[linux-nvidia-6.17]: Backport nvgrace-gpu hugepfnmap, ecc patches and miscellaneous cleanups

Documentation/virt/kvm/api.rst

@@ -7245,6 +7245,41 @@ exit, even without calls to ``KVM_ENABLE_CAP`` or similar.  In this case,
 it will enter with output fields already valid; in the common case, the
 ``unknown.ret`` field of the union will be ``TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED``.
 Userspace need not do anything if it does not wish to support a TDVMCALL.
+
+::
+
+		/* KVM_EXIT_ARM_SEA */
+		struct {
+  #define KVM_EXIT_ARM_SEA_FLAG_GPA_VALID   (1ULL << 0)
+			__u64 flags;
+			__u64 esr;
+			__u64 gva;
+			__u64 gpa;
+		} arm_sea;
+
+Used on arm64 systems. When the VM capability ``KVM_CAP_ARM_SEA_TO_USER`` is
+enabled, a KVM exits to userspace if a guest access causes a synchronous
+external abort (SEA) and the host APEI fails to handle the SEA.
+
+``esr`` is set to a sanitized value of ESR_EL2 from the exception taken to KVM,
+consisting of the following fields:
+
+ - ``ESR_EL2.EC``
+ - ``ESR_EL2.IL``
+ - ``ESR_EL2.FnV``
+ - ``ESR_EL2.EA``
+ - ``ESR_EL2.CM``
+ - ``ESR_EL2.WNR``
+ - ``ESR_EL2.FSC``
+ - ``ESR_EL2.SET`` (when FEAT_RAS is implemented for the VM)
+
+``gva`` is set to the value of FAR_EL2 from the exception taken to KVM when
+``ESR_EL2.FnV == 0``. Otherwise, the value of ``gva`` is unknown.
+
+``gpa`` is set to the faulting IPA from the exception taken to KVM when
+the ``KVM_EXIT_ARM_SEA_FLAG_GPA_VALID`` flag is set. Otherwise, the value of
+``gpa`` is unknown.
+
 ::
 
 		/* Fix the size of the union. */
@@ -8662,6 +8697,18 @@ This capability indicate to the userspace whether a PFNMAP memory region
 can be safely mapped as cacheable. This relies on the presence of
 force write back (FWB) feature support on the hardware.
 
+7.45 KVM_CAP_ARM_SEA_TO_USER
+----------------------------
+
+:Architecture: arm64
+:Target: VM
+:Parameters: none
+:Returns: 0 on success, -EINVAL if unsupported.
+
+When this capability is enabled, KVM may exit to userspace for SEAs taken to
+EL2 resulting from a guest access. See ``KVM_EXIT_ARM_SEA`` for more
+information.
+
 8. Other capabilities.
 ======================
 

MAINTAINERS

@@ -11394,6 +11394,7 @@ M:	Miaohe Lin <linmiaohe@huawei.com>
 R:	Naoya Horiguchi <nao.horiguchi@gmail.com>
 L:	linux-mm@kvack.org
 S:	Maintained
+F:	include/linux/memory-failure.h
 F:	mm/hwpoison-inject.c
 F:	mm/memory-failure.c
 

arch/arm64/configs/defconfig

@@ -1813,9 +1813,7 @@ CONFIG_MEMTEST=y
 CONFIG_NVGRACE_GPU_VFIO_PCI=m
 CONFIG_NVGRACE_EGM=m
 CONFIG_VFIO_DEVICE_CDEV=y
-# CONFIG_VFIO_CONTAINER is not set
 CONFIG_FAULT_INJECTION=y
 CONFIG_IOMMUFD_DRIVER=y
 CONFIG_IOMMUFD=y
 CONFIG_IOMMUFD_TEST=y
-CONFIG_IOMMUFD_VFIO_CONTAINER=y

arch/arm64/include/asm/kvm_host.h

@@ -349,6 +349,8 @@ struct kvm_arch {
 #define KVM_ARCH_FLAG_GUEST_HAS_SVE			9
 	/* MIDR_EL1, REVIDR_EL1, and AIDR_EL1 are writable from userspace */
 #define KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS		10
+	/* Unhandled SEAs are taken to userspace */
+#define KVM_ARCH_FLAG_EXIT_SEA				11
 	unsigned long flags;
 
