Merge tag 'drm-next-2018-10-24' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "This is going to rebuild more than drm as it adds a new helper to
  list.h for doing bulk updates. Seemed like a reasonable addition to
  me.

  Otherwise the usual merge window stuff lots of i915 and amdgpu, not so
  much nouveau, and piles of everything else.

  Core:
   - Adds a new list.h helper for doing bulk list updates for TTM.
   - Don't leak fb address in smem_start to userspace (comes with EXPORT
     workaround for people using mali out of tree hacks)
   - udmabuf device to turn memfd regions into dma-buf
   - Per-plane blend mode property
   - ref/unref replacements with get/put
   - fbdev conflicting framebuffers code cleaned up
   - host-endian format variants
   - panel orientation quirk for Acer One 10

  bridge:
   - TI SN65DSI86 chip support

  vkms:
   - GEM support.
   - Cursor support

  amdgpu:
   - Merge amdkfd and amdgpu into one module
   - CEC over DP AUX support
   - Picasso APU support + VCN dynamic powergating
   - Raven2 APU support
   - Vega20 enablement + kfd support
   - ACP powergating improvements
   - ABGR/XBGR display support
   - VCN jpeg support
   - xGMI support
   - DC i2c/aux cleanup
   - Ycbcr 4:2:0 support
   - GPUVM improvements
   - Powerplay and powerplay endian fixes
   - Display underflow fixes

  vmwgfx:
   - Move vmwgfx specific TTM code to vmwgfx
   - Split out vmwgfx buffer/resource validation code
   - Atomic operation rework

  bochs:
   - use more helpers
   - format/byteorder improvements

  qxl:
   - use more helpers

  i915:
   - GGTT coherency getparam
   - Turn off resource streamer API
   - More Icelake enablement + DMC firmware
   - Full PPGTT for Ivybridge, Haswell and Valleyview
   - DDB distribution based on resolution
   - Limited range DP display support

  nouveau:
   - CEC over DP AUX support
   - Initial HDMI 2.0 support

  virtio-gpu:
   - vmap support for PRIME objects

  tegra:
   - Initial Tegra194 support
   - DMA/IOMMU integration fixes

  msm:
   - a6xx perf improvements + clock prefix
   - GPU preemption optimisations
   - a6xx devfreq support
   - cursor support

  rockchip:
   - PX30 support
   - rgb output interface support

  mediatek:
   - HDMI output support on mt2701 and mt7623

  rcar-du:
   - Interlaced modes on Gen3
   - LVDS on R8A77980
   - D3 and E3 SoC support

  hisilicon:
   - misc fixes

  mxsfb:
   - runtime pm support

  sun4i:
   - R40 TCON support
   - Allwinner A64 support
   - R40 HDMI support

  omapdrm:
   - Driver rework changing display pipeline ordering to use common code
   - DMM memory barrier and irq fixes
   - Errata workarounds

  exynos:
   - out-bridge support for LVDS bridge driver
   - Samsung 16x16 tiled format support
   - Plane alpha and pixel blend mode support

  tilcdc:
   - suspend/resume update

  mali-dp:
   - misc updates"

* tag 'drm-next-2018-10-24' of git://anongit.freedesktop.org/drm/drm: (1382 commits)
  firmware/dmc/icl: Add missing MODULE_FIRMWARE() for Icelake.
  drm/i915/icl: Fix signal_levels
  drm/i915/icl: Fix DDI/TC port clk_off bits
  drm/i915/icl: create function to identify combophy port
  drm/i915/gen9+: Fix initial readout for Y tiled framebuffers
  drm/i915: Large page offsets for pread/pwrite
  drm/i915/selftests: Disable shrinker across mmap-exhaustion
  drm/i915/dp: Link train Fallback on eDP only if fallback link BW can fit panel's native mode
  drm/i915: Fix intel_dp_mst_best_encoder()
  drm/i915: Skip vcpi allocation for MSTB ports that are gone
  drm/i915: Don't unset intel_connector->mst_port
  drm/i915: Only reset seqno if actually idle
  drm/i915: Use the correct crtc when sanitizing plane mapping
  drm/i915: Restore vblank interrupts earlier
  drm/i915: Check fb stride against plane max stride
  drm/amdgpu/vcn:Fix uninitialized symbol error
  drm: panel-orientation-quirks: Add quirk for Acer One 10 (S1003)
  drm/amd/amdgpu: Fix debugfs error handling
  drm/amdgpu: Update gc_9_0 golden settings.
  drm/amd/powerplay: update PPtable with DC BTC and Tvr SocLimit fields
  ...

