nfit.c 55.5 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
/*
 * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of version 2 of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * 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/list_sort.h>
#include <linux/libnvdimm.h>
#include <linux/module.h>
16
#include <linux/mutex.h>
17
#include <linux/ndctl.h>
18
#include <linux/delay.h>
19 20
#include <linux/list.h>
#include <linux/acpi.h>
21
#include <linux/sort.h>
22
#include <linux/pmem.h>
23
#include <linux/io.h>
24
#include <asm/cacheflush.h>
25 26
#include "nfit.h"

27 28 29 30
/*
 * For readq() and writeq() on 32-bit builds, the hi-lo, lo-hi order is
 * irrelevant.
 */
31
#include <linux/io-64-nonatomic-hi-lo.h>
32

33 34 35 36
static bool force_enable_dimms;
module_param(force_enable_dimms, bool, S_IRUGO|S_IWUSR);
MODULE_PARM_DESC(force_enable_dimms, "Ignore _STA (ACPI DIMM device) status");

V
Vishal Verma 已提交
37 38 39 40 41 42 43 44 45
struct nfit_table_prev {
	struct list_head spas;
	struct list_head memdevs;
	struct list_head dcrs;
	struct list_head bdws;
	struct list_head idts;
	struct list_head flushes;
};

46 47
static u8 nfit_uuid[NFIT_UUID_MAX][16];

48
const u8 *to_nfit_uuid(enum nfit_uuids id)
49 50 51
{
	return nfit_uuid[id];
}
52
EXPORT_SYMBOL(to_nfit_uuid);
53

54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74
static struct acpi_nfit_desc *to_acpi_nfit_desc(
		struct nvdimm_bus_descriptor *nd_desc)
{
	return container_of(nd_desc, struct acpi_nfit_desc, nd_desc);
}

static struct acpi_device *to_acpi_dev(struct acpi_nfit_desc *acpi_desc)
{
	struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc;

	/*
	 * If provider == 'ACPI.NFIT' we can assume 'dev' is a struct
	 * acpi_device.
	 */
	if (!nd_desc->provider_name
			|| strcmp(nd_desc->provider_name, "ACPI.NFIT") != 0)
		return NULL;

	return to_acpi_device(acpi_desc->dev);
}

75 76 77 78
static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc,
		struct nvdimm *nvdimm, unsigned int cmd, void *buf,
		unsigned int buf_len)
{
79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95
	struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc);
	const struct nd_cmd_desc *desc = NULL;
	union acpi_object in_obj, in_buf, *out_obj;
	struct device *dev = acpi_desc->dev;
	const char *cmd_name, *dimm_name;
	unsigned long dsm_mask;
	acpi_handle handle;
	const u8 *uuid;
	u32 offset;
	int rc, i;

	if (nvdimm) {
		struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
		struct acpi_device *adev = nfit_mem->adev;

		if (!adev)
			return -ENOTTY;
96
		dimm_name = nvdimm_name(nvdimm);
97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200
		cmd_name = nvdimm_cmd_name(cmd);
		dsm_mask = nfit_mem->dsm_mask;
		desc = nd_cmd_dimm_desc(cmd);
		uuid = to_nfit_uuid(NFIT_DEV_DIMM);
		handle = adev->handle;
	} else {
		struct acpi_device *adev = to_acpi_dev(acpi_desc);

		cmd_name = nvdimm_bus_cmd_name(cmd);
		dsm_mask = nd_desc->dsm_mask;
		desc = nd_cmd_bus_desc(cmd);
		uuid = to_nfit_uuid(NFIT_DEV_BUS);
		handle = adev->handle;
		dimm_name = "bus";
	}

	if (!desc || (cmd && (desc->out_num + desc->in_num == 0)))
		return -ENOTTY;

	if (!test_bit(cmd, &dsm_mask))
		return -ENOTTY;

	in_obj.type = ACPI_TYPE_PACKAGE;
	in_obj.package.count = 1;
	in_obj.package.elements = &in_buf;
	in_buf.type = ACPI_TYPE_BUFFER;
	in_buf.buffer.pointer = buf;
	in_buf.buffer.length = 0;

	/* libnvdimm has already validated the input envelope */
	for (i = 0; i < desc->in_num; i++)
		in_buf.buffer.length += nd_cmd_in_size(nvdimm, cmd, desc,
				i, buf);

	if (IS_ENABLED(CONFIG_ACPI_NFIT_DEBUG)) {
		dev_dbg(dev, "%s:%s cmd: %s input length: %d\n", __func__,
				dimm_name, cmd_name, in_buf.buffer.length);
		print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4,
				4, in_buf.buffer.pointer, min_t(u32, 128,
					in_buf.buffer.length), true);
	}

	out_obj = acpi_evaluate_dsm(handle, uuid, 1, cmd, &in_obj);
	if (!out_obj) {
		dev_dbg(dev, "%s:%s _DSM failed cmd: %s\n", __func__, dimm_name,
				cmd_name);
		return -EINVAL;
	}

	if (out_obj->package.type != ACPI_TYPE_BUFFER) {
		dev_dbg(dev, "%s:%s unexpected output object type cmd: %s type: %d\n",
				__func__, dimm_name, cmd_name, out_obj->type);
		rc = -EINVAL;
		goto out;
	}

	if (IS_ENABLED(CONFIG_ACPI_NFIT_DEBUG)) {
		dev_dbg(dev, "%s:%s cmd: %s output length: %d\n", __func__,
				dimm_name, cmd_name, out_obj->buffer.length);
		print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4,
				4, out_obj->buffer.pointer, min_t(u32, 128,
					out_obj->buffer.length), true);
	}

	for (i = 0, offset = 0; i < desc->out_num; i++) {
		u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, buf,
				(u32 *) out_obj->buffer.pointer);

		if (offset + out_size > out_obj->buffer.length) {
			dev_dbg(dev, "%s:%s output object underflow cmd: %s field: %d\n",
					__func__, dimm_name, cmd_name, i);
			break;
		}

		if (in_buf.buffer.length + offset + out_size > buf_len) {
			dev_dbg(dev, "%s:%s output overrun cmd: %s field: %d\n",
					__func__, dimm_name, cmd_name, i);
			rc = -ENXIO;
			goto out;
		}
		memcpy(buf + in_buf.buffer.length + offset,
				out_obj->buffer.pointer + offset, out_size);
		offset += out_size;
	}
	if (offset + in_buf.buffer.length < buf_len) {
		if (i >= 1) {
			/*
			 * status valid, return the number of bytes left
			 * unfilled in the output buffer
			 */
			rc = buf_len - offset - in_buf.buffer.length;
		} else {
			dev_err(dev, "%s:%s underrun cmd: %s buf_len: %d out_len: %d\n",
					__func__, dimm_name, cmd_name, buf_len,
					offset);
			rc = -ENXIO;
		}
	} else
		rc = 0;

 out:
	ACPI_FREE(out_obj);

	return rc;
201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233
}

static const char *spa_type_name(u16 type)
{
	static const char *to_name[] = {
		[NFIT_SPA_VOLATILE] = "volatile",
		[NFIT_SPA_PM] = "pmem",
		[NFIT_SPA_DCR] = "dimm-control-region",
		[NFIT_SPA_BDW] = "block-data-window",
		[NFIT_SPA_VDISK] = "volatile-disk",
		[NFIT_SPA_VCD] = "volatile-cd",
		[NFIT_SPA_PDISK] = "persistent-disk",
		[NFIT_SPA_PCD] = "persistent-cd",

	};

	if (type > NFIT_SPA_PCD)
		return "unknown";

	return to_name[type];
}

static int nfit_spa_type(struct acpi_nfit_system_address *spa)
{
	int i;

	for (i = 0; i < NFIT_UUID_MAX; i++)
		if (memcmp(to_nfit_uuid(i), spa->range_guid, 16) == 0)
			return i;
	return -1;
}

static bool add_spa(struct acpi_nfit_desc *acpi_desc,
V
Vishal Verma 已提交
234
		struct nfit_table_prev *prev,
235 236
		struct acpi_nfit_system_address *spa)
{
237
	size_t length = min_t(size_t, sizeof(*spa), spa->header.length);
238
	struct device *dev = acpi_desc->dev;
V
Vishal Verma 已提交
239 240 241
	struct nfit_spa *nfit_spa;

	list_for_each_entry(nfit_spa, &prev->spas, list) {
242
		if (memcmp(nfit_spa->spa, spa, length) == 0) {
V
Vishal Verma 已提交
243 244 245 246
			list_move_tail(&nfit_spa->list, &acpi_desc->spas);
			return true;
		}
	}
247

V
Vishal Verma 已提交
248
	nfit_spa = devm_kzalloc(dev, sizeof(*nfit_spa), GFP_KERNEL);
249 250 251 252 253 254 255 256 257 258 259 260
	if (!nfit_spa)
		return false;
	INIT_LIST_HEAD(&nfit_spa->list);
	nfit_spa->spa = spa;
	list_add_tail(&nfit_spa->list, &acpi_desc->spas);
	dev_dbg(dev, "%s: spa index: %d type: %s\n", __func__,
			spa->range_index,
			spa_type_name(nfit_spa_type(spa)));
	return true;
}

static bool add_memdev(struct acpi_nfit_desc *acpi_desc,
V
Vishal Verma 已提交
261
		struct nfit_table_prev *prev,
262 263
		struct acpi_nfit_memory_map *memdev)
{
264
	size_t length = min_t(size_t, sizeof(*memdev), memdev->header.length);
265
	struct device *dev = acpi_desc->dev;
V
Vishal Verma 已提交
266
	struct nfit_memdev *nfit_memdev;
267

