Skip to contentSkip to conversation

Convert timekeeping core to use printk_deferred

RFC PATCH New John Stultz 1 participant 4 messages Apr 23, 2014

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

cover Convert timekeeping core to use printk_deferred

Jiri pointed out a potential deadlock when calling printk while holding the timekeeping seqlock.

Annoyingly, the seqlock lockdep enablement doesn't catch this, as printk disables lockdep.

When looking for possible solutions, one idea was to use a local buffer and defer the printk to later. Ends up there is already similar functionality in printk_sched() to avoid similar style deadlocks w/ the scheduler.

Thus this patchset renames printk_sched to printk_deferred and then moves the affected timekeeping printks to make use of it.

There were some points in the discussion between Jan and Peter that made it seem that there may still be problems lurking in the console layer, and I'm not sure I fully understand their point, so this solution may be incomplete.

Additionally, the same issue likely affects any WARN_ONs as well, but I wanted to get some thoughts on this approach before trying to remove or convert affected WARN_ONS.

Your thoughts and feedback are greatly appreciated!

thanks
-john

Cc Jan Kara <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Jiri Bohac <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Andrew Morton <[email protected]>

John Stultz (3):
printk: Rename printk_sched to printk_deferred
printk: Add printk_once_deferred
timekeeping: Use printk_deferred when holding timekeeping seqlock

 include/linux/printk.h    | 17 ++++++++++++++---
 kernel/printk/printk.c    |  8 ++++----
 kernel/sched/core.c       |  2 +-
 kernel/sched/deadline.c   |  7 +------
 kernel/sched/rt.c         |  8 +-------
 kernel/time/ntp.c         | 15 +++++++++------
 kernel/time/timekeeping.c |  7 ++++---
 7 files changed, 34 insertions(+), 30 deletions(-)
Signature · 1 line
1.8.3.2
#1 lore raw

RFC PATCH 1/3 printk: Rename printk_sched to printk_deferred

After learning we'll need some sort of deferred printk functionality in the timekeeping core, Peter suggested we rename the printk_sched function so it can be reused by needed subsystems.

This only changes the function name and name of the associated buffer. No logic changes.

Cc Jan Kara <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Jiri Bohac <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Andrew Morton <[email protected]>
---
 include/linux/printk.h  | 6 +++---
 kernel/printk/printk.c  | 8 ++++----
 kernel/sched/core.c     | 2 +-
 kernel/sched/deadline.c | 2 +-
 kernel/sched/rt.c       | 2 +-
 5 files changed, 10 insertions(+), 10 deletions(-)
include/linux/printk.h +3 -3
index 8752f75..7847301 100644
@@ -128,9 +128,9 @@ asmlinkage __printf(1, 2) __cold
 int printk(const char *fmt, ...);
 
 /*
- * Special printk facility for scheduler use only, _DO_NOT_USE_ !
+ * Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ !
  */
-__printf(1, 2) __cold int printk_sched(const char *fmt, ...);
+__printf(1, 2) __cold int printk_deferred(const char *fmt, ...);
 
 /*
  * Please don't use printk_ratelimit(), because it shares ratelimiting state
@@ -165,7 +165,7 @@ int printk(const char *s, ...)
 	return 0;
 }
 static inline __printf(1, 2) __cold
-int printk_sched(const char *s, ...)
+int printk_deferred(const char *s, ...)
 {
 	return 0;
 }
kernel/printk/printk.c +4 -4
index a45b509..a9763e4 100644
@@ -2443,14 +2443,14 @@ late_initcall(printk_late_init);
 #define PRINTK_PENDING_SCHED	0x02
 
 static DEFINE_PER_CPU(int, printk_pending);
-static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf);
+static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_deferred_buf);
 
 static void wake_up_klogd_work_func(struct irq_work *irq_work)
 {
 	int pending = __this_cpu_xchg(printk_pending, 0);
 
 	if (pending & PRINTK_PENDING_SCHED) {
-		char *buf = __get_cpu_var(printk_sched_buf);
+		char *buf = __get_cpu_var(printk_deferred_buf);
 		pr_warn("[sched_delayed] %s", buf);
 	}
 