1 files changed, 66 insertions, 173 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
index 06373d44b3da..8af67f649660 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
@@ -24,46 +24,21 @@
 #include <drm/drmP.h>
 #include "amdgpu.h"
 #include "amdgpu_ih.h"
-#include "amdgpu_amdkfd.h"
-
-/**
- * amdgpu_ih_ring_alloc - allocate memory for the IH ring
- *
- * @adev: amdgpu_device pointer
- *
- * Allocate a ring buffer for the interrupt controller.
- * Returns 0 for success, errors for failure.
- */
-static int amdgpu_ih_ring_alloc(struct amdgpu_device *adev)
-{
-	int r;
-
-	/* Allocate ring buffer */
-	if (adev->irq.ih.ring_obj == NULL) {
-		r = amdgpu_bo_create_kernel(adev, adev->irq.ih.ring_size,
-					    PAGE_SIZE, AMDGPU_GEM_DOMAIN_GTT,
-					    &adev->irq.ih.ring_obj,
-					    &adev->irq.ih.gpu_addr,
-					    (void **)&adev->irq.ih.ring);
-		if (r) {
-			DRM_ERROR("amdgpu: failed to create ih ring buffer (%d).\n", r);
-			return r;
-		}
-	}
-	return 0;
-}
 
 /**
  * amdgpu_ih_ring_init - initialize the IH state
  *
  * @adev: amdgpu_device pointer
+ * @ih: ih ring to initialize
+ * @ring_size: ring size to allocate
+ * @use_bus_addr: true when we can use dma_alloc_coherent
  *
  * Initializes the IH state and allocates a buffer
  * for the IH ring buffer.
  * Returns 0 for success, errors for failure.
  */
-int amdgpu_ih_ring_init(struct amdgpu_device *adev, unsigned ring_size,
-			bool use_bus_addr)
+int amdgpu_ih_ring_init(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih,
+			unsigned ring_size, bool use_bus_addr)
 {
 	u32 rb_bufsz;
 	int r;
@@ -71,70 +46,76 @@ int amdgpu_ih_ring_init(struct amdgpu_device *adev, unsigned ring_size,
 	/* Align ring size */
 	rb_bufsz = order_base_2(ring_size / 4);
 	ring_size = (1 << rb_bufsz) * 4;
-	adev->irq.ih.ring_size = ring_size;
-	adev->irq.ih.ptr_mask = adev->irq.ih.ring_size - 1;
-	adev->irq.ih.rptr = 0;
-	adev->irq.ih.use_bus_addr = use_bus_addr;
+	ih->ring_size = ring_size;
+	ih->ptr_mask = ih->ring_size - 1;
+	ih->rptr = 0;
+	ih->use_bus_addr = use_bus_addr;
 
-	if (adev->irq.ih.use_bus_addr) {
-		if (!adev->irq.ih.ring) {
-			/* add 8 bytes for the rptr/wptr shadows and
-			 * add them to the end of the ring allocation.
-			 */
-			adev->irq.ih.ring = pci_alloc_consistent(adev->pdev,
-								 adev->irq.ih.ring_size + 8,
-								 &adev->irq.ih.rb_dma_addr);
-			if (adev->irq.ih.ring == NULL)
-				return -ENOMEM;
-			memset((void *)adev->irq.ih.ring, 0, adev->irq.ih.ring_size + 8);
-			adev->irq.ih.wptr_offs = (adev->irq.ih.ring_size / 4) + 0;
-			adev->irq.ih.rptr_offs = (adev->irq.ih.ring_size / 4) + 1;
-		}
-		return 0;
+	if (use_bus_addr) {
+		if (ih->ring)
+			return 0;
+
+		/* add 8 bytes for the rptr/wptr shadows and
+		 * add them to the end of the ring allocation.
+		 */
+		ih->ring = dma_alloc_coherent(adev->dev, ih->ring_size + 8,
+					      &ih->rb_dma_addr, GFP_KERNEL);
+		if (ih->ring == NULL)
+			return -ENOMEM;
+
+		memset((void *)ih->ring, 0, ih->ring_size + 8);
+		ih->wptr_offs = (ih->ring_size / 4) + 0;
+		ih->rptr_offs = (ih->ring_size / 4) + 1;
 	} else {
-		r = amdgpu_device_wb_get(adev, &adev->irq.ih.wptr_offs);
+		r = amdgpu_device_wb_get(adev, &ih->wptr_offs);
+		if (r)
+			return r;
+
+		r = amdgpu_device_wb_get(adev, &ih->rptr_offs);
 		if (r) {
-			dev_err(adev->dev, "(%d) ih wptr_offs wb alloc failed\n", r);
+			amdgpu_device_wb_free(adev, ih->wptr_offs);
 			return r;
 		}
 
