LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Steven Rostedt <rostedt@goodmis.org>
To: LKML <linux-kernel@vger.kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Christoph Hellwig <hch@infradead.org>,
	Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>,
	Gregory Haskins <ghaskins@novell.com>,
	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>,
	Thomas Gleixner <tglx@linutronix.de>,
	Tim Bird <tim.bird@am.sony.com>, Sam Ravnborg <sam@ravnborg.org>,
	"Frank Ch. Eigler" <fche@redhat.com>,
	John Stultz <johnstul@us.ibm.com>,
	Steven Rostedt <srostedt@redhat.com>
Subject: [RFC PATCH 13/22 -v2] handle accurate time keeping over long delays
Date: Wed, 09 Jan 2008 18:29:27 -0500	[thread overview]
Message-ID: <20080109233044.288563621@goodmis.org> (raw)
In-Reply-To: <20080109232914.676624725@goodmis.org>

[-- Attachment #1: rt-time-starvation-fix.patch --]
[-- Type: text/plain, Size: 9538 bytes --]

Handle accurate time even if there's a long delay between
accumulated clock cycles.

Signed-off-by: John Stultz <johnstul@us.ibm.com>
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
---
 arch/x86/kernel/vsyscall_64.c |    5 ++-
 include/asm-x86/vgtod.h       |    2 -
 include/linux/clocksource.h   |   58 ++++++++++++++++++++++++++++++++++++++++--
 kernel/time/timekeeping.c     |   35 +++++++++++++------------
 4 files changed, 80 insertions(+), 20 deletions(-)

linux-2.6.21-rc5_cycles-accumulated_C7.patch
============================================
Index: linux-compile-i386.git/arch/x86/kernel/vsyscall_64.c
===================================================================
--- linux-compile-i386.git.orig/arch/x86/kernel/vsyscall_64.c	2008-01-09 14:10:20.000000000 -0500
+++ linux-compile-i386.git/arch/x86/kernel/vsyscall_64.c	2008-01-09 14:17:53.000000000 -0500
@@ -86,6 +86,7 @@ void update_vsyscall(struct timespec *wa
 	vsyscall_gtod_data.clock.mask = clock->mask;
 	vsyscall_gtod_data.clock.mult = clock->mult;
 	vsyscall_gtod_data.clock.shift = clock->shift;
+	vsyscall_gtod_data.clock.cycle_accumulated = clock->cycle_accumulated;
 	vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec;
 	vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec;
 	vsyscall_gtod_data.wall_to_monotonic = wall_to_monotonic;
@@ -121,7 +122,7 @@ static __always_inline long time_syscall
 
 static __always_inline void do_vgettimeofday(struct timeval * tv)
 {
-	cycle_t now, base, mask, cycle_delta;
+	cycle_t now, base, accumulated, mask, cycle_delta;
 	unsigned seq;
 	unsigned long mult, shift, nsec;
 	cycle_t (*vread)(void);
@@ -135,6 +136,7 @@ static __always_inline void do_vgettimeo
 		}
 		now = vread();
 		base = __vsyscall_gtod_data.clock.cycle_last;
+		accumulated  = __vsyscall_gtod_data.clock.cycle_accumulated;
 		mask = __vsyscall_gtod_data.clock.mask;
 		mult = __vsyscall_gtod_data.clock.mult;
 		shift = __vsyscall_gtod_data.clock.shift;
@@ -145,6 +147,7 @@ static __always_inline void do_vgettimeo
 
 	/* calculate interval: */
 	cycle_delta = (now - base) & mask;
+	cycle_delta += accumulated;
 	/* convert to nsecs: */
 	nsec += (cycle_delta * mult) >> shift;
 
