Merge branch 'kvm-6.10-fixes' into HEAD

MAINTAINERS

@@ -12383,7 +12383,6 @@ F:	drivers/video/backlight/ktz8866.c
 
 KVM PARAVIRT (KVM/paravirt)
 M:	Paolo Bonzini <pbonzini@redhat.com>
-R:	Wanpeng Li <wanpengli@tencent.com>
 R:	Vitaly Kuznetsov <vkuznets@redhat.com>
 L:	kvm@vger.kernel.org
 S:	Supported

arch/arm64/include/asm/el2_setup.h

@@ -146,7 +146,7 @@
 /* Coprocessor traps */
 .macro __init_el2_cptr
 	__check_hvhe .LnVHE_\@, x1
-	mov	x0, #(CPACR_EL1_FPEN_EL1EN | CPACR_EL1_FPEN_EL0EN)
+	mov	x0, #CPACR_ELx_FPEN
 	msr	cpacr_el1, x0
 	b	.Lskip_set_cptr_\@
 .LnVHE_\@:
@@ -277,7 +277,7 @@
 
 	// (h)VHE case
 	mrs	x0, cpacr_el1			// Disable SVE traps
-	orr	x0, x0, #(CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN)
+	orr	x0, x0, #CPACR_ELx_ZEN
 	msr	cpacr_el1, x0
 	b	.Lskip_set_cptr_\@
 
@@ -298,7 +298,7 @@
 
 	// (h)VHE case
 	mrs	x0, cpacr_el1			// Disable SME traps
-	orr	x0, x0, #(CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN)
+	orr	x0, x0, #CPACR_ELx_SMEN
 	msr	cpacr_el1, x0
 	b	.Lskip_set_cptr_sme_\@
 

arch/arm64/include/asm/kvm_arm.h

@@ -305,6 +305,12 @@
 				 GENMASK(19, 14) |	\
 				 BIT(11))
 
+#define CPTR_VHE_EL2_RES0	(GENMASK(63, 32) |	\
+				 GENMASK(27, 26) |	\
+				 GENMASK(23, 22) |	\
+				 GENMASK(19, 18) |	\
+				 GENMASK(15, 0))
+
 /* Hyp Debug Configuration Register bits */
 #define MDCR_EL2_E2TB_MASK	(UL(0x3))
 #define MDCR_EL2_E2TB_SHIFT	(UL(24))

arch/arm64/include/asm/kvm_emulate.h

@@ -557,6 +557,68 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu)
 		vcpu_set_flag((v), e);					\
 	} while (0)
 
+#define __build_check_all_or_none(r, bits)				\
+	BUILD_BUG_ON(((r) & (bits)) && ((r) & (bits)) != (bits))
+
+#define __cpacr_to_cptr_clr(clr, set)					\
+	({								\
+		u64 cptr = 0;						\
+									\
+		if ((set) & CPACR_ELx_FPEN)				\
+			cptr |= CPTR_EL2_TFP;				\
+		if ((set) & CPACR_ELx_ZEN)				\
+			cptr |= CPTR_EL2_TZ;				\
+		if ((set) & CPACR_ELx_SMEN)				\
+			cptr |= CPTR_EL2_TSM;				\
+		if ((clr) & CPACR_ELx_TTA)				\
+			cptr |= CPTR_EL2_TTA;				\
+		if ((clr) & CPTR_EL2_TAM)				\
+			cptr |= CPTR_EL2_TAM;				\
+		if ((clr) & CPTR_EL2_TCPAC)				\
+			cptr |= CPTR_EL2_TCPAC;				\
+									\
+		cptr;							\
+	})
+
+#define __cpacr_to_cptr_set(clr, set)					\
+	({								\
+		u64 cptr = 0;						\
+									\
+		if ((clr) & CPACR_ELx_FPEN)				\
+			cptr |= CPTR_EL2_TFP;				\
+		if ((clr) & CPACR_ELx_ZEN)				\
+			cptr |= CPTR_EL2_TZ;				\
+		if ((clr) & CPACR_ELx_SMEN)				\
+			cptr |= CPTR_EL2_TSM;				\
+		if ((set) & CPACR_ELx_TTA)				\
+			cptr |= CPTR_EL2_TTA;				\
+		if ((set) & CPTR_EL2_TAM)				\
+			cptr |= CPTR_EL2_TAM;				\
+		if ((set) & CPTR_EL2_TCPAC)				\
+			cptr |= CPTR_EL2_TCPAC;				\
+									\
+		cptr;							\
+	})
+
+#define cpacr_clear_set(clr, set)					\
+	do {								\
+		BUILD_BUG_ON((set) & CPTR_VHE_EL2_RES0);		\
+		BUILD_BUG_ON((clr) & CPACR_ELx_E0POE);			\
+		__build_check_all_or_none((clr), CPACR_ELx_FPEN);	\
+		__build_check_all_or_none((set), CPACR_ELx_FPEN);	\
+		__build_check_all_or_none((clr), CPACR_ELx_ZEN);	\
+		__build_check_all_or_none((set), CPACR_ELx_ZEN);	\
+		__build_check_all_or_none((clr), CPACR_ELx_SMEN);	\
+		__build_check_all_or_none((set), CPACR_ELx_SMEN);	\
+									\
+		if (has_vhe() || has_hvhe())				\
+			sysreg_clear_set(cpacr_el1, clr, set);		\
+		else							\
+			sysreg_clear_set(cptr_el2,			\
+					 __cpacr_to_cptr_clr(clr, set),	\
+					 __cpacr_to_cptr_set(clr, set));\
+	} while (0)
+
 static __always_inline void kvm_write_cptr_el2(u64 val)
 {
 	if (has_vhe() || has_hvhe())
@@ -570,17 +632,16 @@ static __always_inline u64 kvm_get_reset_cptr_el2(struct kvm_vcpu *vcpu)
 	u64 val;
 
