Merge tag 'kvmarm-fixes-5.5-1' of...

Merge tag 'kvmarm-fixes-5.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into kvm-master

KVM/arm fixes for .5.5, take #1

- Fix uninitialised sysreg accessor
- Fix handling of demand-paged device mappings
- Stop spamming the console on IMPDEF sysregs
- Relax mappings of writable memslots
- Assorted cleanups

Documentation/admin-guide/kernel-parameters.txt

@@ -3110,9 +3110,9 @@
 			[X86,PV_OPS] Disable paravirtualized VMware scheduler
 			clock and use the default one.
 
-	no-steal-acc	[X86,KVM] Disable paravirtualized steal time accounting.
-			steal time is computed, but won't influence scheduler
-			behaviour
+	no-steal-acc	[X86,KVM,ARM64] Disable paravirtualized steal time
+			accounting. steal time is computed, but won't
+			influence scheduler behaviour
 
 	nolapic		[X86-32,APIC] Do not enable or use the local APIC.
 

Documentation/virt/kvm/api.txt

@@ -1002,12 +1002,18 @@ Specifying exception.has_esr on a system that does not support it will return
 -EINVAL. Setting anything other than the lower 24bits of exception.serror_esr
 will return -EINVAL.
 
+It is not possible to read back a pending external abort (injected via
+KVM_SET_VCPU_EVENTS or otherwise) because such an exception is always delivered
+directly to the virtual CPU).
+
+
 struct kvm_vcpu_events {
 	struct {
 		__u8 serror_pending;
 		__u8 serror_has_esr;
+		__u8 ext_dabt_pending;
 		/* Align it to 8 bytes */
-		__u8 pad[6];
+		__u8 pad[5];
 		__u64 serror_esr;
 	} exception;
 	__u32 reserved[12];
@@ -1051,9 +1057,23 @@ contain a valid state and shall be written into the VCPU.
 
 ARM/ARM64:
 
+User space may need to inject several types of events to the guest.
+
 Set the pending SError exception state for this VCPU. It is not possible to
 'cancel' an Serror that has been made pending.
 
+If the guest performed an access to I/O memory which could not be handled by
+userspace, for example because of missing instruction syndrome decode
+information or because there is no device mapped at the accessed IPA, then
+userspace can ask the kernel to inject an external abort using the address
+from the exiting fault on the VCPU. It is a programming error to set
+ext_dabt_pending after an exit which was not either KVM_EXIT_MMIO or
+KVM_EXIT_ARM_NISV. This feature is only available if the system supports
+KVM_CAP_ARM_INJECT_EXT_DABT. This is a helper which provides commonality in
+how userspace reports accesses for the above cases to guests, across different
+userspace implementations. Nevertheless, userspace can still emulate all Arm
+exceptions by manipulating individual registers using the KVM_SET_ONE_REG API.
+
 See KVM_GET_VCPU_EVENTS for the data structure.
 
 
@@ -4468,6 +4488,39 @@ Hyper-V SynIC state change. Notification is used to remap SynIC
 event/message pages and to enable/disable SynIC messages/events processing
 in userspace.
 
+		/* KVM_EXIT_ARM_NISV */
+		struct {
+			__u64 esr_iss;
+			__u64 fault_ipa;
+		} arm_nisv;
+
+Used on arm and arm64 systems. If a guest accesses memory not in a memslot,
+KVM will typically return to userspace and ask it to do MMIO emulation on its
+behalf. However, for certain classes of instructions, no instruction decode
+(direction, length of memory access) is provided, and fetching and decoding
+the instruction from the VM is overly complicated to live in the kernel.
+
+Historically, when this situation occurred, KVM would print a warning and kill
+the VM. KVM assumed that if the guest accessed non-memslot memory, it was
+trying to do I/O, which just couldn't be emulated, and the warning message was
+phrased accordingly. However, what happened more often was that a guest bug
+caused access outside the guest memory areas which should lead to a more
+meaningful warning message and an external abort in the guest, if the access
+did not fall within an I/O window.
+
+Userspace implementations can query for KVM_CAP_ARM_NISV_TO_USER, and enable
+this capability at VM creation. Once this is done, these types of errors will
+instead return to userspace with KVM_EXIT_ARM_NISV, with the valid bits from
+the HSR (arm) and ESR_EL2 (arm64) in the esr_iss field, and the faulting IPA
+in the fault_ipa field. Userspace can either fix up the access if it's
+actually an I/O access by decoding the instruction from guest memory (if it's
+very brave) and continue executing the guest, or it can decide to suspend,
+dump, or restart the guest.
+
+Note that KVM does not skip the faulting instruction as it does for
+KVM_EXIT_MMIO, but userspace has to emulate any change to the processing state
+if it decides to decode and emulate the instruction.
+
 		/* Fix the size of the union. */
 		char padding[256];
 	};

Documentation/virt/kvm/arm/pvtime.rst

+.. SPDX-License-Identifier: GPL-2.0
+
+Paravirtualized time support for arm64
+======================================
+
+Arm specification DEN0057/A defines a standard for paravirtualised time
+support for AArch64 guests:
+
+https://developer.arm.com/docs/den0057/a
+
+KVM/arm64 implements the stolen time part of this specification by providing
+some hypervisor service calls to support a paravirtualized guest obtaining a
+view of the amount of time stolen from its execution.
+
+Two new SMCCC compatible hypercalls are defined:
+
+* PV_TIME_FEATURES: 0xC5000020
+* PV_TIME_ST:       0xC5000021
+
+These are only available in the SMC64/HVC64 calling convention as
+paravirtualized time is not available to 32 bit Arm guests. The existence of
+the PV_FEATURES hypercall should be probed using the SMCCC 1.1 ARCH_FEATURES
+mechanism before calling it.
+
+PV_TIME_FEATURES
+    ============= ========    ==========
+    Function ID:  (uint32)    0xC5000020
+    PV_call_id:   (uint32)    The function to query for support.
+                              Currently only PV_TIME_ST is supported.
+    Return value: (int64)     NOT_SUPPORTED (-1) or SUCCESS (0) if the relevant
+                              PV-time feature is supported by the hypervisor.
+    ============= ========    ==========
+
+PV_TIME_ST
+    ============= ========    ==========
+    Function ID:  (uint32)    0xC5000021
+    Return value: (int64)     IPA of the stolen time data structure for this
+                              VCPU. On failure:
+                              NOT_SUPPORTED (-1)
+    ============= ========    ==========
+
+The IPA returned by PV_TIME_ST should be mapped by the guest as normal memory
+with inner and outer write back caching attributes, in the inner shareable
+domain. A total of 16 bytes from the IPA returned are guaranteed to be
+meaningfully filled by the hypervisor (see structure below).
+
+PV_TIME_ST returns the structure for the calling VCPU.
+
+Stolen Time
+-----------
+
+The structure pointed to by the PV_TIME_ST hypercall is as follows:
+
++-------------+-------------+-------------+----------------------------+
+| Field       | Byte Length | Byte Offset | Description                |
++=============+=============+=============+============================+
+| Revision    |      4      |      0      | Must be 0 for version 1.0  |
++-------------+-------------+-------------+----------------------------+
+| Attributes  |      4      |      4      | Must be 0                  |
++-------------+-------------+-------------+----------------------------+
+| Stolen time |      8      |      8      | Stolen time in unsigned    |
+|             |             |             | nanoseconds indicating how |
+|             |             |             | much time this VCPU thread |
+|             |             |             | was involuntarily not      |
+|             |             |             | running on a physical CPU. |
++-------------+-------------+-------------+----------------------------+
+
+All values in the structure are stored little-endian.
+
+The structure will be updated by the hypervisor prior to scheduling a VCPU. It
+will be present within a reserved region of the normal memory given to the
+guest. The guest should not attempt to write into this memory. There is a
+structure per VCPU of the guest.
+
+It is advisable that one or more 64k pages are set aside for the purpose of
+these structures and not used for other purposes, this enables the guest to map
+the region using 64k pages and avoids conflicting attributes with other memory.
+
+For the user space interface see Documentation/virt/kvm/devices/vcpu.txt
+section "3. GROUP: KVM_ARM_VCPU_PVTIME_CTRL".

Documentation/virt/kvm/devices/vcpu.txt

@@ -60,3 +60,17 @@ time to use the number provided for a given timer, overwriting any previously
 configured values on other VCPUs.  Userspace should configure the interrupt
 numbers on at least one VCPU after creating all VCPUs and before running any
 VCPUs.
+
+3. GROUP: KVM_ARM_VCPU_PVTIME_CTRL
+Architectures: ARM64
+
+3.1 ATTRIBUTE: KVM_ARM_VCPU_PVTIME_IPA
+Parameters: 64-bit base address
+Returns: -ENXIO:  Stolen time not implemented
+         -EEXIST: Base address already set for this VCPU
+         -EINVAL: Base address not 64 byte aligned
+
+Specifies the base address of the stolen time structure for this VCPU. The
+base address must be 64 byte aligned and exist within a valid guest memory
+region. See Documentation/virt/kvm/arm/pvtime.txt for more information
+including the layout of the stolen time structure.

arch/arm/include/asm/kvm_arm.h

@@ -162,6 +162,7 @@
 #define HSR_ISV		(_AC(1, UL) << HSR_ISV_SHIFT)
 #define HSR_SRT_SHIFT	(16)
 #define HSR_SRT_MASK	(0xf << HSR_SRT_SHIFT)
+#define HSR_CM		(1 << 8)
 #define HSR_FSC		(0x3f)
 #define HSR_FSC_TYPE	(0x3c)
 #define HSR_SSE		(1 << 21)

arch/arm/include/asm/kvm_emulate.h

@@ -95,12 +95,12 @@ static inline unsigned long *vcpu_hcr(const struct kvm_vcpu *vcpu)
 	return (unsigned long *)&vcpu->arch.hcr;
 }
 
-static inline void vcpu_clear_wfe_traps(struct kvm_vcpu *vcpu)
+static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr &= ~HCR_TWE;
 }
 
-static inline void vcpu_set_wfe_traps(struct kvm_vcpu *vcpu)
+static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr |= HCR_TWE;
 }
@@ -167,6 +167,11 @@ static inline bool kvm_vcpu_dabt_isvalid(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_hsr(vcpu) & HSR_ISV;
 }
 
+static inline unsigned long kvm_vcpu_dabt_iss_nisv_sanitized(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & (HSR_CM | HSR_WNR | HSR_FSC);
+}
+
 static inline bool kvm_vcpu_dabt_iswrite(struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_hsr(vcpu) & HSR_WNR;

arch/arm/include/asm/kvm_host.h

@@ -7,6 +7,7 @@
 #ifndef __ARM_KVM_HOST_H__
 #define __ARM_KVM_HOST_H__
 
+#include <linux/arm-smccc.h>
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/kvm_types.h>
@@ -38,6 +39,7 @@
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
 #define KVM_REQ_VCPU_RESET	KVM_ARCH_REQ(2)
+#define KVM_REQ_RECORD_STEAL	KVM_ARCH_REQ(3)
 
