x86/entry: Remove exception_enter() from most trap handlers

On 64-bit kernels, we don't need it any more: we handle context
tracking directly on entry from user mode and exit to user mode.

On 32-bit kernels, we don't support context tracking at all, so
these callbacks had no effect.

Note: this doesn't change do_page_fault().  Before we do that,
we need to make sure that there is no code that can page fault
from kernel mode with CONTEXT_USER.  The 32-bit fast system call
stack argument code is the only offender I'm aware of right now.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Denys Vlasenko <vda.linux@googlemail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/ae22f4dfebd799c916574089964592be218151f9.1435952415.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/traps.h

@@ -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);
 

arch/x86/kernel/cpu/mcheck/mce.c

@@ -1029,7 +1029,6 @@ 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;
@@ -1055,7 +1054,7 @@ 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);
 
@@ -1227,7 +1226,7 @@ out:
 	local_irq_disable();
 	ist_end_non_atomic();
 done:
-	ist_exit(regs, prev_state);
+	ist_exit(regs);
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
 

arch/x86/kernel/cpu/mcheck/p5.c

@@ -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: */

arch/x86/kernel/cpu/mcheck/winchip.c

@@ -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 */

arch/x86/kernel/traps.c

@@ -108,13 +108,10 @@ static inline void preempt_conditional_cli(struct pt_regs *regs)
 	preempt_count_dec();
 }
 
-enum ctx_state ist_enter(struct pt_regs *regs)
+void ist_enter(struct pt_regs *regs)
 {
-	enum ctx_state prev_state;
-
 	if (user_mode(regs)) {
-		/* Other than that, we're just an exception. */
-		prev_state = exception_enter();
+		CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
 	} else {
 		/*
 		 * We might have interrupted pretty much anything.  In
@@ -123,32 +120,25 @@ enum ctx_state ist_enter(struct pt_regs *regs)
 		 * but we need to notify RCU.
 		 */
 		rcu_nmi_enter();
-		prev_state = CONTEXT_KERNEL;  /* the value is irrelevant. */
 	}
 
 	/*
-	 * We are atomic because we're on the IST stack (or we're on x86_32,
-	 * in which case we still shouldn't schedule).
-	 *
-	 * This must be after exception_enter(), because exception_enter()
-	 * won't do anything if in_interrupt() returns true.
+	 * We are atomic because we're on the IST stack; or we're on
+	 * x86_32, in which case we still shouldn't schedule; or we're
+	 * on x86_64 and entered from user mode, in which case we're
+	 * still atomic unless ist_begin_non_atomic is called.
 	 */
 	preempt_count_add(HARDIRQ_OFFSET);
 
 	/* This code is a bit fragile.  Test it. */
 	rcu_lockdep_assert(rcu_is_watching(), "ist_enter didn't work");
-
-	return prev_state;
 }
 
-void ist_exit(struct pt_regs *regs, enum ctx_state prev_state)
+void ist_exit(struct pt_regs *regs)
 {
-	/* Must be before exception_exit. */
 	preempt_count_sub(HARDIRQ_OFFSET);
 
-	if (user_mode(regs))
-		return exception_exit(prev_state);
-	else
+	if (!user_mode(regs))
 		rcu_nmi_exit();
 }
 
@@ -162,7 +152,7 @@ void ist_exit(struct pt_regs *regs, enum ctx_state prev_state)
  * a double fault, it can be safe to schedule.  ist_begin_non_atomic()
  * begins a non-atomic section within an ist_enter()/ist_exit() region.
  * Callers are responsible for enabling interrupts themselves inside
- * the non-atomic section, and callers must call is_end_non_atomic()
+ * the non-atomic section, and callers must call ist_end_non_atomic()
  * before ist_exit().
  */
 void ist_begin_non_atomic(struct pt_regs *regs)
@@ -289,7 +279,6 @@ NOKPROBE_SYMBOL(do_trap);
 static void do_error_trap(struct pt_regs *regs, long error_code, char *str,
 			  unsigned long trapnr, int signr)
 {
-	enum ctx_state prev_state = exception_enter();
 	siginfo_t info;
 
 	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
@@ -300,8 +289,6 @@ static void do_error_trap(struct pt_regs *regs, long error_code, char *str,
 		do_trap(trapnr, signr, str, regs, error_code,
 			fill_trap_info(regs, signr, trapnr, &info));
 	}
-
-	exception_exit(prev_state);
 }
 
 #define DO_ERROR(trapnr, signr, str, name)				\
@@ -353,7 +340,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 	}
 #endif
 
-	ist_enter(regs);  /* Discard prev_state because we won't return. */
+	ist_enter(regs);
 	notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
 
 	tsk->thread.error_code = error_code;
@@ -373,15 +360,13 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 
 dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 {
-	enum ctx_state prev_state;
 	const struct bndcsr *bndcsr;
 	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;
+		return;
 	conditional_sti(regs);
 
 	if (!user_mode(regs))
@@ -438,9 +423,8 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 		die("bounds", regs, error_code);
 	}
 
-exit:
-	exception_exit(prev_state);
 	return;
+
 exit_trap:
 	/*
 	 * This path out is for all the cases where we could not
@@ -450,36 +434,33 @@ exit_trap:
 	 * time..
 	 */
 	do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, NULL);
-	exception_exit(prev_state);
 }
 
 dotraplinkage void
 do_general_protection(struct pt_regs *regs, long error_code)
 {
 	struct task_struct *tsk;
-	enum ctx_state prev_state;
 
-	prev_state = exception_enter();
 	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
 	conditional_sti(regs);
 
 	if (v8086_mode(regs)) {
 		local_irq_enable();
 		handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
-		goto exit;
+		return;
 	}
 
 	tsk = current;
 	if (!user_mode(regs)) {
 		if (fixup_exception(regs))
-			goto exit;
+			return;
 
 		tsk->thread.error_code = error_code;
 		tsk->thread.trap_nr = X86_TRAP_GP;
 		if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
 			       X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP)
 			die("general protection fault", regs, error_code);
-		goto exit;
+		return;
 	}
 
 	tsk->thread.error_code = error_code;
@@ -495,16 +476,12 @@ do_general_protection(struct pt_regs *regs, long error_code)
 	}
 
 	force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
-exit:
-	exception_exit(prev_state);
 }
 NOKPROBE_SYMBOL(do_general_protection);
 
 /* May run on IST stack. */
 dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 {
-	enum ctx_state prev_state;
-
 #ifdef CONFIG_DYNAMIC_FTRACE
 	/*
 	 * ftrace must be first, everything else may cause a recursive crash.
@@ -517,7 +494,7 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 	if (poke_int3_handler(regs))
 		return;
 
-	prev_state = ist_enter(regs);
+	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,
@@ -544,7 +521,7 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 	preempt_conditional_cli(regs);
 	debug_stack_usage_dec();
 exit:
-	ist_exit(regs, prev_state);
+	ist_exit(regs);
 }
 NOKPROBE_SYMBOL(do_int3);
 
@@ -620,12 +597,11 @@ NOKPROBE_SYMBOL(fixup_bad_iret);
 dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 {
 	struct task_struct *tsk = current;
-	enum ctx_state prev_state;
 	int user_icebp = 0;
 	unsigned long dr6;
 	int si_code;
 
-	prev_state = ist_enter(regs);
+	ist_enter(regs);
 
 	get_debugreg(dr6, 6);
 
@@ -700,7 +676,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	debug_stack_usage_dec();
 
 exit:
-	ist_exit(regs, prev_state);
+	ist_exit(regs);
 }
 NOKPROBE_SYMBOL(do_debug);
 
@@ -752,23 +728,15 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 
 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);
 }
 
 dotraplinkage void
 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);
 }
 
 dotraplinkage void
@@ -780,9 +748,6 @@ do_spurious_interrupt_bug(struct pt_regs *regs, long error_code)
 dotraplinkage void
 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());
 
@@ -794,7 +759,6 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 
 		info.regs = regs;
 		math_emulate(&info);
-		exception_exit(prev_state);
 		return;
 	}
 #endif
@@ -802,7 +766,6 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 #ifdef CONFIG_X86_32
 	conditional_sti(regs);
 #endif
-	exception_exit(prev_state);
 }
 NOKPROBE_SYMBOL(do_device_not_available);
 
@@ -810,9 +773,7 @@ NOKPROBE_SYMBOL(do_device_not_available);
 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 {
 	siginfo_t info;
-	enum ctx_state prev_state;
 
-	prev_state = exception_enter();
 	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
 	local_irq_enable();
 
@@ -825,7 +786,6 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 		do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
 			&info);
 	}
-	exception_exit(prev_state);
 }
 #endif