[Deepin-Kernel-SIG] [linux 6.18.y] [Upstream] Update kernel base to 6.18.49

Documentation/filesystems/fscrypt.rst

@@ -1245,6 +1245,10 @@ astute users may notice some differences in behavior:
 
 - DAX (Direct Access) is not supported on encrypted files.
 
+- Encrypted files cannot be used directly as swap files.  To swap to
+  an encrypted file, set up a loopback device on top of it.
+  Alternatively, encrypted swap can use a dm-crypt device.
+
 - The maximum length of an encrypted symlink is 2 bytes shorter than
   the maximum length of an unencrypted symlink.  For example, on an
   EXT4 filesystem with a 4K block size, unencrypted symlinks can be up

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
 PATCHLEVEL = 18
-SUBLEVEL = 48
+SUBLEVEL = 49
 EXTRAVERSION =
 NAME = Baby Opossum Posse
 

arch/powerpc/perf/hv-gpci.c

@@ -210,7 +210,7 @@ static ssize_t processor_bus_topology_show(struct device *dev, struct device_att
 			0, 0, buf, &n, arg);
 
 	if (!ret)
-		return n;
+		goto out_success;
 
 	if (ret != H_PARAMETER)
 		goto out;
@@ -244,12 +244,14 @@ static ssize_t processor_bus_topology_show(struct device *dev, struct device_att
 				starting_index, 0, buf, &n, arg);
 
 		if (!ret)
-			return n;
+			goto out_success;
 
 		if (ret != H_PARAMETER)
 			goto out;
 	}
 
+out_success:
+	put_cpu_var(hv_gpci_reqb);
 	return n;
 
 out:
@@ -278,7 +280,7 @@ static ssize_t processor_config_show(struct device *dev, struct device_attribute
 			0, 0, buf, &n, arg);
 
 	if (!ret)
-		return n;
+		goto out_success;
 
 	if (ret != H_PARAMETER)
 		goto out;
@@ -312,12 +314,14 @@ static ssize_t processor_config_show(struct device *dev, struct device_attribute
 				starting_index, 0, buf, &n, arg);
 
 		if (!ret)
-			return n;
+			goto out_success;
 
 		if (ret != H_PARAMETER)
 			goto out;
 	}
 
+out_success:
+	put_cpu_var(hv_gpci_reqb);
 	return n;
 
 out:
@@ -346,7 +350,7 @@ static ssize_t affinity_domain_via_virtual_processor_show(struct device *dev,
 			0, 0, buf, &n, arg);
 
 	if (!ret)
-		return n;
+		goto out_success;
 
 	if (ret != H_PARAMETER)
 		goto out;
@@ -382,12 +386,14 @@ static ssize_t affinity_domain_via_virtual_processor_show(struct device *dev,
 				starting_index, secondary_index, buf, &n, arg);
 
 		if (!ret)
-			return n;
+			goto out_success;
 
 		if (ret != H_PARAMETER)
 			goto out;
 	}
 
+out_success:
+	put_cpu_var(hv_gpci_reqb);
 	return n;
 
 out:
@@ -416,7 +422,7 @@ static ssize_t affinity_domain_via_domain_show(struct device *dev, struct device
 			0, 0, buf, &n, arg);
 
 	if (!ret)
-		return n;
+		goto out_success;
 
 	if (ret != H_PARAMETER)
 		goto out;
@@ -448,12 +454,14 @@ static ssize_t affinity_domain_via_domain_show(struct device *dev, struct device
 					starting_index, 0, buf, &n, arg);
 
 		if (!ret)
-			return n;
+			goto out_success;
 
 		if (ret != H_PARAMETER)
 			goto out;
 	}
 
+out_success:
+	put_cpu_var(hv_gpci_reqb);
 	return n;
 
 out:

arch/riscv/kernel/compat_signal.c

@@ -107,6 +107,8 @@ static long compat_restore_sigcontext(struct pt_regs *regs,
 
 	/* sc_regs is structured the same as the start of pt_regs */
 	err = __copy_from_user(&cregs, &sc->sc_regs, sizeof(sc->sc_regs));
+	if (unlikely(err))
+		return err;
 
 	cregs_to_regs(&cregs, regs);
 

arch/riscv/kernel/ptrace.c

@@ -372,8 +372,8 @@ static int compat_riscv_gpr_set(struct task_struct *target,
 	struct compat_user_regs_struct cregs;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &cregs, 0, -1);
-
-	cregs_to_regs(&cregs, task_pt_regs(target));
+	if (!ret)
+		cregs_to_regs(&cregs, task_pt_regs(target));
 
 	return ret;
 }

arch/s390/kvm/vsie.c

@@ -184,6 +184,7 @@ static int setup_apcb10(struct kvm_vcpu *vcpu, struct kvm_s390_apcb1 *apcb_s,
 			    sizeof(struct kvm_s390_apcb0)))
 		return -EFAULT;
 
