From 1b42f017415b46c317e71d41c34ec088417a1883 Mon Sep 17 00:00:00 2001 From: Pawan Gupta Date: Wed, 23 Oct 2019 11:30:45 +0200 Subject: x86/speculation/taa: Add mitigation for TSX Async Abort TSX Async Abort (TAA) is a side channel vulnerability to the internal buffers in some Intel processors similar to Microachitectural Data Sampling (MDS). In this case, certain loads may speculatively pass invalid data to dependent operations when an asynchronous abort condition is pending in a TSX transaction. This includes loads with no fault or assist condition. Such loads may speculatively expose stale data from the uarch data structures as in MDS. Scope of exposure is within the same-thread and cross-thread. This issue affects all current processors that support TSX, but do not have ARCH_CAP_TAA_NO (bit 8) set in MSR_IA32_ARCH_CAPABILITIES. On CPUs which have their IA32_ARCH_CAPABILITIES MSR bit MDS_NO=0, CPUID.MD_CLEAR=1 and the MDS mitigation is clearing the CPU buffers using VERW or L1D_FLUSH, there is no additional mitigation needed for TAA. On affected CPUs with MDS_NO=1 this issue can be mitigated by disabling the Transactional Synchronization Extensions (TSX) feature. A new MSR IA32_TSX_CTRL in future and current processors after a microcode update can be used to control the TSX feature. There are two bits in that MSR: * TSX_CTRL_RTM_DISABLE disables the TSX sub-feature Restricted Transactional Memory (RTM). * TSX_CTRL_CPUID_CLEAR clears the RTM enumeration in CPUID. The other TSX sub-feature, Hardware Lock Elision (HLE), is unconditionally disabled with updated microcode but still enumerated as present by CPUID(EAX=7).EBX{bit4}. The second mitigation approach is similar to MDS which is clearing the affected CPU buffers on return to user space and when entering a guest. Relevant microcode update is required for the mitigation to work. More details on this approach can be found here: https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html The TSX feature can be controlled by the "tsx" command line parameter. If it is force-enabled then "Clear CPU buffers" (MDS mitigation) is deployed. The effective mitigation state can be read from sysfs. [ bp: - massage + comments cleanup - s/TAA_MITIGATION_TSX_DISABLE/TAA_MITIGATION_TSX_DISABLED/g - Josh. - remove partial TAA mitigation in update_mds_branch_idle() - Josh. - s/tsx_async_abort_cmdline/tsx_async_abort_parse_cmdline/g ] Signed-off-by: Pawan Gupta Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Reviewed-by: Josh Poimboeuf --- arch/x86/kernel/cpu/bugs.c | 108 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 108 insertions(+) (limited to 'arch/x86/kernel/cpu/bugs.c') diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 91c2561b905f..58fe3746e333 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -39,6 +39,7 @@ static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); static void __init mds_select_mitigation(void); +static void __init taa_select_mitigation(void); /* The base value of the SPEC_CTRL MSR that always has to be preserved. */ u64 x86_spec_ctrl_base; @@ -105,6 +106,7 @@ void __init check_bugs(void) ssb_select_mitigation(); l1tf_select_mitigation(); mds_select_mitigation(); + taa_select_mitigation(); arch_smt_update(); @@ -268,6 +270,100 @@ static int __init mds_cmdline(char *str) } early_param("mds", mds_cmdline); +#undef pr_fmt +#define pr_fmt(fmt) "TAA: " fmt + +/* Default mitigation for TAA-affected CPUs */ +static enum taa_mitigations taa_mitigation __ro_after_init = TAA_MITIGATION_VERW; +static bool taa_nosmt __ro_after_init; + +static const char * const taa_strings[] = { + [TAA_MITIGATION_OFF] = "Vulnerable", + [TAA_MITIGATION_UCODE_NEEDED] = "Vulnerable: Clear CPU buffers attempted, no microcode", + [TAA_MITIGATION_VERW] = "Mitigation: Clear CPU buffers", + [TAA_MITIGATION_TSX_DISABLED] = "Mitigation: TSX disabled", +}; + +static void __init taa_select_mitigation(void) +{ + u64 ia32_cap; + + if (!boot_cpu_has_bug(X86_BUG_TAA)) { + taa_mitigation = TAA_MITIGATION_OFF; + return; + } + + /* TSX previously disabled by tsx=off */ + if (!boot_cpu_has(X86_FEATURE_RTM)) { + taa_mitigation = TAA_MITIGATION_TSX_DISABLED; + goto out; + } + + if (cpu_mitigations_off()) { + taa_mitigation = TAA_MITIGATION_OFF; + return; + } + + /* TAA mitigation is turned off on the cmdline (tsx_async_abort=off) */ + if (taa_mitigation == TAA_MITIGATION_OFF) + goto out; + + if (boot_cpu_has(X86_FEATURE_MD_CLEAR)) + taa_mitigation = TAA_MITIGATION_VERW; + else + taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; + + /* + * VERW doesn't clear the CPU buffers when MD_CLEAR=1 and MDS_NO=1. + * A microcode update fixes this behavior to clear CPU buffers. It also + * adds support for MSR_IA32_TSX_CTRL which is enumerated by the + * ARCH_CAP_TSX_CTRL_MSR bit. + * + * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode + * update is required. + */ + ia32_cap = x86_read_arch_cap_msr(); + if ( (ia32_cap & ARCH_CAP_MDS_NO) && + !