Merge branch 'drm-next-4.16' of git://people.freedesktop.org/~agd5f/linux into drm-next

First feature request for 4.16.  Highlights:
- RV and Vega header cleanups
- TTM operation context support
- 48 bit GPUVM fixes for Vega/RV
- More smatch fixes
- ECC support for vega10
- Resizeable BAR support
- Multi-display sync support in DC
- SR-IOV fixes
- Various scheduler improvements
- GPU reset fixes and vram lost tracking
- Clean up DC/powerplay interfaces
- DCN display fixes
- Various DC fixes

* 'drm-next-4.16' of git://people.freedesktop.org/~agd5f/linux: (291 commits)
  drm/radeon: Use drm_fb_helper_lastclose() and _poll_changed()
  drm/amdgpu: Use drm_fb_helper_lastclose() and _poll_changed()
  drm/amd/display: Use drm_fb_helper_poll_changed()
  drm/ttm: swap consecutive allocated pooled pages v4
  drm/amdgpu: fix amdgpu_sync_resv v2
  drm/ttm: swap consecutive allocated cached pages v3
  drm/amd/amdgpu: set gtt size according to system memory size only
  drm/amdgpu: Get rid of dep_sync as a seperate object.
  drm/amdgpu: allow specifying vm_block_size for multi level PDs v2
  drm/amdgpu: move validation of the VM size into the VM code
  drm/amdgpu: allow non pot VM size values
  drm/amdgpu: choose number of VM levels based on VM size
  drm/amdgpu: unify VM size handling of Vega10 with older generation
  drm/amdgpu: fix amdgpu_vm_num_entries
  drm/amdgpu: fix VM PD addr shift
  drm/amdgpu: correct vce4.0 fw config for SRIOV (V2)
  drm/amd/display: Don't call dm_log_to_buffer directly in dc_conn_log
  drm/amd/display: Add dm_logger_append_va API
  drm/ttm: Use a static string instead of an array of char *
  drm/amd/display: remove usage of legacy_cursor_update
  ...

1 files changed, 103 insertions, 5 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 2918de2f39ec..ba6d846b08ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -176,7 +176,7 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size)
 	ring = &adev->vce.ring[0];
 	rq = &ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL];
 	r = amd_sched_entity_init(&ring->sched, &adev->vce.entity,
-				  rq, amdgpu_sched_jobs);
+				  rq, amdgpu_sched_jobs, NULL);
 	if (r != 0) {
 		DRM_ERROR("Failed setting up VCE run queue.\n");
 		return r;
@@ -544,6 +544,55 @@ err:
 }
 
 /**
+ * amdgpu_vce_cs_validate_bo - make sure not to cross 4GB boundary
+ *
+ * @p: parser context
+ * @lo: address of lower dword
+ * @hi: address of higher dword
+ * @size: minimum size
+ * @index: bs/fb index
+ *
+ * Make sure that no BO cross a 4GB boundary.
+ */
+static int amdgpu_vce_validate_bo(struct amdgpu_cs_parser *p, uint32_t ib_idx,
+				  int lo, int hi, unsigned size, int32_t index)
+{
+	int64_t offset = ((uint64_t)size) * ((int64_t)index);
+	struct ttm_operation_ctx ctx = { false, false };
+	struct amdgpu_bo_va_mapping *mapping;
+	unsigned i, fpfn, lpfn;
+	struct amdgpu_bo *bo;
+	uint64_t addr;
+	int r;
+
+	addr = ((uint64_t)amdgpu_get_ib_value(p, ib_idx, lo)) |
+	       ((uint64_t)amdgpu_get_ib_value(p, ib_idx, hi)) << 32;
+	if (index >= 0) {
+		addr += offset;
+		fpfn = PAGE_ALIGN(offset) >> PAGE_SHIFT;
+		lpfn = 0x100000000ULL >> PAGE_SHIFT;
+	} else {
+		fpfn = 0;
+		lpfn = (0x100000000ULL - PAGE_ALIGN(offset)) >> PAGE_SHIFT;
+	}
+
+	r = amdgpu_cs_find_mapping(p, addr, &bo, &mapping);
+	if (r) {
+		DRM_ERROR("Can't find BO for addr 0x%010Lx %d %d %d %d\n",
+			  addr, lo, hi, size, index);
+		return r;
+	}
+
+	for (i = 0; i < bo->placement.num_placement; ++i) {
+		bo->placements[i].fpfn = max(bo->placements[i].fpfn, fpfn);
+		bo->placements[i].lpfn = bo->placements[i].fpfn ?
+			min(bo->placements[i].fpfn, lpfn) : lpfn;
+	}
+	return ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+}
+
+
+/**
  * amdgpu_vce_cs_reloc - command submission relocation
  *
  * @p: parser context
@@ -648,12 +697,13 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx)
 	uint32_t allocated = 0;
 	uint32_t tmp, handle = 0;
 	uint32_t *size = &tmp;
-	int i, r = 0, idx = 0;
+	unsigned idx;
+	int i, r = 0;
 
