switch.c 12.9 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17
/*
 * Copyright (C) 2015 - ARM Ltd
 * Author: Marc Zyngier <marc.zyngier@arm.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/>.
 */

18
#include <linux/types.h>
19
#include <linux/jump_label.h>
20
#include <uapi/linux/psci.h>
21

22 23
#include <kvm/arm_psci.h>

24
#include <asm/kvm_asm.h>
25
#include <asm/kvm_emulate.h>
26
#include <asm/kvm_hyp.h>
27
#include <asm/kvm_mmu.h>
28
#include <asm/fpsimd.h>
29
#include <asm/debug-monitors.h>
30

31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49
static bool __hyp_text __fpsimd_enabled_nvhe(void)
{
	return !(read_sysreg(cptr_el2) & CPTR_EL2_TFP);
}

static bool __hyp_text __fpsimd_enabled_vhe(void)
{
	return !!(read_sysreg(cpacr_el1) & CPACR_EL1_FPEN);
}

static hyp_alternate_select(__fpsimd_is_enabled,
			    __fpsimd_enabled_nvhe, __fpsimd_enabled_vhe,
			    ARM64_HAS_VIRT_HOST_EXTN);

bool __hyp_text __fpsimd_enabled(void)
{
	return __fpsimd_is_enabled()();
}

50 51 52 53 54 55
static void __hyp_text __activate_traps_vhe(void)
{
	u64 val;

	val = read_sysreg(cpacr_el1);
	val |= CPACR_EL1_TTA;
56
	val &= ~(CPACR_EL1_FPEN | CPACR_EL1_ZEN);
57 58
	write_sysreg(val, cpacr_el1);

59
	write_sysreg(kvm_get_hyp_vector(), vbar_el1);
60 61 62 63 64 65 66
}

static void __hyp_text __activate_traps_nvhe(void)
{
	u64 val;

	val = CPTR_EL2_DEFAULT;
67
	val |= CPTR_EL2_TTA | CPTR_EL2_TFP | CPTR_EL2_TZ;
68 69 70 71 72 73 74
	write_sysreg(val, cptr_el2);
}

static hyp_alternate_select(__activate_traps_arch,
			    __activate_traps_nvhe, __activate_traps_vhe,
			    ARM64_HAS_VIRT_HOST_EXTN);

75 76 77 78 79 80 81 82 83 84
static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
{
	u64 val;

	/*
	 * We are about to set CPTR_EL2.TFP to trap all floating point
	 * register accesses to EL2, however, the ARM ARM clearly states that
	 * traps are only taken to EL2 if the operation would not otherwise
	 * trap to EL1.  Therefore, always make sure that for 32-bit guests,
	 * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit.
85 86
	 * If FP/ASIMD is not implemented, FPEXC is UNDEFINED and any access to
	 * it will cause an exception.
87 88
	 */
	val = vcpu->arch.hcr_el2;
89

90
	if (!(val & HCR_RW) && system_supports_fpsimd()) {
91 92 93 94
		write_sysreg(1 << 30, fpexc32_el2);
		isb();
	}
	write_sysreg(val, hcr_el2);
95

96 97 98
	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (val & HCR_VSE))
		write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);

99 100
	/* Trap on AArch32 cp15 c15 accesses (EL1 or EL0) */
	write_sysreg(1 << 15, hstr_el2);
101 102 103 104 105 106 107
	/*
	 * Make sure we trap PMU access from EL0 to EL2. Also sanitize
	 * PMSELR_EL0 to make sure it never contains the cycle
	 * counter, which could make a PMXEVCNTR_EL0 access UNDEF at
	 * EL1 instead of being trapped to EL2.
	 */
	write_sysreg(0, pmselr_el0);
108
	write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
109 110 111
	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
	__activate_traps_arch()();
}
112

113 114 115
static void __hyp_text __deactivate_traps_vhe(void)
{
	extern char vectors[];	/* kernel exception vectors */
116
	u64 mdcr_el2 = read_sysreg(mdcr_el2);
117

118 119 120 121 122
	mdcr_el2 &= MDCR_EL2_HPMN_MASK |
		    MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT |
		    MDCR_EL2_TPMS;

	write_sysreg(mdcr_el2, mdcr_el2);
123
	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
124
	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
125
	write_sysreg(vectors, vbar_el1);
126 127
}

