diff mbox series

[v4,4/6] drm/i915/gt: Enable the CCS_FLUSH bit in the pipe control

Message ID 20230717173059.422892-5-andi.shyti@linux.intel.com (mailing list archive)
State New, archived
Headers show
Series Update AUX invalidation sequence | expand

Commit Message

Andi Shyti July 17, 2023, 5:30 p.m. UTC
Enable the CCS_FLUSH bit 13 in the control pipe for render and
compute engines in platforms starting from Meteor Lake (BSPEC
43904 and 47112).

Fixes: 972282c4cf24 ("drm/i915/gen12: Add aux table invalidate for all engines")
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Cc: Jonathan Cavitt <jonathan.cavitt@intel.com>
Cc: Nirmoy Das <nirmoy.das@intel.com>
Cc: <stable@vger.kernel.org> # v5.8+
---
 drivers/gpu/drm/i915/gt/gen8_engine_cs.c     | 10 +++++++++-
 drivers/gpu/drm/i915/gt/intel_engine_types.h |  1 +
 drivers/gpu/drm/i915/gt/intel_gpu_commands.h |  1 +
 3 files changed, 11 insertions(+), 1 deletion(-)

Comments

Andrzej Hajda July 17, 2023, 6:23 p.m. UTC | #1
On 17.07.2023 19:30, Andi Shyti wrote:
> Enable the CCS_FLUSH bit 13 in the control pipe for render and
> compute engines in platforms starting from Meteor Lake (BSPEC
> 43904 and 47112).
> 
> Fixes: 972282c4cf24 ("drm/i915/gen12: Add aux table invalidate for all engines")
> Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
> Cc: Jonathan Cavitt <jonathan.cavitt@intel.com>
> Cc: Nirmoy Das <nirmoy.das@intel.com>
> Cc: <stable@vger.kernel.org> # v5.8+


Reviewed-by: Andrzej Hajda <andrzej.hajda@intel.com>

Regards
Andrzej
> ---
>   drivers/gpu/drm/i915/gt/gen8_engine_cs.c     | 10 +++++++++-
>   drivers/gpu/drm/i915/gt/intel_engine_types.h |  1 +
>   drivers/gpu/drm/i915/gt/intel_gpu_commands.h |  1 +
>   3 files changed, 11 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
> index 3c935d6b68bf0..aa2fb9d72745a 100644
> --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
> +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
> @@ -207,7 +207,7 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
>   	 * memory traffic is quiesced prior.
>   	 */
>   	if ((mode & EMIT_INVALIDATE) && !HAS_FLAT_CCS(engine->i915))
> -		mode |= EMIT_FLUSH;
> +		mode |= EMIT_FLUSH | EMIT_CCS_FLUSH;
>   
>   	if (mode & EMIT_FLUSH) {
>   		u32 bit_group_0 = 0;
> @@ -221,6 +221,14 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
>   
>   		bit_group_0 |= PIPE_CONTROL0_HDC_PIPELINE_FLUSH;
>   
> +		/*
> +		 * When required, in MTL+ platforms we need to
> +		 * set the CCS_FLUSH bit in the pipe control
> +		 */
> +		if (mode & EMIT_CCS_FLUSH &&
> +		    GRAPHICS_VER_FULL(rq->i915) >= IP_VER(12, 70))
> +			bit_group_0 |= PIPE_CONTROL_CCS_FLUSH;
> +
>   		bit_group_1 |= PIPE_CONTROL_TILE_CACHE_FLUSH;
>   		bit_group_1 |= PIPE_CONTROL_FLUSH_L3;
>   		bit_group_1 |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
> diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
> index e99a6fa03d453..e2cae9d02bd62 100644
> --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
> +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
> @@ -514,6 +514,7 @@ struct intel_engine_cs {
>   	int		(*emit_flush)(struct i915_request *request, u32 mode);
>   #define EMIT_INVALIDATE	BIT(0)
>   #define EMIT_FLUSH	BIT(1)
> +#define EMIT_CCS_FLUSH	BIT(2) /* MTL+ */
>   #define EMIT_BARRIER	(EMIT_INVALIDATE | EMIT_FLUSH)
>   	int		(*emit_bb_start)(struct i915_request *rq,
>   					 u64 offset, u32 length,
> diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
> index 5d143e2a8db03..5df7cce23197c 100644
> --- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
> +++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
> @@ -299,6 +299,7 @@
>   #define   PIPE_CONTROL_QW_WRITE				(1<<14)
>   #define   PIPE_CONTROL_POST_SYNC_OP_MASK                (3<<14)
>   #define   PIPE_CONTROL_DEPTH_STALL			(1<<13)
> +#define   PIPE_CONTROL_CCS_FLUSH			(1<<13) /* MTL+ */
>   #define   PIPE_CONTROL_WRITE_FLUSH			(1<<12)
>   #define   PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH	(1<<12) /* gen6+ */
>   #define   PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE	(1<<11) /* MBZ on ILK */
Matt Roper July 17, 2023, 7:40 p.m. UTC | #2
On Mon, Jul 17, 2023 at 07:30:57PM +0200, Andi Shyti wrote:
> Enable the CCS_FLUSH bit 13 in the control pipe for render and
> compute engines in platforms starting from Meteor Lake (BSPEC
> 43904 and 47112).
> 
> Fixes: 972282c4cf24 ("drm/i915/gen12: Add aux table invalidate for all engines")
> Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
> Cc: Jonathan Cavitt <jonathan.cavitt@intel.com>
> Cc: Nirmoy Das <nirmoy.das@intel.com>
> Cc: <stable@vger.kernel.org> # v5.8+
> ---
>  drivers/gpu/drm/i915/gt/gen8_engine_cs.c     | 10 +++++++++-
>  drivers/gpu/drm/i915/gt/intel_engine_types.h |  1 +
>  drivers/gpu/drm/i915/gt/intel_gpu_commands.h |  1 +
>  3 files changed, 11 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
> index 3c935d6b68bf0..aa2fb9d72745a 100644
> --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
> +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
> @@ -207,7 +207,7 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
>  	 * memory traffic is quiesced prior.
>  	 */
>  	if ((mode & EMIT_INVALIDATE) && !HAS_FLAT_CCS(engine->i915))
> -		mode |= EMIT_FLUSH;
> +		mode |= EMIT_FLUSH | EMIT_CCS_FLUSH;

Do we even really need the extra EMIT_* flag?  It seems like just doing
the CCS flush on graphics 12.70 and beyond would probably be fine since
EMIT_FLUSH is only used in two places on those platforms:  an
EMIT_BARRIER in intel_engine_emit_ctx_wa (which happens during device
init, before we've had an opportunity to use CCS for anything) and the
new flush we're adding here in aux invalidation.  All other uses of
EMIT_FLUSH in the driver are specific to non-GuC execlist submission or
to the old ringbuffer-based submission on pre-gen8 platforms.

Anyway, adding the extra condition shouldn't really hurt anything
either, so up to you whether you want to drop it or not.

