mce_power.c 20.8 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28
/*
 * Machine check exception handling CPU-side for power7 and power8
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 *
 * Copyright 2013 IBM Corporation
 * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
 */

#undef DEBUG
#define pr_fmt(fmt) "mce_power: " fmt

#include <linux/types.h>
#include <linux/ptrace.h>
#include <asm/mmu.h>
#include <asm/mce.h>
29
#include <asm/machdep.h>
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
#include <asm/pgtable.h>
#include <asm/pte-walk.h>
#include <asm/sstep.h>
#include <asm/exception-64s.h>

/*
 * Convert an address related to an mm to a PFN. NOTE: we are in real
 * mode, we could potentially race with page table updates.
 */
static unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr)
{
	pte_t *ptep;
	unsigned long flags;
	struct mm_struct *mm;

	if (user_mode(regs))
		mm = current->mm;
	else
		mm = &init_mm;

	local_irq_save(flags);
	if (mm == current->mm)
		ptep = find_current_mm_pte(mm->pgd, addr, NULL, NULL);
	else
		ptep = find_init_mm_pte(addr, NULL);
	local_irq_restore(flags);
	if (!ptep || pte_special(*ptep))
		return ULONG_MAX;
	return pte_pfn(*ptep);
}
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
static void flush_tlb_206(unsigned int num_sets, unsigned int action)
{
	unsigned long rb;
	unsigned int i;

	switch (action) {
	case TLB_INVAL_SCOPE_GLOBAL:
		rb = TLBIEL_INVAL_SET;
		break;
	case TLB_INVAL_SCOPE_LPID:
		rb = TLBIEL_INVAL_SET_LPID;
		break;
	default:
		BUG();
		break;
	}

	asm volatile("ptesync" : : : "memory");
	for (i = 0; i < num_sets; i++) {
		asm volatile("tlbiel %0" : : "r" (rb));
		rb += 1 << TLBIEL_INVAL_SET_SHIFT;
	}
	asm volatile("ptesync" : : : "memory");
}

86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139
static void flush_tlb_300(unsigned int num_sets, unsigned int action)
{
	unsigned long rb;
	unsigned int i;
	unsigned int r;

	switch (action) {
	case TLB_INVAL_SCOPE_GLOBAL:
		rb = TLBIEL_INVAL_SET;
		break;
	case TLB_INVAL_SCOPE_LPID:
		rb = TLBIEL_INVAL_SET_LPID;
		break;
	default:
		BUG();
		break;
	}

	asm volatile("ptesync" : : : "memory");

	if (early_radix_enabled())
		r = 1;
	else
		r = 0;

	/*
	 * First flush table/PWC caches with set 0, then flush the
	 * rest of the sets, partition scope. Radix must then do it
	 * all again with process scope. Hash just has to flush
	 * process table.
	 */
	asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : :
			"r"(rb), "r"(0), "i"(2), "i"(0), "r"(r));
	for (i = 1; i < num_sets; i++) {
		unsigned long set = i * (1<<TLBIEL_INVAL_SET_SHIFT);

		asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : :
				"r"(rb+set), "r"(0), "i"(2), "i"(0), "r"(r));
	}

	asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : :
			"r"(rb), "r"(0), "i"(2), "i"(1), "r"(r));
	if (early_radix_enabled()) {
		for (i = 1; i < num_sets; i++) {
			unsigned long set = i * (1<<TLBIEL_INVAL_SET_SHIFT);

			asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : :
				"r"(rb+set), "r"(0), "i"(2), "i"(1), "r"(r));
		}
	}

	asm volatile("ptesync" : : : "memory");
}

140
/*
141 142
 * Generic routines to flush TLB on POWER processors. These routines
 * are used as flush_tlb hook in the cpu_spec.
143 144 145 146 147 148 149 150 151 152 153 154 155 156
 *
 * action => TLB_INVAL_SCOPE_GLOBAL:  Invalidate all TLBs.
 *	     TLB_INVAL_SCOPE_LPID: Invalidate TLB for current LPID.
 */
void __flush_tlb_power7(unsigned int action)
{
	flush_tlb_206(POWER7_TLB_SETS, action);
}

void __flush_tlb_power8(unsigned int action)
{
	flush_tlb_206(POWER8_TLB_SETS, action);
}

