Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "I Was Almost Tempted To Capitalise Every Word, but then I decided I
  couldn't read it myself!

  I've also got one pull request for the sti driver outstanding.  It
  relied on a commit in Greg's tree and I didn't find out in time, that
  commit is in your tree now so I might send that along once this is
  merged.

  I also had the accidental misfortune to have access to a Skylake on my
  desk for a few days, and I've had to encourage Intel to try harder,
  which seems to be happening now.

  Here is the main drm-next pull request for 4.4.

  Highlights:

  New driver:
        vc4 driver for the Rasberry Pi VPU.
        (From Eric Anholt at Broadcom.)

  Core:
        Atomic fbdev support
        Atomic helpers for runtime pm
        dp/aux i2c STATUS_UPDATE handling
        struct_mutex usage cleanups.
        Generic of probing support.

  Documentation:
        Kerneldoc for VGA switcheroo code.
        Rename to gpu instead of drm to reflect scope.

  i915:
        Skylake GuC firmware fixes
        HPD A support
        VBT backlight fallbacks
        Fastboot by default for some systems
        FBC work
        BXT/SKL workarounds
        Skylake deeper sleep state fixes

  amdgpu:
        Enable GPU scheduler by default
        New atombios opcodes
        GPUVM debugging options
        Stoney support.
        Fencing cleanups.

  radeon:
        More efficient CS checking

  nouveau:
        gk20a instance memory handling improvements.
        Improved PGOB detection and GK107 support
        Kepler GDDR5 PLL statbility improvement
        G8x/GT2xx reclock improvements
        new userspace API compatiblity fixes.

  virtio-gpu:
        Add 3D support - qemu 2.5 has it merged for it's gtk backend.

  msm:
        Initial msm88896 (snapdragon 8200)

  exynos:
        HDMI cleanups
        Enable mixer driver byt default
        Add DECON-TV support

  vmwgfx:
        Move to using memremap + fixes.

  rcar-du:
        Add support for R8A7793/4 DU

  armada:
        Remove support for non-component mode
        Improved plane handling
        Power savings while in DPMS off.

  tda998x:
        Remove unused slave encoder support
        Use more HDMI helpers
        Fix EDID read handling

  dwhdmi:
        Interlace video mode support for ipu-v3/dw_hdmi
        Hotplug state fixes
        Audio driver integration

  imx:
        More color formats support.

  tegra:
        Minor fixes/improvements"

[ Merge fixup: remove unused variable 'dev' that had all uses removed in
  commit 4e270f0880: "drm/gem: Drop struct_mutex requirement from
  drm_gem_mmap_obj" ]

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (764 commits)
  drm/vmwgfx: Relax irq locking somewhat
  drm/vmwgfx: Properly flush cursor updates and page-flips
  drm/i915/skl: disable display side power well support for now
  drm/i915: Extend DSL readout fix to BDW and SKL.
  drm/i915: Do graphics device reset under forcewake
  drm/i915: Skip fence installation for objects with rotated views (v4)
  vga_switcheroo: Drop client power state VGA_SWITCHEROO_INIT
  drm/amdgpu: group together common fence implementation
  drm/amdgpu: remove AMDGPU_FENCE_OWNER_MOVE
  drm/amdgpu: remove now unused fence functions
  drm/amdgpu: fix fence fallback check
  drm/amdgpu: fix stoping the scheduler timeout
  drm/amdgpu: cleanup on error in amdgpu_cs_ioctl()
  drm/i915: Fix locking around GuC firmware load
  drm/amdgpu: update Fiji's Golden setting
  drm/amdgpu: update Fiji's rev id
  drm/amdgpu: extract common code in vi_common_early_init
  drm/amd/scheduler: don't oops on failure to load
  drm/amdgpu: don't oops on failure to load (v2)
  drm/amdgpu: don't VT switch on suspend
  ...

