Merge tag 'drm-intel-gt-next-2021-10-21' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

UAPI Changes:

- Expose multi-LRC submission interface

  Similar to the bonded submission interface but simplified.
  Comes with GuC only implementation for now. See kerneldoc
  for more details.

  Userspace changes: https://github.com/intel/media-driver/pull/1252

- Expose logical engine instance to user

  Needed by the multi-LRC submission interface for GuC

  Userspace changes: https://github.com/intel/media-driver/pull/1252

Driver Changes:

- Fix blank screen booting crashes when CONFIG_CC_OPTIMIZE_FOR_SIZE=y (Hugh)
- Add support for multi-LRC submission in the GuC backend (Matt B)
- Add extra cache flushing before making pages userspace visible (Matt A, Thomas)
- Mark internal GPU object pages dirty so they will be flushed properly (Matt A)

- Move remaining debugfs interfaces i915_wedged/i915_forcewake_user into gt (Andi)
- Replace the unconditional clflushes with drm_clflush_virt_range() (Ville)
- Remove IS_ACTIVE macro completely (Lucas)
- Improve kerneldocs for cache_dirty (Matt A)

- Add missing includes (Lucas)
- Selftest improvements (Matt R, Ran, Matt A)

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/YXFmLKoq8Fg9JxSd@jlahtine-mobl.ger.corp.intel.com

1 files changed, 138 insertions, 1 deletions

diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 9b8e61163c39..914ebd9290e5 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1830,6 +1830,7 @@ struct drm_i915_gem_context_param {
  * Extensions:
  *   i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE)
  *   i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND)
+ *   i915_context_engines_parallel_submit (I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT)
  */
 #define I915_CONTEXT_PARAM_ENGINES	0xa
 
@@ -2105,6 +2106,135 @@ struct i915_context_engines_bond {
 } __attribute__((packed)) name__
 
 /**
+ * struct i915_context_engines_parallel_submit - Configure engine for
+ * parallel submission.
+ *
+ * Setup a slot in the context engine map to allow multiple BBs to be submitted
+ * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU
+ * in parallel. Multiple hardware contexts are created internally in the i915 to
+ * run these BBs. Once a slot is configured for N BBs only N BBs can be
+ * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user
+ * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how
+ * many BBs there are based on the slot's configuration. The N BBs are the last
+ * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set.
+ *
+ * The default placement behavior is to create implicit bonds between each
+ * context if each context maps to more than 1 physical engine (e.g. context is
+ * a virtual engine). Also we only allow contexts of same engine class and these
+ * contexts must be in logically contiguous order. Examples of the placement
+ * behavior are described below. Lastly, the default is to not allow BBs to be
+ * preempted mid-batch. Rather insert coordinated preemption points on all
+ * hardware contexts between each set of BBs. Flags could be added in the future
+ * to change both of these default behaviors.
+ *
+ * Returns -EINVAL if hardware context placement configuration is invalid or if
+ * the placement configuration isn't supported on the platform / submission
+ * interface.
+ * Returns -ENODEV if extension isn't supported on the platform / submission
+ * interface.
+ *
+ * .. code-block:: none
+ *
+ *	Examples syntax:
+ *	CS[X] = generic engine of same class, logical instance X
+ *	INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
+ *
+ *	Example 1 pseudo code:
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=1,
+ *		     engines=CS[0],CS[1])
+ *
+ *	Results in the following valid placement:
+ *	CS[0], CS[1]
+ *
+ *	Example 2 pseudo code:
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=2,
+ *		     engines=CS[0],CS[2],CS[1],CS[3])
+ *
+ *	Results in the following valid placements:
+ *	CS[0], CS[1]
+ *	CS[2], CS[3]
+ *
+ *	This can be thought of as two virtual engines, each containing two
+ *	engines thereby making a 2D array. However, there are bonds tying the
+ *	entries together and placing restrictions on how they can be scheduled.
+ *	Specifically, the scheduler can choose only vertical columns from the 2D
+ *	array. That is, CS[0] is bonded to CS[1] and CS[2] to CS[3]. So if the
+ *	scheduler wants to submit to CS[0], it must also choose CS[1] and vice
+ *	versa. Same for CS[2] requires also using CS[3].
+ *	VE[0] = CS[0], CS[2]
+ *	VE[1] = CS[1], CS[3]
+ *
+ *	Example 3 pseudo code:
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=2,
+ *		     engines=CS[0],CS[1],CS[1],CS[3])
+ *
+ *	Results in the following valid and invalid placements:
+ *	CS[0], CS[1]
+ *	CS[1], CS[3] - Not logically contiguous, return -EINVAL
+ */
+struct i915_context_engines_parallel_submit {
+	/**
+	 * @base: base user extension.
+	 */
+	struct i915_user_extension base;
+
+	/**
+	 * @engine_index: slot for parallel engine
+	 */
+	__u16 engine_index;
+
+	/**
+	 * @width: number of contexts per parallel engine or in other words the
+	 * number of batches in each submission
+	 */
+	__u16 width;
+
+	/**
+	 * @num_siblings: number of siblings per context or in other words the
+	 * number of possible placements for each submission
+	 */
+	__u16 num_siblings;
+
+	/**
+	 * @mbz16: reserved for future use; must be zero
+	 */
+	__u16 mbz16;
+
+	/**
+	 * @flags: all undefined flags must be zero, currently not defined flags
+	 */
+	__u64 flags;
+
+	/**
+	 * @mbz64: reserved for future use; must be zero
+	 */
+	__u64 mbz64[3];
+
+	/**
+	 * @engines: 2-d array of engine instances to configure parallel engine
+	 *
+	 * length = width (i) * num_siblings (j)
+	 * index = j + i * num_siblings
+	 */
+	struct i915_engine_class_instance engines[0];
+
+} __packed;
+
+#define I915_DEFINE_CONTEXT_ENGINES_PARALLEL_SUBMIT(name__, N__) struct { \
+	struct i915_user_extension base; \
+	__u16 engine_index; \
+	__u16 width; \
+	__u16 num_siblings; \
+	__u16 mbz16; \
+	__u64 flags; \
+	__u64 mbz64[3]; \
+	struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
+/**
  * DOC: Context Engine Map uAPI
  *
  * Context engine map is a new way of addressing engines when submitting batch-
@@ -2163,6 +2293,7 @@ struct i915_context_param_engines {
 	__u64 extensions; /* linked chain of extension blocks, 0 terminates */
 #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */
 #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */
+#define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */
 	struct i915_engine_class_instance engines[0];
 } __attribute__((packed));
 
@@ -2781,14 +2912,20 @@ struct drm_i915_engine_info {
 
 	/** @flags: Engine flags. */
 	__u64 flags;
+#define I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE		(1 << 0)
 
 	/** @capabilities: Capabilities of this engine. */
 	__u64 capabilities;
 #define I915_VIDEO_CLASS_CAPABILITY_HEVC		(1 << 0)
 #define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC	(1 << 1)
 
+	/** @logical_instance: Logical instance of engine */
+	__u16 logical_instance;
+
 	/** @rsvd1: Reserved fields. */
-	__u64 rsvd1[4];
+	__u16 rsvd1[3];
+	/** @rsvd2: Reserved fields. */
+	__u64 rsvd2[3];
 };
 
 /**