KVM: arm64: Prefix patches for NV support

index 35a159d131b5..8919e971abdf 100644
@@ -60,9 +60,14 @@
 enum kvm_mode {
 	KVM_MODE_DEFAULT,
 	KVM_MODE_PROTECTED,
+	KVM_MODE_NV,
 	KVM_MODE_NONE,
 };
+#ifdef CONFIG_KVM
 enum kvm_mode kvm_get_mode(void);
+#else
+static inline enum kvm_mode kvm_get_mode(void) { return KVM_MODE_NONE; };
+#endif
 
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 

index a77315b338e6..3fc14ee86239 100644
@@ -1956,6 +1956,20 @@ static void cpu_copy_el2regs(const struct arm64_cpu_capabilities *__unused)
 		write_sysreg(read_sysreg(tpidr_el1), tpidr_el2);
 }
 
+static bool has_nested_virt_support(const struct arm64_cpu_capabilities *cap,
+				    int scope)
+{
+	if (kvm_get_mode() != KVM_MODE_NV)
+		return false;
+
+	if (!has_cpuid_feature(cap, scope)) {
+		pr_warn("unavailable: %s\n", cap->desc);
+		return false;
+	}
+
+	return true;
+}
+
 #ifdef CONFIG_ARM64_PAN
 static void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused)
 {

@@ -2215,6 +2229,17 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = runs_at_el2,
 		.cpu_enable = cpu_copy_el2regs,
 	},
+	{
+		.desc = "Nested Virtualization Support",
+		.capability = ARM64_HAS_NESTED_VIRT,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_nested_virt_support,
+		.sys_reg = SYS_ID_AA64MMFR2_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64MMFR2_EL1_NV_SHIFT,
+		.field_width = 4,
+		.min_field_value = ID_AA64MMFR2_EL1_NV_IMP,
+	},
 	{
 		.capability = ARM64_HAS_32BIT_EL0_DO_NOT_USE,
 		.type = ARM64_CPUCAP_SYSTEM_FEATURE,

index 9c5573bc4614..3fd8f37830f2 100644
@@ -2310,6 +2310,11 @@ static int __init early_kvm_mode_cfg(char *arg)
 		return 0;
 	}
 
+	if (strcmp(arg, "nested") == 0 && !WARN_ON(!is_kernel_in_hyp_mode())) {
+		kvm_mode = KVM_MODE_NV;
+		return 0;
+	}
+
 	return -EINVAL;
 }
 early_param("kvm-arm.mode", early_kvm_mode_cfg);

index a3ee3b605c9b..892d6a5fb2f5 100644
@@ -46,16 +46,17 @@ static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end)
  * long will also starve other vCPUs. We have to also make sure that the page
  * tables are not freed while we released the lock.
  */
-static int stage2_apply_range(struct kvm *kvm, phys_addr_t addr,
+static int stage2_apply_range(struct kvm_s2_mmu *mmu, phys_addr_t addr,
 			      phys_addr_t end,
 			      int (*fn)(struct kvm_pgtable *, u64, u64),
 			      bool resched)
 {
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
 	int ret;
 	u64 next;
 
 	do {
-		struct kvm_pgtable *pgt = kvm->arch.mmu.pgt;
+		struct kvm_pgtable *pgt = mmu->pgt;
 		if (!pgt)
 			return -EINVAL;
 

@@ -71,8 +72,8 @@ static int stage2_apply_range(struct kvm *kvm, phys_addr_t addr,
 	return ret;
 }
 
-#define stage2_apply_range_resched(kvm, addr, end, fn)			\
-	stage2_apply_range(kvm, addr, end, fn, true)
+#define stage2_apply_range_resched(mmu, addr, end, fn)			\
+	stage2_apply_range(mmu, addr, end, fn, true)
 
 static bool memslot_is_logging(struct kvm_memory_slot *memslot)
 {

@@ -235,7 +236,7 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
 	WARN_ON(size & ~PAGE_MASK);
-	WARN_ON(stage2_apply_range(kvm, start, end, kvm_pgtable_stage2_unmap,
+	WARN_ON(stage2_apply_range(mmu, start, end, kvm_pgtable_stage2_unmap,
 				   may_block));
 }
 

@@ -250,7 +251,7 @@ static void stage2_flush_memslot(struct kvm *kvm,
 	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
 	phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
 
-	stage2_apply_range_resched(kvm, addr, end, kvm_pgtable_stage2_flush);
+	stage2_apply_range_resched(&kvm->arch.mmu, addr, end, kvm_pgtable_stage2_flush);
 }
 
 /**

@@ -934,8 +935,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
  */
 static void stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
 {
-	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
-	stage2_apply_range_resched(kvm, addr, end, kvm_pgtable_stage2_wrprotect);
+	stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_wrprotect);
 }
 
