drm/i915: Update error capture code to avoid using the current vma state

With asynchronous migrations, the vma state may be several migrations
ahead of the state that matches the request we're capturing.
Address that by introducing an i915_vma_snapshot structure that
can be used to snapshot relevant state at request submission.
In order to make sure we access the correct memory, the snapshots take
references on relevant sg-tables and memory regions.

Also move the capture list allocation out of the fence signaling
critical path and use the CONFIG_DRM_I915_CAPTURE_ERROR define to
avoid compiling in members and functions used for error capture
when they're not used.

Finally, Introduce lockdep annotation.

v4:
- Break out the capture allocation mode change to a separate patch.
v5:
- Fix compilation error in the !CONFIG_DRM_I915_CAPTURE_ERROR case
  (kernel test robot)
v6:
- Use #if IS_ENABLED() instead of #ifdef to match driver style.
- Move yet another change of allocation mode to the separate patch.
- Commit message rework due to patch reordering.
v7:
- Adjust for removal of region refcounting.

Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Ramalingam C <ramalingam.c@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211129202245.472043-1-thomas.hellstrom@linux.intel.com

1 files changed, 15 insertions, 5 deletions

diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 3c6e8acd1457..0ed01979491b 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -40,6 +40,7 @@
 #include "i915_scheduler.h"
 #include "i915_selftest.h"
 #include "i915_sw_fence.h"
+#include "i915_vma_snapshot.h"
 
 #include <uapi/drm/i915_drm.h>
 
@@ -48,11 +49,17 @@ struct drm_i915_gem_object;
 struct drm_printer;
 struct i915_request;
 
+#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
 struct i915_capture_list {
+	struct i915_vma_snapshot *vma_snapshot;
 	struct i915_capture_list *next;
-	struct i915_vma *vma;
 };
 
+void i915_request_free_capture_list(struct i915_capture_list *capture);
+#else
+#define i915_request_free_capture_list(_a) do {} while (0)
+#endif
+
 #define RQ_TRACE(rq, fmt, ...) do {					\
 	const struct i915_request *rq__ = (rq);				\
 	ENGINE_TRACE(rq__->engine, "fence %llx:%lld, current %d " fmt,	\
@@ -289,10 +296,12 @@ struct i915_request {
 	/** Preallocate space in the ring for the emitting the request */
 	u32 reserved_space;
 
-	/** Batch buffer related to this request if any (used for
-	 * error state dump only).
-	 */
-	struct i915_vma *batch;
+	/** Batch buffer pointer for selftest internal use. */
+	I915_SELFTEST_DECLARE(struct i915_vma *batch);
+
+	struct i915_vma_snapshot batch_snapshot;
+
+#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
 	/**
 	 * Additional buffers requested by userspace to be captured upon
 	 * a GPU hang. The vma/obj on this list are protected by their
@@ -300,6 +309,7 @@ struct i915_request {
 	 * on the active_list (of their final request).
 	 */
 	struct i915_capture_list *capture_list;
+#endif
 
 	/** Time at which this request was emitted, in jiffies. */
 	unsigned long emitted_jiffies;