-		r = amdgpu_device_wb_get(adev, &adev->irq.ih.rptr_offs);
+		r = amdgpu_bo_create_kernel(adev, ih->ring_size, PAGE_SIZE,
+					    AMDGPU_GEM_DOMAIN_GTT,
+					    &ih->ring_obj, &ih->gpu_addr,
+					    (void **)&ih->ring);
 		if (r) {
-			amdgpu_device_wb_free(adev, adev->irq.ih.wptr_offs);
-			dev_err(adev->dev, "(%d) ih rptr_offs wb alloc failed\n", r);
+			amdgpu_device_wb_free(adev, ih->rptr_offs);
+			amdgpu_device_wb_free(adev, ih->wptr_offs);
 			return r;
 		}
-
-		return amdgpu_ih_ring_alloc(adev);
 	}
+	return 0;
 }
 
 /**
  * amdgpu_ih_ring_fini - tear down the IH state
  *
  * @adev: amdgpu_device pointer
+ * @ih: ih ring to tear down
  *
  * Tears down the IH state and frees buffer
  * used for the IH ring buffer.
  */
-void amdgpu_ih_ring_fini(struct amdgpu_device *adev)
+void amdgpu_ih_ring_fini(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih)
 {
-	if (adev->irq.ih.use_bus_addr) {
-		if (adev->irq.ih.ring) {
-			/* add 8 bytes for the rptr/wptr shadows and
-			 * add them to the end of the ring allocation.
-			 */
-			pci_free_consistent(adev->pdev, adev->irq.ih.ring_size + 8,
-					    (void *)adev->irq.ih.ring,
-					    adev->irq.ih.rb_dma_addr);
-			adev->irq.ih.ring = NULL;
-		}
+	if (ih->use_bus_addr) {
+		if (!ih->ring)
+			return;
+
+		/* add 8 bytes for the rptr/wptr shadows and
+		 * add them to the end of the ring allocation.
+		 */
+		dma_free_coherent(adev->dev, ih->ring_size + 8,
+				  (void *)ih->ring, ih->rb_dma_addr);
+		ih->ring = NULL;
 	} else {
-		amdgpu_bo_free_kernel(&adev->irq.ih.ring_obj,
-				      &adev->irq.ih.gpu_addr,
-				      (void **)&adev->irq.ih.ring);
-		amdgpu_device_wb_free(adev, adev->irq.ih.wptr_offs);
-		amdgpu_device_wb_free(adev, adev->irq.ih.rptr_offs);
+		amdgpu_bo_free_kernel(&ih->ring_obj, &ih->gpu_addr,
+				      (void **)&ih->ring);
+		amdgpu_device_wb_free(adev, ih->wptr_offs);
+		amdgpu_device_wb_free(adev, ih->rptr_offs);
 	}
 }
 
@@ -142,133 +123,45 @@ void amdgpu_ih_ring_fini(struct amdgpu_device *adev)
  * amdgpu_ih_process - interrupt handler
  *
  * @adev: amdgpu_device pointer
+ * @ih: ih ring to process
  *
  * Interrupt hander (VI), walk the IH ring.
  * Returns irq process return code.
  */
-int amdgpu_ih_process(struct amdgpu_device *adev)
+int amdgpu_ih_process(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih,
+		      void (*callback)(struct amdgpu_device *adev,
+				       struct amdgpu_ih_ring *ih))
 {
-	struct amdgpu_iv_entry entry;
 	u32 wptr;
 
-	if (!adev->irq.ih.enabled || adev->shutdown)
+	if (!ih->enabled || adev->shutdown)
 		return IRQ_NONE;
 
 	wptr = amdgpu_ih_get_wptr(adev);
 
 restart_ih:
 	/* is somebody else already processing irqs? */
-	if (atomic_xchg(&adev->irq.ih.lock, 1))
+	if (atomic_xchg(&ih->lock, 1))
 		return IRQ_NONE;
 
