The patch titled
Subject: hrtimers: Special-case zero length sleeps
has been added to the -mm tree. Its filename is
hrtimers-special-case-zero-length-sleeps.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
From: Matthew Garrett <mjg@xxxxxxxxxx>
Subject: hrtimers: Special-case zero length sleeps
sleep(0) is a common construct used by applications that want to trigger
the scheduler. sched_yield() might make more sense, but only appeared in
POSIX.1-2001 and so plenty of example code still uses the sleep(0) form.
This wouldn't normally be a problem, but it means that event-driven
applications that are merely trying to avoid starving other processes may
actually end up sleeping due to having large timer_slack values. Special-
casing this seems reasonable.
Signed-off-by: Matthew Garrett <mjg@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Arjan van de Ven <arjan@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxx>
---
kernel/hrtimer.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff -puN kernel/hrtimer.c~hrtimers-special-case-zero-length-sleeps kernel/hrtimer.c
--- a/kernel/hrtimer.c~hrtimers-special-case-zero-length-sleeps
+++ a/kernel/hrtimer.c
@@ -1566,6 +1566,14 @@ long hrtimer_nanosleep(struct timespec *
if (rt_task(current))
slack = 0;
+ /*
+ * Applications will often sleep(0) to indicate that they wish to
+ * be scheduled. Special case that to avoid actually putting them
+ * to sleep for the duration of the slack.
+ */
+ if (rqtp->tv_sec == 0 && rqtp->tv_nsec == 0)
+ slack = 0;
+
hrtimer_init_on_stack(&t.timer, clockid, mode);
hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack);
if (do_nanosleep(&t, mode))
_
Subject: Subject: hrtimers: Special-case zero length sleeps
Patches currently in -mm which might be from mjg@xxxxxxxxxx are
origin.patch
linux-next.patch
acerhdf-add-support-for-aspire-1410-bios-v13314.patch
arch-x86-platform-iris-irisc-register-a-platform-device-and-a-platform-driver.patch
hp_accel-add-a-new-pnp-id.patch
hp_accel-add-axis-mapping-for-hp-probook-elitebook.patch
hrtimers-special-case-zero-length-sleeps.patch
lis3lv02d-avoid-divide-by-zero-due-to-unchecked.patch
lis3-update-maintainer-information.patch
lis3-add-support-for-hp-elitebook-2730p.patch
lis3-add-support-for-hp-elitebook-8540w.patch
hp_accel-add-hp-probook-655x.patch
lis3-free-regulators-if-probe-fails.patch
lis3-change-naming-to-consistent.patch
lis3-change-exported-function-to-use-given.patch
lis3-remove-the-references-to-the-global-variable-in-core-driver.patch
maintainers-add-new-entry-for-ideapad-laptop.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
