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

Pull kvm fixes from Paolo Bonzini:
"RISC-V:

   - Fix a race condition in updating external interrupt for
     trap-n-emulated IMSIC swfile

   - Fix print_reg defaults in get-reg-list selftest

  ARM:

   - Ensure a vCPU's redistributor is unregistered from the MMIO bus if
     vCPU creation fails

   - Fix building KVM selftests for arm64 from the top-level Makefile

  x86:

   - Fix breakage for SEV-ES guests that use XSAVES

  Selftests:

   - Fix bad use of strcat(), by not using strcat() at all"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: SEV: Do not intercept accesses to MSR_IA32_XSS for SEV-ES guests
  KVM: selftests: Fix dynamic generation of configuration names
  RISCV: KVM: update external interrupt atomically for IMSIC swfile
  KVM: riscv: selftests: Fix get-reg-list print_reg defaults
  KVM: selftests: Ensure sysreg-defs.h is generated at the expected path
  KVM: Convert comment into an assertion in kvm_io_bus_register_dev()
  KVM: arm64: vgic: Ensure that slots_lock is held in vgic_register_all_redist_iodevs()
  KVM: arm64: vgic: Force vcpu vgic teardown on vcpu destroy
  KVM: arm64: vgic: Add a non-locking primitive for kvm_vgic_vcpu_destroy()
  KVM: arm64: vgic: Simplify kvm_vgic_destroy()

Author: torvalds

arch/arm64/kvm/arm.c

@@ -410,7 +410,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
 	kvm_timer_vcpu_terminate(vcpu);
 	kvm_pmu_vcpu_destroy(vcpu);
-
+	kvm_vgic_vcpu_destroy(vcpu);
 	kvm_arm_vcpu_destroy(vcpu);
 }
 

arch/arm64/kvm/vgic/vgic-init.c

@@ -368,7 +368,7 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm)
 		vgic_v4_teardown(kvm);
 }
 
-void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
+static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 
@@ -379,29 +379,39 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
 	vgic_flush_pending_lpis(vcpu);
 
 	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
-	vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
+	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
+		vgic_unregister_redist_iodev(vcpu);
+		vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
+	}
 }
 
-static void __kvm_vgic_destroy(struct kvm *kvm)
+void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+
+	mutex_lock(&kvm->slots_lock);
+	__kvm_vgic_vcpu_destroy(vcpu);
+	mutex_unlock(&kvm->slots_lock);
+}
+
+void kvm_vgic_destroy(struct kvm *kvm)
 {
 	struct kvm_vcpu *vcpu;
 	unsigned long i;
 
-	lockdep_assert_held(&kvm->arch.config_lock);
+	mutex_lock(&kvm->slots_lock);
 
 	vgic_debug_destroy(kvm);
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
-		kvm_vgic_vcpu_destroy(vcpu);
+		__kvm_vgic_vcpu_destroy(vcpu);
+
+	mutex_lock(&kvm->arch.config_lock);
 
 	kvm_vgic_dist_destroy(kvm);
-}
 
-void kvm_vgic_destroy(struct kvm *kvm)
-{
-	mutex_lock(&kvm->arch.config_lock);
-	__kvm_vgic_destroy(kvm);
 	mutex_unlock(&kvm->arch.config_lock);
+	mutex_unlock(&kvm->slots_lock);
 }
 
 /**
@@ -469,25 +479,26 @@ int kvm_vgic_map_resources(struct kvm *kvm)
 		type = VGIC_V3;
 	}
 
-	if (ret) {
-		__kvm_vgic_destroy(kvm);
+	if (ret)
 		goto out;
-	}
+
 	dist->ready = true;
 	dist_base = dist->vgic_dist_base;
 	mutex_unlock(&kvm->arch.config_lock);
 
 	ret = vgic_register_dist_iodev(kvm, dist_base, type);
-	if (ret) {
+	if (ret)
 		kvm_err("Unable to register VGIC dist MMIO regions\n");
-		kvm_vgic_destroy(kvm);
-	}
-	mutex_unlock(&kvm->slots_lock);
-	return ret;
 
