sys_regs.c 50.4 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 (C) 2012,2013 - ARM Ltd
 * Author: Marc Zyngier <marc.zyngier@arm.com>
 *
 * Derived from arch/arm/kvm/coproc.c:
 * Copyright (C) 2012 - Virtual Open Systems and Columbia University
 * Authors: Rusty Russell <rusty@rustcorp.com.au>
 *          Christoffer Dall <c.dall@virtualopensystems.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License, version 2, 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.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

#include <linux/kvm_host.h>
24
#include <linux/mm.h>
25
#include <linux/uaccess.h>
26

27 28
#include <asm/cacheflush.h>
#include <asm/cputype.h>
29
#include <asm/debug-monitors.h>
30 31
#include <asm/esr.h>
#include <asm/kvm_arm.h>
32
#include <asm/kvm_asm.h>
33 34 35 36
#include <asm/kvm_coproc.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_host.h>
#include <asm/kvm_mmu.h>
37
#include <asm/perf_event.h>
38

39 40 41 42
#include <trace/events/kvm.h>

#include "sys_regs.h"

43 44
#include "trace.h"

45 46 47 48 49
/*
 * All of this file is extremly similar to the ARM coproc.c, but the
 * types are different. My gut feeling is that it should be pretty
 * easy to merge, but that would be an ABI breakage -- again. VFP
 * would also need to be abstracted.
50 51 52 53
 *
 * For AArch32, we only take care of what is being trapped. Anything
 * that has to do with init and userspace access has to go via the
 * 64bit interface.
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
 */

/* 3 bits per cache level, as per CLIDR, but non-existent caches always 0 */
static u32 cache_levels;

/* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */
#define CSSELR_MAX 12

/* Which cache CCSIDR represents depends on CSSELR value. */
static u32 get_ccsidr(u32 csselr)
{
	u32 ccsidr;

	/* Make sure noone else changes CSSELR during this! */
	local_irq_disable();
	/* Put value into CSSELR */
	asm volatile("msr csselr_el1, %x0" : : "r" (csselr));
	isb();
	/* Read result out of CCSIDR */
	asm volatile("mrs %0, ccsidr_el1" : "=r" (ccsidr));
	local_irq_enable();

	return ccsidr;
}

79 80 81
/*
 * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
 */
82
static bool access_dcsw(struct kvm_vcpu *vcpu,
83
			struct sys_reg_params *p,
84 85 86 87 88
			const struct sys_reg_desc *r)
{
	if (!p->is_write)
		return read_from_write_only(vcpu, p);

89
	kvm_set_way_flush(vcpu);
90 91 92
	return true;
}

93 94
/*
 * Generic accessor for VM registers. Only called as long as HCR_TVM
95 96
 * is set. If the guest enables the MMU, we stop trapping the VM
 * sys_regs and leave it in complete control of the caches.
97 98
 */
static bool access_vm_reg(struct kvm_vcpu *vcpu,
99
			  struct sys_reg_params *p,
100 101
			  const struct sys_reg_desc *r)
{
102
	bool was_enabled = vcpu_has_cache_enabled(vcpu);
103 104 105

	BUG_ON(!p->is_write);

106
	if (!p->is_aarch32) {
107
		vcpu_sys_reg(vcpu, r->reg) = p->regval;
108 109
	} else {
		if (!p->is_32bit)
110 111
			vcpu_cp15_64_high(vcpu, r->reg) = upper_32_bits(p->regval);
		vcpu_cp15_64_low(vcpu, r->reg) = lower_32_bits(p->regval);
112
	}
113

114
	kvm_toggle_cache(vcpu, was_enabled);
115 116 117
	return true;
}

118 119 120 121 122 123 124
/*
 * Trap handler for the GICv3 SGI generation system register.
 * Forward the request to the VGIC emulation.
 * The cp15_64 code makes sure this automatically works
 * for both AArch64 and AArch32 accesses.
 */
static bool access_gic_sgi(struct kvm_vcpu *vcpu,
125
			   struct sys_reg_params *p,
126 127 128 129 130
			   const struct sys_reg_desc *r)
{
	if (!p->is_write)
		return read_from_write_only(vcpu, p);

131
	vgic_v3_dispatch_sgi(vcpu, p->regval);
132 133 134 135

	return true;
}

136
static bool trap_raz_wi(struct kvm_vcpu *vcpu,
137
			struct sys_reg_params *p,
138
			const struct sys_reg_desc *r)
139 140 141 142 143 144 145
{
	if (p->is_write)
		return ignore_write(vcpu, p);
	else
		return read_zero(vcpu, p);
}

146
static bool trap_oslsr_el1(struct kvm_vcpu *vcpu,
147
			   struct sys_reg_params *p,
148 149 150 151 152
			   const struct sys_reg_desc *r)
{
	if (p->is_write) {
		return ignore_write(vcpu, p);
	} else {
153
		p->regval = (1 << 3);
154 155 156 157 158
		return true;
	}
}

static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
159
				   struct sys_reg_params *p,
160 161 162 163 164 165 166
				   const struct sys_reg_desc *r)
{
	if (p->is_write) {
		return ignore_write(vcpu, p);
	} else {
		u32 val;
		asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val));
167
		p->regval = val;
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
		return true;
	}
}

/*
 * We want to avoid world-switching all the DBG registers all the
 * time:
 * 
 * - If we've touched any debug register, it is likely that we're
 *   going to touch more of them. It then makes sense to disable the
 *   traps and start doing the save/restore dance
 * - If debug is active (DBG_MDSCR_KDE or DBG_MDSCR_MDE set), it is
 *   then mandatory to save/restore the registers, as the guest
 *   depends on them.
 * 
 * For this, we use a DIRTY bit, indicating the guest has modified the
 * debug registers, used as follow:
 *
 * On guest entry:
 * - If the dirty bit is set (because we're coming back from trapping),
 *   disable the traps, save host registers, restore guest registers.
 * - If debug is actively in use (DBG_MDSCR_KDE or DBG_MDSCR_MDE set),
 *   set the dirty bit, disable the traps, save host registers,
 *   restore guest registers.
 * - Otherwise, enable the traps
 *
 * On guest exit:
 * - If the dirty bit is set, save guest registers, restore host
 *   registers and clear the dirty bit. This ensure that the host can
 *   now use the debug registers.
 */
static bool trap_debug_regs(struct kvm_vcpu *vcpu,
200
			    struct sys_reg_params *p,
201 202 203
			    const struct sys_reg_desc *r)
{
	if (p->is_write) {
204
		vcpu_sys_reg(vcpu, r->reg) = p->regval;
205 206
		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
	} else {
207
		p->regval = vcpu_sys_reg(vcpu, r->reg);
208 209
	}

210
	trace_trap_reg(__func__, r->reg, p->is_write, p->regval);
211

212 213 214
	return true;
}

215 216 217 218 219 220 221 222 223
/*
 * reg_to_dbg/dbg_to_reg
 *
 * A 32 bit write to a debug register leave top bits alone
 * A 32 bit read from a debug register only returns the bottom bits
 *
 * All writes will set the KVM_ARM64_DEBUG_DIRTY flag to ensure the
 * hyp.S code switches between host and guest values in future.
 */
224 225 226
static void reg_to_dbg(struct kvm_vcpu *vcpu,
		       struct sys_reg_params *p,
		       u64 *dbg_reg)
227
{
228
	u64 val = p->regval;
229 230 231 232 233 234 235 236 237 238

	if (p->is_32bit) {
		val &= 0xffffffffUL;
		val |= ((*dbg_reg >> 32) << 32);
	}

	*dbg_reg = val;
	vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
}

239 240 241
static void dbg_to_reg(struct kvm_vcpu *vcpu,
		       struct sys_reg_params *p,
		       u64 *dbg_reg)
242
{
243
	p->regval = *dbg_reg;
244
	if (p->is_32bit)
245
		p->regval &= 0xffffffffUL;
246 247
}

248 249 250
static bool trap_bvr(struct kvm_vcpu *vcpu,
		     struct sys_reg_params *p,
		     const struct sys_reg_desc *rd)
251 252 253 254 255 256 257 258
{
	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];

	if (p->is_write)
		reg_to_dbg(vcpu, p, dbg_reg);
	else
		dbg_to_reg(vcpu, p, dbg_reg);

