Merge branch kvm-arm64/nv-sve into kvmarm/next

* kvm-arm64/nv-sve:
  : CPTR_EL2, FPSIMD/SVE support for nested
  :
  : This series brings support for honoring the guest hypervisor's CPTR_EL2
  : trap configuration when running a nested guest, along with support for
  : FPSIMD/SVE usage at L1 and L2.
  KVM: arm64: Allow the use of SVE+NV
  KVM: arm64: nv: Add additional trap setup for CPTR_EL2
  KVM: arm64: nv: Add trap description for CPTR_EL2
  KVM: arm64: nv: Add TCPAC/TTA to CPTR->CPACR conversion helper
  KVM: arm64: nv: Honor guest hypervisor's FP/SVE traps in CPTR_EL2
  KVM: arm64: nv: Load guest FP state for ZCR_EL2 trap
  KVM: arm64: nv: Handle CPACR_EL1 traps
  KVM: arm64: Spin off helper for programming CPTR traps
  KVM: arm64: nv: Ensure correct VL is loaded before saving SVE state
  KVM: arm64: nv: Use guest hypervisor's max VL when running nested guest
  KVM: arm64: nv: Save guest's ZCR_EL2 when in hyp context
  KVM: arm64: nv: Load guest hyp's ZCR into EL1 state
  KVM: arm64: nv: Handle ZCR_EL2 traps
  KVM: arm64: nv: Forward SVE traps to guest hypervisor
  KVM: arm64: nv: Forward FP/ASIMD traps to guest hypervisor

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

Author: oupton

arch/arm64/include/asm/kvm_emulate.h

@@ -11,6 +11,7 @@
 #ifndef __ARM64_KVM_EMULATE_H__
 #define __ARM64_KVM_EMULATE_H__
 
+#include <linux/bitfield.h>
 #include <linux/kvm_host.h>
 
 #include <asm/debug-monitors.h>
@@ -55,6 +56,14 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu);
 int kvm_inject_nested_sync(struct kvm_vcpu *vcpu, u64 esr_el2);
 int kvm_inject_nested_irq(struct kvm_vcpu *vcpu);
 
+static inline void kvm_inject_nested_sve_trap(struct kvm_vcpu *vcpu)
+{
+	u64 esr = FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_SVE) |
+		  ESR_ELx_IL;
+
+	kvm_inject_nested_sync(vcpu, esr);
+}
+
 #if defined(__KVM_VHE_HYPERVISOR__) || defined(__KVM_NVHE_HYPERVISOR__)
 static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 {
@@ -638,4 +647,50 @@ static __always_inline void kvm_reset_cptr_el2(struct kvm_vcpu *vcpu)
 
 	kvm_write_cptr_el2(val);
 }
+
+/*
+ * Returns a 'sanitised' view of CPTR_EL2, translating from nVHE to the VHE
+ * format if E2H isn't set.
+ */
+static inline u64 vcpu_sanitised_cptr_el2(const struct kvm_vcpu *vcpu)
+{
+	u64 cptr = __vcpu_sys_reg(vcpu, CPTR_EL2);
+
+	if (!vcpu_el2_e2h_is_set(vcpu))
+		cptr = translate_cptr_el2_to_cpacr_el1(cptr);
+
+	return cptr;
+}
+
+static inline bool ____cptr_xen_trap_enabled(const struct kvm_vcpu *vcpu,
+					     unsigned int xen)
+{
+	switch (xen) {
+	case 0b00:
+	case 0b10:
+		return true;
+	case 0b01:
+		return vcpu_el2_tge_is_set(vcpu) && !vcpu_is_el2(vcpu);
+	case 0b11:
+	default:
+		return false;
+	}
+}
+
+#define __guest_hyp_cptr_xen_trap_enabled(vcpu, xen)				\
+	(!vcpu_has_nv(vcpu) ? false :						\
+	 ____cptr_xen_trap_enabled(vcpu,					\
+				   SYS_FIELD_GET(CPACR_ELx, xen,		\
+						 vcpu_sanitised_cptr_el2(vcpu))))
+
+static inline bool guest_hyp_fpsimd_traps_enabled(const struct kvm_vcpu *vcpu)
+{
+	return __guest_hyp_cptr_xen_trap_enabled(vcpu, FPEN);
+}
+
+static inline bool guest_hyp_sve_traps_enabled(const struct kvm_vcpu *vcpu)
+{
+	return __guest_hyp_cptr_xen_trap_enabled(vcpu, ZEN);
+}
+
 #endif /* __ARM64_KVM_EMULATE_H__ */