(ia32_cap & ARCH_CAP_TSX_CTRL_MSR)) + taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; + + /* + * TSX is enabled, select alternate mitigation for TAA which is + * the same as MDS. Enable MDS static branch to clear CPU buffers. + * + * For guests that can't determine whether the correct microcode is + * present on host, enable the mitigation for UCODE_NEEDED as well. + */ + static_branch_enable(&mds_user_clear); + + if (taa_nosmt || cpu_mitigations_auto_nosmt()) + cpu_smt_disable(false); + +out: + pr_info("%s\n", taa_strings[taa_mitigation]); +} + +static int __init tsx_async_abort_parse_cmdline(char *str) +{ + if (!boot_cpu_has_bug(X86_BUG_TAA)) + return 0; + + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) { + taa_mitigation = TAA_MITIGATION_OFF; + } else if (!strcmp(str, "full")) { + taa_mitigation = TAA_MITIGATION_VERW; + } else if (!strcmp(str, "full,nosmt")) { + taa_mitigation = TAA_MITIGATION_VERW; + taa_nosmt = true; + } + + return 0; +} +early_param("tsx_async_abort", tsx_async_abort_parse_cmdline); + #undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt @@ -786,6 +882,7 @@ static void update_mds_branch_idle(void) } #define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n" +#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n" void cpu_bugs_smt_update(void) { @@ -819,6 +916,17 @@ void cpu_bugs_smt_update(void) break; } + switch (taa_mitigation) { + case TAA_MITIGATION_VERW: + case TAA_MITIGATION_UCODE_NEEDED: + if (sched_smt_active()) + pr_warn_once(TAA_MSG_SMT); + break; + case TAA_MITIGATION_TSX_DISABLED: + case TAA_MITIGATION_OFF: + break; + } + mutex_unlock(&spec_ctrl_mutex); } -- cgit From 6608b45ac5ecb56f9e171252229c39580cc85f0f Mon Sep 17 00:00:00 2001 From: Pawan Gupta Date: Wed, 23 Oct 2019 12:19:51 +0200 Subject: x86/speculation/taa: Add sysfs reporting for TSX Async Abort Add the sysfs reporting file for TSX Async Abort. It exposes the vulnerability and the mitigation state similar to the existing files for the other hardware vulnerabilities. Sysfs file path is: /sys/devices/system/cpu/vulnerabilities/tsx_async_abort Signed-off-by: Pawan Gupta Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Tested-by: Neelima Krishnan Reviewed-by: Mark Gross Reviewed-by: Tony Luck Reviewed-by: Greg Kroah-Hartman Reviewed-by: Josh Poimboeuf --- arch/x86/kernel/cpu/bugs.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'arch/x86/kernel/cpu/bugs.c') diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 58fe3746e333..43c647e19439 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1436,6 +1436,21 @@ static ssize_t mds_show_state(char *buf) sched_smt_active() ? "vulnerable" : "disabled"); } +static ssize_t tsx_async_abort_show_state(char *buf) +{ + if ((taa_mitigation == TAA_MITIGATION_TSX_DISABLED) || + (taa_mitigation == TAA_MITIGATION_OFF)) + return sprintf(buf, "%s\n", taa_strings[taa_mitigation]); + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + return sprintf(buf, "%s; SMT Host state unknown\n", + taa_strings[taa_mitigation]); + } + + return sprintf(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); +} + static char *stibp_state(void) { if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) @@ -1506,6 +1521,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_MDS: return mds_show_state(buf); + case X86_BUG_TAA: + return tsx_async_abort_show_state(buf); + default: break; } @@ -1542,4 +1560,9 @@ ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *bu { return cpu_show_common(dev, attr, buf, X86_BUG_MDS); } + +ssize_t cpu_show_tsx_async_abort(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_TAA); +} #endif -- cgit From db4d30fbb71b47e4ecb11c4efa5d8aad4b03dfae Mon Sep 17 00:00:00 2001 From: Vineela Tummalapalli Date: Mon, 4 Nov 2019 12:22:01 +0100 Subject: x86/bugs: Add ITLB_MULTIHIT bug infrastructure Some processors may incur a machine check error possibly resulting in an unrecoverable CPU lockup when an instruction fetch encounters a TLB multi-hit in the instruction TLB. This can occur when the page size is changed along with either the physical address or cache type. The relevant erratum can be found here: https://bugzilla.kernel.org/show_bug.cgi?id=205195 There are other processors affected for which the erratum does not fully disclose the impact. This issue affects both bare-metal x86 page tables and EPT. It can be mitigated by either eliminating the use of large pages or by using careful TLB invalidations when changing the page size in the page tables. Just like Spectre, Meltdown, L1TF and MDS, a new bit has been allocated in MSR_IA32_ARCH_CAPABILITIES (PSCHANGE_MC_NO) and will be set on CPUs which are mitigated against this issue. Signed-off-by: Vineela Tummalapalli Co-developed-by: Pawan Gupta Signed-off-by: Pawan Gupta Signed-off-by: Paolo Bonzini Signed-off-by: Thomas Gleixner --- arch/x86/kernel/cpu/bugs.