Merge tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for v4.15.

  Core:
   - Atomic object lifetime fixes
   - Atomic iterator improvements
   - Sparse/smatch fixes
   - Legacy kms ioctls to be interruptible
   - EDID override improvements
   - fb/gem helper cleanups
   - Simple outreachy patches
   - Documentation improvements
   - Fix dma-buf rcu races
   - DRM mode object leasing for improving VR use cases.
   - vgaarb improvements for non-x86 platforms.

  New driver:
   - tve200: Faraday Technology TVE200 block.

     This "TV Encoder" encodes a ITU-T BT.656 stream and can be found in
     the StorLink SL3516 (later Cortina Systems CS3516) as well as the
     Grain Media GM8180.

  New bridges:
   - SiI9234 support

  New panels:
   - S6E63J0X03, OTM8009A, Seiko 43WVF1G, 7" rpi touch panel, Toshiba
     LT089AC19000, Innolux AT043TN24

  i915:
   - Remove Coffeelake from alpha support
   - Cannonlake workarounds
   - Infoframe refactoring for DisplayPort
   - VBT updates
   - DisplayPort vswing/emph/buffer translation refactoring
   - CCS fixes
   - Restore GPU clock boost on missed vblanks
   - Scatter list updates for userptr allocations
   - Gen9+ transition watermarks
   - Display IPC (Isochronous Priority Control)
   - Private PAT management
   - GVT: improved error handling and pci config sanitizing
   - Execlist refactoring
   - Transparent Huge Page support
   - User defined priorities support
   - HuC/GuC firmware refactoring
   - DP MST fixes
   - eDP power sequencing fixes
   - Use RCU instead of stop_machine
   - PSR state tracking support
   - Eviction fixes
   - BDW DP aux channel timeout fixes
   - LSPCON fixes
   - Cannonlake PLL fixes

  amdgpu:
   - Per VM BO support
   - Powerplay cleanups
   - CI powerplay support
   - PASID mgr for kfd
   - SR-IOV fixes
   - initial GPU reset for vega10
   - Prime mmap support
   - TTM updates
   - Clock query interface for Raven
   - Fence to handle ioctl
   - UVD encode ring support on Polaris
   - Transparent huge page DMA support
   - Compute LRU pipe tweaks
   - BO flag to allow buffers to opt out of implicit sync
   - CTX priority setting API
   - VRAM lost infrastructure plumbing

  qxl:
   - fix flicker since atomic rework

  amdkfd:
   - Further improvements from internal AMD tree
   - Usermode events
   - Drop radeon support

  nouveau:
   - Pascal temperature sensor support
   - Improved BAR2 handling
   - MMU rework to support Pascal MMU

  exynos:
   - Improved HDMI/mixer support
   - HDMI audio interface support

  tegra:
   - Prep work for tegra186
   - Cleanup/fixes

  msm:
   - Preemption support for a5xx
   - Display fixes for 8x96 (snapdragon 820)
   - Async cursor plane fixes
   - FW loading rework
   - GPU debugging improvements

  vc4:
   - Prep for DSI panels
   - fix T-format tiling scanout
   - New madvise ioctl

  Rockchip:
   - LVDS support

  omapdrm:
   - omap4 HDMI CEC support

  etnaviv:
   - GPU performance counters groundwork

  sun4i:
   - refactor driver load + TCON backend
   - HDMI improvements
   - A31 support
   - Misc fixes

  udl:
   - Probe/EDID read fixes.

  tilcdc:
   - Misc fixes.

  pl111:
   - Support more variants

  adv7511:
   - Improve EDID handling.
   - HDMI CEC support

  sii8620:
   - Add remote control support"

* tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux: (1480 commits)
  drm/rockchip: analogix_dp: Use mutex rather than spinlock
  drm/mode_object: fix documentation for object lookups.
  drm/i915: Reorder context-close to avoid calling i915_vma_close() under RCU
  drm/i915: Move init_clock_gating() back to where it was
  drm/i915: Prune the reservation shared fence array
  drm/i915: Idle the GPU before shinking everything
  drm/i915: Lock llist_del_first() vs llist_del_all()
  drm/i915: Calculate ironlake intermediate watermarks correctly, v2.
  drm/i915: Disable lazy PPGTT page table optimization for vGPU
  drm/i915/execlists: Remove the priority "optimisation"
  drm/i915: Filter out spurious execlists context-switch interrupts
  drm/amdgpu: use irq-safe lock for kiq->ring_lock
  drm/amdgpu: bypass lru touch for KIQ ring submission
  drm/amdgpu: Potential uninitialized variable in amdgpu_vm_update_directories()
  drm/amdgpu: potential uninitialized variable in amdgpu_vce_ring_parse_cs()
  drm/amd/powerplay: initialize a variable before using it
  drm/amd/powerplay: suppress KASAN out of bounds warning in vega10_populate_all_memory_levels
  drm/amd/amdgpu: fix evicted VRAM bo adjudgement condition
  drm/vblank: Tune drm_crtc_accurate_vblank_count() WARN down to a debug
  drm/rockchip: add CONFIG_OF dependency for lvds
  ...

