Merge tag 'amd-drm-next-6.15-2025-02-21' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.15-2025-02-21:

amdgpu:
- Add OEM i2c support for RGB lights, etc.
- Add support for GC 11.5.3
- Add support for GC 11.5.2
- Add support for SDMA 6.1.3
- Add support for NBIO 7.11.2
- Add support for NBIO 7.9.1
- Add support for MMHUB 3.3.2
- Add support for MMHUB 1.8.1
- Add support for SMU 14.0.5
- Add support for SMUIO 13.0.11
- Add support for PSP 14.0.5
- Add support for UMC 12.5.0
- Add support for DCN 3.6.0
- JPEG 4.0.3 updates
- Add dynamic workload profile switching for GC 10-12
- support larger vbios sizes
- GC 9.5.0 updates
- SMU 13.0.12 updates
- SMU 13.0.6 updates
- IP discovery updates
- GC 10 queue reset updates
- DCN 4.0.1 updates
- UHBR link rate fixes
- Aborted suspend fix
- Mark gttsize parameter as deprecated
- GC 10 cleaner shader updates
- PSR-SU fixes
- Clean up PM4 headers
- Cursor fixes
- Enable devcoredump for JPEG
- Misc cleanups
- Runpm cleanups
- MES updates
- GC 9 gfxoff fixes
- Vbios fetching cleanups
- Documentation updates
- Update secondary plane handling
- DML2 updates
- SDMA fixes for MI
- Cleaner shader fixes for GC 11/12
- ACA updates
- Initial JPEG queue reset support
- RAS updates
- Initial RAS CPER support
- DCN/DCE panic screen handling cleanup
- BT2020 fixes
- SR-IOV fixes

amdkfd:
- synchronize pasid values between KGD and KFD
- Misc cleanups
- Improve GTT/VRAM handling for APUs
- Topology updates
- Fix user queue validation on GC 7/8

UAPI:
- Enable "Broadcast RGB" drm property
- Add INFO IOCTL query for virtualization mode
  Proposed userspace:
  https://github.com/ROCm/amdsmi/commit/e663bed7d6b3df79f5959e73981749b1f22ec698

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250221213651.4176031-1-alexander.deucher@amd.com
Signed-off-by: Dave Airlie <airlied@redhat.com>

1 files changed, 26 insertions, 22 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index f0924aa3f4e4..3c3312bbfee8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1864,6 +1864,9 @@ int amdgpu_ras_sysfs_create(struct amdgpu_device *adev,
 	if (!obj || obj->attr_inuse)
 		return -EINVAL;
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_virt_ras_telemetry_block_en(adev, head->block))
+		return 0;
+
 	get_obj(obj);
 
 	snprintf(obj->fs_data.sysfs_name, sizeof(obj->fs_data.sysfs_name),
@@ -3080,31 +3083,29 @@ static void amdgpu_ras_validate_threshold(struct amdgpu_device *adev,
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 
 	/*
-	 * Justification of value bad_page_cnt_threshold in ras structure
-	 *
-	 * Generally, 0 <= amdgpu_bad_page_threshold <= max record length
-	 * in eeprom or amdgpu_bad_page_threshold == -2, introduce two
-	 * scenarios accordingly.
-	 *
-	 * Bad page retirement enablement:
-	 *    - If amdgpu_bad_page_threshold = -2,
-	 *      bad_page_cnt_threshold = typical value by formula.
-	 *
-	 *    - When the value from user is 0 < amdgpu_bad_page_threshold <
-	 *      max record length in eeprom, use it directly.
-	 *
-	 * Bad page retirement disablement:
-	 *    - If amdgpu_bad_page_threshold = 0, bad page retirement
-	 *      functionality is disabled, and bad_page_cnt_threshold will
-	 *      take no effect.
+	 * amdgpu_bad_page_threshold is used to config
+	 * the threshold for the number of bad pages.
+	 * -1:  Threshold is set to default value
+	 *      Driver will issue a warning message when threshold is reached
+	 *      and continue runtime services.
+	 * 0:   Disable bad page retirement
+	 *      Driver will not retire bad pages
+	 *      which is intended for debugging purpose.
+	 * -2:  Threshold is determined by a formula
+	 *      that assumes 1 bad page per 100M of local memory.
+	 *      Driver will continue runtime services when threhold is reached.
+	 * 0 < threshold < max number of bad page records in EEPROM,
+	 *      A user-defined threshold is set
+	 *      Driver will halt runtime services when this custom threshold is reached.
 	 */
-
-	if (amdgpu_bad_page_threshold < 0) {
+	if (amdgpu_bad_page_threshold == -2) {
 		u64 val = adev->gmc.mc_vram_size;
 
 		do_div(val, RAS_BAD_PAGE_COVER);
 		con->bad_page_cnt_threshold = min(lower_32_bits(val),
 						  max_count);
+	} else if (amdgpu_bad_page_threshold == -1) {
+		con->bad_page_cnt_threshold = ((con->reserved_pages_in_bytes) >> 21) << 4;
 	} else {
 		con->bad_page_cnt_threshold = min_t(int, max_count,
 						    amdgpu_bad_page_threshold);
@@ -3759,8 +3760,9 @@ init_ras_enabled_flag:
 	adev->ras_enabled = amdgpu_ras_enable == 0 ? 0 :
 		adev->ras_hw_enabled & amdgpu_ras_mask;
 
-	/* aca is disabled by default */
-	adev->aca.is_enabled = false;
+	/* aca is disabled by default except for psp v13_0_12 */
+	adev->aca.is_enabled =
+		(amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 12));
 
 	/* bad page feature is not applicable to specific app platform */
 	if (adev->gmc.is_app_apu &&
@@ -3848,8 +3850,10 @@ static void amdgpu_ras_init_reserved_vram_size(struct amdgpu_device *adev)
 	case IP_VERSION(13, 0, 2):
 	case IP_VERSION(13, 0, 6):
 	case IP_VERSION(13, 0, 12):
+		con->reserved_pages_in_bytes = AMDGPU_RAS_RESERVED_VRAM_SIZE_DEFAULT;
+		break;
 	case IP_VERSION(13, 0, 14):
-		con->reserved_pages_in_bytes = AMDGPU_RAS_RESERVED_VRAM_SIZE;
+		con->reserved_pages_in_bytes = (AMDGPU_RAS_RESERVED_VRAM_SIZE_DEFAULT << 1);
 		break;
 	default:
 		break;