Merge branch 'drm-intel-next' of git://anongit.freedesktop.org/drm-intel into drm-next

drm-intel-next-2016-05-22:
- cmd-parser support for direct reg->reg loads (Ken Graunke)
- better handle DP++ smart dongles (Ville)
- bxt guc fw loading support (Nick Hoathe)
- remove a bunch of struct typedefs from dpll code (Ander)
- tons of small work all over to avoid casting between drm_device and the i915
  dev struct (Tvrtko&Chris)
- untangle request retiring from other operations, also fixes reset stat corner
  cases (Chris)
- skl atomic watermark support from Matt Roper, yay!
- various wm handling bugfixes from Ville
- big pile of cdclck rework for bxt/skl (Ville)
- CABC (Content Adaptive Brigthness Control) for dsi panels (Jani&Deepak M)
- nonblocking atomic commits for plane-only updates (Maarten Lankhorst)
- bunch of PSR fixes&improvements
- untangle our map/pin/sg_iter code a bit (Dave Gordon)
drm-intel-next-2016-05-08:
- refactor stolen quirks to share code between early quirks and i915 (Joonas)
- refactor gem BO/vma funcstion (Tvrtko&Dave)
- backlight over DPCD support (Yetunde Abedisi)
- more dsi panel sequence support (Jani)
- lots of refactoring around handling iomaps, vma, ring access and related
  topics culmulating in removing the duplicated request tracking in the execlist
  code (Chris & Tvrtko) includes a small patch for core iomapping code
- hw state readout for bxt dsi (Ramalingam C)
- cdclk cleanups (Ville)
- dedupe chv pll code a bit (Ander)
- enable semaphores on gen8+ for legacy submission, to be able to have a direct
  comparison against execlist on the same platform (Chris) Not meant to be used
  for anything else but performance tuning
- lvds border bit hw state checker fix (Jani)
- rpm vs. shrinker/oom-notifier fixes (Praveen Paneri)
- l3 tuning (Imre)
- revert mst dp audio, it's totally non-functional and crash-y (Lyude)
- first official dmc for kbl (Rodrigo)
- and tons of small things all over as usual

* 'drm-intel-next' of git://anongit.freedesktop.org/drm-intel: (194 commits)
  drm/i915: Revert async unpin and nonblocking atomic commit
  drm/i915: Update DRIVER_DATE to 20160522
  drm/i915: Inline sg_next() for the optimised SGL iterator
  drm/i915: Introduce & use new lightweight SGL iterators
  drm/i915: optimise i915_gem_object_map() for small objects
  drm/i915: refactor i915_gem_object_pin_map()
  drm/i915/psr: Implement PSR2 w/a for gen9
  drm/i915/psr: Use ->get_aux_send_ctl functions
  drm/i915/psr: Order DP aux transactions correctly
  drm/i915/psr: Make idle_frames sensible again
  drm/i915/psr: Try to program link training times correctly
  drm/i915/userptr: Convert to drm_i915_private
  drm/i915: Allow nonblocking update of pageflips.
  drm/i915: Check for unpin correctness.
  Reapply "drm/i915: Avoid stalling on pending flips for legacy cursor updates"
  drm/i915: Make unpin async.
  drm/i915: Prepare connectors for nonblocking checks.
  drm/i915: Pass atomic states to fbc update functions.
  drm/i915: Remove reset_counter from intel_crtc.
  drm/i915: Remove queue_flip pointer.
  ...

1 files changed, 35 insertions, 9 deletions

diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index a337f33bec5b..d97f28bfa9db 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -215,7 +215,8 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = {
 	CMD(  MI_RS_CONTEXT,                    SMI,    F,  1,      S  ),
 	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   M  ),
 	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   R  ),
-	CMD(  MI_LOAD_REGISTER_REG,             SMI,   !F,  0xFF,   R  ),
+	CMD(  MI_LOAD_REGISTER_REG,             SMI,   !F,  0xFF,   W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 }    ),
 	CMD(  MI_RS_STORE_DATA_IMM,             SMI,   !F,  0xFF,   S  ),
 	CMD(  MI_LOAD_URB_MEM,                  SMI,   !F,  0xFF,   S  ),
 	CMD(  MI_STORE_URB_MEM,                 SMI,   !F,  0xFF,   S  ),
@@ -750,12 +751,12 @@ int i915_cmd_parser_init_ring(struct intel_engine_cs *engine)
 	int cmd_table_count;
 	int ret;
 
