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, 28 insertions, 55 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
index 70b3a99cffc2..035c351f47c5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
@@ -42,26 +42,26 @@
 
 #include <linux/slab.h>
 #include <linux/device.h>
+#include <linux/kfifo.h>
 #include "kfd_priv.h"
 
-#define KFD_INTERRUPT_RING_SIZE 1024
+#define KFD_IH_NUM_ENTRIES 8192
 
 static void interrupt_wq(struct work_struct *);
 
 int kfd_interrupt_init(struct kfd_dev *kfd)
 {
-	void *interrupt_ring = kmalloc_array(KFD_INTERRUPT_RING_SIZE,
-					kfd->device_info->ih_ring_entry_size,
-					GFP_KERNEL);
-	if (!interrupt_ring)
-		return -ENOMEM;
-
-	kfd->interrupt_ring = interrupt_ring;
-	kfd->interrupt_ring_size =
-		KFD_INTERRUPT_RING_SIZE * kfd->device_info->ih_ring_entry_size;
-	atomic_set(&kfd->interrupt_ring_wptr, 0);
-	atomic_set(&kfd->interrupt_ring_rptr, 0);
+	int r;
+
+	r = kfifo_alloc(&kfd->ih_fifo,
+		KFD_IH_NUM_ENTRIES * kfd->device_info->ih_ring_entry_size,
+		GFP_KERNEL);
+	if (r) {
+		dev_err(kfd_chardev(), "Failed to allocate IH fifo\n");
+		return r;
+	}
 
+	kfd->ih_wq = alloc_workqueue("KFD IH", WQ_HIGHPRI, 1);
 	spin_lock_init(&kfd->interrupt_lock);
 
 	INIT_WORK(&kfd->interrupt_work, interrupt_wq);
@@ -92,74 +92,47 @@ void kfd_interrupt_exit(struct kfd_dev *kfd)
 	spin_unlock_irqrestore(&kfd->interrupt_lock, flags);
 
 	/*
-	 * Flush_scheduled_work ensures that there are no outstanding
+	 * flush_work ensures that there are no outstanding
 	 * work-queue items that will access interrupt_ring. New work items
 	 * can't be created because we stopped interrupt handling above.
 	 */
-	flush_scheduled_work();
+	flush_workqueue(kfd->ih_wq);
 
-	kfree(kfd->interrupt_ring);
+	kfifo_free(&kfd->ih_fifo);
 }
 
 /*
- * This assumes that it can't be called concurrently with itself
- * but only with dequeue_ih_ring_entry.
+ * Assumption: single reader/writer. This function is not re-entrant
  */
 bool enqueue_ih_ring_entry(struct kfd_dev *kfd,	const void *ih_ring_entry)
 {
-	unsigned int rptr = atomic_read(&kfd->interrupt_ring_rptr);
-	unsigned int wptr = atomic_read(&kfd->interrupt_ring_wptr);
+	int count;
 
-	if ((rptr - wptr) % kfd->interrupt_ring_size ==
-					kfd->device_info->ih_ring_entry_size) {
-		/* This is very bad, the system is likely to hang. */
+	count = kfifo_in(&kfd->ih_fifo, ih_ring_entry,
+				kfd->device_info->ih_ring_entry_size);
+	if (count != kfd->device_info->ih_ring_entry_size) {
 		dev_err_ratelimited(kfd_chardev(),
-			"Interrupt ring overflow, dropping interrupt.\n");
+			"Interrupt ring overflow, dropping interrupt %d\n",
+			count);
 		return false;
 	}
 
-	memcpy(kfd->interrupt_ring + wptr, ih_ring_entry,
-			kfd->device_info->ih_ring_entry_size);
-
-	wptr = (wptr + kfd->device_info->ih_ring_entry_size) %
-			kfd->interrupt_ring_size;
-	smp_wmb(); /* Ensure memcpy'd data is visible before wptr update. */
-	atomic_set(&kfd->interrupt_ring_wptr, wptr);
-
 	return true;
 }
 
 /*
- * This assumes that it can't be called concurrently with itself
- * but only with enqueue_ih_ring_entry.
+ * Assumption: single reader/writer. This function is not re-entrant
  */
 static bool dequeue_ih_ring_entry(struct kfd_dev *kfd, void *ih_ring_entry)
 {
-	/*
-	 * Assume that wait queues have an implicit barrier, i.e. anything that
-	 * happened in the ISR before it queued work is visible.
-	 */
-
-	unsigned int wptr = atomic_read(&kfd->interrupt_ring_wptr);
-	unsigned int rptr = atomic_read(&kfd->interrupt_ring_rptr);
+	int count;
 
-	if (rptr == wptr)
-		return false;
-
-	memcpy(ih_ring_entry, kfd->interrupt_ring + rptr,
-			kfd->device_info->ih_ring_entry_size);
-
-	rptr = (rptr + kfd->device_info->ih_ring_entry_size) %
-			kfd->interrupt_ring_size;
+	count = kfifo_out(&kfd->ih_fifo, ih_ring_entry,
+				kfd->device_info->ih_ring_entry_size);
 
-	/*
-	 * Ensure the rptr write update is not visible until
-	 * memcpy has finished reading.
-	 */
-	smp_mb();
-	atomic_set(&kfd->interrupt_ring_rptr, rptr);
+	WARN_ON(count && count != kfd->device_info->ih_ring_entry_size);
 
-	return true;
+	return count == kfd->device_info->ih_ring_entry_size;
 }
 
 static void interrupt_wq(struct work_struct *work)