device.c 31.9 KB
Newer Older
1 2 3 4 5 6 7
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/io-64-nonatomic-lo-hi.h>
8
#include <linux/dmaengine.h>
9 10
#include <linux/irq.h>
#include <linux/msi.h>
11
#include <uapi/linux/idxd.h>
12
#include "../dmaengine.h"
13 14 15
#include "idxd.h"
#include "registers.h"

16 17
static void idxd_cmd_exec(struct idxd_device *idxd, int cmd_code, u32 operand,
			  u32 *status);
18 19
static void idxd_device_wqs_clear_state(struct idxd_device *idxd);
static void idxd_wq_disable_cleanup(struct idxd_wq *wq);
20 21

/* Interrupt control bits */
22
void idxd_mask_msix_vector(struct idxd_device *idxd, int vec_id)
23
{
24
	struct irq_data *data = irq_get_irq_data(idxd->irq_entries[vec_id].vector);
25

26
	pci_msi_mask_irq(data);
27 28 29 30 31 32
}

void idxd_mask_msix_vectors(struct idxd_device *idxd)
{
	struct pci_dev *pdev = idxd->pdev;
	int msixcnt = pci_msix_vec_count(pdev);
33
	int i;
34

35 36
	for (i = 0; i < msixcnt; i++)
		idxd_mask_msix_vector(idxd, i);
37 38
}

39
void idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id)
40
{
41
	struct irq_data *data = irq_get_irq_data(idxd->irq_entries[vec_id].vector);
42

43
	pci_msi_unmask_irq(data);
44 45 46 47 48 49 50 51
}

void idxd_unmask_error_interrupts(struct idxd_device *idxd)
{
	union genctrl_reg genctrl;

	genctrl.bits = ioread32(idxd->reg_base + IDXD_GENCTRL_OFFSET);
	genctrl.softerr_int_en = 1;
52
	genctrl.halt_int_en = 1;
53 54 55 56 57 58 59 60 61
	iowrite32(genctrl.bits, idxd->reg_base + IDXD_GENCTRL_OFFSET);
}

void idxd_mask_error_interrupts(struct idxd_device *idxd)
{
	union genctrl_reg genctrl;

	genctrl.bits = ioread32(idxd->reg_base + IDXD_GENCTRL_OFFSET);
	genctrl.softerr_int_en = 0;
62
	genctrl.halt_int_en = 0;
63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 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
	iowrite32(genctrl.bits, idxd->reg_base + IDXD_GENCTRL_OFFSET);
}

static void free_hw_descs(struct idxd_wq *wq)
{
	int i;

	for (i = 0; i < wq->num_descs; i++)
		kfree(wq->hw_descs[i]);

	kfree(wq->hw_descs);
}

static int alloc_hw_descs(struct idxd_wq *wq, int num)
{
	struct device *dev = &wq->idxd->pdev->dev;
	int i;
	int node = dev_to_node(dev);

	wq->hw_descs = kcalloc_node(num, sizeof(struct dsa_hw_desc *),
				    GFP_KERNEL, node);
	if (!wq->hw_descs)
		return -ENOMEM;

	for (i = 0; i < num; i++) {
		wq->hw_descs[i] = kzalloc_node(sizeof(*wq->hw_descs[i]),
					       GFP_KERNEL, node);
		if (!wq->hw_descs[i]) {
			free_hw_descs(wq);
			return -ENOMEM;
		}
	}

	return 0;
}

static void free_descs(struct idxd_wq *wq)
{
	int i;

	for (i = 0; i < wq->num_descs; i++)
		kfree(wq->descs[i]);

	kfree(wq->descs);
}

static int alloc_descs(struct idxd_wq *wq, int num)
{
	struct device *dev = &wq->idxd->pdev->dev;
	int i;
	int node = dev_to_node(dev);

	wq->descs = kcalloc_node(num, sizeof(struct idxd_desc *),
				 GFP_KERNEL, node);
	if (!wq->descs)
		return -ENOMEM;

	for (i = 0; i < num; i++) {
		wq->descs[i] = kzalloc_node(sizeof(*wq->descs[i]),
					    GFP_KERNEL, node);
		if (!wq->descs[i]) {
			free_descs(wq);
			return -ENOMEM;
		}
	}

	return 0;
}

/* WQ control bits */
int idxd_wq_alloc_resources(struct idxd_wq *wq)
{
	struct idxd_device *idxd = wq->idxd;
	struct device *dev = &idxd->pdev->dev;
	int rc, num_descs, i;

139 140 141
	if (wq->type != IDXD_WQT_KERNEL)
		return 0;

142 143
	num_descs = wq_dedicated(wq) ? wq->size : wq->threshold;
	wq->num_descs = num_descs;
144 145 146 147 148

	rc = alloc_hw_descs(wq, num_descs);
	if (rc < 0)
		return rc;

149 150 151
	wq->compls_size = num_descs * idxd->data->compl_size;
	wq->compls = dma_alloc_coherent(dev, wq->compls_size, &wq->compls_addr, GFP_KERNEL);
	if (!wq->compls) {
152 153 154 155 156 157 158 159
		rc = -ENOMEM;
		goto fail_alloc_compls;
	}

	rc = alloc_descs(wq, num_descs);
	if (rc < 0)
		goto fail_alloc_descs;

160 161
	rc = sbitmap_queue_init_node(&wq->sbq, num_descs, -1, false, GFP_KERNEL,
				     dev_to_node(dev));
162 163 164 165 166 167 168
	if (rc < 0)
		goto fail_sbitmap_init;

	for (i = 0; i < num_descs; i++) {
		struct idxd_desc *desc = wq->descs[i];

		desc->hw = wq->hw_descs[i];
169
		if (idxd->data->type == IDXD_TYPE_DSA)
170
			desc->completion = &wq->compls[i];
171
		else if (idxd->data->type == IDXD_TYPE_IAX)
172
			desc->iax_completion = &wq->iax_compls[i];
173
		desc->compl_dma = wq->compls_addr + idxd->data->compl_size * i;
174 175
		desc->id = i;
		desc->wq = wq;
176
		desc->cpu = -1;
177 178 179 180 181 182 183
	}

	return 0;

 fail_sbitmap_init:
	free_descs(wq);
 fail_alloc_descs:
184
	dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr);
185 186 187 188 189 190 191 192 193
 fail_alloc_compls:
	free_hw_descs(wq);
	return rc;
}

void idxd_wq_free_resources(struct idxd_wq *wq)
{
	struct device *dev = &wq->idxd->pdev->dev;

