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

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

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

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

  Generic:
   - dirty page tracking improvements"

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

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/devices/vm.txt

@@ -141,7 +141,8 @@ struct kvm_s390_vm_cpu_subfunc {
        u8 pcc[16];           # valid with Message-Security-Assist-Extension 4
        u8 ppno[16];          # valid with Message-Security-Assist-Extension 5
        u8 kma[16];           # valid with Message-Security-Assist-Extension 8
-       u8 reserved[1808];    # reserved for future instructions
+       u8 kdsa[16];          # valid with Message-Security-Assist-Extension 9
+       u8 reserved[1792];    # reserved for future instructions
 };
 
 Parameters: address of a buffer to load the subfunction blocks from.

Documentation/virtual/kvm/devices/xive.txt

+POWER9 eXternal Interrupt Virtualization Engine (XIVE Gen1)
+==========================================================
+
+Device types supported:
+  KVM_DEV_TYPE_XIVE     POWER9 XIVE Interrupt Controller generation 1
+
+This device acts as a VM interrupt controller. It provides the KVM
+interface to configure the interrupt sources of a VM in the underlying
+POWER9 XIVE interrupt controller.
+
+Only one XIVE instance may be instantiated. A guest XIVE device
+requires a POWER9 host and the guest OS should have support for the
+XIVE native exploitation interrupt mode. If not, it should run using
+the legacy interrupt mode, referred as XICS (POWER7/8).
+
+* Device Mappings
+
+  The KVM device exposes different MMIO ranges of the XIVE HW which
+  are required for interrupt management. These are exposed to the
+  guest in VMAs populated with a custom VM fault handler.
+
+  1. Thread Interrupt Management Area (TIMA)
+
+  Each thread has an associated Thread Interrupt Management context
+  composed of a set of registers. These registers let the thread
+  handle priority management and interrupt acknowledgment. The most
+  important are :
+
+      - Interrupt Pending Buffer     (IPB)
+      - Current Processor Priority   (CPPR)
+      - Notification Source Register (NSR)
+
+  They are exposed to software in four different pages each proposing
+  a view with a different privilege. The first page is for the
+  physical thread context and the second for the hypervisor. Only the
+  third (operating system) and the fourth (user level) are exposed the
+  guest.
+
+  2. Event State Buffer (ESB)
+
+  Each source is associated with an Event State Buffer (ESB) with
+  either a pair of even/odd pair of pages which provides commands to
+  manage the source: to trigger, to EOI, to turn off the source for
+  instance.
+
+  3. Device pass-through
+
+  When a device is passed-through into the guest, the source
+  interrupts are from a different HW controller (PHB4) and the ESB
+  pages exposed to the guest should accommadate this change.
+
+  The passthru_irq helpers, kvmppc_xive_set_mapped() and
+  kvmppc_xive_clr_mapped() are called when the device HW irqs are
+  mapped into or unmapped from the guest IRQ number space. The KVM
+  device extends these helpers to clear the ESB pages of the guest IRQ
+  number being mapped and then lets the VM fault handler repopulate.
+  The handler will insert the ESB page corresponding to the HW
+  interrupt of the device being passed-through or the initial IPI ESB
+  page if the device has being removed.
+
+  The ESB remapping is fully transparent to the guest and the OS
+  device driver. All handling is done within VFIO and the above
+  helpers in KVM-PPC.
+
+* Groups:
+
+  1. KVM_DEV_XIVE_GRP_CTRL
+  Provides global controls on the device
+  Attributes:
+    1.1 KVM_DEV_XIVE_RESET (write only)
+    Resets the interrupt controller configuration for sources and event
+    queues. To be used by kexec and kdump.
+    Errors: none
+
+    1.2 KVM_DEV_XIVE_EQ_SYNC (write only)
+    Sync all the sources and queues and mark the EQ pages dirty. This
+    to make sure that a consistent memory state is captured when
+    migrating the VM.
+    Errors: none
+
+  2. KVM_DEV_XIVE_GRP_SOURCE (write only)
+  Initializes a new source in the XIVE device and mask it.
+  Attributes:
+    Interrupt source number  (64-bit)
+  The kvm_device_attr.addr points to a __u64 value:
+  bits:     | 63   ....  2 |   1   |   0
+  values:   |    unused    | level | type
+  - type:  0:MSI 1:LSI
+  - level: assertion level in case of an LSI.
+  Errors:
+    -E2BIG:  Interrupt source number is out of range
+    -ENOMEM: Could not create a new source block
+    -EFAULT: Invalid user pointer for attr->addr.
+    -ENXIO:  Could not allocate underlying HW interrupt
+
+  3. KVM_DEV_XIVE_GRP_SOURCE_CONFIG (write only)
+  Configures source targeting
+  Attributes:
+    Interrupt source number  (64-bit)
+  The kvm_device_attr.addr points to a __u64 value:
+  bits:     | 63   ....  33 |  32  | 31 .. 3 |  2 .. 0
+  values:   |    eisn       | mask |  server | priority
+  - priority: 0-7 interrupt priority level
+  - server: CPU number chosen to handle the interrupt
+  - mask: mask flag (unused)
+  - eisn: Effective Interrupt Source Number
+  Errors:
+    -ENOENT: Unknown source number
+    -EINVAL: Not initialized source number
+    -EINVAL: Invalid priority
+    -EINVAL: Invalid CPU number.
+    -EFAULT: Invalid user pointer for attr->addr.
+    -ENXIO:  CPU event queues not configured or configuration of the
+             underlying HW interrupt failed
+    -EBUSY:  No CPU available to serve interrupt
+
+  4. KVM_DEV_XIVE_GRP_EQ_CONFIG (read-write)
+  Configures an event queue of a CPU
+  Attributes:
+    EQ descriptor identifier (64-bit)
+  The EQ descriptor identifier is a tuple (server, priority) :
+  bits:     | 63   ....  32 | 31 .. 3 |  2 .. 0
+  values:   |    unused     |  server | priority
+  The kvm_device_attr.addr points to :
+    struct kvm_ppc_xive_eq {
+	__u32 flags;
+	__u32 qshift;
+	__u64 qaddr;
+	__u32 qtoggle;
+	__u32 qindex;
+	__u8  pad[40];
+    };
+  - flags: queue flags
+    KVM_XIVE_EQ_ALWAYS_NOTIFY (required)
+	forces notification without using the coalescing mechanism
+	provided by the XIVE END ESBs.
+  - qshift: queue size (power of 2)
+  - qaddr: real address of queue
+  - qtoggle: current queue toggle bit
+  - qindex: current queue index
+  - pad: reserved for future use
+  Errors:
+    -ENOENT: Invalid CPU number
+    -EINVAL: Invalid priority
+    -EINVAL: Invalid flags
+    -EINVAL: Invalid queue size
+    -EINVAL: Invalid queue address
+    -EFAULT: Invalid user pointer for attr->addr.
+    -EIO:    Configuration of the underlying HW failed
+
+  5. KVM_DEV_XIVE_GRP_SOURCE_SYNC (write only)
+  Synchronize the source to flush event notifications
+  Attributes:
+    Interrupt source number  (64-bit)
+  Errors:
+    -ENOENT: Unknown source number
+    -EINVAL: Not initialized source number
+
+* VCPU state
+
+  The XIVE IC maintains VP interrupt state in an internal structure
+  called the NVT. When a VP is not dispatched on a HW processor
+  thread, this structure can be updated by HW if the VP is the target
+  of an event notification.
+
+  It is important for migration to capture the cached IPB from the NVT
+  as it synthesizes the priorities of the pending interrupts. We
+  capture a bit more to report debug information.
+
+  KVM_REG_PPC_VP_STATE (2 * 64bits)
+  bits:     |  63  ....  32  |  31  ....  0  |
+  values:   |   TIMA word0   |   TIMA word1  |
+  bits:     | 127       ..........       64  |
+  values:   |            unused              |
+
+* Migration:
+
+  Saving the state of a VM using the XIVE native exploitation mode
+  should follow a specific sequence. When the VM is stopped :
+
+  1. Mask all sources (PQ=01) to stop the flow of events.
+
+  2. Sync the XIVE device with the KVM control KVM_DEV_XIVE_EQ_SYNC to
+  flush any in-flight event notification and to stabilize the EQs. At
+  this stage, the EQ pages are marked dirty to make sure they are
+  transferred in the migration sequence.
+
+  3. Capture the state of the source targeting, the EQs configuration
+  and the state of thread interrupt context registers.
+
+  Restore is similar :
+
+  1. Restore the EQ configuration. As targeting depends on it.
+  2. Restore targeting
+  3. Restore the thread interrupt contexts
+  4. Restore the source states
+  5. Let the vCPU run