Index: linux-compile-i386.git/include/linux/clocksource.h
===================================================================
--- linux-compile-i386.git.orig/include/linux/clocksource.h	2008-01-09 14:07:34.000000000 -0500
+++ linux-compile-i386.git/include/linux/clocksource.h	2008-01-09 15:17:33.000000000 -0500
@@ -50,8 +50,12 @@ struct clocksource;
  * @flags:		flags describing special properties
  * @vread:		vsyscall based read
  * @resume:		resume function for the clocksource, if necessary
+ * @cycle_last:		Used internally by timekeeping core, please ignore.
+ * @cycle_accumulated:	Used internally by timekeeping core, please ignore.
  * @cycle_interval:	Used internally by timekeeping core, please ignore.
  * @xtime_interval:	Used internally by timekeeping core, please ignore.
+ * @xtime_nsec:		Used internally by timekeeping core, please ignore.
+ * @error:		Used internally by timekeeping core, please ignore.
  */
 struct clocksource {
 	/*
@@ -82,7 +86,10 @@ struct clocksource {
 	 * Keep it in a different cache line to dirty no
 	 * more than one cache line.
 	 */
-	cycle_t cycle_last ____cacheline_aligned_in_smp;
+	struct {
+		cycle_t cycle_last, cycle_accumulated;
+	} ____cacheline_aligned_in_smp;
+
 	u64 xtime_nsec;
 	s64 error;
 
@@ -168,11 +175,44 @@ static inline cycle_t clocksource_read(s
 }
 
 /**
+ * clocksource_get_cycles: - Access the clocksource's accumulated cycle value
+ * @cs:		pointer to clocksource being read
+ * @now:	current cycle value
+ *
+ * Uses the clocksource to return the current cycle_t value.
+ * NOTE!!!: This is different from clocksource_read, because it
+ * returns the accumulated cycle value! Must hold xtime lock!
+ */
+static inline cycle_t
+clocksource_get_cycles(struct clocksource *cs, cycle_t now)
+{
+	cycle_t offset = (now - cs->cycle_last) & cs->mask;
+	offset += cs->cycle_accumulated;
+	return offset;
+}
+
+/**
+ * clocksource_accumulate: - Accumulates clocksource cycles
+ * @cs:		pointer to clocksource being read
+ * @now:	current cycle value
+ *
+ * Used to avoids clocksource hardware overflow by periodically
+ * accumulating the current cycle delta. Must hold xtime write lock!
+ */
+static inline void clocksource_accumulate(struct clocksource *cs, cycle_t now)
+{
+	cycle_t offset = (now - cs->cycle_last) & cs->mask;
+	cs->cycle_last = now;
+	cs->cycle_accumulated += offset;
+}
+
+/**
  * cyc2ns - converts clocksource cycles to nanoseconds
  * @cs:		Pointer to clocksource
  * @cycles:	Cycles
  *
  * Uses the clocksource and ntp ajdustment to convert cycle_ts to nanoseconds.
+ * Must hold xtime lock!
  *
  * XXX - This could use some mult_lxl_ll() asm optimization
  */
@@ -184,13 +224,27 @@ static inline s64 cyc2ns(struct clocksou
 }
 
 /**
+ * ns2cyc - converts nanoseconds to clocksource cycles
+ * @cs:		Pointer to clocksource
+ * @nsecs:	Nanoseconds
+ */
+static inline cycle_t ns2cyc(struct clocksource *cs, u64 nsecs)
+{
+	cycle_t ret = nsecs << cs->shift;
+
+	do_div(ret, cs->mult + 1);
+
+	return ret;
+}
+
+/**
  * clocksource_calculate_interval - Calculates a clocksource interval struct
  *
  * @c:		Pointer to clocksource.
  * @length_nsec: Desired interval length in nanoseconds.
  *
  * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment
- * pair and interval request.
+ * pair and interval request. Must hold xtime_lock!
  *
  * Unless you're the timekeeping code, you should not be using this!
  */
Index: linux-compile-i386.git/kernel/time/timekeeping.c
===================================================================
--- linux-compile-i386.git.orig/kernel/time/timekeeping.c	2008-01-09 14:07:34.000000000 -0500
+++ linux-compile-i386.git/kernel/time/timekeeping.c	2008-01-09 15:17:31.000000000 -0500
@@ -66,16 +66,10 @@ static struct clocksource *clock; /* poi
  */
 static inline s64 __get_nsec_offset(void)
 {
-	cycle_t cycle_now, cycle_delta;
+	cycle_t cycle_delta;
 	s64 ns_offset;
 
