* ARM/ARM64 locking fixes

* x86 fixes: PCID, UMIP, locking
 * Improved support for recent Windows version that have a 2048 Hz
 APIC timer.
 * Rename KVM_HINTS_DEDICATED CPUID bit to KVM_HINTS_REALTIME
 * Better behaved selftests.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQEcBAABAgAGBQJa/bkTAAoJEL/70l94x66Dzf8IAJ1GqtXi0CNbq8MvU4QIqw0L
 HLIRoe/QgkTeTUa2fwirEuu5I+/wUyPvy5sAIsn/F5eiZM7nciLm+fYzw6F2uPIm
 lSCqKpVwmh8dPl1SBaqPnTcB1HPVwcCgc2SF9Ph7yZCUwFUtoeUuPj8v6Qy6y21g
 jfobHFZa3MrFgi7kPxOXSrC1qxuNJL9yLB5mwCvCK/K7jj2nrGJkLLDuzgReCqvz
 isOdpof3hz8whXDQG5cTtybBgE9veym4YqJY8R5ANXBKqbFlhaNF1T3xXrdPMISZ
 7bsGgkhYEOqeQsPrFwzAIiFxe2DogFwkn1BcvJ1B+duXrayt5CBnDPRB6Yxg00M=
 =H0d0
 -----END PGP SIGNATURE-----

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

Pull kvm fixes from Paolo Bonzini:

 - ARM/ARM64 locking fixes

 - x86 fixes: PCID, UMIP, locking

 - improved support for recent Windows version that have a 2048 Hz APIC
   timer

 - rename KVM_HINTS_DEDICATED CPUID bit to KVM_HINTS_REALTIME

 - better behaved selftests

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  kvm: rename KVM_HINTS_DEDICATED to KVM_HINTS_REALTIME
  KVM: arm/arm64: VGIC/ITS save/restore: protect kvm_read_guest() calls
  KVM: arm/arm64: VGIC/ITS: protect kvm_read_guest() calls with SRCU lock
  KVM: arm/arm64: VGIC/ITS: Promote irq_lock() in update_affinity
  KVM: arm/arm64: Properly protect VGIC locks from IRQs
  KVM: X86: Lower the default timer frequency limit to 200us
  KVM: vmx: update sec exec controls for UMIP iff emulating UMIP
  kvm: x86: Suppress CR3_PCID_INVD bit only when PCIDs are enabled
  KVM: selftests: exit with 0 status code when tests cannot be run
  KVM: hyperv: idr_find needs RCU protection
  x86: Delay skip of emulated hypercall instruction
  KVM: Extend MAX_IRQ_ROUTES to 4096 for all archs

Documentation/virtual/kvm/cpuid.txt

@@ -72,8 +72,8 @@ KVM_FEATURE_CLOCKSOURCE_STABLE_BIT ||    24 || host will warn if no guest-side
 
 flag                               || value || meaning
 ==================================================================================
-KVM_HINTS_DEDICATED                ||     0 || guest checks this feature bit to
+KVM_HINTS_REALTIME                 ||     0 || guest checks this feature bit to
-                                   ||       || determine if there is vCPU pinning
+                                   ||       || determine that vCPUs are never
-                                   ||       || and there is no vCPU over-commitment,
+                                   ||       || preempted for an unlimited time,
                                    ||       || allowing optimizations
 ----------------------------------------------------------------------------------

arch/arm/include/asm/kvm_mmu.h

@@ -309,6 +309,22 @@ static inline unsigned int kvm_get_vmid_bits(void)
 	return 8;
 }
 