-	DRM_DEBUG("%s: rptr %d, wptr %d\n", __func__, adev->irq.ih.rptr, wptr);
+	DRM_DEBUG("%s: rptr %d, wptr %d\n", __func__, ih->rptr, wptr);
 
 	/* Order reading of wptr vs. reading of IH ring data */
 	rmb();
 
-	while (adev->irq.ih.rptr != wptr) {
-		u32 ring_index = adev->irq.ih.rptr >> 2;
-
-		/* Prescreening of high-frequency interrupts */
-		if (!amdgpu_ih_prescreen_iv(adev)) {
-			adev->irq.ih.rptr &= adev->irq.ih.ptr_mask;
-			continue;
-		}
-
-		/* Before dispatching irq to IP blocks, send it to amdkfd */
-		amdgpu_amdkfd_interrupt(adev,
-				(const void *) &adev->irq.ih.ring[ring_index]);
-
-		entry.iv_entry = (const uint32_t *)
-			&adev->irq.ih.ring[ring_index];
-		amdgpu_ih_decode_iv(adev, &entry);
-		adev->irq.ih.rptr &= adev->irq.ih.ptr_mask;
-
-		amdgpu_irq_dispatch(adev, &entry);
+	while (ih->rptr != wptr) {
+		callback(adev, ih);
+		ih->rptr &= ih->ptr_mask;
 	}
+
 	amdgpu_ih_set_rptr(adev);
-	atomic_set(&adev->irq.ih.lock, 0);
+	atomic_set(&ih->lock, 0);
 
 	/* make sure wptr hasn't changed while processing */
 	wptr = amdgpu_ih_get_wptr(adev);
-	if (wptr != adev->irq.ih.rptr)
+	if (wptr != ih->rptr)
 		goto restart_ih;
 
 	return IRQ_HANDLED;
 }
 
-/**
- * amdgpu_ih_add_fault - Add a page fault record
- *
- * @adev: amdgpu device pointer
- * @key: 64-bit encoding of PASID and address
- *
- * This should be called when a retry page fault interrupt is
- * received. If this is a new page fault, it will be added to a hash
- * table. The return value indicates whether this is a new fault, or
- * a fault that was already known and is already being handled.
- *
- * If there are too many pending page faults, this will fail. Retry
- * interrupts should be ignored in this case until there is enough
- * free space.
- *
- * Returns 0 if the fault was added, 1 if the fault was already known,
- * -ENOSPC if there are too many pending faults.
- */
-int amdgpu_ih_add_fault(struct amdgpu_device *adev, u64 key)
-{
-	unsigned long flags;
-	int r = -ENOSPC;
-
-	if (WARN_ON_ONCE(!adev->irq.ih.faults))
-		/* Should be allocated in <IP>_ih_sw_init on GPUs that
-		 * support retry faults and require retry filtering.
-		 */
-		return r;
-
-	spin_lock_irqsave(&adev->irq.ih.faults->lock, flags);
-
-	/* Only let the hash table fill up to 50% for best performance */
-	if (adev->irq.ih.faults->count >= (1 << (AMDGPU_PAGEFAULT_HASH_BITS-1)))
-		goto unlock_out;
-
-	r = chash_table_copy_in(&adev->irq.ih.faults->hash, key, NULL);
-	if (!r)
-		adev->irq.ih.faults->count++;
-
-	/* chash_table_copy_in should never fail unless we're losing count */
-	WARN_ON_ONCE(r < 0);
-
-unlock_out:
-	spin_unlock_irqrestore(&adev->irq.ih.faults->lock, flags);
-	return r;
-}
-
-/**
- * amdgpu_ih_clear_fault - Remove a page fault record
- *
- * @adev: amdgpu device pointer
- * @key: 64-bit encoding of PASID and address
- *
- * This should be called when a page fault has been handled. Any
- * future interrupt with this key will be processed as a new
- * page fault.
- */
-void amdgpu_ih_clear_fault(struct amdgpu_device *adev, u64 key)
-{
-	unsigned long flags;
-	int r;
-
-	if (!adev->irq.ih.faults)
-		return;
-
-	spin_lock_irqsave(&adev->irq.ih.faults->lock, flags);
-
-	r = chash_table_remove(&adev->irq.ih.faults->hash, key, NULL);
-	if (!WARN_ON_ONCE(r < 0)) {
-		adev->irq.ih.faults->count--;
-		WARN_ON_ONCE(adev->irq.ih.faults->count < 0);
-	}
-
-	spin_unlock_irqrestore(&adev->irq.ih.faults->lock, flags);
-}