Merge tag 'amd-drm-next-5.17-2021-12-02' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.17-2021-12-02:

amdgpu:
- Use generic drm fb helpers
- PSR fixes
- Rework DCN3.1 clkmgr
- DPCD 1.3 fixes
- Misc display fixes can cleanups
- Clock query fixes for APUs
- LTTPR fixes
- DSC fixes
- Misc PM fixes
- RAS fixes
- OLED backlight fix
- SRIOV fixes
- Add STB (Smart Trace Buffer) for supported dGPUs
- IH rework
- Enable seamless boot for DCN3.01

amdkfd:
- Rework more stuff around IP discovery enumeration
- Further clean up of interfaces with amdgpu
- SVM fixes

radeon:
- Indentation fixes

UAPI:
- Add a new KFD header that defines some of the sysfs bitfields and enums that userspace has been using for a while
  The corresponding bit-fields and enums in user mode are defined in
  https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/blob/master/include/hsakmttypes.h

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

# Conflicts:
#	drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211202191643.5970-1-alexander.deucher@amd.com

1 files changed, 35 insertions, 9 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 08133de21fdd..46910e7b2927 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -892,6 +892,38 @@ void amdgpu_ras_mca_query_error_status(struct amdgpu_device *adev,
 	}
 }
 
+static void amdgpu_ras_get_ecc_info(struct amdgpu_device *adev, struct ras_err_data *err_data)
+{
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+	int ret = 0;
+
+	/*
+	 * choosing right query method according to
+	 * whether smu support query error information
+	 */
+	ret = smu_get_ecc_info(&adev->smu, (void *)&(ras->umc_ecc));
+	if (ret == -EOPNOTSUPP) {
+		if (adev->umc.ras_funcs &&
+			adev->umc.ras_funcs->query_ras_error_count)
+			adev->umc.ras_funcs->query_ras_error_count(adev, err_data);
+
+		/* umc query_ras_error_address is also responsible for clearing
+		 * error status
+		 */
+		if (adev->umc.ras_funcs &&
+		    adev->umc.ras_funcs->query_ras_error_address)
+			adev->umc.ras_funcs->query_ras_error_address(adev, err_data);
+	} else if (!ret) {
+		if (adev->umc.ras_funcs &&
+			adev->umc.ras_funcs->ecc_info_query_ras_error_count)
+			adev->umc.ras_funcs->ecc_info_query_ras_error_count(adev, err_data);
+
+		if (adev->umc.ras_funcs &&
+			adev->umc.ras_funcs->ecc_info_query_ras_error_address)
+			adev->umc.ras_funcs->ecc_info_query_ras_error_address(adev, err_data);
+	}
+}
+
 /* query/inject/cure begin */
 int amdgpu_ras_query_error_status(struct amdgpu_device *adev,
 				  struct ras_query_if *info)
@@ -905,15 +937,7 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev,
 
 	switch (info->head.block) {
 	case AMDGPU_RAS_BLOCK__UMC:
-		if (adev->umc.ras_funcs &&
-		    adev->umc.ras_funcs->query_ras_error_count)
-			adev->umc.ras_funcs->query_ras_error_count(adev, &err_data);
-		/* umc query_ras_error_address is also responsible for clearing
-		 * error status
-		 */
-		if (adev->umc.ras_funcs &&
-		    adev->umc.ras_funcs->query_ras_error_address)
-			adev->umc.ras_funcs->query_ras_error_address(adev, &err_data);
+		amdgpu_ras_get_ecc_info(adev, &err_data);
 		break;
 	case AMDGPU_RAS_BLOCK__SDMA:
 		if (adev->sdma.funcs->query_ras_error_count) {
@@ -1935,9 +1959,11 @@ int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev)
 	if (!con || !con->eh_data)
 		return 0;
 
+	mutex_lock(&con->recovery_lock);
 	control = &con->eeprom_control;
 	data = con->eh_data;
 	save_count = data->count - control->ras_num_recs;
+	mutex_unlock(&con->recovery_lock);
 	/* only new entries are saved */
 	if (save_count > 0) {
 		if (amdgpu_ras_eeprom_append(control,