arch/arm64/include/asm/kvm_host.h

@@ -458,6 +458,7 @@ enum vcpu_sysreg {
 	MDCR_EL2,	/* Monitor Debug Configuration Register (EL2) */
 	CPTR_EL2,	/* Architectural Feature Trap Register (EL2) */
 	HACR_EL2,	/* Hypervisor Auxiliary Control Register */
+	ZCR_EL2,	/* SVE Control Register (EL2) */
 	TTBR0_EL2,	/* Translation Table Base Register 0 (EL2) */
 	TTBR1_EL2,	/* Translation Table Base Register 1 (EL2) */
 	TCR_EL2,	/* Translation Control Register (EL2) */
@@ -902,6 +903,9 @@ struct kvm_vcpu_arch {
 
 #define vcpu_sve_max_vq(vcpu)	sve_vq_from_vl((vcpu)->arch.sve_max_vl)
 
+#define vcpu_sve_zcr_elx(vcpu)						\
+	(unlikely(is_hyp_ctxt(vcpu)) ? ZCR_EL2 : ZCR_EL1)
+
 #define vcpu_sve_state_size(vcpu) ({					\
 	size_t __size_ret;						\
 	unsigned int __vcpu_vq;						\
@@ -1026,6 +1030,7 @@ static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
 	case DACR32_EL2:	*val = read_sysreg_s(SYS_DACR32_EL2);	break;
 	case IFSR32_EL2:	*val = read_sysreg_s(SYS_IFSR32_EL2);	break;
 	case DBGVCR32_EL2:	*val = read_sysreg_s(SYS_DBGVCR32_EL2);	break;
+	case ZCR_EL1:		*val = read_sysreg_s(SYS_ZCR_EL12);	break;
 	default:		return false;
 	}
 
@@ -1071,6 +1076,7 @@ static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
 	case DACR32_EL2:	write_sysreg_s(val, SYS_DACR32_EL2);	break;
 	case IFSR32_EL2:	write_sysreg_s(val, SYS_IFSR32_EL2);	break;
 	case DBGVCR32_EL2:	write_sysreg_s(val, SYS_DBGVCR32_EL2);	break;
+	case ZCR_EL1:		write_sysreg_s(val, SYS_ZCR_EL12);	break;
 	default:		return false;
 	}
 

arch/arm64/include/asm/kvm_nested.h

@@ -33,7 +33,7 @@ static inline u64 translate_tcr_el2_to_tcr_el1(u64 tcr)
 
 static inline u64 translate_cptr_el2_to_cpacr_el1(u64 cptr_el2)
 {
-	u64 cpacr_el1 = 0;
+	u64 cpacr_el1 = CPACR_ELx_RES1;
 
 	if (cptr_el2 & CPTR_EL2_TTA)
 		cpacr_el1 |= CPACR_ELx_TTA;
@@ -42,6 +42,8 @@ static inline u64 translate_cptr_el2_to_cpacr_el1(u64 cptr_el2)
 	if (!(cptr_el2 & CPTR_EL2_TZ))
 		cpacr_el1 |= CPACR_ELx_ZEN;
 
+	cpacr_el1 |= cptr_el2 & (CPTR_EL2_TCPAC | CPTR_EL2_TAM);
+
 	return cpacr_el1;
 }
 

arch/arm64/kvm/arm.c

@@ -1458,11 +1458,6 @@ static int kvm_vcpu_init_check_features(struct kvm_vcpu *vcpu,
 	    test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, &features))
 		return -EINVAL;
 
-	/* Disallow NV+SVE for the time being */
-	if (test_bit(KVM_ARM_VCPU_HAS_EL2, &features) &&
-	    test_bit(KVM_ARM_VCPU_SVE, &features))
-		return -EINVAL;
-
 	if (!test_bit(KVM_ARM_VCPU_EL1_32BIT, &features))
 		return 0;
 

arch/arm64/kvm/emulate-nested.c

@@ -79,6 +79,10 @@ enum cgt_group_id {
 	CGT_MDCR_E2TB,
 	CGT_MDCR_TDCC,
 
+	CGT_CPACR_E0POE,
+	CGT_CPTR_TAM,
+	CGT_CPTR_TCPAC,
+
 	/*
 	 * Anything after this point is a combination of coarse trap
 	 * controls, which must all be evaluated to decide what to do.
@@ -106,6 +110,8 @@ enum cgt_group_id {
 	CGT_CNTHCTL_EL1PCTEN = __COMPLEX_CONDITIONS__,
 	CGT_CNTHCTL_EL1PTEN,
 
