Merge tag 'drm-for-v4.9' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "Core:
   - Fence destaging work
   - DRIVER_LEGACY to split off legacy drm drivers
   - drm_mm refactoring
   - Splitting drm_crtc.c into chunks and documenting better
   - Display info fixes
   - rbtree support for prime buffer lookup
   - Simple VGA DAC driver

  Panel:
   - Add Nexus 7 panel
   - More simple panels

  i915:
   - Refactoring GEM naming
   - Refactored vma/active tracking
   - Lockless request lookups
   - Better stolen memory support
   - FBC fixes
   - SKL watermark fixes
   - VGPU improvements
   - dma-buf fencing support
   - Better DP dongle support

  amdgpu:
   - Powerplay for Iceland asics
   - Improved GPU reset support
   - UVD/VEC powergating support for CZ/ST
   - Preinitialised VRAM buffer support
   - Virtual display support
   - Initial SI support
   - GTT rework
   - PCI shutdown callback support
   - HPD IRQ storm fixes

  amdkfd:
   - bugfixes

  tilcdc:
   - Atomic modesetting support

  mediatek:
   - AAL + GAMMA engine support
   - Hook up gamma LUT
   - Temporal dithering support

  imx:
   - Pixel clock from devicetree
   - drm bridge support for LVDS bridges
   - active plane reconfiguration
   - VDIC deinterlacer support
   - Frame synchronisation unit support
   - Color space conversion support

  analogix:
   - PSR support
   - Better panel on/off support

  rockchip:
   - rk3399 vop/crtc support
   - PSR support

  vc4:
   - Interlaced vblank timing
   - 3D rendering CPU overhead reduction
   - HDMI output fixes

  tda998x:
   - HDMI audio ASoC support

  sunxi:
   - Allwinner A33 support
   - better TCON support

  msm:
   - DT binding cleanups
   - Explicit fence-fd support

  sti:
   - remove sti415/416 support

  etnaviv:
   - MMUv2 refactoring
   - GC3000 support

  exynos:
   - Refactoring HDMI DCC/PHY
   - G2D pm regression fix
   - Page fault issues with wait for vblank

  There is no nouveau work in this tree, as Ben didn't get a pull
  request in, and he was fighting moving to atomic and adding mst
  support, so maybe best it waits for a cycle"

* tag 'drm-for-v4.9' of git://people.freedesktop.org/~airlied/linux: (1412 commits)
  drm/crtc: constify drm_crtc_index parameter
  drm/i915: Fix conflict resolution from backmerge of v4.8-rc8 to drm-next
  drm/i915/guc: Unwind GuC workqueue reservation if request construction fails
  drm/i915: Reset the breadcrumbs IRQ more carefully
  drm/i915: Force relocations via cpu if we run out of idle aperture
  drm/i915: Distinguish last emitted request from last submitted request
  drm/i915: Allow DP to work w/o EDID
  drm/i915: Move long hpd handling into the hotplug work
  drm/i915/execlists: Reinitialise context image after GPU hang
  drm/i915: Use correct index for backtracking HUNG semaphores
  drm/i915: Unalias obj->phys_handle and obj->userptr
  drm/i915: Just clear the mmiodebug before a register access
  drm/i915/gen9: only add the planes actually affected by ddb changes
  drm/i915: Allow PCH DPLL sharing regardless of DPLL_SDVO_HIGH_SPEED
  drm/i915/bxt: Fix HDMI DPLL configuration
  drm/i915/gen9: fix the watermark res_blocks value
  drm/i915/gen9: fix plane_blocks_per_line on watermarks calculations
  drm/i915/gen9: minimum scanlines for Y tile is not always 4
  drm/i915/gen9: fix the WaWmMemoryReadLatency implementation
  drm/i915/kbl: KBL also needs to run the SAGV code
  ...

