Merge tag 'drm-intel-next-2016-08-08' of git://anongit.freedesktop.org/drm-intel into drm-next

- refactor ddi buffer programming a bit (Ville)
- large-scale renaming to untangle naming in the gem code (Chris)
- rework vma/active tracking for accurately reaping idle mappings of shared
  objects (Chris)
- misc dp sst/mst probing corner case fixes (Ville)
- tons of cleanup&tunings all around in gem
- lockless (rcu-protected) request lookup, plus use it everywhere for
  non(b)locking waits (Chris)
- pipe crc debugfs fixes (Rodrigo)
- random fixes all over

* tag 'drm-intel-next-2016-08-08' of git://anongit.freedesktop.org/drm-intel: (222 commits)
  drm/i915: Update DRIVER_DATE to 20160808
  drm/i915: fix aliasing_ppgtt leak
  drm/i915: Update comment before i915_spin_request
  drm/i915: Use drm official vblank_no_hw_counter callback.
  drm/i915: Fix copy_to_user usage for pipe_crc
  Revert "drm/i915: Track active streams also for DP SST"
  drm/i915: fix WaInsertDummyPushConstPs
  drm/i915: Assert that the request hasn't been retired
  drm/i915: Repack fence tiling mode and stride into a single integer
  drm/i915: Document and reject invalid tiling modes
  drm/i915: Remove locking for get_tiling
  drm/i915: Remove pinned check from madvise ioctl
  drm/i915: Reduce locking inside swfinish ioctl
  drm/i915: Remove (struct_mutex) locking for busy-ioctl
  drm/i915: Remove (struct_mutex) locking for wait-ioctl
  drm/i915: Do a nonblocking wait first in pread/pwrite
  drm/i915: Remove unused no-shrinker-steal
  drm/i915: Tidy generation of the GTT mmap offset
  drm/i915/shrinker: Wait before acquiring struct_mutex under oom
  drm/i915: Simplify do_idling() (Ironlake vt-d w/a)
  ...

62 files changed, 6154 insertions, 5873 deletions

diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
index 2fe5952e90f1..87aaffc22920 100644
--- a/Documentation/gpu/i915.rst
+++ b/Documentation/gpu/i915.rst
@@ -70,6 +70,9 @@ Frontbuffer Tracking
 .. kernel-doc:: drivers/gpu/drm/i915/intel_frontbuffer.c
    :doc: frontbuffer tracking
 
+.. kernel-doc:: drivers/gpu/drm/i915/intel_frontbuffer.h
+   :internal:
+
 .. kernel-doc:: drivers/gpu/drm/i915/intel_frontbuffer.c
    :internal:
 
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 684fc1cd08fa..dda724f04445 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -25,7 +25,6 @@ i915-$(CONFIG_DEBUG_FS) += i915_debugfs.o
 i915-y += i915_cmd_parser.o \
 	  i915_gem_batch_pool.o \
 	  i915_gem_context.o \
-	  i915_gem_debug.o \
 	  i915_gem_dmabuf.o \
 	  i915_gem_evict.o \
 	  i915_gem_execbuffer.o \
@@ -33,6 +32,7 @@ i915-y += i915_cmd_parser.o \
 	  i915_gem_gtt.o \
 	  i915_gem.o \
 	  i915_gem_render_state.o \
+	  i915_gem_request.o \
 	  i915_gem_shrinker.o \
 	  i915_gem_stolen.o \
 	  i915_gem_tiling.o \
@@ -40,6 +40,7 @@ i915-y += i915_cmd_parser.o \
 	  i915_gpu_error.o \
 	  i915_trace_points.o \
 	  intel_breadcrumbs.o \
+	  intel_engine_cs.o \
 	  intel_lrc.o \
 	  intel_mocs.o \
 	  intel_ringbuffer.o \
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index b0fd6a7b0603..1db829c8b912 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -62,23 +62,23 @@
  * The parser always rejects such commands.
  *
  * The majority of the problematic commands fall in the MI_* range, with only a
- * few specific commands on each ring (e.g. PIPE_CONTROL and MI_FLUSH_DW).
+ * few specific commands on each engine (e.g. PIPE_CONTROL and MI_FLUSH_DW).
  *
  * Implementation:
- * Each ring maintains tables of commands and registers which the parser uses in
- * scanning batch buffers submitted to that ring.
+ * Each engine maintains tables of commands and registers which the parser
+ * uses in scanning batch buffers submitted to that engine.
  *
  * Since the set of commands that the parser must check for is significantly
  * smaller than the number of commands supported, the parser tables contain only
  * those commands required by the parser. This generally works because command
  * opcode ranges have standard command length encodings. So for commands that
  * the parser does not need to check, it can easily skip them. This is
- * implemented via a per-ring length decoding vfunc.
+ * implemented via a per-engine length decoding vfunc.
  *
  * Unfortunately, there are a number of commands that do not follow the standard
  * length encoding for their opcode range, primarily amongst the MI_* commands.
  * To handle this, the parser provides a way to define explicit "skip" entries
- * in the per-ring command tables.
+ * in the per-engine command tables.
  *
  * Other command table entries map fairly directly to high level categories
  * mentioned above: rejected, master-only, register whitelist. The parser
@@ -603,7 +603,7 @@ static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header)
 	return 0;
 }
 