V
Vishal Verma 已提交
268
	list_for_each_entry(nfit_memdev, &prev->memdevs, list)
269
		if (memcmp(nfit_memdev->memdev, memdev, length) == 0) {
V
Vishal Verma 已提交
270 271 272 273 274
			list_move_tail(&nfit_memdev->list, &acpi_desc->memdevs);
			return true;
		}

	nfit_memdev = devm_kzalloc(dev, sizeof(*nfit_memdev), GFP_KERNEL);
275 276 277 278 279 280 281 282 283 284 285 286
	if (!nfit_memdev)
		return false;
	INIT_LIST_HEAD(&nfit_memdev->list);
	nfit_memdev->memdev = memdev;
	list_add_tail(&nfit_memdev->list, &acpi_desc->memdevs);
	dev_dbg(dev, "%s: memdev handle: %#x spa: %d dcr: %d\n",
			__func__, memdev->device_handle, memdev->range_index,
			memdev->region_index);
	return true;
}

static bool add_dcr(struct acpi_nfit_desc *acpi_desc,
V
Vishal Verma 已提交
287
		struct nfit_table_prev *prev,
288 289
		struct acpi_nfit_control_region *dcr)
{
290
	size_t length = min_t(size_t, sizeof(*dcr), dcr->header.length);
291
	struct device *dev = acpi_desc->dev;
V
Vishal Verma 已提交
292 293 294
	struct nfit_dcr *nfit_dcr;

	list_for_each_entry(nfit_dcr, &prev->dcrs, list)
295
		if (memcmp(nfit_dcr->dcr, dcr, length) == 0) {
V
Vishal Verma 已提交
296 297 298
			list_move_tail(&nfit_dcr->list, &acpi_desc->dcrs);
			return true;
		}
299

V
Vishal Verma 已提交
300
	nfit_dcr = devm_kzalloc(dev, sizeof(*nfit_dcr), GFP_KERNEL);
301 302 303 304 305 306 307 308 309 310 311
	if (!nfit_dcr)
		return false;
	INIT_LIST_HEAD(&nfit_dcr->list);
	nfit_dcr->dcr = dcr;
	list_add_tail(&nfit_dcr->list, &acpi_desc->dcrs);
	dev_dbg(dev, "%s: dcr index: %d windows: %d\n", __func__,
			dcr->region_index, dcr->windows);
	return true;
}

static bool add_bdw(struct acpi_nfit_desc *acpi_desc,
V
Vishal Verma 已提交
312
		struct nfit_table_prev *prev,
313 314
		struct acpi_nfit_data_region *bdw)
{
315
	size_t length = min_t(size_t, sizeof(*bdw), bdw->header.length);
316
	struct device *dev = acpi_desc->dev;
V
Vishal Verma 已提交
317 318 319
	struct nfit_bdw *nfit_bdw;

	list_for_each_entry(nfit_bdw, &prev->bdws, list)
320
		if (memcmp(nfit_bdw->bdw, bdw, length) == 0) {
V
Vishal Verma 已提交
321 322 323
			list_move_tail(&nfit_bdw->list, &acpi_desc->bdws);
			return true;
		}
324

V
Vishal Verma 已提交
325
	nfit_bdw = devm_kzalloc(dev, sizeof(*nfit_bdw), GFP_KERNEL);
326 327 328 329 330 331 332 333 334 335
	if (!nfit_bdw)
		return false;
	INIT_LIST_HEAD(&nfit_bdw->list);
	nfit_bdw->bdw = bdw;
	list_add_tail(&nfit_bdw->list, &acpi_desc->bdws);
	dev_dbg(dev, "%s: bdw dcr: %d windows: %d\n", __func__,
			bdw->region_index, bdw->windows);
	return true;
}

336
static bool add_idt(struct acpi_nfit_desc *acpi_desc,
V
Vishal Verma 已提交
337
		struct nfit_table_prev *prev,
338 339
		struct acpi_nfit_interleave *idt)
{
340
	size_t length = min_t(size_t, sizeof(*idt), idt->header.length);
341
	struct device *dev = acpi_desc->dev;
V
Vishal Verma 已提交
342 343 344
	struct nfit_idt *nfit_idt;

	list_for_each_entry(nfit_idt, &prev->idts, list)
345
		if (memcmp(nfit_idt->idt, idt, length) == 0) {
V
Vishal Verma 已提交
346 347 348
			list_move_tail(&nfit_idt->list, &acpi_desc->idts);
			return true;
		}
349

V
Vishal Verma 已提交
350
	nfit_idt = devm_kzalloc(dev, sizeof(*nfit_idt), GFP_KERNEL);
351 352 353 354 355 356 357 358 359 360
	if (!nfit_idt)
		return false;
	INIT_LIST_HEAD(&nfit_idt->list);
	nfit_idt->idt = idt;
	list_add_tail(&nfit_idt->list, &acpi_desc->idts);
	dev_dbg(dev, "%s: idt index: %d num_lines: %d\n", __func__,
			idt->interleave_index, idt->line_count);
	return true;
}

361
static bool add_flush(struct acpi_nfit_desc *acpi_desc,
V
Vishal Verma 已提交
362
		struct nfit_table_prev *prev,
363 364
		struct acpi_nfit_flush_address *flush)
{
365
	size_t length = min_t(size_t, sizeof(*flush), flush->header.length);
366
	struct device *dev = acpi_desc->dev;
V
Vishal Verma 已提交
367
	struct nfit_flush *nfit_flush;
368

V
Vishal Verma 已提交
369
	list_for_each_entry(nfit_flush, &prev->flushes, list)
370
		if (memcmp(nfit_flush->flush, flush, length) == 0) {
V
Vishal Verma 已提交
371 372 373 374 375
			list_move_tail(&nfit_flush->list, &acpi_desc->flushes);
			return true;
		}

	nfit_flush = devm_kzalloc(dev, sizeof(*nfit_flush), GFP_KERNEL);
376 377 378 379 380 381 382 383 384 385
	if (!nfit_flush)
		return false;
	INIT_LIST_HEAD(&nfit_flush->list);
	nfit_flush->flush = flush;
	list_add_tail(&nfit_flush->list, &acpi_desc->flushes);
	dev_dbg(dev, "%s: nfit_flush handle: %d hint_count: %d\n", __func__,
			flush->device_handle, flush->hint_count);
	return true;
}

V
Vishal Verma 已提交
386 387
static void *add_table(struct acpi_nfit_desc *acpi_desc,
		struct nfit_table_prev *prev, void *table, const void *end)
388 389 390 391 392 393 394 395 396
{
	struct device *dev = acpi_desc->dev;
	struct acpi_nfit_header *hdr;
	void *err = ERR_PTR(-ENOMEM);

	if (table >= end)
		return NULL;

	hdr = table;
397 398 399 400 401 402
	if (!hdr->length) {
		dev_warn(dev, "found a zero length table '%d' parsing nfit\n",
			hdr->type);
		return NULL;
	}

403 404
	switch (hdr->type) {
	case ACPI_NFIT_TYPE_SYSTEM_ADDRESS:
V
Vishal Verma 已提交
405
		if (!add_spa(acpi_desc, prev, table))
406 407 408
			return err;
		break;
	case ACPI_NFIT_TYPE_MEMORY_MAP:
V
Vishal Verma 已提交
409
		if (!add_memdev(acpi_desc, prev, table))
410 411 412
			return err;
		break;
	case ACPI_NFIT_TYPE_CONTROL_REGION:
V
Vishal Verma 已提交
413
		if (!add_dcr(acpi_desc, prev, table))
414 415 416
			return err;
		break;
	case ACPI_NFIT_TYPE_DATA_REGION:
V
Vishal Verma 已提交
417
		if (!add_bdw(acpi_desc, prev, table))
418 419 420
			return err;
		break;
	case ACPI_NFIT_TYPE_INTERLEAVE:
V
Vishal Verma 已提交
421
		if (!add_idt(acpi_desc, prev, table))
422
			return err;
423 424
		break;
	case ACPI_NFIT_TYPE_FLUSH_ADDRESS:
V
Vishal Verma 已提交
425
		if (!add_flush(acpi_desc, prev, table))
426
			return err;
427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471
		break;
	case ACPI_NFIT_TYPE_SMBIOS:
		dev_dbg(dev, "%s: smbios\n", __func__);
		break;
	default:
		dev_err(dev, "unknown table '%d' parsing nfit\n", hdr->type);
		break;
	}

	return table + hdr->length;
}

static void nfit_mem_find_spa_bdw(struct acpi_nfit_desc *acpi_desc,
		struct nfit_mem *nfit_mem)
{
	u32 device_handle = __to_nfit_memdev(nfit_mem)->device_handle;
	u16 dcr = nfit_mem->dcr->region_index;
	struct nfit_spa *nfit_spa;

	list_for_each_entry(nfit_spa, &acpi_desc->spas, list) {
		u16 range_index = nfit_spa->spa->range_index;
		int type = nfit_spa_type(nfit_spa->spa);
		struct nfit_memdev *nfit_memdev;

		if (type != NFIT_SPA_BDW)
			continue;

		list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) {
			if (nfit_memdev->memdev->range_index != range_index)
				continue;
			if (nfit_memdev->memdev->device_handle != device_handle)
				continue;
			if (nfit_memdev->memdev->region_index != dcr)
				continue;

			nfit_mem->spa_bdw = nfit_spa->spa;
			return;
		}
	}

	dev_dbg(acpi_desc->dev, "SPA-BDW not found for SPA-DCR %d\n",
			nfit_mem->spa_dcr->range_index);
	nfit_mem->bdw = NULL;
}

