Merge tag 'drm-next-2020-01-30' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Davbe Airlie:
 "This is the main pull request for graphics for 5.6. Usual selection of
  changes all over.

  I've got one outstanding vmwgfx pull that touches mm so kept it
  separate until after all of this lands. I'll try and get it to you
  soon after this, but it might be early next week (nothing wrong with
  code, just my schedule is messy)

  This also hits a lot of fbdev drivers with some cleanups.

  Other notables:
   - vulkan timeline semaphore support added to syncobjs
   - nouveau turing secureboot/graphics support
   - Displayport MST display stream compression support

  Detailed summary:

  uapi:
   - dma-buf heaps added (and fixed)
   - command line add support for panel oreientation
   - command line allow overriding penguin count

  drm:
   - mipi dsi definition updates
   - lockdep annotations for dma_resv
   - remove dma-buf kmap/kunmap support
   - constify fb_ops in all fbdev drivers
   - MST fix for daisy chained hotplug-
   - CTA-861-G modes with VIC >= 193 added
   - fix drm_panel_of_backlight export
   - LVDS decoder support
   - more device based logging support
   - scanline alighment for dumb buffers
   - MST DSC helpers

  scheduler:
   - documentation fixes
   - job distribution improvements

  panel:
   - Logic PD type 28 panel support
   - Jimax8729d MIPI-DSI
   - igenic JZ4770
   - generic DSI devicetree bindings
   - sony acx424AKP panel
   - Leadtek LTK500HD1829
   - xinpeng XPP055C272
   - AUO B116XAK01
   - GiantPlus GPM940B0
   - BOE NV140FHM-N49
   - Satoz SAT050AT40H12R2
   - Sharp LS020B1DD01D panels.

  ttm:
   - use blocking WW lock

  i915:
   - hw/uapi state separation
   - Lock annotation improvements
   - selftest improvements
   - ICL/TGL DSI VDSC support
   - VBT parsing improvments
   - Display refactoring
   - DSI updates + fixes
   - HDCP 2.2 for CFL
   - CML PCI ID fixes
   - GLK+ fbc fix
   - PSR fixes
   - GEN/GT refactor improvments
   - DP MST fixes
   - switch context id alloc to xarray
   - workaround updates
   - LMEM debugfs support
   - tiled monitor fixes
   - ICL+ clock gating programming removed
   - DP MST disable sequence fixed
   - LMEM discontiguous object maps
   - prefaulting for discontiguous objects
   - use LMEM for dumb buffers if possible
   - add LMEM mmap support

  amdgpu:
   - enable sync object timelines for vulkan
   - MST atomic routines
   - enable MST DSC support
   - add DMCUB display microengine support
   - DC OEM i2c support
   - Renoir DC fixes
   - Initial HDCP 2.x support
   - BACO support for Arcturus
   - Use BACO for runtime PM power save
   - gfxoff on navi10
   - gfx10 golden updates and fixes
   - DCN support on POWER
   - GFXOFF for raven1 refresh
   - MM engine idle handlers cleanup
   - 10bpc EDP panel fixes
   - renoir watermark fixes
   - SR-IOV fixes
   - Arcturus VCN fixes
   - GDDR6 training fixes
   - freesync fixes
   - Pollock support

  amdkfd:
   - unify more codepath with amdgpu
   - use KIQ to setup HIQ rather than MMIO

  radeon:
   - fix vma fault handler race
   - PPC DMA fix
   - register check fixes for r100/r200

  nouveau:
   - mmap_sem vs dma_resv fix
   - rewrite the ACR secure boot code for Turing
   - TU10x graphics engine support (TU11x pending)
   - Page kind mapping for turing
   - 10-bit LUT support
   - GP10B Tegra fixes
   - HD audio regression fix

  hisilicon/hibmc:
   - use generic fbdev code and helpers

  rockchip:
   - dsi/px30 support

  virtio:
   - fb damage support
   - static some functions

  vc4:
   - use dma_resv lock wrappers

  msm:
   - use dma_resv lock wrappers
   - sc7180 display + DSI support
   - a618 support
   - UBWC support improvements

  vmwgfx:
   - updates + new logging uapi

  exynos:
   - enable/disable callback cleanups

  etnaviv:
   - use dma_resv lock wrappers

  atmel-hlcdc:
   - clock fixes

  mediatek:
   - cmdq support
   - non-smooth cursor fixes
   - ctm property support

  sun4i:
   - suspend support
   - A64 mipi dsi support

  rcar-du:
   - Color management module support
   - LVDS encoder dual-link support
   - R8A77980 support

  analogic:
   - add support for an6345

  ast:
   - atomic modeset support
   - primary plane garbage fix

  arcgpu:
   - fixes for fourcc handling

  tegra:
   - minor fixes and improvments

  mcde:
   - vblank support

  meson:
   - OSD1 plane AFBC commit

  gma500:
   - add pageflip support
   - reomve global drm_dev

  komeda:
   - tweak debugfs output
   - d32 support
   - runtime PM suppotr

  udl:
   - use generic shmem helpers
   - cleanup and fixes"

* tag 'drm-next-2020-01-30' of git://anongit.freedesktop.org/drm/drm: (1998 commits)
  drm/nouveau/fb/gp102-: allow module to load even when scrubber binary is missing
  drm/nouveau/acr: return error when registering LSF if ACR not supported
  drm/nouveau/disp/gv100-: not all channel types support reporting error codes
  drm/nouveau/disp/nv50-: prevent oops when no channel method map provided
  drm/nouveau: support synchronous pushbuf submission
  drm/nouveau: signal pending fences when channel has been killed
  drm/nouveau: reject attempts to submit to dead channels
  drm/nouveau: zero vma pointer even if we only unreference it rather than free
  drm/nouveau: Add HD-audio component notifier support
  drm/nouveau: fix build error without CONFIG_IOMMU_API
  drm/nouveau/kms/nv04: remove set but not used variable 'width'
  drm/nouveau/kms/nv50: remove set but not unused variable 'nv_connector'
  drm/nouveau/mmu: fix comptag memory leak
  drm/nouveau/gr/gp10b: Use gp100_grctx and gp100_gr_zbc
  drm/nouveau/pmu/gm20b,gp10b: Fix Falcon bootstrapping
  drm/exynos: Rename Exynos to lowercase
  drm/exynos: change callback names
  drm/mst: Don't do atomic checks over disabled managers
  drm/amdgpu: add the lost mutex_init back
  drm/amd/display: skip opp blank or unblank if test pattern enabled
  ...

1 files changed, 61 insertions, 88 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
index 61cd707158e4..a7b17c8deb00 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
@@ -107,13 +107,13 @@ static void acquire_queue(struct kgd_dev *kgd, uint32_t pipe_id,
 	lock_srbm(kgd, mec, pipe, queue_id, 0);
 }
 
-static uint32_t get_queue_mask(struct amdgpu_device *adev,
+static uint64_t get_queue_mask(struct amdgpu_device *adev,
 			       uint32_t pipe_id, uint32_t queue_id)
 {
-	unsigned int bit = (pipe_id * adev->gfx.mec.num_queue_per_pipe +
-			    queue_id) & 31;
+	unsigned int bit = pipe_id * adev->gfx.mec.num_queue_per_pipe +
+			queue_id;
 
-	return ((uint32_t)1) << bit;
+	return 1ull << bit;
 }
 
 static void release_queue(struct kgd_dev *kgd)
@@ -268,21 +268,6 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 	pr_debug("Load hqd of pipe %d queue %d\n", pipe_id, queue_id);
 	acquire_queue(kgd, pipe_id, queue_id);
 
