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

Pull kvm fixes from Paolo Bonzini:
 "x86:
   - Fixes for the new scalable MMU
   - Fixes for migration of nested hypervisors on AMD
   - Fix for clang integrated assembler
   - Fix for left shift by 64 (UBSAN)
   - Small cleanups
   - Straggler SEV-ES patch

  ARM:
   - VM init cleanups
   - PSCI relay cleanups
   - Kill CONFIG_KVM_ARM_PMU
   - Fixup __init annotations
   - Fixup reg_to_encoding()
   - Fix spurious PMCR_EL0 access

  Misc:
   - selftests cleanups"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (38 commits)
  KVM: x86: __kvm_vcpu_halt can be static
  KVM: SVM: Add support for booting APs in an SEV-ES guest
  KVM: nSVM: cancel KVM_REQ_GET_NESTED_STATE_PAGES on nested vmexit
  KVM: nSVM: mark vmcb as dirty when forcingly leaving the guest mode
  KVM: nSVM: correctly restore nested_run_pending on migration
  KVM: x86/mmu: Clarify TDP MMU page list invariants
  KVM: x86/mmu: Ensure TDP MMU roots are freed after yield
  kvm: check tlbs_dirty directly
  KVM: x86: change in pv_eoi_get_pending() to make code more readable
  MAINTAINERS: Really update email address for Sean Christopherson
  KVM: x86: fix shift out of bounds reported by UBSAN
  KVM: selftests: Implement perf_test_util more conventionally
  KVM: selftests: Use vm_create_with_vcpus in create_vm
  KVM: selftests: Factor out guest mode code
  KVM/SVM: Remove leftover __svm_vcpu_run prototype from svm.c
  KVM: SVM: Add register operand to vmsave call in sev_es_vcpu_load
  KVM: x86/mmu: Optimize not-present/MMIO SPTE check in get_mmio_spte()
  KVM: x86/mmu: Use raw level to index into MMIO walks' sptes array
  KVM: x86/mmu: Get root level from walkers when retrieving MMIO SPTE
  KVM: x86/mmu: Use -1 to flag an undefined spte in get_mmio_spte()
  ...

Documentation/virt/kvm/api.rst

@@ -392,9 +392,14 @@ This ioctl is obsolete and has been removed.
 
 Errors:
 
-  =====      =============================
+  =======    ==============================================================
   EINTR      an unmasked signal is pending
-  =====      =============================
+  ENOEXEC    the vcpu hasn't been initialized or the guest tried to execute
+             instructions from device memory (arm64)
+  ENOSYS     data abort outside memslots with no syndrome info and
+             KVM_CAP_ARM_NISV_TO_USER not enabled (arm64)
+  EPERM      SVE feature set but not finalized (arm64)
+  =======    ==============================================================
 
 This ioctl is used to run a guest virtual cpu.  While there are no
 explicit parameters, there is an implicit parameter block that can be

MAINTAINERS

@@ -9776,7 +9776,7 @@ F:	tools/testing/selftests/kvm/s390x/
 
 KERNEL VIRTUAL MACHINE FOR X86 (KVM/x86)
 M:	Paolo Bonzini <[email protected]>
-R:	Sean Christopherson <sean.j.christopherson@intel.com>
+R:	Sean Christopherson <seanjc@google.com>
 R:	Vitaly Kuznetsov <[email protected]>
 R:	Wanpeng Li <[email protected]>
 R:	Jim Mattson <[email protected]>

arch/arm64/include/asm/kvm_host.h

@@ -17,6 +17,7 @@
 #include <linux/jump_label.h>
 #include <linux/kvm_types.h>
 #include <linux/percpu.h>
+#include <linux/psci.h>
 #include <asm/arch_gicv3.h>
 #include <asm/barrier.h>
 #include <asm/cpufeature.h>
@@ -240,6 +241,28 @@ struct kvm_host_data {
 	struct kvm_pmu_events pmu_events;
 };
 
+struct kvm_host_psci_config {
+	/* PSCI version used by host. */
+	u32 version;
+
+	/* Function IDs used by host if version is v0.1. */
+	struct psci_0_1_function_ids function_ids_0_1;
+
+	bool psci_0_1_cpu_suspend_implemented;
+	bool psci_0_1_cpu_on_implemented;
+	bool psci_0_1_cpu_off_implemented;
+	bool psci_0_1_migrate_implemented;
+};
+
+extern struct kvm_host_psci_config kvm_nvhe_sym(kvm_host_psci_config);
+#define kvm_host_psci_config CHOOSE_NVHE_SYM(kvm_host_psci_config)
+
+extern s64 kvm_nvhe_sym(hyp_physvirt_offset);
+#define hyp_physvirt_offset CHOOSE_NVHE_SYM(hyp_physvirt_offset)
+
+extern u64 kvm_nvhe_sym(hyp_cpu_logical_map)[NR_CPUS];
+#define hyp_cpu_logical_map CHOOSE_NVHE_SYM(hyp_cpu_logical_map)
+
 struct vcpu_reset_state {
 	unsigned long	pc;
 	unsigned long	r0;

arch/arm64/kernel/cpufeature.c

@@ -2568,7 +2568,7 @@ static void verify_hyp_capabilities(void)
 	int parange, ipa_max;
 	unsigned int safe_vmid_bits, vmid_bits;
 
-	if (!IS_ENABLED(CONFIG_KVM) || !IS_ENABLED(CONFIG_KVM_ARM_HOST))
+	if (!IS_ENABLED(CONFIG_KVM))
 		return;
 
 	safe_mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);

arch/arm64/kernel/smp.c

@@ -434,7 +434,7 @@ static void __init hyp_mode_check(void)
 			   "CPU: CPUs started in inconsistent modes");
 	else
 		pr_info("CPU: All CPU(s) started at EL1\n");
-	if (IS_ENABLED(CONFIG_KVM))
+	if (IS_ENABLED(CONFIG_KVM) && !is_kernel_in_hyp_mode())
 		kvm_compute_layout();
 }
 

arch/arm64/kvm/Kconfig

@@ -49,14 +49,6 @@ if KVM
 
 source "virt/kvm/Kconfig"
 
-config KVM_ARM_PMU
-	bool "Virtual Performance Monitoring Unit (PMU) support"
-	depends on HW_PERF_EVENTS
-	default y
-	help
-	  Adds support for a virtual Performance Monitoring Unit (PMU) in
-	  virtual machines.
-
 endif # KVM
 
 endif # VIRTUALIZATION

arch/arm64/kvm/Makefile

@@ -24,4 +24,4 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
 	 vgic/vgic-mmio-v3.o vgic/vgic-kvm-device.o \
 	 vgic/vgic-its.o vgic/vgic-debug.o
 
-kvm-$(CONFIG_KVM_ARM_PMU)  += pmu-emul.o
+kvm-$(CONFIG_HW_PERF_EVENTS)  += pmu-emul.o

arch/arm64/kvm/arch_timer.c

@@ -1129,9 +1129,10 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu)
 	if (!irqchip_in_kernel(vcpu->kvm))
 		goto no_vgic;
 
-	if (!vgic_initialized(vcpu->kvm))
-		return -ENODEV;
-
+	/*
+	 * At this stage, we have the guarantee that the vgic is both
+	 * available and initialized.
+	 */
 	if (!timer_irqs_are_valid(vcpu)) {
 		kvm_debug("incorrectly configured timer irqs\n");
 		return -EINVAL;