259 260
	trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg);

261 262 263 264 265 266 267 268
	return true;
}

static int set_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
		const struct kvm_one_reg *reg, void __user *uaddr)
{
	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];

269
	if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0)
270 271 272 273 274 275 276 277 278 279 280 281 282 283
		return -EFAULT;
	return 0;
}

static int get_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
	const struct kvm_one_reg *reg, void __user *uaddr)
{
	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];

	if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0)
		return -EFAULT;
	return 0;
}

284 285
static void reset_bvr(struct kvm_vcpu *vcpu,
		      const struct sys_reg_desc *rd)
286 287 288 289
{
	vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg] = rd->val;
}

290 291 292
static bool trap_bcr(struct kvm_vcpu *vcpu,
		     struct sys_reg_params *p,
		     const struct sys_reg_desc *rd)
293 294 295 296 297 298 299 300
{
	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg];

	if (p->is_write)
		reg_to_dbg(vcpu, p, dbg_reg);
	else
		dbg_to_reg(vcpu, p, dbg_reg);

301 302
	trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg);

303 304 305 306 307 308 309 310
	return true;
}

static int set_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
		const struct kvm_one_reg *reg, void __user *uaddr)
{
	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg];

311
	if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0)
312 313 314 315 316 317 318 319 320 321 322 323 324 325 326
		return -EFAULT;

	return 0;
}

static int get_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
	const struct kvm_one_reg *reg, void __user *uaddr)
{
	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg];

	if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0)
		return -EFAULT;
	return 0;
}

327 328
static void reset_bcr(struct kvm_vcpu *vcpu,
		      const struct sys_reg_desc *rd)
329 330 331 332
{
	vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg] = rd->val;
}

333 334 335
static bool trap_wvr(struct kvm_vcpu *vcpu,
		     struct sys_reg_params *p,
		     const struct sys_reg_desc *rd)
336 337 338 339 340 341 342 343
{
	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg];

	if (p->is_write)
		reg_to_dbg(vcpu, p, dbg_reg);
	else
		dbg_to_reg(vcpu, p, dbg_reg);

344 345 346
	trace_trap_reg(__func__, rd->reg, p->is_write,
		vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]);

347 348 349 350 351 352 353 354
	return true;
}

static int set_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
		const struct kvm_one_reg *reg, void __user *uaddr)
{
	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg];

355
	if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0)
356 357 358 359 360 361 362 363 364 365 366 367 368 369
		return -EFAULT;
	return 0;
}

static int get_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
	const struct kvm_one_reg *reg, void __user *uaddr)
{
	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg];

	if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0)
		return -EFAULT;
	return 0;
}

370 371
static void reset_wvr(struct kvm_vcpu *vcpu,
		      const struct sys_reg_desc *rd)
372 373 374 375
{
	vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg] = rd->val;
}

376 377 378
static bool trap_wcr(struct kvm_vcpu *vcpu,
		     struct sys_reg_params *p,
		     const struct sys_reg_desc *rd)
379 380 381 382 383 384 385 386
{
	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg];

	if (p->is_write)
		reg_to_dbg(vcpu, p, dbg_reg);
	else
		dbg_to_reg(vcpu, p, dbg_reg);

387 388
	trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg);

389 390 391 392 393 394 395 396
	return true;
}

static int set_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
		const struct kvm_one_reg *reg, void __user *uaddr)
{
	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg];

397
	if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0)
398 399 400 401 402 403 404 405 406 407 408 409 410 411
		return -EFAULT;
	return 0;
}

static int get_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
	const struct kvm_one_reg *reg, void __user *uaddr)
{
	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg];

	if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0)
		return -EFAULT;
	return 0;
}

412 413
static void reset_wcr(struct kvm_vcpu *vcpu,
		      const struct sys_reg_desc *rd)
414 415 416 417
{
	vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg] = rd->val;
}

418 419 420 421 422 423 424 425 426 427
static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
	u64 amair;

	asm volatile("mrs %0, amair_el1\n" : "=r" (amair));
	vcpu_sys_reg(vcpu, AMAIR_EL1) = amair;
}

static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
428 429
	u64 mpidr;

430
	/*
431 432 433 434 435
	 * Map the vcpu_id into the first three affinity level fields of
	 * the MPIDR. We limit the number of VCPUs in level 0 due to a
	 * limitation to 16 CPUs in that level in the ICC_SGIxR registers
	 * of the GICv3 to be able to address each CPU directly when
	 * sending IPIs.
436
	 */
437 438 439 440
	mpidr = (vcpu->vcpu_id & 0x0f) << MPIDR_LEVEL_SHIFT(0);
	mpidr |= ((vcpu->vcpu_id >> 4) & 0xff) << MPIDR_LEVEL_SHIFT(1);
	mpidr |= ((vcpu->vcpu_id >> 12) & 0xff) << MPIDR_LEVEL_SHIFT(2);
	vcpu_sys_reg(vcpu, MPIDR_EL1) = (1ULL << 31) | mpidr;
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
static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
	u64 pmcr, val;

	asm volatile("mrs %0, pmcr_el0\n" : "=r" (pmcr));
	/* Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) is reset to UNKNOWN
	 * except PMCR.E resetting to zero.
	 */
	val = ((pmcr & ~ARMV8_PMU_PMCR_MASK)
	       | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E);
	vcpu_sys_reg(vcpu, PMCR_EL0) = val;
}

static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
			const struct sys_reg_desc *r)
{
	u64 val;

	if (!kvm_arm_pmu_v3_ready(vcpu))
		return trap_raz_wi(vcpu, p, r);

	if (p->is_write) {
		/* Only update writeable bits of PMCR */
		val = vcpu_sys_reg(vcpu, PMCR_EL0);
		val &= ~ARMV8_PMU_PMCR_MASK;
		val |= p->regval & ARMV8_PMU_PMCR_MASK;
		vcpu_sys_reg(vcpu, PMCR_EL0) = val;
	} else {
		/* PMCR.P & PMCR.C are RAZ */
		val = vcpu_sys_reg(vcpu, PMCR_EL0)
		      & ~(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C);
		p->regval = val;
	}

	return true;
}

480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495
static bool access_pmselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
			  const struct sys_reg_desc *r)
{
	if (!kvm_arm_pmu_v3_ready(vcpu))
		return trap_raz_wi(vcpu, p, r);

	if (p->is_write)
		vcpu_sys_reg(vcpu, PMSELR_EL0) = p->regval;
	else
		/* return PMSELR.SEL field */
		p->regval = vcpu_sys_reg(vcpu, PMSELR_EL0)
			    & ARMV8_PMU_COUNTER_MASK;

	return true;
}

496 497 498 499
/* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
#define DBG_BCR_BVR_WCR_WVR_EL1(n)					\
	/* DBGBVRn_EL1 */						\
	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b100),	\
500
	  trap_bvr, reset_bvr, n, 0, get_bvr, set_bvr },		\
501 502
	/* DBGBCRn_EL1 */						\
	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b101),	\
503
	  trap_bcr, reset_bcr, n, 0, get_bcr, set_bcr },		\
504 505
	/* DBGWVRn_EL1 */						\
	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b110),	\
506
	  trap_wvr, reset_wvr, n, 0,  get_wvr, set_wvr },		\
507 508
	/* DBGWCRn_EL1 */						\
	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b111),	\
509
	  trap_wcr, reset_wcr, n, 0,  get_wcr, set_wcr }
510

511 512 513
/*
 * Architected system registers.
 * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
514 515 516 517 518 519 520 521 522
 *
 * We could trap ID_DFR0 and tell the guest we don't support performance
 * monitoring.  Unfortunately the patch to make the kernel check ID_DFR0 was
 * NAKed, so it will read the PMCR anyway.
 *
 * Therefore we tell the guest we have 0 counters.  Unfortunately, we
 * must always support PMCCNTR (the cycle counter): we just RAZ/WI for
 * all PM registers, which doesn't crash the guest kernel at least.
 *
523 524 525 526 527 528
 * Debug handling: We do trap most, if not all debug related system
 * registers. The implementation is good enough to ensure that a guest
 * can use these with minimal performance degradation. The drawback is
 * that we don't implement any of the external debug, none of the
 * OSlock protocol. This should be revisited if we ever encounter a
 * more demanding guest...
529 530 531 532 533 534 535 536 537 538 539 540
 */
static const struct sys_reg_desc sys_reg_descs[] = {
	/* DC ISW */
	{ Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b0110), Op2(0b010),
	  access_dcsw },
	/* DC CSW */
	{ Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1010), Op2(0b010),
	  access_dcsw },
	/* DC CISW */
	{ Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b010),
	  access_dcsw },

