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

* kvm-arm64/fpmr:
  : .
  : Add FP8 support to the KVM/arm64 floating point handling.
  :
  : This includes new ID registers (ID_AA64PFR2_EL1 ID_AA64FPFR0_EL1)
  : being made visible to guests, as well as a new confrol register
  : (FPMR) which gets context-switched.
  : .
  KVM: arm64: Expose ID_AA64PFR2_EL1 to userspace and guests
  KVM: arm64: Enable FP8 support when available and configured
  KVM: arm64: Expose ID_AA64FPFR0_EL1 as a writable ID reg
  KVM: arm64: Honor trap routing for FPMR
  KVM: arm64: Add save/restore support for FPMR
  KVM: arm64: Move FPMR into the sysreg array
  KVM: arm64: Add predicate for FPMR support in a VM
  KVM: arm64: Move SVCR into the sysreg array
Signed-off-by: Marc Zyngier <maz@kernel.org>

arch/arm64/include/asm/kvm_host.h

@@ -446,6 +446,10 @@ enum vcpu_sysreg {
 	GCR_EL1,	/* Tag Control Register */
 	TFSRE0_EL1,	/* Tag Fault Status Register (EL0) */
 
+	/* FP/SIMD/SVE */
+	SVCR,
+	FPMR,
+
 	/* 32bit specific registers. */
 	DACR32_EL2,	/* Domain Access Control Register */
 	IFSR32_EL2,	/* Instruction Fault Status Register */
@@ -595,6 +599,16 @@ struct kvm_host_data {
 		struct cpu_sve_state *sve_state;
 	};
 
+	union {
+		/* HYP VA pointer to the host storage for FPMR */
+		u64	*fpmr_ptr;
+		/*
+		 * Used by pKVM only, as it needs to provide storage
+		 * for the host
+		 */
+		u64	fpmr;
+	};
+
 	/* Ownership of the FP regs */
 	enum {
 		FP_STATE_FREE,
@@ -664,8 +678,6 @@ struct kvm_vcpu_arch {
 	void *sve_state;
 	enum fp_type fp_type;
 	unsigned int sve_max_vl;
-	u64 svcr;
-	u64 fpmr;
 
 	/* Stage 2 paging state used by the hardware on next switch */
 	struct kvm_s2_mmu *hw_mmu;
@@ -1473,4 +1485,8 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val);
 		(pa + pi + pa3) == 1;					\
 	})
 
+#define kvm_has_fpmr(k)					\
+	(system_supports_fpmr() &&			\
+	 kvm_has_feat((k), ID_AA64PFR2_EL1, FPMR, IMP))
+
 #endif /* __ARM64_KVM_HOST_H__ */

arch/arm64/kvm/emulate-nested.c

@@ -83,6 +83,7 @@ enum cgt_group_id {
 	CGT_CPTR_TAM,
 	CGT_CPTR_TCPAC,
 
+	CGT_HCRX_EnFPM,
 	CGT_HCRX_TCR2En,
 
 	/*
@@ -372,6 +373,12 @@ static const struct trap_bits coarse_trap_bits[] = {
 		.mask		= CPTR_EL2_TCPAC,
 		.behaviour	= BEHAVE_FORWARD_ANY,
 	},
+	[CGT_HCRX_EnFPM] = {
+		.index		= HCRX_EL2,
+		.value 		= 0,
+		.mask		= HCRX_EL2_EnFPM,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
 	[CGT_HCRX_TCR2En] = {
 		.index		= HCRX_EL2,
 		.value 		= 0,
@@ -1108,6 +1115,7 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
 	SR_TRAP(SYS_CNTP_CTL_EL0,	CGT_CNTHCTL_EL1PTEN),
 	SR_TRAP(SYS_CNTPCT_EL0,		CGT_CNTHCTL_EL1PCTEN),
 	SR_TRAP(SYS_CNTPCTSS_EL0,	CGT_CNTHCTL_EL1PCTEN),
+	SR_TRAP(SYS_FPMR,		CGT_HCRX_EnFPM),
 };
 