-	if (!IS_GEN7(engine->dev))
+	if (!IS_GEN7(engine->i915))
 		return 0;
 
 	switch (engine->id) {
 	case RCS:
-		if (IS_HASWELL(engine->dev)) {
+		if (IS_HASWELL(engine->i915)) {
 			cmd_tables = hsw_render_ring_cmds;
 			cmd_table_count =
 				ARRAY_SIZE(hsw_render_ring_cmds);
@@ -764,7 +765,7 @@ int i915_cmd_parser_init_ring(struct intel_engine_cs *engine)
 			cmd_table_count = ARRAY_SIZE(gen7_render_cmds);
 		}
 
-		if (IS_HASWELL(engine->dev)) {
+		if (IS_HASWELL(engine->i915)) {
 			engine->reg_tables = hsw_render_reg_tables;
 			engine->reg_table_count = ARRAY_SIZE(hsw_render_reg_tables);
 		} else {
@@ -780,7 +781,7 @@ int i915_cmd_parser_init_ring(struct intel_engine_cs *engine)
 		engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
 		break;
 	case BCS:
-		if (IS_HASWELL(engine->dev)) {
+		if (IS_HASWELL(engine->i915)) {
 			cmd_tables = hsw_blt_ring_cmds;
 			cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmds);
 		} else {
@@ -788,7 +789,7 @@ int i915_cmd_parser_init_ring(struct intel_engine_cs *engine)
 			cmd_table_count = ARRAY_SIZE(gen7_blt_cmds);
 		}
 
-		if (IS_HASWELL(engine->dev)) {
+		if (IS_HASWELL(engine->i915)) {
 			engine->reg_tables = hsw_blt_reg_tables;
 			engine->reg_table_count = ARRAY_SIZE(hsw_blt_reg_tables);
 		} else {
@@ -1035,7 +1036,7 @@ bool i915_needs_cmd_parser(struct intel_engine_cs *engine)
 	if (!engine->needs_cmd_parser)
 		return false;
 
-	if (!USES_PPGTT(engine->dev))
+	if (!USES_PPGTT(engine->i915))
 		return false;
 
 	return (i915.enable_cmd_parser == 1);
@@ -1098,6 +1099,11 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 					return false;
 				}
 
+				if (desc->cmd.value == MI_LOAD_REGISTER_REG) {
+					DRM_DEBUG_DRIVER("CMD: Rejected LRR to OACONTROL\n");
+					return false;
+				}
+
 				if (desc->cmd.value == MI_LOAD_REGISTER_IMM(1))
 					*oacontrol_set = (cmd[offset + 1] != 0);
 			}
@@ -1113,6 +1119,12 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 					return false;
 				}
 
+				if (desc->cmd.value == MI_LOAD_REGISTER_REG) {
+					DRM_DEBUG_DRIVER("CMD: Rejected LRR to masked register 0x%08X\n",
+							 reg_addr);
+					return false;
+				}
+
 				if (desc->cmd.value == MI_LOAD_REGISTER_IMM(1) &&
 				    (offset + 2 > length ||
 				     (cmd[offset + 1] & reg->mask) != reg->value)) {
@@ -1275,8 +1287,21 @@ int i915_parse_cmds(struct intel_engine_cs *engine,
  *
  * Return: the current version number of the cmd parser
  */
-int i915_cmd_parser_get_version(void)
+int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv)
 {
+	struct intel_engine_cs *engine;
+	bool active = false;
+
+	/* If the command parser is not enabled, report 0 - unsupported */
+	for_each_engine(engine, dev_priv) {
+		if (i915_needs_cmd_parser(engine)) {
+			active = true;
+			break;
+		}
+	}
+	if (!active)
+		return 0;
+
 	/*
 	 * Command parser version history
 	 *
@@ -1288,6 +1313,7 @@ int i915_cmd_parser_get_version(void)
 	 * 4. L3 atomic chicken bits of HSW_SCRATCH1 and HSW_ROW_CHICKEN3.
 	 * 5. GPGPU dispatch compute indirect registers.
 	 * 6. TIMESTAMP register and Haswell CS GPR registers
+	 * 7. Allow MI_LOAD_REGISTER_REG between whitelisted registers.
 	 */
-	return 6;
+	return 7;
 }