 /**

new file mode 100644
index 000000000000..fd601ea68d13
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ARM64_KVM_NESTED_H
+#define __ARM64_KVM_NESTED_H
+
+#include <linux/kvm_host.h>
+
+static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu)
+{
+	return (!__is_defined(__KVM_NVHE_HYPERVISOR__) &&
+		cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) &&
+		test_bit(KVM_ARM_VCPU_HAS_EL2, vcpu->arch.features));
+}
+
+#endif /* __ARM64_KVM_NESTED_H */

index a7a857f1784d..f8129c624b07 100644
@@ -109,6 +109,7 @@ struct kvm_regs {
 #define KVM_ARM_VCPU_SVE		4 /* enable SVE for this CPU */
 #define KVM_ARM_VCPU_PTRAUTH_ADDRESS	5 /* VCPU uses address authentication */
 #define KVM_ARM_VCPU_PTRAUTH_GENERIC	6 /* VCPU uses generic authentication */
+#define KVM_ARM_VCPU_HAS_EL2		7 /* Support nested virtualization */
 
 struct kvm_vcpu_init {
 	__u32 target;

index e0267f672b8a..d061dcc21578 100644
@@ -27,6 +27,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_mmu.h>
+#include <asm/kvm_nested.h>
 #include <asm/virt.h>
 
 /* Maximum phys_shift supported for any VM on this host */

@@ -38,6 +39,9 @@ static u32 kvm_ipa_limit;
 #define VCPU_RESET_PSTATE_EL1	(PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT | \
 				 PSR_F_BIT | PSR_D_BIT)
 
+#define VCPU_RESET_PSTATE_EL2	(PSR_MODE_EL2h | PSR_A_BIT | PSR_I_BIT | \
+				 PSR_F_BIT | PSR_D_BIT)
+
 #define VCPU_RESET_PSTATE_SVC	(PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \
 				 PSR_AA32_I_BIT | PSR_AA32_F_BIT)
 

@@ -220,6 +224,10 @@ static int kvm_set_vm_width(struct kvm_vcpu *vcpu)
 	if (kvm_has_mte(kvm) && is32bit)
 		return -EINVAL;
 
+	/* NV is incompatible with AArch32 */
+	if (vcpu_has_nv(vcpu) && is32bit)
+		return -EINVAL;
+
 	if (is32bit)
 		set_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags);
 

@@ -272,6 +280,12 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	if (loaded)
 		kvm_arch_vcpu_put(vcpu);
 
+	/* Disallow NV+SVE for the time being */
+	if (vcpu_has_nv(vcpu) && vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	if (!kvm_arm_vcpu_sve_finalized(vcpu)) {
 		if (test_bit(KVM_ARM_VCPU_SVE, vcpu->arch.features)) {
 			ret = kvm_vcpu_enable_sve(vcpu);

@@ -294,6 +308,8 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	default:
 		if (vcpu_el1_is_32bit(vcpu)) {
 			pstate = VCPU_RESET_PSTATE_SVC;
+		} else if (vcpu_has_nv(vcpu)) {
+			pstate = VCPU_RESET_PSTATE_EL2;
 		} else {
 			pstate = VCPU_RESET_PSTATE_EL1;
 		}

index 5626ddb540ce..63643c98e6c3 100644
@@ -24,6 +24,7 @@
 #include <asm/fpsimd.h>
 #include <asm/kvm.h>
 #include <asm/kvm_emulate.h>
+#include <asm/kvm_nested.h>
 #include <asm/sigcontext.h>
 
 #include "trace.h"

@@ -253,6 +254,11 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 			if (!vcpu_el1_is_32bit(vcpu))
 				return -EINVAL;
 			break;
+		case PSR_MODE_EL2h:
+		case PSR_MODE_EL2t:
+			if (!vcpu_has_nv(vcpu))
+				return -EINVAL;
+			fallthrough;
 		case PSR_MODE_EL0t:
 		case PSR_MODE_EL1t:
 		case PSR_MODE_EL1h:

index 8919e971abdf..f53473071bcb 100644
@@ -325,12 +325,43 @@ enum vcpu_sysreg {
 	TFSR_EL1,	/* Tag Fault Status Register (EL1) */
 	TFSRE0_EL1,	/* Tag Fault Status Register (EL0) */
 
-	/* 32bit specific registers. Keep them at the end of the range */
+	/* 32bit specific registers. */
 	DACR32_EL2,	/* Domain Access Control Register */
 	IFSR32_EL2,	/* Instruction Fault Status Register */
 	FPEXC32_EL2,	/* Floating-Point Exception Control Register */
 	DBGVCR32_EL2,	/* Debug Vector Catch Register */
 