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

@@ -1341,6 +1341,7 @@ menu "ARMv8.3 architectural features"
 config ARM64_PTR_AUTH
 	bool "Enable support for pointer authentication"
 	default y
+	depends on !KVM || ARM64_VHE
 	help
 	  Pointer authentication (part of the ARMv8.3 Extensions) provides
 	  instructions for signing and authenticating pointers against secret
@@ -1354,8 +1355,9 @@ config ARM64_PTR_AUTH
 	  context-switched along with the process.
 
 	  The feature is detected at runtime. If the feature is not present in
-	  hardware it will not be advertised to userspace nor will it be
-	  enabled.
+	  hardware it will not be advertised to userspace/KVM guest nor will it
+	  be enabled. However, KVM guest also require VHE mode and hence
+	  CONFIG_ARM64_VHE=y option to use this feature.
 
 endmenu
 

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

@@ -1913,7 +1913,7 @@ 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/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/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.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)
 {

arch/powerpc/include/asm/kvm_host.h

@@ -201,6 +201,8 @@ struct kvmppc_spapr_tce_iommu_table {
 	struct kref kref;
 };
 
+#define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
+
 struct kvmppc_spapr_tce_table {
 	struct list_head list;
 	struct kvm *kvm;
@@ -210,6 +212,7 @@ struct kvmppc_spapr_tce_table {
 	u64 offset;		/* in pages */
 	u64 size;		/* window size in pages */
 	struct list_head iommu_tables;
+	struct mutex alloc_lock;
 	struct page *pages[0];
 };
 
@@ -222,6 +225,7 @@ extern struct kvm_device_ops kvm_xics_ops;
 struct kvmppc_xive;
 struct kvmppc_xive_vcpu;
 extern struct kvm_device_ops kvm_xive_ops;
+extern struct kvm_device_ops kvm_xive_native_ops;
 
 struct kvmppc_passthru_irqmap;
 
@@ -312,7 +316,11 @@ struct kvm_arch {
 #endif
 #ifdef CONFIG_KVM_XICS
 	struct kvmppc_xics *xics;
-	struct kvmppc_xive *xive;
+	struct kvmppc_xive *xive;    /* Current XIVE device in use */
+	struct {
+		struct kvmppc_xive *native;
+		struct kvmppc_xive *xics_on_xive;
+	} xive_devices;
 	struct kvmppc_passthru_irqmap *pimap;
 #endif
 	struct kvmppc_ops *kvm_ops;
@@ -449,6 +457,7 @@ struct kvmppc_passthru_irqmap {
 #define KVMPPC_IRQ_DEFAULT	0
 #define KVMPPC_IRQ_MPIC		1
 #define KVMPPC_IRQ_XICS		2 /* Includes a XIVE option */
+#define KVMPPC_IRQ_XIVE		3 /* XIVE native exploitation mode */
 
 #define MMIO_HPTE_CACHE_SIZE	4
 

arch/powerpc/include/asm/kvm_ppc.h

@@ -197,10 +197,6 @@ extern struct kvmppc_spapr_tce_table *kvmppc_find_table(
 		(iommu_tce_check_ioba((stt)->page_shift, (stt)->offset, \
 				(stt)->size, (ioba), (npages)) ?        \
 				H_PARAMETER : H_SUCCESS)
-extern long kvmppc_tce_to_ua(struct kvm *kvm, unsigned long tce,
-		unsigned long *ua, unsigned long **prmap);
-extern void kvmppc_tce_put(struct kvmppc_spapr_tce_table *tt,
-		unsigned long idx, unsigned long tce);
 extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 			     unsigned long ioba, unsigned long tce);
 extern long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
@@ -273,6 +269,7 @@ union kvmppc_one_reg {
 		u64	addr;
 		u64	length;
 	}	vpaval;
+	u64	xive_timaval[2];
 };
 
 struct kvmppc_ops {
@@ -480,6 +477,9 @@ extern void kvm_hv_vm_activated(void);
 extern void kvm_hv_vm_deactivated(void);
 extern bool kvm_hv_mode_active(void);
 
+extern void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu,
+					struct kvm_nested_guest *nested);
+
 #else
 static inline void __init kvm_cma_reserve(void)
 {}
@@ -594,6 +594,22 @@ extern int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval);
 extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
 			       int level, bool line_status);
 extern void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu);
+
+static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.irq_type == KVMPPC_IRQ_XIVE;
+}
+
+extern int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
+					   struct kvm_vcpu *vcpu, u32 cpu);
+extern void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu);
+extern void kvmppc_xive_native_init_module(void);
+extern void kvmppc_xive_native_exit_module(void);
+extern int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu,
+				     union kvmppc_one_reg *val);
+extern int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu,
+				     union kvmppc_one_reg *val);
+
 #else
 static inline int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server,
 				       u32 priority) { return -1; }
@@ -617,6 +633,21 @@ static inline int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval) { retur
 static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
 				      int level, bool line_status) { return -ENODEV; }
 static inline void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) { }
+
+static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
+	{ return 0; }
+static inline int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
+			  struct kvm_vcpu *vcpu, u32 cpu) { return -EBUSY; }
+static inline void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu) { }
+static inline void kvmppc_xive_native_init_module(void) { }
+static inline void kvmppc_xive_native_exit_module(void) { }
+static inline int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu,
+					    union kvmppc_one_reg *val)
+{ return 0; }
+static inline int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu,
+					    union kvmppc_one_reg *val)
+{ return -ENOENT; }
+
 #endif /* CONFIG_KVM_XIVE */
 
 #if defined(CONFIG_PPC_POWERNV) && defined(CONFIG_KVM_BOOK3S_64_HANDLER)
@@ -665,6 +696,8 @@ long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags,
                         unsigned long pte_index);
 long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
                         unsigned long pte_index);
+long kvmppc_rm_h_page_init(struct kvm_vcpu *vcpu, unsigned long flags,
+			   unsigned long dest, unsigned long src);
 long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
                           unsigned long slb_v, unsigned int status, bool data);
 unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu);

arch/powerpc/include/asm/xive.h

@@ -23,6 +23,7 @@
  * same offset regardless of where the code is executing
  */
 extern void __iomem *xive_tima;
+extern unsigned long xive_tima_os;
 
 /*
  * Offset in the TM area of our current execution level (provided by
@@ -73,6 +74,8 @@ struct xive_q {
 	u32			esc_irq;
 	atomic_t		count;
 	atomic_t		pending_count;
+	u64			guest_qaddr;
+	u32			guest_qshift;
 };
 
 /* Global enable flags for the XIVE support */

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

@@ -482,6 +482,8 @@ struct kvm_ppc_cpu_char {
 #define  KVM_REG_PPC_ICP_PPRI_SHIFT	16	/* pending irq priority */
 #define  KVM_REG_PPC_ICP_PPRI_MASK	0xff
 
