Merge tag 'drm-next-2024-07-26' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Fixes for rc1, mostly amdgpu, i915 and xe, with some other misc ones,
  doesn't seem to be anything too serious.

  amdgpu:
   - Bump driver version for GFX12 DCC
   - DC documention warning fixes
   - VCN unified queue power fix
   - SMU fix
   - RAS fix
   - Display corruption fix
   - SDMA 5.2 workaround
   - GFX12 fixes
   - Uninitialized variable fix
   - VCN/JPEG 4.0.3 fixes
   - Misc display fixes
   - RAS fixes
   - VCN4/5 harvest fix
   - GPU reset fix

  i915:
   - Reset intel_dp->link_trained before retraining the link
   - Don't switch the LTTPR mode on an active link
   - Do not consider preemption during execlists_dequeue for gen8
   - Allow NULL memory region

  xe:
   - xe_exec ioctl minor fix on sync entry cleanup upon error
   - SRIOV: limit VF LMEM provisioning
   - Wedge mode fixes

  v3d:
   - fix indirect dispatch on newer v3d revs

  panel:
   - fix panel backlight bindings"

* tag 'drm-next-2024-07-26' of https://gitlab.freedesktop.org/drm/kernel: (39 commits)
  drm/amdgpu: reset vm state machine after gpu reset(vram lost)
  drm/amdgpu: add missed harvest check for VCN IP v4/v5
  drm/amdgpu: Fix eeprom max record count
  drm/amdgpu: fix ras UE error injection failure issue
  drm/amd/display: Remove ASSERT if significance is zero in math_ceil2
  drm/amd/display: Check for NULL pointer
  drm/amdgpu/vcn: Use offsets local to VCN/JPEG in VF
  drm/amdgpu: Add empty HDP flush function to VCN v4.0.3
  drm/amdgpu: Add empty HDP flush function to JPEG v4.0.3
  drm/amd/amdgpu: Fix uninitialized variable warnings
  drm/amdgpu: Fix atomics on GFX12
  drm/amdgpu/sdma5.2: Update wptr registers as well as doorbell
  drm/i915: Allow NULL memory region
  drm/i915/gt: Do not consider preemption during execlists_dequeue for gen8
  dt-bindings: display: panel: samsung,atna33xc20: Document ATNA45AF01
  drm/xe: Don't suspend device upon wedge
  drm/xe: Wedge the entire device
  drm/xe/pf: Limit fair VF LMEM provisioning
  drm/xe/exec: Fix minor bug related to xe_sync_entry_cleanup
  drm/amd/display: fix corruption with high refresh rates on DCN 3.0
  ...

1 files changed, 51 insertions, 3 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index f53054e39ebb..9bae95538b62 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -45,6 +45,9 @@
 #define VCN_VID_SOC_ADDRESS_2_0		0x1fb00
 #define VCN1_VID_SOC_ADDRESS_3_0	0x48300
 
+#define NORMALIZE_VCN_REG_OFFSET(offset) \
+		(offset & 0x1FFFF)
+
 static int vcn_v4_0_3_start_sriov(struct amdgpu_device *adev);
 static void vcn_v4_0_3_set_unified_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v4_0_3_set_irq_funcs(struct amdgpu_device *adev);
@@ -1375,6 +1378,50 @@ static uint64_t vcn_v4_0_3_unified_ring_get_wptr(struct amdgpu_ring *ring)
 				    regUVD_RB_WPTR);
 }
 
+static void vcn_v4_0_3_enc_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
+				uint32_t val, uint32_t mask)
+{
+	/* For VF, only local offsets should be used */
+	if (amdgpu_sriov_vf(ring->adev))
+		reg = NORMALIZE_VCN_REG_OFFSET(reg);
+
+	amdgpu_ring_write(ring, VCN_ENC_CMD_REG_WAIT);
+	amdgpu_ring_write(ring, reg << 2);
+	amdgpu_ring_write(ring, mask);
+	amdgpu_ring_write(ring, val);
+}
+
+static void vcn_v4_0_3_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val)
+{
+	/* For VF, only local offsets should be used */
+	if (amdgpu_sriov_vf(ring->adev))
+		reg = NORMALIZE_VCN_REG_OFFSET(reg);
+
+	amdgpu_ring_write(ring, VCN_ENC_CMD_REG_WRITE);
+	amdgpu_ring_write(ring,	reg << 2);
+	amdgpu_ring_write(ring, val);
+}
+
+static void vcn_v4_0_3_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
+				unsigned int vmid, uint64_t pd_addr)
+{
+	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->vm_hub];
+
+	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
+
+	/* wait for reg writes */
+	vcn_v4_0_3_enc_ring_emit_reg_wait(ring, hub->ctx0_ptb_addr_lo32 +
+					vmid * hub->ctx_addr_distance,
+					lower_32_bits(pd_addr), 0xffffffff);
+}
+
+static void vcn_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring)
+{
+	/* VCN engine access for HDP flush doesn't work when RRMT is enabled.
+	 * This is a workaround to avoid any HDP flush through VCN ring.
+	 */
+}
+
 /**
  * vcn_v4_0_3_unified_ring_set_wptr - set enc write pointer
  *
@@ -1414,7 +1461,8 @@ static const struct amdgpu_ring_funcs vcn_v4_0_3_unified_ring_vm_funcs = {
 	.emit_ib_size = 5, /* vcn_v2_0_enc_ring_emit_ib */
 	.emit_ib = vcn_v2_0_enc_ring_emit_ib,
 	.emit_fence = vcn_v2_0_enc_ring_emit_fence,
-	.emit_vm_flush = vcn_v2_0_enc_ring_emit_vm_flush,
+	.emit_vm_flush = vcn_v4_0_3_enc_ring_emit_vm_flush,
+	.emit_hdp_flush = vcn_v4_0_3_ring_emit_hdp_flush,
 	.test_ring = amdgpu_vcn_enc_ring_test_ring,
 	.test_ib = amdgpu_vcn_unified_ring_test_ib,
 	.insert_nop = amdgpu_ring_insert_nop,
@@ -1422,8 +1470,8 @@ static const struct amdgpu_ring_funcs vcn_v4_0_3_unified_ring_vm_funcs = {
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.begin_use = amdgpu_vcn_ring_begin_use,
 	.end_use = amdgpu_vcn_ring_end_use,
-	.emit_wreg = vcn_v2_0_enc_ring_emit_wreg,
-	.emit_reg_wait = vcn_v2_0_enc_ring_emit_reg_wait,
+	.emit_wreg = vcn_v4_0_3_enc_ring_emit_wreg,
+	.emit_reg_wait = vcn_v4_0_3_enc_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };