[RFC][PATCH v5 1/2] printk: Make printk() completely async

[Sergey Senozhatsky]

From: Jan Kara <jack@xxxxxxx>

Currently, printk() sometimes waits for message to be printed to console
and sometimes it does not (when console_sem is held by some other
process). In case printk() grabs console_sem and starts printing to
console, it prints messages from kernel printk buffer until the buffer
is empty. When serial console is attached, printing is slow and thus
other CPUs in the system have plenty of time to append new messages to
the buffer while one CPU is printing. Thus the CPU can spend unbounded
amount of time doing printing in console_unlock().  This is especially
serious problem if the printk() calling console_unlock() was called with
interrupts disabled.

In practice users have observed a CPU can spend tens of seconds printing
in console_unlock() (usually during boot when hundreds of SCSI devices
are discovered) resulting in RCU stalls (CPU doing printing doesn't
reach quiescent state for a long time), softlockup reports (IPIs for the
printing CPU don't get served and thus other CPUs are spinning waiting
for the printing CPU to process IPIs), and eventually a machine death
(as messages from stalls and lockups append to printk buffer faster than
we are able to print). So these machines are unable to boot with serial
console attached. Another observed issue is that due to slow printk,
hardware discovery is slow and udev times out before kernel manages to
discover all the attached HW. Also during artificial stress testing SATA
disk disappears from the system because its interrupts aren't served for
too long.

This patch makes printk() completely asynchronous (similar to what
printk_deferred() did until now). It appends message to the kernel
printk buffer and wake_up()s a special dedicated kthread to do the
printing to console. This has the advantage that printing always happens
from a schedulable contex and thus we don't lockup any particular CPU or
even interrupts. Also it has the advantage that printk() is fast and
thus kernel booting is not slowed down by slow serial console.
Disadvantage of this method is that in case of crash there is higher
chance that important messages won't appear in console output (we may
need working scheduling to print message to console). We somewhat
mitigate this risk by switching printk to the original method of
immediate printing to console if oops is in progress.  Also for
debugging purposes we provide printk.synchronous kernel parameter which
resorts to the original printk behavior.

printk() is expected to work under different conditions and in different
scenarios, including corner cases of OOM when all of the workers are busy
(e.g. allocating memory), thus printk() uses its own dedicated printing
kthread, rather than relying on workqueue (even with WQ_MEM_RECLAIM bit
set we potentially can receive delays in printing until workqueue
declares a ->mayday, as noted by Tetsuo Handa). Another thing to mention,
is that deferred printk() messages may appear before printing kthread
created, so in the very beginning we have to print deferred messages
the old way -- via IRQs.

Signed-off-by: Jan Kara <jack@xxxxxxx>
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@xxxxxxxxx>
---
 Documentation/kernel-parameters.txt |  10 ++
 kernel/printk/printk.c              | 215 ++++++++++++++++++++++++++----------
 2 files changed, 167 insertions(+), 58 deletions(-)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index ecc74fa..4745e94 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3114,6 +3114,16 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	printk.time=	Show timing data prefixed to each printk message line
 			Format: <bool>  (1/Y/y=enable, 0/N/n=disable)
 
+	printk.synchronous=
+			By default kernel messages are printed to console
+			asynchronously (except during early boot or when oops
+			is happening). That avoids kernel stalling behind slow
+			serial console and thus avoids softlockups, interrupt
+			timeouts, or userspace timing out during heavy printing.
+			However for debugging problems, printing messages to
+			console immediately may be desirable. This option
+			enables such behavior.
+
 	processor.max_cstate=	[HW,ACPI]
 			Limit processor to maximum C-state
 			max_cstate=9 overrides any DMI blacklist limit.
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index bfbf284..cf7906e 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -46,6 +46,7 @@
 #include <linux/utsname.h>
 #include <linux/ctype.h>
 #include <linux/uio.h>
+#include <linux/kthread.h>
 
 #include <asm/uaccess.h>
 #include <asm-generic/sections.h>
@@ -284,6 +285,105 @@ static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN);
 static char *log_buf = __log_buf;
 static u32 log_buf_len = __LOG_BUF_LEN;
 
