diff mbox series

[v7,3/9] drm/i915/gt: Optimize the migration and clear loop

Message ID 20220328190736.19697-4-ramalingam.c@intel.com (mailing list archive)
State New, archived
Headers show
Series drm/i915/ttm: Evict and restore of compressed object | expand

Commit Message

Ramalingam C March 28, 2022, 7:07 p.m. UTC 
Move the static calculations out of the loops for copy and clear.

Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/i915/gt/intel_migrate.c | 44 ++++++++++++-------------
 1 file changed, 21 insertions(+), 23 deletions(-)

Comments

Vivekanandan, Balasubramani March 29, 2022, 1:23 p.m. UTC | #1 
On 29.03.2022 00:37, Ramalingam C wrote:
> Move the static calculations out of the loops for copy and clear.
> 
> Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
> Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> ---
>  drivers/gpu/drm/i915/gt/intel_migrate.c | 44 ++++++++++++-------------
>  1 file changed, 21 insertions(+), 23 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.c b/drivers/gpu/drm/i915/gt/intel_migrate.c
> index 17dd372a47d1..ec9a9e7cb388 100644
> --- a/drivers/gpu/drm/i915/gt/intel_migrate.c
> +++ b/drivers/gpu/drm/i915/gt/intel_migrate.c
> @@ -526,6 +526,7 @@ intel_context_migrate_copy(struct intel_context *ce,
>  			   struct i915_request **out)
>  {
>  	struct sgt_dma it_src = sg_sgt(src), it_dst = sg_sgt(dst);
> +	u32 src_offset, dst_offset;
>  	struct i915_request *rq;
>  	int err;
>  
> @@ -534,8 +535,20 @@ intel_context_migrate_copy(struct intel_context *ce,
>  
>  	GEM_BUG_ON(ce->ring->size < SZ_64K);
>  
> +	src_offset = 0;
> +	dst_offset = CHUNK_SZ;
> +	if (HAS_64K_PAGES(ce->engine->i915)) {
> +		GEM_BUG_ON(!src_is_lmem && !dst_is_lmem);
> +
> +		src_offset = 0;
> +		dst_offset = 0;
> +		if (src_is_lmem)
> +			src_offset = CHUNK_SZ;
> +		if (dst_is_lmem)
> +			dst_offset = 2 * CHUNK_SZ;
> +	}
> +
>  	do {
> -		u32 src_offset, dst_offset;
>  		int len;
>  
>  		rq = i915_request_create(ce);
> @@ -563,19 +576,6 @@ intel_context_migrate_copy(struct intel_context *ce,
>  		if (err)
>  			goto out_rq;
>  
> -		src_offset = 0;
> -		dst_offset = CHUNK_SZ;
> -		if (HAS_64K_PAGES(ce->engine->i915)) {
> -			GEM_BUG_ON(!src_is_lmem && !dst_is_lmem);
> -
> -			src_offset = 0;
> -			dst_offset = 0;
> -			if (src_is_lmem)
> -				src_offset = CHUNK_SZ;
> -			if (dst_is_lmem)
> -				dst_offset = 2 * CHUNK_SZ;
> -		}
> -
>  		len = emit_pte(rq, &it_src, src_cache_level, src_is_lmem,
>  			       src_offset, CHUNK_SZ);
>  		if (len <= 0) {
> @@ -585,12 +585,10 @@ intel_context_migrate_copy(struct intel_context *ce,
>  
>  		err = emit_pte(rq, &it_dst, dst_cache_level, dst_is_lmem,
>  			       dst_offset, len);
> -		if (err < 0)
> -			goto out_rq;
> -		if (err < len) {
> +		if (err < len)
>  			err = -EINVAL;
> +		if (err < 0)
>  			goto out_rq;
> -		}
With this change, for the case 0 < err < len, now the code does not
reach `goto out_rq`.
Is it the expected behavior? If yes, can you please add some details
regarding this change in the commit description.