128
static void __hyp_text __deactivate_traps_nvhe(void)
129
{
130 131 132 133 134 135
	u64 mdcr_el2 = read_sysreg(mdcr_el2);

	mdcr_el2 &= MDCR_EL2_HPMN_MASK;
	mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;

	write_sysreg(mdcr_el2, mdcr_el2);
136
	write_sysreg(HCR_RW, hcr_el2);
137 138 139 140 141 142 143 144 145
	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
}

static hyp_alternate_select(__deactivate_traps_arch,
			    __deactivate_traps_nvhe, __deactivate_traps_vhe,
			    ARM64_HAS_VIRT_HOST_EXTN);

static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
{
146 147 148 149 150 151 152 153 154
	/*
	 * If we pended a virtual abort, preserve it until it gets
	 * cleared. See D1.14.3 (Virtual Interrupts) for details, but
	 * the crucial bit is "On taking a vSError interrupt,
	 * HCR_EL2.VSE is cleared to 0."
	 */
	if (vcpu->arch.hcr_el2 & HCR_VSE)
		vcpu->arch.hcr_el2 = read_sysreg(hcr_el2);

155
	__deactivate_traps_arch()();
156
	write_sysreg(0, hstr_el2);
157
	write_sysreg(0, pmuserenr_el0);
158 159 160 161 162 163 164 165 166 167 168 169 170 171 172
}

static void __hyp_text __activate_vm(struct kvm_vcpu *vcpu)
{
	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
	write_sysreg(kvm->arch.vttbr, vttbr_el2);
}

static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
{
	write_sysreg(0, vttbr_el2);
}

static void __hyp_text __vgic_save_state(struct kvm_vcpu *vcpu)
{
173 174 175 176
	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
		__vgic_v3_save_state(vcpu);
	else
		__vgic_v2_save_state(vcpu);
177 178 179 180
}

static void __hyp_text __vgic_restore_state(struct kvm_vcpu *vcpu)
{
181 182 183 184
	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
		__vgic_v3_restore_state(vcpu);
	else
		__vgic_v2_restore_state(vcpu);
185 186
}

187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231
static bool __hyp_text __true_value(void)
{
	return true;
}

static bool __hyp_text __false_value(void)
{
	return false;
}

static hyp_alternate_select(__check_arm_834220,
			    __false_value, __true_value,
			    ARM64_WORKAROUND_834220);

static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
{
	u64 par, tmp;

	/*
	 * Resolve the IPA the hard way using the guest VA.
	 *
	 * Stage-1 translation already validated the memory access
	 * rights. As such, we can use the EL1 translation regime, and
	 * don't have to distinguish between EL0 and EL1 access.
	 *
	 * We do need to save/restore PAR_EL1 though, as we haven't
	 * saved the guest context yet, and we may return early...
	 */
	par = read_sysreg(par_el1);
	asm volatile("at s1e1r, %0" : : "r" (far));
	isb();

	tmp = read_sysreg(par_el1);
	write_sysreg(par, par_el1);

	if (unlikely(tmp & 1))
		return false; /* Translation failed, back to guest */

	/* Convert PAR to HPFAR format */
	*hpfar = ((tmp >> 12) & ((1UL << 36) - 1)) << 4;
	return true;
}

static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
{
232 233
	u8 ec;
	u64 esr;
234 235
	u64 hpfar, far;

236 237
	esr = vcpu->arch.fault.esr_el2;
	ec = ESR_ELx_EC(esr);
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

	if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
		return true;

	far = read_sysreg_el2(far);

	/*
	 * The HPFAR can be invalid if the stage 2 fault did not
	 * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
	 * bit is clear) and one of the two following cases are true:
	 *   1. The fault was due to a permission fault
	 *   2. The processor carries errata 834220
	 *
	 * Therefore, for all non S1PTW faults where we either have a
	 * permission fault or the errata workaround is enabled, we
	 * resolve the IPA using the AT instruction.
	 */
	if (!(esr & ESR_ELx_S1PTW) &&
	    (__check_arm_834220()() || (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
		if (!__translate_far_to_hpfar(far, &hpfar))
			return false;
	} else {
		hpfar = read_sysreg(hpfar_el2);
	}

	vcpu->arch.fault.far_el2 = far;
	vcpu->arch.fault.hpfar_el2 = hpfar;
	return true;
}