Reviewed-by: Matt Roper <matthew.d.roper@intel.com>

>  
>  	if (mode & EMIT_FLUSH) {
>  		u32 bit_group_0 = 0;
> @@ -221,6 +221,14 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
>  
>  		bit_group_0 |= PIPE_CONTROL0_HDC_PIPELINE_FLUSH;
>  
> +		/*
> +		 * When required, in MTL+ platforms we need to
> +		 * set the CCS_FLUSH bit in the pipe control
> +		 */
> +		if (mode & EMIT_CCS_FLUSH &&
> +		    GRAPHICS_VER_FULL(rq->i915) >= IP_VER(12, 70))
> +			bit_group_0 |= PIPE_CONTROL_CCS_FLUSH;
> +
>  		bit_group_1 |= PIPE_CONTROL_TILE_CACHE_FLUSH;
>  		bit_group_1 |= PIPE_CONTROL_FLUSH_L3;
>  		bit_group_1 |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
> diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
> index e99a6fa03d453..e2cae9d02bd62 100644
> --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
> +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
> @@ -514,6 +514,7 @@ struct intel_engine_cs {
>  	int		(*emit_flush)(struct i915_request *request, u32 mode);
>  #define EMIT_INVALIDATE	BIT(0)
>  #define EMIT_FLUSH	BIT(1)
> +#define EMIT_CCS_FLUSH	BIT(2) /* MTL+ */
>  #define EMIT_BARRIER	(EMIT_INVALIDATE | EMIT_FLUSH)
>  	int		(*emit_bb_start)(struct i915_request *rq,
>  					 u64 offset, u32 length,
> diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
> index 5d143e2a8db03..5df7cce23197c 100644
> --- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
> +++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
> @@ -299,6 +299,7 @@
>  #define   PIPE_CONTROL_QW_WRITE				(1<<14)
>  #define   PIPE_CONTROL_POST_SYNC_OP_MASK                (3<<14)
>  #define   PIPE_CONTROL_DEPTH_STALL			(1<<13)
> +#define   PIPE_CONTROL_CCS_FLUSH			(1<<13) /* MTL+ */
>  #define   PIPE_CONTROL_WRITE_FLUSH			(1<<12)
>  #define   PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH	(1<<12) /* gen6+ */
>  #define   PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE	(1<<11) /* MBZ on ILK */
> -- 
> 2.40.1
>
diff mbox series

Patch

diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
index 3c935d6b68bf0..aa2fb9d72745a 100644
--- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
@@ -207,7 +207,7 @@  int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
 	 * memory traffic is quiesced prior.
 	 */
 	if ((mode & EMIT_INVALIDATE) && !HAS_FLAT_CCS(engine->i915))
-		mode |= EMIT_FLUSH;
+		mode |= EMIT_FLUSH | EMIT_CCS_FLUSH;
 
 	if (mode & EMIT_FLUSH) {
 		u32 bit_group_0 = 0;
@@ -221,6 +221,14 @@  int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
 
 		bit_group_0 |= PIPE_CONTROL0_HDC_PIPELINE_FLUSH;
 
+		/*
+		 * When required, in MTL+ platforms we need to
+		 * set the CCS_FLUSH bit in the pipe control
+		 */
+		if (mode & EMIT_CCS_FLUSH &&
+		    GRAPHICS_VER_FULL(rq->i915) >= IP_VER(12, 70))
+			bit_group_0 |= PIPE_CONTROL_CCS_FLUSH;
+
 		bit_group_1 |= PIPE_CONTROL_TILE_CACHE_FLUSH;
 		bit_group_1 |= PIPE_CONTROL_FLUSH_L3;
 		bit_group_1 |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index e99a6fa03d453..e2cae9d02bd62 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -514,6 +514,7 @@  struct intel_engine_cs {
 	int		(*emit_flush)(struct i915_request *request, u32 mode);
 #define EMIT_INVALIDATE	BIT(0)
 #define EMIT_FLUSH	BIT(1)
+#define EMIT_CCS_FLUSH	BIT(2) /* MTL+ */
 #define EMIT_BARRIER	(EMIT_INVALIDATE | EMIT_FLUSH)
 	int		(*emit_bb_start)(struct i915_request *rq,
 					 u64 offset, u32 length,
diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index 5d143e2a8db03..5df7cce23197c 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -299,6 +299,7 @@ 
 #define   PIPE_CONTROL_QW_WRITE				(1<<14)
 #define   PIPE_CONTROL_POST_SYNC_OP_MASK                (3<<14)
 #define   PIPE_CONTROL_DEPTH_STALL			(1<<13)
+#define   PIPE_CONTROL_CCS_FLUSH			(1<<13) /* MTL+ */
 #define   PIPE_CONTROL_WRITE_FLUSH			(1<<12)
 #define   PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH	(1<<12) /* gen6+ */
 #define   PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE	(1<<11) /* MBZ on ILK */