-	/* HIQ is set during driver init period with vmid set to 0*/
-	if (m->cp_hqd_vmid == 0) {
-		uint32_t value, mec, pipe;
-
-		mec = (pipe_id / adev->gfx.mec.num_pipe_per_mec) + 1;
-		pipe = (pipe_id % adev->gfx.mec.num_pipe_per_mec);
-
-		pr_debug("kfd: set HIQ, mec:%d, pipe:%d, queue:%d.\n",
-			mec, pipe, queue_id);
-		value = RREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_CP_SCHEDULERS));
-		value = REG_SET_FIELD(value, RLC_CP_SCHEDULERS, scheduler1,
-			((mec << 5) | (pipe << 3) | queue_id | 0x80));
-		WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_CP_SCHEDULERS), value);
-	}
-
 	/* HQD registers extend from CP_MQD_BASE_ADDR to CP_HQD_EOP_WPTR_MEM. */
 	mqd_hqd = &m->cp_mqd_base_addr_lo;
 	hqd_base = SOC15_REG_OFFSET(GC, 0, mmCP_MQD_BASE_ADDR);
@@ -332,9 +317,10 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 		       lower_32_bits((uint64_t)wptr));
 		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_POLL_ADDR_HI),
 		       upper_32_bits((uint64_t)wptr));
-		pr_debug("%s setting CP_PQ_WPTR_POLL_CNTL1 to %x\n", __func__, get_queue_mask(adev, pipe_id, queue_id));
+		pr_debug("%s setting CP_PQ_WPTR_POLL_CNTL1 to %x\n", __func__,
+			 (uint32_t)get_queue_mask(adev, pipe_id, queue_id));
 		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_PQ_WPTR_POLL_CNTL1),
-		       get_queue_mask(adev, pipe_id, queue_id));
+		       (uint32_t)get_queue_mask(adev, pipe_id, queue_id));
 	}
 
 	/* Start the EOP fetcher */
@@ -350,6 +336,59 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 	return 0;
 }
 
+static int kgd_hiq_mqd_load(struct kgd_dev *kgd, void *mqd,
+			    uint32_t pipe_id, uint32_t queue_id,
+			    uint32_t doorbell_off)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	struct amdgpu_ring *kiq_ring = &adev->gfx.kiq.ring;
+	struct v10_compute_mqd *m;
+	uint32_t mec, pipe;
+	int r;
+
+	m = get_mqd(mqd);
+
+	acquire_queue(kgd, pipe_id, queue_id);
+
+	mec = (pipe_id / adev->gfx.mec.num_pipe_per_mec) + 1;
+	pipe = (pipe_id % adev->gfx.mec.num_pipe_per_mec);
+
+	pr_debug("kfd: set HIQ, mec:%d, pipe:%d, queue:%d.\n",
+		 mec, pipe, queue_id);
+
+	spin_lock(&adev->gfx.kiq.ring_lock);
+	r = amdgpu_ring_alloc(kiq_ring, 7);
+	if (r) {
+		pr_err("Failed to alloc KIQ (%d).\n", r);
+		goto out_unlock;
+	}
+
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_MAP_QUEUES, 5));
+	amdgpu_ring_write(kiq_ring,
+			  PACKET3_MAP_QUEUES_QUEUE_SEL(0) | /* Queue_Sel */
+			  PACKET3_MAP_QUEUES_VMID(m->cp_hqd_vmid) | /* VMID */
+			  PACKET3_MAP_QUEUES_QUEUE(queue_id) |
+			  PACKET3_MAP_QUEUES_PIPE(pipe) |
+			  PACKET3_MAP_QUEUES_ME((mec - 1)) |
+			  PACKET3_MAP_QUEUES_QUEUE_TYPE(0) | /*queue_type: normal compute queue */
+			  PACKET3_MAP_QUEUES_ALLOC_FORMAT(0) | /* alloc format: all_on_one_pipe */
+			  PACKET3_MAP_QUEUES_ENGINE_SEL(1) | /* engine_sel: hiq */
+			  PACKET3_MAP_QUEUES_NUM_QUEUES(1)); /* num_queues: must be 1 */
+	amdgpu_ring_write(kiq_ring,
+			  PACKET3_MAP_QUEUES_DOORBELL_OFFSET(doorbell_off));
+	amdgpu_ring_write(kiq_ring, m->cp_mqd_base_addr_lo);
+	amdgpu_ring_write(kiq_ring, m->cp_mqd_base_addr_hi);
+	amdgpu_ring_write(kiq_ring, m->cp_hqd_pq_wptr_poll_addr_lo);
+	amdgpu_ring_write(kiq_ring, m->cp_hqd_pq_wptr_poll_addr_hi);
+	amdgpu_ring_commit(kiq_ring);
+
+out_unlock:
+	spin_unlock(&adev->gfx.kiq.ring_lock);
+	release_queue(kgd);
+
+	return r;
+}
+
 static int kgd_hqd_dump(struct kgd_dev *kgd,
 			uint32_t pipe_id, uint32_t queue_id,
 			uint32_t (**dump)[2], uint32_t *n_regs)
@@ -686,71 +725,6 @@ static bool get_atc_vmid_pasid_mapping_info(struct kgd_dev *kgd,
 	return !!(value & ATC_VMID0_PASID_MAPPING__VALID_MASK);
 }
 