+#define KVM_REG_PPC_VP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x8d)
+
 /* Device control API: PPC-specific devices */
 #define KVM_DEV_MPIC_GRP_MISC		1
 #define   KVM_DEV_MPIC_BASE_ADDR	0	/* 64-bit */
@@ -677,4 +679,48 @@ struct kvm_ppc_cpu_char {
 #define  KVM_XICS_PRESENTED		(1ULL << 43)
 #define  KVM_XICS_QUEUED		(1ULL << 44)
 
+/* POWER9 XIVE Native Interrupt Controller */
+#define KVM_DEV_XIVE_GRP_CTRL		1
+#define   KVM_DEV_XIVE_RESET		1
+#define   KVM_DEV_XIVE_EQ_SYNC		2
+#define KVM_DEV_XIVE_GRP_SOURCE		2	/* 64-bit source identifier */
+#define KVM_DEV_XIVE_GRP_SOURCE_CONFIG	3	/* 64-bit source identifier */
+#define KVM_DEV_XIVE_GRP_EQ_CONFIG	4	/* 64-bit EQ identifier */
+#define KVM_DEV_XIVE_GRP_SOURCE_SYNC	5       /* 64-bit source identifier */
+
+/* Layout of 64-bit XIVE source attribute values */
+#define KVM_XIVE_LEVEL_SENSITIVE	(1ULL << 0)
+#define KVM_XIVE_LEVEL_ASSERTED		(1ULL << 1)
+
+/* Layout of 64-bit XIVE source configuration attribute values */
+#define KVM_XIVE_SOURCE_PRIORITY_SHIFT	0
+#define KVM_XIVE_SOURCE_PRIORITY_MASK	0x7
+#define KVM_XIVE_SOURCE_SERVER_SHIFT	3
+#define KVM_XIVE_SOURCE_SERVER_MASK	0xfffffff8ULL
+#define KVM_XIVE_SOURCE_MASKED_SHIFT	32
+#define KVM_XIVE_SOURCE_MASKED_MASK	0x100000000ULL
+#define KVM_XIVE_SOURCE_EISN_SHIFT	33
+#define KVM_XIVE_SOURCE_EISN_MASK	0xfffffffe00000000ULL
+
+/* Layout of 64-bit EQ identifier */
+#define KVM_XIVE_EQ_PRIORITY_SHIFT	0
+#define KVM_XIVE_EQ_PRIORITY_MASK	0x7
+#define KVM_XIVE_EQ_SERVER_SHIFT	3
+#define KVM_XIVE_EQ_SERVER_MASK		0xfffffff8ULL
+
+/* Layout of EQ configuration values (64 bytes) */
+struct kvm_ppc_xive_eq {
+	__u32 flags;
+	__u32 qshift;
+	__u64 qaddr;
+	__u32 qtoggle;
+	__u32 qindex;
+	__u8  pad[40];
+};
+
+#define KVM_XIVE_EQ_ALWAYS_NOTIFY	0x00000001
+
+#define KVM_XIVE_TIMA_PAGE_OFFSET	0
+#define KVM_XIVE_ESB_PAGE_OFFSET	4
+
 #endif /* __LINUX_KVM_POWERPC_H */

arch/powerpc/kvm/Makefile

@@ -94,7 +94,7 @@ endif
 kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
 	book3s_xics.o
 
-kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o
+kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o book3s_xive_native.o
 kvm-book3s_64-objs-$(CONFIG_SPAPR_TCE_IOMMU) += book3s_64_vio.o
 
 kvm-book3s_64-module-objs := \

arch/powerpc/kvm/book3s.c

@@ -651,6 +651,18 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
 				*val = get_reg_val(id, kvmppc_xics_get_icp(vcpu));
 			break;
 #endif /* CONFIG_KVM_XICS */
+#ifdef CONFIG_KVM_XIVE
+		case KVM_REG_PPC_VP_STATE:
+			if (!vcpu->arch.xive_vcpu) {
+				r = -ENXIO;
+				break;
+			}
+			if (xive_enabled())
+				r = kvmppc_xive_native_get_vp(vcpu, val);
+			else
+				r = -ENXIO;
+			break;
+#endif /* CONFIG_KVM_XIVE */
 		case KVM_REG_PPC_FSCR:
 			*val = get_reg_val(id, vcpu->arch.fscr);
 			break;
@@ -724,6 +736,18 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
 				r = kvmppc_xics_set_icp(vcpu, set_reg_val(id, *val));
 			break;
 #endif /* CONFIG_KVM_XICS */
+#ifdef CONFIG_KVM_XIVE
+		case KVM_REG_PPC_VP_STATE:
+			if (!vcpu->arch.xive_vcpu) {
+				r = -ENXIO;
+				break;
+			}
+			if (xive_enabled())
+				r = kvmppc_xive_native_set_vp(vcpu, val);
+			else
+				r = -ENXIO;
+			break;
+#endif /* CONFIG_KVM_XIVE */
 		case KVM_REG_PPC_FSCR:
 			vcpu->arch.fscr = set_reg_val(id, *val);
 			break;
@@ -891,6 +915,17 @@ void kvmppc_core_destroy_vm(struct kvm *kvm)
 	kvmppc_rtas_tokens_free(kvm);
 	WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables));
 #endif
+
+#ifdef CONFIG_KVM_XICS
+	/*
+	 * Free the XIVE devices which are not directly freed by the
+	 * device 'release' method
+	 */
+	kfree(kvm->arch.xive_devices.native);
+	kvm->arch.xive_devices.native = NULL;
+	kfree(kvm->arch.xive_devices.xics_on_xive);
+	kvm->arch.xive_devices.xics_on_xive = NULL;
+#endif /* CONFIG_KVM_XICS */
 }
 
 int kvmppc_h_logical_ci_load(struct kvm_vcpu *vcpu)
@@ -1050,6 +1085,9 @@ static int kvmppc_book3s_init(void)
 	if (xics_on_xive()) {
 		kvmppc_xive_init_module();
 		kvm_register_device_ops(&kvm_xive_ops, KVM_DEV_TYPE_XICS);
+		kvmppc_xive_native_init_module();
+		kvm_register_device_ops(&kvm_xive_native_ops,
+					KVM_DEV_TYPE_XIVE);
 	} else
 #endif
 		kvm_register_device_ops(&kvm_xics_ops, KVM_DEV_TYPE_XICS);
@@ -1060,8 +1098,10 @@ static int kvmppc_book3s_init(void)
 static void kvmppc_book3s_exit(void)
 {
 #ifdef CONFIG_KVM_XICS
-	if (xics_on_xive())
+	if (xics_on_xive()) {
 		kvmppc_xive_exit_module();
+		kvmppc_xive_native_exit_module();
+	}
 #endif
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	kvmppc_book3s_exit_pr();

arch/powerpc/kvm/book3s_64_vio.c

@@ -228,11 +228,33 @@ static void release_spapr_tce_table(struct rcu_head *head)
 	unsigned long i, npages = kvmppc_tce_pages(stt->size);
 
 	for (i = 0; i < npages; i++)
-		__free_page(stt->pages[i]);
+		if (stt->pages[i])
+			__free_page(stt->pages[i]);
 
 	kfree(stt);
 }
 
+static struct page *kvm_spapr_get_tce_page(struct kvmppc_spapr_tce_table *stt,
+		unsigned long sttpage)
+{
+	struct page *page = stt->pages[sttpage];
+
+	if (page)
+		return page;
+
+	mutex_lock(&stt->alloc_lock);
+	page = stt->pages[sttpage];
+	if (!page) {
+		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		WARN_ON_ONCE(!page);
+		if (page)
+			stt->pages[sttpage] = page;
+	}
+	mutex_unlock(&stt->alloc_lock);
+
+	return page;
+}
+
 static vm_fault_t kvm_spapr_tce_fault(struct vm_fault *vmf)
 {
 	struct kvmppc_spapr_tce_table *stt = vmf->vma->vm_file->private_data;
@@ -241,7 +263,10 @@ static vm_fault_t kvm_spapr_tce_fault(struct vm_fault *vmf)
 	if (vmf->pgoff >= kvmppc_tce_pages(stt->size))
 		return VM_FAULT_SIGBUS;
 