194 195 196
	if (wq->type != IDXD_WQT_KERNEL)
		return;

197 198
	free_hw_descs(wq);
	free_descs(wq);
199
	dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr);
200
	sbitmap_queue_free(&wq->sbq);
201 202 203 204 205 206 207 208 209 210 211 212 213
}

int idxd_wq_enable(struct idxd_wq *wq)
{
	struct idxd_device *idxd = wq->idxd;
	struct device *dev = &idxd->pdev->dev;
	u32 status;

	if (wq->state == IDXD_WQ_ENABLED) {
		dev_dbg(dev, "WQ %d already enabled\n", wq->id);
		return -ENXIO;
	}

214
	idxd_cmd_exec(idxd, IDXD_CMD_ENABLE_WQ, wq->id, &status);
215 216 217 218 219 220 221 222 223 224 225 226

	if (status != IDXD_CMDSTS_SUCCESS &&
	    status != IDXD_CMDSTS_ERR_WQ_ENABLED) {
		dev_dbg(dev, "WQ enable failed: %#x\n", status);
		return -ENXIO;
	}

	wq->state = IDXD_WQ_ENABLED;
	dev_dbg(dev, "WQ %d enabled\n", wq->id);
	return 0;
}

227
int idxd_wq_disable(struct idxd_wq *wq, bool reset_config)
228 229 230 231 232 233 234 235 236 237 238 239 240
{
	struct idxd_device *idxd = wq->idxd;
	struct device *dev = &idxd->pdev->dev;
	u32 status, operand;

	dev_dbg(dev, "Disabling WQ %d\n", wq->id);

	if (wq->state != IDXD_WQ_ENABLED) {
		dev_dbg(dev, "WQ %d in wrong state: %d\n", wq->id, wq->state);
		return 0;
	}

	operand = BIT(wq->id % 16) | ((wq->id / 16) << 16);
241
	idxd_cmd_exec(idxd, IDXD_CMD_DISABLE_WQ, operand, &status);
242 243 244 245 246 247

	if (status != IDXD_CMDSTS_SUCCESS) {
		dev_dbg(dev, "WQ disable failed: %#x\n", status);
		return -ENXIO;
	}

248 249
	if (reset_config)
		idxd_wq_disable_cleanup(wq);
250 251 252 253 254
	wq->state = IDXD_WQ_DISABLED;
	dev_dbg(dev, "WQ %d disabled\n", wq->id);
	return 0;
}

255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270
void idxd_wq_drain(struct idxd_wq *wq)
{
	struct idxd_device *idxd = wq->idxd;
	struct device *dev = &idxd->pdev->dev;
	u32 operand;

	if (wq->state != IDXD_WQ_ENABLED) {
		dev_dbg(dev, "WQ %d in wrong state: %d\n", wq->id, wq->state);
		return;
	}

	dev_dbg(dev, "Draining WQ %d\n", wq->id);
	operand = BIT(wq->id % 16) | ((wq->id / 16) << 16);
	idxd_cmd_exec(idxd, IDXD_CMD_DRAIN_WQ, operand, NULL);
}

271 272 273 274 275 276 277 278 279 280 281 282 283
void idxd_wq_reset(struct idxd_wq *wq)
{
	struct idxd_device *idxd = wq->idxd;
	struct device *dev = &idxd->pdev->dev;
	u32 operand;

	if (wq->state != IDXD_WQ_ENABLED) {
		dev_dbg(dev, "WQ %d in wrong state: %d\n", wq->id, wq->state);
		return;
	}

	operand = BIT(wq->id % 16) | ((wq->id / 16) << 16);
	idxd_cmd_exec(idxd, IDXD_CMD_RESET_WQ, operand, NULL);
284
	idxd_wq_disable_cleanup(wq);
285 286 287
	wq->state = IDXD_WQ_DISABLED;
}

288 289 290 291 292 293 294 295
int idxd_wq_map_portal(struct idxd_wq *wq)
{
	struct idxd_device *idxd = wq->idxd;
	struct pci_dev *pdev = idxd->pdev;
	struct device *dev = &pdev->dev;
	resource_size_t start;

	start = pci_resource_start(pdev, IDXD_WQ_BAR);
296
	start += idxd_get_wq_portal_full_offset(wq->id, IDXD_PORTAL_LIMITED);
297

298 299
	wq->portal = devm_ioremap(dev, start, IDXD_PORTAL_SIZE);
	if (!wq->portal)
300 301 302 303 304 305 306 307 308
		return -ENOMEM;

	return 0;
}

void idxd_wq_unmap_portal(struct idxd_wq *wq)
{
	struct device *dev = &wq->idxd->pdev->dev;

309
	devm_iounmap(dev, wq->portal);
310
	wq->portal = NULL;
311
	wq->portal_offset = 0;
312 313 314 315 316 317 318 319 320 321 322 323
}

void idxd_wqs_unmap_portal(struct idxd_device *idxd)
{
	int i;

	for (i = 0; i < idxd->max_wqs; i++) {
		struct idxd_wq *wq = idxd->wqs[i];

		if (wq->portal)
			idxd_wq_unmap_portal(wq);
	}
324 325 326 327 328 329 330 331 332
}

int idxd_wq_set_pasid(struct idxd_wq *wq, int pasid)
{
	struct idxd_device *idxd = wq->idxd;
	int rc;
	union wqcfg wqcfg;
	unsigned int offset;

333
	rc = idxd_wq_disable(wq, false);
334 335 336 337
	if (rc < 0)
		return rc;

	offset = WQCFG_OFFSET(idxd, wq->id, WQCFG_PASID_IDX);
338
	spin_lock(&idxd->dev_lock);
339 340 341 342
	wqcfg.bits[WQCFG_PASID_IDX] = ioread32(idxd->reg_base + offset);
	wqcfg.pasid_en = 1;
	wqcfg.pasid = pasid;
	iowrite32(wqcfg.bits[WQCFG_PASID_IDX], idxd->reg_base + offset);
343
	spin_unlock(&idxd->dev_lock);
344 345 346 347 348 349 350 351 352 353 354 355 356 357 358

	rc = idxd_wq_enable(wq);
	if (rc < 0)
		return rc;

	return 0;
}

int idxd_wq_disable_pasid(struct idxd_wq *wq)
{
	struct idxd_device *idxd = wq->idxd;
	int rc;
	union wqcfg wqcfg;
	unsigned int offset;

