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

Pull DRM updates from Dave Airlie:
 "Like all good pull reqs this ends with a revert, so it must mean we
  tested it,

[ Ed. That's _one_ way of looking at it ]

  This pull is missing nouveau, Ben has been stuck trying to track down
  a very longstanding bug that revealed itself due to some other
  changes.  I've asked him to send you a direct pull request for nouveau
  once he cleans things up.  I'm away until Monday so don't want to
  delay things, you can make a decision on that when he sends it, I have
  my phone so I can ack things just not really merge much.

  It has one trivial conflict with your tree in armada_drv.c, and also
  the pull request contains some component changes that are already in
  your tree, the base tree from Russell went via Greg's tree already,
  but some stuff still shows up in here that doesn't when I merge my
  tree into yours.

  Otherwise all pretty standard graphics fare, one new driver and
  changes all over the place.

  New drivers:
   - sti kms driver for STMicroelectronics chipsets stih416 and stih407.

  core:
   - lots of cleanups to the drm core
   - DP MST helper code merged
   - universal cursor planes.
   - render nodes enabled by default

  panel:
   - better panel interfaces
   - new panel support
   - non-continuous cock advertising ability

  ttm:
   - shrinker fixes

  i915:
   - hopefully ditched UMS support
   - runtime pm fixes
   - psr tracking and locking - now enabled by default
   - userptr fixes
   - backlight brightness fixes
   - MST support merged
   - runtime PM for dpms
   - primary planes locking fixes
   - gen8 hw semaphore support
   - fbc fixes
   - runtime PM on SOix sleep state hw.
   - mmio base page flipping
   - lots of vlv/chv fixes.
   - universal cursor planes

  radeon:
   - Hawaii fixes
   - display scalar support for non-fixed mode displays
   - new firmware format support
   - dpm on more asics by default
   - GPUVM improvements
   - uncached and wc GTT buffers
   - BOs > visible VRAM

  exynos:
   - i80 interface support
   - module auto-loading
   - ipp driver consolidated.

  armada:
   - irq handling in crtc layer only
   - crtc renumbering
   - add component support
   - DT interaction changes.

  tegra:
   - load as module fixes
   - eDP bpp and sync polarity fixed
   - DSI non-continuous clock mode support
   - better support for importing buffers from nouveau

  msm:
   - mdp5/adq8084 v1.3 hw enablement
   - devicetree clk changse
   - ifc6410 board working

  tda998x:
   - component support
   - DT documentation update

  vmwgfx:
   - fix compat shader namespace"

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (551 commits)
  Revert "drm: drop redundant drm_file->is_master"
  drm/panel: simple: Use devm_gpiod_get_optional()
  drm/dsi: Replace upcasting macro by function
  drm/panel: ld9040: Replace upcasting macro by function
  drm/exynos: dp: Modify driver to support drm_panel
  drm/exynos: Move DP setup into commit()
  drm/panel: simple: Add AUO B133HTN01 panel support
  drm/panel: simple: Support delays in panel functions
  drm/panel: simple: Add proper definition for prepare and unprepare
  drm/panel: s6e8aa0: Add proper definition for prepare and unprepare
  drm/panel: ld9040: Add proper definition for prepare and unprepare
  drm/tegra: Add support for panel prepare and unprepare routines
  drm/exynos: dsi: Add support for panel prepare and unprepare routines
  drm/exynos: dpi: Add support for panel prepare and unprepare routines
  drm/panel: simple: Add dummy prepare and unprepare routines
  drm/panel: s6e8aa0: Add dummy prepare and unprepare routines
  drm/panel: ld9040: Add dummy prepare and unprepare routines
  drm/panel: Provide convenience wrapper for .get_modes()
  drm/panel: add .prepare() and .unprepare() functions
  drm/panel: simple: Remove simple-panel compatible
  ...