arch/arm64/kvm/arm.c

@@ -65,10 +65,6 @@ static bool vgic_present;
 static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled);
 DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
-extern u64 kvm_nvhe_sym(__cpu_logical_map)[NR_CPUS];
-extern u32 kvm_nvhe_sym(kvm_host_psci_version);
-extern struct psci_0_1_function_ids kvm_nvhe_sym(kvm_host_psci_0_1_function_ids);
-
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
@@ -584,11 +580,9 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 		 * Map the VGIC hardware resources before running a vcpu the
 		 * first time on this VM.
 		 */
-		if (unlikely(!vgic_ready(kvm))) {
-			ret = kvm_vgic_map_resources(kvm);
-			if (ret)
-				return ret;
-		}
+		ret = kvm_vgic_map_resources(kvm);
+		if (ret)
+			return ret;
 	} else {
 		/*
 		 * Tell the rest of the code that there are userspace irqchip
@@ -1574,12 +1568,12 @@ static struct notifier_block hyp_init_cpu_pm_nb = {
 	.notifier_call = hyp_init_cpu_pm_notifier,
 };
 
-static void __init hyp_cpu_pm_init(void)
+static void hyp_cpu_pm_init(void)
 {
 	if (!is_protected_kvm_enabled())
 		cpu_pm_register_notifier(&hyp_init_cpu_pm_nb);
 }
-static void __init hyp_cpu_pm_exit(void)
+static void hyp_cpu_pm_exit(void)
 {
 	if (!is_protected_kvm_enabled())
 		cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb);
@@ -1604,9 +1598,12 @@ static void init_cpu_logical_map(void)
 	 * allow any other CPUs from the `possible` set to boot.
 	 */
 	for_each_online_cpu(cpu)
-		kvm_nvhe_sym(__cpu_logical_map)[cpu] = cpu_logical_map(cpu);
+		hyp_cpu_logical_map[cpu] = cpu_logical_map(cpu);
 }
 
+#define init_psci_0_1_impl_state(config, what)	\
+	config.psci_0_1_ ## what ## _implemented = psci_ops.what
+
 static bool init_psci_relay(void)
 {
 	/*
@@ -1618,8 +1615,15 @@ static bool init_psci_relay(void)
 		return false;
 	}
 
-	kvm_nvhe_sym(kvm_host_psci_version) = psci_ops.get_version();
-	kvm_nvhe_sym(kvm_host_psci_0_1_function_ids) = get_psci_0_1_function_ids();
+	kvm_host_psci_config.version = psci_ops.get_version();
+
+	if (kvm_host_psci_config.version == PSCI_VERSION(0, 1)) {
+		kvm_host_psci_config.function_ids_0_1 = get_psci_0_1_function_ids();
+		init_psci_0_1_impl_state(kvm_host_psci_config, cpu_suspend);
+		init_psci_0_1_impl_state(kvm_host_psci_config, cpu_on);
+		init_psci_0_1_impl_state(kvm_host_psci_config, cpu_off);
+		init_psci_0_1_impl_state(kvm_host_psci_config, migrate);
+	}
 	return true;
 }
 

arch/arm64/kvm/hyp/include/hyp/adjust_pc.h

@@ -59,4 +59,13 @@ static inline void __adjust_pc(struct kvm_vcpu *vcpu)
 	}
 }
 
+/*
+ * Skip an instruction while host sysregs are live.
+ * Assumes host is always 64-bit.
+ */
+static inline void kvm_skip_host_instr(void)
+{
+	write_sysreg_el2(read_sysreg_el2(SYS_ELR) + 4, SYS_ELR);
+}
+
 #endif

arch/arm64/kvm/hyp/nvhe/hyp-main.c

@@ -157,11 +157,6 @@ static void default_host_smc_handler(struct kvm_cpu_context *host_ctxt)
 	__kvm_hyp_host_forward_smc(host_ctxt);
 }
 