-	page = stt->pages[vmf->pgoff];
+	page = kvm_spapr_get_tce_page(stt, vmf->pgoff);
+	if (!page)
+		return VM_FAULT_OOM;
+
 	get_page(page);
 	vmf->page = page;
 	return 0;
@@ -296,7 +321,6 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	struct kvmppc_spapr_tce_table *siter;
 	unsigned long npages, size = args->size;
 	int ret = -ENOMEM;
-	int i;
 
 	if (!args->size || args->page_shift < 12 || args->page_shift > 34 ||
 		(args->offset + args->size > (ULLONG_MAX >> args->page_shift)))
@@ -318,14 +342,9 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	stt->offset = args->offset;
 	stt->size = size;
 	stt->kvm = kvm;
+	mutex_init(&stt->alloc_lock);
 	INIT_LIST_HEAD_RCU(&stt->iommu_tables);
 
-	for (i = 0; i < npages; i++) {
-		stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
-		if (!stt->pages[i])
-			goto fail;
-	}
-
 	mutex_lock(&kvm->lock);
 
 	/* Check this LIOBN hasn't been previously allocated */
@@ -352,17 +371,28 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	if (ret >= 0)
 		return ret;
 
- fail:
-	for (i = 0; i < npages; i++)
-		if (stt->pages[i])
-			__free_page(stt->pages[i]);
-
 	kfree(stt);
  fail_acct:
 	kvmppc_account_memlimit(kvmppc_stt_pages(npages), false);
 	return ret;
 }
 
+static long kvmppc_tce_to_ua(struct kvm *kvm, unsigned long tce,
+		unsigned long *ua)
+{
+	unsigned long gfn = tce >> PAGE_SHIFT;
+	struct kvm_memory_slot *memslot;
+
+	memslot = search_memslots(kvm_memslots(kvm), gfn);
+	if (!memslot)
+		return -EINVAL;
+
+	*ua = __gfn_to_hva_memslot(memslot, gfn) |
+		(tce & ~(PAGE_MASK | TCE_PCI_READ | TCE_PCI_WRITE));
+
+	return 0;
+}
+
 static long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt,
 		unsigned long tce)
 {
@@ -378,7 +408,7 @@ static long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt,
 	if (iommu_tce_check_gpa(stt->page_shift, gpa))
 		return H_TOO_HARD;
 
-	if (kvmppc_tce_to_ua(stt->kvm, tce, &ua, NULL))
+	if (kvmppc_tce_to_ua(stt->kvm, tce, &ua))
 		return H_TOO_HARD;
 
 	list_for_each_entry_rcu(stit, &stt->iommu_tables, next) {
@@ -397,6 +427,36 @@ static long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt,
 	return H_SUCCESS;
 }
 
+/*
+ * Handles TCE requests for emulated devices.
+ * Puts guest TCE values to the table and expects user space to convert them.
+ * Cannot fail so kvmppc_tce_validate must be called before it.
+ */
+static void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt,
+		unsigned long idx, unsigned long tce)
+{
+	struct page *page;
+	u64 *tbl;
+	unsigned long sttpage;
+
+	idx -= stt->offset;
+	sttpage = idx / TCES_PER_PAGE;
+	page = stt->pages[sttpage];
+
+	if (!page) {
+		/* We allow any TCE, not just with read|write permissions */
+		if (!tce)
+			return;
+
+		page = kvm_spapr_get_tce_page(stt, sttpage);
+		if (!page)
+			return;
+	}
+	tbl = page_to_virt(page);
+
+	tbl[idx % TCES_PER_PAGE] = tce;
+}
+
 static void kvmppc_clear_tce(struct mm_struct *mm, struct iommu_table *tbl,
 		unsigned long entry)
 {
@@ -551,7 +611,7 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 
 	dir = iommu_tce_direction(tce);
 
-	if ((dir != DMA_NONE) && kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL)) {
+	if ((dir != DMA_NONE) && kvmppc_tce_to_ua(vcpu->kvm, tce, &ua)) {
 		ret = H_PARAMETER;
 		goto unlock_exit;
 	}
@@ -612,7 +672,7 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		return ret;
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	if (kvmppc_tce_to_ua(vcpu->kvm, tce_list, &ua, NULL)) {
+	if (kvmppc_tce_to_ua(vcpu->kvm, tce_list, &ua)) {
 		ret = H_TOO_HARD;
 		goto unlock_exit;
 	}
@@ -647,7 +707,7 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		}
 		tce = be64_to_cpu(tce);
 
-		if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
+		if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua))
 			return H_PARAMETER;
 
 		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {

arch/powerpc/kvm/book3s_64_vio_hv.c

@@ -66,8 +66,6 @@
 
 #endif
 
-#define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
-
 /*
  * Finds a TCE table descriptor by LIOBN.
  *
@@ -88,6 +86,25 @@ struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm *kvm,
 EXPORT_SYMBOL_GPL(kvmppc_find_table);
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+static long kvmppc_rm_tce_to_ua(struct kvm *kvm, unsigned long tce,
+		unsigned long *ua, unsigned long **prmap)
+{
+	unsigned long gfn = tce >> PAGE_SHIFT;
+	struct kvm_memory_slot *memslot;
+
+	memslot = search_memslots(kvm_memslots_raw(kvm), gfn);
+	if (!memslot)
+		return -EINVAL;
+
+	*ua = __gfn_to_hva_memslot(memslot, gfn) |
+		(tce & ~(PAGE_MASK | TCE_PCI_READ | TCE_PCI_WRITE));
+
+	if (prmap)
+		*prmap = &memslot->arch.rmap[gfn - memslot->base_gfn];
+
+	return 0;
+}
+
 /*
  * Validates TCE address.
  * At the moment flags and page mask are validated.
@@ -111,7 +128,7 @@ static long kvmppc_rm_tce_validate(struct kvmppc_spapr_tce_table *stt,
 	if (iommu_tce_check_gpa(stt->page_shift, gpa))
 		return H_PARAMETER;
 
-	if (kvmppc_tce_to_ua(stt->kvm, tce, &ua, NULL))
+	if (kvmppc_rm_tce_to_ua(stt->kvm, tce, &ua, NULL))
 		return H_TOO_HARD;
 
 	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
@@ -129,7 +146,6 @@ static long kvmppc_rm_tce_validate(struct kvmppc_spapr_tce_table *stt,
 
 	return H_SUCCESS;
 }
-#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 /* Note on the use of page_address() in real mode,
  *
@@ -161,13 +177,9 @@ static u64 *kvmppc_page_address(struct page *page)
 /*
  * Handles TCE requests for emulated devices.
  * Puts guest TCE values to the table and expects user space to convert them.
- * Called in both real and virtual modes.
- * Cannot fail so kvmppc_tce_validate must be called before it.
- *
- * WARNING: This will be called in real-mode on HV KVM and virtual
- *          mode on PR KVM
+ * Cannot fail so kvmppc_rm_tce_validate must be called before it.
  */
-void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt,
+static void kvmppc_rm_tce_put(struct kvmppc_spapr_tce_table *stt,
 		unsigned long idx, unsigned long tce)
 {
 	struct page *page;
@@ -175,35 +187,48 @@ void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt,
 
 	idx -= stt->offset;
 	page = stt->pages[idx / TCES_PER_PAGE];
+	/*
+	 * page must not be NULL in real mode,
+	 * kvmppc_rm_ioba_validate() must have taken care of this.
+	 */
+	WARN_ON_ONCE_RM(!page);
 	tbl = kvmppc_page_address(page);
 
 	tbl[idx % TCES_PER_PAGE] = tce;
 }
-EXPORT_SYMBOL_GPL(kvmppc_tce_put);
 