1 files changed, 123 insertions, 55 deletions

diff --git a/drivers/gpu/drm/radeon/ni_dma.c b/drivers/gpu/drm/radeon/ni_dma.c
index 6378e0276691..8a3e6221cece 100644
--- a/drivers/gpu/drm/radeon/ni_dma.c
+++ b/drivers/gpu/drm/radeon/ni_dma.c
@@ -307,7 +307,43 @@ bool cayman_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 }
 
 /**
- * cayman_dma_vm_set_page - update the page tables using the DMA
+ * cayman_dma_vm_copy_pages - update PTEs by copying them from the GART
+ *
+ * @rdev: radeon_device pointer
+ * @ib: indirect buffer to fill with commands
+ * @pe: addr of the page entry
+ * @src: src addr where to copy from
+ * @count: number of page entries to update
+ *
+ * Update PTEs by copying them from the GART using the DMA (cayman/TN).
+ */
+void cayman_dma_vm_copy_pages(struct radeon_device *rdev,
+			      struct radeon_ib *ib,
+			      uint64_t pe, uint64_t src,
+			      unsigned count)
+{
+	unsigned ndw;
+
+	while (count) {
+		ndw = count * 2;
+		if (ndw > 0xFFFFE)
+			ndw = 0xFFFFE;
+
+		ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_COPY,
+						      0, 0, ndw);
+		ib->ptr[ib->length_dw++] = lower_32_bits(pe);
+		ib->ptr[ib->length_dw++] = lower_32_bits(src);
+		ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
+		ib->ptr[ib->length_dw++] = upper_32_bits(src) & 0xff;
+
+		pe += ndw * 4;
+		src += ndw * 4;
+		count -= ndw / 2;
+	}
+}
+
+/**
+ * cayman_dma_vm_write_pages - update PTEs by writing them manually
  *
  * @rdev: radeon_device pointer
  * @ib: indirect buffer to fill with commands
@@ -315,71 +351,103 @@ bool cayman_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
  * @addr: dst addr to write into pe
  * @count: number of page entries to update
  * @incr: increase next addr by incr bytes
- * @flags: hw access flags 
+ * @flags: hw access flags
  *
- * Update the page tables using the DMA (cayman/TN).
+ * Update PTEs by writing them manually using the DMA (cayman/TN).
  */
-void cayman_dma_vm_set_page(struct radeon_device *rdev,
-			    struct radeon_ib *ib,
-			    uint64_t pe,
-			    uint64_t addr, unsigned count,
-			    uint32_t incr, uint32_t flags)
+void cayman_dma_vm_write_pages(struct radeon_device *rdev,
+			       struct radeon_ib *ib,
+			       uint64_t pe,
+			       uint64_t addr, unsigned count,
+			       uint32_t incr, uint32_t flags)
 {
 	uint64_t value;
 	unsigned ndw;
 