359
	rc = idxd_wq_disable(wq, false);
360 361 362 363
	if (rc < 0)
		return rc;

	offset = WQCFG_OFFSET(idxd, wq->id, WQCFG_PASID_IDX);
364
	spin_lock(&idxd->dev_lock);
365 366 367 368
	wqcfg.bits[WQCFG_PASID_IDX] = ioread32(idxd->reg_base + offset);
	wqcfg.pasid_en = 0;
	wqcfg.pasid = 0;
	iowrite32(wqcfg.bits[WQCFG_PASID_IDX], idxd->reg_base + offset);
369
	spin_unlock(&idxd->dev_lock);
370 371 372 373 374 375

	rc = idxd_wq_enable(wq);
	if (rc < 0)
		return rc;

	return 0;
376 377
}

378
static void idxd_wq_disable_cleanup(struct idxd_wq *wq)
379 380 381
{
	struct idxd_device *idxd = wq->idxd;

382
	lockdep_assert_held(&wq->wq_lock);
383
	memset(wq->wqcfg, 0, idxd->wqcfg_size);
384 385 386 387 388
	wq->type = IDXD_WQT_NONE;
	wq->size = 0;
	wq->group = NULL;
	wq->threshold = 0;
	wq->priority = 0;
389
	wq->ats_dis = 0;
390
	clear_bit(WQ_FLAG_DEDICATED, &wq->flags);
391
	clear_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags);
392
	memset(wq->name, 0, WQ_NAME_SIZE);
393 394
	wq->max_xfer_bytes = WQ_DEFAULT_MAX_XFER;
	wq->max_batch_size = WQ_DEFAULT_MAX_BATCH;
395 396
}

397 398 399 400 401 402 403 404 405 406 407 408
static void idxd_wq_ref_release(struct percpu_ref *ref)
{
	struct idxd_wq *wq = container_of(ref, struct idxd_wq, wq_active);

	complete(&wq->wq_dead);
}

int idxd_wq_init_percpu_ref(struct idxd_wq *wq)
{
	int rc;

	memset(&wq->wq_active, 0, sizeof(wq->wq_active));
409 410
	rc = percpu_ref_init(&wq->wq_active, idxd_wq_ref_release,
			     PERCPU_REF_ALLOW_REINIT, GFP_KERNEL);
411 412 413
	if (rc < 0)
		return rc;
	reinit_completion(&wq->wq_dead);
414
	reinit_completion(&wq->wq_resurrect);
415 416 417
	return 0;
}

418
void __idxd_wq_quiesce(struct idxd_wq *wq)
419
{
420
	lockdep_assert_held(&wq->wq_lock);
421
	reinit_completion(&wq->wq_resurrect);
422
	percpu_ref_kill(&wq->wq_active);
423
	complete_all(&wq->wq_resurrect);
424 425 426
	wait_for_completion(&wq->wq_dead);
}

427 428 429 430 431 432 433
void idxd_wq_quiesce(struct idxd_wq *wq)
{
	mutex_lock(&wq->wq_lock);
	__idxd_wq_quiesce(wq);
	mutex_unlock(&wq->wq_lock);
}

434 435 436 437 438 439 440 441 442 443 444 445
/* Device control bits */
static inline bool idxd_is_enabled(struct idxd_device *idxd)
{
	union gensts_reg gensts;

	gensts.bits = ioread32(idxd->reg_base + IDXD_GENSTATS_OFFSET);

	if (gensts.state == IDXD_DEVICE_STATE_ENABLED)
		return true;
	return false;
}

446 447 448 449 450 451 452 453 454
static inline bool idxd_device_is_halted(struct idxd_device *idxd)
{
	union gensts_reg gensts;

	gensts.bits = ioread32(idxd->reg_base + IDXD_GENSTATS_OFFSET);

	return (gensts.state == IDXD_DEVICE_STATE_HALT);
}

455 456 457 458 459
/*
 * This is function is only used for reset during probe and will
 * poll for completion. Once the device is setup with interrupts,
 * all commands will be done via interrupt completion.
 */
460
int idxd_device_init_reset(struct idxd_device *idxd)
461
{
462 463
	struct device *dev = &idxd->pdev->dev;
	union idxd_command_reg cmd;
464

465 466 467 468 469
	if (idxd_device_is_halted(idxd)) {
		dev_warn(&idxd->pdev->dev, "Device is HALTED!\n");
		return -ENXIO;
	}

470 471 472
	memset(&cmd, 0, sizeof(cmd));
	cmd.cmd = IDXD_CMD_RESET_DEVICE;
	dev_dbg(dev, "%s: sending reset for init.\n", __func__);
473
	spin_lock(&idxd->cmd_lock);
474
	iowrite32(cmd.bits, idxd->reg_base + IDXD_CMD_OFFSET);
475

476 477 478
	while (ioread32(idxd->reg_base + IDXD_CMDSTS_OFFSET) &
	       IDXD_CMDSTS_ACTIVE)
		cpu_relax();
479
	spin_unlock(&idxd->cmd_lock);
480
	return 0;
481 482
}

483 484
static void idxd_cmd_exec(struct idxd_device *idxd, int cmd_code, u32 operand,
			  u32 *status)
485 486
{
	union idxd_command_reg cmd;
487
	DECLARE_COMPLETION_ONSTACK(done);
488
	u32 stat;
489

490 491
	if (idxd_device_is_halted(idxd)) {
		dev_warn(&idxd->pdev->dev, "Device is HALTED!\n");
492 493
		if (status)
			*status = IDXD_CMDSTS_HW_ERR;
494 495 496
		return;
	}

497 498 499
	memset(&cmd, 0, sizeof(cmd));
	cmd.cmd = cmd_code;
	cmd.operand = operand;
500 501
	cmd.int_req = 1;

502
	spin_lock(&idxd->cmd_lock);
503 504
	wait_event_lock_irq(idxd->cmd_waitq,
			    !test_bit(IDXD_FLAG_CMD_RUNNING, &idxd->flags),
505
			    idxd->cmd_lock);
506

507 508
	dev_dbg(&idxd->pdev->dev, "%s: sending cmd: %#x op: %#x\n",
		__func__, cmd_code, operand);
509

510
	idxd->cmd_status = 0;
511 512
	__set_bit(IDXD_FLAG_CMD_RUNNING, &idxd->flags);
	idxd->cmd_done = &done;
513 514
	iowrite32(cmd.bits, idxd->reg_base + IDXD_CMD_OFFSET);

515 516 517 518
	/*
	 * After command submitted, release lock and go to sleep until
	 * the command completes via interrupt.
	 */
519
	spin_unlock(&idxd->cmd_lock);
520
	wait_for_completion(&done);
521
	stat = ioread32(idxd->reg_base + IDXD_CMDSTS_OFFSET);
522
	spin_lock(&idxd->cmd_lock);
523 524 525
	if (status)
		*status = stat;
	idxd->cmd_status = stat & GENMASK(7, 0);
526

527 528 529
	__clear_bit(IDXD_FLAG_CMD_RUNNING, &idxd->flags);
	/* Wake up other pending commands */
	wake_up(&idxd->cmd_waitq);
530
	spin_unlock(&idxd->cmd_lock);
531 532 533 534 535 536 537 538 539 540 541 542
}

int idxd_device_enable(struct idxd_device *idxd)
{
	struct device *dev = &idxd->pdev->dev;
	u32 status;

	if (idxd_is_enabled(idxd)) {
		dev_dbg(dev, "Device already enabled\n");
		return -ENXIO;
	}

543
	idxd_cmd_exec(idxd, IDXD_CMD_ENABLE_DEVICE, 0, &status);
544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565

	/* If the command is successful or if the device was enabled */
	if (status != IDXD_CMDSTS_SUCCESS &&
	    status != IDXD_CMDSTS_ERR_DEV_ENABLED) {
		dev_dbg(dev, "%s: err_code: %#x\n", __func__, status);
		return -ENXIO;
	}

	idxd->state = IDXD_DEV_ENABLED;
	return 0;
}

int idxd_device_disable(struct idxd_device *idxd)
{
	struct device *dev = &idxd->pdev->dev;
	u32 status;

	if (!idxd_is_enabled(idxd)) {
		dev_dbg(dev, "Device is not enabled\n");
		return 0;
	}

566
	idxd_cmd_exec(idxd, IDXD_CMD_DISABLE_DEVICE, 0, &status);
567 568 569 570 571

	/* If the command is successful or if the device was disabled */
	if (status != IDXD_CMDSTS_SUCCESS &&
	    !(status & IDXD_CMDSTS_ERR_DIS_DEV_EN)) {
		dev_dbg(dev, "%s: err_code: %#x\n", __func__, status);
572
		return -ENXIO;
573 574
	}

575
	spin_lock(&idxd->dev_lock);
576
	idxd_device_clear_state(idxd);
577
	idxd->state = IDXD_DEV_DISABLED;
578
	spin_unlock(&idxd->dev_lock);
579 580 581
	return 0;
}

582
void idxd_device_reset(struct idxd_device *idxd)
583
{
584
	idxd_cmd_exec(idxd, IDXD_CMD_RESET_DEVICE, 0, NULL);
585
	spin_lock(&idxd->dev_lock);
586
	idxd_device_clear_state(idxd);
587
	idxd->state = IDXD_DEV_DISABLED;
588 589
	idxd_unmask_error_interrupts(idxd);
	idxd_msix_perm_setup(idxd);
590
	spin_unlock(&idxd->dev_lock);
591 592
}

593 594 595 596 597 598 599 600 601 602 603
void idxd_device_drain_pasid(struct idxd_device *idxd, int pasid)
{
	struct device *dev = &idxd->pdev->dev;
	u32 operand;

	operand = pasid;
	dev_dbg(dev, "cmd: %u operand: %#x\n", IDXD_CMD_DRAIN_PASID, operand);
	idxd_cmd_exec(idxd, IDXD_CMD_DRAIN_PASID, operand, NULL);
	dev_dbg(dev, "pasid %d drained\n", pasid);
}

604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656
int idxd_device_request_int_handle(struct idxd_device *idxd, int idx, int *handle,
				   enum idxd_interrupt_type irq_type)
{
	struct device *dev = &idxd->pdev->dev;
	u32 operand, status;

	if (!(idxd->hw.cmd_cap & BIT(IDXD_CMD_REQUEST_INT_HANDLE)))
		return -EOPNOTSUPP;

	dev_dbg(dev, "get int handle, idx %d\n", idx);

	operand = idx & GENMASK(15, 0);
	if (irq_type == IDXD_IRQ_IMS)
		operand |= CMD_INT_HANDLE_IMS;

	dev_dbg(dev, "cmd: %u operand: %#x\n", IDXD_CMD_REQUEST_INT_HANDLE, operand);

	idxd_cmd_exec(idxd, IDXD_CMD_REQUEST_INT_HANDLE, operand, &status);

	if ((status & IDXD_CMDSTS_ERR_MASK) != IDXD_CMDSTS_SUCCESS) {
		dev_dbg(dev, "request int handle failed: %#x\n", status);
		return -ENXIO;
	}

	*handle = (status >> IDXD_CMDSTS_RES_SHIFT) & GENMASK(15, 0);

	dev_dbg(dev, "int handle acquired: %u\n", *handle);
	return 0;
}

int idxd_device_release_int_handle(struct idxd_device *idxd, int handle,
				   enum idxd_interrupt_type irq_type)
{
	struct device *dev = &idxd->pdev->dev;
	u32 operand, status;
	union idxd_command_reg cmd;

	if (!(idxd->hw.cmd_cap & BIT(IDXD_CMD_RELEASE_INT_HANDLE)))
		return -EOPNOTSUPP;

	dev_dbg(dev, "release int handle, handle %d\n", handle);

	memset(&cmd, 0, sizeof(cmd));
	operand = handle & GENMASK(15, 0);

	if (irq_type == IDXD_IRQ_IMS)
		operand |= CMD_INT_HANDLE_IMS;

	cmd.cmd = IDXD_CMD_RELEASE_INT_HANDLE;
	cmd.operand = operand;

	dev_dbg(dev, "cmd: %u operand: %#x\n", IDXD_CMD_RELEASE_INT_HANDLE, operand);

