intel-gfx.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: Matt Roper <matthew.d.roper@intel.com>
To: intel-gfx@lists.freedesktop.org
Subject: [Intel-gfx] [PATCH v4 06/18] drm/i915/xehp: Loop over all gslices for INSTDONE processing
Date: Thu, 29 Jul 2021 09:59:56 -0700	[thread overview]
Message-ID: <20210729170008.2836648-7-matthew.d.roper@intel.com> (raw)
In-Reply-To: <20210729170008.2836648-1-matthew.d.roper@intel.com>

We no longer have traditional slices on Xe_HP platforms, but the
INSTDONE registers are replicated according to gslice representation
which is similar.  We can mostly re-use the existing instdone code with
just a few modifications:

 * Create an alternate instdone loop macro that will iterate over the
   flat DSS space, but still provide the gslice/dss steering values for
   compatibility with the legacy code.

 * We should allocate INSTDONE storage space according to the maximum
   number of gslices rather than the maximum number of legacy slices to
   ensure we have enough storage space to hold all of the values.  XeHP
   design has 8 gslices, whereas older platforms never had more than 3
   slices.

Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c    | 48 +++++++++++---------
 drivers/gpu/drm/i915/gt/intel_engine_types.h | 12 ++++-
 drivers/gpu/drm/i915/gt/intel_sseu.h         |  7 +++
 drivers/gpu/drm/i915/i915_gpu_error.c        | 32 +++++++++----
 4 files changed, 66 insertions(+), 33 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index dea0e522c5c7..06733e86e88b 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1166,16 +1166,16 @@ void intel_engine_get_instdone(const struct intel_engine_cs *engine,
 	u32 mmio_base = engine->mmio_base;
 	int slice;
 	int subslice;
+	int iter;
 
 	memset(instdone, 0, sizeof(*instdone));
 
-	switch (GRAPHICS_VER(i915)) {
-	default:
+	if (GRAPHICS_VER(i915) >= 8) {
 		instdone->instdone =
 			intel_uncore_read(uncore, RING_INSTDONE(mmio_base));
 
 		if (engine->id != RCS0)
-			break;
+			return;
 
 		instdone->slice_common =
 			intel_uncore_read(uncore, GEN7_SC_INSTDONE);
@@ -1185,21 +1185,32 @@ void intel_engine_get_instdone(const struct intel_engine_cs *engine,
 			instdone->slice_common_extra[1] =
 				intel_uncore_read(uncore, GEN12_SC_INSTDONE_EXTRA2);
 		}
-		for_each_instdone_slice_subslice(i915, sseu, slice, subslice) {
-			instdone->sampler[slice][subslice] =
-				read_subslice_reg(engine, slice, subslice,
-						  GEN7_SAMPLER_INSTDONE);
-			instdone->row[slice][subslice] =
-				read_subslice_reg(engine, slice, subslice,
-						  GEN7_ROW_INSTDONE);
+
+		if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+			for_each_instdone_gslice_dss_xehp(i915, sseu, iter, slice, subslice) {
+				instdone->sampler[slice][subslice] =
+					read_subslice_reg(engine, slice, subslice,
+							  GEN7_SAMPLER_INSTDONE);
+				instdone->row[slice][subslice] =
+					read_subslice_reg(engine, slice, subslice,
+							  GEN7_ROW_INSTDONE);
+			}
+		} else {
+			for_each_instdone_slice_subslice(i915, sseu, slice, subslice) {
+				instdone->sampler[slice][subslice] =
+					read_subslice_reg(engine, slice, subslice,
+							  GEN7_SAMPLER_INSTDONE);
+				instdone->row[slice][subslice] =
+					read_subslice_reg(engine, slice, subslice,
+							  GEN7_ROW_INSTDONE);
+			}
 		}
-		break;
-	case 7:
+	} else if (GRAPHICS_VER(i915) >= 7) {
 		instdone->instdone =
 			intel_uncore_read(uncore, RING_INSTDONE(mmio_base));
 
 		if (engine->id != RCS0)
-			break;
+			return;
 
