diff options
Diffstat (limited to 'arch/x86/kernel/process.c')
| -rw-r--r-- | arch/x86/kernel/process.c | 1088 |
1 files changed, 852 insertions, 236 deletions
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 81a5f5e8f142..4c718f8adc59 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -1,33 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/errno.h> #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> -#include <linux/module.h> +#include <linux/sched/idle.h> +#include <linux/sched/debug.h> +#include <linux/sched/task.h> +#include <linux/sched/task_stack.h> +#include <linux/init.h> +#include <linux/export.h> #include <linux/pm.h> -#include <linux/clockchips.h> +#include <linux/tick.h> #include <linux/random.h> #include <linux/user-return-notifier.h> #include <linux/dmi.h> #include <linux/utsname.h> #include <linux/stackprotector.h> -#include <linux/tick.h> #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/cpuid/api.h> #include <asm/apic.h> -#include <asm/syscalls.h> -#include <asm/idle.h> -#include <asm/uaccess.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <linux/uaccess.h> +#include <asm/mwait.h> +#include <asm/fpu/api.h> +#include <asm/fpu/sched.h> +#include <asm/fpu/xstate.h> #include <asm/debugreg.h> #include <asm/nmi.h> +#include <asm/tlbflush.h> +#include <asm/mce.h> +#include <asm/vm86.h> +#include <asm/switch_to.h> +#include <asm/desc.h> +#include <asm/prctl.h> +#include <asm/spec-ctrl.h> +#include <asm/io_bitmap.h> +#include <asm/proto.h> +#include <asm/frame.h> +#include <asm/unwind.h> +#include <asm/tdx.h> +#include <asm/mmu_context.h> +#include <asm/msr.h> +#include <asm/shstk.h> + +#include "process.h" /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -36,27 +64,39 @@ * section. Since TSS's are completely CPU-local, we want them * on exact cacheline boundaries, to eliminate cacheline ping-pong. */ -DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS; - -#ifdef CONFIG_X86_64 -static DEFINE_PER_CPU(unsigned char, is_idle); -static ATOMIC_NOTIFIER_HEAD(idle_notifier); +__visible DEFINE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw) = { + .x86_tss = { + /* + * .sp0 is only used when entering ring 0 from a lower + * privilege level. Since the init task never runs anything + * but ring 0 code, there is no need for a valid value here. + * Poison it. + */ + .sp0 = (1UL << (BITS_PER_LONG-1)) + 1, -void idle_notifier_register(struct notifier_block *n) -{ - atomic_notifier_chain_register(&idle_notifier, n); -} -EXPORT_SYMBOL_GPL(idle_notifier_register); +#ifdef CONFIG_X86_32 + .sp1 = TOP_OF_INIT_STACK, -void idle_notifier_unregister(struct notifier_block *n) -{ - atomic_notifier_chain_unregister(&idle_notifier, n); -} -EXPORT_SYMBOL_GPL(idle_notifier_unregister); + .ss0 = __KERNEL_DS, + .ss1 = __KERNEL_CS, #endif + .io_bitmap_base = IO_BITMAP_OFFSET_INVALID, + }, +}; +EXPORT_PER_CPU_SYMBOL(cpu_tss_rw); -struct kmem_cache *task_xstate_cachep; -EXPORT_SYMBOL_GPL(task_xstate_cachep); +DEFINE_PER_CPU(bool, __tss_limit_invalid); +EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid); + +/* + * The cache may be in an incoherent state and needs flushing during kexec. + * E.g., on SME/TDX platforms, dirty cacheline aliases with and without + * encryption bit(s) can coexist and the cache needs to be flushed before + * booting to the new kernel to avoid the silent memory corruption due to + * dirty cachelines with different encryption property being written back + * to the memory. + */ +DEFINE_PER_CPU(bool, cache_state_incoherent); /* * this gets called so that we can store lazy state into memory and copy the @@ -64,61 +104,181 @@ EXPORT_SYMBOL_GPL(task_xstate_cachep); */ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - int ret; + /* fpu_clone() will initialize the "dst_fpu" memory */ + memcpy_and_pad(dst, arch_task_struct_size, src, sizeof(*dst), 0); + +#ifdef CONFIG_VM86 + dst->thread.vm86 = NULL; +#endif - *dst = *src; - if (fpu_allocated(&src->thread.fpu)) { - memset(&dst->thread.fpu, 0, sizeof(dst->thread.fpu)); - ret = fpu_alloc(&dst->thread.fpu); - if (ret) - return ret; - fpu_copy(dst, src); - } return 0; } -void free_thread_xstate(struct task_struct *tsk) +#ifdef CONFIG_X86_64 +void arch_release_task_struct(struct task_struct *tsk) { - fpu_free(&tsk->thread.fpu); + if (fpu_state_size_dynamic() && !(tsk->flags & (PF_KTHREAD | PF_USER_WORKER))) + fpstate_free(x86_task_fpu(tsk)); } +#endif -void arch_release_task_struct(struct task_struct *tsk) +/* + * Free thread data structures etc.. + */ +void exit_thread(struct task_struct *tsk) { - free_thread_xstate(tsk); + struct thread_struct *t = &tsk->thread; + + if (test_thread_flag(TIF_IO_BITMAP)) + io_bitmap_exit(tsk); + + free_vm86(t); + + shstk_free(tsk); + fpu__drop(tsk); } -void arch_task_cache_init(void) +static int set_new_tls(struct task_struct *p, unsigned long tls) { - task_xstate_cachep = - kmem_cache_create("task_xstate", xstate_size, - __alignof__(union thread_xstate), - SLAB_PANIC | SLAB_NOTRACK, NULL); + struct user_desc __user *utls = (struct user_desc __user *)tls; + + if (in_ia32_syscall()) + return do_set_thread_area(p, -1, utls, 0); + else + return do_set_thread_area_64(p, ARCH_SET_FS, tls); } -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) +__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) { - struct task_struct *me = current; - struct thread_struct *t = &me->thread; - unsigned long *bp = t->io_bitmap_ptr; + u64 clone_flags = args->flags; + unsigned long sp = args->stack; + unsigned long tls = args->tls; + 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); + fork_frame = container_of(childregs, struct fork_frame, regs); + frame = &fork_frame->frame; + + frame->bp = encode_frame_pointer(childregs); + frame->ret_addr = (unsigned long) ret_from_fork_asm; + p->thread.sp = (unsigned long) fork_frame; + p->thread.io_bitmap = NULL; + clear_tsk_thread_flag(p, TIF_IO_BITMAP); + p->thread.iopl_warn = 0; + memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); + +#ifdef CONFIG_X86_64 + current_save_fsgs(); + p->thread.fsindex = current->thread.fsindex; + p->thread.fsbase = current->thread.fsbase; + p->thread.gsindex = current->thread.gsindex; + p->thread.gsbase = current->thread.gsbase; + + 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); + /* + * Clear all status flags including IF and set fixed bit. 64bit + * does not have this initialization as the frame does not contain + * flags. The flags consistency (especially vs. AC) is there + * ensured via objtool, which lacks 32bit support. + */ + frame->flags = X86_EFLAGS_FIXED; +#endif + + /* + * 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)) { + p->thread.pkru = pkru_get_init_value(); + memset(childregs, 0, sizeof(struct pt_regs)); + kthread_frame_init(frame, args->fn, args->fn_arg); + return 0; + } - if (bp) { - struct tss_struct *tss = &per_cpu(init_tss, get_cpu()); + /* + * Clone current's PKRU value from hardware. tsk->thread.pkru + * is only valid when scheduled out. + */ + p->thread.pkru = read_pkru(); - t->io_bitmap_ptr = NULL; - clear_thread_flag(TIF_IO_BITMAP); + frame->bx = 0; + *childregs = *current_pt_regs(); + childregs->ax = 0; + if (sp) + childregs->sp = sp; + + if (unlikely(args->fn)) { /* - * Careful, clear this in the TSS too: + * A user space thread, but it doesn't return to + * ret_after_fork(). + * + * In order to indicate that to tools like gdb, + * we reset the stack and instruction pointers. + * + * It does