541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598
	DBG_BCR_BVR_WCR_WVR_EL1(0),
	DBG_BCR_BVR_WCR_WVR_EL1(1),
	/* MDCCINT_EL1 */
	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b000),
	  trap_debug_regs, reset_val, MDCCINT_EL1, 0 },
	/* MDSCR_EL1 */
	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b010),
	  trap_debug_regs, reset_val, MDSCR_EL1, 0 },
	DBG_BCR_BVR_WCR_WVR_EL1(2),
	DBG_BCR_BVR_WCR_WVR_EL1(3),
	DBG_BCR_BVR_WCR_WVR_EL1(4),
	DBG_BCR_BVR_WCR_WVR_EL1(5),
	DBG_BCR_BVR_WCR_WVR_EL1(6),
	DBG_BCR_BVR_WCR_WVR_EL1(7),
	DBG_BCR_BVR_WCR_WVR_EL1(8),
	DBG_BCR_BVR_WCR_WVR_EL1(9),
	DBG_BCR_BVR_WCR_WVR_EL1(10),
	DBG_BCR_BVR_WCR_WVR_EL1(11),
	DBG_BCR_BVR_WCR_WVR_EL1(12),
	DBG_BCR_BVR_WCR_WVR_EL1(13),
	DBG_BCR_BVR_WCR_WVR_EL1(14),
	DBG_BCR_BVR_WCR_WVR_EL1(15),

	/* MDRAR_EL1 */
	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
	  trap_raz_wi },
	/* OSLAR_EL1 */
	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b100),
	  trap_raz_wi },
	/* OSLSR_EL1 */
	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0001), Op2(0b100),
	  trap_oslsr_el1 },
	/* OSDLR_EL1 */
	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0011), Op2(0b100),
	  trap_raz_wi },
	/* DBGPRCR_EL1 */
	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0100), Op2(0b100),
	  trap_raz_wi },
	/* DBGCLAIMSET_EL1 */
	{ Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1000), Op2(0b110),
	  trap_raz_wi },
	/* DBGCLAIMCLR_EL1 */
	{ Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1001), Op2(0b110),
	  trap_raz_wi },
	/* DBGAUTHSTATUS_EL1 */
	{ Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b110),
	  trap_dbgauthstatus_el1 },

	/* MDCCSR_EL1 */
	{ Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0001), Op2(0b000),
	  trap_raz_wi },
	/* DBGDTR_EL0 */
	{ Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0100), Op2(0b000),
	  trap_raz_wi },
	/* DBGDTR[TR]X_EL0 */
	{ Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0101), Op2(0b000),
	  trap_raz_wi },

599 600 601 602
	/* DBGVCR32_EL2 */
	{ Op0(0b10), Op1(0b100), CRn(0b0000), CRm(0b0111), Op2(0b000),
	  NULL, reset_val, DBGVCR32_EL2, 0 },

603 604 605 606 607
	/* MPIDR_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0000), Op2(0b101),
	  NULL, reset_mpidr, MPIDR_EL1 },
	/* SCTLR_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
608
	  access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 },
609 610 611 612 613
	/* CPACR_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b010),
	  NULL, reset_val, CPACR_EL1, 0 },
	/* TTBR0_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b000),
614
	  access_vm_reg, reset_unknown, TTBR0_EL1 },
615 616
	/* TTBR1_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b001),
617
	  access_vm_reg, reset_unknown, TTBR1_EL1 },
618 619
	/* TCR_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b010),
620
	  access_vm_reg, reset_val, TCR_EL1, 0 },
621 622 623

	/* AFSR0_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b000),
624
	  access_vm_reg, reset_unknown, AFSR0_EL1 },
625 626
	/* AFSR1_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b001),
627
	  access_vm_reg, reset_unknown, AFSR1_EL1 },
628 629
	/* ESR_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0010), Op2(0b000),
630
	  access_vm_reg, reset_unknown, ESR_EL1 },
631 632
	/* FAR_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b0110), CRm(0b0000), Op2(0b000),
633
	  access_vm_reg, reset_unknown, FAR_EL1 },
634 635 636
	/* PAR_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b0111), CRm(0b0100), Op2(0b000),
	  NULL, reset_unknown, PAR_EL1 },
637 638 639

	/* PMINTENSET_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b001),
640
	  trap_raz_wi },
641 642
	/* PMINTENCLR_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b010),
643
	  trap_raz_wi },
644 645 646

	/* MAIR_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0010), Op2(0b000),
647
	  access_vm_reg, reset_unknown, MAIR_EL1 },
648 649
	/* AMAIR_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0011), Op2(0b000),
650
	  access_vm_reg, reset_amair_el1, AMAIR_EL1 },
651 652 653 654

	/* VBAR_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b0000), Op2(0b000),
	  NULL, reset_val, VBAR_EL1, 0 },
655

656 657 658
	/* ICC_SGI1R_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b1011), Op2(0b101),
	  access_gic_sgi },
659 660 661 662
	/* ICC_SRE_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b1100), Op2(0b101),
	  trap_raz_wi },

663 664
	/* CONTEXTIDR_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b001),
665
	  access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
666 667 668 669 670 671 672 673 674 675 676 677 678 679
	/* TPIDR_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b100),
	  NULL, reset_unknown, TPIDR_EL1 },

	/* CNTKCTL_EL1 */
	{ Op0(0b11), Op1(0b000), CRn(0b1110), CRm(0b0001), Op2(0b000),
	  NULL, reset_val, CNTKCTL_EL1, 0},

	/* CSSELR_EL1 */
	{ Op0(0b11), Op1(0b010), CRn(0b0000), CRm(0b0000), Op2(0b000),
	  NULL, reset_unknown, CSSELR_EL1 },

	/* PMCR_EL0 */
	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b000),
680
	  access_pmcr, reset_pmcr, },
681 682
	/* PMCNTENSET_EL0 */
	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b001),
683
	  trap_raz_wi },
684 685
	/* PMCNTENCLR_EL0 */
	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b010),
686
	  trap_raz_wi },
687 688
	/* PMOVSCLR_EL0 */
	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b011),
689
	  trap_raz_wi },
690 691
	/* PMSWINC_EL0 */
	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b100),
692
	  trap_raz_wi },
693 694
	/* PMSELR_EL0 */
	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b101),
695
	  access_pmselr, reset_unknown, PMSELR_EL0 },
696 697
	/* PMCEID0_EL0 */
	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b110),
698
	  trap_raz_wi },
699 700
	/* PMCEID1_EL0 */
	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b111),
701
	  trap_raz_wi },
702 703
	/* PMCCNTR_EL0 */
	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b000),
704
	  trap_raz_wi },
705 706
	/* PMXEVTYPER_EL0 */
	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b001),
707
	  trap_raz_wi },
708 709
	/* PMXEVCNTR_EL0 */
	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b010),
710
	  trap_raz_wi },
711 712
	/* PMUSERENR_EL0 */
	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b000),
713
	  trap_raz_wi },
714 715
	/* PMOVSSET_EL0 */
	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b011),
716
	  trap_raz_wi },
717 718 719 720 721 722 723

	/* TPIDR_EL0 */
	{ Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b010),
	  NULL, reset_unknown, TPIDR_EL0 },
	/* TPIDRRO_EL0 */
	{ Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b011),
	  NULL, reset_unknown, TPIDRRO_EL0 },
724 725 726 727 728 729 730 731 732 733 734 735

