Merge tag 'drm-intel-next-2017-12-01' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

[airlied: fix conflict in intel_dsi.c]

drm-intel-next-2017-12-01:

- Init clock gate fix (Ville)
- Execlists event handling corrections (Chris, Michel)
- Improvements on GPU Cache invalidation and context switch (Chris)
- More perf OA changes (Lionel)
- More selftests improvements and fixes (Chris, Matthew)
- Clean-up on modules parameters (Chris)
- Clean-up around old ringbuffer submission and hw semaphore on old platforms (Chris)
- More Cannonlake stabilization effort (David, James)
- Display planes clean-up and improvements (Ville)
- New PMU interface for perf queries... (Tvrtko)
- ... and other subsequent PMU changes and fixes (Tvrtko, Chris)
- Remove success dmesg noise from rotation (Chris)
- New DMC for Kabylake (Anusha)
- Fixes around atomic commits (Daniel)
- GuC updates and fixes (Sagar, Michal, Chris)
- Couple gmbus/i2c fixes (Ville)
- Use exponential backoff for all our wait_for() (Chris)
- Fixes for i915/fbdev (Chris)
- Backlight fixes (Arnd)
- Updates on shrinker (Chris)
- Make Hotplug enable more robuts (Chris)
- Disable huge pages (TPH) on lack of a needed workaround (Joonas)
- New GuC images for SKL, KBL, BXT (Sagar)
- Add HW Workaround for Geminilake performance (Valtteri)
- Fixes for PPS timings (Imre)
- More IPS fixes (Maarten)
- Many fixes for Display Port on gen2-gen4 (Ville)
- Retry GPU reset making the recover from hang more robust (Chris)

* tag 'drm-intel-next-2017-12-01' of git://anongit.freedesktop.org/drm/drm-intel: (101 commits)
  drm/i915: Update DRIVER_DATE to 20171201
  drm/i915/cnl: Mask previous DDI - PLL mapping
  drm/i915: Remove unsafe i915.enable_rc6
  drm/i915: Sleep and retry a GPU reset if at first we don't succeed
  drm/i915: Interlaced DP output doesn't work on VLV/CHV
  drm/i915: Pass crtc state to intel_pipe_{enable,disable}()
  drm/i915: Wait for pipe to start on i830 as well
  drm/i915: Fix vblank timestamp/frame counter jumps on gen2
  drm/i915: Fix deadlock in i830_disable_pipe()
  drm/i915: Fix has_audio readout for DDI A
  drm/i915: Don't add the "force audio" property to DP connectors that don't support audio
  drm/i915: Disable DP audio for g4x
  drm/i915/selftests: Wake the device before executing requests on the GPU
  drm/i915: Set fake_vma.size as well as fake_vma.node.size for capture
  drm/i915: Tidy up signed/unsigned comparison
  drm/i915: Enable IPS with only sprite plane visible too, v4.
  drm/i915: Make ips_enabled a property depending on whether IPS is enabled, v3.
  drm/i915: Avoid PPS HW/SW state mismatch due to rounding
  drm/i915: Skip switch-to-kernel-context on suspend when wedged
  drm/i915/glk: Apply WaProgramL3SqcReg1DefaultForPerf for GLK too
  ...

1 files changed, 154 insertions, 20 deletions

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index f867aa6c31fc..c68ab3ead83c 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -6,6 +6,7 @@
 #include "i915_gem_batch_pool.h"
 #include "i915_gem_request.h"
 #include "i915_gem_timeline.h"
+#include "i915_pmu.h"
 #include "i915_selftest.h"
 
