pci.c 41.4 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
/*
 * Copyright 2014 IBM Corp.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 */

#include <linux/pci_regs.h>
#include <linux/pci_ids.h>
#include <linux/device.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/sort.h>
#include <linux/pci.h>
#include <linux/of.h>
#include <linux/delay.h>
#include <asm/opal.h>
#include <asm/msi_bitmap.h>
#include <asm/pci-bridge.h> /* for struct pci_controller */
#include <asm/pnv-pci.h>
R
Ryan Grimm 已提交
24
#include <asm/io.h>
25 26

#include "cxl.h"
D
Daniel Axtens 已提交
27
#include <misc/cxl.h>
28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93


#define CXL_PCI_VSEC_ID	0x1280
#define CXL_VSEC_MIN_SIZE 0x80

#define CXL_READ_VSEC_LENGTH(dev, vsec, dest)			\
	{							\
		pci_read_config_word(dev, vsec + 0x6, dest);	\
		*dest >>= 4;					\
	}
#define CXL_READ_VSEC_NAFUS(dev, vsec, dest) \
	pci_read_config_byte(dev, vsec + 0x8, dest)

#define CXL_READ_VSEC_STATUS(dev, vsec, dest) \
	pci_read_config_byte(dev, vsec + 0x9, dest)
#define CXL_STATUS_SECOND_PORT  0x80
#define CXL_STATUS_MSI_X_FULL   0x40
#define CXL_STATUS_MSI_X_SINGLE 0x20
#define CXL_STATUS_FLASH_RW     0x08
#define CXL_STATUS_FLASH_RO     0x04
#define CXL_STATUS_LOADABLE_AFU 0x02
#define CXL_STATUS_LOADABLE_PSL 0x01
/* If we see these features we won't try to use the card */
#define CXL_UNSUPPORTED_FEATURES \
	(CXL_STATUS_MSI_X_FULL | CXL_STATUS_MSI_X_SINGLE)

#define CXL_READ_VSEC_MODE_CONTROL(dev, vsec, dest) \
	pci_read_config_byte(dev, vsec + 0xa, dest)
#define CXL_WRITE_VSEC_MODE_CONTROL(dev, vsec, val) \
	pci_write_config_byte(dev, vsec + 0xa, val)
#define CXL_VSEC_PROTOCOL_MASK   0xe0
#define CXL_VSEC_PROTOCOL_1024TB 0x80
#define CXL_VSEC_PROTOCOL_512TB  0x40
#define CXL_VSEC_PROTOCOL_256TB  0x20 /* Power 8 uses this */
#define CXL_VSEC_PROTOCOL_ENABLE 0x01

#define CXL_READ_VSEC_PSL_REVISION(dev, vsec, dest) \
	pci_read_config_word(dev, vsec + 0xc, dest)
#define CXL_READ_VSEC_CAIA_MINOR(dev, vsec, dest) \
	pci_read_config_byte(dev, vsec + 0xe, dest)
#define CXL_READ_VSEC_CAIA_MAJOR(dev, vsec, dest) \
	pci_read_config_byte(dev, vsec + 0xf, dest)
#define CXL_READ_VSEC_BASE_IMAGE(dev, vsec, dest) \
	pci_read_config_word(dev, vsec + 0x10, dest)

#define CXL_READ_VSEC_IMAGE_STATE(dev, vsec, dest) \
	pci_read_config_byte(dev, vsec + 0x13, dest)
#define CXL_WRITE_VSEC_IMAGE_STATE(dev, vsec, val) \
	pci_write_config_byte(dev, vsec + 0x13, val)
#define CXL_VSEC_USER_IMAGE_LOADED 0x80 /* RO */
#define CXL_VSEC_PERST_LOADS_IMAGE 0x20 /* RW */
#define CXL_VSEC_PERST_SELECT_USER 0x10 /* RW */

#define CXL_READ_VSEC_AFU_DESC_OFF(dev, vsec, dest) \
	pci_read_config_dword(dev, vsec + 0x20, dest)
#define CXL_READ_VSEC_AFU_DESC_SIZE(dev, vsec, dest) \
	pci_read_config_dword(dev, vsec + 0x24, dest)
#define CXL_READ_VSEC_PS_OFF(dev, vsec, dest) \
	pci_read_config_dword(dev, vsec + 0x28, dest)
#define CXL_READ_VSEC_PS_SIZE(dev, vsec, dest) \
	pci_read_config_dword(dev, vsec + 0x2c, dest)


/* This works a little different than the p1/p2 register accesses to make it
 * easier to pull out individual fields */
#define AFUD_READ(afu, off)		in_be64(afu->afu_desc_mmio + off)
94
#define AFUD_READ_LE(afu, off)		in_le64(afu->afu_desc_mmio + off)
95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118
#define EXTRACT_PPC_BIT(val, bit)	(!!(val & PPC_BIT(bit)))
#define EXTRACT_PPC_BITS(val, bs, be)	((val & PPC_BITMASK(bs, be)) >> PPC_BITLSHIFT(be))

#define AFUD_READ_INFO(afu)		AFUD_READ(afu, 0x0)
#define   AFUD_NUM_INTS_PER_PROC(val)	EXTRACT_PPC_BITS(val,  0, 15)
#define   AFUD_NUM_PROCS(val)		EXTRACT_PPC_BITS(val, 16, 31)
#define   AFUD_NUM_CRS(val)		EXTRACT_PPC_BITS(val, 32, 47)
#define   AFUD_MULTIMODE(val)		EXTRACT_PPC_BIT(val, 48)
#define   AFUD_PUSH_BLOCK_TRANSFER(val)	EXTRACT_PPC_BIT(val, 55)
#define   AFUD_DEDICATED_PROCESS(val)	EXTRACT_PPC_BIT(val, 59)
#define   AFUD_AFU_DIRECTED(val)	EXTRACT_PPC_BIT(val, 61)
#define   AFUD_TIME_SLICED(val)		EXTRACT_PPC_BIT(val, 63)
#define AFUD_READ_CR(afu)		AFUD_READ(afu, 0x20)
#define   AFUD_CR_LEN(val)		EXTRACT_PPC_BITS(val, 8, 63)
#define AFUD_READ_CR_OFF(afu)		AFUD_READ(afu, 0x28)
#define AFUD_READ_PPPSA(afu)		AFUD_READ(afu, 0x30)
#define   AFUD_PPPSA_PP(val)		EXTRACT_PPC_BIT(val, 6)
#define   AFUD_PPPSA_PSA(val)		EXTRACT_PPC_BIT(val, 7)
#define   AFUD_PPPSA_LEN(val)		EXTRACT_PPC_BITS(val, 8, 63)
#define AFUD_READ_PPPSA_OFF(afu)	AFUD_READ(afu, 0x38)
#define AFUD_READ_EB(afu)		AFUD_READ(afu, 0x40)
#define   AFUD_EB_LEN(val)		EXTRACT_PPC_BITS(val, 8, 63)
#define AFUD_READ_EB_OFF(afu)		AFUD_READ(afu, 0x48)

119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136
u16 cxl_afu_cr_read16(struct cxl_afu *afu, int cr, u64 off)
{
	u64 aligned_off = off & ~0x3L;
	u32 val;

	val = cxl_afu_cr_read32(afu, cr, aligned_off);
	return (val >> ((off & 0x2) * 8)) & 0xffff;
}

u8 cxl_afu_cr_read8(struct cxl_afu *afu, int cr, u64 off)
{
	u64 aligned_off = off & ~0x3L;
	u32 val;

	val = cxl_afu_cr_read32(afu, cr, aligned_off);
	return (val >> ((off & 0x3) * 8)) & 0xff;
}

137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208
static DEFINE_PCI_DEVICE_TABLE(cxl_pci_tbl) = {
	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x0477), },
	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x044b), },
	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x04cf), },
	{ PCI_DEVICE_CLASS(0x120000, ~0), },

	{ }
};
MODULE_DEVICE_TABLE(pci, cxl_pci_tbl);


/*
 * Mostly using these wrappers to avoid confusion:
 * priv 1 is BAR2, while priv 2 is BAR0
 */
static inline resource_size_t p1_base(struct pci_dev *dev)
{
	return pci_resource_start(dev, 2);
}

static inline resource_size_t p1_size(struct pci_dev *dev)
{
	return pci_resource_len(dev, 2);
}

static inline resource_size_t p2_base(struct pci_dev *dev)
{
	return pci_resource_start(dev, 0);
}

static inline resource_size_t p2_size(struct pci_dev *dev)
{
	return pci_resource_len(dev, 0);
}

static int find_cxl_vsec(struct pci_dev *dev)
{
	int vsec = 0;
	u16 val;

	while ((vsec = pci_find_next_ext_capability(dev, vsec, PCI_EXT_CAP_ID_VNDR))) {
		pci_read_config_word(dev, vsec + 0x4, &val);
		if (val == CXL_PCI_VSEC_ID)
			return vsec;
	}
	return 0;

}

static void dump_cxl_config_space(struct pci_dev *dev)
{
	int vsec;
	u32 val;

	dev_info(&dev->dev, "dump_cxl_config_space\n");

	pci_read_config_dword(dev, PCI_BASE_ADDRESS_0, &val);
	dev_info(&dev->dev, "BAR0: %#.8x\n", val);
	pci_read_config_dword(dev, PCI_BASE_ADDRESS_1, &val);
	dev_info(&dev->dev, "BAR1: %#.8x\n", val);
	pci_read_config_dword(dev, PCI_BASE_ADDRESS_2, &val);
	dev_info(&dev->dev, "BAR2: %#.8x\n", val);
	pci_read_config_dword(dev, PCI_BASE_ADDRESS_3, &val);
	dev_info(&dev->dev, "BAR3: %#.8x\n", val);
	pci_read_config_dword(dev, PCI_BASE_ADDRESS_4, &val);
	dev_info(&dev->dev, "BAR4: %#.8x\n", val);
	pci_read_config_dword(dev, PCI_BASE_ADDRESS_5, &val);
	dev_info(&dev->dev, "BAR5: %#.8x\n", val);

	dev_info(&dev->dev, "p1 regs: %#llx, len: %#llx\n",
		p1_base(dev), p1_size(dev));
	dev_info(&dev->dev, "p2 regs: %#llx, len: %#llx\n",
M
Michael Neuling 已提交
209
		p2_base(dev), p2_size(dev));
210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290
	dev_info(&dev->dev, "BAR 4/5: %#llx, len: %#llx\n",
		pci_resource_start(dev, 4), pci_resource_len(dev, 4));

	if (!(vsec = find_cxl_vsec(dev)))
		return;

#define show_reg(name, what) \
	dev_info(&dev->dev, "cxl vsec: %30s: %#x\n", name, what)

	pci_read_config_dword(dev, vsec + 0x0, &val);
	show_reg("Cap ID", (val >> 0) & 0xffff);
	show_reg("Cap Ver", (val >> 16) & 0xf);
	show_reg("Next Cap Ptr", (val >> 20) & 0xfff);
	pci_read_config_dword(dev, vsec + 0x4, &val);
	show_reg("VSEC ID", (val >> 0) & 0xffff);
	show_reg("VSEC Rev", (val >> 16) & 0xf);
	show_reg("VSEC Length",	(val >> 20) & 0xfff);
	pci_read_config_dword(dev, vsec + 0x8, &val);
	show_reg("Num AFUs", (val >> 0) & 0xff);
	show_reg("Status", (val >> 8) & 0xff);
	show_reg("Mode Control", (val >> 16) & 0xff);
	show_reg("Reserved", (val >> 24) & 0xff);
	pci_read_config_dword(dev, vsec + 0xc, &val);
	show_reg("PSL Rev", (val >> 0) & 0xffff);
	show_reg("CAIA Ver", (val >> 16) & 0xffff);
	pci_read_config_dword(dev, vsec + 0x10, &val);
	show_reg("Base Image Rev", (val >> 0) & 0xffff);
	show_reg("Reserved", (val >> 16) & 0x0fff);
	show_reg("Image Control", (val >> 28) & 0x3);
	show_reg("Reserved", (val >> 30) & 0x1);
	show_reg("Image Loaded", (val >> 31) & 0x1);

	pci_read_config_dword(dev, vsec + 0x14, &val);
	show_reg("Reserved", val);
	pci_read_config_dword(dev, vsec + 0x18, &val);
	show_reg("Reserved", val);
	pci_read_config_dword(dev, vsec + 0x1c, &val);
	show_reg("Reserved", val);

	pci_read_config_dword(dev, vsec + 0x20, &val);
	show_reg("AFU Descriptor Offset", val);
	pci_read_config_dword(dev, vsec + 0x24, &val);
	show_reg("AFU Descriptor Size", val);
	pci_read_config_dword(dev, vsec + 0x28, &val);
	show_reg("Problem State Offset", val);
	pci_read_config_dword(dev, vsec + 0x2c, &val);
	show_reg("Problem State Size", val);

	pci_read_config_dword(dev, vsec + 0x30, &val);
	show_reg("Reserved", val);
	pci_read_config_dword(dev, vsec + 0x34, &val);
	show_reg("Reserved", val);
	pci_read_config_dword(dev, vsec + 0x38, &val);
	show_reg("Reserved", val);
	pci_read_config_dword(dev, vsec + 0x3c, &val);
	show_reg("Reserved", val);

	pci_read_config_dword(dev, vsec + 0x40, &val);
	show_reg("PSL Programming Port", val);
	pci_read_config_dword(dev, vsec + 0x44, &val);
	show_reg("PSL Programming Control", val);

	pci_read_config_dword(dev, vsec + 0x48, &val);
	show_reg("Reserved", val);
	pci_read_config_dword(dev, vsec + 0x4c, &val);
	show_reg("Reserved", val);

	pci_read_config_dword(dev, vsec + 0x50, &val);
	show_reg("Flash Address Register", val);
	pci_read_config_dword(dev, vsec + 0x54, &val);
	show_reg("Flash Size Register", val);
	pci_read_config_dword(dev, vsec + 0x58, &val);
	show_reg("Flash Status/Control Register", val);
	pci_read_config_dword(dev, vsec + 0x58, &val);
	show_reg("Flash Data Port", val);

#undef show_reg
}

static void dump_afu_descriptor(struct cxl_afu *afu)
{
291 292
	u64 val, afu_cr_num, afu_cr_off, afu_cr_len;
	int i;
293 294 295 296 297 298 299 300 301

