diff options
Diffstat (limited to 'drivers/gpu/drm/msm/adreno')
26 files changed, 2862 insertions, 250 deletions
diff --git a/drivers/gpu/drm/msm/adreno/a2xx.xml.h b/drivers/gpu/drm/msm/adreno/a2xx.xml.h index 12b0ba270b5e..14eb52f3e605 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx.xml.h +++ b/drivers/gpu/drm/msm/adreno/a2xx.xml.h @@ -10,13 +10,13 @@ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: - /home/robclark/src/envytools/rnndb/adreno.xml ( 501 bytes, from 2018-07-03 19:37:13) - /home/robclark/src/envytools/rnndb/freedreno_copyright.xml ( 1572 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml ( 36805 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml ( 13634 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml ( 42585 bytes, from 2018-10-04 19:06:37) +- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml ( 42463 bytes, from 2018-11-19 13:44:03) +- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml ( 14201 bytes, from 2018-12-02 17:29:54) +- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml ( 43052 bytes, from 2018-12-02 17:29:54) - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml ( 83840 bytes, from 2018-07-03 19:37:13) - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml ( 112086 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml ( 147240 bytes, from 2018-10-04 19:06:37) -- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml ( 139581 bytes, from 2018-10-04 19:06:42) +- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml ( 147240 bytes, from 2018-12-02 17:29:54) +- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml ( 140790 bytes, from 2018-12-02 17:29:54) - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml ( 10431 bytes, from 2018-09-14 13:03:07) - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml ( 1773 bytes, from 2018-07-03 19:37:13) @@ -239,7 +239,63 @@ enum sq_tex_swiz { enum sq_tex_filter { SQ_TEX_FILTER_POINT = 0, SQ_TEX_FILTER_BILINEAR = 1, - SQ_TEX_FILTER_BICUBIC = 2, + SQ_TEX_FILTER_BASEMAP = 2, + SQ_TEX_FILTER_USE_FETCH_CONST = 3, +}; + +enum sq_tex_aniso_filter { + SQ_TEX_ANISO_FILTER_DISABLED = 0, + SQ_TEX_ANISO_FILTER_MAX_1_1 = 1, + SQ_TEX_ANISO_FILTER_MAX_2_1 = 2, + SQ_TEX_ANISO_FILTER_MAX_4_1 = 3, + SQ_TEX_ANISO_FILTER_MAX_8_1 = 4, + SQ_TEX_ANISO_FILTER_MAX_16_1 = 5, + SQ_TEX_ANISO_FILTER_USE_FETCH_CONST = 7, +}; + +enum sq_tex_dimension { + SQ_TEX_DIMENSION_1D = 0, + SQ_TEX_DIMENSION_2D = 1, + SQ_TEX_DIMENSION_3D = 2, + SQ_TEX_DIMENSION_CUBE = 3, +}; + +enum sq_tex_border_color { + SQ_TEX_BORDER_COLOR_BLACK = 0, + SQ_TEX_BORDER_COLOR_WHITE = 1, + SQ_TEX_BORDER_COLOR_ACBYCR_BLACK = 2, + SQ_TEX_BORDER_COLOR_ACBCRY_BLACK = 3, +}; + +enum sq_tex_sign { + SQ_TEX_SIGN_UNISIGNED = 0, + SQ_TEX_SIGN_SIGNED = 1, + SQ_TEX_SIGN_UNISIGNED_BIASED = 2, + SQ_TEX_SIGN_GAMMA = 3, +}; + +enum sq_tex_endian { + SQ_TEX_ENDIAN_NONE = 0, + SQ_TEX_ENDIAN_8IN16 = 1, + SQ_TEX_ENDIAN_8IN32 = 2, + SQ_TEX_ENDIAN_16IN32 = 3, +}; + +enum sq_tex_clamp_policy { + SQ_TEX_CLAMP_POLICY_D3D = 0, + SQ_TEX_CLAMP_POLICY_OGL = 1, +}; + +enum sq_tex_num_format { + SQ_TEX_NUM_FORMAT_FRAC = 0, + SQ_TEX_NUM_FORMAT_INT = 1, +}; + +enum sq_tex_type { + SQ_TEX_TYPE_0 = 0, + SQ_TEX_TYPE_1 = 1, + SQ_TEX_TYPE_2 = 2, + SQ_TEX_TYPE_3 = 3, }; #define REG_A2XX_RBBM_PATCH_RELEASE 0x00000001 @@ -323,6 +379,18 @@ static inline uint32_t A2XX_MH_MMU_CONFIG_PA_W_CLNT_BEHAVIOR(enum adreno_mmu_cln } #define REG_A2XX_MH_MMU_VA_RANGE 0x00000041 +#define A2XX_MH_MMU_VA_RANGE_NUM_64KB_REGIONS__MASK 0x00000fff +#define A2XX_MH_MMU_VA_RANGE_NUM_64KB_REGIONS__SHIFT 0 +static inline uint32_t A2XX_MH_MMU_VA_RANGE_NUM_64KB_REGIONS(uint32_t val) +{ + return ((val) << A2XX_MH_MMU_VA_RANGE_NUM_64KB_REGIONS__SHIFT) & A2XX_MH_MMU_VA_RANGE_NUM_64KB_REGIONS__MASK; +} +#define A2XX_MH_MMU_VA_RANGE_VA_BASE__MASK 0xfffff000 +#define A2XX_MH_MMU_VA_RANGE_VA_BASE__SHIFT 12 +static inline uint32_t A2XX_MH_MMU_VA_RANGE_VA_BASE(uint32_t val) +{ + return ((val) << A2XX_MH_MMU_VA_RANGE_VA_BASE__SHIFT) & A2XX_MH_MMU_VA_RANGE_VA_BASE__MASK; +} #define REG_A2XX_MH_MMU_PT_BASE 0x00000042 @@ -331,6 +399,8 @@ static inline uint32_t A2XX_MH_MMU_CONFIG_PA_W_CLNT_BEHAVIOR(enum adreno_mmu_cln #define REG_A2XX_MH_MMU_TRAN_ERROR 0x00000044 #define REG_A2XX_MH_MMU_INVALIDATE 0x00000045 +#define A2XX_MH_MMU_INVALIDATE_INVALIDATE_ALL 0x00000001 +#define A2XX_MH_MMU_INVALIDATE_INVALIDATE_TC 0x00000002 #define REG_A2XX_MH_MMU_MPU_BASE 0x00000046 @@ -389,12 +459,19 @@ static inline uint32_t A2XX_MH_MMU_CONFIG_PA_W_CLNT_BEHAVIOR(enum adreno_mmu_cln #define REG_A2XX_RBBM_READ_ERROR 0x000003b3 #define REG_A2XX_RBBM_INT_CNTL 0x000003b4 +#define A2XX_RBBM_INT_CNTL_RDERR_INT_MASK 0x00000001 +#define A2XX_RBBM_INT_CNTL_DISPLAY_UPDATE_INT_MASK 0x00000002 +#define A2XX_RBBM_INT_CNTL_GUI_IDLE_INT_MASK 0x00080000 #define REG_A2XX_RBBM_INT_STATUS 0x000003b5 #define REG_A2XX_RBBM_INT_ACK 0x000003b6 #define REG_A2XX_MASTER_INT_SIGNAL 0x000003b7 +#define A2XX_MASTER_INT_SIGNAL_MH_INT_STAT 0x00000020 +#define A2XX_MASTER_INT_SIGNAL_SQ_INT_STAT 0x04000000 +#define A2XX_MASTER_INT_SIGNAL_CP_INT_STAT 0x40000000 +#define A2XX_MASTER_INT_SIGNAL_RBBM_INT_STAT 0x80000000 #define REG_A2XX_RBBM_PERIPHID1 0x000003f9 @@ -467,6 +544,19 @@ static inline uint32_t A2XX_MH_ARBITER_CONFIG_IN_FLIGHT_LIMIT(uint32_t val) #define A2XX_MH_ARBITER_CONFIG_RB_CLNT_ENABLE 0x02000000 #define A2XX_MH_ARBITER_CONFIG_PA_CLNT_ENABLE 0x04000000 +#define REG_A2XX_MH_INTERRUPT_MASK 0x00000a42 +#define A2XX_MH_INTERRUPT_MASK_AXI_READ_ERROR 0x00000001 +#define A2XX_MH_INTERRUPT_MASK_AXI_WRITE_ERROR 0x00000002 +#define A2XX_MH_INTERRUPT_MASK_MMU_PAGE_FAULT 0x00000004 + +#define REG_A2XX_MH_INTERRUPT_STATUS 0x00000a43 + +#define REG_A2XX_MH_INTERRUPT_CLEAR 0x00000a44 + +#define REG_A2XX_MH_CLNT_INTF_CTRL_CONFIG1 0x00000a54 + +#define REG_A2XX_MH_CLNT_INTF_CTRL_CONFIG2 0x00000a55 + #define REG_A2XX_A220_VSC_BIN_SIZE 0x00000c01 #define A2XX_A220_VSC_BIN_SIZE_WIDTH__MASK 0x0000001f #define A2XX_A220_VSC_BIN_SIZE_WIDTH__SHIFT 0 @@ -648,6 +738,18 @@ static inline uint32_t A2XX_RB_BC_CONTROL_MEM_EXPORT_TIMEOUT_SELECT(uint32_t val #define REG_A2XX_RB_DEBUG_DATA 0x00000f27 #define REG_A2XX_RB_SURFACE_INFO 0x00002000 +#define A2XX_RB_SURFACE_INFO_SURFACE_PITCH__MASK 0x00003fff +#define A2XX_RB_SURFACE_INFO_SURFACE_PITCH__SHIFT 0 +static inline uint32_t A2XX_RB_SURFACE_INFO_SURFACE_PITCH(uint32_t val) +{ + return ((val) << A2XX_RB_SURFACE_INFO_SURFACE_PITCH__SHIFT) & A2XX_RB_SURFACE_INFO_SURFACE_PITCH__MASK; +} +#define A2XX_RB_SURFACE_INFO_MSAA_SAMPLES__MASK 0x0000c000 +#define A2XX_RB_SURFACE_INFO_MSAA_SAMPLES__SHIFT 14 +static inline uint32_t A2XX_RB_SURFACE_INFO_MSAA_SAMPLES(uint32_t val) +{ + return ((val) << A2XX_RB_SURFACE_INFO_MSAA_SAMPLES__SHIFT) & A2XX_RB_SURFACE_INFO_MSAA_SAMPLES__MASK; +} #define REG_A2XX_RB_COLOR_INFO 0x00002001 #define A2XX_RB_COLOR_INFO_FORMAT__MASK 0x0000000f @@ -679,7 +781,7 @@ static inline uint32_t A2XX_RB_COLOR_INFO_SWAP(uint32_t val) #define A2XX_RB_COLOR_INFO_BASE__SHIFT 12 static inline uint32_t A2XX_RB_COLOR_INFO_BASE(uint32_t val) { - return ((val >> 10) << A2XX_RB_COLOR_INFO_BASE__SHIFT) & A2XX_RB_COLOR_INFO_BASE__MASK; + return ((val >> 12) << A2XX_RB_COLOR_INFO_BASE__SHIFT) & A2XX_RB_COLOR_INFO_BASE__MASK; } #define REG_A2XX_RB_DEPTH_INFO 0x00002002 @@ -693,7 +795,7 @@ static inline uint32_t A2XX_RB_DEPTH_INFO_DEPTH_FORMAT(enum adreno_rb_depth_form #define A2XX_RB_DEPTH_INFO_DEPTH_BASE__SHIFT 12 static inline uint32_t A2XX_RB_DEPTH_INFO_DEPTH_BASE(uint32_t val) { - return ((val >> 10) << A2XX_RB_DEPTH_INFO_DEPTH_BASE__SHIFT) & A2XX_RB_DEPTH_INFO_DEPTH_BASE__MASK; + return ((val >> 12) << A2XX_RB_DEPTH_INFO_DEPTH_BASE__SHIFT) & A2XX_RB_DEPTH_INFO_DEPTH_BASE__MASK; } #define REG_A2XX_A225_RB_COLOR_INFO3 0x00002005 @@ -1757,6 +1859,36 @@ static inline uint32_t A2XX_RB_COPY_DEST_OFFSET_Y(uint32_t val) #define REG_A2XX_COHER_STATUS_PM4 0x00000a2b #define REG_A2XX_SQ_TEX_0 0x00000000 +#define A2XX_SQ_TEX_0_TYPE__MASK 0x00000003 +#define A2XX_SQ_TEX_0_TYPE__SHIFT 0 +static inline uint32_t A2XX_SQ_TEX_0_TYPE(enum sq_tex_type val) +{ + return ((val) << A2XX_SQ_TEX_0_TYPE__SHIFT) & A2XX_SQ_TEX_0_TYPE__MASK; +} +#define A2XX_SQ_TEX_0_SIGN_X__MASK 0x0000000c +#define A2XX_SQ_TEX_0_SIGN_X__SHIFT 2 +static inline uint32_t A2XX_SQ_TEX_0_SIGN_X(enum sq_tex_sign val) +{ + return ((val) << A2XX_SQ_TEX_0_SIGN_X__SHIFT) & A2XX_SQ_TEX_0_SIGN_X__MASK; +} +#define A2XX_SQ_TEX_0_SIGN_Y__MASK 0x00000030 +#define A2XX_SQ_TEX_0_SIGN_Y__SHIFT 4 +static inline uint32_t A2XX_SQ_TEX_0_SIGN_Y(enum sq_tex_sign val) +{ + return ((val) << A2XX_SQ_TEX_0_SIGN_Y__SHIFT) & A2XX_SQ_TEX_0_SIGN_Y__MASK; +} +#define A2XX_SQ_TEX_0_SIGN_Z__MASK 0x000000c0 +#define A2XX_SQ_TEX_0_SIGN_Z__SHIFT 6 +static inline uint32_t A2XX_SQ_TEX_0_SIGN_Z(enum sq_tex_sign val) +{ + return ((val) << A2XX_SQ_TEX_0_SIGN_Z__SHIFT) & A2XX_SQ_TEX_0_SIGN_Z__MASK; +} +#define A2XX_SQ_TEX_0_SIGN_W__MASK 0x00000300 +#define A2XX_SQ_TEX_0_SIGN_W__SHIFT 8 +static inline uint32_t A2XX_SQ_TEX_0_SIGN_W(enum sq_tex_sign val) +{ + return ((val) << A2XX_SQ_TEX_0_SIGN_W__SHIFT) & A2XX_SQ_TEX_0_SIGN_W__MASK; +} #define A2XX_SQ_TEX_0_CLAMP_X__MASK 0x00001c00 #define A2XX_SQ_TEX_0_CLAMP_X__SHIFT 10 static inline uint32_t A2XX_SQ_TEX_0_CLAMP_X(enum sq_tex_clamp val) @@ -1775,14 +1907,46 @@ static inline uint32_t A2XX_SQ_TEX_0_CLAMP_Z(enum sq_tex_clamp val) { return ((val) << A2XX_SQ_TEX_0_CLAMP_Z__SHIFT) & A2XX_SQ_TEX_0_CLAMP_Z__MASK; } -#define A2XX_SQ_TEX_0_PITCH__MASK 0xffc00000 +#define A2XX_SQ_TEX_0_PITCH__MASK 0x7fc00000 #define A2XX_SQ_TEX_0_PITCH__SHIFT 22 static inline uint32_t A2XX_SQ_TEX_0_PITCH(uint32_t val) { return ((val >> 5) << A2XX_SQ_TEX_0_PITCH__SHIFT) & A2XX_SQ_TEX_0_PITCH__MASK; } +#define A2XX_SQ_TEX_0_TILED 0x00000002 #define REG_A2XX_SQ_TEX_1 0x00000001 +#define A2XX_SQ_TEX_1_FORMAT__MASK 0x0000003f +#define A2XX_SQ_TEX_1_FORMAT__SHIFT 0 +static inline uint32_t A2XX_SQ_TEX_1_FORMAT(enum a2xx_sq_surfaceformat val) +{ + return ((val) << A2XX_SQ_TEX_1_FORMAT__SHIFT) & A2XX_SQ_TEX_1_FORMAT__MASK; +} +#define A2XX_SQ_TEX_1_ENDIANNESS__MASK 0x000000c0 +#define A2XX_SQ_TEX_1_ENDIANNESS__SHIFT 6 +static inline uint32_t A2XX_SQ_TEX_1_ENDIANNESS(enum sq_tex_endian val) +{ + return ((val) << A2XX_SQ_TEX_1_ENDIANNESS__SHIFT) & A2XX_SQ_TEX_1_ENDIANNESS__MASK; +} +#define A2XX_SQ_TEX_1_REQUEST_SIZE__MASK 0x00000300 +#define A2XX_SQ_TEX_1_REQUEST_SIZE__SHIFT 8 +static inline uint32_t A2XX_SQ_TEX_1_REQUEST_SIZE(uint32_t val) +{ + return ((val) << A2XX_SQ_TEX_1_REQUEST_SIZE__SHIFT) & A2XX_SQ_TEX_1_REQUEST_SIZE__MASK; +} +#define A2XX_SQ_TEX_1_STACKED 0x00000400 +#define A2XX_SQ_TEX_1_CLAMP_POLICY__MASK 0x00000800 +#define A2XX_SQ_TEX_1_CLAMP_POLICY__SHIFT 11 +static inline uint32_t A2XX_SQ_TEX_1_CLAMP_POLICY(enum sq_tex_clamp_policy val) +{ + return ((val) << A2XX_SQ_TEX_1_CLAMP_POLICY__SHIFT) & A2XX_SQ_TEX_1_CLAMP_POLICY__MASK; +} +#define A2XX_SQ_TEX_1_BASE_ADDRESS__MASK 0xfffff000 +#define A2XX_SQ_TEX_1_BASE_ADDRESS__SHIFT 12 +static inline uint32_t A2XX_SQ_TEX_1_BASE_ADDRESS(uint32_t val) +{ + return ((val >> 12) << A2XX_SQ_TEX_1_BASE_ADDRESS__SHIFT) & A2XX_SQ_TEX_1_BASE_ADDRESS__MASK; +} #define REG_A2XX_SQ_TEX_2 0x00000002 #define A2XX_SQ_TEX_2_WIDTH__MASK 0x00001fff @@ -1797,8 +1961,20 @@ static inline uint32_t A2XX_SQ_TEX_2_HEIGHT(uint32_t val) { return ((val) << A2XX_SQ_TEX_2_HEIGHT__SHIFT) & A2XX_SQ_TEX_2_HEIGHT__MASK; } +#define A2XX_SQ_TEX_2_DEPTH__MASK 0xfc000000 +#define A2XX_SQ_TEX_2_DEPTH__SHIFT 26 +static inline uint32_t A2XX_SQ_TEX_2_DEPTH(uint32_t val) +{ + return ((val) << A2XX_SQ_TEX_2_DEPTH__SHIFT) & A2XX_SQ_TEX_2_DEPTH__MASK; +} #define REG_A2XX_SQ_TEX_3 0x00000003 +#define A2XX_SQ_TEX_3_NUM_FORMAT__MASK 0x00000001 +#define A2XX_SQ_TEX_3_NUM_FORMAT__SHIFT 0 +static inline uint32_t A2XX_SQ_TEX_3_NUM_FORMAT(enum sq_tex_num_format val) +{ + return ((val) << A2XX_SQ_TEX_3_NUM_FORMAT__SHIFT) & A2XX_SQ_TEX_3_NUM_FORMAT__MASK; +} #define A2XX_SQ_TEX_3_SWIZ_X__MASK 0x0000000e #define A2XX_SQ_TEX_3_SWIZ_X__SHIFT 1 static inline uint32_t A2XX_SQ_TEX_3_SWIZ_X(enum sq_tex_swiz val) @@ -1823,6 +1999,12 @@ static inline uint32_t A2XX_SQ_TEX_3_SWIZ_W(enum sq_tex_swiz val) { return ((val) << A2XX_SQ_TEX_3_SWIZ_W__SHIFT) & A2XX_SQ_TEX_3_SWIZ_W__MASK; } +#define A2XX_SQ_TEX_3_EXP_ADJUST__MASK 0x0007e000 +#define A2XX_SQ_TEX_3_EXP_ADJUST__SHIFT 13 +static inline uint32_t A2XX_SQ_TEX_3_EXP_ADJUST(uint32_t val) +{ + return ((val) << A2XX_SQ_TEX_3_EXP_ADJUST__SHIFT) & A2XX_SQ_TEX_3_EXP_ADJUST__MASK; +} #define A2XX_SQ_TEX_3_XY_MAG_FILTER__MASK 0x00180000 #define A2XX_SQ_TEX_3_XY_MAG_FILTER__SHIFT 19 static inline uint32_t A2XX_SQ_TEX_3_XY_MAG_FILTER(enum sq_tex_filter val) @@ -1835,6 +2017,104 @@ static inline uint32_t A2XX_SQ_TEX_3_XY_MIN_FILTER(enum sq_tex_filter val) { return ((val) << A2XX_SQ_TEX_3_XY_MIN_FILTER__SHIFT) & A2XX_SQ_TEX_3_XY_MIN_FILTER__MASK; } +#define A2XX_SQ_TEX_3_MIP_FILTER__MASK 0x01800000 +#define A2XX_SQ_TEX_3_MIP_FILTER__SHIFT 23 +static inline uint32_t A2XX_SQ_TEX_3_MIP_FILTER(enum sq_tex_filter val) +{ + return ((val) << A2XX_SQ_TEX_3_MIP_FILTER__SHIFT) & A2XX_SQ_TEX_3_MIP_FILTER__MASK; +} +#define A2XX_SQ_TEX_3_ANISO_FILTER__MASK 0x0e000000 +#define A2XX_SQ_TEX_3_ANISO_FILTER__SHIFT 25 +static inline uint32_t A2XX_SQ_TEX_3_ANISO_FILTER(enum sq_tex_aniso_filter val) +{ + return ((val) << A2XX_SQ_TEX_3_ANISO_FILTER__SHIFT) & A2XX_SQ_TEX_3_ANISO_FILTER__MASK; +} +#define A2XX_SQ_TEX_3_BORDER_SIZE__MASK 0x80000000 +#define A2XX_SQ_TEX_3_BORDER_SIZE__SHIFT 31 +static inline uint32_t A2XX_SQ_TEX_3_BORDER_SIZE(uint32_t val) +{ + return ((val) << A2XX_SQ_TEX_3_BORDER_SIZE__SHIFT) & A2XX_SQ_TEX_3_BORDER_SIZE__MASK; +} + +#define REG_A2XX_SQ_TEX_4 0x00000004 +#define A2XX_SQ_TEX_4_VOL_MAG_FILTER__MASK 0x00000001 +#define A2XX_SQ_TEX_4_VOL_MAG_FILTER__SHIFT 0 +static inline uint32_t A2XX_SQ_TEX_4_VOL_MAG_FILTER(enum sq_tex_filter val) +{ + return ((val) << A2XX_SQ_TEX_4_VOL_MAG_FILTER__SHIFT) & A2XX_SQ_TEX_4_VOL_MAG_FILTER__MASK; +} +#define A2XX_SQ_TEX_4_VOL_MIN_FILTER__MASK 0x00000002 +#define A2XX_SQ_TEX_4_VOL_MIN_FILTER__SHIFT 1 +static inline uint32_t A2XX_SQ_TEX_4_VOL_MIN_FILTER(enum sq_tex_filter val) +{ + return ((val) << A2XX_SQ_TEX_4_VOL_MIN_FILTER__SHIFT) & A2XX_SQ_TEX_4_VOL_MIN_FILTER__MASK; +} +#define A2XX_SQ_TEX_4_MIP_MIN_LEVEL__MASK 0x0000003c +#define A2XX_SQ_TEX_4_MIP_MIN_LEVEL__SHIFT 2 +static inline uint32_t A2XX_SQ_TEX_4_MIP_MIN_LEVEL(uint32_t val) +{ + return ((val) << A2XX_SQ_TEX_4_MIP_MIN_LEVEL__SHIFT) & A2XX_SQ_TEX_4_MIP_MIN_LEVEL__MASK; +} +#define A2XX_SQ_TEX_4_MIP_MAX_LEVEL__MASK 0x000003c0 +#define A2XX_SQ_TEX_4_MIP_MAX_LEVEL__SHIFT 6 +static inline uint32_t A2XX_SQ_TEX_4_MIP_MAX_LEVEL(uint32_t val) +{ + return ((val) << A2XX_SQ_TEX_4_MIP_MAX_LEVEL__SHIFT) & A2XX_SQ_TEX_4_MIP_MAX_LEVEL__MASK; +} +#define A2XX_SQ_TEX_4_MAX_ANISO_WALK 0x00000400 +#define A2XX_SQ_TEX_4_MIN_ANISO_WALK 0x00000800 +#define A2XX_SQ_TEX_4_LOD_BIAS__MASK 0x003ff000 +#define A2XX_SQ_TEX_4_LOD_BIAS__SHIFT 12 +static inline uint32_t A2XX_SQ_TEX_4_LOD_BIAS(float val) +{ + return ((((int32_t)(val * 32.0))) << A2XX_SQ_TEX_4_LOD_BIAS__SHIFT) & A2XX_SQ_TEX_4_LOD_BIAS__MASK; +} +#define A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_H__MASK 0x07c00000 +#define A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_H__SHIFT 22 +static inline uint32_t A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_H(uint32_t val) +{ + return ((val) << A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_H__SHIFT) & A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_H__MASK; +} +#define A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_V__MASK 0xf8000000 +#define A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_V__SHIFT 27 +static inline uint32_t A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_V(uint32_t val) +{ + return ((val) << A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_V__SHIFT) & A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_V__MASK; +} + +#define REG_A2XX_SQ_TEX_5 0x00000005 +#define A2XX_SQ_TEX_5_BORDER_COLOR__MASK 0x00000003 +#define A2XX_SQ_TEX_5_BORDER_COLOR__SHIFT 0 +static inline uint32_t A2XX_SQ_TEX_5_BORDER_COLOR(enum sq_tex_border_color val) +{ + return ((val) << A2XX_SQ_TEX_5_BORDER_COLOR__SHIFT) & A2XX_SQ_TEX_5_BORDER_COLOR__MASK; +} +#define A2XX_SQ_TEX_5_FORCE_BCW_MAX 0x00000004 +#define A2XX_SQ_TEX_5_TRI_CLAMP__MASK 0x00000018 +#define A2XX_SQ_TEX_5_TRI_CLAMP__SHIFT 3 +static inline uint32_t A2XX_SQ_TEX_5_TRI_CLAMP(uint32_t val) +{ + return ((val) << A2XX_SQ_TEX_5_TRI_CLAMP__SHIFT) & A2XX_SQ_TEX_5_TRI_CLAMP__MASK; +} +#define A2XX_SQ_TEX_5_ANISO_BIAS__MASK 0x000001e0 +#define A2XX_SQ_TEX_5_ANISO_BIAS__SHIFT 5 +static