-static void skip_host_instruction(void)
-{
-	write_sysreg_el2(read_sysreg_el2(SYS_ELR) + 4, SYS_ELR);
-}
-
 static void handle_host_smc(struct kvm_cpu_context *host_ctxt)
 {
 	bool handled;
@@ -170,11 +165,8 @@ static void handle_host_smc(struct kvm_cpu_context *host_ctxt)
 	if (!handled)
 		default_host_smc_handler(host_ctxt);
 
-	/*
-	 * Unlike HVC, the return address of an SMC is the instruction's PC.
-	 * Move the return address past the instruction.
-	 */
-	skip_host_instruction();
+	/* SMC was trapped, move ELR past the current PC. */
+	kvm_skip_host_instr();
 }
 
 void handle_trap(struct kvm_cpu_context *host_ctxt)

arch/arm64/kvm/hyp/nvhe/hyp-smp.c

@@ -14,14 +14,14 @@
  * Other CPUs should not be allowed to boot because their features were
  * not checked against the finalized system capabilities.
  */
-u64 __ro_after_init __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
+u64 __ro_after_init hyp_cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
 
 u64 cpu_logical_map(unsigned int cpu)
 {
-	if (cpu >= ARRAY_SIZE(__cpu_logical_map))
+	if (cpu >= ARRAY_SIZE(hyp_cpu_logical_map))
 		hyp_panic();
 
-	return __cpu_logical_map[cpu];
+	return hyp_cpu_logical_map[cpu];
 }
 
 unsigned long __hyp_per_cpu_offset(unsigned int cpu)

arch/arm64/kvm/hyp/nvhe/psci-relay.c

@@ -7,11 +7,8 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
-#include <kvm/arm_hypercalls.h>
 #include <linux/arm-smccc.h>
 #include <linux/kvm_host.h>
-#include <linux/psci.h>
-#include <kvm/arm_psci.h>
 #include <uapi/linux/psci.h>
 
 #include <nvhe/trap_handler.h>
@@ -22,9 +19,8 @@ void kvm_hyp_cpu_resume(unsigned long r0);
 void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt);
 
 /* Config options set by the host. */
-__ro_after_init u32 kvm_host_psci_version;
-__ro_after_init struct psci_0_1_function_ids kvm_host_psci_0_1_function_ids;
-__ro_after_init s64 hyp_physvirt_offset;
+struct kvm_host_psci_config __ro_after_init kvm_host_psci_config;
+s64 __ro_after_init hyp_physvirt_offset;
 
 #define __hyp_pa(x) ((phys_addr_t)((x)) + hyp_physvirt_offset)
 
@@ -47,19 +43,16 @@ struct psci_boot_args {
 static DEFINE_PER_CPU(struct psci_boot_args, cpu_on_args) = PSCI_BOOT_ARGS_INIT;
 static DEFINE_PER_CPU(struct psci_boot_args, suspend_args) = PSCI_BOOT_ARGS_INIT;
 
-static u64 get_psci_func_id(struct kvm_cpu_context *host_ctxt)
-{
-	DECLARE_REG(u64, func_id, host_ctxt, 0);
-
-	return func_id;
-}
+#define	is_psci_0_1(what, func_id)					\
+	(kvm_host_psci_config.psci_0_1_ ## what ## _implemented &&	\
+	 (func_id) == kvm_host_psci_config.function_ids_0_1.what)
 
 static bool is_psci_0_1_call(u64 func_id)
 {
-	return (func_id == kvm_host_psci_0_1_function_ids.cpu_suspend) ||
-	       (func_id == kvm_host_psci_0_1_function_ids.cpu_on) ||
-	       (func_id == kvm_host_psci_0_1_function_ids.cpu_off) ||
-	       (func_id == kvm_host_psci_0_1_function_ids.migrate);
+	return (is_psci_0_1(cpu_suspend, func_id) ||
+		is_psci_0_1(cpu_on, func_id) ||
+		is_psci_0_1(cpu_off, func_id) ||
+		is_psci_0_1(migrate, func_id));
 }
 
 static bool is_psci_0_2_call(u64 func_id)
@@ -69,16 +62,6 @@ static bool is_psci_0_2_call(u64 func_id)
 	       (PSCI_0_2_FN64(0) <= func_id && func_id <= PSCI_0_2_FN64(31));
 }
 