-static int invalidate_tlbs_with_kiq(struct amdgpu_device *adev, uint16_t pasid)
-{
-	signed long r;
-	uint32_t seq;
-	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
-
-	spin_lock(&adev->gfx.kiq.ring_lock);
-	amdgpu_ring_alloc(ring, 12); /* fence + invalidate_tlbs package*/
-	amdgpu_ring_write(ring, PACKET3(PACKET3_INVALIDATE_TLBS, 0));
-	amdgpu_ring_write(ring,
-			PACKET3_INVALIDATE_TLBS_DST_SEL(1) |
-			PACKET3_INVALIDATE_TLBS_PASID(pasid));
-	amdgpu_fence_emit_polling(ring, &seq);
-	amdgpu_ring_commit(ring);
-	spin_unlock(&adev->gfx.kiq.ring_lock);
-
-	r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
-	if (r < 1) {
-		DRM_ERROR("wait for kiq fence error: %ld.\n", r);
-		return -ETIME;
-	}
-
-	return 0;
-}
-
-static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-	int vmid;
-	uint16_t queried_pasid;
-	bool ret;
-	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
-
-	if (amdgpu_emu_mode == 0 && ring->sched.ready)
-		return invalidate_tlbs_with_kiq(adev, pasid);
-
-	for (vmid = 0; vmid < 16; vmid++) {
-		if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid))
-			continue;
-
-		ret = get_atc_vmid_pasid_mapping_info(kgd, vmid,
-				&queried_pasid);
-		if (ret	&& queried_pasid == pasid) {
-			amdgpu_gmc_flush_gpu_tlb(adev, vmid,
-					AMDGPU_GFXHUB_0, 0);
-			break;
-		}
-	}
-
-	return 0;
-}
-
-static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-
-	if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid)) {
-		pr_err("non kfd vmid %d\n", vmid);
-		return 0;
-	}
-
-	amdgpu_gmc_flush_gpu_tlb(adev, vmid, AMDGPU_GFXHUB_0, 0);
-	return 0;
-}
-
 static int kgd_address_watch_disable(struct kgd_dev *kgd)
 {
 	return 0;
@@ -817,6 +791,7 @@ const struct kfd2kgd_calls gfx_v10_kfd2kgd = {
 	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
 	.init_interrupts = kgd_init_interrupts,
 	.hqd_load = kgd_hqd_load,
+	.hiq_mqd_load = kgd_hiq_mqd_load,
 	.hqd_sdma_load = kgd_hqd_sdma_load,
 	.hqd_dump = kgd_hqd_dump,
 	.hqd_sdma_dump = kgd_hqd_sdma_dump,
@@ -832,7 +807,5 @@ const struct kfd2kgd_calls gfx_v10_kfd2kgd = {
 			get_atc_vmid_pasid_mapping_info,
 	.get_tile_config = amdgpu_amdkfd_get_tile_config,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base,
-	.invalidate_tlbs = invalidate_tlbs,
-	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.get_hive_id = amdgpu_amdkfd_get_hive_id,
 };