Merge branch kvm-arm64/wfxt into kvmarm-master/next

* kvm-arm64/wfxt:
: .
: Add support for the WFET/WFIT instructions that provide the same
: service as WFE/WFI, only with a timeout.
: .
KVM: arm64: Expose the WFXT feature to guests
KVM: arm64: Offer early resume for non-blocking WFxT instructions
KVM: arm64: Handle blocking WFIT instruction
KVM: arm64: Introduce kvm_counter_compute_delta() helper
KVM: arm64: Simplify kvm_cpu_has_pending_timer()
arm64: Use WFxT for __delay() when possible
arm64: Add wfet()/wfit() helpers
arm64: Add HWCAP advertising FEAT_WFXT
arm64: Add RV and RN fields for ESR_ELx_WFx_ISS
arm64: Expand ESR_ELx_WFx_ISS_TI to match its ARMv8.7 definition

Signed-off-by: Marc Zyngier <[e-mail]>

Documentation/arm64/cpu-feature-registers.rst

···
      +------------------------------+---------+---------+
      | RPRES                        | [7-4]   |    y    |
      +------------------------------+---------+---------+
+     | WFXT                         | [3-0]   |    y    |
+     +------------------------------+---------+---------+
 
 
 Appendix I: Example

Documentation/arm64/elf_hwcaps.rst

···
 
     Functionality implied by ID_AA64SMFR0_EL1.FA64 == 0b1.
 
+HWCAP2_WFXT
+
+    Functionality implied by ID_AA64ISAR2_EL1.WFXT == 0b0010.
+
 4. Unused AT_HWCAP bits
 -----------------------
 

arch/arm64/include/asm/barrier.h

···
 
 #define sev()		asm volatile("sev" : : : "memory")
 #define wfe()		asm volatile("wfe" : : : "memory")
+#define wfet(val)	asm volatile("msr s0_3_c1_c0_0, %0"	\
+				     : : "r" (val) : "memory")
 #define wfi()		asm volatile("wfi" : : : "memory")
+#define wfit(val)	asm volatile("msr s0_3_c1_c0_1, %0"	\
+				     : : "r" (val) : "memory")
 
 #define isb()		asm volatile("isb" : : : "memory")
 #define dmb(opt)	asm volatile("dmb " #opt : : : "memory")

arch/arm64/include/asm/esr.h

···
 #define ESR_ELx_CV		(UL(1) << 24)
 #define ESR_ELx_COND_SHIFT	(20)
 #define ESR_ELx_COND_MASK	(UL(0xF) << ESR_ELx_COND_SHIFT)
-#define ESR_ELx_WFx_ISS_TI	(UL(1) << 0)
+#define ESR_ELx_WFx_ISS_RN	(UL(0x1F) << 5)
+#define ESR_ELx_WFx_ISS_RV	(UL(1) << 2)
+#define ESR_ELx_WFx_ISS_TI	(UL(3) << 0)
+#define ESR_ELx_WFx_ISS_WFxT	(UL(2) << 0)
 #define ESR_ELx_WFx_ISS_WFI	(UL(0) << 0)
 #define ESR_ELx_WFx_ISS_WFE	(UL(1) << 0)
 #define ESR_ELx_xVC_IMM_MASK	((1UL << 16) - 1)
···
 #define DISR_EL1_ESR_MASK	(ESR_ELx_AET | ESR_ELx_EA | ESR_ELx_FSC)
 
 /* ESR value templates for specific events */
-#define ESR_ELx_WFx_MASK	(ESR_ELx_EC_MASK | ESR_ELx_WFx_ISS_TI)
+#define ESR_ELx_WFx_MASK	(ESR_ELx_EC_MASK |			\
+				 (ESR_ELx_WFx_ISS_TI & ~ESR_ELx_WFx_ISS_WFxT))
 #define ESR_ELx_WFx_WFI_VAL	((ESR_ELx_EC_WFx << ESR_ELx_EC_SHIFT) |	\
 				 ESR_ELx_WFx_ISS_WFI)
 

arch/arm64/include/asm/hwcap.h

···
 #define KERNEL_HWCAP_SME_B16F32		__khwcap2_feature(SME_B16F32)
 #define KERNEL_HWCAP_SME_F32F32		__khwcap2_feature(SME_F32F32)
 #define KERNEL_HWCAP_SME_FA64		__khwcap2_feature(SME_FA64)
+#define KERNEL_HWCAP_WFXT		__khwcap2_feature(WFXT)
 
 /*
  * This yields a mask that user programs can use to figure out what

arch/arm64/include/asm/kvm_host.h

···
 #define KVM_ARM64_FP_FOREIGN_FPSTATE	(1 << 14)
 #define KVM_ARM64_ON_UNSUPPORTED_CPU	(1 << 15) /* Physical CPU not in supported_cpus */
 #define KVM_ARM64_HOST_SME_ENABLED	(1 << 16) /* SME enabled for EL0 */
+#define KVM_ARM64_WFIT			(1 << 17) /* WFIT instruction trapped */
 
