Merge tag 'kvmarm-for-v5.2' of...

Merge tag 'kvmarm-for-v5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm updates for 5.2

- guest SVE support
- guest Pointer Authentication support
- Better discrimination of perf counters between host and guests

Conflicts:
	include/uapi/linux/kvm.h

Documentation/arm64/perf.txt

+Perf Event Attributes
+=====================
+
+Author: Andrew Murray <andrew.murray@arm.com>
+Date: 2019-03-06
+
+exclude_user
+------------
+
+This attribute excludes userspace.
+
+Userspace always runs at EL0 and thus this attribute will exclude EL0.
+
+
+exclude_kernel
+--------------
+
+This attribute excludes the kernel.
+
+The kernel runs at EL2 with VHE and EL1 without. Guest kernels always run
+at EL1.
+
+For the host this attribute will exclude EL1 and additionally EL2 on a VHE
+system.
+
+For the guest this attribute will exclude EL1. Please note that EL2 is
+never counted within a guest.
+
+
+exclude_hv
+----------
+
+This attribute excludes the hypervisor.
+
+For a VHE host this attribute is ignored as we consider the host kernel to
+be the hypervisor.
+
+For a non-VHE host this attribute will exclude EL2 as we consider the
+hypervisor to be any code that runs at EL2 which is predominantly used for
+guest/host transitions.
+
+For the guest this attribute has no effect. Please note that EL2 is
+never counted within a guest.
+
+
+exclude_host / exclude_guest
+----------------------------
+
+These attributes exclude the KVM host and guest, respectively.
+
+The KVM host may run at EL0 (userspace), EL1 (non-VHE kernel) and EL2 (VHE
+kernel or non-VHE hypervisor).
+
+The KVM guest may run at EL0 (userspace) and EL1 (kernel).
+
+Due to the overlapping exception levels between host and guests we cannot
+exclusively rely on the PMU's hardware exception filtering - therefore we
+must enable/disable counting on the entry and exit to the guest. This is
+performed differently on VHE and non-VHE systems.
+
+For non-VHE systems we exclude EL2 for exclude_host - upon entering and
+exiting the guest we disable/enable the event as appropriate based on the
+exclude_host and exclude_guest attributes.
+
+For VHE systems we exclude EL1 for exclude_guest and exclude both EL0,EL2
+for exclude_host. Upon entering and exiting the guest we modify the event
+to include/exclude EL0 as appropriate based on the exclude_host and
+exclude_guest attributes.
+
+The statements above also apply when these attributes are used within a
+non-VHE guest however please note that EL2 is never counted within a guest.
+
+
+Accuracy
+--------
+
+On non-VHE hosts we enable/disable counters on the entry/exit of host/guest
+transition at EL2 - however there is a period of time between
+enabling/disabling the counters and entering/exiting the guest. We are
+able to eliminate counters counting host events on the boundaries of guest
+entry/exit when counting guest events by filtering out EL2 for
+exclude_host. However when using !exclude_hv there is a small blackout
+window at the guest entry/exit where host events are not captured.
+
+On VHE systems there are no blackout windows.

Documentation/arm64/pointer-authentication.txt

@@ -87,7 +87,21 @@ used to get and set the keys for a thread.
 Virtualization
 --------------
 
-Pointer authentication is not currently supported in KVM guests. KVM
-will mask the feature bits from ID_AA64ISAR1_EL1, and attempted use of
-the feature will result in an UNDEFINED exception being injected into
-the guest.
+Pointer authentication is enabled in KVM guest when each virtual cpu is
+initialised by passing flags KVM_ARM_VCPU_PTRAUTH_[ADDRESS/GENERIC] and
+requesting these two separate cpu features to be enabled. The current KVM
+guest implementation works by enabling both features together, so both
+these userspace flags are checked before enabling pointer authentication.
+The separate userspace flag will allow to have no userspace ABI changes
+if support is added in the future to allow these two features to be
+enabled independently of one another.
+
+As Arm Architecture specifies that Pointer Authentication feature is
+implemented along with the VHE feature so KVM arm64 ptrauth code relies
+on VHE mode to be present.
+
+Additionally, when these vcpu feature flags are not set then KVM will
+filter out the Pointer Authentication system key registers from
+KVM_GET/SET_REG_* ioctls and mask those features from cpufeature ID
+register. Any attempt to use the Pointer Authentication instructions will
+result in an UNDEFINED exception being injected into the guest.

Documentation/virtual/kvm/api.txt

@@ -1883,6 +1883,12 @@ Architectures: all
 Type: vcpu ioctl
 Parameters: struct kvm_one_reg (in)
 Returns: 0 on success, negative value on failure
+Errors:
+  ENOENT:   no such register
+  EINVAL:   invalid register ID, or no such register
+  EPERM:    (arm64) register access not allowed before vcpu finalization
+(These error codes are indicative only: do not rely on a specific error
+code being returned in a specific situation.)
 
 struct kvm_one_reg {
        __u64 id;
@@ -2120,6 +2126,37 @@ contains elements ranging from 32 to 128 bits. The index is a 32bit
 value in the kvm_regs structure seen as a 32bit array.
   0x60x0 0000 0010 <index into the kvm_regs struct:16>
 
+Specifically:
+    Encoding            Register  Bits  kvm_regs member
+----------------------------------------------------------------
+  0x6030 0000 0010 0000 X0          64  regs.regs[0]
+  0x6030 0000 0010 0002 X1          64  regs.regs[1]
+    ...
+  0x6030 0000 0010 003c X30         64  regs.regs[30]
+  0x6030 0000 0010 003e SP          64  regs.sp
+  0x6030 0000 0010 0040 PC          64  regs.pc
+  0x6030 0000 0010 0042 PSTATE      64  regs.pstate
+  0x6030 0000 0010 0044 SP_EL1      64  sp_el1
+  0x6030 0000 0010 0046 ELR_EL1     64  elr_el1
+  0x6030 0000 0010 0048 SPSR_EL1    64  spsr[KVM_SPSR_EL1] (alias SPSR_SVC)
+  0x6030 0000 0010 004a SPSR_ABT    64  spsr[KVM_SPSR_ABT]
+  0x6030 0000 0010 004c SPSR_UND    64  spsr[KVM_SPSR_UND]
+  0x6030 0000 0010 004e SPSR_IRQ    64  spsr[KVM_SPSR_IRQ]
+  0x6060 0000 0010 0050 SPSR_FIQ    64  spsr[KVM_SPSR_FIQ]
+  0x6040 0000 0010 0054 V0         128  fp_regs.vregs[0]    (*)
+  0x6040 0000 0010 0058 V1         128  fp_regs.vregs[1]    (*)
+    ...
+  0x6040 0000 0010 00d0 V31        128  fp_regs.vregs[31]   (*)
+  0x6020 0000 0010 00d4 FPSR        32  fp_regs.fpsr
+  0x6020 0000 0010 00d5 FPCR        32  fp_regs.fpcr
+
+(*) These encodings are not accepted for SVE-enabled vcpus.  See
+    KVM_ARM_VCPU_INIT.
+
+    The equivalent register content can be accessed via bits [127:0] of
+    the corresponding SVE Zn registers instead for vcpus that have SVE
+    enabled (see below).
+
 arm64 CCSIDR registers are demultiplexed by CSSELR value:
   0x6020 0000 0011 00 <csselr:8>
 
@@ -2129,6 +2166,64 @@ arm64 system registers have the following id bit patterns:
 arm64 firmware pseudo-registers have the following bit pattern:
   0x6030 0000 0014 <regno:16>
 
+arm64 SVE registers have the following bit patterns:
+  0x6080 0000 0015 00 <n:5> <slice:5>   Zn bits[2048*slice + 2047 : 2048*slice]
+  0x6050 0000 0015 04 <n:4> <slice:5>   Pn bits[256*slice + 255 : 256*slice]
+  0x6050 0000 0015 060 <slice:5>        FFR bits[256*slice + 255 : 256*slice]
+  0x6060 0000 0015 ffff                 KVM_REG_ARM64_SVE_VLS pseudo-register
+
+Access to register IDs where 2048 * slice >= 128 * max_vq will fail with
+ENOENT.  max_vq is the vcpu's maximum supported vector length in 128-bit
+quadwords: see (**) below.
+
+These registers are only accessible on vcpus for which SVE is enabled.
+See KVM_ARM_VCPU_INIT for details.
+
+In addition, except for KVM_REG_ARM64_SVE_VLS, these registers are not
+accessible until the vcpu's SVE configuration has been finalized
+using KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE).  See KVM_ARM_VCPU_INIT
+and KVM_ARM_VCPU_FINALIZE for more information about this procedure.
+
+KVM_REG_ARM64_SVE_VLS is a pseudo-register that allows the set of vector
+lengths supported by the vcpu to be discovered and configured by
+userspace.  When transferred to or from user memory via KVM_GET_ONE_REG
+or KVM_SET_ONE_REG, the value of this register is of type
+__u64[KVM_ARM64_SVE_VLS_WORDS], and encodes the set of vector lengths as
+follows:
+
+__u64 vector_lengths[KVM_ARM64_SVE_VLS_WORDS];
+
+if (vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX &&
+    ((vector_lengths[(vq - KVM_ARM64_SVE_VQ_MIN) / 64] >>
+		((vq - KVM_ARM64_SVE_VQ_MIN) % 64)) & 1))
+	/* Vector length vq * 16 bytes supported */
+else
+	/* Vector length vq * 16 bytes not supported */
+
+(**) The maximum value vq for which the above condition is true is
+max_vq.  This is the maximum vector length available to the guest on
+this vcpu, and determines which register slices are visible through
+this ioctl interface.
+
+(See Documentation/arm64/sve.txt for an explanation of the "vq"
+nomenclature.)
+
+KVM_REG_ARM64_SVE_VLS is only accessible after KVM_ARM_VCPU_INIT.
+KVM_ARM_VCPU_INIT initialises it to the best set of vector lengths that
+the host supports.
+
+Userspace may subsequently modify it if desired until the vcpu's SVE
+configuration is finalized using KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE).
+
+Apart from simply removing all vector lengths from the host set that
+exceed some value, support for arbitrarily chosen sets of vector lengths
+is hardware-dependent and may not be available.  Attempting to configure
+an invalid set of vector lengths via KVM_SET_ONE_REG will fail with
+EINVAL.
+
+After the vcpu's SVE configuration is finalized, further attempts to
+write this register will fail with EPERM.
+
 
 MIPS registers are mapped using the lower 32 bits.  The upper 16 of that is
 the register group type:
@@ -2181,6 +2276,12 @@ Architectures: all
 Type: vcpu ioctl
 Parameters: struct kvm_one_reg (in and out)
 Returns: 0 on success, negative value on failure
+Errors include:
+  ENOENT:   no such register
+  EINVAL:   invalid register ID, or no such register
+  EPERM:    (arm64) register access not allowed before vcpu finalization
+(These error codes are indicative only: do not rely on a specific error
+code being returned in a specific situation.)
 
 This ioctl allows to receive the value of a single register implemented
 in a vcpu. The register to read is indicated by the "id" field of the
@@ -2673,6 +2774,49 @@ Possible features:
 	- KVM_ARM_VCPU_PMU_V3: Emulate PMUv3 for the CPU.
 	  Depends on KVM_CAP_ARM_PMU_V3.
 
+	- KVM_ARM_VCPU_PTRAUTH_ADDRESS: Enables Address Pointer authentication
+	  for arm64 only.
+	  Depends on KVM_CAP_ARM_PTRAUTH_ADDRESS.
+	  If KVM_CAP_ARM_PTRAUTH_ADDRESS and KVM_CAP_ARM_PTRAUTH_GENERIC are
+	  both present, then both KVM_ARM_VCPU_PTRAUTH_ADDRESS and
+	  KVM_ARM_VCPU_PTRAUTH_GENERIC must be requested or neither must be
+	  requested.
+
+	- KVM_ARM_VCPU_PTRAUTH_GENERIC: Enables Generic Pointer authentication
+	  for arm64 only.
+	  Depends on KVM_CAP_ARM_PTRAUTH_GENERIC.
+	  If KVM_CAP_ARM_PTRAUTH_ADDRESS and KVM_CAP_ARM_PTRAUTH_GENERIC are
+	  both present, then both KVM_ARM_VCPU_PTRAUTH_ADDRESS and
+	  KVM_ARM_VCPU_PTRAUTH_GENERIC must be requested or neither must be
+	  requested.
+
+	- KVM_ARM_VCPU_SVE: Enables SVE for the CPU (arm64 only).
+	  Depends on KVM_CAP_ARM_SVE.
+	  Requires KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE):
+
+	   * After KVM_ARM_VCPU_INIT:
+
+	      - KVM_REG_ARM64_SVE_VLS may be read using KVM_GET_ONE_REG: the
+	        initial value of this pseudo-register indicates the best set of
+	        vector lengths possible for a vcpu on this host.
+
+	   * Before KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE):
+
+	      - KVM_RUN and KVM_GET_REG_LIST are not available;
+
+	      - KVM_GET_ONE_REG and KVM_SET_ONE_REG cannot be used to access
+	        the scalable archietctural SVE registers
+	        KVM_REG_ARM64_SVE_ZREG(), KVM_REG_ARM64_SVE_PREG() or
+	        KVM_REG_ARM64_SVE_FFR;
+
+	      - KVM_REG_ARM64_SVE_VLS may optionally be written using
+	        KVM_SET_ONE_REG, to modify the set of vector lengths available
+	        for the vcpu.
+
+	   * After KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE):
+
+	      - the KVM_REG_ARM64_SVE_VLS pseudo-register is immutable, and can
+	        no longer be written using KVM_SET_ONE_REG.
 
 4.83 KVM_ARM_PREFERRED_TARGET
 
@@ -3887,6 +4031,40 @@ number of valid entries in the 'entries' array, which is then filled.
 'index' and 'flags' fields in 'struct kvm_cpuid_entry2' are currently reserved,
 userspace should not expect to get any particular value there.
 