-	/* read clocksource: */
-	cycle_now = clocksource_read(clock);
-
-	/* calculate the delta since the last update_wall_time: */
-	cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
-
-	/* convert to nanoseconds: */
+	cycle_delta = clocksource_get_cycles(clock, clocksource_read(clock));
 	ns_offset = cyc2ns(clock, cycle_delta);
 
 	return ns_offset;
@@ -195,7 +189,7 @@ static void change_clocksource(void)
 
 	clock = new;
 	clock->cycle_last = now;
-
+	clock->cycle_accumulated = 0;
 	clock->error = 0;
 	clock->xtime_nsec = 0;
 	clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH);
@@ -205,9 +199,15 @@ static void change_clocksource(void)
 	printk(KERN_INFO "Time: %s clocksource has been installed.\n",
 	       clock->name);
 }
+
+void timekeeping_accumulate(void)
+{
+	clocksource_accumulate(clock, clocksource_read(clock));
+}
 #else
 static inline void change_clocksource(void) { }
 static inline s64 __get_nsec_offset(void) { return 0; }
+void timekeeping_accumulate(void) { }
 #endif
 
 /**
@@ -302,6 +302,7 @@ static int timekeeping_resume(struct sys
 	timespec_add_ns(&xtime, timekeeping_suspend_nsecs);
 	/* re-base the last cycle value */
 	clock->cycle_last = clocksource_read(clock);
+	clock->cycle_accumulated = 0;
 	clock->error = 0;
 	timekeeping_suspended = 0;
 	write_sequnlock_irqrestore(&xtime_lock, flags);
@@ -448,27 +449,29 @@ static void clocksource_adjust(s64 offse
  */
 void update_wall_time(void)
 {
-	cycle_t offset;
+	cycle_t cycle_now, offset;
 
 	/* Make sure we're fully resumed: */
 	if (unlikely(timekeeping_suspended))
 		return;
 
 #ifdef CONFIG_GENERIC_TIME
-	offset = (clocksource_read(clock) - clock->cycle_last) & clock->mask;
+	cycle_now = clocksource_read(clock);
 #else
-	offset = clock->cycle_interval;
+	cycle_now = clock->cycle_last + clock->cycle_interval;
 #endif
+	offset = (cycle_now - clock->cycle_last) & clock->mask;
+	clocksource_accumulate(clock, cycle_now);
+
 	clock->xtime_nsec += (s64)xtime.tv_nsec << clock->shift;
 
 	/* normally this loop will run just once, however in the
 	 * case of lost or late ticks, it will accumulate correctly.
 	 */
-	while (offset >= clock->cycle_interval) {
+	while (clock->cycle_accumulated >= clock->cycle_interval) {
 		/* accumulate one interval */
 		clock->xtime_nsec += clock->xtime_interval;
-		clock->cycle_last += clock->cycle_interval;
-		offset -= clock->cycle_interval;
+		clock->cycle_accumulated -= clock->cycle_interval;
 
 		if (clock->xtime_nsec >= (u64)NSEC_PER_SEC << clock->shift) {
 			clock->xtime_nsec -= (u64)NSEC_PER_SEC << clock->shift;
@@ -482,7 +485,7 @@ void update_wall_time(void)
 	}
 
 	/* correct the clock when NTP error is too big */
-	clocksource_adjust(offset);
+	clocksource_adjust(clock->cycle_accumulated);
 
