diff options
Diffstat (limited to 'arch/x86/entry/common.c')
-rw-r--r-- | arch/x86/entry/common.c | 106 |
1 files changed, 53 insertions, 53 deletions
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 03663740c866..e79d93d44ecd 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -26,6 +26,7 @@ #include <asm/traps.h> #include <asm/vdso.h> #include <asm/uaccess.h> +#include <asm/cpufeature.h> #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> @@ -44,6 +45,8 @@ __visible void enter_from_user_mode(void) CT_WARN_ON(ct_state() != CONTEXT_USER); user_exit(); } +#else +static inline void enter_from_user_mode(void) {} #endif static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch) @@ -84,17 +87,6 @@ unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch) work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY; -#ifdef CONFIG_CONTEXT_TRACKING - /* - * If TIF_NOHZ is set, we are required to call user_exit() before - * doing anything that could touch RCU. - */ - if (work & _TIF_NOHZ) { - enter_from_user_mode(); - work &= ~_TIF_NOHZ; - } -#endif - #ifdef CONFIG_SECCOMP /* * Do seccomp first -- it should minimize exposure of other @@ -171,16 +163,6 @@ long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch, if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) BUG_ON(regs != task_pt_regs(current)); - /* - * If we stepped into a sysenter/syscall insn, it trapped in - * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP. - * If user-mode had set TF itself, then it's still clear from - * do_debug() and we need to set it again to restore the user - * state. If we entered on the slow path, TF was already set. - */ - if (work & _TIF_SINGLESTEP) - regs->flags |= X86_EFLAGS_TF; - #ifdef CONFIG_SECCOMP /* * Call seccomp_phase2 before running the other hooks so that @@ -268,6 +250,7 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) /* Called with IRQs disabled. */ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) { + struct thread_info *ti = pt_regs_to_thread_info(regs); u32 cached_flags; if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled())) @@ -275,12 +258,22 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) lockdep_sys_exit(); - cached_flags = - READ_ONCE(pt_regs_to_thread_info(regs)->flags); + cached_flags = READ_ONCE(ti->flags); if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS)) exit_to_usermode_loop(regs, cached_flags); +#ifdef CONFIG_COMPAT + /* + * Compat syscalls set TS_COMPAT. Make sure we clear it before + * returning to user mode. We need to clear it *after* signal + * handling, because syscall restart has a fixup for compat + * syscalls. The fixup is exercised by the ptrace_syscall_32 + * selftest. + */ + ti->status &= ~TS_COMPAT; +#endif + user_enter(); } @@ -332,33 +325,45 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs) if (unlikely(cached_flags & SYSCALL_EXIT_WORK_FLAGS)) syscall_slow_exit_work(regs, cached_flags); -#ifdef CONFIG_COMPAT + local_irq_disable(); + prepare_exit_to_usermode(regs); +} + +#ifdef CONFIG_X86_64 +__visible void do_syscall_64(struct pt_regs *regs) +{ + struct thread_info *ti = pt_regs_to_thread_info(regs); + unsigned long nr = regs->orig_ax; + + enter_from_user_mode(); + local_irq_enable(); + + if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) + nr = syscall_trace_enter(regs); + /* - * Compat syscalls set TS_COMPAT. Make sure we clear it before - * returning to user mode. + * NB: Native and x32 syscalls are dispatched from the same + * table. The only functional difference is the x32 bit in + * regs->orig_ax, which changes the behavior of some syscalls. */ - ti->status &= ~TS_COMPAT; -#endif + if (likely((nr & __SYSCALL_MASK) < NR_syscalls)) { + regs->ax = sys_call_table[nr & __SYSCALL_MASK]( + regs->di, regs->si, regs->dx, + regs->r10, regs->r8, regs->r9); + } - local_irq_disable(); - prepare_exit_to_usermode(regs); + syscall_return_slowpath(regs); } +#endif #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) /* - * Does a 32-bit syscall. Called with IRQs on and does all entry and - * exit work and returns with IRQs off. This function is extremely hot - * in workloads that use it, and it's usually called from + * Does a 32-bit syscall. Called with IRQs on in CONTEXT_KERNEL. Does + * all entry and exit work and returns with IRQs off. This function is + * extremely hot in workloads that use it, and it's usually called from * do_fast_syscall_32, so forcibly inline it to improve performance. */ -#ifdef CONFIG_X86_32 -/* 32-bit kernels use a trap gate for INT80, and the asm code calls here. */ -__visible -#else -/* 64-bit kernels use do_syscall_32_irqs_off() instead. */ -static -#endif -__always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) +static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) { struct thread_info *ti = pt_regs_to_thread_info(regs); unsigned int nr = (unsigned int)regs->orig_ax; @@ -393,14 +398,13 @@ __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) syscall_return_slowpath(regs); } -#ifdef CONFIG_X86_64 -/* Handles INT80 on 64-bit kernels */ -__visible void do_syscall_32_irqs_off(struct pt_regs *regs) +/* Handles int $0x80 */ +__visible void do_int80_syscall_32(struct pt_regs *regs) { + enter_from_user_mode(); local_irq_enable(); do_syscall_32_irqs_on(regs); } -#endif /* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */ __visible long do_fast_syscall_32(struct pt_regs *regs) @@ -420,12 +424,11 @@ __visible long do_fast_syscall_32(struct pt_regs *regs) */ regs->ip = landing_pad; - /* - * Fetch EBP from where the vDSO stashed it. - * - * WARNING: We are in CONTEXT_USER and RCU isn't paying attention! - */ + enter_from_user_mode(); + local_irq_enable(); + + /* Fetch EBP from where the vDSO stashed it. */ if ( #ifdef CONFIG_X86_64 /* @@ -443,9 +446,6 @@ __visible long do_fast_syscall_32(struct pt_regs *regs) /* User code screwed up. */ local_irq_disable(); regs->ax = -EFAULT; -#ifdef CONFIG_CONTEXT_TRACKING - enter_from_user_mode(); -#endif prepare_exit_to_usermode(regs); return 0; /* Keep it simple: use IRET. */ } |