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
@@ -76,6 +78,14 @@ struct kvm_arch {
 
 	/* Mandated version of PSCI */
 	u32 psci_version;
+
+	/*
+	 * If we encounter a data abort without valid instruction syndrome
+	 * information, report this to user space.  User space can (and
+	 * should) opt in to this feature if KVM_CAP_ARM_NISV_TO_USER is
+	 * supported.
+	 */
+	bool return_nisv_io_abort_to_user;
 };
 
 #define KVM_NR_MEM_OBJS     40
@@ -323,6 +333,29 @@ static inline int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
+static inline long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu)
+{
+	return SMCCC_RET_NOT_SUPPORTED;
+}
+
+static inline gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
+{
+	return GPA_INVALID;
+}
+
+static inline void kvm_update_stolen_time(struct kvm_vcpu *vcpu)
+{
+}
+
+static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
+{
+}
+
+static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch)
+{
+	return false;
+}
+
 void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
 
 struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);

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

@@ -131,8 +131,9 @@ struct kvm_vcpu_events {
 	struct {
 		__u8 serror_pending;
 		__u8 serror_has_esr;
+		__u8 ext_dabt_pending;
 		/* Align it to 8 bytes */
-		__u8 pad[6];
+		__u8 pad[5];
 		__u64 serror_esr;
 	} exception;
 	__u32 reserved[12];

arch/arm/kvm/Makefile

@@ -24,7 +24,7 @@ obj-y += kvm-arm.o init.o interrupts.o
 obj-y += handle_exit.o guest.o emulate.o reset.o
 obj-y += coproc.o coproc_a15.o coproc_a7.o   vgic-v3-coproc.o
 obj-y += $(KVM)/arm/arm.o $(KVM)/arm/mmu.o $(KVM)/arm/mmio.o
-obj-y += $(KVM)/arm/psci.o $(KVM)/arm/perf.o
+obj-y += $(KVM)/arm/psci.o $(KVM)/arm/perf.o $(KVM)/arm/hypercalls.o
 obj-y += $(KVM)/arm/aarch32.o
 
 obj-y += $(KVM)/arm/vgic/vgic.o

arch/arm/kvm/guest.c

@@ -21,6 +21,10 @@
 #define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU }
 
 struct kvm_stats_debugfs_item debugfs_entries[] = {
+	VCPU_STAT(halt_successful_poll),
+	VCPU_STAT(halt_attempted_poll),
+	VCPU_STAT(halt_poll_invalid),
+	VCPU_STAT(halt_wakeup),
 	VCPU_STAT(hvc_exit_stat),
 	VCPU_STAT(wfe_exit_stat),
 	VCPU_STAT(wfi_exit_stat),
@@ -255,6 +259,12 @@ int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
 {
 	events->exception.serror_pending = !!(*vcpu_hcr(vcpu) & HCR_VA);
 
+	/*
+	 * We never return a pending ext_dabt here because we deliver it to
+	 * the virtual CPU directly when setting the event and it's no longer
+	 * 'pending' at this point.
+	 */
+
 	return 0;
 }
 
@@ -263,12 +273,16 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
 {
 	bool serror_pending = events->exception.serror_pending;
 	bool has_esr = events->exception.serror_has_esr;
+	bool ext_dabt_pending = events->exception.ext_dabt_pending;
 
 	if (serror_pending && has_esr)
 		return -EINVAL;
 	else if (serror_pending)
 		kvm_inject_vabt(vcpu);
 
+	if (ext_dabt_pending)
+		kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+
 	return 0;
 }
 

arch/arm/kvm/handle_exit.c

@@ -9,7 +9,7 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
 #include <asm/kvm_mmu.h>
-#include <kvm/arm_psci.h>
+#include <kvm/arm_hypercalls.h>
 #include <trace/events/kvm.h>
 
 #include "trace.h"

arch/arm/mm/proc-v7-bugs.c

 // SPDX-License-Identifier: GPL-2.0
 #include <linux/arm-smccc.h>
 #include <linux/kernel.h>
-#include <linux/psci.h>
 #include <linux/smp.h>
 
 #include <asm/cp15.h>
@@ -75,26 +74,20 @@ static void cpu_v7_spectre_init(void)
 	case ARM_CPU_PART_CORTEX_A72: {
 		struct arm_smccc_res res;
 
-		if (psci_ops.smccc_version == SMCCC_VERSION_1_0)
-			break;
-
-		switch (psci_ops.conduit) {
-		case PSCI_CONDUIT_HVC:
-			arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+		arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				     ARM_SMCCC_ARCH_WORKAROUND_1, &res);
 		if ((int)res.a0 != 0)
-				break;
+			return;
+
+		switch (arm_smccc_1_1_get_conduit()) {
+		case SMCCC_CONDUIT_HVC:
 			per_cpu(harden_branch_predictor_fn, cpu) =
 				call_hvc_arch_workaround_1;
 			cpu_do_switch_mm = cpu_v7_hvc_switch_mm;
 			spectre_v2_method = "hypervisor";
 			break;
 
-		case PSCI_CONDUIT_SMC:
-			arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
-					  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-			if ((int)res.a0 != 0)
-				break;
+		case SMCCC_CONDUIT_SMC:
 			per_cpu(harden_branch_predictor_fn, cpu) =
 				call_smc_arch_workaround_1;
 			cpu_do_switch_mm = cpu_v7_smc_switch_mm;

arch/arm64/include/asm/kvm_arm.h

@@ -61,7 +61,6 @@
  * RW:		64bit by default, can be overridden for 32bit VMs
  * TAC:		Trap ACTLR
  * TSC:		Trap SMC
- * TVM:		Trap VM ops (until M+C set in SCTLR_EL1)
  * TSW:		Trap cache operations by set/way
  * TWE:		Trap WFE
  * TWI:		Trap WFI
@@ -74,7 +73,7 @@
  * SWIO:	Turn set/way invalidates into set/way clean+invalidate
  */
 #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
-			 HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \
+			 HCR_BSU_IS | HCR_FB | HCR_TAC | \
 			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \
 			 HCR_FMO | HCR_IMO)
 #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)

arch/arm64/include/asm/kvm_emulate.h

@@ -53,8 +53,18 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 		/* trap error record accesses */
 		vcpu->arch.hcr_el2 |= HCR_TERR;
 	}
-	if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB))
+
+	if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) {
 		vcpu->arch.hcr_el2 |= HCR_FWB;
+	} else {
+		/*
+		 * For non-FWB CPUs, we trap VM ops (HCR_EL2.TVM) until M+C
+		 * get set in SCTLR_EL1 such that we can detect when the guest
+		 * MMU gets turned on and do the necessary cache maintenance
+		 * then.
+		 */
+		vcpu->arch.hcr_el2 |= HCR_TVM;
+	}
 
 	if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features))
 		vcpu->arch.hcr_el2 &= ~HCR_RW;
@@ -77,14 +87,19 @@ static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu)
 	return (unsigned long *)&vcpu->arch.hcr_el2;
 }
 
-static inline void vcpu_clear_wfe_traps(struct kvm_vcpu *vcpu)
+static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr_el2 &= ~HCR_TWE;
+	if (atomic_read(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count))
+		vcpu->arch.hcr_el2 &= ~HCR_TWI;
+	else
+		vcpu->arch.hcr_el2 |= HCR_TWI;
 }
 
-static inline void vcpu_set_wfe_traps(struct kvm_vcpu *vcpu)
+static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr_el2 |= HCR_TWE;
+	vcpu->arch.hcr_el2 |= HCR_TWI;
 }
 
 static inline void vcpu_ptrauth_enable(struct kvm_vcpu *vcpu)
@@ -258,6 +273,11 @@ static inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu)
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV);
 }
 
+static inline unsigned long kvm_vcpu_dabt_iss_nisv_sanitized(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & (ESR_ELx_CM | ESR_ELx_WNR | ESR_ELx_FSC);
+}
+
 static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu)
 {
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SSE);

arch/arm64/include/asm/kvm_host.h

@@ -44,6 +44,7 @@
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
 #define KVM_REQ_VCPU_RESET	KVM_ARCH_REQ(2)
+#define KVM_REQ_RECORD_STEAL	KVM_ARCH_REQ(3)
 
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
@@ -83,6 +84,14 @@ struct kvm_arch {
 
 	/* Mandated version of PSCI */
 	u32 psci_version;
+
+	/*
+	 * If we encounter a data abort without valid instruction syndrome
+	 * information, report this to user space.  User space can (and
+	 * should) opt in to this feature if KVM_CAP_ARM_NISV_TO_USER is
+	 * supported.
+	 */
+	bool return_nisv_io_abort_to_user;
 };
 
 #define KVM_NR_MEM_OBJS     40
@@ -338,6 +347,13 @@ struct kvm_vcpu_arch {
 	/* True when deferrable sysregs are loaded on the physical CPU,
 	 * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */
 	bool sysregs_loaded_on_cpu;
+
+	/* Guest PV state */
+	struct {
+		u64 steal;
+		u64 last_steal;
+		gpa_t base;
+	} steal;
 };
 
 /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
@@ -478,6 +494,27 @@ void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
+long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu);
+gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu);
+void kvm_update_stolen_time(struct kvm_vcpu *vcpu);
+
+int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr);
+int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr);
+int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr);
+
+static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
+{
+	vcpu_arch->steal.base = GPA_INVALID;
+}
+
+static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch)
+{
+	return (vcpu_arch->steal.base != GPA_INVALID);
+}
+
 void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome);
 
 struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);

arch/arm64/include/asm/paravirt.h

@@ -21,6 +21,13 @@ static inline u64 paravirt_steal_clock(int cpu)
 {
 	return pv_ops.time.steal_clock(cpu);
 }
-#endif
+
+int __init pv_time_init(void);
+
+#else
+
+#define pv_time_init() do {} while (0)
+
+#endif // CONFIG_PARAVIRT
 
 #endif

arch/arm64/include/asm/pvclock-abi.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2019 Arm Ltd. */
+
+#ifndef __ASM_PVCLOCK_ABI_H
+#define __ASM_PVCLOCK_ABI_H
+
+/* The below structure is defined in ARM DEN0057A */
+
+struct pvclock_vcpu_stolen_time {
+	__le32 revision;
+	__le32 attributes;
+	__le64 stolen_time;
+	/* Structure must be 64 byte aligned, pad to that size */
+	u8 padding[48];
+} __packed;
+
+#endif

