Re: [Intel-gfx] [PATCH v5 2/9] drm/i915/gt: Optimize the migration and clear loop

[Intel]

On 3/21/22 23:44, Ramalingam C wrote:

Move the static calculations out of the loops for copy and clear.

Signed-off-by: Ramalingam C <ramalinga...@intel.com>

Reviewed-by: Thomas Hellström <thomas.hellst...@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 73199ebf0671..b656685a486d 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)
@@ -694,6 +692,7 @@ 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);

@@ -701,8 +700,11 @@ 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);

@@ -730,10 +732,6 @@ 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;