the same kernel frame setup to return to a kernel + * function that a kernel thread does. */ - memset(tss->io_bitmap, 0xff, t->io_bitmap_max); - t->io_bitmap_max = 0; - put_cpu(); - kfree(bp); + childregs->sp = 0; + childregs->ip = 0; + kthread_frame_init(frame, args->fn, args->fn_arg); + return 0; } - drop_fpu(me); + /* Set a new TLS for the child thread? */ + if (clone_flags & CLONE_SETTLS) + ret = set_new_tls(p, tls); + + if (!ret && unlikely(test_tsk_thread_flag(current, TIF_IO_BITMAP))) + io_bitmap_share(p); + + return ret; +} + +static void pkru_flush_thread(void) +{ + /* + * If PKRU is enabled the default PKRU value has to be loaded into + * the hardware right here (similar to context switch). + */ + pkru_write_default(); } void flush_thread(void) @@ -127,18 +287,9 @@ void flush_thread(void) flush_ptrace_hw_breakpoint(tsk); memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - drop_init_fpu(tsk); - /* - * Free the FPU state for non xsave platforms. They get reallocated - * lazily at the first use. - */ - if (!use_eager_fpu()) - free_thread_xstate(tsk); -} -static void hard_disable_TSC(void) -{ - write_cr4(read_cr4() | X86_CR4_TSD); + fpu_flush_thread(); + pkru_flush_thread(); } void disable_TSC(void) @@ -149,15 +300,10 @@ void disable_TSC(void) * Must flip the CPU state synchronously with * TIF_NOTSC in the current running context. */ - hard_disable_TSC(); + cr4_set_bits(X86_CR4_TSD); preempt_enable(); } -static void hard_enable_TSC(void) -{ - write_cr4(read_cr4() & ~X86_CR4_TSD); -} - static void enable_TSC(void) { preempt_disable(); @@ -166,7 +312,7 @@ static void enable_TSC(void) * Must flip the CPU state synchronously with * TIF_NOTSC in the current running context. */ - hard_enable_TSC(); + cr4_clear_bits(X86_CR4_TSD); preempt_enable(); } @@ -194,232 +340,657 @@ int set_tsc_mode(unsigned int val) return 0; } -void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, - struct tss_struct *tss) -{ - struct thread_struct *prev, *next; - - prev = &prev_p->thread; - next = &next_p->thread; - - if (test_tsk_thread_flag(prev_p, TIF_BLOCKSTEP) ^ - test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) { - unsigned long debugctl = get_debugctlmsr(); +DEFINE_PER_CPU(u64, msr_misc_features_shadow); - debugctl &= ~DEBUGCTLMSR_BTF; - if (test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) - debugctl |= DEBUGCTLMSR_BTF; - - update_debugctlmsr(debugctl); - } +static void set_cpuid_faulting(bool on) +{ - if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ - test_tsk_thread_flag(next_p, TIF_NOTSC)) { - /* prev and next are different */ - if (test_tsk_thread_flag(next_p, TIF_NOTSC)) - hard_disable_TSC(); + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) { + u64 msrval; + + msrval = this_cpu_read(msr_misc_features_shadow); + msrval &= ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT; + msrval |= (on << MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT); + this_cpu_write(msr_misc_features_shadow, msrval); + wrmsrq(MSR_MISC_FEATURES_ENABLES, msrval); + } else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + if (on) + msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_CPUID_USER_DIS_BIT); else - hard_enable_TSC(); + msr_clear_bit(MSR_K7_HWCR, MSR_K7_HWCR_CPUID_USER_DIS_BIT); } +} - if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { +static void disable_cpuid(void) +{ + preempt_disable(); + if (!test_and_set_thread_flag(TIF_NOCPUID)) { /* - * Copy the relevant range of the IO bitmap. - * Normally this is 128 bytes or less: + * Must flip the CPU state synchronously with + * TIF_NOCPUID in the current running context. */ - memcpy(tss->io_bitmap, next->io_bitmap_ptr, - max(prev->io_bitmap_max, next->io_bitmap_max)); - } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) { + set_cpuid_faulting(true); + } + preempt_enable(); +} + +static void enable_cpuid(void) +{ + preempt_disable(); + if (test_and_clear_thread_flag(TIF_NOCPUID)) { /* - * Clear any possible leftover bits: + * Must flip the CPU state synchronously with + * TIF_NOCPUID in the current running context. */ - memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); + set_cpuid_faulting(false); } - propagate_user_return_notify(prev_p, next_p); + preempt_enable(); +} + +static int get_cpuid_mode(void) +{ + return !test_thread_flag(TIF_NOCPUID); +} + +static int set_cpuid_mode(unsigned long cpuid_enabled) +{ + if (!boot_cpu_has(X86_FEATURE_CPUID_FAULT)) + return -ENODEV; + + if (cpuid_enabled) + enable_cpuid(); + else + disable_cpuid(); + + return 0; } /* - * Idle related variables and functions + * Called immediately after a successful exec. */ -unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE; -EXPORT_SYMBOL(boot_option_idle_override); +void arch_setup_new_exec(void) +{ + /* If cpuid was previously disabled for this task, re-enable it. */ + if (test_thread_flag(TIF_NOCPUID)) + enable_cpuid(); -static void (*x86_idle)(void); + /* + * Don't inherit TIF_SSBD across exec boundary when + * PR_SPEC_DISABLE_NOEXEC is used. + */ + if (test_thread_flag(TIF_SSBD) && + task_spec_ssb_noexec(current)) { + clear_thread_flag(TIF_SSBD); + task_clear_spec_ssb_disable(current); + task_clear_spec_ssb_noexec(current); + speculation_ctrl_update(read_thread_flags()); + } -#ifndef CONFIG_SMP -static inline void play_dead(void) -{ - BUG(); + mm_reset_untag_mask(current->mm); } -#endif -#ifdef CONFIG_X86_64 -void enter_idle(void) +#ifdef CONFIG_X86_IOPL_IOPERM +static inline void switch_to_bitmap(unsigned long tifp) { - this_cpu_write(is_idle, 1); - atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL); + /* + * Invalidate I/O bitmap if the previous task used it. This prevents + * any possible leakage of an active I/O bitmap. + * + * If the next task has an I/O bitmap it will handle it on exit to + * user mode. + */ + if (tifp & _TIF_IO_BITMAP) + tss_invalidate_io_bitmap(); } -static void __exit_idle(void) +static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm) { - if (x86_test_and_clear_bit_percpu(0, is_idle) == 0) - return; - atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL); + /* + * Copy at least the byte range of the incoming tasks bitmap which + * covers the permitted I/O ports. + * + * If the previous task which used an I/O bitmap had more bits + * permitted, then the copy needs to cover those as well so they + * get turned off. + */ + memcpy(tss->io_bitmap.bitmap, iobm->bitmap, + max(tss->io_bitmap.prev_max, iobm->max)); + + /* + * Store the new max and the sequence number of this bitmap + * and a pointer to the bitmap itself. + */ + tss->io_bitmap.prev_max = iobm->max; + tss->io_bitmap.prev_sequence = iobm->sequence; } -/* Called from interrupts to signify idle end */ -void exit_idle(void) +/** + * native_tss_update_io_bitmap - Update I/O bitmap before exiting to user mode + */ +void native_tss_update_io_bitmap(void) { - /* idle loop has pid 0 */ - if (current->pid) + struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); + struct thread_struct *t = ¤t->thread; + u16 *base = &tss->x86_tss.io_bitmap_base; + + if (!test_thread_flag(TIF_IO_BITMAP)) { + native_tss_invalidate_io_bitmap(); return; - __exit_idle(); + } + + if (IS_ENABLED(CONFIG_X86_IOPL_IOPERM) && t->iopl_emul == 3) { + *base = IO_BITMAP_OFFSET_VALID_ALL; + } else { + struct io_bitmap *iobm = t->io_bitmap; + + if (WARN_ON_ONCE(!iobm)) { + clear_thread_flag(TIF_IO_BITMAP); + native_tss_invalidate_io_bitmap(); + } + + /* + * Only copy bitmap data when the sequence number differs. The + * update time is accounted to the incoming task. + */ + if (tss->io_bitmap.prev_sequence != iobm->sequence) + tss_copy_io_bitmap(tss, iobm); + + /* Enable the bitmap */ + *base = IO_BITMAP_OFFSET_VALID_MAP; + } + + /* + * 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 the bitmap is outside + * the TSS limit. + */ + refresh_tss_limit(); } +#else /* CONFIG_X86_IOPL_IOPERM */ +static inline void switch_to_bitmap(unsigned long tifp) { } #endif -void arch_cpu_idle_enter(void) +#ifdef CONFIG_SMP + +struct ssb_state { + struct ssb_state *shared_state; + raw_spinlock_t lock; + unsigned int disable_state; + unsigned long local_state; +}; + +#define LSTATE_SSB 0 + +static DEFINE_PER_CPU(struct ssb_state, ssb_state); + +void speculative_store_bypass_ht_init(void) { - local_touch_nmi(); - enter_idle(); + struct ssb_state *st = this_cpu_ptr(&ssb_state); + unsigned int this_cpu = smp_processor_id(); + unsigned int cpu; + + st->local_state = 0; + + /* + * Shared state setup happens once on the first bringup + * of the CPU. It's not destroyed on CPU hotunplug. + */ + if (st->shared_state) + return; + + raw_spin_lock_init(&st->lock); + + /* + * Go over HT siblings and check whether one of them has set up the + * shared state pointer already. + */ + for_each_cpu(cpu, topology_sibling_cpumask(this_cpu)) { + if (cpu == this_cpu) + continue; + + if (!per_cpu(ssb_state, cpu).shared_state) + continue; + + /* Link it to the state of the sibling: */ + st->shared_state = per_cpu(ssb_state, cpu).shared_state; + return; + } + + /* + * First HT sibling to come up on the core. Link shared state of + * the first HT sibling to itself. The siblings on the same core + * which come up later will see the shared state pointer and link + * themselves to the state of this CPU. + */ + st->shared_state = st; } -void arch_cpu_idle_exit(void) +/* + * Logic is: First HT sibling enables SSBD for both siblings in the core + * and last sibling to disable it, disables it for the whole core. This how + * MSR_SPEC_CTRL works in "hardware": + * + * CORE_SPEC_CTRL = THREAD0_SPEC_CTRL | THREAD1_SPEC_CTRL + */ +static __always_inline void amd_set_core_ssb_state(unsigned long tifn) { - __exit_idle(); + struct ssb_state *st = this_cpu_ptr(&ssb_state); + u64 msr = x86_amd_ls_cfg_base; + + if (!static_cpu_has(X86_FEATURE_ZEN)) { + msr |= ssbd_tif_to_amd_ls_cfg(tifn); + wrmsrq(MSR_AMD64_LS_CFG, msr); + return; + } + + if (tifn & _TIF_SSBD) { + /* + * Since this can race with prctl(), block reentry on the + * same CPU. + */ + if (__test_and_set_bit(LSTATE_SSB, &st->local_state)) + return; + + msr |= x86_amd_ls_cfg_ssbd_mask; + + raw_spin_lock(&st->shared_state->lock); + /* First sibling enables SSBD: */ + if (!st->shared_state->disable_state) + wrmsrq(MSR_AMD64_LS_CFG, msr); + st->shared_state->disable_state++; + raw_spin_unlock(&st->shared_state->lock); + } else { + if (!__test_and_clear_bit(LSTATE_SSB, &st->local_state)) + return; + + raw_spin_lock(&st->shared_state->lock); + st->shared_state->disable_state--; + if (!st->shared_state->disable_state) + wrmsrq(MSR_AMD64_LS_CFG, msr); + raw_spin_unlock(&st->shared_state->lock); + } } +#else +static __always_inline void amd_set_core_ssb_state(unsigned long tifn) +{ + u64 msr = x86_amd_ls_cfg_base | ssbd_tif_to_amd_ls_cfg(tifn); -void arch_cpu_idle_dead(void) + wrmsrq(MSR_AMD64_LS_CFG, msr); +} +#endif + +static __always_inline void amd_set_ssb_virt_state(unsigned long tifn) { - play_dead(); + /* + * SSBD has the same definition in SPEC_CTRL and VIRT_SPEC_CTRL, + * so ssbd_tif_to_spec_ctrl() just works. + */ + wrmsrq(MSR_AMD64_VIRT_SPEC_CTRL, ssbd_tif_to_spec_ctrl(tifn)); } /* - * Called from the generic idle code. + * Update the MSRs managing speculation control, during context switch. + * + * tifp: Previous task's thread flags + * tifn: Next task's thread flags */ -void arch_cpu_idle(void) +static __always_inline void __speculation_ctrl_update(unsigned long tifp, + unsigned long tifn) { - if (cpuidle_idle_call()) - x86_idle(); - else - local_irq_enable(); + unsigned long tif_diff = tifp ^ tifn; + u64 msr = x86_spec_ctrl_base; + bool updmsr = false; + + lockdep_assert_irqs_disabled(); + + /* Handle change of TIF_SSBD depending on the mitigation method. */ + if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) { + if (tif_diff & _TIF_SSBD) + amd_set_ssb_virt_state(tifn); + } else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) { + if (tif_diff & _TIF_SSBD) + amd_set_core_ssb_state(tifn); + } else if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + static_cpu_has(X86_FEATURE_AMD_SSBD)) { + updmsr |= !!(tif_diff & _TIF_SSBD); + msr |= ssbd_tif_to_spec_ctrl(tifn); + } + + /* Only evaluate TIF_SPEC_IB if conditional STIBP is enabled. */ + if (IS_ENABLED(CONFIG_SMP) && + static_branch_unlikely(&switch_to_cond_stibp)) { + updmsr |= !!(tif_diff & _TIF_SPEC_IB); + msr |= stibp_tif_to_spec_ctrl(tifn); + } + + if (updmsr) + update_spec_ctrl_cond(msr); +} + +static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk) +{ + if (test_and_clear_tsk_thread_flag(tsk, TIF_SPEC_FORCE_UPDATE)) { + if (task_spec_ssb_disable(tsk)) + set_tsk_thread_flag(tsk, TIF_SSBD); + else + clear_tsk_thread_flag(tsk, TIF_SSBD); + + if (task_spec_ib_disable(tsk)) + set_tsk_thread_flag(tsk, TIF_SPEC_IB); + else + clear_tsk_thread_flag(tsk, TIF_SPEC_IB); + } + /* Return the updated threadinfo flags*/ + return read_task_thread_flags(tsk); +} + +void speculation_ctrl_update(unsigned long tif) +{ + unsigned long flags; + + /* Forced update. Make sure all relevant TIF flags are different */ + local_irq_save(flags); + __speculation_ctrl_update(~tif, tif); + local_irq_restore(flags); +} + +/* Called from seccomp/prctl update */ +void speculation_ctrl_update_current(void) +{ + preempt_disable(); + speculation_ctrl_update(speculation_ctrl_update_tif(current)); + preempt_enable(); +} + +static inline void cr4_toggle_bits_irqsoff(unsigned long mask) +{ + unsigned long newval, cr4 = this_cpu_read(cpu_tlbstate.cr4); + + newval = cr4 ^ mask; + if (newval != cr4) { + this_cpu_write(cpu_tlbstate.cr4, newval); + __write_cr4(newval); + } +} + +void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p) +{ + unsigned long tifp, tifn; + + tifn = read_task_thread_flags(next_p); + tifp = read_task_thread_flags(prev_p); + + switch_to_bitmap(tifp); + + propagate_user_return_notify(prev_p, next_p); + + if ((tifp & _TIF_BLOCKSTEP || tifn & _TIF_BLOCKSTEP) && + arch_has_block_step()) { + unsigned long debugctl, msk; + + rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctl); + debugctl &= ~DEBUGCTLMSR_BTF; + msk = tifn & _TIF_BLOCKSTEP; + debugctl |= (msk >> TIF_BLOCKSTEP) << DEBUGCTLMSR_BTF_SHIFT; + wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctl); + } + + if ((tifp ^ tifn) & _TIF_NOTSC) + cr4_toggle_bits_irqsoff(X86_CR4_TSD); + + if ((tifp ^ tifn) & _TIF_NOCPUID) + set_cpuid_faulting(!!(tifn & _TIF_NOCPUID)); + + if (likely(!((tifp | tifn) & _TIF_SPEC_FORCE_UPDATE))) { + __speculation_ctrl_update(tifp, tifn); + } else { + speculation_ctrl_update_tif(prev_p); + tifn = speculation_ctrl_update_tif(next_p); + + /* Enforce MSR update to ensure consistent state */ + __speculation_ctrl_update(~tifn, tifn); + } } /* + * Idle related variables and functions + */ +unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE; +EXPORT_SYMBOL(boot_option_idle_override); + +/* * We use this if we don't have any better idle routine.. */ -void default_idle(void) +void __cpuidle default_idle(void) { - trace_cpu_idle_rcuidle(1, smp_processor_id()); - safe_halt(); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); + raw_safe_halt(); + raw_local_irq_disable(); } -#ifdef CONFIG_APM_MODULE +#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 __noreturn play_dead(void) +{ + BUG(); +} +#endif + +void arch_cpu_idle_enter(void) +{ + tsc_verify_tsc_adjust(false); + local_touch_nmi(); +} + +void __noreturn arch_cpu_idle_dead(void) +{ + play_dead(); +} + +/* + * Called from the generic idle code. + */ +void __cpuidle arch_cpu_idle(void) +{ + static_call(x86_idle)(); +} +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 -void stop_this_cpu(void *dummy) + +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(c); - for (;;) - halt(); -} + if (this_cpu_read(cache_state_incoherent)) + 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); -bool amd_e400_c1e_detected; -EXPORT_SYMBOL(amd_e400_c1e_detected); +#ifdef CONFIG_SMP + if (smp_ops.stop_this_cpu) { + smp_ops.stop_this_cpu(); + BUG(); + } +#endif -static cpumask_var_t amd_e400_c1e_mask; + for (;;) { + /* + * Use native_halt() so that memory contents don't change + * (stack usage and variables) after possibly issuing the + * wbinvd() above. + */ + native_halt(); + } +} -void amd_e400_remove_cpu(int cpu) +/* + * 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. + * + * Do not prefer MWAIT if MONITOR instruction has a bug or idle=nomwait + * is passed to kernel commandline parameter. + */ +static __init bool prefer_mwait_c1_over_halt(void) { - if (amd_e400_c1e_mask != NULL) - cpumask_clear_cpu(cpu, amd_e400_c1e_mask); + const struct cpuinfo_x86 *c = &boot_cpu_data; + u32 eax, ebx, ecx, edx; + + /* 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 false; + + /* 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_LEAF_MWAIT, &eax, &ebx, &ecx, &edx); + + /* + * If MWAIT extensions are not available, it is safe to use MWAIT + * with EAX=0, ECX=0. + */ + if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) + return true; + + /* + * If MWAIT extensions are available, there should be at least one + * MWAIT C1 substate present. + */ + return !!(edx & MWAIT_C1_SUBSTATE_MASK); } /* - * AMD Erratum 400 aware idle routine. We check for C1E active in the interrupt - * pending message MSR. If we detect C1E, then we handle it the same - * way as C3 power states (local apic timer and TSC stop) + * MONITOR/MWAIT with no hints, used for default C1 state. This invokes MWAIT + * with interrupts enabled and no flags, which is backwards compatible with the + * original MWAIT implementation. */ -static void amd_e400_idle(void) +static __cpuidle void mwait_idle(void) { - if (!amd_e400_c1e_detected) { - u32 lo, hi; + if (need_resched()) + return; - rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi); + x86_idle_clear_cpu_buffers(); - if (lo & K8_INTP_C1E_ACTIVE_MASK) { - amd_e400_c1e_detected = true; - 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 (!current_set_polling_and_test()) { + const void *addr = ¤t_thread_info()->flags; - if (amd_e400_c1e_detected) { - int cpu = smp_processor_id(); - - if (!cpumask_test_cpu(cpu, amd_e400_c1e_mask)) { - cpumask_set_cpu(cpu, amd_e400_c1e_mask); - /* - * Force broadcast so ACPI can not interfere. - */ - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE, - &cpu); - pr_info("Switch to broadcast mode on CPU%d\n", cpu); - } - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu); + alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr)); + __monitor(addr, 0, 0); + if (need_resched()) + goto out; - default_idle(); + __sti_mwait(0, 0); + raw_local_irq_disable(); + } - /* - * The switch back from broadcast mode needs to be - * called with interrupts disabled. - */ - local_irq_disable(); - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu); - local_irq_enable(); - } else - default_idle(); +out: + __current_clr_polling(); } -void __cpuinit 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 (cpu_has_bug(c, X86_BUG_AMD_APIC_C1E)) { - /* E400: APIC timer interrupt does not wake up CPU from C1e */ - pr_info("using AMD E400 aware idle routine\n"); - x86_idle = amd_e400_idle; - } else - x86_idle = default_idle; + /* 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"); + static_call_update(x86_idle, mwait_idle); + } else if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { + pr_info("using TDX aware idle routine\n"); + static_call_update(x86_idle, tdx_halt); + } else { + static_call_update(x86_idle, default_idle); + } +} + +void amd_e400_c1e_apic_setup(void) +{ + if (boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) { + pr_info("Switch to broadcast mode on CPU%d\n", smp_processor_id()); + local_irq_disable(); + tick_broadcast_force(); + local_irq_enable(); + } } -void __init init_amd_e400_c1e_mask(void) +void __init arch_post_acpi_subsys_init(void) { - /* If we're using amd_e400_idle, we need to allocate amd_e400_c1e_mask. */ - if (x86_idle == amd_e400_idle) - zalloc_cpumask_var(&amd_e400_c1e_mask, GFP_KERNEL); + u32 lo, hi; + + if (!boot_cpu_has_bug(X86_BUG_AMD_E400)) + return; + + /* + * AMD E400 detection needs to happen after ACPI has been enabled. If + * the machine is affected K8_INTP_C1E_ACTIVE_MASK bits are set in + * MSR_K8_INT_PENDING_MSG. + */ + rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi); + if (!(lo & K8_INTP_C1E_ACTIVE_MASK)) + return; + + boot_cpu_set_bug(X86_BUG_AMD_APIC_C1E); + + if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) + mark_tsc_unstable("TSC halt in AMD C1E"); + + 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) @@ -432,25 +1003,14 @@ 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 C2/C3 - * states. In such case it won't touch the variable - * of boot_option_idle_override. - */ + /* 'idle=nomwait' disables MWAIT for idle */ boot_option_idle_override = IDLE_NOMWAIT; - } else - return -1; + } else { + return -EINVAL; + } return 0; } @@ -459,13 +1019,69 @@ 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) { - unsigned long range_end = mm->brk + 0x02000000; - return randomize_range(mm->brk, range_end, 0) ? : mm->brk; + if (mmap_is_ia32()) + return randomize_page(mm->brk, SZ_32M); + + return randomize_page(mm->brk, SZ_1G); } +/* + * Called from fs/proc with a reference on @p to find the function + * which called into schedule(). This needs to be done carefully + * because the task might wake up and we might look at a stack + * changing under us. + */ +unsigned long __get_wchan(struct task_struct *p) +{ + struct unwind_state state; + unsigned long addr = 0; + + if (!try_get_task_stack(p)) + return 0; + + for (unwind_start(&state, p, NULL, NULL); !unwind_done(&state); + unwind_next_frame(&state)) { + addr = unwind_get_return_address(&state); + if (!addr) + break; + if (in_sched_functions(addr)) + continue; + break; + } + + put_task_stack(p); + + return addr; +} + +SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) +{ + switch (option) { + case ARCH_GET_CPUID: + return get_cpuid_mode(); + case ARCH_SET_CPUID: + return set_cpuid_mode(arg2); + case ARCH_GET_XCOMP_SUPP: + case ARCH_GET_XCOMP_PERM: + case ARCH_REQ_XCOMP_PERM: + case ARCH_GET_XCOMP_GUEST_PERM: + case ARCH_REQ_XCOMP_GUEST_PERM: + return fpu_xstate_prctl(option, arg2); + } + + if (!in_ia32_syscall()) + return do_arch_prctl_64(current, option, arg2); + + return -EINVAL; +} + +SYSCALL_DEFINE0(ni_syscall) +{ + return -ENOSYS; +} |