	/* DACR32_EL2 */
	{ Op0(0b11), Op1(0b100), CRn(0b0011), CRm(0b0000), Op2(0b000),
	  NULL, reset_unknown, DACR32_EL2 },
	/* IFSR32_EL2 */
	{ Op0(0b11), Op1(0b100), CRn(0b0101), CRm(0b0000), Op2(0b001),
	  NULL, reset_unknown, IFSR32_EL2 },
	/* FPEXC32_EL2 */
	{ Op0(0b11), Op1(0b100), CRn(0b0101), CRm(0b0011), Op2(0b000),
	  NULL, reset_val, FPEXC32_EL2, 0x70 },
};

736
static bool trap_dbgidr(struct kvm_vcpu *vcpu,
737
			struct sys_reg_params *p,
738 739 740 741 742
			const struct sys_reg_desc *r)
{
	if (p->is_write) {
		return ignore_write(vcpu, p);
	} else {
743 744 745
		u64 dfr = read_system_reg(SYS_ID_AA64DFR0_EL1);
		u64 pfr = read_system_reg(SYS_ID_AA64PFR0_EL1);
		u32 el3 = !!cpuid_feature_extract_field(pfr, ID_AA64PFR0_EL3_SHIFT);
746

747 748 749 750
		p->regval = ((((dfr >> ID_AA64DFR0_WRPS_SHIFT) & 0xf) << 28) |
			     (((dfr >> ID_AA64DFR0_BRPS_SHIFT) & 0xf) << 24) |
			     (((dfr >> ID_AA64DFR0_CTX_CMPS_SHIFT) & 0xf) << 20)
			     | (6 << 16) | (el3 << 14) | (el3 << 12));
751 752 753 754 755
		return true;
	}
}

static bool trap_debug32(struct kvm_vcpu *vcpu,
756
			 struct sys_reg_params *p,
757 758 759
			 const struct sys_reg_desc *r)
{
	if (p->is_write) {
760
		vcpu_cp14(vcpu, r->reg) = p->regval;
761 762
		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
	} else {
763
		p->regval = vcpu_cp14(vcpu, r->reg);
764 765 766 767 768
	}

	return true;
}

769 770 771 772 773 774 775 776 777 778 779
/* AArch32 debug register mappings
 *
 * AArch32 DBGBVRn is mapped to DBGBVRn_EL1[31:0]
 * AArch32 DBGBXVRn is mapped to DBGBVRn_EL1[63:32]
 *
 * All control registers and watchpoint value registers are mapped to
 * the lower 32 bits of their AArch64 equivalents. We share the trap
 * handlers with the above AArch64 code which checks what mode the
 * system is in.
 */

780 781 782
static bool trap_xvr(struct kvm_vcpu *vcpu,
		     struct sys_reg_params *p,
		     const struct sys_reg_desc *rd)
783 784 785 786 787 788 789
{
	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];

	if (p->is_write) {
		u64 val = *dbg_reg;

		val &= 0xffffffffUL;
790
		val |= p->regval << 32;
791 792 793 794
		*dbg_reg = val;

		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
	} else {
795
		p->regval = *dbg_reg >> 32;
796 797
	}

798 799
	trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg);

800 801 802 803 804 805 806 807 808 809 810 811 812 813 814
	return true;
}

#define DBG_BCR_BVR_WCR_WVR(n)						\
	/* DBGBVRn */							\
	{ Op1( 0), CRn( 0), CRm((n)), Op2( 4), trap_bvr, NULL, n }, 	\
	/* DBGBCRn */							\
	{ Op1( 0), CRn( 0), CRm((n)), Op2( 5), trap_bcr, NULL, n },	\
	/* DBGWVRn */							\
	{ Op1( 0), CRn( 0), CRm((n)), Op2( 6), trap_wvr, NULL, n },	\
	/* DBGWCRn */							\
	{ Op1( 0), CRn( 0), CRm((n)), Op2( 7), trap_wcr, NULL, n }

#define DBGBXVR(n)							\
	{ Op1( 0), CRn( 1), CRm((n)), Op2( 1), trap_xvr, NULL, n }
815 816 817 818

/*
 * Trapped cp14 registers. We generally ignore most of the external
 * debug, on the principle that they don't really make sense to a
819
 * guest. Revisit this one day, would this principle change.
820
 */
821
static const struct sys_reg_desc cp14_regs[] = {
822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902
	/* DBGIDR */
	{ Op1( 0), CRn( 0), CRm( 0), Op2( 0), trap_dbgidr },
	/* DBGDTRRXext */
	{ Op1( 0), CRn( 0), CRm( 0), Op2( 2), trap_raz_wi },

	DBG_BCR_BVR_WCR_WVR(0),
	/* DBGDSCRint */
	{ Op1( 0), CRn( 0), CRm( 1), Op2( 0), trap_raz_wi },
	DBG_BCR_BVR_WCR_WVR(1),
	/* DBGDCCINT */
	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32 },
	/* DBGDSCRext */
	{ Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32 },
	DBG_BCR_BVR_WCR_WVR(2),
	/* DBGDTR[RT]Xint */
	{ Op1( 0), CRn( 0), CRm( 3), Op2( 0), trap_raz_wi },
	/* DBGDTR[RT]Xext */
	{ Op1( 0), CRn( 0), CRm( 3), Op2( 2), trap_raz_wi },
	DBG_BCR_BVR_WCR_WVR(3),
	DBG_BCR_BVR_WCR_WVR(4),
	DBG_BCR_BVR_WCR_WVR(5),
	/* DBGWFAR */
	{ Op1( 0), CRn( 0), CRm( 6), Op2( 0), trap_raz_wi },
	/* DBGOSECCR */
	{ Op1( 0), CRn( 0), CRm( 6), Op2( 2), trap_raz_wi },
	DBG_BCR_BVR_WCR_WVR(6),
	/* DBGVCR */
	{ Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32 },
	DBG_BCR_BVR_WCR_WVR(7),
	DBG_BCR_BVR_WCR_WVR(8),
	DBG_BCR_BVR_WCR_WVR(9),
	DBG_BCR_BVR_WCR_WVR(10),
	DBG_BCR_BVR_WCR_WVR(11),
	DBG_BCR_BVR_WCR_WVR(12),
	DBG_BCR_BVR_WCR_WVR(13),
	DBG_BCR_BVR_WCR_WVR(14),
	DBG_BCR_BVR_WCR_WVR(15),

	/* DBGDRAR (32bit) */
	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), trap_raz_wi },

	DBGBXVR(0),
	/* DBGOSLAR */
	{ Op1( 0), CRn( 1), CRm( 0), Op2( 4), trap_raz_wi },
	DBGBXVR(1),
	/* DBGOSLSR */
	{ Op1( 0), CRn( 1), CRm( 1), Op2( 4), trap_oslsr_el1 },
	DBGBXVR(2),
	DBGBXVR(3),
	/* DBGOSDLR */
	{ Op1( 0), CRn( 1), CRm( 3), Op2( 4), trap_raz_wi },
	DBGBXVR(4),
	/* DBGPRCR */
	{ Op1( 0), CRn( 1), CRm( 4), Op2( 4), trap_raz_wi },
	DBGBXVR(5),
	DBGBXVR(6),
	DBGBXVR(7),
	DBGBXVR(8),
	DBGBXVR(9),
	DBGBXVR(10),
	DBGBXVR(11),
	DBGBXVR(12),
	DBGBXVR(13),
	DBGBXVR(14),
	DBGBXVR(15),

	/* DBGDSAR (32bit) */
	{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), trap_raz_wi },

	/* DBGDEVID2 */
	{ Op1( 0), CRn( 7), CRm( 0), Op2( 7), trap_raz_wi },
	/* DBGDEVID1 */
	{ Op1( 0), CRn( 7), CRm( 1), Op2( 7), trap_raz_wi },
	/* DBGDEVID */
	{ Op1( 0), CRn( 7), CRm( 2), Op2( 7), trap_raz_wi },
	/* DBGCLAIMSET */
	{ Op1( 0), CRn( 7), CRm( 8), Op2( 6), trap_raz_wi },
	/* DBGCLAIMCLR */
	{ Op1( 0), CRn( 7), CRm( 9), Op2( 6), trap_raz_wi },
	/* DBGAUTHSTATUS */
	{ Op1( 0), CRn( 7), CRm(14), Op2( 6), trap_dbgauthstatus_el1 },
903 904
};

905 906
/* Trapped cp14 64bit registers */
static const struct sys_reg_desc cp14_64_regs[] = {
907 908 909 910 911
	/* DBGDRAR (64bit) */
	{ Op1( 0), CRm( 1), .access = trap_raz_wi },

	/* DBGDSAR (64bit) */
	{ Op1( 0), CRm( 2), .access = trap_raz_wi },
912 913
};

914 915 916 917 918
/*
 * Trapped cp15 registers. TTBR0/TTBR1 get a double encoding,
 * depending on the way they are accessed (as a 32bit or a 64bit
 * register).
 */
919
static const struct sys_reg_desc cp15_regs[] = {
920 921
	{ Op1( 0), CRn( 0), CRm(12), Op2( 0), access_gic_sgi },

922
	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, NULL, c1_SCTLR },
923 924 925 926 927 928 929 930 931 932 933
	{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
	{ Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 },
	{ Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR },
	{ Op1( 0), CRn( 3), CRm( 0), Op2( 0), access_vm_reg, NULL, c3_DACR },
	{ Op1( 0), CRn( 5), CRm( 0), Op2( 0), access_vm_reg, NULL, c5_DFSR },
	{ Op1( 0), CRn( 5), CRm( 0), Op2( 1), access_vm_reg, NULL, c5_IFSR },
	{ Op1( 0), CRn( 5), CRm( 1), Op2( 0), access_vm_reg, NULL, c5_ADFSR },
	{ Op1( 0), CRn( 5), CRm( 1), Op2( 1), access_vm_reg, NULL, c5_AIFSR },
	{ Op1( 0), CRn( 6), CRm( 0), Op2( 0), access_vm_reg, NULL, c6_DFAR },
	{ Op1( 0), CRn( 6), CRm( 0), Op2( 2), access_vm_reg, NULL, c6_IFAR },

934 935 936 937 938 939
	/*
	 * DC{C,I,CI}SW operations:
	 */
	{ Op1( 0), CRn( 7), CRm( 6), Op2( 2), access_dcsw },
	{ Op1( 0), CRn( 7), CRm(10), Op2( 2), access_dcsw },
	{ Op1( 0), CRn( 7), CRm(14), Op2( 2), access_dcsw },
940

941
	/* PMU */
942
	{ Op1( 0), CRn( 9), CRm(12), Op2( 0), access_pmcr },
943 944 945
	{ Op1( 0), CRn( 9), CRm(12), Op2( 1), trap_raz_wi },
	{ Op1( 0), CRn( 9), CRm(12), Op2( 2), trap_raz_wi },
	{ Op1( 0), CRn( 9), CRm(12), Op2( 3), trap_raz_wi },
946
	{ Op1( 0), CRn( 9), CRm(12), Op2( 5), access_pmselr },
947 948 949 950 951 952 953 954
	{ Op1( 0), CRn( 9), CRm(12), Op2( 6), trap_raz_wi },
	{ Op1( 0), CRn( 9), CRm(12), Op2( 7), trap_raz_wi },
	{ Op1( 0), CRn( 9), CRm(13), Op2( 0), trap_raz_wi },
	{ Op1( 0), CRn( 9), CRm(13), Op2( 1), trap_raz_wi },
	{ Op1( 0), CRn( 9), CRm(13), Op2( 2), trap_raz_wi },
	{ Op1( 0), CRn( 9), CRm(14), Op2( 0), trap_raz_wi },
	{ Op1( 0), CRn( 9), CRm(14), Op2( 1), trap_raz_wi },
	{ Op1( 0), CRn( 9), CRm(14), Op2( 2), trap_raz_wi },
955 956 957 958 959

	{ Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, c10_PRRR },
	{ Op1( 0), CRn(10), CRm( 2), Op2( 1), access_vm_reg, NULL, c10_NMRR },
	{ Op1( 0), CRn(10), CRm( 3), Op2( 0), access_vm_reg, NULL, c10_AMAIR0 },
	{ Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 },
960 961 962 963

	/* ICC_SRE */
	{ Op1( 0), CRn(12), CRm(12), Op2( 5), trap_raz_wi },

964
	{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
965 966 967 968
};

static const struct sys_reg_desc cp15_64_regs[] = {
	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
969
	{ Op1( 0), CRn( 0), CRm(12), Op2( 0), access_gic_sgi },
970
	{ Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 },
971 972 973 974 975 976 977 978 979 980 981 982
};

/* Target specific emulation tables */
static struct kvm_sys_reg_target_table *target_tables[KVM_ARM_NUM_TARGETS];

void kvm_register_target_sys_reg_table(unsigned int target,
				       struct kvm_sys_reg_target_table *table)
{
	target_tables[target] = table;
}

/* Get specific register table for this target. */
983 984 985
static const struct sys_reg_desc *get_target_table(unsigned target,
						   bool mode_is_64,
						   size_t *num)
986 987 988 989
{
	struct kvm_sys_reg_target_table *table;

	table = target_tables[target];
990 991 992 993 994 995 996
	if (mode_is_64) {
		*num = table->table64.num;
		return table->table64.table;
	} else {
		*num = table->table32.num;
		return table->table32.table;
	}
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
}

static const struct sys_reg_desc *find_reg(const struct sys_reg_params *params,
					 const struct sys_reg_desc table[],
					 unsigned int num)
{
	unsigned int i;

	for (i = 0; i < num; i++) {
		const struct sys_reg_desc *r = &table[i];

		if (params->Op0 != r->Op0)
			continue;
		if (params->Op1 != r->Op1)
			continue;
		if (params->CRn != r->CRn)
			continue;
		if (params->CRm != r->CRm)
			continue;
		if (params->Op2 != r->Op2)
			continue;

		return r;
	}
	return NULL;
}

1024 1025 1026 1027 1028 1029
int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
	kvm_inject_undefined(vcpu);
	return 1;
}

1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040
/*
 * emulate_cp --  tries to match a sys_reg access in a handling table, and
 *                call the corresponding trap handler.
 *
 * @params: pointer to the descriptor of the access
 * @table: array of trap descriptors
 * @num: size of the trap descriptor array
 *
 * Return 0 if the access has been handled, and -1 if not.
 */
static int emulate_cp(struct kvm_vcpu *vcpu,
1041
		      struct sys_reg_params *params,
1042 1043
		      const struct sys_reg_desc *table,
		      size_t num)
1044
{
1045
	const struct sys_reg_desc *r;
1046

1047 1048
	if (!table)
		return -1;	/* Not handled */
1049 1050 1051

	r = find_reg(params, table, num);

1052
	if (r) {
1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063
		/*
		 * Not having an accessor means that we have
		 * configured a trap that we don't know how to
		 * handle. This certainly qualifies as a gross bug
		 * that should be fixed right away.
		 */
		BUG_ON(!r->access);

		if (likely(r->access(vcpu, params, r))) {
			/* Skip instruction, since it was emulated */
			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
1064 1065
			/* Handled */
			return 0;
1066
		}
1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079
	}

	/* Not handled */
	return -1;
}

static void unhandled_cp_access(struct kvm_vcpu *vcpu,
				struct sys_reg_params *params)
{
	u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu);
	int cp;

	switch(hsr_ec) {
1080 1081
	case ESR_ELx_EC_CP15_32:
	case ESR_ELx_EC_CP15_64:
1082 1083
		cp = 15;
		break;
1084 1085
	case ESR_ELx_EC_CP14_MR:
	case ESR_ELx_EC_CP14_64:
1086 1087 1088 1089
		cp = 14;
		break;
	default:
		WARN_ON((cp = -1));
1090 1091
	}

1092 1093
	kvm_err("Unsupported guest CP%d access at: %08lx\n",
		cp, *vcpu_pc(vcpu));
1094 1095 1096 1097 1098
	print_sys_reg_instr(params);
	kvm_inject_undefined(vcpu);
}

/**
1099
 * kvm_handle_cp_64 -- handles a mrrc/mcrr trap on a guest CP14/CP15 access
1100 1101 1102
 * @vcpu: The VCPU pointer
 * @run:  The kvm_run struct
 */
1103 1104 1105 1106 1107
static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
			    const struct sys_reg_desc *global,
			    size_t nr_global,
			    const struct sys_reg_desc *target_specific,
			    size_t nr_specific)
1108 1109 1110
{
	struct sys_reg_params params;
	u32 hsr = kvm_vcpu_get_hsr(vcpu);
1111
	int Rt = (hsr >> 5) & 0xf;
1112 1113
	int Rt2 = (hsr >> 10) & 0xf;