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

@@ -164,8 +164,9 @@ struct kvm_vcpu_events {
 	struct {
 		__u8 serror_pending;
 		__u8 serror_has_esr;
+		__u8 ext_dabt_pending;
 		/* Align it to 8 bytes */
-		__u8 pad[6];
+		__u8 pad[5];
 		__u64 serror_esr;
 	} exception;
 	__u32 reserved[12];
@@ -323,6 +324,8 @@ struct kvm_vcpu_events {
 #define KVM_ARM_VCPU_TIMER_CTRL		1
 #define   KVM_ARM_VCPU_TIMER_IRQ_VTIMER		0
 #define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER		1
+#define KVM_ARM_VCPU_PVTIME_CTRL	2
+#define   KVM_ARM_VCPU_PVTIME_IPA	0
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_VCPU2_SHIFT		28

arch/arm64/kernel/cpu_errata.c

@@ -6,7 +6,6 @@
  */
 
 #include <linux/arm-smccc.h>
-#include <linux/psci.h>
 #include <linux/types.h>
 #include <linux/cpu.h>
 #include <asm/cpu.h>
@@ -167,9 +166,7 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn,
 }
 #endif	/* CONFIG_KVM_INDIRECT_VECTORS */
 
-#include <uapi/linux/psci.h>
 #include <linux/arm-smccc.h>
-#include <linux/psci.h>
 
 static void call_smc_arch_workaround_1(void)
 {
@@ -213,44 +210,32 @@ static int detect_harden_bp_fw(void)
 	struct arm_smccc_res res;
 	u32 midr = read_cpuid_id();
 
-	if (psci_ops.smccc_version == SMCCC_VERSION_1_0)
-		return -1;
-
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
-		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 			     ARM_SMCCC_ARCH_WORKAROUND_1, &res);
+
 	switch ((int)res.a0) {
 	case 1:
 		/* Firmware says we're just fine */
 		return 0;
 	case 0:
-			cb = call_hvc_arch_workaround_1;
-			/* This is a guest, no need to patch KVM vectors */
-			smccc_start = NULL;
-			smccc_end = NULL;
 		break;
 	default:
 		return -1;
 	}
+
+	switch (arm_smccc_1_1_get_conduit()) {
+	case SMCCC_CONDUIT_HVC:
+		cb = call_hvc_arch_workaround_1;
+		/* This is a guest, no need to patch KVM vectors */
+		smccc_start = NULL;
+		smccc_end = NULL;
 		break;
 
-	case PSCI_CONDUIT_SMC:
-		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
-				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-		switch ((int)res.a0) {
-		case 1:
-			/* Firmware says we're just fine */
-			return 0;
-		case 0:
+	case SMCCC_CONDUIT_SMC:
 		cb = call_smc_arch_workaround_1;
 		smccc_start = __smccc_workaround_1_smc_start;
 		smccc_end = __smccc_workaround_1_smc_end;
 		break;
-		default:
-			return -1;
-		}
-		break;
 
 	default:
 		return -1;
@@ -309,11 +294,11 @@ void __init arm64_update_smccc_conduit(struct alt_instr *alt,
 
 	BUG_ON(nr_inst != 1);
 
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
+	switch (arm_smccc_1_1_get_conduit()) {
+	case SMCCC_CONDUIT_HVC:
 		insn = aarch64_insn_get_hvc_value();
 		break;
-	case PSCI_CONDUIT_SMC:
+	case SMCCC_CONDUIT_SMC:
 		insn = aarch64_insn_get_smc_value();
 		break;
 	default:
@@ -339,6 +324,8 @@ void __init arm64_enable_wa2_handling(struct alt_instr *alt,
 
 void arm64_set_ssbd_mitigation(bool state)
 {
+	int conduit;
+
 	if (!IS_ENABLED(CONFIG_ARM64_SSBD)) {
 		pr_info_once("SSBD disabled by kernel configuration\n");
 		return;
@@ -352,19 +339,10 @@ void arm64_set_ssbd_mitigation(bool state)
 		return;
 	}
 
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
-		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL);
-		break;
-
-	case PSCI_CONDUIT_SMC:
-		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL);
-		break;
+	conduit = arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_WORKAROUND_2, state,
+				       NULL);
 
-	default:
-		WARN_ON_ONCE(1);
-		break;
-	}
+	WARN_ON_ONCE(conduit == SMCCC_CONDUIT_NONE);
 }
 
 static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
@@ -374,6 +352,7 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 	bool required = true;
 	s32 val;
 	bool this_cpu_safe = false;
+	int conduit;
 
 	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
 
@@ -391,25 +370,10 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 		goto out_printmsg;
 	}
 
-	if (psci_ops.smccc_version == SMCCC_VERSION_1_0) {
-		ssbd_state = ARM64_SSBD_UNKNOWN;
-		if (!this_cpu_safe)
-			__ssb_safe = false;
-		return false;
-	}
-
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
-		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+	conduit = arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				       ARM_SMCCC_ARCH_WORKAROUND_2, &res);
-		break;
 
-	case PSCI_CONDUIT_SMC:
-		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
-				  ARM_SMCCC_ARCH_WORKAROUND_2, &res);
-		break;
-
-	default:
+	if (conduit == SMCCC_CONDUIT_NONE) {
 		ssbd_state = ARM64_SSBD_UNKNOWN;
 		if (!this_cpu_safe)
 			__ssb_safe = false;

arch/arm64/kernel/paravirt.c

@@ -6,13 +6,153 @@
  * Author: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
  */
 
+#define pr_fmt(fmt) "arm-pv: " fmt
+
+#include <linux/arm-smccc.h>
+#include <linux/cpuhotplug.h>
 #include <linux/export.h>
+#include <linux/io.h>
 #include <linux/jump_label.h>
+#include <linux/printk.h>
+#include <linux/psci.h>
+#include <linux/reboot.h>
+#include <linux/slab.h>
 #include <linux/types.h>
+
 #include <asm/paravirt.h>
+#include <asm/pvclock-abi.h>
+#include <asm/smp_plat.h>
 
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
 struct paravirt_patch_template pv_ops;
 EXPORT_SYMBOL_GPL(pv_ops);
+
+struct pv_time_stolen_time_region {
+	struct pvclock_vcpu_stolen_time *kaddr;
+};
+
+static DEFINE_PER_CPU(struct pv_time_stolen_time_region, stolen_time_region);
+
+static bool steal_acc = true;
+static int __init parse_no_stealacc(char *arg)
+{
+	steal_acc = false;
+	return 0;
+}
+
+early_param("no-steal-acc", parse_no_stealacc);
+
+/* return stolen time in ns by asking the hypervisor */
+static u64 pv_steal_clock(int cpu)
+{
+	struct pv_time_stolen_time_region *reg;
+
+	reg = per_cpu_ptr(&stolen_time_region, cpu);
+	if (!reg->kaddr) {
+		pr_warn_once("stolen time enabled but not configured for cpu %d\n",
+			     cpu);
+		return 0;
+	}
+
+	return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time));
+}
+
+static int stolen_time_dying_cpu(unsigned int cpu)
+{
+	struct pv_time_stolen_time_region *reg;
+
+	reg = this_cpu_ptr(&stolen_time_region);
+	if (!reg->kaddr)
+		return 0;
+
+	memunmap(reg->kaddr);
+	memset(reg, 0, sizeof(*reg));
+
+	return 0;
+}
+
+static int init_stolen_time_cpu(unsigned int cpu)
+{
+	struct pv_time_stolen_time_region *reg;
+	struct arm_smccc_res res;
+
+	reg = this_cpu_ptr(&stolen_time_region);
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_HV_PV_TIME_ST, &res);
+
+	if (res.a0 == SMCCC_RET_NOT_SUPPORTED)
+		return -EINVAL;
+
+	reg->kaddr = memremap(res.a0,
+			      sizeof(struct pvclock_vcpu_stolen_time),
+			      MEMREMAP_WB);
+
+	if (!reg->kaddr) {
+		pr_warn("Failed to map stolen time data structure\n");
+		return -ENOMEM;
+	}
+
+	if (le32_to_cpu(reg->kaddr->revision) != 0 ||
+	    le32_to_cpu(reg->kaddr->attributes) != 0) {
+		pr_warn_once("Unexpected revision or attributes in stolen time data\n");
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+static int pv_time_init_stolen_time(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state(CPUHP_AP_ARM_KVMPV_STARTING,
+				"hypervisor/arm/pvtime:starting",
+				init_stolen_time_cpu, stolen_time_dying_cpu);
+	if (ret < 0)
+		return ret;
+	return 0;
+}
+
+static bool has_pv_steal_clock(void)
+{
+	struct arm_smccc_res res;
+
+	/* To detect the presence of PV time support we require SMCCC 1.1+ */
+	if (psci_ops.smccc_version < SMCCC_VERSION_1_1)
+		return false;
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+			     ARM_SMCCC_HV_PV_TIME_FEATURES, &res);
+
+	if (res.a0 != SMCCC_RET_SUCCESS)
+		return false;
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_HV_PV_TIME_FEATURES,
+			     ARM_SMCCC_HV_PV_TIME_ST, &res);
+
+	return (res.a0 == SMCCC_RET_SUCCESS);
+}
+
+int __init pv_time_init(void)
+{
+	int ret;
+
+	if (!has_pv_steal_clock())
+		return 0;
+
+	ret = pv_time_init_stolen_time();
+	if (ret)
+		return ret;
+
+	pv_ops.time.steal_clock = pv_steal_clock;
+
+	static_key_slow_inc(&paravirt_steal_enabled);
+	if (steal_acc)
+		static_key_slow_inc(&paravirt_steal_rq_enabled);
+
+	pr_info("using stolen time PV\n");
+
+	return 0;
+}

arch/arm64/kernel/sdei.c

@@ -2,6 +2,7 @@
 // Copyright (C) 2017 Arm Ltd.
 #define pr_fmt(fmt) "sdei: " fmt
 
+#include <linux/arm-smccc.h>
 #include <linux/arm_sdei.h>
 #include <linux/hardirq.h>
 #include <linux/irqflags.h>
@@ -161,7 +162,7 @@ unsigned long sdei_arch_get_entry_point(int conduit)
 			return 0;
 	}
 
-	sdei_exit_mode = (conduit == CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC;
+	sdei_exit_mode = (conduit == SMCCC_CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC;
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	if (arm64_kernel_unmapped_at_el0()) {

arch/arm64/kernel/time.c

@@ -30,6 +30,7 @@
 
 #include <asm/thread_info.h>
 #include <asm/stacktrace.h>
+#include <asm/paravirt.h>
 
 unsigned long profile_pc(struct pt_regs *regs)
 {
@@ -65,4 +66,6 @@ void __init time_init(void)
 
