Merge tag 'drm-next-2020-02-07' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Just some fixes for this merge window: the tegra changes fix some
  regressions in the merge, nouveau has a few modesetting fixes.

  The amdgpu fixes are bit bigger, but they contain a couple of weeks of
  fixes, and don't seem to contain anything that isn't really a fix.

  Summary:

  tegra:
   - merge window regression fixes

  nouveau:
   - couple of volta/turing modesetting fixes

  amdgpu:
   - EDC fixes for Arcturus
   - GDDR6 memory training fixe
   - Fix for reading gfx clockgating registers while in GFXOFF state
   - i2c freq fixes
   - Misc display fixes
   - TLB invalidation fix when using semaphores
   - VCN 2.5 instancing fixes
   - Switch raven1 gfxoff to a blacklist
   - Coreboot workaround for KV/KB
   - Root cause dongle fixes for display and revert workaround
   - Enable GPU reset for renoir and navi
   - Navi overclocking fixes
   - Fix up confusing warnings in display clock validation on raven

  amdkfd:
   - SDMA fix

  radeon:
   - Misc LUT fixes"

* tag 'drm-next-2020-02-07' of git://anongit.freedesktop.org/drm/drm: (90 commits)
  gpu: host1x: Set DMA direction only for DMA-mapped buffer objects
  drm/tegra: Reuse IOVA mapping where possible
  drm/tegra: Relax IOMMU usage criteria on old Tegra
  drm/amd/dm/mst: Ignore payload update failures
  drm/amdgpu: update default voltage for boot od table for navi1x
  drm/amdgpu/smu10: fix smu10_get_clock_by_type_with_voltage
  drm/amdgpu/smu10: fix smu10_get_clock_by_type_with_latency
  drm/amdgpu/display: handle multiple numbers of fclks in dcn_calcs.c (v2)
  drm/amdgpu: fetch default VDDC curve voltages (v2)
  drm/amdgpu/smu_v11_0: Correct behavior of restoring default tables (v2)
  drm/amdgpu/navi10: add OD_RANGE for navi overclocking
  drm/amdgpu/navi: fix index for OD MCLK
  drm/amd/display: Fix HW/SW state mismatch
  drm/amd/display: Fix a typo when computing dsc configuration
  drm/amd/powerplay: fix navi10 system intermittent reboot issue V2
  drm/amdkfd: Fix a bug in SDMA RLC queue counting under HWS mode
  drm/amd/display: Only enable cursor on pipes that need it
  drm/nouveau/kms/gv100-: avoid sending a core update until the first modeset
  drm/nouveau/kms/gv100-: move window ownership setup into modesetting path
  drm/nouveau/disp/gv100-: halt NV_PDISP_FE_RM_INTR_STAT_CTRL_DISP_ERROR storms
  ...

1 files changed, 94 insertions, 2 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index b88b8b82bb64..0f960b498792 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -296,7 +296,7 @@ int amdgpu_gfx_kiq_init_ring(struct amdgpu_device *adev,
 
 	spin_lock_init(&kiq->ring_lock);
 
-	r = amdgpu_device_wb_get(adev, &adev->virt.reg_val_offs);
+	r = amdgpu_device_wb_get(adev, &kiq->reg_val_offs);
 	if (r)
 		return r;
 
@@ -321,7 +321,7 @@ int amdgpu_gfx_kiq_init_ring(struct amdgpu_device *adev,
 
 void amdgpu_gfx_kiq_free_ring(struct amdgpu_ring *ring)
 {
-	amdgpu_device_wb_free(ring->adev, ring->adev->virt.reg_val_offs);
+	amdgpu_device_wb_free(ring->adev, ring->adev->gfx.kiq.reg_val_offs);
 	amdgpu_ring_fini(ring);
 }
 
@@ -658,3 +658,95 @@ int amdgpu_gfx_cp_ecc_error_irq(struct amdgpu_device *adev,
 	amdgpu_ras_interrupt_dispatch(adev, &ih_data);
 	return 0;
 }
+
+uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg)
+{
+	signed long r, cnt = 0;
+	unsigned long flags;
+	uint32_t seq;
+	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
+	struct amdgpu_ring *ring = &kiq->ring;
+
+	BUG_ON(!ring->funcs->emit_rreg);
+
+	spin_lock_irqsave(&kiq->ring_lock, flags);
+	amdgpu_ring_alloc(ring, 32);
+	amdgpu_ring_emit_rreg(ring, reg);
+	amdgpu_fence_emit_polling(ring, &seq);
+	amdgpu_ring_commit(ring);
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
+
+	r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
+
+	/* don't wait anymore for gpu reset case because this way may
+	 * block gpu_recover() routine forever, e.g. this virt_kiq_rreg
+	 * is triggered in TTM and ttm_bo_lock_delayed_workqueue() will
+	 * never return if we keep waiting in virt_kiq_rreg, which cause
+	 * gpu_recover() hang there.
+	 *
+	 * also don't wait anymore for IRQ context
+	 * */
+	if (r < 1 && (adev->in_gpu_reset || in_interrupt()))
+		goto failed_kiq_read;
+
+	might_sleep();
+	while (r < 1 && cnt++ < MAX_KIQ_REG_TRY) {
+		msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
+		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
+	}
+
+	if (cnt > MAX_KIQ_REG_TRY)
+		goto failed_kiq_read;
+
+	return adev->wb.wb[kiq->reg_val_offs];
+
+failed_kiq_read:
+	pr_err("failed to read reg:%x\n", reg);
+	return ~0;
+}
+
+void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v)
+{
+	signed long r, cnt = 0;
+	unsigned long flags;
+	uint32_t seq;
+	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
+	struct amdgpu_ring *ring = &kiq->ring;
+
+	BUG_ON(!ring->funcs->emit_wreg);
+
+	spin_lock_irqsave(&kiq->ring_lock, flags);
+	amdgpu_ring_alloc(ring, 32);
+	amdgpu_ring_emit_wreg(ring, reg, v);
+	amdgpu_fence_emit_polling(ring, &seq);
+	amdgpu_ring_commit(ring);
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
+
+	r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
+
+	/* don't wait anymore for gpu reset case because this way may
+	 * block gpu_recover() routine forever, e.g. this virt_kiq_rreg
+	 * is triggered in TTM and ttm_bo_lock_delayed_workqueue() will
+	 * never return if we keep waiting in virt_kiq_rreg, which cause
+	 * gpu_recover() hang there.
+	 *
+	 * also don't wait anymore for IRQ context
+	 * */
+	if (r < 1 && (adev->in_gpu_reset || in_interrupt()))
+		goto failed_kiq_write;
+
+	might_sleep();
+	while (r < 1 && cnt++ < MAX_KIQ_REG_TRY) {
+
+		msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
+		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
+	}
+
+	if (cnt > MAX_KIQ_REG_TRY)
+		goto failed_kiq_write;
+
+	return;
+
+failed_kiq_write:
+	pr_err("failed to write reg:%x\n", reg);
+}