-static bool is_psci_call(u64 func_id)
-{
-	switch (kvm_host_psci_version) {
-	case PSCI_VERSION(0, 1):
-		return is_psci_0_1_call(func_id);
-	default:
-		return is_psci_0_2_call(func_id);
-	}
-}
-
 static unsigned long psci_call(unsigned long fn, unsigned long arg0,
 			       unsigned long arg1, unsigned long arg2)
 {
@@ -248,15 +231,14 @@ asmlinkage void __noreturn kvm_host_psci_cpu_entry(bool is_cpu_on)
 
 static unsigned long psci_0_1_handler(u64 func_id, struct kvm_cpu_context *host_ctxt)
 {
-	if ((func_id == kvm_host_psci_0_1_function_ids.cpu_off) ||
-	    (func_id == kvm_host_psci_0_1_function_ids.migrate))
+	if (is_psci_0_1(cpu_off, func_id) || is_psci_0_1(migrate, func_id))
 		return psci_forward(host_ctxt);
-	else if (func_id == kvm_host_psci_0_1_function_ids.cpu_on)
+	if (is_psci_0_1(cpu_on, func_id))
 		return psci_cpu_on(func_id, host_ctxt);
-	else if (func_id == kvm_host_psci_0_1_function_ids.cpu_suspend)
+	if (is_psci_0_1(cpu_suspend, func_id))
 		return psci_cpu_suspend(func_id, host_ctxt);
-	else
-		return PSCI_RET_NOT_SUPPORTED;
+
+	return PSCI_RET_NOT_SUPPORTED;
 }
 
 static unsigned long psci_0_2_handler(u64 func_id, struct kvm_cpu_context *host_ctxt)
@@ -298,20 +280,23 @@ static unsigned long psci_1_0_handler(u64 func_id, struct kvm_cpu_context *host_
 
 bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt)
 {
-	u64 func_id = get_psci_func_id(host_ctxt);
+	DECLARE_REG(u64, func_id, host_ctxt, 0);
 	unsigned long ret;
 
-	if (!is_psci_call(func_id))
-		return false;
-
-	switch (kvm_host_psci_version) {
+	switch (kvm_host_psci_config.version) {
 	case PSCI_VERSION(0, 1):
+		if (!is_psci_0_1_call(func_id))
+			return false;
 		ret = psci_0_1_handler(func_id, host_ctxt);
 		break;
 	case PSCI_VERSION(0, 2):
+		if (!is_psci_0_2_call(func_id))
+			return false;
 		ret = psci_0_2_handler(func_id, host_ctxt);
 		break;
 	default:
+		if (!is_psci_0_2_call(func_id))
+			return false;
 		ret = psci_1_0_handler(func_id, host_ctxt);
 		break;
 	}

arch/arm64/kvm/pmu-emul.c

@@ -850,8 +850,6 @@ int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
 		   return -EINVAL;
 	}
 
-	kvm_pmu_vcpu_reset(vcpu);
-
 	return 0;
 }
 

arch/arm64/kvm/sys_regs.c

@@ -594,6 +594,10 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	u64 pmcr, val;
 
+	/* No PMU available, PMCR_EL0 may UNDEF... */
+	if (!kvm_arm_support_pmu_v3())
+		return;
+
 	pmcr = read_sysreg(pmcr_el0);
 	/*
 	 * Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) are reset to UNKNOWN
@@ -919,7 +923,7 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 
 #define reg_to_encoding(x)						\
 	sys_reg((u32)(x)->Op0, (u32)(x)->Op1,				\
-		(u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2);
+		(u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2)
 
 /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
 #define DBG_BCR_BVR_WCR_WVR_EL1(n)					\