+4.119 KVM_ARM_VCPU_FINALIZE
+
+Architectures: arm, arm64
+Type: vcpu ioctl
+Parameters: int feature (in)
+Returns: 0 on success, -1 on error
+Errors:
+  EPERM:     feature not enabled, needs configuration, or already finalized
+  EINVAL:    feature unknown or not present
+
+Recognised values for feature:
+  arm64      KVM_ARM_VCPU_SVE (requires KVM_CAP_ARM_SVE)
+
+Finalizes the configuration of the specified vcpu feature.
+
+The vcpu must already have been initialised, enabling the affected feature, by
+means of a successful KVM_ARM_VCPU_INIT call with the appropriate flag set in
+features[].
+
+For affected vcpu features, this is a mandatory step that must be performed
+before the vcpu is fully usable.
+
+Between KVM_ARM_VCPU_INIT and KVM_ARM_VCPU_FINALIZE, the feature may be
+configured by use of ioctls such as KVM_SET_ONE_REG.  The exact configuration
+that should be performaned and how to do it are feature-dependent.
+
+Other calls that depend on a particular feature being finalized, such as
+KVM_RUN, KVM_GET_REG_LIST, KVM_GET_ONE_REG and KVM_SET_ONE_REG, will fail with
+-EPERM unless the feature has already been finalized by means of a
+KVM_ARM_VCPU_FINALIZE call.
+
+See KVM_ARM_VCPU_INIT for details of vcpu features that require finalization
+using this ioctl.
+
 5. The kvm_run structure
 ------------------------
 

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__ */

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__ */

arch/arm64/Kconfig

@@ -1288,6 +1288,7 @@ 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
@@ -1301,8 +1302,9 @@ 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
 

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
 

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

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;

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__ */

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);
 
 void activate_traps_vhe_load(struct kvm_vcpu *vcpu);
 void deactivate_traps_vhe_put(void);

arch/arm64/include/asm/kvm_ptrauth.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/* arch/arm64/include/asm/kvm_ptrauth.h: Guest/host ptrauth save/restore
+ * Copyright 2019 Arm Limited
+ * Authors: Mark Rutland <mark.rutland@arm.com>
+ *         Amit Daniel Kachhap <amit.kachhap@arm.com>
+ */
+
+#ifndef __ASM_KVM_PTRAUTH_H
+#define __ASM_KVM_PTRAUTH_H
+
+#ifdef __ASSEMBLY__
+
+#include <asm/sysreg.h>
+
+#ifdef	CONFIG_ARM64_PTR_AUTH
+
+#define PTRAUTH_REG_OFFSET(x)	(x - CPU_APIAKEYLO_EL1)
+
+/*
+ * CPU_AP*_EL1 values exceed immediate offset range (512) for stp
+ * instruction so below macros takes CPU_APIAKEYLO_EL1 as base and
+ * calculates the offset of the keys from this base to avoid an extra add
+ * instruction. These macros assumes the keys offsets follow the order of
+ * the sysreg enum in kvm_host.h.
+ */
+.macro	ptrauth_save_state base, reg1, reg2
+	mrs_s	\reg1, SYS_APIAKEYLO_EL1
+	mrs_s	\reg2, SYS_APIAKEYHI_EL1
+	stp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APIAKEYLO_EL1)]
+	mrs_s	\reg1, SYS_APIBKEYLO_EL1
+	mrs_s	\reg2, SYS_APIBKEYHI_EL1
+	stp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APIBKEYLO_EL1)]
+	mrs_s	\reg1, SYS_APDAKEYLO_EL1
+	mrs_s	\reg2, SYS_APDAKEYHI_EL1
+	stp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APDAKEYLO_EL1)]
+	mrs_s	\reg1, SYS_APDBKEYLO_EL1
+	mrs_s	\reg2, SYS_APDBKEYHI_EL1
+	stp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APDBKEYLO_EL1)]
+	mrs_s	\reg1, SYS_APGAKEYLO_EL1
+	mrs_s	\reg2, SYS_APGAKEYHI_EL1
+	stp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APGAKEYLO_EL1)]
+.endm
+
+.macro	ptrauth_restore_state base, reg1, reg2
+	ldp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APIAKEYLO_EL1)]
+	msr_s	SYS_APIAKEYLO_EL1, \reg1
+	msr_s	SYS_APIAKEYHI_EL1, \reg2
+	ldp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APIBKEYLO_EL1)]
+	msr_s	SYS_APIBKEYLO_EL1, \reg1
+	msr_s	SYS_APIBKEYHI_EL1, \reg2
+	ldp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APDAKEYLO_EL1)]
+	msr_s	SYS_APDAKEYLO_EL1, \reg1
+	msr_s	SYS_APDAKEYHI_EL1, \reg2
+	ldp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APDBKEYLO_EL1)]
+	msr_s	SYS_APDBKEYLO_EL1, \reg1
+	msr_s	SYS_APDBKEYHI_EL1, \reg2
+	ldp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APGAKEYLO_EL1)]
+	msr_s	SYS_APGAKEYLO_EL1, \reg1
+	msr_s	SYS_APGAKEYHI_EL1, \reg2
+.endm
+
+/*
+ * Both ptrauth_switch_to_guest and ptrauth_switch_to_host macros will
+ * check for the presence of one of the cpufeature flag
+ * ARM64_HAS_ADDRESS_AUTH_ARCH or ARM64_HAS_ADDRESS_AUTH_IMP_DEF and
+ * then proceed ahead with the save/restore of Pointer Authentication
+ * key registers.
+ */
+.macro ptrauth_switch_to_guest g_ctxt, reg1, reg2, reg3
+alternative_if ARM64_HAS_ADDRESS_AUTH_ARCH
+	b	1000f
+alternative_else_nop_endif
+alternative_if_not ARM64_HAS_ADDRESS_AUTH_IMP_DEF
+	b	1001f
+alternative_else_nop_endif
+1000:
+	ldr	\reg1, [\g_ctxt, #(VCPU_HCR_EL2 - VCPU_CONTEXT)]
+	and	\reg1, \reg1, #(HCR_API | HCR_APK)
+	cbz	\reg1, 1001f
+	add	\reg1, \g_ctxt, #CPU_APIAKEYLO_EL1
+	ptrauth_restore_state	\reg1, \reg2, \reg3
+1001:
+.endm
+
+.macro ptrauth_switch_to_host g_ctxt, h_ctxt, reg1, reg2, reg3
+alternative_if ARM64_HAS_ADDRESS_AUTH_ARCH
+	b	2000f
+alternative_else_nop_endif
+alternative_if_not ARM64_HAS_ADDRESS_AUTH_IMP_DEF
+	b	2001f
+alternative_else_nop_endif
+2000:
+	ldr	\reg1, [\g_ctxt, #(VCPU_HCR_EL2 - VCPU_CONTEXT)]
+	and	\reg1, \reg1, #(HCR_API | HCR_APK)
+	cbz	\reg1, 2001f
+	add	\reg1, \g_ctxt, #CPU_APIAKEYLO_EL1
+	ptrauth_save_state	\reg1, \reg2, \reg3
+	add	\reg1, \h_ctxt, #CPU_APIAKEYLO_EL1
+	ptrauth_restore_state	\reg1, \reg2, \reg3
+	isb
+2001:
+.endm
+
+#else /* !CONFIG_ARM64_PTR_AUTH */
+.macro ptrauth_switch_to_guest g_ctxt, reg1, reg2, reg3
+.endm
+.macro ptrauth_switch_to_host g_ctxt, h_ctxt, reg1, reg2, reg3
+.endm
+#endif /* CONFIG_ARM64_PTR_AUTH */
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_KVM_PTRAUTH_H */

arch/arm64/include/asm/sysreg.h

@@ -454,6 +454,9 @@
 #define SYS_ICH_LR14_EL2		__SYS__LR8_EL2(6)
 #define SYS_ICH_LR15_EL2		__SYS__LR8_EL2(7)
 
+/* VHE encodings for architectural EL0/1 system registers */
+#define SYS_ZCR_EL12			sys_reg(3, 5, 1, 2, 0)
+
 /* Common SCTLR_ELx flags. */
 #define SCTLR_ELx_DSSBS	(_BITUL(44))
 #define SCTLR_ELx_ENIA	(_BITUL(31))

arch/arm64/include/uapi/asm/kvm.h

@@ -35,6 +35,7 @@
 #include <linux/psci.h>
 #include <linux/types.h>
 #include <asm/ptrace.h>
+#include <asm/sve_context.h>
 
 #define __KVM_HAVE_GUEST_DEBUG
 #define __KVM_HAVE_IRQ_LINE
@@ -102,6 +103,9 @@ struct kvm_regs {
 #define KVM_ARM_VCPU_EL1_32BIT		1 /* CPU running a 32bit VM */
 #define KVM_ARM_VCPU_PSCI_0_2		2 /* CPU uses PSCI v0.2 */
 #define KVM_ARM_VCPU_PMU_V3		3 /* Support guest PMUv3 */
+#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 */
 
 struct kvm_vcpu_init {
 	__u32 target;
@@ -226,6 +230,45 @@ struct kvm_vcpu_events {
 					 KVM_REG_ARM_FW | ((r) & 0xffff))
 #define KVM_REG_ARM_PSCI_VERSION	KVM_REG_ARM_FW_REG(0)
 
+/* SVE registers */
+#define KVM_REG_ARM64_SVE		(0x15 << KVM_REG_ARM_COPROC_SHIFT)
+
+/* Z- and P-regs occupy blocks at the following offsets within this range: */
+#define KVM_REG_ARM64_SVE_ZREG_BASE	0
+#define KVM_REG_ARM64_SVE_PREG_BASE	0x400
+#define KVM_REG_ARM64_SVE_FFR_BASE	0x600
+
+#define KVM_ARM64_SVE_NUM_ZREGS		__SVE_NUM_ZREGS
+#define KVM_ARM64_SVE_NUM_PREGS		__SVE_NUM_PREGS
+
+#define KVM_ARM64_SVE_MAX_SLICES	32
+
+#define KVM_REG_ARM64_SVE_ZREG(n, i)					\
+	(KVM_REG_ARM64 | KVM_REG_ARM64_SVE | KVM_REG_ARM64_SVE_ZREG_BASE | \
+	 KVM_REG_SIZE_U2048 |						\
+	 (((n) & (KVM_ARM64_SVE_NUM_ZREGS - 1)) << 5) |			\
+	 ((i) & (KVM_ARM64_SVE_MAX_SLICES - 1)))
+
+#define KVM_REG_ARM64_SVE_PREG(n, i)					\
+	(KVM_REG_ARM64 | KVM_REG_ARM64_SVE | KVM_REG_ARM64_SVE_PREG_BASE | \
+	 KVM_REG_SIZE_U256 |						\
+	 (((n) & (KVM_ARM64_SVE_NUM_PREGS - 1)) << 5) |			\
+	 ((i) & (KVM_ARM64_SVE_MAX_SLICES - 1)))
+
+#define KVM_REG_ARM64_SVE_FFR(i)					\
+	(KVM_REG_ARM64 | KVM_REG_ARM64_SVE | KVM_REG_ARM64_SVE_FFR_BASE | \
+	 KVM_REG_SIZE_U256 |						\
+	 ((i) & (KVM_ARM64_SVE_MAX_SLICES - 1)))
+
+#define KVM_ARM64_SVE_VQ_MIN __SVE_VQ_MIN
+#define KVM_ARM64_SVE_VQ_MAX __SVE_VQ_MAX
+
+/* Vector lengths pseudo-register: */
+#define KVM_REG_ARM64_SVE_VLS		(KVM_REG_ARM64 | KVM_REG_ARM64_SVE | \
+					 KVM_REG_SIZE_U512 | 0xffff)
+#define KVM_ARM64_SVE_VLS_WORDS	\
+	((KVM_ARM64_SVE_VQ_MAX - KVM_ARM64_SVE_VQ_MIN) / 64 + 1)
+
 /* Device Control API: ARM VGIC */
 #define KVM_DEV_ARM_VGIC_GRP_ADDR	0
 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1

arch/arm64/kernel/asm-offsets.c

@@ -125,9 +125,16 @@ int main(void)
   DEFINE(VCPU_CONTEXT,		offsetof(struct kvm_vcpu, arch.ctxt));
   DEFINE(VCPU_FAULT_DISR,	offsetof(struct kvm_vcpu, arch.fault.disr_el1));
   DEFINE(VCPU_WORKAROUND_FLAGS,	offsetof(struct kvm_vcpu, arch.workaround_flags));
+  DEFINE(VCPU_HCR_EL2,		offsetof(struct kvm_vcpu, arch.hcr_el2));
   DEFINE(CPU_GP_REGS,		offsetof(struct kvm_cpu_context, gp_regs));
+  DEFINE(CPU_APIAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APIAKEYLO_EL1]));
+  DEFINE(CPU_APIBKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APIBKEYLO_EL1]));
+  DEFINE(CPU_APDAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APDAKEYLO_EL1]));
+  DEFINE(CPU_APDBKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APDBKEYLO_EL1]));
+  DEFINE(CPU_APGAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APGAKEYLO_EL1]));
   DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_regs, regs));
   DEFINE(HOST_CONTEXT_VCPU,	offsetof(struct kvm_cpu_context, __hyp_running_vcpu));
+  DEFINE(HOST_DATA_CONTEXT,	offsetof(struct kvm_host_data, host_ctxt));
 #endif
 #ifdef CONFIG_CPU_PM
   DEFINE(CPU_CTX_SP,		offsetof(struct cpu_suspend_ctx, sp));

arch/arm64/kernel/cpufeature.c

@@ -1863,7 +1863,7 @@ static void verify_sve_features(void)
 	unsigned int len = zcr & ZCR_ELx_LEN_MASK;
 
 	if (len < safe_len || sve_verify_vq_map()) {
-		pr_crit("CPU%d: SVE: required vector length(s) missing\n",
+		pr_crit("CPU%d: SVE: vector length support mismatch\n",
 			smp_processor_id());
 		cpu_die_early();
 	}

arch/arm64/kernel/fpsimd.c

@@ -18,6 +18,7 @@
  */
 
 #include <linux/bitmap.h>
+#include <linux/bitops.h>
 #include <linux/bottom_half.h>
 #include <linux/bug.h>
 #include <linux/cache.h>
@@ -48,6 +49,7 @@
 #include <asm/sigcontext.h>
 #include <asm/sysreg.h>
 #include <asm/traps.h>
+#include <asm/virt.h>
 