472
static void nfit_mem_init_bdw(struct acpi_nfit_desc *acpi_desc,
473 474 475
		struct nfit_mem *nfit_mem, struct acpi_nfit_system_address *spa)
{
	u16 dcr = __to_nfit_memdev(nfit_mem)->region_index;
476
	struct nfit_memdev *nfit_memdev;
477
	struct nfit_flush *nfit_flush;
478
	struct nfit_bdw *nfit_bdw;
479 480
	struct nfit_idt *nfit_idt;
	u16 idt_idx, range_index;
481 482 483 484 485 486 487 488 489

	list_for_each_entry(nfit_bdw, &acpi_desc->bdws, list) {
		if (nfit_bdw->bdw->region_index != dcr)
			continue;
		nfit_mem->bdw = nfit_bdw->bdw;
		break;
	}

	if (!nfit_mem->bdw)
490
		return;
491 492

	nfit_mem_find_spa_bdw(acpi_desc, nfit_mem);
493 494

	if (!nfit_mem->spa_bdw)
495
		return;
496 497 498 499 500 501 502 503 504 505 506 507 508 509

	range_index = nfit_mem->spa_bdw->range_index;
	list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) {
		if (nfit_memdev->memdev->range_index != range_index ||
				nfit_memdev->memdev->region_index != dcr)
			continue;
		nfit_mem->memdev_bdw = nfit_memdev->memdev;
		idt_idx = nfit_memdev->memdev->interleave_index;
		list_for_each_entry(nfit_idt, &acpi_desc->idts, list) {
			if (nfit_idt->idt->interleave_index != idt_idx)
				continue;
			nfit_mem->idt_bdw = nfit_idt->idt;
			break;
		}
510 511 512 513 514 515 516 517

		list_for_each_entry(nfit_flush, &acpi_desc->flushes, list) {
			if (nfit_flush->flush->device_handle !=
					nfit_memdev->memdev->device_handle)
				continue;
			nfit_mem->nfit_flush = nfit_flush;
			break;
		}
518 519
		break;
	}
520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537
}

static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
		struct acpi_nfit_system_address *spa)
{
	struct nfit_mem *nfit_mem, *found;
	struct nfit_memdev *nfit_memdev;
	int type = nfit_spa_type(spa);

	switch (type) {
	case NFIT_SPA_DCR:
	case NFIT_SPA_PM:
		break;
	default:
		return 0;
	}

	list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) {
538 539 540
		struct nfit_dcr *nfit_dcr;
		u32 device_handle;
		u16 dcr;
541 542 543 544 545

		if (nfit_memdev->memdev->range_index != spa->range_index)
			continue;
		found = NULL;
		dcr = nfit_memdev->memdev->region_index;
546
		device_handle = nfit_memdev->memdev->device_handle;
547
		list_for_each_entry(nfit_mem, &acpi_desc->dimms, list)
548 549
			if (__to_nfit_memdev(nfit_mem)->device_handle
					== device_handle) {
550 551 552 553 554 555 556 557 558 559 560 561
				found = nfit_mem;
				break;
			}

		if (found)
			nfit_mem = found;
		else {
			nfit_mem = devm_kzalloc(acpi_desc->dev,
					sizeof(*nfit_mem), GFP_KERNEL);
			if (!nfit_mem)
				return -ENOMEM;
			INIT_LIST_HEAD(&nfit_mem->list);
562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586
			list_add(&nfit_mem->list, &acpi_desc->dimms);
		}

		list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) {
			if (nfit_dcr->dcr->region_index != dcr)
				continue;
			/*
			 * Record the control region for the dimm.  For
			 * the ACPI 6.1 case, where there are separate
			 * control regions for the pmem vs blk
			 * interfaces, be sure to record the extended
			 * blk details.
			 */
			if (!nfit_mem->dcr)
				nfit_mem->dcr = nfit_dcr->dcr;
			else if (nfit_mem->dcr->windows == 0
					&& nfit_dcr->dcr->windows)
				nfit_mem->dcr = nfit_dcr->dcr;
			break;
		}

		if (dcr && !nfit_mem->dcr) {
			dev_err(acpi_desc->dev, "SPA %d missing DCR %d\n",
					spa->range_index, dcr);
			return -ENODEV;
587 588 589
		}

		if (type == NFIT_SPA_DCR) {
590 591 592
			struct nfit_idt *nfit_idt;
			u16 idt_idx;

593 594 595
			/* multiple dimms may share a SPA when interleaved */
			nfit_mem->spa_dcr = spa;
			nfit_mem->memdev_dcr = nfit_memdev->memdev;
596 597 598 599 600 601 602
			idt_idx = nfit_memdev->memdev->interleave_index;
			list_for_each_entry(nfit_idt, &acpi_desc->idts, list) {
				if (nfit_idt->idt->interleave_index != idt_idx)
					continue;
				nfit_mem->idt_dcr = nfit_idt->idt;
				break;
			}
603
			nfit_mem_init_bdw(acpi_desc, nfit_mem, spa);
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
		} else {
			/*
			 * A single dimm may belong to multiple SPA-PM
			 * ranges, record at least one in addition to
			 * any SPA-DCR range.
			 */
			nfit_mem->memdev_pmem = nfit_memdev->memdev;
		}
	}

	return 0;
}

static int nfit_mem_cmp(void *priv, struct list_head *_a, struct list_head *_b)
{
	struct nfit_mem *a = container_of(_a, typeof(*a), list);
	struct nfit_mem *b = container_of(_b, typeof(*b), list);
	u32 handleA, handleB;

	handleA = __to_nfit_memdev(a)->device_handle;
	handleB = __to_nfit_memdev(b)->device_handle;
	if (handleA < handleB)
		return -1;
	else if (handleA > handleB)
		return 1;
	return 0;
}

static int nfit_mem_init(struct acpi_nfit_desc *acpi_desc)
{
	struct nfit_spa *nfit_spa;

	/*
	 * For each SPA-DCR or SPA-PMEM address range find its
	 * corresponding MEMDEV(s).  From each MEMDEV find the
	 * corresponding DCR.  Then, if we're operating on a SPA-DCR,
	 * try to find a SPA-BDW and a corresponding BDW that references
	 * the DCR.  Throw it all into an nfit_mem object.  Note, that
	 * BDWs are optional.
	 */
	list_for_each_entry(nfit_spa, &acpi_desc->spas, list) {
		int rc;

		rc = nfit_mem_dcr_init(acpi_desc, nfit_spa->spa);
		if (rc)
			return rc;
	}

	list_sort(NULL, &acpi_desc->dimms, nfit_mem_cmp);

	return 0;
}

657 658 659 660 661 662 663
static ssize_t revision_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);

664
	return sprintf(buf, "%d\n", acpi_desc->acpi_header.revision);
665 666 667 668 669 670 671 672 673 674 675 676 677
}
static DEVICE_ATTR_RO(revision);

static struct attribute *acpi_nfit_attributes[] = {
	&dev_attr_revision.attr,
	NULL,
};

static struct attribute_group acpi_nfit_attribute_group = {
	.name = "nfit",
	.attrs = acpi_nfit_attributes,
};

678
const struct attribute_group *acpi_nfit_attribute_groups[] = {
679 680 681 682
	&nvdimm_bus_attribute_group,
	&acpi_nfit_attribute_group,
	NULL,
};
683
EXPORT_SYMBOL_GPL(acpi_nfit_attribute_groups);
684

685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763
static struct acpi_nfit_memory_map *to_nfit_memdev(struct device *dev)
{
	struct nvdimm *nvdimm = to_nvdimm(dev);
	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);

	return __to_nfit_memdev(nfit_mem);
}

static struct acpi_nfit_control_region *to_nfit_dcr(struct device *dev)
{
	struct nvdimm *nvdimm = to_nvdimm(dev);
	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);

	return nfit_mem->dcr;
}

static ssize_t handle_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct acpi_nfit_memory_map *memdev = to_nfit_memdev(dev);

	return sprintf(buf, "%#x\n", memdev->device_handle);
}
static DEVICE_ATTR_RO(handle);

static ssize_t phys_id_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct acpi_nfit_memory_map *memdev = to_nfit_memdev(dev);

	return sprintf(buf, "%#x\n", memdev->physical_id);
}
static DEVICE_ATTR_RO(phys_id);

static ssize_t vendor_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);

	return sprintf(buf, "%#x\n", dcr->vendor_id);
}
static DEVICE_ATTR_RO(vendor);

static ssize_t rev_id_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);

	return sprintf(buf, "%#x\n", dcr->revision_id);
}
static DEVICE_ATTR_RO(rev_id);

static ssize_t device_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);

	return sprintf(buf, "%#x\n", dcr->device_id);
}
static DEVICE_ATTR_RO(device);

static ssize_t format_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);

	return sprintf(buf, "%#x\n", dcr->code);
}
static DEVICE_ATTR_RO(format);

static ssize_t serial_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);

	return sprintf(buf, "%#x\n", dcr->serial_number);
}
static DEVICE_ATTR_RO(serial);

764 765 766 767 768 769
static ssize_t flags_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	u16 flags = to_nfit_memdev(dev)->flags;

	return sprintf(buf, "%s%s%s%s%s\n",
770 771 772
		flags & ACPI_NFIT_MEM_SAVE_FAILED ? "save_fail " : "",
		flags & ACPI_NFIT_MEM_RESTORE_FAILED ? "restore_fail " : "",
		flags & ACPI_NFIT_MEM_FLUSH_FAILED ? "flush_fail " : "",
773
		flags & ACPI_NFIT_MEM_NOT_ARMED ? "not_armed " : "",
774
		flags & ACPI_NFIT_MEM_HEALTH_OBSERVED ? "smart_event " : "");
775 776 777
}
static DEVICE_ATTR_RO(flags);

