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, 26 insertions, 27 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 8d65b096db90..43f44cc201cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -147,6 +147,10 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 		}
 	}
 
+	/* from vcn4 and above, only unified queue is used */
+	adev->vcn.using_unified_queue =
+		amdgpu_ip_version(adev, UVD_HWIP, 0) >= IP_VERSION(4, 0, 0);
+
 	hdr = (const struct common_firmware_header *)adev->vcn.fw[0]->data;
 	adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version);
 
@@ -275,18 +279,6 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
 	return 0;
 }
 
-/* from vcn4 and above, only unified queue is used */
-static bool amdgpu_vcn_using_unified_queue(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-	bool ret = false;
-
-	if (amdgpu_ip_version(adev, UVD_HWIP, 0) >= IP_VERSION(4, 0, 0))
-		ret = true;
-
-	return ret;
-}
-
 bool amdgpu_vcn_is_disabled_vcn(struct amdgpu_device *adev, enum vcn_ring_type type, uint32_t vcn_instance)
 {
 	bool ret = false;
@@ -397,7 +389,9 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 		for (i = 0; i < adev->vcn.num_enc_rings; ++i)
 			fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_enc[i]);
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)	{
+		/* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
+		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
+		    !adev->vcn.using_unified_queue) {
 			struct dpg_pause_state new_state;
 
 			if (fence[j] ||
@@ -443,7 +437,9 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
 	amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
 	       AMD_PG_STATE_UNGATE);
 
-	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)	{
+	/* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
+	    !adev->vcn.using_unified_queue) {
 		struct dpg_pause_state new_state;
 
 		if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC) {
@@ -469,8 +465,12 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
 
 void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring)
 {
+	struct amdgpu_device *adev = ring->adev;
+
+	/* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
 	if (ring->adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
-		ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC)
+	    ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC &&
+	    !adev->vcn.using_unified_queue)
 		atomic_dec(&ring->adev->vcn.inst[ring->me].dpg_enc_submission_cnt);
 
 	atomic_dec(&ring->adev->vcn.total_submission_cnt);
@@ -724,12 +724,11 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	uint64_t addr = AMDGPU_GPU_PAGE_ALIGN(ib_msg->gpu_addr);
-	bool sq = amdgpu_vcn_using_unified_queue(ring);
 	uint32_t *ib_checksum;
 	uint32_t ib_pack_in_dw;
 	int i, r;
 
-	if (sq)
+	if (adev->vcn.using_unified_queue)
 		ib_size_dw += 8;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL,
@@ -742,7 +741,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
 	ib->length_dw = 0;
 
 	/* single queue headers */
-	if (sq) {
+	if (adev->vcn.using_unified_queue) {
 		ib_pack_in_dw = sizeof(struct amdgpu_vcn_decode_buffer) / sizeof(uint32_t)
 						+ 4 + 2; /* engine info + decoding ib in dw */
 		ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, ib_pack_in_dw, false);
@@ -761,7 +760,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (sq)
+	if (adev->vcn.using_unified_queue)
 		amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, ib_pack_in_dw);
 
 	r = amdgpu_job_submit_direct(job, ring, &f);
@@ -851,15 +850,15 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
 					 struct dma_fence **fence)
 {
 	unsigned int ib_size_dw = 16;
+	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
 	uint32_t *ib_checksum = NULL;
 	uint64_t addr;
-	bool sq = amdgpu_vcn_using_unified_queue(ring);
 	int i, r;
 
-	if (sq)
+	if (adev->vcn.using_unified_queue)
 		ib_size_dw += 8;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL,
@@ -873,7 +872,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
 
 	ib->length_dw = 0;
 
-	if (sq)
+	if (adev->vcn.using_unified_queue)
 		ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true);
 
 	ib->ptr[ib->length_dw++] = 0x00000018;
@@ -895,7 +894,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (sq)
+	if (adev->vcn.using_unified_queue)
 		amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11);
 
 	r = amdgpu_job_submit_direct(job, ring, &f);
@@ -918,15 +917,15 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 					  struct dma_fence **fence)
 {
 	unsigned int ib_size_dw = 16;
+	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
 	uint32_t *ib_checksum = NULL;
 	uint64_t addr;
-	bool sq = amdgpu_vcn_using_unified_queue(ring);
 	int i, r;
 
-	if (sq)
+	if (adev->vcn.using_unified_queue)
 		ib_size_dw += 8;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL,
@@ -940,7 +939,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 
 	ib->length_dw = 0;
 
-	if (sq)
+	if (adev->vcn.using_unified_queue)
 		ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true);
 
 	ib->ptr[ib->length_dw++] = 0x00000018;
@@ -962,7 +961,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (sq)
+	if (adev->vcn.using_unified_queue)
 		amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11);
 
 	r = amdgpu_job_submit_direct(job, ring, &f);