From: Pawan Gupta pawan.kumar.gupta@linux.intel.com
stable inclusion from stable-v4.19.248 commit e0d1437042f0b491bf2cb7880628b0bd7783f80d category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5D5RS CVE: CVE-2022-21123,CVE-2022-21125,CVE-2022-21166
--------------------------------
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 [cascardo: arch/x86/kvm/vmx.c has been split and context adjustment at vmx_vcpu_run] [cascardo: moved functions so they are after struct vcpu_vmx definition] [cascardo: fb_clear is disabled/enabled around __vmx_vcpu_run] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Conflicts: arch/x86/kvm/vmx.c Signed-off-by: Yipeng Zou zouyipeng@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com Reviewed-by: Liao Chang liaochang1@huawei.com Signed-off-by: Yongqiang Liu liuyongqiang13@huawei.com --- arch/x86/include/asm/msr-index.h | 6 +++ arch/x86/kvm/vmx.c | 73 +++++++++++++++++++++++++++++++- arch/x86/kvm/x86.c | 4 ++ 3 files changed, 82 insertions(+), 1 deletion(-)
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index eb0d0d5a99c8..a29505c3d14d 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -115,6 +115,11 @@ * 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) /* @@ -132,6 +137,7 @@ /* 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.c b/arch/x86/kvm/vmx.c index 35ad46d13191..1869d1c4dcd0 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -212,6 +212,9 @@ 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; @@ -1045,6 +1048,8 @@ 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; };
enum segment_cache_field { @@ -2117,6 +2122,60 @@ static inline void __invept(unsigned long ext, u64 eptp, gpa_t gpa) BUG_ON(error); }
+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 struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) { int i; @@ -4348,9 +4407,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } break; } - ret = kvm_set_msr_common(vcpu, 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; }
@@ -6803,6 +6866,8 @@ 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); }
/* @@ -10818,6 +10883,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) kvm_arch_has_assigned_device(vcpu->kvm)) mds_clear_cpu_buffers();
+ vmx_disable_fb_clear(vmx); + asm( /* Store host registers */ "push %%" _ASM_DX "; push %%" _ASM_BP ";" @@ -10941,6 +11008,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) #endif );
+ vmx_enable_fb_clear(vmx); + /* * We do not use IBRS in the kernel. If this vCPU has used the * SPEC_CTRL MSR it may have left it on; save the value and @@ -14640,6 +14709,8 @@ static int __init vmx_init(void) } }
+ vmx_setup_fb_clear_ctrl(); + #ifdef CONFIG_KEXEC_CORE rcu_assign_pointer(crash_vmclear_loaded_vmcss, crash_vmclear_local_loaded_vmcss); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 06df5c23267a..5da2811219ec 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1228,6 +1228,10 @@ u64 kvm_get_arch_capabilities(void)
/* KVM does not emulate MSR_IA32_TSX_CTRL. */ data &= ~ARCH_CAP_TSX_CTRL_MSR; + + /* Guests don't need to know "Fill buffer clear control" exists */ + data &= ~ARCH_CAP_FB_CLEAR_CTRL; + return data; }