 struct drm_printer;
@@ -47,16 +48,6 @@ struct intel_hw_status_page {
 /* seqno size is actually only a uint32, but since we plan to use MI_FLUSH_DW to
  * do the writes, and that must have qw aligned offsets, simply pretend it's 8b.
  */
-#define gen8_semaphore_seqno_size sizeof(uint64_t)
-#define GEN8_SEMAPHORE_OFFSET(__from, __to)			     \
-	(((__from) * I915_NUM_ENGINES  + (__to)) * gen8_semaphore_seqno_size)
-#define GEN8_SIGNAL_OFFSET(__ring, to)			     \
-	(dev_priv->semaphore->node.start + \
-	 GEN8_SEMAPHORE_OFFSET((__ring)->id, (to)))
-#define GEN8_WAIT_OFFSET(__ring, from)			     \
-	(dev_priv->semaphore->node.start + \
-	 GEN8_SEMAPHORE_OFFSET(from, (__ring)->id))
-
 enum intel_engine_hangcheck_action {
 	ENGINE_IDLE = 0,
 	ENGINE_WAIT,
@@ -252,6 +243,7 @@ struct intel_engine_execlists {
 	unsigned int active;
 #define EXECLISTS_ACTIVE_USER 0
 #define EXECLISTS_ACTIVE_PREEMPT 1
+#define EXECLISTS_ACTIVE_HWACK 2
 
 	/**
 	 * @port_mask: number of execlist ports - 1
@@ -348,6 +340,43 @@ struct intel_engine_cs {
 		I915_SELFTEST_DECLARE(bool mock : 1);
 	} breadcrumbs;
 
+	struct {
+		/**
+		 * @enable: Bitmask of enable sample events on this engine.
+		 *
+		 * Bits correspond to sample event types, for instance
+		 * I915_SAMPLE_QUEUED is bit 0 etc.
+		 */
+		u32 enable;
+		/**
+		 * @enable_count: Reference count for the enabled samplers.
+		 *
+		 * Index number corresponds to the bit number from @enable.
+		 */
+		unsigned int enable_count[I915_PMU_SAMPLE_BITS];
+		/**
+		 * @sample: Counter values for sampling events.
+		 *
+		 * Our internal timer stores the current counters in this field.
+		 */
+#define I915_ENGINE_SAMPLE_MAX (I915_SAMPLE_SEMA + 1)
+		struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_MAX];
+		/**
+		 * @busy_stats: Has enablement of engine stats tracking been
+		 * 		requested.
+		 */
+		bool busy_stats;
+		/**
+		 * @disable_busy_stats: Work item for busy stats disabling.
+		 *
+		 * Same as with @enable_busy_stats action, with the difference
+		 * that we delay it in case there are rapid enable-disable
+		 * actions, which can happen during tool startup (like perf
+		 * stat).
+		 */
+		struct delayed_work disable_busy_stats;
+	} pmu;
+
 	/*
 	 * A pool of objects to use as shadow copies of client batch buffers
 	 * when the command parser is enabled. Prevents the client from
@@ -467,18 +496,15 @@ struct intel_engine_cs {
 	 *  ie. transpose of f(x, y)
 	 */
 	struct {
-		union {
 #define GEN6_SEMAPHORE_LAST	VECS_HW
 #define GEN6_NUM_SEMAPHORES	(GEN6_SEMAPHORE_LAST + 1)
 #define GEN6_SEMAPHORES_MASK	GENMASK(GEN6_SEMAPHORE_LAST, 0)
-			struct {
-				/* our mbox written by others */
-				u32		wait[GEN6_NUM_SEMAPHORES];
-				/* mboxes this ring signals to */
-				i915_reg_t	signal[GEN6_NUM_SEMAPHORES];
-			} mbox;
-			u64		signal_ggtt[I915_NUM_ENGINES];
-		};
+		struct {
+			/* our mbox written by others */
+			u32		wait[GEN6_NUM_SEMAPHORES];
+			/* mboxes this ring signals to */
+			i915_reg_t	signal[GEN6_NUM_SEMAPHORES];
+		} mbox;
 
 		/* AKA wait() */
 		int	(*sync_to)(struct drm_i915_gem_request *req,
@@ -506,13 +532,16 @@ struct intel_engine_cs {
 	 * stream (ring).
 	 */
 	struct i915_gem_context *legacy_active_context;
+	struct i915_hw_ppgtt *legacy_active_ppgtt;
 
 	/* status_notifier: list of callbacks for context-switch changes */
 	struct atomic_notifier_head context_status_notifier;
 
 	struct intel_engine_hangcheck hangcheck;
 
