Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "This is dominated by a couple large series for ARM and x86
  respectively, but apart from that things are calm.

  ARM:

   - Large set of FP/SVE fixes for pKVM, addressing the fallout from the
     per-CPU data rework and making sure that the host is not involved
     in the FP/SVE switching any more

   - Allow FEAT_BTI to be enabled with NV now that FEAT_PAUTH is
     completely supported

   - Fix for the respective priorities of Failed PAC, Illegal Execution
     state and Instruction Abort exceptions

   - Fix the handling of AArch32 instruction traps failing their
     condition code, which was broken by the introduction of
     ESR_EL2.ISS2

   - Allow vcpus running in AArch32 state to be restored in System mode

   - Fix AArch32 GPR restore that would lose the 64 bit state under some
     conditions

  RISC-V:

   - No need to use mask when hart-index-bits is 0

   - Fix incorrect reg_subtype labels in
     kvm_riscv_vcpu_set_reg_isa_ext()

  x86:

   - Fixes and debugging help for the #VE sanity check.

     Also disable it by default, even for CONFIG_DEBUG_KERNEL, because
     it was found to trigger spuriously (most likely a processor erratum
     as the exact symptoms vary by generation).

   - Avoid WARN() when two NMIs arrive simultaneously during an
     NMI-disabled situation (GIF=0 or interrupt shadow) when the
     processor supports virtual NMI.

     While generally KVM will not request an NMI window when virtual
     NMIs are supported, in this case it *does* have to single-step over
     the interrupt shadow or enable the STGI intercept, in order to
     deliver the latched second NMI.

   - Drop support for hand tuning APIC timer advancement from userspace.

     Since we have adaptive tuning, and it has proved to work well, drop
     the module parameter for manual configuration and with it a few
     stupid bugs that it had"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (32 commits)
  KVM: x86/mmu: Don't save mmu_invalidate_seq after checking private attr
  KVM: arm64: Ensure that SME controls are disabled in protected mode
  KVM: arm64: Refactor CPACR trap bit setting/clearing to use ELx format
  KVM: arm64: Consolidate initializing the host data's fpsimd_state/sve in pKVM
  KVM: arm64: Eagerly restore host fpsimd/sve state in pKVM
  KVM: arm64: Allocate memory mapped at hyp for host sve state in pKVM
  KVM: arm64: Specialize handling of host fpsimd state on trap
  KVM: arm64: Abstract set/clear of CPTR_EL2 bits behind helper
  KVM: arm64: Fix prototype for __sve_save_state/__sve_restore_state
  KVM: arm64: Reintroduce __sve_save_state
  KVM: x86: Drop support for hand tuning APIC timer advancement from userspace
  KVM: SEV-ES: Delegate LBR virtualization to the processor
  KVM: SEV-ES: Disallow SEV-ES guests when X86_FEATURE_LBRV is absent
  KVM: SEV-ES: Prevent MSR access post VMSA encryption
  RISC-V: KVM: Fix incorrect reg_subtype labels in kvm_riscv_vcpu_set_reg_isa_ext function
  RISC-V: KVM: No need to use mask when hart-index-bit is 0
  KVM: arm64: nv: Expose BTI and CSV_frac to a guest hypervisor
  KVM: arm64: nv: Fix relative priorities of exceptions generated by ERETAx
  KVM: arm64: AArch32: Fix spurious trapping of conditional instructions
  KVM: arm64: Allow AArch32 PSTATE.M to be restored as System mode
  ...

Author: torvalds

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 |
-		       CPACR_EL1_ZEN_EL1EN);
+		val = (CPACR_ELx_FPEN | 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
-		 * FPACCOMBINE, deliver an exception right away.  If we
-		 * don't, then let the mangled ELR value trickle down the
+		 * Oh no, ERETAx failed to authenticate.
+		 *
+		 * 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,
-					 CPACR_EL1_SMEN_EL0EN |
-					 CPACR_EL1_SMEN_EL1EN);
+			sysreg_clear_set(CPACR_EL1, 0, CPACR_ELx_SMEN);
 		else
 			sysreg_clear_set(CPACR_EL1,
 					 CPACR_EL1_SMEN_EL0EN,