#define show_reg(name, what) \
	dev_info(&afu->dev, "afu desc: %30s: %#llx\n", name, what)

	val = AFUD_READ_INFO(afu);
	show_reg("num_ints_per_process", AFUD_NUM_INTS_PER_PROC(val));
	show_reg("num_of_processes", AFUD_NUM_PROCS(val));
	show_reg("num_of_afu_CRs", AFUD_NUM_CRS(val));
	show_reg("req_prog_mode", val & 0xffffULL);
302
	afu_cr_num = AFUD_NUM_CRS(val);
303 304 305 306 307 308 309 310 311 312 313

	val = AFUD_READ(afu, 0x8);
	show_reg("Reserved", val);
	val = AFUD_READ(afu, 0x10);
	show_reg("Reserved", val);
	val = AFUD_READ(afu, 0x18);
	show_reg("Reserved", val);

	val = AFUD_READ_CR(afu);
	show_reg("Reserved", (val >> (63-7)) & 0xff);
	show_reg("AFU_CR_len", AFUD_CR_LEN(val));
314
	afu_cr_len = AFUD_CR_LEN(val) * 256;
315 316

	val = AFUD_READ_CR_OFF(afu);
317
	afu_cr_off = val;
318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333
	show_reg("AFU_CR_offset", val);

	val = AFUD_READ_PPPSA(afu);
	show_reg("PerProcessPSA_control", (val >> (63-7)) & 0xff);
	show_reg("PerProcessPSA Length", AFUD_PPPSA_LEN(val));

	val = AFUD_READ_PPPSA_OFF(afu);
	show_reg("PerProcessPSA_offset", val);

	val = AFUD_READ_EB(afu);
	show_reg("Reserved", (val >> (63-7)) & 0xff);
	show_reg("AFU_EB_len", AFUD_EB_LEN(val));

	val = AFUD_READ_EB_OFF(afu);
	show_reg("AFU_EB_offset", val);

334 335 336 337 338
	for (i = 0; i < afu_cr_num; i++) {
		val = AFUD_READ_LE(afu, afu_cr_off + i * afu_cr_len);
		show_reg("CR Vendor", val & 0xffff);
		show_reg("CR Device", (val >> 16) & 0xffff);
	}
339 340 341 342 343 344 345 346 347 348
#undef show_reg
}

static int init_implementation_adapter_regs(struct cxl *adapter, struct pci_dev *dev)
{
	struct device_node *np;
	const __be32 *prop;
	u64 psl_dsnctl;
	u64 chipid;

349
	if (!(np = pnv_pci_get_phb_node(dev)))
350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380
		return -ENODEV;

	while (np && !(prop = of_get_property(np, "ibm,chip-id", NULL)))
		np = of_get_next_parent(np);
	if (!np)
		return -ENODEV;
	chipid = be32_to_cpup(prop);
	of_node_put(np);

	/* Tell PSL where to route data to */
	psl_dsnctl = 0x02E8900002000000ULL | (chipid << (63-5));
	cxl_p1_write(adapter, CXL_PSL_DSNDCTL, psl_dsnctl);
	cxl_p1_write(adapter, CXL_PSL_RESLCKTO, 0x20000000200ULL);
	/* snoop write mask */
	cxl_p1_write(adapter, CXL_PSL_SNWRALLOC, 0x00000000FFFFFFFFULL);
	/* set fir_accum */
	cxl_p1_write(adapter, CXL_PSL_FIR_CNTL, 0x0800000000000000ULL);
	/* for debugging with trace arrays */
	cxl_p1_write(adapter, CXL_PSL_TRACE, 0x0000FF7C00000000ULL);

	return 0;
}

static int init_implementation_afu_regs(struct cxl_afu *afu)
{
	/* read/write masks for this slice */
	cxl_p1n_write(afu, CXL_PSL_APCALLOC_A, 0xFFFFFFFEFEFEFEFEULL);
	/* APC read/write masks for this slice */
	cxl_p1n_write(afu, CXL_PSL_COALLOC_A, 0xFF000000FEFEFEFEULL);
	/* for debugging with trace arrays */
	cxl_p1n_write(afu, CXL_PSL_SLICE_TRACE, 0x0000FFFF00000000ULL);
I
Ian Munsie 已提交
381
	cxl_p1n_write(afu, CXL_PSL_RXCTL_A, CXL_PSL_RXCTL_AFUHP_4S);
382 383 384 385 386 387 388 389 390 391 392 393

	return 0;
}

int cxl_setup_irq(struct cxl *adapter, unsigned int hwirq,
			 unsigned int virq)
{
	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);

	return pnv_cxl_ioda_msi_setup(dev, hwirq, virq);
}

394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428
int cxl_update_image_control(struct cxl *adapter)
{
	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);
	int rc;
	int vsec;
	u8 image_state;

	if (!(vsec = find_cxl_vsec(dev))) {
		dev_err(&dev->dev, "ABORTING: CXL VSEC not found!\n");
		return -ENODEV;
	}

	if ((rc = CXL_READ_VSEC_IMAGE_STATE(dev, vsec, &image_state))) {
		dev_err(&dev->dev, "failed to read image state: %i\n", rc);
		return rc;
	}

	if (adapter->perst_loads_image)
		image_state |= CXL_VSEC_PERST_LOADS_IMAGE;
	else
		image_state &= ~CXL_VSEC_PERST_LOADS_IMAGE;

	if (adapter->perst_select_user)
		image_state |= CXL_VSEC_PERST_SELECT_USER;
	else
		image_state &= ~CXL_VSEC_PERST_SELECT_USER;

	if ((rc = CXL_WRITE_VSEC_IMAGE_STATE(dev, vsec, image_state))) {
		dev_err(&dev->dev, "failed to update image control: %i\n", rc);
		return rc;
	}

	return 0;
}

429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542
int cxl_alloc_one_irq(struct cxl *adapter)
{
	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);

	return pnv_cxl_alloc_hwirqs(dev, 1);
}

void cxl_release_one_irq(struct cxl *adapter, int hwirq)
{
	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);

	return pnv_cxl_release_hwirqs(dev, hwirq, 1);
}

int cxl_alloc_irq_ranges(struct cxl_irq_ranges *irqs, struct cxl *adapter, unsigned int num)
{
	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);

	return pnv_cxl_alloc_hwirq_ranges(irqs, dev, num);
}

void cxl_release_irq_ranges(struct cxl_irq_ranges *irqs, struct cxl *adapter)
{
	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);

	pnv_cxl_release_hwirq_ranges(irqs, dev);
}

static int setup_cxl_bars(struct pci_dev *dev)
{
	/* Safety check in case we get backported to < 3.17 without M64 */
	if ((p1_base(dev) < 0x100000000ULL) ||
	    (p2_base(dev) < 0x100000000ULL)) {
		dev_err(&dev->dev, "ABORTING: M32 BAR assignment incompatible with CXL\n");
		return -ENODEV;
	}

	/*
	 * BAR 4/5 has a special meaning for CXL and must be programmed with a
	 * special value corresponding to the CXL protocol address range.
	 * For POWER 8 that means bits 48:49 must be set to 10
	 */
	pci_write_config_dword(dev, PCI_BASE_ADDRESS_4, 0x00000000);
	pci_write_config_dword(dev, PCI_BASE_ADDRESS_5, 0x00020000);

	return 0;
}

/* pciex node: ibm,opal-m64-window = <0x3d058 0x0 0x3d058 0x0 0x8 0x0>; */
static int switch_card_to_cxl(struct pci_dev *dev)
{
	int vsec;
	u8 val;
	int rc;

	dev_info(&dev->dev, "switch card to CXL\n");

	if (!(vsec = find_cxl_vsec(dev))) {
		dev_err(&dev->dev, "ABORTING: CXL VSEC not found!\n");
		return -ENODEV;
	}

	if ((rc = CXL_READ_VSEC_MODE_CONTROL(dev, vsec, &val))) {
		dev_err(&dev->dev, "failed to read current mode control: %i", rc);
		return rc;
	}
	val &= ~CXL_VSEC_PROTOCOL_MASK;
	val |= CXL_VSEC_PROTOCOL_256TB | CXL_VSEC_PROTOCOL_ENABLE;
	if ((rc = CXL_WRITE_VSEC_MODE_CONTROL(dev, vsec, val))) {
		dev_err(&dev->dev, "failed to enable CXL protocol: %i", rc);
		return rc;
	}
	/*
	 * The CAIA spec (v0.12 11.6 Bi-modal Device Support) states
	 * we must wait 100ms after this mode switch before touching
	 * PCIe config space.
	 */
	msleep(100);

