Merge tag 'drm-next-2021-02-19' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "A pretty normal tree, lots of refactoring across the board, ttm, i915,
  nouveau, and bunch of features in various drivers.

  docs:
   - lots of updated docs

  core:
   - require crtc to have unique primary plane
   - fourcc macro fix
   - PCI bar quirk for bar resizing
   - don't sent hotplug on error
   - move vm code to legacy
   - nuke hose only used on old oboslete alpha

  dma-buf:
   - kernel doc updates
   - improved lock tracking

  dp/hdmi:
   - DP-HDMI2.1 protocol converter support

  ttm:
   - bo size handling cleanup
   - release a pinned bo warning
   - cleanup lru handler
   - avoid using pages with drm_prime_sg_to_page_addr_arrays

  cma-helper:
   - prime/mmap fixes

  bridge:
   - add DP support

  gma500:
   - remove gma3600 support

  i915:
   - try eDP fast/narrow link again with fallback
   - Intel eDP backlight control
   - replace display register read/write macros
   - refactor intel_display.c
   - display power improvements
   - HPD code cleanup
   - Rocketlake display fixes
   - Power/backlight/RPM fixes
   - DG1 display fix
   - IVB/BYT clear residuals security fix again
   - make i915 mitigations options via parameter
   - HSW GT1 GPU hangs fixes
   - DG1 workaround hang fixes
   - TGL DMAR hang avoidance
   - Lots of GT fixes
   - follow on fixes for residuals clear
   - gen7 per-engine-reset support
   - HDCP2.2 + HDCP1.4 GEN12 DP MST support
   - TGL clear color support
   - backlight refactoring
   - VRR/Adaptive sync enabling on DP/EDP for TGL+
   - async flips for all ilk+

  amdgpu:
   - rework IH ring handling (Vega/Navi)
   - rework HDP handling (Vega/Navi)
   - swSMU updates for renoir/vangogh
   - Sienna Cichild overdrive support
   - FP16 on DCE8-11 support
   - GPU reset on navy flounder/vangogh
   - SMU profile fixes for APU
   - SR-IOV fixes
   - Vangogh SMU fixes
   - fan speed control fixes

  amdkfd:
   - config handling fix
   - buffer free fix
   - recursive lock warnings fix

  nouveau:
   - Turing MMU fault recovery fixes
   - mDP connectors reporting fix
   - audio locking fixes
   - rework engines/instances code to support new scheme

  tegra:
   - VIC newer firmware support
   - display/gr2d fixes for older tegra
   - pm reference leak fix

  mediatek:
   - SOC MT8183 support
   - decouple sub driver + share mtk mutex driver

  radeon:
   - PCI resource fix for some platforms

  ingenic:
   - pm support
   - 8-bit delta RGB panels

  vmwgfx:
   - managed driver helpers

  vc4:
   - BCM2711 DSI1 support
   - converted to atomic helpers
   - enable 10/12 bpc outputs
   - gem prime mmap helpers
   - CEC fix

  omap:
   - use degamma table
   - CTM support
   - rework DSI support

  imx:
   - stack usage fixes
   - drm managed support
   - imx-tve clock provider leak fix
-

  rcar-du:
   - default mode fixes
   - conversion to managed API

  hisilicon:
   - use simple encoder

  vkms:
   - writeback connector support

  d3:
   - BT2020 support"

* tag 'drm-next-2021-02-19' of git://anongit.freedesktop.org/drm/drm: (1459 commits)
  drm/amdgpu: Set reference clock to 100Mhz on Renoir (v2)
  drm/radeon: OLAND boards don't have VCE
  drm/amdkfd: Fix recursive lock warnings
  drm/amd/display: Add FPU wrappers to dcn21_validate_bandwidth()
  drm/amd/display: Fix potential integer overflow
  drm/amdgpu/display: remove hdcp_srm sysfs on device removal
  drm/amdgpu: fix CGTS_TCC_DISABLE register offset on gfx10.3
  drm/i915/gt: Correct surface base address for renderclear
  drm/i915: Disallow plane x+w>stride on ilk+ with X-tiling
  drm/nouveau/top/ga100: initial support
  drm/nouveau/top: add ioctrl/nvjpg
  drm/nouveau/privring: rename from ibus
  drm/nouveau/nvkm: remove nvkm_subdev.index
  drm/nouveau/nvkm: determine subdev id/order from layout
  drm/nouveau/vic: switch to instanced constructor
  drm/nouveau/sw: switch to instanced constructor
  drm/nouveau/sec2: switch to instanced constructor
  drm/nouveau/sec: switch to instanced constructor
  drm/nouveau/pm: switch to instanced constructor
  drm/nouveau/nvenc: switch to instanced constructor
  ...