 	if (has_vhe()) {
-		val = (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN |
+		val = (CPACR_ELx_FPEN | CPACR_EL1_ZEN_EL1EN);
-		       CPACR_EL1_ZEN_EL1EN);
 		if (cpus_have_final_cap(ARM64_SME))
 			val |= CPACR_EL1_SMEN_EL1EN;
 	} else if (has_hvhe()) {
-		val = (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN);
+		val = CPACR_ELx_FPEN;
 
 		if (!vcpu_has_sve(vcpu) || !guest_owns_fp_regs())
-			val |= CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN;
+			val |= CPACR_ELx_ZEN;
 		if (cpus_have_final_cap(ARM64_SME))
-			val |= CPACR_EL1_SMEN_EL1EN | CPACR_EL1_SMEN_EL0EN;
+			val |= CPACR_ELx_SMEN;
 	} else {
 		val = CPTR_NVHE_EL2_RES1;
 

arch/arm64/include/asm/kvm_host.h

@@ -76,6 +76,7 @@ static inline enum kvm_mode kvm_get_mode(void) { return KVM_MODE_NONE; };
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
 extern unsigned int __ro_after_init kvm_sve_max_vl;
+extern unsigned int __ro_after_init kvm_host_sve_max_vl;
 int __init kvm_arm_init_sve(void);
 
 u32 __attribute_const__ kvm_target_cpu(void);
@@ -521,6 +522,20 @@ struct kvm_cpu_context {
 	u64 *vncr_array;
 };
 
+struct cpu_sve_state {
+	__u64 zcr_el1;
+
+	/*
+	 * Ordering is important since __sve_save_state/__sve_restore_state
+	 * relies on it.
+	 */
+	__u32 fpsr;
+	__u32 fpcr;
+
+	/* Must be SVE_VQ_BYTES (128 bit) aligned. */
+	__u8 sve_regs[];
+};
+
 /*
  * This structure is instantiated on a per-CPU basis, and contains
  * data that is:
@@ -534,7 +549,15 @@ struct kvm_cpu_context {
  */
 struct kvm_host_data {
 	struct kvm_cpu_context host_ctxt;
-	struct user_fpsimd_state *fpsimd_state;	/* hyp VA */
+
+	/*
+	 * All pointers in this union are hyp VA.
+	 * sve_state is only used in pKVM and if system_supports_sve().
+	 */
+	union {
+		struct user_fpsimd_state *fpsimd_state;
+		struct cpu_sve_state *sve_state;
+	};
 
 	/* Ownership of the FP regs */
 	enum {

arch/arm64/include/asm/kvm_hyp.h

@@ -111,7 +111,8 @@ void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu);
 
 void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
 void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
-void __sve_restore_state(void *sve_pffr, u32 *fpsr);
+void __sve_save_state(void *sve_pffr, u32 *fpsr, int save_ffr);
+void __sve_restore_state(void *sve_pffr, u32 *fpsr, int restore_ffr);
 
 u64 __guest_enter(struct kvm_vcpu *vcpu);
 
@@ -142,5 +143,6 @@ extern u64 kvm_nvhe_sym(id_aa64smfr0_el1_sys_val);
 
 extern unsigned long kvm_nvhe_sym(__icache_flags);
 extern unsigned int kvm_nvhe_sym(kvm_arm_vmid_bits);
+extern unsigned int kvm_nvhe_sym(kvm_host_sve_max_vl);
 
 #endif /* __ARM64_KVM_HYP_H__ */

arch/arm64/include/asm/kvm_pkvm.h

@@ -128,4 +128,13 @@ static inline unsigned long hyp_ffa_proxy_pages(void)
 	return (2 * KVM_FFA_MBOX_NR_PAGES) + DIV_ROUND_UP(desc_max, PAGE_SIZE);
 }
 
+static inline size_t pkvm_host_sve_state_size(void)
+{
+	if (!system_supports_sve())
+		return 0;
+
+	return size_add(sizeof(struct cpu_sve_state),
+			SVE_SIG_REGS_SIZE(sve_vq_from_vl(kvm_host_sve_max_vl)));
+}
+
 #endif	/* __ARM64_KVM_PKVM_H__ */

arch/arm64/kvm/arm.c

@@ -1931,6 +1931,11 @@ static unsigned long nvhe_percpu_order(void)
 	return size ? get_order(size) : 0;
 }
 
+static size_t pkvm_host_sve_state_order(void)
+{
+	return get_order(pkvm_host_sve_state_size());
+}
+
 /* A lookup table holding the hypervisor VA for each vector slot */
 static void *hyp_spectre_vector_selector[BP_HARDEN_EL2_SLOTS];
 
@@ -2310,12 +2315,20 @@ static void __init teardown_subsystems(void)
 
 static void __init teardown_hyp_mode(void)
 {
+	bool free_sve = system_supports_sve() && is_protected_kvm_enabled();
 	int cpu;
 
 	free_hyp_pgds();
 	for_each_possible_cpu(cpu) {
 		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
 		free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order());
+
+		if (free_sve) {
+			struct cpu_sve_state *sve_state;
+
+			sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state;
+			free_pages((unsigned long) sve_state, pkvm_host_sve_state_order());
+		}
 	}
 }
 
@@ -2398,6 +2411,58 @@ static int __init kvm_hyp_init_protection(u32 hyp_va_bits)
 	return 0;
 }
 
+static int init_pkvm_host_sve_state(void)
+{
+	int cpu;
+
+	if (!system_supports_sve())
+		return 0;
+
+	/* Allocate pages for host sve state in protected mode. */
+	for_each_possible_cpu(cpu) {
+		struct page *page = alloc_pages(GFP_KERNEL, pkvm_host_sve_state_order());
+
+		if (!page)
+			return -ENOMEM;
+
+		per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state = page_address(page);
+	}
+
+	/*
+	 * Don't map the pages in hyp since these are only used in protected
+	 * mode, which will (re)create its own mapping when initialized.
+	 */
+
+	return 0;
+}
+
+/*
+ * Finalizes the initialization of hyp mode, once everything else is initialized
+ * and the initialziation process cannot fail.
+ */
+static void finalize_init_hyp_mode(void)
+{
+	int cpu;
+
+	if (system_supports_sve() && is_protected_kvm_enabled()) {
+		for_each_possible_cpu(cpu) {
+			struct cpu_sve_state *sve_state;
+
+			sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state;
+			per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state =
+				kern_hyp_va(sve_state);
+		}
+	} else {
+		for_each_possible_cpu(cpu) {
+			struct user_fpsimd_state *fpsimd_state;
+
+			fpsimd_state = &per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->host_ctxt.fp_regs;
+			per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->fpsimd_state =
+				kern_hyp_va(fpsimd_state);
+		}
+	}
+}
+
 static void pkvm_hyp_init_ptrauth(void)
 {
 	struct kvm_cpu_context *hyp_ctxt;
@@ -2566,6 +2631,10 @@ static int __init init_hyp_mode(void)
 			goto out_err;
 		}
 
+		err = init_pkvm_host_sve_state();
+		if (err)
+			goto out_err;
+
 		err = kvm_hyp_init_protection(hyp_va_bits);
 		if (err) {
 			kvm_err("Failed to init hyp memory protection\n");
@@ -2730,6 +2799,13 @@ static __init int kvm_arm_init(void)
 	if (err)
 		goto out_subs;
 
+	/*
+	 * This should be called after initialization is done and failure isn't
+	 * possible anymore.
+	 */
+	if (!in_hyp_mode)
+		finalize_init_hyp_mode();
+
 	kvm_arm_initialised = true;
 
 	return 0;

arch/arm64/kvm/emulate-nested.c

@@ -2181,16 +2181,23 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
 	if (forward_traps(vcpu, HCR_NV))
 		return;
 
+	spsr = vcpu_read_sys_reg(vcpu, SPSR_EL2);
+	spsr = kvm_check_illegal_exception_return(vcpu, spsr);
+
 	/* Check for an ERETAx */
 	esr = kvm_vcpu_get_esr(vcpu);
 	if (esr_iss_is_eretax(esr) && !kvm_auth_eretax(vcpu, &elr)) {
 		/*
-		 * Oh no, ERETAx failed to authenticate.  If we have
+		 * Oh no, ERETAx failed to authenticate.
-		 * FPACCOMBINE, deliver an exception right away.  If we
+		 *
-		 * don't, then let the mangled ELR value trickle down the
+		 * If we have FPACCOMBINE and we don't have a pending
+		 * Illegal Execution State exception (which has priority
+		 * over FPAC), deliver an exception right away.
+		 *
+		 * Otherwise, let the mangled ELR value trickle down the
 		 * ERET handling, and the guest will have a little surprise.
 		 */
-		if (kvm_has_pauth(vcpu->kvm, FPACCOMBINE)) {
+		if (kvm_has_pauth(vcpu->kvm, FPACCOMBINE) && !(spsr & PSR_IL_BIT)) {
 			esr &= ESR_ELx_ERET_ISS_ERETA;
 			esr |= FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_FPAC);
 			kvm_inject_nested_sync(vcpu, esr);
@@ -2201,17 +2208,11 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
 	preempt_disable();
 	kvm_arch_vcpu_put(vcpu);
 
