Merge tag 'amd-drm-next-6.7-2023-10-13' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.7-2023-10-13:

amdgpu:
- DC replay fixes
- Misc code cleanups and spelling fixes
- Documentation updates
- RAS EEPROM Updates
- FRU EEPROM Updates
- IP discovery updates
- SR-IOV fixes
- RAS updates
- DC PQ fixes
- SMU 13.0.6 updates
- GC 11.5 Support
- NBIO 7.11 Support
- GMC 11 Updates
- Reset fixes
- SMU 11.5 Updates
- SMU 13.0 OD support
- Use flexible arrays for bo list handling
- W=1 Fixes
- SubVP fixes
- DPIA fixes
- DCN 3.5 Support
- Devcoredump fixes
- VPE 6.1 support
- VCN 4.0 Updates
- S/G display fixes
- DML fixes
- DML2 Support
- MST fixes
- VRR fixes
- Enable seamless boot in more cases
- Enable content type property for HDMI
- OLED fixes
- Rework and clean up GPUVM TLB flushing
- DC ODM fixes
- DP 2.x fixes
- AGP aperture fixes
- SDMA firmware loading cleanups
- Cyan Skillfish GPU clock counter fix
- GC 11 GART fix
- Cache GPU fault info for userspace queries
- DC cursor check fixes
- eDP fixes
- DC FP handling fixes
- Variable sized array fixes
- SMU 13.0.x fixes
- IB start and size alignment fixes for VCN
- SMU 14 Support
- Suspend and resume sequence rework
- vkms fix

amdkfd:
- GC 11 fixes
- GC 10 fixes
- Doorbell fixes
- CWSR fixes
- SVM fixes
- Clean up GC info enumeration
- Rework memory limit handling
- Coherent memory handling fixes
- Use partial migrations in GPU faults
- TLB flush fixes
- DMA unmap fixes
- GC 9.4.3 fixes
- SQ interrupt fix
- GTT mapping fix
- GC 11.5 Support

radeon:
- Misc code cleanups
- W=1 Fixes
- Fix possible buffer overflow
- Fix possible NULL pointer dereference

UAPI:
- Add EXT_COHERENT memory allocation flags.  These allow for system scope atomics.
  Proposed userspace: https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/pull/88
- Add support for new VPE engine.  This is a memory to memory copy engine with advanced scaling, CSC, and color management features
  Proposed mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25713
- Add INFO IOCTL interface to query GPU faults
  Proposed Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23238
  Proposed libdrm MR: https://gitlab.freedesktop.org/mesa/drm/-/merge_requests/298

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231013175758.1735031-1-alexander.deucher@amd.com

1 files changed, 30 insertions, 22 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index cd37f45e01a1..dff66e1ae7ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -469,7 +469,7 @@ static int sdma_v4_0_irq_id_to_seq(unsigned client_id)
 
 static void sdma_v4_0_init_golden_registers(struct amdgpu_device *adev)
 {
-	switch (adev->ip_versions[SDMA0_HWIP][0]) {
+	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
 	case IP_VERSION(4, 0, 0):
 		soc15_program_register_sequence(adev,
 						golden_settings_sdma_4,
@@ -539,7 +539,7 @@ static void sdma_v4_0_setup_ulv(struct amdgpu_device *adev)
 	 * The only chips with SDMAv4 and ULV are VG10 and VG20.
 	 * Server SKUs take a different hysteresis setting from other SKUs.
 	 */
-	switch (adev->ip_versions[SDMA0_HWIP][0]) {
+	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
 	case IP_VERSION(4, 0, 0):
 		if (adev->pdev->device == 0x6860)
 			break;
@@ -578,8 +578,10 @@ static int sdma_v4_0_init_microcode(struct amdgpu_device *adev)
 	int ret, i;
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
-		if (adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 2, 2) ||
-                    adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 4, 0)) {
+		if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) ==
+			    IP_VERSION(4, 2, 2) ||
+		    amdgpu_ip_version(adev, SDMA0_HWIP, 0) ==
+			    IP_VERSION(4, 4, 0)) {
 			/* Acturus & Aldebaran will leverage the same FW memory
 			   for every SDMA instance */
 			ret = amdgpu_sdma_init_microcode(adev, 0, true);
@@ -978,7 +980,8 @@ static void sdma_v4_0_ctx_switch_enable(struct amdgpu_device *adev, bool enable)
 		 * Arcturus for the moment and firmware version 14
 		 * and above.
 		 */
-		if (adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 2, 2) &&
+		if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) ==
+			    IP_VERSION(4, 2, 2) &&
 		    adev->sdma.instance[i].fw_version >= 14)
 			WREG32_SDMA(i, mmSDMA0_PUB_DUMMY_REG2, enable);
 		/* Extend page fault timeout to avoid interrupt storm */
@@ -1255,7 +1258,7 @@ static void sdma_v4_0_init_pg(struct amdgpu_device *adev)
 	if (!(adev->pg_flags & AMD_PG_SUPPORT_SDMA))
 		return;
 
-	switch (adev->ip_versions[SDMA0_HWIP][0]) {
+	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
 	case IP_VERSION(4, 1, 0):
         case IP_VERSION(4, 1, 1):
 	case IP_VERSION(4, 1, 2):
@@ -1698,7 +1701,7 @@ static bool sdma_v4_0_fw_support_paging_queue(struct amdgpu_device *adev)
 {
 	uint fw_version = adev->sdma.instance[0].fw_version;
 