Regards,
Bala
>  
>  		err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
>  		if (err)
> @@ -691,6 +689,7 @@ intel_context_migrate_clear(struct intel_context *ce,
>  {
>  	struct sgt_dma it = sg_sgt(sg);
>  	struct i915_request *rq;
> +	u32 offset;
>  	int err;
>  
>  	GEM_BUG_ON(ce->vm != ce->engine->gt->migrate.context->vm);
> @@ -698,8 +697,11 @@ intel_context_migrate_clear(struct intel_context *ce,
>  
>  	GEM_BUG_ON(ce->ring->size < SZ_64K);
>  
> +	offset = 0;
> +	if (HAS_64K_PAGES(ce->engine->i915) && is_lmem)
> +		offset = CHUNK_SZ;
> +
>  	do {
> -		u32 offset;
>  		int len;
>  
>  		rq = i915_request_create(ce);
> @@ -727,10 +729,6 @@ intel_context_migrate_clear(struct intel_context *ce,
>  		if (err)
>  			goto out_rq;
>  
> -		offset = 0;
> -		if (HAS_64K_PAGES(ce->engine->i915) && is_lmem)
> -			offset = CHUNK_SZ;
> -
>  		len = emit_pte(rq, &it, cache_level, is_lmem, offset, CHUNK_SZ);
>  		if (len <= 0) {
>  			err = len;
> -- 
> 2.20.1
>
Ramalingam C April 5, 2022, 10:10 a.m. UTC | #2 
On 2022-03-29 at 18:53:42 +0530, Balasubramani Vivekanandan wrote:
> On 29.03.2022 00:37, Ramalingam C wrote:
> > Move the static calculations out of the loops for copy and clear.
> > 
> > Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
> > Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> > ---
> >  drivers/gpu/drm/i915/gt/intel_migrate.c | 44 ++++++++++++-------------
> >  1 file changed, 21 insertions(+), 23 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.c b/drivers/gpu/drm/i915/gt/intel_migrate.c
> > index 17dd372a47d1..ec9a9e7cb388 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_migrate.c
> > +++ b/drivers/gpu/drm/i915/gt/intel_migrate.c
> > @@ -526,6 +526,7 @@ intel_context_migrate_copy(struct intel_context *ce,
> >  			   struct i915_request **out)
> >  {
> >  	struct sgt_dma it_src = sg_sgt(src), it_dst = sg_sgt(dst);
> > +	u32 src_offset, dst_offset;
> >  	struct i915_request *rq;
> >  	int err;
> >  
> > @@ -534,8 +535,20 @@ intel_context_migrate_copy(struct intel_context *ce,
> >  
> >  	GEM_BUG_ON(ce->ring->size < SZ_64K);
> >  
> > +	src_offset = 0;
> > +	dst_offset = CHUNK_SZ;
> > +	if (HAS_64K_PAGES(ce->engine->i915)) {
> > +		GEM_BUG_ON(!src_is_lmem && !dst_is_lmem);
> > +
> > +		src_offset = 0;
> > +		dst_offset = 0;
> > +		if (src_is_lmem)
> > +			src_offset = CHUNK_SZ;
> > +		if (dst_is_lmem)
> > +			dst_offset = 2 * CHUNK_SZ;
> > +	}
> > +
> >  	do {
> > -		u32 src_offset, dst_offset;
> >  		int len;
> >  
> >  		rq = i915_request_create(ce);
> > @@ -563,19 +576,6 @@ intel_context_migrate_copy(struct intel_context *ce,
> >  		if (err)
> >  			goto out_rq;
> >  
> > -		src_offset = 0;
> > -		dst_offset = CHUNK_SZ;
> > -		if (HAS_64K_PAGES(ce->engine->i915)) {
> > -			GEM_BUG_ON(!src_is_lmem && !dst_is_lmem);
> > -
> > -			src_offset = 0;
> > -			dst_offset = 0;
> > -			if (src_is_lmem)
> > -				src_offset = CHUNK_SZ;
> > -			if (dst_is_lmem)
> > -				dst_offset = 2 * CHUNK_SZ;
> > -		}
> > -
> >  		len = emit_pte(rq, &it_src, src_cache_level, src_is_lmem,
> >  			       src_offset, CHUNK_SZ);
> >  		if (len <= 0) {
> > @@ -585,12 +585,10 @@ intel_context_migrate_copy(struct intel_context *ce,
> >  
> >  		err = emit_pte(rq, &it_dst, dst_cache_level, dst_is_lmem,
> >  			       dst_offset, len);
> > -		if (err < 0)
> > -			goto out_rq;
> > -		if (err < len) {
> > +		if (err < len)
> >  			err = -EINVAL;
> > +		if (err < 0)
> >  			goto out_rq;
> > -		}
> With this change, for the case 0 < err < len, now the code does not
> reach `goto out_rq`.

With this change, flow will land into out_rq for all err < len.
But just now i am noticing we are overwriding all error code with
-EINVAL. I will fix that.

