From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com> stable inclusion from stable-v6.6.106 commit f866eef8d1c65504d30923c3f14082ad294d0e6d category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/ICXM9O CVE: CVE-2025-40300 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- Commit 2f8f173413f1cbf52660d04df92d0069c4306d25 upstream. VMSCAPE is a vulnerability that exploits insufficient branch predictor isolation between a guest and a userspace hypervisor (like QEMU). Existing mitigations already protect kernel/KVM from a malicious guest. Userspace can additionally be protected by flushing the branch predictors after a VMexit. Since it is the userspace that consumes the poisoned branch predictors, conditionally issue an IBPB after a VMexit and before returning to userspace. Workloads that frequently switch between hypervisor and userspace will incur the most overhead from the new IBPB. This new IBPB is not integrated with the existing IBPB sites. For instance, a task can use the existing speculation control prctl() to get an IBPB at context switch time. With this implementation, the IBPB is doubled up: one at context switch and another before running userspace. The intent is to integrate and optimize these cases post-embargo. [ dhansen: elaborate on suboptimal IBPB solution ] Suggested-by: Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com> Reviewed-by: Borislav Petkov (AMD) <bp@alien8.de> Acked-by: Sean Christopherson <seanjc@google.com> Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Conflicts: arch/x86/include/asm/cpufeatures.h [context conflict] Signed-off-by: Bowen You <youbowen2@huawei.com> --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/entry-common.h | 7 +++++++ arch/x86/include/asm/nospec-branch.h | 2 ++ arch/x86/kernel/cpu/bugs.c | 8 ++++++++ arch/x86/kvm/x86.c | 9 +++++++++ 5 files changed, 27 insertions(+) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 1688c2c667fb..271ebb8fdf71 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -493,6 +493,7 @@ #define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */ #define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */ #define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */ +#define X86_FEATURE_IBPB_EXIT_TO_USER (21*32+14) /* Use IBPB on exit-to-userspace, see VMSCAPE bug */ /* HYGON-defined CPU features, CPUID level 0x8c860000:0 (EDX), word 29 */ #define X86_FEATURE_HYGON_SM3 (29*32 + 1) /* "sm3" SM3 instructions */ diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index fb2809b20b0a..bb0a5ecc807f 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -83,6 +83,13 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, * 8 (ia32) bits. */ choose_random_kstack_offset(rdtsc()); + + /* Avoid unnecessary reads of 'x86_ibpb_exit_to_user' */ + if (cpu_feature_enabled(X86_FEATURE_IBPB_EXIT_TO_USER) && + this_cpu_read(x86_ibpb_exit_to_user)) { + indirect_branch_prediction_barrier(); + this_cpu_write(x86_ibpb_exit_to_user, false); + } } #define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index ee642d26e304..b6a768e5909d 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -547,6 +547,8 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) extern u64 x86_pred_cmd; +DECLARE_PER_CPU(bool, x86_ibpb_exit_to_user); + static inline void indirect_branch_prediction_barrier(void) { alternative_msr_write(MSR_IA32_PRED_CMD, x86_pred_cmd, X86_FEATURE_USE_IBPB); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 7df458a6553e..4342947a2fa6 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -58,6 +58,14 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); DEFINE_PER_CPU(u64, x86_spec_ctrl_current); EXPORT_SYMBOL_GPL(x86_spec_ctrl_current); +/* + * Set when the CPU has run a potentially malicious guest. An IBPB will + * be needed to before running userspace. That IBPB will flush the branch + * predictor content. + */ +DEFINE_PER_CPU(bool, x86_ibpb_exit_to_user); +EXPORT_PER_CPU_SYMBOL_GPL(x86_ibpb_exit_to_user); + u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; EXPORT_SYMBOL_GPL(x86_pred_cmd); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 914153ae6e5f..64402ec72b2d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11002,6 +11002,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (vcpu->arch.guest_fpu.xfd_err) wrmsrl(MSR_IA32_XFD_ERR, 0); + /* + * Mark this CPU as needing a branch predictor flush before running + * userspace. Must be done before enabling preemption to ensure it gets + * set for the CPU that actually ran the guest, and not the CPU that it + * may migrate to. + */ + if (cpu_feature_enabled(X86_FEATURE_IBPB_EXIT_TO_USER)) + this_cpu_write(x86_ibpb_exit_to_user, true); + /* * Consume any pending interrupts, including the possible source of * VM-Exit on SVM and any ticks that occur between VM-Exit and now. -- 2.34.1