-static bool validate_cmds_sorted(struct intel_engine_cs *engine,
+static bool validate_cmds_sorted(const struct intel_engine_cs *engine,
 				 const struct drm_i915_cmd_table *cmd_tables,
 				 int cmd_table_count)
 {
@@ -624,8 +624,10 @@ static bool validate_cmds_sorted(struct intel_engine_cs *engine,
 			u32 curr = desc->cmd.value & desc->cmd.mask;
 
 			if (curr < previous) {
-				DRM_ERROR("CMD: table not sorted ring=%d table=%d entry=%d cmd=0x%08X prev=0x%08X\n",
-					  engine->id, i, j, curr, previous);
+				DRM_ERROR("CMD: %s [%d] command table not sorted: "
+					  "table=%d entry=%d cmd=0x%08X prev=0x%08X\n",
+					  engine->name, engine->id,
+					  i, j, curr, previous);
 				ret = false;
 			}
 
@@ -636,7 +638,7 @@ static bool validate_cmds_sorted(struct intel_engine_cs *engine,
 	return ret;
 }
 
-static bool check_sorted(int ring_id,
+static bool check_sorted(const struct intel_engine_cs *engine,
 			 const struct drm_i915_reg_descriptor *reg_table,
 			 int reg_count)
 {
@@ -648,8 +650,10 @@ static bool check_sorted(int ring_id,
 		u32 curr = i915_mmio_reg_offset(reg_table[i].addr);
 
 		if (curr < previous) {
-			DRM_ERROR("CMD: table not sorted ring=%d entry=%d reg=0x%08X prev=0x%08X\n",
-				  ring_id, i, curr, previous);
+			DRM_ERROR("CMD: %s [%d] register table not sorted: "
+				  "entry=%d reg=0x%08X prev=0x%08X\n",
+				  engine->name, engine->id,
+				  i, curr, previous);
 			ret = false;
 		}
 
@@ -666,7 +670,7 @@ static bool validate_regs_sorted(struct intel_engine_cs *engine)
 
 	for (i = 0; i < engine->reg_table_count; i++) {
 		table = &engine->reg_tables[i];
-		if (!check_sorted(engine->id, table->regs, table->num_regs))
+		if (!check_sorted(engine, table->regs, table->num_regs))
 			return false;
 	}
 
@@ -736,7 +740,7 @@ static void fini_hash_table(struct intel_engine_cs *engine)
 }
 
 /**
- * i915_cmd_parser_init_ring() - set cmd parser related fields for a ringbuffer
+ * intel_engine_init_cmd_parser() - set cmd parser related fields for an engine
  * @engine: the engine to initialize
  *
  * Optionally initializes fields related to batch buffer command parsing in the
@@ -745,7 +749,7 @@ static void fini_hash_table(struct intel_engine_cs *engine)
  *
  * Return: non-zero if initialization fails
  */
-int i915_cmd_parser_init_ring(struct intel_engine_cs *engine)
+int intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
 {
 	const struct drm_i915_cmd_table *cmd_tables;
 	int cmd_table_count;
@@ -806,8 +810,7 @@ int i915_cmd_parser_init_ring(struct intel_engine_cs *engine)
 		engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
 		break;
 	default:
-		DRM_ERROR("CMD: cmd_parser_init with unknown ring: %d\n",
-			  engine->id);
+		MISSING_CASE(engine->id);
 		BUG();
 	}
 
@@ -829,13 +832,13 @@ int i915_cmd_parser_init_ring(struct intel_engine_cs *engine)
 }
 
 /**
- * i915_cmd_parser_fini_ring() - clean up cmd parser related fields
+ * intel_engine_cleanup_cmd_parser() - clean up cmd parser related fields
  * @engine: the engine to clean up
  *
  * Releases any resources related to command parsing that may have been
- * initialized for the specified ring.
+ * initialized for the specified engine.
  */
-void i915_cmd_parser_fini_ring(struct intel_engine_cs *engine)
+void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine)
 {
 	if (!engine->needs_cmd_parser)
 		return;
@@ -866,9 +869,9 @@ find_cmd_in_table(struct intel_engine_cs *engine,
  * Returns a pointer to a descriptor for the command specified by cmd_header.
  *
  * The caller must supply space for a default descriptor via the default_desc
- * parameter. If no descriptor for the specified command exists in the ring's
+ * parameter. If no descriptor for the specified command exists in the engine's
  * command parser tables, this function fills in default_desc based on the
- * ring's default length encoding and returns default_desc.
+ * engine's default length encoding and returns default_desc.
  */
 static const struct drm_i915_cmd_descriptor*
 find_cmd(struct intel_engine_cs *engine,
@@ -1023,15 +1026,16 @@ unpin_src:
 }
 
 /**
- * i915_needs_cmd_parser() - should a given ring use software command parsing?
+ * intel_engine_needs_cmd_parser() - should a given engine use software
+ *                                   command parsing?
  * @engine: the engine in question
  *
  * Only certain platforms require software batch buffer command parsing, and
  * only when enabled via module parameter.
  *
- * Return: true if the ring requires software command parsing
+ * Return: true if the engine requires software command parsing
  */
-bool i915_needs_cmd_parser(struct intel_engine_cs *engine)
+bool intel_engine_needs_cmd_parser(struct intel_engine_cs *engine)
 {
 	if (!engine->needs_cmd_parser)
 		return false;
@@ -1078,8 +1082,8 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 						   reg_addr);
 
 			if (!reg) {
-				DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (ring=%d)\n",
-						 reg_addr, *cmd, engine->id);
+				DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (exec_id=%d)\n",
+						 reg_addr, *cmd, engine->exec_id);
 				return false;
 			}
 
@@ -1159,11 +1163,11 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 				desc->bits[i].mask;
 
 			if (dword != desc->bits[i].expected) {
-				DRM_DEBUG_DRIVER("CMD: Rejected command 0x%08X for bitmask 0x%08X (exp=0x%08X act=0x%08X) (ring=%d)\n",
+				DRM_DEBUG_DRIVER("CMD: Rejected command 0x%08X for bitmask 0x%08X (exp=0x%08X act=0x%08X) (exec_id=%d)\n",
 						 *cmd,
 						 desc->bits[i].mask,
 						 desc->bits[i].expected,
-						 dword, engine->id);
+						 dword, engine->exec_id);
 				return false;
 			}
 		}
@@ -1189,12 +1193,12 @@ static bool check_cmd(const struct intel_engine_cs *engine,
  * Return: non-zero if the parser finds violations or otherwise fails; -EACCES
  * if the batch appears legal but should use hardware parsing
  */
-int i915_parse_cmds(struct intel_engine_cs *engine,
-		    struct drm_i915_gem_object *batch_obj,
-		    struct drm_i915_gem_object *shadow_batch_obj,
-		    u32 batch_start_offset,
-		    u32 batch_len,
-		    bool is_master)
+int intel_engine_cmd_parser(struct intel_engine_cs *engine,
+			    struct drm_i915_gem_object *batch_obj,
+			    struct drm_i915_gem_object *shadow_batch_obj,
+			    u32 batch_start_offset,
+			    u32 batch_len,
+			    bool is_master)
 {
 	u32 *cmd, *batch_base, *batch_end;
 	struct drm_i915_cmd_descriptor default_desc = { 0 };
@@ -1295,7 +1299,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv)
 
 	/* If the command parser is not enabled, report 0 - unsupported */
 	for_each_engine(engine, dev_priv) {
-		if (i915_needs_cmd_parser(engine)) {
+		if (intel_engine_needs_cmd_parser(engine)) {
 			active = true;
 			break;
 		}
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 9b03cb2813bd..f62285c1ed7f 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -91,7 +91,7 @@ static int i915_capabilities(struct seq_file *m, void *data)
 
 static char get_active_flag(struct drm_i915_gem_object *obj)
 {
-	return obj->active ? '*' : ' ';
+	return i915_gem_object_is_active(obj) ? '*' : ' ';
 }
 
 static char get_pin_flag(struct drm_i915_gem_object *obj)
@@ -101,7 +101,7 @@ static char get_pin_flag(struct drm_i915_gem_object *obj)
 
