[Intel-gfx] [PATCH v2 06/15] drm/i915/tdr: Capture engine state before reset

[Arun Siluvery]

Minimal state of engine is saved before resetting it, this state includes
head, current active request.

A consistency check is performed on the active request to make sure that
the context HW is executing is same as the one for the active request. This
check is important because engine recovery in execlist mode relies on the
context resubmission after reset. If the state is inconsistent,
resubmission can cause unforseen side-effects such as unexpected
preemptions.

Engine is restarted after reset with this state.

Signed-off-by: Tomas Elf <tomas.elf at intel.com>
Signed-off-by: Arun Siluvery <arun.siluvery at linux.intel.com>
---
 drivers/gpu/drm/i915/intel_lrc.c        | 80 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_lrc.h        |  3 ++
 drivers/gpu/drm/i915/intel_ringbuffer.h | 10 +++++
 3 files changed, 93 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 35255ce..b83552a 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1022,6 +1022,82 @@ void intel_lr_context_unpin(struct i915_gem_context *ctx,
 	i915_gem_context_unreference(ctx);
 }
 
+/**
+ * intel_execlist_get_current_request() - returns request currently processed
+ * by the given engine
+ *
+ * @engine: Engine currently running context to be returned.
+ *
+ * Returns:
+ *  req - if a valid req is found in the execlist queue and HW also agrees.
+ *        caller has to dereference at the end of its lifecycle.
+ *  NULL - otherwise
+ */
+static struct drm_i915_gem_request *
+intel_execlist_get_current_request(struct intel_engine_cs *engine)
+{
+	struct drm_i915_gem_request *req;
+	unsigned long flags;
+
+	spin_lock_irqsave(&engine->execlist_lock, flags);
+
+	req = list_first_entry_or_null(&engine->execlist_queue,
+				       struct drm_i915_gem_request,
+				       execlist_link);
+	/*
+	 * Only acknowledge the request in the execlist queue if it's actually
+	 * been submitted to hardware, otherwise there's the risk of
+	 * inconsistency between the (unsubmitted) request and the idle
+	 * hardware state.
+	 */
+	if (req && req->ctx && req->elsp_submitted) {
+		u32 execlist_status;
+		u32 hw_context;
+		u32 hw_active;
+		struct drm_i915_private *dev_priv = engine->i915;
+
+		hw_context = I915_READ(RING_EXECLIST_STATUS_CTX_ID(engine));
+		execlist_status = I915_READ(RING_EXECLIST_STATUS_LO(engine));
+		hw_active = ((execlist_status & EXECLIST_STATUS_ELEMENT0_ACTIVE) ||
+			     (execlist_status & EXECLIST_STATUS_ELEMENT1_ACTIVE));
+
+		/* If both HW and driver agrees then we found it */
+		if (hw_active && hw_context == req->ctx->hw_id)
+			i915_gem_request_reference(req);
+	} else {
+		req = NULL;
+		WARN(1, "No active request for %s\n", engine->name);
+	}
+
+	spin_unlock_irqrestore(&engine->execlist_lock, flags);
+
+	return req;
+}
+
+/**
+ * gen8_engine_state_save() - save minimum engine state
+ * @engine: engine whose state is to be saved
+ * @state: location where the state is saved
+ *
+ * captured engine state includes head, tail, active request. After reset,
+ * engine is restarted with this state.
+ *
+ * Returns:
+ *	0 if ok, otherwise propagates error codes.
+ */
+static int gen8_engine_state_save(struct intel_engine_cs *engine,
+				  struct intel_engine_cs_state *state)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+
+	state->head = I915_READ_HEAD(engine);
+	state->req = intel_execlist_get_current_request(engine);
+	if (!state->req)
+		return -EINVAL;
+
+	return 0;
+}
+
 static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req)
 {
 	int ret, i;
@@ -1977,6 +2053,10 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 	engine->emit_bb_start = gen8_emit_bb_start;
 	engine->get_seqno = gen8_get_seqno;
 	engine->set_seqno = gen8_set_seqno;
+
+	/* engine reset supporting functions */
+	engine->save = gen8_engine_state_save;
+
 	if (IS_BXT_REVID(engine->i915, 0, BXT_REVID_A1)) {
 		engine->irq_seqno_barrier = bxt_a_seqno_barrier;
 		engine->set_seqno = bxt_a_set_seqno;
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index a8db42a..0ef6fb5 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -31,7 +31,10 @@
 /* Execlists regs */
 #define RING_ELSP(ring)				_MMIO((ring)->mmio_base + 0x230)
 #define RING_EXECLIST_STATUS_LO(ring)		_MMIO((ring)->mmio_base + 0x234)
+#define   EXECLIST_STATUS_ELEMENT0_ACTIVE       (1 << 14)
+#define   EXECLIST_STATUS_ELEMENT1_ACTIVE       (1 << 15)
 #define RING_EXECLIST_STATUS_HI(ring)		_MMIO((ring)->mmio_base + 0x234 + 4)
+#define RING_EXECLIST_STATUS_CTX_ID(ring)	RING_EXECLIST_STATUS_HI(ring)
 #define RING_CONTEXT_CONTROL(ring)		_MMIO((ring)->mmio_base + 0x244)
 #define	  CTX_CTRL_INHIBIT_SYN_CTX_SWITCH	(1 << 3)
 #define	  CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT	(1 << 0)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index b33c876..daf2727 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -141,6 +141,12 @@ struct  i915_ctx_workarounds {
 	struct drm_i915_gem_object *obj;
 };
 
+struct intel_engine_cs_state {
+	u32 head;
+	u32 tail;
+	struct drm_i915_gem_request *req;
+};
+
 struct intel_engine_cs {
 	struct drm_i915_private *i915;
 	const char	*name;
@@ -204,6 +210,10 @@ struct intel_engine_cs {
 #define I915_DISPATCH_RS     0x4
 	void		(*cleanup)(struct intel_engine_cs *ring);
 
+	/* engine reset supporting functions */
+	int (*save)(struct intel_engine_cs *engine,
+		    struct intel_engine_cs_state *state);
+
 	/* GEN8 signal/wait table - never trust comments!
 	 *	  signal to	signal to    signal to   signal to      signal to
 	 *	    RCS		   VCS          BCS        VECS		 VCS2
-- 
1.9.1