From: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
To: Ben Widawsky <benjamin.widawsky@intel.com>,
Tvrtko Ursulin <tursulin@ursulin.net>
Cc: Intel-gfx@lists.freedesktop.org
Subject: Re: [RFC 04/14] drm/i915/pmu: Decouple uAPI engine ids
Date: Wed, 26 Jul 2017 10:04:23 +0100 [thread overview]
Message-ID: <2bfe1455-693c-1828-8ccd-7fa3d7c6e187@linux.intel.com> (raw)
In-Reply-To: <20170725011817.GA4922@intel.com>
On 25/07/2017 02:18, Ben Widawsky wrote:
> On 17-07-18 15:36:08, Tvrtko Ursulin wrote:
>> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>>
>> As elsewhere in the code we have to decouple the binary
>> engine identifiers for easier maintenance.
>>
>> Also the sampler mask was incorrect in the timer callback.
>>
>
> I don't quite understand the point of this patch... can you perhaps
> embellish
> the commit message?
It is to decouple the ABI namespace from the driver internal enumeration
of engines and so allow the latter to be refactored in the future, and
at the same time fix the fist patch to index engines other than RCS
correctly.
I did not bother with smart commit message for the first few patches
since they really should be squashed with the first one from Chris.
Regards,
Tvrtko
>> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>> ---
>> drivers/gpu/drm/i915/i915_pmu.c | 44
>> ++++++++++++++++++++++++++++++++++++-----
>> 1 file changed, 39 insertions(+), 5 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/i915_pmu.c
>> b/drivers/gpu/drm/i915/i915_pmu.c
>> index f03ddad44da6..9a8208dba7a9 100644
>> --- a/drivers/gpu/drm/i915/i915_pmu.c
>> +++ b/drivers/gpu/drm/i915/i915_pmu.c
>> @@ -10,6 +10,25 @@
>> #define RING_MASK 0xffffffff
>> #define RING_MAX 32
>>
>> +#define ENGINE_SAMPLE_MASK (0xf)
>> +#define ENGINE_SAMPLE_BITS (4)
>> +
>> +static const unsigned int engine_map[I915_NUM_ENGINES] = {
>> + [RCS] = I915_SAMPLE_RCS,
>> + [BCS] = I915_SAMPLE_BCS,
>> + [VCS] = I915_SAMPLE_VCS,
>> + [VCS2] = I915_SAMPLE_VCS2,
>> + [VECS] = I915_SAMPLE_VECS,
>> +};
>> +
>> +static const unsigned int user_engine_map[I915_NUM_ENGINES] = {
>> + [I915_SAMPLE_RCS] = RCS,
>> + [I915_SAMPLE_BCS] = BCS,
>> + [I915_SAMPLE_VCS] = VCS,
>> + [I915_SAMPLE_VCS2] = VCS2,
>> + [I915_SAMPLE_VECS] = VECS,
>> +};
>> +
>> static void engines_sample(struct drm_i915_private *dev_priv)
>> {
>> struct intel_engine_cs *engine;
>> @@ -26,9 +45,16 @@ static void engines_sample(struct drm_i915_private
>> *dev_priv)
>> return;
>>
>> for_each_engine(engine, dev_priv, id) {
>> + unsigned int user_engine = engine_map[id];
>> u32 val;
>>
>> - if ((dev_priv->pmu.enable & (0x7 << (4*id))) == 0)
>> + if (WARN_ON_ONCE(id >= ARRAY_SIZE(engine_map)))
>> + continue;
>> + else
>> + user_engine = engine_map[id];
>> +
>> + if (!(dev_priv->pmu.enable &
>> + (ENGINE_SAMPLE_MASK << (ENGINE_SAMPLE_BITS * user_engine))))
>> continue;
>>
>> if (i915_seqno_passed(intel_engine_get_seqno(engine),
>> @@ -112,6 +138,11 @@ static int engine_event_init(struct perf_event
>> *event)
>> int engine = event->attr.config >> 2;
>> int sample = event->attr.config & 3;
>>
>> + if (WARN_ON_ONCE(engine >= ARRAY_SIZE(user_engine_map)))
>> + return -ENOENT;
>> + else
>> + engine = user_engine_map[engine];
>> +
>> switch (sample) {
>> case I915_SAMPLE_QUEUED:
>> case I915_SAMPLE_BUSY:
>> @@ -125,9 +156,6 @@ static int engine_event_init(struct perf_event
>> *event)
>> return -ENOENT;
>> }
>>
>> - if (engine >= I915_NUM_ENGINES)
>> - return -ENOENT;
>> -
>> if (!i915->engine[engine])
>> return -ENODEV;
>>
>> @@ -369,7 +397,13 @@ static void i915_pmu_event_read(struct perf_event
>> *event)
>> if (event->attr.config < 32) {
>> int engine = event->attr.config >> 2;
>> int sample = event->attr.config & 3;
>> - val = i915->engine[engine]->pmu_sample[sample];
>> +
>> + if (WARN_ON_ONCE(engine >= ARRAY_SIZE(user_engine_map))) {
>> + /* Do nothing */
>> + } else {
>> + engine = user_engine_map[engine];
>> + val = i915->engine[engine]->pmu_sample[sample];
>> + }
>> } else switch (event->attr.config) {
>> case I915_PMU_ACTUAL_FREQUENCY:
>> val = i915->pmu.sample[__I915_SAMPLE_FREQ_ACT];
>> --
>> 2.9.4
>>
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2017-07-26 9:04 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-07-18 14:36 [RFC 00/14] i915 PMU and engine busy stats Tvrtko Ursulin
2017-07-18 14:36 ` [RFC 01/14] RFC drm/i915: Expose a PMU interface for perf queries Tvrtko Ursulin
2017-07-19 9:53 ` Kamble, Sagar A
2017-07-20 8:55 ` Tvrtko Ursulin
2017-07-25 1:09 ` Ben Widawsky
2017-07-18 14:36 ` [RFC 02/14] drm/i915/pmu: Add VCS2 engine to the PMU uAPI Tvrtko Ursulin
2017-07-18 14:36 ` [RFC 03/14] drm/i915/pmu: Add queued samplers " Tvrtko Ursulin
2017-07-18 14:36 ` [RFC 04/14] drm/i915/pmu: Decouple uAPI engine ids Tvrtko Ursulin
2017-07-25 1:18 ` Ben Widawsky
2017-07-26 9:04 ` Tvrtko Ursulin [this message]
2017-07-18 14:36 ` [RFC 05/14] drm/i915/pmu: Helper to extract engine and sampler from PMU config Tvrtko Ursulin
2017-07-18 14:36 ` [RFC 06/14] drm/i915/pmu: Only sample enabled samplers Tvrtko Ursulin
2017-07-18 14:36 ` [RFC 07/14] drm/i915/pmu: Add fake regs Tvrtko Ursulin
2017-07-25 1:20 ` Ben Widawsky
2017-07-26 9:07 ` Tvrtko Ursulin
2017-07-18 14:36 ` [RFC 08/14] drm/i915/pmu: Expose events in sysfs Tvrtko Ursulin
2017-07-18 14:36 ` [RFC 09/14] drm/i915/pmu: Suspend sampling when GPU is idle Tvrtko Ursulin
2017-07-18 14:36 ` [RFC 10/14] drm/i915: Wrap context schedule notification Tvrtko Ursulin
2017-07-18 14:36 ` [RFC 11/14] drm/i915: Engine busy time tracking Tvrtko Ursulin
2017-07-18 15:19 ` Chris Wilson
2017-07-19 9:12 ` Tvrtko Ursulin
2017-07-19 10:46 ` Chris Wilson
2017-07-18 14:36 ` [RFC 12/14] drm/i915: Interface for controling engine stats collection Tvrtko Ursulin
2017-07-18 15:22 ` Chris Wilson
2017-07-19 9:30 ` Tvrtko Ursulin
2017-07-19 11:04 ` Chris Wilson
2017-07-20 9:07 ` Tvrtko Ursulin
2017-07-18 15:43 ` Chris Wilson
2017-07-18 18:43 ` Chris Wilson
2017-07-19 9:34 ` Tvrtko Ursulin
2017-07-25 1:28 ` Ben Widawsky
2017-07-18 14:36 ` [RFC 13/14] drm/i915: Export engine busy stats in debugfs Tvrtko Ursulin
2017-07-18 14:36 ` [RFC 14/14] drm/i915/pmu: Wire up engine busy stats to PMU Tvrtko Ursulin
2017-07-18 14:58 ` ✓ Fi.CI.BAT: success for i915 PMU and engine busy stats Patchwork
2017-07-19 12:05 ` [RFC 00/14] " Chris Wilson
2017-07-20 9:03 ` Tvrtko Ursulin
2017-07-26 10:34 ` Tvrtko Ursulin
2017-07-26 10:55 ` Chris Wilson
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=2bfe1455-693c-1828-8ccd-7fa3d7c6e187@linux.intel.com \
--to=tvrtko.ursulin@linux.intel.com \
--cc=Intel-gfx@lists.freedesktop.org \
--cc=benjamin.widawsky@intel.com \
--cc=tursulin@ursulin.net \
/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