drm/i915/gt: Pipelined page migration

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@chris-wilson.co.uk>
Co-developed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210617063018.92802-8-thomas.hellstrom@linux.intel.com

1 files changed, 45 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.h b/drivers/gpu/drm/i915/gt/intel_migrate.h
new file mode 100644
index 0000000000000..32c61190ed735
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_migrate.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef __INTEL_MIGRATE__
+#define __INTEL_MIGRATE__
+
+#include "intel_migrate_types.h"
+
+struct dma_fence;
+struct i915_request;
+struct i915_gem_ww_ctx;
+struct intel_gt;
+struct scatterlist;
+enum i915_cache_level;
+
+int intel_migrate_init(struct intel_migrate *m, struct intel_gt *gt);
+
+struct intel_context *intel_migrate_create_context(struct intel_migrate *m);
+
+int intel_migrate_copy(struct intel_migrate *m,
+		       struct i915_gem_ww_ctx *ww,
+		       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);
+
+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);
+
+void intel_migrate_fini(struct intel_migrate *m);
+
+#endif /* __INTEL_MIGRATE__ */