All of lore.kernel.org
 help / color / mirror / Atom feed
From: Lucas De Marchi <lucas.demarchi@intel.com>
To: intel-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>,
	Caz Yokoyama <caz.yokoyama@intel.com>
Subject: [PATCH 1/4] drm/i915/gen12: Add recommended hardware tuning value
Date: Wed, 24 Mar 2021 13:04:59 -0700	[thread overview]
Message-ID: <20210324200502.1731265-2-lucas.demarchi@intel.com> (raw)
In-Reply-To: <20210324200502.1731265-1-lucas.demarchi@intel.com>

From: Caz Yokoyama <caz.yokoyama@intel.com>

Follow Bspec 31870 to set recommended tuning values for certain GT
register.  These values aren't workarounds per-se, but it's best to
handle them in the same general area of the driver, especially since
there may be real workarounds that update other bits of the same
registers.

At the moment the only value we need to worry about is the
TDS_TIMER setting in FF_MODE2.  This setting was previously
described as "Wa_1604555607" on some platforms, but the spec
tells us that we should continue to program this on all current
gen12 platforms, even those that do not have that WA.

Bspec: 31870

v2: Rephrase some comments to make them clearer (Matt)

Cc: Clinton Taylor <clinton.a.taylor@intel.com>
Signed-off-by: Caz Yokoyama <caz.yokoyama@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 48 ++++++++++++++++-----
 1 file changed, 37 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 3b4a7da60f0b..2e367f95b989 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -646,9 +646,38 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN11_DIS_PICK_2ND_EU);
 }
 
+/*
+ * These settings aren't actually workarounds, but general tuning settings that
+ * need to be programmed on several platforms.
+ */
+static void gen12_ctx_gt_tuning_init(struct intel_engine_cs *engine,
+				     struct i915_wa_list *wal)
+{
+	/*
+	 * Although some platforms refer to it as Wa_1604555607, we need to
+	 * program it even on those that don't explicitly list that
+	 * workaround.
+	 *
+	 * Note that the programming of this register is further modified
+	 * according to the FF_MODE2 guidance given by Wa_1608008084:gen12.
+	 * Wa_1608008084 tells us the FF_MODE2 register will return the wrong
+	 * value when read. The default value for this register is zero for all
+	 * fields and there are no bit masks. So instead of doing a RMW we
+	 * should just write TDS timer value. For the same reason read
+	 * verification is ignored.
+	 */
+	wa_add(wal,
+	       FF_MODE2,
+	       FF_MODE2_TDS_TIMER_MASK,
+	       FF_MODE2_TDS_TIMER_128,
+	       0);
+}
+
 static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine,
 				       struct i915_wa_list *wal)
 {
+	gen12_ctx_gt_tuning_init(engine, wal);
+
 	/*
 	 * Wa_1409142259:tgl
 	 * Wa_1409347922:tgl
@@ -675,19 +704,15 @@ static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	gen12_ctx_workarounds_init(engine, wal);
 
 	/*
-	 * Wa_1604555607:tgl,rkl
+	 * Wa_16011163337
 	 *
-	 * Note that the implementation of this workaround is further modified
-	 * according to the FF_MODE2 guidance given by Wa_1608008084:gen12.
-	 * FF_MODE2 register will return the wrong value when read. The default
-	 * value for this register is zero for all fields and there are no bit
-	 * masks. So instead of doing a RMW we should just write the GS Timer
-	 * and TDS timer values for Wa_1604555607 and Wa_16011163337.
+	 * Like in gen12_ctx_gt_tuning_init(), read verification is ignored due
+	 * to Wa_1608008084.
 	 */
 	wa_add(wal,
 	       FF_MODE2,
-	       FF_MODE2_GS_TIMER_MASK | FF_MODE2_TDS_TIMER_MASK,
-	       FF_MODE2_GS_TIMER_224  | FF_MODE2_TDS_TIMER_128,
+	       FF_MODE2_GS_TIMER_MASK,
+	       FF_MODE2_GS_TIMER_224,
 	       0);
 }
 
@@ -707,12 +732,13 @@ static void dg1_ctx_workarounds_init(struct intel_engine_cs *engine,
 	/*
 	 * Wa_16011163337
 	 *
-	 * Like in tgl_ctx_workarounds_init(), read verification is ignored due
+	 * Like in gen12_ctx_gt_tuning_init(), read verification is ignored due
 	 * to Wa_1608008084.
 	 */
 	wa_add(wal,
 	       FF_MODE2,
-	       FF_MODE2_GS_TIMER_MASK, FF_MODE2_GS_TIMER_224, 0);
+	       FF_MODE2_GS_TIMER_MASK,
+	       FF_MODE2_GS_TIMER_224, 0);
 }
 
 static void
-- 
2.31.0

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

WARNING: multiple messages have this Message-ID (diff)
From: Lucas De Marchi <lucas.demarchi@intel.com>
To: intel-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Subject: [Intel-gfx] [PATCH 1/4] drm/i915/gen12: Add recommended hardware tuning value
Date: Wed, 24 Mar 2021 13:04:59 -0700	[thread overview]
Message-ID: <20210324200502.1731265-2-lucas.demarchi@intel.com> (raw)
In-Reply-To: <20210324200502.1731265-1-lucas.demarchi@intel.com>

From: Caz Yokoyama <caz.yokoyama@intel.com>

Follow Bspec 31870 to set recommended tuning values for certain GT
register.  These values aren't workarounds per-se, but it's best to
handle them in the same general area of the driver, especially since
there may be real workarounds that update other bits of the same
registers.

At the moment the only value we need to worry about is the
TDS_TIMER setting in FF_MODE2.  This setting was previously
described as "Wa_1604555607" on some platforms, but the spec
tells us that we should continue to program this on all current
gen12 platforms, even those that do not have that WA.

Bspec: 31870

v2: Rephrase some comments to make them clearer (Matt)

Cc: Clinton Taylor <clinton.a.taylor@intel.com>
Signed-off-by: Caz Yokoyama <caz.yokoyama@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 48 ++++++++++++++++-----
 1 file changed, 37 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 3b4a7da60f0b..2e367f95b989 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -646,9 +646,38 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN11_DIS_PICK_2ND_EU);
 }
 
+/*
+ * These settings aren't actually workarounds, but general tuning settings that
+ * need to be programmed on several platforms.
+ */
+static void gen12_ctx_gt_tuning_init(struct intel_engine_cs *engine,
+				     struct i915_wa_list *wal)
+{
+	/*
+	 * Although some platforms refer to it as Wa_1604555607, we need to
+	 * program it even on those that don't explicitly list that
+	 * workaround.
+	 *
+	 * Note that the programming of this register is further modified
+	 * according to the FF_MODE2 guidance given by Wa_1608008084:gen12.
+	 * Wa_1608008084 tells us the FF_MODE2 register will return the wrong
+	 * value when read. The default value for this register is zero for all
+	 * fields and there are no bit masks. So instead of doing a RMW we
+	 * should just write TDS timer value. For the same reason read
+	 * verification is ignored.
+	 */
+	wa_add(wal,
+	       FF_MODE2,
+	       FF_MODE2_TDS_TIMER_MASK,
+	       FF_MODE2_TDS_TIMER_128,
+	       0);
+}
+
 static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine,
 				       struct i915_wa_list *wal)
 {
+	gen12_ctx_gt_tuning_init(engine, wal);
+
 	/*
 	 * Wa_1409142259:tgl
 	 * Wa_1409347922:tgl
@@ -675,19 +704,15 @@ static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
 	gen12_ctx_workarounds_init(engine, wal);
 
 	/*
-	 * Wa_1604555607:tgl,rkl
+	 * Wa_16011163337
 	 *
-	 * Note that the implementation of this workaround is further modified
-	 * according to the FF_MODE2 guidance given by Wa_1608008084:gen12.
-	 * FF_MODE2 register will return the wrong value when read. The default
-	 * value for this register is zero for all fields and there are no bit
-	 * masks. So instead of doing a RMW we should just write the GS Timer
-	 * and TDS timer values for Wa_1604555607 and Wa_16011163337.
+	 * Like in gen12_ctx_gt_tuning_init(), read verification is ignored due
+	 * to Wa_1608008084.
 	 */
 	wa_add(wal,
 	       FF_MODE2,
-	       FF_MODE2_GS_TIMER_MASK | FF_MODE2_TDS_TIMER_MASK,
-	       FF_MODE2_GS_TIMER_224  | FF_MODE2_TDS_TIMER_128,
+	       FF_MODE2_GS_TIMER_MASK,
+	       FF_MODE2_GS_TIMER_224,
 	       0);
 }
 
@@ -707,12 +732,13 @@ static void dg1_ctx_workarounds_init(struct intel_engine_cs *engine,
 	/*
 	 * Wa_16011163337
 	 *
-	 * Like in tgl_ctx_workarounds_init(), read verification is ignored due
+	 * Like in gen12_ctx_gt_tuning_init(), read verification is ignored due
 	 * to Wa_1608008084.
 	 */
 	wa_add(wal,
 	       FF_MODE2,
-	       FF_MODE2_GS_TIMER_MASK, FF_MODE2_GS_TIMER_224, 0);
+	       FF_MODE2_GS_TIMER_MASK,
+	       FF_MODE2_GS_TIMER_224, 0);
 }
 
 static void
-- 
2.31.0

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

  reply	other threads:[~2021-03-24 20:05 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-24 20:04 [PATCH 0/4] drm/i915: missing workarounds and refactors Lucas De Marchi
2021-03-24 20:04 ` [Intel-gfx] " Lucas De Marchi
2021-03-24 20:04 ` Lucas De Marchi [this message]
2021-03-24 20:04   ` [Intel-gfx] [PATCH 1/4] drm/i915/gen12: Add recommended hardware tuning value Lucas De Marchi
2021-03-24 20:05 ` [PATCH 2/4] drm/i915/icl: add Wa_22010271021 for all gen11 Lucas De Marchi
2021-03-24 20:05   ` [Intel-gfx] " Lucas De Marchi
2021-03-24 20:05 ` [PATCH 3/4] drm/i915: Move Wa_16011163337 to gen12_ctx_workarounds_init() Lucas De Marchi
2021-03-24 20:05   ` [Intel-gfx] " Lucas De Marchi
2021-03-24 20:05 ` [PATCH 4/4] drm/i915: Add Wa_14011060649 Lucas De Marchi
2021-03-24 20:05   ` [Intel-gfx] " Lucas De Marchi
2021-03-25 16:28 ` [Intel-gfx] ✗ Fi.CI.DOCS: warning for drm/i915: missing workarounds and refactors Patchwork
2021-03-25 16:54 ` [Intel-gfx] ✗ Fi.CI.BAT: failure " Patchwork
2021-04-08 18:29 ` [Intel-gfx] ✗ Fi.CI.DOCS: warning for drm/i915: missing workarounds and refactors (rev2) Patchwork
2021-04-08 18:50 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2021-04-08 19:53 ` [Intel-gfx] ✓ Fi.CI.IGT: " 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=20210324200502.1731265-2-lucas.demarchi@intel.com \
    --to=lucas.demarchi@intel.com \
    --cc=caz.yokoyama@intel.com \
    --cc=daniel.vetter@ffwll.ch \
    --cc=dri-devel@lists.freedesktop.org \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.