268 269 270 271 272
/* Skip an instruction which has been emulated. Returns true if
 * execution can continue or false if we need to exit hyp mode because
 * single-step was in effect.
 */
static bool __hyp_text __skip_instr(struct kvm_vcpu *vcpu)
273 274 275 276 277 278 279 280 281 282 283 284
{
	*vcpu_pc(vcpu) = read_sysreg_el2(elr);

	if (vcpu_mode_is_32bit(vcpu)) {
		vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(spsr);
		kvm_skip_instr32(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
		write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, spsr);
	} else {
		*vcpu_pc(vcpu) += 4;
	}

	write_sysreg_el2(*vcpu_pc(vcpu), elr);
285 286 287 288 289 290 291 292

	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
		vcpu->arch.fault.esr_el2 =
			(ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT) | 0x22;
		return false;
	} else {
		return true;
	}
293 294
}

295
int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
296 297 298
{
	struct kvm_cpu_context *host_ctxt;
	struct kvm_cpu_context *guest_ctxt;
299
	bool fp_enabled;
300 301 302 303 304
	u64 exit_code;

	vcpu = kern_hyp_va(vcpu);

	host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
305
	host_ctxt->__hyp_running_vcpu = vcpu;
306 307
	guest_ctxt = &vcpu->arch.ctxt;

308
	__sysreg_save_host_state(host_ctxt);
309 310 311 312 313 314
	__debug_cond_save_host_state(vcpu);

	__activate_traps(vcpu);
	__activate_vm(vcpu);

	__vgic_restore_state(vcpu);
315
	__timer_enable_traps(vcpu);
316 317 318

	/*
	 * We must restore the 32-bit state before the sysregs, thanks
319
	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
320 321
	 */
	__sysreg32_restore_state(vcpu);
322
	__sysreg_restore_guest_state(guest_ctxt);
323 324 325
	__debug_restore_state(vcpu, kern_hyp_va(vcpu->arch.debug_ptr), guest_ctxt);

	/* Jump in the fire! */
326
again:
327 328 329
	exit_code = __guest_enter(vcpu, host_ctxt);
	/* And we're baaack! */

330 331
	if (ARM_EXCEPTION_CODE(exit_code) != ARM_EXCEPTION_IRQ)
		vcpu->arch.fault.esr_el2 = read_sysreg_el2(esr);
332 333 334 335 336 337
	/*
	 * We're using the raw exception code in order to only process
	 * the trap if no SError is pending. We will come back to the
	 * same PC once the SError has been injected, and replay the
	 * trapping instruction.
	 */
338 339 340
	if (exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu))
		goto again;

341 342 343 344 345 346 347 348 349 350
	if (static_branch_unlikely(&vgic_v2_cpuif_trap) &&
	    exit_code == ARM_EXCEPTION_TRAP) {
		bool valid;

		valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW &&
			kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
			kvm_vcpu_dabt_isvalid(vcpu) &&
			!kvm_vcpu_dabt_isextabt(vcpu) &&
			!kvm_vcpu_dabt_iss1tw(vcpu);

351 352 353 354
		if (valid) {
			int ret = __vgic_v2_perform_cpuif_access(vcpu);

			if (ret == 1) {
355 356 357 358
				if (__skip_instr(vcpu))
					goto again;
				else
					exit_code = ARM_EXCEPTION_TRAP;
359 360 361
			}

			if (ret == -1) {
362 363 364 365 366 367 368 369
				/* Promote an illegal access to an
				 * SError. If we would be returning
				 * due to single-step clear the SS
				 * bit so handle_exit knows what to
				 * do after dealing with the error.
				 */
				if (!__skip_instr(vcpu))
					*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
370 371 372 373
				exit_code = ARM_EXCEPTION_EL1_SERROR;
			}

