Merge tag 'amd-drm-next-6.9-2024-02-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.9-2024-02-09:

amdgpu:
- Validate DMABuf imports in compute VMs
- Add RAS ACA framework
- PSP 13 fixes
- Misc code cleanups
- Replay fixes
- Atom interpretor PS, WS bounds checking
- DML2 fixes
- Audio fixes
- DCN 3.5 Z state fixes
- Remove deprecated ida_simple usage
- UBSAN fixes
- RAS fixes
- Enable seq64 infrastructure
- DC color block enablement
- Documentation updates
- DC documentation updates
- DMCUB updates
- S3 fixes
- VCN 4.0.5 fixes
- DP MST fixes
- SR-IOV fixes

amdkfd:
- Validate DMABuf imports in compute VMs
- SVM fixes
- Trap handler updates

radeon:
- Atom interpretor PS, WS bounds checking
- Misc code cleanups

UAPI:
- Bump KFD version so UMDs know that the fixes that enable the management of
  VA mappings in compute VMs using the GEM_VA ioctl for DMABufs exported from KFD are present
- Add INFO query for input power.  This matches the existing INFO query for average
  power.  Used in gaming HUDs, etc.
  Example userspace: https://github.com/Umio-Yasuno/libdrm-amdgpu-sys-rs/tree/input_power

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240209221459.5453-1-alexander.deucher@amd.com

1 files changed, 8 insertions, 2 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
index 417a6726c71b..26d2ae498daf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
@@ -21,7 +21,7 @@
 #ifndef __AMDGPU_UMC_H__
 #define __AMDGPU_UMC_H__
 #include "amdgpu_ras.h"
-
+#include "amdgpu_mca.h"
 /*
  * (addr / 256) * 4096, the higher 26 bits in ErrorAddr
  * is the index of 4KB block
@@ -64,6 +64,8 @@ struct amdgpu_umc_ras {
 				      void *ras_error_status);
 	void (*ecc_info_query_ras_error_address)(struct amdgpu_device *adev,
 					void *ras_error_status);
+	bool (*check_ecc_err_status)(struct amdgpu_device *adev,
+			enum amdgpu_mca_error_type type, void *ras_error_status);
 	/* support different eeprom table version for different asic */
 	void (*set_eeprom_table_version)(struct amdgpu_ras_eeprom_table_header *hdr);
 };
@@ -100,7 +102,8 @@ struct amdgpu_umc {
 
 int amdgpu_umc_ras_sw_init(struct amdgpu_device *adev);
 int amdgpu_umc_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block);
-int amdgpu_umc_poison_handler(struct amdgpu_device *adev, bool reset);
+int amdgpu_umc_poison_handler(struct amdgpu_device *adev,
+			enum amdgpu_ras_block block, bool reset);
 int amdgpu_umc_process_ecc_irq(struct amdgpu_device *adev,
 		struct amdgpu_irq_src *source,
 		struct amdgpu_iv_entry *entry);
@@ -118,4 +121,7 @@ int amdgpu_umc_page_retirement_mca(struct amdgpu_device *adev,
 
 int amdgpu_umc_loop_channels(struct amdgpu_device *adev,
 			umc_func func, void *data);
+
+int amdgpu_umc_bad_page_polling_timeout(struct amdgpu_device *adev,
+			bool reset, uint32_t timeout_ms);
 #endif