+	goto out_slots;
 out:
 	mutex_unlock(&kvm->arch.config_lock);
+out_slots:
 	mutex_unlock(&kvm->slots_lock);
+
+	if (ret)
+		kvm_vgic_destroy(kvm);
+
 	return ret;
 }
 

arch/arm64/kvm/vgic/vgic-mmio-v3.c

@@ -820,7 +820,7 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
-static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu)
+void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu)
 {
 	struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev;
 
@@ -833,6 +833,8 @@ static int vgic_register_all_redist_iodevs(struct kvm *kvm)
 	unsigned long c;
 	int ret = 0;
 
+	lockdep_assert_held(&kvm->slots_lock);
+
 	kvm_for_each_vcpu(c, vcpu, kvm) {
 		ret = vgic_register_redist_iodev(vcpu);
 		if (ret)

arch/arm64/kvm/vgic/vgic.h

@@ -241,6 +241,7 @@ int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq);
 int vgic_v3_save_pending_tables(struct kvm *kvm);
 int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count);
 int vgic_register_redist_iodev(struct kvm_vcpu *vcpu);
+void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu);
 bool vgic_v3_check_base(struct kvm *kvm);
 
 void vgic_v3_load(struct kvm_vcpu *vcpu);

arch/riscv/kvm/aia_imsic.c

@@ -55,6 +55,7 @@ struct imsic {
 	/* IMSIC SW-file */
 	struct imsic_mrif *swfile;
 	phys_addr_t swfile_pa;
+	spinlock_t swfile_extirq_lock;
 };
 
 #define imsic_vs_csr_read(__c)			\
@@ -613,12 +614,23 @@ static void imsic_swfile_extirq_update(struct kvm_vcpu *vcpu)
 {
 	struct imsic *imsic = vcpu->arch.aia_context.imsic_state;
 	struct imsic_mrif *mrif = imsic->swfile;
+	unsigned long flags;
+
+	/*
+	 * The critical section is necessary during external interrupt
+	 * updates to avoid the risk of losing interrupts due to potential
+	 * interruptions between reading topei and updating pending status.
+	 */
+
+	spin_lock_irqsave(&imsic->swfile_extirq_lock, flags);
 
 	if (imsic_mrif_atomic_read(mrif, &mrif->eidelivery) &&
 	    imsic_mrif_topei(mrif, imsic->nr_eix, imsic->nr_msis))
 		kvm_riscv_vcpu_set_interrupt(vcpu, IRQ_VS_EXT);
 	else
 		kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_EXT);
+
+	spin_unlock_irqrestore(&imsic->swfile_extirq_lock, flags);
 }
 
 static void imsic_swfile_read(struct kvm_vcpu *vcpu, bool clear,
@@ -1039,6 +1051,7 @@ int kvm_riscv_vcpu_aia_imsic_init(struct kvm_vcpu *vcpu)
 	}
 	imsic->swfile = page_to_virt(swfile_page);
 	imsic->swfile_pa = page_to_phys(swfile_page);
+	spin_lock_init(&imsic->swfile_extirq_lock);
 
 	/* Setup IO device */
 	kvm_iodevice_init(&imsic->iodev, &imsic_iodoev_ops);

arch/x86/kvm/svm/sev.c

@@ -2972,6 +2972,25 @@ static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm)
 
 		set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux);
 	}
+
+	/*
+	 * For SEV-ES, accesses to MSR_IA32_XSS should not be intercepted if
+	 * the host/guest supports its use.
+	 *
+	 * guest_can_use() checks a number of requirements on the host/guest to
+	 * ensure that MSR_IA32_XSS is available, but it might report true even
+	 * if X86_FEATURE_XSAVES isn't configured in the guest to ensure host
+	 * MSR_IA32_XSS is always properly restored. For SEV-ES, it is better
+	 * to further check that the guest CPUID actually supports
+	 * X86_FEATURE_XSAVES so that accesses to MSR_IA32_XSS by misbehaved
+	 * guests will still get intercepted and caught in the normal
+	 * kvm_emulate_rdmsr()/kvm_emulated_wrmsr() paths.
+	 */
+	if (guest_can_use(vcpu, X86_FEATURE_XSAVES) &&
+	    guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
+		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 1, 1);
+	else
+		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 0, 0);
 }
 
