drm/i915: Make for_each_engine_masked() more compact and quicker

Rather than walk the full array of engines checking whether each is in
the mask in turn, we can use the mask to jump to the right engines. This
should quicker for a sparse array of engines or mask, whilst generating
smaller code:

   text	   data	    bss	    dec	    hex	filename
1251010	   4579	    800	1256389	 132bc5	drivers/gpu/drm/i915/i915.ko
1250530	   4579	    800	1255909	 1329e5	drivers/gpu/drm/i915/i915.ko

The downside is that we have to pass in a temporary, alas no C99
iterators yet.

[P.S. Joonas doesn't like having to pass extra temporaries into the
macro, and even less that I called them tmp. As yet, we haven't found a
macro that avoids passing in a temporary that is smaller. We probably
will get C99 iterators first!]
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160827075401.16470-2-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/i915_drv.h

@@ -2093,13 +2093,16 @@ static inline struct drm_i915_private *guc_to_i915(struct intel_guc *guc)
 		for_each_if (((id__) = (engine__)->id, \
 			      intel_engine_initialized(engine__)))
 
+#define __mask_next_bit(mask) ({					\
+	int __idx = ffs(mask) - 1;					\
+	mask &= ~BIT(__idx);						\
+	__idx;								\
+})
+
 /* Iterator over subset of engines selected by mask */
-#define for_each_engine_masked(engine__, dev_priv__, mask__) \
-	for ((engine__) = &(dev_priv__)->engine[0]; \
-	     (engine__) < &(dev_priv__)->engine[I915_NUM_ENGINES]; \
-	     (engine__)++) \
-		for_each_if (((mask__) & intel_engine_flag(engine__)) && \
-			     intel_engine_initialized(engine__))
+#define for_each_engine_masked(engine__, dev_priv__, mask__, tmp__) \
+	for (tmp__ = mask__ & INTEL_INFO(dev_priv__)->ring_mask;	\
+	     tmp__ ? (engine__ = &(dev_priv__)->engine[__mask_next_bit(tmp__)]), 1 : 0; )
 
 enum hdmi_force_audio {
 	HDMI_AUDIO_OFF_DVI = -2,	/* no aux data for HDMI-DVI converter */

drivers/gpu/drm/i915/i915_gem_request.c

@@ -766,6 +766,7 @@ static bool engine_retire_requests(struct intel_engine_cs *engine)
 void i915_gem_retire_requests(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	unsigned int tmp;
 
 	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 
@@ -774,7 +775,7 @@ void i915_gem_retire_requests(struct drm_i915_private *dev_priv)
 
 	GEM_BUG_ON(!dev_priv->gt.awake);
 
-	for_each_engine_masked(engine, dev_priv, dev_priv->gt.active_engines)
+	for_each_engine_masked(engine, dev_priv, dev_priv->gt.active_engines, tmp)
 		if (engine_retire_requests(engine))
 			dev_priv->gt.active_engines &= ~intel_engine_flag(engine);
 

drivers/gpu/drm/i915/i915_guc_submission.c

@@ -330,6 +330,7 @@ static void guc_init_ctx_desc(struct intel_guc *guc,
 	struct i915_gem_context *ctx = client->owner;
 	struct guc_context_desc desc;
 	struct sg_table *sg;
+	unsigned int tmp;
 	u32 gfx_addr;
 
 	memset(&desc, 0, sizeof(desc));
@@ -339,7 +340,7 @@ static void guc_init_ctx_desc(struct intel_guc *guc,
 	desc.priority = client->priority;
 	desc.db_id = client->doorbell_id;
 
-	for_each_engine_masked(engine, dev_priv, client->engines) {
+	for_each_engine_masked(engine, dev_priv, client->engines, tmp) {
 		struct intel_context *ce = &ctx->engine[engine->id];
 		uint32_t guc_engine_id = engine->guc_id;
 		struct guc_execlist_context *lrc = &desc.lrc[guc_engine_id];

drivers/gpu/drm/i915/i915_irq.c

@@ -3169,6 +3169,7 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 
 	if (hung) {
 		char msg[80];
+		unsigned int tmp;
 		int len;
 
 		/* If some rings hung but others were still busy, only
@@ -3178,7 +3179,7 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 			hung &= ~stuck;
 		len = scnprintf(msg, sizeof(msg),
 				"%s on ", stuck == hung ? "No progress" : "Hang");
-		for_each_engine_masked(engine, dev_priv, hung)
+		for_each_engine_masked(engine, dev_priv, hung, tmp)
 			len += scnprintf(msg + len, sizeof(msg) - len,
 					 "%s, ", engine->name);
 		msg[len-2] = '\0';

drivers/gpu/drm/i915/intel_uncore.c

@@ -1597,8 +1597,10 @@ static int gen6_reset_engines(struct drm_i915_private *dev_priv,
 	if (engine_mask == ALL_ENGINES) {
 		hw_mask = GEN6_GRDOM_FULL;
 	} else {
+		unsigned int tmp;
+
 		hw_mask = 0;
-		for_each_engine_masked(engine, dev_priv, engine_mask)
+		for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
 			hw_mask |= hw_engine_mask[engine->id];
 	}
 
@@ -1714,15 +1716,16 @@ static int gen8_reset_engines(struct drm_i915_private *dev_priv,
 			      unsigned engine_mask)
 {
 	struct intel_engine_cs *engine;
+	unsigned int tmp;
 
-	for_each_engine_masked(engine, dev_priv, engine_mask)
+	for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
 		if (gen8_request_engine_reset(engine))
 			goto not_ready;
 
 	return gen6_reset_engines(dev_priv, engine_mask);
 
 not_ready:
-	for_each_engine_masked(engine, dev_priv, engine_mask)
+	for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
 		gen8_unrequest_engine_reset(engine);
 
 	return -EIO;