Home| summaryrefslogtreecommitdiff |
diff options
| author | Takashi Iwai <tiwai@suse.de> | 2019-05-02 17:15:46 +0200 |
|---|---|---|
| committer | Takashi Iwai <tiwai@suse.de> | 2019-05-02 17:15:46 +0200 |
| commit | 59c137b7188b55f3f4726c21b548db6db5f78895 (patch) | |
| tree | 0d451b7b2707d5d03b8e1f93fa0f49a9c2bb879c | |
| parent | 0518be22fa8b4b30a02cb2483a6964164fec63fe (diff) | |
| parent | 3bc3c8eb16aae4ebe954e717a6da30e87e150cc1 (diff) | |
Merge branch 'users/bpetkov/SLE15/15-bsc1111331-2' into SLE15rpm-4.12.14-150.17--sle15-updatesrpm-4.12.14-150.17
Pull x86 fixes from Borislav Petkov
suse-commit: bf13fb81c5073eaf79b2cb0b3d1bd48b6974c59a
43 files changed, 707 insertions, 182 deletions
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 6cae60929cb6..1afba2acce34 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -380,6 +380,7 @@ What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/spectre_v2 /sys/devices/system/cpu/vulnerabilities/spec_store_bypass /sys/devices/system/cpu/vulnerabilities/l1tf + /sys/devices/system/cpu/vulnerabilities/mds 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 b557af2832a8..9fb9ea189121 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2209,6 +2209,30 @@ Format: <first>,<last> Specifies range of consoles to be captured by the MDA. + mds= [X86,INTEL] + Control mitigation for the Micro-architectural Data + Sampling (MDS) vulnerability. + + Certain CPUs are vulnerable to an exploit against CPU + internal buffers which can forward information to a + disclosure gadget under certain conditions. + + In vulnerable processors, the speculatively + forwarded data can be used in a cache side channel + attack, to access data to which the attacker does + not have direct access. + + This parameter controls the MDS mitigation. The + options are: + + full - Enable MDS mitigation on vulnerable CPUs + full,nosmt - Enable MDS mitigation and disable + SMT on vulnerable CPUs + off - Unconditionally disable MDS mitigation + + Not specifying this option is equivalent to + mds=full. + mem=nn[KMG] [KNL,BOOT] Force usage of a specific amount of memory Amount of memory to be used when the kernel is not able to see the whole system memory or for test. @@ -2374,6 +2398,7 @@ spectre_v2_user=off [X86] spec_store_bypass_disable=off [X86,PPC] l1tf=off [X86] + mds=off [X86] auto (default) Mitigate all CPU vulnerabilities, but leave SMT @@ -2388,6 +2413,7 @@ if needed. This is for users who always want to be fully mitigated, even if it means losing SMT. Equivalent to: l1tf=flush,nosmt [X86] + mds=full,nosmt [X86] mminit_loglevel= [KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this diff --git a/Documentation/index.rst b/Documentation/index.rst index bc67dbf76eb0..102bb6987a9e 100644 --- a/Documentation/index.rst +++ b/Documentation/index.rst @@ -34,6 +34,7 @@ the kernel interface as seen by application developers. :maxdepth: 2 userspace-api/index + x86/index Introduction to kernel development diff --git a/Documentation/x86/conf.py b/Documentation/x86/conf.py new file mode 100644 index 000000000000..33c5c3142e20 --- /dev/null +++ b/Documentation/x86/conf.py @@ -0,0 +1,10 @@ +# -*- coding: utf-8; mode: python -*- + +project = "X86 architecture specific documentation" + +tags.add("subproject") + +latex_documents = [ + ('index', 'x86.tex', project, + 'The kernel development community', 'manual'), +] diff --git a/Documentation/x86/index.rst b/Documentation/x86/index.rst new file mode 100644 index 000000000000..ef389dcf1b1d --- /dev/null +++ b/Documentation/x86/index.rst @@ -0,0 +1,8 @@ +========================== +x86 architecture specifics +========================== + +.. toctree:: + :maxdepth: 1 + + mds diff --git a/Documentation/x86/mds.rst b/Documentation/x86/mds.rst new file mode 100644 index 000000000000..7e5b1d2fc29c --- /dev/null +++ b/Documentation/x86/mds.rst @@ -0,0 +1,224 @@ +Microarchitectural Data Sampling (MDS) mitigation +================================================= + +.. _mds: + +Overview +-------- + +Microarchitectural Data Sampling (MDS) is a family of side channel attacks +on internal buffers in Intel CPUs. The variants are: + + - Microarchitectural Store Buffer Data Sampling (MSBDS) (CVE-2018-12126) + - Microarchitectural Fill Buffer Data Sampling (MFBDS) (CVE-2018-12130) + - Microarchitectural Load Port Data Sampling (MLPDS) (CVE-2018-12127) + +MSBDS leaks Store Buffer Entries which can be speculatively forwarded to a +dependent load (store-to-load forwarding) as an optimization. The forward +can also happen to a faulting or assisting load operation for a different +memory address, which can be exploited under certain conditions. Store +buffers are partitioned between Hyper-Threads so cross thread forwarding is +not possible. But if a thread enters or exits a sleep state the store +buffer is repartitioned which can expose data from one thread to the other. + +MFBDS leaks Fill Buffer Entries. Fill buffers are used internally to manage +L1 miss situations and to hold data which is returned or sent in response +to a memory or I/O operation. Fill buffers can forward data to a load +operation and also write data to the cache. When the fill buffer is +deallocated it can retain the stale data of the preceding operations which +can then be forwarded to a faulting or assisting load operation, which can +be exploited under certain conditions. Fill buffers are shared between +Hyper-Threads so cross thread leakage is possible. + +MLPDS leaks Load Port Data. Load ports are used to perform load operations +from memory or I/O. The received data is then forwarded to the register +file or a subsequent operation. In some implementations the Load Port can +contain stale data from a previous operation which can be forwarded to +faulting or assisting loads under certain conditions, which again can be +exploited eventually. Load ports are shared between Hyper-Threads so cross +thread leakage is possible. + + +Exposure assumptions +-------------------- + +It is assumed that attack code resides in user space or in a guest with one +exception. The rationale behind this assumption is that the code construct +needed for exploiting MDS requires: + + - to control the load to trigger a fault or assist + + - to have a disclosure gadget which exposes the speculatively accessed + data for consumption through a side channel. + + - to control the pointer through which the disclosure gadget exposes the + data + +The existence of such a construct in the kernel cannot be excluded with +100% certainty, but the complexity involved makes it extremly unlikely. + +There is one exception, which is untrusted BPF. The functionality of +untrusted BPF is limited, but it needs to be thoroughly investigated +whether it can be used to create such a construct. + + +Mitigation strategy +------------------- + +All variants have the same mitigation strategy at least for the single CPU +thread case (SMT off): Force the CPU to clear the affected buffers. + +This is achieved by using the otherwise unused and obsolete VERW +instruction in combination with a microcode update. The microcode clears +the affected CPU buffers when the VERW instruction is executed. + +For virtualization there are two ways to achieve CPU buffer +clearing. Either the modified VERW instruction or via the L1D Flush +command. The latter is issued when L1TF mitigation is enabled so the extra +VERW can be avoided. If the CPU is not affected by L1TF then VERW needs to +be issued. + +If the VERW instruction with the supplied segment selector argument is +executed on a CPU without the microcode update there is no side effect +other than a small number of pointlessly wasted CPU cycles. + +This does not protect against cross Hyper-Thread attacks except for MSBDS +which is only exploitable cross Hyper-thread when one of the Hyper-Threads +enters a C-state. + +The kernel provides a function to invoke the buffer clearing: + + mds_clear_cpu_buffers() + +The mitigation is invoked on kernel/userspace, hypervisor/guest and C-state +(idle) transitions. + +As a special quirk to address virtualization scenarios where the host has +the microcode updated, but the hypervisor does not (yet) expose the +MD_CLEAR CPUID bit to guests, the kernel issues the VERW instruction in the +hope that it might actually clear the buffers. The state is reflected +accordingly. + +According to current knowledge additional mitigations inside the kernel +itself are not required because the necessary gadgets to expose the leaked +data cannot be controlled in a way which allows exploitation from malicious +user space or VM guests. + +Kernel internal mitigation modes +-------------------------------- + + ======= ============================================================ + off Mitigation is disabled. Either the CPU is not affected or + mds=off is supplied on the kernel command line + + full Mitigation is eanbled. CPU is affected and MD_CLEAR is + advertised in CPUID. + + vmwerv Mitigation is enabled. CPU is affected and MD_CLEAR is not + advertised in CPUID. That is mainly for virtualization + scenarios where the host has the updated microcode but the + hypervisor does not expose MD_CLEAR in CPUID. It's a best + effort approach without guarantee. + + full,nosmt The same as mds=full, with SMT disabled on vulnerable + CPUs. This is the complete mitigation. + + ======= ============================================================ + +If the CPU is affected and mds=off is not supplied on the kernel command +line then the kernel selects the appropriate mitigation mode depending on +the availability of the MD_CLEAR CPUID bit. + +Mitigation points +----------------- + +1. Return to user space +^^^^^^^^^^^^^^^^^^^^^^^ + + When transitioning from kernel to user space the CPU buffers are flushed + on affected CPUs when the mitigation is not disabled on the kernel + command line. The migitation is enabled through the static key + mds_user_clear. + + The mitigation is invoked in prepare_exit_to_usermode() which covers + most of the kernel to user space transitions. There are a few exceptions + which are not invoking prepare_exit_to_usermode() on return to user + space. These exceptions use the paranoid exit code. + + - Non Maskable Interrupt (NMI): + + Access to sensible data like keys, credentials in the NMI context is + mostly theoretical: The CPU can do prefetching or execute a + misspeculated code path and thereby fetching data which might end up + leaking through a buffer. + + But for mounting other attacks the kernel stack address of the task is + already valuable information. So in full mitigation mode, the NMI is + mitigated on the return from do_nmi() to provide almost complete + coverage. + + - Double fault (#DF): + + A double fault is usually fatal, but the ESPFIX workaround, which can + be triggered from user space through modify_ldt(2) is a recoverable + double fault. #DF uses the paranoid exit path, so explicit mitigation + in the double fault handler is required. + + - Machine Check Exception (#MC): + + Another corner case is a #MC which hits between the CPU buffer clear + invocation and the actual return to user. As this still is in kernel + space it takes the paranoid exit path which does not clear the CPU + buffers. So the #MC handler repopulates the buffers to some + extent. Machine checks are not reliably controllable and the window is + extremly small so mitigation would just tick a checkbox that this + theoretical corner case is covered. To keep the amount of special + cases small, ignore #MC. + + - Debug Exception (#DB): + + This takes the paranoid exit path only when the INT1 breakpoint is in + kernel space. #DB on a user space address takes the regular exit path, + so no extra mitigation required. + + +2. C-State transition +^^^^^^^^^^^^^^^^^^^^^ + + When a CPU goes idle and enters a C-State the CPU buffers need to be + cleared on affected CPUs when SMT is active. This addresses the + repartitioning of the store buffer when one of the Hyper-Threads enters + a C-State. + + When SMT is inactive, i.e. either the CPU does not support it or all + sibling threads are offline CPU buffer clearing is not required. + + The idle clearing is enabled on CPUs which are only affected by MSBDS + and not by any other MDS variant. The other MDS variants cannot be + protected against cross Hyper-Thread attacks because the Fill Buffer and + the Load Ports are shared. So on CPUs affected by other variants, the + idle clearing would be a window dressing exercise and is therefore not + activated. + + The invocation is controlled by the static key mds_idle_clear which is + switched depending on the chosen mitigation mode and the SMT state of + the system. + + The buffer clear is only invoked before entering the C-State to prevent + that stale data from the idling CPU from spilling to the Hyper-Thread + sibling after the store buffer got repartitioned and all entries are + available to the non idle sibling. + + When coming out of idle the store buffer is partitioned again so each + sibling has half of it available. The back from idle CPU could be then + speculatively exposed to contents of the sibling. The buffers are + flushed either on exit to user space or on VMENTER so malicious code + in user space or the guest cannot speculatively access them. + + The mitigation is hooked into all variants of halt()/mwait(), but does + not cover the legacy ACPI IO-Port mechanism because the ACPI idle driver + has been superseded by the intel_idle driver around 2010 and is + preferred on all affected CPUs which are expected to gain the MD_CLEAR + functionality in microcode. Aside of that the IO-Port mechanism is a + legacy interface which is only used on older systems which are either + not affected or do not receive microcode updates anymore. diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index b84b94ebdab4..60920243d703 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -30,6 +30,7 @@ #include <asm/vdso.h> #include <linux/uaccess.h> #include <asm/cpufeature.h> +#include <asm/nospec-branch.h> #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> @@ -208,6 +209,8 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) #endif user_enter_irqoff(); + + mds_user_clear_cpu_buffers(); } #define SYSCALL_EXIT_WORK_FLAGS \ diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index e597853ee884..9b7b777176bf 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3871,11 +3871,11 @@ __init int intel_pmu_init(void) pr_cont("Nehalem events, "); break; - case INTEL_FAM6_ATOM_PINEVIEW: - case INTEL_FAM6_ATOM_LINCROFT: - case INTEL_FAM6_ATOM_PENWELL: - case INTEL_FAM6_ATOM_CLOVERVIEW: - case INTEL_FAM6_ATOM_CEDARVIEW: + case INTEL_FAM6_ATOM_BONNELL: + case INTEL_FAM6_ATOM_BONNELL_MID: + case INTEL_FAM6_ATOM_SALTWELL: + case INTEL_FAM6_ATOM_SALTWELL_MID: + case INTEL_FAM6_ATOM_SALTWELL_TABLET: memcpy(hw_cache_event_ids, atom_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -3887,9 +3887,11 @@ __init int intel_pmu_init(void) pr_cont("Atom events, "); break; - case INTEL_FAM6_ATOM_SILVERMONT1: - case INTEL_FAM6_ATOM_SILVERMONT2: + case INTEL_FAM6_ATOM_SILVERMONT: + case INTEL_FAM6_ATOM_SILVERMONT_X: + case INTEL_FAM6_ATOM_SILVERMONT_MID: case INTEL_FAM6_ATOM_AIRMONT: + case INTEL_FAM6_ATOM_AIRMONT_MID: memcpy(hw_cache_event_ids, slm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs, @@ -3906,7 +3908,7 @@ __init int intel_pmu_init(void) break; case INTEL_FAM6_ATOM_GOLDMONT: - case INTEL_FAM6_ATOM_DENVERTON: + case INTEL_FAM6_ATOM_GOLDMONT_X: memcpy(hw_cache_event_ids, glm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs, diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 53da7f3aa6e0..37b48ec31c79 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -531,8 +531,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_ULT, hswult_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT1, slm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT2, slm_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT, slm_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT_X, slm_cstates), X86_CSTATES_MODEL(INTEL_FAM6_ATOM_AIRMONT, slm_cstates), X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_CORE, snb_cstates), diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index be0b1968d60a..68144a341903 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -61,8 +61,8 @@ static bool test_intel(int idx) case INTEL_FAM6_BROADWELL_GT3E: case INTEL_FAM6_BROADWELL_X: - case INTEL_FAM6_ATOM_SILVERMONT1: - case INTEL_FAM6_ATOM_SILVERMONT2: + case INTEL_FAM6_ATOM_SILVERMONT: + case INTEL_FAM6_ATOM_SILVERMONT_X: case INTEL_FAM6_ATOM_AIRMONT: if (idx == PERF_MSR_SMI) return true; diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 995d1b8e36e6..e283be0d79bd 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -342,6 +342,7 @@ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ #define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ +#define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ @@ -379,4 +380,6 @@ #define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ #define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */ #define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */ +#define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ +#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index bd00c57a3b2c..2d3649de0fac 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -50,19 +50,23 @@ /* "Small Core" Processors (Atom) */ -#define INTEL_FAM6_ATOM_PINEVIEW 0x1C -#define INTEL_FAM6_ATOM_LINCROFT 0x26 -#define INTEL_FAM6_ATOM_PENWELL 0x27 -#define INTEL_FAM6_ATOM_CLOVERVIEW 0x35 -#define INTEL_FAM6_ATOM_CEDARVIEW 0x36 -#define INTEL_FAM6_ATOM_SILVERMONT1 0x37 /* BayTrail/BYT / Valleyview */ -#define INTEL_FAM6_ATOM_SILVERMONT2 0x4D /* Avaton/Rangely */ -#define INTEL_FAM6_ATOM_AIRMONT 0x4C /* CherryTrail / Braswell */ -#define INTEL_FAM6_ATOM_MERRIFIELD 0x4A /* Tangier */ -#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Anniedale */ -#define INTEL_FAM6_ATOM_GOLDMONT 0x5C -#define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */ -#define INTEL_FAM6_ATOM_GEMINI_LAKE 0x7A +#define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ +#define INTEL_FAM6_ATOM_BONNELL_MID 0x26 /* Silverthorne, Lincroft */ + +#define INTEL_FAM6_ATOM_SALTWELL 0x36 /* Cedarview */ +#define INTEL_FAM6_ATOM_SALTWELL_MID 0x27 /* Penwell */ +#define INTEL_FAM6_ATOM_SALTWELL_TABLET 0x35 /* Cloverview */ + +#define INTEL_FAM6_ATOM_SILVERMONT 0x37 /* Bay Trail, Valleyview */ +#define INTEL_FAM6_ATOM_SILVERMONT_X 0x4D /* Avaton, Rangely */ +#define INTEL_FAM6_ATOM_SILVERMONT_MID 0x4A /* Merriefield */ + +#define INTEL_FAM6_ATOM_AIRMONT 0x4C /* Cherry Trail, Braswell */ +#define INTEL_FAM6_ATOM_AIRMONT_MID 0x5A /* Moorefield */ + +#define INTEL_FAM6_ATOM_GOLDMONT 0x5C /* Apollo Lake */ +#define INTEL_FAM6_ATOM_GOLDMONT_X 0x5F /* Denverton */ +#define INTEL_FAM6_ATOM_GOLDMONT_PLUS 0x7A /* Gemini Lake */ #define INTEL_FAM6_ATOM_TREMONT_X 0x86 /* Jacobswille */ /* Xeon Phi */ diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index d937781e1047..f6e182f34501 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -5,6 +5,8 @@ #ifndef __ASSEMBLY__ +#include <asm/nospec-branch.h> + /* Provide __cpuidle; we can't safely include <linux/cpu.h> */ #define __cpuidle __attribute__((__section__(".cpuidle.text"))) @@ -50,11 +52,13 @@ static inline void native_irq_enable(void) static inline __cpuidle void native_safe_halt(void) { + mds_idle_clear_cpu_buffers(); asm volatile("sti; hlt": : :"memory"); } static inline __cpuidle void native_halt(void) { + mds_idle_clear_cpu_buffers(); asm volatile("hlt": : :"memory"); } diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 812fef2839e8..207dc68a9434 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_MSR_INDEX_H #define _ASM_X86_MSR_INDEX_H +#include <linux/bits.h> + /* * CPU model specific register (MSR) numbers. * @@ -39,14 +41,14 @@ /* Intel MSRs. Some also available on other CPUs */ #define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */ -#define SPEC_CTRL_IBRS (1 << 0) /* Indirect Branch Restricted Speculation */ +#define SPEC_CTRL_IBRS BIT(0) /* Indirect Branch Restricted Speculation */ #define SPEC_CTRL_STIBP_SHIFT 1 /* Single Thread Indirect Branch Predictor (STIBP) bit */ -#define SPEC_CTRL_STIBP (1 << SPEC_CTRL_STIBP_SHIFT) /* STIBP mask */ +#define SPEC_CTRL_STIBP BIT(SPEC_CTRL_STIBP_SHIFT) /* STIBP mask */ #define SPEC_CTRL_SSBD_SHIFT 2 /* Speculative Store Bypass Disable bit */ -#define SPEC_CTRL_SSBD (1 << SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ +#define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ -#define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */ +#define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ #define MSR_PPIN_CTL 0x0000004e #define MSR_PPIN 0x0000004f @@ -68,20 +70,25 @@ #define MSR_MTRRcap 0x000000fe #define MSR_IA32_ARCH_CAPABILITIES 0x0000010a -#define ARCH_CAP_RDCL_NO (1 << 0) /* Not susceptible to Meltdown */ -#define ARCH_CAP_IBRS_ALL (1 << 1) /* Enhanced IBRS support */ -#define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH (1 << 3) /* Skip L1D flush on vmentry */ -#define ARCH_CAP_SSB_NO (1 << 4) /* - * Not susceptible to Speculative Store Bypass - * attack, so no Speculative Store Bypass - * control required. - */ +#define ARCH_CAP_RDCL_NO BIT(0) /* Not susceptible to Meltdown */ +#define ARCH_CAP_IBRS_ALL BIT(1) /* Enhanced IBRS support */ +#define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH BIT(3) /* Skip L1D flush on vmentry */ +#define ARCH_CAP_SSB_NO BIT(4) /* + * Not susceptible to Speculative Store Bypass + * attack, so no Speculative Store Bypass + * control required. + */ +#define ARCH_CAP_MDS_NO BIT(5) /* + * Not susceptible to + * Microarchitectural Data + * Sampling (MDS) vulnerabilities. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b -#define L1D_FLUSH (1 << 0) /* - * Writeback and invalidate the - * L1 data cache. - */ +#define L1D_FLUSH BIT(0) /* + * Writeback and invalidate the + * L1 data cache. + */ #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index e2cea24bfec9..634e144c0f75 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -40,6 +40,8 @@ static inline void __monitorx(const void *eax, unsigned long ecx, static inline void __mwait(unsigned long eax, unsigned long ecx) { + mds_idle_clear_cpu_buffers(); + /* "mwait %eax, %ecx;" */ asm volatile(".byte 0x0f, 0x01, 0xc9;" :: "a" (eax), "c" (ecx)); @@ -74,6 +76,8 @@ static inline void __mwait(unsigned long eax, unsigned long ecx) static inline void __mwaitx(unsigned long eax, unsigned long ebx, unsigned long ecx) { + /* No MDS buffer clear as this is AMD/HYGON only */ + /* "mwaitx %eax, %ebx, %ecx;" */ asm volatile(".byte 0x0f, 0x01, 0xfb;" :: "a" (eax), "b" (ebx), "c" (ecx)); @@ -81,6 +85,8 @@ static inline void __mwaitx(unsigned long eax, unsigned long ebx, static inline void __sti_mwait(unsigned long eax, unsigned long ecx) { + mds_idle_clear_cpu_buffers(); + trace_hardirqs_on(); /* "mwait %eax, %ecx;" */ asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 849acf1cdd5f..279c4e44b112 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -352,6 +352,56 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); +DECLARE_STATIC_KEY_FALSE(mds_user_clear); +DECLARE_STATIC_KEY_FALSE(mds_idle_clear); + +#include <asm/segment.h> + +/** + * mds_clear_cpu_buffers - Mitigation for MDS vulnerability + * + * This uses the otherwise unused and obsolete VERW instruction in + * combination with microcode which triggers a CPU buffer flush when the + * instruction is executed. + */ +static inline void mds_clear_cpu_buffers(void) +{ + static const u16 ds = __KERNEL_DS; + + /* + * Has to be the memory-operand variant because only that + * guarantees the CPU buffer flush functionality according to + * documentation. The register-operand variant does not. + * Works with any segment selector, but a valid writable + * data segment is the fastest variant. + * + * "cc" clobber is required because VERW modifies ZF. + */ + asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc"); +} + +/** + * mds_user_clear_cpu_buffers - Mitigation for MDS vulnerability + * + * Clear CPU buffers if the corresponding static key is enabled + */ +static inline void mds_user_clear_cpu_buffers(void) +{ + if (static_branch_likely(&mds_user_clear)) + mds_clear_cpu_buffers(); +} + +/** + * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability + * + * Clear CPU buffers if the corresponding static key is enabled + */ +static inline void mds_idle_clear_cpu_buffers(void) +{ + if (static_branch_likely(&mds_idle_clear)) + mds_clear_cpu_buffers(); +} + #endif /* __ASSEMBLY__ */ /* diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index b7a43f614d1e..44a5f5ae801a 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -984,4 +984,10 @@ enum l1tf_mitigations { extern enum l1tf_mitigations l1tf_mitigation; +enum mds_mitigations { + MDS_MITIGATION_OFF, + MDS_MITIGATION_FULL, + MDS_MITIGATION_VMWERV, +}; + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 8a080b942074..c1023744d228 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -34,6 +34,7 @@ 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); /* The base value of the SPEC_CTRL MSR that always has to be preserved. */ u64 x86_spec_ctrl_base; @@ -60,6 +61,13 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); /* Control unconditional IBPB in switch_mm() */ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb); +/* Control MDS CPU buffer clear before returning to user space */ +DEFINE_STATIC_KEY_FALSE(mds_user_clear); +EXPORT_SYMBOL_GPL(mds_user_clear); +/* Control MDS CPU buffer clear before idling (halt, mwait) */ +DEFINE_STATIC_KEY_FALSE(mds_idle_clear); +EXPORT_SYMBOL_GPL(mds_idle_clear); + void __init check_bugs(void) { identify_boot_cpu(); @@ -98,6 +106,10 @@ void __init check_bugs(void) l1tf_select_mitigation(); + mds_select_mitigation(); + + arch_smt_update(); + #ifdef CONFIG_X86_32 /* * Check whether we are able to run this kernel safely on SMP. @@ -328,6 +340,61 @@ early_param("l1tf", l1tf_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "MDS: " fmt + +/* Default mitigation for L1TF-affected CPUs */ +static enum mds_mitigations mds_mitigation __ro_after_init = MDS_MITIGATION_FULL; +static bool mds_nosmt __ro_after_init = false; + +static const char * const mds_strings[] = { + [MDS_MITIGATION_OFF] = "Vulnerable", + [MDS_MITIGATION_FULL] = "Mitigation: Clear CPU buffers", + [MDS_MITIGATION_VMWERV] = "Vulnerable: Clear CPU buffers attempted, no microcode", +}; + +static void __init mds_select_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) { + mds_mitigation = MDS_MITIGATION_OFF; + return; + } + + if (mds_mitigation == MDS_MITIGATION_FULL) { + if (!boot_cpu_has(X86_FEATURE_MD_CLEAR)) + mds_mitigation = MDS_MITIGATION_VMWERV; + + static_branch_enable(&mds_user_clear); + + if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) && + (mds_nosmt || cpu_mitigations_auto_nosmt())) + cpu_smt_disable(false); + } + + pr_info("%s\n", mds_strings[mds_mitigation]); +} + +static int __init mds_cmdline(char *str) +{ + if (!boot_cpu_has_bug(X86_BUG_MDS)) + return 0; + + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + mds_mitigation = MDS_MITIGATION_OFF; + else if (!strcmp(str, "full")) + mds_mitigation = MDS_MITIGATION_FULL; + else if (!strcmp(str, "full,nosmt")) { + mds_mitigation = MDS_MITIGATION_FULL; + mds_nosmt = true; + } + + return 0; +} +early_param("mds", mds_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = @@ -694,9 +761,6 @@ specv2_set_mode: /* Set up IBPB and STIBP depending on the general spectre V2 command */ spectre_v2_user_select_mitigation(cmd); - - /* Enable STIBP if appropriate */ - arch_smt_update(); } static void update_stibp_msr(void * __unused) @@ -730,6 +794,31 @@ static void update_indir_branch_cond(void) static_branch_disable(&switch_to_cond_stibp); } +#undef pr_fmt +#define pr_fmt(fmt) fmt + +/* Update the static key controlling the MDS CPU