1 files changed, 155 insertions, 29 deletions

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 6b2067f10824..2863d5a65187 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -8,6 +8,8 @@
 #include "i915_gem_timeline.h"
 #include "i915_selftest.h"
 
+struct drm_printer;
+
 #define I915_CMD_HASH_ORDER 9
 
 /* Early gen2 devices have a cacheline of just 32 bytes, using 64 is overkill,
@@ -185,6 +187,104 @@ struct i915_priolist {
 	int priority;
 };
 
+/**
+ * struct intel_engine_execlists - execlist submission queue and port state
+ *
+ * The struct intel_engine_execlists represents the combined logical state of
+ * driver and the hardware state for execlist mode of submission.
+ */
+struct intel_engine_execlists {
+	/**
+	 * @irq_tasklet: softirq tasklet for bottom handler
+	 */
+	struct tasklet_struct irq_tasklet;
+
+	/**
+	 * @default_priolist: priority list for I915_PRIORITY_NORMAL
+	 */
+	struct i915_priolist default_priolist;
+
+	/**
+	 * @no_priolist: priority lists disabled
+	 */
+	bool no_priolist;
+
+	/**
+	 * @port: execlist port states
+	 *
+	 * For each hardware ELSP (ExecList Submission Port) we keep
+	 * track of the last request and the number of times we submitted
+	 * that port to hw. We then count the number of times the hw reports
+	 * a context completion or preemption. As only one context can
+	 * be active on hw, we limit resubmission of context to port[0]. This
+	 * is called Lite Restore, of the context.
+	 */
+	struct execlist_port {
+		/**
+		 * @request_count: combined request and submission count
+		 */
+		struct drm_i915_gem_request *request_count;
+#define EXECLIST_COUNT_BITS 2
+#define port_request(p) ptr_mask_bits((p)->request_count, EXECLIST_COUNT_BITS)
+#define port_count(p) ptr_unmask_bits((p)->request_count, EXECLIST_COUNT_BITS)
+#define port_pack(rq, count) ptr_pack_bits(rq, count, EXECLIST_COUNT_BITS)
+#define port_unpack(p, count) ptr_unpack_bits((p)->request_count, count, EXECLIST_COUNT_BITS)
+#define port_set(p, packed) ((p)->request_count = (packed))
+#define port_isset(p) ((p)->request_count)
+#define port_index(p, execlists) ((p) - (execlists)->port)
+
+		/**
+		 * @context_id: context ID for port
+		 */
+		GEM_DEBUG_DECL(u32 context_id);
+
+#define EXECLIST_MAX_PORTS 2
+	} port[EXECLIST_MAX_PORTS];
+
+	/**
+	 * @active: is the HW active? We consider the HW as active after
+	 * submitting any context for execution and until we have seen the
+	 * last context completion event. After that, we do not expect any
+	 * more events until we submit, and so can park the HW.
+	 *
+	 * As we have a small number of different sources from which we feed
+	 * the HW, we track the state of each inside a single bitfield.
+	 */
+	unsigned int active;
+#define EXECLISTS_ACTIVE_USER 0
+#define EXECLISTS_ACTIVE_PREEMPT 1
+
+	/**
+	 * @port_mask: number of execlist ports - 1
+	 */
+	unsigned int port_mask;
+
+	/**
+	 * @queue: queue of requests, in priority lists
+	 */
+	struct rb_root queue;
+
+	/**
+	 * @first: leftmost level in priority @queue
+	 */
+	struct rb_node *first;
+
+	/**
+	 * @fw_domains: forcewake domains for irq tasklet
+	 */
+	unsigned int fw_domains;
+
+	/**
+	 * @csb_head: context status buffer head
+	 */
+	unsigned int csb_head;
+
+	/**
+	 * @csb_use_mmio: access csb through mmio, instead of hwsp
+	 */
+	bool csb_use_mmio;
+};
+
 #define INTEL_ENGINE_CS_MAX_NAME 8
 
 struct intel_engine_cs {
@@ -307,6 +407,14 @@ struct intel_engine_cs {
 	void		(*schedule)(struct drm_i915_gem_request *request,
 				    int priority);
 
+	/*
+	 * Cancel all requests on the hardware, or queued for execution.
+	 * This should only cancel the ready requests that have been
+	 * submitted to the engine (via the engine->submit_request callback).
+	 * This is called when marking the device as wedged.
+	 */
+	void		(*cancel_requests)(struct intel_engine_cs *engine);
+
 	/* Some chipsets are not quite as coherent as advertised and need
 	 * an expensive kick to force a true read of the up-to-date seqno.
 	 * However, the up-to-date seqno is not always required and the last
@@ -373,25 +481,7 @@ struct intel_engine_cs {
 		u32	*(*signal)(struct drm_i915_gem_request *req, u32 *cs);
 	} semaphore;
 
-	/* Execlists */
-	struct tasklet_struct irq_tasklet;
-	struct i915_priolist default_priolist;
-	bool no_priolist;
-	struct execlist_port {
-		struct drm_i915_gem_request *request_count;
-#define EXECLIST_COUNT_BITS 2
-#define port_request(p) ptr_mask_bits((p)->request_count, EXECLIST_COUNT_BITS)
-#define port_count(p) ptr_unmask_bits((p)->request_count, EXECLIST_COUNT_BITS)
-#define port_pack(rq, count) ptr_pack_bits(rq, count, EXECLIST_COUNT_BITS)
-#define port_unpack(p, count) ptr_unpack_bits((p)->request_count, count, EXECLIST_COUNT_BITS)
-#define port_set(p, packed) ((p)->request_count = (packed))
-#define port_isset(p) ((p)->request_count)
-#define port_index(p, e) ((p) - (e)->execlist_port)
-		GEM_DEBUG_DECL(u32 context_id);
-	} execlist_port[2];
-	struct rb_root execlist_queue;
-	struct rb_node *execlist_first;
-	unsigned int fw_domains;
+	struct intel_engine_execlists execlists;
 
 	/* Contexts are pinned whilst they are active on the GPU. The last
 	 * context executed remains active whilst the GPU is idle - the
@@ -444,6 +534,46 @@ struct intel_engine_cs {
 	u32 (*get_cmd_length_mask)(u32 cmd_header);
 };
 
+static inline void
+execlists_set_active(struct intel_engine_execlists *execlists,
+		     unsigned int bit)
+{
+	__set_bit(bit, (unsigned long *)&execlists->active);
+}
+
+static inline void
+execlists_clear_active(struct intel_engine_execlists *execlists,
+		       unsigned int bit)
+{
+	__clear_bit(bit, (unsigned long *)&execlists->active);
+}
+
+static inline bool
+execlists_is_active(const struct intel_engine_execlists *execlists,
+		    unsigned int bit)
+{
+	return test_bit(bit, (unsigned long *)&execlists->active);
+}
+
+static inline unsigned int
+execlists_num_ports(const struct intel_engine_execlists * const execlists)
+{
+	return execlists->port_mask + 1;
+}
+
+static inline void
+execlists_port_complete(struct intel_engine_execlists * const execlists,
+			struct execlist_port * const port)
+{
+	const unsigned int m = execlists->port_mask;
+
+	GEM_BUG_ON(port_index(port, execlists) != 0);
+	GEM_BUG_ON(!execlists_is_active(execlists, EXECLISTS_ACTIVE_USER));
+
+	memmove(port, port + 1, m * sizeof(struct execlist_port));
+	memset(port + m, 0, sizeof(struct execlist_port));
+}
+
 static inline unsigned int
 intel_engine_flag(const struct intel_engine_cs *engine)
 {
@@ -497,6 +627,10 @@ intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value)
 #define I915_GEM_HWS_SCRATCH_INDEX	0x40
 #define I915_GEM_HWS_SCRATCH_ADDR (I915_GEM_HWS_SCRATCH_INDEX << MI_STORE_DWORD_INDEX_SHIFT)
 
+#define I915_HWS_CSB_BUF0_INDEX		0x10
+#define I915_HWS_CSB_WRITE_INDEX	0x1f
+#define CNL_HWS_CSB_WRITE_INDEX		0x2f
+
 struct intel_ring *
 intel_engine_create_ring(struct intel_engine_cs *engine, int size);
 int intel_ring_pin(struct intel_ring *ring,
@@ -736,16 +870,8 @@ bool intel_engines_are_idle(struct drm_i915_private *dev_priv);
 void intel_engines_mark_idle(struct drm_i915_private *i915);
 void intel_engines_reset_default_submission(struct drm_i915_private *i915);
 
-static inline bool
-__intel_engine_can_store_dword(unsigned int gen, unsigned int class)
-{
-	if (gen <= 2)
-		return false; /* uses physical not virtual addresses */
+bool intel_engine_can_store_dword(struct intel_engine_cs *engine);
 
-	if (gen == 6 && class == VIDEO_DECODE_CLASS)
-		return false; /* b0rked */
-
-	return true;
-}
+void intel_engine_dump(struct intel_engine_cs *engine, struct drm_printer *p);
 
 #endif /* _INTEL_RINGBUFFER_H_ */