public inbox for intel-gfx@lists.freedesktop.org
 help / color / mirror / Atom feed
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
To: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: intel-gfx@lists.freedesktop.org
Subject: Re: [Intel-gfx] [PATCH 01/19] drm/i915/perf: Fix OA filtering logic for GuC mode
Date: Tue, 6 Sep 2022 10:39:29 -0700	[thread overview]
Message-ID: <YxeF0b6ohtFcDXf6@unerlige-ril> (raw)
In-Reply-To: <9afc705a-87a1-c51e-b223-e32accbcd2fe@intel.com>

On Tue, Sep 06, 2022 at 05:33:00PM +0300, Lionel Landwerlin wrote:
>On 23/08/2022 23:41, Umesh Nerlige Ramappa wrote:
>>With GuC mode of submission, GuC is in control of defining the context id field
>>that is part of the OA reports. To filter reports, UMD and KMD must know what sw
>>context id was chosen by GuC. There is not interface between KMD and GuC to
>>determine this, so read the upper-dword of EXECLIST_STATUS to filter/squash OA
>>reports for the specific context.
>>
>>Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
>
>
>I assume you checked with GuC that this doesn't change as the context 
>is running?

Correct.

>
>With i915/execlist submission mode, we had to ask i915 to pin the 
>sw_id/ctx_id.
>

 From GuC perspective, the context id can change once KMD de-registers 
the context and that will not happen while the context is in use.