+	/* EL2 registers */
+	VPIDR_EL2,	/* Virtualization Processor ID Register */
+	VMPIDR_EL2,	/* Virtualization Multiprocessor ID Register */
+	SCTLR_EL2,	/* System Control Register (EL2) */
+	ACTLR_EL2,	/* Auxiliary Control Register (EL2) */
+	HCR_EL2,	/* Hypervisor Configuration Register */
+	MDCR_EL2,	/* Monitor Debug Configuration Register (EL2) */
+	CPTR_EL2,	/* Architectural Feature Trap Register (EL2) */
+	HSTR_EL2,	/* Hypervisor System Trap Register */
+	HACR_EL2,	/* Hypervisor Auxiliary Control Register */
+	TTBR0_EL2,	/* Translation Table Base Register 0 (EL2) */
+	TTBR1_EL2,	/* Translation Table Base Register 1 (EL2) */
+	TCR_EL2,	/* Translation Control Register (EL2) */
+	VTTBR_EL2,	/* Virtualization Translation Table Base Register */
+	VTCR_EL2,	/* Virtualization Translation Control Register */
+	SPSR_EL2,	/* EL2 saved program status register */
+	ELR_EL2,	/* EL2 exception link register */
+	AFSR0_EL2,	/* Auxiliary Fault Status Register 0 (EL2) */
+	AFSR1_EL2,	/* Auxiliary Fault Status Register 1 (EL2) */
+	ESR_EL2,	/* Exception Syndrome Register (EL2) */
+	FAR_EL2,	/* Fault Address Register (EL2) */
+	HPFAR_EL2,	/* Hypervisor IPA Fault Address Register */
+	MAIR_EL2,	/* Memory Attribute Indirection Register (EL2) */
+	AMAIR_EL2,	/* Auxiliary Memory Attribute Indirection Register (EL2) */
+	VBAR_EL2,	/* Vector Base Address Register (EL2) */
+	RVBAR_EL2,	/* Reset Vector Base Address Register */
+	CONTEXTIDR_EL2,	/* Context ID Register (EL2) */
+	TPIDR_EL2,	/* EL2 Software Thread ID Register */
+	CNTHCTL_EL2,	/* Counter-timer Hypervisor Control register */
+	SP_EL2,		/* EL2 Stack Pointer */
+
 	NR_SYS_REGS	/* Nothing after this line! */
 };
 

index 193583df2d9c..e5d826dc0b63 100644
@@ -183,6 +183,62 @@ static __always_inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num,
 		vcpu_gp_regs(vcpu)->regs[reg_num] = val;
 }
 
+static inline bool vcpu_is_el2_ctxt(const struct kvm_cpu_context *ctxt)
+{
+	switch (ctxt->regs.pstate & (PSR_MODE32_BIT | PSR_MODE_MASK)) {
+	case PSR_MODE_EL2h:
+	case PSR_MODE_EL2t:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static inline bool vcpu_is_el2(const struct kvm_vcpu *vcpu)
+{
+	return vcpu_is_el2_ctxt(&vcpu->arch.ctxt);
+}
+
+static inline bool __vcpu_el2_e2h_is_set(const struct kvm_cpu_context *ctxt)
+{
+	return ctxt_sys_reg(ctxt, HCR_EL2) & HCR_E2H;
+}
+
+static inline bool vcpu_el2_e2h_is_set(const struct kvm_vcpu *vcpu)
+{
+	return __vcpu_el2_e2h_is_set(&vcpu->arch.ctxt);
+}
+
+static inline bool __vcpu_el2_tge_is_set(const struct kvm_cpu_context *ctxt)
+{
+	return ctxt_sys_reg(ctxt, HCR_EL2) & HCR_TGE;
+}
+
+static inline bool vcpu_el2_tge_is_set(const struct kvm_vcpu *vcpu)
+{
+	return __vcpu_el2_tge_is_set(&vcpu->arch.ctxt);
+}
+
+static inline bool __is_hyp_ctxt(const struct kvm_cpu_context *ctxt)
+{
+	/*
+	 * We are in a hypervisor context if the vcpu mode is EL2 or
+	 * E2H and TGE bits are set. The latter means we are in the user space
+	 * of the VHE kernel. ARMv8.1 ARM describes this as 'InHost'
+	 *
+	 * Note that the HCR_EL2.{E2H,TGE}={0,1} isn't really handled in the
+	 * rest of the KVM code, and will result in a misbehaving guest.
+	 */
+	return vcpu_is_el2_ctxt(ctxt) ||
+		(__vcpu_el2_e2h_is_set(ctxt) && __vcpu_el2_tge_is_set(ctxt)) ||
+		__vcpu_el2_tge_is_set(ctxt);
+}
+
+static inline bool is_hyp_ctxt(const struct kvm_vcpu *vcpu)
+{
+	return __is_hyp_ctxt(&vcpu->arch.ctxt);
+}
+
 /*
  * The layout of SPSR for an AArch32 state is different when observed from an
  * AArch64 SPSR_ELx or an AArch32 SPSR_*. This function generates the AArch32

index 1312fb48f18b..d13f168abe4b 100644
@@ -490,23 +490,51 @@
 
 #define SYS_PMCCFILTR_EL0		sys_reg(3, 3, 14, 15, 7)
 
