From mboxrd@z Thu Jan 1 00:00:00 1970 From: jintack.lim@linaro.org (Jintack Lim) Date: Mon, 2 Oct 2017 22:11:13 -0500 Subject: [RFC PATCH v2 31/31] KVM: arm64: Fixes to toggle_cache for nesting In-Reply-To: <1507000273-3735-1-git-send-email-jintack.lim@linaro.org> References: <1507000273-3735-1-git-send-email-jintack.lim@linaro.org> Message-ID: <1507000273-3735-29-git-send-email-jintack.lim@linaro.org> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org From: Christoffer Dall So far we were flushing almost the entire universe whenever a VM would load/unload the SCTLR_EL1 and the two versions of that register had different MMU enabled settings. This turned out to be so slow that it prevented forward progress for a nested VM, because a scheduler timer tick interrupt would always be pending when we reached the nested VM. To avoid this problem, we consider the SCTLR_EL2 when evaluating if caches are on or off when entering virtual EL2 (because this is the value that we end up shadowing onto the hardware EL1 register). Signed-off-by: Christoffer Dall Signed-off-by: Jintack Lim --- arch/arm64/include/asm/kvm_mmu.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 601f431..7a1c581 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -240,7 +240,10 @@ static inline bool kvm_page_empty(void *ptr) static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) { - return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101; + if (vcpu_mode_el2(vcpu)) + return (vcpu_sys_reg(vcpu, SCTLR_EL2) & 0b101) == 0b101; + else + return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101; } static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, -- 1.9.1