Thanks,
Umesh

>
>If that's not the case then filtering is broken.
>
>
>-Lionel
>
>
>>---
>>  drivers/gpu/drm/i915/gt/intel_lrc.h |   2 +
>>  drivers/gpu/drm/i915/i915_perf.c    | 141 ++++++++++++++++++++++++----
>>  2 files changed, 124 insertions(+), 19 deletions(-)
>>
>>diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h
>>index a390f0813c8b..7111bae759f3 100644
>>--- a/drivers/gpu/drm/i915/gt/intel_lrc.h
>>+++ b/drivers/gpu/drm/i915/gt/intel_lrc.h
>>@@ -110,6 +110,8 @@ enum {
>>  #define XEHP_SW_CTX_ID_WIDTH			16
>>  #define XEHP_SW_COUNTER_SHIFT			58
>>  #define XEHP_SW_COUNTER_WIDTH			6
>>+#define GEN12_GUC_SW_CTX_ID_SHIFT		39
>>+#define GEN12_GUC_SW_CTX_ID_WIDTH		16
>>  static inline void lrc_runtime_start(struct intel_context *ce)
>>  {
>>diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
>>index f3c23fe9ad9c..735244a3aedd 100644
>>--- a/drivers/gpu/drm/i915/i915_perf.c
>>+++ b/drivers/gpu/drm/i915/i915_perf.c
>>@@ -1233,6 +1233,125 @@ static struct intel_context *oa_pin_context(struct i915_perf_stream *stream)
>>  	return stream->pinned_ctx;
>>  }
>>+static int
>>+__store_reg_to_mem(struct i915_request *rq, i915_reg_t reg, u32 ggtt_offset)
>>+{
>>+	u32 *cs, cmd;
>>+
>>+	cmd = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
>>+	if (GRAPHICS_VER(rq->engine->i915) >= 8)
>>+		cmd++;
>>+
>>+	cs = intel_ring_begin(rq, 4);
>>+	if (IS_ERR(cs))
>>+		return PTR_ERR(cs);
>>+
>>+	*cs++ = cmd;
>>+	*cs++ = i915_mmio_reg_offset(reg);
>>+	*cs++ = ggtt_offset;
>>+	*cs++ = 0;
>>+
>>+	intel_ring_advance(rq, cs);
>>+
>>+	return 0;
>>+}
>>+
>>+static int
>>+__read_reg(struct intel_context *ce, i915_reg_t reg, u32 ggtt_offset)
>>+{
>>+	struct i915_request *rq;
>>+	int err;
>>+
>>+	rq = i915_request_create(ce);
>>+	if (IS_ERR(rq))
>>+		return PTR_ERR(rq);
>>+
>>+	i915_request_get(rq);
>>+
>>+	err = __store_reg_to_mem(rq, reg, ggtt_offset);
>>+
>>+	i915_request_add(rq);
>>+	if (!err && i915_request_wait(rq, 0, HZ / 2) < 0)
>>+		err = -ETIME;
>>+
>>+	i915_request_put(rq);
>>+
>>+	return err;
>>+}
>>+
>>+static int
>>+gen12_guc_sw_ctx_id(struct intel_context *ce, u32 *ctx_id)
>>+{
>>+	struct i915_vma *scratch;
>>+	u32 *val;
>>+	int err;
>>+
>>+	scratch = __vm_create_scratch_for_read_pinned(&ce->engine->gt->ggtt->vm, 4);
>>+	if (IS_ERR(scratch))
>>+		return PTR_ERR(scratch);
>>+
>>+	err = i915_vma_sync(scratch);
>>+	if (err)
>>+		goto err_scratch;
>>+
>>+	err = __read_reg(ce, RING_EXECLIST_STATUS_HI(ce->engine->mmio_base),
>>+			 i915_ggtt_offset(scratch));
>>+	if (err)
>>+		goto err_scratch;
>>+
>>+	val = i915_gem_object_pin_map_unlocked(scratch->obj, I915_MAP_WB);
>>+	if (IS_ERR(val)) {
>>+		err = PTR_ERR(val);
>>+		goto err_scratch;
>>+	}
>>+
>>+	*ctx_id = *val;
>>+	i915_gem_object_unpin_map(scratch->obj);
>>+
>>+err_scratch:
>>+	i915_vma_unpin_and_release(&scratch, 0);
>>+	return err;
>>+}
>>+
>>+/*
>>+ * For execlist mode of submission, pick an unused context id
>>+ * 0 - (NUM_CONTEXT_TAG -1) are used by other contexts
>>+ * XXX_MAX_CONTEXT_HW_ID is used by idle context
>>+ *
>>+ * For GuC mode of submission read context id from the upper dword of the
>>+ * EXECLIST_STATUS register.
>>+ */
>>+static int gen12_get_render_context_id(struct i915_perf_stream *stream)
>>+{
>>+	u32 ctx_id, mask;
>>+	int ret;
>>+
>>+	if (intel_engine_uses_guc(stream->engine)) {
>>+		ret = gen12_guc_sw_ctx_id(stream->pinned_ctx, &ctx_id);
>>+		if (ret)
>>+			return ret;
>>+
>>+		mask = ((1U << GEN12_GUC_SW_CTX_ID_WIDTH) - 1) <<
>>+			(GEN12_GUC_SW_CTX_ID_SHIFT - 32);
>>+	} else if (GRAPHICS_VER_FULL(stream->engine->i915) >= IP_VER(12, 50)) {
>>+		ctx_id = (XEHP_MAX_CONTEXT_HW_ID - 1) <<
>>+			(XEHP_SW_CTX_ID_SHIFT - 32);
>>+
>>+		mask = ((1U << XEHP_SW_CTX_ID_WIDTH) - 1) <<
>>+			(XEHP_SW_CTX_ID_SHIFT - 32);
>>+	} else {
>>+		ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) <<
>>+			 (GEN11_SW_CTX_ID_SHIFT - 32);
>>+
>>+		mask = ((1U << GEN11_SW_CTX_ID_WIDTH) - 1) <<
>>+			(GEN11_SW_CTX_ID_SHIFT - 32);
>>+	}
>>+	stream->specific_ctx_id = ctx_id & mask;
>>+	stream->specific_ctx_id_mask = mask;
>>+
>>+	return 0;
>>+}
>>+
>>  /**
>>   * oa_get_render_ctx_id - determine and hold ctx hw id
>>   * @stream: An i915-perf stream opened for OA metrics
>>@@ -1246,6 +1365,7 @@ static struct intel_context *oa_pin_context(struct i915_perf_stream *stream)
>>  static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
>>  {
>>  	struct intel_context *ce;
>>+	int ret = 0;
>>  	ce = oa_pin_context(stream);
>>  	if (IS_ERR(ce))
>>@@ -1292,24 +1412,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
>>  	case 11:
>>  	case 12:
>>-		if (GRAPHICS_VER_FULL(ce->engine->i915) >= IP_VER(12, 50)) {
>>-			stream->specific_ctx_id_mask =
>>-				((1U << XEHP_SW_CTX_ID_WIDTH) - 1) <<
>>-				(XEHP_SW_CTX_ID_SHIFT - 32);
>>-			stream->specific_ctx_id =
>>-				(XEHP_MAX_CONTEXT_HW_ID - 1) <<
>>-				(XEHP_SW_CTX_ID_SHIFT - 32);
>>-		} else {
>>-			stream->specific_ctx_id_mask =
>>-				((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
>>-			/*
>>-			 * Pick an unused context id
>>-			 * 0 - BITS_PER_LONG are used by other contexts
>>-			 * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context
>>-			 */
>>-			stream->specific_ctx_id =
>>-				(GEN12_MAX_CONTEXT_HW_ID - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
>>-		}
>>+		ret = gen12_get_render_context_id(stream);
>>  		break;
>>  	default:
>>@@ -1323,7 +1426,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
>>  		stream->specific_ctx_id,
>>  		stream->specific_ctx_id_mask);
>>-	return 0;
>>+	return ret;
>>  }
>>  /**
>
>

  reply	other threads:[~2022-09-06 17:39 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 [this message]
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 ` [Intel-gfx] [PATCH 06/19] drm/i915/perf: Use helpers to process reports w.r.t. OA buffer size Umesh Nerlige Ramappa
2022-09-14 16:04   ` 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 01/19] drm/i915/perf: Fix OA filtering logic for GuC mode 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=YxeF0b6ohtFcDXf6@unerlige-ril \
    --to=umesh.nerlige.ramappa@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=lionel.g.landwerlin@intel.com \
    /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