-long kvmppc_tce_to_ua(struct kvm *kvm, unsigned long tce,
-		unsigned long *ua, unsigned long **prmap)
+/*
+ * TCEs pages are allocated in kvmppc_rm_tce_put() which won't be able to do so
+ * in real mode.
+ * Check if kvmppc_rm_tce_put() can succeed in real mode, i.e. a TCEs page is
+ * allocated or not required (when clearing a tce entry).
+ */
+static long kvmppc_rm_ioba_validate(struct kvmppc_spapr_tce_table *stt,
+		unsigned long ioba, unsigned long npages, bool clearing)
 {
-	unsigned long gfn = tce >> PAGE_SHIFT;
-	struct kvm_memory_slot *memslot;
+	unsigned long i, idx, sttpage, sttpages;
+	unsigned long ret = kvmppc_ioba_validate(stt, ioba, npages);
 
-	memslot = search_memslots(kvm_memslots(kvm), gfn);
-	if (!memslot)
-		return -EINVAL;
-
-	*ua = __gfn_to_hva_memslot(memslot, gfn) |
-		(tce & ~(PAGE_MASK | TCE_PCI_READ | TCE_PCI_WRITE));
+	if (ret)
+		return ret;
+	/*
+	 * clearing==true says kvmppc_rm_tce_put won't be allocating pages
+	 * for empty tces.
+	 */
+	if (clearing)
+		return H_SUCCESS;
 
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	if (prmap)
-		*prmap = &memslot->arch.rmap[gfn - memslot->base_gfn];
-#endif
+	idx = (ioba >> stt->page_shift) - stt->offset;
+	sttpage = idx / TCES_PER_PAGE;
+	sttpages = _ALIGN_UP(idx % TCES_PER_PAGE + npages, TCES_PER_PAGE) /
+			TCES_PER_PAGE;
+	for (i = sttpage; i < sttpage + sttpages; ++i)
+		if (!stt->pages[i])
+			return H_TOO_HARD;
 
-	return 0;
+	return H_SUCCESS;
 }
-EXPORT_SYMBOL_GPL(kvmppc_tce_to_ua);
 
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 static long iommu_tce_xchg_rm(struct mm_struct *mm, struct iommu_table *tbl,
 		unsigned long entry, unsigned long *hpa,
 		enum dma_data_direction *direction)
@@ -381,7 +406,7 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	if (!stt)
 		return H_TOO_HARD;
 
-	ret = kvmppc_ioba_validate(stt, ioba, 1);
+	ret = kvmppc_rm_ioba_validate(stt, ioba, 1, tce == 0);
 	if (ret != H_SUCCESS)
 		return ret;
 
@@ -390,7 +415,7 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		return ret;
 
 	dir = iommu_tce_direction(tce);
-	if ((dir != DMA_NONE) && kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
+	if ((dir != DMA_NONE) && kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
 		return H_PARAMETER;
 
 	entry = ioba >> stt->page_shift;
@@ -409,7 +434,7 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		}
 	}
 
-	kvmppc_tce_put(stt, entry, tce);
+	kvmppc_rm_tce_put(stt, entry, tce);
 
 	return H_SUCCESS;
 }
@@ -480,7 +505,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	if (tce_list & (SZ_4K - 1))
 		return H_PARAMETER;
 
-	ret = kvmppc_ioba_validate(stt, ioba, npages);
+	ret = kvmppc_rm_ioba_validate(stt, ioba, npages, false);
 	if (ret != H_SUCCESS)
 		return ret;
 
@@ -492,7 +517,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		 */
 		struct mm_iommu_table_group_mem_t *mem;
 
-		if (kvmppc_tce_to_ua(vcpu->kvm, tce_list, &ua, NULL))
+		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce_list, &ua, NULL))
 			return H_TOO_HARD;
 
 		mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K);
@@ -508,7 +533,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		 * We do not require memory to be preregistered in this case
 		 * so lock rmap and do __find_linux_pte_or_hugepte().
 		 */
-		if (kvmppc_tce_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
+		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
 			return H_TOO_HARD;
 
 		rmap = (void *) vmalloc_to_phys(rmap);
@@ -542,7 +567,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		unsigned long tce = be64_to_cpu(((u64 *)tces)[i]);
 
 		ua = 0;
-		if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
+		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
 			return H_PARAMETER;
 
 		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
@@ -557,7 +582,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 			}
 		}
 
-		kvmppc_tce_put(stt, entry + i, tce);
+		kvmppc_rm_tce_put(stt, entry + i, tce);
 	}
 
 unlock_exit:
@@ -583,7 +608,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 	if (!stt)
 		return H_TOO_HARD;
 
-	ret = kvmppc_ioba_validate(stt, ioba, npages);
+	ret = kvmppc_rm_ioba_validate(stt, ioba, npages, tce_value == 0);
 	if (ret != H_SUCCESS)
 		return ret;
 
@@ -610,7 +635,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 	}
 
 	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
-		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
+		kvmppc_rm_tce_put(stt, ioba >> stt->page_shift, tce_value);
 
 	return H_SUCCESS;
 }
@@ -635,6 +660,10 @@ long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 
 	idx = (ioba >> stt->page_shift) - stt->offset;
 	page = stt->pages[idx / TCES_PER_PAGE];
+	if (!page) {
+		vcpu->arch.regs.gpr[4] = 0;
+		return H_SUCCESS;
+	}
 	tbl = (u64 *)page_address(page);
 
 	vcpu->arch.regs.gpr[4] = tbl[idx % TCES_PER_PAGE];

arch/powerpc/kvm/book3s_hv.c

@@ -750,7 +750,7 @@ static bool kvmppc_doorbell_pending(struct kvm_vcpu *vcpu)
 	/*
 	 * Ensure that the read of vcore->dpdes comes after the read
 	 * of vcpu->doorbell_request.  This barrier matches the
-	 * smb_wmb() in kvmppc_guest_entry_inject().
+	 * smp_wmb() in kvmppc_guest_entry_inject().
 	 */
 	smp_rmb();
 	vc = vcpu->arch.vcore;
@@ -802,6 +802,80 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags,
 	}
 }
 