+/*
+ * We are not in the kvm->srcu critical section most of the time, so we take
+ * the SRCU read lock here. Since we copy the data from the user page, we
+ * can immediately drop the lock again.
+ */
+static inline int kvm_read_guest_lock(struct kvm *kvm,
+				      gpa_t gpa, void *data, unsigned long len)
+{
+	int srcu_idx = srcu_read_lock(&kvm->srcu);
+	int ret = kvm_read_guest(kvm, gpa, data, len);
+
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+	return ret;
+}
+
 static inline void *kvm_get_hyp_vector(void)
 {
 	return kvm_ksym_ref(__kvm_hyp_vector);

arch/arm64/include/asm/kvm_mmu.h

@@ -360,6 +360,22 @@ static inline unsigned int kvm_get_vmid_bits(void)
 	return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8;
 }
 
+/*
+ * We are not in the kvm->srcu critical section most of the time, so we take
+ * the SRCU read lock here. Since we copy the data from the user page, we
+ * can immediately drop the lock again.
+ */
+static inline int kvm_read_guest_lock(struct kvm *kvm,
+				      gpa_t gpa, void *data, unsigned long len)
+{
+	int srcu_idx = srcu_read_lock(&kvm->srcu);
+	int ret = kvm_read_guest(kvm, gpa, data, len);
+
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+	return ret;
+}
+
 #ifdef CONFIG_KVM_INDIRECT_VECTORS
 /*
  * EL2 vectors can be mapped and rerouted in a number of ways,

arch/x86/include/uapi/asm/kvm_para.h

@@ -29,7 +29,7 @@
 #define KVM_FEATURE_PV_TLB_FLUSH	9
 #define KVM_FEATURE_ASYNC_PF_VMEXIT	10
 
-#define KVM_HINTS_DEDICATED      0
+#define KVM_HINTS_REALTIME      0
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.

arch/x86/kernel/kvm.c

@@ -457,7 +457,7 @@ static void __init sev_map_percpu_data(void)
 static void __init kvm_smp_prepare_cpus(unsigned int max_cpus)
 {
 	native_smp_prepare_cpus(max_cpus);
-	if (kvm_para_has_hint(KVM_HINTS_DEDICATED))
+	if (kvm_para_has_hint(KVM_HINTS_REALTIME))
 		static_branch_disable(&virt_spin_lock_key);
 }
 
@@ -553,7 +553,7 @@ static void __init kvm_guest_init(void)
 	}
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
-	    !kvm_para_has_hint(KVM_HINTS_DEDICATED) &&
+	    !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
 	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME))
 		pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
 
@@ -649,7 +649,7 @@ static __init int kvm_setup_pv_tlb_flush(void)
 	int cpu;
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
-	    !kvm_para_has_hint(KVM_HINTS_DEDICATED) &&
+	    !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
 	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
 		for_each_possible_cpu(cpu) {
 			zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
@@ -745,7 +745,7 @@ void __init kvm_spinlock_init(void)
 	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
 		return;
 
-	if (kvm_para_has_hint(KVM_HINTS_DEDICATED))
+	if (kvm_para_has_hint(KVM_HINTS_REALTIME))
 		return;
 
 	__pv_init_lock_hash();

arch/x86/kvm/hyperv.c

@@ -1265,7 +1265,7 @@ static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
 	struct kvm_run *run = vcpu->run;
 
 	kvm_hv_hypercall_set_result(vcpu, run->hyperv.u.hcall.result);
-	return 1;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param)
@@ -1296,8 +1296,10 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param)
 	if (param & ~KVM_HYPERV_CONN_ID_MASK)
 		return HV_STATUS_INVALID_HYPERCALL_INPUT;
 
-	/* conn_to_evt is protected by vcpu->kvm->srcu */
+	/* the eventfd is protected by vcpu->kvm->srcu, but conn_to_evt isn't */
+	rcu_read_lock();
 	eventfd = idr_find(&vcpu->kvm->arch.hyperv.conn_to_evt, param);
+	rcu_read_unlock();
 	if (!eventfd)
 		return HV_STATUS_INVALID_PORT_ID;
 

arch/x86/kvm/vmx.c

@@ -1494,6 +1494,12 @@ static inline bool cpu_has_vmx_vmfunc(void)
 		SECONDARY_EXEC_ENABLE_VMFUNC;
 }
 
+static bool vmx_umip_emulated(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_DESC;
+}
+
 static inline bool report_flexpriority(void)
 {
 	return flexpriority_enabled;
@@ -4761,14 +4767,16 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	else
 		hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON;
 
-	if ((cr4 & X86_CR4_UMIP) && !boot_cpu_has(X86_FEATURE_UMIP)) {
+	if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) {
-		vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
+		if (cr4 & X86_CR4_UMIP) {
-			      SECONDARY_EXEC_DESC);
+			vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
-		hw_cr4 &= ~X86_CR4_UMIP;
-	} else if (!is_guest_mode(vcpu) ||
-	           !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC))
-		vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
 				SECONDARY_EXEC_DESC);
+			hw_cr4 &= ~X86_CR4_UMIP;
+		} else if (!is_guest_mode(vcpu) ||
+			!nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC))
+			vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+					SECONDARY_EXEC_DESC);
+	}
 
 	if (cr4 & X86_CR4_VMXE) {
 		/*
@@ -9497,12 +9505,6 @@ static bool vmx_xsaves_supported(void)
 		SECONDARY_EXEC_XSAVES;
 }
 
-static bool vmx_umip_emulated(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_DESC;
-}
-
 static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
 {
 	u32 exit_intr_info;

arch/x86/kvm/x86.c

@@ -114,7 +114,7 @@ module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);
 static bool __read_mostly report_ignored_msrs = true;
 module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR);
 
-unsigned int min_timer_period_us = 500;
+unsigned int min_timer_period_us = 200;
 module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
 
 static bool __read_mostly kvmclock_periodic_sync = true;
@@ -843,7 +843,10 @@ EXPORT_SYMBOL_GPL(kvm_set_cr4);
 int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 {
 #ifdef CONFIG_X86_64
-	cr3 &= ~CR3_PCID_INVD;
+	bool pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE);
+
+	if (pcid_enabled)
+		cr3 &= ~CR3_PCID_INVD;
 #endif
 
 	if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) {
@@ -6671,12 +6674,13 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu)
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
-	int op_64_bit, r;
+	int op_64_bit;
 
-	r = kvm_skip_emulated_instruction(vcpu);
+	if (kvm_hv_hypercall_enabled(vcpu->kvm)) {
-
+		if (!kvm_hv_hypercall(vcpu))
-	if (kvm_hv_hypercall_enabled(vcpu->kvm))
+			return 0;
-		return kvm_hv_hypercall(vcpu);
+		goto out;
+	}
 
 	nr = kvm_register_read(vcpu, VCPU_REGS_RAX);
 	a0 = kvm_register_read(vcpu, VCPU_REGS_RBX);
@@ -6697,7 +6701,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 
 	if (kvm_x86_ops->get_cpl(vcpu) != 0) {
 		ret = -KVM_EPERM;
-		goto out;
+		goto out_error;
 	}
 
 	switch (nr) {
@@ -6717,12 +6721,14 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 		ret = -KVM_ENOSYS;
 		break;
 	}
-out:
+out_error:
 	if (!op_64_bit)
 		ret = (u32)ret;
 	kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
+
+out:
 	++vcpu->stat.hypercalls;
-	return r;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);
 

include/linux/kvm_host.h

@@ -1045,13 +1045,7 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)
 
 #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 
-#ifdef CONFIG_S390
+#define KVM_MAX_IRQ_ROUTES 4096 /* might need extension/rework in the future */
-#define KVM_MAX_IRQ_ROUTES 4096 //FIXME: we can have more than that...
-#elif defined(CONFIG_ARM64)
-#define KVM_MAX_IRQ_ROUTES 4096
-#else
-#define KVM_MAX_IRQ_ROUTES 1024
-#endif
 
 bool kvm_arch_can_set_irq_routing(struct kvm *kvm);
 int kvm_set_irq_routing(struct kvm *kvm,

tools/testing/selftests/kvm/Makefile

@@ -15,7 +15,7 @@ LIBKVM += $(LIBKVM_$(UNAME_M))
 
 INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
-CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_HDR_PATH) -Iinclude -I$(<D)
+CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -I..
 