+/*
+ * When true, printing to console will happen synchronously unless someone else
+ * is already printing messages.
+ *
+ * The default value on UP systems is 'true'.
+ */
+static bool __read_mostly printk_sync = !IS_ENABLED(CONFIG_SMP);
+module_param_named(synchronous, printk_sync, bool, S_IRUGO);
+MODULE_PARM_DESC(synchronous, "make printing to console synchronous");
+
+/* Printing kthread for async vprintk_emit() */
+static struct task_struct *printk_kthread;
+/* When `true' - printing thread has messages to print */
+static bool need_flush_console;
+
+static int printing_func(void *data)
+{
+	while (1) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (!need_flush_console)
+			schedule();
+
+		__set_current_state(TASK_RUNNING);
+		need_flush_console = false;
+
+		console_lock();
+		console_unlock();
+	}
+
+	return 0;
+}
+
+static int __init init_printk_kthread(void)
+{
+	struct task_struct *thread;
+
+	if (printk_sync)
+		return 0;
+
+	thread = kthread_run(printing_func, NULL, "printk");
+	if (IS_ERR(thread)) {
+		pr_err("printk: unable to create printing thread\n");
+		printk_sync = true;
+	} else {
+		printk_kthread = thread;
+	}
+	return 0;
+}
+late_initcall(init_printk_kthread);
+
+/*
+ * Delayed printk version, for scheduler-internal messages:
+ */
+#define PRINTK_PENDING_WAKEUP	(1<<0)
+#define PRINTK_PENDING_OUTPUT	(1<<1)
+
+static DEFINE_PER_CPU(int, printk_pending);
+
+static void wake_up_klogd_work_func(struct irq_work *irq_work)
+{
+	int pending = __this_cpu_xchg(printk_pending, 0);
+
+	if (pending & PRINTK_PENDING_OUTPUT) {
+		/* If trylock fails, someone else is doing the printing */
+		if (console_trylock())
+			console_unlock();
+	}
+
+	if (pending & PRINTK_PENDING_WAKEUP)
+		wake_up_interruptible(&log_wait);
+}
+
+static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
+	.func = wake_up_klogd_work_func,
+	.flags = IRQ_WORK_LAZY,
+};
+
+void wake_up_klogd(void)
+{
+	preempt_disable();
+	if (waitqueue_active(&log_wait)) {
+		this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
+		irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
+	}
+	preempt_enable();
+}
+
+int printk_deferred(const char *fmt, ...)
+{
+	va_list args;
+	int r;
+
+	va_start(args, fmt);
+	r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, 0, fmt, args);
+	va_end(args);
+
+	return r;
+}
+
 /* Return log buffer address */
 char *log_buf_addr_get(void)
 {
@@ -1608,6 +1708,8 @@ asmlinkage int vprintk_emit(int facility, int level,
 			    const char *dict, size_t dictlen,
 			    const char *fmt, va_list args)
 {
+	/* cpu currently holding logbuf_lock in this function */
+	static unsigned int logbuf_cpu = UINT_MAX;
 	static bool recursion_bug;
 	static char textbuf[LOG_LINE_MAX];
 	char *text = textbuf;
@@ -1617,12 +1719,21 @@ asmlinkage int vprintk_emit(int facility, int level,
 	int this_cpu;
 	int printed_len = 0;
 	bool in_sched = false;
-	/* cpu currently holding logbuf_lock in this function */
-	static unsigned int logbuf_cpu = UINT_MAX;
+	bool in_panic = console_loglevel == CONSOLE_LOGLEVEL_MOTORMOUTH;
+	bool sync_print = printk_sync;
+
+	/* disable async printk */
+	if (in_panic)
+		printk_sync = true;
 
 	if (level == LOGLEVEL_SCHED) {
 		level = LOGLEVEL_DEFAULT;
+		/*
+		 * Deferred sched messages must not be printed
+		 * synchronously regardless the @printk_sync or @in_panic.
+		 */
 		in_sched = true;
+		sync_print = false;
 	}
 
 	boot_delay_msec(level);
@@ -1655,10 +1766,23 @@ asmlinkage int vprintk_emit(int facility, int level,
 	raw_spin_lock(&logbuf_lock);
 	logbuf_cpu = this_cpu;
 
+	/*
+	 * Set printing_func() sleep condition early, under the @logbuf_lock.
+	 * So printing kthread (if RUNNING) will go to console_lock() and spin
+	 * on @logbuf_lock.
+	 */
+	if (!printk_sync)
+		need_flush_console = true;
+
 	if (unlikely(recursion_bug)) {
 		static const char recursion_msg[] =
 			"BUG: recent printk recursion!";
 
+		/* disable async printk */
+		printk_sync = true;
+		if (!in_sched)
+			sync_print = true;
+
 		recursion_bug = false;
 		/* emit KERN_CRIT message */
 		printed_len += log_store(0, 2, LOG_PREFIX|LOG_NEWLINE, 0,
@@ -1748,13 +1872,42 @@ asmlinkage int vprintk_emit(int facility, int level,
 						 dict, dictlen, text, text_len);
 	}
 
+	/*
+	 * By default we print message to console asynchronously so that kernel
+	 * doesn't get stalled due to slow serial console. That can lead to
+	 * softlockups, lost interrupts, or userspace timing out under heavy
+	 * printing load.
+	 *
+	 * However we resort to synchronous printing of messages during early
+	 * boot, when synchronous printing was explicitly requested by
+	 * kernel parameter, or when console_verbose() was called to print
+	 * everything during panic / oops.
+	 */
+	if (!sync_print) {
+		if (in_sched) {
+			/*
+			 * @in_sched messages may come too early, when we don't
+			 * yet have @printk_kthread. We can't print deferred
+			 * messages directly, because this may deadlock, route
+			 * them via IRQ context.
+			 */
+			__this_cpu_or(printk_pending,
+					PRINTK_PENDING_OUTPUT);
+			irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
+		} else if (printk_kthread && !in_panic) {
+			/* Offload printing to a schedulable context. */
+			wake_up_process(printk_kthread);
+		} else {
+			sync_print = true;
+		}
+	}
+
 	logbuf_cpu = UINT_MAX;
 	raw_spin_unlock(&logbuf_lock);
 	lockdep_on();
 	local_irq_restore(flags);
 
-	/* If called from the scheduler, we can not call up(). */
-	if (!in_sched) {
+	if (sync_print) {
 		lockdep_off();
 		/*
 		 * Try to acquire and then immediately release the console
@@ -2723,60 +2876,6 @@ late_initcall(printk_late_init);
 
 #if defined CONFIG_PRINTK
 /*
- * Delayed printk version, for scheduler-internal messages:
- */
-#define PRINTK_PENDING_WAKEUP	0x01
-#define PRINTK_PENDING_OUTPUT	0x02
-
-static DEFINE_PER_CPU(int, printk_pending);
-
-static void wake_up_klogd_work_func(struct irq_work *irq_work)
-{
-	int pending = __this_cpu_xchg(printk_pending, 0);
-
-	if (pending & PRINTK_PENDING_OUTPUT) {
-		/* If trylock fails, someone else is doing the printing */
-		if (console_trylock())
-			console_unlock();
-	}
-
-	if (pending & PRINTK_PENDING_WAKEUP)
-		wake_up_interruptible(&log_wait);
-}
-
-static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
-	.func = wake_up_klogd_work_func,
-	.flags = IRQ_WORK_LAZY,
-};
-
-void wake_up_klogd(void)
-{
-	preempt_disable();
-	if (waitqueue_active(&log_wait)) {
-		this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
-		irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
-	}
-	preempt_enable();
-}
-
-int printk_deferred(const char *fmt, ...)
-{
-	va_list args;
-	int r;
-
-	preempt_disable();
-	va_start(args, fmt);
-	r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, 0, fmt, args);
-	va_end(args);
-
-	__this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
-	irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
-	preempt_enable();
-
-	return r;
-}
-
-/*
  * printk rate limiting, lifted from the networking subsystem.
  *
  * This enforces a rate limit: not more than 10 kernel messages
-- 
2.8.0.rc0