost virtual I_T Nexus as active with the
1250 1251 1252 1253 1254 1255 1256 1257 1258 1259
	 * 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);
	tv_tpg->tpg_nexus = tv_nexus;

	mutex_unlock(&tv_tpg->tv_tpg_mutex);
	return 0;
}

1260
static int tcm_vhost_drop_nexus(struct tcm_vhost_tpg *tpg)
1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277
{
	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;
	}

1278
	if (tpg->tv_tpg_port_count != 0) {
1279
		mutex_unlock(&tpg->tv_tpg_mutex);
1280
		pr_err("Unable to remove TCM_vhost I_T Nexus with"
1281
			" active TPG port count: %d\n",
1282 1283
			tpg->tv_tpg_port_count);
		return -EBUSY;
1284 1285
	}

1286
	if (tpg->tv_tpg_vhost_count != 0) {
1287
		mutex_unlock(&tpg->tv_tpg_mutex);
1288
		pr_err("Unable to remove TCM_vhost I_T Nexus with"
1289
			" active TPG vhost count: %d\n",
1290 1291
			tpg->tv_tpg_vhost_count);
		return -EBUSY;
1292 1293
	}

1294
	pr_debug("TCM_vhost_ConfigFS: Removing I_T Nexus to emulated"
1295 1296 1297
		" %s Initiator Port: %s\n", tcm_vhost_dump_proto_id(tpg->tport),
		tv_nexus->tvn_se_sess->se_node_acl->initiatorname);
	/*
1298
	 * Release the SCSI I_T Nexus to the emulated vhost Target Port
1299 1300 1301 1302 1303 1304 1305 1306 1307
	 */
	transport_deregister_session(tv_nexus->tvn_se_sess);
	tpg->tpg_nexus = NULL;
	mutex_unlock(&tpg->tv_tpg_mutex);

	kfree(tv_nexus);
	return 0;
}

1308
static ssize_t tcm_vhost_tpg_show_nexus(struct se_portal_group *se_tpg,
1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328
	char *page)
{
	struct tcm_vhost_tpg *tv_tpg = container_of(se_tpg,
				struct tcm_vhost_tpg, se_tpg);
	struct tcm_vhost_nexus *tv_nexus;
	ssize_t ret;

	mutex_lock(&tv_tpg->tv_tpg_mutex);
	tv_nexus = tv_tpg->tpg_nexus;
	if (!tv_nexus) {
		mutex_unlock(&tv_tpg->tv_tpg_mutex);
		return -ENODEV;
	}
	ret = snprintf(page, PAGE_SIZE, "%s\n",
			tv_nexus->tvn_se_sess->se_node_acl->initiatorname);
	mutex_unlock(&tv_tpg->tv_tpg_mutex);

	return ret;
}

1329
static ssize_t tcm_vhost_tpg_store_nexus(struct se_portal_group *se_tpg,
1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413
	const char *page,
	size_t count)
{
	struct tcm_vhost_tpg *tv_tpg = container_of(se_tpg,
				struct tcm_vhost_tpg, se_tpg);
	struct tcm_vhost_tport *tport_wwn = tv_tpg->tport;
	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)) {
		ret = tcm_vhost_drop_nexus(tv_tpg);
		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';

	ret = tcm_vhost_make_nexus(tv_tpg, port_ptr);
	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,
};

1414
static struct se_portal_group *tcm_vhost_make_tpg(struct se_wwn *wwn,
1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461
	struct config_group *group,
	const char *name)
{
	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);
	/*
1462
	 * Release the virtual I_T Nexus for this vhost TPG
1463 1464 1465 1466 1467 1468 1469 1470 1471
	 */
	tcm_vhost_drop_nexus(tpg);
	/*
	 * Deregister the se_tpg from TCM..
	 */
	core_tpg_deregister(se_tpg);
	kfree(tpg);
}

1472
static struct se_wwn *tcm_vhost_make_tport(struct target_fabric_configfs *tf,
1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 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 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665
	struct config_group *group,
	const char *name)
{
	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);
}

static ssize_t tcm_vhost_wwn_show_attr_version(
	struct target_fabric_configfs *tf,
	char *page)
{
	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,
	.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;
1666 1667 1668 1669
	/*
	 * Use our own dedicated workqueue for submitting I/O into
	 * target core to avoid contention within system_wq.
	 */
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 1696 1697 1698 1699 1700 1701 1702
	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);
};

MODULE_DESCRIPTION("TCM_VHOST series fabric driver");
MODULE_LICENSE("GPL");
module_init(tcm_vhost_init);
module_exit(tcm_vhost_exit);