	return 0;
}

static int cxl_map_slice_regs(struct cxl_afu *afu, struct cxl *adapter, struct pci_dev *dev)
{
	u64 p1n_base, p2n_base, afu_desc;
	const u64 p1n_size = 0x100;
	const u64 p2n_size = 0x1000;

	p1n_base = p1_base(dev) + 0x10000 + (afu->slice * p1n_size);
	p2n_base = p2_base(dev) + (afu->slice * p2n_size);
	afu->psn_phys = p2_base(dev) + (adapter->ps_off + (afu->slice * adapter->ps_size));
	afu_desc = p2_base(dev) + adapter->afu_desc_off + (afu->slice * adapter->afu_desc_size);

	if (!(afu->p1n_mmio = ioremap(p1n_base, p1n_size)))
		goto err;
	if (!(afu->p2n_mmio = ioremap(p2n_base, p2n_size)))
		goto err1;
	if (afu_desc) {
		if (!(afu->afu_desc_mmio = ioremap(afu_desc, adapter->afu_desc_size)))
			goto err2;
	}

	return 0;
err2:
	iounmap(afu->p2n_mmio);
err1:
	iounmap(afu->p1n_mmio);
err:
	dev_err(&afu->dev, "Error mapping AFU MMIO regions\n");
	return -ENOMEM;
}

static void cxl_unmap_slice_regs(struct cxl_afu *afu)
{
543
	if (afu->p2n_mmio) {
544
		iounmap(afu->p2n_mmio);
545 546 547
		afu->p2n_mmio = NULL;
	}
	if (afu->p1n_mmio) {
548
		iounmap(afu->p1n_mmio);
549 550 551 552 553 554
		afu->p1n_mmio = NULL;
	}
	if (afu->afu_desc_mmio) {
		iounmap(afu->afu_desc_mmio);
		afu->afu_desc_mmio = NULL;
	}
555 556 557 558 559 560 561 562
}

static void cxl_release_afu(struct device *dev)
{
	struct cxl_afu *afu = to_cxl_afu(dev);

	pr_devel("cxl_release_afu\n");

563
	idr_destroy(&afu->contexts_idr);
564 565
	cxl_release_spa(afu);

566 567 568 569 570 571 572 573 574 575 576 577 578 579 580
	kfree(afu);
}

static struct cxl_afu *cxl_alloc_afu(struct cxl *adapter, int slice)
{
	struct cxl_afu *afu;

	if (!(afu = kzalloc(sizeof(struct cxl_afu), GFP_KERNEL)))
		return NULL;

	afu->adapter = adapter;
	afu->dev.parent = &adapter->dev;
	afu->dev.release = cxl_release_afu;
	afu->slice = slice;
	idr_init(&afu->contexts_idr);
581
	mutex_init(&afu->contexts_lock);
582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598
	spin_lock_init(&afu->afu_cntl_lock);
	mutex_init(&afu->spa_mutex);

	afu->prefault_mode = CXL_PREFAULT_NONE;
	afu->irqs_max = afu->adapter->user_irqs;

	return afu;
}

/* Expects AFU struct to have recently been zeroed out */
static int cxl_read_afu_descriptor(struct cxl_afu *afu)
{
	u64 val;

	val = AFUD_READ_INFO(afu);
	afu->pp_irqs = AFUD_NUM_INTS_PER_PROC(val);
	afu->max_procs_virtualised = AFUD_NUM_PROCS(val);
599
	afu->crs_num = AFUD_NUM_CRS(val);
600 601 602 603 604 605 606 607 608 609 610 611 612 613

	if (AFUD_AFU_DIRECTED(val))
		afu->modes_supported |= CXL_MODE_DIRECTED;
	if (AFUD_DEDICATED_PROCESS(val))
		afu->modes_supported |= CXL_MODE_DEDICATED;
	if (AFUD_TIME_SLICED(val))
		afu->modes_supported |= CXL_MODE_TIME_SLICED;

	val = AFUD_READ_PPPSA(afu);
	afu->pp_size = AFUD_PPPSA_LEN(val) * 4096;
	afu->psa = AFUD_PPPSA_PSA(val);
	if ((afu->pp_psa = AFUD_PPPSA_PP(val)))
		afu->pp_offset = AFUD_READ_PPPSA_OFF(afu);

614 615 616 617
	val = AFUD_READ_CR(afu);
	afu->crs_len = AFUD_CR_LEN(val) * 256;
	afu->crs_offset = AFUD_READ_CR_OFF(afu);

618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633

	/* eb_len is in multiple of 4K */
	afu->eb_len = AFUD_EB_LEN(AFUD_READ_EB(afu)) * 4096;
	afu->eb_offset = AFUD_READ_EB_OFF(afu);

	/* eb_off is 4K aligned so lower 12 bits are always zero */
	if (EXTRACT_PPC_BITS(afu->eb_offset, 0, 11) != 0) {
		dev_warn(&afu->dev,
			 "Invalid AFU error buffer offset %Lx\n",
			 afu->eb_offset);
		dev_info(&afu->dev,
			 "Ignoring AFU error buffer in the descriptor\n");
		/* indicate that no afu buffer exists */
		afu->eb_len = 0;
	}

634 635 636 637 638
	return 0;
}

static int cxl_afu_descriptor_looks_ok(struct cxl_afu *afu)
{
639 640
	int i;

641 642 643 644 645 646 647 648 649
	if (afu->psa && afu->adapter->ps_size <
			(afu->pp_offset + afu->pp_size*afu->max_procs_virtualised)) {
		dev_err(&afu->dev, "per-process PSA can't fit inside the PSA!\n");
		return -ENODEV;
	}

	if (afu->pp_psa && (afu->pp_size < PAGE_SIZE))
		dev_warn(&afu->dev, "AFU uses < PAGE_SIZE per-process PSA!");

650 651 652 653 654 655 656
	for (i = 0; i < afu->crs_num; i++) {
		if ((cxl_afu_cr_read32(afu, i, 0) == 0)) {
			dev_err(&afu->dev, "ABORTING: AFU configuration record %i is invalid\n", i);
			return -EINVAL;
		}
	}

657 658 659 660 661 662 663 664 665 666 667 668 669 670
	return 0;
}

static int sanitise_afu_regs(struct cxl_afu *afu)
{
	u64 reg;

