Fixes for interrupt controller emulation in ARM/ARM64 and x86, plus a one-liner

x86 KVM guest fix.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQEcBAABAgAGBQJZ/fZuAAoJEL/70l94x66DHVkH/i99gyP/BoFaNfooesXpy89o
 VcjuHzp4XYvUmhP1rCGYqYQEVZYrgsqKAsxL5cyN1nF5SWxebpM8cD96yM7lQx2Y
 Ap5rxYWldn41ZmRRLQzCRKgwPG+V+yMlVTDM8FG/PKJyRTG7fMUEN6IBlRZF2yZr
 DNmy2s//JafEUL3TDq2IXCvfZ1d5VEsCfI2xiYsIzQxwKZ1bHFNqbTqWJZr3Xns1
 xL9e0VjMtNaGtyyCs0ZDjco3kAVQp58Q5+BhnL4/P+uqThjFDrpjQ3RmF0mtC95n
 TKQuUP7QpLUoq74RwHa8tP4IpWj2EZLjefOw/s1Uv2XtieJrRmNIHT0OOGBj9O8=
 =uYvL
 -----END PGP SIGNATURE-----

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

Pull KVM fixes from Paolo Bonzini:
 "Fixes for interrupt controller emulation in ARM/ARM64 and x86, plus a
  one-liner x86 KVM guest fix"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: Update APICv on APIC reset
  KVM: VMX: Do not fully reset PI descriptor on vCPU reset
  kvm: Return -ENODEV from update_persistent_clock
  KVM: arm/arm64: vgic-its: Check GITS_BASER Valid bit before saving tables
  KVM: arm/arm64: vgic-its: Check CBASER/BASER validity before enabling the ITS
  KVM: arm/arm64: vgic-its: Fix vgic_its_restore_collection_table returned value
  KVM: arm/arm64: vgic-its: Fix return value for device table restore
  arm/arm64: kvm: Disable branch profiling in HYP code
  arm/arm64: kvm: Move initialization completion message
  arm/arm64: KVM: set right LR register value for 32 bit guest when inject abort
  KVM: arm64: its: Fix missing dynamic allocation check in scan_its_table

arch/arm/kvm/emulate.c

@@ -227,7 +227,7 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu)
 	u32 return_offset = (is_thumb) ? 2 : 4;
 
 	kvm_update_psr(vcpu, UND_MODE);
-	*vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) - return_offset;
+	*vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
 
 	/* Branch to exception vector */
 	*vcpu_pc(vcpu) = exc_vector_base(vcpu) + vect_offset;
@@ -239,10 +239,8 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu)
  */
 static void inject_abt(struct kvm_vcpu *vcpu, bool is_pabt, unsigned long addr)
 {
-	unsigned long cpsr = *vcpu_cpsr(vcpu);
-	bool is_thumb = (cpsr & PSR_T_BIT);
 	u32 vect_offset;
-	u32 return_offset = (is_thumb) ? 4 : 0;
+	u32 return_offset = (is_pabt) ? 4 : 8;
 	bool is_lpae;
 
 	kvm_update_psr(vcpu, ABT_MODE);

arch/arm/kvm/hyp/Makefile

@@ -3,7 +3,7 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
-ccflags-y += -fno-stack-protector
+ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING
 
 KVM=../../../../virt/kvm
 

arch/arm64/kvm/hyp/Makefile

@@ -3,7 +3,7 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
-ccflags-y += -fno-stack-protector
+ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING
 
 KVM=../../../../virt/kvm
 

arch/arm64/kvm/inject_fault.c

@@ -33,12 +33,26 @@
 #define LOWER_EL_AArch64_VECTOR		0x400
 #define LOWER_EL_AArch32_VECTOR		0x600
 
+/*
+ * Table taken from ARMv8 ARM DDI0487B-B, table G1-10.
+ */
+static const u8 return_offsets[8][2] = {
+	[0] = { 0, 0 },		/* Reset, unused */
+	[1] = { 4, 2 },		/* Undefined */
+	[2] = { 0, 0 },		/* SVC, unused */
+	[3] = { 4, 4 },		/* Prefetch abort */
+	[4] = { 8, 8 },		/* Data abort */
+	[5] = { 0, 0 },		/* HVC, unused */
+	[6] = { 4, 4 },		/* IRQ, unused */
+	[7] = { 4, 4 },		/* FIQ, unused */
+};
+
 static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 {
 	unsigned long cpsr;
 	unsigned long new_spsr_value = *vcpu_cpsr(vcpu);
 	bool is_thumb = (new_spsr_value & COMPAT_PSR_T_BIT);
-	u32 return_offset = (is_thumb) ? 4 : 0;
+	u32 return_offset = return_offsets[vect_offset >> 2][is_thumb];
 	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
 
 	cpsr = mode | COMPAT_PSR_I_BIT;