 static DEFINE_XARRAY(sr_forward_xa);

arch/arm64/kvm/fpsimd.c

@@ -63,6 +63,7 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 	 */
 	*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
 	*host_data_ptr(fpsimd_state) = kern_hyp_va(&current->thread.uw.fpsimd_state);
+	*host_data_ptr(fpmr_ptr) = kern_hyp_va(&current->thread.uw.fpmr);
 
 	vcpu_clear_flag(vcpu, HOST_SVE_ENABLED);
 	if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN)
@@ -134,8 +135,8 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
 		fp_state.sve_state = vcpu->arch.sve_state;
 		fp_state.sve_vl = vcpu->arch.sve_max_vl;
 		fp_state.sme_state = NULL;
-		fp_state.svcr = &vcpu->arch.svcr;
-		fp_state.fpmr = &vcpu->arch.fpmr;
+		fp_state.svcr = &__vcpu_sys_reg(vcpu, SVCR);
+		fp_state.fpmr = &__vcpu_sys_reg(vcpu, FPMR);
 		fp_state.fp_type = &vcpu->arch.fp_type;
 
 		if (vcpu_has_sve(vcpu))

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

@@ -403,6 +403,9 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 	else
 		__fpsimd_restore_state(&vcpu->arch.ctxt.fp_regs);
 
+	if (kvm_has_fpmr(kern_hyp_va(vcpu->kvm)))
+		write_sysreg_s(__vcpu_sys_reg(vcpu, FPMR), SYS_FPMR);
+
 	/* Skip restoring fpexc32 for AArch64 guests */
 	if (!(read_sysreg(hcr_el2) & HCR_RW))
 		write_sysreg(__vcpu_sys_reg(vcpu, FPEXC32_EL2), fpexc32_el2);

arch/arm64/kvm/hyp/nvhe/hyp-main.c

@@ -62,6 +62,8 @@ static void fpsimd_sve_flush(void)
 
 static void fpsimd_sve_sync(struct kvm_vcpu *vcpu)
 {
+	bool has_fpmr;
+
 	if (!guest_owns_fp_regs())
 		return;
 
@@ -73,11 +75,18 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu)
 	else
 		__fpsimd_save_state(&vcpu->arch.ctxt.fp_regs);
 
+	has_fpmr = kvm_has_fpmr(kern_hyp_va(vcpu->kvm));
+	if (has_fpmr)
+		__vcpu_sys_reg(vcpu, FPMR) = read_sysreg_s(SYS_FPMR);
+
 	if (system_supports_sve())
 		__hyp_sve_restore_host();
 	else
 		__fpsimd_restore_state(*host_data_ptr(fpsimd_state));
 
+	if (has_fpmr)
+		write_sysreg_s(*host_data_ptr(fpmr), SYS_FPMR);
+
 	*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
 }
 

arch/arm64/kvm/hyp/nvhe/switch.c

@@ -197,6 +197,15 @@ static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
 	} else {
 		__fpsimd_save_state(*host_data_ptr(fpsimd_state));
 	}
+
+	if (kvm_has_fpmr(kern_hyp_va(vcpu->kvm))) {
+		u64 val = read_sysreg_s(SYS_FPMR);
+
+		if (unlikely(is_protected_kvm_enabled()))
+			*host_data_ptr(fpmr) = val;
+		else
+			**host_data_ptr(fpmr_ptr) = val;
+	}
 }
 
 static const exit_handler_fn hyp_exit_handlers[] = {

arch/arm64/kvm/hyp/vhe/switch.c

@@ -312,6 +312,9 @@ static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code)
 static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
 {
 	__fpsimd_save_state(*host_data_ptr(fpsimd_state));
+
+	if (kvm_has_fpmr(vcpu->kvm))
+		**host_data_ptr(fpmr_ptr) = read_sysreg_s(SYS_FPMR);
 }
 