1 files changed, 67 insertions, 5 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 37639214cbbb..84d2eaa38101 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -29,6 +29,7 @@
 
 #include "amdgpu.h"
 #include "amdgpu_gfx.h"
+#include "amdgpu_ring.h"
 #include "vi.h"
 #include "vi_structs.h"
 #include "vid.h"
@@ -1923,8 +1924,7 @@ static int gfx_v8_0_compute_ring_init(struct amdgpu_device *adev, int ring_id,
 		+ ((ring->me - 1) * adev->gfx.mec.num_pipe_per_mec)
 		+ ring->pipe;
 
-	hw_prio = amdgpu_gfx_is_high_priority_compute_queue(adev, ring->pipe,
-							    ring->queue) ?
+	hw_prio = amdgpu_gfx_is_high_priority_compute_queue(adev, ring) ?
 			AMDGPU_GFX_PIPE_PRIO_HIGH : AMDGPU_RING_PRIO_DEFAULT;
 	/* type-2 packets are deprecated on MEC, use type-3 instead */
 	r = amdgpu_ring_init(adev, ring, 1024,
@@ -4442,8 +4442,7 @@ static void gfx_v8_0_mqd_set_priority(struct amdgpu_ring *ring, struct vi_mqd *m
 	struct amdgpu_device *adev = ring->adev;
 
 	if (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE) {
-		if (amdgpu_gfx_is_high_priority_compute_queue(adev, ring->pipe,
-							      ring->queue)) {
+		if (amdgpu_gfx_is_high_priority_compute_queue(adev, ring)) {
 			mqd->cp_hqd_pipe_priority = AMDGPU_GFX_PIPE_PRIO_HIGH;
 			mqd->cp_hqd_queue_priority =
 				AMDGPU_GFX_QUEUE_PRIORITY_MAXIMUM;
@@ -6847,6 +6846,66 @@ static void gfx_v8_0_emit_mem_sync_compute(struct amdgpu_ring *ring)
 	amdgpu_ring_write(ring, 0x0000000A);	/* poll interval */
 }
 
+
+/* mmSPI_WCL_PIPE_PERCENT_CS[0-7]_DEFAULT values are same */
+#define mmSPI_WCL_PIPE_PERCENT_CS_DEFAULT	0x0000007f
+static void gfx_v8_0_emit_wave_limit_cs(struct amdgpu_ring *ring,
+					uint32_t pipe, bool enable)
+{
+	uint32_t val;
+	uint32_t wcl_cs_reg;
+
+	val = enable ? 0x1 : mmSPI_WCL_PIPE_PERCENT_CS_DEFAULT;
+
+	switch (pipe) {
+	case 0:
+		wcl_cs_reg = mmSPI_WCL_PIPE_PERCENT_CS0;
+		break;
+	case 1:
+		wcl_cs_reg = mmSPI_WCL_PIPE_PERCENT_CS1;
+		break;
+	case 2:
+		wcl_cs_reg = mmSPI_WCL_PIPE_PERCENT_CS2;
+		break;
+	case 3:
+		wcl_cs_reg = mmSPI_WCL_PIPE_PERCENT_CS3;
+		break;
+	default:
+		DRM_DEBUG("invalid pipe %d\n", pipe);
+		return;
+	}
+
+	amdgpu_ring_emit_wreg(ring, wcl_cs_reg, val);
+
+}
+
+#define mmSPI_WCL_PIPE_PERCENT_GFX_DEFAULT	0x07ffffff
+static void gfx_v8_0_emit_wave_limit(struct amdgpu_ring *ring, bool enable)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t val;
+	int i;
+
+	/* mmSPI_WCL_PIPE_PERCENT_GFX is 7 bit multiplier register to limit
+	 * number of gfx waves. Setting 5 bit will make sure gfx only gets
+	 * around 25% of gpu resources.
+	 */
+	val = enable ? 0x1f : mmSPI_WCL_PIPE_PERCENT_GFX_DEFAULT;
+	amdgpu_ring_emit_wreg(ring, mmSPI_WCL_PIPE_PERCENT_GFX, val);
+
+	/* Restrict waves for normal/low priority compute queues as well
+	 * to get best QoS for high priority compute jobs.
+	 *
+	 * amdgpu controls only 1st ME(0-3 CS pipes).
+	 */
+	for (i = 0; i < adev->gfx.mec.num_pipe_per_mec; i++) {
+		if (i != ring->pipe)
+			gfx_v8_0_emit_wave_limit_cs(ring, i, enable);
+
+	}
+
+}
+
 static const struct amd_ip_funcs gfx_v8_0_ip_funcs = {
 	.name = "gfx_v8_0",
 	.early_init = gfx_v8_0_early_init,
@@ -6930,7 +6989,9 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_compute = {
 		7 + /* gfx_v8_0_ring_emit_pipeline_sync */
 		VI_FLUSH_GPU_TLB_NUM_WREG * 5 + 7 + /* gfx_v8_0_ring_emit_vm_flush */
 		7 + 7 + 7 + /* gfx_v8_0_ring_emit_fence_compute x3 for user fence, vm fence */
-		7, /* gfx_v8_0_emit_mem_sync_compute */
+		7 + /* gfx_v8_0_emit_mem_sync_compute */
+		5 + /* gfx_v8_0_emit_wave_limit for updating mmSPI_WCL_PIPE_PERCENT_GFX register */
+		15, /* for updating 3 mmSPI_WCL_PIPE_PERCENT_CS registers */
 	.emit_ib_size =	7, /* gfx_v8_0_ring_emit_ib_compute */
 	.emit_ib = gfx_v8_0_ring_emit_ib_compute,
 	.emit_fence = gfx_v8_0_ring_emit_fence_compute,
@@ -6944,6 +7005,7 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_compute = {
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.emit_wreg = gfx_v8_0_ring_emit_wreg,
 	.emit_mem_sync = gfx_v8_0_emit_mem_sync_compute,
+	.emit_wave_limit = gfx_v8_0_emit_wave_limit,
 };
 
 static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_kiq = {