arch/x86/kernel/kvmclock.c

@@ -79,7 +79,7 @@ static void kvm_get_wallclock(struct timespec *now)
 
 static int kvm_set_wallclock(const struct timespec *now)
 {
-	return -1;
+	return -ENODEV;
 }
 
 static u64 kvm_clock_read(void)

arch/x86/kvm/lapic.c

@@ -1992,6 +1992,11 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 				vcpu->arch.apic_base | MSR_IA32_APICBASE_BSP);
 	vcpu->arch.pv_eoi.msr_val = 0;
 	apic_update_ppr(apic);
+	if (vcpu->arch.apicv_active) {
+		kvm_x86_ops->apicv_post_state_restore(vcpu);
+		kvm_x86_ops->hwapic_irr_update(vcpu, -1);
+		kvm_x86_ops->hwapic_isr_update(vcpu, -1);
+	}
 
 	vcpu->arch.apic_arb_prio = 0;
 	vcpu->arch.apic_attention = 0;

arch/x86/kvm/vmx.c

@@ -5619,9 +5619,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 
 	kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
 
-	if (kvm_vcpu_apicv_active(vcpu))
-		memset(&vmx->pi_desc, 0, sizeof(struct pi_desc));
-
 	if (vmx->vpid != 0)
 		vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
 

virt/kvm/arm/arm.c

@@ -1326,21 +1326,12 @@ static void teardown_hyp_mode(void)
 {
 	int cpu;
 
-	if (is_kernel_in_hyp_mode())
-		return;
-
 	free_hyp_pgds();
 	for_each_possible_cpu(cpu)
 		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
 	hyp_cpu_pm_exit();
 }
 
-static int init_vhe_mode(void)
-{
-	kvm_info("VHE mode initialized successfully\n");
-	return 0;
-}
-
 /**
  * Inits Hyp-mode on all online CPUs
  */
@@ -1421,8 +1412,6 @@ static int init_hyp_mode(void)
 		}
 	}
 
-	kvm_info("Hyp mode initialized successfully\n");
-
 	return 0;
 
 out_err:
@@ -1456,6 +1445,7 @@ int kvm_arch_init(void *opaque)
 {
 	int err;
 	int ret, cpu;
+	bool in_hyp_mode;
 
 	if (!is_hyp_mode_available()) {
 		kvm_err("HYP mode not available\n");
@@ -1474,21 +1464,28 @@ int kvm_arch_init(void *opaque)
 	if (err)
 		return err;
 
-	if (is_kernel_in_hyp_mode())
-		err = init_vhe_mode();
-	else
+	in_hyp_mode = is_kernel_in_hyp_mode();
+
+	if (!in_hyp_mode) {
 		err = init_hyp_mode();
-	if (err)
-		goto out_err;
+		if (err)
+			goto out_err;
+	}
 
 	err = init_subsystems();
 	if (err)
 		goto out_hyp;
 
+	if (in_hyp_mode)
+		kvm_info("VHE mode initialized successfully\n");
+	else
+		kvm_info("Hyp mode initialized successfully\n");
+
 	return 0;
 
 out_hyp:
-	teardown_hyp_mode();
+	if (!in_hyp_mode)
+		teardown_hyp_mode();
 out_err:
 	teardown_common_resources();
 	return err;

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

@@ -1466,6 +1466,16 @@ static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its,
 {
 	mutex_lock(&its->cmd_lock);
 
+	/*
+	 * It is UNPREDICTABLE to enable the ITS if any of the CBASER or
+	 * device/collection BASER are invalid
+	 */
+	if (!its->enabled && (val & GITS_CTLR_ENABLE) &&
+		(!(its->baser_device_table & GITS_BASER_VALID) ||
+		 !(its->baser_coll_table & GITS_BASER_VALID) ||
+		 !(its->cbaser & GITS_CBASER_VALID)))
+		goto out;
+
 	its->enabled = !!(val & GITS_CTLR_ENABLE);
 
 	/*
@@ -1474,6 +1484,7 @@ static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its,
 	 */
 	vgic_its_process_commands(kvm, its);
 
+out:
 	mutex_unlock(&its->cmd_lock);
 }
 
@@ -1801,37 +1812,33 @@ typedef int (*entry_fn_t)(struct vgic_its *its, u32 id, void *entry,
 static int scan_its_table(struct vgic_its *its, gpa_t base, int size, int esz,
 			  int start_id, entry_fn_t fn, void *opaque)
 {
-	void *entry = kzalloc(esz, GFP_KERNEL);
 	struct kvm *kvm = its->dev->kvm;
 	unsigned long len = size;
 	int id = start_id;
 	gpa_t gpa = base;
+	char entry[esz];
 	int ret;
 
+	memset(entry, 0, esz);
+
 	while (len > 0) {
 		int next_offset;
 		size_t byte_offset;
 
 		ret = kvm_read_guest(kvm, gpa, entry, esz);
 		if (ret)
-			goto out;
+			return ret;
 
 		next_offset = fn(its, id, entry, opaque);
-		if (next_offset <= 0) {
-			ret = next_offset;
-			goto out;
-		}
+		if (next_offset <= 0)
+			return next_offset;
 
 		byte_offset = next_offset * esz;
 		id += next_offset;
 		gpa += byte_offset;
 		len -= byte_offset;
 	}
-	ret =  1;
-
-out:
-	kfree(entry);
-	return ret;
+	return 1;
 }
 
 /**
@@ -1940,6 +1947,14 @@ static int vgic_its_save_itt(struct vgic_its *its, struct its_device *device)
 	return 0;
 }
 
+/**
+ * vgic_its_restore_itt - restore the ITT of a device
+ *
+ * @its: its handle
+ * @dev: device handle
+ *
+ * Return 0 on success, < 0 on error
+ */
 static int vgic_its_restore_itt(struct vgic_its *its, struct its_device *dev)
 {
 	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
@@ -1951,6 +1966,10 @@ static int vgic_its_restore_itt(struct vgic_its *its, struct its_device *dev)
 	ret = scan_its_table(its, base, max_size, ite_esz, 0,
 			     vgic_its_restore_ite, dev);
 
+	/* scan_its_table returns +1 if all ITEs are invalid */
+	if (ret > 0)
+		ret = 0;
+
 	return ret;
 }
 
@@ -2048,11 +2067,12 @@ static int vgic_its_device_cmp(void *priv, struct list_head *a,
 static int vgic_its_save_device_tables(struct vgic_its *its)
 {
 	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+	u64 baser = its->baser_device_table;
 	struct its_device *dev;
 	int dte_esz = abi->dte_esz;
-	u64 baser;
 
-	baser = its->baser_device_table;
+	if (!(baser & GITS_BASER_VALID))
+		return 0;
 
 	list_sort(NULL, &its->device_list, vgic_its_device_cmp);
 
@@ -2107,10 +2127,7 @@ static int handle_l1_dte(struct vgic_its *its, u32 id, void *addr,
 	ret = scan_its_table(its, gpa, SZ_64K, dte_esz,
 			     l2_start_id, vgic_its_restore_dte, NULL);
 
-	if (ret <= 0)
-		return ret;
-
-	return 1;
+	return ret;
 }
 
 /**
@@ -2140,8 +2157,9 @@ static int vgic_its_restore_device_tables(struct vgic_its *its)
 				     vgic_its_restore_dte, NULL);
 	}
 
+	/* scan_its_table returns +1 if all entries are invalid */
 	if (ret > 0)
-		ret = -EINVAL;
+		ret = 0;
 
 	return ret;
 }
@@ -2198,17 +2216,17 @@ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz)
 static int vgic_its_save_collection_table(struct vgic_its *its)
 {
 	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+	u64 baser = its->baser_coll_table;
+	gpa_t gpa = BASER_ADDRESS(baser);
 	struct its_collection *collection;
 	u64 val;
-	gpa_t gpa;
 	size_t max_size, filled = 0;
 	int ret, cte_esz = abi->cte_esz;
 
-	gpa = BASER_ADDRESS(its->baser_coll_table);
-	if (!gpa)
+	if (!(baser & GITS_BASER_VALID))
 		return 0;
 
-	max_size = GITS_BASER_NR_PAGES(its->baser_coll_table) * SZ_64K;
+	max_size = GITS_BASER_NR_PAGES(baser) * SZ_64K;
 
 	list_for_each_entry(collection, &its->collection_list, coll_list) {
 		ret = vgic_its_save_cte(its, collection, gpa, cte_esz);
@@ -2239,17 +2257,18 @@ static int vgic_its_save_collection_table(struct vgic_its *its)
 static int vgic_its_restore_collection_table(struct vgic_its *its)
 {
 	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+	u64 baser = its->baser_coll_table;
 	int cte_esz = abi->cte_esz;
 	size_t max_size, read = 0;
 	gpa_t gpa;
 	int ret;
 
-	if (!(its->baser_coll_table & GITS_BASER_VALID))
+	if (!(baser & GITS_BASER_VALID))
 		return 0;
 
-	gpa = BASER_ADDRESS(its->baser_coll_table);
+	gpa = BASER_ADDRESS(baser);
 
-	max_size = GITS_BASER_NR_PAGES(its->baser_coll_table) * SZ_64K;
+	max_size = GITS_BASER_NR_PAGES(baser) * SZ_64K;
 
 	while (read < max_size) {
 		ret = vgic_its_restore_cte(its, gpa, cte_esz);
@@ -2258,6 +2277,10 @@ static int vgic_its_restore_collection_table(struct vgic_its *its)
 		gpa += cte_esz;
 		read += cte_esz;
 	}
+
+	if (ret > 0)
+		return 0;
+
 	return ret;
 }