From 8c774604b6ecaca495fa3d27c21593269627f48f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 6 Aug 2026 10:10:21 +0100 Subject: [PATCH] KVM: arm64: Consider SCTLR_EL2.M when mapping the L1 VNCR page We record a VNCR TLB even when SCTLR_EL2.M is 0 in order to make our life easier. But this is not something that the architecture anticipate. As a consequence, a hypervisor is free to set VNCR_EL2 to some PA when SCTLR_EL2.M==0, use it to run a guest which indirectly accesses the VNCR page, then eventually set SCTLR_EL2.M==1 with the same VA. Yes, this is odd, but apparently legal. A common trick in HW is to invalidate the TLBs on SCTLR_ELx.M being flipped. But doing this is a not a good idea for us (we'd need to trap SCTLR accesses), and wouldn't scale as we nest deeper. Instead, use the fact that the S1 MMU being off at the point of translation is cached in our TLB, and if it doesn't match the current MMU state, leave the VNCR unmapped. Fixes: 2a359e072596f ("KVM: arm64: nv: Handle mapping of VNCR_EL2 at EL2") Signed-off-by: Marc Zyngier Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260806091026.620700-4-maz@kernel.org Signed-off-by: Oliver Upton --- arch/arm64/include/asm/kvm_nested.h | 7 +++++++ arch/arm64/kvm/at.c | 2 -- arch/arm64/kvm/nested.c | 4 ++++ 3 files changed, 11 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h index 012d711034d1..bfed664d823b 100644 --- a/arch/arm64/include/asm/kvm_nested.h +++ b/arch/arm64/include/asm/kvm_nested.h @@ -388,6 +388,8 @@ struct s1_walk_result { bool failed; }; +#define S1_MMU_DISABLED (-127) + static inline void fail_s1_walk(struct s1_walk_result *wr, u8 fst, bool s1ptw) { wr->fst = fst; @@ -396,6 +398,11 @@ static inline void fail_s1_walk(struct s1_walk_result *wr, u8 fst, bool s1ptw) wr->failed = true; } +static inline bool s1_walk_translated(struct s1_walk_result *wr) +{ + return wr->level != S1_MMU_DISABLED; +} + 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 640f2dc00a8b..0926426b8798 100644 --- a/arch/arm64/kvm/at.c +++ b/arch/arm64/kvm/at.c @@ -11,8 +11,6 @@ #include #include -#define S1_MMU_DISABLED (-127) - static int get_ia_size(struct s1_walk_info *wi) { return 64 - wi->txsz; diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 035cda256e2a..27bc7ee4b338 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -1578,6 +1578,10 @@ static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu) if (!vt->valid) return; + /* We cache the MMU state in the TLB. Check that it matches. */ + if (!!(vcpu_read_sys_reg(vcpu, SCTLR_EL2) & SCTLR_ELx_M) != s1_walk_translated(&vt->wr)) + return; + if (read_vncr_el2(vcpu) != vt->gva) return;