Merge tag 'drm-next-2020-10-15' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Not a major amount of change, the i915 trees got split into display
  and gt trees to better facilitate higher level review, and there's a
  major refactoring of i915 GEM locking to use more core kernel concepts
  (like ww-mutexes). msm gets per-process pagetables, older AMD SI cards
  get DC support, nouveau got a bump in displayport support with common
  code extraction from i915.

  Outside of drm this contains a couple of patches for hexint
  moduleparams which you've acked, and a virtio common code tree that
  you should also get via it's regular path.

  New driver:
   - Cadence MHDP8546 DisplayPort bridge driver

  core:
   - cross-driver scatterlist cleanups
   - devm_drm conversions
   - remove drm_dev_init
   - devm_drm_dev_alloc conversion

  ttm:
   - lots of refactoring and cleanups

  bridges:
   - chained bridge support in more drivers

  panel:
   - misc new panels

  scheduler:
   - cleanup priority levels

  displayport:
   - refactor i915 code into helpers for nouveau

  i915:
   - split into display and GT trees
   - WW locking refactoring in GEM
   - execbuf2 extension mechanism
   - syncobj timeline support
   - GEN 12 HOBL display powersaving
   - Rocket Lake display additions
   - Disable FBC on Tigerlake
   - Tigerlake Type-C + DP improvements
   - Hotplug interrupt refactoring

  amdgpu:
   - Sienna Cichlid updates
   - Navy Flounder updates
   - DCE6 (SI) support for DC
   - Plane rotation enabled
   - TMZ state info ioctl
   - PCIe DPC recovery support
   - DC interrupt handling refactor
   - OLED panel fixes

  amdkfd:
   - add SMI events for thermal throttling
   - SMI interface events ioctl update
   - process eviction counters

  radeon:
   - move to dma_ for allocations
   - expose sclk via sysfs

  msm:
   - DSI support for sm8150/sm8250
   - per-process GPU pagetable support
   - Displayport support

  mediatek:
   - move HDMI phy driver to PHY
   - convert mtk-dpi to bridge API
   - disable mt2701 tmds

  tegra:
   - bridge support

  exynos:
   - misc cleanups

  vc4:
   - dual display cleanups

  ast:
   - cleanups

  gma500:
   - conversion to GPIOd API

  hisilicon:
   - misc reworks

  ingenic:
   - clock handling and format improvements

  mcde:
   - DSI support

  mgag200:
   - desktop g200 support

  mxsfb:
   - i.MX7 + i.MX8M
   - alpha plane support

  panfrost:
   - devfreq support
   - amlogic SoC support

  ps8640:
   - EDID from eDP retrieval

  tidss:
   - AM65xx YUV workaround

  virtio:
   - virtio-gpu exported resources

  rcar-du:
   - R8A7742, R8A774E1 and R8A77961 support
   - YUV planar format fixes
   - non-visible plane handling
   - VSP device reference count fix
   - Kconfig fix to avoid displaying disabled options in .config"

* tag 'drm-next-2020-10-15' of git://anongit.freedesktop.org/drm/drm: (1494 commits)
  drm/ingenic: Fix bad revert
  drm/amdgpu: Fix invalid number of character '{' in amdgpu_acpi_init
  drm/amdgpu: Remove warning for virtual_display
  drm/amdgpu: kfd_initialized can be static
  drm/amd/pm: setup APU dpm clock table in SMU HW initialization
  drm/amdgpu: prevent spurious warning
  drm/amdgpu/swsmu: fix ARC build errors
  drm/amd/display: Fix OPTC_DATA_FORMAT programming
  drm/amd/display: Don't allow pstate if no support in blank
  drm/panfrost: increase readl_relaxed_poll_timeout values
  MAINTAINERS: Update entry for st7703 driver after the rename
  Revert "gpu/drm: ingenic: Add option to mmap GEM buffers cached"
  drm/amd/display: HDMI remote sink need mode validation for Linux
  drm/amd/display: Change to correct unit on audio rate
  drm/amd/display: Avoid set zero in the requested clk
  drm/amdgpu: align frag_end to covered address space
  drm/amdgpu: fix NULL pointer dereference for Renoir
  drm/vmwgfx: fix regression in thp code due to ttm init refactor.
  drm/amdgpu/swsmu: add interrupt work handler for smu11 parts
  drm/amdgpu/swsmu: add interrupt work function
  ...