 #define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \
 				 KVM_GUESTDBG_USE_SW_BP | \

arch/arm64/include/uapi/asm/hwcap.h

···
 #define HWCAP2_SME_B16F32	(1 << 28)
 #define HWCAP2_SME_F32F32	(1 << 29)
 #define HWCAP2_SME_FA64		(1 << 30)
+#define HWCAP2_WFXT		(1UL << 31)
 
 #endif /* _UAPI__ASM_HWCAP_H */

arch/arm64/kernel/cpufeature.c

···
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH),
 		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_GPA3_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_RPRES_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_WFXT_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
···
 		.cpu_enable = fa64_kernel_enable,
 	},
 #endif /* CONFIG_ARM64_SME */
+	{
+		.desc = "WFx with timeout",
+		.capability = ARM64_HAS_WFXT,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.sys_reg = SYS_ID_AA64ISAR2_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64ISAR2_WFXT_SHIFT,
+		.field_width = 4,
+		.matches = has_cpuid_feature,
+		.min_field_value = ID_AA64ISAR2_WFXT_SUPPORTED,
+	},
 	{},
 };
 
···
 	HWCAP_CAP(SYS_ID_AA64MMFR0_EL1, ID_AA64MMFR0_ECV_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ECV),
 	HWCAP_CAP(SYS_ID_AA64MMFR1_EL1, ID_AA64MMFR1_AFP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AFP),
 	HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_RPRES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RPRES),
+	HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_WFXT_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_WFXT_SUPPORTED, CAP_HWCAP, KERNEL_HWCAP_WFXT),
 #ifdef CONFIG_ARM64_SME
 	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SME_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_SME, CAP_HWCAP, KERNEL_HWCAP_SME),
 	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_FA64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_FA64, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),

arch/arm64/kernel/cpuinfo.c

···
 	[KERNEL_HWCAP_SME_B16F32]	= "smeb16f32",
 	[KERNEL_HWCAP_SME_F32F32]	= "smef32f32",
 	[KERNEL_HWCAP_SME_FA64]		= "smefa64",
+	[KERNEL_HWCAP_WFXT]		= "wfxt",
 };
 
 #ifdef CONFIG_COMPAT

arch/arm64/kvm/arch_timer.c

···
 	return IRQ_HANDLED;
 }
 
-static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx)
+static u64 kvm_counter_compute_delta(struct arch_timer_context *timer_ctx,
+				     u64 val)
 {
-	u64 cval, now;
+	u64 now = kvm_phys_timer_read() - timer_get_offset(timer_ctx);
 
-	cval = timer_get_cval(timer_ctx);
-	now = kvm_phys_timer_read() - timer_get_offset(timer_ctx);
-
-	if (now < cval) {
+	if (now < val) {
 		u64 ns;
 
 		ns = cyclecounter_cyc2ns(timecounter->cc,
-					 cval - now,
+					 val - now,
 					 timecounter->mask,
 					 &timecounter->frac);
 		return ns;
···
 	return 0;
 }
 
+static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx)
+{
+	return kvm_counter_compute_delta(timer_ctx, timer_get_cval(timer_ctx));
+}
+
 static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx)
 {
 	WARN_ON(timer_ctx && timer_ctx->loaded);
 	return timer_ctx &&
 		((timer_get_ctl(timer_ctx) &
 		  (ARCH_TIMER_CTRL_IT_MASK | ARCH_TIMER_CTRL_ENABLE)) == ARCH_TIMER_CTRL_ENABLE);
+}
+
+static bool vcpu_has_wfit_active(struct kvm_vcpu *vcpu)
+{
+	return (cpus_have_final_cap(ARM64_HAS_WFXT) &&
+		(vcpu->arch.flags & KVM_ARM64_WFIT));
+}
+
+static u64 wfit_delay_ns(struct kvm_vcpu *vcpu)
+{
+	struct arch_timer_context *ctx = vcpu_vtimer(vcpu);
+	u64 val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu));
+
+	return kvm_counter_compute_delta(ctx, val);
 }
 
 /*
···
 		if (kvm_timer_irq_can_fire(ctx))
 			min_delta = min(min_delta, kvm_timer_compute_delta(ctx));
 	}
+
+	if (vcpu_has_wfit_active(vcpu))
+		min_delta = min(min_delta, wfit_delay_ns(vcpu));
 
 	/* If none of timers can fire, then return 0 */
 	if (min_delta == ULLONG_MAX)
···
 	return cval <= now;
 }
 
-bool kvm_timer_is_pending(struct kvm_vcpu *vcpu)
+int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
-	struct timer_map map;
-
-	get_timer_map(vcpu, &map);
-
-	return kvm_timer_should_fire(map.direct_vtimer) ||
-	       kvm_timer_should_fire(map.direct_ptimer) ||
-	       kvm_timer_should_fire(map.emul_ptimer);
+	return vcpu_has_wfit_active(vcpu) && wfit_delay_ns(vcpu) == 0;
 }
 