+	memset(apcb_s, 0, sizeof(*apcb_s));
 	apcb_s->apm[0] = apcb_h->apm[0] & tmp.apm[0];
 	apcb_s->aqm[0] = apcb_h->aqm[0] & tmp.aqm[0] & 0xffff000000000000UL;
 	apcb_s->adm[0] = apcb_h->adm[0] & tmp.adm[0] & 0xffff000000000000UL;

arch/x86/kernel/cpu/amd.c

@@ -514,11 +514,13 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		case 0x00 ... 0x2f:
 		case 0x40 ... 0x4f:
 		case 0x60 ... 0x7f:
+		case 0xd0 ... 0xd7:
 			setup_force_cpu_cap(X86_FEATURE_ZEN5);
 			break;
 		case 0x50 ... 0x5f:
 		case 0x80 ... 0xaf:
-		case 0xc0 ... 0xef:
+		case 0xc0 ... 0xcf:
+		case 0xd8 ... 0xef:
 			setup_force_cpu_cap(X86_FEATURE_ZEN6);
 			break;
 		default:

arch/x86/kvm/mmu/page_track.c

@@ -130,22 +130,42 @@ void __kvm_write_track_remove_gfn(struct kvm *kvm,
 	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
 
-/*
- * check if the corresponding access on the specified guest page is tracked.
- */
+static bool __kvm_gfn_is_write_tracked(const struct kvm_memory_slot *slot,
+				       gfn_t gfn)
+{
+	int index;
+
+	if (!slot)
+		return false;
+
+	index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K);
+	return !!READ_ONCE(slot->arch.gfn_write_track[index]);
+}
+
+/* check if write access is tracked on the specified guest page.  */
 bool kvm_gfn_is_write_tracked(struct kvm *kvm,
 			      const struct kvm_memory_slot *slot, gfn_t gfn)
 {
-	int index;
+	const struct kvm_memory_slot *other_slot;
 
 	if (!slot)
 		return false;
 
 	if (!kvm_page_track_write_tracking_enabled(kvm))
 		return false;
 
-	index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K);
-	return !!READ_ONCE(slot->arch.gfn_write_track[index]);
+	BUILD_BUG_ON(KVM_MAX_NR_ADDRESS_SPACES > 2);
+
+	if (__kvm_gfn_is_write_tracked(slot, gfn))
+		return true;
+
+	if (kvm_arch_nr_memslot_as_ids(kvm) > 1) {
+		other_slot = __gfn_to_memslot(__kvm_memslots(kvm, slot->as_id ^ 1), gfn);
+		if (__kvm_gfn_is_write_tracked(other_slot, gfn))
+			return true;
+	}
+
+	return false;
 }
 
 #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING

arch/x86/kvm/svm/sev.c

@@ -2844,8 +2844,12 @@ int sev_mem_enc_register_region(struct kvm *kvm,
 	if (!region)
 		return -ENOMEM;
 
+	/*
+	 * Do NOT specify FOLL_WRITE, as KVM isn't using the pinned pages to
+	 * write memory, and FOLL_LONGTERM itself triggers CoW unshare.
+	 */
 	region->pages = sev_pin_memory(kvm, range->addr, range->size, &region->npages,
-				       FOLL_WRITE | FOLL_LONGTERM);
+				       FOLL_LONGTERM);
 	if (IS_ERR(region->pages)) {
 		ret = PTR_ERR(region->pages);
 		goto e_free;
@@ -4199,43 +4203,29 @@ static int snp_begin_psc(struct vcpu_svm *svm)
 	BUG();
 }
 
-/*
- * Invoked as part of svm_vcpu_reset() processing of an init event.
- */
-static void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu)
+static void sev_snp_reload_vmsa(struct kvm_vcpu *vcpu, gpa_t gpa)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct kvm_memory_slot *slot;
+	gfn_t gfn = gpa_to_gfn(gpa);
 	struct page *page;
 	kvm_pfn_t pfn;
-	gfn_t gfn;
-
-	guard(mutex)(&svm->sev_es.snp_vmsa_mutex);
-
-	if (!svm->sev_es.snp_ap_waiting_for_reset)
-		return;
-
-	svm->sev_es.snp_ap_waiting_for_reset = false;
 
-	/* Mark the vCPU as offline and not runnable */
-	vcpu->arch.pv.pv_unhalted = false;
-	kvm_set_mp_state(vcpu, KVM_MP_STATE_HALTED);
+	lockdep_assert_held(&svm->sev_es.snp_vmsa_mutex);
 
-	/* Clear use of the VMSA */
+	/* Clear use of the VMSA. */
 	svm->vmcb->control.vmsa_pa = INVALID_PAGE;
+	svm->sev_es.snp_guest_vmsa_gpa = INVALID_PAGE;
 
 	/*
 	 * When replacing the VMSA during SEV-SNP AP creation,
 	 * mark the VMCB dirty so that full state is always reloaded.
 	 */
 	vmcb_mark_all_dirty(svm->vmcb);
 
-	if (!VALID_PAGE(svm->sev_es.snp_vmsa_gpa))
+	if (!VALID_PAGE(gpa))
 		return;
 
-	gfn = gpa_to_gfn(svm->sev_es.snp_vmsa_gpa);
-	svm->sev_es.snp_vmsa_gpa = INVALID_PAGE;
-
 	slot = gfn_to_memslot(vcpu->kvm, gfn);
 	if (!slot)
 		return;
@@ -4259,11 +4249,9 @@ static void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu)
 	svm->sev_es.snp_has_guest_vmsa = true;
 
 	/* Use the new VMSA */
+	svm->sev_es.snp_guest_vmsa_gpa = gpa;
 	svm->vmcb->control.vmsa_pa = pfn_to_hpa(pfn);
 
-	/* Mark the vCPU as runnable */
-	kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
-
 	/*
 	 * gmem pages aren't currently migratable, but if this ever changes
 	 * then care should be taken to ensure svm->sev_es.vmsa is pinned
@@ -4272,6 +4260,40 @@ static void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu)
 	kvm_release_page_clean(page);
 }
 
+/*
+ * Invoked as part of svm_vcpu_reset() processing of an init event.
+ */
+static void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	gpa_t gpa;
+
+	guard(mutex)(&svm->sev_es.snp_vmsa_mutex);
+
+	if (!svm->sev_es.snp_ap_waiting_for_reset)
+		return;
+
+	svm->sev_es.snp_ap_waiting_for_reset = false;
+
+	/* Mark the vCPU as offline and not runnable */
+	vcpu->arch.pv.pv_unhalted = false;
+	kvm_set_mp_state(vcpu, KVM_MP_STATE_HALTED);
+
+	gpa = svm->sev_es.snp_pending_vmsa_gpa;
+	svm->sev_es.snp_pending_vmsa_gpa = INVALID_PAGE;
+
+	sev_snp_reload_vmsa(vcpu, gpa);
+
+	/*
+	 * Mark the vCPU as runnable for CREATE requests, indicated by a valid
+	 * VMSA GPA, even if installing the VMSA failed, so that KVM_RUN will
+	 * fail instead of blocking indefinitely and hanging the vCPU, e.g. if
+	 * the backing guest_memfd page is unavailable.
+	 */
+	if (VALID_PAGE(gpa))
+		kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
+}
+
 static int sev_snp_ap_creation(struct vcpu_svm *svm)
 {
 	struct kvm_sev_info *sev = to_kvm_sev_info(svm->vcpu.kvm);
@@ -4325,10 +4347,10 @@ static int sev_snp_ap_creation(struct vcpu_svm *svm)
 			return -EINVAL;
 		}
 
-		target_svm->sev_es.snp_vmsa_gpa = svm->vmcb->control.exit_info_2;
+		target_svm->sev_es.snp_pending_vmsa_gpa = svm->vmcb->control.exit_info_2;
 		break;
 	case SVM_VMGEXIT_AP_DESTROY:
-		target_svm->sev_es.snp_vmsa_gpa = INVALID_PAGE;
+		target_svm->sev_es.snp_pending_vmsa_gpa = INVALID_PAGE;
 		break;
 	default:
 		vcpu_unimpl(vcpu, "vmgexit: invalid AP creation request [%#x] from guest\n",
@@ -4922,6 +4944,8 @@ int sev_vcpu_create(struct kvm_vcpu *vcpu)
 	}
 
 	svm->sev_es.vmsa = page_address(vmsa_page);
+	svm->sev_es.snp_pending_vmsa_gpa = INVALID_PAGE;
+	svm->sev_es.snp_guest_vmsa_gpa = INVALID_PAGE;
 
 	vcpu->arch.guest_tsc_protected = snp_is_secure_tsc_enabled(vcpu->kvm);
 

arch/x86/kvm/svm/svm.c

@@ -5301,6 +5301,10 @@ struct kvm_x86_ops svm_x86_ops __initdata = {
 
 	.vm_copy_enc_context_from = sev_vm_copy_enc_context_from,
 	.vm_move_enc_context_from = sev_vm_move_enc_context_from,
+
+	.gmem_prepare = sev_gmem_prepare,
+	.gmem_invalidate = sev_gmem_invalidate,
+	.gmem_max_mapping_level = sev_gmem_max_mapping_level,
 #endif
 	.check_emulate_instruction = svm_check_emulate_instruction,
 
@@ -5312,10 +5316,6 @@ struct kvm_x86_ops svm_x86_ops __initdata = {
 	.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
 	.vcpu_get_apicv_inhibit_reasons = avic_vcpu_get_apicv_inhibit_reasons,
 	.alloc_apic_backing_page = svm_alloc_apic_backing_page,
-
-	.gmem_prepare = sev_gmem_prepare,
-	.gmem_invalidate = sev_gmem_invalidate,
-	.gmem_max_mapping_level = sev_gmem_max_mapping_level,
 };
 
 /*