diff options
Diffstat (limited to 'arch/x86/kernel/process.c')
| -rw-r--r-- | arch/x86/kernel/process.c | 240 |
1 files changed, 136 insertions, 104 deletions
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 58a6ea472db9..b8441147eb5e 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -5,6 +5,7 @@ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/smp.h> +#include <linux/cpu.h> #include <linux/prctl.h> #include <linux/slab.h> #include <linux/sched.h> @@ -24,8 +25,10 @@ #include <linux/cpuidle.h> #include <linux/acpi.h> #include <linux/elf-randomize.h> +#include <linux/static_call.h> #include <trace/events/power.h> #include <linux/hw_breakpoint.h> +#include <linux/entry-common.h> #include <asm/cpu.h> #include <asm/apic.h> #include <linux/uaccess.h> @@ -47,6 +50,8 @@ #include <asm/frame.h> #include <asm/unwind.h> #include <asm/tdx.h> +#include <asm/mmu_context.h> +#include <asm/shstk.h> #include "process.h" @@ -118,6 +123,7 @@ void exit_thread(struct task_struct *tsk) free_vm86(t); + shstk_free(tsk); fpu__drop(fpu); } @@ -131,6 +137,25 @@ static int set_new_tls(struct task_struct *p, unsigned long tls) return do_set_thread_area_64(p, ARCH_SET_FS, tls); } +__visible void ret_from_fork(struct task_struct *prev, struct pt_regs *regs, + int (*fn)(void *), void *fn_arg) +{ + schedule_tail(prev); + + /* Is this a kernel thread? */ + if (unlikely(fn)) { + fn(fn_arg); + /* + * A kernel thread is allowed to return here after successfully + * calling kernel_execve(). Exit to userspace to complete the + * execve() syscall. + */ + regs->ax = 0; + } + + syscall_exit_to_user_mode(regs); +} + int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; @@ -139,6 +164,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) struct inactive_task_frame *frame; struct fork_frame *fork_frame; struct pt_regs *childregs; + unsigned long new_ssp; int ret = 0; childregs = task_pt_regs(p); @@ -146,7 +172,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) frame = &fork_frame->frame; frame->bp = encode_frame_pointer(childregs); - frame->ret_addr = (unsigned long) ret_from_fork; + frame->ret_addr = (unsigned long) ret_from_fork_asm; p->thread.sp = (unsigned long) fork_frame; p->thread.io_bitmap = NULL; p->thread.iopl_warn = 0; @@ -161,6 +187,9 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) savesegment(es, p->thread.es); savesegment(ds, p->thread.ds); + + if (p->mm && (clone_flags & (CLONE_VM | CLONE_VFORK)) == CLONE_VM) + set_bit(MM_CONTEXT_LOCK_LAM, &p->mm->context.flags); #else p->thread.sp0 = (unsigned long) (childregs + 1); savesegment(gs, p->thread.gs); @@ -173,7 +202,16 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) frame->flags = X86_EFLAGS_FIXED; #endif - fpu_clone(p, clone_flags, args->fn); + /* + * Allocate a new shadow stack for thread if needed. If shadow stack, + * is disabled, new_ssp will remain 0, and fpu_clone() will know not to + * update it. + */ + new_ssp = shstk_alloc_thread_stack(p, clone_flags, args->stack_size); + if (IS_ERR_VALUE(new_ssp)) + return PTR_ERR((void *)new_ssp); + + fpu_clone(p, clone_flags, args->fn, new_ssp); /* Kernel thread ? */ if (unlikely(p->flags & PF_KTHREAD)) { @@ -367,6 +405,8 @@ void arch_setup_new_exec(void) task_clear_spec_ssb_noexec(current); speculation_ctrl_update(read_thread_flags()); } + + mm_reset_untag_mask(current->mm); } #ifdef CONFIG_X86_IOPL_IOPERM @@ -437,7 +477,7 @@ void native_tss_update_io_bitmap(void) /* * Make sure that the TSS limit is covering the IO bitmap. It might have * been cut down by a VMEXIT to 0x67 which would cause a subsequent I/O - * access from user space to trigger a #GP because tbe bitmap is outside + * access from user space to trigger a #GP because the bitmap is outside * the TSS limit. */ refresh_tss_limit(); @@ -600,7 +640,7 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp, } if (updmsr) - write_spec_ctrl_current(msr, false); + update_spec_ctrl_cond(msr); } static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk) @@ -694,10 +734,27 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p) unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE; EXPORT_SYMBOL(boot_option_idle_override); -static void (*x86_idle)(void); +/* + * We use this if we don't have any better idle routine.. + */ +void __cpuidle default_idle(void) +{ + raw_safe_halt(); + raw_local_irq_disable(); +} +#if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE) +EXPORT_SYMBOL(default_idle); +#endif + +DEFINE_STATIC_CALL_NULL(x86_idle, default_idle); + +static bool x86_idle_set(void) +{ + return !!static_call_query(x86_idle); +} #ifndef CONFIG_SMP -static inline void play_dead(void) +static inline void __noreturn play_dead(void) { BUG(); } @@ -709,7 +766,7 @@ void arch_cpu_idle_enter(void) local_touch_nmi(); } -void arch_cpu_idle_dead(void) +void __noreturn arch_cpu_idle_dead(void) { play_dead(); } @@ -717,42 +774,43 @@ void arch_cpu_idle_dead(void) /* * Called from the generic idle code. */ -void arch_cpu_idle(void) +void __cpuidle arch_cpu_idle(void) { - x86_idle(); + static_call(x86_idle)(); } - -/* - * We use this if we don't have any better idle routine.. - */ -void __cpuidle default_idle(void) -{ - raw_safe_halt(); -} -#if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE) -EXPORT_SYMBOL(default_idle); -#endif +EXPORT_SYMBOL_GPL(arch_cpu_idle); #ifdef CONFIG_XEN bool xen_set_default_idle(void) { - bool ret = !!x86_idle; + bool ret = x86_idle_set(); - x86_idle = default_idle; + static_call_update(x86_idle, default_idle); return ret; } #endif +struct cpumask cpus_stop_mask; + void __noreturn stop_this_cpu(void *dummy) { + struct cpuinfo_x86 *c = this_cpu_ptr(&cpu_info); + unsigned int cpu = smp_processor_id(); + local_irq_disable(); + /* - * Remove this CPU: + * Remove this CPU from the online mask and disable it + * unconditionally. This might be redundant in case that the reboot + * vector was handled late and stop_other_cpus() sent an NMI. + * + * According to SDM and APM NMIs can be accepted even after soft + * disabling the local APIC. */ - set_cpu_online(smp_processor_id(), false); + set_cpu_online(cpu, false); disable_local_APIC(); - mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); + mcheck_cpu_clear(c); /* * Use wbinvd on processors that support SME. This provides support @@ -766,8 +824,17 @@ void __noreturn stop_this_cpu(void *dummy) * Test the CPUID bit directly because the machine might've cleared * X86_FEATURE_SME due to cmdline options. */ - if (cpuid_eax(0x8000001f) & BIT(0)) + if (c->extended_cpuid_level >= 0x8000001f && (cpuid_eax(0x8000001f) & BIT(0))) native_wbinvd(); + + /* + * This brings a cache line back and dirties it, but + * native_stop_other_cpus() will overwrite cpus_stop_mask after it + * observed that all CPUs reported stop. This write will invalidate + * the related cache line on this CPU. + */ + cpumask_clear_cpu(cpu, &cpus_stop_mask); + for (;;) { /* * Use native_halt() so that memory contents don't change @@ -779,37 +846,6 @@ void __noreturn stop_this_cpu(void *dummy) } /* - * AMD Erratum 400 aware idle routine. We handle it the same way as C3 power - * states (local apic timer and TSC stop). - * - * XXX this function is completely buggered vs RCU and tracing. - */ -static void amd_e400_idle(void) -{ - /* - * We cannot use static_cpu_has_bug() here because X86_BUG_AMD_APIC_C1E - * gets set after static_cpu_has() places have been converted via - * alternatives. - */ - if (!boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) { - default_idle(); - return; - } - - tick_broadcast_enter(); - - default_idle(); - - /* - * The switch back from broadcast mode needs to be called with - * interrupts disabled. - */ - raw_local_irq_disable(); - tick_broadcast_exit(); - raw_local_irq_enable(); -} - -/* * Prefer MWAIT over HALT if MWAIT is supported, MWAIT_CPUID leaf * exists and whenever MONITOR/MWAIT extensions are present there is at * least one C1 substate. @@ -817,21 +853,22 @@ static void amd_e400_idle(void) * Do not prefer MWAIT if MONITOR instruction has a bug or idle=nomwait * is passed to kernel commandline parameter. */ -static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) +static __init bool prefer_mwait_c1_over_halt(void) { + const struct cpuinfo_x86 *c = &boot_cpu_data; u32 eax, ebx, ecx, edx; - /* User has disallowed the use of MWAIT. Fallback to HALT */ - if (boot_option_idle_override == IDLE_NOMWAIT) - return 0; + /* If override is enforced on the command line, fall back to HALT. */ + if (boot_option_idle_override != IDLE_NO_OVERRIDE) + return false; /* MWAIT is not supported on this platform. Fallback to HALT */ if (!cpu_has(c, X86_FEATURE_MWAIT)) - return 0; + return false; - /* Monitor has a bug. Fallback to HALT */ - if (boot_cpu_has_bug(X86_BUG_MONITOR)) - return 0; + /* Monitor has a bug or APIC stops in C1E. Fallback to HALT */ + if (boot_cpu_has_bug(X86_BUG_MONITOR) || boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) + return false; cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx); @@ -840,13 +877,13 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) * with EAX=0, ECX=0. */ if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) - return 1; + return true; /* * If MWAIT extensions are available, there should be at least one * MWAIT C1 substate present. */ - return (edx & MWAIT_C1_SUBSTATE_MASK); + return !!(edx & MWAIT_C1_SUBSTATE_MASK); } /* @@ -864,36 +901,35 @@ static __cpuidle void mwait_idle(void) } __monitor((void *)¤t_thread_info()->flags, 0, 0); - if (!need_resched()) + if (!need_resched()) { __sti_mwait(0, 0); - else - raw_local_irq_enable(); - } else { - raw_local_irq_enable(); + raw_local_irq_disable(); + } } __current_clr_polling(); } -void select_idle_routine(const struct cpuinfo_x86 *c) +void __init select_idle_routine(void) { -#ifdef CONFIG_SMP - if (boot_option_idle_override == IDLE_POLL && smp_num_siblings > 1) - pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n"); -#endif - if (x86_idle || boot_option_idle_override == IDLE_POLL) + if (boot_option_idle_override == IDLE_POLL) { + if (IS_ENABLED(CONFIG_SMP) && __max_threads_per_core > 1) + pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n"); return; + } - if (boot_cpu_has_bug(X86_BUG_AMD_E400)) { - pr_info("using AMD E400 aware idle routine\n"); - x86_idle = amd_e400_idle; - } else if (prefer_mwait_c1_over_halt(c)) { + /* Required to guard against xen_set_default_idle() */ + if (x86_idle_set()) + return; + + if (prefer_mwait_c1_over_halt()) { pr_info("using mwait in idle threads\n"); - x86_idle = mwait_idle; + static_call_update(x86_idle, mwait_idle); } else if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { pr_info("using TDX aware idle routine\n"); - x86_idle = tdx_safe_halt; - } else - x86_idle = default_idle; + static_call_update(x86_idle, tdx_safe_halt); + } else { + static_call_update(x86_idle, default_idle); + } } void amd_e400_c1e_apic_setup(void) @@ -926,7 +962,10 @@ void __init arch_post_acpi_subsys_init(void) if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) mark_tsc_unstable("TSC halt in AMD C1E"); - pr_info("System has AMD C1E enabled\n"); + + if (IS_ENABLED(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST_IDLE)) + static_branch_enable(&arch_needs_tick_broadcast); + pr_info("System has AMD C1E erratum E400. Workaround enabled.\n"); } static int __init idle_setup(char *str) @@ -939,24 +978,14 @@ static int __init idle_setup(char *str) boot_option_idle_override = IDLE_POLL; cpu_idle_poll_ctrl(true); } else if (!strcmp(str, "halt")) { - /* - * When the boot option of idle=halt is added, halt is - * forced to be used for CPU idle. In such case CPU C2/C3 - * won't be used again. - * To continue to load the CPU idle driver, don't touch - * the boot_option_idle_override. - */ - x86_idle = default_idle; + /* 'idle=halt' HALT for idle. C-states are disabled. */ boot_option_idle_override = IDLE_HALT; } else if (!strcmp(str, "nomwait")) { - /* - * If the boot option of "idle=nomwait" is added, - * it means that mwait will be disabled for CPU C1/C2/C3 - * states. - */ + /* 'idle=nomwait' disables MWAIT for idle */ boot_option_idle_override = IDLE_NOMWAIT; - } else - return -1; + } else { + return -EINVAL; + } return 0; } @@ -965,13 +994,16 @@ early_param("idle", idle_setup); unsigned long arch_align_stack(unsigned long sp) { if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) - sp -= get_random_int() % 8192; + sp -= get_random_u32_below(8192); return sp & ~0xf; } unsigned long arch_randomize_brk(struct mm_struct *mm) { - return randomize_page(mm->brk, 0x02000000); + if (mmap_is_ia32()) + return randomize_page(mm->brk, SZ_32M); + + return randomize_page(mm->brk, SZ_1G); } /* |