From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
To: intel-gfx@lists.freedesktop.org
Subject: [Intel-gfx] [PATCH 06/19] drm/i915/perf: Use helpers to process reports w.r.t. OA buffer size
Date: Tue, 23 Aug 2022 20:41:42 +0000 [thread overview]
Message-ID: <20220823204155.8178-7-umesh.nerlige.ramappa@intel.com> (raw)
In-Reply-To: <20220823204155.8178-1-umesh.nerlige.ramappa@intel.com>
DG2 has a new feature to supports OA buffer sizes up to 128Mb by
toggling a bit in OA_DEBUG. This would eventually be a user configurable
parameter. Use OA buffer vma size in all calculations with some helpers.
v2: Let compiler decide inline (Jani)
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
---
drivers/gpu/drm/i915/i915_perf.c | 46 +++++++++++++++++++++-----------
1 file changed, 31 insertions(+), 15 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 6fc4f0d8fc5a..bbf1c574f393 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -385,6 +385,21 @@ static struct ctl_table_header *sysctl_header;
static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer);
+static u32 _oa_taken(struct i915_perf_stream * stream, u32 tail, u32 head)
+{
+ u32 size = stream->oa_buffer.vma->size;
+
+ return tail >= head ? tail - head : size - (head - tail);
+}
+
+static u32 _rewind_tail(struct i915_perf_stream * stream, u32 relative_hw_tail,
+ u32 rewind_delta)
+{
+ return rewind_delta > relative_hw_tail ?
+ stream->oa_buffer.vma->size - (rewind_delta - relative_hw_tail) :
+ relative_hw_tail - rewind_delta;
+}
+
void i915_oa_config_release(struct kref *ref)
{
struct i915_oa_config *oa_config =
@@ -487,12 +502,14 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
* sizes need not be integral multiples or 64 or powers of 2.
* Compute potentially partially landed report in the OA buffer
*/
- partial_report_size = OA_TAKEN(hw_tail, stream->oa_buffer.tail);
+ partial_report_size =
+ _oa_taken(stream, hw_tail, stream->oa_buffer.tail);
partial_report_size %= report_size;
/* Subtract partial amount off the tail */
- hw_tail = gtt_offset + ((hw_tail - partial_report_size) &
- (stream->oa_buffer.vma->size - 1));
+ hw_tail = gtt_offset + _rewind_tail(stream,
+ hw_tail - gtt_offset,
+ partial_report_size);
now = ktime_get_mono_fast_ns();
@@ -527,16 +544,16 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
* memory in the order they were written to.
* If not : (╯°□°)╯︵ ┻━┻
*/
- while (OA_TAKEN(tail, aged_tail) >= report_size) {
+ while (_oa_taken(stream, tail, aged_tail) >= report_size) {
u32 *report32 = (void *)(stream->oa_buffer.vaddr + tail);
if (report32[0] != 0 || report32[1] != 0)
break;
- tail = (tail - report_size) & (OA_BUFFER_SIZE - 1);
+ tail = _rewind_tail(stream, tail, report_size);
}
- if (OA_TAKEN(hw_tail, tail) > report_size &&
+ if (_oa_taken(stream, hw_tail, tail) > report_size &&
__ratelimit(&stream->perf->tail_pointer_race))
DRM_NOTE("unlanded report(s) head=0x%x "
"tail=0x%x hw_tail=0x%x\n",
@@ -547,8 +564,9 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
stream->oa_buffer.aging_timestamp = now;
}
- pollin = OA_TAKEN(stream->oa_buffer.tail - gtt_offset,
- stream->oa_buffer.head - gtt_offset) >= report_size;
+ pollin = _oa_taken(stream,
+ stream->oa_buffer.tail,
+ stream->oa_buffer.head) >= report_size;
spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags);
@@ -679,11 +697,9 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
int report_size = stream->oa_buffer.format_size;
u8 *oa_buf_base = stream->oa_buffer.vaddr;
u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
- u32 mask = (OA_BUFFER_SIZE - 1);
size_t start_offset = *offset;
unsigned long flags;
- u32 head, tail;
- u32 taken;
+ u32 head, tail, size;
int ret = 0;
if (drm_WARN_ON(&uncore->i915->drm, !stream->enabled))
@@ -693,6 +709,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
head = stream->oa_buffer.head;
tail = stream->oa_buffer.tail;
+ size = stream->oa_buffer.vma->size;
spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags);
@@ -711,16 +728,15 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
* all a power of two).