 static bool kvm_hyp_handle_tlbi_el2(struct kvm_vcpu *vcpu, u64 *exit_code)

arch/arm64/kvm/sys_regs.c

@@ -1545,6 +1545,10 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
 
 		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_SME);
 		break;
+	case SYS_ID_AA64PFR2_EL1:
+		/* We only expose FPMR */
+		val &= ID_AA64PFR2_EL1_FPMR;
+		break;
 	case SYS_ID_AA64ISAR1_EL1:
 		if (!vcpu_has_ptrauth(vcpu))
 			val &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_APA) |
@@ -1675,6 +1679,24 @@ static unsigned int sve_visibility(const struct kvm_vcpu *vcpu,
 	return REG_HIDDEN;
 }
 
+static unsigned int sme_visibility(const struct kvm_vcpu *vcpu,
+				   const struct sys_reg_desc *rd)
+{
+	if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SME, IMP))
+		return 0;
+
+	return REG_HIDDEN;
+}
+
+static unsigned int fp8_visibility(const struct kvm_vcpu *vcpu,
+				   const struct sys_reg_desc *rd)
+{
+	if (kvm_has_fpmr(vcpu->kvm))
+		return 0;
+
+	return REG_HIDDEN;
+}
+
 static u64 read_sanitised_id_aa64pfr0_el1(struct kvm_vcpu *vcpu,
 					  const struct sys_reg_desc *rd)
 {
@@ -2369,12 +2391,12 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 		   ID_AA64PFR0_EL1_AdvSIMD |
 		   ID_AA64PFR0_EL1_FP), },
 	ID_SANITISED(ID_AA64PFR1_EL1),
-	ID_UNALLOCATED(4,2),
+	ID_WRITABLE(ID_AA64PFR2_EL1, ID_AA64PFR2_EL1_FPMR),
 	ID_UNALLOCATED(4,3),
 	ID_WRITABLE(ID_AA64ZFR0_EL1, ~ID_AA64ZFR0_EL1_RES0),
 	ID_HIDDEN(ID_AA64SMFR0_EL1),
 	ID_UNALLOCATED(4,6),
-	ID_UNALLOCATED(4,7),
+	ID_WRITABLE(ID_AA64FPFR0_EL1, ~ID_AA64FPFR0_EL1_RES0),
 
 	/* CRm=5 */
 	{ SYS_DESC(SYS_ID_AA64DFR0_EL1),
@@ -2541,7 +2563,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 			     CTR_EL0_IDC_MASK |
 			     CTR_EL0_DminLine_MASK |
 			     CTR_EL0_IminLine_MASK),
-	{ SYS_DESC(SYS_SVCR), undef_access },
+	{ SYS_DESC(SYS_SVCR), undef_access, reset_val, SVCR, 0, .visibility = sme_visibility  },
+	{ SYS_DESC(SYS_FPMR), undef_access, reset_val, FPMR, 0, .visibility = fp8_visibility },
 
 	{ PMU_SYS_REG(PMCR_EL0), .access = access_pmcr, .reset = reset_pmcr,
 	  .reg = PMCR_EL0, .get_user = get_pmcr, .set_user = set_pmcr },
@@ -4566,6 +4589,9 @@ void kvm_calculate_traps(struct kvm_vcpu *vcpu)
 
 		if (kvm_has_feat(kvm, ID_AA64MMFR3_EL1, TCRX, IMP))
 			vcpu->arch.hcrx_el2 |= HCRX_EL2_TCR2En;
+
+		if (kvm_has_fpmr(kvm))
+			vcpu->arch.hcrx_el2 |= HCRX_EL2_EnFPM;
 	}
 
 	if (test_bit(KVM_ARCH_FLAG_FGU_INITIALIZED, &kvm->arch.flags))