 		instdone->slice_common =
 			intel_uncore_read(uncore, GEN7_SC_INSTDONE);
@@ -1207,22 +1218,15 @@ void intel_engine_get_instdone(const struct intel_engine_cs *engine,
 			intel_uncore_read(uncore, GEN7_SAMPLER_INSTDONE);
 		instdone->row[0][0] =
 			intel_uncore_read(uncore, GEN7_ROW_INSTDONE);
-
-		break;
-	case 6:
-	case 5:
-	case 4:
+	} else if (GRAPHICS_VER(i915) >= 4) {
 		instdone->instdone =
 			intel_uncore_read(uncore, RING_INSTDONE(mmio_base));
 		if (engine->id == RCS0)
 			/* HACK: Using the wrong struct member */
 			instdone->slice_common =
 				intel_uncore_read(uncore, GEN4_INSTDONE1);
-		break;
-	case 3:
-	case 2:
+	} else {
 		instdone->instdone = intel_uncore_read(uncore, GEN2_INSTDONE);
-		break;
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index ed91bcff20eb..0b4846b01626 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -67,8 +67,8 @@ struct intel_instdone {
 	/* The following exist only in the RCS engine */
 	u32 slice_common;
 	u32 slice_common_extra[2];
-	u32 sampler[I915_MAX_SLICES][I915_MAX_SUBSLICES];
-	u32 row[I915_MAX_SLICES][I915_MAX_SUBSLICES];
+	u32 sampler[GEN_MAX_GSLICES][I915_MAX_SUBSLICES];
+	u32 row[GEN_MAX_GSLICES][I915_MAX_SUBSLICES];
 };
 
 /*
@@ -578,4 +578,12 @@ intel_engine_has_relative_mmio(const struct intel_engine_cs * const engine)
 		for_each_if((instdone_has_slice(dev_priv_, sseu_, slice_)) && \
 			    (instdone_has_subslice(dev_priv_, sseu_, slice_, \
 						    subslice_)))
+
+#define for_each_instdone_gslice_dss_xehp(dev_priv_, sseu_, iter_, gslice_, dss_) \
+	for ((iter_) = 0, (gslice_) = 0, (dss_) = 0; \
+	     (iter_) < GEN_MAX_SUBSLICES; \
+	     (iter_)++, (gslice_) = (iter_) / GEN_DSS_PER_GSLICE, \
+	     (dss_) = (iter_) % GEN_DSS_PER_GSLICE) \
+		for_each_if(intel_sseu_has_subslice((sseu_), 0, (iter_)))
+
 #endif /* __INTEL_ENGINE_TYPES_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index 1073471d1980..74487650b08f 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -26,6 +26,9 @@ struct drm_printer;
 #define GEN_DSS_PER_CSLICE	8
 #define GEN_DSS_PER_MSLICE	8
 
+#define GEN_MAX_GSLICES		(GEN_MAX_SUBSLICES / GEN_DSS_PER_GSLICE)
+#define GEN_MAX_CSLICES		(GEN_MAX_SUBSLICES / GEN_DSS_PER_CSLICE)
+
 struct sseu_dev_info {
 	u8 slice_mask;
 	u8 subslice_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICE_STRIDE];
@@ -78,6 +81,10 @@ intel_sseu_has_subslice(const struct sseu_dev_info *sseu, int slice,
 	u8 mask;
 	int ss_idx = subslice / BITS_PER_BYTE;
 
+	if (slice >= sseu->max_slices ||
+	    subslice >= sseu->max_subslices)
+		return false;
+
 	GEM_BUG_ON(ss_idx >= sseu->ss_stride);
 
 	mask = sseu->subslice_mask[slice * sseu->ss_stride + ss_idx];
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 0f08bcfbe964..8230bc3ac8a9 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -444,15 +444,29 @@ static void error_print_instdone(struct drm_i915_error_state_buf *m,
 	if (GRAPHICS_VER(m->i915) <= 6)
 		return;
 
-	for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice)
-		err_printf(m, "  SAMPLER_INSTDONE[%d][%d]: 0x%08x\n",
-			   slice, subslice,
-			   ee->instdone.sampler[slice][subslice]);
-
-	for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice)
-		err_printf(m, "  ROW_INSTDONE[%d][%d]: 0x%08x\n",
-			   slice, subslice,
-			   ee->instdone.row[slice][subslice]);
+	if (GRAPHICS_VER_FULL(m->i915) >= IP_VER(12, 50)) {
+		int iter;
+
+		for_each_instdone_gslice_dss_xehp(m->i915, sseu, iter, slice, subslice)
+			err_printf(m, "  SAMPLER_INSTDONE[%d][%d]: 0x%08x\n",
+				   slice, subslice,
+				   ee->instdone.sampler[slice][subslice]);
+
+		for_each_instdone_gslice_dss_xehp(m->i915, sseu, iter, slice, subslice)
+			err_printf(m, "  ROW_INSTDONE[%d][%d]: 0x%08x\n",
+				   slice, subslice,
+				   ee->instdone.row[slice][subslice]);
+	} else {
+		for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice)
+			err_printf(m, "  SAMPLER_INSTDONE[%d][%d]: 0x%08x\n",
+				   slice, subslice,
+				   ee->instdone.sampler[slice][subslice]);
+
+		for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice)
+			err_printf(m, "  ROW_INSTDONE[%d][%d]: 0x%08x\n",
+				   slice, subslice,
+				   ee->instdone.row[slice][subslice]);
+	}
 