 # After inclusion, $(OUTPUT) is defined and
 # $(TEST_GEN_PROGS) starts with $(OUTPUT)/

tools/testing/selftests/kvm/include/test_util.h

@@ -19,6 +19,7 @@
 #include <errno.h>
 #include <unistd.h>
 #include <fcntl.h>
+#include "kselftest.h"
 
 ssize_t test_write(int fd, const void *buf, size_t count);
 ssize_t test_read(int fd, void *buf, size_t count);

tools/testing/selftests/kvm/lib/kvm_util.c

@@ -50,8 +50,8 @@ int kvm_check_cap(long cap)
 	int kvm_fd;
 
 	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
-	TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i",
+	if (kvm_fd < 0)
-		KVM_DEV_PATH, kvm_fd, errno);
+		exit(KSFT_SKIP);
 
 	ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap);
 	TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n"
@@ -91,8 +91,8 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 
 	vm->mode = mode;
 	kvm_fd = open(KVM_DEV_PATH, perm);
-	TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i",
+	if (kvm_fd < 0)
-		KVM_DEV_PATH, kvm_fd, errno);
+		exit(KSFT_SKIP);
 
 	/* Create VM. */
 	vm->fd = ioctl(kvm_fd, KVM_CREATE_VM, NULL);
@@ -418,8 +418,8 @@ struct kvm_cpuid2 *kvm_get_supported_cpuid(void)
 
 	cpuid = allocate_kvm_cpuid2();
 	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
-	TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i",
+	if (kvm_fd < 0)
-		KVM_DEV_PATH, kvm_fd, errno);
+		exit(KSFT_SKIP);
 
 	ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid);
 	TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n",
@@ -675,8 +675,8 @@ static int vcpu_mmap_sz(void)
 	int dev_fd, ret;
 
 	dev_fd = open(KVM_DEV_PATH, O_RDONLY);
-	TEST_ASSERT(dev_fd >= 0, "%s open %s failed, rc: %i errno: %i",
+	if (dev_fd < 0)
-		__func__, KVM_DEV_PATH, dev_fd, errno);
+		exit(KSFT_SKIP);
 
 	ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL);
 	TEST_ASSERT(ret >= sizeof(struct kvm_run),

tools/testing/selftests/kvm/sync_regs_test.c

@@ -85,6 +85,9 @@ static void compare_vcpu_events(struct kvm_vcpu_events *left,
 {
 }
 
+#define TEST_SYNC_FIELDS   (KVM_SYNC_X86_REGS|KVM_SYNC_X86_SREGS|KVM_SYNC_X86_EVENTS)
+#define INVALID_SYNC_FIELD 0x80000000
+
 int main(int argc, char *argv[])
 {
 	struct kvm_vm *vm;
@@ -98,9 +101,14 @@ int main(int argc, char *argv[])
 	setbuf(stdout, NULL);
 
 	cap = kvm_check_cap(KVM_CAP_SYNC_REGS);
-	TEST_ASSERT((unsigned long)cap == KVM_SYNC_X86_VALID_FIELDS,
+	if ((cap & TEST_SYNC_FIELDS) != TEST_SYNC_FIELDS) {
-		    "KVM_CAP_SYNC_REGS (0x%x) != KVM_SYNC_X86_VALID_FIELDS (0x%lx)\n",
+		fprintf(stderr, "KVM_CAP_SYNC_REGS not supported, skipping test\n");
-		    cap, KVM_SYNC_X86_VALID_FIELDS);
+		exit(KSFT_SKIP);
+	}
+	if ((cap & INVALID_SYNC_FIELD) != 0) {
+		fprintf(stderr, "The \"invalid\" field is not invalid, skipping test\n");
+		exit(KSFT_SKIP);
+	}
 
