Merge tag 'amd-drm-next-6.6-2023-08-11' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amdgpu:
- SDMA 6.1.0 support
- SMU 13.x fixes
- PSP 13.x fixes
- HDP 6.1 support
- SMUIO 14.0 support
- IH 6.1 support
- Coding style cleanups
- Misc display fixes
- Initial Freesync panel replay support
- RAS fixes
- SDMA 5.2 MGCG updates
- SR-IOV fixes
- DCN3+ gamma fix
- Revert zpos properly until IGT regression is fixed
- NBIO 7.9 fixes
- Use TTM to manage the doorbell BAR
- Async flip fix
- DPIA tracing support
- DCN 3.x TMDS HDMI fixes
- FRU fixes

amdkfd:
- Coding style cleanups
- SVM fixes
- Trap handler fixes
- Convert older APUs to use dGPU path like newer APUs
- Drop IOMMUv2 path as it is no longer used

radeon:
- Coding style cleanups

drm buddy:
- Fix debugging output

UAPI:
- A new memory pool was added to amdgpu_drm.h since we converted doorbell BAR management to use TTM,
  but userspace is blocked from allocating from it at this point, so kind of not really anything new
  here per se

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

# -----BEGIN PGP SIGNATURE-----
#
# iHUEABYKAB0WIQQgO5Idg2tXNTSZAr293/aFa7yZ2AUCZNahZwAKCRC93/aFa7yZ
# 2KNjAP0UV2vJZjrze7OQI/YoI+40UlGjS81nKGlMIN3eR8nzvAD/c9McLJViL82R
# idEAK7tsr/MaCKoPAlED7CkUZiHNlQw=
# =4w7I
# -----END PGP SIGNATURE-----
# gpg: Signature made Sat 12 Aug 2023 07:00:23 AEST
# gpg:                using EDDSA key 203B921D836B5735349902BDBDDFF6856BBC99D8
# gpg: Can't check signature: No public key
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230811211554.7804-1-alexander.deucher@amd.com

1 files changed, 37 insertions, 33 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 62011a521833..886c7c6f1c3b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -35,6 +35,7 @@
 #include "amdgpu_xgmi.h"
 #include "ivsrcid/nbio/irqsrcs_nbif_7_4.h"
 #include "nbio_v4_3.h"
+#include "nbio_v7_9.h"
 #include "atom.h"
 #include "amdgpu_reset.h"
 
@@ -757,16 +758,6 @@ static int __amdgpu_ras_feature_enable(struct amdgpu_device *adev,
 	return 0;
 }
 
-static int amdgpu_ras_check_feature_allowed(struct amdgpu_device *adev,
-		struct ras_common_if *head)
-{
-	if (amdgpu_ras_is_feature_allowed(adev, head) ||
-		amdgpu_ras_is_poison_mode_supported(adev))
-		return 1;
-	else
-		return 0;
-}
-
 /* wrapper of psp_ras_enable_features */
 int amdgpu_ras_feature_enable(struct amdgpu_device *adev,
 		struct ras_common_if *head, bool enable)
@@ -778,7 +769,16 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev,
 	if (!con)
 		return -EINVAL;
 
-	if (head->block == AMDGPU_RAS_BLOCK__GFX) {
+	/* Do not enable ras feature if it is not allowed */
+	if (enable &&
+	    head->block != AMDGPU_RAS_BLOCK__GFX &&
+	    !amdgpu_ras_is_feature_allowed(adev, head))
+		goto out;
+
+	/* Only enable gfx ras feature from host side */
+	if (head->block == AMDGPU_RAS_BLOCK__GFX &&
+	    !amdgpu_sriov_vf(adev) &&
+	    !amdgpu_ras_intr_triggered()) {
 		info = kzalloc(sizeof(union ta_ras_cmd_input), GFP_KERNEL);
 		if (!info)
 			return -ENOMEM;
@@ -794,16 +794,7 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev,
 				.error_type = amdgpu_ras_error_to_ta(head->type),
 			};
 		}
-	}
-
-	/* Do not enable if it is not allowed. */
-	if (enable && !amdgpu_ras_check_feature_allowed(adev, head))
-		goto out;
 
-	/* Only enable ras feature operation handle on host side */
-	if (head->block == AMDGPU_RAS_BLOCK__GFX &&
-		!amdgpu_sriov_vf(adev) &&
-		!amdgpu_ras_intr_triggered()) {
 		ret = psp_ras_enable_features(&adev->psp, info, enable);
 		if (ret) {
 			dev_err(adev->dev, "ras %s %s failed poison:%d ret:%d\n",
@@ -2654,6 +2645,10 @@ int amdgpu_ras_init(struct amdgpu_device *adev)
 			 * check DF RAS */
 			adev->nbio.ras = &nbio_v4_3_ras;
 		break;
+	case IP_VERSION(7, 9, 0):
+		if (!adev->gmc.is_app_apu)
+			adev->nbio.ras = &nbio_v7_9_ras;
+		break;
 	default:
 		/* nbio ras is not available */
 		break;
@@ -2777,23 +2772,28 @@ int amdgpu_ras_block_late_init(struct amdgpu_device *adev,
 			goto cleanup;
 	}
 
-	r = amdgpu_ras_sysfs_create(adev, ras_block);
-	if (r)
-		goto interrupt;
+	if (ras_obj->hw_ops &&
+	    (ras_obj->hw_ops->query_ras_error_count ||
+	     ras_obj->hw_ops->query_ras_error_status)) {
+		r = amdgpu_ras_sysfs_create(adev, ras_block);
+		if (r)
+			goto interrupt;
 
-	/* Those are the cached values at init.
-	 */
-	query_info = kzalloc(sizeof(struct ras_query_if), GFP_KERNEL);
-	if (!query_info)
-		return -ENOMEM;
-	memcpy(&query_info->head, ras_block, sizeof(struct ras_common_if));
+		/* Those are the cached values at init.
+		 */
+		query_info = kzalloc(sizeof(*query_info), GFP_KERNEL);
+		if (!query_info)
+			return -ENOMEM;
+		memcpy(&query_info->head, ras_block, sizeof(struct ras_common_if));
 
-	if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count, query_info) == 0) {
-		atomic_set(&con->ras_ce_count, ce_count);
-		atomic_set(&con->ras_ue_count, ue_count);
+		if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count, query_info) == 0) {
+			atomic_set(&con->ras_ce_count, ce_count);
+			atomic_set(&con->ras_ue_count, ue_count);
+		}
+
+		kfree(query_info);
 	}
 
-	kfree(query_info);
 	return 0;
 
 interrupt:
@@ -3148,6 +3148,10 @@ int amdgpu_ras_is_supported(struct amdgpu_device *adev,
 	 * that the ras block supports ras function.
 	 */
 	if (!ret &&
+	    (block == AMDGPU_RAS_BLOCK__GFX ||
+	     block == AMDGPU_RAS_BLOCK__SDMA ||
+	     block == AMDGPU_RAS_BLOCK__VCN ||
+	     block == AMDGPU_RAS_BLOCK__JPEG) &&
 	    amdgpu_ras_is_poison_mode_supported(adev) &&
 	    amdgpu_ras_get_ras_block(adev, block, 0))
 		ret = 1;