From: Pawan Gupta pawan.kumar.gupta@linux.intel.com
stable inclusion from stable-v5.10.123 commit bde15fdcce44956278b4f50680b7363ca126ffb9 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5D5RS CVE: CVE-2022-21123,CVE-2022-21125,CVE-2022-21166
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=l...
--------------------------------
commit 027bbb884be006b05d9c577d6401686053aa789e upstream
The enumeration of MD_CLEAR in CPUID(EAX=7,ECX=0).EDX{bit 10} is not an accurate indicator on all CPUs of whether the VERW instruction will overwrite fill buffers. FB_CLEAR enumeration in IA32_ARCH_CAPABILITIES{bit 17} covers the case of CPUs that are not vulnerable to MDS/TAA, indicating that microcode does overwrite fill buffers.
Guests running in VMM environments may not be aware of all the capabilities/vulnerabilities of the host CPU. Specifically, a guest may apply MDS/TAA mitigations when a virtual CPU is enumerated as vulnerable to MDS/TAA even when the physical CPU is not. On CPUs that enumerate FB_CLEAR_CTRL the VMM may set FB_CLEAR_DIS to skip overwriting of fill buffers by the VERW instruction. This is done by setting FB_CLEAR_DIS during VMENTER and resetting on VMEXIT. For guests that enumerate FB_CLEAR (explicitly asking for fill buffer clear capability) the VMM will not use FB_CLEAR_DIS.
Irrespective of guest state, host overwrites CPU buffers before VMENTER to protect itself from an MMIO capable guest, as part of mitigation for MMIO Stale Data vulnerabilities.
Signed-off-by: Pawan Gupta pawan.kumar.gupta@linux.intel.com Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Conflicts: arch/x86/kvm/vmx/vmx.h Signed-off-by: Yipeng Zou zouyipeng@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Reviewed-by: Liao Chang liaochang1@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- arch/x86/include/asm/msr-index.h | 6 +++ arch/x86/kvm/vmx/vmx.c | 69 ++++++++++++++++++++++++++ arch/x86/kvm/vmx/vmx.h | 2 + arch/x86/kvm/x86.c | 3 ++ tools/arch/x86/include/asm/msr-index.h | 6 +++ 5 files changed, 86 insertions(+)
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index de883d3520d8..2b0af5eb5131 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -133,6 +133,11 @@ * VERW clears CPU fill buffer * even on MDS_NO CPUs. */ +#define ARCH_CAP_FB_CLEAR_CTRL BIT(18) /* + * MSR_IA32_MCU_OPT_CTRL[FB_CLEAR_DIS] + * bit available to control VERW + * behavior. + */
#define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* @@ -150,6 +155,7 @@ /* SRBDS support */ #define MSR_IA32_MCU_OPT_CTRL 0x00000123 #define RNGDS_MITG_DIS BIT(0) +#define FB_CLEAR_DIS BIT(3) /* CPU Fill buffer clear disable */
#define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index ba6a34ab9247..79889d27aa5b 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -226,6 +226,9 @@ static const struct { #define L1D_CACHE_ORDER 4 static void *vmx_l1d_flush_pages;
+/* Control for disabling CPU Fill buffer clear */ +static bool __read_mostly vmx_fb_clear_ctrl_available; + static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) { struct page *page; @@ -357,6 +360,60 @@ static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp) return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option); }
+static void vmx_setup_fb_clear_ctrl(void) +{ + u64 msr; + + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES) && + !boot_cpu_has_bug(X86_BUG_MDS) && + !boot_cpu_has_bug(X86_BUG_TAA)) { + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr); + if (msr & ARCH_CAP_FB_CLEAR_CTRL) + vmx_fb_clear_ctrl_available = true; + } +} + +static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx) +{ + u64 msr; + + if (!vmx->disable_fb_clear) + return; + + rdmsrl(MSR_IA32_MCU_OPT_CTRL, msr); + msr |= FB_CLEAR_DIS; + wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr); + /* Cache the MSR value to avoid reading it later */ + vmx->msr_ia32_mcu_opt_ctrl = msr; +} + +static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) +{ + if (!vmx->disable_fb_clear) + return; + + vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS; + wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl); +} + +static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) +{ + vmx->disable_fb_clear = vmx_fb_clear_ctrl_available; + + /* + * If guest will not execute VERW, there is no need to set FB_CLEAR_DIS + * at VMEntry. Skip the MSR read/write when a guest has no use case to + * execute VERW. + */ + if ((vcpu->arch.arch_capabilities & ARCH_CAP_FB_CLEAR) || + ((vcpu->arch.arch_capabilities & ARCH_CAP_MDS_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_TAA_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_PSDP_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_FBSDP_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_SBDR_SSDP_NO))) + vmx->disable_fb_clear = false; +} + static const struct kernel_param_ops vmentry_l1d_flush_ops = { .set = vmentry_l1d_flush_set, .get = vmentry_l1d_flush_get, @@ -2259,6 +2316,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) ret = kvm_set_msr_common(vcpu, msr_info); }
+ /* FB_CLEAR may have changed, also update the FB_CLEAR_DIS behavior */ + if (msr_index == MSR_IA32_ARCH_CAPABILITIES) + vmx_update_fb_clear_dis(vcpu, vmx); + return ret; }
@@ -4531,6 +4592,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vpid_sync_context(vmx->vpid); if (init_event) vmx_clear_hlt(vcpu); + + vmx_update_fb_clear_dis(vcpu, vmx); }
static void enable_irq_window(struct kvm_vcpu *vcpu) @@ -6714,6 +6777,8 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, kvm_arch_has_assigned_device(vcpu->kvm)) mds_clear_cpu_buffers();
+ vmx_disable_fb_clear(vmx); + if (vcpu->arch.cr2 != native_read_cr2()) native_write_cr2(vcpu->arch.cr2);
@@ -6722,6 +6787,8 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
vcpu->arch.cr2 = native_read_cr2();
+ vmx_enable_fb_clear(vmx); + /* * VMEXIT disables interrupts (host state), but tracing and lockdep * have them in state 'on' as recorded before entering guest mode. @@ -8108,6 +8175,8 @@ static int __init vmx_init(void) return r; }
+ vmx_setup_fb_clear_ctrl(); + for_each_possible_cpu(cpu) { INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index c0b52498e4bb..05eca210a5ff 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -325,6 +325,8 @@ struct vcpu_vmx { u64 msr_ia32_feature_control; u64 msr_ia32_feature_control_valid_bits; u64 ept_pointer; + u64 msr_ia32_mcu_opt_ctrl; + bool disable_fb_clear;
struct pt_desc pt_desc; struct lbr_desc lbr_desc; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index eb6c42e40ec4..1f857bc5ac6e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1459,6 +1459,9 @@ static u64 kvm_get_arch_capabilities(void) */ }
+ /* Guests don't need to know "Fill buffer clear control" exists */ + data &= ~ARCH_CAP_FB_CLEAR_CTRL; + return data; }
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 8e343fc95ae6..7b9259868243 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -133,6 +133,11 @@ * VERW clears CPU fill buffer * even on MDS_NO CPUs. */ +#define ARCH_CAP_FB_CLEAR_CTRL BIT(18) /* + * MSR_IA32_MCU_OPT_CTRL[FB_CLEAR_DIS] + * bit available to control VERW + * behavior. + */
#define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* @@ -150,6 +155,7 @@ /* SRBDS support */ #define MSR_IA32_MCU_OPT_CTRL 0x00000123 #define RNGDS_MITG_DIS BIT(0) +#define FB_CLEAR_DIS BIT(3) /* CPU Fill buffer clear disable */
#define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175