5 files changed, 98 insertions, 160 deletions

diff --git a/include/linux/fence-array.h b/include/linux/fence-array.h
index 86baaa45567c..a44794e508df 100644
--- a/include/linux/fence-array.h
+++ b/include/linux/fence-array.h
@@ -52,6 +52,16 @@ struct fence_array {
 extern const struct fence_ops fence_array_ops;
 
 /**
+ * fence_is_array - check if a fence is from the array subsclass
+ *
+ * Return true if it is a fence_array and false otherwise.
+ */
+static inline bool fence_is_array(struct fence *fence)
+{
+	return fence->ops == &fence_array_ops;
+}
+
+/**
  * to_fence_array - cast a fence to a fence_array
  * @fence: fence to cast to a fence_array
  *
diff --git a/include/linux/fence.h b/include/linux/fence.h
index 2ac6fa5f4712..0d763053f97a 100644
--- a/include/linux/fence.h
+++ b/include/linux/fence.h
@@ -60,7 +60,7 @@ struct fence_cb;
  * implementer of the fence for its own purposes. Can be used in different
  * ways by different fence implementers, so do not rely on this.
  *
- * *) Since atomic bitops are used, this is not guaranteed to be the case.
+ * Since atomic bitops are used, this is not guaranteed to be the case.
  * Particularly, if the bit was set, but fence_signal was called right
  * before this bit was set, it would have been able to set the
  * FENCE_FLAG_SIGNALED_BIT, before enable_signaling was called.
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index 645ad06b5d52..58df02bd93c9 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -31,16 +31,16 @@
  * See Documentation/io-mapping.txt
  */
 
-#ifdef CONFIG_HAVE_ATOMIC_IOMAP
-
-#include <asm/iomap.h>
-
 struct io_mapping {
 	resource_size_t base;
 	unsigned long size;
 	pgprot_t prot;
+	void __iomem *iomem;
 };
 
+#ifdef CONFIG_HAVE_ATOMIC_IOMAP
+
+#include <asm/iomap.h>
 /*
  * For small address space machines, mapping large objects
  * into the kernel virtual space isn't practical. Where
@@ -49,34 +49,25 @@ struct io_mapping {
  */
 
 static inline struct io_mapping *
-io_mapping_create_wc(resource_size_t base, unsigned long size)
+io_mapping_init_wc(struct io_mapping *iomap,
+		   resource_size_t base,
+		   unsigned long size)
 {
-	struct io_mapping *iomap;
 	pgprot_t prot;
 
-	iomap = kmalloc(sizeof(*iomap), GFP_KERNEL);
-	if (!iomap)
-		goto out_err;
-
 	if (iomap_create_wc(base, size, &prot))
-		goto out_free;
+		return NULL;
 
 	iomap->base = base;
 	iomap->size = size;
 	iomap->prot = prot;
 	return iomap;
-
-out_free:
-	kfree(iomap);
-out_err:
-	return NULL;
 }
 
 static inline void
-io_mapping_free(struct io_mapping *mapping)
+io_mapping_fini(struct io_mapping *mapping)
 {
 	iomap_free(mapping->base, mapping->size);
-	kfree(mapping);
 }
 
 /* Atomic map/unmap */
@@ -121,21 +112,46 @@ io_mapping_unmap(void __iomem *vaddr)
 #else
 
 #include <linux/uaccess.h>
-
-/* this struct isn't actually defined anywhere */
-struct io_mapping;
+#include <asm/pgtable.h>
 
 /* Create the io_mapping object*/
 static inline struct io_mapping *
-io_mapping_create_wc(resource_size_t base, unsigned long size)
+io_mapping_init_wc(struct io_mapping *iomap,
+		   resource_size_t base,
+		   unsigned long size)
 {
-	return (struct io_mapping __force *) ioremap_wc(base, size);
+	iomap->base = base;
+	iomap->size = size;
+	iomap->iomem = ioremap_wc(base, size);
+#if defined(pgprot_noncached_wc) /* archs can't agree on a name ... */
+	iomap->prot = pgprot_noncached_wc(PAGE_KERNEL);
+#elif defined(pgprot_writecombine)
+	iomap->prot = pgprot_writecombine(PAGE_KERNEL);
+#else
+	iomap->prot = pgprot_noncached(PAGE_KERNEL);
+#endif
+
+	return iomap;
 }
 
