drm/i915 Implement LMEM backup and restore for suspend / resume

Just evict unpinned objects to system. For pinned LMEM objects,
make a backup system object and blit the contents to that.

Backup is performed in three steps,
1: Opportunistically evict evictable objects using the gpu blitter.
2: After gt idle, evict evictable objects using the gpu blitter. This will
be modified in an upcoming patch to backup pinned objects that are not used
by the blitter itself.
3: Backup remaining pinned objects using memcpy.

Also move uC suspend to after 2) to make sure we have a functional GuC
during 2) if using GuC submission.

v2:
- Major refactor to make sure gem_exec_suspend@hang-SX subtests work, and
  suspend / resume works with a slightly modified GuC submission enabling
  patch series.

v3:
- Fix a potential use-after-free (Matthew Auld)
- Use i915_gem_object_create_shmem() instead of
  i915_gem_object_create_region (Matthew Auld)
- Minor simplifications (Matthew Auld)
- Fix up kerneldoc for i195_ttm_restore_region().
- Final lmem_suspend() call moved to i915_gem_backup_suspend from
  i915_gem_suspend_late, since the latter gets called at driver unload
  and we don't unnecessarily want to run it at that time.

v4:
- Interface change of ttm- & lmem suspend / resume functions to use
  flags rather than bools. (Matthew Auld)
- Completely drop the i915_gem_backup_suspend change (Matthew Auld)

Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210922062527.865433-5-thomas.hellstrom@linux.intel.com

1 files changed, 87 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 8b9d7d14c4bd..12b37b4c1192 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -5,6 +5,7 @@
  */
 
 #include "gem/i915_gem_pm.h"
+#include "gem/i915_gem_ttm_pm.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
 #include "gt/intel_gt_requests.h"
@@ -39,6 +40,84 @@ void i915_gem_suspend(struct drm_i915_private *i915)
 	i915_gem_drain_freed_objects(i915);
 }
 
+static int lmem_restore(struct drm_i915_private *i915, u32 flags)
+{
+	struct intel_memory_region *mr;
+	int ret = 0, id;
+
+	for_each_memory_region(mr, i915, id) {
+		if (mr->type == INTEL_MEMORY_LOCAL) {
+			ret = i915_ttm_restore_region(mr, flags);
+			if (ret)
+				break;
+		}
+	}
+
+	return ret;
+}
+
+static int lmem_suspend(struct drm_i915_private *i915, u32 flags)
+{
+	struct intel_memory_region *mr;
+	int ret = 0, id;
+
+	for_each_memory_region(mr, i915, id) {
+		if (mr->type == INTEL_MEMORY_LOCAL) {
+			ret = i915_ttm_backup_region(mr, flags);
+			if (ret)
+				break;
+		}
+	}
+
+	return ret;
+}
+
+static void lmem_recover(struct drm_i915_private *i915)
+{
+	struct intel_memory_region *mr;
+	int id;
+
+	for_each_memory_region(mr, i915, id)
+		if (mr->type == INTEL_MEMORY_LOCAL)
+			i915_ttm_recover_region(mr);
+}
+
+int i915_gem_backup_suspend(struct drm_i915_private *i915)
+{
+	int ret;
+
+	/* Opportunistically try to evict unpinned objects */
+	ret = lmem_suspend(i915, I915_TTM_BACKUP_ALLOW_GPU);
+	if (ret)
+		goto out_recover;
+
+	i915_gem_suspend(i915);
+
+	/*
+	 * More objects may have become unpinned as requests were
+	 * retired. Now try to evict again. The gt may be wedged here
+	 * in which case we automatically fall back to memcpy.
+	 */
+	ret = lmem_suspend(i915, I915_TTM_BACKUP_ALLOW_GPU);
+	if (ret)
+		goto out_recover;
+
+	/*
+	 * Remaining objects are backed up using memcpy once we've stopped
+	 * using the migrate context.
+	 */
+	ret = lmem_suspend(i915, I915_TTM_BACKUP_PINNED);
+	if (ret)
+		goto out_recover;
+
+	return 0;
+
+out_recover:
+	lmem_recover(i915);
+
+	return ret;
+}
+
 void i915_gem_suspend_late(struct drm_i915_private *i915)
 {
 	struct drm_i915_gem_object *obj;
@@ -128,12 +207,20 @@ int i915_gem_freeze_late(struct drm_i915_private *i915)
 
 void i915_gem_resume(struct drm_i915_private *i915)
 {
+	int ret;
+
 	GEM_TRACE("%s\n", dev_name(i915->drm.dev));
 
+	ret = lmem_restore(i915, 0);
+	GEM_WARN_ON(ret);
+
 	/*
 	 * As we didn't flush the kernel context before suspend, we cannot
 	 * guarantee that the context image is complete. So let's just reset
 	 * it and start again.
 	 */
 	intel_gt_resume(&i915->gt);
+
+	ret = lmem_restore(i915, I915_TTM_BACKUP_ALLOW_GPU);
+	GEM_WARN_ON(ret);
 }