	/*
	 * Clear out any regs that contain either an IVTE or address or may be
	 * waiting on an acknowledgement to try to be a bit safer as we bring
	 * it online
	 */
	reg = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
	if ((reg & CXL_AFU_Cntl_An_ES_MASK) != CXL_AFU_Cntl_An_ES_Disabled) {
671
		dev_warn(&afu->dev, "WARNING: AFU was not disabled: %#016llx\n", reg);
672
		if (__cxl_afu_reset(afu))
673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691
			return -EIO;
		if (cxl_afu_disable(afu))
			return -EIO;
		if (cxl_psl_purge(afu))
			return -EIO;
	}
	cxl_p1n_write(afu, CXL_PSL_SPAP_An, 0x0000000000000000);
	cxl_p1n_write(afu, CXL_PSL_IVTE_Limit_An, 0x0000000000000000);
	cxl_p1n_write(afu, CXL_PSL_IVTE_Offset_An, 0x0000000000000000);
	cxl_p1n_write(afu, CXL_PSL_AMBAR_An, 0x0000000000000000);
	cxl_p1n_write(afu, CXL_PSL_SPOffset_An, 0x0000000000000000);
	cxl_p1n_write(afu, CXL_HAURP_An, 0x0000000000000000);
	cxl_p2n_write(afu, CXL_CSRP_An, 0x0000000000000000);
	cxl_p2n_write(afu, CXL_AURP1_An, 0x0000000000000000);
	cxl_p2n_write(afu, CXL_AURP0_An, 0x0000000000000000);
	cxl_p2n_write(afu, CXL_SSTP1_An, 0x0000000000000000);
	cxl_p2n_write(afu, CXL_SSTP0_An, 0x0000000000000000);
	reg = cxl_p2n_read(afu, CXL_PSL_DSISR_An);
	if (reg) {
692
		dev_warn(&afu->dev, "AFU had pending DSISR: %#016llx\n", reg);
693 694 695 696 697 698 699 700
		if (reg & CXL_PSL_DSISR_TRANS)
			cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_AE);
		else
			cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_A);
	}
	reg = cxl_p1n_read(afu, CXL_PSL_SERR_An);
	if (reg) {
		if (reg & ~0xffff)
701
			dev_warn(&afu->dev, "AFU had pending SERR: %#016llx\n", reg);
702 703 704 705
		cxl_p1n_write(afu, CXL_PSL_SERR_An, reg & ~0xffff);
	}
	reg = cxl_p2n_read(afu, CXL_PSL_ErrStat_An);
	if (reg) {
706
		dev_warn(&afu->dev, "AFU had pending error status: %#016llx\n", reg);
707 708 709 710 711 712
		cxl_p2n_write(afu, CXL_PSL_ErrStat_An, reg);
	}

	return 0;
}

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
#define ERR_BUFF_MAX_COPY_SIZE PAGE_SIZE
/*
 * afu_eb_read:
 * Called from sysfs and reads the afu error info buffer. The h/w only supports
 * 4/8 bytes aligned access. So in case the requested offset/count arent 8 byte
 * aligned the function uses a bounce buffer which can be max PAGE_SIZE.
 */
ssize_t cxl_afu_read_err_buffer(struct cxl_afu *afu, char *buf,
				loff_t off, size_t count)
{
	loff_t aligned_start, aligned_end;
	size_t aligned_length;
	void *tbuf;
	const void __iomem *ebuf = afu->afu_desc_mmio + afu->eb_offset;

	if (count == 0 || off < 0 || (size_t)off >= afu->eb_len)
		return 0;

	/* calculate aligned read window */
	count = min((size_t)(afu->eb_len - off), count);
	aligned_start = round_down(off, 8);
	aligned_end = round_up(off + count, 8);
	aligned_length = aligned_end - aligned_start;

	/* max we can copy in one read is PAGE_SIZE */
	if (aligned_length > ERR_BUFF_MAX_COPY_SIZE) {
		aligned_length = ERR_BUFF_MAX_COPY_SIZE;
		count = ERR_BUFF_MAX_COPY_SIZE - (off & 0x7);
	}

	/* use bounce buffer for copy */
	tbuf = (void *)__get_free_page(GFP_TEMPORARY);
	if (!tbuf)
		return -ENOMEM;

	/* perform aligned read from the mmio region */
	memcpy_fromio(tbuf, ebuf + aligned_start, aligned_length);
	memcpy(buf, tbuf + (off & 0x7), count);

	free_page((unsigned long)tbuf);

	return count;
}

D
Daniel Axtens 已提交
757
static int cxl_configure_afu(struct cxl_afu *afu, struct cxl *adapter, struct pci_dev *dev)
758 759 760 761
{
	int rc;

	if ((rc = cxl_map_slice_regs(afu, adapter, dev)))
D
Daniel Axtens 已提交
762
		return rc;
763 764

	if ((rc = sanitise_afu_regs(afu)))
D
Daniel Axtens 已提交
765
		goto err1;
766 767

	/* We need to reset the AFU before we can read the AFU descriptor */
768
	if ((rc = __cxl_afu_reset(afu)))
D
Daniel Axtens 已提交
769
		goto err1;
770 771 772 773 774

	if (cxl_verbose)
		dump_afu_descriptor(afu);

	if ((rc = cxl_read_afu_descriptor(afu)))
D
Daniel Axtens 已提交
775
		goto err1;
776 777

	if ((rc = cxl_afu_descriptor_looks_ok(afu)))
D
Daniel Axtens 已提交
778
		goto err1;
779 780

	if ((rc = init_implementation_afu_regs(afu)))
D
Daniel Axtens 已提交
781
		goto err1;
782 783

	if ((rc = cxl_register_serr_irq(afu)))
D
Daniel Axtens 已提交
784
		goto err1;
785 786

	if ((rc = cxl_register_psl_irq(afu)))
D
Daniel Axtens 已提交
787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820
		goto err2;

	return 0;

err2:
	cxl_release_serr_irq(afu);
err1:
	cxl_unmap_slice_regs(afu);
	return rc;
}

static void cxl_deconfigure_afu(struct cxl_afu *afu)
{
	cxl_release_psl_irq(afu);
	cxl_release_serr_irq(afu);
	cxl_unmap_slice_regs(afu);
}

static int cxl_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev)
{
	struct cxl_afu *afu;
	int rc;

	afu = cxl_alloc_afu(adapter, slice);
	if (!afu)
		return -ENOMEM;

	rc = dev_set_name(&afu->dev, "afu%i.%i", adapter->adapter_num, slice);
	if (rc)
		goto err_free;

	rc = cxl_configure_afu(afu, adapter, dev);
	if (rc)
		goto err_free;
821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836

	/* Don't care if this fails */
	cxl_debugfs_afu_add(afu);

	/*
	 * After we call this function we must not free the afu directly, even
	 * if it returns an error!
	 */
	if ((rc = cxl_register_afu(afu)))
		goto err_put1;

	if ((rc = cxl_sysfs_afu_add(afu)))
		goto err_put1;

	adapter->afu[afu->slice] = afu;

837 838 839
	if ((rc = cxl_pci_vphb_add(afu)))
		dev_info(&afu->dev, "Can't register vPHB\n");

840 841 842
	return 0;

err_put1:
D
Daniel Axtens 已提交
843
	cxl_deconfigure_afu(afu);
844
	cxl_debugfs_afu_remove(afu);
D
Daniel Axtens 已提交
845
	device_unregister(&afu->dev);
846
	return rc;
D
Daniel Axtens 已提交
847 848 849 850 851

err_free:
	kfree(afu);
	return rc;

852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870
}

static void cxl_remove_afu(struct cxl_afu *afu)
{
	pr_devel("cxl_remove_afu\n");

	if (!afu)
		return;

	cxl_sysfs_afu_remove(afu);
	cxl_debugfs_afu_remove(afu);

	spin_lock(&afu->adapter->afu_list_lock);
	afu->adapter->afu[afu->slice] = NULL;
	spin_unlock(&afu->adapter->afu_list_lock);

	cxl_context_detach_all(afu);
	cxl_afu_deactivate_mode(afu);

D
Daniel Axtens 已提交
871
	cxl_deconfigure_afu(afu);
872 873 874
	device_unregister(&afu->dev);
}

R
Ryan Grimm 已提交
875 876 877 878 879 880 881
int cxl_reset(struct cxl *adapter)
{
	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);
	int rc;
	int i;
	u32 val;

882 883 884 885 886 887
	if (adapter->perst_same_image) {
		dev_warn(&dev->dev,
			 "cxl: refusing to reset/reflash when perst_reloads_same_image is set.\n");
		return -EINVAL;
	}

R
Ryan Grimm 已提交
888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913
	dev_info(&dev->dev, "CXL reset\n");