 static inline void
-io_mapping_free(struct io_mapping *mapping)
+io_mapping_fini(struct io_mapping *mapping)
+{
+	iounmap(mapping->iomem);
+}
+
+/* Non-atomic map/unmap */
+static inline void __iomem *
+io_mapping_map_wc(struct io_mapping *mapping,
+		  unsigned long offset,
+		  unsigned long size)
+{
+	return mapping->iomem + offset;
+}
+
+static inline void
+io_mapping_unmap(void __iomem *vaddr)
 {
-	iounmap((void __force __iomem *) mapping);
 }
 
 /* Atomic map/unmap */
@@ -145,30 +161,42 @@ io_mapping_map_atomic_wc(struct io_mapping *mapping,
 {
 	preempt_disable();
 	pagefault_disable();
-	return ((char __force __iomem *) mapping) + offset;
+	return io_mapping_map_wc(mapping, offset, PAGE_SIZE);
 }
 
 static inline void
 io_mapping_unmap_atomic(void __iomem *vaddr)
 {
+	io_mapping_unmap(vaddr);
 	pagefault_enable();
 	preempt_enable();
 }
 
-/* Non-atomic map/unmap */
-static inline void __iomem *
-io_mapping_map_wc(struct io_mapping *mapping,
-		  unsigned long offset,
-		  unsigned long size)
+#endif /* HAVE_ATOMIC_IOMAP */
+
+static inline struct io_mapping *
+io_mapping_create_wc(resource_size_t base,
+		     unsigned long size)
 {
-	return ((char __force __iomem *) mapping) + offset;
+	struct io_mapping *iomap;
+
+	iomap = kmalloc(sizeof(*iomap), GFP_KERNEL);
+	if (!iomap)
+		return NULL;
+
+	if (!io_mapping_init_wc(iomap, base, size)) {
+		kfree(iomap);
+		return NULL;
+	}
+
+	return iomap;
 }
 
 static inline void
-io_mapping_unmap(void __iomem *vaddr)
+io_mapping_free(struct io_mapping *iomap)
 {
+	io_mapping_fini(iomap);
+	kfree(iomap);
 }
 
-#endif /* HAVE_ATOMIC_IOMAP */
-
 #endif /* _LINUX_IO_MAPPING_H */
diff --git a/include/linux/sync_file.h b/include/linux/sync_file.h
index c6ffe8b0725c..aa17ccfc2f57 100644
--- a/include/linux/sync_file.h
+++ b/include/linux/sync_file.h
@@ -19,12 +19,7 @@
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/fence.h>
-
-struct sync_file_cb {
-	struct fence_cb cb;
-	struct fence *fence;
-	struct sync_file *sync_file;
-};
+#include <linux/fence-array.h>
 
 /**
  * struct sync_file - sync file to export to the userspace
@@ -32,10 +27,9 @@ struct sync_file_cb {
  * @kref:		reference count on fence.
  * @name:		name of sync_file.  Useful for debugging
  * @sync_file_list:	membership in global file list
- * @num_fences:		number of sync_pts in the fence
  * @wq:			wait queue for fence signaling
- * @status:		0: signaled, >0:active, <0: error
- * @cbs:		sync_pts callback information
+ * @fence:		fence with the fences in the sync_file
+ * @cb:			fence callback information
  */
 struct sync_file {
 	struct file		*file;
@@ -44,14 +38,16 @@ struct sync_file {
 #ifdef CONFIG_DEBUG_FS
 	struct list_head	sync_file_list;
 #endif
-	int num_fences;
 
 	wait_queue_head_t	wq;
-	atomic_t		status;
 
-	struct sync_file_cb	cbs[];
+	struct fence		*fence;
+	struct fence_cb cb;
 };
 