 #define FPEXC_IOF	(1 << 0)
 #define FPEXC_DZF	(1 << 1)
@@ -119,6 +121,8 @@
  */
 struct fpsimd_last_state_struct {
 	struct user_fpsimd_state *st;
+	void *sve_state;
+	unsigned int sve_vl;
 };
 
 static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);
@@ -130,14 +134,23 @@ static int sve_default_vl = -1;
 
 /* Maximum supported vector length across all CPUs (initially poisoned) */
 int __ro_after_init sve_max_vl = SVE_VL_MIN;
-/* Set of available vector lengths, as vq_to_bit(vq): */
-static __ro_after_init DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX);
+int __ro_after_init sve_max_virtualisable_vl = SVE_VL_MIN;
+
+/*
+ * Set of available vector lengths,
+ * where length vq encoded as bit __vq_to_bit(vq):
+ */
+__ro_after_init DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX);
+/* Set of vector lengths present on at least one cpu: */
+static __ro_after_init DECLARE_BITMAP(sve_vq_partial_map, SVE_VQ_MAX);
+
 static void __percpu *efi_sve_state;
 
 #else /* ! CONFIG_ARM64_SVE */
 
 /* Dummy declaration for code that will be optimised out: */
 extern __ro_after_init DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX);
+extern __ro_after_init DECLARE_BITMAP(sve_vq_partial_map, SVE_VQ_MAX);
 extern void __percpu *efi_sve_state;
 
 #endif /* ! CONFIG_ARM64_SVE */
@@ -235,14 +248,15 @@ static void task_fpsimd_load(void)
  */
 void fpsimd_save(void)
 {
-	struct user_fpsimd_state *st = __this_cpu_read(fpsimd_last_state.st);
+	struct fpsimd_last_state_struct const *last =
+		this_cpu_ptr(&fpsimd_last_state);
 	/* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */
 
 	WARN_ON(!in_softirq() && !irqs_disabled());
 
 	if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
 		if (system_supports_sve() && test_thread_flag(TIF_SVE)) {
-			if (WARN_ON(sve_get_vl() != current->thread.sve_vl)) {
+			if (WARN_ON(sve_get_vl() != last->sve_vl)) {
 				/*
 				 * Can't save the user regs, so current would
 				 * re-enter user with corrupt state.
@@ -252,31 +266,14 @@ void fpsimd_save(void)
 				return;
 			}
 
-			sve_save_state(sve_pffr(&current->thread), &st->fpsr);
+			sve_save_state((char *)last->sve_state +
+						sve_ffr_offset(last->sve_vl),
+				       &last->st->fpsr);
 		} else
-			fpsimd_save_state(st);
+			fpsimd_save_state(last->st);
 	}
 }
 
-/*
- * 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 unsigned int vq_to_bit(unsigned int vq)
-{
-	return SVE_VQ_MAX - vq;
-}
-
-static unsigned int bit_to_vq(unsigned int bit)
-{
-	if (WARN_ON(bit >= SVE_VQ_MAX))
-		bit = SVE_VQ_MAX - 1;
-
-	return SVE_VQ_MAX - bit;
-}
-
 /*
  * All vector length selection from userspace comes through here.
  * We're on a slow path, so some sanity-checks are included.
@@ -298,8 +295,8 @@ static unsigned int find_supported_vector_length(unsigned int vl)
 		vl = max_vl;
 
 	bit = find_next_bit(sve_vq_map, SVE_VQ_MAX,
-			    vq_to_bit(sve_vq_from_vl(vl)));
-	return sve_vl_from_vq(bit_to_vq(bit));
+			    __vq_to_bit(sve_vq_from_vl(vl)));
+	return sve_vl_from_vq(__bit_to_vq(bit));
 }
 
 #ifdef CONFIG_SYSCTL
@@ -550,7 +547,6 @@ int sve_set_vector_length(struct task_struct *task,
 		local_bh_disable();
 
 		fpsimd_save();
-		set_thread_flag(TIF_FOREIGN_FPSTATE);
 	}
 
 	fpsimd_flush_task_state(task);
@@ -624,12 +620,6 @@ int sve_get_current_vl(void)
 	return sve_prctl_status(0);
 }
 
-/*
- * Bitmap for temporary storage of the per-CPU set of supported vector lengths
- * during secondary boot.
- */
-static DECLARE_BITMAP(sve_secondary_vq_map, SVE_VQ_MAX);
-
 static void sve_probe_vqs(DECLARE_BITMAP(map, SVE_VQ_MAX))
 {
 	unsigned int vq, vl;
@@ -644,40 +634,82 @@ static void sve_probe_vqs(DECLARE_BITMAP(map, SVE_VQ_MAX))
 		write_sysreg_s(zcr | (vq - 1), SYS_ZCR_EL1); /* self-syncing */
 		vl = sve_get_vl();
 		vq = sve_vq_from_vl(vl); /* skip intervening lengths */
-		set_bit(vq_to_bit(vq), map);
+		set_bit(__vq_to_bit(vq), map);
 	}
 }
 
+/*
+ * Initialise the set of known supported VQs for the boot CPU.
+ * This is called during kernel boot, before secondary CPUs are brought up.
+ */
 void __init sve_init_vq_map(void)
 {
 	sve_probe_vqs(sve_vq_map);
+	bitmap_copy(sve_vq_partial_map, sve_vq_map, SVE_VQ_MAX);
 }
 
 /*
  * If we haven't committed to the set of supported VQs yet, filter out
  * those not supported by the current CPU.
+ * This function is called during the bring-up of early secondary CPUs only.
  */
 void sve_update_vq_map(void)
 {
-	sve_probe_vqs(sve_secondary_vq_map);
-	bitmap_and(sve_vq_map, sve_vq_map, sve_secondary_vq_map, SVE_VQ_MAX);
+	DECLARE_BITMAP(tmp_map, SVE_VQ_MAX);
+
+	sve_probe_vqs(tmp_map);
+	bitmap_and(sve_vq_map, sve_vq_map, tmp_map, SVE_VQ_MAX);
+	bitmap_or(sve_vq_partial_map, sve_vq_partial_map, tmp_map, SVE_VQ_MAX);
 }
 
-/* Check whether the current CPU supports all VQs in the committed set */
+/*
+ * Check whether the current CPU supports all VQs in the committed set.
+ * This function is called during the bring-up of late secondary CPUs only.
+ */
 int sve_verify_vq_map(void)
 {
-	int ret = 0;
+	DECLARE_BITMAP(tmp_map, SVE_VQ_MAX);
+	unsigned long b;
 
-	sve_probe_vqs(sve_secondary_vq_map);
-	bitmap_andnot(sve_secondary_vq_map, sve_vq_map, sve_secondary_vq_map,
-		      SVE_VQ_MAX);
-	if (!bitmap_empty(sve_secondary_vq_map, SVE_VQ_MAX)) {
+	sve_probe_vqs(tmp_map);
+
+	bitmap_complement(tmp_map, tmp_map, SVE_VQ_MAX);
+	if (bitmap_intersects(tmp_map, sve_vq_map, SVE_VQ_MAX)) {
 		pr_warn("SVE: cpu%d: Required vector length(s) missing\n",
 			smp_processor_id());
-		ret = -EINVAL;
+		return -EINVAL;
 	}
 
-	return ret;
+	if (!IS_ENABLED(CONFIG_KVM) || !is_hyp_mode_available())
+		return 0;
+
+	/*
+	 * For KVM, it is necessary to ensure that this CPU doesn't
+	 * support any vector length that guests may have probed as
+	 * unsupported.
+	 */
+
+	/* Recover the set of supported VQs: */
+	bitmap_complement(tmp_map, tmp_map, SVE_VQ_MAX);
+	/* Find VQs supported that are not globally supported: */
+	bitmap_andnot(tmp_map, tmp_map, sve_vq_map, SVE_VQ_MAX);
+
+	/* Find the lowest such VQ, if any: */
+	b = find_last_bit(tmp_map, SVE_VQ_MAX);
+	if (b >= SVE_VQ_MAX)
+		return 0; /* no mismatches */
+
+	/*
+	 * Mismatches above sve_max_virtualisable_vl are fine, since
+	 * no guest is allowed to configure ZCR_EL2.LEN to exceed this:
+	 */
+	if (sve_vl_from_vq(__bit_to_vq(b)) <= sve_max_virtualisable_vl) {
+		pr_warn("SVE: cpu%d: Unsupported vector length(s) present\n",
+			smp_processor_id());
+		return -EINVAL;
+	}
+
+	return 0;
 }
 
 static void __init sve_efi_setup(void)
@@ -744,6 +776,8 @@ u64 read_zcr_features(void)
 void __init sve_setup(void)
 {
 	u64 zcr;
+	DECLARE_BITMAP(tmp_map, SVE_VQ_MAX);
+	unsigned long b;
 
 	if (!system_supports_sve())
 		return;
@@ -753,8 +787,8 @@ void __init sve_setup(void)
 	 * so sve_vq_map must have at least SVE_VQ_MIN set.
 	 * If something went wrong, at least try to patch it up:
 	 */
-	if (WARN_ON(!test_bit(vq_to_bit(SVE_VQ_MIN), sve_vq_map)))
-		set_bit(vq_to_bit(SVE_VQ_MIN), sve_vq_map);
+	if (WARN_ON(!test_bit(__vq_to_bit(SVE_VQ_MIN), sve_vq_map)))
+		set_bit(__vq_to_bit(SVE_VQ_MIN), sve_vq_map);
 
 	zcr = read_sanitised_ftr_reg(SYS_ZCR_EL1);
 	sve_max_vl = sve_vl_from_vq((zcr & ZCR_ELx_LEN_MASK) + 1);
@@ -772,11 +806,31 @@ void __init sve_setup(void)
 	 */
 	sve_default_vl = find_supported_vector_length(64);
 
+	bitmap_andnot(tmp_map, sve_vq_partial_map, sve_vq_map,
+		      SVE_VQ_MAX);
+
+	b = find_last_bit(tmp_map, SVE_VQ_MAX);
+	if (b >= SVE_VQ_MAX)
+		/* No non-virtualisable VLs found */
+		sve_max_virtualisable_vl = SVE_VQ_MAX;
+	else if (WARN_ON(b == SVE_VQ_MAX - 1))
+		/* No virtualisable VLs?  This is architecturally forbidden. */
+		sve_max_virtualisable_vl = SVE_VQ_MIN;
+	else /* b + 1 < SVE_VQ_MAX */
+		sve_max_virtualisable_vl = sve_vl_from_vq(__bit_to_vq(b + 1));
+
+	if (sve_max_virtualisable_vl > sve_max_vl)
+		sve_max_virtualisable_vl = sve_max_vl;
+
 	pr_info("SVE: maximum available vector length %u bytes per vector\n",
 		sve_max_vl);
 	pr_info("SVE: default vector length %u bytes per vector\n",
 		sve_default_vl);
 
+	/* KVM decides whether to support mismatched systems. Just warn here: */
+	if (sve_max_virtualisable_vl < sve_max_vl)
+		pr_warn("SVE: unvirtualisable vector lengths present\n");
+
 	sve_efi_setup();
 }
 
@@ -816,12 +870,11 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs)
 	local_bh_disable();
 
 	fpsimd_save();
-	fpsimd_to_sve(current);
 
 	/* Force ret_to_user to reload the registers: */
 	fpsimd_flush_task_state(current);
-	set_thread_flag(TIF_FOREIGN_FPSTATE);
 
+	fpsimd_to_sve(current);
 	if (test_and_set_thread_flag(TIF_SVE))
 		WARN_ON(1); /* SVE access shouldn't have trapped */
 
@@ -894,9 +947,9 @@ void fpsimd_flush_thread(void)
 
 	local_bh_disable();
 
+	fpsimd_flush_task_state(current);
 	memset(&current->thread.uw.fpsimd_state, 0,
 	       sizeof(current->thread.uw.fpsimd_state));
-	fpsimd_flush_task_state(current);
 
 	if (system_supports_sve()) {
 		clear_thread_flag(TIF_SVE);
@@ -933,8 +986,6 @@ void fpsimd_flush_thread(void)
 			current->thread.sve_vl_onexec = 0;
 	}
 
-	set_thread_flag(TIF_FOREIGN_FPSTATE);
-
 	local_bh_enable();
 }
 
@@ -974,6 +1025,8 @@ void fpsimd_bind_task_to_cpu(void)
 		this_cpu_ptr(&fpsimd_last_state);
 
 	last->st = &current->thread.uw.fpsimd_state;
+	last->sve_state = current->thread.sve_state;
+	last->sve_vl = current->thread.sve_vl;
 	current->thread.fpsimd_cpu = smp_processor_id();
 
 	if (system_supports_sve()) {
@@ -987,7 +1040,8 @@ void fpsimd_bind_task_to_cpu(void)
 	}
 }
 
-void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st)
+void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
+			      unsigned int sve_vl)
 {
 	struct fpsimd_last_state_struct *last =
 		this_cpu_ptr(&fpsimd_last_state);
@@ -995,6 +1049,8 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st)
 	WARN_ON(!in_softirq() && !irqs_disabled());
 
 	last->st = st;
+	last->sve_state = sve_state;
+	last->sve_vl = sve_vl;
 }
 
 /*
@@ -1043,12 +1099,29 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state)
 
 /*
  * Invalidate live CPU copies of task t's FPSIMD state
+ *
+ * This function may be called with preemption enabled.  The barrier()
+ * ensures that the assignment to fpsimd_cpu is visible to any
+ * preemption/softirq that could race with set_tsk_thread_flag(), so
+ * that TIF_FOREIGN_FPSTATE cannot be spuriously re-cleared.
+ *
+ * The final barrier ensures that TIF_FOREIGN_FPSTATE is seen set by any
+ * subsequent code.
  */
 void fpsimd_flush_task_state(struct task_struct *t)
 {
 	t->thread.fpsimd_cpu = NR_CPUS;
+
+	barrier();
+	set_tsk_thread_flag(t, TIF_FOREIGN_FPSTATE);
+
+	barrier();
 }
 
+/*
+ * Invalidate any task's FPSIMD state that is present on this cpu.
+ * This function must be called with softirqs disabled.
+ */
 void fpsimd_flush_cpu_state(void)
 {
 	__this_cpu_write(fpsimd_last_state.st, NULL);

arch/arm64/kernel/perf_event.c

@@ -26,6 +26,7 @@
 
 #include <linux/acpi.h>
 #include <linux/clocksource.h>
+#include <linux/kvm_host.h>
 #include <linux/of.h>
 #include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
@@ -528,12 +529,21 @@ static inline int armv8pmu_enable_counter(int idx)
 
 static inline void armv8pmu_enable_event_counter(struct perf_event *event)
 {
+	struct perf_event_attr *attr = &event->attr;
 	int idx = event->hw.idx;
+	u32 counter_bits = BIT(ARMV8_IDX_TO_COUNTER(idx));
 
-	armv8pmu_enable_counter(idx);
 	if (armv8pmu_event_is_chained(event))
-		armv8pmu_enable_counter(idx - 1);
-	isb();
+		counter_bits |= BIT(ARMV8_IDX_TO_COUNTER(idx - 1));
+
+	kvm_set_pmu_events(counter_bits, attr);
+
+	/* We rely on the hypervisor switch code to enable guest counters */
+	if (!kvm_pmu_counter_deferred(attr)) {
+		armv8pmu_enable_counter(idx);
+		if (armv8pmu_event_is_chained(event))
+			armv8pmu_enable_counter(idx - 1);
+	}
 }
 
 static inline int armv8pmu_disable_counter(int idx)
@@ -546,11 +556,21 @@ static inline int armv8pmu_disable_counter(int idx)
 static inline void armv8pmu_disable_event_counter(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
+	struct perf_event_attr *attr = &event->attr;
 	int idx = hwc->idx;
+	u32 counter_bits = BIT(ARMV8_IDX_TO_COUNTER(idx));
 
 	if (armv8pmu_event_is_chained(event))
-		armv8pmu_disable_counter(idx - 1);
-	armv8pmu_disable_counter(idx);
+		counter_bits |= BIT(ARMV8_IDX_TO_COUNTER(idx - 1));
+
+	kvm_clr_pmu_events(counter_bits);
+
+	/* We rely on the hypervisor switch code to disable guest counters */
+	if (!kvm_pmu_counter_deferred(attr)) {
+		if (armv8pmu_event_is_chained(event))
+			armv8pmu_disable_counter(idx - 1);
+		armv8pmu_disable_counter(idx);
+	}
 }
 
 static inline int armv8pmu_enable_intens(int idx)
@@ -827,14 +847,23 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 	 * with other architectures (x86 and Power).
 	 */
 	if (is_kernel_in_hyp_mode()) {
-		if (!attr->exclude_kernel)
+		if (!attr->exclude_kernel && !attr->exclude_host)
 			config_base |= ARMV8_PMU_INCLUDE_EL2;
-	} else {
-		if (attr->exclude_kernel)
+		if (attr->exclude_guest)
 			config_base |= ARMV8_PMU_EXCLUDE_EL1;
-		if (!attr->exclude_hv)
+		if (attr->exclude_host)
+			config_base |= ARMV8_PMU_EXCLUDE_EL0;
+	} else {
+		if (!attr->exclude_hv && !attr->exclude_host)
 			config_base |= ARMV8_PMU_INCLUDE_EL2;
 	}
+
+	/*
+	 * Filter out !VHE kernels and guest kernels
+	 */
+	if (attr->exclude_kernel)
+		config_base |= ARMV8_PMU_EXCLUDE_EL1;
+
 	if (attr->exclude_user)
 		config_base |= ARMV8_PMU_EXCLUDE_EL0;
 
@@ -864,6 +893,9 @@ static void armv8pmu_reset(void *info)
 		armv8pmu_disable_intens(idx);
 	}
 
+	/* Clear the counters we flip at guest entry/exit */
+	kvm_clr_pmu_events(U32_MAX);
+
 	/*
 	 * Initialize & Reset PMNC. Request overflow interrupt for
 	 * 64 bit cycle counter but cheat in armv8pmu_write_counter().

arch/arm64/kernel/signal.c

@@ -296,11 +296,6 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
 	 */
 
 	fpsimd_flush_task_state(current);
-	barrier();
-	/* From now, fpsimd_thread_switch() won't clear TIF_FOREIGN_FPSTATE */
-
-	set_thread_flag(TIF_FOREIGN_FPSTATE);
-	barrier();
 	/* From now, fpsimd_thread_switch() won't touch thread.sve_state */
 
 	sve_alloc(current);

arch/arm64/kvm/Makefile

@@ -17,7 +17,7 @@ kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/psci.o $(KVM)/arm/perf.o
 kvm-$(CONFIG_KVM_ARM_HOST) += inject_fault.o regmap.o va_layout.o
 kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o
 kvm-$(CONFIG_KVM_ARM_HOST) += guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o
-kvm-$(CONFIG_KVM_ARM_HOST) += vgic-sys-reg-v3.o fpsimd.o
+kvm-$(CONFIG_KVM_ARM_HOST) += vgic-sys-reg-v3.o fpsimd.o pmu.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/aarch32.o
 
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic.o

arch/arm64/kvm/fpsimd.c

@@ -9,6 +9,7 @@
 #include <linux/sched.h>
 #include <linux/thread_info.h>
 #include <linux/kvm_host.h>
+#include <asm/fpsimd.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_host.h>
 #include <asm/kvm_mmu.h>
@@ -85,9 +86,12 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
 	WARN_ON_ONCE(!irqs_disabled());
 
 	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) {
-		fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.gp_regs.fp_regs);
+		fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.gp_regs.fp_regs,
+					 vcpu->arch.sve_state,
+					 vcpu->arch.sve_max_vl);
+
 		clear_thread_flag(TIF_FOREIGN_FPSTATE);
-		clear_thread_flag(TIF_SVE);
+		update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu));
 	}
 }
 
@@ -100,14 +104,21 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
 void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 {
 	unsigned long flags;
+	bool host_has_sve = system_supports_sve();
+	bool guest_has_sve = vcpu_has_sve(vcpu);
 
 	local_irq_save(flags);
 
 	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) {
+		u64 *guest_zcr = &vcpu->arch.ctxt.sys_regs[ZCR_EL1];
+
 		/* Clean guest FP state to memory and invalidate cpu view */
 		fpsimd_save();
 		fpsimd_flush_cpu_state();
-	} else if (system_supports_sve()) {
+
+		if (guest_has_sve)
+			*guest_zcr = read_sysreg_s(SYS_ZCR_EL12);
+	} else if (host_has_sve) {
 		/*
 		 * The FPSIMD/SVE state in the CPU has not been touched, and we
 		 * have SVE (and VHE): CPACR_EL1 (alias CPTR_EL2) has been

arch/arm64/kvm/guest.c

@@ -19,18 +19,25 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/bits.h>
 #include <linux/errno.h>
 #include <linux/err.h>
+#include <linux/nospec.h>
 #include <linux/kvm_host.h>
 #include <linux/module.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
 #include <kvm/arm_psci.h>
 #include <asm/cputype.h>
 #include <linux/uaccess.h>
+#include <asm/fpsimd.h>
 #include <asm/kvm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
+#include <asm/kvm_host.h>
+#include <asm/sigcontext.h>
 
 #include "trace.h"
 
@@ -52,12 +59,19 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static bool core_reg_offset_is_vreg(u64 off)
+{
+	return off >= KVM_REG_ARM_CORE_REG(fp_regs.vregs) &&
+		off < KVM_REG_ARM_CORE_REG(fp_regs.fpsr);
+}
+
 static u64 core_reg_offset_from_id(u64 id)
 {
 	return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE);
 }
 
-static int validate_core_offset(const struct kvm_one_reg *reg)
+static int validate_core_offset(const struct kvm_vcpu *vcpu,
+				const struct kvm_one_reg *reg)
 {
 	u64 off = core_reg_offset_from_id(reg->id);
 	int size;
@@ -89,11 +103,19 @@ static int validate_core_offset(const struct kvm_one_reg *reg)
 		return -EINVAL;
 	}
 
-	if (KVM_REG_SIZE(reg->id) == size &&
-	    IS_ALIGNED(off, size / sizeof(__u32)))
-		return 0;
+	if (KVM_REG_SIZE(reg->id) != size ||
+	    !IS_ALIGNED(off, size / sizeof(__u32)))
+		return -EINVAL;
 
-	return -EINVAL;
+	/*
+	 * The KVM_REG_ARM64_SVE regs must be used instead of
+	 * KVM_REG_ARM_CORE for accessing the FPSIMD V-registers on
+	 * SVE-enabled vcpus:
+	 */
+	if (vcpu_has_sve(vcpu) && core_reg_offset_is_vreg(off))
+		return -EINVAL;
+
+	return 0;
 }
 
 static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
@@ -115,7 +137,7 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	    (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
 		return -ENOENT;
 
-	if (validate_core_offset(reg))
+	if (validate_core_offset(vcpu, reg))
 		return -EINVAL;
 
 	if (copy_to_user(uaddr, ((u32 *)regs) + off, KVM_REG_SIZE(reg->id)))
@@ -140,7 +162,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	    (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
 		return -ENOENT;
 
-	if (validate_core_offset(reg))
+	if (validate_core_offset(vcpu, reg))
 		return -EINVAL;
 
 	if (KVM_REG_SIZE(reg->id) > sizeof(tmp))
@@ -183,6 +205,239 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	return err;
 }
 