778 779 780 781 782 783 784 785
static struct attribute *acpi_nfit_dimm_attributes[] = {
	&dev_attr_handle.attr,
	&dev_attr_phys_id.attr,
	&dev_attr_vendor.attr,
	&dev_attr_device.attr,
	&dev_attr_format.attr,
	&dev_attr_serial.attr,
	&dev_attr_rev_id.attr,
786
	&dev_attr_flags.attr,
787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807
	NULL,
};

static umode_t acpi_nfit_dimm_attr_visible(struct kobject *kobj,
		struct attribute *a, int n)
{
	struct device *dev = container_of(kobj, struct device, kobj);

	if (to_nfit_dcr(dev))
		return a->mode;
	else
		return 0;
}

static struct attribute_group acpi_nfit_dimm_attribute_group = {
	.name = "nfit",
	.attrs = acpi_nfit_dimm_attributes,
	.is_visible = acpi_nfit_dimm_attr_visible,
};

static const struct attribute_group *acpi_nfit_dimm_attribute_groups[] = {
808
	&nvdimm_attribute_group,
809
	&nd_device_attribute_group,
810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825
	&acpi_nfit_dimm_attribute_group,
	NULL,
};

static struct nvdimm *acpi_nfit_dimm_by_handle(struct acpi_nfit_desc *acpi_desc,
		u32 device_handle)
{
	struct nfit_mem *nfit_mem;

	list_for_each_entry(nfit_mem, &acpi_desc->dimms, list)
		if (__to_nfit_memdev(nfit_mem)->device_handle == device_handle)
			return nfit_mem->nvdimm;

	return NULL;
}

826 827 828 829 830 831
static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
		struct nfit_mem *nfit_mem, u32 device_handle)
{
	struct acpi_device *adev, *adev_dimm;
	struct device *dev = acpi_desc->dev;
	const u8 *uuid = to_nfit_uuid(NFIT_DEV_DIMM);
832
	int i;
833 834 835 836 837 838 839 840 841 842 843

	nfit_mem->dsm_mask = acpi_desc->dimm_dsm_force_en;
	adev = to_acpi_dev(acpi_desc);
	if (!adev)
		return 0;

	adev_dimm = acpi_find_child_device(adev, device_handle, false);
	nfit_mem->adev = adev_dimm;
	if (!adev_dimm) {
		dev_err(dev, "no ACPI.NFIT device with _ADR %#x, disabling...\n",
				device_handle);
844
		return force_enable_dimms ? 0 : -ENODEV;
845 846 847 848 849 850
	}

	for (i = ND_CMD_SMART; i <= ND_CMD_VENDOR; i++)
		if (acpi_check_dsm(adev_dimm->handle, uuid, 1, 1ULL << i))
			set_bit(i, &nfit_mem->dsm_mask);

851
	return 0;
852 853
}

854 855 856
static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
{
	struct nfit_mem *nfit_mem;
857
	int dimm_count = 0;
858 859 860 861 862

	list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) {
		struct nvdimm *nvdimm;
		unsigned long flags = 0;
		u32 device_handle;
863
		u16 mem_flags;
864
		int rc;
865 866 867 868

		device_handle = __to_nfit_memdev(nfit_mem)->device_handle;
		nvdimm = acpi_nfit_dimm_by_handle(acpi_desc, device_handle);
		if (nvdimm) {
V
Vishal Verma 已提交
869
			dimm_count++;
870 871 872 873 874 875
			continue;
		}

		if (nfit_mem->bdw && nfit_mem->memdev_pmem)
			flags |= NDD_ALIASING;

876
		mem_flags = __to_nfit_memdev(nfit_mem)->flags;
877
		if (mem_flags & ACPI_NFIT_MEM_NOT_ARMED)
878 879
			flags |= NDD_UNARMED;

880 881 882 883
		rc = acpi_nfit_add_dimm(acpi_desc, nfit_mem, device_handle);
		if (rc)
			continue;

884
		nvdimm = nvdimm_create(acpi_desc->nvdimm_bus, nfit_mem,
885 886
				acpi_nfit_dimm_attribute_groups,
				flags, &nfit_mem->dsm_mask);
887 888 889 890
		if (!nvdimm)
			return -ENOMEM;

		nfit_mem->nvdimm = nvdimm;
891
		dimm_count++;
892 893 894 895

		if ((mem_flags & ACPI_NFIT_MEM_FAILED_MASK) == 0)
			continue;

896
		dev_info(acpi_desc->dev, "%s flags:%s%s%s%s\n",
897
				nvdimm_name(nvdimm),
898 899 900
		  mem_flags & ACPI_NFIT_MEM_SAVE_FAILED ? " save_fail" : "",
		  mem_flags & ACPI_NFIT_MEM_RESTORE_FAILED ? " restore_fail":"",
		  mem_flags & ACPI_NFIT_MEM_FLUSH_FAILED ? " flush_fail" : "",
901
		  mem_flags & ACPI_NFIT_MEM_NOT_ARMED ? " not_armed" : "");
902

903 904
	}

905
	return nvdimm_bus_check_dimm_count(acpi_desc->nvdimm_bus, dimm_count);
906 907
}

908 909 910 911 912 913 914
static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
{
	struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc;
	const u8 *uuid = to_nfit_uuid(NFIT_DEV_BUS);
	struct acpi_device *adev;
	int i;

915
	nd_desc->dsm_mask = acpi_desc->bus_dsm_force_en;
916 917 918 919 920 921 922 923 924
	adev = to_acpi_dev(acpi_desc);
	if (!adev)
		return;

	for (i = ND_CMD_ARS_CAP; i <= ND_CMD_ARS_STATUS; i++)
		if (acpi_check_dsm(adev->handle, uuid, 1, 1ULL << i))
			set_bit(i, &nd_desc->dsm_mask);
}

925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947
static ssize_t range_index_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);
	struct nfit_spa *nfit_spa = nd_region_provider_data(nd_region);

	return sprintf(buf, "%d\n", nfit_spa->spa->range_index);
}
static DEVICE_ATTR_RO(range_index);

static struct attribute *acpi_nfit_region_attributes[] = {
	&dev_attr_range_index.attr,
	NULL,
};

static struct attribute_group acpi_nfit_region_attribute_group = {
	.name = "nfit",
	.attrs = acpi_nfit_region_attributes,
};

static const struct attribute_group *acpi_nfit_region_attribute_groups[] = {
	&nd_region_attribute_group,
	&nd_mapping_attribute_group,
948
	&nd_device_attribute_group,
949
	&nd_numa_attribute_group,
950 951 952 953
	&acpi_nfit_region_attribute_group,
	NULL,
};

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 1004 1005 1006 1007 1008 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
/* enough info to uniquely specify an interleave set */
struct nfit_set_info {
	struct nfit_set_info_map {
		u64 region_offset;
		u32 serial_number;
		u32 pad;
	} mapping[0];
};

static size_t sizeof_nfit_set_info(int num_mappings)
{
	return sizeof(struct nfit_set_info)
		+ num_mappings * sizeof(struct nfit_set_info_map);
}

static int cmp_map(const void *m0, const void *m1)
{
	const struct nfit_set_info_map *map0 = m0;
	const struct nfit_set_info_map *map1 = m1;

	return memcmp(&map0->region_offset, &map1->region_offset,
			sizeof(u64));
}

/* Retrieve the nth entry referencing this spa */
static struct acpi_nfit_memory_map *memdev_from_spa(
		struct acpi_nfit_desc *acpi_desc, u16 range_index, int n)
{
	struct nfit_memdev *nfit_memdev;

	list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list)
		if (nfit_memdev->memdev->range_index == range_index)
			if (n-- == 0)
				return nfit_memdev->memdev;
	return NULL;
}

static int acpi_nfit_init_interleave_set(struct acpi_nfit_desc *acpi_desc,
		struct nd_region_desc *ndr_desc,
		struct acpi_nfit_system_address *spa)
{
	int i, spa_type = nfit_spa_type(spa);
	struct device *dev = acpi_desc->dev;
	struct nd_interleave_set *nd_set;
	u16 nr = ndr_desc->num_mappings;
	struct nfit_set_info *info;

	if (spa_type == NFIT_SPA_PM || spa_type == NFIT_SPA_VOLATILE)
		/* pass */;
	else
		return 0;

	nd_set = devm_kzalloc(dev, sizeof(*nd_set), GFP_KERNEL);
	if (!nd_set)
		return -ENOMEM;

	info = devm_kzalloc(dev, sizeof_nfit_set_info(nr), GFP_KERNEL);
	if (!info)
		return -ENOMEM;
	for (i = 0; i < nr; i++) {
		struct nd_mapping *nd_mapping = &ndr_desc->nd_mapping[i];
		struct nfit_set_info_map *map = &info->mapping[i];
		struct nvdimm *nvdimm = nd_mapping->nvdimm;
		struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
		struct acpi_nfit_memory_map *memdev = memdev_from_spa(acpi_desc,
				spa->range_index, i);

		if (!memdev || !nfit_mem->dcr) {
			dev_err(dev, "%s: failed to find DCR\n", __func__);
			return -ENODEV;
		}

		map->region_offset = memdev->region_offset;
		map->serial_number = nfit_mem->dcr->serial_number;
	}

	sort(&info->mapping[0], nr, sizeof(struct nfit_set_info_map),
			cmp_map, NULL);
	nd_set->cookie = nd_fletcher64(info, sizeof_nfit_set_info(nr), 0);
	ndr_desc->nd_set = nd_set;
	devm_kfree(dev, info);

	return 0;
}

1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053
static u64 to_interleave_offset(u64 offset, struct nfit_blk_mmio *mmio)
{
	struct acpi_nfit_interleave *idt = mmio->idt;
	u32 sub_line_offset, line_index, line_offset;
	u64 line_no, table_skip_count, table_offset;

	line_no = div_u64_rem(offset, mmio->line_size, &sub_line_offset);
	table_skip_count = div_u64_rem(line_no, mmio->num_lines, &line_index);
	line_offset = idt->line_offset[line_index]
		* mmio->line_size;
	table_offset = table_skip_count * mmio->table_size;

	return mmio->base_offset + line_offset + table_offset + sub_line_offset;
}

1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071
static void wmb_blk(struct nfit_blk *nfit_blk)
{

	if (nfit_blk->nvdimm_flush) {
		/*
		 * The first wmb() is needed to 'sfence' all previous writes
		 * such that they are architecturally visible for the platform
		 * buffer flush.  Note that we've already arranged for pmem
		 * writes to avoid the cache via arch_memcpy_to_pmem().  The
		 * final wmb() ensures ordering for the NVDIMM flush write.
		 */
		wmb();
		writeq(1, nfit_blk->nvdimm_flush);
		wmb();
	} else
		wmb_pmem();
}

1072
static u32 read_blk_stat(struct nfit_blk *nfit_blk, unsigned int bw)
1073 1074 1075 1076 1077 1078 1079
{
	struct nfit_blk_mmio *mmio = &nfit_blk->mmio[DCR];
	u64 offset = nfit_blk->stat_offset + mmio->size * bw;

	if (mmio->num_lines)
		offset = to_interleave_offset(offset, mmio);