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'arch/x86/kernel/cpu/bugs.c') diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 43c647e19439..5364beda8c61 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1419,6 +1419,11 @@ static ssize_t l1tf_show_state(char *buf) } #endif +static ssize_t itlb_multihit_show_state(char *buf) +{ + return sprintf(buf, "Processor vulnerable\n"); +} + static ssize_t mds_show_state(char *buf) { if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { @@ -1524,6 +1529,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_TAA: return tsx_async_abort_show_state(buf); + case X86_BUG_ITLB_MULTIHIT: + return itlb_multihit_show_state(buf); + default: break; } @@ -1565,4 +1573,9 @@ ssize_t cpu_show_tsx_async_abort(struct device *dev, struct device_attribute *at { return cpu_show_common(dev, attr, buf, X86_BUG_TAA); } + +ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT); +} #endif -- cgit From b8e8c8303ff28c61046a4d0f6ea99aea609a7dc0 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 4 Nov 2019 12:22:02 +0100 Subject: kvm: mmu: ITLB_MULTIHIT mitigation With some Intel processors, putting the same virtual address in the TLB as both a 4 KiB and 2 MiB page can confuse the instruction fetch unit and cause the processor to issue a machine check resulting in a CPU lockup. Unfortunately when EPT page tables use huge pages, it is possible for a malicious guest to cause this situation. Add a knob to mark huge pages as non-executable. When the nx_huge_pages parameter is enabled (and we are using EPT), all huge pages are marked as NX. If the guest attempts to execute in one of those pages, the page is broken down into 4K pages, which are then marked executable. This is not an issue for shadow paging (except nested EPT), because then the host is in control of TLB flushes and the problematic situation cannot happen. With nested EPT, again the nested guest can cause problems shadow and direct EPT is treated in the same way. [ tglx: Fixup default to auto and massage wording a bit ] Originally-by: Junaid Shahid Signed-off-by: Paolo Bonzini Signed-off-by: Thomas Gleixner --- arch/x86/kernel/cpu/bugs.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel/cpu/bugs.c') diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 5364beda8c61..850005590167 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1257,6 +1257,9 @@ void x86_spec_ctrl_setup_ap(void) x86_amd_ssb_disable(); } +bool itlb_multihit_kvm_mitigation; +EXPORT_SYMBOL_GPL(itlb_multihit_kvm_mitigation); + #undef pr_fmt #define pr_fmt(fmt) "L1TF: " fmt @@ -1412,17 +1415,25 @@ static ssize_t l1tf_show_state(char *buf) l1tf_vmx_states[l1tf_vmx_mitigation], sched_smt_active() ? "vulnerable" : "disabled"); } + +static ssize_t itlb_multihit_show_state(char *buf) +{ + if (itlb_multihit_kvm_mitigation) + return sprintf(buf, "KVM: Mitigation: Split huge pages\n"); + else + return sprintf(buf, "KVM: Vulnerable\n"); +} #else static ssize_t l1tf_show_state(char *buf) { return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); } -#endif static ssize_t itlb_multihit_show_state(char *buf) { return sprintf(buf, "Processor vulnerable\n"); } +#endif static ssize_t mds_show_state(char *buf) { -- cgit From 012206a822a8b6ac09125bfaa210a95b9eb8f1c1 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 6 Nov 2019 20:26:46 -0600 Subject: x86/speculation/taa: Fix printing of TAA_MSG_SMT on IBRS_ALL CPUs For new IBRS_ALL CPUs, the Enhanced IBRS check at the beginning of cpu_bugs_smt_update() causes the function to return early, unintentionally skipping the MDS and TAA logic. This is not a problem for MDS, because there appears to be no overlap between IBRS_ALL and MDS-affected CPUs. So the MDS mitigation would be disabled and nothing would need to be done in this function anyway. But for TAA, the TAA_MSG_SMT string will never get printed on Cascade Lake and newer. The check is superfluous anyway: when 'spectre_v2_enabled' is SPECTRE_V2_IBRS_ENHANCED, 'spectre_v2_user' is always SPECTRE_V2_USER_NONE, and so the 'spectre_v2_user' switch statement handles it appropriately by doing nothing. So just remove the check. Fixes: 1b42f017415b ("x86/speculation/taa: Add mitigation for TSX Async Abort") Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Reviewed-by: Tyler Hicks Reviewed-by: Borislav Petkov --- arch/x86/kernel/cpu/bugs.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'arch/x86/kernel/cpu/bugs.c') diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 850005590167..4c7b0fa15a19 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -886,10 +886,6 @@ static void update_mds_branch_idle(void) void cpu_bugs_smt_update(void) { - /* Enhanced IBRS implies STIBP. No update required. */ - if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) - return; - mutex_lock(&spec_ctrl_mutex); switch (spectre_v2_user) { -- cgit