[PATCH v4 1/5] KVM: riscv: Avoid overwriting G-stage tables with huge leaves

[PATCH v4 1/5] KVM: riscv: Avoid overwriting G-stage tables with huge leaves

[Jinyu Tang]

RISC-V KVM can overwrite an existing G-stage table entry when
installing a huge leaf mapping. If the target huge range already has a
lower-level page table, kvm_riscv_gstage_set_pte() can replace the
non-leaf entry with a leaf PTE and disconnect the lower-level page
table.

Reject replacing a valid table entry with a leaf PTE. If huge-page
installation hits such a conflict, fall back to a 4K mapping for the
original faulting GPA in the MMU fault path, where the original GPA and
HFN are still available.

Suggested-by: Sashiko <sashiko-bot@kernel.org>
Fixes: 9d05c1fee837 ("RISC-V: KVM: Implement stage2 page table programming")
Signed-off-by: Jinyu Tang <jinyu.tang@linux.dev>
---
 arch/riscv/kvm/gstage.c |  6 ++++++
 arch/riscv/kvm/mmu.c    | 24 +++++++++++++++++++++++-
 2 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/gstage.c b/arch/riscv/kvm/gstage.c
index e5002cb9cbef..54d45addf18f 100644
--- a/arch/riscv/kvm/gstage.c
+++ b/arch/riscv/kvm/gstage.c
@@ -174,6 +174,12 @@ int kvm_riscv_gstage_set_pte(struct kvm_gstage *gstage,
 
 	if (pte_val(*ptep) != pte_val(map->pte)) {
 		bool was_invalid = !pte_val(*ptep);
+
+		/* Avoid replacing an existing lower-level table with a leaf mapping. */
+		if (!gstage_pte_leaf(ptep) && !was_invalid &&
+		    gstage_pte_leaf(&map->pte))
+			return -EEXIST;
+
 		set_pte(ptep, map->pte);
 		if (gstage_pte_leaf(ptep) &&
 		    !(was_invalid && riscv_has_extension_unlikely(RISCV_ISA_EXT_SVVPTC)))
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index 6035b5ec9503..bfd6168ebe30 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -625,10 +625,11 @@ int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 		      struct kvm_gstage_mapping *out_map)
 {
 	int ret;
-	kvm_pfn_t hfn;
+	kvm_pfn_t fault_hfn, hfn;
 	bool is_hugetlb;
 	bool writable;
 	unsigned int vma_pageshift;
+	gpa_t fault_gpa = gpa;
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	struct vm_area_struct *vma;
 	struct kvm *kvm = vcpu->kvm;
@@ -709,6 +710,7 @@ int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 	}
 	if (is_error_noslot_pfn(hfn))
 		return -EFAULT;
+	fault_hfn = hfn + ((fault_gpa >> PAGE_SHIFT) - gfn);
 
 	/*
 	 * If logging is active then we allow writable pages only
@@ -734,9 +736,29 @@ int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 		mark_page_dirty_in_slot(kvm, memslot, gfn);
 		ret = kvm_riscv_gstage_map_page(&gstage, pcache, gpa, hfn << PAGE_SHIFT,
 						vma_pagesize, false, true, out_map);
+		if (ret == -EEXIST) {
+			/*
+			 * Retry at 4K granularity for the original faulting GPA
+			 * when a huge leaf cannot replace an existing table.
+			 */
+			ret = kvm_riscv_gstage_map_page(&gstage, pcache, fault_gpa,
+							fault_hfn << PAGE_SHIFT,
+							PAGE_SIZE, false, true,
+							out_map);
+		}
 	} else {
 		ret = kvm_riscv_gstage_map_page(&gstage, pcache, gpa, hfn << PAGE_SHIFT,
 						vma_pagesize, true, true, out_map);
+		if (ret == -EEXIST) {
+			/*
+			 * Retry at 4K granularity for the original faulting GPA
+			 * when a huge leaf cannot replace an existing table.
+			 */
+			ret = kvm_riscv_gstage_map_page(&gstage, pcache, fault_gpa,
+							fault_hfn << PAGE_SHIFT,
+							PAGE_SIZE, true, true,
+							out_map);
+		}
 	}
 
 	if (ret)
-- 
2.43.0


_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv

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

[Jinyu Tang]

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


_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv