All of lore.kernel.org
 help / color / mirror / Atom feed
From: Matt Roper <matthew.d.roper@intel.com>
To: intel-gfx@lists.freedesktop.org
Cc: Jani Nikula <jani.nikula@intel.com>
Subject: [Intel-gfx] [PATCH v2 4/6] drm/i915: Parameterize MI_PREDICATE registers
Date: Mon, 24 Jan 2022 18:08:24 -0800	[thread overview]
Message-ID: <20220125020826.2693097-5-matthew.d.roper@intel.com> (raw)
In-Reply-To: <20220125020826.2693097-1-matthew.d.roper@intel.com>

The various MI_PREDICATE registers have per-engine instances.  Today we
only utilize the RCS0 instance of each, but that will likely change in
the future; switch to parameterized register definitions to make these
easier to work with going forward.

Of special note is MI_PREDICATE_RESULT_2; we only use it in one place in
the driver today in HSW-specific code.  It turns out that the bspec
(page 94) lists two different offsets for this register on HSW; one is
in the standard location shared by all other platforms (base + 0x3bc)
and the other is an unusual location (0x2214).  We're using the second,
non-standard offset in i915 today; that offset doesn't exist on any
other platforms (and it's not even 100% clear that it's correct for HSW)
so I've renamed the current non-standard definition to
HSW_MI_PREDICATE_RESULT_2; the new cross-platform parameterized macro
(which is still unused at the moment) uses the standard offset.

Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_engine_regs.h | 11 +++++++++++
 drivers/gpu/drm/i915/gt/intel_gt.c          |  2 +-
 drivers/gpu/drm/i915/i915_cmd_parser.c      |  4 ++--
 drivers/gpu/drm/i915/i915_perf.c            |  8 ++++----
 drivers/gpu/drm/i915/i915_reg.h             | 11 +----------
 5 files changed, 19 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_regs.h b/drivers/gpu/drm/i915/gt/intel_engine_regs.h
index daf4a241cf77..e9fec6214073 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_regs.h
@@ -142,6 +142,17 @@
 		(REG_FIELD_PREP(CMD_CCTL_WRITE_OVERRIDE_MASK, (write) << 1) | \
 		 REG_FIELD_PREP(CMD_CCTL_READ_OVERRIDE_MASK, (read) << 1))
 
+#define MI_PREDICATE_RESULT_2(base)		_MMIO((base) + 0x3bc)
+#define   LOWER_SLICE_ENABLED			(1 << 0)
+#define   LOWER_SLICE_DISABLED			(0 << 0)
+#define MI_PREDICATE_SRC0(base)			_MMIO((base) + 0x400)
+#define MI_PREDICATE_SRC0_UDW(base)		_MMIO((base) + 0x400 + 4)
+#define MI_PREDICATE_SRC1(base)			_MMIO((base) + 0x408)
+#define MI_PREDICATE_SRC1_UDW(base)		_MMIO((base) + 0x408 + 4)
+#define MI_PREDICATE_DATA(base)			_MMIO((base) + 0x410)
+#define MI_PREDICATE_RESULT(base)		_MMIO((base) + 0x418)
+#define MI_PREDICATE_RESULT_1(base)		_MMIO((base) + 0x41c)
+
 #define RING_PP_DIR_DCLV(base)			_MMIO((base) + 0x220)
 #define   PP_DIR_DCLV_2G			0xffffffff
 #define RING_PP_DIR_BASE(base)			_MMIO((base) + 0x228)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 622cdfed8a8b..3889efb3ffa4 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -209,7 +209,7 @@ int intel_gt_init_hw(struct intel_gt *gt)
 
 	if (IS_HASWELL(i915))
 		intel_uncore_write(uncore,
-				   MI_PREDICATE_RESULT_2,
+				   HSW_MI_PREDICATE_RESULT_2,
 				   IS_HSW_GT3(i915) ?
 				   LOWER_SLICE_ENABLED : LOWER_SLICE_DISABLED);
 
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 96c398051084..332b8ffb58f8 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -611,8 +611,8 @@ static const struct drm_i915_reg_descriptor gen7_render_regs[] = {
 	REG64(PS_INVOCATION_COUNT),
 	REG64(PS_DEPTH_COUNT),
 	REG64_IDX(RING_TIMESTAMP, RENDER_RING_BASE),
-	REG64(MI_PREDICATE_SRC0),
-	REG64(MI_PREDICATE_SRC1),
+	REG64_IDX(MI_PREDICATE_SRC0, RENDER_RING_BASE),
+	REG64_IDX(MI_PREDICATE_SRC1, RENDER_RING_BASE),
 	REG32(GEN7_3DPRIM_END_OFFSET),
 	REG32(GEN7_3DPRIM_START_VERTEX),
 	REG32(GEN7_3DPRIM_VERTEX_COUNT),
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 1253e396a911..547a242c5e49 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1684,7 +1684,7 @@ static int alloc_noa_wait(struct i915_perf_stream *stream)
 			stream, cs, true /* save */, CS_GPR(i),
 			INTEL_GT_SCRATCH_FIELD_PERF_CS_GPR + 8 * i, 2);
 	cs = save_restore_register(
-		stream, cs, true /* save */, MI_PREDICATE_RESULT_1,
+		stream, cs, true /* save */, MI_PREDICATE_RESULT_1(RENDER_RING_BASE),
 		INTEL_GT_SCRATCH_FIELD_PERF_PREDICATE_RESULT_1, 1);
 
 	/* First timestamp snapshot location. */
@@ -1738,7 +1738,7 @@ static int alloc_noa_wait(struct i915_perf_stream *stream)
 	 */
 	*cs++ = MI_LOAD_REGISTER_REG | (3 - 2);
 	*cs++ = i915_mmio_reg_offset(CS_GPR(JUMP_PREDICATE));
-	*cs++ = i915_mmio_reg_offset(MI_PREDICATE_RESULT_1);
+	*cs++ = i915_mmio_reg_offset(MI_PREDICATE_RESULT_1(RENDER_RING_BASE));
 
 	/* Restart from the beginning if we had timestamps roll over. */
 	*cs++ = (GRAPHICS_VER(i915) < 8 ?
@@ -1775,7 +1775,7 @@ static int alloc_noa_wait(struct i915_perf_stream *stream)
 	 */
 	*cs++ = MI_LOAD_REGISTER_REG | (3 - 2);
 	*cs++ = i915_mmio_reg_offset(CS_GPR(JUMP_PREDICATE));
-	*cs++ = i915_mmio_reg_offset(MI_PREDICATE_RESULT_1);
+	*cs++ = i915_mmio_reg_offset(MI_PREDICATE_RESULT_1(RENDER_RING_BASE));
 
 	/* Predicate the jump.  */
 	*cs++ = (GRAPHICS_VER(i915) < 8 ?
@@ -1791,7 +1791,7 @@ static int alloc_noa_wait(struct i915_perf_stream *stream)
 			stream, cs, false /* restore */, CS_GPR(i),
 			INTEL_GT_SCRATCH_FIELD_PERF_CS_GPR + 8 * i, 2);
 	cs = save_restore_register(
-		stream, cs, false /* restore */, MI_PREDICATE_RESULT_1,
+		stream, cs, false /* restore */, MI_PREDICATE_RESULT_1(RENDER_RING_BASE),
 		INTEL_GT_SCRATCH_FIELD_PERF_PREDICATE_RESULT_1, 1);
 
 	/* And return to the ring. */
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 573dea4516ef..bba9648fe7e8 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -398,16 +398,7 @@
 #define VGA_CR_INDEX_CGA 0x3d4
 #define VGA_CR_DATA_CGA 0x3d5
 
-#define MI_PREDICATE_SRC0	_MMIO(0x2400)
-#define MI_PREDICATE_SRC0_UDW	_MMIO(0x2400 + 4)
-#define MI_PREDICATE_SRC1	_MMIO(0x2408)
-#define MI_PREDICATE_SRC1_UDW	_MMIO(0x2408 + 4)
-#define MI_PREDICATE_DATA       _MMIO(0x2410)
-#define MI_PREDICATE_RESULT     _MMIO(0x2418)
-#define MI_PREDICATE_RESULT_1   _MMIO(0x241c)
-#define MI_PREDICATE_RESULT_2	_MMIO(0x2214)
-#define  LOWER_SLICE_ENABLED	(1 << 0)
-#define  LOWER_SLICE_DISABLED	(0 << 0)
+#define HSW_MI_PREDICATE_RESULT_2	_MMIO(0x2214)
 
 /*
  * Registers used only by the command parser
-- 
2.34.1


  parent reply	other threads:[~2022-01-25  2:08 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-25  2:08 [Intel-gfx] [PATCH v2 0/6] Second round of i915_reg.h splitting Matt Roper
2022-01-25  2:08 ` [Intel-gfx] [PATCH v2 1/6] drm/i915/perf: Move OA regs to their own header Matt Roper
2022-01-26 22:08   ` Lucas De Marchi
2022-01-25  2:08 ` [Intel-gfx] [PATCH v2 2/6] drm/i915/perf: Express OA register ranges with i915_range Matt Roper
2022-01-26 22:19   ` Lucas De Marchi
2022-01-27 21:28   ` Umesh Nerlige Ramappa
2022-01-25  2:08 ` [Intel-gfx] [PATCH v2 3/6] drm/i915: Parameterize R_PWR_CLK_STATE register definition Matt Roper
2022-01-26 22:19   ` Lucas De Marchi
2022-01-25  2:08 ` Matt Roper [this message]
2022-01-26 22:23   ` [Intel-gfx] [PATCH v2 4/6] drm/i915: Parameterize MI_PREDICATE registers Lucas De Marchi
2022-01-25  2:08 ` [Intel-gfx] [PATCH v2 5/6] drm/i915: Move GT registers to their own header file Matt Roper
2022-01-26 22:31   ` Lucas De Marchi
2022-01-25  2:08 ` [Intel-gfx] [PATCH v2 6/6] drm/i915: Only include i915_reg.h from .c files Matt Roper
2022-01-26 22:35   ` Lucas De Marchi
2022-01-25  2:58 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Second round of i915_reg.h splitting (rev2) Patchwork
2022-01-25  2:59 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2022-01-25  3:32 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2022-01-25  8:14 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " 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=20220125020826.2693097-5-matthew.d.roper@intel.com \
    --to=matthew.d.roper@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=jani.nikula@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 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.