+#define SYS_VPIDR_EL2			sys_reg(3, 4, 0, 0, 0)
+#define SYS_VMPIDR_EL2			sys_reg(3, 4, 0, 0, 5)
+
 #define SYS_SCTLR_EL2			sys_reg(3, 4, 1, 0, 0)
+#define SYS_ACTLR_EL2			sys_reg(3, 4, 1, 0, 1)
+#define SYS_HCR_EL2			sys_reg(3, 4, 1, 1, 0)
+#define SYS_MDCR_EL2			sys_reg(3, 4, 1, 1, 1)
+#define SYS_CPTR_EL2			sys_reg(3, 4, 1, 1, 2)
+#define SYS_HSTR_EL2			sys_reg(3, 4, 1, 1, 3)
 #define SYS_HFGRTR_EL2			sys_reg(3, 4, 1, 1, 4)
 #define SYS_HFGWTR_EL2			sys_reg(3, 4, 1, 1, 5)
 #define SYS_HFGITR_EL2			sys_reg(3, 4, 1, 1, 6)
+#define SYS_HACR_EL2			sys_reg(3, 4, 1, 1, 7)
+
+#define SYS_TTBR0_EL2			sys_reg(3, 4, 2, 0, 0)
+#define SYS_TTBR1_EL2			sys_reg(3, 4, 2, 0, 1)
+#define SYS_TCR_EL2			sys_reg(3, 4, 2, 0, 2)
+#define SYS_VTTBR_EL2			sys_reg(3, 4, 2, 1, 0)
+#define SYS_VTCR_EL2			sys_reg(3, 4, 2, 1, 2)
+
 #define SYS_TRFCR_EL2			sys_reg(3, 4, 1, 2, 1)
 #define SYS_HDFGRTR_EL2			sys_reg(3, 4, 3, 1, 4)
 #define SYS_HDFGWTR_EL2			sys_reg(3, 4, 3, 1, 5)
 #define SYS_HAFGRTR_EL2			sys_reg(3, 4, 3, 1, 6)
 #define SYS_SPSR_EL2			sys_reg(3, 4, 4, 0, 0)
 #define SYS_ELR_EL2			sys_reg(3, 4, 4, 0, 1)
+#define SYS_SP_EL1			sys_reg(3, 4, 4, 1, 0)
 #define SYS_IFSR32_EL2			sys_reg(3, 4, 5, 0, 1)
+#define SYS_AFSR0_EL2			sys_reg(3, 4, 5, 1, 0)
+#define SYS_AFSR1_EL2			sys_reg(3, 4, 5, 1, 1)
 #define SYS_ESR_EL2			sys_reg(3, 4, 5, 2, 0)
 #define SYS_VSESR_EL2			sys_reg(3, 4, 5, 2, 3)
 #define SYS_FPEXC32_EL2			sys_reg(3, 4, 5, 3, 0)
 #define SYS_TFSR_EL2			sys_reg(3, 4, 5, 6, 0)
 
-#define SYS_VDISR_EL2			sys_reg(3, 4, 12, 1,  1)
+#define SYS_FAR_EL2			sys_reg(3, 4, 6, 0, 0)
+#define SYS_HPFAR_EL2			sys_reg(3, 4, 6, 0, 4)
+
+#define SYS_MAIR_EL2			sys_reg(3, 4, 10, 2, 0)
+#define SYS_AMAIR_EL2			sys_reg(3, 4, 10, 3, 0)
+
+#define SYS_VBAR_EL2			sys_reg(3, 4, 12, 0, 0)
+#define SYS_RVBAR_EL2			sys_reg(3, 4, 12, 0, 1)
+#define SYS_RMR_EL2			sys_reg(3, 4, 12, 0, 2)
+#define SYS_VDISR_EL2			sys_reg(3, 4, 12, 1, 1)
 #define __SYS__AP0Rx_EL2(x)		sys_reg(3, 4, 12, 8, x)
 #define SYS_ICH_AP0R0_EL2		__SYS__AP0Rx_EL2(0)
 #define SYS_ICH_AP0R1_EL2		__SYS__AP0Rx_EL2(1)

@@ -548,6 +576,12 @@
 #define SYS_ICH_LR14_EL2		__SYS__LR8_EL2(6)
 #define SYS_ICH_LR15_EL2		__SYS__LR8_EL2(7)
 
+#define SYS_CONTEXTIDR_EL2		sys_reg(3, 4, 13, 0, 1)
+#define SYS_TPIDR_EL2			sys_reg(3, 4, 13, 0, 2)
+
+#define SYS_CNTVOFF_EL2			sys_reg(3, 4, 14, 0, 3)
+#define SYS_CNTHCTL_EL2			sys_reg(3, 4, 14, 1, 0)
+
 /* VHE encodings for architectural EL0/1 system registers */
 #define SYS_SCTLR_EL12			sys_reg(3, 5, 1, 0, 0)
 #define SYS_TTBR0_EL12			sys_reg(3, 5, 2, 0, 0)

@@ -570,6 +604,8 @@
 #define SYS_CNTV_CTL_EL02		sys_reg(3, 5, 14, 3, 1)
 #define SYS_CNTV_CVAL_EL02		sys_reg(3, 5, 14, 3, 2)
 
+#define SYS_SP_EL2			sys_reg(3, 6,  4, 1, 0)
+
 /* Common SCTLR_ELx flags. */
 #define SCTLR_ELx_ENTP2	(BIT(60))
 #define SCTLR_ELx_DSSBS	(BIT(44))

145 lines not on this page · raw message

index 53749d3a0996..1a1abda6af74 100644
@@ -1587,6 +1587,14 @@ static bool access_ccsidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
        return true;
 }
 
+static void nv_reset_val(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+       BUG_ON(!r->reg);
+       BUG_ON(r->reg >= NR_SYS_REGS);
+       if (vcpu_has_nv(vcpu))
+               __vcpu_sys_reg(vcpu, r->reg) = r->val;
+}
+
 static unsigned int mte_visibility(const struct kvm_vcpu *vcpu,
                                   const struct sys_reg_desc *rd)
 {

@@ -2190,7 +2198,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
        EL2_REG(CONTEXTIDR_EL2, access_rw, reset_val, 0),
        EL2_REG(TPIDR_EL2, access_rw, reset_val, 0),
 
