x86: Rewrite exit-to-userspace code

index 83a91f976330..35ab97e4bb9b 100644
@@ -22,7 +22,8 @@ extern int kmalloc_ok;
 extern unsigned long alloc_stack(int order, int atomic);
 extern void free_stack(unsigned long stack, int order);
 
-extern int do_signal(void);
+struct pt_regs;
+extern void do_signal(struct pt_regs *regs);
 extern void interrupt_end(void);
 extern void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs);
 

index 68b9119841cd..a6d922672b9f 100644
@@ -90,12 +90,14 @@ void *__switch_to(struct task_struct *from, struct task_struct *to)
 
 void interrupt_end(void)
 {
+	struct pt_regs *regs = &current->thread.regs;
+
 	if (need_resched())
 		schedule();
 	if (test_thread_flag(TIF_SIGPENDING))
-		do_signal();
+		do_signal(regs);
 	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
-		tracehook_notify_resume(&current->thread.regs);
+		tracehook_notify_resume(regs);
 }
 
 void exit_thread(void)

index 4f60e4aad790..57acbd67d85d 100644
@@ -64,7 +64,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	signal_setup_done(err, ksig, singlestep);
 }
 
-static int kern_do_signal(struct pt_regs *regs)
+void do_signal(struct pt_regs *regs)
 {
 	struct ksignal ksig;
 	int handled_sig = 0;

@@ -110,10 +110,4 @@ static int kern_do_signal(struct pt_regs *regs)
 	 */
 	if (!handled_sig)
 		restore_saved_sigmask();
-	return handled_sig;
-}
-
-int do_signal(void)
-{
-	return kern_do_signal(&current->thread.regs);
 }

index f1b3eb14b855..2077248e8a72 100644
@@ -291,7 +291,7 @@ void fix_range_common(struct mm_struct *mm, unsigned long start_addr,
 		/* We are under mmap_sem, release it such that current can terminate */
 		up_write(&current->mm->mmap_sem);
 		force_sig(SIGKILL, current);
-		do_signal();
+		do_signal(&current->thread.regs);
 	}
 }
 

index 8e4daf44e980..481311becb05 100644
@@ -172,7 +172,7 @@ static void bad_segv(struct faultinfo fi, unsigned long ip)
 void fatal_sigsegv(void)
 {
 	force_sigsegv(SIGSEGV, current);
-	do_signal();
+	do_signal(&current->thread.regs);
 	/*
 	 * This is to tell gcc that we're not returning - do_signal
 	 * can, in general, return, but in this case, it's not, since

index 2821838256b4..3f5ac9b86f69 100644
@@ -57,6 +57,19 @@ static inline void context_tracking_task_switch(struct task_struct *prev,
 	if (context_tracking_is_enabled())
 		__context_tracking_task_switch(prev, next);
 }
+
+/**
+ * ct_state() - return the current context tracking state if known
+ *
+ * Returns the current cpu's context tracking state if context tracking
+ * is enabled.  If context tracking is disabled, returns
+ * CONTEXT_DISABLED.  This should be used primarily for debugging.
+ */
+static inline enum ctx_state ct_state(void)
+{
+	return context_tracking_is_enabled() ?
+		this_cpu_read(context_tracking.state) : CONTEXT_DISABLED;
+}
 #else
 static inline void user_enter(void) { }
 static inline void user_exit(void) { }

@@ -64,8 +77,10 @@ static inline enum ctx_state exception_enter(void) { return 0; }
 static inline void exception_exit(enum ctx_state prev_ctx) { }
 static inline void context_tracking_task_switch(struct task_struct *prev,
 						struct task_struct *next) { }
+static inline enum ctx_state ct_state(void) { return CONTEXT_DISABLED; }
 #endif /* !CONFIG_CONTEXT_TRACKING */
 
+#define CT_WARN_ON(cond) WARN_ON(context_tracking_is_enabled() && (cond))
 
 #ifdef CONFIG_CONTEXT_TRACKING_FORCE
 extern void context_tracking_init(void);

index 6b7b96a32b75..d4aec2805849 100644
@@ -13,6 +13,7 @@ struct context_tracking {
 	 */
 	bool active;
 	enum ctx_state {
+		CONTEXT_DISABLED = -1,	/* returned by ct_state() if unknown */
 		CONTEXT_KERNEL = 0,
 		CONTEXT_USER,
 		CONTEXT_GUEST,

index ae9fc7cc360e..980e4330fb59 100644
@@ -544,6 +544,8 @@ int notrace notify_die(enum die_val val, const char *str,
 		.signr	= sig,
 
 	};
+	rcu_lockdep_assert(rcu_is_watching(),
+			   "notify_die called but RCU thinks we're quiescent");
 	return atomic_notifier_call_chain(&die_chain, val, &args);
 }
 NOKPROBE_SYMBOL(notify_die);

253 lines not on this page · raw message

index 31eab867e6d3..b42408bcf6b5 100644
@@ -30,6 +30,7 @@ typedef sigset_t compat_sigset_t;
 #endif /* __ASSEMBLY__ */
 #include <uapi/asm/signal.h>
 #ifndef __ASSEMBLY__
+extern void do_signal(struct pt_regs *regs);
 extern void do_notify_resume(struct pt_regs *, void *, __u32);
 
 #define __ARCH_HAS_SA_RESTORER

214 lines not on this page · raw message

index 1ea14fd53933..c0ad42a640b9 100644
@@ -683,7 +683,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
  * want to handle. Thus you cannot kill init even with a SIGKILL even by
  * mistake.
  */
-static void do_signal(struct pt_regs *regs)
+void do_signal(struct pt_regs *regs)
 {
 	struct ksignal ksig;
 

@@ -718,32 +718,6 @@ static void do_signal(struct pt_regs *regs)
 	restore_saved_sigmask();
 }
 
-/*
- * notification of userspace execution resumption
- * - triggered by the TIF_WORK_MASK flags
- */
-__visible void
-do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
-{
-	user_exit();
-
-	if (thread_info_flags & _TIF_UPROBE)
-		uprobe_notify_resume(regs);
-
-	/* deal with pending signal delivery */
-	if (thread_info_flags & _TIF_SIGPENDING)
-		do_signal(regs);
-
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
-		tracehook_notify_resume(regs);
-	}
-	if (thread_info_flags & _TIF_USER_RETURN_NOTIFY)
-		fire_user_return_notifiers();
-
-	user_enter();
-}
-
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
 {
 	struct task_struct *me = current;

index de379366f6d1..3f947488c9c1 100644
@@ -291,6 +291,8 @@ static void do_error_trap(struct pt_regs *regs, long error_code, char *str,
 	enum ctx_state prev_state = exception_enter();
 	siginfo_t info;
 
+	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
+
 	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) !=
 			NOTIFY_STOP) {
 		conditional_sti(regs);

@@ -377,6 +379,7 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 	siginfo_t *info;
 
 	prev_state = exception_enter();
+	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
 	if (notify_die(DIE_TRAP, "bounds", regs, error_code,
 			X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP)
 		goto exit;

@@ -458,6 +461,7 @@ do_general_protection(struct pt_regs *regs, long error_code)
 	enum ctx_state prev_state;
 
 	prev_state = exception_enter();
+	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
 	conditional_sti(regs);
 
 	if (v8086_mode(regs)) {

@@ -515,6 +519,7 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 		return;
 
 	prev_state = ist_enter(regs);
+	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
 	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
 				SIGTRAP) == NOTIFY_STOP)

@@ -794,6 +799,7 @@ dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
 	enum ctx_state prev_state;
 
 	prev_state = exception_enter();
+	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
 	math_error(regs, error_code, X86_TRAP_MF);
 	exception_exit(prev_state);
 }

@@ -804,6 +810,7 @@ do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
 	enum ctx_state prev_state;
 
 	prev_state = exception_enter();
+	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
 	math_error(regs, error_code, X86_TRAP_XF);
 	exception_exit(prev_state);
 }

@@ -862,6 +869,7 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 	enum ctx_state prev_state;
 
 	prev_state = exception_enter();
+	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
 	BUG_ON(use_eager_fpu());
 
 #ifdef CONFIG_MATH_EMULATION

@@ -891,6 +899,7 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 	enum ctx_state prev_state;
 
 	prev_state = exception_enter();
+	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
 	local_irq_enable();
 
 	info.si_signo = SIGILL;

index 348465473e55..8a7e35af7164 100644
@@ -28,6 +28,15 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
+#ifdef CONFIG_CONTEXT_TRACKING
+/* Called on entry from user mode with IRQs off. */
+__visible void enter_from_user_mode(void)
+{
+	CT_WARN_ON(ct_state() != CONTEXT_USER);
+	user_exit();
+}
+#endif
+
 static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
 {
 #ifdef CONFIG_X86_64

@@ -65,14 +74,16 @@ unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch)
 	work = ACCESS_ONCE(current_thread_info()->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) {
-		user_exit();
+		enter_from_user_mode();
 		work &= ~_TIF_NOHZ;
 	}
+#endif
 
 #ifdef CONFIG_SECCOMP
 	/*

index 8a7e35af7164..82c7a67204f1 100644
@@ -207,6 +207,7 @@ long syscall_trace_enter(struct pt_regs *regs)
 		return syscall_trace_enter_phase2(regs, arch, phase1_result);
 }
 
+/* Deprecated. */
 void syscall_trace_leave(struct pt_regs *regs)
 {
 	bool step;

@@ -237,8 +238,117 @@ void syscall_trace_leave(struct pt_regs *regs)
 	user_enter();
 }
 
+static struct thread_info *pt_regs_to_thread_info(struct pt_regs *regs)
+{
+	unsigned long top_of_stack =
+		(unsigned long)(regs + 1) + TOP_OF_KERNEL_STACK_PADDING;
+	return (struct thread_info *)(top_of_stack - THREAD_SIZE);
+}
+
+/* Called with IRQs disabled. */
+__visible void prepare_exit_to_usermode(struct pt_regs *regs)
+{
+	if (WARN_ON(!irqs_disabled()))
+		local_irq_enable();
+
+	/*
+	 * In order to return to user mode, we need to have IRQs off with
+	 * none of _TIF_SIGPENDING, _TIF_NOTIFY_RESUME, _TIF_USER_RETURN_NOTIFY,
+	 * _TIF_UPROBE, or _TIF_NEED_RESCHED set.  Several of these flags
+	 * can be set at any time on preemptable kernels if we have IRQs on,
+	 * so we need to loop.  Disabling preemption wouldn't help: doing the
+	 * work to clear some of the flags can sleep.
+	 */
+	while (true) {
+		u32 cached_flags =
+			READ_ONCE(pt_regs_to_thread_info(regs)->flags);
+
+		if (!(cached_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME |
+				      _TIF_UPROBE | _TIF_NEED_RESCHED)))
+			break;
+
+		/* We have work to do. */
+		local_irq_enable();
+
+		if (cached_flags & _TIF_NEED_RESCHED)
+			schedule();
+
+		if (cached_flags & _TIF_UPROBE)
+			uprobe_notify_resume(regs);
+
+		/* deal with pending signal delivery */
+		if (cached_flags & _TIF_SIGPENDING)
+			do_signal(regs);
+
+		if (cached_flags & _TIF_NOTIFY_RESUME) {
+			clear_thread_flag(TIF_NOTIFY_RESUME);
+			tracehook_notify_resume(regs);
+		}
+
+		if (cached_flags & _TIF_USER_RETURN_NOTIFY)
+			fire_user_return_notifiers();
+
+		/* Disable IRQs and retry */
+		local_irq_disable();
+	}
+
+	user_enter();
+}
+
+/*
+ * Called with IRQs on and fully valid regs.  Returns with IRQs off in a
+ * state such that we can immediately switch to user mode.
+ */
+__visible void syscall_return_slowpath(struct pt_regs *regs)
+{
+	struct thread_info *ti = pt_regs_to_thread_info(regs);
+	u32 cached_flags = READ_ONCE(ti->flags);
+	bool step;
+
+	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
+
+	if (WARN(irqs_disabled(), "syscall %ld left IRQs disabled",
+		 regs->orig_ax))
+		local_irq_enable();
+
+	/*
+	 * First do one-time work.  If these work items are enabled, we
+	 * want to run them exactly once per syscall exit with IRQs on.
+	 */
+	if (cached_flags & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT |
+			    _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT)) {
+		audit_syscall_exit(regs);
+
+		if (cached_flags & _TIF_SYSCALL_TRACEPOINT)
+			trace_sys_exit(regs, regs->ax);
+
+		/*
+		 * If TIF_SYSCALL_EMU is set, we only get here because of
+		 * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP).
+		 * We already reported this syscall instruction in
+		 * syscall_trace_enter().
+		 */
+		step = unlikely(
+			(cached_flags & (_TIF_SINGLESTEP | _TIF_SYSCALL_EMU))
+			== _TIF_SINGLESTEP);
+		if (step || cached_flags & _TIF_SYSCALL_TRACE)
+			tracehook_report_syscall_exit(regs, step);
+	}
+
+#ifdef CONFIG_COMPAT
+	/*
+	 * Compat syscalls set TS_COMPAT.  Make sure we clear it before
+	 * returning to user mode.
+	 */
+	ti->status &= ~TS_COMPAT;
+#endif
+
+	local_irq_disable();
+	prepare_exit_to_usermode(regs);
+}
+
 /*
- * notification of userspace execution resumption
+ * Deprecated notification of userspace execution resumption
  * - triggered by the TIF_WORK_MASK flags
  */
 __visible void

index c5380bea2a36..c3496619740a 100644
@@ -112,8 +112,8 @@ asmlinkage void smp_threshold_interrupt(void);
 asmlinkage void smp_deferred_error_interrupt(void);
 #endif
 
-extern enum ctx_state ist_enter(struct pt_regs *regs);
-extern void ist_exit(struct pt_regs *regs, enum ctx_state prev_state);
+extern void ist_enter(struct pt_regs *regs);
+extern void ist_exit(struct pt_regs *regs);
 extern void ist_begin_non_atomic(struct pt_regs *regs);
 extern void ist_end_non_atomic(void);
 

index 5b974c97e31e..29cba90eb96d 100644
@@ -1026,7 +1026,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 {
 	struct mca_config *cfg = &mca_cfg;
 	struct mce m, *final;
-	enum ctx_state prev_state;
 	int i;
 	int worst = 0;
 	int severity;

@@ -1052,7 +1051,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	int flags = MF_ACTION_REQUIRED;
 	int lmce = 0;
 
-	prev_state = ist_enter(regs);
+	ist_enter(regs);
 
 	this_cpu_inc(mce_exception_count);
 

@@ -1224,7 +1223,7 @@ out:
 	local_irq_disable();
 	ist_end_non_atomic();
 done:
-	ist_exit(regs, prev_state);
+	ist_exit(regs);
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
 

index 737b0ad4e61a..12402e10aeff 100644
@@ -19,10 +19,9 @@ int mce_p5_enabled __read_mostly;
 /* Machine check handler for Pentium class Intel CPUs: */
 static void pentium_machine_check(struct pt_regs *regs, long error_code)
 {
-	enum ctx_state prev_state;
 	u32 loaddr, hi, lotype;
 
-	prev_state = ist_enter(regs);
+	ist_enter(regs);
 
 	rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi);
 	rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi);

@@ -39,7 +38,7 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code)
 
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
 
-	ist_exit(regs, prev_state);
+	ist_exit(regs);
 }
 
 /* Set up machine check reporting for processors with Intel style MCE: */

index 44f138296fbe..01dd8702880b 100644
@@ -15,12 +15,12 @@
 /* Machine check handler for WinChip C6: */
 static void winchip_machine_check(struct pt_regs *regs, long error_code)
 {
-	enum ctx_state prev_state = ist_enter(regs);
+	ist_enter(regs);
 
 	printk(KERN_EMERG "CPU0: Machine Check Exception.\n");
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
 
-	ist_exit(regs, prev_state);
+	ist_exit(regs);
 }
 
 /* Set up machine check reporting on the Winchip C6 series */

264 lines not on this page · raw message

deleted file mode 100644
index 1fe49704b146..000000000000
@@ -1,10 +0,0 @@
-#ifndef _ASM_X86_CONTEXT_TRACKING_H
-#define _ASM_X86_CONTEXT_TRACKING_H
-
-#ifdef CONFIG_CONTEXT_TRACKING
-# define SCHEDULE_USER call schedule_user
-#else
-# define SCHEDULE_USER call schedule
-#endif
-
-#endif

index 88b366487b0e..6233de046c08 100644
@@ -216,8 +216,23 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 	unsigned vector = ~regs->orig_ax;
 	unsigned irq;
 
+	/*
+	 * NB: Unlike exception entries, IRQ entries do not reliably
+	 * handle context tracking in the low-level entry code.  This is
+	 * because syscall entries execute briefly with IRQs on before
+	 * updating context tracking state, so we can take an IRQ from
+	 * kernel mode with CONTEXT_USER.  The low-level entry code only
+	 * updates the context if we came from user mode, so we won't
+	 * switch to CONTEXT_KERNEL.  We'll fix that once the syscall
+	 * code is cleaned up enough that we can cleanly defer enabling
+	 * IRQs.
+	 */
+
 	entering_irq();
 
+	/* entering_irq() tells RCU that we're not quiescent.  Check it. */
+	rcu_lockdep_assert(rcu_is_watching(), "IRQ failed to wake up RCU");
+
 	irq = __this_cpu_read(vector_irq[vector]);
 
 	if (!handle_irq(irq, regs)) {