[PATCH OLK-6.6 0/3] CVE-2025-40300
CVE-2025-40300 Pawan Gupta (3): x86/vmscape: Add conditional IBPB mitigation x86/vmscape: Enumerate VMSCAPE bug x86/vmscape: Enable the mitigation .../ABI/testing/sysfs-devices-system-cpu | 1 + .../admin-guide/kernel-parameters.txt | 11 +++ arch/x86/Kconfig | 8 ++ arch/x86/include/asm/cpufeatures.h | 2 + arch/x86/include/asm/entry-common.h | 7 ++ arch/x86/include/asm/nospec-branch.h | 2 + arch/x86/kernel/cpu/bugs.c | 86 +++++++++++++++++++ arch/x86/kernel/cpu/common.c | 58 +++++++++---- arch/x86/kvm/x86.c | 9 ++ drivers/base/cpu.c | 3 + include/linux/cpu.h | 1 + 11 files changed, 170 insertions(+), 18 deletions(-) -- 2.34.1
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
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com> stable inclusion from stable-v6.6.106 commit 813cb831439c754922687d1562ec02446f9aa8ae 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 a508cec6e5215a3fbc7e73ae86a5c5602187934d upstream. The VMSCAPE vulnerability may allow a guest to cause Branch Target Injection (BTI) in userspace hypervisors. Kernels (both host and guest) have existing defenses against direct BTI attacks from guests. There are also inter-process BTI mitigations which prevent processes from attacking each other. However, the threat in this case is to a userspace hypervisor within the same process as the attacker. Userspace hypervisors have access to their own sensitive data like disk encryption keys and also typically have access to all guest data. This means guest userspace may use the hypervisor as a confused deputy to attack sensitive guest kernel data. There are no existing mitigations for these attacks. Introduce X86_BUG_VMSCAPE for this vulnerability and set it on affected Intel and AMD CPUs. Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Reviewed-by: Borislav Petkov (AMD) <bp@alien8.de> 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 arch/x86/kernel/cpu/common.c [context conflict] Signed-off-by: Bowen You <youbowen2@huawei.com> --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/kernel/cpu/common.c | 58 ++++++++++++++++++++---------- 2 files changed, 41 insertions(+), 18 deletions(-) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 271ebb8fdf71..7e1cf4af7ba5 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -551,4 +551,5 @@ #define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ #define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */ #define X86_BUG_IBPB_NO_RET X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */ +#define X86_BUG_VMSCAPE X86_BUG( 1*32+10) /* "vmscape" CPU is affected by VMSCAPE attacks from guests */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index f337ff292ca3..88d6dd9fa0ad 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1280,6 +1280,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define GDS BIT(6) /* CPU is affected by Register File Data Sampling */ #define RFDS BIT(7) +/* CPU is affected by VMSCAPE */ +#define VMSCAPE BIT(11) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1291,40 +1293,52 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(BROADWELL_G, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPPINGS(CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED), + VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPINGS(0x0, 0x5), VMSCAPE), + VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | VMSCAPE), + VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS | VMSCAPE), + VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS | VMSCAPE), + VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x0, 0xb), VMSCAPE), + VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS | VMSCAPE), + VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x0, 0xc), VMSCAPE), + VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS | VMSCAPE), + VULNBL_INTEL_STEPPINGS(CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED | VMSCAPE), VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS), VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO | GDS), - VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS | VMSCAPE), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED | VMSCAPE), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS | VMSCAPE), VULNBL_INTEL_STEPPINGS(TIGERLAKE_L, X86_STEPPING_ANY, GDS), VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS), VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(ALDERLAKE, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(ALDERLAKE_L, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(RAPTORLAKE, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(RAPTORLAKE_P, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(RAPTORLAKE_S, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(ATOM_GRACEMONT, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE, X86_STEPPING_ANY, RFDS | VMSCAPE), + VULNBL_INTEL_STEPPINGS(ALDERLAKE_L, X86_STEPPING_ANY, RFDS | VMSCAPE), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE, X86_STEPPING_ANY, RFDS | VMSCAPE), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE_P, X86_STEPPING_ANY, RFDS | VMSCAPE), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE_S, X86_STEPPING_ANY, RFDS | VMSCAPE), + VULNBL_INTEL_STEPPINGS(METEORLAKE_L, X86_STEPPING_ANY, VMSCAPE), + VULNBL_INTEL_STEPPINGS(ARROWLAKE_H, X86_STEPPING_ANY, VMSCAPE), + VULNBL_INTEL_STEPPINGS(ARROWLAKE, X86_STEPPING_ANY, VMSCAPE), + VULNBL_INTEL_STEPPINGS(ARROWLAKE_U, X86_STEPPING_ANY, VMSCAPE), + VULNBL_INTEL_STEPPINGS(LUNARLAKE_M, X86_STEPPING_ANY, VMSCAPE), + VULNBL_INTEL_STEPPINGS(SAPPHIRERAPIDS_X,X86_STEPPING_ANY, VMSCAPE), + VULNBL_INTEL_STEPPINGS(GRANITERAPIDS_X, X86_STEPPING_ANY, VMSCAPE), + VULNBL_INTEL_STEPPINGS(EMERALDRAPIDS_X, X86_STEPPING_ANY, VMSCAPE), + VULNBL_INTEL_STEPPINGS(ATOM_GRACEMONT, X86_STEPPING_ANY, RFDS | VMSCAPE), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO | RFDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT, X86_STEPPING_ANY, RFDS), VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_D, X86_STEPPING_ANY, RFDS), VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_PLUS, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_CRESTMONT_X, X86_STEPPING_ANY, VMSCAPE), VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), - VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO), - VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO), - VULNBL_AMD(0x19, SRSO), + VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO | VMSCAPE), + VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO | VMSCAPE), + VULNBL_AMD(0x19, SRSO | VMSCAPE), {} }; @@ -1494,6 +1508,14 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_AMD_IBPB) && !cpu_has(c, X86_FEATURE_AMD_IBPB_RET)) setup_force_cpu_bug(X86_BUG_IBPB_NO_RET); + /* + * Set the bug only on bare-metal. A nested hypervisor should already be + * deploying IBPB to isolate itself from nested guests. + */ + if (cpu_matches(cpu_vuln_blacklist, VMSCAPE) && + !boot_cpu_has(X86_FEATURE_HYPERVISOR)) + setup_force_cpu_bug(X86_BUG_VMSCAPE); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; -- 2.34.1
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com> stable inclusion from stable-v6.6.106 commit 556c1ad666ad90c50ec8fccb930dd5046cfbecfb 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 556c1ad666ad90c50ec8fccb930dd5046cfbecfb upstream. Enable the previously added mitigation for VMscape. Add the cmdline vmscape={off|ibpb|force} and sysfs reporting. Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Reviewed-by: Borislav Petkov (AMD) <bp@alien8.de> Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Conflicts: arch/x86/Kconfig drivers/base/cpu.c include/linux/cpu.h arch/x86/kernel/cpu/bugs.c Documentation/ABI/testing/sysfs-devices-system-cpu [context conflict] Signed-off-by: Bowen You <youbowen2@huawei.com> --- .../ABI/testing/sysfs-devices-system-cpu | 1 + .../admin-guide/kernel-parameters.txt | 11 +++ arch/x86/Kconfig | 8 ++ arch/x86/kernel/cpu/bugs.c | 78 +++++++++++++++++++ drivers/base/cpu.c | 3 + include/linux/cpu.h | 1 + 6 files changed, 102 insertions(+) diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 2dda58587ce4..9783a0631ec8 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -565,6 +565,7 @@ What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/spectre_v2 /sys/devices/system/cpu/vulnerabilities/srbds /sys/devices/system/cpu/vulnerabilities/tsx_async_abort + /sys/devices/system/cpu/vulnerabilities/vmscape Date: January 2018 Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> Description: Information about CPU vulnerabilities diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 97b63dc11457..9b6210ea94a4 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3427,6 +3427,7 @@ srbds=off [X86,INTEL] ssbd=force-off [ARM64] tsx_async_abort=off [X86] + vmscape=off [X86] Exceptions: This does not have any effect on @@ -7207,6 +7208,16 @@ vmpoff= [KNL,S390] Perform z/VM CP command after power off. Format: <command> + vmscape= [X86] Controls mitigation for VMscape attacks. + VMscape attacks can leak information from a userspace + hypervisor to a guest via speculative side-channels. + + off - disable the mitigation + ibpb - use Indirect Branch Prediction Barrier + (IBPB) mitigation (default) + force - force vulnerability detection even on + unaffected processors + vsyscall= [X86-64] Controls the behavior of vsyscalls (i.e. calls to fixed addresses of 0xffffffffff600x00 from legacy diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e8c26aae7057..2c8b8407cf0a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2675,6 +2675,14 @@ config MITIGATION_SPECTRE_BHI indirect branches. See <file:Documentation/admin-guide/hw-vuln/spectre.rst> +config MITIGATION_VMSCAPE + bool "Mitigate VMSCAPE" + depends on KVM + default y + help + Enable mitigation for VMSCAPE attacks. VMSCAPE is a hardware security + vulnerability on Intel and AMD CPUs that may allow a guest to do + Spectre v2 style attacks on userspace hypervisor. endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 4342947a2fa6..93571dfca4a6 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -49,6 +49,7 @@ static void __init srbds_select_mitigation(void); static void __init l1d_flush_select_mitigation(void); static void __init srso_select_mitigation(void); static void __init gds_select_mitigation(void); +static void __init vmscape_select_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -183,6 +184,7 @@ void __init cpu_select_mitigations(void) */ srso_select_mitigation(); gds_select_mitigation(); + vmscape_select_mitigation(); } /* @@ -2689,6 +2691,68 @@ static void __init srso_select_mitigation(void) x86_pred_cmd = PRED_CMD_SBPB; } +#undef pr_fmt +#define pr_fmt(fmt) "VMSCAPE: " fmt + +enum vmscape_mitigations { + VMSCAPE_MITIGATION_NONE, + VMSCAPE_MITIGATION_AUTO, + VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER, + VMSCAPE_MITIGATION_IBPB_ON_VMEXIT, +}; + +static const char * const vmscape_strings[] = { + [VMSCAPE_MITIGATION_NONE] = "Vulnerable", + /* [VMSCAPE_MITIGATION_AUTO] */ + [VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER] = "Mitigation: IBPB before exit to userspace", + [VMSCAPE_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT", +}; + +static enum vmscape_mitigations vmscape_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_VMSCAPE) ? VMSCAPE_MITIGATION_AUTO : VMSCAPE_MITIGATION_NONE; + +static int __init vmscape_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) { + vmscape_mitigation = VMSCAPE_MITIGATION_NONE; + } else if (!strcmp(str, "ibpb")) { + vmscape_mitigation = VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER; + } else if (!strcmp(str, "force")) { + setup_force_cpu_bug(X86_BUG_VMSCAPE); + vmscape_mitigation = VMSCAPE_MITIGATION_AUTO; + } else { + pr_err("Ignoring unknown vmscape=%s option.\n", str); + } + + return 0; +} +early_param("vmscape", vmscape_parse_cmdline); + +static void __init vmscape_select_mitigation(void) +{ + if (cpu_mitigations_off() || + !boot_cpu_has_bug(X86_BUG_VMSCAPE) || + !boot_cpu_has(X86_FEATURE_IBPB)) { + vmscape_mitigation = VMSCAPE_MITIGATION_NONE; + return; + } + + if (vmscape_mitigation == VMSCAPE_MITIGATION_AUTO) + vmscape_mitigation = VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER; + + if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB || + srso_mitigation == SRSO_MITIGATION_IBPB_ON_VMEXIT) + vmscape_mitigation = VMSCAPE_MITIGATION_IBPB_ON_VMEXIT; + + if (vmscape_mitigation == VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER) + setup_force_cpu_cap(X86_FEATURE_IBPB_EXIT_TO_USER); + + pr_info("%s\n", vmscape_strings[vmscape_mitigation]); +} + #undef pr_fmt #define pr_fmt(fmt) fmt @@ -2925,6 +2989,11 @@ static ssize_t gds_show_state(char *buf) return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]); } +static ssize_t vmscape_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", vmscape_strings[vmscape_mitigation]); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -2983,6 +3052,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_RFDS: return rfds_show_state(buf); + case X86_BUG_VMSCAPE: + return vmscape_show_state(buf); + default: break; } @@ -3062,4 +3134,10 @@ ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attrib { return cpu_show_common(dev, attr, buf, X86_BUG_RFDS); } + + +ssize_t cpu_show_vmscape(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_VMSCAPE); +} #endif diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 738d66612229..7b09ff396a24 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -603,6 +603,7 @@ CPU_SHOW_VULN_FALLBACK(retbleed); CPU_SHOW_VULN_FALLBACK(spec_rstack_overflow); CPU_SHOW_VULN_FALLBACK(gds); CPU_SHOW_VULN_FALLBACK(reg_file_data_sampling); +CPU_SHOW_VULN_FALLBACK(vmscape); static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); @@ -618,6 +619,7 @@ static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL); static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling, NULL); +static DEVICE_ATTR(vmscape, 0444, cpu_show_vmscape, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -634,6 +636,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_spec_rstack_overflow.attr, &dev_attr_gather_data_sampling.attr, &dev_attr_reg_file_data_sampling.attr, + &dev_attr_vmscape.attr, NULL }; diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 75f0344bd3b9..e4079434a160 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -77,6 +77,7 @@ extern ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_vmscape(struct device *dev, struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, -- 2.34.1
反馈： 您发送到kernel@openeuler.org的补丁/补丁集，已成功转换为PR！ PR链接地址： https://gitee.com/openeuler/kernel/pulls/18360 邮件列表地址：https://mailweb.openeuler.org/archives/list/kernel@openeuler.org/message/INO... FeedBack: The patch(es) which you have sent to kernel@openeuler.org mailing list has been converted to a pull request successfully! Pull request link: https://gitee.com/openeuler/kernel/pulls/18360 Mailing list address: https://mailweb.openeuler.org/archives/list/kernel@openeuler.org/message/INO...
participants (2)
-
Bowen You -
patchwork bot