On 09/06/2021 07:34, Thomas Hellström wrote:
From: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
If we pipeline the PTE updates and then do the copy of those pages
within a single unpreemptible command packet, we can submit the copies
and leave them to be scheduled without having to synchronously wait
under a global lock. In order to manage migration, we need to
preallocate the page tables (and keep them pinned and available for use
at any time), causing a bottleneck for migrations as all clients must
contend on the limited resources. By inlining the ppGTT updates and
performing the blit atomically, each client only owns the PTE while in
use, and so we can reschedule individual operations however we see fit.
And most importantly, we do not need to take a global lock on the shared
vm, and wait until the operation is complete before releasing the lock
for others to claim the PTE for themselves.
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Co-developed-by: Thomas Hellström <thomas.hellstrom@xxxxxxxxxxxxxxx>
Signed-off-by: Thomas Hellström <thomas.hellstrom@xxxxxxxxxxxxxxx>
---
v2:
- Add a TODO for huge LMEM ptes (Pointed out by Matthew Auld)
- Use intel_engine_destroy_pinned_context() to properly take the pinned
context timeline off the engine list. (CI warning).
---
<snip>
+
+int
+intel_context_migrate_copy(struct intel_context *ce,
+ struct dma_fence *await,
+ struct scatterlist *src,
+ enum i915_cache_level src_cache_level,
+ bool src_is_lmem,
+ struct scatterlist *dst,
+ enum i915_cache_level dst_cache_level,
+ bool dst_is_lmem,
+ struct i915_request **out)
+{
+ struct sgt_dma it_src = sg_sgt(src), it_dst = sg_sgt(dst);
+ struct i915_request *rq;
+ int err;
+
+ *out = NULL;
+
+ /* GEM_BUG_ON(ce->vm != migrate_vm); */
Should we drop this?
+
+ GEM_BUG_ON(ce->ring->size < SZ_64K);
+
+ do {
+ int len;
+
+ rq = i915_request_create(ce);
+ if (IS_ERR(rq)) {
+ err = PTR_ERR(rq);
+ goto out_ce;
+ }
+
+ if (await) {
+ err = i915_request_await_dma_fence(rq, await);
+ if (err)
+ goto out_rq;
+
+ if (rq->engine->emit_init_breadcrumb) {
+ err = rq->engine->emit_init_breadcrumb(rq);
+ if (err)
+ goto out_rq;
+ }
+
+ await = NULL;
+ }
+
+ /* The PTE updates + copy must not be interrupted. */
+ err = emit_no_arbitration(rq);
+ if (err)
+ goto out_rq;
+
+ len = emit_pte(rq, &it_src, src_cache_level, src_is_lmem, 0,
+ CHUNK_SZ);
+ if (len <= 0) {
+ err = len;
+ goto out_rq;
+ }
+
+ err = emit_pte(rq, &it_dst, dst_cache_level, dst_is_lmem,
+ CHUNK_SZ, len);
+ if (err < 0)
+ goto out_rq;
+ if (err < len) {
+ err = -EINVAL;
+ goto out_rq;
+ }
+
+ err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
+ if (err)
+ goto out_rq;
+
+ err = emit_copy(rq, len);
+
+ /* Arbitration is re-enabled between requests. */
+out_rq:
+ if (*out)
+ i915_request_put(*out);
+ *out = i915_request_get(rq);
+ i915_request_add(rq);
+ if (err || !it_src.sg || !sg_dma_len(it_src.sg))
+ break;
+
+ cond_resched();
+ } while (1);
+
+out_ce:
+ return err;
+}
+