1080
	return readl(mmio->addr.base + offset);
1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104
}

static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw,
		resource_size_t dpa, unsigned int len, unsigned int write)
{
	u64 cmd, offset;
	struct nfit_blk_mmio *mmio = &nfit_blk->mmio[DCR];

	enum {
		BCW_OFFSET_MASK = (1ULL << 48)-1,
		BCW_LEN_SHIFT = 48,
		BCW_LEN_MASK = (1ULL << 8) - 1,
		BCW_CMD_SHIFT = 56,
	};

	cmd = (dpa >> L1_CACHE_SHIFT) & BCW_OFFSET_MASK;
	len = len >> L1_CACHE_SHIFT;
	cmd |= ((u64) len & BCW_LEN_MASK) << BCW_LEN_SHIFT;
	cmd |= ((u64) write) << BCW_CMD_SHIFT;

	offset = nfit_blk->cmd_offset + mmio->size * bw;
	if (mmio->num_lines)
		offset = to_interleave_offset(offset, mmio);

1105
	writeq(cmd, mmio->addr.base + offset);
1106
	wmb_blk(nfit_blk);
1107 1108

	if (nfit_blk->dimm_flags & ND_BLK_DCR_LATCH)
1109
		readq(mmio->addr.base + offset);
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
}

static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk,
		resource_size_t dpa, void *iobuf, size_t len, int rw,
		unsigned int lane)
{
	struct nfit_blk_mmio *mmio = &nfit_blk->mmio[BDW];
	unsigned int copied = 0;
	u64 base_offset;
	int rc;

	base_offset = nfit_blk->bdw_offset + dpa % L1_CACHE_BYTES
		+ lane * mmio->size;
	write_blk_ctl(nfit_blk, lane, dpa, len, rw);
	while (len) {
		unsigned int c;
		u64 offset;

		if (mmio->num_lines) {
			u32 line_offset;

			offset = to_interleave_offset(base_offset + copied,
					mmio);
			div_u64_rem(offset, mmio->line_size, &line_offset);
			c = min_t(size_t, len, mmio->line_size - line_offset);
		} else {
			offset = base_offset + nfit_blk->bdw_offset;
			c = len;
		}

		if (rw)
1141
			memcpy_to_pmem(mmio->addr.aperture + offset,
1142
					iobuf + copied, c);
1143 1144 1145 1146 1147
		else {
			if (nfit_blk->dimm_flags & ND_BLK_READ_FLUSH)
				mmio_flush_range((void __force *)
					mmio->addr.aperture + offset, c);

1148
			memcpy_from_pmem(iobuf + copied,
1149 1150
					mmio->addr.aperture + offset, c);
		}
1151 1152 1153 1154

		copied += c;
		len -= c;
	}
1155 1156 1157 1158

	if (rw)
		wmb_blk(nfit_blk);

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
	rc = read_blk_stat(nfit_blk, lane) ? -EIO : 0;
	return rc;
}

static int acpi_nfit_blk_region_do_io(struct nd_blk_region *ndbr,
		resource_size_t dpa, void *iobuf, u64 len, int rw)
{
	struct nfit_blk *nfit_blk = nd_blk_region_provider_data(ndbr);
	struct nfit_blk_mmio *mmio = &nfit_blk->mmio[BDW];
	struct nd_region *nd_region = nfit_blk->nd_region;
	unsigned int lane, copied = 0;
	int rc = 0;

	lane = nd_region_acquire_lane(nd_region);
	while (len) {
		u64 c = min(len, mmio->size);

		rc = acpi_nfit_blk_single_io(nfit_blk, dpa + copied,
				iobuf + copied, c, rw, lane);
		if (rc)
			break;

		copied += c;
		len -= c;
	}
	nd_region_release_lane(nd_region, lane);

	return rc;
}

static void nfit_spa_mapping_release(struct kref *kref)
{
	struct nfit_spa_mapping *spa_map = to_spa_map(kref);
	struct acpi_nfit_system_address *spa = spa_map->spa;
	struct acpi_nfit_desc *acpi_desc = spa_map->acpi_desc;

	WARN_ON(!mutex_is_locked(&acpi_desc->spa_map_mutex));
	dev_dbg(acpi_desc->dev, "%s: SPA%d\n", __func__, spa->range_index);
1197 1198 1199 1200
	if (spa_map->type == SPA_MAP_APERTURE)
		memunmap((void __force *)spa_map->addr.aperture);
	else
		iounmap(spa_map->addr.base);
1201 1202 1203 1204 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
	release_mem_region(spa->address, spa->length);
	list_del(&spa_map->list);
	kfree(spa_map);
}

static struct nfit_spa_mapping *find_spa_mapping(
		struct acpi_nfit_desc *acpi_desc,
		struct acpi_nfit_system_address *spa)
{
	struct nfit_spa_mapping *spa_map;

	WARN_ON(!mutex_is_locked(&acpi_desc->spa_map_mutex));
	list_for_each_entry(spa_map, &acpi_desc->spa_maps, list)
		if (spa_map->spa == spa)
			return spa_map;

	return NULL;
}

static void nfit_spa_unmap(struct acpi_nfit_desc *acpi_desc,
		struct acpi_nfit_system_address *spa)
{
	struct nfit_spa_mapping *spa_map;

	mutex_lock(&acpi_desc->spa_map_mutex);
	spa_map = find_spa_mapping(acpi_desc, spa);

	if (spa_map)
		kref_put(&spa_map->kref, nfit_spa_mapping_release);
	mutex_unlock(&acpi_desc->spa_map_mutex);
}

static void __iomem *__nfit_spa_map(struct acpi_nfit_desc *acpi_desc,
1234
		struct acpi_nfit_system_address *spa, enum spa_map_type type)
1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245
{
	resource_size_t start = spa->address;
	resource_size_t n = spa->length;
	struct nfit_spa_mapping *spa_map;
	struct resource *res;

	WARN_ON(!mutex_is_locked(&acpi_desc->spa_map_mutex));

	spa_map = find_spa_mapping(acpi_desc, spa);
	if (spa_map) {
		kref_get(&spa_map->kref);
1246
		return spa_map->addr.base;
1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261
	}

	spa_map = kzalloc(sizeof(*spa_map), GFP_KERNEL);
	if (!spa_map)
		return NULL;

	INIT_LIST_HEAD(&spa_map->list);
	spa_map->spa = spa;
	kref_init(&spa_map->kref);
	spa_map->acpi_desc = acpi_desc;

	res = request_mem_region(start, n, dev_name(acpi_desc->dev));
	if (!res)
		goto err_mem;

1262 1263 1264 1265 1266 1267 1268
	spa_map->type = type;
	if (type == SPA_MAP_APERTURE)
		spa_map->addr.aperture = (void __pmem *)memremap(start, n,
							ARCH_MEMREMAP_PMEM);
	else
		spa_map->addr.base = ioremap_nocache(start, n);

1269

1270
	if (!spa_map->addr.base)
1271 1272 1273
		goto err_map;

	list_add_tail(&spa_map->list, &acpi_desc->spa_maps);
1274
	return spa_map->addr.base;
1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286

 err_map:
	release_mem_region(start, n);
 err_mem:
	kfree(spa_map);
	return NULL;
}

/**
 * nfit_spa_map - interleave-aware managed-mappings of acpi_nfit_system_address ranges
 * @nvdimm_bus: NFIT-bus that provided the spa table entry
 * @nfit_spa: spa table to map
1287
 * @type: aperture or control region
1288 1289 1290 1291 1292 1293 1294 1295 1296
 *
 * In the case where block-data-window apertures and
 * dimm-control-regions are interleaved they will end up sharing a
 * single request_mem_region() + ioremap() for the address range.  In
 * the style of devm nfit_spa_map() mappings are automatically dropped
 * when all region devices referencing the same mapping are disabled /
 * unbound.
 */
static void __iomem *nfit_spa_map(struct acpi_nfit_desc *acpi_desc,
1297
		struct acpi_nfit_system_address *spa, enum spa_map_type type)
1298 1299 1300 1301
{
	void __iomem *iomem;

	mutex_lock(&acpi_desc->spa_map_mutex);
1302
	iomem = __nfit_spa_map(acpi_desc, spa, type);
1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322
	mutex_unlock(&acpi_desc->spa_map_mutex);

	return iomem;
}

static int nfit_blk_init_interleave(struct nfit_blk_mmio *mmio,
		struct acpi_nfit_interleave *idt, u16 interleave_ways)
{
	if (idt) {
		mmio->num_lines = idt->line_count;
		mmio->line_size = idt->line_size;
		if (interleave_ways == 0)
			return -ENXIO;
		mmio->table_size = mmio->num_lines * interleave_ways
			* mmio->line_size;
	}

	return 0;
}

1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336
static int acpi_nfit_blk_get_flags(struct nvdimm_bus_descriptor *nd_desc,
		struct nvdimm *nvdimm, struct nfit_blk *nfit_blk)
{
	struct nd_cmd_dimm_flags flags;
	int rc;

	memset(&flags, 0, sizeof(flags));
	rc = nd_desc->ndctl(nd_desc, nvdimm, ND_CMD_DIMM_FLAGS, &flags,
			sizeof(flags));

	if (rc >= 0 && flags.status == 0)
		nfit_blk->dimm_flags = flags.flags;
	else if (rc == -ENOTTY) {
		/* fall back to a conservative default */
1337
		nfit_blk->dimm_flags = ND_BLK_DCR_LATCH | ND_BLK_READ_FLUSH;
1338 1339 1340 1341 1342 1343 1344
		rc = 0;
	} else
		rc = -ENXIO;

	return rc;
}

1345 1346 1347 1348 1349 1350
static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
		struct device *dev)
{
	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
	struct nd_blk_region *ndbr = to_nd_blk_region(dev);
1351
	struct nfit_flush *nfit_flush;
1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362
	struct nfit_blk_mmio *mmio;
	struct nfit_blk *nfit_blk;
	struct nfit_mem *nfit_mem;
	struct nvdimm *nvdimm;
	int rc;

	nvdimm = nd_blk_region_to_dimm(ndbr);
	nfit_mem = nvdimm_provider_data(nvdimm);
	if (!nfit_mem || !nfit_mem->dcr || !nfit_mem->bdw) {
		dev_dbg(dev, "%s: missing%s%s%s\n", __func__,
				nfit_mem ? "" : " nfit_mem",
1363 1364
				(nfit_mem && nfit_mem->dcr) ? "" : " dcr",
				(nfit_mem && nfit_mem->bdw) ? "" : " bdw");
1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376
		return -ENXIO;
	}

	nfit_blk = devm_kzalloc(dev, sizeof(*nfit_blk), GFP_KERNEL);
	if (!nfit_blk)
		return -ENOMEM;
	nd_blk_region_set_provider_data(ndbr, nfit_blk);
	nfit_blk->nd_region = to_nd_region(dev);