inline uint32_t A2XX_SQ_TEX_5_ANISO_BIAS(float val) +{ + return ((((int32_t)(val * 1.0))) << A2XX_SQ_TEX_5_ANISO_BIAS__SHIFT) & A2XX_SQ_TEX_5_ANISO_BIAS__MASK; +} +#define A2XX_SQ_TEX_5_DIMENSION__MASK 0x00000600 +#define A2XX_SQ_TEX_5_DIMENSION__SHIFT 9 +static inline uint32_t A2XX_SQ_TEX_5_DIMENSION(enum sq_tex_dimension val) +{ + return ((val) << A2XX_SQ_TEX_5_DIMENSION__SHIFT) & A2XX_SQ_TEX_5_DIMENSION__MASK; +} +#define A2XX_SQ_TEX_5_PACKED_MIPS 0x00000800 +#define A2XX_SQ_TEX_5_MIP_ADDRESS__MASK 0xfffff000 +#define A2XX_SQ_TEX_5_MIP_ADDRESS__SHIFT 12 +static inline uint32_t A2XX_SQ_TEX_5_MIP_ADDRESS(uint32_t val) +{ + return ((val >> 12) << A2XX_SQ_TEX_5_MIP_ADDRESS__SHIFT) & A2XX_SQ_TEX_5_MIP_ADDRESS__MASK; +} #endif /* A2XX_XML */ diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c new file mode 100644 index 000000000000..1f83bc18d500 --- /dev/null +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c @@ -0,0 +1,492 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 The Linux Foundation. All rights reserved. */ + +#include "a2xx_gpu.h" +#include "msm_gem.h" +#include "msm_mmu.h" + +extern bool hang_debug; + +static void a2xx_dump(struct msm_gpu *gpu); +static bool a2xx_idle(struct msm_gpu *gpu); + +static bool a2xx_me_init(struct msm_gpu *gpu) +{ + struct msm_ringbuffer *ring = gpu->rb[0]; + + OUT_PKT3(ring, CP_ME_INIT, 18); + + /* All fields present (bits 9:0) */ + OUT_RING(ring, 0x000003ff); + /* Disable/Enable Real-Time Stream processing (present but ignored) */ + OUT_RING(ring, 0x00000000); + /* Enable (2D <-> 3D) implicit synchronization (present but ignored) */ + OUT_RING(ring, 0x00000000); + + OUT_RING(ring, REG_A2XX_RB_SURFACE_INFO - 0x2000); + OUT_RING(ring, REG_A2XX_PA_SC_WINDOW_OFFSET - 0x2000); + OUT_RING(ring, REG_A2XX_VGT_MAX_VTX_INDX - 0x2000); + OUT_RING(ring, REG_A2XX_SQ_PROGRAM_CNTL - 0x2000); + OUT_RING(ring, REG_A2XX_RB_DEPTHCONTROL - 0x2000); + OUT_RING(ring, REG_A2XX_PA_SU_POINT_SIZE - 0x2000); + OUT_RING(ring, REG_A2XX_PA_SC_LINE_CNTL - 0x2000); + OUT_RING(ring, REG_A2XX_PA_SU_POLY_OFFSET_FRONT_SCALE - 0x2000); + + /* Vertex and Pixel Shader Start Addresses in instructions + * (3 DWORDS per instruction) */ + OUT_RING(ring, 0x80000180); + /* Maximum Contexts */ + OUT_RING(ring, 0x00000001); + /* Write Confirm Interval and The CP will wait the + * wait_interval * 16 clocks between polling */ + OUT_RING(ring, 0x00000000); + /* NQ and External Memory Swap */ + OUT_RING(ring, 0x00000000); + /* protected mode error checking (0x1f2 is REG_AXXX_CP_INT_CNTL) */ + OUT_RING(ring, 0x200001f2); + /* Disable header dumping and Header dump address */ + OUT_RING(ring, 0x00000000); + /* Header dump size */ + OUT_RING(ring, 0x00000000); + + /* enable protected mode */ + OUT_PKT3(ring, CP_SET_PROTECTED_MODE, 