 	/* Calibrate the delay loop directly */
 	lpj_fine = arch_timer_rate / HZ;
+
+	pv_time_init();
 }

arch/arm64/kvm/Kconfig

@@ -21,6 +21,8 @@ if VIRTUALIZATION
 config KVM
 	bool "Kernel-based Virtual Machine (KVM) support"
 	depends on OF
+	# for TASKSTATS/TASK_DELAY_ACCT:
+	depends on NET && MULTIUSER
 	select MMU_NOTIFIER
 	select PREEMPT_NOTIFIERS
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
@@ -39,6 +41,8 @@ config KVM
 	select IRQ_BYPASS_MANAGER
 	select HAVE_KVM_IRQ_BYPASS
 	select HAVE_KVM_VCPU_RUN_PID_CHANGE
+	select TASKSTATS
+	select TASK_DELAY_ACCT
 	---help---
 	  Support hosting virtualized guest machines.
 	  We don't support KVM with 16K page tables yet, due to the multiple

arch/arm64/kvm/Makefile

@@ -13,6 +13,8 @@ obj-$(CONFIG_KVM_ARM_HOST) += hyp/
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arm.o $(KVM)/arm/mmu.o $(KVM)/arm/mmio.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/psci.o $(KVM)/arm/perf.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hypercalls.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/pvtime.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

arch/arm64/kvm/guest.c

@@ -34,6 +34,10 @@
 #define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU }
 
 struct kvm_stats_debugfs_item debugfs_entries[] = {
+	VCPU_STAT(halt_successful_poll),
+	VCPU_STAT(halt_attempted_poll),
+	VCPU_STAT(halt_poll_invalid),
+	VCPU_STAT(halt_wakeup),
 	VCPU_STAT(hvc_exit_stat),
 	VCPU_STAT(wfe_exit_stat),
 	VCPU_STAT(wfi_exit_stat),
@@ -712,6 +716,12 @@ int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
 	if (events->exception.serror_pending && events->exception.serror_has_esr)
 		events->exception.serror_esr = vcpu_get_vsesr(vcpu);
 
+	/*
+	 * We never return a pending ext_dabt here because we deliver it to
+	 * the virtual CPU directly when setting the event and it's no longer
+	 * 'pending' at this point.
+	 */
+
 	return 0;
 }
 
@@ -720,6 +730,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
 {
 	bool serror_pending = events->exception.serror_pending;
 	bool has_esr = events->exception.serror_has_esr;
+	bool ext_dabt_pending = events->exception.ext_dabt_pending;
 
 	if (serror_pending && has_esr) {
 		if (!cpus_have_const_cap(ARM64_HAS_RAS_EXTN))
@@ -733,6 +744,9 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
 		kvm_inject_vabt(vcpu);
 	}
 
+	if (ext_dabt_pending)
+		kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+
 	return 0;
 }
 
@@ -858,6 +872,9 @@ int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
 	case KVM_ARM_VCPU_TIMER_CTRL:
 		ret = kvm_arm_timer_set_attr(vcpu, attr);
 		break;
+	case KVM_ARM_VCPU_PVTIME_CTRL:
+		ret = kvm_arm_pvtime_set_attr(vcpu, attr);
+		break;
 	default:
 		ret = -ENXIO;
 		break;
@@ -878,6 +895,9 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
 	case KVM_ARM_VCPU_TIMER_CTRL:
 		ret = kvm_arm_timer_get_attr(vcpu, attr);
 		break;
+	case KVM_ARM_VCPU_PVTIME_CTRL:
+		ret = kvm_arm_pvtime_get_attr(vcpu, attr);
+		break;
 	default:
 		ret = -ENXIO;
 		break;
@@ -898,6 +918,9 @@ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
 	case KVM_ARM_VCPU_TIMER_CTRL:
 		ret = kvm_arm_timer_has_attr(vcpu, attr);
 		break;
+	case KVM_ARM_VCPU_PVTIME_CTRL:
+		ret = kvm_arm_pvtime_has_attr(vcpu, attr);
+		break;
 	default:
 		ret = -ENXIO;
 		break;

arch/arm64/kvm/handle_exit.c

@@ -11,8 +11,6 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 
-#include <kvm/arm_psci.h>
-
 #include <asm/esr.h>
 #include <asm/exception.h>
 #include <asm/kvm_asm.h>
@@ -22,6 +20,8 @@
 #include <asm/debug-monitors.h>
 #include <asm/traps.h>
 
+#include <kvm/arm_hypercalls.h>
+
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 

arch/arm64/kvm/inject_fault.c

@@ -109,7 +109,7 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 
 /**
  * kvm_inject_dabt - inject a data abort into the guest
- * @vcpu: The VCPU to receive the undefined exception
+ * @vcpu: The VCPU to receive the data abort
  * @addr: The address to report in the DFAR
  *
  * It is assumed that this code is called from the VCPU thread and that the
@@ -125,7 +125,7 @@ void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr)
 
 /**
  * kvm_inject_pabt - inject a prefetch abort into the guest
- * @vcpu: The VCPU to receive the undefined exception
+ * @vcpu: The VCPU to receive the prefetch abort
  * @addr: The address to report in the DFAR
  *
  * It is assumed that this code is called from the VCPU thread and that the

arch/arm64/kvm/sys_regs.c

@@ -2098,9 +2098,9 @@ static void unhandled_cp_access(struct kvm_vcpu *vcpu,
 		WARN_ON(1);
 	}
 
-	kvm_err("Unsupported guest CP%d access at: %08lx [%08lx]\n",
+	print_sys_reg_msg(params,
+			  "Unsupported guest CP%d access at: %08lx [%08lx]\n",
 			  cp, *vcpu_pc(vcpu), *vcpu_cpsr(vcpu));
-	print_sys_reg_instr(params);
 	kvm_inject_undefined(vcpu);
 }
 
@@ -2233,6 +2233,12 @@ int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
 				NULL, 0);
 }
 
+static bool is_imp_def_sys_reg(struct sys_reg_params *params)
+{
+	// See ARM DDI 0487E.a, section D12.3.2
+	return params->Op0 == 3 && (params->CRn & 0b1011) == 0b1011;
+}
+
 static int emulate_sys_reg(struct kvm_vcpu *vcpu,
 			   struct sys_reg_params *params)
 {
@@ -2248,10 +2254,12 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu,
 
 	if (likely(r)) {
 		perform_access(vcpu, params, r);
+	} else if (is_imp_def_sys_reg(params)) {
+		kvm_inject_undefined(vcpu);
 	} else {
-		kvm_err("Unsupported guest sys_reg access at: %lx [%08lx]\n",
+		print_sys_reg_msg(params,
+				  "Unsupported guest sys_reg access at: %lx [%08lx]\n",
 				  *vcpu_pc(vcpu), *vcpu_cpsr(vcpu));
-		print_sys_reg_instr(params);
 		kvm_inject_undefined(vcpu);
 	}
 	return 1;
@@ -2360,8 +2368,11 @@ static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu,
 	if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM64_SYSREG)
 		return NULL;
 
+	if (!index_to_params(id, &params))
+		return NULL;
+
 	table = get_target_table(vcpu->arch.target, true, &num);
-	r = find_reg_by_id(id, &params, table, num);
+	r = find_reg(&params, table, num);
 	if (!r)
 		r = find_reg(&params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
 

arch/arm64/kvm/sys_regs.h

@@ -62,11 +62,24 @@ struct sys_reg_desc {
 #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)
+static __printf(2, 3)
+inline void print_sys_reg_msg(const struct sys_reg_params *p,
+				       char *fmt, ...)
 {
+	va_list va;
+
+	va_start(va, fmt);
 	/* Look, we even formatted it for you to paste into the table! */
-	kvm_pr_unimpl(" { Op0(%2u), Op1(%2u), CRn(%2u), CRm(%2u), Op2(%2u), func_%s },\n",
+	kvm_pr_unimpl("%pV { Op0(%2u), Op1(%2u), CRn(%2u), CRm(%2u), Op2(%2u), func_%s },\n",
+		      &(struct va_format){ fmt, &va },
 		      p->Op0, p->Op1, p->CRn, p->CRm, p->Op2, p->is_write ? "write" : "read");
+	va_end(va);
+}
+
+static inline void print_sys_reg_instr(const struct sys_reg_params *p)
+{
+	/* GCC warns on an empty format string */
+	print_sys_reg_msg(p, "%s", "");
 }
 
 static inline bool ignore_write(struct kvm_vcpu *vcpu,

drivers/firmware/arm_sdei.c

@@ -967,29 +967,29 @@ static int sdei_get_conduit(struct platform_device *pdev)
 	if (np) {
 		if (of_property_read_string(np, "method", &method)) {
 			pr_warn("missing \"method\" property\n");
-			return CONDUIT_INVALID;
+			return SMCCC_CONDUIT_NONE;
 		}
 
 		if (!strcmp("hvc", method)) {
 			sdei_firmware_call = &sdei_smccc_hvc;
-			return CONDUIT_HVC;
+			return SMCCC_CONDUIT_HVC;
 		} else if (!strcmp("smc", method)) {
 			sdei_firmware_call = &sdei_smccc_smc;
-			return CONDUIT_SMC;
+			return SMCCC_CONDUIT_SMC;
 		}
 
 		pr_warn("invalid \"method\" property: %s\n", method);
 	} else if (IS_ENABLED(CONFIG_ACPI) && !acpi_disabled) {
 		if (acpi_psci_use_hvc()) {
 			sdei_firmware_call = &sdei_smccc_hvc;
-			return CONDUIT_HVC;
+			return SMCCC_CONDUIT_HVC;
 		} else {
 			sdei_firmware_call = &sdei_smccc_smc;
-			return CONDUIT_SMC;
+			return SMCCC_CONDUIT_SMC;
 		}
 	}
 
-	return CONDUIT_INVALID;
+	return SMCCC_CONDUIT_NONE;
 }
 
 static int sdei_probe(struct platform_device *pdev)

drivers/firmware/psci/psci.c

@@ -53,10 +53,18 @@ bool psci_tos_resident_on(int cpu)
 }
 
 struct psci_operations psci_ops = {
-	.conduit = PSCI_CONDUIT_NONE,
+	.conduit = SMCCC_CONDUIT_NONE,
 	.smccc_version = SMCCC_VERSION_1_0,
 };
 
+enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void)
+{
+	if (psci_ops.smccc_version < SMCCC_VERSION_1_1)
+		return SMCCC_CONDUIT_NONE;
+
+	return psci_ops.conduit;
+}
+
 typedef unsigned long (psci_fn)(unsigned long, unsigned long,
 				unsigned long, unsigned long);
 static psci_fn *invoke_psci_fn;
@@ -212,13 +220,13 @@ static unsigned long psci_migrate_info_up_cpu(void)
 			      0, 0, 0);
 }
 
-static void set_conduit(enum psci_conduit conduit)
+static void set_conduit(enum arm_smccc_conduit conduit)
 {
 	switch (conduit) {
-	case PSCI_CONDUIT_HVC:
+	case SMCCC_CONDUIT_HVC:
 		invoke_psci_fn = __invoke_psci_fn_hvc;
 		break;
-	case PSCI_CONDUIT_SMC:
+	case SMCCC_CONDUIT_SMC:
 		invoke_psci_fn = __invoke_psci_fn_smc;
 		break;
 	default:
@@ -240,9 +248,9 @@ static int get_set_conduit_method(struct device_node *np)
 	}
 
 	if (!strcmp("hvc", method)) {
-		set_conduit(PSCI_CONDUIT_HVC);
+		set_conduit(SMCCC_CONDUIT_HVC);
 	} else if (!strcmp("smc", method)) {
-		set_conduit(PSCI_CONDUIT_SMC);
+		set_conduit(SMCCC_CONDUIT_SMC);
 	} else {
 		pr_warn("invalid \"method\" property: %s\n", method);
 		return -EINVAL;
@@ -583,9 +591,9 @@ int __init psci_acpi_init(void)
 	pr_info("probing for conduit method from ACPI.\n");
 
 	if (acpi_psci_use_hvc())
-		set_conduit(PSCI_CONDUIT_HVC);
+		set_conduit(SMCCC_CONDUIT_HVC);
 	else
-		set_conduit(PSCI_CONDUIT_SMC);
+		set_conduit(SMCCC_CONDUIT_SMC);
 
 	return psci_probe();
 }

drivers/irqchip/irq-gic-v4.c

@@ -141,12 +141,17 @@ static int its_send_vpe_cmd(struct its_vpe *vpe, struct its_cmd_info *info)
 int its_schedule_vpe(struct its_vpe *vpe, bool on)
 {
 	struct its_cmd_info info;
+	int ret;
 
 	WARN_ON(preemptible());
 
 	info.cmd_type = on ? SCHEDULE_VPE : DESCHEDULE_VPE;
 
-	return its_send_vpe_cmd(vpe, &info);
+	ret = its_send_vpe_cmd(vpe, &info);
+	if (!ret)
+		vpe->resident = on;
+
+	return ret;
 }
 
 int its_invall_vpe(struct its_vpe *vpe)

include/Kbuild

@@ -67,6 +67,8 @@ header-test-			+= keys/big_key-type.h
 header-test-			+= keys/request_key_auth-type.h
 header-test-			+= keys/trusted.h
 header-test-			+= kvm/arm_arch_timer.h
+header-test-$(CONFIG_ARM)	+= kvm/arm_hypercalls.h
+header-test-$(CONFIG_ARM64)	+= kvm/arm_hypercalls.h
 header-test-			+= kvm/arm_pmu.h
 header-test-$(CONFIG_ARM)	+= kvm/arm_psci.h
 header-test-$(CONFIG_ARM64)	+= kvm/arm_psci.h

include/kvm/arm_hypercalls.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2019 Arm Ltd. */
+
+#ifndef __KVM_ARM_HYPERCALLS_H
+#define __KVM_ARM_HYPERCALLS_H
+
+#include <asm/kvm_emulate.h>
+
+int kvm_hvc_call_handler(struct kvm_vcpu *vcpu);
+
+static inline u32 smccc_get_function(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_reg(vcpu, 0);
+}
+
+static inline unsigned long smccc_get_arg1(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_reg(vcpu, 1);
+}
+
+static inline unsigned long smccc_get_arg2(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_reg(vcpu, 2);
+}
+
+static inline unsigned long smccc_get_arg3(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_reg(vcpu, 3);
+}
+
+static inline void smccc_set_retval(struct kvm_vcpu *vcpu,
+				    unsigned long a0,
+				    unsigned long a1,
+				    unsigned long a2,
+				    unsigned long a3)
+{
+	vcpu_set_reg(vcpu, 0, a0);
+	vcpu_set_reg(vcpu, 1, a1);
+	vcpu_set_reg(vcpu, 2, a2);
+	vcpu_set_reg(vcpu, 3, a3);
+}
+
+#endif

include/kvm/arm_psci.h

@@ -40,7 +40,7 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu, struct kvm *kvm)
 }
 
 
-int kvm_hvc_call_handler(struct kvm_vcpu *vcpu);
+int kvm_psci_call(struct kvm_vcpu *vcpu);
 
 struct kvm_one_reg;
 

include/kvm/arm_vgic.h

@@ -240,7 +240,7 @@ struct vgic_dist {
 	 * Contains the attributes and gpa of the LPI configuration table.
 	 * Since we report GICR_TYPER.CommonLPIAff as 0b00, we can share
 	 * one address across all redistributors.
-	 * GICv3 spec: 6.1.2 "LPI Configuration tables"
+	 * GICv3 spec: IHI 0069E 6.1.1 "LPI Configuration tables"
 	 */
 	u64			propbaser;
 
@@ -378,8 +378,6 @@ static inline int kvm_vgic_get_max_vcpus(void)
 	return kvm_vgic_global_state.max_gic_vcpus;
 }
 
-int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
-
 /**
  * kvm_vgic_setup_default_irq_routing:
  * Setup a default flat gsi routing table mapping all SPIs
@@ -396,7 +394,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int irq,
 int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int irq,
 				 struct kvm_kernel_irq_routing_entry *irq_entry);
 
-void kvm_vgic_v4_enable_doorbell(struct kvm_vcpu *vcpu);
-void kvm_vgic_v4_disable_doorbell(struct kvm_vcpu *vcpu);
+int vgic_v4_load(struct kvm_vcpu *vcpu);
+int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db);
 
 #endif /* __KVM_ARM_VGIC_H */

include/linux/arm-smccc.h

@@ -45,6 +45,7 @@
 #define ARM_SMCCC_OWNER_SIP		2
 #define ARM_SMCCC_OWNER_OEM		3
 #define ARM_SMCCC_OWNER_STANDARD	4
+#define ARM_SMCCC_OWNER_STANDARD_HYP	5
 #define ARM_SMCCC_OWNER_TRUSTED_APP	48
 #define ARM_SMCCC_OWNER_TRUSTED_APP_END	49
 #define ARM_SMCCC_OWNER_TRUSTED_OS	50
@@ -80,6 +81,22 @@
 
 #include <linux/linkage.h>
 #include <linux/types.h>
+
+enum arm_smccc_conduit {
+	SMCCC_CONDUIT_NONE,
+	SMCCC_CONDUIT_SMC,
+	SMCCC_CONDUIT_HVC,
+};
+
+/**
+ * arm_smccc_1_1_get_conduit()
+ *
+ * Returns the conduit to be used for SMCCCv1.1 or later.
+ *
+ * When SMCCCv1.1 is not present, returns SMCCC_CONDUIT_NONE.
+ */
+enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void);
+
 /**
  * struct arm_smccc_res - Result from SMC/HVC call
  * @a0-a3 result values from registers 0 to 3
@@ -302,5 +319,63 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 #define SMCCC_RET_NOT_SUPPORTED			-1
 #define SMCCC_RET_NOT_REQUIRED			-2
 
+/*
+ * Like arm_smccc_1_1* but always returns SMCCC_RET_NOT_SUPPORTED.
+ * Used when the SMCCC conduit is not defined. The empty asm statement
+ * avoids compiler warnings about unused variables.
+ */
+#define __fail_smccc_1_1(...)						\
+	do {								\
+		__declare_args(__count_args(__VA_ARGS__), __VA_ARGS__);	\
+		asm ("" __constraints(__count_args(__VA_ARGS__)));	\
+		if (___res)						\
+			___res->a0 = SMCCC_RET_NOT_SUPPORTED;		\
+	} while (0)
+
+/*
+ * arm_smccc_1_1_invoke() - make an SMCCC v1.1 compliant call
+ *
+ * This is a variadic macro taking one to eight source arguments, and
+ * an optional return structure.
+ *
+ * @a0-a7: arguments passed in registers 0 to 7
+ * @res: result values from registers 0 to 3
+ *
+ * This macro will make either an HVC call or an SMC call depending on the
+ * current SMCCC conduit. If no valid conduit is available then -1
+ * (SMCCC_RET_NOT_SUPPORTED) is returned in @res.a0 (if supplied).
+ *
+ * The return value also provides the conduit that was used.
+ */
+#define arm_smccc_1_1_invoke(...) ({					\
+		int method = arm_smccc_1_1_get_conduit();		\
+		switch (method) {					\
+		case SMCCC_CONDUIT_HVC:					\
+			arm_smccc_1_1_hvc(__VA_ARGS__);			\
+			break;						\
+		case SMCCC_CONDUIT_SMC:					\
+			arm_smccc_1_1_smc(__VA_ARGS__);			\
+			break;						\
+		default:						\
+			__fail_smccc_1_1(__VA_ARGS__);			\
+			method = SMCCC_CONDUIT_NONE;			\
+			break;						\
+		}							\
+		method;							\
+	})
+
+/* Paravirtualised time calls (defined by ARM DEN0057A) */
+#define ARM_SMCCC_HV_PV_TIME_FEATURES				\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,			\
+			   ARM_SMCCC_SMC_64,			\
+			   ARM_SMCCC_OWNER_STANDARD_HYP,	\
+			   0x20)
+
+#define ARM_SMCCC_HV_PV_TIME_ST					\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,			\
+			   ARM_SMCCC_SMC_64,			\
+			   ARM_SMCCC_OWNER_STANDARD_HYP,	\
+			   0x21)
+
 #endif /*__ASSEMBLY__*/
 #endif /*__LINUX_ARM_SMCCC_H*/

include/linux/arm_sdei.h

@@ -5,12 +5,6 @@
 
 #include <uapi/linux/arm_sdei.h>
 
-enum sdei_conduit_types {
-	CONDUIT_INVALID = 0,
-	CONDUIT_SMC,
-	CONDUIT_HVC,
-};
-
 #include <acpi/ghes.h>
 
