Merge branch 'drm-next-4.15' of git://people.freedesktop.org/~agd5f/linux into drm-next

First feature pull for 4.15.  Highlights:
- Per VM BO support
- Lots of powerplay cleanups
- Powerplay support for CI
- pasid mgr for kfd
- interrupt infrastructure for recoverable page faults
- SR-IOV fixes
- initial GPU reset for vega10
- prime mmap support
- ttm page table debugging improvements
- lots of bug fixes

* 'drm-next-4.15' of git://people.freedesktop.org/~agd5f/linux: (232 commits)
  drm/amdgpu: clarify license in amdgpu_trace_points.c
  drm/amdgpu: Add gem_prime_mmap support
  drm/amd/powerplay: delete dead code in smumgr
  drm/amd/powerplay: delete SMUM_FIELD_MASK
  drm/amd/powerplay: delete SMUM_WAIT_INDIRECT_FIELD
  drm/amd/powerplay: delete SMUM_READ_FIELD
  drm/amd/powerplay: delete SMUM_SET_FIELD
  drm/amd/powerplay: delete SMUM_READ_VFPF_INDIRECT_FIELD
  drm/amd/powerplay: delete SMUM_WRITE_VFPF_INDIRECT_FIELD
  drm/amd/powerplay: delete SMUM_WRITE_FIELD
  drm/amd/powerplay: delete SMU_WRITE_INDIRECT_FIELD
  drm/amd/powerplay: move macros to hwmgr.h
  drm/amd/powerplay: move PHM_WAIT_VFPF_INDIRECT_FIELD to hwmgr.h
  drm/amd/powerplay: move SMUM_WAIT_VFPF_INDIRECT_FIELD_UNEQUAL to hwmgr.h
  drm/amd/powerplay: move SMUM_WAIT_INDIRECT_FIELD_UNEQUAL to hwmgr.h
  drm/amd/powerplay: add new helper functions in hwmgr.h
  drm/amd/powerplay: use SMU_IND_INDEX/DATA_11 pair
  drm/amd/powerplay: refine powerplay code.
  drm/amd/powerplay: delete dead code in hwmgr.h
  drm/amd/powerplay: refine interface in struct pp_smumgr_func
  ...

1 files changed, 82 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
index 3ab4c65ecc8b..f5f27e4f0f7f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
@@ -169,6 +169,12 @@ restart_ih:
 	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]);
@@ -190,3 +196,79 @@ 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);
+}