[PATCH v3 1/5] KVM: arm64: nv: Respect read-only PFN when mapping L1 VNCR

[PATCH v3 1/5] KVM: arm64: nv: Respect read-only PFN when mapping L1 VNCR

[Oliver Upton]

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.

Cc: stable@vger.kernel.org
Fixes: 2a359e072596 ("KVM: arm64: nv: Handle mapping of VNCR_EL2 at EL2")
Link: https://lore.kernel.org/kvm/20260608082603.16AEC1F00893@smtp.kernel.org/
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 arch/arm64/kvm/nested.c | 36 ++++++++++++++++++++++++++----------
 1 file changed, 26 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 3a5571c3c114..903ccabca78c 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -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;
@@ -1401,7 +1402,7 @@ 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);
@@ -1410,6 +1411,8 @@ 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) {
@@ -1420,28 +1423,41 @@ 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;
 
 		kvm_make_request(KVM_REQ_MAP_L1_VNCR_EL2, vcpu);
-		kvm_release_faultin_page(vcpu->kvm, page, false, vt->wr.pw);
+		kvm_release_faultin_page(vcpu->kvm, page, false, vt->wr.pw && vt->hpa_writable);
 	}
 
-	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);
 }
@@ -1475,7 +1491,7 @@ 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;
@@ -1523,7 +1539,7 @@ 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;
@@ -1567,7 +1583,7 @@ 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;
-- 
2.47.3

[PATCH v3 2/5] KVM: arm64: nv: Inject SEA if kvm_translate_vncr() can't resolve PFN

[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(). Get rid of the BUG_ON() in the fault injection
path while at it.

Cc: stable@vger.kernel.org
Fixes: 2a359e072596 ("KVM: arm64: nv: Handle mapping of VNCR_EL2 at EL2")
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 arch/arm64/include/asm/kvm_nested.h |  8 ++++++++
 arch/arm64/kvm/at.c                 |  8 --------
 arch/arm64/kvm/nested.c             | 10 ++++++----
 3 files changed, 14 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index dc2957662ff2..cbdaaa2a2903 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -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,
diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c
index 30e6fa8ac07c..8263c648207b 100644
--- a/arch/arm64/kvm/at.c
+++ b/arch/arm64/kvm/at.c
@@ -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)
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 903ccabca78c..53dea9c3f14f 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -1395,15 +1395,19 @@ 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) {
@@ -1530,8 +1534,6 @@ int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu)
 			 * Translation failed, inject the corresponding
 			 * exception back to EL2.
 			 */
-			BUG_ON(!vt->wr.failed);
-
 			esr &= ~ESR_ELx_FSC;
 			esr |= FIELD_PREP(ESR_ELx_FSC, vt->wr.fst);
 
-- 
2.47.3

[PATCH v3 3/5] KVM: arm64: nv: Re-translate VNCR before injecting abort

[Oliver Upton]

KVM faults in the VNCR page with FOLL_WRITE whenever the guest aborts
for a write, similar to how a regular stage-2 mapping is handled. It is
entirely possible that the guest reads from the VNCR before writing to
it, in which case the PFN could only be read-only.

Invalidate the VNCR TLB and re-fetch the translation upon taking a VNCR
abort, allowing the host mapping to be faulted in for write the second
time around. Interestingly enough, this also satisfies the ordering
requirements of FEAT_ETS2/3 between descriptor updates and MMU faults.

Cc: stable@vger.kernel.org
Fixes: 2a359e072596 ("KVM: arm64: nv: Handle mapping of VNCR_EL2 at EL2")
Reported-by: Sashiko <sashiko-bot@kernel.org>
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 arch/arm64/kvm/nested.c | 111 +++++++++++++++-------------------------
 1 file changed, 42 insertions(+), 69 deletions(-)

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 53dea9c3f14f..7fffd86eee94 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -1466,88 +1466,61 @@ static void handle_vncr_perm(struct kvm_vcpu *vcpu)
 	kvm_inject_nested_sync(vcpu, esr);
 }
 
-static bool kvm_vncr_tlb_lookup(struct kvm_vcpu *vcpu)
-{
-	struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
-
-	lockdep_assert_held_read(&vcpu->kvm->mmu_lock);
-
-	if (!vt->valid)
-		return false;
-
-	if (read_vncr_el2(vcpu) != vt->gva)
-		return false;
-
-	if (vt->wr.nG)
-		return get_asid_by_regime(vcpu, TR_EL20) == vt->wr.asid;
-
-	return true;
-}
-
 int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu)
 {
 	struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
 	u64 esr = kvm_vcpu_get_esr(vcpu);
+	bool is_gmem = false;
+	bool perm;
+	int ret;
 
 	WARN_ON_ONCE(!(esr & ESR_ELx_VNCR));
 
 	if (kvm_vcpu_abt_issea(vcpu))
 		return kvm_handle_guest_sea(vcpu);
 