buffer clear in idle */ +static void update_mds_branch_idle(void) +{ + /* + * Enable the idle clearing if SMT is active on CPUs which are + * affected only by MSBDS and not any other MDS variant. + * + * The other variants cannot be mitigated when SMT is enabled, so + * clearing the buffers on idle just to prevent the Store Buffer + * repartitioning leak would be a window dressing exercise. + */ + if (!boot_cpu_has_bug(X86_BUG_MSBDS_ONLY)) + return; + + if (sched_smt_active()) + static_branch_enable(&mds_idle_clear); + else + static_branch_disable(&mds_idle_clear); +} + +#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" + void arch_smt_update(void) { /* Enhanced IBRS implies STIBP. No update required. */ @@ -750,6 +839,17 @@ void arch_smt_update(void) break; } + switch (mds_mitigation) { + case MDS_MITIGATION_FULL: + case MDS_MITIGATION_VMWERV: + if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY)) + pr_warn_once(MDS_MSG_SMT); + update_mds_branch_idle(); + break; + case MDS_MITIGATION_OFF: + break; + } + mutex_unlock(&spec_ctrl_mutex); } @@ -1093,6 +1193,23 @@ static ssize_t l1tf_show_state(char *buf) } #endif +static ssize_t mds_show_state(char *buf) +{ + if (!hypervisor_is_type(X86_HYPER_NATIVE)) { + return sprintf(buf, "%s; SMT Host state unknown\n", + mds_strings[mds_mitigation]); + } + + if (boot_cpu_has(X86_BUG_MSBDS_ONLY)) { + return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], + (mds_mitigation == MDS_MITIGATION_OFF ? "vulnerable" : + sched_smt_active() ? "mitigated" : "disabled")); + } + + return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); +} + static char *stibp_state(void) { if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) @@ -1159,6 +1276,10 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr return l1tf_show_state(buf); break; + + case X86_BUG_MDS: + return mds_show_state(buf); + default: break; } @@ -1190,4 +1311,9 @@ ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *b { return cpu_show_common(dev, attr, buf, X86_BUG_L1TF); } + +ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_MDS); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d6fe81bfa28a..1b53caf30805 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -898,85 +898,95 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #endif } -static const __initconst struct x86_cpu_id cpu_no_speculation[] = { - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW, X86_FEATURE_ANY }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW, X86_FEATURE_ANY }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT, X86_FEATURE_ANY }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL, X86_FEATURE_ANY }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW, X86_FEATURE_ANY }, - { X86_VENDOR_CENTAUR, 5 }, - { X86_VENDOR_INTEL, 5 }, - { X86_VENDOR_NSC, 5 }, - { X86_VENDOR_ANY, 4 }, +#define NO_SPECULATION BIT(0) +#define NO_MELTDOWN BIT(1) +#define NO_SSB BIT(2) +#define NO_L1TF BIT(3) +#define NO_MDS BIT(4) +#define MSBDS_ONLY BIT(5) + +#define VULNWL(_vendor, _family, _model, _whitelist) \ + { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } + +#define VULNWL_INTEL(model, whitelist) \ + VULNWL(INTEL, 6, INTEL_FAM6_##model, whitelist) + +#define VULNWL_AMD(family, whitelist) \ + VULNWL(AMD, family, X86_MODEL_ANY, whitelist) + +static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { + VULNWL(ANY, 4, X86_MODEL_ANY, NO_SPECULATION), + VULNWL(CENTAUR, 5, X86_MODEL_ANY, NO_SPECULATION), + VULNWL(INTEL, 5, X86_MODEL_ANY, NO_SPECULATION), + VULNWL(NSC, 5, X86_MODEL_ANY, NO_SPECULATION), + + /* Intel Family 6 */ + VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION), + VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION), + VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION), + VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION), + VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION), + + VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY), + VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY), + VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY), + VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY), + VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY), + VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY), + + VULNWL_INTEL(CORE_YONAH, NO_SSB), + + VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY), + + VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF), + VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF), + VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF), + + /* AMD Family 0xf - 0x12 */ + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), + + /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS), {} }; -static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { - { X86_VENDOR_AMD }, - {} -}; - -static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = { - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_CORE_YONAH }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM }, - { X86_VENDOR_CENTAUR, 5, }, - { X86_VENDOR_INTEL, 5, }, - { X86_VENDOR_NSC, 5, }, - { X86_VENDOR_AMD, 0x12, }, - { X86_VENDOR_AMD, 0x11, }, - { X86_VENDOR_AMD, 0x10, }, - { X86_VENDOR_AMD, 0xf, }, - { X86_VENDOR_ANY, 4, }, - {} -}; +static bool __init cpu_matches(unsigned long which) +{ + const struct x86_cpu_id *m = x86_match_cpu(cpu_vuln_whitelist); -static const __initconst struct x86_cpu_id cpu_no_l1tf[] = { - /* in addition to cpu_no_speculation */ - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MOOREFIELD }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_DENVERTON }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GEMINI_LAKE }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM }, - {} -}; + return m && !!(m->driver_data & which); +} static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = 0; + if (cpu_matches(NO_SPECULATION)) + return; + + setup_force_cpu_bug(X86_BUG_SPECTRE_V1); + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); - if (!x86_match_cpu(cpu_no_spec_store_bypass) && - !