[PATCH v4 3/5] KVM: riscv: Implement KVM_PRE_FAULT_MEMORY

[Jinyu Tang <jinyu.tang@linux.dev>]

The generic KVM_PRE_FAULT_MEMORY ioctl lets userspace populate KVM page
tables before running a vCPU over a GPA range. x86 already supports the
ioctl, but RISC-V does not expose the capability and has no arch hook.

Add the RISC-V arch hook and reuse the existing G-stage fault mapping
path with a read access. Report progress using the G-stage mapping
returned by the map path, so the ioctl can advance by the actual leaf
size that covers the requested GPA. Retry until a mapping is installed
or a signal, VM-dead request, or real error is observed.

Signed-off-by: Jinyu Tang <jinyu.tang@linux.dev>
---
 arch/riscv/kvm/Kconfig  |  1 +
 arch/riscv/kvm/gstage.c |  3 +++
 arch/riscv/kvm/mmu.c    | 45 ++++++++++++++++++++++++++++++++++++++++-
 arch/riscv/kvm/vm.c     |  1 +
 4 files changed, 49 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
index ec2cee0a39e0..8ac209e8ac87 100644
--- a/arch/riscv/kvm/Kconfig
+++ b/arch/riscv/kvm/Kconfig
@@ -28,6 +28,7 @@ config KVM
 	select KVM_COMMON
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_GENERIC_HARDWARE_ENABLING
+	select KVM_GENERIC_PRE_FAULT_MEMORY
 	select KVM_MMIO
 	select VIRT_XFER_TO_GUEST_WORK
 	select SCHED_INFO
diff --git a/arch/riscv/kvm/gstage.c b/arch/riscv/kvm/gstage.c
index 54d45addf18f..dff315dfd24e 100644
--- a/arch/riscv/kvm/gstage.c
+++ b/arch/riscv/kvm/gstage.c
@@ -286,6 +286,9 @@ int kvm_riscv_gstage_map_page(struct kvm_gstage *gstage,
 						    out_map->level, true);
 		} else if (ALIGN_DOWN(PFN_PHYS(pte_pfn(ptep_get(ptep))), page_size) == hpa) {
 			kvm_riscv_gstage_update_pte_prot(gstage, ptep_level, gpa, ptep, prot);
+			out_map->addr = ALIGN_DOWN(gpa, page_size);
+			out_map->level = ptep_level;
+			out_map->pte = ptep_get(ptep);
 			return 0;
 		}
 	}
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index 2fabcd409991..f6ca86da53eb 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -717,7 +717,7 @@ int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 	if (hfn == KVM_PFN_ERR_HWPOISON) {
 		send_sig_mceerr(BUS_MCEERR_AR, (void __user *)hva,
 				vma_pageshift, current);
-		return 0;
+		return -EFAULT;
 	}
 	if (is_error_noslot_pfn(hfn))
 		return -EFAULT;
@@ -782,6 +782,49 @@ int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 	return ret;
 }
 
+long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
+				    struct kvm_pre_fault_memory *range)
+{
+	struct kvm_gstage_mapping out_map = { 0 };
+	struct kvm_memory_slot *memslot;
+	unsigned long map_size;
+	unsigned long hva;
+	gpa_t end;
+	gfn_t gfn;
+	int ret;
+
+	gfn = gpa_to_gfn(range->gpa);
+	memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+	if (!memslot)
+		return -ENOENT;
+
+	hva = gfn_to_hva_memslot_prot(memslot, gfn, NULL);
+	if (kvm_is_error_hva(hva))
+		return -ENOENT;
+
+	for (;;) {
+		if (signal_pending(current))
+			return -EINTR;
+
+		if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu))
+			return -EIO;
+
+		cond_resched();
+		ret = kvm_riscv_mmu_map(vcpu, memslot, range->gpa, hva, false, &out_map);
+		if (ret)
+			return ret;
+
+		if (!pte_val(out_map.pte))
+			continue;
+
+		map_size = PAGE_SIZE << (out_map.level * kvm_riscv_gstage_index_bits);
+		end = out_map.addr + map_size;
+		break;
+	}
+
+	return min_t(u64, range->size, end - range->gpa);
+}
+
 int kvm_riscv_mmu_alloc_pgd(struct kvm *kvm)
 {
 	struct page *pgd_page;
diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c
index a9f083feeb76..58500a19b33b 100644
--- a/arch/riscv/kvm/vm.c
+++ b/arch/riscv/kvm/vm.c
@@ -187,6 +187,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_MP_STATE:
 	case KVM_CAP_IMMEDIATE_EXIT:
 	case KVM_CAP_SET_GUEST_DEBUG:
+	case KVM_CAP_PRE_FAULT_MEMORY:
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
-- 
2.43.0