 	p->job->vm = NULL;
 	ib->gpu_addr = amdgpu_sa_bo_gpu_addr(ib->sa_bo);
 
-	while (idx < ib->length_dw) {
+	for (idx = 0; idx < ib->length_dw;) {
 		uint32_t len = amdgpu_get_ib_value(p, ib_idx, idx);
 		uint32_t cmd = amdgpu_get_ib_value(p, ib_idx, idx + 1);
 
@@ -664,6 +714,54 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx)
 		}
 
 		switch (cmd) {
+		case 0x00000002: /* task info */
+			fb_idx = amdgpu_get_ib_value(p, ib_idx, idx + 6);
+			bs_idx = amdgpu_get_ib_value(p, ib_idx, idx + 7);
+			break;
+
+		case 0x03000001: /* encode */
+			r = amdgpu_vce_validate_bo(p, ib_idx, idx + 10,
+						   idx + 9, 0, 0);
+			if (r)
+				goto out;
+
+			r = amdgpu_vce_validate_bo(p, ib_idx, idx + 12,
+						   idx + 11, 0, 0);
+			if (r)
+				goto out;
+			break;
+
+		case 0x05000001: /* context buffer */
+			r = amdgpu_vce_validate_bo(p, ib_idx, idx + 3,
+						   idx + 2, 0, 0);
+			if (r)
+				goto out;
+			break;
+
+		case 0x05000004: /* video bitstream buffer */
+			tmp = amdgpu_get_ib_value(p, ib_idx, idx + 4);
+			r = amdgpu_vce_validate_bo(p, ib_idx, idx + 3, idx + 2,
+						   tmp, bs_idx);
+			if (r)
+				goto out;
+			break;
+
+		case 0x05000005: /* feedback buffer */
+			r = amdgpu_vce_validate_bo(p, ib_idx, idx + 3, idx + 2,
+						   4096, fb_idx);
+			if (r)
+				goto out;
+			break;
+		}
+
+		idx += len / 4;
+	}
+
+	for (idx = 0; idx < ib->length_dw;) {
+		uint32_t len = amdgpu_get_ib_value(p, ib_idx, idx);
+		uint32_t cmd = amdgpu_get_ib_value(p, ib_idx, idx + 1);
+
+		switch (cmd) {
 		case 0x00000001: /* session */
 			handle = amdgpu_get_ib_value(p, ib_idx, idx + 2);
 			session_idx = amdgpu_vce_validate_handle(p, handle,
@@ -954,7 +1052,7 @@ int amdgpu_vce_ring_test_ring(struct amdgpu_ring *ring)
 	}
 
 	if (i < timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n",
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n",
 			 ring->idx, i);
 	} else {
 		DRM_ERROR("amdgpu: ring %d test failed\n",
@@ -999,7 +1097,7 @@ int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	} else if (r < 0) {
 		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
 	} else {
-		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
 		r = 0;
 	}
 error: