diff options
Diffstat (limited to 'arch/x86/kernel/process.c')
-rw-r--r-- | arch/x86/kernel/process.c | 71 |
1 files changed, 45 insertions, 26 deletions
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b8441147eb5e..704883c21f3a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -30,6 +30,7 @@ #include <linux/hw_breakpoint.h> #include <linux/entry-common.h> #include <asm/cpu.h> +#include <asm/cpuid/api.h> #include <asm/apic.h> #include <linux/uaccess.h> #include <asm/mwait.h> @@ -51,6 +52,7 @@ #include <asm/unwind.h> #include <asm/tdx.h> #include <asm/mmu_context.h> +#include <asm/msr.h> #include <asm/shstk.h> #include "process.h" @@ -92,12 +94,12 @@ EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid); */ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - memcpy(dst, src, arch_task_struct_size); + /* 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 - /* Drop the copied pointer to current's fpstate */ - dst->thread.fpu.fpstate = NULL; return 0; } @@ -105,8 +107,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) #ifdef CONFIG_X86_64 void arch_release_task_struct(struct task_struct *tsk) { - if (fpu_state_size_dynamic()) - fpstate_free(&tsk->thread.fpu); + if (fpu_state_size_dynamic() && !(tsk->flags & (PF_KTHREAD | PF_USER_WORKER))) + fpstate_free(x86_task_fpu(tsk)); } #endif @@ -116,7 +118,6 @@ void arch_release_task_struct(struct task_struct *tsk) void exit_thread(struct task_struct *tsk) { struct thread_struct *t = &tsk->thread; - struct fpu *fpu = &t->fpu; if (test_thread_flag(TIF_IO_BITMAP)) io_bitmap_exit(tsk); @@ -124,7 +125,7 @@ void exit_thread(struct task_struct *tsk) free_vm86(t); shstk_free(tsk); - fpu__drop(fpu); + fpu__drop(tsk); } static int set_new_tls(struct task_struct *p, unsigned long tls) @@ -175,6 +176,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) 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)); @@ -338,7 +340,7 @@ static void set_cpuid_faulting(bool on) msrval &= ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT; msrval |= (on << MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT); this_cpu_write(msr_misc_features_shadow, msrval); - wrmsrl(MSR_MISC_FEATURES_ENABLES, msrval); + wrmsrq(MSR_MISC_FEATURES_ENABLES, msrval); } static void disable_cpuid(void) @@ -463,6 +465,11 @@ void native_tss_update_io_bitmap(void) } 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. @@ -555,7 +562,7 @@ static __always_inline void amd_set_core_ssb_state(unsigned long tifn) if (!static_cpu_has(X86_FEATURE_ZEN)) { msr |= ssbd_tif_to_amd_ls_cfg(tifn); - wrmsrl(MSR_AMD64_LS_CFG, msr); + wrmsrq(MSR_AMD64_LS_CFG, msr); return; } @@ -572,7 +579,7 @@ static __always_inline void amd_set_core_ssb_state(unsigned long tifn) raw_spin_lock(&st->shared_state->lock); /* First sibling enables SSBD: */ if (!st->shared_state->disable_state) - wrmsrl(MSR_AMD64_LS_CFG, msr); + wrmsrq(MSR_AMD64_LS_CFG, msr); st->shared_state->disable_state++; raw_spin_unlock(&st->shared_state->lock); } else { @@ -582,7 +589,7 @@ static __always_inline void amd_set_core_ssb_state(unsigned long tifn) raw_spin_lock(&st->shared_state->lock); st->shared_state->disable_state--; if (!st->shared_state->disable_state) - wrmsrl(MSR_AMD64_LS_CFG, msr); + wrmsrq(MSR_AMD64_LS_CFG, msr); raw_spin_unlock(&st->shared_state->lock); } } @@ -591,7 +598,7 @@ 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); - wrmsrl(MSR_AMD64_LS_CFG, msr); + wrmsrq(MSR_AMD64_LS_CFG, msr); } #endif @@ -601,7 +608,7 @@ static __always_inline void amd_set_ssb_virt_state(unsigned long tifn) * SSBD has the same definition in SPEC_CTRL and VIRT_SPEC_CTRL, * so ssbd_tif_to_spec_ctrl() just works. */ - wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, ssbd_tif_to_spec_ctrl(tifn)); + wrmsrq(MSR_AMD64_VIRT_SPEC_CTRL, ssbd_tif_to_spec_ctrl(tifn)); } /* @@ -704,11 +711,11 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p) arch_has_block_step()) { unsigned long debugctl, msk; - rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctl); debugctl &= ~DEBUGCTLMSR_BTF; msk = tifn & _TIF_BLOCKSTEP; debugctl |= (msk >> TIF_BLOCKSTEP) << DEBUGCTLMSR_BTF_SHIFT; - wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctl); } if ((tifp ^ tifn) & _TIF_NOTSC) @@ -825,7 +832,7 @@ void __noreturn stop_this_cpu(void *dummy) * X86_FEATURE_SME due to cmdline options. */ if (c->extended_cpuid_level >= 0x8000001f && (cpuid_eax(0x8000001f) & BIT(0))) - native_wbinvd(); + wbinvd(); /* * This brings a cache line back and dirties it, but @@ -835,11 +842,18 @@ void __noreturn stop_this_cpu(void *dummy) */ cpumask_clear_cpu(cpu, &cpus_stop_mask); +#ifdef CONFIG_SMP + if (smp_ops.stop_this_cpu) { + smp_ops.stop_this_cpu(); + BUG(); + } +#endif + for (;;) { /* * Use native_halt() so that memory contents don't change * (stack usage and variables) after possibly issuing the - * native_wbinvd() above. + * wbinvd() above. */ native_halt(); } @@ -870,7 +884,7 @@ static __init bool prefer_mwait_c1_over_halt(void) 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); + cpuid(CPUID_LEAF_MWAIT, &eax, &ebx, &ecx, &edx); /* * If MWAIT extensions are not available, it is safe to use MWAIT @@ -894,13 +908,10 @@ static __init bool prefer_mwait_c1_over_halt(void) static __cpuidle void mwait_idle(void) { if (!current_set_polling_and_test()) { - if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) { - mb(); /* quirk */ - clflush((void *)¤t_thread_info()->flags); - mb(); /* quirk */ - } + const void *addr = ¤t_thread_info()->flags; - __monitor((void *)¤t_thread_info()->flags, 0, 0); + alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr)); + __monitor(addr, 0, 0); if (!need_resched()) { __sti_mwait(0, 0); raw_local_irq_disable(); @@ -926,7 +937,7 @@ void __init select_idle_routine(void) 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_safe_halt); + static_call_update(x86_idle, tdx_halt); } else { static_call_update(x86_idle, default_idle); } @@ -1035,7 +1046,7 @@ unsigned long __get_wchan(struct task_struct *p) return addr; } -long do_arch_prctl_common(int option, unsigned long arg2) +SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) { switch (option) { case ARCH_GET_CPUID: @@ -1050,5 +1061,13 @@ long do_arch_prctl_common(int option, unsigned long arg2) 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; +} |