157 158
void __flush_tlb_power9(unsigned int action)
{
159 160
	unsigned int num_sets;

161
	if (early_radix_enabled())
162 163 164
		num_sets = POWER9_TLB_SETS_RADIX;
	else
		num_sets = POWER9_TLB_SETS_HASH;
165

166
	flush_tlb_300(num_sets, action);
167 168 169
}


170
/* flush SLBs and reload */
171
#ifdef CONFIG_PPC_BOOK3S_64
172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193
static void flush_and_reload_slb(void)
{
	struct slb_shadow *slb;
	unsigned long i, n;

	/* Invalidate all SLBs */
	asm volatile("slbmte %0,%0; slbia" : : "r" (0));

#ifdef CONFIG_KVM_BOOK3S_HANDLER
	/*
	 * If machine check is hit when in guest or in transition, we will
	 * only flush the SLBs and continue.
	 */
	if (get_paca()->kvm_hstate.in_guest)
		return;
#endif

	/* For host kernel, reload the SLBs from shadow SLB buffer. */
	slb = get_slb_shadow();
	if (!slb)
		return;

194
	n = min_t(u32, be32_to_cpu(slb->persistent), SLB_MIN_SIZE);
195 196 197

	/* Load up the SLB entries from shadow SLB */
	for (i = 0; i < n; i++) {
198 199
		unsigned long rb = be64_to_cpu(slb->save_area[i].esid);
		unsigned long rs = be64_to_cpu(slb->save_area[i].vsid);
200 201 202 203 204

		rb = (rb & ~0xFFFul) | i;
		asm volatile("slbmte %0,%1" : : "r" (rs), "r" (rb));
	}
}
205
#endif
206

207 208 209 210 211 212 213 214 215 216 217
static void flush_erat(void)
{
	asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
}

#define MCE_FLUSH_SLB 1
#define MCE_FLUSH_TLB 2
#define MCE_FLUSH_ERAT 3

static int mce_flush(int what)
{
218
#ifdef CONFIG_PPC_BOOK3S_64
219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237
	if (what == MCE_FLUSH_SLB) {
		flush_and_reload_slb();
		return 1;
	}
#endif
	if (what == MCE_FLUSH_ERAT) {
		flush_erat();
		return 1;
	}
	if (what == MCE_FLUSH_TLB) {
		if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
			cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL);
			return 1;
		}
	}

	return 0;
}

238
#define SRR1_MC_LOADSTORE(srr1)	((srr1) & PPC_BIT(42))
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
struct mce_ierror_table {
	unsigned long srr1_mask;
	unsigned long srr1_value;
	bool nip_valid; /* nip is a valid indicator of faulting address */
	unsigned int error_type;
	unsigned int error_subtype;
	unsigned int initiator;
	unsigned int severity;
};

static const struct mce_ierror_table mce_p7_ierror_table[] = {
{ 0x00000000001c0000, 0x0000000000040000, true,
  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_IFETCH,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
{ 0x00000000001c0000, 0x0000000000080000, true,
  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
{ 0x00000000001c0000, 0x00000000000c0000, true,
  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
{ 0x00000000001c0000, 0x0000000000100000, true,
  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_INDETERMINATE, /* BOTH */
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
{ 0x00000000001c0000, 0x0000000000140000, true,
  MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
{ 0x00000000001c0000, 0x0000000000180000, true,
  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
{ 0x00000000001c0000, 0x00000000001c0000, true,
  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_IFETCH,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
{ 0, 0, 0, 0, 0, 0 } };

