diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-11-11 01:59:30 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-11-11 01:59:30 +0300 |
commit | c0d12d769299e1e08338988c7745009e0db2a4a0 (patch) | |
tree | 196e23330996b4094cd2f1b1c4aaaef09db1f44a /drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h | |
parent | ac347a0655dbc7d885e217c89dddd16e2800bd58 (diff) | |
parent | 03df0fc007ca4713fa1e716329af556f981807e4 (diff) | |
download | linux-c0d12d769299e1e08338988c7745009e0db2a4a0.tar.xz |
Merge tag 'drm-next-2023-11-10' of git://anongit.freedesktop.org/drm/drm
Pull drm fixes from Daniel Vetter:
"Dave's VPN to the big machine died, so it's on me to do fixes pr this
and next week while everyone else is at plumbers.
- big pile of amd fixes, but mostly for hw support newly added in 6.7
- i915 fixes, mostly minor things
- qxl memory leak fix
- vc4 uaf fix in mock helpers
- syncobj fix for DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE"
* tag 'drm-next-2023-11-10' of git://anongit.freedesktop.org/drm/drm: (78 commits)
drm/amdgpu: fix error handling in amdgpu_vm_init
drm/amdgpu: Fix possible null pointer dereference
drm/amdgpu: move UVD and VCE sched entity init after sched init
drm/amdgpu: move kfd_resume before the ip late init
drm/amd: Explicitly check for GFXOFF to be enabled for s0ix
drm/amdgpu: Change WREG32_RLC to WREG32_SOC15_RLC where inst != 0 (v2)
drm/amdgpu: Use correct KIQ MEC engine for gfx9.4.3 (v5)
drm/amdgpu: add smu v13.0.6 pcs xgmi ras error query support
drm/amdgpu: fix software pci_unplug on some chips
drm/amd/display: remove duplicated argument
drm/amdgpu: correct mca debugfs dump reg list
drm/amdgpu: correct acclerator check architecutre dump
drm/amdgpu: add pcs xgmi v6.4.0 ras support
drm/amdgpu: Change extended-scope MTYPE on GC 9.4.3
drm/amdgpu: disable smu v13.0.6 mca debug mode by default
drm/amdgpu: Support multiple error query modes
drm/amdgpu: refine smu v13.0.6 mca dump driver
drm/amdgpu: Do not program PF-only regs in hdp_v4_0.c under SRIOV (v2)
drm/amdgpu: Skip PCTL0_MMHUB_DEEPSLEEP_IB write in jpegv4.0.3 under SRIOV
drm: amd: Resolve Sphinx unexpected indentation warning
...
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h')
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h | 60 |
1 files changed, 56 insertions, 4 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h index 28ad463cf5c9..2b488fcf2f95 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h @@ -25,6 +25,27 @@ #define MCA_MAX_REGS_COUNT (16) +#define MCA_REG_FIELD(x, h, l) (((x) & GENMASK_ULL(h, l)) >> l) +#define MCA_REG__STATUS__VAL(x) MCA_REG_FIELD(x, 63, 63) +#define MCA_REG__STATUS__OVERFLOW(x) MCA_REG_FIELD(x, 62, 62) +#define MCA_REG__STATUS__UC(x) MCA_REG_FIELD(x, 61, 61) +#define MCA_REG__STATUS__EN(x) MCA_REG_FIELD(x, 60, 60) +#define MCA_REG__STATUS__MISCV(x) MCA_REG_FIELD(x, 59, 59) +#define MCA_REG__STATUS__ADDRV(x) MCA_REG_FIELD(x, 58, 58) +#define MCA_REG__STATUS__PCC(x) MCA_REG_FIELD(x, 57, 57) +#define MCA_REG__STATUS__ERRCOREIDVAL(x) MCA_REG_FIELD(x, 56, 56) +#define MCA_REG__STATUS__TCC(x) MCA_REG_FIELD(x, 55, 55) +#define MCA_REG__STATUS__SYNDV(x) MCA_REG_FIELD(x, 53, 53) +#define MCA_REG__STATUS__CECC(x) MCA_REG_FIELD(x, 46, 46) +#define MCA_REG__STATUS__UECC(x) MCA_REG_FIELD(x, 45, 45) +#define MCA_REG__STATUS__DEFERRED(x) MCA_REG_FIELD(x, 44, 44) +#define MCA_REG__STATUS__POISON(x) MCA_REG_FIELD(x, 43, 43) +#define MCA_REG__STATUS__SCRUB(x) MCA_REG_FIELD(x, 40, 40) +#define MCA_REG__STATUS__ERRCOREID(x) MCA_REG_FIELD(x, 