*/
if (drm_WARN_ONCE(&uncore->i915->drm,
- head > stream->oa_buffer.vma->size ||
- tail > stream->oa_buffer.vma->size,
+ head > size || tail > size,
"Inconsistent OA buffer pointers: head = %u, tail = %u\n",
head, tail))
return -EIO;
for (/* none */;
- (taken = OA_TAKEN(tail, head));
- head = (head + report_size) & mask) {
+ _oa_taken(stream, tail, head);
+ head = (head + report_size) % size) {
u8 *report = oa_buf_base + head;
u32 *report32 = (void *)report;
u32 ctx_id;
--
2.25.1
next prev parent reply other threads:[~2022-08-23 20:42 UTC|newest]
Thread overview: 84+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-08-23 20:41 [Intel-gfx] [PATCH 00/19] Add DG2 OA support Umesh Nerlige Ramappa
2022-08-23 20:41 ` [Intel-gfx] [PATCH 01/19] drm/i915/perf: Fix OA filtering logic for GuC mode Umesh Nerlige Ramappa
2022-09-06 14:33 ` Lionel Landwerlin
2022-09-06 17:39 ` Umesh Nerlige Ramappa
2022-09-06 18:39 ` Lionel Landwerlin
2022-09-14 22:26 ` Umesh Nerlige Ramappa
2022-09-14 23:13 ` Umesh Nerlige Ramappa
2022-09-15 22:49 ` Umesh Nerlige Ramappa
2022-09-20 3:22 ` Dixit, Ashutosh
2022-09-22 3:51 ` Dixit, Ashutosh
2022-09-22 11:05 ` Lionel Landwerlin
2022-09-09 23:47 ` Dixit, Ashutosh
2022-09-13 3:08 ` Dixit, Ashutosh
2022-09-14 23:37 ` Umesh Nerlige Ramappa
2022-09-14 23:36 ` Umesh Nerlige Ramappa
2022-09-22 3:44 ` Dixit, Ashutosh
2022-09-22 3:49 ` Dixit, Ashutosh
2022-08-23 20:41 ` [Intel-gfx] [PATCH 02/19] drm/i915/perf: Add OA formats for DG2 Umesh Nerlige Ramappa
2022-09-06 19:35 ` Lionel Landwerlin
2022-09-06 19:46 ` Umesh Nerlige Ramappa
2022-09-06 19:59 ` Lionel Landwerlin
2022-09-13 15:40 ` Dixit, Ashutosh
2022-09-14 20:54 ` Umesh Nerlige Ramappa
2022-09-14 21:16 ` Dixit, Ashutosh
2022-08-23 20:41 ` [Intel-gfx] [PATCH 03/19] drm/i915/perf: Fix noa wait predication " Umesh Nerlige Ramappa
2022-09-20 0:35 ` Dixit, Ashutosh
2022-08-23 20:41 ` [Intel-gfx] [PATCH 04/19] drm/i915/perf: Determine gen12 oa ctx offset at runtime Umesh Nerlige Ramappa
2022-09-06 19:48 ` Lionel Landwerlin
2022-09-06 20:35 ` Umesh Nerlige Ramappa
2022-09-08 18:32 ` Lionel Landwerlin
2022-09-08 23:04 ` Umesh Nerlige Ramappa
2022-08-23 20:41 ` [Intel-gfx] [PATCH 05/19] drm/i915/perf: Enable commands per clock reporting in OA Umesh Nerlige Ramappa
2022-09-06 19:51 ` Lionel Landwerlin
2022-09-14 0:19 ` Dixit, Ashutosh
2022-09-15 0:04 ` Umesh Nerlige Ramappa
2022-08-23 20:41 ` Umesh Nerlige Ramappa [this message]
2022-09-14 16:04 ` [Intel-gfx] [PATCH 06/19] drm/i915/perf: Use helpers to process reports w.r.t. OA buffer size Dixit, Ashutosh
2022-09-14 18:19 ` Umesh Nerlige Ramappa
2022-09-14 19:07 ` Dixit, Ashutosh
2022-08-23 20:41 ` [Intel-gfx] [PATCH 07/19] drm/i915/perf: Simply use stream->ctx Umesh Nerlige Ramappa
2022-09-06 19:52 ` Lionel Landwerlin
2022-08-23 20:41 ` [Intel-gfx] [PATCH 08/19] drm/i915/perf: Move gt-specific data from i915->perf to gt->perf Umesh Nerlige Ramappa
2022-09-06 19:54 ` Lionel Landwerlin
2022-09-14 18:20 ` Dixit, Ashutosh