static const struct mce_ierror_table mce_p8_ierror_table[] = {
275
{ 0x00000000081c0000, 0x0000000000040000, true,
276 277
  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_IFETCH,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
278
{ 0x00000000081c0000, 0x0000000000080000, true,
279 280
  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
281
{ 0x00000000081c0000, 0x00000000000c0000, true,
282 283
  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
284
{ 0x00000000081c0000, 0x0000000000100000, true,
285 286
  MCE_ERROR_TYPE_ERAT,MCE_ERAT_ERROR_MULTIHIT,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
287
{ 0x00000000081c0000, 0x0000000000140000, true,
288 289
  MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
290
{ 0x00000000081c0000, 0x0000000000180000, true,
291 292
  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
293
{ 0x00000000081c0000, 0x00000000001c0000, true,
294 295
  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_IFETCH,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
296 297 298 299 300 301
{ 0x00000000081c0000, 0x0000000008000000, true,
  MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_IFETCH_TIMEOUT,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
{ 0x00000000081c0000, 0x0000000008040000, true,
  MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322
{ 0, 0, 0, 0, 0, 0 } };

static const struct mce_ierror_table mce_p9_ierror_table[] = {
{ 0x00000000081c0000, 0x0000000000040000, true,
  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_IFETCH,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
{ 0x00000000081c0000, 0x0000000000080000, true,
  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
{ 0x00000000081c0000, 0x00000000000c0000, true,
  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
{ 0x00000000081c0000, 0x0000000000100000, true,
  MCE_ERROR_TYPE_ERAT,MCE_ERAT_ERROR_MULTIHIT,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
{ 0x00000000081c0000, 0x0000000000140000, true,
  MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
{ 0x00000000081c0000, 0x0000000000180000, true,
  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
323 324 325
{ 0x00000000081c0000, 0x00000000001c0000, true,
  MCE_ERROR_TYPE_RA,  MCE_RA_ERROR_IFETCH_FOREIGN,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388
{ 0x00000000081c0000, 0x0000000008000000, true,
  MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_IFETCH_TIMEOUT,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
{ 0x00000000081c0000, 0x0000000008040000, true,
  MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
{ 0x00000000081c0000, 0x00000000080c0000, true,
  MCE_ERROR_TYPE_RA,  MCE_RA_ERROR_IFETCH,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
{ 0x00000000081c0000, 0x0000000008100000, true,
  MCE_ERROR_TYPE_RA,  MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
{ 0x00000000081c0000, 0x0000000008140000, false,
  MCE_ERROR_TYPE_RA,  MCE_RA_ERROR_STORE,
  MCE_INITIATOR_CPU,  MCE_SEV_FATAL, }, /* ASYNC is fatal */
{ 0x00000000081c0000, 0x0000000008180000, false,
  MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_STORE_TIMEOUT,
  MCE_INITIATOR_CPU,  MCE_SEV_FATAL, }, /* ASYNC is fatal */
{ 0x00000000081c0000, 0x00000000081c0000, true,
  MCE_ERROR_TYPE_RA,  MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN,
  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
{ 0, 0, 0, 0, 0, 0 } };

struct mce_derror_table {
	unsigned long dsisr_value;
	bool dar_valid; /* dar is a valid indicator of faulting address */
	unsigned int error_type;
	unsigned int error_subtype;
	unsigned int initiator;
	unsigned int severity;
};

static const struct mce_derror_table mce_p7_derror_table[] = {
{ 0x00008000, false,
  MCE_ERROR_TYPE_UE,   MCE_UE_ERROR_LOAD_STORE,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00004000, true,
  MCE_ERROR_TYPE_UE,   MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00000800, true,
  MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00000400, true,
  MCE_ERROR_TYPE_TLB,  MCE_TLB_ERROR_MULTIHIT,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00000100, true,
  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_PARITY,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00000080, true,
  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_MULTIHIT,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00000040, true,
  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_INDETERMINATE, /* BOTH */
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0, false, 0, 0, 0, 0 } };