+	CGT_CPTR_TTA,
+
 	/* Must be last */
 	__NR_CGT_GROUP_IDS__
 };
@@ -345,6 +351,24 @@ static const struct trap_bits coarse_trap_bits[] = {
 		.mask		= MDCR_EL2_TDCC,
 		.behaviour	= BEHAVE_FORWARD_ANY,
 	},
+	[CGT_CPACR_E0POE] = {
+		.index		= CPTR_EL2,
+		.value		= CPACR_ELx_E0POE,
+		.mask		= CPACR_ELx_E0POE,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_CPTR_TAM] = {
+		.index		= CPTR_EL2,
+		.value		= CPTR_EL2_TAM,
+		.mask		= CPTR_EL2_TAM,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_CPTR_TCPAC] = {
+		.index		= CPTR_EL2,
+		.value		= CPTR_EL2_TCPAC,
+		.mask		= CPTR_EL2_TCPAC,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
 };
 
 #define MCB(id, ...)						\
@@ -410,12 +434,26 @@ static enum trap_behaviour check_cnthctl_el1pten(struct kvm_vcpu *vcpu)
 	return BEHAVE_FORWARD_ANY;
 }
 
+static enum trap_behaviour check_cptr_tta(struct kvm_vcpu *vcpu)
+{
+	u64 val = __vcpu_sys_reg(vcpu, CPTR_EL2);
+
+	if (!vcpu_el2_e2h_is_set(vcpu))
+		val = translate_cptr_el2_to_cpacr_el1(val);
+
+	if (val & CPACR_ELx_TTA)
+		return BEHAVE_FORWARD_ANY;
+
+	return BEHAVE_HANDLE_LOCALLY;
+}
+
 #define CCC(id, fn)				\
 	[id - __COMPLEX_CONDITIONS__] = fn
 
 static const complex_condition_check ccc[] = {
 	CCC(CGT_CNTHCTL_EL1PCTEN, check_cnthctl_el1pcten),
 	CCC(CGT_CNTHCTL_EL1PTEN, check_cnthctl_el1pten),
+	CCC(CGT_CPTR_TTA, check_cptr_tta),
 };
 
 /*
@@ -1000,6 +1038,59 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
 	SR_TRAP(SYS_TRBPTR_EL1, 	CGT_MDCR_E2TB),
 	SR_TRAP(SYS_TRBSR_EL1, 		CGT_MDCR_E2TB),
 	SR_TRAP(SYS_TRBTRG_EL1,		CGT_MDCR_E2TB),
+	SR_TRAP(SYS_CPACR_EL1,		CGT_CPTR_TCPAC),
+	SR_TRAP(SYS_AMUSERENR_EL0,	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCFGR_EL0,		CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCGCR_EL0,		CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCNTENCLR0_EL0,	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCNTENCLR1_EL0,	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCNTENSET0_EL0,	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCNTENSET1_EL0,	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCR_EL0,		CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR0_EL0(0),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR0_EL0(1),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR0_EL0(2),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR0_EL0(3),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(0),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(1),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(2),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(3),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(4),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(5),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(6),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(7),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(8),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(9),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(10),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(11),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(12),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(13),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(14),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(15),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER0_EL0(0),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER0_EL0(1),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER0_EL0(2),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER0_EL0(3),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(0),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(1),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(2),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(3),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(4),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(5),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(6),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(7),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(8),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(9),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(10),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(11),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(12),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(13),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(14),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(15),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_POR_EL0,		CGT_CPACR_E0POE),
+	/* op0=2, op1=1, and CRn<0b1000 */
+	SR_RANGE_TRAP(sys_reg(2, 1, 0, 0, 0),
+		      sys_reg(2, 1, 7, 15, 7), CGT_CPTR_TTA),
 	SR_TRAP(SYS_CNTP_TVAL_EL0,	CGT_CNTHCTL_EL1PTEN),
 	SR_TRAP(SYS_CNTP_CVAL_EL0,	CGT_CNTHCTL_EL1PTEN),
 	SR_TRAP(SYS_CNTP_CTL_EL0,	CGT_CNTHCTL_EL1PTEN),

arch/arm64/kvm/fpsimd.c

@@ -178,7 +178,13 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 
 	if (guest_owns_fp_regs()) {
 		if (vcpu_has_sve(vcpu)) {
-			__vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR);
+			u64 zcr = read_sysreg_el1(SYS_ZCR);
+
+			/*
+			 * If the vCPU is in the hyp context then ZCR_EL1 is
+			 * loaded with its vEL2 counterpart.
+			 */
+			__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr;
 