	/* map block aperture memory */
	nfit_blk->bdw_offset = nfit_mem->bdw->offset;
	mmio = &nfit_blk->mmio[BDW];
1377
	mmio->addr.base = nfit_spa_map(acpi_desc, nfit_mem->spa_bdw,
1378
			SPA_MAP_APERTURE);
1379
	if (!mmio->addr.base) {
1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399
		dev_dbg(dev, "%s: %s failed to map bdw\n", __func__,
				nvdimm_name(nvdimm));
		return -ENOMEM;
	}
	mmio->size = nfit_mem->bdw->size;
	mmio->base_offset = nfit_mem->memdev_bdw->region_offset;
	mmio->idt = nfit_mem->idt_bdw;
	mmio->spa = nfit_mem->spa_bdw;
	rc = nfit_blk_init_interleave(mmio, nfit_mem->idt_bdw,
			nfit_mem->memdev_bdw->interleave_ways);
	if (rc) {
		dev_dbg(dev, "%s: %s failed to init bdw interleave\n",
				__func__, nvdimm_name(nvdimm));
		return rc;
	}

	/* map block control memory */
	nfit_blk->cmd_offset = nfit_mem->dcr->command_offset;
	nfit_blk->stat_offset = nfit_mem->dcr->status_offset;
	mmio = &nfit_blk->mmio[DCR];
1400
	mmio->addr.base = nfit_spa_map(acpi_desc, nfit_mem->spa_dcr,
1401
			SPA_MAP_CONTROL);
1402
	if (!mmio->addr.base) {
1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418
		dev_dbg(dev, "%s: %s failed to map dcr\n", __func__,
				nvdimm_name(nvdimm));
		return -ENOMEM;
	}
	mmio->size = nfit_mem->dcr->window_size;
	mmio->base_offset = nfit_mem->memdev_dcr->region_offset;
	mmio->idt = nfit_mem->idt_dcr;
	mmio->spa = nfit_mem->spa_dcr;
	rc = nfit_blk_init_interleave(mmio, nfit_mem->idt_dcr,
			nfit_mem->memdev_dcr->interleave_ways);
	if (rc) {
		dev_dbg(dev, "%s: %s failed to init dcr interleave\n",
				__func__, nvdimm_name(nvdimm));
		return rc;
	}

1419 1420 1421 1422 1423 1424 1425
	rc = acpi_nfit_blk_get_flags(nd_desc, nvdimm, nfit_blk);
	if (rc < 0) {
		dev_dbg(dev, "%s: %s failed get DIMM flags\n",
				__func__, nvdimm_name(nvdimm));
		return rc;
	}

1426 1427 1428 1429 1430 1431 1432 1433
	nfit_flush = nfit_mem->nfit_flush;
	if (nfit_flush && nfit_flush->flush->hint_count != 0) {
		nfit_blk->nvdimm_flush = devm_ioremap_nocache(dev,
				nfit_flush->flush->hint_address[0], 8);
		if (!nfit_blk->nvdimm_flush)
			return -ENOMEM;
	}

1434
	if (!arch_has_wmb_pmem() && !nfit_blk->nvdimm_flush)
1435 1436
		dev_warn(dev, "unable to guarantee persistence of writes\n");

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 1462 1463 1464 1465 1466 1467 1468
	if (mmio->line_size == 0)
		return 0;

	if ((u32) nfit_blk->cmd_offset % mmio->line_size
			+ 8 > mmio->line_size) {
		dev_dbg(dev, "cmd_offset crosses interleave boundary\n");
		return -ENXIO;
	} else if ((u32) nfit_blk->stat_offset % mmio->line_size
			+ 8 > mmio->line_size) {
		dev_dbg(dev, "stat_offset crosses interleave boundary\n");
		return -ENXIO;
	}

	return 0;
}

static void acpi_nfit_blk_region_disable(struct nvdimm_bus *nvdimm_bus,
		struct device *dev)
{
	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
	struct nd_blk_region *ndbr = to_nd_blk_region(dev);
	struct nfit_blk *nfit_blk = nd_blk_region_provider_data(ndbr);
	int i;

	if (!nfit_blk)
		return; /* never enabled */

	/* auto-free BLK spa mappings */
	for (i = 0; i < 2; i++) {
		struct nfit_blk_mmio *mmio = &nfit_blk->mmio[i];

1469
		if (mmio->addr.base)
1470 1471 1472 1473 1474 1475
			nfit_spa_unmap(acpi_desc, mmio->spa);
	}
	nd_blk_region_set_provider_data(ndbr, NULL);
	/* devm will free nfit_blk */
}

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
static int ars_get_cap(struct nvdimm_bus_descriptor *nd_desc,
		struct nd_cmd_ars_cap *cmd, u64 addr, u64 length)
{
	cmd->address = addr;
	cmd->length = length;

	return nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_CAP, cmd,
			sizeof(*cmd));
}

static int ars_do_start(struct nvdimm_bus_descriptor *nd_desc,
		struct nd_cmd_ars_start *cmd, u64 addr, u64 length)
{
	int rc;

	cmd->address = addr;
	cmd->length = length;
	cmd->type = ND_ARS_PERSISTENT;

	while (1) {
		rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_START, cmd,
				sizeof(*cmd));
		if (rc)
			return rc;
		switch (cmd->status) {
		case 0:
			return 0;
		case 1:
			/* ARS unsupported, but we should never get here */
			return 0;
1506
		case 6:
1507 1508 1509 1510 1511 1512 1513 1514 1515 1516
			/* ARS is in progress */
			msleep(1000);
			break;
		default:
			return -ENXIO;
		}
	}
}

static int ars_get_status(struct nvdimm_bus_descriptor *nd_desc,
1517
		struct nd_cmd_ars_status *cmd, u32 size)
1518 1519 1520 1521 1522
{
	int rc;

	while (1) {
		rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_STATUS, cmd,
1523
			size);
1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537
		if (rc || cmd->status & 0xffff)
			return -ENXIO;

		/* Check extended status (Upper two bytes) */
		switch (cmd->status >> 16) {
		case 0:
			return 0;
		case 1:
			/* ARS is in progress */
			msleep(1000);
			break;
		case 2:
			/* No ARS performed for the current boot */
			return 0;
1538 1539
		case 3:
			/* TODO: error list overflow support */
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
		default:
			return -ENXIO;
		}
	}
}

static int ars_status_process_records(struct nvdimm_bus *nvdimm_bus,
		struct nd_cmd_ars_status *ars_status, u64 start)
{
	int rc;
	u32 i;

	/*
	 * The address field returned by ars_status should be either
	 * less than or equal to the address we last started ARS for.
	 * The (start, length) returned by ars_status should also have
	 * non-zero overlap with the range we started ARS for.
	 * If this is not the case, bail.
	 */
	if (ars_status->address > start ||
			(ars_status->address + ars_status->length < start))
		return -ENXIO;

	for (i = 0; i < ars_status->num_records; i++) {
		rc = nvdimm_bus_add_poison(nvdimm_bus,
				ars_status->records[i].err_address,
				ars_status->records[i].length);
		if (rc)
			return rc;
	}

	return 0;
}

static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc,
		struct nd_region_desc *ndr_desc)
{
	struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc;
	struct nvdimm_bus *nvdimm_bus = acpi_desc->nvdimm_bus;
	struct nd_cmd_ars_status *ars_status = NULL;
	struct nd_cmd_ars_start *ars_start = NULL;
	struct nd_cmd_ars_cap *ars_cap = NULL;
	u64 start, len, cur, remaining;
1583
	u32 ars_status_size;
1584 1585 1586 1587 1588 1589 1590 1591 1592
	int rc;

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

	start = ndr_desc->res->start;
	len = ndr_desc->res->end - ndr_desc->res->start + 1;

1593 1594 1595 1596 1597
	/*
	 * If ARS is unimplemented, unsupported, or if the 'Persistent Memory
	 * Scrub' flag in extended status is not set, skip this but continue
	 * initialization
	 */
1598
	rc = ars_get_cap(nd_desc, ars_cap, start, len);
1599 1600 1601 1602 1603 1604
	if (rc == -ENOTTY) {
		dev_dbg(acpi_desc->dev,
			"Address Range Scrub is not implemented, won't create an error list\n");
		rc = 0;
		goto out;
	}
1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619
	if (rc)
		goto out;

	if ((ars_cap->status & 0xffff) ||
		!(ars_cap->status >> 16 & ND_ARS_PERSISTENT)) {
		dev_warn(acpi_desc->dev,
			"ARS unsupported (status: 0x%x), won't create an error list\n",
			ars_cap->status);
		goto out;
	}

	/*
	 * Check if a full-range ARS has been run. If so, use those results
	 * without having to start a new ARS.
	 */
1620 1621
	ars_status_size = ars_cap->max_ars_out;
	ars_status = kzalloc(ars_status_size, GFP_KERNEL);
1622 1623 1624 1625 1626
	if (!ars_status) {
		rc = -ENOMEM;
		goto out;
	}

1627
	rc = ars_get_status(nd_desc, ars_status, ars_status_size);
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
	if (rc)
		goto out;

	if (ars_status->address <= start &&
		(ars_status->address + ars_status->length >= start + len)) {
		rc = ars_status_process_records(nvdimm_bus, ars_status, start);
		goto out;
	}