 #ifdef CONFIG_ARM_SDE_INTERFACE

include/linux/cpuhotplug.h

@@ -136,6 +136,7 @@ enum cpuhp_state {
 	/* Must be the last timer callback */
 	CPUHP_AP_DUMMY_TIMER_STARTING,
 	CPUHP_AP_ARM_XEN_STARTING,
+	CPUHP_AP_ARM_KVMPV_STARTING,
 	CPUHP_AP_ARM_CORESIGHT_STARTING,
 	CPUHP_AP_ARM64_ISNDEP_STARTING,
 	CPUHP_AP_SMPCFD_DYING,

include/linux/irqchip/arm-gic-v4.h

@@ -32,9 +32,13 @@ struct its_vm {
 struct its_vpe {
 	struct page 		*vpt_page;
 	struct its_vm		*its_vm;
+	/* per-vPE VLPI tracking */
+	atomic_t		vlpi_count;
 	/* Doorbell interrupt */
 	int			irq;
 	irq_hw_number_t		vpe_db_lpi;
+	/* VPE resident */
+	bool			resident;
 	/* VPE proxy mapping */
 	int			vpe_proxy_event;
 	/*

include/linux/kvm_host.h

@@ -746,6 +746,28 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 				  unsigned long len);
 int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 			      gpa_t gpa, unsigned long len);
+
+#define __kvm_put_guest(kvm, gfn, offset, value, type)			\
+({									\
+	unsigned long __addr = gfn_to_hva(kvm, gfn);			\
+	type __user *__uaddr = (type __user *)(__addr + offset);	\
+	int __ret = -EFAULT;						\
+									\
+	if (!kvm_is_error_hva(__addr))					\
+		__ret = put_user(value, __uaddr);			\
+	if (!__ret)							\
+		mark_page_dirty(kvm, gfn);				\
+	__ret;								\
+})
+
+#define kvm_put_guest(kvm, gpa, value, type)				\
+({									\
+	gpa_t __gpa = gpa;						\
+	struct kvm *__kvm = kvm;					\
+	__kvm_put_guest(__kvm, __gpa >> PAGE_SHIFT,			\
+			offset_in_page(__gpa), (value), type);		\
+})
+
 int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
 int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
@@ -1241,7 +1263,7 @@ extern unsigned int halt_poll_ns_grow_start;
 extern unsigned int halt_poll_ns_shrink;
 
 struct kvm_device {
-	struct kvm_device_ops *ops;
+	const struct kvm_device_ops *ops;
 	struct kvm *kvm;
 	void *private;
 	struct list_head vm_node;
@@ -1294,7 +1316,7 @@ struct kvm_device_ops {
 void kvm_device_get(struct kvm_device *dev);
 void kvm_device_put(struct kvm_device *dev);
 struct kvm_device *kvm_device_from_filp(struct file *filp);
-int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type);
+int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type);
 void kvm_unregister_device_ops(u32 type);
 
 extern struct kvm_device_ops kvm_mpic_ops;

include/linux/kvm_types.h

@@ -35,6 +35,8 @@ typedef unsigned long  gva_t;
 typedef u64            gpa_t;
 typedef u64            gfn_t;
 
+#define GPA_INVALID	(~(gpa_t)0)
+
 typedef unsigned long  hva_t;
 typedef u64            hpa_t;
 typedef u64            hfn_t;

include/linux/psci.h

@@ -7,6 +7,7 @@
 #ifndef __LINUX_PSCI_H
 #define __LINUX_PSCI_H
 
+#include <linux/arm-smccc.h>
 #include <linux/init.h>
 #include <linux/types.h>
 
@@ -18,12 +19,6 @@ bool psci_tos_resident_on(int cpu);
 int psci_cpu_suspend_enter(u32 state);
 bool psci_power_state_is_valid(u32 state);
 
-enum psci_conduit {
-	PSCI_CONDUIT_NONE,
-	PSCI_CONDUIT_SMC,
-	PSCI_CONDUIT_HVC,
-};
-
 enum smccc_version {
 	SMCCC_VERSION_1_0,
 	SMCCC_VERSION_1_1,
@@ -38,7 +33,7 @@ struct psci_operations {
 	int (*affinity_info)(unsigned long target_affinity,
 			unsigned long lowest_affinity_level);
 	int (*migrate_info_type)(void);
-	enum psci_conduit conduit;
+	enum arm_smccc_conduit conduit;
 	enum smccc_version smccc_version;
 };
 

include/uapi/linux/kvm.h

@@ -235,6 +235,7 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_S390_STSI        25
 #define KVM_EXIT_IOAPIC_EOI       26
 #define KVM_EXIT_HYPERV           27
+#define KVM_EXIT_ARM_NISV         28
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -394,6 +395,11 @@ struct kvm_run {
 		} eoi;
 		/* KVM_EXIT_HYPERV */
 		struct kvm_hyperv_exit hyperv;
+		/* KVM_EXIT_ARM_NISV */
+		struct {
+			__u64 esr_iss;
+			__u64 fault_ipa;
+		} arm_nisv;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1000,6 +1006,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PMU_EVENT_FILTER 173
 #define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174
 #define KVM_CAP_HYPERV_DIRECT_TLBFLUSH 175
+#define KVM_CAP_ARM_NISV_TO_USER 176
+#define KVM_CAP_ARM_INJECT_EXT_DABT 177
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1227,6 +1235,8 @@ enum kvm_device_type {
 #define KVM_DEV_TYPE_ARM_VGIC_ITS	KVM_DEV_TYPE_ARM_VGIC_ITS
 	KVM_DEV_TYPE_XIVE,
 #define KVM_DEV_TYPE_XIVE		KVM_DEV_TYPE_XIVE
+	KVM_DEV_TYPE_ARM_PV_TIME,
+#define KVM_DEV_TYPE_ARM_PV_TIME	KVM_DEV_TYPE_ARM_PV_TIME
 	KVM_DEV_TYPE_MAX,
 };
 

virt/kvm/arm/arch_timer.c

@@ -80,7 +80,7 @@ static inline bool userspace_irqchip(struct kvm *kvm)
 static void soft_timer_start(struct hrtimer *hrt, u64 ns)
 {
 	hrtimer_start(hrt, ktime_add_ns(ktime_get(), ns),
-		      HRTIMER_MODE_ABS);
+		      HRTIMER_MODE_ABS_HARD);
 }
 
 static void soft_timer_cancel(struct hrtimer *hrt)
@@ -697,11 +697,11 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
 	update_vtimer_cntvoff(vcpu, kvm_phys_timer_read());
 	ptimer->cntvoff = 0;
 
-	hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
 	timer->bg_timer.function = kvm_bg_timer_expire;
 
-	hrtimer_init(&vtimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	hrtimer_init(&ptimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer_init(&vtimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
+	hrtimer_init(&ptimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
 	vtimer->hrtimer.function = kvm_hrtimer_expire;
 	ptimer->hrtimer.function = kvm_hrtimer_expire;
 

virt/kvm/arm/arm.c

@@ -40,6 +40,10 @@
 #include <asm/kvm_coproc.h>
 #include <asm/sections.h>
 
+#include <kvm/arm_hypercalls.h>
+#include <kvm/arm_pmu.h>
+#include <kvm/arm_psci.h>
+
 #ifdef REQUIRES_VIRT
 __asm__(".arch_extension	virt");
 #endif
@@ -98,6 +102,26 @@ int kvm_arch_check_processor_compat(void)
 	return 0;
 }
 
+int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
+			    struct kvm_enable_cap *cap)
+{
+	int r;
+
+	if (cap->flags)
+		return -EINVAL;
+
+	switch (cap->cap) {
+	case KVM_CAP_ARM_NISV_TO_USER:
+		r = 0;
+		kvm->arch.return_nisv_io_abort_to_user = true;
+		break;
+	default:
+		r = -EINVAL;
+		break;
+	}
+
+	return r;
+}
 
 /**
  * kvm_arch_init_vm - initializes a VM data structure
@@ -197,6 +221,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_IMMEDIATE_EXIT:
 	case KVM_CAP_VCPU_EVENTS:
 	case KVM_CAP_ARM_IRQ_LINE_LAYOUT_2:
+	case KVM_CAP_ARM_NISV_TO_USER:
+	case KVM_CAP_ARM_INJECT_EXT_DABT:
 		r = 1;
 		break;
 	case KVM_CAP_ARM_SET_DEVICE_ADDR:
@@ -322,20 +348,24 @@ void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
 	/*
 	 * If we're about to block (most likely because we've just hit a
 	 * WFI), we need to sync back the state of the GIC CPU interface
-	 * so that we have the lastest PMR and group enables. This ensures
+	 * so that we have the latest PMR and group enables. This ensures
 	 * that kvm_arch_vcpu_runnable has up-to-date data to decide
 	 * whether we have pending interrupts.
+	 *
+	 * For the same reason, we want to tell GICv4 that we need
+	 * doorbells to be signalled, should an interrupt become pending.
 	 */
 	preempt_disable();
 	kvm_vgic_vmcr_sync(vcpu);
+	vgic_v4_put(vcpu, true);
 	preempt_enable();
-
-	kvm_vgic_v4_enable_doorbell(vcpu);
 }
 
 void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
 {
-	kvm_vgic_v4_disable_doorbell(vcpu);
+	preempt_disable();
+	vgic_v4_load(vcpu);
+	preempt_enable();
 }
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
@@ -351,6 +381,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 	kvm_arm_reset_debug_ptr(vcpu);
 
+	kvm_arm_pvtime_vcpu_init(&vcpu->arch);
+
 	return kvm_vgic_vcpu_init(vcpu);
 }
 
@@ -380,11 +412,13 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	kvm_vcpu_load_sysregs(vcpu);
 	kvm_arch_vcpu_load_fp(vcpu);
 	kvm_vcpu_pmu_restore_guest(vcpu);
+	if (kvm_arm_is_pvtime_enabled(&vcpu->arch))
+		kvm_make_request(KVM_REQ_RECORD_STEAL, vcpu);
 
 	if (single_task_running())
-		vcpu_clear_wfe_traps(vcpu);
+		vcpu_clear_wfx_traps(vcpu);
 	else
-		vcpu_set_wfe_traps(vcpu);
+		vcpu_set_wfx_traps(vcpu);
 
 	vcpu_ptrauth_setup_lazy(vcpu);
 }
@@ -645,6 +679,9 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu)
 		 * that a VCPU sees new virtual interrupts.
 		 */
 		kvm_check_request(KVM_REQ_IRQ_PENDING, vcpu);
+
+		if (kvm_check_request(KVM_REQ_RECORD_STEAL, vcpu))
+			kvm_update_stolen_time(vcpu);
 	}
 }
 
