x86/dumpstack: Allow preemption in show_stack_log_lvl() and dump_trace()

show_stack_log_lvl() and dump_trace() are already preemption safe:

- If they're running in irq or exception context, preemption is already
  disabled and the percpu stack pointers can be trusted.

- If they're running with preemption enabled, they must be running on
  the task stack anyway, so it doesn't matter if they're comparing the
  stack pointer against a percpu stack pointer from this CPU or another
  one: either way it won't match.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Byungchul Park <byungchul.park@lge.com>
Cc: Denys Vlasenko <dvlasenk@redhat.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: Nilay Vaish <nilayvaish@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/a0ca0b1044eca97d4f0ec7c1619cf80b3b65560d.1473371307.git.jpoimboe@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 15 insertions, 25 deletions

diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index c533b8b5a373..da5cd62f93ab 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -24,16 +24,16 @@ static void *is_irq_stack(void *p, void *irq)
 }
 
 
-static void *is_hardirq_stack(unsigned long *stack, int cpu)
+static void *is_hardirq_stack(unsigned long *stack)
 {
-	void *irq = per_cpu(hardirq_stack, cpu);
+	void *irq = this_cpu_read(hardirq_stack);
 
 	return is_irq_stack(stack, irq);
 }
 
-static void *is_softirq_stack(unsigned long *stack, int cpu)
+static void *is_softirq_stack(unsigned long *stack)
 {
-	void *irq = per_cpu(softirq_stack, cpu);
+	void *irq = this_cpu_read(softirq_stack);
 
 	return is_irq_stack(stack, irq);
 }
@@ -42,7 +42,6 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp,
 		const struct stacktrace_ops *ops, void *data)
 {
-	const unsigned cpu = get_cpu();
 	int graph = 0;
 	u32 *prev_esp;
 
@@ -53,9 +52,9 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	for (;;) {
 		void *end_stack;
 
-		end_stack = is_hardirq_stack(stack, cpu);
+		end_stack = is_hardirq_stack(stack);
 		if (!end_stack)
-			end_stack = is_softirq_stack(stack, cpu);
+			end_stack = is_softirq_stack(stack);
 
 		bp = ops->walk_stack(task, stack, bp, ops, data,
 				     end_stack, &graph);
@@ -74,7 +73,6 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 			break;
 		touch_nmi_watchdog();
 	}
-	put_cpu();
 }
 EXPORT_SYMBOL(dump_trace);
 
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index b243352c779e..07373bec76f1 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -31,8 +31,8 @@ static char x86_stack_ids[][8] = {
 #endif
 };
 
-static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
-					 unsigned *usedp, char **idp)
+static unsigned long *in_exception_stack(unsigned long stack, unsigned *usedp,
+					 char **idp)
 {
 	unsigned k;
 
@@ -41,7 +41,7 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
 	 * 'stack' is in one of them:
 	 */
 	for (k = 0; k < N_EXCEPTION_STACKS; k++) {
-		unsigned long end = per_cpu(orig_ist, cpu).ist[k];
+		unsigned long end = raw_cpu_ptr(&orig_ist)->ist[k];
 		/*
 		 * Is 'stack' above this exception frame's end?
 		 * If yes then skip to the next frame.
@@ -111,7 +111,7 @@ enum stack_type {
 };
 
 static enum stack_type
-analyze_stack(int cpu, struct task_struct *task, unsigned long *stack,
+analyze_stack(struct task_struct *task, unsigned long *stack,
 	      unsigned long **stack_end, unsigned long *irq_stack,
 	      unsigned *used, char **id)
 {
@@ -121,8 +121,7 @@ analyze_stack(int cpu, struct task_struct *task, unsigned long *stack,
 	if ((unsigned long)task_stack_page(task) == addr)
 		return STACK_IS_NORMAL;
 
-	*stack_end = in_exception_stack(cpu, (unsigned long)stack,
-					used, id);
+	*stack_end = in_exception_stack((unsigned long)stack, used, id);
 	if (*stack_end)
 		return STACK_IS_EXCEPTION;
 
@@ -149,8 +148,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp,
 		const struct stacktrace_ops *ops, void *data)
 {
-	const unsigned cpu = get_cpu();
-	unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu);
+	unsigned long *irq_stack = (unsigned long *)this_cpu_read(irq_stack_ptr);
 	unsigned used = 0;
 	int graph = 0;
 	int done = 0;
@@ -169,8 +167,8 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		enum stack_type stype;
 		char *id;
 
-		stype = analyze_stack(cpu, task, stack, &stack_end,
-				      irq_stack, &used, &id);
+		stype = analyze_stack(task, stack, &stack_end, irq_stack, &used,
+				      &id);
 
 		/* Default finish unless specified to continue */
 		done = 1;
@@ -225,7 +223,6 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	 * This handles the process stack:
 	 */
 	bp = ops->walk_stack(task, stack, bp, ops, data, NULL, &graph);
-	put_cpu();
 }
 EXPORT_SYMBOL(dump_trace);
 
@@ -236,13 +233,9 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	unsigned long *irq_stack_end;
 	unsigned long *irq_stack;
 	unsigned long *stack;
-	int cpu;
 	int i;
 
-	preempt_disable();
-	cpu = smp_processor_id();
-
-	irq_stack_end = (unsigned long *)(per_cpu(irq_stack_ptr, cpu));
+	irq_stack_end = (unsigned long *)this_cpu_read(irq_stack_ptr);
 	irq_stack     = irq_stack_end - (IRQ_STACK_SIZE / sizeof(long));
 
 	sp = sp ? : get_stack_pointer(task, regs);
@@ -274,7 +267,6 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		stack++;
 		touch_nmi_watchdog();
 	}
-	preempt_enable();
 
 	pr_cont("\n");
 	show_trace_log_lvl(task, regs, sp, bp, log_lvl);