 void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm)

arch/x86/kvm/svm/svm.c

@@ -103,6 +103,7 @@ static const struct svm_direct_access_msrs {
 	{ .index = MSR_IA32_LASTBRANCHTOIP,		.always = false },
 	{ .index = MSR_IA32_LASTINTFROMIP,		.always = false },
 	{ .index = MSR_IA32_LASTINTTOIP,		.always = false },
+	{ .index = MSR_IA32_XSS,			.always = false },
 	{ .index = MSR_EFER,				.always = false },
 	{ .index = MSR_IA32_CR_PAT,			.always = false },
 	{ .index = MSR_AMD64_SEV_ES_GHCB,		.always = true  },

arch/x86/kvm/svm/svm.h

@@ -30,7 +30,7 @@
 #define	IOPM_SIZE PAGE_SIZE * 3
 #define	MSRPM_SIZE PAGE_SIZE * 2
 
-#define MAX_DIRECT_ACCESS_MSRS	46
+#define MAX_DIRECT_ACCESS_MSRS	47
 #define MSRPM_OFFSETS	32
 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
 extern bool npt_enabled;

tools/testing/selftests/kvm/Makefile

@@ -17,16 +17,6 @@ else
 	ARCH_DIR := $(ARCH)
 endif
 
-ifeq ($(ARCH),arm64)
-tools_dir := $(top_srcdir)/tools
-arm64_tools_dir := $(tools_dir)/arch/arm64/tools/
-GEN_HDRS := $(top_srcdir)/tools/arch/arm64/include/generated/
-CFLAGS += -I$(GEN_HDRS)
-
-$(GEN_HDRS): $(wildcard $(arm64_tools_dir)/*)
-	$(MAKE) -C $(arm64_tools_dir) O=$(tools_dir)
-endif
-
 LIBKVM += lib/assert.c
 LIBKVM += lib/elf.c
 LIBKVM += lib/guest_modes.c
@@ -234,6 +224,22 @@ CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
 ifeq ($(ARCH),s390)
 	CFLAGS += -march=z10
 endif
+ifeq ($(ARCH),arm64)
+tools_dir := $(top_srcdir)/tools
+arm64_tools_dir := $(tools_dir)/arch/arm64/tools/
+
+ifneq ($(abs_objdir),)
+arm64_hdr_outdir := $(abs_objdir)/tools/
+else
+arm64_hdr_outdir := $(tools_dir)/
+endif
+
+GEN_HDRS := $(arm64_hdr_outdir)arch/arm64/include/generated/
+CFLAGS += -I$(GEN_HDRS)
+
+$(GEN_HDRS): $(wildcard $(arm64_tools_dir)/*)
+	$(MAKE) -C $(arm64_tools_dir) OUTPUT=$(arm64_hdr_outdir)
+endif
 
 no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \
         $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)

tools/testing/selftests/kvm/get-reg-list.c

@@ -71,11 +71,12 @@ static const char *config_name(struct vcpu_reg_list *c)
 	for_each_sublist(c, s) {
 		if (!strcmp(s->name, "base"))
 			continue;
-		strcat(c->name + len, s->name);
-		len += strlen(s->name) + 1;
-		c->name[len - 1] = '+';
+		if (len)
+			c->name[len++] = '+';
+		strcpy(c->name + len, s->name);
+		len += strlen(s->name);
 	}
-	c->name[len - 1] = '\0';
+	c->name[len] = '\0';
 
 	return c->name;
 }