 	/* Create VM */
 	vm = vm_create_default(VCPU_ID, guest_code);
@@ -108,7 +116,14 @@ int main(int argc, char *argv[])
 	run = vcpu_state(vm, VCPU_ID);
 
 	/* Request reading invalid register set from VCPU. */
-	run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS << 1;
+	run->kvm_valid_regs = INVALID_SYNC_FIELD;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(rv < 0 && errno == EINVAL,
+		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+		    rv);
+	vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0;
+
+	run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
 	rv = _vcpu_run(vm, VCPU_ID);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
 		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
@@ -116,7 +131,14 @@ int main(int argc, char *argv[])
 	vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0;
 
 	/* Request setting invalid register set into VCPU. */
-	run->kvm_dirty_regs = KVM_SYNC_X86_VALID_FIELDS << 1;
+	run->kvm_dirty_regs = INVALID_SYNC_FIELD;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(rv < 0 && errno == EINVAL,
+		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+		    rv);
+	vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0;
+
+	run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
 	rv = _vcpu_run(vm, VCPU_ID);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
 		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
@@ -125,7 +147,7 @@ int main(int argc, char *argv[])
 
 	/* Request and verify all valid register sets. */
 	/* TODO: BUILD TIME CHECK: TEST_ASSERT(KVM_SYNC_X86_NUM_FIELDS != 3); */
-	run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS;
+	run->kvm_valid_regs = TEST_SYNC_FIELDS;
 	rv = _vcpu_run(vm, VCPU_ID);
 	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
 		    "Unexpected exit reason: %u (%s),\n",
@@ -146,7 +168,7 @@ int main(int argc, char *argv[])
 	run->s.regs.sregs.apic_base = 1 << 11;
 	/* TODO run->s.regs.events.XYZ = ABC; */
 
-	run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS;
+	run->kvm_valid_regs = TEST_SYNC_FIELDS;
 	run->kvm_dirty_regs = KVM_SYNC_X86_REGS | KVM_SYNC_X86_SREGS;
 	rv = _vcpu_run(vm, VCPU_ID);
 	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
@@ -172,7 +194,7 @@ int main(int argc, char *argv[])
 	/* Clear kvm_dirty_regs bits, verify new s.regs values are
 	 * overwritten with existing guest values.
 	 */
-	run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS;
+	run->kvm_valid_regs = TEST_SYNC_FIELDS;
 	run->kvm_dirty_regs = 0;
 	run->s.regs.regs.r11 = 0xDEADBEEF;
 	rv = _vcpu_run(vm, VCPU_ID);
@@ -211,7 +233,7 @@ int main(int argc, char *argv[])
 	 * with kvm_sync_regs values.
 	 */
 	run->kvm_valid_regs = 0;
-	run->kvm_dirty_regs = KVM_SYNC_X86_VALID_FIELDS;
+	run->kvm_dirty_regs = TEST_SYNC_FIELDS;
 	run->s.regs.regs.r11 = 0xBBBB;
 	rv = _vcpu_run(vm, VCPU_ID);
 	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,

tools/testing/selftests/kvm/vmx_tsc_adjust_test.c

@@ -189,8 +189,8 @@ int main(int argc, char *argv[])
 	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
 
 	if (!(entry->ecx & CPUID_VMX)) {
-		printf("nested VMX not enabled, skipping test");
+		fprintf(stderr, "nested VMX not enabled, skipping test\n");
-		return 0;
+		exit(KSFT_SKIP);
 	}
 
 	vm = vm_create_default_vmx(VCPU_ID, (void *) l1_guest_code);

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

@@ -211,6 +211,7 @@ static int vgic_debug_show(struct seq_file *s, void *v)
 	struct vgic_state_iter *iter = (struct vgic_state_iter *)v;
 	struct vgic_irq *irq;
 	struct kvm_vcpu *vcpu = NULL;
+	unsigned long flags;
 
 	if (iter->dist_id == 0) {
 		print_dist_state(s, &kvm->arch.vgic);
@@ -227,9 +228,9 @@ static int vgic_debug_show(struct seq_file *s, void *v)
 		irq = &kvm->arch.vgic.spis[iter->intid - VGIC_NR_PRIVATE_IRQS];
 	}
 