	/*
	 * ARS_STATUS can overflow if the number of poison entries found is
	 * greater than the maximum buffer size (ars_cap->max_ars_out)
	 * To detect overflow, check if the length field of ars_status
	 * is less than the length we supplied. If so, process the
	 * error entries we got, adjust the start point, and start again
	 */
	ars_start = kzalloc(sizeof(*ars_start), GFP_KERNEL);
	if (!ars_start)
		return -ENOMEM;

	cur = start;
	remaining = len;
	do {
		u64 done, end;

		rc = ars_do_start(nd_desc, ars_start, cur, remaining);
		if (rc)
			goto out;

1657
		rc = ars_get_status(nd_desc, ars_status, ars_status_size);
1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678
		if (rc)
			goto out;

		rc = ars_status_process_records(nvdimm_bus, ars_status, cur);
		if (rc)
			goto out;

		end = min(cur + remaining,
			ars_status->address + ars_status->length);
		done = end - cur;
		cur += done;
		remaining -= done;
	} while (remaining);

 out:
	kfree(ars_cap);
	kfree(ars_start);
	kfree(ars_status);
	return rc;
}

1679 1680 1681 1682 1683 1684 1685
static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc,
		struct nd_mapping *nd_mapping, struct nd_region_desc *ndr_desc,
		struct acpi_nfit_memory_map *memdev,
		struct acpi_nfit_system_address *spa)
{
	struct nvdimm *nvdimm = acpi_nfit_dimm_by_handle(acpi_desc,
			memdev->device_handle);
1686
	struct nd_blk_region_desc *ndbr_desc;
1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710
	struct nfit_mem *nfit_mem;
	int blk_valid = 0;

	if (!nvdimm) {
		dev_err(acpi_desc->dev, "spa%d dimm: %#x not found\n",
				spa->range_index, memdev->device_handle);
		return -ENODEV;
	}

	nd_mapping->nvdimm = nvdimm;
	switch (nfit_spa_type(spa)) {
	case NFIT_SPA_PM:
	case NFIT_SPA_VOLATILE:
		nd_mapping->start = memdev->address;
		nd_mapping->size = memdev->region_size;
		break;
	case NFIT_SPA_DCR:
		nfit_mem = nvdimm_provider_data(nvdimm);
		if (!nfit_mem || !nfit_mem->bdw) {
			dev_dbg(acpi_desc->dev, "spa%d %s missing bdw\n",
					spa->range_index, nvdimm_name(nvdimm));
		} else {
			nd_mapping->size = nfit_mem->bdw->capacity;
			nd_mapping->start = nfit_mem->bdw->start_address;
V
Vishal Verma 已提交
1711
			ndr_desc->num_lanes = nfit_mem->bdw->windows;
1712 1713 1714 1715 1716
			blk_valid = 1;
		}

		ndr_desc->nd_mapping = nd_mapping;
		ndr_desc->num_mappings = blk_valid;
1717 1718 1719
		ndbr_desc = to_blk_region_desc(ndr_desc);
		ndbr_desc->enable = acpi_nfit_blk_region_enable;
		ndbr_desc->disable = acpi_nfit_blk_region_disable;
1720
		ndbr_desc->do_io = acpi_desc->blk_do_io;
1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733
		if (!nvdimm_blk_region_create(acpi_desc->nvdimm_bus, ndr_desc))
			return -ENOMEM;
		break;
	}

	return 0;
}

static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
		struct nfit_spa *nfit_spa)
{
	static struct nd_mapping nd_mappings[ND_MAX_MAPPINGS];
	struct acpi_nfit_system_address *spa = nfit_spa->spa;
1734 1735
	struct nd_blk_region_desc ndbr_desc;
	struct nd_region_desc *ndr_desc;
1736 1737 1738
	struct nfit_memdev *nfit_memdev;
	struct nvdimm_bus *nvdimm_bus;
	struct resource res;
1739
	int count = 0, rc;
1740

V
Vishal Verma 已提交
1741 1742 1743
	if (nfit_spa->is_registered)
		return 0;

1744 1745 1746 1747 1748 1749 1750 1751
	if (spa->range_index == 0) {
		dev_dbg(acpi_desc->dev, "%s: detected invalid spa index\n",
				__func__);
		return 0;
	}

	memset(&res, 0, sizeof(res));
	memset(&nd_mappings, 0, sizeof(nd_mappings));
1752
	memset(&ndbr_desc, 0, sizeof(ndbr_desc));
1753 1754
	res.start = spa->address;
	res.end = res.start + spa->length - 1;
1755 1756 1757 1758
	ndr_desc = &ndbr_desc.ndr_desc;
	ndr_desc->res = &res;
	ndr_desc->provider_data = nfit_spa;
	ndr_desc->attr_groups = acpi_nfit_region_attribute_groups;
1759 1760 1761 1762 1763 1764
	if (spa->flags & ACPI_NFIT_PROXIMITY_VALID)
		ndr_desc->numa_node = acpi_map_pxm_to_online_node(
						spa->proximity_domain);
	else
		ndr_desc->numa_node = NUMA_NO_NODE;

1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776
	list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) {
		struct acpi_nfit_memory_map *memdev = nfit_memdev->memdev;
		struct nd_mapping *nd_mapping;

		if (memdev->range_index != spa->range_index)
			continue;
		if (count >= ND_MAX_MAPPINGS) {
			dev_err(acpi_desc->dev, "spa%d exceeds max mappings %d\n",
					spa->range_index, ND_MAX_MAPPINGS);
			return -ENXIO;
		}
		nd_mapping = &nd_mappings[count++];
1777
		rc = acpi_nfit_init_mapping(acpi_desc, nd_mapping, ndr_desc,
1778 1779 1780 1781 1782
				memdev, spa);
		if (rc)
			return rc;
	}

1783 1784 1785
	ndr_desc->nd_mapping = nd_mappings;
	ndr_desc->num_mappings = count;
	rc = acpi_nfit_init_interleave_set(acpi_desc, ndr_desc, spa);
1786 1787 1788
	if (rc)
		return rc;

1789 1790
	nvdimm_bus = acpi_desc->nvdimm_bus;
	if (nfit_spa_type(spa) == NFIT_SPA_PM) {
1791 1792 1793 1794 1795 1796 1797
		rc = acpi_nfit_find_poison(acpi_desc, ndr_desc);
		if (rc) {
			dev_err(acpi_desc->dev,
				"error while performing ARS to find poison: %d\n",
				rc);
			return rc;
		}
1798
		if (!nvdimm_pmem_region_create(nvdimm_bus, ndr_desc))
1799 1800
			return -ENOMEM;
	} else if (nfit_spa_type(spa) == NFIT_SPA_VOLATILE) {
1801
		if (!nvdimm_volatile_region_create(nvdimm_bus, ndr_desc))
1802 1803
			return -ENOMEM;
	}
V
Vishal Verma 已提交
1804 1805

	nfit_spa->is_registered = 1;
1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821
	return 0;
}

static int acpi_nfit_register_regions(struct acpi_nfit_desc *acpi_desc)
{
	struct nfit_spa *nfit_spa;

	list_for_each_entry(nfit_spa, &acpi_desc->spas, list) {
		int rc = acpi_nfit_register_region(acpi_desc, nfit_spa);

		if (rc)
			return rc;
	}
	return 0;
}

V
Vishal Verma 已提交
1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838
static int acpi_nfit_check_deletions(struct acpi_nfit_desc *acpi_desc,
		struct nfit_table_prev *prev)
{
	struct device *dev = acpi_desc->dev;

	if (!list_empty(&prev->spas) ||
			!list_empty(&prev->memdevs) ||
			!list_empty(&prev->dcrs) ||
			!list_empty(&prev->bdws) ||
			!list_empty(&prev->idts) ||
			!list_empty(&prev->flushes)) {
		dev_err(dev, "new nfit deletes entries (unsupported)\n");
		return -ENXIO;
	}
	return 0;
}

1839
int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz)
1840 1841
{
	struct device *dev = acpi_desc->dev;
V
Vishal Verma 已提交
1842
	struct nfit_table_prev prev;
1843 1844
	const void *end;
	u8 *data;
1845
	int rc;
1846

V
Vishal Verma 已提交
1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867
	mutex_lock(&acpi_desc->init_mutex);

	INIT_LIST_HEAD(&prev.spas);
	INIT_LIST_HEAD(&prev.memdevs);
	INIT_LIST_HEAD(&prev.dcrs);
	INIT_LIST_HEAD(&prev.bdws);
	INIT_LIST_HEAD(&prev.idts);
	INIT_LIST_HEAD(&prev.flushes);

	list_cut_position(&prev.spas, &acpi_desc->spas,
				acpi_desc->spas.prev);
	list_cut_position(&prev.memdevs, &acpi_desc->memdevs,
				acpi_desc->memdevs.prev);
	list_cut_position(&prev.dcrs, &acpi_desc->dcrs,
				acpi_desc->dcrs.prev);
	list_cut_position(&prev.bdws, &acpi_desc->bdws,
				acpi_desc->bdws.prev);
	list_cut_position(&prev.idts, &acpi_desc->idts,
				acpi_desc->idts.prev);
	list_cut_position(&prev.flushes, &acpi_desc->flushes,
				acpi_desc->flushes.prev);
1868 1869 1870 1871

	data = (u8 *) acpi_desc->nfit;
	end = data + sz;
	while (!IS_ERR_OR_NULL(data))
V
Vishal Verma 已提交
1872
		data = add_table(acpi_desc, &prev, data, end);
1873 1874 1875 1876

	if (IS_ERR(data)) {
		dev_dbg(dev, "%s: nfit table parsing error: %ld\n", __func__,
				PTR_ERR(data));
V
Vishal Verma 已提交
1877 1878
		rc = PTR_ERR(data);
		goto out_unlock;
1879 1880
	}

V
Vishal Verma 已提交
1881 1882 1883 1884 1885 1886 1887 1888
	rc = acpi_nfit_check_deletions(acpi_desc, &prev);
	if (rc)
		goto out_unlock;

	if (nfit_mem_init(acpi_desc) != 0) {
		rc = -ENOMEM;
		goto out_unlock;
	}
1889

1890 1891
	acpi_nfit_init_dsms(acpi_desc);