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -79,6 +79,8 @@ extern int amdgpu_bapm;
 extern int amdgpu_deep_color;
 extern int amdgpu_vm_size;
 extern int amdgpu_vm_block_size;
+extern int amdgpu_vm_fault_stop;
+extern int amdgpu_vm_debug;
 extern int amdgpu_enable_scheduler;
 extern int amdgpu_sched_jobs;
 extern int amdgpu_sched_hw_submission;
@@ -343,7 +345,6 @@ struct amdgpu_ring_funcs {
 	/* testing functions */
 	int (*test_ring)(struct amdgpu_ring *ring);
 	int (*test_ib)(struct amdgpu_ring *ring);
-	bool (*is_lockup)(struct amdgpu_ring *ring);
 	/* insert NOP packets */
 	void (*insert_nop)(struct amdgpu_ring *ring, uint32_t count);
 };
@@ -404,7 +405,6 @@ struct amdgpu_fence_driver {
 /* some special values for the owner field */
 #define AMDGPU_FENCE_OWNER_UNDEFINED	((void*)0ul)
 #define AMDGPU_FENCE_OWNER_VM		((void*)1ul)
-#define AMDGPU_FENCE_OWNER_MOVE		((void*)2ul)
 
 #define AMDGPU_FENCE_FLAG_64BIT         (1 << 0)
 #define AMDGPU_FENCE_FLAG_INT           (1 << 1)
@@ -446,58 +446,11 @@ int amdgpu_fence_wait_next(struct amdgpu_ring *ring);
 int amdgpu_fence_wait_empty(struct amdgpu_ring *ring);
 unsigned amdgpu_fence_count_emitted(struct amdgpu_ring *ring);
 
-signed long amdgpu_fence_wait_any(struct amdgpu_device *adev,
-				  struct fence **array,
-				  uint32_t count,
-				  bool intr,
-				  signed long t);
-struct amdgpu_fence *amdgpu_fence_ref(struct amdgpu_fence *fence);
-void amdgpu_fence_unref(struct amdgpu_fence **fence);
-
 bool amdgpu_fence_need_sync(struct amdgpu_fence *fence,
 			    struct amdgpu_ring *ring);
 void amdgpu_fence_note_sync(struct amdgpu_fence *fence,
 			    struct amdgpu_ring *ring);
 
-static inline struct amdgpu_fence *amdgpu_fence_later(struct amdgpu_fence *a,
-						      struct amdgpu_fence *b)
-{
-	if (!a) {
-		return b;
-	}
-
-	if (!b) {
-		return a;
-	}
-
-	BUG_ON(a->ring != b->ring);
-
-	if (a->seq > b->seq) {
-		return a;
-	} else {
-		return b;
-	}
-}
-
-static inline bool amdgpu_fence_is_earlier(struct amdgpu_fence *a,
-					   struct amdgpu_fence *b)
-{
-	if (!a) {
-		return false;
-	}
-
-	if (!b) {
-		return true;
-	}
-
-	BUG_ON(a->ring != b->ring);
-
-	return a->seq < b->seq;
-}
-
-int amdgpu_user_fence_emit(struct amdgpu_ring *ring, struct amdgpu_user_fence *user,
-			   void *owner, struct amdgpu_fence **fence);
-
 /*
  * TTM.
  */
@@ -708,7 +661,7 @@ void amdgpu_semaphore_free(struct amdgpu_device *adev,
  */
 struct amdgpu_sync {
 	struct amdgpu_semaphore *semaphores[AMDGPU_NUM_SYNCS];
-	struct amdgpu_fence	*sync_to[AMDGPU_MAX_RINGS];
+	struct fence		*sync_to[AMDGPU_MAX_RINGS];
 	DECLARE_HASHTABLE(fences, 4);
 	struct fence	        *last_vm_update;
 };
@@ -905,8 +858,6 @@ struct amdgpu_ring {
 	unsigned		ring_size;
 	unsigned		ring_free_dw;
 	int			count_dw;
-	atomic_t		last_rptr;
-	atomic64_t		last_activity;
 	uint64_t		gpu_addr;
 	uint32_t		align_mask;
 	uint32_t		ptr_mask;
@@ -960,6 +911,11 @@ struct amdgpu_ring {
 #define AMDGPU_PTE_FRAG_64KB	(4 << 7)
 #define AMDGPU_LOG2_PAGES_PER_FRAG 4
 