-	spin_lock(&irq->irq_lock);
+	spin_lock_irqsave(&irq->irq_lock, flags);
 	print_irq_state(s, irq, vcpu);
-	spin_unlock(&irq->irq_lock);
+	spin_unlock_irqrestore(&irq->irq_lock, flags);
 
 	return 0;
 }

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

@@ -52,6 +52,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intid), *oldirq;
+	unsigned long flags;
 	int ret;
 
 	/* In this case there is no put, since we keep the reference. */
@@ -71,7 +72,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
 	irq->intid = intid;
 	irq->target_vcpu = vcpu;
 
-	spin_lock(&dist->lpi_list_lock);
+	spin_lock_irqsave(&dist->lpi_list_lock, flags);
 
 	/*
 	 * There could be a race with another vgic_add_lpi(), so we need to
@@ -99,7 +100,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
 	dist->lpi_list_count++;
 
 out_unlock:
-	spin_unlock(&dist->lpi_list_lock);
+	spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
 
 	/*
 	 * We "cache" the configuration table entries in our struct vgic_irq's.
@@ -280,8 +281,8 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
 	int ret;
 	unsigned long flags;
 
-	ret = kvm_read_guest(kvm, propbase + irq->intid - GIC_LPI_OFFSET,
+	ret = kvm_read_guest_lock(kvm, propbase + irq->intid - GIC_LPI_OFFSET,
-			     &prop, 1);
+				  &prop, 1);
 
 	if (ret)
 		return ret;
@@ -315,6 +316,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	struct vgic_irq *irq;
+	unsigned long flags;
 	u32 *intids;
 	int irq_count, i = 0;
 
@@ -330,7 +332,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
 	if (!intids)
 		return -ENOMEM;
 
-	spin_lock(&dist->lpi_list_lock);
+	spin_lock_irqsave(&dist->lpi_list_lock, flags);
 	list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
 		if (i == irq_count)
 			break;
@@ -339,7 +341,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
 			continue;
 		intids[i++] = irq->intid;
 	}
-	spin_unlock(&dist->lpi_list_lock);
+	spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
 
 	*intid_ptr = intids;
 	return i;
@@ -348,10 +350,11 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
 static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu)
 {
 	int ret = 0;
+	unsigned long flags;
 
-	spin_lock(&irq->irq_lock);
+	spin_lock_irqsave(&irq->irq_lock, flags);
 	irq->target_vcpu = vcpu;
-	spin_unlock(&irq->irq_lock);
+	spin_unlock_irqrestore(&irq->irq_lock, flags);
 
 	if (irq->hw) {
 		struct its_vlpi_map map;
@@ -441,8 +444,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
 		 * this very same byte in the last iteration. Reuse that.
 		 */
 		if (byte_offset != last_byte_offset) {
-			ret = kvm_read_guest(vcpu->kvm, pendbase + byte_offset,
+			ret = kvm_read_guest_lock(vcpu->kvm,
-					     &pendmask, 1);
+						  pendbase + byte_offset,
+						  &pendmask, 1);
 			if (ret) {
 				kfree(intids);
 				return ret;
@@ -786,7 +790,7 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id,
 		return false;
 