-	spsr = __vcpu_sys_reg(vcpu, SPSR_EL2);
-	spsr = kvm_check_illegal_exception_return(vcpu, spsr);
 	if (!esr_iss_is_eretax(esr))
 		elr = __vcpu_sys_reg(vcpu, ELR_EL2);
 
 	trace_kvm_nested_eret(vcpu, elr, spsr);
 
-	/*
-	 * Note that the current exception level is always the virtual EL2,
-	 * since we set HCR_EL2.NV bit only when entering the virtual EL2.
-	 */
 	*vcpu_pc(vcpu) = elr;
 	*vcpu_cpsr(vcpu) = spsr;
 

arch/arm64/kvm/fpsimd.c

@@ -90,6 +90,13 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 			fpsimd_save_and_flush_cpu_state();
 		}
 	}
+
+	/*
+	 * If normal guests gain SME support, maintain this behavior for pKVM
+	 * guests, which don't support SME.
+	 */
+	WARN_ON(is_protected_kvm_enabled() && system_supports_sme() &&
+		read_sysreg_s(SYS_SVCR));
 }
 
 /*
@@ -161,9 +168,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 	if (has_vhe() && system_supports_sme()) {
 		/* Also restore EL0 state seen on entry */
 		if (vcpu_get_flag(vcpu, HOST_SME_ENABLED))
-			sysreg_clear_set(CPACR_EL1, 0,
+			sysreg_clear_set(CPACR_EL1, 0, CPACR_ELx_SMEN);
-					 CPACR_EL1_SMEN_EL0EN |
-					 CPACR_EL1_SMEN_EL1EN);
 		else
 			sysreg_clear_set(CPACR_EL1,
 					 CPACR_EL1_SMEN_EL0EN,

arch/arm64/kvm/guest.c

@@ -251,6 +251,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		case PSR_AA32_MODE_SVC:
 		case PSR_AA32_MODE_ABT:
 		case PSR_AA32_MODE_UND:
+		case PSR_AA32_MODE_SYS:
 			if (!vcpu_el1_is_32bit(vcpu))
 				return -EINVAL;
 			break;
@@ -276,7 +277,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) {
 		int i, nr_reg;
 
-		switch (*vcpu_cpsr(vcpu)) {
+		switch (*vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK) {
 		/*
 		 * Either we are dealing with user mode, and only the
 		 * first 15 registers (+ PC) must be narrowed to 32bit.

arch/arm64/kvm/hyp/aarch32.c

@@ -50,9 +50,23 @@ bool kvm_condition_valid32(const struct kvm_vcpu *vcpu)
 	u32 cpsr_cond;
 	int cond;
 
-	/* Top two bits non-zero?  Unconditional. */
+	/*
-	if (kvm_vcpu_get_esr(vcpu) >> 30)
+	 * These are the exception classes that could fire with a
+	 * conditional instruction.
+	 */
+	switch (kvm_vcpu_trap_get_class(vcpu)) {
+	case ESR_ELx_EC_CP15_32:
+	case ESR_ELx_EC_CP15_64:
+	case ESR_ELx_EC_CP14_MR:
+	case ESR_ELx_EC_CP14_LS:
+	case ESR_ELx_EC_FP_ASIMD:
+	case ESR_ELx_EC_CP10_ID:
+	case ESR_ELx_EC_CP14_64:
+	case ESR_ELx_EC_SVC32:
+		break;
+	default:
 		return true;
+	}
 
 	/* Is condition field valid? */
 	cond = kvm_vcpu_get_condition(vcpu);

arch/arm64/kvm/hyp/fpsimd.S

@@ -25,3 +25,9 @@ SYM_FUNC_START(__sve_restore_state)
 	sve_load 0, x1, x2, 3
 	ret
 SYM_FUNC_END(__sve_restore_state)
+
+SYM_FUNC_START(__sve_save_state)
+	mov	x2, #1
+	sve_save 0, x1, x2, 3
+	ret
+SYM_FUNC_END(__sve_save_state)

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

@@ -316,10 +316,24 @@ static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu)
 {
 	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);
+			    &vcpu->arch.ctxt.fp_regs.fpsr,
+			    true);
 	write_sysreg_el1(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR);
 }
 
+static inline void __hyp_sve_save_host(void)
+{
+	struct cpu_sve_state *sve_state = *host_data_ptr(sve_state);
+
+	sve_state->zcr_el1 = read_sysreg_el1(SYS_ZCR);
+	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
+	__sve_save_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_sve_max_vl),
+			 &sve_state->fpsr,
+			 true);
+}
+
+static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu);
+
 /*
  * We trap the first access to the FP/SIMD to save the host context and
  * restore the guest context lazily.
@@ -330,7 +344,6 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	bool sve_guest;
 	u8 esr_ec;
-	u64 reg;
 
 	if (!system_supports_fpsimd())
 		return false;
@@ -353,24 +366,15 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 	/* Valid trap.  Switch the context: */
 
