From: Chris Wilson <chris@chris-wilson.co.uk>
To: intel-gfx@lists.freedesktop.org
Subject: [CI 16/20] drm/i915: Only query timestamp when measuring elapsed time
Date: Thu, 19 May 2016 12:32:52 +0100 [thread overview]
Message-ID: <1463657576-32063-16-git-send-email-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <1463657576-32063-1-git-send-email-chris@chris-wilson.co.uk>
Avoid the two calls to ktime_get_raw_ns() (at best it reads the TSC) as
we only need to compute the elapsed time for a timed wait.
v2: Eliminate the unused local variable reducing the function size by 64
bytes (using the storage space on the callers stack rather than adding
to our stack frame)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
drivers/gpu/drm/i915/i915_gem.c | 14 +++++---------
1 file changed, 5 insertions(+), 9 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index b48a3b46e86f..2c254cf49c15 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1215,7 +1215,6 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
int state = interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE;
struct intel_wait wait;
unsigned long timeout_remain;
- s64 before = 0; /* Only to silence a compiler warning. */
int ret = 0;
might_sleep();
@@ -1234,12 +1233,9 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
if (*timeout == 0)
return -ETIME;
+ /* Record current time in case interrupted, or wedged */
timeout_remain = nsecs_to_jiffies_timeout(*timeout);
-
- /*
- * Record current time in case interrupted by signal, or wedged.
- */
- before = ktime_get_raw_ns();
+ *timeout += ktime_get_raw_ns();
}
trace_i915_gem_request_wait_begin(req);
@@ -1296,9 +1292,9 @@ complete:
trace_i915_gem_request_wait_end(req);
if (timeout) {
- s64 tres = *timeout - (ktime_get_raw_ns() - before);
-
- *timeout = tres < 0 ? 0 : tres;
+ *timeout -= ktime_get_raw_ns();
+ if (*timeout < 0)
+ *timeout = 0;
/*
* Apparently ktime isn't accurate enough and occasionally has a
--
2.8.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2016-05-19 11:33 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-05-19 11:32 [CI 01/20] drm: Restore double clflush on the last partial cacheline Chris Wilson
2016-05-19 11:32 ` [CI 02/20] drm/i915/shrinker: Flush active on objects before counting Chris Wilson
2016-05-19 12:14 ` Tvrtko Ursulin
2016-05-19 11:32 ` [CI 03/20] drm/i915: Delay queuing hangcheck to wait-request Chris Wilson
2016-05-19 12:34 ` Tvrtko Ursulin
2016-05-19 12:52 ` Chris Wilson
2016-05-19 11:32 ` [CI 04/20] drm/i915: Remove the dedicated hangcheck workqueue Chris Wilson
2016-05-19 12:50 ` Tvrtko Ursulin
2016-05-19 13:13 ` Chris Wilson
2016-05-20 12:07 ` Tvrtko Ursulin
2016-05-20 12:23 ` Chris Wilson
2016-05-23 8:55 ` Tvrtko Ursulin
2016-05-19 11:32 ` [CI 05/20] drm/i915: Make queueing the hangcheck work inline Chris Wilson
2016-05-19 12:53 ` Tvrtko Ursulin
2016-05-19 13:18 ` Chris Wilson
2016-05-19 11:32 ` [CI 06/20] drm/i915: Slaughter the thundering i915_wait_request herd Chris Wilson
2016-05-20 12:04 ` Tvrtko Ursulin
2016-05-20 12:19 ` Chris Wilson
2016-05-23 8:53 ` Tvrtko Ursulin
2016-06-06 10:14 ` Chris Wilson
2016-06-06 11:04 ` Tvrtko Ursulin
2016-05-19 11:32 ` [CI 07/20] drm/i915: Remove the lazy_coherency parameter from request-completed? Chris Wilson
2016-05-19 11:32 ` [CI 08/20] drm/i915: Use HWS for seqno tracking everywhere Chris Wilson
2016-05-19 11:32 ` [CI 09/20] drm/i915: Stop mapping the scratch page into CPU space Chris Wilson
2016-05-19 11:32 ` [CI 10/20] drm/i915: Allocate scratch page from stolen Chris Wilson
2016-05-19 11:32 ` [CI 11/20] drm/i915: Refactor scratch object allocation for gen2 w/a buffer Chris Wilson
2016-05-19 11:32 ` [CI 12/20] drm/i915: Add a delay between interrupt and inspecting the final seqno (ilk) Chris Wilson
2016-05-19 11:32 ` [CI 13/20] drm/i915: Check the CPU cached value of seqno after waking the waiter Chris Wilson
2016-05-19 11:32 ` [CI 14/20] drm/i915: Only apply one barrier after a breadcrumb interrupt is posted Chris Wilson
2016-05-19 11:32 ` [CI 15/20] drm/i915: Stop setting wraparound seqno on initialisation Chris Wilson
2016-05-19 11:32 ` Chris Wilson [this message]
2016-05-19 15:44 ` [CI 16/20] drm/i915: Only query timestamp when measuring elapsed time Tvrtko Ursulin
2016-05-20 12:20 ` Chris Wilson
2016-05-23 8:54 ` Tvrtko Ursulin
2016-05-19 11:32 ` [CI 17/20] drm/i915: Convert trace-irq to the breadcrumb waiter Chris Wilson
2016-05-19 11:32 ` [CI 18/20] drm/i915: Move the get/put irq locking into the caller Chris Wilson
2016-05-19 11:32 ` [CI 19/20] drm/i915: Simplify enabling user-interrupts with L3-remapping Chris Wilson
2016-05-19 11:32 ` [CI 20/20] drm/i915: Remove debug noise on detecting fault-injection of missed interrupts Chris Wilson
2016-05-19 12:07 ` ✗ Ro.CI.BAT: warning for series starting with [CI,01/20] drm: Restore double clflush on the last partial cacheline Patchwork
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=1463657576-32063-16-git-send-email-chris@chris-wilson.co.uk \
--to=chris@chris-wilson.co.uk \
--cc=intel-gfx@lists.freedesktop.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).