657
	spin_lock(&idxd->cmd_lock);
658 659 660 661 662
	iowrite32(cmd.bits, idxd->reg_base + IDXD_CMD_OFFSET);

	while (ioread32(idxd->reg_base + IDXD_CMDSTS_OFFSET) & IDXD_CMDSTS_ACTIVE)
		cpu_relax();
	status = ioread32(idxd->reg_base + IDXD_CMDSTS_OFFSET);
663
	spin_unlock(&idxd->cmd_lock);
664 665 666 667 668 669 670 671 672 673

	if ((status & IDXD_CMDSTS_ERR_MASK) != IDXD_CMDSTS_SUCCESS) {
		dev_dbg(dev, "release int handle failed: %#x\n", status);
		return -ENXIO;
	}

	dev_dbg(dev, "int handle released.\n");
	return 0;
}

674
/* Device configuration bits */
675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727
static void idxd_engines_clear_state(struct idxd_device *idxd)
{
	struct idxd_engine *engine;
	int i;

	lockdep_assert_held(&idxd->dev_lock);
	for (i = 0; i < idxd->max_engines; i++) {
		engine = idxd->engines[i];
		engine->group = NULL;
	}
}

static void idxd_groups_clear_state(struct idxd_device *idxd)
{
	struct idxd_group *group;
	int i;

	lockdep_assert_held(&idxd->dev_lock);
	for (i = 0; i < idxd->max_groups; i++) {
		group = idxd->groups[i];
		memset(&group->grpcfg, 0, sizeof(group->grpcfg));
		group->num_engines = 0;
		group->num_wqs = 0;
		group->use_token_limit = false;
		group->tokens_allowed = 0;
		group->tokens_reserved = 0;
		group->tc_a = -1;
		group->tc_b = -1;
	}
}

static void idxd_device_wqs_clear_state(struct idxd_device *idxd)
{
	int i;

	lockdep_assert_held(&idxd->dev_lock);
	for (i = 0; i < idxd->max_wqs; i++) {
		struct idxd_wq *wq = idxd->wqs[i];

		if (wq->state == IDXD_WQ_ENABLED) {
			idxd_wq_disable_cleanup(wq);
			wq->state = IDXD_WQ_DISABLED;
		}
	}
}

void idxd_device_clear_state(struct idxd_device *idxd)
{
	idxd_groups_clear_state(idxd);
	idxd_engines_clear_state(idxd);
	idxd_device_wqs_clear_state(idxd);
}

728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757
void idxd_msix_perm_setup(struct idxd_device *idxd)
{
	union msix_perm mperm;
	int i, msixcnt;

	msixcnt = pci_msix_vec_count(idxd->pdev);
	if (msixcnt < 0)
		return;

	mperm.bits = 0;
	mperm.pasid = idxd->pasid;
	mperm.pasid_en = device_pasid_enabled(idxd);
	for (i = 1; i < msixcnt; i++)
		iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8);
}

void idxd_msix_perm_clear(struct idxd_device *idxd)
{
	union msix_perm mperm;
	int i, msixcnt;

	msixcnt = pci_msix_vec_count(idxd->pdev);
	if (msixcnt < 0)
		return;

	mperm.bits = 0;
	for (i = 1; i < msixcnt; i++)
		iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8);
}

758 759 760 761 762 763 764 765 766 767
static void idxd_group_config_write(struct idxd_group *group)
{
	struct idxd_device *idxd = group->idxd;
	struct device *dev = &idxd->pdev->dev;
	int i;
	u32 grpcfg_offset;

	dev_dbg(dev, "Writing group %d cfg registers\n", group->id);

	/* setup GRPWQCFG */
768 769 770
	for (i = 0; i < GRPWQCFG_STRIDES; i++) {
		grpcfg_offset = GRPWQCFG_OFFSET(idxd, group->id, i);
		iowrite64(group->grpcfg.wqs[i], idxd->reg_base + grpcfg_offset);
771 772 773 774 775 776
		dev_dbg(dev, "GRPCFG wq[%d:%d: %#x]: %#llx\n",
			group->id, i, grpcfg_offset,
			ioread64(idxd->reg_base + grpcfg_offset));
	}

	/* setup GRPENGCFG */
777
	grpcfg_offset = GRPENGCFG_OFFSET(idxd, group->id);
778 779 780 781 782
	iowrite64(group->grpcfg.engines, idxd->reg_base + grpcfg_offset);
	dev_dbg(dev, "GRPCFG engs[%d: %#x]: %#llx\n", group->id,
		grpcfg_offset, ioread64(idxd->reg_base + grpcfg_offset));

	/* setup GRPFLAGS */
783
	grpcfg_offset = GRPFLGCFG_OFFSET(idxd, group->id);
784 785 786 787 788 789 790 791 792 793 794 795 796 797
	iowrite32(group->grpcfg.flags.bits, idxd->reg_base + grpcfg_offset);
	dev_dbg(dev, "GRPFLAGS flags[%d: %#x]: %#x\n",
		group->id, grpcfg_offset,
		ioread32(idxd->reg_base + grpcfg_offset));
}

static int idxd_groups_config_write(struct idxd_device *idxd)

{
	union gencfg_reg reg;
	int i;
	struct device *dev = &idxd->pdev->dev;

	/* Setup bandwidth token limit */
798
	if (idxd->hw.gen_cap.config_en && idxd->token_limit) {
799 800 801 802 803 804 805 806 807
		reg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET);
		reg.token_limit = idxd->token_limit;
		iowrite32(reg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET);
	}

	dev_dbg(dev, "GENCFG(%#x): %#x\n", IDXD_GENCFG_OFFSET,
		ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET));

	for (i = 0; i < idxd->max_groups; i++) {
808
		struct idxd_group *group = idxd->groups[i];
809 810 811 812 813 814 815

		idxd_group_config_write(group);
	}

	return 0;
}

816 817 818 819 820 821 822 823 824
static bool idxd_device_pasid_priv_enabled(struct idxd_device *idxd)
{
	struct pci_dev *pdev = idxd->pdev;

	if (pdev->pasid_enabled && (pdev->pasid_features & PCI_PASID_CAP_PRIV))
		return true;
	return false;
}

825 826 827 828 829 830 831 832 833 834
static int idxd_wq_config_write(struct idxd_wq *wq)
{
	struct idxd_device *idxd = wq->idxd;
	struct device *dev = &idxd->pdev->dev;
	u32 wq_offset;
	int i;

	if (!wq->group)
		return 0;