+/* Copy guest memory in place - must reside within a single memslot */
+static int kvmppc_copy_guest(struct kvm *kvm, gpa_t to, gpa_t from,
+				  unsigned long len)
+{
+	struct kvm_memory_slot *to_memslot = NULL;
+	struct kvm_memory_slot *from_memslot = NULL;
+	unsigned long to_addr, from_addr;
+	int r;
+
+	/* Get HPA for from address */
+	from_memslot = gfn_to_memslot(kvm, from >> PAGE_SHIFT);
+	if (!from_memslot)
+		return -EFAULT;
+	if ((from + len) >= ((from_memslot->base_gfn + from_memslot->npages)
+			     << PAGE_SHIFT))
+		return -EINVAL;
+	from_addr = gfn_to_hva_memslot(from_memslot, from >> PAGE_SHIFT);
+	if (kvm_is_error_hva(from_addr))
+		return -EFAULT;
+	from_addr |= (from & (PAGE_SIZE - 1));
+
+	/* Get HPA for to address */
+	to_memslot = gfn_to_memslot(kvm, to >> PAGE_SHIFT);
+	if (!to_memslot)
+		return -EFAULT;
+	if ((to + len) >= ((to_memslot->base_gfn + to_memslot->npages)
+			   << PAGE_SHIFT))
+		return -EINVAL;
+	to_addr = gfn_to_hva_memslot(to_memslot, to >> PAGE_SHIFT);
+	if (kvm_is_error_hva(to_addr))
+		return -EFAULT;
+	to_addr |= (to & (PAGE_SIZE - 1));
+
+	/* Perform copy */
+	r = raw_copy_in_user((void __user *)to_addr, (void __user *)from_addr,
+			     len);
+	if (r)
+		return -EFAULT;
+	mark_page_dirty(kvm, to >> PAGE_SHIFT);
+	return 0;
+}
+
+static long kvmppc_h_page_init(struct kvm_vcpu *vcpu, unsigned long flags,
+			       unsigned long dest, unsigned long src)
+{
+	u64 pg_sz = SZ_4K;		/* 4K page size */
+	u64 pg_mask = SZ_4K - 1;
+	int ret;
+
+	/* Check for invalid flags (H_PAGE_SET_LOANED covers all CMO flags) */
+	if (flags & ~(H_ICACHE_INVALIDATE | H_ICACHE_SYNCHRONIZE |
+		      H_ZERO_PAGE | H_COPY_PAGE | H_PAGE_SET_LOANED))
+		return H_PARAMETER;
+
+	/* dest (and src if copy_page flag set) must be page aligned */
+	if ((dest & pg_mask) || ((flags & H_COPY_PAGE) && (src & pg_mask)))
+		return H_PARAMETER;
+
+	/* zero and/or copy the page as determined by the flags */
+	if (flags & H_COPY_PAGE) {
+		ret = kvmppc_copy_guest(vcpu->kvm, dest, src, pg_sz);
+		if (ret < 0)
+			return H_PARAMETER;
+	} else if (flags & H_ZERO_PAGE) {
+		ret = kvm_clear_guest(vcpu->kvm, dest, pg_sz);
+		if (ret < 0)
+			return H_PARAMETER;
+	}
+
+	/* We can ignore the remaining flags */
+
+	return H_SUCCESS;
+}
+
 static int kvm_arch_vcpu_yield_to(struct kvm_vcpu *target)
 {
 	struct kvmppc_vcore *vcore = target->arch.vcore;
@@ -1004,6 +1078,11 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		if (nesting_enabled(vcpu->kvm))
 			ret = kvmhv_copy_tofrom_guest_nested(vcpu);
 		break;
+	case H_PAGE_INIT:
+		ret = kvmppc_h_page_init(vcpu, kvmppc_get_gpr(vcpu, 4),
+					 kvmppc_get_gpr(vcpu, 5),
+					 kvmppc_get_gpr(vcpu, 6));
+		break;
 	default:
 		return RESUME_HOST;
 	}
@@ -1048,6 +1127,7 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd)
 	case H_IPOLL:
 	case H_XIRR_X:
 #endif
+	case H_PAGE_INIT:
 		return 1;
 	}
 
@@ -2505,37 +2585,6 @@ static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu)
 	}
 }
 
-static void kvmppc_radix_check_need_tlb_flush(struct kvm *kvm, int pcpu,
-					      struct kvm_nested_guest *nested)
-{
-	cpumask_t *need_tlb_flush;
-	int lpid;
-
-	if (!cpu_has_feature(CPU_FTR_HVMODE))
-		return;
-
-	if (cpu_has_feature(CPU_FTR_ARCH_300))
-		pcpu &= ~0x3UL;
-
-	if (nested) {
-		lpid = nested->shadow_lpid;
-		need_tlb_flush = &nested->need_tlb_flush;
-	} else {
-		lpid = kvm->arch.lpid;
-		need_tlb_flush = &kvm->arch.need_tlb_flush;
-	}
-
-	mtspr(SPRN_LPID, lpid);
-	isync();
-	smp_mb();
-
-	if (cpumask_test_cpu(pcpu, need_tlb_flush)) {
-		radix__local_flush_tlb_lpid_guest(lpid);
-		/* Clear the bit after the TLB flush */
-		cpumask_clear_cpu(pcpu, need_tlb_flush);
-	}
-}
-
 static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc)
 {
 	int cpu;
@@ -3229,19 +3278,11 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	for (sub = 0; sub < core_info.n_subcores; ++sub)
 		spin_unlock(&core_info.vc[sub]->lock);
 
-	if (kvm_is_radix(vc->kvm)) {
-		/*
-		 * Do we need to flush the process scoped TLB for the LPAR?
-		 *
-		 * On POWER9, individual threads can come in here, but the
-		 * TLB is shared between the 4 threads in a core, hence
-		 * invalidating on one thread invalidates for all.
-		 * Thus we make all 4 threads use the same bit here.
-		 *
-		 * Hash must be flushed in realmode in order to use tlbiel.
-		 */
-		kvmppc_radix_check_need_tlb_flush(vc->kvm, pcpu, NULL);
-	}
+	guest_enter_irqoff();
+
+	srcu_idx = srcu_read_lock(&vc->kvm->srcu);
+
+	this_cpu_disable_ftrace();
 
 	/*
 	 * Interrupts will be enabled once we get into the guest,
@@ -3249,19 +3290,14 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	 */
 	trace_hardirqs_on();
 
-	guest_enter_irqoff();
-
-	srcu_idx = srcu_read_lock(&vc->kvm->srcu);
-
-	this_cpu_disable_ftrace();
-
 	trap = __kvmppc_vcore_entry();
 
+	trace_hardirqs_off();
+
 	this_cpu_enable_ftrace();
 
 	srcu_read_unlock(&vc->kvm->srcu, srcu_idx);
 
-	trace_hardirqs_off();
 	set_irq_happened(trap);
 
 	spin_lock(&vc->lock);
@@ -3514,6 +3550,7 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 #ifdef CONFIG_ALTIVEC
 	load_vr_state(&vcpu->arch.vr);
 #endif
+	mtspr(SPRN_VRSAVE, vcpu->arch.vrsave);
 
 	mtspr(SPRN_DSCR, vcpu->arch.dscr);
 	mtspr(SPRN_IAMR, vcpu->arch.iamr);
@@ -3605,6 +3642,7 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 #ifdef CONFIG_ALTIVEC
 	store_vr_state(&vcpu->arch.vr);
 #endif
+	vcpu->arch.vrsave = mfspr(SPRN_VRSAVE);
 
 	if (cpu_has_feature(CPU_FTR_TM) ||
 	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
@@ -3970,7 +4008,7 @@ int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
 			  unsigned long lpcr)
 {
 	int trap, r, pcpu;
-	int srcu_idx;
+	int srcu_idx, lpid;
 	struct kvmppc_vcore *vc;
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_nested_guest *nested = vcpu->arch.nested;
@@ -4046,8 +4084,12 @@ int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
 	vc->vcore_state = VCORE_RUNNING;
 	trace_kvmppc_run_core(vc, 0);
 
