printk/nmi: generic solution for safe printk in NMI

printk() takes some locks and could not be used a safe way in NMI
context.

The chance of a deadlock is real especially when printing stacks from
all CPUs.  This particular problem has been addressed on x86 by the
commit a9edc8809328 ("x86/nmi: Perform a safe NMI stack trace on all
CPUs").

The patchset brings two big advantages.  First, it makes the NMI
backtraces safe on all architectures for free.  Second, it makes all NMI
messages almost safe on all architectures (the temporary buffer is
limited.  We still should keep the number of messages in NMI context at
minimum).

Note that there already are several messages printed in NMI context:
WARN_ON(in_nmi()), BUG_ON(in_nmi()), anything being printed out from MCE
handlers.  These are not easy to avoid.

This patch reuses most of the code and makes it generic.  It is useful
for all messages and architectures that support NMI.

The alternative printk_func is set when entering and is reseted when
leaving NMI context.  It queues IRQ work to copy the messages into the
main ring buffer in a safe context.

__printk_nmi_flush() copies all available messages and reset the buffer.
Then we could use a simple cmpxchg operations to get synchronized with
writers.  There is also used a spinlock to get synchronized with other
flushers.

We do not longer use seq_buf because it depends on external lock.  It
would be hard to make all supported operations safe for a lockless use.
It would be confusing and error prone to make only some operations safe.

The code is put into separate printk/nmi.c as suggested by Steven
Rostedt.  It needs a per-CPU buffer and is compiled only on
architectures that call nmi_enter().  This is achieved by the new
HAVE_NMI Kconfig flag.

The are MN10300 and Xtensa architectures.  We need to clean up NMI
handling there first.  Let's do it separately.

The patch is heavily based on the draft from Peter Zijlstra, see

  https://lkml.org/lkml/2015/6/10/327

[arnd@arndb.de: printk-nmi: use %zu format string for size_t]
[akpm@linux-foundation.org: min_t->min - all types are size_t here]
Signed-off-by: Petr Mladek <pmladek@suse.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Jan Kara <jack@suse.cz>
Acked-by: Russell King <rmk+kernel@arm.linux.org.uk>	[arm part]
Cc: Daniel Thompson <daniel.thompson@linaro.org>
Cc: Jiri Kosina <jkosina@suse.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: David Miller <davem@davemloft.net>
Cc: Daniel Thompson <daniel.thompson@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 5 insertions, 84 deletions

diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c
index 6019c53c669e..26caf51cc238 100644
--- a/lib/nmi_backtrace.c
+++ b/lib/nmi_backtrace.c
@@ -16,33 +16,14 @@
 #include <linux/delay.h>
 #include <linux/kprobes.h>
 #include <linux/nmi.h>
-#include <linux/seq_buf.h>
 
 #ifdef arch_trigger_all_cpu_backtrace
 /* For reliability, we're prepared to waste bits here. */
 static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
-static cpumask_t printtrace_mask;
-
-#define NMI_BUF_SIZE		4096
-
-struct nmi_seq_buf {
-	unsigned char		buffer[NMI_BUF_SIZE];
-	struct seq_buf		seq;
-};
-
-/* Safe printing in NMI context */
-static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq);
 
 /* "in progress" flag of arch_trigger_all_cpu_backtrace */
 static unsigned long backtrace_flag;
 
-static void print_seq_line(struct nmi_seq_buf *s, int start, int end)
-{
-	const char *buf = s->buffer + start;
-
-	printk("%.*s", (end - start) + 1, buf);
-}
-
 /*
  * When raise() is called it will be is passed a pointer to the
  * backtrace_mask. Architectures that call nmi_cpu_backtrace()
@@ -52,8 +33,7 @@ static void print_seq_line(struct nmi_seq_buf *s, int start, int end)
 void nmi_trigger_all_cpu_backtrace(bool include_self,
 				   void (*raise)(cpumask_t *mask))
 {
-	struct nmi_seq_buf *s;
-	int i, cpu, this_cpu = get_cpu();
+	int i, this_cpu = get_cpu();
 
 	if (test_and_set_bit(0, &backtrace_flag)) {
 		/*
@@ -68,17 +48,6 @@ void nmi_trigger_all_cpu_backtrace(bool include_self,
 	if (!include_self)
 		cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask));
 
-	cpumask_copy(&printtrace_mask, to_cpumask(backtrace_mask));
-
-	/*
-	 * Set up per_cpu seq_buf buffers that the NMIs running on the other
-	 * CPUs will write to.
-	 */
-	for_each_cpu(cpu, to_cpumask(backtrace_mask)) {
-		s = &per_cpu(nmi_print_seq, cpu);
-		seq_buf_init(&s->seq, s->buffer, NMI_BUF_SIZE);
-	}
-
 	if (!cpumask_empty(to_cpumask(backtrace_mask))) {
 		pr_info("Sending NMI to %s CPUs:\n",
 			(include_self ? "all" : "other"));
@@ -94,73 +63,25 @@ void nmi_trigger_all_cpu_backtrace(bool include_self,
 	}
 
 	/*
-	 * Now that all the NMIs have triggered, we can dump out their
-	 * back traces safely to the console.
+	 * Force flush any remote buffers that might be stuck in IRQ context
+	 * and therefore could not run their irq_work.
 	 */
-	for_each_cpu(cpu, &printtrace_mask) {
-		int len, last_i = 0;
+	printk_nmi_flush();
 
-		s = &per_cpu(nmi_print_seq, cpu);
-		len = seq_buf_used(&s->seq);
-		if (!len)
-			continue;
-
-		/* Print line by line. */
-		for (i = 0; i < len; i++) {
-			if (s->buffer[i] == '\n') {
-				print_seq_line(s, last_i, i);
-				last_i = i + 1;
-			}
-		}
-		/* Check if there was a partial line. */
-		if (last_i < len) {
-			print_seq_line(s, last_i, len - 1);
-			pr_cont("\n");
-		}
-	}
-
-	clear_bit(0, &backtrace_flag);
-	smp_mb__after_atomic();
+	clear_bit_unlock(0, &backtrace_flag);
 	put_cpu();
 }
 
-/*
- * It is not safe to call printk() directly from NMI handlers.
- * It may be fine if the NMI detected a lock up and we have no choice
- * but to do so, but doing a NMI on all other CPUs to get a back trace
- * can be done with a sysrq-l. We don't want that to lock up, which
- * can happen if the NMI interrupts a printk in progress.
- *
- * Instead, we redirect the vprintk() to this nmi_vprintk() that writes
- * the content into a per cpu seq_buf buffer. Then when the NMIs are
- * all done, we can safely dump the contents of the seq_buf to a printk()
- * from a non NMI context.
- */
-static int nmi_vprintk(const char *fmt, va_list args)
-{
-	struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq);
-	unsigned int len = seq_buf_used(&s->seq);
-
-	seq_buf_vprintf(&s->seq, fmt, args);
-	return seq_buf_used(&s->seq) - len;
-}
-
 bool nmi_cpu_backtrace(struct pt_regs *regs)
 {
 	int cpu = smp_processor_id();
 
 	if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
-		printk_func_t printk_func_save = this_cpu_read(printk_func);
-
-		/* Replace printk to write into the NMI seq */
-		this_cpu_write(printk_func, nmi_vprintk);
 		pr_warn("NMI backtrace for cpu %d\n", cpu);
 		if (regs)
 			show_regs(regs);
 		else
 			dump_stack();
-		this_cpu_write(printk_func, printk_func_save);
-
 		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
 		return true;
 	}