+#define vq_word(vq) (((vq) - SVE_VQ_MIN) / 64)
+#define vq_mask(vq) ((u64)1 << ((vq) - SVE_VQ_MIN) % 64)
+
+static bool vq_present(
+	const u64 (*const vqs)[KVM_ARM64_SVE_VLS_WORDS],
+	unsigned int vq)
+{
+	return (*vqs)[vq_word(vq)] & vq_mask(vq);
+}
+
+static int get_sve_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	unsigned int max_vq, vq;
+	u64 vqs[KVM_ARM64_SVE_VLS_WORDS];
+
+	if (!vcpu_has_sve(vcpu))
+		return -ENOENT;
+
+	if (WARN_ON(!sve_vl_valid(vcpu->arch.sve_max_vl)))
+		return -EINVAL;
+
+	memset(vqs, 0, sizeof(vqs));
+
+	max_vq = sve_vq_from_vl(vcpu->arch.sve_max_vl);
+	for (vq = SVE_VQ_MIN; vq <= max_vq; ++vq)
+		if (sve_vq_available(vq))
+			vqs[vq_word(vq)] |= vq_mask(vq);
+
+	if (copy_to_user((void __user *)reg->addr, vqs, sizeof(vqs)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int set_sve_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	unsigned int max_vq, vq;
+	u64 vqs[KVM_ARM64_SVE_VLS_WORDS];
+
+	if (!vcpu_has_sve(vcpu))
+		return -ENOENT;
+
+	if (kvm_arm_vcpu_sve_finalized(vcpu))
+		return -EPERM; /* too late! */
+
+	if (WARN_ON(vcpu->arch.sve_state))
+		return -EINVAL;
+
+	if (copy_from_user(vqs, (const void __user *)reg->addr, sizeof(vqs)))
+		return -EFAULT;
+
+	max_vq = 0;
+	for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; ++vq)
+		if (vq_present(&vqs, vq))
+			max_vq = vq;
+
+	if (max_vq > sve_vq_from_vl(kvm_sve_max_vl))
+		return -EINVAL;
+
+	/*
+	 * Vector lengths supported by the host can't currently be
+	 * hidden from the guest individually: instead we can only set a
+	 * maxmium via ZCR_EL2.LEN.  So, make sure the available vector
+	 * lengths match the set requested exactly up to the requested
+	 * maximum:
+	 */
+	for (vq = SVE_VQ_MIN; vq <= max_vq; ++vq)
+		if (vq_present(&vqs, vq) != sve_vq_available(vq))
+			return -EINVAL;
+
+	/* Can't run with no vector lengths at all: */
+	if (max_vq < SVE_VQ_MIN)
+		return -EINVAL;
+
+	/* vcpu->arch.sve_state will be alloc'd by kvm_vcpu_finalize_sve() */
+	vcpu->arch.sve_max_vl = sve_vl_from_vq(max_vq);
+
+	return 0;
+}
+
+#define SVE_REG_SLICE_SHIFT	0
+#define SVE_REG_SLICE_BITS	5
+#define SVE_REG_ID_SHIFT	(SVE_REG_SLICE_SHIFT + SVE_REG_SLICE_BITS)
+#define SVE_REG_ID_BITS		5
+
+#define SVE_REG_SLICE_MASK					\
+	GENMASK(SVE_REG_SLICE_SHIFT + SVE_REG_SLICE_BITS - 1,	\
+		SVE_REG_SLICE_SHIFT)
+#define SVE_REG_ID_MASK							\
+	GENMASK(SVE_REG_ID_SHIFT + SVE_REG_ID_BITS - 1, SVE_REG_ID_SHIFT)
+
+#define SVE_NUM_SLICES (1 << SVE_REG_SLICE_BITS)
+
+#define KVM_SVE_ZREG_SIZE KVM_REG_SIZE(KVM_REG_ARM64_SVE_ZREG(0, 0))
+#define KVM_SVE_PREG_SIZE KVM_REG_SIZE(KVM_REG_ARM64_SVE_PREG(0, 0))
+
+/*
+ * Number of register slices required to cover each whole SVE register.
+ * NOTE: Only the first slice every exists, for now.
+ * If you are tempted to modify this, you must also rework sve_reg_to_region()
+ * to match:
+ */
+#define vcpu_sve_slices(vcpu) 1
+
+/* Bounds of a single SVE register slice within vcpu->arch.sve_state */
+struct sve_state_reg_region {
+	unsigned int koffset;	/* offset into sve_state in kernel memory */
+	unsigned int klen;	/* length in kernel memory */
+	unsigned int upad;	/* extra trailing padding in user memory */
+};
+
+/*
+ * Validate SVE register ID and get sanitised bounds for user/kernel SVE
+ * register copy
+ */
+static int sve_reg_to_region(struct sve_state_reg_region *region,
+			     struct kvm_vcpu *vcpu,
+			     const struct kvm_one_reg *reg)
+{
+	/* reg ID ranges for Z- registers */
+	const u64 zreg_id_min = KVM_REG_ARM64_SVE_ZREG(0, 0);
+	const u64 zreg_id_max = KVM_REG_ARM64_SVE_ZREG(SVE_NUM_ZREGS - 1,
+						       SVE_NUM_SLICES - 1);
+
+	/* reg ID ranges for P- registers and FFR (which are contiguous) */
+	const u64 preg_id_min = KVM_REG_ARM64_SVE_PREG(0, 0);
+	const u64 preg_id_max = KVM_REG_ARM64_SVE_FFR(SVE_NUM_SLICES - 1);
+
+	unsigned int vq;
+	unsigned int reg_num;
+
+	unsigned int reqoffset, reqlen; /* User-requested offset and length */
+	unsigned int maxlen; /* Maxmimum permitted length */
+
+	size_t sve_state_size;
+
+	const u64 last_preg_id = KVM_REG_ARM64_SVE_PREG(SVE_NUM_PREGS - 1,
+							SVE_NUM_SLICES - 1);
+
+	/* Verify that the P-regs and FFR really do have contiguous IDs: */
+	BUILD_BUG_ON(KVM_REG_ARM64_SVE_FFR(0) != last_preg_id + 1);
+
+	/* Verify that we match the UAPI header: */
+	BUILD_BUG_ON(SVE_NUM_SLICES != KVM_ARM64_SVE_MAX_SLICES);
+
+	reg_num = (reg->id & SVE_REG_ID_MASK) >> SVE_REG_ID_SHIFT;
+
+	if (reg->id >= zreg_id_min && reg->id <= zreg_id_max) {
+		if (!vcpu_has_sve(vcpu) || (reg->id & SVE_REG_SLICE_MASK) > 0)
+			return -ENOENT;
+
+		vq = sve_vq_from_vl(vcpu->arch.sve_max_vl);
+
+		reqoffset = SVE_SIG_ZREG_OFFSET(vq, reg_num) -
+				SVE_SIG_REGS_OFFSET;
+		reqlen = KVM_SVE_ZREG_SIZE;
+		maxlen = SVE_SIG_ZREG_SIZE(vq);
+	} else if (reg->id >= preg_id_min && reg->id <= preg_id_max) {
+		if (!vcpu_has_sve(vcpu) || (reg->id & SVE_REG_SLICE_MASK) > 0)
+			return -ENOENT;
+
+		vq = sve_vq_from_vl(vcpu->arch.sve_max_vl);
+
+		reqoffset = SVE_SIG_PREG_OFFSET(vq, reg_num) -
+				SVE_SIG_REGS_OFFSET;
+		reqlen = KVM_SVE_PREG_SIZE;
+		maxlen = SVE_SIG_PREG_SIZE(vq);
+	} else {
+		return -EINVAL;
+	}
+
+	sve_state_size = vcpu_sve_state_size(vcpu);
+	if (WARN_ON(!sve_state_size))
+		return -EINVAL;
+
+	region->koffset = array_index_nospec(reqoffset, sve_state_size);
+	region->klen = min(maxlen, reqlen);
+	region->upad = reqlen - region->klen;
+
+	return 0;
+}
+
+static int get_sve_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	int ret;
+	struct sve_state_reg_region region;
+	char __user *uptr = (char __user *)reg->addr;
+
+	/* Handle the KVM_REG_ARM64_SVE_VLS pseudo-reg as a special case: */
+	if (reg->id == KVM_REG_ARM64_SVE_VLS)
+		return get_sve_vls(vcpu, reg);
+
+	/* Try to interpret reg ID as an architectural SVE register... */
+	ret = sve_reg_to_region(&region, vcpu, reg);
+	if (ret)
+		return ret;
+
+	if (!kvm_arm_vcpu_sve_finalized(vcpu))
+		return -EPERM;
+
+	if (copy_to_user(uptr, vcpu->arch.sve_state + region.koffset,
+			 region.klen) ||
+	    clear_user(uptr + region.klen, region.upad))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int set_sve_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	int ret;
+	struct sve_state_reg_region region;
+	const char __user *uptr = (const char __user *)reg->addr;
+
+	/* Handle the KVM_REG_ARM64_SVE_VLS pseudo-reg as a special case: */
+	if (reg->id == KVM_REG_ARM64_SVE_VLS)
+		return set_sve_vls(vcpu, reg);
+
+	/* Try to interpret reg ID as an architectural SVE register... */
+	ret = sve_reg_to_region(&region, vcpu, reg);
+	if (ret)
+		return ret;
+
+	if (!kvm_arm_vcpu_sve_finalized(vcpu))
+		return -EPERM;
+
+	if (copy_from_user(vcpu->arch.sve_state + region.koffset, uptr,
+			   region.klen))
+		return -EFAULT;
+
+	return 0;
+}
+
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
 	return -EINVAL;
@@ -193,9 +448,37 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	return -EINVAL;
 }
 
-static unsigned long num_core_regs(void)
+static int copy_core_reg_indices(const struct kvm_vcpu *vcpu,
+				 u64 __user *uindices)
+{
+	unsigned int i;
+	int n = 0;
+	const u64 core_reg = KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE;
+
+	for (i = 0; i < sizeof(struct kvm_regs) / sizeof(__u32); i++) {
+		/*
+		 * The KVM_REG_ARM64_SVE regs must be used instead of
+		 * KVM_REG_ARM_CORE for accessing the FPSIMD V-registers on
+		 * SVE-enabled vcpus:
+		 */
+		if (vcpu_has_sve(vcpu) && core_reg_offset_is_vreg(i))
+			continue;
+
+		if (uindices) {
+			if (put_user(core_reg | i, uindices))
+				return -EFAULT;
+			uindices++;
+		}
+
+		n++;
+	}
+
+	return n;
+}
+
+static unsigned long num_core_regs(const struct kvm_vcpu *vcpu)
 {
-	return sizeof(struct kvm_regs) / sizeof(__u32);
+	return copy_core_reg_indices(vcpu, NULL);
 }
 
 /**
@@ -251,6 +534,67 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0;
 }
 
+static unsigned long num_sve_regs(const struct kvm_vcpu *vcpu)
+{
+	const unsigned int slices = vcpu_sve_slices(vcpu);
+
+	if (!vcpu_has_sve(vcpu))
+		return 0;
+
+	/* Policed by KVM_GET_REG_LIST: */
+	WARN_ON(!kvm_arm_vcpu_sve_finalized(vcpu));
+
+	return slices * (SVE_NUM_PREGS + SVE_NUM_ZREGS + 1 /* FFR */)
+		+ 1; /* KVM_REG_ARM64_SVE_VLS */
+}
+
+static int copy_sve_reg_indices(const struct kvm_vcpu *vcpu,
+				u64 __user *uindices)
+{
+	const unsigned int slices = vcpu_sve_slices(vcpu);
+	u64 reg;
+	unsigned int i, n;
+	int num_regs = 0;
+
+	if (!vcpu_has_sve(vcpu))
+		return 0;
+
+	/* Policed by KVM_GET_REG_LIST: */
+	WARN_ON(!kvm_arm_vcpu_sve_finalized(vcpu));
+
+	/*
+	 * Enumerate this first, so that userspace can save/restore in
+	 * the order reported by KVM_GET_REG_LIST:
+	 */
+	reg = KVM_REG_ARM64_SVE_VLS;
+	if (put_user(reg, uindices++))
+		return -EFAULT;
+	++num_regs;
+
+	for (i = 0; i < slices; i++) {
+		for (n = 0; n < SVE_NUM_ZREGS; n++) {
+			reg = KVM_REG_ARM64_SVE_ZREG(n, i);
+			if (put_user(reg, uindices++))
+				return -EFAULT;
+			num_regs++;
+		}
+
+		for (n = 0; n < SVE_NUM_PREGS; n++) {
+			reg = KVM_REG_ARM64_SVE_PREG(n, i);
+			if (put_user(reg, uindices++))
+				return -EFAULT;
+			num_regs++;
+		}
+
+		reg = KVM_REG_ARM64_SVE_FFR(i);
+		if (put_user(reg, uindices++))
+			return -EFAULT;
+		num_regs++;
+	}
+
+	return num_regs;
+}
+
 /**
  * kvm_arm_num_regs - how many registers do we present via KVM_GET_ONE_REG
  *
@@ -258,8 +602,15 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
  */
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
 {
-	return num_core_regs() + kvm_arm_num_sys_reg_descs(vcpu)
-		+ kvm_arm_get_fw_num_regs(vcpu)	+ NUM_TIMER_REGS;
+	unsigned long res = 0;
+
+	res += num_core_regs(vcpu);
+	res += num_sve_regs(vcpu);
+	res += kvm_arm_num_sys_reg_descs(vcpu);
+	res += kvm_arm_get_fw_num_regs(vcpu);
+	res += NUM_TIMER_REGS;
+
+	return res;
 }
 
 /**
@@ -269,23 +620,25 @@ unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
  */
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 {
-	unsigned int i;
-	const u64 core_reg = KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE;
 	int ret;
 
-	for (i = 0; i < sizeof(struct kvm_regs) / sizeof(__u32); i++) {
-		if (put_user(core_reg | i, uindices))
-			return -EFAULT;
-		uindices++;
-	}
+	ret = copy_core_reg_indices(vcpu, uindices);
+	if (ret < 0)
+		return ret;
+	uindices += ret;
+
+	ret = copy_sve_reg_indices(vcpu, uindices);
+	if (ret < 0)
+		return ret;
+	uindices += ret;
 
 	ret = kvm_arm_copy_fw_reg_indices(vcpu, uindices);
-	if (ret)
+	if (ret < 0)
 		return ret;
 	uindices += kvm_arm_get_fw_num_regs(vcpu);
 
 	ret = copy_timer_indices(vcpu, uindices);
-	if (ret)
+	if (ret < 0)
 		return ret;
 	uindices += NUM_TIMER_REGS;
 
@@ -298,12 +651,11 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if ((reg->id & ~KVM_REG_SIZE_MASK) >> 32 != KVM_REG_ARM64 >> 32)
 		return -EINVAL;
 
-	/* Register group 16 means we want a core register. */
-	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
-		return get_core_reg(vcpu, reg);
-
-	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
-		return kvm_arm_get_fw_reg(vcpu, reg);
+	switch (reg->id & KVM_REG_ARM_COPROC_MASK) {
+	case KVM_REG_ARM_CORE:	return get_core_reg(vcpu, reg);
+	case KVM_REG_ARM_FW:	return kvm_arm_get_fw_reg(vcpu, reg);
+	case KVM_REG_ARM64_SVE:	return get_sve_reg(vcpu, reg);
+	}
 
 	if (is_timer_reg(reg->id))
 		return get_timer_reg(vcpu, reg);
@@ -317,12 +669,11 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if ((reg->id & ~KVM_REG_SIZE_MASK) >> 32 != KVM_REG_ARM64 >> 32)
 		return -EINVAL;
 
-	/* Register group 16 means we set a core register. */
-	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
-		return set_core_reg(vcpu, reg);
-
-	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
-		return kvm_arm_set_fw_reg(vcpu, reg);
+	switch (reg->id & KVM_REG_ARM_COPROC_MASK) {
+	case KVM_REG_ARM_CORE:	return set_core_reg(vcpu, reg);
+	case KVM_REG_ARM_FW:	return kvm_arm_set_fw_reg(vcpu, reg);
+	case KVM_REG_ARM64_SVE:	return set_sve_reg(vcpu, reg);
+	}
 
 	if (is_timer_reg(reg->id))
 		return set_timer_reg(vcpu, reg);

arch/arm64/kvm/handle_exit.c

@@ -173,20 +173,40 @@ static int handle_sve(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 1;
 }
 
+#define __ptrauth_save_key(regs, key)						\
+({										\
+	regs[key ## KEYLO_EL1] = read_sysreg_s(SYS_ ## key ## KEYLO_EL1);	\
+	regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);	\
+})
+
+/*
+ * Handle the guest trying to use a ptrauth instruction, or trying to access a
+ * ptrauth register.
+ */
+void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *ctxt;
+
+	if (vcpu_has_ptrauth(vcpu)) {
+		vcpu_ptrauth_enable(vcpu);
+		ctxt = vcpu->arch.host_cpu_context;
+		__ptrauth_save_key(ctxt->sys_regs, APIA);
+		__ptrauth_save_key(ctxt->sys_regs, APIB);
+		__ptrauth_save_key(ctxt->sys_regs, APDA);
+		__ptrauth_save_key(ctxt->sys_regs, APDB);
+		__ptrauth_save_key(ctxt->sys_regs, APGA);
+	} else {
+		kvm_inject_undefined(vcpu);
+	}
+}
+
 /*
  * Guest usage of a ptrauth instruction (which the guest EL1 did not turn into
  * a NOP).
  */
 static int kvm_handle_ptrauth(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	/*
-	 * We don't currently support ptrauth in a guest, and we mask the ID
-	 * registers to prevent well-behaved guests from trying to make use of
-	 * it.
-	 *
-	 * Inject an UNDEF, as if the feature really isn't present.
-	 */
-	kvm_inject_undefined(vcpu);
+	kvm_arm_vcpu_ptrauth_trap(vcpu);
 	return 1;
 }
 

arch/arm64/kvm/hyp/entry.S

@@ -24,6 +24,7 @@
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmu.h>
+#include <asm/kvm_ptrauth.h>
 
