From: Steven Rostedt <rostedt@goodmis.org>
Subject: x86: Do not disable preemption in int3 on 32bit

Preemption must be disabled before enabling interrupts in do_trap
on x86_64 because the stack in use for int3 and debug is a per CPU
stack set by th IST. But 32bit does not have an IST and the stack
still belongs to the current task and there is no problem in scheduling
out the task.

Keep preemption enabled on X86_32 when enabling interrupts for
do_trap().

The name of the function is changed from preempt_conditional_sti/cli()
to conditional_sti/cli_ist(), to annotate that this function is used
when the stack is on the IST.

Cc: stable-rt@vger.kernel.org
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 arch/x86/kernel/traps.c |   32 +++++++++++++++++++++++---------
 1 file changed, 23 insertions(+), 9 deletions(-)

Index: linux-stable/arch/x86/kernel/traps.c
===================================================================
--- linux-stable.orig/arch/x86/kernel/traps.c
+++ linux-stable/arch/x86/kernel/traps.c
@@ -87,9 +87,21 @@ static inline void conditional_sti(struc
 		local_irq_enable();
 }
 
-static inline void preempt_conditional_sti(struct pt_regs *regs)
+static inline void conditional_sti_ist(struct pt_regs *regs)
 {
+#ifdef CONFIG_X86_64
+	/*
+	 * X86_64 uses a per CPU stack on the IST for certain traps
+	 * like int3. The task can not be preempted when using one
+	 * of these stacks, thus preemption must be disabled, otherwise
+	 * the stack can be corrupted if the task is scheduled out,
+	 * and another task comes in and uses this stack.
+	 *
+	 * On x86_32 the task keeps its own stack and it is OK if the
+	 * task schedules out.
+	 */
 	inc_preempt_count();
+#endif
 	if (regs->flags & X86_EFLAGS_IF)
 		local_irq_enable();
 }
@@ -100,11 +112,13 @@ static inline void conditional_cli(struc
 		local_irq_disable();
 }
 
-static inline void preempt_conditional_cli(struct pt_regs *regs)
+static inline void conditional_cli_ist(struct pt_regs *regs)
 {
 	if (regs->flags & X86_EFLAGS_IF)
 		local_irq_disable();
+#ifdef CONFIG_X86_64
 	dec_preempt_count();
+#endif
 }
 
 static void __kprobes
@@ -225,9 +239,9 @@ dotraplinkage void do_stack_segment(stru
 	if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
 			X86_TRAP_SS, SIGBUS) == NOTIFY_STOP)
 		return;
-	preempt_conditional_sti(regs);
+	conditional_sti_ist(regs);
 	do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
-	preempt_conditional_cli(regs);
+	conditional_cli_ist(regs);
 }
 
 dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
@@ -327,9 +341,9 @@ dotraplinkage void __kprobes notrace do_
 	 * as we may switch to the interrupt stack.
 	 */
 	debug_stack_usage_inc();
-	preempt_conditional_sti(regs);
+	conditional_sti_ist(regs);
 	do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
-	preempt_conditional_cli(regs);
+	conditional_cli_ist(regs);
 	debug_stack_usage_dec();
 }
 
@@ -430,12 +444,12 @@ dotraplinkage void __kprobes do_debug(st
 	debug_stack_usage_inc();
 
 	/* It's safe to allow irq's after DR6 has been saved */
-	preempt_conditional_sti(regs);
+	conditional_sti_ist(regs);
 
 	if (regs->flags & X86_VM_MASK) {
 		handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code,
 					X86_TRAP_DB);
-		preempt_conditional_cli(regs);
+		conditional_cli_ist(regs);
 		debug_stack_usage_dec();
 		return;
 	}
@@ -455,7 +469,7 @@ dotraplinkage void __kprobes do_debug(st
 	si_code = get_si_code(tsk->thread.debugreg6);
 	if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp)
 		send_sigtrap(tsk, regs, error_code, si_code);
-	preempt_conditional_cli(regs);
+	conditional_cli_ist(regs);
 	debug_stack_usage_dec();
 
 	return;