1114 1115
	params.is_aarch32 = true;
	params.is_32bit = false;
1116 1117 1118 1119 1120 1121 1122 1123 1124
	params.CRm = (hsr >> 1) & 0xf;
	params.is_write = ((hsr & 1) == 0);

	params.Op0 = 0;
	params.Op1 = (hsr >> 16) & 0xf;
	params.Op2 = 0;
	params.CRn = 0;

	/*
1125
	 * Make a 64-bit value out of Rt and Rt2. As we use the same trap
1126 1127 1128
	 * backends between AArch32 and AArch64, we get away with it.
	 */
	if (params.is_write) {
1129 1130
		params.regval = vcpu_get_reg(vcpu, Rt) & 0xffffffff;
		params.regval |= vcpu_get_reg(vcpu, Rt2) << 32;
1131 1132
	}

1133 1134 1135 1136 1137 1138
	if (!emulate_cp(vcpu, &params, target_specific, nr_specific))
		goto out;
	if (!emulate_cp(vcpu, &params, global, nr_global))
		goto out;

	unhandled_cp_access(vcpu, &params);
1139

1140
out:
1141
	/* Split up the value between registers for the read side */
1142
	if (!params.is_write) {
1143 1144
		vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval));
		vcpu_set_reg(vcpu, Rt2, upper_32_bits(params.regval));
1145 1146 1147 1148 1149 1150
	}

	return 1;
}

/**
1151
 * kvm_handle_cp_32 -- handles a mrc/mcr trap on a guest CP14/CP15 access
1152 1153 1154
 * @vcpu: The VCPU pointer
 * @run:  The kvm_run struct
 */
1155 1156 1157 1158 1159
static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
			    const struct sys_reg_desc *global,
			    size_t nr_global,
			    const struct sys_reg_desc *target_specific,
			    size_t nr_specific)
1160 1161 1162
{
	struct sys_reg_params params;
	u32 hsr = kvm_vcpu_get_hsr(vcpu);
1163
	int Rt  = (hsr >> 5) & 0xf;
1164

1165 1166
	params.is_aarch32 = true;
	params.is_32bit = true;
1167
	params.CRm = (hsr >> 1) & 0xf;
1168
	params.regval = vcpu_get_reg(vcpu, Rt);
1169 1170 1171 1172 1173 1174
	params.is_write = ((hsr & 1) == 0);
	params.CRn = (hsr >> 10) & 0xf;
	params.Op0 = 0;
	params.Op1 = (hsr >> 14) & 0x7;
	params.Op2 = (hsr >> 17) & 0x7;

1175 1176 1177 1178
	if (!emulate_cp(vcpu, &params, target_specific, nr_specific) ||
	    !emulate_cp(vcpu, &params, global, nr_global)) {
		if (!params.is_write)
			vcpu_set_reg(vcpu, Rt, params.regval);
1179
		return 1;
1180
	}
1181 1182

	unhandled_cp_access(vcpu, &params);
1183 1184 1185
	return 1;
}

1186 1187 1188 1189 1190 1191 1192
int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
	const struct sys_reg_desc *target_specific;
	size_t num;

	target_specific = get_target_table(vcpu->arch.target, false, &num);
	return kvm_handle_cp_64(vcpu,
1193
				cp15_64_regs, ARRAY_SIZE(cp15_64_regs),
1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210
				target_specific, num);
}

int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
	const struct sys_reg_desc *target_specific;
	size_t num;

	target_specific = get_target_table(vcpu->arch.target, false, &num);
	return kvm_handle_cp_32(vcpu,
				cp15_regs, ARRAY_SIZE(cp15_regs),
				target_specific, num);
}

int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
	return kvm_handle_cp_64(vcpu,
1211
				cp14_64_regs, ARRAY_SIZE(cp14_64_regs),
1212 1213 1214 1215 1216 1217 1218 1219 1220 1221
				NULL, 0);
}

int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
	return kvm_handle_cp_32(vcpu,
				cp14_regs, ARRAY_SIZE(cp14_regs),
				NULL, 0);
}

1222
static int emulate_sys_reg(struct kvm_vcpu *vcpu,
1223
			   struct sys_reg_params *params)
1224 1225 1226 1227
{
	size_t num;
	const struct sys_reg_desc *table, *r;

1228
	table = get_target_table(vcpu->arch.target, true, &num);
1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277

	/* Search target-specific then generic table. */
	r = find_reg(params, table, num);
	if (!r)
		r = find_reg(params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));

	if (likely(r)) {
		/*
		 * Not having an accessor means that we have
		 * configured a trap that we don't know how to
		 * handle. This certainly qualifies as a gross bug
		 * that should be fixed right away.
		 */
		BUG_ON(!r->access);

		if (likely(r->access(vcpu, params, r))) {
			/* Skip instruction, since it was emulated */
			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
			return 1;
		}
		/* If access function fails, it should complain. */
	} else {
		kvm_err("Unsupported guest sys_reg access at: %lx\n",
			*vcpu_pc(vcpu));
		print_sys_reg_instr(params);
	}
	kvm_inject_undefined(vcpu);
	return 1;
}

static void reset_sys_reg_descs(struct kvm_vcpu *vcpu,
			      const struct sys_reg_desc *table, size_t num)
{
	unsigned long i;

	for (i = 0; i < num; i++)
		if (table[i].reset)
			table[i].reset(vcpu, &table[i]);
}

/**
 * kvm_handle_sys_reg -- handles a mrs/msr trap on a guest sys_reg access
 * @vcpu: The VCPU pointer
 * @run:  The kvm_run struct
 */
int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
	struct sys_reg_params params;
	unsigned long esr = kvm_vcpu_get_hsr(vcpu);
1278 1279
	int Rt = (esr >> 5) & 0x1f;
	int ret;
1280

1281 1282
	trace_kvm_handle_sys_reg(esr);

1283 1284
	params.is_aarch32 = false;
	params.is_32bit = false;
1285 1286 1287 1288 1289
	params.Op0 = (esr >> 20) & 3;
	params.Op1 = (esr >> 14) & 0x7;
	params.CRn = (esr >> 10) & 0xf;
	params.CRm = (esr >> 1) & 0xf;
	params.Op2 = (esr >> 17) & 0x7;
1290
	params.regval = vcpu_get_reg(vcpu, Rt);
1291 1292
	params.is_write = !(esr & 1);

1293 1294 1295 1296 1297
	ret = emulate_sys_reg(vcpu, &params);

	if (!params.is_write)
		vcpu_set_reg(vcpu, Rt, params.regval);
	return ret;
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
}

/******************************************************************************
 * Userspace API
 *****************************************************************************/

static bool index_to_params(u64 id, struct sys_reg_params *params)
{
	switch (id & KVM_REG_SIZE_MASK) {
	case KVM_REG_SIZE_U64:
		/* Any unused index bits means it's not valid. */
		if (id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK
			      | KVM_REG_ARM_COPROC_MASK
			      | KVM_REG_ARM64_SYSREG_OP0_MASK
			      | KVM_REG_ARM64_SYSREG_OP1_MASK
			      | KVM_REG_ARM64_SYSREG_CRN_MASK
			      | KVM_REG_ARM64_SYSREG_CRM_MASK
			      | KVM_REG_ARM64_SYSREG_OP2_MASK))
			return false;
		params->Op0 = ((id & KVM_REG_ARM64_SYSREG_OP0_MASK)
			       >> KVM_REG_ARM64_SYSREG_OP0_SHIFT);
		params->Op1 = ((id & KVM_REG_ARM64_SYSREG_OP1_MASK)
			       >> KVM_REG_ARM64_SYSREG_OP1_SHIFT);
		params->CRn = ((id & KVM_REG_ARM64_SYSREG_CRN_MASK)
			       >> KVM_REG_ARM64_SYSREG_CRN_SHIFT);
		params->CRm = ((id & KVM_REG_ARM64_SYSREG_CRM_MASK)
			       >> KVM_REG_ARM64_SYSREG_CRM_SHIFT);
		params->Op2 = ((id & KVM_REG_ARM64_SYSREG_OP2_MASK)
			       >> KVM_REG_ARM64_SYSREG_OP2_SHIFT);
		return true;
	default:
		return false;
	}
}

