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

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - support for SVE and Pointer Authentication in guests
   - PMU improvements

  POWER:
   - support for direct access to the POWER9 XIVE interrupt controller
   - memory and performance optimizations

  x86:
   - support for accessing memory not backed by struct page
   - fixes and refactoring

  Generic:
   - dirty page tracking improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (155 commits)
  kvm: fix compilation on aarch64
  Revert "KVM: nVMX: Expose RDPMC-exiting only when guest supports PMU"
  kvm: x86: Fix L1TF mitigation for shadow MMU
  KVM: nVMX: Disable intercept for FS/GS base MSRs in vmcs02 when possible
  KVM: PPC: Book3S: Remove useless checks in 'release' method of KVM device
  KVM: PPC: Book3S HV: XIVE: Fix spelling mistake "acessing" -> "accessing"
  KVM: PPC: Book3S HV: Make sure to load LPID for radix VCPUs
  kvm: nVMX: Set nested_run_pending in vmx_set_nested_state after checks complete
  tests: kvm: Add tests for KVM_SET_NESTED_STATE
  KVM: nVMX: KVM_SET_NESTED_STATE - Tear down old EVMCS state before setting new state
  tests: kvm: Add tests for KVM_CAP_MAX_VCPUS and KVM_CAP_MAX_CPU_ID
  tests: kvm: Add tests to .gitignore
  KVM: Introduce KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
  KVM: Fix kvm_clear_dirty_log_protect off-by-(minus-)one
  KVM: Fix the bitmap range to copy during clear dirty
  KVM: arm64: Fix ptrauth ID register masking logic
  KVM: x86: use direct accessors for RIP and RSP
  KVM: VMX: Use accessors for GPRs outside of dedicated caching logic
  KVM: x86: Omit caching logic for always-available GPRs
  kvm, x86: Properly check whether a pfn is an MMIO or not
  ...

72 files changed, 4481 insertions, 911 deletions

diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 8927cae7c966..efb0e2c0d84c 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -343,4 +343,6 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
 	}
 }
 
+static inline void vcpu_ptrauth_setup_lazy(struct kvm_vcpu *vcpu) {}
+
 #endif /* __ARM_KVM_EMULATE_H__ */
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 770d73257ad9..075e1921fdd9 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -19,6 +19,7 @@
 #ifndef __ARM_KVM_HOST_H__
 #define __ARM_KVM_HOST_H__
 
+#include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/kvm_types.h>
 #include <asm/cputype.h>
@@ -53,6 +54,8 @@
 
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
+static inline int kvm_arm_init_sve(void) { return 0; }
+
 u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode);
 int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
@@ -150,9 +153,13 @@ struct kvm_cpu_context {
 	u32 cp15[NR_CP15_REGS];
 };
 
-typedef struct kvm_cpu_context kvm_cpu_context_t;
+struct kvm_host_data {
+	struct kvm_cpu_context host_ctxt;
+};
+
+typedef struct kvm_host_data kvm_host_data_t;
 
-static inline void kvm_init_host_cpu_context(kvm_cpu_context_t *cpu_ctxt,
+static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt,
 					     int cpu)
 {
 	/* The host's MPIDR is immutable, so let's set it up at boot time */
@@ -182,7 +189,7 @@ struct kvm_vcpu_arch {
 	struct kvm_vcpu_fault_info fault;
 
 	/* Host FP context */
-	kvm_cpu_context_t *host_cpu_context;
+	struct kvm_cpu_context *host_cpu_context;
 
 	/* VGIC state */
 	struct vgic_cpu vgic_cpu;
@@ -361,6 +368,9 @@ static inline void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) {}
 
+static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {}
+static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {}
+
 static inline void kvm_arm_vhe_guest_enter(void) {}
 static inline void kvm_arm_vhe_guest_exit(void) {}
 
@@ -409,4 +419,14 @@ static inline int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
 	return 0;
 }
 
+static inline int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature)
+{
+	return -EINVAL;
+}
+
+static inline bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu)
+{
+	return true;
+}
+
 #endif /* __ARM_KVM_HOST_H__ */
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 69a59a5d1143..4780eb7af842 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1341,6 +1341,7 @@ menu "ARMv8.3 architectural features"
 config ARM64_PTR_AUTH
 	bool "Enable support for pointer authentication"
 	default y
+	depends on !KVM || ARM64_VHE
 	help
 	  Pointer authentication (part of the ARMv8.3 Extensions) provides
 	  instructions for signing and authenticating pointers against secret
@@ -1354,8 +1355,9 @@ config ARM64_PTR_AUTH
 	  context-switched along with the process.
 