 	/* Each 1st level entry is represented by a 64-bit value. */
-	if (kvm_read_guest(its->dev->kvm,
+	if (kvm_read_guest_lock(its->dev->kvm,
 			   BASER_ADDRESS(baser) + index * sizeof(indirect_ptr),
 			   &indirect_ptr, sizeof(indirect_ptr)))
 		return false;
@@ -1367,8 +1371,8 @@ static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its)
 	cbaser = CBASER_ADDRESS(its->cbaser);
 
 	while (its->cwriter != its->creadr) {
-		int ret = kvm_read_guest(kvm, cbaser + its->creadr,
+		int ret = kvm_read_guest_lock(kvm, cbaser + its->creadr,
-					 cmd_buf, ITS_CMD_SIZE);
+					      cmd_buf, ITS_CMD_SIZE);
 		/*
 		 * If kvm_read_guest() fails, this could be due to the guest
 		 * programming a bogus value in CBASER or something else going
@@ -1893,7 +1897,7 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, int esz,
 		int next_offset;
 		size_t byte_offset;
 
-		ret = kvm_read_guest(kvm, gpa, entry, esz);
+		ret = kvm_read_guest_lock(kvm, gpa, entry, esz);
 		if (ret)
 			return ret;
 
@@ -2263,7 +2267,7 @@ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz)
 	int ret;
 
 	BUG_ON(esz > sizeof(val));
-	ret = kvm_read_guest(kvm, gpa, &val, esz);
+	ret = kvm_read_guest_lock(kvm, gpa, &val, esz);
 	if (ret)
 		return ret;
 	val = le64_to_cpu(val);

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

@@ -344,7 +344,7 @@ retry:
 	bit_nr = irq->intid % BITS_PER_BYTE;
 	ptr = pendbase + byte_offset;
 
-	ret = kvm_read_guest(kvm, ptr, &val, 1);
+	ret = kvm_read_guest_lock(kvm, ptr, &val, 1);
 	if (ret)
 		return ret;
 
@@ -397,7 +397,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
 		ptr = pendbase + byte_offset;
 
 		if (byte_offset != last_byte_offset) {
-			ret = kvm_read_guest(kvm, ptr, &val, 1);
+			ret = kvm_read_guest_lock(kvm, ptr, &val, 1);
 			if (ret)
 				return ret;
 			last_byte_offset = byte_offset;

virt/kvm/arm/vgic/vgic.c

@@ -43,9 +43,13 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = {
  * kvm->lock (mutex)
  *   its->cmd_lock (mutex)
  *     its->its_lock (mutex)
- *       vgic_cpu->ap_list_lock
+ *       vgic_cpu->ap_list_lock		must be taken with IRQs disabled
- *         kvm->lpi_list_lock
+ *         kvm->lpi_list_lock		must be taken with IRQs disabled
- *           vgic_irq->irq_lock
+ *           vgic_irq->irq_lock		must be taken with IRQs disabled
+ *
+ * As the ap_list_lock might be taken from the timer interrupt handler,
+ * we have to disable IRQs before taking this lock and everything lower
+ * than it.
  *
  * If you need to take multiple locks, always take the upper lock first,
  * then the lower ones, e.g. first take the its_lock, then the irq_lock.
@@ -72,8 +76,9 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	struct vgic_irq *irq = NULL;
+	unsigned long flags;
 
-	spin_lock(&dist->lpi_list_lock);
+	spin_lock_irqsave(&dist->lpi_list_lock, flags);
 
 	list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
 		if (irq->intid != intid)
@@ -89,7 +94,7 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid)
 	irq = NULL;
 
 out_unlock:
-	spin_unlock(&dist->lpi_list_lock);
+	spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
 
 	return irq;
 }
@@ -134,19 +139,20 @@ static void vgic_irq_release(struct kref *ref)
 void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
+	unsigned long flags;
 
 	if (irq->intid < VGIC_MIN_LPI)
 		return;
 
-	spin_lock(&dist->lpi_list_lock);
+	spin_lock_irqsave(&dist->lpi_list_lock, flags);
 	if (!kref_put(&irq->refcount, vgic_irq_release)) {
-		spin_unlock(&dist->lpi_list_lock);
+		spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
 		return;
 	};
 
 	list_del(&irq->lpi_list);
 	dist->lpi_list_count--;
-	spin_unlock(&dist->lpi_list_lock);
+	spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
 
 	kfree(irq);
 }