 	/* First disable enough traps to allow us to update the registers */
-	if (has_vhe() || has_hvhe()) {
+	if (sve_guest || (is_protected_kvm_enabled() && system_supports_sve()))
-		reg = CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN;
+		cpacr_clear_set(0, CPACR_ELx_FPEN | CPACR_ELx_ZEN);
-		if (sve_guest)
+	else
-			reg |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;
+		cpacr_clear_set(0, CPACR_ELx_FPEN);
-
-		sysreg_clear_set(cpacr_el1, 0, reg);
-	} else {
-		reg = CPTR_EL2_TFP;
-		if (sve_guest)
-			reg |= CPTR_EL2_TZ;
-
-		sysreg_clear_set(cptr_el2, reg, 0);
-	}
 	isb();
 
 	/* Write out the host state if it's in the registers */
 	if (host_owns_fp_regs())
-		__fpsimd_save_state(*host_data_ptr(fpsimd_state));
+		kvm_hyp_save_fpsimd_host(vcpu);
 
 	/* Restore the guest state */
 	if (sve_guest)

arch/arm64/kvm/hyp/include/nvhe/pkvm.h

@@ -59,7 +59,6 @@ static inline bool pkvm_hyp_vcpu_is_protected(struct pkvm_hyp_vcpu *hyp_vcpu)
 }
 
 void pkvm_hyp_vm_table_init(void *tbl);
-void pkvm_host_fpsimd_state_init(void);
 
 int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva,
 		   unsigned long pgd_hva);

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

@@ -23,20 +23,80 @@ DEFINE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
 
 void __kvm_hyp_host_forward_smc(struct kvm_cpu_context *host_ctxt);
 
+static void __hyp_sve_save_guest(struct kvm_vcpu *vcpu)
+{
+	__vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR);
+	/*
+	 * On saving/restoring guest sve state, always use the maximum VL for
+	 * the guest. The layout of the data when saving the sve state depends
+	 * on the VL, so use a consistent (i.e., the maximum) guest VL.
+	 */
+	sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2);
+	__sve_save_state(vcpu_sve_pffr(vcpu), &vcpu->arch.ctxt.fp_regs.fpsr, true);
+	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
+}
+
+static void __hyp_sve_restore_host(void)
+{
+	struct cpu_sve_state *sve_state = *host_data_ptr(sve_state);
+
+	/*
+	 * On saving/restoring host sve state, always use the maximum VL for
+	 * the host. The layout of the data when saving the sve state depends
+	 * on the VL, so use a consistent (i.e., the maximum) host VL.
+	 *
+	 * Setting ZCR_EL2 to ZCR_ELx_LEN_MASK sets the effective length
+	 * supported by the system (or limited at EL3).
+	 */
+	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
+	__sve_restore_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_sve_max_vl),
+			    &sve_state->fpsr,
+			    true);
+	write_sysreg_el1(sve_state->zcr_el1, SYS_ZCR);
+}
+
+static void fpsimd_sve_flush(void)
+{
+	*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
+}
+
+static void fpsimd_sve_sync(struct kvm_vcpu *vcpu)
+{
+	if (!guest_owns_fp_regs())
+		return;
+
+	cpacr_clear_set(0, CPACR_ELx_FPEN | CPACR_ELx_ZEN);
+	isb();
+
+	if (vcpu_has_sve(vcpu))
+		__hyp_sve_save_guest(vcpu);
+	else
+		__fpsimd_save_state(&vcpu->arch.ctxt.fp_regs);
+
+	if (system_supports_sve())
+		__hyp_sve_restore_host();
+	else
+		__fpsimd_restore_state(*host_data_ptr(fpsimd_state));
+
+	*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
+}
+
 static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 {
 	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
 
+	fpsimd_sve_flush();
+
 	hyp_vcpu->vcpu.arch.ctxt	= host_vcpu->arch.ctxt;
 
 	hyp_vcpu->vcpu.arch.sve_state	= kern_hyp_va(host_vcpu->arch.sve_state);
-	hyp_vcpu->vcpu.arch.sve_max_vl	= host_vcpu->arch.sve_max_vl;
+	/* Limit guest vector length to the maximum supported by the host.  */
+	hyp_vcpu->vcpu.arch.sve_max_vl	= min(host_vcpu->arch.sve_max_vl, kvm_host_sve_max_vl);
 
 	hyp_vcpu->vcpu.arch.hw_mmu	= host_vcpu->arch.hw_mmu;
 
 	hyp_vcpu->vcpu.arch.hcr_el2	= host_vcpu->arch.hcr_el2;
 	hyp_vcpu->vcpu.arch.mdcr_el2	= host_vcpu->arch.mdcr_el2;
-	hyp_vcpu->vcpu.arch.cptr_el2	= host_vcpu->arch.cptr_el2;
 
 	hyp_vcpu->vcpu.arch.iflags	= host_vcpu->arch.iflags;
 