1892 1893
	rc = acpi_nfit_register_dimms(acpi_desc);
	if (rc)
V
Vishal Verma 已提交
1894 1895 1896
		goto out_unlock;

	rc = acpi_nfit_register_regions(acpi_desc);
1897

V
Vishal Verma 已提交
1898 1899 1900
 out_unlock:
	mutex_unlock(&acpi_desc->init_mutex);
	return rc;
1901
}
1902
EXPORT_SYMBOL_GPL(acpi_nfit_init);
1903

V
Vishal Verma 已提交
1904
static struct acpi_nfit_desc *acpi_nfit_desc_init(struct acpi_device *adev)
1905 1906 1907 1908 1909 1910 1911
{
	struct nvdimm_bus_descriptor *nd_desc;
	struct acpi_nfit_desc *acpi_desc;
	struct device *dev = &adev->dev;

	acpi_desc = devm_kzalloc(dev, sizeof(*acpi_desc), GFP_KERNEL);
	if (!acpi_desc)
V
Vishal Verma 已提交
1912
		return ERR_PTR(-ENOMEM);
1913 1914 1915

	dev_set_drvdata(dev, acpi_desc);
	acpi_desc->dev = dev;
1916
	acpi_desc->blk_do_io = acpi_nfit_blk_region_do_io;
1917 1918 1919
	nd_desc = &acpi_desc->nd_desc;
	nd_desc->provider_name = "ACPI.NFIT";
	nd_desc->ndctl = acpi_nfit_ctl;
1920
	nd_desc->attr_groups = acpi_nfit_attribute_groups;
1921 1922

	acpi_desc->nvdimm_bus = nvdimm_bus_register(dev, nd_desc);
V
Vishal Verma 已提交
1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965
	if (!acpi_desc->nvdimm_bus) {
		devm_kfree(dev, acpi_desc);
		return ERR_PTR(-ENXIO);
	}

	INIT_LIST_HEAD(&acpi_desc->spa_maps);
	INIT_LIST_HEAD(&acpi_desc->spas);
	INIT_LIST_HEAD(&acpi_desc->dcrs);
	INIT_LIST_HEAD(&acpi_desc->bdws);
	INIT_LIST_HEAD(&acpi_desc->idts);
	INIT_LIST_HEAD(&acpi_desc->flushes);
	INIT_LIST_HEAD(&acpi_desc->memdevs);
	INIT_LIST_HEAD(&acpi_desc->dimms);
	mutex_init(&acpi_desc->spa_map_mutex);
	mutex_init(&acpi_desc->init_mutex);

	return acpi_desc;
}

static int acpi_nfit_add(struct acpi_device *adev)
{
	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
	struct acpi_nfit_desc *acpi_desc;
	struct device *dev = &adev->dev;
	struct acpi_table_header *tbl;
	acpi_status status = AE_OK;
	acpi_size sz;
	int rc;

	status = acpi_get_table_with_size("NFIT", 0, &tbl, &sz);
	if (ACPI_FAILURE(status)) {
		/* This is ok, we could have an nvdimm hotplugged later */
		dev_dbg(dev, "failed to find NFIT at startup\n");
		return 0;
	}

	acpi_desc = acpi_nfit_desc_init(adev);
	if (IS_ERR(acpi_desc)) {
		dev_err(dev, "%s: error initializing acpi_desc: %ld\n",
				__func__, PTR_ERR(acpi_desc));
		return PTR_ERR(acpi_desc);
	}

1966 1967 1968 1969 1970 1971 1972
	/*
	 * Save the acpi header for later and then skip it,
	 * making nfit point to the first nfit table header.
	 */
	acpi_desc->acpi_header = *tbl;
	acpi_desc->nfit = (void *) tbl + sizeof(struct acpi_table_nfit);
	sz -= sizeof(struct acpi_table_nfit);
V
Vishal Verma 已提交
1973 1974 1975 1976

	/* Evaluate _FIT and override with that if present */
	status = acpi_evaluate_object(adev->handle, "_FIT", NULL, &buf);
	if (ACPI_SUCCESS(status) && buf.length > 0) {
1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988
		union acpi_object *obj;
		/*
		 * Adjust for the acpi_object header of the _FIT
		 */
		obj = buf.pointer;
		if (obj->type == ACPI_TYPE_BUFFER) {
			acpi_desc->nfit =
				(struct acpi_nfit_header *)obj->buffer.pointer;
			sz = obj->buffer.length;
		} else
			dev_dbg(dev, "%s invalid type %d, ignoring _FIT\n",
				 __func__, (int) obj->type);
V
Vishal Verma 已提交
1989
	}
1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006

	rc = acpi_nfit_init(acpi_desc, sz);
	if (rc) {
		nvdimm_bus_unregister(acpi_desc->nvdimm_bus);
		return rc;
	}
	return 0;
}

static int acpi_nfit_remove(struct acpi_device *adev)
{
	struct acpi_nfit_desc *acpi_desc = dev_get_drvdata(&adev->dev);

	nvdimm_bus_unregister(acpi_desc->nvdimm_bus);
	return 0;
}

V
Vishal Verma 已提交
2007 2008 2009 2010
static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
{
	struct acpi_nfit_desc *acpi_desc = dev_get_drvdata(&adev->dev);
	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
2011 2012
	struct acpi_nfit_header *nfit_saved;
	union acpi_object *obj;
V
Vishal Verma 已提交
2013 2014 2015 2016 2017 2018 2019 2020 2021 2022
	struct device *dev = &adev->dev;
	acpi_status status;
	int ret;

	dev_dbg(dev, "%s: event: %d\n", __func__, event);

	device_lock(dev);
	if (!dev->driver) {
		/* dev->driver may be null if we're being removed */
		dev_dbg(dev, "%s: no driver found for dev\n", __func__);
2023
		goto out_unlock;
V
Vishal Verma 已提交
2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042
	}

	if (!acpi_desc) {
		acpi_desc = acpi_nfit_desc_init(adev);
		if (IS_ERR(acpi_desc)) {
			dev_err(dev, "%s: error initializing acpi_desc: %ld\n",
				__func__, PTR_ERR(acpi_desc));
			goto out_unlock;
		}
	}

	/* Evaluate _FIT */
	status = acpi_evaluate_object(adev->handle, "_FIT", NULL, &buf);
	if (ACPI_FAILURE(status)) {
		dev_err(dev, "failed to evaluate _FIT\n");
		goto out_unlock;
	}

	nfit_saved = acpi_desc->nfit;
2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055
	obj = buf.pointer;
	if (obj->type == ACPI_TYPE_BUFFER) {
		acpi_desc->nfit =
			(struct acpi_nfit_header *)obj->buffer.pointer;
		ret = acpi_nfit_init(acpi_desc, obj->buffer.length);
		if (ret) {
			/* Merge failed, restore old nfit, and exit */
			acpi_desc->nfit = nfit_saved;
			dev_err(dev, "failed to merge updated NFIT\n");
		}
	} else {
		/* Bad _FIT, restore old nfit */
		dev_err(dev, "Invalid _FIT\n");
V
Vishal Verma 已提交
2056 2057 2058 2059 2060 2061 2062
	}
	kfree(buf.pointer);

 out_unlock:
	device_unlock(dev);
}

2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074
static const struct acpi_device_id acpi_nfit_ids[] = {
	{ "ACPI0012", 0 },
	{ "", 0 },
};
MODULE_DEVICE_TABLE(acpi, acpi_nfit_ids);

static struct acpi_driver acpi_nfit_driver = {
	.name = KBUILD_MODNAME,
	.ids = acpi_nfit_ids,
	.ops = {
		.add = acpi_nfit_add,
		.remove = acpi_nfit_remove,
V
Vishal Verma 已提交
2075
		.notify = acpi_nfit_notify,
2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111
	},
};

static __init int nfit_init(void)
{
	BUILD_BUG_ON(sizeof(struct acpi_table_nfit) != 40);
	BUILD_BUG_ON(sizeof(struct acpi_nfit_system_address) != 56);
	BUILD_BUG_ON(sizeof(struct acpi_nfit_memory_map) != 48);
	BUILD_BUG_ON(sizeof(struct acpi_nfit_interleave) != 20);
	BUILD_BUG_ON(sizeof(struct acpi_nfit_smbios) != 9);
	BUILD_BUG_ON(sizeof(struct acpi_nfit_control_region) != 80);
	BUILD_BUG_ON(sizeof(struct acpi_nfit_data_region) != 40);

	acpi_str_to_uuid(UUID_VOLATILE_MEMORY, nfit_uuid[NFIT_SPA_VOLATILE]);
	acpi_str_to_uuid(UUID_PERSISTENT_MEMORY, nfit_uuid[NFIT_SPA_PM]);
	acpi_str_to_uuid(UUID_CONTROL_REGION, nfit_uuid[NFIT_SPA_DCR]);
	acpi_str_to_uuid(UUID_DATA_REGION, nfit_uuid[NFIT_SPA_BDW]);
	acpi_str_to_uuid(UUID_VOLATILE_VIRTUAL_DISK, nfit_uuid[NFIT_SPA_VDISK]);
	acpi_str_to_uuid(UUID_VOLATILE_VIRTUAL_CD, nfit_uuid[NFIT_SPA_VCD]);
	acpi_str_to_uuid(UUID_PERSISTENT_VIRTUAL_DISK, nfit_uuid[NFIT_SPA_PDISK]);
	acpi_str_to_uuid(UUID_PERSISTENT_VIRTUAL_CD, nfit_uuid[NFIT_SPA_PCD]);
	acpi_str_to_uuid(UUID_NFIT_BUS, nfit_uuid[NFIT_DEV_BUS]);
	acpi_str_to_uuid(UUID_NFIT_DIMM, nfit_uuid[NFIT_DEV_DIMM]);

	return acpi_bus_register_driver(&acpi_nfit_driver);
}

static __exit void nfit_exit(void)
{
	acpi_bus_unregister_driver(&acpi_nfit_driver);
}

module_init(nfit_init);
module_exit(nfit_exit);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Intel Corporation");