			/* 0 falls through to be handler out of EL2 */
374 375 376
		}
	}

377 378 379 380 381 382 383
	if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
	    exit_code == ARM_EXCEPTION_TRAP &&
	    (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 ||
	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) {
		int ret = __vgic_v3_perform_cpuif_access(vcpu);

		if (ret == 1) {
384 385 386 387
			if (__skip_instr(vcpu))
				goto again;
			else
				exit_code = ARM_EXCEPTION_TRAP;
388 389 390 391 392
		}

		/* 0 falls through to be handled out of EL2 */
	}

393 394 395 396
	if (cpus_have_const_cap(ARM64_HARDEN_BP_POST_GUEST_EXIT)) {
		u32 midr = read_cpuid_id();

		/* Apply BTAC predictors mitigation to all Falkor chips */
397 398
		if (((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR) ||
		    ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1)) {
399
			__qcom_hyp_sanitize_btac_predictors();
400
		}
401 402
	}

403 404
	fp_enabled = __fpsimd_enabled();

405
	__sysreg_save_guest_state(guest_ctxt);
406
	__sysreg32_save_state(vcpu);
407
	__timer_disable_traps(vcpu);
408 409 410 411 412
	__vgic_save_state(vcpu);

	__deactivate_traps(vcpu);
	__deactivate_vm(vcpu);

413
	__sysreg_restore_host_state(host_ctxt);
414

415 416 417 418 419
	if (fp_enabled) {
		__fpsimd_save_state(&guest_ctxt->gp_regs.fp_regs);
		__fpsimd_restore_state(&host_ctxt->gp_regs.fp_regs);
	}

420
	__debug_save_state(vcpu, kern_hyp_va(vcpu->arch.debug_ptr), guest_ctxt);
421 422 423 424
	/*
	 * This must come after restoring the host sysregs, since a non-VHE
	 * system may enable SPE here and make use of the TTBRs.
	 */
425 426 427 428
	__debug_cond_restore_host_state(vcpu);

	return exit_code;
}
M
Marc Zyngier 已提交
429 430 431

static const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n";

432
static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par,
433
					     struct kvm_cpu_context *__host_ctxt)
M
Marc Zyngier 已提交
434
{
435
	struct kvm_vcpu *vcpu;
436
	unsigned long str_va;
437

438 439 440 441 442 443 444 445 446
	vcpu = __host_ctxt->__hyp_running_vcpu;

	if (read_sysreg(vttbr_el2)) {
		__timer_disable_traps(vcpu);
		__deactivate_traps(vcpu);
		__deactivate_vm(vcpu);
		__sysreg_restore_host_state(__host_ctxt);
	}

447 448 449 450 451 452 453 454
	/*
	 * Force the panic string to be loaded from the literal pool,
	 * making sure it is a kernel address and not a PC-relative
	 * reference.
	 */
	asm volatile("ldr %0, =__hyp_panic_string" : "=r" (str_va));

	__hyp_do_panic(str_va,
455 456
		       spsr,  elr,
		       read_sysreg(esr_el2),   read_sysreg_el2(far),
457
		       read_sysreg(hpfar_el2), par, vcpu);
458 459
}

460 461
static void __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par,
				 struct kvm_cpu_context *host_ctxt)
462
{
463 464 465 466 467 468
	struct kvm_vcpu *vcpu;
	vcpu = host_ctxt->__hyp_running_vcpu;

	__deactivate_traps(vcpu);
	__sysreg_restore_host_state(host_ctxt);

469 470 471
	panic(__hyp_panic_string,
	      spsr,  elr,
	      read_sysreg_el2(esr),   read_sysreg_el2(far),
472
	      read_sysreg(hpfar_el2), par, vcpu);
473 474
}

475
void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
476 477 478
{
	u64 spsr = read_sysreg_el2(spsr);
	u64 elr = read_sysreg_el2(elr);
M
Marc Zyngier 已提交
479 480
	u64 par = read_sysreg(par_el1);

481 482 483 484
	if (!has_vhe())
		__hyp_call_panic_nvhe(spsr, elr, par, host_ctxt);
	else
		__hyp_call_panic_vhe(spsr, elr, par, host_ctxt);
M
Marc Zyngier 已提交
485 486 487

	unreachable();
}