/* Decode an index value, and find the sys_reg_desc entry. */
static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu,
						    u64 id)
{
	size_t num;
	const struct sys_reg_desc *table, *r;
	struct sys_reg_params params;

	/* We only do sys_reg for now. */
	if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM64_SYSREG)
		return NULL;

	if (!index_to_params(id, &params))
		return NULL;

1348
	table = get_target_table(vcpu->arch.target, true, &num);
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
	r = find_reg(&params, table, num);
	if (!r)
		r = find_reg(&params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));

	/* Not saved in the sys_reg array? */
	if (r && !r->reg)
		r = NULL;

	return r;
}

/*
 * These are the invariant sys_reg registers: we let the guest see the
 * host versions of these, so they're part of the guest state.
 *
 * A future CPU may provide a mechanism to present different values to
 * the guest, or a future kvm may trap them.
 */

#define FUNCTION_INVARIANT(reg)						\
	static void get_##reg(struct kvm_vcpu *v,			\
			      const struct sys_reg_desc *r)		\
	{								\
		u64 val;						\
									\
		asm volatile("mrs %0, " __stringify(reg) "\n"		\
			     : "=r" (val));				\
		((struct sys_reg_desc *)r)->val = val;			\
	}

FUNCTION_INVARIANT(midr_el1)
FUNCTION_INVARIANT(ctr_el0)
FUNCTION_INVARIANT(revidr_el1)
FUNCTION_INVARIANT(id_pfr0_el1)
FUNCTION_INVARIANT(id_pfr1_el1)
FUNCTION_INVARIANT(id_dfr0_el1)
FUNCTION_INVARIANT(id_afr0_el1)
FUNCTION_INVARIANT(id_mmfr0_el1)
FUNCTION_INVARIANT(id_mmfr1_el1)
FUNCTION_INVARIANT(id_mmfr2_el1)
FUNCTION_INVARIANT(id_mmfr3_el1)
FUNCTION_INVARIANT(id_isar0_el1)
FUNCTION_INVARIANT(id_isar1_el1)
FUNCTION_INVARIANT(id_isar2_el1)
FUNCTION_INVARIANT(id_isar3_el1)
FUNCTION_INVARIANT(id_isar4_el1)
FUNCTION_INVARIANT(id_isar5_el1)
FUNCTION_INVARIANT(clidr_el1)
FUNCTION_INVARIANT(aidr_el1)

/* ->val is filled in by kvm_sys_reg_table_init() */
static struct sys_reg_desc invariant_sys_regs[] = {
	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0000), Op2(0b000),
	  NULL, get_midr_el1 },
	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0000), Op2(0b110),
	  NULL, get_revidr_el1 },
	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b000),
	  NULL, get_id_pfr0_el1 },
	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b001),
	  NULL, get_id_pfr1_el1 },
	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b010),
	  NULL, get_id_dfr0_el1 },
	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b011),
	  NULL, get_id_afr0_el1 },
	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b100),
	  NULL, get_id_mmfr0_el1 },
	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b101),
	  NULL, get_id_mmfr1_el1 },
	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b110),
	  NULL, get_id_mmfr2_el1 },
	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b111),
	  NULL, get_id_mmfr3_el1 },
	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b000),
	  NULL, get_id_isar0_el1 },
	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b001),
	  NULL, get_id_isar1_el1 },
	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b010),
	  NULL, get_id_isar2_el1 },
	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b011),
	  NULL, get_id_isar3_el1 },
	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b100),
	  NULL, get_id_isar4_el1 },
	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b101),
	  NULL, get_id_isar5_el1 },
	{ Op0(0b11), Op1(0b001), CRn(0b0000), CRm(0b0000), Op2(0b001),
	  NULL, get_clidr_el1 },
	{ Op0(0b11), Op1(0b001), CRn(0b0000), CRm(0b0000), Op2(0b111),
	  NULL, get_aidr_el1 },
	{ Op0(0b11), Op1(0b011), CRn(0b0000), CRm(0b0000), Op2(0b001),
	  NULL, get_ctr_el0 },
};

1441
static int reg_from_user(u64 *val, const void __user *uaddr, u64 id)
1442 1443 1444 1445 1446 1447
{
	if (copy_from_user(val, uaddr, KVM_REG_SIZE(id)) != 0)
		return -EFAULT;
	return 0;
}

1448
static int reg_to_user(void __user *uaddr, const u64 *val, u64 id)
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
{
	if (copy_to_user(uaddr, val, KVM_REG_SIZE(id)) != 0)
		return -EFAULT;
	return 0;
}

static int get_invariant_sys_reg(u64 id, void __user *uaddr)
{
	struct sys_reg_params params;
	const struct sys_reg_desc *r;

	if (!index_to_params(id, &params))
		return -ENOENT;

	r = find_reg(&params, invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs));
	if (!r)
		return -ENOENT;

	return reg_to_user(uaddr, &r->val, id);
}

static int set_invariant_sys_reg(u64 id, void __user *uaddr)
{
	struct sys_reg_params params;
	const struct sys_reg_desc *r;
	int err;
	u64 val = 0; /* Make sure high bits are 0 for 32-bit regs */

	if (!index_to_params(id, &params))
		return -ENOENT;
	r = find_reg(&params, invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs));
	if (!r)
		return -ENOENT;

	err = reg_from_user(&val, uaddr, id);
	if (err)
		return err;

	/* This is what we mean by invariant: you can't change it. */
	if (r->val != val)
		return -EINVAL;

	return 0;
}

static bool is_valid_cache(u32 val)
{
	u32 level, ctype;

	if (val >= CSSELR_MAX)
1499
		return false;
1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590

	/* Bottom bit is Instruction or Data bit.  Next 3 bits are level. */
	level = (val >> 1);
	ctype = (cache_levels >> (level * 3)) & 7;

	switch (ctype) {
	case 0: /* No cache */
		return false;
	case 1: /* Instruction cache only */
		return (val & 1);
	case 2: /* Data cache only */
	case 4: /* Unified cache */
		return !(val & 1);
	case 3: /* Separate instruction and data caches */
		return true;
	default: /* Reserved: we can't know instruction or data. */
		return false;
	}
}

static int demux_c15_get(u64 id, void __user *uaddr)
{
	u32 val;
	u32 __user *uval = uaddr;

	/* Fail if we have unknown bits set. */
	if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK
		   | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1)))
		return -ENOENT;

	switch (id & KVM_REG_ARM_DEMUX_ID_MASK) {
	case KVM_REG_ARM_DEMUX_ID_CCSIDR:
		if (KVM_REG_SIZE(id) != 4)
			return -ENOENT;
		val = (id & KVM_REG_ARM_DEMUX_VAL_MASK)
			>> KVM_REG_ARM_DEMUX_VAL_SHIFT;
		if (!is_valid_cache(val))
			return -ENOENT;

		return put_user(get_ccsidr(val), uval);
	default:
		return -ENOENT;
	}
}

static int demux_c15_set(u64 id, void __user *uaddr)
{
	u32 val, newval;
	u32 __user *uval = uaddr;

	/* Fail if we have unknown bits set. */
	if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK
		   | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1)))
		return -ENOENT;

	switch (id & KVM_REG_ARM_DEMUX_ID_MASK) {
	case KVM_REG_ARM_DEMUX_ID_CCSIDR:
		if (KVM_REG_SIZE(id) != 4)
			return -ENOENT;
		val = (id & KVM_REG_ARM_DEMUX_VAL_MASK)
			>> KVM_REG_ARM_DEMUX_VAL_SHIFT;
		if (!is_valid_cache(val))
			return -ENOENT;

		if (get_user(newval, uval))
			return -EFAULT;

