Skip to contentSkip to conversation

KVM: arm64: nv: A couple more VNCR fixes

PATCH New Oliver Upton 1 participant 3 messages Jun 8

Subsystems (3)
lore
Share & tools
lore

Oliver Upton

author maintainer
#0 lore raw

cover KVM: arm64: nv: A couple more VNCR fixes

Another day, another handful of ugly MMU bugs.

The first addresses an issue where the host stage-1 VNCR mapping only relies on the guest stage-1 permissions, potentially allowing RW accesses to an RO PFN.

The second avoids a BUG_ON() in the case that the output of stage-1 translation exists outside of a memslot, and instead does the usual thing and injects an SEA.

Based on kvmarm/next since the first pile of MMU changes was taken (thanks!)

Oliver Upton (2):
KVM: arm64: nv: Respect read-only PFN when mapping L1 VNCR
KVM: arm64: nv: Inject SEA if kvm_translate_vncr() can't resolve PFN

 arch/arm64/include/asm/kvm_nested.h |  8 ++++++
 arch/arm64/kvm/at.c                 |  8 ------
 arch/arm64/kvm/nested.c             | 40 +++++++++++++++++++++--------
 3 files changed, 38 insertions(+), 18 deletions(-)

base-commit: 406f0c31f47877db036e885f15830106b89ca950

Signature · 1 line
2.47.3
author maintainer
#1 lore raw

PATCH 1/2 KVM: arm64: nv: Respect read-only PFN when mapping L1 VNCR

KVM currently maps the L1 VNCR into the host stage-1 by relying entirely on the permissions of the guest stage-1. At the same time, it is entirely possible that the backing PFN is read-only (e.g. RO memslot), meaning that the L1 VNCR should use at most a read-only mapping.

Cache the writability of the PFN in the VNCR TLB and use it to constrain the resulting fixmap permissions. Promote VNCR permission faults to an SEA in the case where the guest attempts to write to a read-only endpoint. Conveniently, this also plugs a page leak found by Sashiko [*] resulting from the early return for a read-only PFN.

Fixes 2a359e072596 ("KVM: arm64: nv: Handle mapping of VNCR_EL2 at EL2")
---
 arch/arm64/kvm/nested.c | 34 +++++++++++++++++++++++++---------
 1 file changed, 25 insertions(+), 9 deletions(-)
arch/arm64/kvm/nested.c +25 -9
index 257813289c76..cdbdf47fa6a2 100644
@@ -24,6 +24,7 @@ struct vncr_tlb {
 	struct s1_walk_result	wr;
 
 	u64			hpa;
+	bool			hpa_writable;
 
 	/* -1 when not mapped on a CPU */
 	int			cpu;
@@ -1395,7 +1396,7 @@ static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem)
 	if (!*is_gmem) {
 		pfn = __kvm_faultin_pfn(memslot, gfn, write_fault ? FOLL_WRITE : 0,
 					&writable, &page);
-		if (is_error_noslot_pfn(pfn) || (write_fault && !writable))
+		if (is_error_noslot_pfn(pfn))
 			return -EFAULT;
 	} else {
 		ret = kvm_gmem_get_pfn(vcpu->kvm, memslot, gfn, &pfn, &page, NULL);
@@ -1404,6 +1405,8 @@ static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem)
 					      write_fault, false, false);
 			return ret;
 		}
+
+		writable = !(memslot->flags & KVM_MEM_READONLY);
 	}
 
 	scoped_guard(write_lock, &vcpu->kvm->mmu_lock) {
@@ -1414,6 +1417,7 @@ static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem)
 
 		vt->gva = va;
 		vt->hpa = pfn << PAGE_SHIFT;
+		vt->hpa_writable = writable;
 		vt->valid = true;
 		vt->cpu = -1;
 
@@ -1421,21 +1425,33 @@ static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem)
 		kvm_release_faultin_page(vcpu->kvm, page, false, vt->wr.pw);
 	}
 
-	if (vt->wr.pw)
+	if (vt->wr.pw && vt->hpa_writable)
 		mark_page_dirty(vcpu->kvm, gfn);
 
 	return 0;
 }
 
-static void inject_vncr_perm(struct kvm_vcpu *vcpu)
+static void handle_vncr_perm(struct kvm_vcpu *vcpu)
 {
 	struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
 	u64 esr = kvm_vcpu_get_esr(vcpu);
+	u64 fsc;
+
+	/*
+	 * Promote to an external abort if the stage-1 permits writes but the
+	 * HPA is read-only (e.g. RO memslot).
+	 */
+	if (kvm_is_write_fault(vcpu) && vt->wr.pw && !vt->hpa_writable)
+		fsc = ESR_ELx_FSC_EXTABT;
+	/*
+	 * Otherwise, inject a permission fault using the guest's translation
+	 * level rather than the host's.
+	 */
+	else
+		fsc = ESR_ELx_FSC_PERM_L(vt->wr.level);
 