-	trace_radeon_vm_set_page(pe, addr, count, incr, flags);
-
-	if ((flags & R600_PTE_SYSTEM) || (count == 1)) {
-		while (count) {
-			ndw = count * 2;
-			if (ndw > 0xFFFFE)
-				ndw = 0xFFFFE;
-
-			/* for non-physically contiguous pages (system) */
-			ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_WRITE, 0, 0, ndw);
-			ib->ptr[ib->length_dw++] = pe;
-			ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
-			for (; ndw > 0; ndw -= 2, --count, pe += 8) {
-				if (flags & R600_PTE_SYSTEM) {
-					value = radeon_vm_map_gart(rdev, addr);
-					value &= 0xFFFFFFFFFFFFF000ULL;
-				} else if (flags & R600_PTE_VALID) {
-					value = addr;
-				} else {
-					value = 0;
-				}
-				addr += incr;
-				value |= flags;
-				ib->ptr[ib->length_dw++] = value;
-				ib->ptr[ib->length_dw++] = upper_32_bits(value);
-			}
-		}
-	} else {
-		while (count) {
-			ndw = count * 2;
-			if (ndw > 0xFFFFE)
-				ndw = 0xFFFFE;
-
-			if (flags & R600_PTE_VALID)
+	while (count) {
+		ndw = count * 2;
+		if (ndw > 0xFFFFE)
+			ndw = 0xFFFFE;
+
+		/* for non-physically contiguous pages (system) */
+		ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_WRITE,
+						      0, 0, ndw);
+		ib->ptr[ib->length_dw++] = pe;
+		ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
+		for (; ndw > 0; ndw -= 2, --count, pe += 8) {
+			if (flags & R600_PTE_SYSTEM) {
+				value = radeon_vm_map_gart(rdev, addr);
+				value &= 0xFFFFFFFFFFFFF000ULL;
+			} else if (flags & R600_PTE_VALID) {
 				value = addr;
-			else
+			} else {
 				value = 0;
-			/* for physically contiguous pages (vram) */
-			ib->ptr[ib->length_dw++] = DMA_PTE_PDE_PACKET(ndw);
-			ib->ptr[ib->length_dw++] = pe; /* dst addr */
-			ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
-			ib->ptr[ib->length_dw++] = flags; /* mask */
-			ib->ptr[ib->length_dw++] = 0;
-			ib->ptr[ib->length_dw++] = value; /* value */
+			}
+			addr += incr;
+			value |= flags;
+			ib->ptr[ib->length_dw++] = value;
 			ib->ptr[ib->length_dw++] = upper_32_bits(value);
-			ib->ptr[ib->length_dw++] = incr; /* increment size */
-			ib->ptr[ib->length_dw++] = 0;
-			pe += ndw * 4;
-			addr += (ndw / 2) * incr;
-			count -= ndw / 2;
 		}
 	}
+}
+
+/**
+ * cayman_dma_vm_set_pages - update the page tables using the DMA
+ *
+ * @rdev: radeon_device pointer
+ * @ib: indirect buffer to fill with commands
+ * @pe: addr of the page entry
+ * @addr: dst addr to write into pe
+ * @count: number of page entries to update
+ * @incr: increase next addr by incr bytes
+ * @flags: hw access flags
+ *
+ * Update the page tables using the DMA (cayman/TN).
+ */
+void cayman_dma_vm_set_pages(struct radeon_device *rdev,
+			     struct radeon_ib *ib,
+			     uint64_t pe,
+			     uint64_t addr, unsigned count,
+			     uint32_t incr, uint32_t flags)
+{
+	uint64_t value;
+	unsigned ndw;
+
+	while (count) {
+		ndw = count * 2;
+		if (ndw > 0xFFFFE)
+			ndw = 0xFFFFE;
+
+		if (flags & R600_PTE_VALID)
+			value = addr;
+		else
+			value = 0;
+
+		/* for physically contiguous pages (vram) */
+		ib->ptr[ib->length_dw++] = DMA_PTE_PDE_PACKET(ndw);
+		ib->ptr[ib->length_dw++] = pe; /* dst addr */
+		ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
+		ib->ptr[ib->length_dw++] = flags; /* mask */
+		ib->ptr[ib->length_dw++] = 0;
+		ib->ptr[ib->length_dw++] = value; /* value */
+		ib->ptr[ib->length_dw++] = upper_32_bits(value);
+		ib->ptr[ib->length_dw++] = incr; /* increment size */
+		ib->ptr[ib->length_dw++] = 0;
+
+		pe += ndw * 4;
+		addr += (ndw / 2) * incr;
+		count -= ndw / 2;
+	}
+}
+
+/**
+ * cayman_dma_vm_pad_ib - pad the IB to the required number of dw
+ *
+ * @ib: indirect buffer to fill with padding
+ *
+ */
+void cayman_dma_vm_pad_ib(struct radeon_ib *ib)
+{
 	while (ib->length_dw & 0x7)
 		ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0);
 }