Ram.
> Is it the expected behavior? If yes, can you please add some details
> regarding this change in the commit description.
> 
> Regards,
> Bala
> >  
> >  		err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
> >  		if (err)
> > @@ -691,6 +689,7 @@ intel_context_migrate_clear(struct intel_context *ce,
> >  {
> >  	struct sgt_dma it = sg_sgt(sg);
> >  	struct i915_request *rq;
> > +	u32 offset;
> >  	int err;
> >  
> >  	GEM_BUG_ON(ce->vm != ce->engine->gt->migrate.context->vm);
> > @@ -698,8 +697,11 @@ intel_context_migrate_clear(struct intel_context *ce,
> >  
> >  	GEM_BUG_ON(ce->ring->size < SZ_64K);
> >  
> > +	offset = 0;
> > +	if (HAS_64K_PAGES(ce->engine->i915) && is_lmem)
> > +		offset = CHUNK_SZ;
> > +
> >  	do {
> > -		u32 offset;
> >  		int len;
> >  
> >  		rq = i915_request_create(ce);
> > @@ -727,10 +729,6 @@ intel_context_migrate_clear(struct intel_context *ce,
> >  		if (err)
> >  			goto out_rq;
> >  
> > -		offset = 0;
> > -		if (HAS_64K_PAGES(ce->engine->i915) && is_lmem)
> > -			offset = CHUNK_SZ;
> > -
> >  		len = emit_pte(rq, &it, cache_level, is_lmem, offset, CHUNK_SZ);
> >  		if (len <= 0) {
> >  			err = len;
> > -- 
> > 2.20.1
> >
diff mbox series

Patch

diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.c b/drivers/gpu/drm/i915/gt/intel_migrate.c
index 17dd372a47d1..ec9a9e7cb388 100644
--- a/drivers/gpu/drm/i915/gt/intel_migrate.c
+++ b/drivers/gpu/drm/i915/gt/intel_migrate.c
@@ -526,6 +526,7 @@  intel_context_migrate_copy(struct intel_context *ce,
 			   struct i915_request **out)
 {
 	struct sgt_dma it_src = sg_sgt(src), it_dst = sg_sgt(dst);
+	u32 src_offset, dst_offset;
 	struct i915_request *rq;
 	int err;
 
@@ -534,8 +535,20 @@  intel_context_migrate_copy(struct intel_context *ce,
 
 	GEM_BUG_ON(ce->ring->size < SZ_64K);
 
+	src_offset = 0;
+	dst_offset = CHUNK_SZ;
+	if (HAS_64K_PAGES(ce->engine->i915)) {
+		GEM_BUG_ON(!src_is_lmem && !dst_is_lmem);
+
+		src_offset = 0;
+		dst_offset = 0;
+		if (src_is_lmem)
+			src_offset = CHUNK_SZ;
+		if (dst_is_lmem)
+			dst_offset = 2 * CHUNK_SZ;
+	}
+
 	do {
-		u32 src_offset, dst_offset;
 		int len;
 
 		rq = i915_request_create(ce);
@@ -563,19 +576,6 @@  intel_context_migrate_copy(struct intel_context *ce,
 		if (err)
 			goto out_rq;
 
-		src_offset = 0;
-		dst_offset = CHUNK_SZ;
-		if (HAS_64K_PAGES(ce->engine->i915)) {
-			GEM_BUG_ON(!src_is_lmem && !dst_is_lmem);
-
-			src_offset = 0;
-			dst_offset = 0;
-			if (src_is_lmem)
-				src_offset = CHUNK_SZ;
-			if (dst_is_lmem)
-				dst_offset = 2 * CHUNK_SZ;
-		}
-
 		len = emit_pte(rq, &it_src, src_cache_level, src_is_lmem,
 			       src_offset, CHUNK_SZ);
 		if (len <= 0) {
@@ -585,12 +585,10 @@  intel_context_migrate_copy(struct intel_context *ce,
 
 		err = emit_pte(rq, &it_dst, dst_cache_level, dst_is_lmem,
 			       dst_offset, len);
-		if (err < 0)
-			goto out_rq;
-		if (err < len) {
+		if (err < len)
 			err = -EINVAL;
+		if (err < 0)
 			goto out_rq;
-		}
 
 		err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
 		if (err)
@@ -691,6 +689,7 @@  intel_context_migrate_clear(struct intel_context *ce,
 {
 	struct sgt_dma it = sg_sgt(sg);
 	struct i915_request *rq;
+	u32 offset;
 	int err;
 
 	GEM_BUG_ON(ce->vm != ce->engine->gt->migrate.context->vm);
@@ -698,8 +697,11 @@  intel_context_migrate_clear(struct intel_context *ce,
 
 	GEM_BUG_ON(ce->ring->size < SZ_64K);
 
+	offset = 0;
+	if (HAS_64K_PAGES(ce->engine->i915) && is_lmem)
+		offset = CHUNK_SZ;
+
 	do {
-		u32 offset;
 		int len;
 
 		rq = i915_request_create(ce);
@@ -727,10 +729,6 @@  intel_context_migrate_clear(struct intel_context *ce,
 		if (err)
 			goto out_rq;
 
-		offset = 0;
-		if (HAS_64K_PAGES(ce->engine->i915) && is_lmem)
-			offset = CHUNK_SZ;
-
 		len = emit_pte(rq, &it, cache_level, is_lmem, offset, CHUNK_SZ);
 		if (len <= 0) {
 			err = len;