 #define CPU_GP_REG_OFFSET(x)	(CPU_GP_REGS + x)
 #define CPU_XREG_OFFSET(x)	CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x)
@@ -64,6 +65,13 @@ ENTRY(__guest_enter)
 
 	add	x18, x0, #VCPU_CONTEXT
 
+	// Macro ptrauth_switch_to_guest format:
+	// 	ptrauth_switch_to_guest(guest cxt, tmp1, tmp2, tmp3)
+	// The below macro to restore guest keys is not implemented in C code
+	// as it may cause Pointer Authentication key signing mismatch errors
+	// when this feature is enabled for kernel code.
+	ptrauth_switch_to_guest x18, x0, x1, x2
+
 	// Restore guest regs x0-x17
 	ldp	x0, x1,   [x18, #CPU_XREG_OFFSET(0)]
 	ldp	x2, x3,   [x18, #CPU_XREG_OFFSET(2)]
@@ -118,6 +126,13 @@ ENTRY(__guest_exit)
 
 	get_host_ctxt	x2, x3
 
+	// Macro ptrauth_switch_to_guest format:
+	// 	ptrauth_switch_to_host(guest cxt, host cxt, tmp1, tmp2, tmp3)
+	// The below macro to save/restore keys is not implemented in C code
+	// as it may cause Pointer Authentication key signing mismatch errors
+	// when this feature is enabled for kernel code.
+	ptrauth_switch_to_host x1, x2, x3, x4, x5
+
 	// Now restore the host regs
 	restore_callee_saved_regs x2
 

arch/arm64/kvm/hyp/switch.c

@@ -100,7 +100,10 @@ static void activate_traps_vhe(struct kvm_vcpu *vcpu)
 	val = read_sysreg(cpacr_el1);
 	val |= CPACR_EL1_TTA;
 	val &= ~CPACR_EL1_ZEN;
-	if (!update_fp_enabled(vcpu)) {
+	if (update_fp_enabled(vcpu)) {
+		if (vcpu_has_sve(vcpu))
+			val |= CPACR_EL1_ZEN;
+	} else {
 		val &= ~CPACR_EL1_FPEN;
 		__activate_traps_fpsimd32(vcpu);
 	}
@@ -317,16 +320,48 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
 	return true;
 }
 
-static bool __hyp_text __hyp_switch_fpsimd(struct kvm_vcpu *vcpu)
+/* Check for an FPSIMD/SVE trap and handle as appropriate */
+static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 {
-	struct user_fpsimd_state *host_fpsimd = vcpu->arch.host_fpsimd_state;
+	bool vhe, sve_guest, sve_host;
+	u8 hsr_ec;
 
-	if (has_vhe())
-		write_sysreg(read_sysreg(cpacr_el1) | CPACR_EL1_FPEN,
-			     cpacr_el1);
-	else
+	if (!system_supports_fpsimd())
+		return false;
+
+	if (system_supports_sve()) {
+		sve_guest = vcpu_has_sve(vcpu);
+		sve_host = vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE;
+		vhe = true;
+	} else {
+		sve_guest = false;
+		sve_host = false;
+		vhe = has_vhe();
+	}
+
+	hsr_ec = kvm_vcpu_trap_get_class(vcpu);
+	if (hsr_ec != ESR_ELx_EC_FP_ASIMD &&
+	    hsr_ec != ESR_ELx_EC_SVE)
+		return false;
+
+	/* Don't handle SVE traps for non-SVE vcpus here: */
+	if (!sve_guest)
+		if (hsr_ec != ESR_ELx_EC_FP_ASIMD)
+			return false;
+
+	/* Valid trap.  Switch the context: */
+
+	if (vhe) {
+		u64 reg = read_sysreg(cpacr_el1) | CPACR_EL1_FPEN;
+
+		if (sve_guest)
+			reg |= CPACR_EL1_ZEN;
+
+		write_sysreg(reg, cpacr_el1);
+	} else {
 		write_sysreg(read_sysreg(cptr_el2) & ~(u64)CPTR_EL2_TFP,
 			     cptr_el2);
+	}
 
 	isb();
 
@@ -335,21 +370,28 @@ static bool __hyp_text __hyp_switch_fpsimd(struct kvm_vcpu *vcpu)
 		 * In the SVE case, VHE is assumed: it is enforced by
 		 * Kconfig and kvm_arch_init().
 		 */
-		if (system_supports_sve() &&
-		    (vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE)) {
+		if (sve_host) {
 			struct thread_struct *thread = container_of(
-				host_fpsimd,
+				vcpu->arch.host_fpsimd_state,
 				struct thread_struct, uw.fpsimd_state);
 
-			sve_save_state(sve_pffr(thread), &host_fpsimd->fpsr);
+			sve_save_state(sve_pffr(thread),
+				       &vcpu->arch.host_fpsimd_state->fpsr);
 		} else {
-			__fpsimd_save_state(host_fpsimd);
+			__fpsimd_save_state(vcpu->arch.host_fpsimd_state);
 		}
 
 		vcpu->arch.flags &= ~KVM_ARM64_FP_HOST;
 	}
 
-	__fpsimd_restore_state(&vcpu->arch.ctxt.gp_regs.fp_regs);
+	if (sve_guest) {
+		sve_load_state(vcpu_sve_pffr(vcpu),
+			       &vcpu->arch.ctxt.gp_regs.fp_regs.fpsr,
+			       sve_vq_from_vl(vcpu->arch.sve_max_vl) - 1);
+		write_sysreg_s(vcpu->arch.ctxt.sys_regs[ZCR_EL1], SYS_ZCR_EL12);
+	} else {
+		__fpsimd_restore_state(&vcpu->arch.ctxt.gp_regs.fp_regs);
+	}
 
 	/* Skip restoring fpexc32 for AArch64 guests */
 	if (!(read_sysreg(hcr_el2) & HCR_RW))
@@ -385,10 +427,10 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 	 * and restore the guest context lazily.
 	 * If FP/SIMD is not implemented, handle the trap and inject an
 	 * undefined instruction exception to the guest.
+	 * Similarly for trapped SVE accesses.
 	 */
-	if (system_supports_fpsimd() &&
-	    kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_FP_ASIMD)
-		return __hyp_switch_fpsimd(vcpu);
+	if (__hyp_handle_fpsimd(vcpu))
+		return true;
 
 	if (!__populate_fault_info(vcpu))
 		return true;
@@ -524,6 +566,7 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;
+	bool pmu_switch_needed;
 	u64 exit_code;
 
 	/*
@@ -543,6 +586,8 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
 	host_ctxt->__hyp_running_vcpu = vcpu;
 	guest_ctxt = &vcpu->arch.ctxt;
 
+	pmu_switch_needed = __pmu_switch_to_guest(host_ctxt);
+
 	__sysreg_save_state_nvhe(host_ctxt);
 
 	__activate_vm(kern_hyp_va(vcpu->kvm));
@@ -589,6 +634,9 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
 	 */
 	__debug_switch_to_host(vcpu);
 
+	if (pmu_switch_needed)
+		__pmu_switch_to_host(host_ctxt);
+
 	/* Returning to host will clear PSR.I, remask PMR if needed */
 	if (system_uses_irq_prio_masking())
 		gic_write_pmr(GIC_PRIO_IRQOFF);

arch/arm64/kvm/pmu.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2019 Arm Limited
+ * Author: Andrew Murray <Andrew.Murray@arm.com>
+ */
+#include <linux/kvm_host.h>
+#include <linux/perf_event.h>
+#include <asm/kvm_hyp.h>
+
+/*
+ * Given the perf event attributes and system type, determine
+ * if we are going to need to switch counters at guest entry/exit.
+ */
+static bool kvm_pmu_switch_needed(struct perf_event_attr *attr)
+{
+	/**
+	 * With VHE the guest kernel runs at EL1 and the host at EL2,
+	 * where user (EL0) is excluded then we have no reason to switch
+	 * counters.
+	 */
+	if (has_vhe() && attr->exclude_user)
+		return false;
+
+	/* Only switch if attributes are different */
+	return (attr->exclude_host != attr->exclude_guest);
+}
+
+/*
+ * Add events to track that we may want to switch at guest entry/exit
+ * time.
+ */
+void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr)
+{
+	struct kvm_host_data *ctx = this_cpu_ptr(&kvm_host_data);
+
+	if (!kvm_pmu_switch_needed(attr))
+		return;
+
+	if (!attr->exclude_host)
+		ctx->pmu_events.events_host |= set;
+	if (!attr->exclude_guest)
+		ctx->pmu_events.events_guest |= set;
+}
+
+/*
+ * Stop tracking events
+ */
+void kvm_clr_pmu_events(u32 clr)
+{
+	struct kvm_host_data *ctx = this_cpu_ptr(&kvm_host_data);
+
+	ctx->pmu_events.events_host &= ~clr;
+	ctx->pmu_events.events_guest &= ~clr;
+}
+
+/**
+ * Disable host events, enable guest events
+ */
+bool __hyp_text __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
+{
+	struct kvm_host_data *host;
+	struct kvm_pmu_events *pmu;
+
+	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
+	pmu = &host->pmu_events;
+
+	if (pmu->events_host)
+		write_sysreg(pmu->events_host, pmcntenclr_el0);
+
+	if (pmu->events_guest)
+		write_sysreg(pmu->events_guest, pmcntenset_el0);
+
+	return (pmu->events_host || pmu->events_guest);
+}
+
+/**
+ * Disable guest events, enable host events
+ */
+void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
+{
+	struct kvm_host_data *host;
+	struct kvm_pmu_events *pmu;
+
+	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
+	pmu = &host->pmu_events;
+
+	if (pmu->events_guest)
+		write_sysreg(pmu->events_guest, pmcntenclr_el0);
+
+	if (pmu->events_host)
+		write_sysreg(pmu->events_host, pmcntenset_el0);
+}
+
+#define PMEVTYPER_READ_CASE(idx)				\
+	case idx:						\
+		return read_sysreg(pmevtyper##idx##_el0)
+
+#define PMEVTYPER_WRITE_CASE(idx)				\
+	case idx:						\
+		write_sysreg(val, pmevtyper##idx##_el0);	\
+		break
+
+#define PMEVTYPER_CASES(readwrite)				\
+	PMEVTYPER_##readwrite##_CASE(0);			\
+	PMEVTYPER_##readwrite##_CASE(1);			\
+	PMEVTYPER_##readwrite##_CASE(2);			\
+	PMEVTYPER_##readwrite##_CASE(3);			\
+	PMEVTYPER_##readwrite##_CASE(4);			\
+	PMEVTYPER_##readwrite##_CASE(5);			\
+	PMEVTYPER_##readwrite##_CASE(6);			\
+	PMEVTYPER_##readwrite##_CASE(7);			\
+	PMEVTYPER_##readwrite##_CASE(8);			\
+	PMEVTYPER_##readwrite##_CASE(9);			\
+	PMEVTYPER_##readwrite##_CASE(10);			\
+	PMEVTYPER_##readwrite##_CASE(11);			\
+	PMEVTYPER_##readwrite##_CASE(12);			\
+	PMEVTYPER_##readwrite##_CASE(13);			\
+	PMEVTYPER_##readwrite##_CASE(14);			\
+	PMEVTYPER_##readwrite##_CASE(15);			\
+	PMEVTYPER_##readwrite##_CASE(16);			\
+	PMEVTYPER_##readwrite##_CASE(17);			\
+	PMEVTYPER_##readwrite##_CASE(18);			\
+	PMEVTYPER_##readwrite##_CASE(19);			\
+	PMEVTYPER_##readwrite##_CASE(20);			\
+	PMEVTYPER_##readwrite##_CASE(21);			\
+	PMEVTYPER_##readwrite##_CASE(22);			\
+	PMEVTYPER_##readwrite##_CASE(23);			\
+	PMEVTYPER_##readwrite##_CASE(24);			\
+	PMEVTYPER_##readwrite##_CASE(25);			\
+	PMEVTYPER_##readwrite##_CASE(26);			\
+	PMEVTYPER_##readwrite##_CASE(27);			\
+	PMEVTYPER_##readwrite##_CASE(28);			\
+	PMEVTYPER_##readwrite##_CASE(29);			\
+	PMEVTYPER_##readwrite##_CASE(30)
+
+/*
+ * Read a value direct from PMEVTYPER<idx> where idx is 0-30
+ * or PMCCFILTR_EL0 where idx is ARMV8_PMU_CYCLE_IDX (31).
+ */
+static u64 kvm_vcpu_pmu_read_evtype_direct(int idx)
+{
+	switch (idx) {
+	PMEVTYPER_CASES(READ);
+	case ARMV8_PMU_CYCLE_IDX:
+		return read_sysreg(pmccfiltr_el0);
+	default:
+		WARN_ON(1);
+	}
+
+	return 0;
+}
+
+/*
+ * Write a value direct to PMEVTYPER<idx> where idx is 0-30
+ * or PMCCFILTR_EL0 where idx is ARMV8_PMU_CYCLE_IDX (31).
+ */
+static void kvm_vcpu_pmu_write_evtype_direct(int idx, u32 val)
+{
+	switch (idx) {
+	PMEVTYPER_CASES(WRITE);
+	case ARMV8_PMU_CYCLE_IDX:
+		write_sysreg(val, pmccfiltr_el0);
+		break;
+	default:
+		WARN_ON(1);
+	}
+}
+
+/*
+ * Modify ARMv8 PMU events to include EL0 counting
+ */
+static void kvm_vcpu_pmu_enable_el0(unsigned long events)
+{
+	u64 typer;
+	u32 counter;
+
+	for_each_set_bit(counter, &events, 32) {
+		typer = kvm_vcpu_pmu_read_evtype_direct(counter);
+		typer &= ~ARMV8_PMU_EXCLUDE_EL0;
+		kvm_vcpu_pmu_write_evtype_direct(counter, typer);
+	}
+}
+
+/*
+ * Modify ARMv8 PMU events to exclude EL0 counting
+ */
+static void kvm_vcpu_pmu_disable_el0(unsigned long events)
+{
+	u64 typer;
+	u32 counter;
+
+	for_each_set_bit(counter, &events, 32) {
+		typer = kvm_vcpu_pmu_read_evtype_direct(counter);
+		typer |= ARMV8_PMU_EXCLUDE_EL0;
+		kvm_vcpu_pmu_write_evtype_direct(counter, typer);
+	}
+}
+
+/*
+ * On VHE ensure that only guest events have EL0 counting enabled
+ */
+void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_host_data *host;
+	u32 events_guest, events_host;
+
+	if (!has_vhe())
+		return;
+
+	host_ctxt = vcpu->arch.host_cpu_context;
+	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
+	events_guest = host->pmu_events.events_guest;
+	events_host = host->pmu_events.events_host;
+
+	kvm_vcpu_pmu_enable_el0(events_guest);
+	kvm_vcpu_pmu_disable_el0(events_host);
+}
+
+/*
+ * On VHE ensure that only host events have EL0 counting enabled
+ */
+void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_host_data *host;
+	u32 events_guest, events_host;
+
+	if (!has_vhe())
+		return;
+
+	host_ctxt = vcpu->arch.host_cpu_context;
+	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
+	events_guest = host->pmu_events.events_guest;
+	events_host = host->pmu_events.events_host;
+
+	kvm_vcpu_pmu_enable_el0(events_host);
+	kvm_vcpu_pmu_disable_el0(events_guest);
+}

arch/arm64/kvm/reset.c

@@ -20,20 +20,26 @@
  */
 
 #include <linux/errno.h>
+#include <linux/kernel.h>
 #include <linux/kvm_host.h>
 #include <linux/kvm.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/types.h>
 