 	/* store full nanoseconds into xtime */
 	xtime.tv_nsec = (s64)clock->xtime_nsec >> clock->shift;
Index: linux-compile-i386.git/include/asm-x86/vgtod.h
===================================================================
--- linux-compile-i386.git.orig/include/asm-x86/vgtod.h	2008-01-09 14:07:34.000000000 -0500
+++ linux-compile-i386.git/include/asm-x86/vgtod.h	2008-01-09 14:17:53.000000000 -0500
@@ -15,7 +15,7 @@ struct vsyscall_gtod_data {
 	struct timezone sys_tz;
 	struct { /* extract of a clocksource struct */
 		cycle_t (*vread)(void);
-		cycle_t	cycle_last;
+		cycle_t	cycle_last, cycle_accumulated;
 		cycle_t	mask;
 		u32	mult;
 		u32	shift;

-- 

  parent reply	other threads:[~2008-01-09 23:33 UTC|newest]

Thread overview: 100+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-01-09 23:29 [RFC PATCH 00/22 -v2] mcount and latency tracing utility -v2 Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 01/22 -v2] Add basic support for gcc profiler instrumentation Steven Rostedt
2008-01-10 18:19   ` Jan Kiszka
2008-01-10 19:54     ` Steven Rostedt
2008-01-10 23:02     ` Steven Rostedt
2008-01-10 18:28   ` Sam Ravnborg
2008-01-10 19:10     ` Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 02/22 -v2] Annotate core code that should not be traced Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 03/22 -v2] x86_64: notrace annotations Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 04/22 -v2] add notrace annotations to vsyscall Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 05/22 -v2] add notrace annotations for NMI routines Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 06/22 -v2] mcount based trace in the form of a header file library Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 07/22 -v2] tracer add debugfs interface Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 08/22 -v2] mcount tracer output file Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 09/22 -v2] mcount tracer show task comm and pid Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 10/22 -v2] Add a symbol only trace output Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 11/22 -v2] Reset the tracer when started Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 12/22 -v2] separate out the percpu date into a percpu struct Steven Rostedt
2008-01-09 23:29 ` Steven Rostedt [this message]
2008-01-10  0:00   ` [RFC PATCH 13/22 -v2] handle accurate time keeping over long delays john stultz
2008-01-10  0:09     ` Steven Rostedt
2008-01-10 19:54     ` Tony Luck
2008-01-10 20:15       ` Steven Rostedt
2008-01-10 20:41         ` john stultz
2008-01-10 20:29       ` john stultz
2008-01-10 20:42         ` Mathieu Desnoyers
2008-01-10 21:25           ` john stultz
2008-01-10 22:00             ` Mathieu Desnoyers
2008-01-10 22:40               ` Steven Rostedt
2008-01-10 22:51               ` john stultz
2008-01-10 23:05                 ` john stultz
2008-01-10 21:33         ` [RFC PATCH 13/22 -v2] handle accurate time keeping over longdelays Luck, Tony
2008-01-10  0:19   ` [RFC PATCH 13/22 -v2] handle accurate time keeping over long delays john stultz
2008-01-10  0:25     ` Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 14/22 -v2] time keeping add cycle_raw for actual incrementation Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 15/22 -v2] initialize the clock source to jiffies clock Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 16/22 -v2] add get_monotonic_cycles Steven Rostedt
2008-01-10  3:28   ` Daniel Walker
2008-01-15 21:46   ` Mathieu Desnoyers
2008-01-15 22:01     ` Steven Rostedt
2008-01-15 22:03       ` Steven Rostedt
2008-01-15 22:08       ` Mathieu Desnoyers
2008-01-16  1:38         ` Steven Rostedt
2008-01-16  3:17           ` Mathieu Desnoyers
2008-01-16 13:17             ` Steven Rostedt
2008-01-16 14:56               ` Mathieu Desnoyers
2008-01-16 15:06                 ` Steven Rostedt
2008-01-16 15:28                   ` Mathieu Desnoyers
2008-01-16 15:58                     ` Steven Rostedt