-       EL2_REG(CNTVOFF_EL2, access_rw, reset_val, 0),
+       EL2_REG(CNTVOFF_EL2, access_rw, nv_reset_val, 0),
        EL2_REG(CNTHCTL_EL2, access_rw, reset_val, 0),
 
        EL12_REG(SCTLR, access_vm_reg, reset_val, 0x00C50078),

index 26b0c97df986..bea827b76c22 100644
@@ -350,4 +350,21 @@
 #define CPACR_EL1_DEFAULT	(CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN |\
 				 CPACR_EL1_ZEN_EL1EN)
 
+#define kvm_mode_names				\
+	{ PSR_MODE_EL0t,	"EL0t" },	\
+	{ PSR_MODE_EL1t,	"EL1t" },	\
+	{ PSR_MODE_EL1h,	"EL1h" },	\
+	{ PSR_MODE_EL2t,	"EL2t" },	\
+	{ PSR_MODE_EL2h,	"EL2h" },	\
+	{ PSR_MODE_EL3t,	"EL3t" },	\
+	{ PSR_MODE_EL3h,	"EL3h" },	\
+	{ PSR_AA32_MODE_USR,	"32-bit USR" },	\
+	{ PSR_AA32_MODE_FIQ,	"32-bit FIQ" },	\
+	{ PSR_AA32_MODE_IRQ,	"32-bit IRQ" },	\
+	{ PSR_AA32_MODE_SVC,	"32-bit SVC" },	\
+	{ PSR_AA32_MODE_ABT,	"32-bit ABT" },	\
+	{ PSR_AA32_MODE_HYP,	"32-bit HYP" },	\
+	{ PSR_AA32_MODE_UND,	"32-bit UND" },	\
+	{ PSR_AA32_MODE_SYS,	"32-bit SYS" }
+
 #endif /* __ARM64_KVM_ARM_H__ */

index e5d826dc0b63..7e3fa8b387f6 100644
@@ -33,6 +33,12 @@ enum exception_type {
 	except_type_serror	= 0x180,
 };
 
+#define kvm_exception_type_names		\
+	{ except_type_sync,	"SYNC"   },	\
+	{ except_type_irq,	"IRQ"    },	\
+	{ except_type_fiq,	"FIQ"    },	\
+	{ except_type_serror,	"SERROR" }
+
 bool kvm_condition_valid32(const struct kvm_vcpu *vcpu);
 void kvm_skip_instr32(struct kvm_vcpu *vcpu);
 

@@ -44,6 +50,10 @@ void kvm_inject_size_fault(struct kvm_vcpu *vcpu);
 
 void kvm_vcpu_wfi(struct kvm_vcpu *vcpu);
 
+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);
+
 #if defined(__KVM_VHE_HYPERVISOR__) || defined(__KVM_NVHE_HYPERVISOR__)
 static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 {

index f53473071bcb..1b585a4dd122 100644
@@ -634,7 +634,7 @@ struct kvm_vcpu_arch {
 #define EXCEPT_AA64_EL1_IRQ	__vcpu_except_flags(1)
 #define EXCEPT_AA64_EL1_FIQ	__vcpu_except_flags(2)
 #define EXCEPT_AA64_EL1_SERR	__vcpu_except_flags(3)
-/* For AArch64 with NV (one day): */
+/* For AArch64 with NV: */
 #define EXCEPT_AA64_EL2_SYNC	__vcpu_except_flags(4)
 #define EXCEPT_AA64_EL2_IRQ	__vcpu_except_flags(5)
 #define EXCEPT_AA64_EL2_FIQ	__vcpu_except_flags(6)

203 lines not on this page · raw message

91 lines not on this page · raw message

93 lines not on this page · raw message

71 lines not on this page · raw message

index e778eefcf214..2d8c09cf3e49 100644
@@ -16,6 +16,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_mmu.h>
+#include <asm/kvm_nested.h>
 #include <asm/debug-monitors.h>
 #include <asm/stacktrace/nvhe.h>
 #include <asm/traps.h>

@@ -41,6 +42,16 @@ static int handle_hvc(struct kvm_vcpu *vcpu)
 			    kvm_vcpu_hvc_get_imm(vcpu));
 	vcpu->stat.hvc_exit_stat++;
 
+	/* Forward hvc instructions to the virtual EL2 if the guest has EL2. */
+	if (vcpu_has_nv(vcpu)) {
+		if (vcpu_read_sys_reg(vcpu, HCR_EL2) & HCR_HCD)
+			kvm_inject_undefined(vcpu);
+		else
+			kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+
+		return 1;
+	}
+
 	ret = kvm_hvc_call_handler(vcpu);
 	if (ret < 0) {
 		vcpu_set_reg(vcpu, 0, ~0UL);

index 206de10524e3..d4dd949b921e 100644
@@ -272,6 +272,10 @@
 		(((e) & ESR_ELx_SYS64_ISS_OP2_MASK) >>		\
 		 ESR_ELx_SYS64_ISS_OP2_SHIFT))
 
+/* ISS field definitions for ERET/ERETAA/ERETAB trapping */
+#define ESR_ELx_ERET_ISS_ERET		0x2
+#define ESR_ELx_ERET_ISS_ERETA		0x1
+
 /*
  * ISS field definitions for floating-point exception traps
  * (FP_EXC_32/FP_EXC_64).