+#define POLL_ENABLED FENCE_FLAG_USER_BITS
+
 struct sync_file *sync_file_create(struct fence *fence);
+struct fence *sync_file_get_fence(int fd);
 
 #endif /* _LINUX_SYNC_H */
diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h
index 8c3b412d84df..ee162e3e879b 100644
--- a/include/linux/vgaarb.h
+++ b/include/linux/vgaarb.h
@@ -73,34 +73,6 @@ static inline void vga_set_legacy_decoding(struct pci_dev *pdev,
 					   unsigned int decodes) { };
 #endif
 
-/**
- *     vga_get         - acquire & locks VGA resources
- *
- *     @pdev: pci device of the VGA card or NULL for the system default
- *     @rsrc: bit mask of resources to acquire and lock
- *     @interruptible: blocking should be interruptible by signals ?
- *
- *     This function acquires VGA resources for the given
- *     card and mark those resources locked. If the resource requested
- *     are "normal" (and not legacy) resources, the arbiter will first check
- *     whether the card is doing legacy decoding for that type of resource. If
- *     yes, the lock is "converted" into a legacy resource lock.
- *     The arbiter will first look for all VGA cards that might conflict
- *     and disable their IOs and/or Memory access, including VGA forwarding
- *     on P2P bridges if necessary, so that the requested resources can
- *     be used. Then, the card is marked as locking these resources and
- *     the IO and/or Memory accesse are enabled on the card (including
- *     VGA forwarding on parent P2P bridges if any).
- *     This function will block if some conflicting card is already locking
- *     one of the required resources (or any resource on a different bus
- *     segment, since P2P bridges don't differenciate VGA memory and IO
- *     afaik). You can indicate whether this blocking should be interruptible
- *     by a signal (for userland interface) or not.
- *     Must not be called at interrupt time or in atomic context.
- *     If the card already owns the resources, the function succeeds.
- *     Nested calls are supported (a per-resource counter is maintained)
- */
-
 #if defined(CONFIG_VGA_ARB)
 extern int vga_get(struct pci_dev *pdev, unsigned int rsrc, int interruptible);
 #else
@@ -108,11 +80,14 @@ static inline int vga_get(struct pci_dev *pdev, unsigned int rsrc, int interrupt
 #endif
 
 /**
- *     vga_get_interruptible
+ * vga_get_interruptible
+ * @pdev: pci device of the VGA card or NULL for the system default
+ * @rsrc: bit mask of resources to acquire and lock
  *
- *     Shortcut to vga_get
+ * Shortcut to vga_get with interruptible set to true.
+ *
+ * On success, release the VGA resource again with vga_put().
  */
-
 static inline int vga_get_interruptible(struct pci_dev *pdev,
 					unsigned int rsrc)
 {
@@ -120,47 +95,26 @@ static inline int vga_get_interruptible(struct pci_dev *pdev,
 }
 
 /**
- *     vga_get_uninterruptible
+ * vga_get_uninterruptible - shortcut to vga_get()
+ * @pdev: pci device of the VGA card or NULL for the system default
+ * @rsrc: bit mask of resources to acquire and lock
  *
- *     Shortcut to vga_get
+ * Shortcut to vga_get with interruptible set to false.
+ *
+ * On success, release the VGA resource again with vga_put().
  */
-
 static inline int vga_get_uninterruptible(struct pci_dev *pdev,
 					  unsigned int rsrc)
 {
        return vga_get(pdev, rsrc, 0);
 }
 
-/**
- *     vga_tryget      - try to acquire & lock legacy VGA resources
- *
- *     @pdev: pci devivce of VGA card or NULL for system default
- *     @rsrc: bit mask of resources to acquire and lock
- *
- *     This function performs the same operation as vga_get(), but
- *     will return an error (-EBUSY) instead of blocking if the resources
- *     are already locked by another card. It can be called in any context
- */
-
 #if defined(CONFIG_VGA_ARB)
 extern int vga_tryget(struct pci_dev *pdev, unsigned int rsrc);
 #else
 static inline int vga_tryget(struct pci_dev *pdev, unsigned int rsrc) { return 0; }
 #endif
 