2008-01-16 17:00                       ` Mathieu Desnoyers
2008-01-16 17:49                         ` Mathieu Desnoyers
2008-01-16 19:43                         ` Steven Rostedt
2008-01-16 20:17                           ` Mathieu Desnoyers
2008-01-16 20:45                             ` Tim Bird
2008-01-16 20:49                             ` Steven Rostedt
2008-01-17 20:08                             ` Steven Rostedt
2008-01-17 20:37                               ` Frank Ch. Eigler
2008-01-17 21:03                                 ` Steven Rostedt
2008-01-18 22:26                                   ` Mathieu Desnoyers
2008-01-18 22:49                                     ` Steven Rostedt
2008-01-18 23:19                                       ` Mathieu Desnoyers
2008-01-19  3:36                                         ` Frank Ch. Eigler
2008-01-19  3:55                                           ` Steven Rostedt
2008-01-19  4:23                                             ` Frank Ch. Eigler
2008-01-19 15:29                                               ` Mathieu Desnoyers
2008-01-19  3:32                                       ` Frank Ch. Eigler
2008-01-16 18:01                       ` Tim Bird
2008-01-16 22:36                 ` john stultz
2008-01-16 22:51                   ` john stultz
2008-01-16 23:33                     ` Steven Rostedt
2008-01-17  2:28                       ` john stultz
2008-01-17  2:40                         ` Mathieu Desnoyers
2008-01-17  2:50                           ` Mathieu Desnoyers
2008-01-17  3:02                             ` Steven Rostedt
2008-01-17  3:21                             ` Paul Mackerras
2008-01-17  3:39                               ` Steven Rostedt
2008-01-17  4:22                                 ` Mathieu Desnoyers
2008-01-17  4:25                                 ` Mathieu Desnoyers
2008-01-17  4:14                               ` Mathieu Desnoyers
2008-01-17 15:22                                 ` Steven Rostedt
2008-01-17 17:46                                 ` Linus Torvalds
2008-01-17  2:51                           ` Steven Rostedt
2008-01-16 23:39                     ` Mathieu Desnoyers
2008-01-16 23:50                       ` Steven Rostedt
2008-01-17  0:36                         ` Steven Rostedt
2008-01-17  0:33                       ` john stultz
2008-01-17  2:20                         ` Mathieu Desnoyers
2008-01-17  1:03                       ` Linus Torvalds
2008-01-17  1:35                         ` Mathieu Desnoyers
2008-01-17  2:20                       ` john stultz
2008-01-17  2:35                         ` Mathieu Desnoyers
2008-01-09 23:29 ` [RFC PATCH 17/22 -v2] Add timestamps to tracer Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 18/22 -v2] Sort trace by timestamp Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 19/22 -v2] speed up the output of the tracer Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 20/22 -v2] Add latency_trace format tor tracer Steven Rostedt
2008-01-10  3:41   ` Daniel Walker
2008-01-09 23:29 ` [RFC PATCH 21/22 -v2] Split out specific tracing functions Steven Rostedt
2008-01-09 23:29 ` [RFC PATCH 22/22 -v2] Trace irq disabled critical timings Steven Rostedt
2008-01-10  3:58   ` Daniel Walker
2008-01-10 14:45     ` Steven Rostedt

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20080109233044.288563621@goodmis.org \
    --to=rostedt@goodmis.org \
    --cc=a.p.zijlstra@chello.nl \
    --cc=acme@ghostprotocols.net \
    --cc=akpm@linux-foundation.org \
    --cc=fche@redhat.com \
    --cc=ghaskins@novell.com \
    --cc=hch@infradead.org \
    --cc=johnstul@us.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mathieu.desnoyers@polymtl.ca \
    --cc=mingo@elte.hu \
    --cc=sam@ravnborg.org \
    --cc=srostedt@redhat.com \
    --cc=tglx@linutronix.de \
    --cc=tim.bird@am.sony.com \
    --cc=torvalds@linux-foundation.org \
    --subject='Re: [RFC PATCH 13/22 -v2] handle accurate time keeping over long delays' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).