@@ -2473,7 +2473,7 @@ void wake_up_klogd(void)
 	preempt_enable();
 }
 
-int printk_sched(const char *fmt, ...)
+int printk_deferred(const char *fmt, ...)
 {
 	unsigned long flags;
 	va_list args;
@@ -2481,7 +2481,7 @@ int printk_sched(const char *fmt, ...)
 	int r;
 
 	local_irq_save(flags);
-	buf = __get_cpu_var(printk_sched_buf);
+	buf = __get_cpu_var(printk_deferred_buf);
 
 	va_start(args, fmt);
 	r = vsnprintf(buf, PRINTK_BUF_SIZE, fmt, args);
kernel/sched/core.c +1 -1
index 268a45e..423704c 100644
@@ -1320,7 +1320,7 @@ out:
 		 * leave kernel.
 		 */
 		if (p->mm && printk_ratelimit()) {
-			printk_sched("process %d (%s) no longer affine to cpu%d\n",
+			printk_deferred("process %d (%s) no longer affine to cpu%d\n",
 					task_pid_nr(p), p->comm, cpu);
 		}
 	}
kernel/sched/deadline.c +1 -1
index b080957..657ed68 100644
@@ -352,7 +352,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
 
 		if (!lag_once) {
 			lag_once = true;
-			printk_sched("sched: DL replenish lagged to much\n");
+			printk_deferred("sched: DL replenish lagged to much\n");
 		}
 		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
 		dl_se->runtime = pi_se->dl_runtime;
kernel/sched/rt.c +1 -1
index bd2267a..c19b3cc 100644
@@ -857,7 +857,7 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 
 			if (!once) {
 				once = true;
-				printk_sched("sched: RT throttling activated\n");
+				printk_deferred("sched: RT throttling activated\n");
 			}
 		} else {
 			/*
Signature · 1 line
1.8.3.2
#2 lore raw

RFC PATCH 2/3 printk: Add printk_once_deferred

In reply to John Stultz

Two of the three prink_deferred uses are really printk_once style uses, so add a printk_once_deferred macro to simplify those call sites.

Cc Jan Kara <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Jiri Bohac <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Andrew Morton <[email protected]>
---
 include/linux/printk.h  | 11 +++++++++++
 kernel/sched/deadline.c |  7 +------
 kernel/sched/rt.c       |  8 +-------
 3 files changed, 13 insertions(+), 13 deletions(-)
include/linux/printk.h +11 -0
index 7847301..bd21234 100644
@@ -266,9 +266,20 @@ extern asmlinkage void dump_stack(void) __cold;
 		printk(fmt, ##__VA_ARGS__);			\
 	}							\
 })
+#define printk_once_deferred(fmt, ...)				\
+({								\
+	static bool __print_once __read_mostly;			\
+								\
+	if (!__print_once) {					\
+		__print_once = true;				\
+		printk_deferred(fmt, ##__VA_ARGS__);		\
+	}							\
+})
 #else
 #define printk_once(fmt, ...)					\
 	no_printk(fmt, ##__VA_ARGS__)
+#define printk_once_deferred(fmt, ...)				\
+	no_printk(fmt, ##__VA_ARGS__)
 #endif
 
 #define pr_emerg_once(fmt, ...)					\
kernel/sched/deadline.c +1 -6
index 657ed68..3ec96bd 100644
@@ -348,12 +348,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
 	 * entity.
 	 */
 	if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
-		static bool lag_once = false;
-
-		if (!lag_once) {
-			lag_once = true;
-			printk_deferred("sched: DL replenish lagged to much\n");
-		}
+		printk_once_deferred("sched: DL replenish lagged to much\n");
 		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
 		dl_se->runtime = pi_se->dl_runtime;
 	}
kernel/sched/rt.c +1 -7
index c19b3cc..722e9a3 100644
@@ -851,14 +851,8 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 		 * but accrue some time due to boosting.
 		 */
 		if (likely(rt_b->rt_runtime)) {
-			static bool once = false;
-
 			rt_rq->rt_throttled = 1;
-
-			if (!once) {
-				once = true;
-				printk_deferred("sched: RT throttling activated\n");
-			}
+			printk_once_deferred("sched: RT throttling activated\n");
 		} else {
 			/*
 			 * In case we did anyway, make it go away,
Signature · 1 line
1.8.3.2
#3 lore raw

RFC PATCH 3/3 timekeeping: Use printk_deferred when holding timekeeping seqlock

In reply to John Stultz

Jiri Bohac pointed out that there are rare but potential deadlock possibilities when calling printk while holding the timekeeping seqlock.

This is due to printk() triggering console sem wakeup, which can cause scheduling code to trigger hrtimers which may try to read the time.

Specifically, as Jiri pointed out, that path is:
printk

    vprintk_emit
      console_unlock
        up(&console_sem)
          __up
	    wake_up_process
	      try_to_wake_up
	        ttwu_do_activate
		  ttwu_activate
		    activate_task
		      enqueue_task
		        enqueue_task_fair
			  hrtick_update
			    hrtick_start_fair
			      hrtick_start_fair
			        get_time
				  ktime_get
				    --> endless loop on
				    read_seqcount_retry(&timekeeper_seq, ...)

This patch tries to avoid this issue by using printk_deferred (previously named printk_sched) which should defer printing via a irq_work_queue.

Cc Jan Kara <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Jiri Bohac <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Andrew Morton <[email protected]>
---
 kernel/time/ntp.c         | 15 +++++++++------
 kernel/time/timekeeping.c |  7 ++++---
 2 files changed, 13 insertions(+), 9 deletions(-)
kernel/time/ntp.c +9 -6
index 419a52c..5b0ac4d 100644
@@ -786,8 +786,9 @@ static long hardpps_update_freq(struct pps_normtime freq_norm)
 		time_status |= STA_PPSERROR;
 		pps_errcnt++;
 		pps_dec_freq_interval();
-		pr_err("hardpps: PPSERROR: interval too long - %ld s\n",
-				freq_norm.sec);
+		printk_deferred(KERN_ERR
+			"hardpps: PPSERROR: interval too long - %ld s\n",
+			freq_norm.sec);
 		return 0;
 	}
 
@@ -800,7 +801,8 @@ static long hardpps_update_freq(struct pps_normtime freq_norm)
 	delta = shift_right(ftemp - pps_freq, NTP_SCALE_SHIFT);
 	pps_freq = ftemp;
 	if (delta > PPS_MAXWANDER || delta < -PPS_MAXWANDER) {
-		pr_warning("hardpps: PPSWANDER: change=%ld\n", delta);
+		printk_deferred(KERN_WARNING
+				"hardpps: PPSWANDER: change=%ld\n", delta);
 		time_status |= STA_PPSWANDER;
 		pps_stbcnt++;
 		pps_dec_freq_interval();
@@ -844,8 +846,9 @@ static void hardpps_update_phase(long error)
 	 * the time offset is updated.
 	 */
 	if (jitter > (pps_jitter << PPS_POPCORN)) {
-		pr_warning("hardpps: PPSJITTER: jitter=%ld, limit=%ld\n",
-		       jitter, (pps_jitter << PPS_POPCORN));
+		printk_deferred(KERN_WARNING
+				"hardpps: PPSJITTER: jitter=%ld, limit=%ld\n",
+				jitter, (pps_jitter << PPS_POPCORN));
 		time_status |= STA_PPSJITTER;
 		pps_jitcnt++;
 	} else if (time_status & STA_PPSTIME) {
@@ -902,7 +905,7 @@ void __hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
 		time_status |= STA_PPSJITTER;
 		/* restart the frequency calibration interval */
 		pps_fbase = *raw_ts;
-		pr_err("hardpps: PPSJITTER: bad pulse\n");
+		printk_deferred(KERN_ERR "hardpps: PPSJITTER: bad pulse\n");
 		return;
 	}
 
kernel/time/timekeeping.c +4 -3
index f7df8ea..ffd3113 100644
@@ -852,8 +852,9 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
 							struct timespec *delta)
 {
 	if (!timespec_valid_strict(delta)) {
-		printk(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid "
-					"sleep delta value!\n");
+		printk_deferred(KERN_WARNING
+				"__timekeeping_inject_sleeptime: Invalid "
+				"sleep delta value!\n");
 		return;
 	}
 	tk_xtime_add(tk, delta);
@@ -1157,7 +1158,7 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
 
 	if (unlikely(tk->clock->maxadj &&
 		(tk->mult + adj > tk->clock->mult + tk->clock->maxadj))) {
-		printk_once(KERN_WARNING
+		printk_once_deferred(KERN_WARNING
 			"Adjusting %s more than 11%% (%ld vs %ld)\n",
 			tk->clock->name, (long)tk->mult + adj,
 			(long)tk->clock->mult + tk->clock->maxadj);
Signature · 1 line
1.8.3.2