-	if (cpu_has_feature(CPU_FTR_HVMODE))
-		kvmppc_radix_check_need_tlb_flush(kvm, pcpu, nested);
+	if (cpu_has_feature(CPU_FTR_HVMODE)) {
+		lpid = nested ? nested->shadow_lpid : kvm->arch.lpid;
+		mtspr(SPRN_LPID, lpid);
+		isync();
+		kvmppc_check_need_tlb_flush(kvm, pcpu, nested);
+	}
 
 	trace_hardirqs_on();
 	guest_enter_irqoff();

arch/powerpc/kvm/book3s_hv_builtin.c

@@ -805,3 +805,60 @@ void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu)
 		vcpu->arch.doorbell_request = 0;
 	}
 }
+
+static void flush_guest_tlb(struct kvm *kvm)
+{
+	unsigned long rb, set;
+
+	rb = PPC_BIT(52);	/* IS = 2 */
+	if (kvm_is_radix(kvm)) {
+		/* R=1 PRS=1 RIC=2 */
+		asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+			     : : "r" (rb), "i" (1), "i" (1), "i" (2),
+			       "r" (0) : "memory");
+		for (set = 1; set < kvm->arch.tlb_sets; ++set) {
+			rb += PPC_BIT(51);	/* increment set number */
+			/* R=1 PRS=1 RIC=0 */
+			asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+				     : : "r" (rb), "i" (1), "i" (1), "i" (0),
+				       "r" (0) : "memory");
+		}
+	} else {
+		for (set = 0; set < kvm->arch.tlb_sets; ++set) {
+			/* R=0 PRS=0 RIC=0 */
+			asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+				     : : "r" (rb), "i" (0), "i" (0), "i" (0),
+				       "r" (0) : "memory");
+			rb += PPC_BIT(51);	/* increment set number */
+		}
+	}
+	asm volatile("ptesync": : :"memory");
+}
+
+void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu,
+				 struct kvm_nested_guest *nested)
+{
+	cpumask_t *need_tlb_flush;
+
+	/*
+	 * On POWER9, individual threads can come in here, but the
+	 * TLB is shared between the 4 threads in a core, hence
+	 * invalidating on one thread invalidates for all.
+	 * Thus we make all 4 threads use the same bit.
+	 */
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		pcpu = cpu_first_thread_sibling(pcpu);
+
+	if (nested)
+		need_tlb_flush = &nested->need_tlb_flush;
+	else
+		need_tlb_flush = &kvm->arch.need_tlb_flush;
+
+	if (cpumask_test_cpu(pcpu, need_tlb_flush)) {
+		flush_guest_tlb(kvm);
+
+		/* Clear the bit after the TLB flush */
+		cpumask_clear_cpu(pcpu, need_tlb_flush);
+	}
+}
+EXPORT_SYMBOL_GPL(kvmppc_check_need_tlb_flush);

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -13,6 +13,7 @@
 #include <linux/hugetlb.h>
 #include <linux/module.h>
 #include <linux/log2.h>
+#include <linux/sizes.h>
 
 #include <asm/trace.h>
 #include <asm/kvm_ppc.h>
@@ -867,6 +868,149 @@ long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
 	return ret;
 }
 
+static int kvmppc_get_hpa(struct kvm_vcpu *vcpu, unsigned long gpa,
+			  int writing, unsigned long *hpa,
+			  struct kvm_memory_slot **memslot_p)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_memory_slot *memslot;
+	unsigned long gfn, hva, pa, psize = PAGE_SHIFT;
+	unsigned int shift;
+	pte_t *ptep, pte;
+
+	/* Find the memslot for this address */
+	gfn = gpa >> PAGE_SHIFT;
+	memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
+	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
+		return H_PARAMETER;
+
+	/* Translate to host virtual address */
+	hva = __gfn_to_hva_memslot(memslot, gfn);
+
+	/* Try to find the host pte for that virtual address */
+	ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
+	if (!ptep)
+		return H_TOO_HARD;
+	pte = kvmppc_read_update_linux_pte(ptep, writing);
+	if (!pte_present(pte))
+		return H_TOO_HARD;
+
+	/* Convert to a physical address */
+	if (shift)
+		psize = 1UL << shift;
+	pa = pte_pfn(pte) << PAGE_SHIFT;
+	pa |= hva & (psize - 1);
+	pa |= gpa & ~PAGE_MASK;
+
+	if (hpa)
+		*hpa = pa;
+	if (memslot_p)
+		*memslot_p = memslot;
+
+	return H_SUCCESS;
+}
+
+static long kvmppc_do_h_page_init_zero(struct kvm_vcpu *vcpu,
+				       unsigned long dest)
+{
+	struct kvm_memory_slot *memslot;
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long pa, mmu_seq;
+	long ret = H_SUCCESS;
+	int i;
+
+	/* Used later to detect if we might have been invalidated */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
+
+	ret = kvmppc_get_hpa(vcpu, dest, 1, &pa, &memslot);
+	if (ret != H_SUCCESS)
+		return ret;
+
+	/* Check if we've been invalidated */
+	raw_spin_lock(&kvm->mmu_lock.rlock);
+	if (mmu_notifier_retry(kvm, mmu_seq)) {
+		ret = H_TOO_HARD;
+		goto out_unlock;
+	}
+
+	/* Zero the page */
+	for (i = 0; i < SZ_4K; i += L1_CACHE_BYTES, pa += L1_CACHE_BYTES)
+		dcbz((void *)pa);
+	kvmppc_update_dirty_map(memslot, dest >> PAGE_SHIFT, PAGE_SIZE);
+
+out_unlock:
+	raw_spin_unlock(&kvm->mmu_lock.rlock);
+	return ret;
+}
+
+static long kvmppc_do_h_page_init_copy(struct kvm_vcpu *vcpu,
+				       unsigned long dest, unsigned long src)
+{
+	unsigned long dest_pa, src_pa, mmu_seq;
+	struct kvm_memory_slot *dest_memslot;
+	struct kvm *kvm = vcpu->kvm;
+	long ret = H_SUCCESS;
+
+	/* Used later to detect if we might have been invalidated */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
+
+	ret = kvmppc_get_hpa(vcpu, dest, 1, &dest_pa, &dest_memslot);
+	if (ret != H_SUCCESS)
+		return ret;
+	ret = kvmppc_get_hpa(vcpu, src, 0, &src_pa, NULL);
+	if (ret != H_SUCCESS)
+		return ret;
+
+	/* Check if we've been invalidated */
+	raw_spin_lock(&kvm->mmu_lock.rlock);
+	if (mmu_notifier_retry(kvm, mmu_seq)) {
+		ret = H_TOO_HARD;
+		goto out_unlock;
+	}
+
+	/* Copy the page */
+	memcpy((void *)dest_pa, (void *)src_pa, SZ_4K);
+
+	kvmppc_update_dirty_map(dest_memslot, dest >> PAGE_SHIFT, PAGE_SIZE);
+
+out_unlock:
+	raw_spin_unlock(&kvm->mmu_lock.rlock);
+	return ret;
+}
+
+long kvmppc_rm_h_page_init(struct kvm_vcpu *vcpu, unsigned long flags,
+			   unsigned long dest, unsigned long src)
+{
+	struct kvm *kvm = vcpu->kvm;
+	u64 pg_mask = SZ_4K - 1;	/* 4K page size */
+	long ret = H_SUCCESS;
+
+	/* Don't handle radix mode here, go up to the virtual mode handler */
+	if (kvm_is_radix(kvm))
+		return H_TOO_HARD;
+
+	/* Check for invalid flags (H_PAGE_SET_LOANED covers all CMO flags) */
+	if (flags & ~(H_ICACHE_INVALIDATE | H_ICACHE_SYNCHRONIZE |
+		      H_ZERO_PAGE | H_COPY_PAGE | H_PAGE_SET_LOANED))
+		return H_PARAMETER;
+
+	/* dest (and src if copy_page flag set) must be page aligned */
+	if ((dest & pg_mask) || ((flags & H_COPY_PAGE) && (src & pg_mask)))
+		return H_PARAMETER;
+
+	/* zero and/or copy the page as determined by the flags */
+	if (flags & H_COPY_PAGE)
+		ret = kvmppc_do_h_page_init_copy(vcpu, dest, src);
+	else if (flags & H_ZERO_PAGE)
+		ret = kvmppc_do_h_page_init_zero(vcpu, dest);
+
+	/* We can ignore the other flags */
+
+	return ret;
+}
+
 void kvmppc_invalidate_hpte(struct kvm *kvm, __be64 *hptep,
 			unsigned long pte_index)
 {

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -589,11 +589,8 @@ kvmppc_hv_entry:
 1:
 #endif
 
-	/* Use cr7 as an indication of radix mode */
 	ld	r5, HSTATE_KVM_VCORE(r13)
 	ld	r9, VCORE_KVM(r5)	/* pointer to struct kvm */
-	lbz	r0, KVM_RADIX(r9)
-	cmpwi	cr7, r0, 0
 