static const struct mce_derror_table mce_p8_derror_table[] = {
{ 0x00008000, false,
  MCE_ERROR_TYPE_UE,   MCE_UE_ERROR_LOAD_STORE,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00004000, true,
  MCE_ERROR_TYPE_UE,   MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
389 390 391 392 393 394
{ 0x00002000, true,
  MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_LOAD_TIMEOUT,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00001000, true,
  MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453
{ 0x00000800, true,
  MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00000400, true,
  MCE_ERROR_TYPE_TLB,  MCE_TLB_ERROR_MULTIHIT,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00000200, true,
  MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, /* SECONDARY ERAT */
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00000100, true,
  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_PARITY,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00000080, true,
  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_MULTIHIT,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0, false, 0, 0, 0, 0 } };

static const struct mce_derror_table mce_p9_derror_table[] = {
{ 0x00008000, false,
  MCE_ERROR_TYPE_UE,   MCE_UE_ERROR_LOAD_STORE,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00004000, true,
  MCE_ERROR_TYPE_UE,   MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00002000, true,
  MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_LOAD_TIMEOUT,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00001000, true,
  MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00000800, true,
  MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00000400, true,
  MCE_ERROR_TYPE_TLB,  MCE_TLB_ERROR_MULTIHIT,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00000200, false,
  MCE_ERROR_TYPE_USER, MCE_USER_ERROR_TLBIE,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00000100, true,
  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_PARITY,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00000080, true,
  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_MULTIHIT,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00000040, true,
  MCE_ERROR_TYPE_RA,   MCE_RA_ERROR_LOAD,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00000020, false,
  MCE_ERROR_TYPE_RA,   MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00000010, false,
  MCE_ERROR_TYPE_RA,   MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0x00000008, false,
  MCE_ERROR_TYPE_RA,   MCE_RA_ERROR_LOAD_STORE_FOREIGN,
  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
{ 0, false, 0, 0, 0, 0 } };

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
static int mce_find_instr_ea_and_pfn(struct pt_regs *regs, uint64_t *addr,
					uint64_t *phys_addr)
{
	/*
	 * Carefully look at the NIP to determine
	 * the instruction to analyse. Reading the NIP
	 * in real-mode is tricky and can lead to recursive
	 * faults
	 */
	int instr;
	unsigned long pfn, instr_addr;
	struct instruction_op op;
	struct pt_regs tmp = *regs;

	pfn = addr_to_pfn(regs, regs->nip);
	if (pfn != ULONG_MAX) {
		instr_addr = (pfn << PAGE_SHIFT) + (regs->nip & ~PAGE_MASK);
		instr = *(unsigned int *)(instr_addr);
		if (!analyse_instr(&op, &tmp, instr)) {
			pfn = addr_to_pfn(regs, op.ea);
			*addr = op.ea;
			*phys_addr = (pfn << PAGE_SHIFT);
			return 0;
		}
		/*
		 * analyse_instr() might fail if the instruction
		 * is not a load/store, although this is unexpected
		 * for load/store errors or if we got the NIP
		 * wrong
		 */
	}
	*addr = 0;
	return -1;
}

489
static int mce_handle_ierror(struct pt_regs *regs,
490
		const struct mce_ierror_table table[],
491 492
		struct mce_error_info *mce_err, uint64_t *addr,
		uint64_t *phys_addr)
493
{
494
	uint64_t srr1 = regs->msr;
495
	int handled = 0;
496 497 498 499 500 501 502 503
	int i;

	*addr = 0;

	for (i = 0; table[i].srr1_mask; i++) {
		if ((srr1 & table[i].srr1_mask) != table[i].srr1_value)
			continue;