 #include <kvm/arm_arch_timer.h>
 
 #include <asm/cpufeature.h>
 #include <asm/cputype.h>
+#include <asm/fpsimd.h>
 #include <asm/ptrace.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_coproc.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_mmu.h>
+#include <asm/virt.h>
 
 /* Maximum phys_shift supported for any VM on this host */
 static u32 kvm_ipa_limit;
@@ -92,6 +98,14 @@ int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ARM_VM_IPA_SIZE:
 		r = kvm_ipa_limit;
 		break;
+	case KVM_CAP_ARM_SVE:
+		r = system_supports_sve();
+		break;
+	case KVM_CAP_ARM_PTRAUTH_ADDRESS:
+	case KVM_CAP_ARM_PTRAUTH_GENERIC:
+		r = has_vhe() && system_supports_address_auth() &&
+				 system_supports_generic_auth();
+		break;
 	default:
 		r = 0;
 	}
@@ -99,13 +113,148 @@ int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	return r;
 }
 
+unsigned int kvm_sve_max_vl;
+
+int kvm_arm_init_sve(void)
+{
+	if (system_supports_sve()) {
+		kvm_sve_max_vl = sve_max_virtualisable_vl;
+
+		/*
+		 * The get_sve_reg()/set_sve_reg() ioctl interface will need
+		 * to be extended with multiple register slice support in
+		 * order to support vector lengths greater than
+		 * SVE_VL_ARCH_MAX:
+		 */
+		if (WARN_ON(kvm_sve_max_vl > SVE_VL_ARCH_MAX))
+			kvm_sve_max_vl = SVE_VL_ARCH_MAX;
+
+		/*
+		 * Don't even try to make use of vector lengths that
+		 * aren't available on all CPUs, for now:
+		 */
+		if (kvm_sve_max_vl < sve_max_vl)
+			pr_warn("KVM: SVE vector length for guests limited to %u bytes\n",
+				kvm_sve_max_vl);
+	}
+
+	return 0;
+}
+
+static int kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu)
+{
+	if (!system_supports_sve())
+		return -EINVAL;
+
+	/* Verify that KVM startup enforced this when SVE was detected: */
+	if (WARN_ON(!has_vhe()))
+		return -EINVAL;
+
+	vcpu->arch.sve_max_vl = kvm_sve_max_vl;
+
+	/*
+	 * Userspace can still customize the vector lengths by writing
+	 * KVM_REG_ARM64_SVE_VLS.  Allocation is deferred until
+	 * kvm_arm_vcpu_finalize(), which freezes the configuration.
+	 */
+	vcpu->arch.flags |= KVM_ARM64_GUEST_HAS_SVE;
+
+	return 0;
+}
+
+/*
+ * Finalize vcpu's maximum SVE vector length, allocating
+ * vcpu->arch.sve_state as necessary.
+ */
+static int kvm_vcpu_finalize_sve(struct kvm_vcpu *vcpu)
+{
+	void *buf;
+	unsigned int vl;
+
+	vl = vcpu->arch.sve_max_vl;
+
+	/*
+	 * Resposibility for these properties is shared between
+	 * kvm_arm_init_arch_resources(), kvm_vcpu_enable_sve() and
+	 * set_sve_vls().  Double-check here just to be sure:
+	 */
+	if (WARN_ON(!sve_vl_valid(vl) || vl > sve_max_virtualisable_vl ||
+		    vl > SVE_VL_ARCH_MAX))
+		return -EIO;
+
+	buf = kzalloc(SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl)), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	vcpu->arch.sve_state = buf;
+	vcpu->arch.flags |= KVM_ARM64_VCPU_SVE_FINALIZED;
+	return 0;
+}
+
+int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature)
+{
+	switch (feature) {
+	case KVM_ARM_VCPU_SVE:
+		if (!vcpu_has_sve(vcpu))
+			return -EINVAL;
+
+		if (kvm_arm_vcpu_sve_finalized(vcpu))
+			return -EPERM;
+
+		return kvm_vcpu_finalize_sve(vcpu);
+	}
+
+	return -EINVAL;
+}
+
+bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu)
+{
+	if (vcpu_has_sve(vcpu) && !kvm_arm_vcpu_sve_finalized(vcpu))
+		return false;
+
+	return true;
+}
+
+void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
+{
+	kfree(vcpu->arch.sve_state);
+}
+
+static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu)
+{
+	if (vcpu_has_sve(vcpu))
+		memset(vcpu->arch.sve_state, 0, vcpu_sve_state_size(vcpu));
+}
+
+static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
+{
+	/* Support ptrauth only if the system supports these capabilities. */
+	if (!has_vhe())
+		return -EINVAL;
+
+	if (!system_supports_address_auth() ||
+	    !system_supports_generic_auth())
+		return -EINVAL;
+	/*
+	 * For now make sure that both address/generic pointer authentication
+	 * features are requested by the userspace together.
+	 */
+	if (!test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
+	    !test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features))
+		return -EINVAL;
+
+	vcpu->arch.flags |= KVM_ARM64_GUEST_HAS_PTRAUTH;
+	return 0;
+}
+
 /**
  * kvm_reset_vcpu - sets core registers and sys_regs to reset value
  * @vcpu: The VCPU pointer
  *
  * This function finds the right table above and sets the registers on
  * the virtual CPU struct to their architecturally defined reset
- * values.
+ * values, except for registers whose reset is deferred until
+ * kvm_arm_vcpu_finalize().
  *
  * Note: This function can be called from two paths: The KVM_ARM_VCPU_INIT
  * ioctl or as part of handling a request issued by another VCPU in the PSCI
@@ -131,6 +280,22 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	if (loaded)
 		kvm_arch_vcpu_put(vcpu);
 
+	if (!kvm_arm_vcpu_sve_finalized(vcpu)) {
+		if (test_bit(KVM_ARM_VCPU_SVE, vcpu->arch.features)) {
+			ret = kvm_vcpu_enable_sve(vcpu);
+			if (ret)
+				goto out;
+		}
+	} else {
+		kvm_vcpu_reset_sve(vcpu);
+	}
+
+	if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
+	    test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features)) {
+		if (kvm_vcpu_enable_ptrauth(vcpu))
+			goto out;
+	}
+
 	switch (vcpu->arch.target) {
 	default:
 		if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {

arch/arm64/kvm/sys_regs.c

@@ -695,6 +695,7 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		val |= p->regval & ARMV8_PMU_PMCR_MASK;
 		__vcpu_sys_reg(vcpu, PMCR_EL0) = val;
 		kvm_pmu_handle_pmcr(vcpu, val);
+		kvm_vcpu_pmu_restore_guest(vcpu);
 	} else {
 		/* PMCR.P & PMCR.C are RAZ */
 		val = __vcpu_sys_reg(vcpu, PMCR_EL0)
@@ -850,6 +851,7 @@ static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	if (p->is_write) {
 		kvm_pmu_set_counter_event_type(vcpu, p->regval, idx);
 		__vcpu_sys_reg(vcpu, reg) = p->regval & ARMV8_PMU_EVTYPE_MASK;
+		kvm_vcpu_pmu_restore_guest(vcpu);
 	} else {
 		p->regval = __vcpu_sys_reg(vcpu, reg) & ARMV8_PMU_EVTYPE_MASK;
 	}
@@ -875,6 +877,7 @@ static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 			/* accessing PMCNTENSET_EL0 */
 			__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) |= val;
 			kvm_pmu_enable_counter(vcpu, val);
+			kvm_vcpu_pmu_restore_guest(vcpu);
 		} else {
 			/* accessing PMCNTENCLR_EL0 */
 			__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= ~val;
@@ -1007,6 +1010,37 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	{ SYS_DESC(SYS_PMEVTYPERn_EL0(n)),					\
 	  access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), }
 
+static bool trap_ptrauth(struct kvm_vcpu *vcpu,
+			 struct sys_reg_params *p,
+			 const struct sys_reg_desc *rd)
+{
+	kvm_arm_vcpu_ptrauth_trap(vcpu);
+
+	/*
+	 * Return false for both cases as we never skip the trapped
+	 * instruction:
+	 *
+	 * - Either we re-execute the same key register access instruction
+	 *   after enabling ptrauth.
+	 * - Or an UNDEF is injected as ptrauth is not supported/enabled.
+	 */
+	return false;
+}
+
+static unsigned int ptrauth_visibility(const struct kvm_vcpu *vcpu,
+			const struct sys_reg_desc *rd)
+{
+	return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN_USER | REG_HIDDEN_GUEST;
+}
+
+#define __PTRAUTH_KEY(k)						\
+	{ SYS_DESC(SYS_## k), trap_ptrauth, reset_unknown, k,		\
+	.visibility = ptrauth_visibility}
+
+#define PTRAUTH_KEY(k)							\
+	__PTRAUTH_KEY(k ## KEYLO_EL1),					\
+	__PTRAUTH_KEY(k ## KEYHI_EL1)
+
 static bool access_arch_timer(struct kvm_vcpu *vcpu,
 			      struct sys_reg_params *p,
 			      const struct sys_reg_desc *r)
@@ -1044,25 +1078,20 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu,
 }
 
 /* Read a sanitised cpufeature ID register by sys_reg_desc */
-static u64 read_id_reg(struct sys_reg_desc const *r, bool raz)
+static u64 read_id_reg(const struct kvm_vcpu *vcpu,
+		struct sys_reg_desc const *r, bool raz)
 {
 	u32 id = sys_reg((u32)r->Op0, (u32)r->Op1,
 			 (u32)r->CRn, (u32)r->CRm, (u32)r->Op2);
 	u64 val = raz ? 0 : read_sanitised_ftr_reg(id);
 
-	if (id == SYS_ID_AA64PFR0_EL1) {
-		if (val & (0xfUL << ID_AA64PFR0_SVE_SHIFT))
-			kvm_debug("SVE unsupported for guests, suppressing\n");
-
+	if (id == SYS_ID_AA64PFR0_EL1 && !vcpu_has_sve(vcpu)) {
 		val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
-	} else if (id == SYS_ID_AA64ISAR1_EL1) {
-		const u64 ptrauth_mask = (0xfUL << ID_AA64ISAR1_APA_SHIFT) |
-					 (0xfUL << ID_AA64ISAR1_API_SHIFT) |
-					 (0xfUL << ID_AA64ISAR1_GPA_SHIFT) |
-					 (0xfUL << ID_AA64ISAR1_GPI_SHIFT);
-		if (val & ptrauth_mask)
-			kvm_debug("ptrauth unsupported for guests, suppressing\n");
-		val &= ~ptrauth_mask;
+	} else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) {
+		val &= ~((0xfUL << ID_AA64ISAR1_APA_SHIFT) |
+			 (0xfUL << ID_AA64ISAR1_API_SHIFT) |
+			 (0xfUL << ID_AA64ISAR1_GPA_SHIFT) |
+			 (0xfUL << ID_AA64ISAR1_GPI_SHIFT));
 	}
 
 	return val;
@@ -1078,7 +1107,7 @@ static bool __access_id_reg(struct kvm_vcpu *vcpu,
 	if (p->is_write)
 		return write_to_read_only(vcpu, p, r);
 
-	p->regval = read_id_reg(r, raz);
+	p->regval = read_id_reg(vcpu, r, raz);
 	return true;
 }
 
@@ -1100,6 +1129,81 @@ static int reg_from_user(u64 *val, const void __user *uaddr, u64 id);
 static int reg_to_user(void __user *uaddr, const u64 *val, u64 id);
 static u64 sys_reg_to_index(const struct sys_reg_desc *reg);
 