@@ -1315,7 +1352,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	}
 }
 
-static void cpu_init_hyp_mode(void *dummy)
+static void cpu_init_hyp_mode(void)
 {
 	phys_addr_t pgd_ptr;
 	unsigned long hyp_stack_ptr;
@@ -1349,7 +1386,7 @@ static void cpu_hyp_reinit(void)
 	if (is_kernel_in_hyp_mode())
 		kvm_timer_init_vhe();
 	else
-		cpu_init_hyp_mode(NULL);
+		cpu_init_hyp_mode();
 
 	kvm_arm_init_debug();
 

virt/kvm/arm/hypercalls.c

+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019 Arm Ltd.
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_emulate.h>
+
+#include <kvm/arm_hypercalls.h>
+#include <kvm/arm_psci.h>
+
+int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
+{
+	u32 func_id = smccc_get_function(vcpu);
+	long val = SMCCC_RET_NOT_SUPPORTED;
+	u32 feature;
+	gpa_t gpa;
+
+	switch (func_id) {
+	case ARM_SMCCC_VERSION_FUNC_ID:
+		val = ARM_SMCCC_VERSION_1_1;
+		break;
+	case ARM_SMCCC_ARCH_FEATURES_FUNC_ID:
+		feature = smccc_get_arg1(vcpu);
+		switch (feature) {
+		case ARM_SMCCC_ARCH_WORKAROUND_1:
+			switch (kvm_arm_harden_branch_predictor()) {
+			case KVM_BP_HARDEN_UNKNOWN:
+				break;
+			case KVM_BP_HARDEN_WA_NEEDED:
+				val = SMCCC_RET_SUCCESS;
+				break;
+			case KVM_BP_HARDEN_NOT_REQUIRED:
+				val = SMCCC_RET_NOT_REQUIRED;
+				break;
+			}
+			break;
+		case ARM_SMCCC_ARCH_WORKAROUND_2:
+			switch (kvm_arm_have_ssbd()) {
+			case KVM_SSBD_FORCE_DISABLE:
+			case KVM_SSBD_UNKNOWN:
+				break;
+			case KVM_SSBD_KERNEL:
+				val = SMCCC_RET_SUCCESS;
+				break;
+			case KVM_SSBD_FORCE_ENABLE:
+			case KVM_SSBD_MITIGATED:
+				val = SMCCC_RET_NOT_REQUIRED;
+				break;
+			}
+			break;
+		case ARM_SMCCC_HV_PV_TIME_FEATURES:
+			val = SMCCC_RET_SUCCESS;
+			break;
+		}
+		break;
+	case ARM_SMCCC_HV_PV_TIME_FEATURES:
+		val = kvm_hypercall_pv_features(vcpu);
+		break;
+	case ARM_SMCCC_HV_PV_TIME_ST:
+		gpa = kvm_init_stolen_time(vcpu);
+		if (gpa != GPA_INVALID)
+			val = gpa;
+		break;
+	default:
+		return kvm_psci_call(vcpu);
+	}
+
+	smccc_set_retval(vcpu, val, 0, 0, 0);
+	return 1;
+}

virt/kvm/arm/mmio.c

@@ -167,7 +167,14 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		if (ret)
 			return ret;
 	} else {
-		kvm_err("load/store instruction decoding not implemented\n");
+		if (vcpu->kvm->arch.return_nisv_io_abort_to_user) {
+			run->exit_reason = KVM_EXIT_ARM_NISV;
+			run->arm_nisv.esr_iss = kvm_vcpu_dabt_iss_nisv_sanitized(vcpu);
+			run->arm_nisv.fault_ipa = fault_ipa;
+			return 0;
+		}
+
+		kvm_pr_unimpl("Data abort outside memslots with no valid syndrome info\n");
 		return -ENOSYS;
 	}
 

virt/kvm/arm/mmu.c

@@ -38,6 +38,11 @@ static unsigned long io_map_base;
 #define KVM_S2PTE_FLAG_IS_IOMAP		(1UL << 0)
 #define KVM_S2_FLAG_LOGGING_ACTIVE	(1UL << 1)
 
+static bool is_iomap(unsigned long flags)
+{
+	return flags & KVM_S2PTE_FLAG_IS_IOMAP;
+}
+
 static bool memslot_is_logging(struct kvm_memory_slot *memslot)
 {
 	return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY);
@@ -1698,6 +1703,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 	vma_pagesize = vma_kernel_pagesize(vma);
 	if (logging_active ||
+	    (vma->vm_flags & VM_PFNMAP) ||
 	    !fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) {
 		force_pte = true;
 		vma_pagesize = PAGE_SIZE;
@@ -1760,6 +1766,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			writable = false;
 	}
 
+	if (exec_fault && is_iomap(flags))
+		return -ENOEXEC;
+
 	spin_lock(&kvm->mmu_lock);
 	if (mmu_notifier_retry(kvm, mmu_seq))
 		goto out_unlock;
@@ -1781,7 +1790,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (writable)
 		kvm_set_pfn_dirty(pfn);
 
-	if (fault_status != FSC_PERM)
+	if (fault_status != FSC_PERM && !is_iomap(flags))
 		clean_dcache_guest_page(pfn, vma_pagesize);
 
 	if (exec_fault)
@@ -1948,9 +1957,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
 		if (is_iabt) {
 			/* Prefetch Abort on I/O address */
-			kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
-			ret = 1;
-			goto out_unlock;
+			ret = -ENOEXEC;
+			goto out;
 		}
 
 		/*
@@ -1992,6 +2000,11 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
 	if (ret == 0)
 		ret = 1;
+out:
+	if (ret == -ENOEXEC) {
+		kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+		ret = 1;
+	}
 out_unlock:
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	return ret;
@@ -2301,15 +2314,6 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		if (!vma || vma->vm_start >= reg_end)
 			break;
 
-		/*
-		 * Mapping a read-only VMA is only allowed if the
-		 * memory region is configured as read-only.
-		 */
-		if (writable && !(vma->vm_flags & VM_WRITE)) {
-			ret = -EPERM;
-			break;
-		}
-
 		/*
 		 * Take the intersection of this VMA with the memory region
 		 */

virt/kvm/arm/psci.c

@@ -15,6 +15,7 @@
 #include <asm/kvm_host.h>
 
 #include <kvm/arm_psci.h>
+#include <kvm/arm_hypercalls.h>
 
 /*
  * This is an implementation of the Power State Coordination Interface
@@ -23,38 +24,6 @@
 
 #define AFFINITY_MASK(level)	~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1)
 
-static u32 smccc_get_function(struct kvm_vcpu *vcpu)
-{
-	return vcpu_get_reg(vcpu, 0);
-}
-
-static unsigned long smccc_get_arg1(struct kvm_vcpu *vcpu)
-{
-	return vcpu_get_reg(vcpu, 1);
-}
-
-static unsigned long smccc_get_arg2(struct kvm_vcpu *vcpu)
-{
-	return vcpu_get_reg(vcpu, 2);
-}
-
-static unsigned long smccc_get_arg3(struct kvm_vcpu *vcpu)
-{
-	return vcpu_get_reg(vcpu, 3);
-}
-
-static void smccc_set_retval(struct kvm_vcpu *vcpu,
-			     unsigned long a0,
-			     unsigned long a1,
-			     unsigned long a2,
-			     unsigned long a3)
-{
-	vcpu_set_reg(vcpu, 0, a0);
-	vcpu_set_reg(vcpu, 1, a1);
-	vcpu_set_reg(vcpu, 2, a2);
-	vcpu_set_reg(vcpu, 3, a3);
-}
-
 static unsigned long psci_affinity_mask(unsigned long affinity_level)
 {
 	if (affinity_level <= 3)
@@ -373,7 +342,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
  * Errors:
  * -EINVAL: Unrecognized PSCI function
  */
-static int kvm_psci_call(struct kvm_vcpu *vcpu)
+int kvm_psci_call(struct kvm_vcpu *vcpu)
 {
 	switch (kvm_psci_version(vcpu, vcpu->kvm)) {
 	case KVM_ARM_PSCI_1_0:
@@ -387,55 +356,6 @@ static int kvm_psci_call(struct kvm_vcpu *vcpu)
 	};
 }
 
-int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
-{
-	u32 func_id = smccc_get_function(vcpu);
-	u32 val = SMCCC_RET_NOT_SUPPORTED;
-	u32 feature;
-
-	switch (func_id) {
-	case ARM_SMCCC_VERSION_FUNC_ID:
-		val = ARM_SMCCC_VERSION_1_1;
-		break;
-	case ARM_SMCCC_ARCH_FEATURES_FUNC_ID:
-		feature = smccc_get_arg1(vcpu);
-		switch(feature) {
-		case ARM_SMCCC_ARCH_WORKAROUND_1:
-			switch (kvm_arm_harden_branch_predictor()) {
-			case KVM_BP_HARDEN_UNKNOWN:
-				break;
-			case KVM_BP_HARDEN_WA_NEEDED:
-				val = SMCCC_RET_SUCCESS;
-				break;
-			case KVM_BP_HARDEN_NOT_REQUIRED:
-				val = SMCCC_RET_NOT_REQUIRED;
-				break;
-			}
-			break;
-		case ARM_SMCCC_ARCH_WORKAROUND_2:
-			switch (kvm_arm_have_ssbd()) {
-			case KVM_SSBD_FORCE_DISABLE:
-			case KVM_SSBD_UNKNOWN:
-				break;
-			case KVM_SSBD_KERNEL:
-				val = SMCCC_RET_SUCCESS;
-				break;
-			case KVM_SSBD_FORCE_ENABLE:
-			case KVM_SSBD_MITIGATED:
-				val = SMCCC_RET_NOT_REQUIRED;
-				break;
-			}
-			break;
-		}
-		break;
-	default:
-		return kvm_psci_call(vcpu);
-	}
-
-	smccc_set_retval(vcpu, val, 0, 0, 0);
-	return 1;
-}
-
 int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu)
 {
 	return 3;		/* PSCI version and two workaround registers */

virt/kvm/arm/pvtime.c

+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019 Arm Ltd.
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_mmu.h>
+#include <asm/pvclock-abi.h>
+
+#include <kvm/arm_hypercalls.h>
+
+void kvm_update_stolen_time(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	u64 steal;
+	__le64 steal_le;
+	u64 offset;
+	int idx;
+	u64 base = vcpu->arch.steal.base;
+
+	if (base == GPA_INVALID)
+		return;
+
+	/* Let's do the local bookkeeping */
+	steal = vcpu->arch.steal.steal;
+	steal += current->sched_info.run_delay - vcpu->arch.steal.last_steal;
+	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
+	vcpu->arch.steal.steal = steal;
+
+	steal_le = cpu_to_le64(steal);
+	idx = srcu_read_lock(&kvm->srcu);
+	offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time);
+	kvm_put_guest(kvm, base + offset, steal_le, u64);
+	srcu_read_unlock(&kvm->srcu, idx);
+}
+
+long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu)
+{
+	u32 feature = smccc_get_arg1(vcpu);
+	long val = SMCCC_RET_NOT_SUPPORTED;
+
+	switch (feature) {
+	case ARM_SMCCC_HV_PV_TIME_FEATURES:
+	case ARM_SMCCC_HV_PV_TIME_ST:
+		val = SMCCC_RET_SUCCESS;
+		break;
+	}
+
+	return val;
+}
+
+gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
+{
+	struct pvclock_vcpu_stolen_time init_values = {};
+	struct kvm *kvm = vcpu->kvm;
+	u64 base = vcpu->arch.steal.base;
+	int idx;
+
+	if (base == GPA_INVALID)
+		return base;
+
+	/*
+	 * Start counting stolen time from the time the guest requests
+	 * the feature enabled.
+	 */
+	vcpu->arch.steal.steal = 0;
+	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	kvm_write_guest(kvm, base, &init_values, sizeof(init_values));
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	return base;
+}
+
+int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr)
+{
+	u64 __user *user = (u64 __user *)attr->addr;
+	struct kvm *kvm = vcpu->kvm;
+	u64 ipa;
+	int ret = 0;
+	int idx;
+
+	if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
+		return -ENXIO;
+
+	if (get_user(ipa, user))
+		return -EFAULT;
+	if (!IS_ALIGNED(ipa, 64))
+		return -EINVAL;
+	if (vcpu->arch.steal.base != GPA_INVALID)
+		return -EEXIST;
+
+	/* Check the address is in a valid memslot */
+	idx = srcu_read_lock(&kvm->srcu);
+	if (kvm_is_error_hva(gfn_to_hva(kvm, ipa >> PAGE_SHIFT)))
+		ret = -EINVAL;
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	if (!ret)
+		vcpu->arch.steal.base = ipa;
+
+	return ret;
+}
+
+int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr)
+{
+	u64 __user *user = (u64 __user *)attr->addr;
+	u64 ipa;
+
+	if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
+		return -ENXIO;
+
+	ipa = vcpu->arch.steal.base;
+
+	if (put_user(ipa, user))
+		return -EFAULT;
+	return 0;
+}
+
+int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr)
+{
+	switch (attr->attr) {
+	case KVM_ARM_VCPU_PVTIME_IPA:
+		return 0;
+	}
+	return -ENXIO;
+}

virt/kvm/arm/vgic/vgic-init.c

@@ -70,7 +70,7 @@ void kvm_vgic_early_init(struct kvm *kvm)
  */
 int kvm_vgic_create(struct kvm *kvm, u32 type)
 {
-	int i, vcpu_lock_idx = -1, ret;
+	int i, ret;
 	struct kvm_vcpu *vcpu;
 
 	if (irqchip_in_kernel(kvm))
@@ -86,17 +86,9 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 		!kvm_vgic_global_state.can_emulate_gicv2)
 		return -ENODEV;
 