-	/* Adjust the fault level to reflect that of the guest's */
 	esr &= ~ESR_ELx_FSC;
-	esr |= FIELD_PREP(ESR_ELx_FSC,
-			  ESR_ELx_FSC_PERM_L(vt->wr.level));
+	esr |= FIELD_PREP(ESR_ELx_FSC, fsc);
 
 	kvm_inject_nested_sync(vcpu, esr);
 }
@@ -1469,7 +1485,7 @@ int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu)
 		return kvm_handle_guest_sea(vcpu);
 
 	if (esr_fsc_is_permission_fault(esr)) {
-		inject_vncr_perm(vcpu);
+		handle_vncr_perm(vcpu);
 	} else if (esr_fsc_is_translation_fault(esr)) {
 		bool valid, is_gmem = false;
 		int ret;
@@ -1517,7 +1533,7 @@ int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu)
 			break;
 		case -EPERM:
 			/* Hack to deal with POE until we get kernel support */
-			inject_vncr_perm(vcpu);
+			handle_vncr_perm(vcpu);
 			break;
 		case 0:
 			break;
@@ -1561,7 +1577,7 @@ static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu)
 
 	vt->cpu = smp_processor_id();
 
-	if (vt->wr.pw && vt->wr.pr)
+	if (vt->hpa_writable && vt->wr.pw && vt->wr.pr)
 		prot = PAGE_KERNEL;
 	else if (vt->wr.pr)
 		prot = PAGE_KERNEL_RO;
Signature · 1 line
2.47.3
author maintainer
#2 lore raw

PATCH 2/2 KVM: arm64: nv: Inject SEA if kvm_translate_vncr() can't resolve PFN

In reply to Oliver Upton

kvm_handle_vncr_abort() assumes that s1_walk_result conveys an abort when kvm_translate_vncr() returns -EFAULT. This is not always the case as it's possible to encounter 'late' failures on the output of S1 translation, e.g. a GFN outside of the memslots.

Fix it by preparing an external abort before returning from kvm_translate_vncr().

Fixes b55d3bd1e0b7 ("KVM: arm64: nv: Inject SEA if kvm_translate_vncr() can't resolve PFN")
---
 arch/arm64/include/asm/kvm_nested.h | 8 ++++++++
 arch/arm64/kvm/at.c                 | 8 --------
 arch/arm64/kvm/nested.c             | 8 ++++++--
 3 files changed, 14 insertions(+), 10 deletions(-)
arch/arm64/include/asm/kvm_nested.h +8 -0
index dc2957662ff2..cbdaaa2a2903 100644
@@ -388,6 +388,14 @@ struct s1_walk_result {
 	bool	failed;
 };
 
+static inline void fail_s1_walk(struct s1_walk_result *wr, u8 fst, bool s1ptw)
+{
+	wr->fst		= fst;
+	wr->ptw		= s1ptw;
+	wr->s2		= s1ptw;
+	wr->failed	= true;
+}
+
 int __kvm_translate_va(struct kvm_vcpu *vcpu, struct s1_walk_info *wi,
 		       struct s1_walk_result *wr, u64 va);
 int __kvm_find_s1_desc_level(struct kvm_vcpu *vcpu, u64 va, u64 ipa,
arch/arm64/kvm/at.c +0 -8
index 30e6fa8ac07c..8263c648207b 100644
@@ -11,14 +11,6 @@
 #include <asm/kvm_mmu.h>
 #include <asm/lsui.h>
 
-static void fail_s1_walk(struct s1_walk_result *wr, u8 fst, bool s1ptw)
-{
-	wr->fst		= fst;
-	wr->ptw		= s1ptw;
-	wr->s2		= s1ptw;
-	wr->failed	= true;
-}
-
 #define S1_MMU_DISABLED		(-127)
 
 static int get_ia_size(struct s1_walk_info *wi)
arch/arm64/kvm/nested.c +6 -2
index cdbdf47fa6a2..940247b3530b 100644
@@ -1389,15 +1389,19 @@ static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem)
 
 	gfn = vt->wr.pa >> PAGE_SHIFT;
 	memslot = gfn_to_memslot(vcpu->kvm, gfn);
-	if (!memslot)
+	if (!memslot) {
+		fail_s1_walk(&vt->wr, ESR_ELx_FSC_EXTABT, false);
 		return -EFAULT;
+	}
 
 	*is_gmem = kvm_slot_has_gmem(memslot);
 	if (!*is_gmem) {
 		pfn = __kvm_faultin_pfn(memslot, gfn, write_fault ? FOLL_WRITE : 0,
 					&writable, &page);
-		if (is_error_noslot_pfn(pfn))
+		if (is_error_noslot_pfn(pfn)) {
+			fail_s1_walk(&vt->wr, ESR_ELx_FSC_EXTABT, false);
 			return -EFAULT;
+		}
 	} else {
 		ret = kvm_gmem_get_pfn(vcpu->kvm, memslot, gfn, &pfn, &page, NULL);
 		if (ret) {
Signature · 1 line
2.47.3