@@ -54,10 +114,11 @@ static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 	struct vgic_v3_cpu_if *host_cpu_if = &host_vcpu->arch.vgic_cpu.vgic_v3;
 	unsigned int i;
 
+	fpsimd_sve_sync(&hyp_vcpu->vcpu);
+
 	host_vcpu->arch.ctxt		= hyp_vcpu->vcpu.arch.ctxt;
 
 	host_vcpu->arch.hcr_el2		= hyp_vcpu->vcpu.arch.hcr_el2;
-	host_vcpu->arch.cptr_el2	= hyp_vcpu->vcpu.arch.cptr_el2;
 
 	host_vcpu->arch.fault		= hyp_vcpu->vcpu.arch.fault;
 
@@ -79,6 +140,17 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
 		struct pkvm_hyp_vcpu *hyp_vcpu;
 		struct kvm *host_kvm;
 
+		/*
+		 * KVM (and pKVM) doesn't support SME guests for now, and
+		 * ensures that SME features aren't enabled in pstate when
+		 * loading a vcpu. Therefore, if SME features enabled the host
+		 * is misbehaving.
+		 */
+		if (unlikely(system_supports_sme() && read_sysreg_s(SYS_SVCR))) {
+			ret = -EINVAL;
+			goto out;
+		}
+
 		host_kvm = kern_hyp_va(host_vcpu->kvm);
 		hyp_vcpu = pkvm_load_hyp_vcpu(host_kvm->arch.pkvm.handle,
 					      host_vcpu->vcpu_idx);
@@ -405,11 +477,7 @@ void handle_trap(struct kvm_cpu_context *host_ctxt)
 		handle_host_smc(host_ctxt);
 		break;
 	case ESR_ELx_EC_SVE:
-		if (has_hvhe())
+		cpacr_clear_set(0, CPACR_ELx_ZEN);
-			sysreg_clear_set(cpacr_el1, 0, (CPACR_EL1_ZEN_EL1EN |
-							CPACR_EL1_ZEN_EL0EN));
-		else
-			sysreg_clear_set(cptr_el2, CPTR_EL2_TZ, 0);
 		isb();
 		sve_cond_update_zcr_vq(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
 		break;

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

@@ -18,6 +18,8 @@ unsigned long __icache_flags;
 /* Used by kvm_get_vttbr(). */
 unsigned int kvm_arm_vmid_bits;
 
+unsigned int kvm_host_sve_max_vl;
+
 /*
  * Set trap register values based on features in ID_AA64PFR0.
  */
@@ -63,7 +65,7 @@ static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu)
 	/* Trap SVE */
 	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_SVE), feature_ids)) {
 		if (has_hvhe())
-			cptr_clear |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;
+			cptr_clear |= CPACR_ELx_ZEN;
 		else
 			cptr_set |= CPTR_EL2_TZ;
 	}
@@ -247,17 +249,6 @@ void pkvm_hyp_vm_table_init(void *tbl)
 	vm_table = tbl;
 }
 
-void pkvm_host_fpsimd_state_init(void)
-{
-	unsigned long i;
-
-	for (i = 0; i < hyp_nr_cpus; i++) {
-		struct kvm_host_data *host_data = per_cpu_ptr(&kvm_host_data, i);
-
-		host_data->fpsimd_state = &host_data->host_ctxt.fp_regs;
-	}
-}
-
 /*
  * Return the hyp vm structure corresponding to the handle.
  */
@@ -586,6 +577,8 @@ unlock:
 	if (ret)
 		unmap_donated_memory(hyp_vcpu, sizeof(*hyp_vcpu));
 
+	hyp_vcpu->vcpu.arch.cptr_el2 = kvm_get_reset_cptr_el2(&hyp_vcpu->vcpu);
+
 	return ret;
 }
 

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

@@ -67,6 +67,28 @@ static int divide_memory_pool(void *virt, unsigned long size)
 	return 0;
 }
 
+static int pkvm_create_host_sve_mappings(void)
+{
+	void *start, *end;
+	int ret, i;
+
+	if (!system_supports_sve())
+		return 0;
+
+	for (i = 0; i < hyp_nr_cpus; i++) {
+		struct kvm_host_data *host_data = per_cpu_ptr(&kvm_host_data, i);
+		struct cpu_sve_state *sve_state = host_data->sve_state;
+
+		start = kern_hyp_va(sve_state);
+		end = start + PAGE_ALIGN(pkvm_host_sve_state_size());
+		ret = pkvm_create_mappings(start, end, PAGE_HYP);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
 				 unsigned long *per_cpu_base,
 				 u32 hyp_va_bits)
@@ -125,6 +147,8 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
 			return ret;
 	}
 
+	pkvm_create_host_sve_mappings();
+
 	/*
 	 * Map the host sections RO in the hypervisor, but transfer the
 	 * ownership from the host to the hypervisor itself to make sure they
@@ -300,7 +324,6 @@ void __noreturn __pkvm_init_finalise(void)
 		goto out;
 
 	pkvm_hyp_vm_table_init(vm_table_base);
-	pkvm_host_fpsimd_state_init();
 out:
 	/*
 	 * We tail-called to here from handle___pkvm_init() and will not return,

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

@@ -48,15 +48,14 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 	val |= has_hvhe() ? CPACR_EL1_TTA : CPTR_EL2_TTA;
 	if (cpus_have_final_cap(ARM64_SME)) {
 		if (has_hvhe())
-			val &= ~(CPACR_EL1_SMEN_EL1EN | CPACR_EL1_SMEN_EL0EN);
+			val &= ~CPACR_ELx_SMEN;
 		else
 			val |= CPTR_EL2_TSM;
 	}
 
 	if (!guest_owns_fp_regs()) {
 		if (has_hvhe())
-			val &= ~(CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN |
+			val &= ~(CPACR_ELx_FPEN | CPACR_ELx_ZEN);
-				 CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN);
 		else
 			val |= CPTR_EL2_TFP | CPTR_EL2_TZ;
 
@@ -182,6 +181,25 @@ static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code)
 		kvm_handle_pvm_sysreg(vcpu, exit_code));
 }
 
+static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Non-protected kvm relies on the host restoring its sve state.
+	 * Protected kvm restores the host's sve state as not to reveal that
+	 * fpsimd was used by a guest nor leak upper sve bits.
+	 */
+	if (unlikely(is_protected_kvm_enabled() && system_supports_sve())) {
+		__hyp_sve_save_host();
+
+		/* Re-enable SVE traps if not supported for the guest vcpu. */
+		if (!vcpu_has_sve(vcpu))
+			cpacr_clear_set(CPACR_ELx_ZEN, 0);
+
+	} else {
+		__fpsimd_save_state(*host_data_ptr(fpsimd_state));
+	}
+}
+
 static const exit_handler_fn hyp_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]		= NULL,
 	[ESR_ELx_EC_CP15_32]		= kvm_hyp_handle_cp15_32,

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

@@ -93,8 +93,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 
 	val = read_sysreg(cpacr_el1);
 	val |= CPACR_ELx_TTA;
-	val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN |
+	val &= ~(CPACR_ELx_ZEN | CPACR_ELx_SMEN);
-		 CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN);
 
 	/*
 	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
@@ -109,9 +108,9 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 
 	if (guest_owns_fp_regs()) {
 		if (vcpu_has_sve(vcpu))
-			val |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;
+			val |= CPACR_ELx_ZEN;
 	} else {
-		val &= ~(CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN);
+		val &= ~CPACR_ELx_FPEN;
 		__activate_traps_fpsimd32(vcpu);
 	}
 
@@ -262,6 +261,11 @@ static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code)
 	return true;
 }
 
+static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
+{
+	__fpsimd_save_state(*host_data_ptr(fpsimd_state));
+}
+
 static const exit_handler_fn hyp_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]		= NULL,
 	[ESR_ELx_EC_CP15_32]		= kvm_hyp_handle_cp15_32,

arch/arm64/kvm/nested.c

@@ -58,8 +58,10 @@ static u64 limit_nv_id_reg(u32 id, u64 val)
 		break;
 
 	case SYS_ID_AA64PFR1_EL1:
-		/* Only support SSBS */
+		/* Only support BTI, SSBS, CSV2_frac */
-		val &= NV_FTR(PFR1, SSBS);
+		val &= (NV_FTR(PFR1, BT)	|
+			NV_FTR(PFR1, SSBS)	|
+			NV_FTR(PFR1, CSV2_frac));
 		break;
 
 	case SYS_ID_AA64MMFR0_EL1:

arch/arm64/kvm/reset.c

@@ -32,6 +32,7 @@
 
 /* Maximum phys_shift supported for any VM on this host */
 static u32 __ro_after_init kvm_ipa_limit;
+unsigned int __ro_after_init kvm_host_sve_max_vl;
 
 /*
  * ARMv8 Reset Values
@@ -51,6 +52,8 @@ int __init kvm_arm_init_sve(void)
 {
 	if (system_supports_sve()) {
 		kvm_sve_max_vl = sve_max_virtualisable_vl();
+		kvm_host_sve_max_vl = sve_max_vl();
+		kvm_nvhe_sym(kvm_host_sve_max_vl) = kvm_host_sve_max_vl;
 
 		/*
 		 * The get_sve_reg()/set_sve_reg() ioctl interface will need

arch/riscv/kvm/aia_device.c

@@ -237,10 +237,11 @@ static gpa_t aia_imsic_ppn(struct kvm_aia *aia, gpa_t addr)
 
 static u32 aia_imsic_hart_index(struct kvm_aia *aia, gpa_t addr)
 {
-	u32 hart, group = 0;
+	u32 hart = 0, group = 0;
 