-	if (esr_fsc_is_permission_fault(esr)) {
-		handle_vncr_perm(vcpu);
-	} else if (esr_fsc_is_translation_fault(esr)) {
-		bool valid, is_gmem = false;
-		int ret;
-
-		scoped_guard(read_lock, &vcpu->kvm->mmu_lock)
-			valid = kvm_vncr_tlb_lookup(vcpu);
-
-		if (!valid)
-			ret = kvm_translate_vncr(vcpu, &is_gmem);
-		else
-			ret = -EPERM;
+	if (!esr_fsc_is_translation_fault(esr) && !esr_fsc_is_permission_fault(esr)) {
+		WARN_ONCE(1, "Unhandled VNCR abort, ESR=%llx\n", esr);
+		return 1;
+	}
 
-		switch (ret) {
-		case -EAGAIN:
-			/* Let's try again... */
-			break;
-		case -ENOMEM:
-			/*
-			 * For guest_memfd, this indicates that it failed to
-			 * create a folio to back the memory. Inform userspace.
-			 */
-			if (is_gmem)
-				return 0;
-			/* Otherwise, let's try again... */
-			break;
-		case -EFAULT:
-		case -EIO:
-		case -EHWPOISON:
-			if (is_gmem)
-				return 0;
-			fallthrough;
-		case -EINVAL:
-		case -ENOENT:
-		case -EACCES:
-			/*
-			 * Translation failed, inject the corresponding
-			 * exception back to EL2.
-			 */
-			esr &= ~ESR_ELx_FSC;
-			esr |= FIELD_PREP(ESR_ELx_FSC, vt->wr.fst);
+	ret = kvm_translate_vncr(vcpu, &is_gmem);
+	switch (ret) {
+	case -EAGAIN:
+		/* Let's try again... */
+		return 1;
+	case -ENOMEM:
+		/*
+		 * For guest_memfd, this indicates that it failed to
+		 * create a folio to back the memory. Inform userspace.
+		 */
+		if (is_gmem)
+			return 0;
+		/* Otherwise, let's try again... */
+		break;
+	case -EFAULT:
+	case -EIO:
+	case -EHWPOISON:
+		if (is_gmem)
+			return 0;
+		fallthrough;
+	case -EINVAL:
+	case -ENOENT:
+	case -EACCES:
+		/*
+		 * Translation failed, inject the corresponding
+		 * exception back to EL2.
+		 */
+		esr &= ~ESR_ELx_FSC;
+		esr |= FIELD_PREP(ESR_ELx_FSC, vt->wr.fst);
 
-			kvm_inject_nested_sync(vcpu, esr);
-			break;
-		case -EPERM:
-			/* Hack to deal with POE until we get kernel support */
+		kvm_inject_nested_sync(vcpu, esr);
+		break;
+	case 0:
+		perm = kvm_is_write_fault(vcpu) ? vt->wr.pw && vt->hpa_writable : vt->wr.pr;
+		if (!perm)
 			handle_vncr_perm(vcpu);
-			break;
-		case 0:
-			break;
-		}
-	} else {
-		WARN_ONCE(1, "Unhandled VNCR abort, ESR=%llx\n", esr);
+		break;
 	}
 
 	return 1;
-- 
2.47.3

[PATCH v3 4/5] KVM: arm64: nv: Inject SEA if guest VNCR isn't normal memory

[Oliver Upton]

When constructing an L1 VNCR mapping, KVM unconditionally uses cacheable
memory attributes, even if the underlying PFN isn't memory. This gets
particularly hairy if the endpoint doesn't support cacheable memory
attributes, potentially throwing an SError on writeback...

While KVM does permit cacheable memory attributes on certain PFNMAP
VMAs, kvm_translate_vncr() isn't currently grabbing the VMA. So do the
simpler thing for now and just reject everything that isn't memory.

Cc: stable@vger.kernel.org
Fixes: 2a359e072596 ("KVM: arm64: nv: Handle mapping of VNCR_EL2 at EL2")
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 arch/arm64/kvm/nested.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 7fffd86eee94..d4c9a9b05e3f 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -1419,6 +1419,17 @@ static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem)
 		writable = !(memslot->flags & KVM_MEM_READONLY);
 	}
 
+	/*
+	 * FIXME: This check is too restrictive as KVM allows cacheable memory
+	 * attributes for PFNMAP VMAs that have cacheable attributes in host
+	 * stage-1.
+	 */
+	if (!pfn_is_map_memory(pfn)) {
+		kvm_release_faultin_page(vcpu->kvm, page, true, false);
+		fail_s1_walk(&vt->wr, ESR_ELx_FSC_EXTABT, false);
+		return -EINVAL;
+	}
+
 	scoped_guard(write_lock, &vcpu->kvm->mmu_lock) {
 		if (mmu_invalidate_retry(vcpu->kvm, mmu_seq)) {
 			kvm_release_faultin_page(vcpu->kvm, page, true, false);
-- 
2.47.3