index bea827b76c22..e24825dcda6b 100644
@@ -344,7 +344,7 @@
 	ECN(SP_ALIGN), ECN(FP_EXC32), ECN(FP_EXC64), ECN(SERROR), \
 	ECN(BREAKPT_LOW), ECN(BREAKPT_CUR), ECN(SOFTSTP_LOW), \
 	ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \
-	ECN(BKPT32), ECN(VECTOR32), ECN(BRK64)
+	ECN(BKPT32), ECN(VECTOR32), ECN(BRK64), ECN(ERET)
 
 #define CPACR_EL1_TTA		(1 << 28)
 #define CPACR_EL1_DEFAULT	(CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN |\

index 2d8c09cf3e49..e75101f2aa6c 100644
@@ -207,6 +207,15 @@ static int kvm_handle_ptrauth(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int kvm_handle_eret(struct kvm_vcpu *vcpu)
+{
+	if (kvm_vcpu_get_esr(vcpu) & ESR_ELx_ERET_ISS_ERET)
+		return kvm_handle_ptrauth(vcpu);
+
+	kvm_emulate_nested_eret(vcpu);
+	return 1;
+}
+
 static exit_handle_fn arm_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]	= kvm_handle_unknown_ec,
 	[ESR_ELx_EC_WFx]	= kvm_handle_wfx,

@@ -222,6 +231,7 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[ESR_ELx_EC_SMC64]	= handle_smc,
 	[ESR_ELx_EC_SYS64]	= kvm_handle_sys_reg,
 	[ESR_ELx_EC_SVE]	= handle_sve,
+	[ESR_ELx_EC_ERET]	= kvm_handle_eret,
 	[ESR_ELx_EC_IABT_LOW]	= kvm_handle_guest_abort,
 	[ESR_ELx_EC_DABT_LOW]	= kvm_handle_guest_abort,
 	[ESR_ELx_EC_SOFTSTP_LOW]= kvm_handle_guest_debug,

index e75101f2aa6c..b0c343c4e062 100644
@@ -63,6 +63,8 @@ static int handle_hvc(struct kvm_vcpu *vcpu)
 
 static int handle_smc(struct kvm_vcpu *vcpu)
 {
+	int ret;
+
 	/*
 	 * "If an SMC instruction executed at Non-secure EL1 is
 	 * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a

@@ -70,10 +72,28 @@ static int handle_smc(struct kvm_vcpu *vcpu)
 	 *
 	 * We need to advance the PC after the trap, as it would
 	 * otherwise return to the same address...
+	 *
+	 * If imm is non-zero, it's not defined, so just skip it.
+	 */
+	if (kvm_vcpu_hvc_get_imm(vcpu)) {
+		vcpu_set_reg(vcpu, 0, ~0UL);
+		kvm_incr_pc(vcpu);
+		return 1;
+	}
+
+	/*
+	 * If imm is zero, it's a psci call.
+	 * Note that on ARMv8.3, even if EL3 is not implemented, SMC executed
+	 * at Non-secure EL1 is trapped to EL2 if HCR_EL2.TSC==1, rather than
+	 * being treated as UNDEFINED.
 	 */
-	vcpu_set_reg(vcpu, 0, ~0UL);
+	ret = kvm_hvc_call_handler(vcpu);
+	if (ret < 0)
+		vcpu_set_reg(vcpu, 0, ~0UL);
+
 	kvm_incr_pc(vcpu);
-	return 1;
+
+	return ret;
 }
 
 /*

index 1e6ae3b2e6dd..de209059fd34 100644
@@ -1538,6 +1538,30 @@ static bool access_sp_el1(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static bool access_elr(struct kvm_vcpu *vcpu,
+		       struct sys_reg_params *p,
+		       const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		vcpu_write_sys_reg(vcpu, p->regval, ELR_EL1);
+	else
+		p->regval = vcpu_read_sys_reg(vcpu, ELR_EL1);
+
+	return true;
+}
+
+static bool access_spsr(struct kvm_vcpu *vcpu,
+			struct sys_reg_params *p,
+			const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		__vcpu_sys_reg(vcpu, SPSR_EL1) = p->regval;
+	else
+		p->regval = __vcpu_sys_reg(vcpu, SPSR_EL1);
+
+	return true;
+}
+
 /*
  * Architected system registers.
  * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2

@@ -1694,6 +1718,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	PTRAUTH_KEY(APDB),
 	PTRAUTH_KEY(APGA),
 
+	{ SYS_DESC(SYS_SPSR_EL1), access_spsr},
+	{ SYS_DESC(SYS_ELR_EL1), access_elr},
+
 	{ SYS_DESC(SYS_AFSR0_EL1), access_vm_reg, reset_unknown, AFSR0_EL1 },
 	{ SYS_DESC(SYS_AFSR1_EL1), access_vm_reg, reset_unknown, AFSR1_EL1 },
 	{ SYS_DESC(SYS_ESR_EL1), access_vm_reg, reset_unknown, ESR_EL1 },

@@ -1741,7 +1768,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_LORC_EL1), trap_loregion },
 	{ SYS_DESC(SYS_LORID_EL1), trap_loregion },
 
-	{ SYS_DESC(SYS_VBAR_EL1), NULL, reset_val, VBAR_EL1, 0 },
+	{ SYS_DESC(SYS_VBAR_EL1), access_rw, reset_val, VBAR_EL1, 0 },
 	{ SYS_DESC(SYS_DISR_EL1), NULL, reset_val, DISR_EL1, 0 },
 
 	{ SYS_DESC(SYS_ICC_IAR0_EL1), write_to_read_only },

index 1b585a4dd122..70eab7a6386b 100644
@@ -645,6 +645,8 @@ struct kvm_vcpu_arch {
 #define DEBUG_STATE_SAVE_SPE	__vcpu_single_flag(iflags, BIT(5))
 /* Save TRBE context if active  */
 #define DEBUG_STATE_SAVE_TRBE	__vcpu_single_flag(iflags, BIT(6))
+/* vcpu running in HYP context */
+#define VCPU_HYP_CONTEXT	__vcpu_single_flag(iflags, BIT(7))
 
 /* SVE enabled for host EL0 */
 #define HOST_SVE_ENABLED	__vcpu_single_flag(sflags, BIT(0))

index baa5b9b3dde5..0fbbf2870b7b 100644
@@ -156,9 +156,26 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	write_sysreg_el1(ctxt_sys_reg(ctxt, SPSR_EL1),	SYS_SPSR);
 }
 
+/* Read the VCPU state's PSTATE, but translate (v)EL2 to EL1. */
+static inline u64 to_hw_pstate(const struct kvm_cpu_context *ctxt)
+{
+	u64 mode = ctxt->regs.pstate & (PSR_MODE_MASK | PSR_MODE32_BIT);
+
+	switch (mode) {
+	case PSR_MODE_EL2t:
+		mode = PSR_MODE_EL1t;
+		break;
+	case PSR_MODE_EL2h:
+		mode = PSR_MODE_EL1h;
+		break;
+	}
+
+	return (ctxt->regs.pstate & ~(PSR_MODE_MASK | PSR_MODE32_BIT)) | mode;
+}
+
 static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
 {
-	u64 pstate = ctxt->regs.pstate;
+	u64 pstate = to_hw_pstate(ctxt);
 	u64 mode = pstate & PSR_AA32_MODE_MASK;
 
 	/*

index 1a97391fedd2..76ea9392363d 100644
@@ -120,6 +120,25 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
 
 static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
+	/*
+	 * If we were in HYP context on entry, adjust the PSTATE view
+	 * so that the usual helpers work correctly.
+	 */
+	if (unlikely(vcpu_get_flag(vcpu, VCPU_HYP_CONTEXT))) {
+		u64 mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT);
+
+		switch (mode) {
+		case PSR_MODE_EL1t:
+			mode = PSR_MODE_EL2t;
+			break;
+		case PSR_MODE_EL1h:
+			mode = PSR_MODE_EL2h;
+			break;
+		}
+
+		*vcpu_cpsr(vcpu) &= ~(PSR_MODE_MASK | PSR_MODE32_BIT);
+		*vcpu_cpsr(vcpu) |= mode;
+	}
 }
 
 /* Switch to the guest for VHE systems running in EL2 */

@@ -154,6 +173,11 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 	sysreg_restore_guest_state_vhe(guest_ctxt);
 	__debug_switch_to_guest(vcpu);
 
+	if (is_hyp_ctxt(vcpu))
+		vcpu_set_flag(vcpu, VCPU_HYP_CONTEXT);
+	else
+		vcpu_clear_flag(vcpu, VCPU_HYP_CONTEXT);
+
 	do {
 		/* Jump in the fire! */
 		exit_code = __guest_enter(vcpu);

index de209059fd34..55a14c86a455 100644
@@ -2980,7 +2980,7 @@ int kvm_sys_reg_get_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg,
 	int ret;
 
 	r = id_to_sys_reg_desc(vcpu, reg->id, table, num);
-	if (!r)
+	if (!r || sysreg_hidden_user(vcpu, r))
 		return -ENOENT;
 
 	if (r->get_user) {

@@ -3024,7 +3024,7 @@ int kvm_sys_reg_set_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg,
 		return -EFAULT;
 
 	r = id_to_sys_reg_desc(vcpu, reg->id, table, num);
-	if (!r)
+	if (!r || sysreg_hidden_user(vcpu, r))
 		return -ENOENT;
 
 	if (sysreg_user_write_ignore(vcpu, r))

@@ -3118,7 +3118,7 @@ static int walk_one_sys_reg(const struct kvm_vcpu *vcpu,
 	if (!(rd->reg || rd->get_user))
 		return 0;
 
-	if (sysreg_hidden(vcpu, rd))
+	if (sysreg_hidden_user(vcpu, rd))
 		return 0;
 
 	if (!copy_reg_to_user(rd, uind))

index e4ebb3a379fd..6b11f2cc7146 100644
@@ -85,8 +85,9 @@ struct sys_reg_desc {
 };
 
 #define REG_HIDDEN		(1 << 0) /* hidden from userspace and guest */
-#define REG_RAZ			(1 << 1) /* RAZ from userspace and guest */
-#define REG_USER_WI		(1 << 2) /* WI from userspace only */
+#define REG_HIDDEN_USER		(1 << 1) /* hidden from userspace only */
+#define REG_RAZ			(1 << 2) /* RAZ from userspace and guest */
+#define REG_USER_WI		(1 << 3) /* WI from userspace only */
 
 static __printf(2, 3)
 inline void print_sys_reg_msg(const struct sys_reg_params *p,