(ia32_cap & ARCH_CAP_SSB_NO) && + if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); - if (x86_match_cpu(cpu_no_speculation)) - return; - - setup_force_cpu_bug(X86_BUG_SPECTRE_V1); - setup_force_cpu_bug(X86_BUG_SPECTRE_V2); - if (ia32_cap & ARCH_CAP_IBRS_ALL) setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); - if (x86_match_cpu(cpu_no_meltdown)) + if (!cpu_matches(NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) { + setup_force_cpu_bug(X86_BUG_MDS); + if (cpu_matches(MSBDS_ONLY)) + setup_force_cpu_bug(X86_BUG_MSBDS_ONLY); + } + + if (cpu_matches(NO_MELTDOWN)) return; /* Rogue Data Cache Load? No! */ @@ -985,7 +995,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); - if (x86_match_cpu(cpu_no_l1tf)) + if (cpu_matches(NO_L1TF)) return; setup_force_cpu_bug(X86_BUG_L1TF); diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 18bc9b51ac9b..086cf1d1d71d 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -34,6 +34,7 @@ #include <asm/x86_init.h> #include <asm/reboot.h> #include <asm/cache.h> +#include <asm/nospec-branch.h> #define CREATE_TRACE_POINTS #include <trace/events/nmi.h> @@ -533,6 +534,9 @@ nmi_restart: write_cr2(this_cpu_read(nmi_cr2)); if (this_cpu_dec_return(nmi_state)) goto nmi_restart; + + if (user_mode(regs)) + mds_user_clear_cpu_buffers(); } NOKPROBE_SYMBOL(do_nmi); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 2501816f5d8b..68f65420ad0c 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -59,6 +59,7 @@ #include <asm/alternative.h> #include <asm/fpu/xstate.h> #include <asm/trace/mpx.h> +#include <asm/nospec-branch.h> #include <asm/mpx.h> #include <asm/vm86.h> @@ -393,6 +394,13 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) regs->ip = (unsigned long)general_protection; regs->sp = (unsigned long)&gpregs->orig_ax; + /* + * This situation can be triggered by userspace via + * modify_ldt(2) and the return does not take the regular + * user space exit, so a CPU buffer clear is required when + * MDS mitigation is enabled. + */ + mds_user_clear_cpu_buffers(); return; } #endif diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index a3633285a2e5..692c1cf24faf 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -620,7 +620,7 @@ unsigned long native_calibrate_tsc(void) case INTEL_FAM6_KABYLAKE_DESKTOP: crystal_khz = 24000; /* 24.0 MHz */ break; - case INTEL_FAM6_ATOM_DENVERTON: + case INTEL_FAM6_ATOM_GOLDMONT_X: crystal_khz = 25000; /* 25.0 MHz */ break; case INTEL_FAM6_ATOM_GOLDMONT: diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 873baf0b7799..087c5d40795a 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -367,7 +367,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 0x80000008.ebx */ const u32 kvm_cpuid_8000_0008_ebx_x86_features = - F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | F(AMD_SSB_NO); + F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | + F(AMD_SSB_NO) | F(AMD_STIBP); /* cpuid 0xC0000001.edx */ const u32 kvm_cpuid_C000_0001_edx_x86_features = @@ -395,7 +396,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | - F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES); + F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) | + F(MD_CLEAR); /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c82f029e2949..88701bdbb090 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -9717,8 +9717,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->__launched = vmx->loaded_vmcs->launched; + /* L1D Flush includes CPU buffer clear to mitigate MDS */ if (static_branch_unlikely(&vmx_l1d_should_flush)) vmx_l1d_flush(vcpu); + else if (static_branch_unlikely(&mds_user_clear)) + mds_clear_cpu_buffers(); asm( /* Store host registers */ diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c index d49d3be81953..ecb5866aaf84 100644 --- a/arch/x86/platform/atom/punit_atom_debug.c +++ b/arch/x86/platform/atom/punit_atom_debug.c @@ -154,8 +154,8 @@ static void punit_dbgfs_unregister(void) (kernel_ulong_t)&drv_data } static const struct x86_cpu_id intel_punit_cpu_ids[] = { - ICPU(INTEL_FAM6_ATOM_SILVERMONT1, punit_device_byt), - ICPU(INTEL_FAM6_ATOM_MERRIFIELD, punit_device_tng), + ICPU(INTEL_FAM6_ATOM_SILVERMONT, punit_device_byt), + ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID, punit_device_tng), ICPU(INTEL_FAM6_ATOM_AIRMONT, punit_device_cht), {} }; diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bt.c b/arch/x86/platform/intel-mid/device_libs/platform_bt.c index 5a0483e7bf66..31dce781364c 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_bt.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_bt.c @@ -68,7 +68,7 @@ static struct bt_sfi_data tng_bt_sfi_data __initdata = { { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (kernel_ulong_t)&ddata } static const struct x86_cpu_id bt_sfi_cpu_ids[] = { - ICPU(INTEL_FAM6_ATOM_MERRIFIELD, tng_bt_sfi_data), + ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID, tng_bt_sfi_data), {} }; diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index b85dadb4501b..0a06872f1719 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -291,7 +291,7 @@ static const struct lpss_device_desc bsw_spi_dev_desc = { #define ICPU(model) { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, } static const struct x86_cpu_id lpss_cpu_ids[] = { - ICPU(INTEL_FAM6_ATOM_SILVERMONT1), /* Valleyview, Bay Trail */ + ICPU(INTEL_FAM6_ATOM_SILVERMONT), /* Valleyview, Bay Trail */ ICPU(INTEL_FAM6_ATOM_AIRMONT), /* Braswell, Cherry Trail */ {} }; diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c index 95444f5f00a0..9997eac8fdec 100644 --- a/drivers/acpi/x86/utils.c +++ b/drivers/acpi/x86/utils.c @@ -54,7 +54,7 @@ static const struct always_present_id always_present_ids[] = { * Bay / Cherry Trail PWM directly poked by GPU driver in win10, * but Linux uses a separate PWM driver, harmless if not used. */ - ENTRY("80860F09", "1", ICPU(INTEL_FAM6_ATOM_SILVERMONT1), {}), + ENTRY("80860F09", "1", ICPU(INTEL_FAM6_ATOM_SILVERMONT), {}), ENTRY("80862288", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), {}), /* * The INT0002 device is necessary to clear wakeup interrupt sources diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 93758b528d8f..32b52e6bd13b 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -533,11 +533,18 @@ ssize_t __weak cpu_show_l1tf(struct device *dev, return sprintf(buf, "Not affected\n"); } +ssize_t __weak cpu_show_mds(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL); static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL); +static DEVICE_ATTR(mds, 0444, cpu_show_mds, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -545,6 +552,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_spectre_v2.attr, &dev_attr_spec_store_bypass.attr, &dev_attr_l1tf.attr, + &dev_attr_mds.attr, NULL }; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index b97c7afe970e..6f8f913f096e 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2052,7 +2052,7 @@ static const struct pstate_funcs knl_funcs = { static const struct x86_cpu_id intel_pstate_cpu_ids[] = { ICPU(INTEL_FAM6_SANDYBRIDGE, core_funcs), ICPU(INTEL_FAM6_SANDYBRIDGE_X, core_funcs), - ICPU(INTEL_FAM6_ATOM_SILVERMONT1, silvermont_funcs), + ICPU(INTEL_FAM6_ATOM_SILVERMONT, silvermont_funcs), ICPU(INTEL_FAM6_IVYBRIDGE, core_funcs), ICPU(INTEL_FAM6_HASWELL_CORE, core_funcs), ICPU(INTEL_FAM6_BROADWELL_CORE, core_funcs), @@ -2069,7 +2069,7 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = { ICPU(INTEL_FAM6_XEON_PHI_KNL, knl_funcs), ICPU(INTEL_FAM6_XEON_PHI_KNM, knl_funcs), ICPU(INTEL_FAM6_ATOM_GOLDMONT, core_funcs), - ICPU(INTEL_FAM6_ATOM_GEMINI_LAKE, core_funcs), + ICPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS, core_funcs), ICPU(INTEL_FAM6_SKYLAKE_X, core_funcs), {} }; diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c index df28b65358d2..903a4f1fadcc 100644 --- a/drivers/edac/pnd2_edac.c +++ b/drivers/edac/pnd2_edac.c @@ -1541,7 +1541,7 @@ static struct dunit_ops dnv_ops = { static const struct x86_cpu_id pnd2_cpuids[] = { { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT, 