504 505 506 507 508 509 510 511 512 513 514 515 516 517
		/* attempt to correct the error */
		switch (table[i].error_type) {
		case MCE_ERROR_TYPE_SLB:
			handled = mce_flush(MCE_FLUSH_SLB);
			break;
		case MCE_ERROR_TYPE_ERAT:
			handled = mce_flush(MCE_FLUSH_ERAT);
			break;
		case MCE_ERROR_TYPE_TLB:
			handled = mce_flush(MCE_FLUSH_TLB);
			break;
		}

		/* now fill in mce_error_info */
518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543
		mce_err->error_type = table[i].error_type;
		switch (table[i].error_type) {
		case MCE_ERROR_TYPE_UE:
			mce_err->u.ue_error_type = table[i].error_subtype;
			break;
		case MCE_ERROR_TYPE_SLB:
			mce_err->u.slb_error_type = table[i].error_subtype;
			break;
		case MCE_ERROR_TYPE_ERAT:
			mce_err->u.erat_error_type = table[i].error_subtype;
			break;
		case MCE_ERROR_TYPE_TLB:
			mce_err->u.tlb_error_type = table[i].error_subtype;
			break;
		case MCE_ERROR_TYPE_USER:
			mce_err->u.user_error_type = table[i].error_subtype;
			break;
		case MCE_ERROR_TYPE_RA:
			mce_err->u.ra_error_type = table[i].error_subtype;
			break;
		case MCE_ERROR_TYPE_LINK:
			mce_err->u.link_error_type = table[i].error_subtype;
			break;
		}
		mce_err->severity = table[i].severity;
		mce_err->initiator = table[i].initiator;
544
		if (table[i].nip_valid) {
545
			*addr = regs->nip;
546 547 548 549 550 551 552 553 554 555 556 557 558 559
			if (mce_err->severity == MCE_SEV_ERROR_SYNC &&
				table[i].error_type == MCE_ERROR_TYPE_UE) {
				unsigned long pfn;

				if (get_paca()->in_mce < MAX_MCE_DEPTH) {
					pfn = addr_to_pfn(regs, regs->nip);
					if (pfn != ULONG_MAX) {
						*phys_addr =
							(pfn << PAGE_SHIFT);
						handled = 1;
					}
				}
			}
		}
560
		return handled;
561 562
	}

563 564 565
	mce_err->error_type = MCE_ERROR_TYPE_UNKNOWN;
	mce_err->severity = MCE_SEV_ERROR_SYNC;
	mce_err->initiator = MCE_INITIATOR_CPU;
566 567

	return 0;
568 569
}

570
static int mce_handle_derror(struct pt_regs *regs,
571
		const struct mce_derror_table table[],
572 573
		struct mce_error_info *mce_err, uint64_t *addr,
		uint64_t *phys_addr)
574
{
575
	uint64_t dsisr = regs->dsisr;
576 577
	int handled = 0;
	int found = 0;
578 579 580 581 582 583 584 585
	int i;

	*addr = 0;

	for (i = 0; table[i].dsisr_value; i++) {
		if (!(dsisr & table[i].dsisr_value))
			continue;

586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610
		/* attempt to correct the error */
		switch (table[i].error_type) {
		case MCE_ERROR_TYPE_SLB:
			if (mce_flush(MCE_FLUSH_SLB))
				handled = 1;
			break;
		case MCE_ERROR_TYPE_ERAT:
			if (mce_flush(MCE_FLUSH_ERAT))
				handled = 1;
			break;
		case MCE_ERROR_TYPE_TLB:
			if (mce_flush(MCE_FLUSH_TLB))
				handled = 1;
			break;
		}

		/*
		 * Attempt to handle multiple conditions, but only return
		 * one. Ensure uncorrectable errors are first in the table
		 * to match.
		 */
		if (found)
			continue;

		/* now fill in mce_error_info */
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
		mce_err->error_type = table[i].error_type;
		switch (table[i].error_type) {
		case MCE_ERROR_TYPE_UE:
			mce_err->u.ue_error_type = table[i].error_subtype;
			break;
		case MCE_ERROR_TYPE_SLB:
			mce_err->u.slb_error_type = table[i].error_subtype;
			break;
		case MCE_ERROR_TYPE_ERAT:
			mce_err->u.erat_error_type = table[i].error_subtype;
			break;
		case MCE_ERROR_TYPE_TLB:
			mce_err->u.tlb_error_type = table[i].error_subtype;
			break;
		case MCE_ERROR_TYPE_USER:
			mce_err->u.user_error_type = table[i].error_subtype;
			break;
		case MCE_ERROR_TYPE_RA:
			mce_err->u.ra_error_type = table[i].error_subtype;
			break;
		case MCE_ERROR_TYPE_LINK:
			mce_err->u.link_error_type = table[i].error_subtype;
			break;
		}
		mce_err->severity = table[i].severity;
		mce_err->initiator = table[i].initiator;
		if (table[i].dar_valid)
			*addr = regs->dar;
639 640 641 642 643 644 645 646 647 648 649
		else if (mce_err->severity == MCE_SEV_ERROR_SYNC &&
				table[i].error_type == MCE_ERROR_TYPE_UE) {
			/*
			 * We do a maximum of 4 nested MCE calls, see
			 * kernel/exception-64s.h
			 */
			if (get_paca()->in_mce < MAX_MCE_DEPTH)
				if (!mce_find_instr_ea_and_pfn(regs, addr,
								phys_addr))
					handled = 1;
		}
650
		found = 1;
651
	}
652

653 654 655
	if (found)
		return handled;

656 657 658
	mce_err->error_type = MCE_ERROR_TYPE_UNKNOWN;
	mce_err->severity = MCE_SEV_ERROR_SYNC;
	mce_err->initiator = MCE_INITIATOR_CPU;
659 660

	return 0;
661 662
}

663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680
static long mce_handle_ue_error(struct pt_regs *regs)
{
	long handled = 0;

	/*
	 * On specific SCOM read via MMIO we may get a machine check
	 * exception with SRR0 pointing inside opal. If that is the
	 * case OPAL may have recovery address to re-read SCOM data in
	 * different way and hence we can recover from this MC.
	 */

	if (ppc_md.mce_check_early_recovery) {
		if (ppc_md.mce_check_early_recovery(regs))
			handled = 1;
	}
	return handled;
}

681 682 683
static long mce_handle_error(struct pt_regs *regs,
		const struct mce_derror_table dtable[],
		const struct mce_ierror_table itable[])
684
{
685
	struct mce_error_info mce_err = { 0 };
686
	uint64_t addr, phys_addr;
687 688
	uint64_t srr1 = regs->msr;
	long handled;
689

690
	if (SRR1_MC_LOADSTORE(srr1))
691 692
		handled = mce_handle_derror(regs, dtable, &mce_err, &addr,
				&phys_addr);
693
	else
694 695
		handled = mce_handle_ierror(regs, itable, &mce_err, &addr,
				&phys_addr);
696

697
	if (!handled && mce_err.error_type == MCE_ERROR_TYPE_UE)
698 699
		handled = mce_handle_ue_error(regs);

700
	save_mce_event(regs, handled, &mce_err, regs->nip, addr, phys_addr);
701

702 703
	return handled;
}
704

705
long __machine_check_early_realmode_p7(struct pt_regs *regs)
706
{
707 708
	/* P7 DD1 leaves top bits of DSISR undefined */
	regs->dsisr &= 0x0000ffff;
709

710
	return mce_handle_error(regs, mce_p7_derror_table, mce_p7_ierror_table);
711 712
}

713
long __machine_check_early_realmode_p8(struct pt_regs *regs)
714
{
715
	return mce_handle_error(regs, mce_p8_derror_table, mce_p8_ierror_table);
716 717 718 719
}

long __machine_check_early_realmode_p9(struct pt_regs *regs)
{
720
	return mce_handle_error(regs, mce_p9_derror_table, mce_p9_ierror_table);
721
}