 	  The feature is detected at runtime. If the feature is not present in
-	  hardware it will not be advertised to userspace nor will it be
-	  enabled.
+	  hardware it will not be advertised to userspace/KVM guest nor will it
+	  be enabled. However, KVM guest also require VHE mode and hence
+	  CONFIG_ARM64_VHE=y option to use this feature.
 
 endmenu
 
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index dd1ad3950ef5..df62bbd33a9a 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -24,10 +24,13 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/bitmap.h>
 #include <linux/build_bug.h>
+#include <linux/bug.h>
 #include <linux/cache.h>
 #include <linux/init.h>
 #include <linux/stddef.h>
+#include <linux/types.h>
 
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /* Masks for extracting the FPSR and FPCR from the FPSCR */
@@ -56,7 +59,8 @@ extern void fpsimd_restore_current_state(void);
 extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
 
 extern void fpsimd_bind_task_to_cpu(void);
-extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state);
+extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
+				     void *sve_state, unsigned int sve_vl);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
 extern void fpsimd_flush_cpu_state(void);
@@ -87,6 +91,29 @@ extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
 extern u64 read_zcr_features(void);
 
 extern int __ro_after_init sve_max_vl;
+extern int __ro_after_init sve_max_virtualisable_vl;
+extern __ro_after_init DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX);
+
+/*
+ * Helpers to translate bit indices in sve_vq_map to VQ values (and
+ * vice versa).  This allows find_next_bit() to be used to find the
+ * _maximum_ VQ not exceeding a certain value.
+ */
+static inline unsigned int __vq_to_bit(unsigned int vq)
+{
+	return SVE_VQ_MAX - vq;
+}
+
+static inline unsigned int __bit_to_vq(unsigned int bit)
+{
+	return SVE_VQ_MAX - bit;
+}
+
+/* Ensure vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX before calling this function */
+static inline bool sve_vq_available(unsigned int vq)
+{
+	return test_bit(__vq_to_bit(vq), sve_vq_map);
+}
 
 #ifdef CONFIG_ARM64_SVE
 
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index f5b79e995f40..ff73f5462aca 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -108,7 +108,8 @@ extern u32 __kvm_get_mdcr_el2(void);
 .endm
 
 .macro get_host_ctxt reg, tmp
-	hyp_adr_this_cpu \reg, kvm_host_cpu_state, \tmp
+	hyp_adr_this_cpu \reg, kvm_host_data, \tmp
+	add	\reg, \reg, #HOST_DATA_CONTEXT
 .endm
 
 .macro get_vcpu_ptr vcpu, ctxt
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index d3842791e1c4..613427fafff9 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -98,6 +98,22 @@ static inline void vcpu_set_wfe_traps(struct kvm_vcpu *vcpu)
 	vcpu->arch.hcr_el2 |= HCR_TWE;
 }
 
+static inline void vcpu_ptrauth_enable(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.hcr_el2 |= (HCR_API | HCR_APK);
+}
+
+static inline void vcpu_ptrauth_disable(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.hcr_el2 &= ~(HCR_API | HCR_APK);
+}
+
+static inline void vcpu_ptrauth_setup_lazy(struct kvm_vcpu *vcpu)
+{
+	if (vcpu_has_ptrauth(vcpu))
+		vcpu_ptrauth_disable(vcpu);
+}
+
 static inline unsigned long vcpu_get_vsesr(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.vsesr_el2;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index a01fe087e022..2a8d3f8ca22c 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -22,9 +22,13 @@
 #ifndef __ARM64_KVM_HOST_H__
 #define __ARM64_KVM_HOST_H__
 