+/* How to programm VM fault handling */
+#define AMDGPU_VM_FAULT_STOP_NEVER	0
+#define AMDGPU_VM_FAULT_STOP_FIRST	1
+#define AMDGPU_VM_FAULT_STOP_ALWAYS	2
+
 struct amdgpu_vm_pt {
 	struct amdgpu_bo		*bo;
 	uint64_t			addr;
@@ -971,7 +927,7 @@ struct amdgpu_vm_id {
 	/* last flushed PD/PT update */
 	struct fence	        *flushed_updates;
 	/* last use of vmid */
-	struct amdgpu_fence	*last_id_use;
+	struct fence		*last_id_use;
 };
 
 struct amdgpu_vm {
@@ -1004,7 +960,7 @@ struct amdgpu_vm {
 };
 
 struct amdgpu_vm_manager {
-	struct amdgpu_fence		*active[AMDGPU_NUM_VM];
+	struct fence			*active[AMDGPU_NUM_VM];
 	uint32_t			max_pfn;
 	/* number of VMIDs */
 	unsigned			nvm;
@@ -1223,8 +1179,6 @@ void amdgpu_ring_commit(struct amdgpu_ring *ring);
 void amdgpu_ring_unlock_commit(struct amdgpu_ring *ring);
 void amdgpu_ring_undo(struct amdgpu_ring *ring);
 void amdgpu_ring_unlock_undo(struct amdgpu_ring *ring);
-void amdgpu_ring_lockup_update(struct amdgpu_ring *ring);
-bool amdgpu_ring_test_lockup(struct amdgpu_ring *ring);
 unsigned amdgpu_ring_backup(struct amdgpu_ring *ring,
 			    uint32_t **data);
 int amdgpu_ring_restore(struct amdgpu_ring *ring,
@@ -1234,6 +1188,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 		     struct amdgpu_irq_src *irq_src, unsigned irq_type,
 		     enum amdgpu_ring_type ring_type);
 void amdgpu_ring_fini(struct amdgpu_ring *ring);
+struct amdgpu_ring *amdgpu_ring_from_fence(struct fence *f);
 
 /*
  * CS.
@@ -1709,7 +1664,7 @@ struct amdgpu_vce {
 /*
  * SDMA
  */
-struct amdgpu_sdma {
+struct amdgpu_sdma_instance {
 	/* SDMA firmware */
 	const struct firmware	*fw;
 	uint32_t		fw_version;
@@ -1719,6 +1674,13 @@ struct amdgpu_sdma {
 	bool			burst_nop;
 };
 
+struct amdgpu_sdma {
+	struct amdgpu_sdma_instance instance[AMDGPU_MAX_SDMA_INSTANCES];
+	struct amdgpu_irq_src	trap_irq;
+	struct amdgpu_irq_src	illegal_inst_irq;
+	int 			num_instances;
+};
+
 /*
  * Firmware
  */
@@ -1751,11 +1713,11 @@ void amdgpu_test_syncing(struct amdgpu_device *adev);
 int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr);
 void amdgpu_mn_unregister(struct amdgpu_bo *bo);
 #else
-static int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
+static inline int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
 {
 	return -ENODEV;
 }
-static void amdgpu_mn_unregister(struct amdgpu_bo *bo) {}
+static inline void amdgpu_mn_unregister(struct amdgpu_bo *bo) {}
 #endif
 
