[PATCH v4 4/5] printk/nmi: increase the size of NMI buffer and make it configurable

[Petr Mladek]

Testing has shown that the backtrace sometimes does not fit into the 4kB
temporary buffer that is used in NMI context.  The warnings are gone when
I double the temporary buffer size.

This patch doubles the buffer size and makes it configurable.

Note that this problem existed even in the x86-specific implementation
that was added by the commit a9edc8809328 ("x86/nmi: Perform a safe NMI
stack trace on all CPUs").  Nobody noticed it because it did not print any
warnings.

Signed-off-by: Petr Mladek <pmladek@xxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Russell King <rmk+kernel@xxxxxxxxxxxxxxxx>
Cc: Daniel Thompson <daniel.thompson@xxxxxxxxxx>
Cc: Jiri Kosina <jkosina@xxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ralf Baechle <ralf@xxxxxxxxxxxxxx>
Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Martin Schwidefsky <schwidefsky@xxxxxxxxxx>
Cc: David Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
 init/Kconfig        | 22 ++++++++++++++++++++++
 kernel/printk/nmi.c |  3 ++-
 2 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/init/Kconfig b/init/Kconfig
index fd10deeefc22..1c9be9396a4a 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -861,6 +861,28 @@ config LOG_CPU_MAX_BUF_SHIFT
 		     13 =>   8 KB for each CPU
 		     12 =>   4 KB for each CPU
 
+config NMI_LOG_BUF_SHIFT
+	int "Temporary per-CPU NMI log buffer size (12 => 4KB, 13 => 8KB)"
+	range 10 21
+	default 13
+	depends on PRINTK_NMI
+	help
+	  Select the size of a per-CPU buffer where NMI messages are temporary
+	  stored. They are copied to the main log buffer in a safe context
+	  to avoid a deadlock. The value defines the size as a power of 2.
+
+	  NMI messages are rare and limited. The largest one is when
+	  a backtrace is printed. It usually fits into 4KB. Select
+	  8KB if you want to be on the safe side.
+
+	  Examples:
+		     17 => 128 KB for each CPU
+		     16 =>  64 KB for each CPU
+		     15 =>  32 KB for each CPU
+		     14 =>  16 KB for each CPU
+		     13 =>   8 KB for each CPU
+		     12 =>   4 KB for each CPU
+
 #
 # Architectures with an unreliable sched_clock() should select this:
 #
diff --git a/kernel/printk/nmi.c b/kernel/printk/nmi.c
index 572f94922230..bf08557d7e3d 100644
--- a/kernel/printk/nmi.c
+++ b/kernel/printk/nmi.c
@@ -41,7 +41,8 @@ DEFINE_PER_CPU(printk_func_t, printk_func) = vprintk_default;
 static int printk_nmi_irq_ready;
 atomic_t nmi_message_lost;
 
-#define NMI_LOG_BUF_LEN (4096 - sizeof(atomic_t) - sizeof(struct irq_work))
+#define NMI_LOG_BUF_LEN ((1 << CONFIG_NMI_LOG_BUF_SHIFT) -		\
+			 sizeof(atomic_t) - sizeof(struct irq_work))
 
 struct nmi_seq_buf {
 	atomic_t		len;	/* length of written data */
-- 
1.8.5.6