 static char get_tiling_flag(struct drm_i915_gem_object *obj)
 {
-	switch (obj->tiling_mode) {
+	switch (i915_gem_object_get_tiling(obj)) {
 	default:
 	case I915_TILING_NONE: return ' ';
 	case I915_TILING_X: return 'X';
@@ -125,7 +125,7 @@ static u64 i915_gem_obj_total_ggtt_size(struct drm_i915_gem_object *obj)
 	struct i915_vma *vma;
 
 	list_for_each_entry(vma, &obj->vma_list, obj_link) {
-		if (vma->is_ggtt && drm_mm_node_allocated(&vma->node))
+		if (i915_vma_is_ggtt(vma) && drm_mm_node_allocated(&vma->node))
 			size += vma->node.size;
 	}
 
@@ -138,6 +138,7 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 	struct intel_engine_cs *engine;
 	struct i915_vma *vma;
+	unsigned int frontbuffer_bits;
 	int pin_count = 0;
 	enum intel_engine_id id;
 
@@ -155,17 +156,20 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		   obj->base.write_domain);
 	for_each_engine_id(engine, dev_priv, id)
 		seq_printf(m, "%x ",
-				i915_gem_request_get_seqno(obj->last_read_req[id]));
+			   i915_gem_active_get_seqno(&obj->last_read[id],
+						     &obj->base.dev->struct_mutex));
 	seq_printf(m, "] %x %x%s%s%s",
-		   i915_gem_request_get_seqno(obj->last_write_req),
-		   i915_gem_request_get_seqno(obj->last_fenced_req),
+		   i915_gem_active_get_seqno(&obj->last_write,
+					     &obj->base.dev->struct_mutex),
+		   i915_gem_active_get_seqno(&obj->last_fence,
+					     &obj->base.dev->struct_mutex),
 		   i915_cache_level_str(to_i915(obj->base.dev), obj->cache_level),
 		   obj->dirty ? " dirty" : "",
 		   obj->madv == I915_MADV_DONTNEED ? " purgeable" : "");
 	if (obj->base.name)
 		seq_printf(m, " (name: %d)", obj->base.name);
 	list_for_each_entry(vma, &obj->vma_list, obj_link) {
-		if (vma->pin_count > 0)
+		if (i915_vma_is_pinned(vma))
 			pin_count++;
 	}
 	seq_printf(m, " (pinned x %d)", pin_count);
@@ -174,10 +178,13 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 	if (obj->fence_reg != I915_FENCE_REG_NONE)
 		seq_printf(m, " (fence: %d)", obj->fence_reg);
 	list_for_each_entry(vma, &obj->vma_list, obj_link) {
+		if (!drm_mm_node_allocated(&vma->node))
+			continue;
+
 		seq_printf(m, " (%sgtt offset: %08llx, size: %08llx",
-			   vma->is_ggtt ? "g" : "pp",
+			   i915_vma_is_ggtt(vma) ? "g" : "pp",
 			   vma->node.start, vma->node.size);
-		if (vma->is_ggtt)
+		if (i915_vma_is_ggtt(vma))
 			seq_printf(m, ", type: %u", vma->ggtt_view.type);
 		seq_puts(m, ")");
 	}
@@ -192,11 +199,15 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		*t = '\0';
 		seq_printf(m, " (%s mappable)", s);
 	}
-	if (obj->last_write_req != NULL)
-		seq_printf(m, " (%s)",
-			   i915_gem_request_get_engine(obj->last_write_req)->name);
-	if (obj->frontbuffer_bits)
-		seq_printf(m, " (frontbuffer: 0x%03x)", obj->frontbuffer_bits);
+
+	engine = i915_gem_active_get_engine(&obj->last_write,
+					    &obj->base.dev->struct_mutex);
+	if (engine)
+		seq_printf(m, " (%s)", engine->name);
+
+	frontbuffer_bits = atomic_read(&obj->frontbuffer_bits);
+	if (frontbuffer_bits)
+		seq_printf(m, " (frontbuffer: 0x%03x)", frontbuffer_bits);
 }
 
 static int i915_gem_object_list_info(struct seq_file *m, void *data)
@@ -338,46 +349,29 @@ static int per_file_stats(int id, void *ptr, void *data)
 
 	stats->count++;
 	stats->total += obj->base.size;
-
+	if (!obj->bind_count)
+		stats->unbound += obj->base.size;
 	if (obj->base.name || obj->base.dma_buf)
 		stats->shared += obj->base.size;
 