 			/*
 			 * Restore the VL that was saved when bound to the CPU,
@@ -189,11 +195,14 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 			 * Note that this means that at guest exit ZCR_EL1 is
 			 * not necessarily the same as on guest entry.
 			 *
-			 * Restoring the VL isn't needed in VHE mode since
-			 * ZCR_EL2 (accessed via ZCR_EL1) would fulfill the same
-			 * role when doing the save from EL2.
+			 * ZCR_EL2 holds the guest hypervisor's VL when running
+			 * a nested guest, which could be smaller than the
+			 * max for the vCPU. Similar to above, we first need to
+			 * switch to a VL consistent with the layout of the
+			 * vCPU's SVE state. KVM support for NV implies VHE, so
+			 * using the ZCR_EL1 alias is safe.
 			 */
-			if (!has_vhe())
+			if (!has_vhe() || (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)))
 				sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1,
 						       SYS_ZCR_EL1);
 		}

arch/arm64/kvm/handle_exit.c

@@ -94,11 +94,19 @@ static int handle_smc(struct kvm_vcpu *vcpu)
 }
 
 /*
- * Guest access to FP/ASIMD registers are routed to this handler only
- * when the system doesn't support FP/ASIMD.
+ * This handles the cases where the system does not support FP/ASIMD or when
+ * we are running nested virtualization and the guest hypervisor is trapping
+ * FP/ASIMD accesses by its guest guest.
+ *
+ * All other handling of guest vs. host FP/ASIMD register state is handled in
+ * fixup_guest_exit().
  */
-static int handle_no_fpsimd(struct kvm_vcpu *vcpu)
+static int kvm_handle_fpasimd(struct kvm_vcpu *vcpu)
 {
+	if (guest_hyp_fpsimd_traps_enabled(vcpu))
+		return kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+
+	/* This is the case when the system doesn't support FP/ASIMD. */
 	kvm_inject_undefined(vcpu);
 	return 1;
 }
@@ -209,6 +217,9 @@ static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu)
  */
 static int handle_sve(struct kvm_vcpu *vcpu)
 {
+	if (guest_hyp_sve_traps_enabled(vcpu))
+		return kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+
 	kvm_inject_undefined(vcpu);
 	return 1;
 }
@@ -304,7 +315,7 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[ESR_ELx_EC_BREAKPT_LOW]= kvm_handle_guest_debug,
 	[ESR_ELx_EC_BKPT32]	= kvm_handle_guest_debug,
 	[ESR_ELx_EC_BRK64]	= kvm_handle_guest_debug,
-	[ESR_ELx_EC_FP_ASIMD]	= handle_no_fpsimd,
+	[ESR_ELx_EC_FP_ASIMD]	= kvm_handle_fpasimd,
 	[ESR_ELx_EC_PAC]	= kvm_handle_ptrauth,
 };
 

arch/arm64/kvm/hyp/include/hyp/switch.h

@@ -314,11 +314,24 @@ static bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code)
 
 static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * The vCPU's saved SVE state layout always matches the max VL of the
+	 * vCPU. Start off with the max VL so we can load the SVE state.
+	 */
 	sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2);
 	__sve_restore_state(vcpu_sve_pffr(vcpu),
 			    &vcpu->arch.ctxt.fp_regs.fpsr,
 			    true);
-	write_sysreg_el1(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR);
+
+	/*
+	 * The effective VL for a VM could differ from the max VL when running a
+	 * nested guest, as the guest hypervisor could select a smaller VL. Slap
+	 * that into hardware before wrapping up.
+	 */
+	if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))
+		sve_cond_update_zcr_vq(__vcpu_sys_reg(vcpu, ZCR_EL2), SYS_ZCR_EL2);
+
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)), SYS_ZCR);
 }
 
 static inline void __hyp_sve_save_host(void)
@@ -354,10 +367,19 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 	/* Only handle traps the vCPU can support here: */
 	switch (esr_ec) {
 	case ESR_ELx_EC_FP_ASIMD:
+		/* Forward traps to the guest hypervisor as required */
+		if (guest_hyp_fpsimd_traps_enabled(vcpu))
+			return false;
 		break;
+	case ESR_ELx_EC_SYS64:
+		if (WARN_ON_ONCE(!is_hyp_ctxt(vcpu)))
+			return false;
+		fallthrough;
 	case ESR_ELx_EC_SVE:
 		if (!sve_guest)
 			return false;
+		if (guest_hyp_sve_traps_enabled(vcpu))
+			return false;
 		break;
 	default:
 		return false;