-	hart = (addr >> (aia->nr_guest_bits + IMSIC_MMIO_PAGE_SHIFT)) &
+	if (aia->nr_hart_bits)
-		GENMASK_ULL(aia->nr_hart_bits - 1, 0);
+		hart = (addr >> (aia->nr_guest_bits + IMSIC_MMIO_PAGE_SHIFT)) &
+		       GENMASK_ULL(aia->nr_hart_bits - 1, 0);
 	if (aia->nr_group_bits)
 		group = (addr >> aia->nr_group_shift) &
 			GENMASK_ULL(aia->nr_group_bits - 1, 0);

arch/riscv/kvm/vcpu_onereg.c

@@ -724,9 +724,9 @@ static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu,
 	switch (reg_subtype) {
 	case KVM_REG_RISCV_ISA_SINGLE:
 		return riscv_vcpu_set_isa_ext_single(vcpu, reg_num, reg_val);
-	case KVM_REG_RISCV_SBI_MULTI_EN:
+	case KVM_REG_RISCV_ISA_MULTI_EN:
 		return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, true);
-	case KVM_REG_RISCV_SBI_MULTI_DIS:
+	case KVM_REG_RISCV_ISA_MULTI_DIS:
 		return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, false);
 	default:
 		return -ENOENT;

arch/x86/kvm/mmu/mmu.c

@@ -4450,9 +4450,6 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 			return RET_PF_EMULATE;
 	}
 
-	fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq;
-	smp_rmb();
-
 	/*
 	 * Check for a relevant mmu_notifier invalidation event before getting
 	 * the pfn from the primary MMU, and before acquiring mmu_lock.

arch/x86/kvm/x86.c

@@ -10718,13 +10718,12 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 
 	bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256);
 
+	static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
+
 	if (irqchip_split(vcpu->kvm))
 		kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors);
-	else {
+	else if (ioapic_in_kernel(vcpu->kvm))
-		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
+		kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
-		if (ioapic_in_kernel(vcpu->kvm))
-			kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
-	}
 
 	if (is_guest_mode(vcpu))
 		vcpu->arch.load_eoi_exitmap_pending = true;

virt/kvm/dirty_ring.c

@@ -55,6 +55,9 @@ static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask)
 	struct kvm_memory_slot *memslot;
 	int as_id, id;
 
+	if (!mask)
+		return;
+
 	as_id = slot >> 16;
 	id = (u16)slot;
 

virt/kvm/guest_memfd.c

@@ -567,8 +567,9 @@ static int __kvm_gmem_get_pfn(struct file *file, struct kvm_memory_slot *slot,
 		return PTR_ERR(folio);
 
 	if (folio_test_hwpoison(folio)) {
-		r = -EHWPOISON;
+		folio_unlock(folio);
-		goto out_unlock;
+		folio_put(folio);
+		return -EHWPOISON;
 	}
 
 	page = folio_file_page(folio, index);
@@ -579,7 +580,6 @@ static int __kvm_gmem_get_pfn(struct file *file, struct kvm_memory_slot *slot,
 
 	r = 0;
 
-out_unlock:
 	folio_unlock(folio);
 
 	return r;

virt/kvm/kvm_main.c

@@ -4427,7 +4427,7 @@ static long kvm_vcpu_ioctl(struct file *filp,
 		struct kvm_regs *kvm_regs;
 
 		r = -ENOMEM;
-		kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL_ACCOUNT);
+		kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL);
 		if (!kvm_regs)
 			goto out;
 		r = kvm_arch_vcpu_ioctl_get_regs(vcpu, kvm_regs);
@@ -4454,8 +4454,7 @@ out_free1:
 		break;
 	}
 	case KVM_GET_SREGS: {
-		kvm_sregs = kzalloc(sizeof(struct kvm_sregs),
+		kvm_sregs = kzalloc(sizeof(struct kvm_sregs), GFP_KERNEL);
-				    GFP_KERNEL_ACCOUNT);
 		r = -ENOMEM;
 		if (!kvm_sregs)
 			goto out;
@@ -4547,7 +4546,7 @@ out_free1:
 		break;
 	}
 	case KVM_GET_FPU: {
-		fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL_ACCOUNT);
+		fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL);
 		r = -ENOMEM;
 		if (!fpu)
 			goto out;
@@ -6210,7 +6209,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
 	active = kvm_active_vms;
 	mutex_unlock(&kvm_lock);
 
-	env = kzalloc(sizeof(*env), GFP_KERNEL_ACCOUNT);
+	env = kzalloc(sizeof(*env), GFP_KERNEL);
 	if (!env)
 		return;
 
@@ -6226,7 +6225,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
 	add_uevent_var(env, "PID=%d", kvm->userspace_pid);
 
 	if (!IS_ERR(kvm->debugfs_dentry)) {
-		char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL_ACCOUNT);
+		char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL);
 
 		if (p) {
 			tmp = dentry_path_raw(kvm->debugfs_dentry, p, PATH_MAX);