From: sboyd@codeaurora.org (Stephen Boyd)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v4 02/17] sched_clock: Use seqcount instead of rolling our own
Date: Thu, 18 Jul 2013 16:21:15 -0700 [thread overview]
Message-ID: <1374189690-10810-3-git-send-email-sboyd@codeaurora.org> (raw)
In-Reply-To: <1374189690-10810-1-git-send-email-sboyd@codeaurora.org>
We're going to increase the cyc value to 64 bits in the near
future. Doing that is going to break the custom seqcount
implementation in the sched_clock code because 64 bit numbers
aren't guaranteed to be atomic. Replace the cyc_copy with a
seqcount to avoid this problem.
Cc: Russell King <linux@arm.linux.org.uk>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
---
kernel/time/sched_clock.c | 27 ++++++++-------------------
1 file changed, 8 insertions(+), 19 deletions(-)
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index a326f27..396f7b9 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -14,11 +14,12 @@
#include <linux/syscore_ops.h>
#include <linux/timer.h>
#include <linux/sched_clock.h>
+#include <linux/seqlock.h>
struct clock_data {
u64 epoch_ns;
u32 epoch_cyc;
- u32 epoch_cyc_copy;
+ seqcount_t seq;
unsigned long rate;
u32 mult;
u32 shift;
@@ -54,23 +55,16 @@ static unsigned long long notrace sched_clock_32(void)
u64 epoch_ns;
u32 epoch_cyc;
u32 cyc;
+ unsigned long seq;
if (cd.suspended)
return cd.epoch_ns;
- /*
- * Load the epoch_cyc and epoch_ns atomically. We do this by
- * ensuring that we always write epoch_cyc, epoch_ns and
- * epoch_cyc_copy in strict order, and read them in strict order.
- * If epoch_cyc and epoch_cyc_copy are not equal, then we're in
- * the middle of an update, and we should repeat the load.
- */
do {
+ seq = read_seqcount_begin(&cd.seq);
epoch_cyc = cd.epoch_cyc;
- smp_rmb();
epoch_ns = cd.epoch_ns;
- smp_rmb();
- } while (epoch_cyc != cd.epoch_cyc_copy);
+ } while (read_seqcount_retry(&cd.seq, seq));
cyc = read_sched_clock();
cyc = (cyc - epoch_cyc) & sched_clock_mask;
@@ -90,16 +84,12 @@ static void notrace update_sched_clock(void)
ns = cd.epoch_ns +
cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
cd.mult, cd.shift);
- /*
- * Write epoch_cyc and epoch_ns in a way that the update is
- * detectable in cyc_to_fixed_sched_clock().
- */
+
raw_local_irq_save(flags);
- cd.epoch_cyc_copy = cyc;
- smp_wmb();
+ write_seqcount_begin(&cd.seq);
cd.epoch_ns = ns;
- smp_wmb();
cd.epoch_cyc = cyc;
+ write_seqcount_end(&cd.seq);
raw_local_irq_restore(flags);
}
@@ -195,7 +185,6 @@ static int sched_clock_suspend(void)
static void sched_clock_resume(void)
{
cd.epoch_cyc = read_sched_clock();
- cd.epoch_cyc_copy = cd.epoch_cyc;
cd.suspended = false;
}
--
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
hosted by The Linux Foundation
next prev parent reply other threads:[~2013-07-18 23:21 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-07-18 23:21 [PATCH v4 00/17] 64-bit friendly generic sched_clock() Stephen Boyd
