diff options
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r-- | arch/x86/kernel/callthunks.c | 5 | ||||
-rw-r--r-- | arch/x86/kernel/cet.c | 30 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/amd.c | 2 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/cacheinfo.c | 43 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/common.c | 38 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/intel.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/mshyperv.c | 58 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/topology.c | 6 | ||||
-rw-r--r-- | arch/x86/kernel/fpu/signal.c | 20 | ||||
-rw-r--r-- | arch/x86/kernel/fpu/xstate.h | 27 | ||||
-rw-r--r-- | arch/x86/kernel/relocate_kernel_64.S | 8 | ||||
-rw-r--r-- | arch/x86/kernel/static_call.c | 9 | ||||
-rw-r--r-- | arch/x86/kernel/vmlinux.lds.S | 4 |
13 files changed, 183 insertions, 71 deletions
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index 465647456753..f17d16607882 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -143,11 +143,6 @@ static bool skip_addr(void *dest) dest < (void*)relocate_kernel + KEXEC_CONTROL_CODE_MAX_SIZE) return true; #endif -#ifdef CONFIG_XEN - if (dest >= (void *)hypercall_page && - dest < (void*)hypercall_page + PAGE_SIZE) - return true; -#endif return false; } diff --git a/arch/x86/kernel/cet.c b/arch/x86/kernel/cet.c index d2c732a34e5d..303bf74d175b 100644 --- a/arch/x86/kernel/cet.c +++ b/arch/x86/kernel/cet.c @@ -81,6 +81,34 @@ static void do_user_cp_fault(struct pt_regs *regs, unsigned long error_code) static __ro_after_init bool ibt_fatal = true; +/* + * By definition, all missing-ENDBRANCH #CPs are a result of WFE && !ENDBR. + * + * For the kernel IBT no ENDBR selftest where #CPs are deliberately triggered, + * the WFE state of the interrupted context needs to be cleared to let execution + * continue. Otherwise when the CPU resumes from the instruction that just + * caused the previous #CP, another missing-ENDBRANCH #CP is raised and the CPU + * enters a dead loop. + * + * This is not a problem with IDT because it doesn't preserve WFE and IRET doesn't + * set WFE. But FRED provides space on the entry stack (in an expanded CS area) + * to save and restore the WFE state, thus the WFE state is no longer clobbered, + * so software must clear it. + */ +static void ibt_clear_fred_wfe(struct pt_regs *regs) +{ + /* + * No need to do any FRED checks. + * + * For IDT event delivery, the high-order 48 bits of CS are pushed + * as 0s into the stack, and later IRET ignores these bits. + * + * For FRED, a test to check if fred_cs.wfe is set would be dropped + * by compilers. + */ + regs->fred_cs.wfe = 0; +} + static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) { if ((error_code & CP_EC) != CP_ENDBR) { @@ -90,6 +118,7 @@ static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) if (unlikely(regs->ip == (unsigned long)&ibt_selftest_noendbr)) { regs->ax = 0; + ibt_clear_fred_wfe(regs); return; } @@ -97,6 +126,7 @@ static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) if (!ibt_fatal) { printk(KERN_DEFAULT CUT_HERE); __warn(__FILE__, __LINE__, (void *)regs->ip, TAINT_WARN, regs, NULL); + ibt_clear_fred_wfe(regs); return; } BUG(); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index d8408aafeed9..79d2e17f6582 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1065,7 +1065,7 @@ static void init_amd(struct cpuinfo_x86 *c) */ if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && cpu_has(c, X86_FEATURE_AUTOIBRS)) - WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS)); + WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS) < 0); /* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */ clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE); diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index 392d09c936d6..e6fa03ed9172 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -178,8 +178,6 @@ struct _cpuid4_info_regs { struct amd_northbridge *nb; }; -static unsigned short num_cache_leaves; - /* AMD doesn't have CPUID4. Emulate it here to report the same information to the user. This makes some assumptions about the machine: L2 not shared, no SMT etc. that is currently true on AMD CPUs. @@ -717,20 +715,23 @@ void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c) void init_amd_cacheinfo(struct cpuinfo_x86 *c) { + struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index); if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { - num_cache_leaves = find_num_cache_leaves(c); + ci->num_leaves = find_num_cache_leaves(c); } else if (c->extended_cpuid_level >= 0x80000006) { if (cpuid_edx(0x80000006) & 0xf000) - num_cache_leaves = 4; + ci->num_leaves = 4; else - num_cache_leaves = 3; + ci->num_leaves = 3; } } void init_hygon_cacheinfo(struct cpuinfo_x86 *c) { - num_cache_leaves = find_num_cache_leaves(c); + struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index); + + ci->num_leaves = find_num_cache_leaves(c); } void init_intel_cacheinfo(struct cpuinfo_x86 *c) @@ -740,21 +741,21 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c) unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */ unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */ unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb; + struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index); if (c->cpuid_level > 3) { - static int is_initialized; - - if (is_initialized == 0) { - /* Init num_cache_leaves from boot CPU */ - num_cache_leaves = find_num_cache_leaves(c); - is_initialized++; - } + /* + * There should be at least one leaf. A non-zero value means + * that the number of leaves has been initialized. + */ + if (!ci->num_leaves) + ci->num_leaves = find_num_cache_leaves(c); /* * Whenever possible use cpuid(4), deterministic cache * parameters cpuid leaf to find the cache details */ - for (i = 0; i < num_cache_leaves; i++) { + for (i = 0; i < ci->num_leaves; i++) { struct _cpuid4_info_regs this_leaf = {}; int retval; @@ -790,14 +791,14 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c) * Don't use cpuid2 if cpuid4 is supported. For P4, we use cpuid2 for * trace cache */ - if ((num_cache_leaves == 0 || c->x86 == 15) && c->cpuid_level > 1) { + if ((!ci->num_leaves || c->x86 == 15) && c->cpuid_level > 1) { /* supports eax=2 call */ int j, n; unsigned int regs[4]; unsigned char *dp = (unsigned char *)regs; int only_trace = 0; - if (num_cache_leaves != 0 && c->x86 == 15) + if (ci->num_leaves && c->x86 == 15) only_trace = 1; /* Number of times to iterate */ @@ -991,14 +992,12 @@ static void ci_leaf_init(struct cacheinfo *this_leaf, int init_cache_level(unsigned int cpu) { - struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu); - if (!num_cache_leaves) + /* There should be at least one leaf. */ + if (!ci->num_leaves) return -ENOENT; - if (!this_cpu_ci) - return -EINVAL; - this_cpu_ci->num_levels = 3; - this_cpu_ci->num_leaves = num_cache_leaves; + return 0; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a5c28975c608..3e9037690814 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -867,7 +867,7 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c) tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]); } -static void get_cpu_vendor(struct cpuinfo_x86 *c) +void get_cpu_vendor(struct cpuinfo_x86 *c) { char *v = c->x86_vendor_id; int i; @@ -1649,15 +1649,11 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) detect_nopl(); } -void __init early_cpu_init(void) +void __init init_cpu_devs(void) { const struct cpu_dev *const *cdev; int count = 0; -#ifdef CONFIG_PROCESSOR_SELECT - pr_info("KERNEL supported cpus:\n"); -#endif - for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) { const struct cpu_dev *cpudev = *cdev; @@ -1665,20 +1661,30 @@ void __init early_cpu_init(void) break; cpu_devs[count] = cpudev; count++; + } +} +void __init early_cpu_init(void) +{ #ifdef CONFIG_PROCESSOR_SELECT - { - unsigned int j; - - for (j = 0; j < 2; j++) { - if (!cpudev->c_ident[j]) - continue; - pr_info(" %s %s\n", cpudev->c_vendor, - cpudev->c_ident[j]); - } - } + unsigned int i, j; + + pr_info("KERNEL supported cpus:\n"); #endif + + init_cpu_devs(); + +#ifdef CONFIG_PROCESSOR_SELECT + for (i = 0; i < X86_VENDOR_NUM && cpu_devs[i]; i++) { + for (j = 0; j < 2; j++) { + if (!cpu_devs[i]->c_ident[j]) + continue; + pr_info(" %s %s\n", cpu_devs[i]->c_vendor, + cpu_devs[i]->c_ident[j]); + } } +#endif + early_identify_cpu(&boot_cpu_data); } diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index d1de300af173..8ded9f859a3a 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -555,7 +555,9 @@ static void init_intel(struct cpuinfo_x86 *c) c->x86_vfm == INTEL_WESTMERE_EX)) set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR); - if (boot_cpu_has(X86_FEATURE_MWAIT) && c->x86_vfm == INTEL_ATOM_GOLDMONT) + if (boot_cpu_has(X86_FEATURE_MWAIT) && + (c->x86_vfm == INTEL_ATOM_GOLDMONT || + c->x86_vfm == INTEL_LUNARLAKE_M)) set_cpu_bug(c, X86_BUG_MONITOR); #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index d18078834ded..dc12fe5ef3ca 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -223,6 +223,63 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs) hyperv_cleanup(); } #endif /* CONFIG_CRASH_DUMP */ + +static u64 hv_ref_counter_at_suspend; +static void (*old_save_sched_clock_state)(void); +static void (*old_restore_sched_clock_state)(void); + +/* + * Hyper-V clock counter resets during hibernation. Save and restore clock + * offset during suspend/resume, while also considering the time passed + * before suspend. This is to make sure that sched_clock using hv tsc page + * based clocksource, proceeds from where it left off during suspend and + * it shows correct time for the timestamps of kernel messages after resume. + */ +static void save_hv_clock_tsc_state(void) +{ + hv_ref_counter_at_suspend = hv_read_reference_counter(); +} + +static void restore_hv_clock_tsc_state(void) +{ + /* + * Adjust the offsets used by hv tsc clocksource to + * account for the time spent before hibernation. + * adjusted value = reference counter (time) at suspend + * - reference counter (time) now. + */ + hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter()); +} + +/* + * Functions to override save_sched_clock_state and restore_sched_clock_state + * functions of x86_platform. The Hyper-V clock counter is reset during + * suspend-resume and the offset used to measure time needs to be + * corrected, post resume. + */ +static void hv_save_sched_clock_state(void) +{ + old_save_sched_clock_state(); + save_hv_clock_tsc_state(); +} + +static void hv_restore_sched_clock_state(void) +{ + restore_hv_clock_tsc_state(); + old_restore_sched_clock_state(); +} + +static void __init x86_setup_ops_for_tsc_pg_clock(void) +{ + if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) + return; + + old_save_sched_clock_state = x86_platform.save_sched_clock_state; + x86_platform.save_sched_clock_state = hv_save_sched_clock_state; + + old_restore_sched_clock_state = x86_platform.restore_sched_clock_state; + x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state; +} #endif /* CONFIG_HYPERV */ static uint32_t __init ms_hyperv_platform(void) @@ -579,6 +636,7 @@ static void __init ms_hyperv_init_platform(void) /* Register Hyper-V specific clocksource */ hv_init_clocksource(); + x86_setup_ops_for_tsc_pg_clock(); hv_vtl_init_platform(); #endif /* diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 621a151ccf7d..b2e313ea17bf 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -428,8 +428,8 @@ void __init topology_apply_cmdline_limits_early(void) { unsigned int possible = nr_cpu_ids; - /* 'maxcpus=0' 'nosmp' 'nolapic' 'disableapic' 'noapic' */ - if (!setup_max_cpus || ioapic_is_disabled || apic_is_disabled) + /* 'maxcpus=0' 'nosmp' 'nolapic' 'disableapic' */ + if (!setup_max_cpus || apic_is_disabled) possible = 1; /* 'possible_cpus=N' */ @@ -443,7 +443,7 @@ void __init topology_apply_cmdline_limits_early(void) static __init bool restrict_to_up(void) { - if (!smp_found_config || ioapic_is_disabled) + if (!smp_found_config) return true; /* * XEN PV is special as it does not advertise the local APIC diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 1065ab995305..8f62e0666dea 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -64,16 +64,6 @@ setfx: } /* - * Update the value of PKRU register that was already pushed onto the signal frame. - */ -static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u32 pkru) -{ - if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE))) - return 0; - return __put_user(pkru, (unsigned int __user *)get_xsave_addr_user(buf, XFEATURE_PKRU)); -} - -/* * Signal frame handlers. */ static inline bool save_fsave_header(struct task_struct *tsk, void __user *buf) @@ -168,14 +158,8 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf, u32 pkru) { - int err = 0; - - if (use_xsave()) { - err = xsave_to_user_sigframe(buf); - if (!err) - err = update_pkru_in_sigframe(buf, pkru); - return err; - } + if (use_xsave()) + return xsave_to_user_sigframe(buf, pkru); if (use_fxsr()) return fxsave_to_user_sigframe((struct fxregs_state __user *) buf); diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index 0b86a5002c84..aa16f1a1bbcf 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -69,6 +69,28 @@ static inline u64 xfeatures_mask_independent(void) return fpu_kernel_cfg.independent_features; } +/* + * Update the value of PKRU register that was already pushed onto the signal frame. + */ +static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u64 mask, u32 pkru) +{ + u64 xstate_bv; + int err; + + if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE))) + return 0; + + /* Mark PKRU as in-use so that it is restored correctly. */ + xstate_bv = (mask & xfeatures_in_use()) | XFEATURE_MASK_PKRU; + + err = __put_user(xstate_bv, &buf->header.xfeatures); + if (err) + return err; + + /* Update PKRU value in the userspace xsave buffer. */ + return __put_user(pkru, (unsigned int __user *)get_xsave_addr_user(buf, XFEATURE_PKRU)); +} + /* XSAVE/XRSTOR wrapper functions */ #ifdef CONFIG_X86_64 @@ -256,7 +278,7 @@ static inline u64 xfeatures_need_sigframe_write(void) * The caller has to zero buf::header before calling this because XSAVE* * does not touch the reserved fields in the header. */ -static inline int xsave_to_user_sigframe(struct xregs_state __user *buf) +static inline int xsave_to_user_sigframe(struct xregs_state __user *buf, u32 pkru) { /* * Include the features which are not xsaved/rstored by the kernel @@ -281,6 +303,9 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf) XSTATE_OP(XSAVE, buf, lmask, hmask, err); clac(); + if (!err) + err = update_pkru_in_sigframe(buf, mask, pkru); + return err; } diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index e9e88c342f75..540443d699e3 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -13,6 +13,7 @@ #include <asm/pgtable_types.h> #include <asm/nospec-branch.h> #include <asm/unwind_hints.h> +#include <asm/asm-offsets.h> /* * Must be relocatable PIC code callable as a C function, in particular @@ -242,6 +243,13 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) movq CR0(%r8), %r8 movq %rax, %cr3 movq %r8, %cr0 + +#ifdef CONFIG_KEXEC_JUMP + /* Saved in save_processor_state. */ + movq $saved_context, %rax + lgdt saved_context_gdt_desc(%rax) +#endif + movq %rbp, %rax popf diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 4eefaac64c6c..9eed0c144dad 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -172,6 +172,15 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) } EXPORT_SYMBOL_GPL(arch_static_call_transform); +noinstr void __static_call_update_early(void *tramp, void *func) +{ + BUG_ON(system_state != SYSTEM_BOOTING); + BUG_ON(!early_boot_irqs_disabled); + BUG_ON(static_call_initialized); + __text_gen_insn(tramp, JMP32_INSN_OPCODE, tramp, func, JMP32_INSN_SIZE); + sync_core(); +} + #ifdef CONFIG_MITIGATION_RETHUNK /* * This is called by apply_returns() to fix up static call trampolines, diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index fab3ac9a4574..6a17396c8174 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -519,14 +519,10 @@ INIT_PER_CPU(irq_stack_backing_store); * linker will never mark as relocatable. (Using just ABSOLUTE() is not * sufficient for that). */ -#ifdef CONFIG_XEN #ifdef CONFIG_XEN_PV xen_elfnote_entry_value = ABSOLUTE(xen_elfnote_entry) + ABSOLUTE(startup_xen); #endif -xen_elfnote_hypercall_page_value = - ABSOLUTE(xen_elfnote_hypercall_page) + ABSOLUTE(hypercall_page); -#endif #ifdef CONFIG_PVH xen_elfnote_phys32_entry_value = ABSOLUTE(xen_elfnote_phys32_entry) + ABSOLUTE(pvh_start_xen - LOAD_OFFSET); |