-	switch (adev->ip_versions[SDMA0_HWIP][0]) {
+	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
 	case IP_VERSION(4, 0, 0):
 		return fw_version >= 430;
 	case IP_VERSION(4, 0, 1):
@@ -1717,13 +1720,11 @@ static int sdma_v4_0_early_init(void *handle)
 	int r;
 
 	r = sdma_v4_0_init_microcode(adev);
-	if (r) {
-		DRM_ERROR("Failed to load sdma firmware!\n");
+	if (r)
 		return r;
-	}
 
 	/* TODO: Page queue breaks driver reload under SRIOV */
-	if ((adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 0, 0)) &&
+	if ((amdgpu_ip_version(adev, SDMA0_HWIP, 0) == IP_VERSION(4, 0, 0)) &&
 	    amdgpu_sriov_vf((adev)))
 		adev->sdma.has_page_queue = false;
 	else if (sdma_v4_0_fw_support_paging_queue(adev))
@@ -1823,7 +1824,9 @@ static int sdma_v4_0_sw_init(void *handle)
 		 * On Arcturus, SDMA instance 5~7 has a different vmhub
 		 * type(AMDGPU_MMHUB1).
 		 */
-		if (adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 2, 2) && i >= 5)
+		if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) ==
+			    IP_VERSION(4, 2, 2) &&
+		    i >= 5)
 			ring->vm_hub = AMDGPU_MMHUB1(0);
 		else
 			ring->vm_hub = AMDGPU_MMHUB0(0);
@@ -1843,8 +1846,10 @@ static int sdma_v4_0_sw_init(void *handle)
 			/* paging queue use same doorbell index/routing as gfx queue
 			 * with 0x400 (4096 dwords) offset on second doorbell page
 			 */
-			if (adev->ip_versions[SDMA0_HWIP][0] >= IP_VERSION(4, 0, 0) &&
-			    adev->ip_versions[SDMA0_HWIP][0] < IP_VERSION(4, 2, 0)) {
+			if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) >=
+				    IP_VERSION(4, 0, 0) &&
+			    amdgpu_ip_version(adev, SDMA0_HWIP, 0) <
+				    IP_VERSION(4, 2, 0)) {
 				ring->doorbell_index =
 					adev->doorbell_index.sdma_engine[i] << 1;
 				ring->doorbell_index += 0x400;
@@ -1856,7 +1861,9 @@ static int sdma_v4_0_sw_init(void *handle)
 					(adev->doorbell_index.sdma_engine[i] + 1) << 1;
 			}
 
-			if (adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 2, 2) && i >= 5)
+			if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) ==
+				    IP_VERSION(4, 2, 2) &&
+			    i >= 5)
 				ring->vm_hub = AMDGPU_MMHUB1(0);
 			else
 				ring->vm_hub = AMDGPU_MMHUB0(0);
@@ -1890,8 +1897,8 @@ static int sdma_v4_0_sw_fini(void *handle)
 			amdgpu_ring_fini(&adev->sdma.instance[i].page);
 	}
 
-	if (adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 2, 2) ||
-            adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 4, 0))
+	if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) == IP_VERSION(4, 2, 2) ||
+	    amdgpu_ip_version(adev, SDMA0_HWIP, 0) == IP_VERSION(4, 4, 0))
 		amdgpu_sdma_destroy_inst_ctx(adev, true);
 	else
 		amdgpu_sdma_destroy_inst_ctx(adev, false);
@@ -2036,14 +2043,16 @@ static int sdma_v4_0_process_trap_irq(struct amdgpu_device *adev,
 		amdgpu_fence_process(&adev->sdma.instance[instance].ring);
 		break;
 	case 1:
-		if (adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 2, 0))
+		if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) ==
+		    IP_VERSION(4, 2, 0))
 			amdgpu_fence_process(&adev->sdma.instance[instance].page);
 		break;
 	case 2:
 		/* XXX compute */
 		break;
 	case 3:
-		if (adev->ip_versions[SDMA0_HWIP][0] != IP_VERSION(4, 2, 0))
+		if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) !=
+		    IP_VERSION(4, 2, 0))
 			amdgpu_fence_process(&adev->sdma.instance[instance].page);
 		break;
 	}
@@ -2259,7 +2268,7 @@ static int sdma_v4_0_set_powergating_state(void *handle,
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	switch (adev->ip_versions[SDMA0_HWIP][0]) {
+	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
 	case IP_VERSION(4, 1, 0):
 	case IP_VERSION(4, 1, 1):
 	case IP_VERSION(4, 1, 2):
@@ -2622,7 +2631,7 @@ static struct amdgpu_sdma_ras sdma_v4_0_ras = {
 
 static void sdma_v4_0_set_ras_funcs(struct amdgpu_device *adev)
 {
-	switch (adev->ip_versions[SDMA0_HWIP][0]) {
+	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
 	case IP_VERSION(4, 2, 0):
 	case IP_VERSION(4, 2, 2):
 		adev->sdma.ras = &sdma_v4_0_ras;
@@ -2633,7 +2642,6 @@ static void sdma_v4_0_set_ras_funcs(struct amdgpu_device *adev)
 	default:
 		break;
 	}
-
 }
 
 const struct amdgpu_ip_block_version sdma_v4_0_ip_block = {