 /*
···
 	 */
 	if (!kvm_timer_irq_can_fire(map.direct_vtimer) &&
 	    !kvm_timer_irq_can_fire(map.direct_ptimer) &&
-	    !kvm_timer_irq_can_fire(map.emul_ptimer))
+	    !kvm_timer_irq_can_fire(map.emul_ptimer) &&
+	    !vcpu_has_wfit_active(vcpu))
 		return;
 
 	/*

arch/arm64/kvm/arm.c

···
 	kvm_arm_vcpu_destroy(vcpu);
 }
 
-int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
-{
-	return kvm_timer_is_pending(vcpu);
-}
-
 void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
 {
 
···
 	preempt_enable();
 
 	kvm_vcpu_halt(vcpu);
+	vcpu->arch.flags &= ~KVM_ARM64_WFIT;
 	kvm_clear_request(KVM_REQ_UNHALT, vcpu);
 
 	preempt_disable();

arch/arm64/kvm/handle_exit.c

···
  *
  * @vcpu:	the vcpu pointer
  *
- * WFE: Yield the CPU and come back to this vcpu when the scheduler
+ * WFE[T]: Yield the CPU and come back to this vcpu when the scheduler
  * decides to.
  * WFI: Simply call kvm_vcpu_halt(), which will halt execution of
  * world-switches and schedule other host processes until there is an
  * incoming IRQ or FIQ to the VM.
+ * WFIT: Same as WFI, with a timed wakeup implemented as a background timer
+ *
+ * WF{I,E}T can immediately return if the deadline has already expired.
  */
 static int kvm_handle_wfx(struct kvm_vcpu *vcpu)
 {
-	if (kvm_vcpu_get_esr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
+	u64 esr = kvm_vcpu_get_esr(vcpu);
+
+	if (esr & ESR_ELx_WFx_ISS_WFE) {
 		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
 		vcpu->stat.wfe_exit_stat++;
-		kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu));
 	} else {
 		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false);
 		vcpu->stat.wfi_exit_stat++;
-		kvm_vcpu_wfi(vcpu);
 	}
 
+	if (esr & ESR_ELx_WFx_ISS_WFxT) {
+		if (esr & ESR_ELx_WFx_ISS_RV) {
+			u64 val, now;
+
+			now = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_TIMER_CNT);
+			val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu));
+
+			if (now >= val)
+				goto out;
+		} else {
+			/* Treat WFxT as WFx if RN is invalid */
+			esr &= ~ESR_ELx_WFx_ISS_WFxT;
+		}
+	}
+
+	if (esr & ESR_ELx_WFx_ISS_WFE) {
+		kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu));
+	} else {
+		if (esr & ESR_ELx_WFx_ISS_WFxT)
+			vcpu->arch.flags |= KVM_ARM64_WFIT;
+
+		kvm_vcpu_wfi(vcpu);
+	}
+out:
 	kvm_incr_pc(vcpu);
 
 	return 1;

arch/arm64/kvm/sys_regs.c

···
 		if (!vcpu_has_ptrauth(vcpu))
 			val &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR2_APA3) |
 				 ARM64_FEATURE_MASK(ID_AA64ISAR2_GPA3));
+		if (!cpus_have_final_cap(ARM64_HAS_WFXT))
+			val &= ~ARM64_FEATURE_MASK(ID_AA64ISAR2_WFXT);
 		break;
 	case SYS_ID_AA64DFR0_EL1:
 		/* Limit debug to ARMv8.0 */

arch/arm64/lib/delay.c

···
 {
 	cycles_t start = get_cycles();
 
-	if (arch_timer_evtstrm_available()) {
+	if (cpus_have_const_cap(ARM64_HAS_WFXT)) {
+		u64 end = start + cycles;
+
+		/*
+		 * Start with WFIT. If an interrupt makes us resume
+		 * early, use a WFET loop to complete the delay.
+		 */
+		wfit(end);
+		while ((get_cycles() - start) < cycles)
+			wfet(end);
+	} else 	if (arch_timer_evtstrm_available()) {
 		const cycles_t timer_evt_period =
 			USECS_TO_CYCLES(ARCH_TIMER_EVT_STREAM_PERIOD_US);
 

arch/arm64/tools/cpucaps

···
 HAS_SYSREG_GIC_CPUIF
 HAS_TLB_RANGE
 HAS_VIRT_HOST_EXTN
+HAS_WFXT
 HW_DBM
 KVM_PROTECTED_MODE
 MISMATCHED_CACHE_TYPE

include/kvm/arm_arch_timer.h

···
 int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr);
 int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr);
 
-bool kvm_timer_is_pending(struct kvm_vcpu *vcpu);
-
 u64 kvm_phys_timer_read(void);
 
 void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu);