lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20160804125618.6db9b5b3@gandalf.local.home>
Date:	Thu, 4 Aug 2016 12:56:18 -0400
From:	Steven Rostedt <rostedt@...dmis.org>
To:	linux-kernel@...r.kernel.org, linux-rt-users@...r.kernel.org
Cc:	Ingo Molnar <mingo@...nel.org>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Clark Williams <williams@...hat.com>,
	Thomas Gleixner <tglx@...utronix.de>,
	Jon Masters <jcm@...hat.com>, Daniel Wagner <wagi@...om.org>,
	Carsten Emde <C.Emde@...dl.org>,
	Sebastian Andrzej Siewior <bigeasy@...utronix.de>
Subject: [RFC][PATCH 4/3] tracing: Add NMI tracing in hwlat detector


As NMIs can also cause latency when interrupts are disabled, the hwlat
detectory has no way to know if the latency it detects is from an NMI or an
SMI or some other hardware glitch.

As ftrace_nmi_enter/exit() funtions are no longer used (except for sh, which
isn't supported anymore), I converted those to "arch_ftrace_nmi_enter/exit"
and use ftrace_nmi_enter/exit() to check if hwlat detector is tracing or
not, and if so, it calls into the hwlat utility.

Since the hwlat detector only has a single kthread that is spinning with
interrupts disabled, it marks what CPU it is on, and if the NMI callback
happens on that CPU, it records the time spent in that NMI. This is added to
the output that is generated by the hwlat detector as:

 [1] inner:0 outer:8 ts:1470329211.586481492 nmi-total:0 nmi-count:0
 [2] inner:0 outer:4 ts:1470329231.619726657 nmi-total:4 nmi-count:1
 [3] inner:0 outer:5 ts:1470329234.550761052 nmi-total:4 nmi-count:1
 [4] inner:8 outer:0 ts:1470329263.655911668 nmi-total:0 nmi-count:0

All time is still tracked in microseconds.

Is the nmi-count even required? I could also modify it to not show the
NMI information if there wasn't any NMIs.

Signed-off-by: Steven Rostedt <rostedt@...dmis.org>
---
 arch/sh/kernel/ftrace.c      |  4 ++--
 include/linux/ftrace_irq.h   | 31 +++++++++++++++++++++++++++----
 kernel/trace/trace_entries.h |  8 ++++++--
 kernel/trace/trace_hwlat.c   | 44 ++++++++++++++++++++++++++++++++++++++++++++
 kernel/trace/trace_output.c  |  6 ++++--
 5 files changed, 83 insertions(+), 10 deletions(-)

diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c
index 38993e09ef03..deb9eba3a43d 100644
--- a/arch/sh/kernel/ftrace.c
+++ b/arch/sh/kernel/ftrace.c
@@ -139,7 +139,7 @@ static void ftrace_mod_code(void)
 		clear_mod_flag();
 }
 
-void ftrace_nmi_enter(void)
+void arch_ftrace_nmi_enter(void)
 {
 	if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) {
 		smp_rmb();
@@ -150,7 +150,7 @@ void ftrace_nmi_enter(void)
 	smp_mb();
 }
 
-void ftrace_nmi_exit(void)
+void arch_ftrace_nmi_exit(void)
 {
 	/* Finish all executions before clearing nmi_running */
 	smp_mb();
diff --git a/include/linux/ftrace_irq.h b/include/linux/ftrace_irq.h
index dca7bf8cffe2..4ec2c9b205f2 100644
--- a/include/linux/ftrace_irq.h
+++ b/include/linux/ftrace_irq.h
@@ -3,11 +3,34 @@
 
 
 #ifdef CONFIG_FTRACE_NMI_ENTER
-extern void ftrace_nmi_enter(void);
-extern void ftrace_nmi_exit(void);
+extern void arch_ftrace_nmi_enter(void);
+extern void arch_ftrace_nmi_exit(void);
 #else
-static inline void ftrace_nmi_enter(void) { }
-static inline void ftrace_nmi_exit(void) { }
+static inline void arch_ftrace_nmi_enter(void) { }
+static inline void arch_ftrace_nmi_exit(void) { }
 #endif
 
+#ifdef CONFIG_HWLAT_TRACER
+extern bool trace_hwlat_callback_enabled;
+extern void trace_hwlat_callback(bool enter);
+#endif
+
+static inline void ftrace_nmi_enter(void)
+{
+#ifdef CONFIG_HWLAT_TRACER
+	if (trace_hwlat_callback_enabled)
+		trace_hwlat_callback(true);
+#endif
+	arch_ftrace_nmi_enter();
+}
+
+static inline void ftrace_nmi_exit(void)
+{
+	arch_ftrace_nmi_exit();
+#ifdef CONFIG_HWLAT_TRACER
+	if (trace_hwlat_callback_enabled)
+		trace_hwlat_callback(false);
+#endif
+}
+
 #endif /* _LINUX_FTRACE_IRQ_H */
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index 70d47dd99359..d1cc37e78f99 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -330,18 +330,22 @@ FTRACE_ENTRY(hwlat, hwlat_entry,
 	F_STRUCT(
 		__field(	u64,			duration	)
 		__field(	u64,			outer_duration	)
+		__field(	u64,			nmi_total_ts	)
 		__field_struct( struct timespec,	timestamp	)
 		__field_desc(	long,	timestamp,	tv_sec		)
 		__field_desc(	long,	timestamp,	tv_nsec		)
+		__field(	unsigned int,		nmi_count	)
 		__field(	unsigned int,		seqnum		)
 	),
 
-	F_printk("cnt:%u\tts:%010lu.%010lu\tinner:%llu\touter:%llu\n",
+	F_printk("cnt:%u\tts:%010lu.%010lu\tinner:%llu\touter:%llunmi-ts:%llu\tnmi-count:%u\n",
 		 __entry->seqnum,
 		 __entry->tv_sec,
 		 __entry->tv_nsec,
 		 __entry->duration,
-		 __entry->outer_duration),
+		 __entry->outer_duration,
+		 __entry->nmi_total_ts,
+		 __entry->nmi_count),
 
 	FILTER_OTHER
 );
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index f0b5b2944ee7..0c7ca6082721 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -64,6 +64,15 @@ static struct dentry *hwlat_sample_window;	/* sample window us */
 /* Save the previous tracing_thresh value */
 static unsigned long save_tracing_thresh;
 
+/* NMI timestamp counters */
+static u64 nmi_ts_start;
+static u64 nmi_total_ts;
+static int nmi_count;
+static int nmi_cpu;
+
+/* Tells NMIs to call back to the hwlat tracer to record timestamps */
+bool trace_hwlat_callback_enabled;
+
 /* If the user changed threshold, remember it */
 static u64 last_tracing_thresh = DEFAULT_LAT_THRESHOLD * NSEC_PER_USEC;
 
@@ -72,7 +81,9 @@ struct hwlat_sample {
 	u64		seqnum;		/* unique sequence */
 	u64		duration;	/* delta */
 	u64		outer_duration;	/* delta (outer loop) */
+	u64		nmi_total_ts;	/* Total time spent in NMIs */
 	struct timespec	timestamp;	/* wall time */
+	int		nmi_count;	/* # NMIs during this sample */
 };
 
 /* keep the global state somewhere. */
@@ -112,6 +123,8 @@ static void trace_hwlat_sample(struct hwlat_sample *sample)
 	entry->duration			= sample->duration;
 	entry->outer_duration		= sample->outer_duration;
 	entry->timestamp		= sample->timestamp;
+	entry->nmi_total_ts		= sample->nmi_total_ts;
+	entry->nmi_count		= sample->nmi_count;
 
 	if (!call_filter_check_discard(call, entry, buffer, event))
 		__buffer_unlock_commit(buffer, event);
@@ -125,6 +138,19 @@ static void trace_hwlat_sample(struct hwlat_sample *sample)
 #define init_time(a, b)	(a = b)
 #define time_u64(a)	a
 
+void trace_hwlat_callback(bool enter)
+{
+	if (smp_processor_id() != nmi_cpu)
+		return;
+
+	if (enter)
+		nmi_ts_start = time_get();
+	else {
+		nmi_total_ts = time_get() - nmi_ts_start;
+		nmi_count++;
+	}
+}
+
 /**
  * get_sample - sample the CPU TSC and look for likely hardware latencies
  *
@@ -144,6 +170,14 @@ static int get_sample(void)
 
 	do_div(thresh, NSEC_PER_USEC); /* modifies interval value */
 
+	nmi_cpu = smp_processor_id();
+	nmi_total_ts = 0;
+	nmi_count = 0;
+	/* Make sure NMIs see this first */
+	barrier();
+
+	trace_hwlat_callback_enabled = true;
+
 	init_time(last_t2, 0);
 	start = time_get(); /* start timestamp */
 
@@ -188,6 +222,10 @@ static int get_sample(void)
 
 	} while (total <= hwlat_data.sample_width);
 
+	barrier(); /* finish the above in the view for NMIs */
+	trace_hwlat_callback_enabled = false;
+	barrier(); /* Make sure nmi_total_ts is no longer updated */
+
 	ret = 0;
 
 	/* If we exceed the threshold value, we have found a hardware latency */
@@ -196,11 +234,17 @@ static int get_sample(void)
 
 		ret = 1;
 
+		/* We read in microseconds */
+		if (nmi_total_ts)
+			do_div(nmi_total_ts, NSEC_PER_USEC);
+
 		hwlat_data.count++;
 		s.seqnum = hwlat_data.count;
 		s.duration = sample;
 		s.outer_duration = outer_sample;
 		s.timestamp = CURRENT_TIME;
+		s.nmi_total_ts = nmi_total_ts;
+		s.nmi_count = nmi_count;
 		trace_hwlat_sample(&s);
 
 		/* Keep a running maximum ever recorded hardware latency */
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index cc5db62a3929..892359b75b61 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1109,12 +1109,14 @@ trace_hwlat_print(struct trace_iterator *iter, int flags,
 
 	trace_assign_type(field, entry);
 
-	trace_seq_printf(s, "[%u] inner:%llu outer:%lld ts:%ld.%09ld\n",
+	trace_seq_printf(s, "[%u] inner:%llu outer:%lld ts:%ld.%09ld nmi-total:%llu nmi-count:%u\n",
 			 field->seqnum,
 			 field->duration,
 			 field->outer_duration,
 			 field->timestamp.tv_sec,
-			 field->timestamp.tv_nsec);
+			 field->timestamp.tv_nsec,
+			 field->nmi_total_ts,
+			 field->nmi_count);
 
 	return trace_handle_return(s);
 }
-- 
1.9.3

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