 	if (GRAPHICS_VER(m->i915) < 12)
 		return;
-- 
2.25.4

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  parent reply	other threads:[~2021-07-29 17:00 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-29 16:59 [Intel-gfx] [PATCH v4 00/18] Begin enabling Xe_HP SDV and DG2 platforms Matt Roper
2021-07-29 16:59 ` [Intel-gfx] [PATCH v4 01/18] drm/i915/xehp: handle new steering options Matt Roper
2021-08-04 19:53   ` Lucas De Marchi
2021-07-29 16:59 ` [Intel-gfx] [PATCH v4 02/18] drm/i915/xehpsdv: Define steering tables Matt Roper
2021-08-04 20:13   ` Lucas De Marchi
2021-07-29 16:59 ` [Intel-gfx] [PATCH v4 03/18] drm/i915/dg2: Add forcewake table Matt Roper
2021-08-04  0:15   ` Souza, Jose
2021-07-29 16:59 ` [Intel-gfx] [PATCH v4 04/18] drm/i915/dg2: Update LNCF steering ranges Matt Roper
2021-08-04 20:16   ` Lucas De Marchi
2021-07-29 16:59 ` [Intel-gfx] [PATCH v4 05/18] drm/i915/dg2: Add SQIDI steering Matt Roper
2021-08-04 20:22   ` Lucas De Marchi
2021-08-05 15:11     ` Matt Roper
2021-07-29 16:59 ` Matt Roper [this message]
2021-07-29 16:59 ` [Intel-gfx] [PATCH v4 07/18] drm/i915/dg2: Report INSTDONE_GEOM values in error state Matt Roper
2021-07-29 16:59 ` [Intel-gfx] [PATCH v4 08/18] drm/i915/xehp: Changes to ss/eu definitions Matt Roper
2021-08-04  0:17   ` Souza, Jose
2021-07-29 16:59 ` [Intel-gfx] [PATCH v4 09/18] drm/i915/xehpsdv: Add maximum sseu limits Matt Roper
2021-08-04 20:26   ` Lucas De Marchi
2021-07-29 17:00 ` [Intel-gfx] [PATCH v4 10/18] drm/i915/xehpsdv: Add compute DSS type Matt Roper
2021-08-04 20:36   ` Lucas De Marchi
2021-08-04 21:00     ` Matt Roper
2021-07-29 17:00 ` [Intel-gfx] [PATCH v4 11/18] drm/i915/dg2: DG2 uses the same sseu limits as XeHP SDV Matt Roper
2021-07-29 17:00 ` [Intel-gfx] [PATCH v4 12/18] drm/i915/xehpsdv: Define MOCS table for " Matt Roper
2021-07-29 17:31   ` Lucas De Marchi
2021-07-30  7:16     ` Siddiqui, Ayaz A
2021-07-30 17:01       ` Matt Roper
2021-07-29 17:00 ` [Intel-gfx] [PATCH v4 13/18] drm/i915/dg2: Define MOCS table for DG2 Matt Roper
2021-07-29 17:00 ` [Intel-gfx] [PATCH v4 14/18] drm/i915/xehpsdv: factor out function to read RP_STATE_CAP Matt Roper
2021-07-29 17:00 ` [Intel-gfx] [PATCH v4 15/18] drm/i915/xehpsdv: Read correct RP_STATE_CAP register Matt Roper
2021-07-29 17:00 ` [Intel-gfx] [PATCH v4 16/18] drm/i915/dg2: Add new LRI reg offsets Matt Roper
2021-07-29 17:00 ` [Intel-gfx] [PATCH v4 17/18] drm/i915/dg2: Maintain backward-compatible nested batch behavior Matt Roper
2021-07-29 17:00 ` [Intel-gfx] [PATCH v4 18/18] drm/i915/dg2: Configure PCON in DP pre-enable path Matt Roper
2021-07-29 20:59 ` [Intel-gfx] ✗ Fi.CI.BUILD: failure for Begin enabling Xe_HP SDV and DG2 platforms (rev8) 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=20210729170008.2836648-7-matthew.d.roper@intel.com \
    --to=matthew.d.roper@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    --subject='Re: [Intel-gfx] [PATCH v4 06/18] drm/i915/xehp: Loop over all gslices for INSTDONE processing' \
    /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

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).