 /*
@@ -1947,7 +1909,6 @@ struct amdgpu_device {
 	struct device			*dev;
 	struct drm_device		*ddev;
 	struct pci_dev			*pdev;
-	struct rw_semaphore		exclusive_lock;
 
 	/* ASIC */
 	enum amd_asic_type		asic_type;
@@ -1961,7 +1922,6 @@ struct amdgpu_device {
 	bool				suspend;
 	bool				need_dma32;
 	bool				accel_working;
-	bool				needs_reset;
 	struct work_struct 		reset_work;
 	struct notifier_block		acpi_nb;
 	struct amdgpu_i2c_chan		*i2c_bus[AMDGPU_MAX_I2C_BUS];
@@ -2065,9 +2025,7 @@ struct amdgpu_device {
 	struct amdgpu_gfx		gfx;
 
 	/* sdma */
-	struct amdgpu_sdma		sdma[AMDGPU_MAX_SDMA_INSTANCES];
-	struct amdgpu_irq_src		sdma_trap_irq;
-	struct amdgpu_irq_src		sdma_illegal_inst_irq;
+	struct amdgpu_sdma		sdma;
 
 	/* uvd */
 	bool				has_uvd;
@@ -2204,17 +2162,18 @@ static inline void amdgpu_ring_write(struct amdgpu_ring *ring, uint32_t v)
 	ring->ring_free_dw--;
 }
 
-static inline struct amdgpu_sdma * amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
+static inline struct amdgpu_sdma_instance *
+amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 	int i;
 
-	for (i = 0; i < AMDGPU_MAX_SDMA_INSTANCES; i++)
-		if (&adev->sdma[i].ring == ring)
+	for (i = 0; i < adev->sdma.num_instances; i++)
+		if (&adev->sdma.instance[i].ring == ring)
 			break;
 
 	if (i < AMDGPU_MAX_SDMA_INSTANCES)
-		return &adev->sdma[i];
+		return &adev->sdma.instance[i];
 	else
 		return NULL;
 }
@@ -2241,7 +2200,6 @@ static inline struct amdgpu_sdma * amdgpu_get_sdma_instance(struct amdgpu_ring *
 #define amdgpu_ring_parse_cs(r, p, ib) ((r)->funcs->parse_cs((p), (ib)))
 #define amdgpu_ring_test_ring(r) (r)->funcs->test_ring((r))
 #define amdgpu_ring_test_ib(r) (r)->funcs->test_ib((r))
-#define amdgpu_ring_is_lockup(r) (r)->funcs->is_lockup((r))
 #define amdgpu_ring_get_rptr(r) (r)->funcs->get_rptr((r))
 #define amdgpu_ring_get_wptr(r) (r)->funcs->get_wptr((r))
 #define amdgpu_ring_set_wptr(r) (r)->funcs->set_wptr((r))
@@ -2350,10 +2308,10 @@ void amdgpu_driver_preclose_kms(struct drm_device *dev,
 				struct drm_file *file_priv);
 int amdgpu_suspend_kms(struct drm_device *dev, bool suspend, bool fbcon);
 int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon);
-u32 amdgpu_get_vblank_counter_kms(struct drm_device *dev, int crtc);
-int amdgpu_enable_vblank_kms(struct drm_device *dev, int crtc);
-void amdgpu_disable_vblank_kms(struct drm_device *dev, int crtc);
-int amdgpu_get_vblank_timestamp_kms(struct drm_device *dev, int crtc,
+u32 amdgpu_get_vblank_counter_kms(struct drm_device *dev, unsigned int pipe);
+int amdgpu_enable_vblank_kms(struct drm_device *dev, unsigned int pipe);
+void amdgpu_disable_vblank_kms(struct drm_device *dev, unsigned int pipe);
+int amdgpu_get_vblank_timestamp_kms(struct drm_device *dev, unsigned int pipe,
 				    int *max_error,
 				    struct timeval *vblank_time,
 				    unsigned flags);