	/* pcie_warm_reset requests a fundamental pci reset which includes a
	 * PERST assert/deassert.  PERST triggers a loading of the image
	 * if "user" or "factory" is selected in sysfs */
	if ((rc = pci_set_pcie_reset_state(dev, pcie_warm_reset))) {
		dev_err(&dev->dev, "cxl: pcie_warm_reset failed\n");
		return rc;
	}

	/* the PERST done above fences the PHB.  So, reset depends on EEH
	 * to unbind the driver, tell Sapphire to reinit the PHB, and rebind
	 * the driver.  Do an mmio read explictly to ensure EEH notices the
	 * fenced PHB.  Retry for a few seconds before giving up. */
	i = 0;
	while (((val = mmio_read32be(adapter->p1_mmio)) != 0xffffffff) &&
		(i < 5)) {
		msleep(500);
		i++;
	}

	if (val != 0xffffffff)
		dev_err(&dev->dev, "cxl: PERST failed to trigger EEH\n");

	return rc;
}
914 915 916 917 918 919 920 921

static int cxl_map_adapter_regs(struct cxl *adapter, struct pci_dev *dev)
{
	if (pci_request_region(dev, 2, "priv 2 regs"))
		goto err1;
	if (pci_request_region(dev, 0, "priv 1 regs"))
		goto err2;

922
	pr_devel("cxl_map_adapter_regs: p1: %#016llx %#llx, p2: %#016llx %#llx",
923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945
			p1_base(dev), p1_size(dev), p2_base(dev), p2_size(dev));

	if (!(adapter->p1_mmio = ioremap(p1_base(dev), p1_size(dev))))
		goto err3;

	if (!(adapter->p2_mmio = ioremap(p2_base(dev), p2_size(dev))))
		goto err4;

	return 0;

err4:
	iounmap(adapter->p1_mmio);
	adapter->p1_mmio = NULL;
err3:
	pci_release_region(dev, 0);
err2:
	pci_release_region(dev, 2);
err1:
	return -ENOMEM;
}

static void cxl_unmap_adapter_regs(struct cxl *adapter)
{
946
	if (adapter->p1_mmio) {
947
		iounmap(adapter->p1_mmio);
948 949 950 951
		adapter->p1_mmio = NULL;
		pci_release_region(to_pci_dev(adapter->dev.parent), 2);
	}
	if (adapter->p2_mmio) {
952
		iounmap(adapter->p2_mmio);
953 954 955
		adapter->p2_mmio = NULL;
		pci_release_region(to_pci_dev(adapter->dev.parent), 0);
	}
956 957 958 959 960 961 962 963 964 965 966
}

static int cxl_read_vsec(struct cxl *adapter, struct pci_dev *dev)
{
	int vsec;
	u32 afu_desc_off, afu_desc_size;
	u32 ps_off, ps_size;
	u16 vseclen;
	u8 image_state;

	if (!(vsec = find_cxl_vsec(dev))) {
967
		dev_err(&dev->dev, "ABORTING: CXL VSEC not found!\n");
968 969 970 971 972
		return -ENODEV;
	}

	CXL_READ_VSEC_LENGTH(dev, vsec, &vseclen);
	if (vseclen < CXL_VSEC_MIN_SIZE) {
973
		dev_err(&dev->dev, "ABORTING: CXL VSEC too short\n");
974 975 976 977 978 979 980 981 982 983
		return -EINVAL;
	}

	CXL_READ_VSEC_STATUS(dev, vsec, &adapter->vsec_status);
	CXL_READ_VSEC_PSL_REVISION(dev, vsec, &adapter->psl_rev);
	CXL_READ_VSEC_CAIA_MAJOR(dev, vsec, &adapter->caia_major);
	CXL_READ_VSEC_CAIA_MINOR(dev, vsec, &adapter->caia_minor);
	CXL_READ_VSEC_BASE_IMAGE(dev, vsec, &adapter->base_image);
	CXL_READ_VSEC_IMAGE_STATE(dev, vsec, &image_state);
	adapter->user_image_loaded = !!(image_state & CXL_VSEC_USER_IMAGE_LOADED);
984
	adapter->perst_select_user = !!(image_state & CXL_VSEC_USER_IMAGE_LOADED);
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

	CXL_READ_VSEC_NAFUS(dev, vsec, &adapter->slices);
	CXL_READ_VSEC_AFU_DESC_OFF(dev, vsec, &afu_desc_off);
	CXL_READ_VSEC_AFU_DESC_SIZE(dev, vsec, &afu_desc_size);
	CXL_READ_VSEC_PS_OFF(dev, vsec, &ps_off);
	CXL_READ_VSEC_PS_SIZE(dev, vsec, &ps_size);

	/* Convert everything to bytes, because there is NO WAY I'd look at the
	 * code a month later and forget what units these are in ;-) */
	adapter->ps_off = ps_off * 64 * 1024;
	adapter->ps_size = ps_size * 64 * 1024;
	adapter->afu_desc_off = afu_desc_off * 64 * 1024;
	adapter->afu_desc_size = afu_desc_size *64 * 1024;

	/* Total IRQs - 1 PSL ERROR - #AFU*(1 slice error + 1 DSI) */
	adapter->user_irqs = pnv_cxl_get_irq_count(dev) - 1 - 2*adapter->slices;

	return 0;
}

static int cxl_vsec_looks_ok(struct cxl *adapter, struct pci_dev *dev)
{
	if (adapter->vsec_status & CXL_STATUS_SECOND_PORT)
		return -EBUSY;

	if (adapter->vsec_status & CXL_UNSUPPORTED_FEATURES) {
1011
		dev_err(&dev->dev, "ABORTING: CXL requires unsupported features\n");
1012 1013 1014 1015 1016 1017
		return -EINVAL;
	}

	if (!adapter->slices) {
		/* Once we support dynamic reprogramming we can use the card if
		 * it supports loadable AFUs */
1018
		dev_err(&dev->dev, "ABORTING: Device has no AFUs\n");
1019 1020 1021 1022
		return -EINVAL;
	}

	if (!adapter->afu_desc_off || !adapter->afu_desc_size) {
1023
		dev_err(&dev->dev, "ABORTING: VSEC shows no AFU descriptors\n");
1024 1025 1026 1027
		return -EINVAL;
	}

	if (adapter->ps_size > p2_size(dev) - adapter->ps_off) {
1028
		dev_err(&dev->dev, "ABORTING: Problem state size larger than "
1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042
				   "available in BAR2: 0x%llx > 0x%llx\n",
			 adapter->ps_size, p2_size(dev) - adapter->ps_off);
		return -EINVAL;
	}

	return 0;
}

static void cxl_release_adapter(struct device *dev)
{
	struct cxl *adapter = to_cxl_adapter(dev);

	pr_devel("cxl_release_adapter\n");

1043 1044
	cxl_remove_adapter_nr(adapter);

1045 1046 1047
	kfree(adapter);
}

1048
static struct cxl *cxl_alloc_adapter(void)
1049 1050 1051 1052 1053 1054 1055 1056
{
	struct cxl *adapter;

	if (!(adapter = kzalloc(sizeof(struct cxl), GFP_KERNEL)))
		return NULL;

	spin_lock_init(&adapter->afu_list_lock);

1057 1058 1059 1060 1061 1062
	if (cxl_alloc_adapter_nr(adapter))
		goto err1;

	if (dev_set_name(&adapter->dev, "card%i", adapter->adapter_num))
		goto err2;