1 files changed, 61 insertions, 21 deletions

diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index 954753600625..2b93b33b05e4 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -22,6 +22,54 @@ extern bool hang_debug;
 static void a4xx_dump(struct msm_gpu *gpu);
 static bool a4xx_idle(struct msm_gpu *gpu);
 
+static void a4xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
+{
+	struct msm_drm_private *priv = gpu->dev->dev_private;
+	struct msm_ringbuffer *ring = submit->ring;
+	unsigned int i;
+
+	for (i = 0; i < submit->nr_cmds; i++) {
+		switch (submit->cmd[i].type) {
+		case MSM_SUBMIT_CMD_IB_TARGET_BUF:
+			/* ignore IB-targets */
+			break;
+		case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
+			/* ignore if there has not been a ctx switch: */
+			if (priv->lastctx == submit->queue->ctx)
+				break;
+			fallthrough;
+		case MSM_SUBMIT_CMD_BUF:
+			OUT_PKT3(ring, CP_INDIRECT_BUFFER_PFE, 2);
+			OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
+			OUT_RING(ring, submit->cmd[i].size);
+			OUT_PKT2(ring);
+			break;
+		}
+	}
+
+	OUT_PKT0(ring, REG_AXXX_CP_SCRATCH_REG2, 1);
+	OUT_RING(ring, submit->seqno);
+
+	/* Flush HLSQ lazy updates to make sure there is nothing
+	 * pending for indirect loads after the timestamp has
+	 * passed:
+	 */
+	OUT_PKT3(ring, CP_EVENT_WRITE, 1);
+	OUT_RING(ring, HLSQ_FLUSH);
+
+	/* wait for idle before cache flush/interrupt */
+	OUT_PKT3(ring, CP_WAIT_FOR_IDLE, 1);
+	OUT_RING(ring, 0x00000000);
+
+	/* BIT(31) of CACHE_FLUSH_TS triggers CACHE_FLUSH_TS IRQ from GPU */
+	OUT_PKT3(ring, CP_EVENT_WRITE, 3);
+	OUT_RING(ring, CACHE_FLUSH_TS | BIT(31));
+	OUT_RING(ring, rbmemptr(ring, fence));
+	OUT_RING(ring, submit->seqno);
+
+	adreno_flush(gpu, ring, REG_A4XX_CP_RB_WPTR);
+}
+
 /*
  * a4xx_enable_hwcg() - Program the clock control registers
  * @device: The adreno device pointer
@@ -129,7 +177,7 @@ static bool a4xx_me_init(struct msm_gpu *gpu)
 	OUT_RING(ring, 0x00000000);
 	OUT_RING(ring, 0x00000000);
 
-	gpu->funcs->flush(gpu, ring);
+	adreno_flush(gpu, ring, REG_A4XX_CP_RB_WPTR);
 	return a4xx_idle(gpu);
 }
 
@@ -515,17 +563,6 @@ static struct msm_gpu_state *a4xx_gpu_state_get(struct msm_gpu *gpu)
 	return state;
 }
 
-/* Register offset defines for A4XX, in order of enum adreno_regs */
-static const unsigned int a4xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
-	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE, REG_A4XX_CP_RB_BASE),
-	REG_ADRENO_SKIP(REG_ADRENO_CP_RB_BASE_HI),
-	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR_ADDR, REG_A4XX_CP_RB_RPTR_ADDR),
-	REG_ADRENO_SKIP(REG_ADRENO_CP_RB_RPTR_ADDR_HI),
-	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR, REG_A4XX_CP_RB_RPTR),
-	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_WPTR, REG_A4XX_CP_RB_WPTR),
-	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_A4XX_CP_RB_CNTL),
-};
-
 static void a4xx_dump(struct msm_gpu *gpu)
 {
 	printk("status:   %08x\n",
@@ -576,6 +613,12 @@ static int a4xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
 	return 0;
 }
 
+static u32 a4xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
+{
+	ring->memptrs->rptr = gpu_read(gpu, REG_A4XX_CP_RB_RPTR);
+	return ring->memptrs->rptr;
+}
+
 static const struct adreno_gpu_funcs funcs = {
 	.base = {
 		.get_param = adreno_get_param,
@@ -583,8 +626,7 @@ static const struct adreno_gpu_funcs funcs = {
 		.pm_suspend = a4xx_pm_suspend,
 		.pm_resume = a4xx_pm_resume,
 		.recover = a4xx_recover,
-		.submit = adreno_submit,
-		.flush = adreno_flush,
+		.submit = a4xx_submit,
 		.active_ring = adreno_active_ring,
 		.irq = a4xx_irq,
 		.destroy = a4xx_destroy,
@@ -594,6 +636,7 @@ static const struct adreno_gpu_funcs funcs = {
 		.gpu_state_get = a4xx_gpu_state_get,
 		.gpu_state_put = adreno_gpu_state_put,
 		.create_address_space = adreno_iommu_create_address_space,
+		.get_rptr = a4xx_get_rptr,
 	},
 	.get_timestamp = a4xx_get_timestamp,
 };
@@ -631,15 +674,12 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev)
 
 	adreno_gpu->registers = adreno_is_a405(adreno_gpu) ? a405_registers :
 							     a4xx_registers;
-	adreno_gpu->reg_offsets = a4xx_register_offsets;
 
 	/* if needed, allocate gmem: */
-	if (adreno_is_a4xx(adreno_gpu)) {
-		ret = adreno_gpu_ocmem_init(dev->dev, adreno_gpu,
-					    &a4xx_gpu->ocmem);
-		if (ret)
-			goto fail;
-	}
+	ret = adreno_gpu_ocmem_init(dev->dev, adreno_gpu,
+				    &a4xx_gpu->ocmem);
+	if (ret)
+		goto fail;
 
 	if (!gpu->aspace) {
 		/* TODO we think it is possible to configure the GPU to