+#include <linux/bitmap.h>
 #include <linux/types.h>
+#include <linux/jump_label.h>
 #include <linux/kvm_types.h>
+#include <linux/percpu.h>
 #include <asm/arch_gicv3.h>
+#include <asm/barrier.h>
 #include <asm/cpufeature.h>
 #include <asm/daifflags.h>
 #include <asm/fpsimd.h>
@@ -45,7 +49,7 @@
 
 #define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS
 
-#define KVM_VCPU_MAX_FEATURES 4
+#define KVM_VCPU_MAX_FEATURES 7
 
 #define KVM_REQ_SLEEP \
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
@@ -54,8 +58,12 @@
 
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
+extern unsigned int kvm_sve_max_vl;
+int kvm_arm_init_sve(void);
+
 int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
+void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu);
 int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext);
 void __extended_idmap_trampoline(phys_addr_t boot_pgd, phys_addr_t idmap_start);
 
@@ -117,6 +125,7 @@ enum vcpu_sysreg {
 	SCTLR_EL1,	/* System Control Register */
 	ACTLR_EL1,	/* Auxiliary Control Register */
 	CPACR_EL1,	/* Coprocessor Access Control */
+	ZCR_EL1,	/* SVE Control */
 	TTBR0_EL1,	/* Translation Table Base Register 0 */
 	TTBR1_EL1,	/* Translation Table Base Register 1 */
 	TCR_EL1,	/* Translation Control Register */
@@ -152,6 +161,18 @@ enum vcpu_sysreg {
 	PMSWINC_EL0,	/* Software Increment Register */
 	PMUSERENR_EL0,	/* User Enable Register */
 
+	/* Pointer Authentication Registers in a strict increasing order. */
+	APIAKEYLO_EL1,
+	APIAKEYHI_EL1,
+	APIBKEYLO_EL1,
+	APIBKEYHI_EL1,
+	APDAKEYLO_EL1,
+	APDAKEYHI_EL1,
+	APDBKEYLO_EL1,
+	APDBKEYHI_EL1,
+	APGAKEYLO_EL1,
+	APGAKEYHI_EL1,
+
 	/* 32bit specific registers. Keep them at the end of the range */
 	DACR32_EL2,	/* Domain Access Control Register */
 	IFSR32_EL2,	/* Instruction Fault Status Register */
@@ -212,7 +233,17 @@ struct kvm_cpu_context {
 	struct kvm_vcpu *__hyp_running_vcpu;
 };
 
-typedef struct kvm_cpu_context kvm_cpu_context_t;
+struct kvm_pmu_events {
+	u32 events_host;
+	u32 events_guest;
+};
+
+struct kvm_host_data {
+	struct kvm_cpu_context host_ctxt;
+	struct kvm_pmu_events pmu_events;
+};
+
+typedef struct kvm_host_data kvm_host_data_t;
 
 struct vcpu_reset_state {
 	unsigned long	pc;
@@ -223,6 +254,8 @@ struct vcpu_reset_state {
 
 struct kvm_vcpu_arch {
 	struct kvm_cpu_context ctxt;
+	void *sve_state;
+	unsigned int sve_max_vl;
 
 	/* HYP configuration */
 	u64 hcr_el2;
@@ -255,7 +288,7 @@ struct kvm_vcpu_arch {
 	struct kvm_guest_debug_arch external_debug_state;
 
 	/* Pointer to host CPU context */
-	kvm_cpu_context_t *host_cpu_context;
+	struct kvm_cpu_context *host_cpu_context;
 
 	struct thread_info *host_thread_info;	/* hyp VA */
 	struct user_fpsimd_state *host_fpsimd_state;	/* hyp VA */
@@ -318,12 +351,40 @@ struct kvm_vcpu_arch {
 	bool sysregs_loaded_on_cpu;
 };
 
+/* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
+#define vcpu_sve_pffr(vcpu) ((void *)((char *)((vcpu)->arch.sve_state) + \
+				      sve_ffr_offset((vcpu)->arch.sve_max_vl)))
+
+#define vcpu_sve_state_size(vcpu) ({					\
+	size_t __size_ret;						\
+	unsigned int __vcpu_vq;						\
+									\
+	if (WARN_ON(!sve_vl_valid((vcpu)->arch.sve_max_vl))) {		\
+		__size_ret = 0;						\
+	} else {							\
+		__vcpu_vq = sve_vq_from_vl((vcpu)->arch.sve_max_vl);	\
+		__size_ret = SVE_SIG_REGS_SIZE(__vcpu_vq);		\
+	}								\
+									\
+	__size_ret;							\
+})
+
 /* vcpu_arch flags field values: */
 #define KVM_ARM64_DEBUG_DIRTY		(1 << 0)
 #define KVM_ARM64_FP_ENABLED		(1 << 1) /* guest FP regs loaded */
 #define KVM_ARM64_FP_HOST		(1 << 2) /* host FP regs loaded */
 #define KVM_ARM64_HOST_SVE_IN_USE	(1 << 3) /* backup for host TIF_SVE */
 #define KVM_ARM64_HOST_SVE_ENABLED	(1 << 4) /* SVE enabled for EL0 */
+#define KVM_ARM64_GUEST_HAS_SVE		(1 << 5) /* SVE exposed to guest */
+#define KVM_ARM64_VCPU_SVE_FINALIZED	(1 << 6) /* SVE config completed */
+#define KVM_ARM64_GUEST_HAS_PTRAUTH	(1 << 7) /* PTRAUTH exposed to guest */
+
+#define vcpu_has_sve(vcpu) (system_supports_sve() && \
+			    ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_SVE))
+
+#define vcpu_has_ptrauth(vcpu)	((system_supports_address_auth() || \
+				  system_supports_generic_auth()) && \
+				 ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_PTRAUTH))
 
 #define vcpu_gp_regs(v)		(&(v)->arch.ctxt.gp_regs)
 
@@ -432,9 +493,9 @@ void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome);
 
 struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
 
-DECLARE_PER_CPU(kvm_cpu_context_t, kvm_host_cpu_state);
+DECLARE_PER_CPU(kvm_host_data_t, kvm_host_data);
 
-static inline void kvm_init_host_cpu_context(kvm_cpu_context_t *cpu_ctxt,
+static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt,
 					     int cpu)
 {
 	/* The host's MPIDR is immutable, so let's set it up at boot time */
@@ -452,8 +513,8 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
 	 * kernel's mapping to the linear mapping, and store it in tpidr_el2
 	 * so that we can use adr_l to access per-cpu variables in EL2.
 	 */
-	u64 tpidr_el2 = ((u64)this_cpu_ptr(&kvm_host_cpu_state) -
-			 (u64)kvm_ksym_ref(kvm_host_cpu_state));
+	u64 tpidr_el2 = ((u64)this_cpu_ptr(&kvm_host_data) -
+			 (u64)kvm_ksym_ref(kvm_host_data));
 
 	/*
 	 * Call initialization code, and switch to the full blown HYP code.
@@ -491,9 +552,10 @@ static inline bool kvm_arch_requires_vhe(void)
 	return false;
 }
 
+void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu);
+
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
-static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
 
@@ -516,11 +578,28 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu);
 
+static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr)
+{
+	return (!has_vhe() && attr->exclude_host);
+}
+
 #ifdef CONFIG_KVM /* Avoid conflicts with core headers if CONFIG_KVM=n */
 static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 {
 	return kvm_arch_vcpu_run_map_fp(vcpu);
 }
+
+void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr);
+void kvm_clr_pmu_events(u32 clr);
+
+void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt);
+bool __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt);
+
+void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu);
+void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu);
+#else
+static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {}
+static inline void kvm_clr_pmu_events(u32 clr) {}
 #endif
 
 static inline void kvm_arm_vhe_guest_enter(void)
@@ -594,4 +673,10 @@ void kvm_arch_free_vm(struct kvm *kvm);
 
 int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type);
 
+int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature);
+bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
+
+#define kvm_arm_vcpu_sve_finalized(vcpu) \
+	((vcpu)->arch.flags & KVM_ARM64_VCPU_SVE_FINALIZED)
+
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index c3060833b7a5..09fe8bd15f6e 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -149,7 +149,6 @@ void __debug_switch_to_host(struct kvm_vcpu *vcpu);
 
 void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
 void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
-bool __fpsimd_enabled(void);