1063
	return adapter;
1064 1065 1066 1067 1068 1069

err2:
	cxl_remove_adapter_nr(adapter);
err1:
	kfree(adapter);
	return NULL;
1070 1071 1072 1073 1074 1075 1076 1077
}

static int sanitise_adapter_regs(struct cxl *adapter)
{
	cxl_p1_write(adapter, CXL_PSL_ErrIVTE, 0x0000000000000000);
	return cxl_tlb_slb_invalidate(adapter);
}

1078 1079 1080 1081
/* This should contain *only* operations that can safely be done in
 * both creation and recovery.
 */
static int cxl_configure_adapter(struct cxl *adapter, struct pci_dev *dev)
1082 1083 1084
{
	int rc;

1085 1086 1087
	adapter->dev.parent = &dev->dev;
	adapter->dev.release = cxl_release_adapter;
	pci_set_drvdata(dev, adapter);
1088

1089 1090 1091 1092 1093
	rc = pci_enable_device(dev);
	if (rc) {
		dev_err(&dev->dev, "pci_enable_device failed: %i\n", rc);
		return rc;
	}
1094

1095
	if ((rc = cxl_read_vsec(adapter, dev)))
1096
		return rc;
1097 1098

	if ((rc = cxl_vsec_looks_ok(adapter, dev)))
1099
	        return rc;
1100 1101

	if ((rc = setup_cxl_bars(dev)))
1102
		return rc;
1103

1104
	if ((rc = switch_card_to_cxl(dev)))
1105
		return rc;
1106

1107
	if ((rc = cxl_update_image_control(adapter)))
1108
		return rc;
1109

1110
	if ((rc = cxl_map_adapter_regs(adapter, dev)))
1111
		return rc;
1112 1113

	if ((rc = sanitise_adapter_regs(adapter)))
1114
		goto err;
1115 1116

	if ((rc = init_implementation_adapter_regs(adapter, dev)))
1117
		goto err;
1118

R
Ryan Grimm 已提交
1119
	if ((rc = pnv_phb_to_cxl_mode(dev, OPAL_PHB_CAPI_MODE_CAPI)))
1120
		goto err;
1121

R
Ryan Grimm 已提交
1122 1123
	/* If recovery happened, the last step is to turn on snooping.
	 * In the non-recovery case this has no effect */
1124 1125
	if ((rc = pnv_phb_to_cxl_mode(dev, OPAL_PHB_CAPI_MODE_SNOOP_ON)))
		goto err;
R
Ryan Grimm 已提交
1126

1127
	if ((rc = cxl_register_psl_err_irq(adapter)))
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 1153 1154 1155 1156 1157 1158 1159 1160
		goto err;

	return 0;

err:
	cxl_unmap_adapter_regs(adapter);
	return rc;

}

static void cxl_deconfigure_adapter(struct cxl *adapter)
{
	struct pci_dev *pdev = to_pci_dev(adapter->dev.parent);

	cxl_release_psl_err_irq(adapter);
	cxl_unmap_adapter_regs(adapter);

	pci_disable_device(pdev);
}

static struct cxl *cxl_init_adapter(struct pci_dev *dev)
{
	struct cxl *adapter;
	int rc;

	adapter = cxl_alloc_adapter();
	if (!adapter)
		return ERR_PTR(-ENOMEM);

	/* Set defaults for parameters which need to persist over
	 * configure/reconfigure
	 */
	adapter->perst_loads_image = true;
1161
	adapter->perst_same_image = false;
1162 1163 1164 1165 1166 1167 1168

	rc = cxl_configure_adapter(adapter, dev);
	if (rc) {
		pci_disable_device(dev);
		cxl_release_adapter(&adapter->dev);
		return ERR_PTR(rc);
	}
1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185

	/* Don't care if this one fails: */
	cxl_debugfs_adapter_add(adapter);

	/*
	 * After we call this function we must not free the adapter directly,
	 * even if it returns an error!
	 */
	if ((rc = cxl_register_adapter(adapter)))
		goto err_put1;

	if ((rc = cxl_sysfs_adapter_add(adapter)))
		goto err_put1;

	return adapter;

err_put1:
1186 1187 1188
	/* This should mirror cxl_remove_adapter, except without the
	 * sysfs parts
	 */
1189
	cxl_debugfs_adapter_remove(adapter);
1190 1191
	cxl_deconfigure_adapter(adapter);
	device_unregister(&adapter->dev);
1192 1193 1194 1195 1196
	return ERR_PTR(rc);
}

static void cxl_remove_adapter(struct cxl *adapter)
{
1197
	pr_devel("cxl_remove_adapter\n");
1198 1199 1200 1201

	cxl_sysfs_adapter_remove(adapter);
	cxl_debugfs_adapter_remove(adapter);

1202
	cxl_deconfigure_adapter(adapter);
1203

1204
	device_unregister(&adapter->dev);
1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224
}

static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
{
	struct cxl *adapter;
	int slice;
	int rc;

	pci_dev_get(dev);

	if (cxl_verbose)
		dump_cxl_config_space(dev);

	adapter = cxl_init_adapter(dev);
	if (IS_ERR(adapter)) {
		dev_err(&dev->dev, "cxl_init_adapter failed: %li\n", PTR_ERR(adapter));
		return PTR_ERR(adapter);
	}

	for (slice = 0; slice < adapter->slices; slice++) {
D
Daniel Axtens 已提交
1225
		if ((rc = cxl_init_afu(adapter, slice, dev))) {
1226
			dev_err(&dev->dev, "AFU %i failed to initialise: %i\n", slice, rc);
D
Daniel Axtens 已提交
1227 1228 1229 1230 1231 1232
			continue;
		}

		rc = cxl_afu_select_best_mode(adapter->afu[slice]);
		if (rc)
			dev_err(&dev->dev, "AFU %i failed to start: %i\n", slice, rc);
1233 1234 1235 1236 1237 1238 1239 1240
	}

	return 0;
}

static void cxl_remove(struct pci_dev *dev)
{
	struct cxl *adapter = pci_get_drvdata(dev);
1241 1242
	struct cxl_afu *afu;
	int i;
1243 1244 1245 1246 1247

	/*
	 * Lock to prevent someone grabbing a ref through the adapter list as
	 * we are removing it
	 */
1248 1249 1250 1251 1252
	for (i = 0; i < adapter->slices; i++) {
		afu = adapter->afu[i];
		cxl_pci_vphb_remove(afu);
		cxl_remove_afu(afu);
	}
1253 1254 1255
	cxl_remove_adapter(adapter);
}

D
Daniel Axtens 已提交
1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506
static pci_ers_result_t cxl_vphb_error_detected(struct cxl_afu *afu,
						pci_channel_state_t state)
{
	struct pci_dev *afu_dev;
	pci_ers_result_t result = PCI_ERS_RESULT_NEED_RESET;
	pci_ers_result_t afu_result = PCI_ERS_RESULT_NEED_RESET;

	/* There should only be one entry, but go through the list
	 * anyway
	 */
	list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {
		if (!afu_dev->driver)
			continue;

		afu_dev->error_state = state;

		if (afu_dev->driver->err_handler)
			afu_result = afu_dev->driver->err_handler->error_detected(afu_dev,
										  state);
		/* Disconnect trumps all, NONE trumps NEED_RESET */
		if (afu_result == PCI_ERS_RESULT_DISCONNECT)
			result = PCI_ERS_RESULT_DISCONNECT;
		else if ((afu_result == PCI_ERS_RESULT_NONE) &&
			 (result == PCI_ERS_RESULT_NEED_RESET))
			result = PCI_ERS_RESULT_NONE;
	}
	return result;
}

static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,
					       pci_channel_state_t state)
{
	struct cxl *adapter = pci_get_drvdata(pdev);
	struct cxl_afu *afu;
	pci_ers_result_t result = PCI_ERS_RESULT_NEED_RESET;
	int i;