835 836 837 838 839 840 841 842
	/*
	 * Instead of memset the entire shadow copy of WQCFG, copy from the hardware after
	 * wq reset. This will copy back the sticky values that are present on some devices.
	 */
	for (i = 0; i < WQCFG_STRIDES(idxd); i++) {
		wq_offset = WQCFG_OFFSET(idxd, wq->id, i);
		wq->wqcfg->bits[i] = ioread32(idxd->reg_base + wq_offset);
	}
843

844 845 846
	if (wq->size == 0 && wq->type != IDXD_WQT_NONE)
		wq->size = WQ_DEFAULT_QUEUE_DEPTH;

847
	/* byte 0-3 */
848
	wq->wqcfg->wq_size = wq->size;
849 850

	/* bytes 4-7 */
851
	wq->wqcfg->wq_thresh = wq->threshold;
852 853

	/* byte 8-11 */
854 855 856 857 858 859 860 861 862
	if (wq_dedicated(wq))
		wq->wqcfg->mode = 1;

	if (device_pasid_enabled(idxd)) {
		wq->wqcfg->pasid_en = 1;
		if (wq->type == IDXD_WQT_KERNEL && wq_dedicated(wq))
			wq->wqcfg->pasid = idxd->pasid;
	}

863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881
	/*
	 * Here the priv bit is set depending on the WQ type. priv = 1 if the
	 * WQ type is kernel to indicate privileged access. This setting only
	 * matters for dedicated WQ. According to the DSA spec:
	 * If the WQ is in dedicated mode, WQ PASID Enable is 1, and the
	 * Privileged Mode Enable field of the PCI Express PASID capability
	 * is 0, this field must be 0.
	 *
	 * In the case of a dedicated kernel WQ that is not able to support
	 * the PASID cap, then the configuration will be rejected.
	 */
	wq->wqcfg->priv = !!(wq->type == IDXD_WQT_KERNEL);
	if (wq_dedicated(wq) && wq->wqcfg->pasid_en &&
	    !idxd_device_pasid_priv_enabled(idxd) &&
	    wq->type == IDXD_WQT_KERNEL) {
		idxd->cmd_status = IDXD_SCMD_WQ_NO_PRIV;
		return -EOPNOTSUPP;
	}

882
	wq->wqcfg->priority = wq->priority;
883

884 885 886 887
	if (idxd->hw.gen_cap.block_on_fault &&
	    test_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags))
		wq->wqcfg->bof = 1;

888 889 890
	if (idxd->hw.wq_cap.wq_ats_support)
		wq->wqcfg->wq_ats_disable = wq->ats_dis;

891
	/* bytes 12-15 */
892 893
	wq->wqcfg->max_xfer_shift = ilog2(wq->max_xfer_bytes);
	wq->wqcfg->max_batch_shift = ilog2(wq->max_batch_size);
894 895

	dev_dbg(dev, "WQ %d CFGs\n", wq->id);
896 897 898
	for (i = 0; i < WQCFG_STRIDES(idxd); i++) {
		wq_offset = WQCFG_OFFSET(idxd, wq->id, i);
		iowrite32(wq->wqcfg->bits[i], idxd->reg_base + wq_offset);
899 900 901 902 903 904 905 906 907 908 909 910 911
		dev_dbg(dev, "WQ[%d][%d][%#x]: %#x\n",
			wq->id, i, wq_offset,
			ioread32(idxd->reg_base + wq_offset));
	}

	return 0;
}

static int idxd_wqs_config_write(struct idxd_device *idxd)
{
	int i, rc;

	for (i = 0; i < idxd->max_wqs; i++) {
912
		struct idxd_wq *wq = idxd->wqs[i];
913 914 915 916 917 918 919 920 921 922 923 924 925 926 927

		rc = idxd_wq_config_write(wq);
		if (rc < 0)
			return rc;
	}

	return 0;
}

static void idxd_group_flags_setup(struct idxd_device *idxd)
{
	int i;

	/* TC-A 0 and TC-B 1 should be defaults */
	for (i = 0; i < idxd->max_groups; i++) {
928
		struct idxd_group *group = idxd->groups[i];
929 930

		if (group->tc_a == -1)
931
			group->tc_a = group->grpcfg.flags.tc_a = 0;
932 933 934
		else
			group->grpcfg.flags.tc_a = group->tc_a;
		if (group->tc_b == -1)
935
			group->tc_b = group->grpcfg.flags.tc_b = 1;
936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954
		else
			group->grpcfg.flags.tc_b = group->tc_b;
		group->grpcfg.flags.use_token_limit = group->use_token_limit;
		group->grpcfg.flags.tokens_reserved = group->tokens_reserved;
		if (group->tokens_allowed)
			group->grpcfg.flags.tokens_allowed =
				group->tokens_allowed;
		else
			group->grpcfg.flags.tokens_allowed = idxd->max_tokens;
	}
}

static int idxd_engines_setup(struct idxd_device *idxd)
{
	int i, engines = 0;
	struct idxd_engine *eng;
	struct idxd_group *group;

	for (i = 0; i < idxd->max_groups; i++) {
955
		group = idxd->groups[i];
956 957 958 959
		group->grpcfg.engines = 0;
	}

	for (i = 0; i < idxd->max_engines; i++) {
960
		eng = idxd->engines[i];
961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983
		group = eng->group;

		if (!group)
			continue;

		group->grpcfg.engines |= BIT(eng->id);
		engines++;
	}

	if (!engines)
		return -EINVAL;

	return 0;
}

static int idxd_wqs_setup(struct idxd_device *idxd)
{
	struct idxd_wq *wq;
	struct idxd_group *group;
	int i, j, configured = 0;
	struct device *dev = &idxd->pdev->dev;

	for (i = 0; i < idxd->max_groups; i++) {
984
		group = idxd->groups[i];
985 986 987 988 989
		for (j = 0; j < 4; j++)
			group->grpcfg.wqs[j] = 0;
	}

	for (i = 0; i < idxd->max_wqs; i++) {
990
		wq = idxd->wqs[i];
991 992 993 994 995
		group = wq->group;

		if (!wq->group)
			continue;