+/* Visibility overrides for SVE-specific control registers */
+static unsigned int sve_visibility(const struct kvm_vcpu *vcpu,
+				   const struct sys_reg_desc *rd)
+{
+	if (vcpu_has_sve(vcpu))
+		return 0;
+
+	return REG_HIDDEN_USER | REG_HIDDEN_GUEST;
+}
+
+/* Visibility overrides for SVE-specific ID registers */
+static unsigned int sve_id_visibility(const struct kvm_vcpu *vcpu,
+				      const struct sys_reg_desc *rd)
+{
+	if (vcpu_has_sve(vcpu))
+		return 0;
+
+	return REG_HIDDEN_USER;
+}
+
+/* Generate the emulated ID_AA64ZFR0_EL1 value exposed to the guest */
+static u64 guest_id_aa64zfr0_el1(const struct kvm_vcpu *vcpu)
+{
+	if (!vcpu_has_sve(vcpu))
+		return 0;
+
+	return read_sanitised_ftr_reg(SYS_ID_AA64ZFR0_EL1);
+}
+
+static bool access_id_aa64zfr0_el1(struct kvm_vcpu *vcpu,
+				   struct sys_reg_params *p,
+				   const struct sys_reg_desc *rd)
+{
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, rd);
+
+	p->regval = guest_id_aa64zfr0_el1(vcpu);
+	return true;
+}
+
+static int get_id_aa64zfr0_el1(struct kvm_vcpu *vcpu,
+		const struct sys_reg_desc *rd,
+		const struct kvm_one_reg *reg, void __user *uaddr)
+{
+	u64 val;
+
+	if (WARN_ON(!vcpu_has_sve(vcpu)))
+		return -ENOENT;
+
+	val = guest_id_aa64zfr0_el1(vcpu);
+	return reg_to_user(uaddr, &val, reg->id);
+}
+
+static int set_id_aa64zfr0_el1(struct kvm_vcpu *vcpu,
+		const struct sys_reg_desc *rd,
+		const struct kvm_one_reg *reg, void __user *uaddr)
+{
+	const u64 id = sys_reg_to_index(rd);
+	int err;
+	u64 val;
+
+	if (WARN_ON(!vcpu_has_sve(vcpu)))
+		return -ENOENT;
+
+	err = reg_from_user(&val, uaddr, id);
+	if (err)
+		return err;
+
+	/* This is what we mean by invariant: you can't change it. */
+	if (val != guest_id_aa64zfr0_el1(vcpu))
+		return -EINVAL;
+
+	return 0;
+}
+
 /*
  * cpufeature ID register user accessors
  *
@@ -1107,16 +1211,18 @@ static u64 sys_reg_to_index(const struct sys_reg_desc *reg);
  * are stored, and for set_id_reg() we don't allow the effective value
  * to be changed.
  */
-static int __get_id_reg(const struct sys_reg_desc *rd, void __user *uaddr,
+static int __get_id_reg(const struct kvm_vcpu *vcpu,
+			const struct sys_reg_desc *rd, void __user *uaddr,
 			bool raz)
 {
 	const u64 id = sys_reg_to_index(rd);
-	const u64 val = read_id_reg(rd, raz);
+	const u64 val = read_id_reg(vcpu, rd, raz);
 
 	return reg_to_user(uaddr, &val, id);
 }
 
-static int __set_id_reg(const struct sys_reg_desc *rd, void __user *uaddr,
+static int __set_id_reg(const struct kvm_vcpu *vcpu,
+			const struct sys_reg_desc *rd, void __user *uaddr,
 			bool raz)
 {
 	const u64 id = sys_reg_to_index(rd);
@@ -1128,7 +1234,7 @@ static int __set_id_reg(const struct sys_reg_desc *rd, void __user *uaddr,
 		return err;
 
 	/* This is what we mean by invariant: you can't change it. */
-	if (val != read_id_reg(rd, raz))
+	if (val != read_id_reg(vcpu, rd, raz))
 		return -EINVAL;
 
 	return 0;
@@ -1137,25 +1243,25 @@ static int __set_id_reg(const struct sys_reg_desc *rd, void __user *uaddr,
 static int get_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 		      const struct kvm_one_reg *reg, void __user *uaddr)
 {
-	return __get_id_reg(rd, uaddr, false);
+	return __get_id_reg(vcpu, rd, uaddr, false);
 }
 
 static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 		      const struct kvm_one_reg *reg, void __user *uaddr)
 {
-	return __set_id_reg(rd, uaddr, false);
+	return __set_id_reg(vcpu, rd, uaddr, false);
 }
 
 static int get_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 			  const struct kvm_one_reg *reg, void __user *uaddr)
 {
-	return __get_id_reg(rd, uaddr, true);
+	return __get_id_reg(vcpu, rd, uaddr, true);
 }
 
 static int set_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 			  const struct kvm_one_reg *reg, void __user *uaddr)
 {
-	return __set_id_reg(rd, uaddr, true);
+	return __set_id_reg(vcpu, rd, uaddr, true);
 }
 
 static bool access_ctr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
@@ -1343,7 +1449,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	ID_SANITISED(ID_AA64PFR1_EL1),
 	ID_UNALLOCATED(4,2),
 	ID_UNALLOCATED(4,3),
-	ID_UNALLOCATED(4,4),
+	{ SYS_DESC(SYS_ID_AA64ZFR0_EL1), access_id_aa64zfr0_el1, .get_user = get_id_aa64zfr0_el1, .set_user = set_id_aa64zfr0_el1, .visibility = sve_id_visibility },
 	ID_UNALLOCATED(4,5),
 	ID_UNALLOCATED(4,6),
 	ID_UNALLOCATED(4,7),
@@ -1380,10 +1486,17 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	{ SYS_DESC(SYS_SCTLR_EL1), access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 },
 	{ SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 },
+	{ SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility },
 	{ SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 },
 	{ SYS_DESC(SYS_TTBR1_EL1), access_vm_reg, reset_unknown, TTBR1_EL1 },
 	{ SYS_DESC(SYS_TCR_EL1), access_vm_reg, reset_val, TCR_EL1, 0 },
 
+	PTRAUTH_KEY(APIA),
+	PTRAUTH_KEY(APIB),
+	PTRAUTH_KEY(APDA),
+	PTRAUTH_KEY(APDB),
+	PTRAUTH_KEY(APGA),
+
 	{ 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 },
@@ -1924,6 +2037,12 @@ static void perform_access(struct kvm_vcpu *vcpu,
 {
 	trace_kvm_sys_access(*vcpu_pc(vcpu), params, r);
 
+	/* Check for regs disabled by runtime config */
+	if (sysreg_hidden_from_guest(vcpu, r)) {
+		kvm_inject_undefined(vcpu);
+		return;
+	}
+
 	/*
 	 * Not having an accessor means that we have configured a trap
 	 * that we don't know how to handle. This certainly qualifies
@@ -2435,6 +2554,10 @@ int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg
 	if (!r)
 		return get_invariant_sys_reg(reg->id, uaddr);
 
+	/* Check for regs disabled by runtime config */
+	if (sysreg_hidden_from_user(vcpu, r))
+		return -ENOENT;
+
 	if (r->get_user)
 		return (r->get_user)(vcpu, r, reg, uaddr);
 
@@ -2456,6 +2579,10 @@ int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg
 	if (!r)
 		return set_invariant_sys_reg(reg->id, uaddr);
 
+	/* Check for regs disabled by runtime config */
+	if (sysreg_hidden_from_user(vcpu, r))
+		return -ENOENT;
+
 	if (r->set_user)
 		return (r->set_user)(vcpu, r, reg, uaddr);
 
@@ -2512,7 +2639,8 @@ static bool copy_reg_to_user(const struct sys_reg_desc *reg, u64 __user **uind)
 	return true;
 }
 
-static int walk_one_sys_reg(const struct sys_reg_desc *rd,
+static int walk_one_sys_reg(const struct kvm_vcpu *vcpu,
+			    const struct sys_reg_desc *rd,
 			    u64 __user **uind,
 			    unsigned int *total)
 {
@@ -2523,6 +2651,9 @@ static int walk_one_sys_reg(const struct sys_reg_desc *rd,
 	if (!(rd->reg || rd->get_user))
 		return 0;
 
+	if (sysreg_hidden_from_user(vcpu, rd))
+		return 0;
+
 	if (!copy_reg_to_user(rd, uind))
 		return -EFAULT;
 
@@ -2551,9 +2682,9 @@ static int walk_sys_regs(struct kvm_vcpu *vcpu, u64 __user *uind)
 		int cmp = cmp_sys_reg(i1, i2);
 		/* target-specific overrides generic entry. */
 		if (cmp <= 0)
-			err = walk_one_sys_reg(i1, &uind, &total);
+			err = walk_one_sys_reg(vcpu, i1, &uind, &total);
 		else
-			err = walk_one_sys_reg(i2, &uind, &total);
+			err = walk_one_sys_reg(vcpu, i2, &uind, &total);
 
 		if (err)
 			return err;

arch/arm64/kvm/sys_regs.h

@@ -64,8 +64,15 @@ struct sys_reg_desc {
 			const struct kvm_one_reg *reg, void __user *uaddr);
 	int (*set_user)(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 			const struct kvm_one_reg *reg, void __user *uaddr);
+
+	/* Return mask of REG_* runtime visibility overrides */
+	unsigned int (*visibility)(const struct kvm_vcpu *vcpu,
+				   const struct sys_reg_desc *rd);
 };
 
+#define REG_HIDDEN_USER		(1 << 0) /* hidden from userspace ioctls */
+#define REG_HIDDEN_GUEST	(1 << 1) /* hidden from guest */
+
 static inline void print_sys_reg_instr(const struct sys_reg_params *p)
 {
 	/* Look, we even formatted it for you to paste into the table! */
@@ -102,6 +109,24 @@ static inline void reset_val(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r
 	__vcpu_sys_reg(vcpu, r->reg) = r->val;
 }
 
+static inline bool sysreg_hidden_from_guest(const struct kvm_vcpu *vcpu,
+					    const struct sys_reg_desc *r)
+{
+	if (likely(!r->visibility))
+		return false;
+
+	return r->visibility(vcpu, r) & REG_HIDDEN_GUEST;
+}
+
+static inline bool sysreg_hidden_from_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_USER;
+}
+
 static inline int cmp_sys_reg(const struct sys_reg_desc *i1,
 			      const struct sys_reg_desc *i2)
 {

include/uapi/linux/kvm.h

@@ -990,6 +990,9 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_HYPERV_CPUID 167
 #define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 168
 #define KVM_CAP_PPC_IRQ_XIVE 169
+#define KVM_CAP_ARM_SVE 170
+#define KVM_CAP_ARM_PTRAUTH_ADDRESS 171
+#define KVM_CAP_ARM_PTRAUTH_GENERIC 172
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1147,6 +1150,7 @@ struct kvm_dirty_tlb {
 #define KVM_REG_SIZE_U256	0x0050000000000000ULL
 #define KVM_REG_SIZE_U512	0x0060000000000000ULL
 #define KVM_REG_SIZE_U1024	0x0070000000000000ULL
+#define KVM_REG_SIZE_U2048	0x0080000000000000ULL
 
 struct kvm_reg_list {
 	__u64 n; /* number of regs */
@@ -1444,6 +1448,9 @@ struct kvm_enc_region {
 /* Available with KVM_CAP_HYPERV_CPUID */
 #define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2)
 
+/* Available with KVM_CAP_ARM_SVE */
+#define KVM_ARM_VCPU_FINALIZE	  _IOW(KVMIO,  0xc2, int)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */

virt/kvm/arm/arm.c

@@ -56,7 +56,7 @@
 __asm__(".arch_extension	virt");
 #endif
 
-DEFINE_PER_CPU(kvm_cpu_context_t, kvm_host_cpu_state);
+DEFINE_PER_CPU(kvm_host_data_t, kvm_host_data);
 static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
 
 /* Per-CPU variable containing the currently running vcpu. */
@@ -357,8 +357,10 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	int *last_ran;
+	kvm_host_data_t *cpu_data;
 
 	last_ran = this_cpu_ptr(vcpu->kvm->arch.last_vcpu_ran);
+	cpu_data = this_cpu_ptr(&kvm_host_data);
 
 	/*
 	 * We might get preempted before the vCPU actually runs, but
@@ -370,18 +372,21 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	}
 
 	vcpu->cpu = cpu;
-	vcpu->arch.host_cpu_context = this_cpu_ptr(&kvm_host_cpu_state);
+	vcpu->arch.host_cpu_context = &cpu_data->host_ctxt;
 
 	kvm_arm_set_running_vcpu(vcpu);
 	kvm_vgic_load(vcpu);
 	kvm_timer_vcpu_load(vcpu);
 	kvm_vcpu_load_sysregs(vcpu);
 	kvm_arch_vcpu_load_fp(vcpu);
+	kvm_vcpu_pmu_restore_guest(vcpu);
 
 	if (single_task_running())
 		vcpu_clear_wfe_traps(vcpu);
 	else
 		vcpu_set_wfe_traps(vcpu);
+
+	vcpu_ptrauth_setup_lazy(vcpu);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -390,6 +395,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	kvm_vcpu_put_sysregs(vcpu);
 	kvm_timer_vcpu_put(vcpu);
 	kvm_vgic_put(vcpu);
+	kvm_vcpu_pmu_restore_host(vcpu);
 
 	vcpu->cpu = -1;
 
@@ -542,6 +548,9 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 	if (likely(vcpu->arch.has_run_once))
 		return 0;
 
+	if (!kvm_arm_vcpu_is_finalized(vcpu))
+		return -EPERM;
+
 	vcpu->arch.has_run_once = true;
 
 	if (likely(irqchip_in_kernel(kvm))) {
@@ -1113,6 +1122,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		if (unlikely(!kvm_vcpu_initialized(vcpu)))
 			break;
 
+		r = -EPERM;
+		if (!kvm_arm_vcpu_is_finalized(vcpu))
+			break;
+
 		r = -EFAULT;
 		if (copy_from_user(&reg_list, user_list, sizeof(reg_list)))
 			break;
@@ -1166,6 +1179,17 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 
 		return kvm_arm_vcpu_set_events(vcpu, &events);
 	}
+	case KVM_ARM_VCPU_FINALIZE: {
+		int what;
+
+		if (!kvm_vcpu_initialized(vcpu))
+			return -ENOEXEC;
+
+		if (get_user(what, (const int __user *)argp))
+			return -EFAULT;
+
+		return kvm_arm_vcpu_finalize(vcpu, what);
+	}
 	default:
 		r = -EINVAL;
 	}
@@ -1546,11 +1570,11 @@ static int init_hyp_mode(void)
 	}
 
 	for_each_possible_cpu(cpu) {
-		kvm_cpu_context_t *cpu_ctxt;
+		kvm_host_data_t *cpu_data;
 
-		cpu_ctxt = per_cpu_ptr(&kvm_host_cpu_state, cpu);
-		kvm_init_host_cpu_context(cpu_ctxt, cpu);
-		err = create_hyp_mappings(cpu_ctxt, cpu_ctxt + 1, PAGE_HYP);
+		cpu_data = per_cpu_ptr(&kvm_host_data, cpu);
+		kvm_init_host_cpu_context(&cpu_data->host_ctxt, cpu);
+		err = create_hyp_mappings(cpu_data, cpu_data + 1, PAGE_HYP);
 
 		if (err) {
 			kvm_err("Cannot map host CPU state: %d\n", err);
@@ -1661,6 +1685,10 @@ int kvm_arch_init(void *opaque)
 	if (err)
 		return err;
 
+	err = kvm_arm_init_sve();
+	if (err)
+		return err;
+
 	if (!in_hyp_mode) {
 		err = init_hyp_mode();
 		if (err)