kernel.git/arch/x86/kernel/cpu/common.c, branch master

x86/topo: Add topology_num_nodes_per_package()

2026-03-04T15:35:08Z

Use the MADT and SRAT table data to compute __num_nodes_per_package. Specifically, SRAT has already been parsed in x86_numa_init(), which is called before acpi_boot_init() which parses MADT. So both are available in topology_init_possible_cpus(). This number is useful to divinate the various Intel CoD/SNC and AMD NPS modes, since the platforms are failing to provide this otherwise. Doing it this way is independent of the number of online CPUs and other such shenanigans. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ingo Molnar Tested-by: Tony Luck Tested-by: K Prateek Nayak Tested-by: Zhang Rui Tested-by: Chen Yu Tested-by: Kyle Meyer Link: https://patch.msgid.link/20260303110100.004091624@infradead.org

x86/cpufeature: Replace X86_FEATURE_SYSENTER32 with X86_FEATURE_SYSFAST32

2026-01-14T00:37:58Z

In most cases, the use of "fast 32-bit system call" depends either on X86_FEATURE_SEP or X86_FEATURE_SYSENTER32 || X86_FEATURE_SYSCALL32. However, nearly all the logic for both is identical. Define X86_FEATURE_SYSFAST32 which indicates that *either* SYSENTER32 or SYSCALL32 should be used, for either 32- or 64-bit kernels. This defaults to SYSENTER; use SYSCALL if the SYSCALL32 bit is also set. As this removes ALL existing uses of X86_FEATURE_SYSENTER32, which is a kernel-only synthetic feature bit, simply remove it and replace it with X86_FEATURE_SYSFAST32. This leaves an unused alternative for a true 32-bit kernel, but that should really not matter in any way. The clearing of X86_FEATURE_SYSCALL32 can be removed once the patches for automatically clearing disabled features has been merged. Signed-off-by: H. Peter Anvin (Intel) Signed-off-by: Dave Hansen Link: https://patch.msgid.link/20251216212606.1325678-10-hpa@zytor.com

Merge tag 'x86_cpu_for_6.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2025-12-02T22:48:08Z

Pull x86 CPU feature updates from Dave Hansen: "The biggest thing of note here is Linear Address Space Separation (LASS). It represents the first time I can think of that the upper=>kernel/lower=>user address space convention is actually recognized by the hardware on x86. It ensures that userspace can not even get the hardware to _start_ page walks for the kernel address space. This, of course, is a really nice generic side channel defense. This is really only a down payment on LASS support. There are still some details to work out in its interaction with EFI calls and vsyscall emulation. For now, LASS is disabled if either of those features is compiled in (which is almost always the case). There's also one straggler commit in here which converts an under-utilized AMD CPU feature leaf into a generic Linux-defined leaf so more feature can be packed in there. Summary: - Enable Linear Address Space Separation (LASS) - Change X86_FEATURE leaf 17 from an AMD leaf to Linux-defined" * tag 'x86_cpu_for_6.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/cpu: Enable LASS during CPU initialization selftests/x86: Update the negative vsyscall tests to expect a #GP x86/traps: Communicate a LASS violation in #GP message x86/kexec: Disable LASS during relocate kernel x86/alternatives: Disable LASS when patching kernel code x86/asm: Introduce inline memcpy and memset x86/cpu: Add an LASS dependency on SMAP x86/cpufeatures: Enumerate the LASS feature bits x86/cpufeatures: Make X86_FEATURE leaf 17 Linux-specific

Merge tag 'x86_misc_for_6.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2025-12-02T22:16:42Z

Pull misc x86 updates from Dave Hansen: "The most significant are some changes to ensure that symbols exported for KVM are used only by KVM modules themselves, along with some related cleanups. In true x86/misc fashion, the other patch is completely unrelated and just enhances an existing pr_warn() to make it clear to users how they have tainted their kernel when something is mucking with MSRs. Summary: - Make MSR-induced taint easier for users to track down - Restrict KVM-specific exports to KVM itself" * tag 'x86_misc_for_6.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86: Restrict KVM-induced symbol exports to KVM modules where obvious/possible x86/mm: Drop unnecessary export of "ptdump_walk_pgd_level_debugfs" x86/mtrr: Drop unnecessary export of "mtrr_state" x86/bugs: Drop unnecessary export of "x86_spec_ctrl_base" x86/msr: Add CPU_OUT_OF_SPEC taint name to "unrecognized" pr_warn(msg)

x86/cpu: Enable LASS during CPU initialization

2025-11-18T18:38:27Z

Linear Address Space Separation (LASS) mitigates a class of side-channel attacks that rely on speculative access across the user/kernel boundary. Enable LASS along with similar security features if the platform supports it. While at it, remove the comment above the SMAP/SMEP/UMIP/LASS setup instead of updating it, as the whole sequence is quite self-explanatory. Some EFI runtime and boot services may rely on 1:1 mappings in the lower half during early boot and even after SetVirtualAddressMap(). To avoid tripping LASS, the initial CR4 programming would need to be delayed until EFI has completely finished entering virtual mode (including efi_free_boot_services()). Also, LASS would need to be temporarily disabled while switching to efi_mm to avoid potential faults on stray runtime accesses. Similarly, legacy vsyscall page accesses are flagged by LASS resulting in a #GP (instead of a #PF). Without LASS, the #PF handler emulates the accesses and returns the appropriate values. Equivalent emulation support is required in the #GP handler with LASS enabled. In case of vsyscall XONLY (execute only) mode, the faulting address is readily available in the RIP which would make it easier to reuse the #PF emulation logic. For now, keep it simple and disable LASS if either of those are compiled in. Though not ideal, this makes it easier to start testing LASS support in some environments. In future, LASS support can easily be expanded to support EFI and legacy vsyscalls. Signed-off-by: Sohil Mehta Signed-off-by: Dave Hansen Reviewed-by: Dave Hansen Link: https://patch.msgid.link/20251118182911.2983253-9-sohil.mehta%40intel.com

x86: Restrict KVM-induced symbol exports to KVM modules where obvious/possible

2025-11-12T23:29:38Z

Extend KVM's export macro framework to provide EXPORT_SYMBOL_FOR_KVM(), and use the helper macro to export symbols for KVM throughout x86 if and only if KVM will build one or more modules, and only for those modules. To avoid unnecessary exports when CONFIG_KVM=m but kvm.ko will not be built (because no vendor modules are selected), let arch code #define EXPORT_SYMBOL_FOR_KVM to suppress/override the exports. Note, the set of symbols to restrict to KVM was generated by manual search and audit; any "misses" are due to human error, not some grand plan. Signed-off-by: Sean Christopherson Signed-off-by: Dave Hansen Acked-by: Kai Huang Tested-by: Kai Huang Link: https://patch.msgid.link/20251112173944.1380633-5-seanjc%40google.com

x86: uaccess: don't use runtime-const rewriting in modules

2025-11-05T01:24:36Z

The runtime-const infrastructure was never designed to handle the modular case, because the constant fixup is only done at boot time for core kernel code. But by the time I used it for the x86-64 user space limit handling in commit 86e6b1547b3d ("x86: fix user address masking non-canonical speculation issue"), I had completely repressed that fact. And it all happens to work because the only code that currently actually gets inlined by modules is for the access_ok() limit check, where the default constant value works even when not fixed up. Because at least I had intentionally made it be something that is in the non-canonical address space region. But it's technically very wrong, and it does mean that at least in theory, the use of 'access_ok()' + '__get_user()' can trigger the same speculation issue with non-canonical addresses that the original commit was all about. The pattern is unusual enough that this probably doesn't matter in practice, but very wrong is still very wrong. Also, let's fix it before the nice optimized scoped user accessor helpers that Thomas Gleixner is working on cause this pseudo-constant to then be more widely used. This all came up due to an unrelated discussion with Mateusz Guzik about using the runtime const infrastructure for names_cachep accesses too. There the modular case was much more obviously broken, and Mateusz noted it in his 'v2' of the patch series. That then made me notice how broken 'access_ok()' had been in modules all along. Mea culpa, mea maxima culpa. Fix it by simply not using the runtime-const code in modules, and just using the USER_PTR_MAX variable value instead. This is not performance-critical like the core user accessor functions (get_user() and friends) are. Also make sure this doesn't get forgotten the next time somebody wants to do runtime constant optimizations by having the x86 runtime-const.h header file error out if included by modules. Fixes: 86e6b1547b3d ("x86: fix user address masking non-canonical speculation issue") Acked-by: Borislav Petkov Acked-by: Sean Christopherson Cc: Thomas Gleixner Triggered-by: Mateusz Guzik Link: https://lore.kernel.org/all/20251030105242.801528-1-mjguzik@gmail.com/ Signed-off-by: Linus Torvalds

x86/cpufeatures: Make X86_FEATURE leaf 17 Linux-specific

2025-10-13T14:21:25Z

That cpuinfo_x86.x86_capability[] element was supposed to mirror CPUID flags from CPUID_0x80000007_EBX but that leaf has still to this day only three bits defined in it. So move those bits to scattered.c and free the capability element for synthetic flags. No functional changes. Signed-off-by: Borislav Petkov (AMD)

Merge tag 'ras_core_for_v6.18_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2025-09-30T19:43:17Z

Pull x86 RAS updates from Borislav Petkov: - Unify and refactor the MCA arch side and better separate code - Cleanup and simplify the AMD RAS side, unify code, drop unused stuff * tag 'ras_core_for_v6.18_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/mce: Add a clear_bank() helper x86/mce: Move machine_check_poll() status checks to helper functions x86/mce: Separate global and per-CPU quirks x86/mce: Do 'UNKNOWN' vendor check early x86/mce: Define BSP-only SMCA init x86/mce: Define BSP-only init x86/mce: Set CR4.MCE last during init x86/mce: Remove __mcheck_cpu_init_early() x86/mce: Cleanup bank processing on init x86/mce/amd: Put list_head in threshold_bank x86/mce/amd: Remove smca_banks_map x86/mce/amd: Remove return value for mce_threshold_{create,remove}_device() x86/mce/amd: Rename threshold restart function

x86/mce: Define BSP-only init

2025-09-11T10:22:37Z

Currently, MCA initialization is executed identically on each CPU as they are brought online. However, a number of MCA initialization tasks only need to be done once. Define a function to collect all 'global' init tasks and call this from the BSP only. Start with CPU features. Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Qiuxu Zhuo Reviewed-by: Tony Luck Reviewed-by: Nikolay Borisov Tested-by: Tony Luck Link: https://lore.kernel.org/20250908-wip-mca-updates-v6-0-eef5d6c74b9c@amd.com