Merge tag 'amd-drm-next-6.11-2024-06-07' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.11-2024-06-07:

amdgpu:
- DCN 4.0.x support
- DCN 3.5 updates
- GC 12.0 support
- DP MST fixes
- Cursor fixes
- MES11 updates
- MMHUB 4.1 support
- DML2 Updates
- DCN 3.1.5 fixes
- IPS fixes
- Various code cleanups
- GMC 12.0 support
- SDMA 7.0 support
- SMU 13 updates
- SR-IOV fixes
- VCN 5.x fixes
- MES12 support
- SMU 14.x updates
- Devcoredump improvements
- Fixes for HDP flush on platforms with >4k pages
- GC 9.4.3 fixes
- RAS ACA updates
- Silence UBSAN flex array warnings
- MMHUB 3.3 updates

amdkfd:
- Contiguous VRAM allocations
- GC 12.0 support
- SDMA 7.0 support
- SR-IOV fixes

radeon:
- Backlight workaround for iMac
- Silence UBSAN flex array warnings

UAPI:
- GFX12 modifier and DCC support
  Proposed Mesa changes:
  https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29510
- KFD GFX ALU exceptions
  Proposed ROCdebugger changes:
  https://github.com/ROCm/ROCdbgapi/commit/08c760622b6601abf906f75abbc5e21d9fd425df
  https://github.com/ROCm/ROCgdb/commit/944fe1c1414a68700414e86e32273b6bfa62ba6f
- KFD Contiguous VRAM allocation flag
  Proposed ROCr/HIP changes:
  https://github.com/ROCm/ROCT-Thunk-Interface/commit/f7b4a269914a3ab4f1e2453c2879adb97b5cc9e5
  https://github.com/ROCm/ROCR-Runtime/pull/214/commits/26e8530d05a775872cb06dde6693db72be0c454a
  https://github.com/ROCm/clr/commit/1d48f2a1ab38b632919c4b7274899b3faf4279ff

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240607195900.902537-1-alexander.deucher@amd.com

1 files changed, 63 insertions, 8 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 1d955652f3ba..19b1817b55d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -329,8 +329,9 @@ int amdgpu_gfx_kiq_init_ring(struct amdgpu_device *adev, int xcc_id)
 
 	ring->eop_gpu_addr = kiq->eop_gpu_addr;
 	ring->no_scheduler = true;
-	snprintf(ring->name, sizeof(ring->name), "kiq_%d.%d.%d.%d",
-		 xcc_id, ring->me, ring->pipe, ring->queue);
+	snprintf(ring->name, sizeof(ring->name), "kiq_%hhu.%hhu.%hhu.%hhu",
+		 (unsigned char)xcc_id, (unsigned char)ring->me,
+		 (unsigned char)ring->pipe, (unsigned char)ring->queue);
 	r = amdgpu_ring_init(adev, ring, 1024, irq, AMDGPU_CP_KIQ_IRQ_DRIVER0,
 			     AMDGPU_RING_PRIO_DEFAULT, NULL);
 	if (r)
@@ -539,7 +540,8 @@ int amdgpu_gfx_disable_kcq(struct amdgpu_device *adev, int xcc_id)
 	}
 
 	ras = amdgpu_ras_get_context(adev);
-	if ((amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3)) &&
+	if ((amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
+	     amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4)) &&
 		ras && (atomic_read(&ras->in_recovery) || hive_ras_recovery)) {
 		spin_unlock(&kiq->ring_lock);
 		return 0;
@@ -598,6 +600,44 @@ int amdgpu_queue_mask_bit_to_set_resource_bit(struct amdgpu_device *adev,
 	return set_resource_bit;
 }
 
+static int amdgpu_gfx_mes_enable_kcq(struct amdgpu_device *adev, int xcc_id)
+{
+	struct amdgpu_kiq *kiq = &adev->gfx.kiq[xcc_id];
+	struct amdgpu_ring *kiq_ring = &kiq->ring;
+	uint64_t queue_mask = ~0ULL;
+	int r, i, j;
+
+	amdgpu_device_flush_hdp(adev, NULL);
+
+	if (!adev->enable_uni_mes) {
+		spin_lock(&kiq->ring_lock);
+		r = amdgpu_ring_alloc(kiq_ring, kiq->pmf->set_resources_size);
+		if (r) {
+			dev_err(adev->dev, "Failed to lock KIQ (%d).\n", r);
+			spin_unlock(&kiq->ring_lock);
+			return r;
+		}
+
+		kiq->pmf->kiq_set_resources(kiq_ring, queue_mask);
+		r = amdgpu_ring_test_helper(kiq_ring);
+		spin_unlock(&kiq->ring_lock);
+		if (r)
+			dev_err(adev->dev, "KIQ failed to set resources\n");
+	}
+
+	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
+		j = i + xcc_id * adev->gfx.num_compute_rings;
+		r = amdgpu_mes_map_legacy_queue(adev,
+						&adev->gfx.compute_ring[j]);
+		if (r) {
+			dev_err(adev->dev, "failed to map compute queue\n");
+			return r;
+		}
+	}
+
+	return 0;
+}
+
 int amdgpu_gfx_enable_kcq(struct amdgpu_device *adev, int xcc_id)
 {
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq[xcc_id];
@@ -605,6 +645,9 @@ int amdgpu_gfx_enable_kcq(struct amdgpu_device *adev, int xcc_id)
 	uint64_t queue_mask = 0;
 	int r, i, j;
 
+	if (adev->enable_mes)
+		return amdgpu_gfx_mes_enable_kcq(adev, xcc_id);
+
 	if (!kiq->pmf || !kiq->pmf->kiq_map_queues || !kiq->pmf->kiq_set_resources)
 		return -EINVAL;
 
@@ -623,10 +666,11 @@ int amdgpu_gfx_enable_kcq(struct amdgpu_device *adev, int xcc_id)
 		queue_mask |= (1ull << amdgpu_queue_mask_bit_to_set_resource_bit(adev, i));
 	}
 
-	DRM_INFO("kiq ring mec %d pipe %d q %d\n", kiq_ring->me, kiq_ring->pipe,
-							kiq_ring->queue);
 	amdgpu_device_flush_hdp(adev, NULL);
 
+	DRM_INFO("kiq ring mec %d pipe %d q %d\n", kiq_ring->me, kiq_ring->pipe,
+		 kiq_ring->queue);
+
 	spin_lock(&kiq->ring_lock);
 	r = amdgpu_ring_alloc(kiq_ring, kiq->pmf->map_queues_size *
 					adev->gfx.num_compute_rings +
@@ -637,9 +681,6 @@ int amdgpu_gfx_enable_kcq(struct amdgpu_device *adev, int xcc_id)
 		return r;
 	}
 
-	if (adev->enable_mes)
-		queue_mask = ~0ULL;
-
 	kiq->pmf->kiq_set_resources(kiq_ring, queue_mask);
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 		j = i + xcc_id * adev->gfx.num_compute_rings;
@@ -666,6 +707,20 @@ int amdgpu_gfx_enable_kgq(struct amdgpu_device *adev, int xcc_id)
 
 	amdgpu_device_flush_hdp(adev, NULL);
 
+	if (adev->enable_mes) {
+		for (i = 0; i < adev->gfx.num_gfx_rings; i++) {
+			j = i + xcc_id * adev->gfx.num_gfx_rings;
+			r = amdgpu_mes_map_legacy_queue(adev,
+							&adev->gfx.gfx_ring[j]);
+			if (r) {
+				DRM_ERROR("failed to map gfx queue\n");
+				return r;
+			}
+		}
+
+		return 0;
+	}
+
 	spin_lock(&kiq->ring_lock);
 	/* No need to map kcq on the slave */
 	if (amdgpu_gfx_is_master_xcc(adev, xcc_id)) {