@@ -152,6 +153,15 @@ static inline bool sysreg_hidden(const struct kvm_vcpu *vcpu,
 	return sysreg_visibility(vcpu, r) & REG_HIDDEN;
 }
 
+static inline bool sysreg_hidden_user(const struct kvm_vcpu *vcpu,
+				      const struct sys_reg_desc *r)
+{
+	if (likely(!r->visibility))
+		return false;
+
+	return r->visibility(vcpu, r) & (REG_HIDDEN | REG_HIDDEN_USER);
+}
+
 static inline bool sysreg_visible_as_raz(const struct kvm_vcpu *vcpu,
 					 const struct sys_reg_desc *r)
 {

index 55a14c86a455..f5dd4f4eaaf0 100644
@@ -1482,6 +1482,26 @@ static unsigned int el2_visibility(const struct kvm_vcpu *vcpu,
 	.val = v,				\
 }
 
+/*
+ * EL{0,1}2 registers are the EL2 view on an EL0 or EL1 register when
+ * HCR_EL2.E2H==1, and only in the sysreg table for convenience of
+ * handling traps. Given that, they are always hidden from userspace.
+ */
+static unsigned int elx2_visibility(const struct kvm_vcpu *vcpu,
+				    const struct sys_reg_desc *rd)
+{
+	return REG_HIDDEN_USER;
+}
+
+#define EL12_REG(name, acc, rst, v) {		\
+	SYS_DESC(SYS_##name##_EL12),		\
+	.access = acc,				\
+	.reset = rst,				\
+	.reg = name##_EL1,			\
+	.val = v,				\
+	.visibility = elx2_visibility,		\
+}
+
 /* sys_reg_desc initialiser for known cpufeature ID registers */
 #define ID_SANITISED(name) {			\
 	SYS_DESC(SYS_##name),			\

@@ -2031,6 +2051,23 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	EL2_REG(CNTVOFF_EL2, access_rw, reset_val, 0),
 	EL2_REG(CNTHCTL_EL2, access_rw, reset_val, 0),
 
+	EL12_REG(SCTLR, access_vm_reg, reset_val, 0x00C50078),
+	EL12_REG(CPACR, access_rw, reset_val, 0),
+	EL12_REG(TTBR0, access_vm_reg, reset_unknown, 0),
+	EL12_REG(TTBR1, access_vm_reg, reset_unknown, 0),
+	EL12_REG(TCR, access_vm_reg, reset_val, 0),
+	{ SYS_DESC(SYS_SPSR_EL12), access_spsr},
+	{ SYS_DESC(SYS_ELR_EL12), access_elr},
+	EL12_REG(AFSR0, access_vm_reg, reset_unknown, 0),
+	EL12_REG(AFSR1, access_vm_reg, reset_unknown, 0),
+	EL12_REG(ESR, access_vm_reg, reset_unknown, 0),
+	EL12_REG(FAR, access_vm_reg, reset_unknown, 0),
+	EL12_REG(MAIR, access_vm_reg, reset_unknown, 0),
+	EL12_REG(AMAIR, access_vm_reg, reset_amair_el1, 0),
+	EL12_REG(VBAR, access_rw, reset_val, 0),
+	EL12_REG(CONTEXTIDR, access_vm_reg, reset_val, 0),
+	EL12_REG(CNTKCTL, access_rw, reset_val, 0),
+
 	EL2_REG(SP_EL2, NULL, reset_unknown, 0),
 };
 

index fd601ea68d13..8fb67f032fd1 100644
@@ -11,4 +11,10 @@ static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu)
 		test_bit(KVM_ARM_VCPU_HAS_EL2, vcpu->arch.features));
 }
 
+struct sys_reg_params;
+struct sys_reg_desc;
+
+void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p,
+			  const struct sys_reg_desc *r);
+
 #endif /* __ARM64_KVM_NESTED_H */

162 lines not on this page · raw message

index f5dd4f4eaaf0..82c1f8d786f7 100644
@@ -1223,6 +1223,9 @@ static bool access_id_reg(struct kvm_vcpu *vcpu,
 		return write_to_read_only(vcpu, p, r);
 
 	p->regval = read_id_reg(vcpu, r);
+	if (vcpu_has_nv(vcpu))
+		access_nested_id_reg(vcpu, p, r);
+
 	return true;
 }
 

index e4a7e6369499..2890d57bec30 100644
@@ -115,6 +115,7 @@ alternative_cb_end
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
+#include <asm/kvm_emulate.h>
 #include <asm/kvm_host.h>
 
 void kvm_update_va_mask(struct alt_instr *alt,

@@ -192,7 +193,15 @@ struct kvm;
 
 static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 {
-	return (vcpu_read_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
+	u64 cache_bits = SCTLR_ELx_M | SCTLR_ELx_C;
+	int reg;
+
+	if (vcpu_is_el2(vcpu))
+		reg = SCTLR_EL2;
+	else
+		reg = SCTLR_EL1;
+
+	return (vcpu_read_sys_reg(vcpu, reg) & cache_bits) == cache_bits;
 }
 
 static inline void __clean_dcache_guest_page(void *va, size_t size)