-	/*
-	 * Any time a vcpu is run, vcpu_load is called which tries to grab the
-	 * vcpu->mutex.  By grabbing the vcpu->mutex of all VCPUs we ensure
-	 * that no other VCPUs are run while we create the vgic.
-	 */
 	ret = -EBUSY;
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (!mutex_trylock(&vcpu->mutex))
-			goto out_unlock;
-		vcpu_lock_idx = i;
-	}
+	if (!lock_all_vcpus(kvm))
+		return ret;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		if (vcpu->arch.has_run_once)
@@ -125,10 +117,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 		INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions);
 
 out_unlock:
-	for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
-		vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
-		mutex_unlock(&vcpu->mutex);
-	}
+	unlock_all_vcpus(kvm);
 	return ret;
 }
 
@@ -177,6 +166,7 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
 			break;
 		default:
 			kfree(dist->spis);
+			dist->spis = NULL;
 			return -EINVAL;
 		}
 	}
@@ -203,6 +193,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 
 	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
 	raw_spin_lock_init(&vgic_cpu->ap_list_lock);
+	atomic_set(&vgic_cpu->vgic_v3.its_vpe.vlpi_count, 0);
 
 	/*
 	 * Enable and configure all SGIs to be edge-triggered and

virt/kvm/arm/vgic/vgic-its.c

@@ -360,7 +360,10 @@ static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu)
 		if (ret)
 			return ret;
 
+		if (map.vpe)
+			atomic_dec(&map.vpe->vlpi_count);
 		map.vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
+		atomic_inc(&map.vpe->vlpi_count);
 
 		ret = its_map_vlpi(irq->host_irq, &map);
 	}

virt/kvm/arm/vgic/vgic-v3.c

@@ -357,14 +357,14 @@ int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq)
 }
 
 /**
- * vgic_its_save_pending_tables - Save the pending tables into guest RAM
+ * vgic_v3_save_pending_tables - Save the pending tables into guest RAM
  * kvm lock and all vcpu lock must be held
  */
 int vgic_v3_save_pending_tables(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
-	int last_byte_offset = -1;
 	struct vgic_irq *irq;
+	gpa_t last_ptr = ~(gpa_t)0;
 	int ret;
 	u8 val;
 
@@ -384,11 +384,11 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
 		bit_nr = irq->intid % BITS_PER_BYTE;
 		ptr = pendbase + byte_offset;
 
-		if (byte_offset != last_byte_offset) {
+		if (ptr != last_ptr) {
 			ret = kvm_read_guest_lock(kvm, ptr, &val, 1);
 			if (ret)
 				return ret;
-			last_byte_offset = byte_offset;
+			last_ptr = ptr;
 		}
 
 		stored = val & (1U << bit_nr);
@@ -664,6 +664,8 @@ void vgic_v3_load(struct kvm_vcpu *vcpu)
 
 	if (has_vhe())
 		__vgic_v3_activate_traps(vcpu);
+
+	WARN_ON(vgic_v4_load(vcpu));
 }
 
 void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu)
@@ -676,6 +678,8 @@ void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu)
 
 void vgic_v3_put(struct kvm_vcpu *vcpu)
 {
+	WARN_ON(vgic_v4_put(vcpu, false));
+
 	vgic_v3_vmcr_sync(vcpu);
 
 	kvm_call_hyp(__vgic_v3_save_aprs, vcpu);

virt/kvm/arm/vgic/vgic-v4.c

@@ -85,6 +85,10 @@ static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info)
 {
 	struct kvm_vcpu *vcpu = info;
 
+	/* We got the message, no need to fire again */
+	if (!irqd_irq_disabled(&irq_to_desc(irq)->irq_data))
+		disable_irq_nosync(irq);
+
 	vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true;
 	kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
 	kvm_vcpu_kick(vcpu);
@@ -192,20 +196,30 @@ void vgic_v4_teardown(struct kvm *kvm)
 	its_vm->vpes = NULL;
 }
 
-int vgic_v4_sync_hwstate(struct kvm_vcpu *vcpu)
+int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db)
 {
-	if (!vgic_supports_direct_msis(vcpu->kvm))
+	struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
+	struct irq_desc *desc = irq_to_desc(vpe->irq);
+
+	if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident)
 		return 0;
 
-	return its_schedule_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe, false);
+	/*
+	 * If blocking, a doorbell is required. Undo the nested
+	 * disable_irq() calls...
+	 */
+	while (need_db && irqd_irq_disabled(&desc->irq_data))
+		enable_irq(vpe->irq);
+
+	return its_schedule_vpe(vpe, false);
 }
 
-int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu)
+int vgic_v4_load(struct kvm_vcpu *vcpu)
 {
-	int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq;
+	struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
 	int err;
 
-	if (!vgic_supports_direct_msis(vcpu->kvm))
+	if (!vgic_supports_direct_msis(vcpu->kvm) || vpe->resident)
 		return 0;
 
 	/*
@@ -214,11 +228,14 @@ int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu)
 	 * doc in drivers/irqchip/irq-gic-v4.c to understand how this
 	 * turns into a VMOVP command at the ITS level.
 	 */
-	err = irq_set_affinity(irq, cpumask_of(smp_processor_id()));
+	err = irq_set_affinity(vpe->irq, cpumask_of(smp_processor_id()));
 	if (err)
 		return err;
 
-	err = its_schedule_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe, true);
+	/* Disabled the doorbell, as we're about to enter the guest */
+	disable_irq_nosync(vpe->irq);
+
+	err = its_schedule_vpe(vpe, true);
 	if (err)
 		return err;
 
@@ -226,9 +243,7 @@ int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu)
 	 * Now that the VPE is resident, let's get rid of a potential
 	 * doorbell interrupt that would still be pending.
 	 */
-	err = irq_set_irqchip_state(irq, IRQCHIP_STATE_PENDING, false);
-
-	return err;
+	return irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false);
 }
 
 static struct vgic_its *vgic_get_its(struct kvm *kvm,
@@ -266,7 +281,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq,
 
 	mutex_lock(&its->its_lock);
 
-	/* Perform then actual DevID/EventID -> LPI translation. */
+	/* Perform the actual DevID/EventID -> LPI translation. */
 	ret = vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid,
 				   irq_entry->msi.data, &irq);
 	if (ret)
@@ -294,6 +309,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq,
 
 	irq->hw		= true;
 	irq->host_irq	= virq;
+	atomic_inc(&map.vpe->vlpi_count);
 
 out:
 	mutex_unlock(&its->its_lock);
@@ -327,6 +343,7 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq,
 
 	WARN_ON(!(irq->hw && irq->host_irq == virq));
 	if (irq->hw) {
+		atomic_dec(&irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count);
 		irq->hw = false;
 		ret = its_unmap_vlpi(virq);
 	}
@@ -335,21 +352,3 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq,
 	mutex_unlock(&its->its_lock);
 	return ret;
 }
-
-void kvm_vgic_v4_enable_doorbell(struct kvm_vcpu *vcpu)
-{
-	if (vgic_supports_direct_msis(vcpu->kvm)) {
-		int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq;
-		if (irq)
-			enable_irq(irq);
-	}
-}
-
-void kvm_vgic_v4_disable_doorbell(struct kvm_vcpu *vcpu)
-{
-	if (vgic_supports_direct_msis(vcpu->kvm)) {
-		int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq;
-		if (irq)
-			disable_irq(irq);
-	}
-}

virt/kvm/arm/vgic/vgic.c

@@ -857,8 +857,6 @@ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 
-	WARN_ON(vgic_v4_sync_hwstate(vcpu));
-
 	/* An empty ap_list_head implies used_lrs == 0 */
 	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
 		return;
@@ -882,8 +880,6 @@ static inline void vgic_restore_state(struct kvm_vcpu *vcpu)
 /* Flush our emulation state into the GIC hardware before entering the guest. */
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 {
-	WARN_ON(vgic_v4_flush_hwstate(vcpu));
-
 	/*
 	 * If there are no virtual interrupts active or pending for this
 	 * VCPU, then there is no work to do and we can bail out without

virt/kvm/arm/vgic/vgic.h

@@ -316,7 +316,5 @@ void vgic_its_invalidate_cache(struct kvm *kvm);
 bool vgic_supports_direct_msis(struct kvm *kvm);
 int vgic_v4_init(struct kvm *kvm);
 void vgic_v4_teardown(struct kvm *kvm);
-int vgic_v4_sync_hwstate(struct kvm_vcpu *vcpu);
-int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu);
 
 #endif

virt/kvm/kvm_main.c

@@ -3115,14 +3115,14 @@ struct kvm_device *kvm_device_from_filp(struct file *filp)
 	return filp->private_data;
 }
 
-static struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = {
+static const struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = {
 #ifdef CONFIG_KVM_MPIC
 	[KVM_DEV_TYPE_FSL_MPIC_20]	= &kvm_mpic_ops,
 	[KVM_DEV_TYPE_FSL_MPIC_42]	= &kvm_mpic_ops,
 #endif
 };
 
-int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type)
+int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type)
 {
 	if (type >= ARRAY_SIZE(kvm_device_ops_table))
 		return -ENOSPC;
@@ -3143,7 +3143,7 @@ void kvm_unregister_device_ops(u32 type)
 static int kvm_ioctl_create_device(struct kvm *kvm,
 				   struct kvm_create_device *cd)
 {
-	struct kvm_device_ops *ops = NULL;
+	const struct kvm_device_ops *ops = NULL;
 	struct kvm_device *dev;
 	bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
 	int type;