996
		if (wq_shared(wq) && !device_swq_supported(idxd)) {
997
			idxd->cmd_status = IDXD_SCMD_WQ_NO_SWQ_SUPPORT;
998
			dev_warn(dev, "No shared wq support but configured.\n");
999 1000 1001 1002 1003 1004 1005
			return -EINVAL;
		}

		group->grpcfg.wqs[wq->id / 64] |= BIT(wq->id % 64);
		configured++;
	}

1006 1007
	if (configured == 0) {
		idxd->cmd_status = IDXD_SCMD_WQ_NONE_CONFIGURED;
1008
		return -EINVAL;
1009
	}
1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038

	return 0;
}

int idxd_device_config(struct idxd_device *idxd)
{
	int rc;

	lockdep_assert_held(&idxd->dev_lock);
	rc = idxd_wqs_setup(idxd);
	if (rc < 0)
		return rc;

	rc = idxd_engines_setup(idxd);
	if (rc < 0)
		return rc;

	idxd_group_flags_setup(idxd);

	rc = idxd_wqs_config_write(idxd);
	if (rc < 0)
		return rc;

	rc = idxd_groups_config_write(idxd);
	if (rc < 0)
		return rc;

	return 0;
}
1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 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 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152

static int idxd_wq_load_config(struct idxd_wq *wq)
{
	struct idxd_device *idxd = wq->idxd;
	struct device *dev = &idxd->pdev->dev;
	int wqcfg_offset;
	int i;

	wqcfg_offset = WQCFG_OFFSET(idxd, wq->id, 0);
	memcpy_fromio(wq->wqcfg, idxd->reg_base + wqcfg_offset, idxd->wqcfg_size);

	wq->size = wq->wqcfg->wq_size;
	wq->threshold = wq->wqcfg->wq_thresh;

	/* The driver does not support shared WQ mode in read-only config yet */
	if (wq->wqcfg->mode == 0 || wq->wqcfg->pasid_en)
		return -EOPNOTSUPP;

	set_bit(WQ_FLAG_DEDICATED, &wq->flags);

	wq->priority = wq->wqcfg->priority;

	for (i = 0; i < WQCFG_STRIDES(idxd); i++) {
		wqcfg_offset = WQCFG_OFFSET(idxd, wq->id, i);
		dev_dbg(dev, "WQ[%d][%d][%#x]: %#x\n", wq->id, i, wqcfg_offset, wq->wqcfg->bits[i]);
	}

	return 0;
}

static void idxd_group_load_config(struct idxd_group *group)
{
	struct idxd_device *idxd = group->idxd;
	struct device *dev = &idxd->pdev->dev;
	int i, j, grpcfg_offset;

	/*
	 * Load WQS bit fields
	 * Iterate through all 256 bits 64 bits at a time
	 */
	for (i = 0; i < GRPWQCFG_STRIDES; i++) {
		struct idxd_wq *wq;

		grpcfg_offset = GRPWQCFG_OFFSET(idxd, group->id, i);
		group->grpcfg.wqs[i] = ioread64(idxd->reg_base + grpcfg_offset);
		dev_dbg(dev, "GRPCFG wq[%d:%d: %#x]: %#llx\n",
			group->id, i, grpcfg_offset, group->grpcfg.wqs[i]);

		if (i * 64 >= idxd->max_wqs)
			break;

		/* Iterate through all 64 bits and check for wq set */
		for (j = 0; j < 64; j++) {
			int id = i * 64 + j;

			/* No need to check beyond max wqs */
			if (id >= idxd->max_wqs)
				break;

			/* Set group assignment for wq if wq bit is set */
			if (group->grpcfg.wqs[i] & BIT(j)) {
				wq = idxd->wqs[id];
				wq->group = group;
			}
		}
	}

	grpcfg_offset = GRPENGCFG_OFFSET(idxd, group->id);
	group->grpcfg.engines = ioread64(idxd->reg_base + grpcfg_offset);
	dev_dbg(dev, "GRPCFG engs[%d: %#x]: %#llx\n", group->id,
		grpcfg_offset, group->grpcfg.engines);

	/* Iterate through all 64 bits to check engines set */
	for (i = 0; i < 64; i++) {
		if (i >= idxd->max_engines)
			break;

		if (group->grpcfg.engines & BIT(i)) {
			struct idxd_engine *engine = idxd->engines[i];

			engine->group = group;
		}
	}

	grpcfg_offset = GRPFLGCFG_OFFSET(idxd, group->id);
	group->grpcfg.flags.bits = ioread32(idxd->reg_base + grpcfg_offset);
	dev_dbg(dev, "GRPFLAGS flags[%d: %#x]: %#x\n",
		group->id, grpcfg_offset, group->grpcfg.flags.bits);
}

int idxd_device_load_config(struct idxd_device *idxd)
{
	union gencfg_reg reg;
	int i, rc;

	reg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET);
	idxd->token_limit = reg.token_limit;

	for (i = 0; i < idxd->max_groups; i++) {
		struct idxd_group *group = idxd->groups[i];

		idxd_group_load_config(group);
	}

	for (i = 0; i < idxd->max_wqs; i++) {
		struct idxd_wq *wq = idxd->wqs[i];

		rc = idxd_wq_load_config(wq);
		if (rc < 0)
			return rc;
	}

	return 0;
}
1153

1154
int __drv_enable_wq(struct idxd_wq *wq)
1155 1156 1157 1158 1159 1160 1161
{
	struct idxd_device *idxd = wq->idxd;
	struct device *dev = &idxd->pdev->dev;
	int rc = -ENXIO;

	lockdep_assert_held(&wq->wq_lock);

1162 1163
	if (idxd->state != IDXD_DEV_ENABLED) {
		idxd->cmd_status = IDXD_SCMD_DEV_NOT_ENABLED;
1164
		goto err;
1165
	}
1166 1167 1168

	if (wq->state != IDXD_WQ_DISABLED) {
		dev_dbg(dev, "wq %d already enabled.\n", wq->id);
1169
		idxd->cmd_status = IDXD_SCMD_WQ_ENABLED;
1170 1171 1172 1173 1174 1175
		rc = -EBUSY;
		goto err;
	}

	if (!wq->group) {
		dev_dbg(dev, "wq %d not attached to group.\n", wq->id);
1176
		idxd->cmd_status = IDXD_SCMD_WQ_NO_GRP;
1177 1178 1179 1180
		goto err;
	}

	if (strlen(wq->name) == 0) {
1181
		idxd->cmd_status = IDXD_SCMD_WQ_NO_NAME;
1182 1183 1184 1185 1186 1187 1188
		dev_dbg(dev, "wq %d name not set.\n", wq->id);
		goto err;
	}