2013-07-18 23:21 ` [PATCH v4 01/17] clocksource: Extract max nsec calculation into separate function Stephen Boyd
2013-07-18 23:21 ` Stephen Boyd [this message]
2013-07-19 9:03 ` [PATCH v4 02/17] sched_clock: Use seqcount instead of rolling our own Will Deacon
2013-07-19 14:20 ` Nicolas Pitre
2013-07-19 14:27 ` Russell King - ARM Linux
2013-07-18 23:21 ` [PATCH v4 03/17] sched_clock: Use an hrtimer instead of timer Stephen Boyd
2013-07-22 18:21 ` John Stultz
2013-07-22 18:45 ` Stephen Boyd
2013-07-22 18:58 ` Stephen Boyd
2013-07-22 19:07 ` Russell King - ARM Linux
2013-07-22 20:48 ` John Stultz
2013-07-22 20:50 ` Stephen Boyd
2013-07-18 23:21 ` [PATCH v4 04/17] sched_clock: Add support for >32 bit sched_clock Stephen Boyd
2013-07-19 9:23 ` Baruch Siach
2013-07-19 16:29 ` Stephen Boyd
2013-07-18 23:21 ` [PATCH v4 05/17] arch_timer: Move to generic sched_clock framework Stephen Boyd
2013-10-02 17:44 ` Will Deacon
2013-10-14 18:44 ` Kevin Hilman
2013-10-14 18:55 ` Stephen Boyd
2013-10-14 20:14 ` Kevin Hilman
2013-10-14 20:18 ` John Stultz
2013-10-14 20:14 ` John Stultz
2013-07-18 23:21 ` [PATCH v4 06/17] sched_clock: Remove sched_clock_func() hook Stephen Boyd
2013-07-18 23:21 ` [PATCH v4 07/17] clocksource: bcm2835: Switch to sched_clock_register() Stephen Boyd
2013-07-19 19:34 ` Stephen Warren
2013-07-30 10:04 ` Daniel Lezcano
2013-07-30 16:12 ` John Stultz
2013-07-18 23:21 ` [PATCH v4 08/17] ocksource: dbx500-prcmu: " Stephen Boyd
2013-07-19 0:18 ` Stephen Boyd
2013-07-18 23:21 ` [PATCH v4 09/17] clocksource: dw_apb_timer_of: " Stephen Boyd
2013-07-18 23:21 ` [PATCH v4 10/17] clocksource: mxs_timer: " Stephen Boyd
2013-07-22 8:10 ` Shawn Guo
2013-07-22 16:23 ` Stephen Boyd
2013-07-18 23:21 ` [PATCH v4 11/17] clocksource: nomadik: " Stephen Boyd
2013-07-18 23:21 ` [PATCH v4 12/17] clocksource: samsung_pwm_timer: " Stephen Boyd
2013-07-18 23:21 ` [PATCH v4 13/17] clocksource: tegra: " Stephen Boyd
2013-07-19 19:34 ` Stephen Warren
2013-07-18 23:21 ` [PATCH v4 14/17] clocksource: time-armada-370-xp: " Stephen Boyd
2013-08-06 9:04 ` Gregory CLEMENT
2013-07-18 23:21 ` [PATCH v4 15/17] clocksource: sirf: Switch to sched_clock_register() and use 64 bits Stephen Boyd
2013-07-18 23:21 ` [PATCH v4 16/17] clocksource: vf_pit_timer: Switch to sched_clock_register() Stephen Boyd
2013-07-18 23:21 ` [PATCH v4 17/17] sched_clock: Deprecate setup_sched_clock() Stephen Boyd
2013-07-18 23:59 ` [PATCH v4 00/17] 64-bit friendly generic sched_clock() John Stultz
2013-07-19 0:23 ` Stephen Boyd
2013-10-02 17:47 ` Will Deacon
2013-10-02 18:02 ` John Stultz
2013-10-02 18:13 ` Will Deacon
2013-07-20 20:51 ` Linus Walleij
2013-07-22 16:24 ` Stephen Boyd
2013-07-22 17:07 ` John Stultz
2013-07-24 14:44 ` Christopher Covington
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=1374189690-10810-3-git-send-email-sboyd@codeaurora.org \
--to=sboyd@codeaurora.org \
--cc=linux-arm-kernel@lists.infradead.org \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).