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, 15 insertions, 20 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
index c50202215f6b..01d50ad603d3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -222,9 +222,9 @@ static struct aca_bank_error *new_bank_error(struct aca_error *aerr, struct aca_
 	INIT_LIST_HEAD(&bank_error->node);
 	memcpy(&bank_error->info, info, sizeof(*info));
 
-	mutex_lock(&aerr->lock);
+	spin_lock(&aerr->lock);
 	list_add_tail(&bank_error->node, &aerr->list);
-	mutex_unlock(&aerr->lock);
+	spin_unlock(&aerr->lock);
 
 	return bank_error;
 }
@@ -235,7 +235,7 @@ static struct aca_bank_error *find_bank_error(struct aca_error *aerr, struct aca
 	struct aca_bank_info *tmp_info;
 	bool found = false;
 
-	mutex_lock(&aerr->lock);
+	spin_lock(&aerr->lock);
 	list_for_each_entry(bank_error, &aerr->list, node) {
 		tmp_info = &bank_error->info;
 		if (tmp_info->socket_id == info->socket_id &&
@@ -246,7 +246,7 @@ static struct aca_bank_error *find_bank_error(struct aca_error *aerr, struct aca
 	}
 
 out_unlock:
-	mutex_unlock(&aerr->lock);
+	spin_unlock(&aerr->lock);
 
 	return found ? bank_error : NULL;
 }
@@ -474,7 +474,7 @@ static int aca_log_aca_error(struct aca_handle *handle, enum aca_error_type type
 	struct aca_error *aerr = &error_cache->errors[type];
 	struct aca_bank_error *bank_error, *tmp;
 
-	mutex_lock(&aerr->lock);
+	spin_lock(&aerr->lock);
 
 	if (list_empty(&aerr->list))
 		goto out_unlock;
@@ -485,7 +485,7 @@ static int aca_log_aca_error(struct aca_handle *handle, enum aca_error_type type
 	}
 
 out_unlock:
-	mutex_unlock(&aerr->lock);
+	spin_unlock(&aerr->lock);
 
 	return 0;
 }
@@ -534,7 +534,7 @@ int amdgpu_aca_get_error_data(struct amdgpu_device *adev, struct aca_handle *han
 	if (aca_handle_is_valid(handle))
 		return -EOPNOTSUPP;
 
-	if (!(BIT(type) & handle->mask))
+	if ((type < 0) || (!(BIT(type) & handle->mask)))
 		return  0;
 
 	return __aca_get_error_data(adev, handle, type, err_data, qctx);
@@ -542,7 +542,7 @@ int amdgpu_aca_get_error_data(struct amdgpu_device *adev, struct aca_handle *han
 
 static void aca_error_init(struct aca_error *aerr, enum aca_error_type type)
 {
-	mutex_init(&aerr->lock);
+	spin_lock_init(&aerr->lock);
 	INIT_LIST_HEAD(&aerr->list);
 	aerr->type = type;
 	aerr->nr_errors = 0;
@@ -561,11 +561,10 @@ static void aca_error_fini(struct aca_error *aerr)
 {
 	struct aca_bank_error *bank_error, *tmp;
 
-	mutex_lock(&aerr->lock);
+	spin_lock(&aerr->lock);
 	list_for_each_entry_safe(bank_error, tmp, &aerr->list, node)
 		aca_bank_error_remove(aerr, bank_error);
-
-	mutex_destroy(&aerr->lock);
+	spin_unlock(&aerr->lock);
 }
 
 static void aca_fini_error_cache(struct aca_handle *handle)
@@ -686,7 +685,8 @@ static void aca_manager_fini(struct aca_handle_manager *mgr)
 
 bool amdgpu_aca_is_enabled(struct amdgpu_device *adev)
 {
-	return adev->aca.is_enabled;
+	return (adev->aca.is_enabled ||
+		adev->debug_enable_ras_aca);
 }
 
 int amdgpu_aca_init(struct amdgpu_device *adev)
@@ -712,13 +712,6 @@ void amdgpu_aca_fini(struct amdgpu_device *adev)
 	atomic_set(&aca->ue_update_flag, 0);
 }
 
-int amdgpu_aca_reset(struct amdgpu_device *adev)
-{
-	amdgpu_aca_fini(adev);
-
-	return amdgpu_aca_init(adev);
-}
-
 void amdgpu_aca_set_smu_funcs(struct amdgpu_device *adev, const struct aca_smu_funcs *smu_funcs)
 {
 	struct amdgpu_aca *aca = &adev->aca;
@@ -892,7 +885,9 @@ DEFINE_DEBUGFS_ATTRIBUTE(aca_debug_mode_fops, NULL, amdgpu_aca_smu_debug_mode_se
 void amdgpu_aca_smu_debugfs_init(struct amdgpu_device *adev, struct dentry *root)
 {
 #if defined(CONFIG_DEBUG_FS)
-	if (!root || adev->ip_versions[MP1_HWIP][0] != IP_VERSION(13, 0, 6))
+	if (!root ||
+	    (adev->ip_versions[MP1_HWIP][0] != IP_VERSION(13, 0, 6) &&
+	     adev->ip_versions[MP1_HWIP][0] != IP_VERSION(13, 0, 14)))
 		return;
 
 	debugfs_create_file("aca_debug_mode", 0200, root, adev, &aca_debug_mode_fops);