 	/* VM-wide vCPU feature set */

arch/arm64/kvm/arm.c

@@ -133,6 +133,10 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 		}
 		mutex_unlock(&kvm->lock);
 		break;
+	case KVM_CAP_ARM_SEA_TO_USER:
+		r = 0;
+		set_bit(KVM_ARCH_FLAG_EXIT_SEA, &kvm->arch.flags);
+		break;
 	default:
 		break;
 	}
@@ -322,6 +326,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_IRQFD_RESAMPLE:
 	case KVM_CAP_COUNTER_OFFSET:
 	case KVM_CAP_ARM_WRITABLE_IMP_ID_REGS:
+	case KVM_CAP_ARM_SEA_TO_USER:
 		r = 1;
 		break;
 	case KVM_CAP_SET_GUEST_DEBUG2:

arch/arm64/kvm/mmu.c

@@ -1493,7 +1493,6 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	bool s2_force_noncacheable = false, vfio_allow_any_uc = false;
 	unsigned long mmu_seq;
 	phys_addr_t ipa = fault_ipa;
-	unsigned long mt;
 	struct kvm *kvm = vcpu->kvm;
 	struct vm_area_struct *vma;
 	short vma_shift;
@@ -1613,8 +1612,6 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		vma_pagesize = min(vma_pagesize, (long)max_map_size);
 	}
 
-	mt = FIELD_GET(PTE_ATTRINDX_MASK, pgprot_val(vma->vm_page_prot));
-
 	/*
 	 * Both the canonical IPA and fault IPA must be hugepage-aligned to
 	 * ensure we find the right PFN and lay down the mapping in the right
@@ -1698,7 +1695,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		writable = false;
 	}
 
-	if (exec_fault && s2_force_noncacheable && mt != MT_NORMAL)
+	if (exec_fault && s2_force_noncacheable)
 		ret = -ENOEXEC;
 
 	if (ret) {
@@ -1819,8 +1816,48 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 	read_unlock(&vcpu->kvm->mmu_lock);
 }
 
+/*
+ * Returns true if the SEA should be handled locally within KVM if the abort
+ * is caused by a kernel memory allocation (e.g. stage-2 table memory).
+ */
+static bool host_owns_sea(struct kvm_vcpu *vcpu, u64 esr)
+{
+	/*
+	 * Without FEAT_RAS HCR_EL2.TEA is RES0, meaning any external abort
+	 * taken from a guest EL to EL2 is due to a host-imposed access (e.g.
+	 * stage-2 PTW).
+	 */
+	if (!cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
+		return true;
+
+	/* KVM owns the VNCR when the vCPU isn't in a nested context. */
+	if (is_hyp_ctxt(vcpu) && !kvm_vcpu_trap_is_iabt(vcpu) && (esr & ESR_ELx_VNCR))
+		return true;
+
+	/*
+	 * Determining if an external abort during a table walk happened at
+	 * stage-2 is only possible with S1PTW is set. Otherwise, since KVM
+	 * sets HCR_EL2.TEA, SEAs due to a stage-1 walk (i.e. accessing the
+	 * PA of the stage-1 descriptor) can reach here and are reported
+	 * with a TTW ESR value.
+	 */
+	return (esr_fsc_is_sea_ttw(esr) && (esr & ESR_ELx_S1PTW));
+}
+
 int kvm_handle_guest_sea(struct kvm_vcpu *vcpu)
 {
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_run *run = vcpu->run;
+	u64 esr = kvm_vcpu_get_esr(vcpu);
+	u64 esr_mask = ESR_ELx_EC_MASK	|
+		       ESR_ELx_IL	|
+		       ESR_ELx_FnV	|
+		       ESR_ELx_EA	|
+		       ESR_ELx_CM	|
+		       ESR_ELx_WNR	|
+		       ESR_ELx_FSC;
+	u64 ipa;
+
 	/*
 	 * Give APEI the opportunity to claim the abort before handling it
 	 * within KVM. apei_claim_sea() expects to be called with IRQs enabled.
@@ -1829,7 +1866,33 @@ int kvm_handle_guest_sea(struct kvm_vcpu *vcpu)
 	if (apei_claim_sea(NULL) == 0)
 		return 1;
 
-	return kvm_inject_serror(vcpu);
+	if (host_owns_sea(vcpu, esr) ||
+	    !test_bit(KVM_ARCH_FLAG_EXIT_SEA, &vcpu->kvm->arch.flags))
+		return kvm_inject_serror(vcpu);
+
+	/* ESR_ELx.SET is RES0 when FEAT_RAS isn't implemented. */
+	if (kvm_has_ras(kvm))
+		esr_mask |= ESR_ELx_SET_MASK;
+
+	/*
+	 * Exit to userspace, and provide faulting guest virtual and physical
+	 * addresses in case userspace wants to emulate SEA to guest by
+	 * writing to FAR_ELx and HPFAR_ELx registers.
+	 */
+	memset(&run->arm_sea, 0, sizeof(run->arm_sea));
+	run->exit_reason = KVM_EXIT_ARM_SEA;
+	run->arm_sea.esr = esr & esr_mask;
+
+	if (!(esr & ESR_ELx_FnV))
+		run->arm_sea.gva = kvm_vcpu_get_hfar(vcpu);
+
+	ipa = kvm_vcpu_get_fault_ipa(vcpu);
+	if (ipa != INVALID_GPA) {
+		run->arm_sea.flags |= KVM_EXIT_ARM_SEA_FLAG_GPA_VALID;
+		run->arm_sea.gpa = ipa;
+	}
+
+	return 0;
 }
 
 /**