2022-08-23 20:41 ` [Intel-gfx] [PATCH 09/19] drm/i915/perf: Replace gt->perf.lock with stream->lock for file ops Umesh Nerlige Ramappa
2022-09-14 19:04 ` Dixit, Ashutosh
2022-08-23 20:41 ` [Intel-gfx] [PATCH 10/19] drm/i915/perf: Use gt-specific ggtt for OA and noa-wait buffers Umesh Nerlige Ramappa
2022-09-06 19:56 ` Lionel Landwerlin
2022-09-06 20:28 ` Umesh Nerlige Ramappa
2022-09-06 20:31 ` Lionel Landwerlin
2022-08-23 20:41 ` [Intel-gfx] [PATCH 11/19] drm/i915/perf: Store a pointer to oa_format in oa_buffer Umesh Nerlige Ramappa
2022-09-06 19:56 ` Lionel Landwerlin
2022-09-14 20:43 ` Dixit, Ashutosh
2022-08-23 20:41 ` [Intel-gfx] [PATCH 12/19] drm/i915/perf: Parse 64bit report header formats correctly Umesh Nerlige Ramappa
2022-09-16 0:47 ` Dixit, Ashutosh
2022-08-23 20:41 ` [Intel-gfx] [PATCH 13/19] drm/i915/perf: Add Wa_16010703925:dg2 Umesh Nerlige Ramappa
2022-09-16 1:08 ` Dixit, Ashutosh
2022-08-23 20:41 ` [Intel-gfx] [PATCH 14/19] drm/i915/perf: Add Wa_1608133521:dg2 Umesh Nerlige Ramappa
2022-08-29 14:04 ` Jani Nikula
2022-09-16 1:21 ` Dixit, Ashutosh
2022-09-16 18:19 ` Umesh Nerlige Ramappa
2022-08-23 20:41 ` [Intel-gfx] [PATCH 15/19] drm/i915/perf: Add Wa_1508761755:dg2 Umesh Nerlige Ramappa
2022-09-16 1:34 ` Dixit, Ashutosh
2022-08-23 20:41 ` [Intel-gfx] [PATCH 16/19] drm/i915/perf: Apply Wa_18013179988 Umesh Nerlige Ramappa
2022-09-16 5:16 ` Dixit, Ashutosh
2022-09-16 15:22 ` Dixit, Ashutosh
2022-09-16 19:04 ` Umesh Nerlige Ramappa
2022-09-16 18:56 ` Umesh Nerlige Ramappa
2022-09-16 19:57 ` Dixit, Ashutosh
2022-09-16 20:25 ` Umesh Nerlige Ramappa
2022-09-16 21:00 ` Dixit, Ashutosh
2022-09-19 21:21 ` Umesh Nerlige Ramappa
2022-09-20 1:24 ` Dixit, Ashutosh
2022-08-23 20:41 ` [Intel-gfx] [PATCH 17/19] drm/i915/perf: Save/restore EU flex counters across reset Umesh Nerlige Ramappa
2022-09-16 5:40 ` Dixit, Ashutosh
2022-08-23 20:41 ` [Intel-gfx] [PATCH 18/19] drm/i915/guc: Support OA when Wa_16011777198 is enabled Umesh Nerlige Ramappa
2022-09-16 21:41 ` Dixit, Ashutosh
2022-09-16 21:48 ` Umesh Nerlige Ramappa
2022-08-23 20:41 ` [Intel-gfx] [PATCH 19/19] drm/i915/perf: Enable OA for DG2 Umesh Nerlige Ramappa
2022-08-23 21:11 ` [Intel-gfx] [PATCH 02/19] drm/i915/perf: Add OA formats " Umesh Nerlige Ramappa
2022-08-23 21:12 ` [Intel-gfx] [PATCH 19/19] drm/i915/perf: Enable OA " Umesh Nerlige Ramappa
2022-08-23 22:07 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Add DG2 OA support (rev2) Patchwork
2022-08-23 22:07 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
-- strict thread matches above, loose matches on Subject: below --
2022-08-23 0:03 [Intel-gfx] [PATCH 00/19] Add DG2 OA support Umesh Nerlige Ramappa
2022-08-23 0:03 ` [Intel-gfx] [PATCH 06/19] drm/i915/perf: Use helpers to process reports w.r.t. OA buffer size Umesh Nerlige Ramappa
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=20220823204155.8178-7-umesh.nerlige.ramappa@intel.com \
--to=umesh.nerlige.ramappa@intel.com \
--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