-	bool needs_cmd_parser;
+#define I915_ENGINE_NEEDS_CMD_PARSER BIT(0)
+#define I915_ENGINE_SUPPORTS_STATS   BIT(1)
+	unsigned int flags;
 
 	/*
 	 * Table of commands the command parser needs to know about
@@ -537,8 +566,50 @@ struct intel_engine_cs {
 	 * certain bits to encode the command length in the header).
 	 */
 	u32 (*get_cmd_length_mask)(u32 cmd_header);
+
+	struct {
+		/**
+		 * @lock: Lock protecting the below fields.
+		 */
+		spinlock_t lock;
+		/**
+		 * @enabled: Reference count indicating number of listeners.
+		 */
+		unsigned int enabled;
+		/**
+		 * @active: Number of contexts currently scheduled in.
+		 */
+		unsigned int active;
+		/**
+		 * @enabled_at: Timestamp when busy stats were enabled.
+		 */
+		ktime_t enabled_at;
+		/**
+		 * @start: Timestamp of the last idle to active transition.
+		 *
+		 * Idle is defined as active == 0, active is active > 0.
+		 */
+		ktime_t start;
+		/**
+		 * @total: Total time this engine was busy.
+		 *
+		 * Accumulated time not counting the most recent block in cases
+		 * where engine is currently busy (active > 0).
+		 */
+		ktime_t total;
+	} stats;
 };
 
+static inline bool intel_engine_needs_cmd_parser(struct intel_engine_cs *engine)
+{
+	return engine->flags & I915_ENGINE_NEEDS_CMD_PARSER;
+}
+
+static inline bool intel_engine_supports_stats(struct intel_engine_cs *engine)
+{
+	return engine->flags & I915_ENGINE_SUPPORTS_STATS;
+}
+
 static inline void
 execlists_set_active(struct intel_engine_execlists *execlists,
 		     unsigned int bit)
@@ -939,4 +1010,67 @@ bool intel_engine_can_store_dword(struct intel_engine_cs *engine);
 
 void intel_engine_dump(struct intel_engine_cs *engine, struct drm_printer *p);
 
+struct intel_engine_cs *
+intel_engine_lookup_user(struct drm_i915_private *i915, u8 class, u8 instance);
+
+static inline void intel_engine_context_in(struct intel_engine_cs *engine)
+{
+	unsigned long flags;
+
+	if (READ_ONCE(engine->stats.enabled) == 0)
+		return;
+
+	spin_lock_irqsave(&engine->stats.lock, flags);
+
+	if (engine->stats.enabled > 0) {
+		if (engine->stats.active++ == 0)
+			engine->stats.start = ktime_get();
+		GEM_BUG_ON(engine->stats.active == 0);
+	}
+
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+}
+
+static inline void intel_engine_context_out(struct intel_engine_cs *engine)
+{
+	unsigned long flags;
+
+	if (READ_ONCE(engine->stats.enabled) == 0)
+		return;
+
+	spin_lock_irqsave(&engine->stats.lock, flags);
+
+	if (engine->stats.enabled > 0) {
+		ktime_t last;
+
+		if (engine->stats.active && --engine->stats.active == 0) {
+			/*
+			 * Decrement the active context count and in case GPU
+			 * is now idle add up to the running total.
+			 */
+			last = ktime_sub(ktime_get(), engine->stats.start);
+
+			engine->stats.total = ktime_add(engine->stats.total,
+							last);
+		} else if (engine->stats.active == 0) {
+			/*
+			 * After turning on engine stats, context out might be
+			 * the first event in which case we account from the
+			 * time stats gathering was turned on.
+			 */
+			last = ktime_sub(ktime_get(), engine->stats.enabled_at);
+
+			engine->stats.total = ktime_add(engine->stats.total,
+							last);
+		}
+	}
+
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+}
+
+int intel_enable_engine_stats(struct intel_engine_cs *engine);
+void intel_disable_engine_stats(struct intel_engine_cs *engine);
+
+ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine);
+
 #endif /* _INTEL_RINGBUFFER_H_ */