	/* Shared WQ checks */
	if (wq_shared(wq)) {
		if (!device_swq_supported(idxd)) {
1189
			idxd->cmd_status = IDXD_SCMD_WQ_NO_SVM;
1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201
			dev_dbg(dev, "PASID not enabled and shared wq.\n");
			goto err;
		}
		/*
		 * Shared wq with the threshold set to 0 means the user
		 * did not set the threshold or transitioned from a
		 * dedicated wq but did not set threshold. A value
		 * of 0 would effectively disable the shared wq. The
		 * driver does not allow a value of 0 to be set for
		 * threshold via sysfs.
		 */
		if (wq->threshold == 0) {
1202
			idxd->cmd_status = IDXD_SCMD_WQ_NO_THRESH;
1203 1204 1205 1206 1207
			dev_dbg(dev, "Shared wq and threshold 0.\n");
			goto err;
		}
	}

1208
	rc = 0;
1209
	spin_lock(&idxd->dev_lock);
1210 1211
	if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
		rc = idxd_device_config(idxd);
1212
	spin_unlock(&idxd->dev_lock);
1213 1214 1215 1216 1217
	if (rc < 0) {
		dev_dbg(dev, "Writing wq %d config failed: %d\n", wq->id, rc);
		goto err;
	}

1218 1219 1220 1221 1222 1223 1224
	/*
	 * Device has 1 misc interrupt and N interrupts for descriptor completion. To
	 * assign WQ to interrupt, we will take the N+1 interrupt since vector 0 is
	 * for the misc interrupt.
	 */
	wq->ie = &idxd->irq_entries[wq->id + 1];

1225 1226 1227 1228 1229 1230 1231 1232
	rc = idxd_wq_enable(wq);
	if (rc < 0) {
		dev_dbg(dev, "wq %d enabling failed: %d\n", wq->id, rc);
		goto err;
	}

	rc = idxd_wq_map_portal(wq);
	if (rc < 0) {
1233
		idxd->cmd_status = IDXD_SCMD_WQ_PORTAL_ERR;
1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257
		dev_dbg(dev, "wq %d portal mapping failed: %d\n", wq->id, rc);
		goto err_map_portal;
	}

	wq->client_count = 0;
	return 0;

err_map_portal:
	rc = idxd_wq_disable(wq, false);
	if (rc < 0)
		dev_dbg(dev, "wq %s disable failed\n", dev_name(wq_confdev(wq)));
err:
	return rc;
}

int drv_enable_wq(struct idxd_wq *wq)
{
	int rc;

	mutex_lock(&wq->wq_lock);
	rc = __drv_enable_wq(wq);
	mutex_unlock(&wq->wq_lock);
	return rc;
}
1258

1259
void __drv_disable_wq(struct idxd_wq *wq)
1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274
{
	struct idxd_device *idxd = wq->idxd;
	struct device *dev = &idxd->pdev->dev;

	lockdep_assert_held(&wq->wq_lock);

	if (idxd_wq_refcount(wq))
		dev_warn(dev, "Clients has claim on wq %d: %d\n",
			 wq->id, idxd_wq_refcount(wq));

	idxd_wq_unmap_portal(wq);

	idxd_wq_drain(wq);
	idxd_wq_reset(wq);

1275
	wq->ie = NULL;
1276 1277 1278 1279 1280 1281 1282 1283 1284
	wq->client_count = 0;
}

void drv_disable_wq(struct idxd_wq *wq)
{
	mutex_lock(&wq->wq_lock);
	__drv_disable_wq(wq);
	mutex_unlock(&wq->wq_lock);
}
1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295

int idxd_device_drv_probe(struct idxd_dev *idxd_dev)
{
	struct idxd_device *idxd = idxd_dev_to_idxd(idxd_dev);
	int rc = 0;

	/*
	 * Device should be in disabled state for the idxd_drv to load. If it's in
	 * enabled state, then the device was altered outside of driver's control.
	 * If the state is in halted state, then we don't want to proceed.
	 */
1296 1297
	if (idxd->state != IDXD_DEV_DISABLED) {
		idxd->cmd_status = IDXD_SCMD_DEV_ENABLED;
1298
		return -ENXIO;
1299
	}
1300 1301

	/* Device configuration */
1302
	spin_lock(&idxd->dev_lock);
1303 1304
	if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
		rc = idxd_device_config(idxd);
1305
	spin_unlock(&idxd->dev_lock);
1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317
	if (rc < 0)
		return -ENXIO;

	/* Start device */
	rc = idxd_device_enable(idxd);
	if (rc < 0)
		return rc;

	/* Setup DMA device without channels */
	rc = idxd_register_dma_device(idxd);
	if (rc < 0) {
		idxd_device_disable(idxd);
1318
		idxd->cmd_status = IDXD_SCMD_DEV_DMA_ERR;
1319 1320 1321
		return rc;
	}

1322
	idxd->cmd_status = 0;
1323 1324
	return 0;
}
1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346

void idxd_device_drv_remove(struct idxd_dev *idxd_dev)
{
	struct device *dev = &idxd_dev->conf_dev;
	struct idxd_device *idxd = idxd_dev_to_idxd(idxd_dev);
	int i;

	for (i = 0; i < idxd->max_wqs; i++) {
		struct idxd_wq *wq = idxd->wqs[i];
		struct device *wq_dev = wq_confdev(wq);

		if (wq->state == IDXD_WQ_DISABLED)
			continue;
		dev_warn(dev, "Active wq %d on disable %s.\n", i, dev_name(wq_dev));
		device_release_driver(wq_dev);
	}

	idxd_unregister_dma_device(idxd);
	idxd_device_disable(idxd);
	if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
		idxd_device_reset(idxd);
}
1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359

static enum idxd_dev_type dev_types[] = {
	IDXD_DEV_DSA,
	IDXD_DEV_IAX,
	IDXD_DEV_NONE,
};

struct idxd_device_driver idxd_drv = {
	.type = dev_types,
	.probe = idxd_device_drv_probe,
	.remove = idxd_device_drv_remove,
	.name = "idxd",
};
1360
EXPORT_SYMBOL_GPL(idxd_drv);