[PATCH v2 16/17] x86/nmi: Perform a safe NMI stack trace on all CPUs

[Wang Long <long.wanglong@huawei.com>]

From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>

commit a9edc88093287183ac934be44f295f183b2c62dd upstream.

When trigger_all_cpu_backtrace() is called on x86, it will trigger an
NMI on each CPU and call show_regs(). But this can lead to a hard lock
up if the NMI comes in on another printk().

In order to avoid this, when the NMI triggers, it switches the printk
routine for that CPU to call a NMI safe printk function that records the
printk in a per_cpu seq_buf descriptor. After all NMIs have finished
recording its data, the seq_bufs are printed in a safe context.

Link: http://lkml.kernel.org/p/20140619213952.360076309@goodmis.org
Link: http://lkml.kernel.org/r/20141115050605.055232587@goodmis.org

Tested-by: Jiri Kosina <jkosina@suse.cz>
Acked-by: Jiri Kosina <jkosina@suse.cz>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Petr Mladek <pmladek@suse.cz>
[wanglong: backport to 3.10 stable
- adjust context
]
Signed-off-by: Wang Long <long.wanglong@huawei.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/x86/kernel/apic/hw_nmi.c | 86 +++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 83 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index a698d71..eebe5ec 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -18,6 +18,7 @@
 #include <linux/nmi.h>
 #include <linux/module.h>
 #include <linux/delay.h>
+#include <linux/seq_buf.h>
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 u64 hw_nmi_get_sample_period(int watchdog_thresh)
@@ -29,12 +30,33 @@ u64 hw_nmi_get_sample_period(int watchdog_thresh)
 #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_var_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);
+}
+
 void arch_trigger_all_cpu_backtrace(void)
 {
+	struct nmi_seq_buf *s;
+	int len;
+	int cpu;
 	int i;
 
 	if (test_and_set_bit(0, &backtrace_flag))
@@ -45,6 +67,15 @@ void arch_trigger_all_cpu_backtrace(void)
 		return;
 
 	cpumask_copy(to_cpumask(backtrace_mask), cpu_online_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);
+	}
 
 	printk(KERN_INFO "sending NMI to all CPUs:\n");
 	apic->send_IPI_all(NMI_VECTOR);
@@ -56,10 +87,57 @@ void arch_trigger_all_cpu_backtrace(void)
 		mdelay(1);
 	}
 
+	/*
+	 * Now that all the NMIs have triggered, we can dump out their
+	 * back traces safely to the console.
+	 */
+	for_each_cpu(cpu, printtrace_mask) {
+		int last_i = 0;
+
+		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_clear_bit();
 }
 
+/*
+ * 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;
+}
+
 static int __kprobes
 arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs)
 {
@@ -68,12 +146,14 @@ arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs)
 	cpu = smp_processor_id();
 
 	if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
-		static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED;
+		printk_func_t printk_func_save = this_cpu_read(printk_func);
 
-		arch_spin_lock(&lock);
+		/* Replace printk to write into the NMI seq */
+		this_cpu_write(printk_func, nmi_vprintk);
 		printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
 		show_regs(regs);
-		arch_spin_unlock(&lock);
+		this_cpu_write(printk_func, printk_func_save);
+
 		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
 		return NMI_HANDLED;
 	}
-- 
1.8.3.4