	/* At this point, we could still have an interrupt pending.
	 * Let's try to get them out of the way before they do
	 * anything we don't like.
	 */
	schedule();

	/* If we're permanently dead, give up. */
	if (state == pci_channel_io_perm_failure) {
		/* Tell the AFU drivers; but we don't care what they
		 * say, we're going away.
		 */
		for (i = 0; i < adapter->slices; i++) {
			afu = adapter->afu[i];
			cxl_vphb_error_detected(afu, state);
		}
		return PCI_ERS_RESULT_DISCONNECT;
	}

	/* Are we reflashing?
	 *
	 * If we reflash, we could come back as something entirely
	 * different, including a non-CAPI card. As such, by default
	 * we don't participate in the process. We'll be unbound and
	 * the slot re-probed. (TODO: check EEH doesn't blindly rebind
	 * us!)
	 *
	 * However, this isn't the entire story: for reliablity
	 * reasons, we usually want to reflash the FPGA on PERST in
	 * order to get back to a more reliable known-good state.
	 *
	 * This causes us a bit of a problem: if we reflash we can't
	 * trust that we'll come back the same - we could have a new
	 * image and been PERSTed in order to load that
	 * image. However, most of the time we actually *will* come
	 * back the same - for example a regular EEH event.
	 *
	 * Therefore, we allow the user to assert that the image is
	 * indeed the same and that we should continue on into EEH
	 * anyway.
	 */
	if (adapter->perst_loads_image && !adapter->perst_same_image) {
		/* TODO take the PHB out of CXL mode */
		dev_info(&pdev->dev, "reflashing, so opting out of EEH!\n");
		return PCI_ERS_RESULT_NONE;
	}

	/*
	 * At this point, we want to try to recover.  We'll always
	 * need a complete slot reset: we don't trust any other reset.
	 *
	 * Now, we go through each AFU:
	 *  - We send the driver, if bound, an error_detected callback.
	 *    We expect it to clean up, but it can also tell us to give
	 *    up and permanently detach the card. To simplify things, if
	 *    any bound AFU driver doesn't support EEH, we give up on EEH.
	 *
	 *  - We detach all contexts associated with the AFU. This
	 *    does not free them, but puts them into a CLOSED state
	 *    which causes any the associated files to return useful
	 *    errors to userland. It also unmaps, but does not free,
	 *    any IRQs.
	 *
	 *  - We clean up our side: releasing and unmapping resources we hold
	 *    so we can wire them up again when the hardware comes back up.
	 *
	 * Driver authors should note:
	 *
	 *  - Any contexts you create in your kernel driver (except
	 *    those associated with anonymous file descriptors) are
	 *    your responsibility to free and recreate. Likewise with
	 *    any attached resources.
	 *
	 *  - We will take responsibility for re-initialising the
	 *    device context (the one set up for you in
	 *    cxl_pci_enable_device_hook and accessed through
	 *    cxl_get_context). If you've attached IRQs or other
	 *    resources to it, they remains yours to free.
	 *
	 * You can call the same functions to release resources as you
	 * normally would: we make sure that these functions continue
	 * to work when the hardware is down.
	 *
	 * Two examples:
	 *
	 * 1) If you normally free all your resources at the end of
	 *    each request, or if you use anonymous FDs, your
	 *    error_detected callback can simply set a flag to tell
	 *    your driver not to start any new calls. You can then
	 *    clear the flag in the resume callback.
	 *
	 * 2) If you normally allocate your resources on startup:
	 *     * Set a flag in error_detected as above.
	 *     * Let CXL detach your contexts.
	 *     * In slot_reset, free the old resources and allocate new ones.
	 *     * In resume, clear the flag to allow things to start.
	 */
	for (i = 0; i < adapter->slices; i++) {
		afu = adapter->afu[i];

		result = cxl_vphb_error_detected(afu, state);

		/* Only continue if everyone agrees on NEED_RESET */
		if (result != PCI_ERS_RESULT_NEED_RESET)
			return result;

		cxl_context_detach_all(afu);
		cxl_afu_deactivate_mode(afu);
		cxl_deconfigure_afu(afu);
	}
	cxl_deconfigure_adapter(adapter);

	return result;
}

static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev)
{
	struct cxl *adapter = pci_get_drvdata(pdev);
	struct cxl_afu *afu;
	struct cxl_context *ctx;
	struct pci_dev *afu_dev;
	pci_ers_result_t afu_result = PCI_ERS_RESULT_RECOVERED;
	pci_ers_result_t result = PCI_ERS_RESULT_RECOVERED;
	int i;

	if (cxl_configure_adapter(adapter, pdev))
		goto err;

	for (i = 0; i < adapter->slices; i++) {
		afu = adapter->afu[i];

		if (cxl_configure_afu(afu, adapter, pdev))
			goto err;

		if (cxl_afu_select_best_mode(afu))
			goto err;

		cxl_pci_vphb_reconfigure(afu);

		list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {
			/* Reset the device context.
			 * TODO: make this less disruptive
			 */
			ctx = cxl_get_context(afu_dev);

			if (ctx && cxl_release_context(ctx))
				goto err;

			ctx = cxl_dev_context_init(afu_dev);
			if (!ctx)
				goto err;

			afu_dev->dev.archdata.cxl_ctx = ctx;

			if (cxl_afu_check_and_enable(afu))
				goto err;

			afu_dev->error_state = pci_channel_io_normal;

			/* If there's a driver attached, allow it to
			 * chime in on recovery. Drivers should check
			 * if everything has come back OK, but
			 * shouldn't start new work until we call
			 * their resume function.
			 */
			if (!afu_dev->driver)
				continue;

			if (afu_dev->driver->err_handler &&
			    afu_dev->driver->err_handler->slot_reset)
				afu_result = afu_dev->driver->err_handler->slot_reset(afu_dev);

			if (afu_result == PCI_ERS_RESULT_DISCONNECT)
				result = PCI_ERS_RESULT_DISCONNECT;
		}
	}
	return result;

err:
	/* All the bits that happen in both error_detected and cxl_remove
	 * should be idempotent, so we don't need to worry about leaving a mix
	 * of unconfigured and reconfigured resources.
	 */
	dev_err(&pdev->dev, "EEH recovery failed. Asking to be disconnected.\n");
	return PCI_ERS_RESULT_DISCONNECT;
}

static void cxl_pci_resume(struct pci_dev *pdev)
{
	struct cxl *adapter = pci_get_drvdata(pdev);
	struct cxl_afu *afu;
	struct pci_dev *afu_dev;
	int i;

	/* Everything is back now. Drivers should restart work now.
	 * This is not the place to be checking if everything came back up
	 * properly, because there's no return value: do that in slot_reset.
	 */
	for (i = 0; i < adapter->slices; i++) {
		afu = adapter->afu[i];

		list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {
			if (afu_dev->driver && afu_dev->driver->err_handler &&
			    afu_dev->driver->err_handler->resume)
				afu_dev->driver->err_handler->resume(afu_dev);
		}
	}
}

static const struct pci_error_handlers cxl_err_handler = {
	.error_detected = cxl_pci_error_detected,
	.slot_reset = cxl_pci_slot_reset,
	.resume = cxl_pci_resume,
};

1507 1508 1509 1510 1511
struct pci_driver cxl_pci_driver = {
	.name = "cxl-pci",
	.id_table = cxl_pci_tbl,
	.probe = cxl_probe,
	.remove = cxl_remove,
M
Michael Neuling 已提交
1512
	.shutdown = cxl_remove,
D
Daniel Axtens 已提交
1513
	.err_handler = &cxl_err_handler,
1514
};