drm/i915/gt: Optimize the migration and clear loop

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

v2:
  Fix the loss of proper error code on emit_pte

Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Reviewed-by: Thomas Hellstrom <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220405150840.29351-4-ramalingam.c@intel.com

diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.c b/drivers/gpu/drm/i915/gt/intel_migrate.c
index e81f202..e0f1c72 100644 (file)
--- 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;
 
@@ -535,8 +536,18 @@ 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)) {
+               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);
@@ -564,17 +575,6 @@ 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)) {
-                       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) {
@@ -690,6 +690,7 @@ 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);
@@ -697,8 +698,11 @@ 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);
@@ -726,10 +730,6 @@ 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;