Merge tag 'amd-drm-next-6.7-2023-10-13' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.7-2023-10-13:

amdgpu:
- DC replay fixes
- Misc code cleanups and spelling fixes
- Documentation updates
- RAS EEPROM Updates
- FRU EEPROM Updates
- IP discovery updates
- SR-IOV fixes
- RAS updates
- DC PQ fixes
- SMU 13.0.6 updates
- GC 11.5 Support
- NBIO 7.11 Support
- GMC 11 Updates
- Reset fixes
- SMU 11.5 Updates
- SMU 13.0 OD support
- Use flexible arrays for bo list handling
- W=1 Fixes
- SubVP fixes
- DPIA fixes
- DCN 3.5 Support
- Devcoredump fixes
- VPE 6.1 support
- VCN 4.0 Updates
- S/G display fixes
- DML fixes
- DML2 Support
- MST fixes
- VRR fixes
- Enable seamless boot in more cases
- Enable content type property for HDMI
- OLED fixes
- Rework and clean up GPUVM TLB flushing
- DC ODM fixes
- DP 2.x fixes
- AGP aperture fixes
- SDMA firmware loading cleanups
- Cyan Skillfish GPU clock counter fix
- GC 11 GART fix
- Cache GPU fault info for userspace queries
- DC cursor check fixes
- eDP fixes
- DC FP handling fixes
- Variable sized array fixes
- SMU 13.0.x fixes
- IB start and size alignment fixes for VCN
- SMU 14 Support
- Suspend and resume sequence rework
- vkms fix

amdkfd:
- GC 11 fixes
- GC 10 fixes
- Doorbell fixes
- CWSR fixes
- SVM fixes
- Clean up GC info enumeration
- Rework memory limit handling
- Coherent memory handling fixes
- Use partial migrations in GPU faults
- TLB flush fixes
- DMA unmap fixes
- GC 9.4.3 fixes
- SQ interrupt fix
- GTT mapping fix
- GC 11.5 Support

radeon:
- Misc code cleanups
- W=1 Fixes
- Fix possible buffer overflow
- Fix possible NULL pointer dereference

UAPI:
- Add EXT_COHERENT memory allocation flags.  These allow for system scope atomics.
  Proposed userspace: https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/pull/88
- Add support for new VPE engine.  This is a memory to memory copy engine with advanced scaling, CSC, and color management features
  Proposed mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25713
- Add INFO IOCTL interface to query GPU faults
  Proposed Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23238
  Proposed libdrm MR: https://gitlab.freedesktop.org/mesa/drm/-/merge_requests/298

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

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231013175758.1735031-1-alexander.deucher@amd.com

1 files changed, 33 insertions, 2 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index ffb49b2d533a..0a5c8a107fb2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -28,6 +28,7 @@
 #include <linux/list.h>
 #include "ta_ras_if.h"
 #include "amdgpu_ras_eeprom.h"
+#include "amdgpu_smuio.h"
 
 struct amdgpu_iv_entry;
 
@@ -389,9 +390,12 @@ struct amdgpu_ras {
 	/* ras infrastructure */
 	/* for ras itself. */
 	uint32_t features;
+	uint32_t schema;
 	struct list_head head;
 	/* sysfs */
 	struct device_attribute features_attr;
+	struct device_attribute version_attr;
+	struct device_attribute schema_attr;
 	struct bin_attribute badpages_attr;
 	struct dentry *de_ras_eeprom_table;
 	/* block array */
@@ -436,17 +440,33 @@ struct amdgpu_ras {
 };
 
 struct ras_fs_data {
-	char sysfs_name[32];
+	char sysfs_name[48];
 	char debugfs_name[32];
 };
 
+struct ras_err_info {
+	struct amdgpu_smuio_mcm_config_info mcm_info;
+	u64 ce_count;
+	u64 ue_count;
+};
+
+struct ras_err_node {
+	struct list_head node;
+	struct ras_err_info err_info;
+};
+
 struct ras_err_data {
 	unsigned long ue_count;
 	unsigned long ce_count;
 	unsigned long err_addr_cnt;
 	struct eeprom_table_record *err_addr;
+	u32 err_list_count;
+	struct list_head err_node_list;
 };
 
+#define for_each_ras_error(err_node, err_data) \
+	list_for_each_entry(err_node, &(err_data)->err_node_list, node)
+
 struct ras_err_handler_data {
 	/* point to bad page records array */
 	struct eeprom_table_record *bps;
@@ -493,7 +513,10 @@ struct ras_manager {
 	/* IH data */
 	struct ras_ih_data ih_data;
 
-	struct ras_err_data err_data;
+	struct {
+		unsigned long ue_count;
+		unsigned long ce_count;
+	} err_data;
 };
 
 struct ras_badpage {
@@ -767,4 +790,12 @@ void amdgpu_ras_inst_reset_ras_error_count(struct amdgpu_device *adev,
 					   const struct amdgpu_ras_err_status_reg_entry *reg_list,
 					   uint32_t reg_list_size,
 					   uint32_t instance);
+
+int amdgpu_ras_error_data_init(struct ras_err_data *err_data);
+void amdgpu_ras_error_data_fini(struct ras_err_data *err_data);
+int amdgpu_ras_error_statistic_ce_count(struct ras_err_data *err_data,
+					struct amdgpu_smuio_mcm_config_info *mcm_info, u64 count);
+int amdgpu_ras_error_statistic_ue_count(struct ras_err_data *err_data,
+					struct amdgpu_smuio_mcm_config_info *mcm_info, u64 count);
+
 #endif