-	if (USES_FULL_PPGTT(obj->base.dev)) {
-		list_for_each_entry(vma, &obj->vma_list, obj_link) {
-			struct i915_hw_ppgtt *ppgtt;
-
-			if (!drm_mm_node_allocated(&vma->node))
-				continue;
+	list_for_each_entry(vma, &obj->vma_list, obj_link) {
+		if (!drm_mm_node_allocated(&vma->node))
+			continue;
 
-			if (vma->is_ggtt) {
-				stats->global += obj->base.size;
-				continue;
-			}
+		if (i915_vma_is_ggtt(vma)) {
+			stats->global += vma->node.size;
+		} else {
+			struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vma->vm);
 
-			ppgtt = container_of(vma->vm, struct i915_hw_ppgtt, base);
-			if (ppgtt->file_priv != stats->file_priv)
+			if (ppgtt->base.file != stats->file_priv)
 				continue;
-
-			if (obj->active) /* XXX per-vma statistic */
-				stats->active += obj->base.size;
-			else
-				stats->inactive += obj->base.size;
-
-			return 0;
-		}
-	} else {
-		if (i915_gem_obj_ggtt_bound(obj)) {
-			stats->global += obj->base.size;
-			if (obj->active)
-				stats->active += obj->base.size;
-			else
-				stats->inactive += obj->base.size;
-			return 0;
 		}
-	}
 
-	if (!list_empty(&obj->global_list))
-		stats->unbound += obj->base.size;
+		if (i915_vma_is_active(vma))
+			stats->active += vma->node.size;
+		else
+			stats->inactive += vma->node.size;
+	}
 
 	return 0;
 }
@@ -425,8 +419,8 @@ static int per_file_ctx_stats(int id, void *ptr, void *data)
 	for (n = 0; n < ARRAY_SIZE(ctx->engine); n++) {
 		if (ctx->engine[n].state)
 			per_file_stats(0, ctx->engine[n].state, data);
-		if (ctx->engine[n].ringbuf)
-			per_file_stats(0, ctx->engine[n].ringbuf->obj, data);
+		if (ctx->engine[n].ring)
+			per_file_stats(0, ctx->engine[n].ring->obj, data);
 	}
 
 	return 0;
@@ -754,13 +748,13 @@ static int i915_gem_request_info(struct seq_file *m, void *data)
 		int count;
 
 		count = 0;
-		list_for_each_entry(req, &engine->request_list, list)
+		list_for_each_entry(req, &engine->request_list, link)
 			count++;
 		if (count == 0)
 			continue;
 
 		seq_printf(m, "%s requests: %d\n", engine->name, count);
-		list_for_each_entry(req, &engine->request_list, list) {
+		list_for_each_entry(req, &engine->request_list, link) {
 			struct task_struct *task;
 
 			rcu_read_lock();
@@ -768,7 +762,7 @@ static int i915_gem_request_info(struct seq_file *m, void *data)
 			if (req->pid)
 				task = pid_task(req->pid, PIDTYPE_PID);
 			seq_printf(m, "    %x @ %d: %s [%d]\n",
-				   req->seqno,
+				   req->fence.seqno,
 				   (int) (jiffies - req->emitted_jiffies),
 				   task ? task->comm : "<unknown>",
 				   task ? task->pid : -1);
@@ -1205,8 +1199,6 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 
 	intel_runtime_pm_get(dev_priv);
 
-	flush_delayed_work(&dev_priv->rps.delayed_resume_work);
-
 	if (IS_GEN5(dev)) {
 		u16 rgvswctl = I915_READ16(MEMSWCTL);
 		u16 rgvstat = I915_READ16(MEMSTAT_ILK);
@@ -1381,6 +1373,8 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 			   intel_gpu_freq(dev_priv, dev_priv->rps.idle_freq));
 		seq_printf(m, "Min freq: %d MHz\n",
 			   intel_gpu_freq(dev_priv, dev_priv->rps.min_freq));
+		seq_printf(m, "Boost freq: %d MHz\n",
+			   intel_gpu_freq(dev_priv, dev_priv->rps.boost_freq));
 		seq_printf(m, "Max freq: %d MHz\n",
 			   intel_gpu_freq(dev_priv, dev_priv->rps.max_freq));
 		seq_printf(m,
@@ -1419,7 +1413,7 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 	intel_runtime_pm_get(dev_priv);
 
 	for_each_engine_id(engine, dev_priv, id) {
-		acthd[id] = intel_ring_get_active_head(engine);
+		acthd[id] =