		/* This is also invariant: you can't change it. */
		if (newval != get_ccsidr(val))
			return -EINVAL;
		return 0;
	default:
		return -ENOENT;
	}
}

int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
{
	const struct sys_reg_desc *r;
	void __user *uaddr = (void __user *)(unsigned long)reg->addr;

	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX)
		return demux_c15_get(reg->id, uaddr);

	if (KVM_REG_SIZE(reg->id) != sizeof(__u64))
		return -ENOENT;

	r = index_to_sys_reg_desc(vcpu, reg->id);
	if (!r)
		return get_invariant_sys_reg(reg->id, uaddr);

1591 1592 1593
	if (r->get_user)
		return (r->get_user)(vcpu, r, reg, uaddr);

1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611
	return reg_to_user(uaddr, &vcpu_sys_reg(vcpu, r->reg), reg->id);
}

int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
{
	const struct sys_reg_desc *r;
	void __user *uaddr = (void __user *)(unsigned long)reg->addr;

	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX)
		return demux_c15_set(reg->id, uaddr);

	if (KVM_REG_SIZE(reg->id) != sizeof(__u64))
		return -ENOENT;

	r = index_to_sys_reg_desc(vcpu, reg->id);
	if (!r)
		return set_invariant_sys_reg(reg->id, uaddr);

1612 1613 1614
	if (r->set_user)
		return (r->set_user)(vcpu, r, reg, uaddr);

1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630
	return reg_from_user(&vcpu_sys_reg(vcpu, r->reg), uaddr, reg->id);
}

static unsigned int num_demux_regs(void)
{
	unsigned int i, count = 0;

	for (i = 0; i < CSSELR_MAX; i++)
		if (is_valid_cache(i))
			count++;

	return count;
}

static int write_demux_regids(u64 __user *uindices)
{
1631
	u64 val = KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX;
1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675
	unsigned int i;

	val |= KVM_REG_ARM_DEMUX_ID_CCSIDR;
	for (i = 0; i < CSSELR_MAX; i++) {
		if (!is_valid_cache(i))
			continue;
		if (put_user(val | i, uindices))
			return -EFAULT;
		uindices++;
	}
	return 0;
}

static u64 sys_reg_to_index(const struct sys_reg_desc *reg)
{
	return (KVM_REG_ARM64 | KVM_REG_SIZE_U64 |
		KVM_REG_ARM64_SYSREG |
		(reg->Op0 << KVM_REG_ARM64_SYSREG_OP0_SHIFT) |
		(reg->Op1 << KVM_REG_ARM64_SYSREG_OP1_SHIFT) |
		(reg->CRn << KVM_REG_ARM64_SYSREG_CRN_SHIFT) |
		(reg->CRm << KVM_REG_ARM64_SYSREG_CRM_SHIFT) |
		(reg->Op2 << KVM_REG_ARM64_SYSREG_OP2_SHIFT));
}

static bool copy_reg_to_user(const struct sys_reg_desc *reg, u64 __user **uind)
{
	if (!*uind)
		return true;

	if (put_user(sys_reg_to_index(reg), *uind))
		return false;

	(*uind)++;
	return true;
}

/* Assumed ordered tables, see kvm_sys_reg_table_init. */
static int walk_sys_regs(struct kvm_vcpu *vcpu, u64 __user *uind)
{
	const struct sys_reg_desc *i1, *i2, *end1, *end2;
	unsigned int total = 0;
	size_t num;

	/* We check for duplicates here, to allow arch-specific overrides. */
1676
	i1 = get_target_table(vcpu->arch.target, true, &num);
1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737
	end1 = i1 + num;
	i2 = sys_reg_descs;
	end2 = sys_reg_descs + ARRAY_SIZE(sys_reg_descs);

	BUG_ON(i1 == end1 || i2 == end2);

	/* Walk carefully, as both tables may refer to the same register. */
	while (i1 || i2) {
		int cmp = cmp_sys_reg(i1, i2);
		/* target-specific overrides generic entry. */
		if (cmp <= 0) {
			/* Ignore registers we trap but don't save. */
			if (i1->reg) {
				if (!copy_reg_to_user(i1, &uind))
					return -EFAULT;
				total++;
			}
		} else {
			/* Ignore registers we trap but don't save. */
			if (i2->reg) {
				if (!copy_reg_to_user(i2, &uind))
					return -EFAULT;
				total++;
			}
		}

		if (cmp <= 0 && ++i1 == end1)
			i1 = NULL;
		if (cmp >= 0 && ++i2 == end2)
			i2 = NULL;
	}
	return total;
}

unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu)
{
	return ARRAY_SIZE(invariant_sys_regs)
		+ num_demux_regs()
		+ walk_sys_regs(vcpu, (u64 __user *)NULL);
}

int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
{
	unsigned int i;
	int err;

	/* Then give them all the invariant registers' indices. */
	for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++) {
		if (put_user(sys_reg_to_index(&invariant_sys_regs[i]), uindices))
			return -EFAULT;
		uindices++;
	}

	err = walk_sys_regs(vcpu, uindices);
	if (err < 0)
		return err;
	uindices += err;

	return write_demux_regids(uindices);
}

1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751
static int check_sysreg_table(const struct sys_reg_desc *table, unsigned int n)
{
	unsigned int i;

	for (i = 1; i < n; i++) {
		if (cmp_sys_reg(&table[i-1], &table[i]) >= 0) {
			kvm_err("sys_reg table %p out of order (%d)\n", table, i - 1);
			return 1;
		}
	}

	return 0;
}

1752 1753 1754 1755 1756 1757
void kvm_sys_reg_table_init(void)
{
	unsigned int i;
	struct sys_reg_desc clidr;

	/* Make sure tables are unique and in order. */
1758 1759 1760 1761 1762 1763
	BUG_ON(check_sysreg_table(sys_reg_descs, ARRAY_SIZE(sys_reg_descs)));
	BUG_ON(check_sysreg_table(cp14_regs, ARRAY_SIZE(cp14_regs)));
	BUG_ON(check_sysreg_table(cp14_64_regs, ARRAY_SIZE(cp14_64_regs)));
	BUG_ON(check_sysreg_table(cp15_regs, ARRAY_SIZE(cp15_regs)));
	BUG_ON(check_sysreg_table(cp15_64_regs, ARRAY_SIZE(cp15_64_regs)));
	BUG_ON(check_sysreg_table(invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs)));
1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805

	/* We abuse the reset function to overwrite the table itself. */
	for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++)
		invariant_sys_regs[i].reset(NULL, &invariant_sys_regs[i]);

	/*
	 * CLIDR format is awkward, so clean it up.  See ARM B4.1.20:
	 *
	 *   If software reads the Cache Type fields from Ctype1
	 *   upwards, once it has seen a value of 0b000, no caches
	 *   exist at further-out levels of the hierarchy. So, for
	 *   example, if Ctype3 is the first Cache Type field with a
	 *   value of 0b000, the values of Ctype4 to Ctype7 must be
	 *   ignored.
	 */
	get_clidr_el1(NULL, &clidr); /* Ugly... */
	cache_levels = clidr.val;
	for (i = 0; i < 7; i++)
		if (((cache_levels >> (i*3)) & 7) == 0)
			break;
	/* Clear all higher bits. */
	cache_levels &= (1 << (i*3))-1;
}

/**
 * kvm_reset_sys_regs - sets system registers to reset value
 * @vcpu: The VCPU pointer
 *
 * This function finds the right table above and sets the registers on the
 * virtual CPU struct to their architecturally defined reset values.
 */
void kvm_reset_sys_regs(struct kvm_vcpu *vcpu)
{
	size_t num;
	const struct sys_reg_desc *table;

	/* Catch someone adding a register without putting in reset entry. */
	memset(&vcpu->arch.ctxt.sys_regs, 0x42, sizeof(vcpu->arch.ctxt.sys_regs));

	/* Generic chip reset first (so target could override). */
	reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));

1806
	table = get_target_table(vcpu->arch.target, true, &num);
1807 1808 1809 1810 1811 1812
	reset_sys_reg_descs(vcpu, table, num);

	for (num = 1; num < NR_SYS_REGS; num++)
		if (vcpu_sys_reg(vcpu, num) == 0x4242424242424242)
			panic("Didn't reset vcpu_sys_reg(%zi)", num);
}