 	/*
 	 * POWER7/POWER8 host -> guest partition switch code.
@@ -616,9 +613,6 @@ kvmppc_hv_entry:
 	cmpwi	r6,0
 	bne	10f
 
-	/* Radix has already switched LPID and flushed core TLB */
-	bne	cr7, 22f
-
 	lwz	r7,KVM_LPID(r9)
 BEGIN_FTR_SECTION
 	ld	r6,KVM_SDR1(r9)
@@ -630,41 +624,13 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	mtspr	SPRN_LPID,r7
 	isync
 
-	/* See if we need to flush the TLB. Hash has to be done in RM */
-	lhz	r6,PACAPACAINDEX(r13)	/* test_bit(cpu, need_tlb_flush) */
-BEGIN_FTR_SECTION
-	/*
-	 * On POWER9, individual threads can come in here, but the
-	 * TLB is shared between the 4 threads in a core, hence
-	 * invalidating on one thread invalidates for all.
-	 * Thus we make all 4 threads use the same bit here.
-	 */
-	clrrdi	r6,r6,2
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-	clrldi	r7,r6,64-6		/* extract bit number (6 bits) */
-	srdi	r6,r6,6			/* doubleword number */
-	sldi	r6,r6,3			/* address offset */
-	add	r6,r6,r9
-	addi	r6,r6,KVM_NEED_FLUSH	/* dword in kvm->arch.need_tlb_flush */
-	li	r8,1
-	sld	r8,r8,r7
-	ld	r7,0(r6)
-	and.	r7,r7,r8
-	beq	22f
-	/* Flush the TLB of any entries for this LPID */
-	lwz	r0,KVM_TLB_SETS(r9)
-	mtctr	r0
-	li	r7,0x800		/* IS field = 0b10 */
-	ptesync
-	li	r0,0			/* RS for P9 version of tlbiel */
-28:	tlbiel	r7			/* On P9, rs=0, RIC=0, PRS=0, R=0 */
-	addi	r7,r7,0x1000
-	bdnz	28b
-	ptesync
-23:	ldarx	r7,0,r6			/* clear the bit after TLB flushed */
-	andc	r7,r7,r8
-	stdcx.	r7,0,r6
-	bne	23b
+	/* See if we need to flush the TLB. */
+	mr	r3, r9			/* kvm pointer */
+	lhz	r4, PACAPACAINDEX(r13)	/* physical cpu number */
+	li	r5, 0			/* nested vcpu pointer */
+	bl	kvmppc_check_need_tlb_flush
+	nop
+	ld	r5, HSTATE_KVM_VCORE(r13)
 
 	/* Add timebase offset onto timebase */
 22:	ld	r8,VCORE_TB_OFFSET(r5)
@@ -980,17 +946,27 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 
 #ifdef CONFIG_KVM_XICS
 	/* We are entering the guest on that thread, push VCPU to XIVE */
-	ld	r10, HSTATE_XIVE_TIMA_PHYS(r13)
-	cmpldi	cr0, r10, 0
-	beq	no_xive
 	ld	r11, VCPU_XIVE_SAVED_STATE(r4)
 	li	r9, TM_QW1_OS
+	lwz	r8, VCPU_XIVE_CAM_WORD(r4)
+	li	r7, TM_QW1_OS + TM_WORD2
+	mfmsr	r0
+	andi.	r0, r0, MSR_DR		/* in real mode? */
+	beq	2f
+	ld	r10, HSTATE_XIVE_TIMA_VIRT(r13)
+	cmpldi	cr1, r10, 0
+	beq     cr1, no_xive
+	eieio
+	stdx	r11,r9,r10
+	stwx	r8,r7,r10
+	b	3f
+2:	ld	r10, HSTATE_XIVE_TIMA_PHYS(r13)
+	cmpldi	cr1, r10, 0
+	beq	cr1, no_xive
 	eieio
 	stdcix	r11,r9,r10
-	lwz	r11, VCPU_XIVE_CAM_WORD(r4)
-	li	r9, TM_QW1_OS + TM_WORD2
-	stwcix	r11,r9,r10
-	li	r9, 1
+	stwcix	r8,r7,r10
+3:	li	r9, 1
 	stb	r9, VCPU_XIVE_PUSHED(r4)
 	eieio
 
@@ -1009,12 +985,16 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	 * on, we mask it.
 	 */
 	lbz	r0, VCPU_XIVE_ESC_ON(r4)
-	cmpwi	r0,0
-	beq	1f
-	ld	r10, VCPU_XIVE_ESC_RADDR(r4)
+	cmpwi	cr1, r0,0
+	beq	cr1, 1f
 	li	r9, XIVE_ESB_SET_PQ_01
+	beq	4f			/* in real mode? */
+	ld	r10, VCPU_XIVE_ESC_VADDR(r4)
+	ldx	r0, r10, r9
+	b	5f
+4:	ld	r10, VCPU_XIVE_ESC_RADDR(r4)
 	ldcix	r0, r10, r9
-	sync
+5:	sync
 
 	/* We have a possible subtle race here: The escalation interrupt might
 	 * have fired and be on its way to the host queue while we mask it,
@@ -2292,7 +2272,7 @@ hcall_real_table:
 #endif
 	.long	0		/* 0x24 - H_SET_SPRG0 */
 	.long	DOTSYM(kvmppc_h_set_dabr) - hcall_real_table
-	.long	0		/* 0x2c */
+	.long	DOTSYM(kvmppc_rm_h_page_init) - hcall_real_table
 	.long	0		/* 0x30 */
 	.long	0		/* 0x34 */
 	.long	0		/* 0x38 */

arch/powerpc/sysdev/xive/native.c

@@ -521,6 +521,9 @@ u32 xive_native_default_eq_shift(void)
 }
 EXPORT_SYMBOL_GPL(xive_native_default_eq_shift);
 
+unsigned long xive_tima_os;
+EXPORT_SYMBOL_GPL(xive_tima_os);
+
 bool __init xive_native_init(void)
 {
 	struct device_node *np;
@@ -573,6 +576,14 @@ bool __init xive_native_init(void)
 	for_each_possible_cpu(cpu)
 		kvmppc_set_xive_tima(cpu, r.start, tima);
 
+	/* Resource 2 is OS window */
+	if (of_address_to_resource(np, 2, &r)) {
+		pr_err("Failed to get thread mgmnt area resource\n");
+		return false;
+	}
+
+	xive_tima_os = r.start;
+
 	/* Grab size of provisionning pages */
 	xive_parse_provisioning(np);
 

arch/s390/include/asm/cpacf.h

@@ -28,6 +28,7 @@
 #define CPACF_KMCTR		0xb92d		/* MSA4 */
 #define CPACF_PRNO		0xb93c		/* MSA5 */
 #define CPACF_KMA		0xb929		/* MSA8 */
+#define CPACF_KDSA		0xb93a		/* MSA9 */
 
 /*
  * En/decryption modifier bits

arch/s390/include/asm/kvm_host.h

@@ -278,6 +278,7 @@ struct kvm_s390_sie_block {
 #define ECD_HOSTREGMGMT	0x20000000
 #define ECD_MEF		0x08000000
 #define ECD_ETOKENF	0x02000000
+#define ECD_ECC		0x00200000
 	__u32	ecd;			/* 0x01c8 */
 	__u8	reserved1cc[18];	/* 0x01cc */
 	__u64	pp;			/* 0x01de */
@@ -312,6 +313,7 @@ struct kvm_vcpu_stat {
 	u64 halt_successful_poll;
 	u64 halt_attempted_poll;
 	u64 halt_poll_invalid;
+	u64 halt_no_poll_steal;
 	u64 halt_wakeup;
 	u64 instruction_lctl;
 	u64 instruction_lctlg;