-/**
- *     vga_put         - release lock on legacy VGA resources
- *
- *     @pdev: pci device of VGA card or NULL for system default
- *     @rsrc: but mask of resource to release
- *
- *     This function releases resources previously locked by vga_get()
- *     or vga_tryget(). The resources aren't disabled right away, so
- *     that a subsequence vga_get() on the same card will succeed
- *     immediately. Resources have a counter, so locks are only
- *     released if the counter reaches 0.
- */
-
 #if defined(CONFIG_VGA_ARB)
 extern void vga_put(struct pci_dev *pdev, unsigned int rsrc);
 #else
@@ -168,25 +122,6 @@ extern void vga_put(struct pci_dev *pdev, unsigned int rsrc);
 #endif
 
 
-/**
- *     vga_default_device
- *
- *     This can be defined by the platform. The default implementation
- *     is rather dumb and will probably only work properly on single
- *     vga card setups and/or x86 platforms.
- *
- *     If your VGA default device is not PCI, you'll have to return
- *     NULL here. In this case, I assume it will not conflict with
- *     any PCI card. If this is not true, I'll have to define two archs
- *     hooks for enabling/disabling the VGA default device if that is
- *     possible. This may be a problem with real _ISA_ VGA cards, in
- *     addition to a PCI one. I don't know at this point how to deal
- *     with that card. Can theirs IOs be disabled at all ? If not, then
- *     I suppose it's a matter of having the proper arch hook telling
- *     us about it, so we basically never allow anybody to succeed a
- *     vga_get()...
- */
-
 #ifdef CONFIG_VGA_ARB
 extern struct pci_dev *vga_default_device(void);
 extern void vga_set_default_device(struct pci_dev *pdev);
@@ -195,14 +130,11 @@ static inline struct pci_dev *vga_default_device(void) { return NULL; };
 static inline void vga_set_default_device(struct pci_dev *pdev) { };
 #endif
 
-/**
- *     vga_conflicts
- *
- *     Architectures should define this if they have several
- *     independent PCI domains that can afford concurrent VGA
- *     decoding
+/*
+ * Architectures should define this if they have several
+ * independent PCI domains that can afford concurrent VGA
+ * decoding
  */
-
 #ifndef __ARCH_HAS_VGA_CONFLICT
 static inline int vga_conflicts(struct pci_dev *p1, struct pci_dev *p2)
 {
@@ -210,34 +142,6 @@ static inline int vga_conflicts(struct pci_dev *p1, struct pci_dev *p2)
 }
 #endif
 
-/**
- *	vga_client_register
- *
- *	@pdev: pci device of the VGA client
- *	@cookie: client cookie to be used in callbacks
- *	@irq_set_state: irq state change callback
- *	@set_vga_decode: vga decode change callback
- *
- * 	return value: 0 on success, -1 on failure
- * 	Register a client with the VGA arbitration logic
- *
- *	Clients have two callback mechanisms they can use.
- *	irq enable/disable callback -
- *		If a client can't disable its GPUs VGA resources, then we
- *		need to be able to ask it to turn off its irqs when we
- *		turn off its mem and io decoding.
- *	set_vga_decode
- *		If a client can disable its GPU VGA resource, it will
- *		get a callback from this to set the encode/decode state
- *
- * Rationale: we cannot disable VGA decode resources unconditionally
- * some single GPU laptops seem to require ACPI or BIOS access to the
- * VGA registers to control things like backlights etc.
- * Hopefully newer multi-GPU laptops do something saner, and desktops
- * won't have any special ACPI for this.
- * They driver will get a callback when VGA arbitration is first used
- * by userspace since we some older X servers have issues.
- */
 #if defined(CONFIG_VGA_ARB)
 int vga_client_register(struct pci_dev *pdev, void *cookie,
 			void (*irq_set_state)(void *cookie, bool state),