0, (kernel_ulong_t)&apl_ops }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_DENVERTON, 0, (kernel_ulong_t)&dnv_ops }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT_X, 0, (kernel_ulong_t)&dnv_ops }, { } }; MODULE_DEVICE_TABLE(x86cpu, pnd2_cpuids); diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 008eb4d58a86..ec95c0d56fa7 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1069,14 +1069,14 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = { ICPU(INTEL_FAM6_WESTMERE, idle_cpu_nehalem), ICPU(INTEL_FAM6_WESTMERE_EP, idle_cpu_nehalem), ICPU(INTEL_FAM6_NEHALEM_EX, idle_cpu_nehalem), - ICPU(INTEL_FAM6_ATOM_PINEVIEW, idle_cpu_atom), - ICPU(INTEL_FAM6_ATOM_LINCROFT, idle_cpu_lincroft), + ICPU(INTEL_FAM6_ATOM_BONNELL, idle_cpu_atom), + ICPU(INTEL_FAM6_ATOM_BONNELL_MID, idle_cpu_lincroft), ICPU(INTEL_FAM6_WESTMERE_EX, idle_cpu_nehalem), ICPU(INTEL_FAM6_SANDYBRIDGE, idle_cpu_snb), ICPU(INTEL_FAM6_SANDYBRIDGE_X, idle_cpu_snb), - ICPU(INTEL_FAM6_ATOM_CEDARVIEW, idle_cpu_atom), - ICPU(INTEL_FAM6_ATOM_SILVERMONT1, idle_cpu_byt), - ICPU(INTEL_FAM6_ATOM_MERRIFIELD, idle_cpu_tangier), + ICPU(INTEL_FAM6_ATOM_SALTWELL, idle_cpu_atom), + ICPU(INTEL_FAM6_ATOM_SILVERMONT, idle_cpu_byt), + ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID, idle_cpu_tangier), ICPU(INTEL_FAM6_ATOM_AIRMONT, idle_cpu_cht), ICPU(INTEL_FAM6_IVYBRIDGE, idle_cpu_ivb), ICPU(INTEL_FAM6_IVYBRIDGE_X, idle_cpu_ivt), @@ -1084,7 +1084,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = { ICPU(INTEL_FAM6_HASWELL_X, idle_cpu_hsw), ICPU(INTEL_FAM6_HASWELL_ULT, idle_cpu_hsw), ICPU(INTEL_FAM6_HASWELL_GT3E, idle_cpu_hsw), - ICPU(INTEL_FAM6_ATOM_SILVERMONT2, idle_cpu_avn), + ICPU(INTEL_FAM6_ATOM_SILVERMONT_X, idle_cpu_avn), ICPU(INTEL_FAM6_BROADWELL_CORE, idle_cpu_bdw), ICPU(INTEL_FAM6_BROADWELL_GT3E, idle_cpu_bdw), ICPU(INTEL_FAM6_BROADWELL_X, idle_cpu_bdw), @@ -1097,8 +1097,8 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = { ICPU(INTEL_FAM6_XEON_PHI_KNL, idle_cpu_knl), ICPU(INTEL_FAM6_XEON_PHI_KNM, idle_cpu_knl), ICPU(INTEL_FAM6_ATOM_GOLDMONT, idle_cpu_bxt), - ICPU(INTEL_FAM6_ATOM_GEMINI_LAKE, idle_cpu_bxt), - ICPU(INTEL_FAM6_ATOM_DENVERTON, idle_cpu_dnv), + ICPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS, idle_cpu_bxt), + ICPU(INTEL_FAM6_ATOM_GOLDMONT_X, idle_cpu_dnv), ICPU(INTEL_FAM6_ATOM_TREMONT_X, idle_cpu_dnv), {} }; @@ -1311,7 +1311,7 @@ static void intel_idle_state_table_update(void) ivt_idle_state_table_update(); break; case INTEL_FAM6_ATOM_GOLDMONT: - case INTEL_FAM6_ATOM_GEMINI_LAKE: + case INTEL_FAM6_ATOM_GOLDMONT_PLUS: bxt_idle_state_table_update(); break; case INTEL_FAM6_SKYLAKE_DESKTOP: diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index b3fb155f50e4..dd3cad2d4d65 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -128,7 +128,7 @@ static const struct sdhci_acpi_chip sdhci_acpi_chip_int = { static bool sdhci_acpi_byt(void) { static const struct x86_cpu_id byt[] = { - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT }, {} }; diff --git a/drivers/pci/pci-mid.c b/drivers/pci/pci-mid.c index 1c4af7227bca..a8e15e8c474c 100644 --- a/drivers/pci/pci-mid.c +++ b/drivers/pci/pci-mid.c @@ -71,8 +71,8 @@ static const struct pci_platform_pm_ops mid_pci_platform_pm = { * arch/x86/platform/intel-mid/pwr.c. */ static const struct x86_cpu_id lpss_cpu_ids[] = { - ICPU(INTEL_FAM6_ATOM_PENWELL), - ICPU(INTEL_FAM6_ATOM_MERRIFIELD), + ICPU(INTEL_FAM6_ATOM_SALTWELL_MID), + ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID), {} }; diff --git a/drivers/platform/x86/intel_int0002_vgpio.c b/drivers/platform/x86/intel_int0002_vgpio.c index 92dc230ef5b2..08107731afe0 100644 --- a/drivers/platform/x86/intel_int0002_vgpio.c +++ b/drivers/platform/x86/intel_int0002_vgpio.c @@ -60,7 +60,7 @@ static const struct x86_cpu_id int0002_cpu_ids[] = { /* * Limit ourselves to Cherry Trail for now, until testing shows we * need to handle the INT0002 device on Baytrail too. - * ICPU(INTEL_FAM6_ATOM_SILVERMONT1), * Valleyview, Bay Trail * + * ICPU(INTEL_FAM6_ATOM_SILVERMONT), * Valleyview, Bay Trail * */ ICPU(INTEL_FAM6_ATOM_AIRMONT), /* Braswell, Cherry Trail */ {} diff --git a/drivers/platform/x86/intel_mid_powerbtn.c b/drivers/platform/x86/intel_mid_powerbtn.c index 871cfa682519..ee45d61127f1 100644 --- a/drivers/platform/x86/intel_mid_powerbtn.c +++ b/drivers/platform/x86/intel_mid_powerbtn.c @@ -125,8 +125,8 @@ static struct mid_pb_ddata mrfld_ddata = { { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (kernel_ulong_t)&ddata } static const struct x86_cpu_id mid_pb_cpu_ids[] = { - ICPU(INTEL_FAM6_ATOM_PENWELL, mfld_ddata), - ICPU(INTEL_FAM6_ATOM_MERRIFIELD, mrfld_ddata), + ICPU(INTEL_FAM6_ATOM_SALTWELL_MID, mfld_ddata), + ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID, mrfld_ddata), {} }; diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c index 9ff30d1cddf6..225b50f01a13 100644 --- a/drivers/powercap/intel_rapl.c +++ b/drivers/powercap/intel_rapl.c @@ -1159,13 +1159,13 @@ static const struct x86_cpu_id rapl_ids[] __initconst = { RAPL_CPU(INTEL_FAM6_KABYLAKE_MOBILE, rapl_defaults_core), RAPL_CPU(INTEL_FAM6_KABYLAKE_DESKTOP, rapl_defaults_core), - RAPL_CPU(INTEL_FAM6_ATOM_SILVERMONT1, rapl_defaults_byt), + RAPL_CPU(INTEL_FAM6_ATOM_SILVERMONT, rapl_defaults_byt), RAPL_CPU(INTEL_FAM6_ATOM_AIRMONT, rapl_defaults_cht), - RAPL_CPU(INTEL_FAM6_ATOM_MERRIFIELD, rapl_defaults_tng), - RAPL_CPU(INTEL_FAM6_ATOM_MOOREFIELD, rapl_defaults_ann), + RAPL_CPU(INTEL_FAM6_ATOM_SILVERMONT_MID,rapl_defaults_tng), + RAPL_CPU(INTEL_FAM6_ATOM_AIRMONT_MID, rapl_defaults_ann), RAPL_CPU(INTEL_FAM6_ATOM_GOLDMONT, rapl_defaults_core), - RAPL_CPU(INTEL_FAM6_ATOM_GEMINI_LAKE, rapl_defaults_core), - RAPL_CPU(INTEL_FAM6_ATOM_DENVERTON, rapl_defaults_core), + RAPL_CPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS, rapl_defaults_core), + RAPL_CPU(INTEL_FAM6_ATOM_GOLDMONT_X, rapl_defaults_core), RAPL_CPU(INTEL_FAM6_ATOM_TREMONT_X, rapl_defaults_core), RAPL_CPU(INTEL_FAM6_XEON_PHI_KNL, rapl_defaults_hsw_server), diff --git a/drivers/thermal/intel_soc_dts_thermal.c b/drivers/thermal/intel_soc_dts_thermal.c index c27868b2c6af..ce2722edd307 100644 --- a/drivers/thermal/intel_soc_dts_thermal.c +++ b/drivers/thermal/intel_soc_dts_thermal.c @@ -43,7 +43,7 @@ static irqreturn_t soc_irq_thread_fn(int irq, void *dev_data) } static const struct x86_cpu_id soc_thermal_ids[] = { - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1, 0, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT, 0, BYT_SOC_DTS_APIC_IRQ}, {} }; diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 229eef0da61e..c4d2daa2e2da 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -1,28 +1,9 @@ #ifndef _LINUX_BITOPS_H #define _LINUX_BITOPS_H #include <asm/types.h> +#include <linux/bits.h> -#ifdef __KERNEL__ -#define BIT(nr) (1UL << (nr)) -#define BIT_ULL(nr) (1ULL << (nr)) -#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) -#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) -#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG)) -#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG) -#define BITS_PER_BYTE 8 #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) -#endif - -/* - * Create a contiguous bitmask starting at bit position @l and ending at - * position @h. For example - * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. - */ -#define GENMASK(h, l) \ - (((~0UL) << (l)) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) - -#define GENMASK_ULL(h, l) \ - (((~0ULL) << (l)) & (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); diff --git a/include/linux/bits.h b/include/linux/bits.h new file mode 100644 index 000000000000..2b7b532c1d51 --- /dev/null +++ b/include/linux/bits.