37, 32) +#define MCA_REG__STATUS__ADDRLSB(x) MCA_REG_FIELD(x, 29, 24) +#define MCA_REG__STATUS__ERRORCODEEXT(x) MCA_REG_FIELD(x, 21, 16) +#define MCA_REG__STATUS__ERRORCODE(x) MCA_REG_FIELD(x, 15, 0) + enum amdgpu_mca_ip { AMDGPU_MCA_IP_UNKNOW = -1, AMDGPU_MCA_IP_PSP = 0, @@ -33,6 +54,7 @@ enum amdgpu_mca_ip { AMDGPU_MCA_IP_SMU, AMDGPU_MCA_IP_MP5, AMDGPU_MCA_IP_UMC, + AMDGPU_MCA_IP_PCS_XGMI, AMDGPU_MCA_IP_COUNT, }; @@ -57,6 +79,15 @@ struct amdgpu_mca { const struct amdgpu_mca_smu_funcs *mca_funcs; }; +enum mca_reg_idx { + MCA_REG_IDX_STATUS = 1, + MCA_REG_IDX_ADDR = 2, + MCA_REG_IDX_MISC0 = 3, + MCA_REG_IDX_IPID = 5, + MCA_REG_IDX_SYND = 6, + MCA_REG_IDX_COUNT = 16, +}; + struct mca_bank_info { int socket_id; int aid; @@ -72,18 +103,28 @@ struct mca_bank_entry { uint64_t regs[MCA_MAX_REGS_COUNT]; }; +struct mca_bank_node { + struct mca_bank_entry entry; + struct list_head node; +}; + +struct mca_bank_set { + int nr_entries; + struct list_head list; +}; + struct amdgpu_mca_smu_funcs { int max_ue_count; int max_ce_count; int (*mca_set_debug_mode)(struct amdgpu_device *adev, bool enable); - int (*mca_get_error_count)(struct amdgpu_device *adev, enum amdgpu_ras_block blk, - enum amdgpu_mca_error_type type, uint32_t *count); + int (*mca_get_ras_mca_set)(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type, + struct mca_bank_set *mca_set); + int (*mca_parse_mca_error_count)(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type, + struct mca_bank_entry *entry, uint32_t *count); int (*mca_get_valid_mca_count)(struct amdgpu_device *adev, enum amdgpu_mca_error_type type, uint32_t *count); int (*mca_get_mca_entry)(struct amdgpu_device *adev, enum amdgpu_mca_error_type type, int idx, struct mca_bank_entry *entry); - int (*mca_get_ras_mca_idx_array)(struct amdgpu_device *adev, enum amdgpu_ras_block blk, - enum amdgpu_mca_error_type type, int *idx_array, int *idx_array_size); }; void amdgpu_mca_query_correctable_error_count(struct amdgpu_device *adev, @@ -107,11 +148,22 @@ int amdgpu_mca_mpio_ras_sw_init(struct amdgpu_device *adev); void amdgpu_mca_smu_init_funcs(struct amdgpu_device *adev, const struct amdgpu_mca_smu_funcs *mca_funcs); int amdgpu_mca_smu_set_debug_mode(struct amdgpu_device *adev, bool enable); int amdgpu_mca_smu_get_valid_mca_count(struct amdgpu_device *adev, enum amdgpu_mca_error_type type, uint32_t *count); +int amdgpu_mca_smu_get_mca_set_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block blk, + enum amdgpu_mca_error_type type, uint32_t *total); int amdgpu_mca_smu_get_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type, uint32_t *count); +int amdgpu_mca_smu_parse_mca_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block blk, + enum amdgpu_mca_error_type type, struct mca_bank_entry *entry, uint32_t *count); +int amdgpu_mca_smu_get_mca_set(struct amdgpu_device *adev, enum amdgpu_ras_block blk, + enum amdgpu_mca_error_type type, struct mca_bank_set *mca_set); int amdgpu_mca_smu_get_mca_entry(struct amdgpu_device *adev, enum amdgpu_mca_error_type type, int idx, struct mca_bank_entry *entry); void amdgpu_mca_smu_debugfs_init(struct amdgpu_device *adev, struct dentry *root); +void amdgpu_mca_bank_set_init(struct mca_bank_set *mca_set); +int amdgpu_mca_bank_set_add_entry(struct mca_bank_set *mca_set, struct mca_bank_entry *entry); +void amdgpu_mca_bank_set_release(struct mca_bank_set *mca_set); +int amdgpu_mca_smu_log_ras_error(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type, struct ras_err_data *err_data); + #endif |