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_BITS_H +#define __LINUX_BITS_H +#include <asm/bitsperlong.h> + +#define BIT(nr) (1UL << (nr)) +#define BIT_ULL(nr) (1ULL << (nr)) +#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) +#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) +#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG)) +#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG) +#define BITS_PER_BYTE 8 + +/* + * Create a contiguous bitmask starting at bit position @l and ending at + * position @h. For example + * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. + */ +#define GENMASK(h, l) \ + (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) + +#define GENMASK_ULL(h, l) \ + (((~0ULL) - (1ULL << (l)) + 1) & \ + (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) + +#endif /* __LINUX_BITS_H */ diff --git a/include/linux/cpu.h b/include/linux/cpu.h index cf5b0d9c4483..9bd30749d04f 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -56,6 +56,8 @@ extern ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_mds(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile index 8792ad8dbf83..7aea57e88bf4 100644 --- a/tools/power/x86/turbostat/Makefile +++ b/tools/power/x86/turbostat/Makefile @@ -8,7 +8,7 @@ ifeq ("$(origin O)", "command line") endif turbostat : turbostat.c -CFLAGS += -Wall +override CFLAGS += -Wall -I../../../include CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"' CFLAGS += -DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"' diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index d19c18bf5f3d..bbafe59c014d 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -1839,7 +1839,7 @@ int has_turbo_ratio_group_limits(int family, int model) switch (model) { case INTEL_FAM6_ATOM_GOLDMONT: case INTEL_FAM6_SKYLAKE_X: - case INTEL_FAM6_ATOM_DENVERTON: + case INTEL_FAM6_ATOM_GOLDMONT_X: return 1; } return 0; @@ -2701,9 +2701,9 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) pkg_cstate_limits = skx_pkg_cstate_limits; has_misc_feature_control = 1; break; - case INTEL_FAM6_ATOM_SILVERMONT1: /* BYT */ + case INTEL_FAM6_ATOM_SILVERMONT: /* BYT */ no_MSR_MISC_PWR_MGMT = 1; - case INTEL_FAM6_ATOM_SILVERMONT2: /* AVN */ + case INTEL_FAM6_ATOM_SILVERMONT_X: /* AVN */ pkg_cstate_limits = slv_pkg_cstate_limits; break; case INTEL_FAM6_ATOM_AIRMONT: /* AMT */ @@ -2715,8 +2715,8 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) pkg_cstate_limits = phi_pkg_cstate_limits; break; case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ - case INTEL_FAM6_ATOM_GEMINI_LAKE: - case INTEL_FAM6_ATOM_DENVERTON: /* DNV */ + case INTEL_FAM6_ATOM_GOLDMONT_PLUS: + case INTEL_FAM6_ATOM_GOLDMONT_X: /* DNV */ pkg_cstate_limits = bxt_pkg_cstate_limits; break; default: @@ -2745,9 +2745,9 @@ int has_slv_msrs(unsigned int family, unsigned int model) return 0; switch (model) { - case INTEL_FAM6_ATOM_SILVERMONT1: - case INTEL_FAM6_ATOM_MERRIFIELD: - case INTEL_FAM6_ATOM_MOOREFIELD: + case INTEL_FAM6_ATOM_SILVERMONT: + case INTEL_FAM6_ATOM_SILVERMONT_MID: + case INTEL_FAM6_ATOM_AIRMONT_MID: return 1; } return 0; @@ -2759,7 +2759,7 @@ int is_dnv(unsigned int family, unsigned int model) return 0; switch (model) { - case INTEL_FAM6_ATOM_DENVERTON: + case INTEL_FAM6_ATOM_GOLDMONT_X: return 1; } return 0; @@ -3275,8 +3275,8 @@ double get_tdp(unsigned int model) return ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units; switch (model) { - case INTEL_FAM6_ATOM_SILVERMONT1: - case INTEL_FAM6_ATOM_SILVERMONT2: + case INTEL_FAM6_ATOM_SILVERMONT: + case INTEL_FAM6_ATOM_SILVERMONT_X: return 30.0; default: return 135.0; @@ -3342,7 +3342,7 @@ void rapl_probe(unsigned int family, unsigned int model) } break; case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ - case INTEL_FAM6_ATOM_GEMINI_LAKE: + case INTEL_FAM6_ATOM_GOLDMONT_PLUS: do_rapl = RAPL_PKG | RAPL_PKG_POWER_INFO; if (rapl_joules) BIC_PRESENT(BIC_Pkg_J); @@ -3400,8 +3400,8 @@ void rapl_probe(unsigned int family, unsigned int model) BIC_PRESENT(BIC_RAMWatt); } break; - case INTEL_FAM6_ATOM_SILVERMONT1: /* BYT */ - case INTEL_FAM6_ATOM_SILVERMONT2: /* AVN */ + case INTEL_FAM6_ATOM_SILVERMONT: /* BYT */ + case INTEL_FAM6_ATOM_SILVERMONT_X: /* AVN */ do_rapl = RAPL_PKG | RAPL_CORES; if (rapl_joules) { BIC_PRESENT(BIC_Pkg_J); @@ -3411,7 +3411,7 @@ void rapl_probe(unsigned int family, unsigned int model) BIC_PRESENT(BIC_CorWatt); } break; - case INTEL_FAM6_ATOM_DENVERTON: /* DNV */ + case INTEL_FAM6_ATOM_GOLDMONT_X: /* DNV */ do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO | RAPL_CORES_ENERGY_STATUS; BIC_PRESENT(BIC_PKG__); BIC_PRESENT(BIC_RAM__); @@ -3434,7 +3434,7 @@ void rapl_probe(unsigned int family, unsigned int model) return; rapl_power_units = 1.0 / (1 << (msr & 0xF)); - if (model == INTEL_FAM6_ATOM_SILVERMONT1) + if (model == INTEL_FAM6_ATOM_SILVERMONT) rapl_energy_units = 1.0 * (1 << (msr >> 8 & 0x1F)) / 1000000; else rapl_energy_units = 1.0 / (1 << (msr >> 8 & 0x1F)); @@ -3684,8 +3684,8 @@ int has_snb_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ case INTEL_FAM6_SKYLAKE_X: /* SKX */ case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ - case INTEL_FAM6_ATOM_GEMINI_LAKE: - case INTEL_FAM6_ATOM_DENVERTON: /* DNV */ + case INTEL_FAM6_ATOM_GOLDMONT_PLUS: + case INTEL_FAM6_ATOM_GOLDMONT_X: /* DNV */ return 1; } return 0; @@ -3716,7 +3716,7 @@ int has_hsw_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ - case INTEL_FAM6_ATOM_GEMINI_LAKE: + case INTEL_FAM6_ATOM_GOLDMONT_PLUS: return 1; } return 0; @@ -3750,8 +3750,8 @@ int is_slm(unsigned int family, unsigned int model) if (!genuine_intel) return 0; switch (model) { - case INTEL_FAM6_ATOM_SILVERMONT1: /* BYT */ - case INTEL_FAM6_ATOM_SILVERMONT2: /* AVN */ + case INTEL_FAM6_ATOM_SILVERMONT: /* BYT */ + case INTEL_FAM6_ATOM_SILVERMONT_X: /* AVN */ return 1; } return 0; @@ -4106,11 +4106,11 @@ void process_cpuid() crystal_hz = 24000000; /* 24.0 MHz */ break; case INTEL_FAM6_SKYLAKE_X: /* SKX */ - case INTEL_FAM6_ATOM_DENVERTON: /* DNV */ + case INTEL_FAM6_ATOM_GOLDMONT_X: /* DNV */ crystal_hz = 25000000; /* 25.0 MHz */ break; case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ - case INTEL_FAM6_ATOM_GEMINI_LAKE: + case INTEL_FAM6_ATOM_GOLDMONT_PLUS: crystal_hz = 19200000; /* 19.2 MHz */ break; default: |