1); + OUT_RING(ring, 1); + + gpu->funcs->flush(gpu, ring); + return a2xx_idle(gpu); +} + +static int a2xx_hw_init(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + dma_addr_t pt_base, tran_error; + uint32_t *ptr, len; + int i, ret; + + msm_gpummu_params(gpu->aspace->mmu, &pt_base, &tran_error); + + DBG("%s", gpu->name); + + /* halt ME to avoid ucode upload issues on a20x */ + gpu_write(gpu, REG_AXXX_CP_ME_CNTL, AXXX_CP_ME_CNTL_HALT); + + gpu_write(gpu, REG_A2XX_RBBM_PM_OVERRIDE1, 0xfffffffe); + gpu_write(gpu, REG_A2XX_RBBM_PM_OVERRIDE2, 0xffffffff); + + /* note: kgsl uses 0x00000001 after first reset on a22x */ + gpu_write(gpu, REG_A2XX_RBBM_SOFT_RESET, 0xffffffff); + msleep(30); + gpu_write(gpu, REG_A2XX_RBBM_SOFT_RESET, 0x00000000); + + if (adreno_is_a225(adreno_gpu)) + gpu_write(gpu, REG_A2XX_SQ_FLOW_CONTROL, 0x18000000); + + /* note: kgsl uses 0x0000ffff for a20x */ + gpu_write(gpu, REG_A2XX_RBBM_CNTL, 0x00004442); + + /* MPU: physical range */ + gpu_write(gpu, REG_A2XX_MH_MMU_MPU_BASE, 0x00000000); + gpu_write(gpu, REG_A2XX_MH_MMU_MPU_END, 0xfffff000); + + gpu_write(gpu, REG_A2XX_MH_MMU_CONFIG, A2XX_MH_MMU_CONFIG_MMU_ENABLE | + A2XX_MH_MMU_CONFIG_RB_W_CLNT_BEHAVIOR(BEH_TRAN_RNG) | + A2XX_MH_MMU_CONFIG_CP_W_CLNT_BEHAVIOR(BEH_TRAN_RNG) | + A2XX_MH_MMU_CONFIG_CP_R0_CLNT_BEHAVIOR(BEH_TRAN_RNG) | + A2XX_MH_MMU_CONFIG_CP_R1_CLNT_BEHAVIOR(BEH_TRAN_RNG) | + A2XX_MH_MMU_CONFIG_CP_R2_CLNT_BEHAVIOR(BEH_TRAN_RNG) | + A2XX_MH_MMU_CONFIG_CP_R3_CLNT_BEHAVIOR(BEH_TRAN_RNG) | + A2XX_MH_MMU_CONFIG_CP_R4_CLNT_BEHAVIOR(BEH_TRAN_RNG) | + A2XX_MH_MMU_CONFIG_VGT_R0_CLNT_BEHAVIOR(BEH_TRAN_RNG) | + A2XX_MH_MMU_CONFIG_VGT_R1_CLNT_BEHAVIOR(BEH_TRAN_RNG) | + A2XX_MH_MMU_CONFIG_TC_R_CLNT_BEHAVIOR(BEH_TRAN_RNG) | + A2XX_MH_MMU_CONFIG_PA_W_CLNT_BEHAVIOR(BEH_TRAN_RNG)); + + /* same as parameters in adreno_gpu */ + gpu_write(gpu, REG_A2XX_MH_MMU_VA_RANGE, SZ_16M | + A2XX_MH_MMU_VA_RANGE_NUM_64KB_REGIONS(0xfff)); + + gpu_write(gpu, REG_A2XX_MH_MMU_PT_BASE, pt_base); + gpu_write(gpu, REG_A2XX_MH_MMU_TRAN_ERROR, tran_error); + + gpu_write(gpu, REG_A2XX_MH_MMU_INVALIDATE, + A2XX_MH_MMU_INVALIDATE_INVALIDATE_ALL | + A2XX_MH_MMU_INVALIDATE_INVALIDATE_TC); + + gpu_write(gpu, REG_A2XX_MH_ARBITER_CONFIG, + A2XX_MH_ARBITER_CONFIG_SAME_PAGE_LIMIT(16) | + A2XX_MH_ARBITER_CONFIG_L1_ARB_ENABLE | + A2XX_MH_ARBITER_CONFIG_L1_ARB_HOLD_ENABLE | + A2XX_MH_ARBITER_CONFIG_PAGE_SIZE(1) | + A2XX_MH_ARBITER_CONFIG_TC_REORDER_ENABLE | + A2XX_MH_ARBITER_CONFIG_TC_ARB_HOLD_ENABLE | + A2XX_MH_ARBITER_CONFIG_IN_FLIGHT_LIMIT_ENABLE | + A2XX_MH_ARBITER_CONFIG_IN_FLIGHT_LIMIT(8) | + A2XX_MH_ARBITER_CONFIG_CP_CLNT_ENABLE | + A2XX_MH_ARBITER_CONFIG_VGT_CLNT_ENABLE | + A2XX_MH_ARBITER_CONFIG_TC_CLNT_ENABLE | + A2XX_MH_ARBITER_CONFIG_RB_CLNT_ENABLE | + A2XX_MH_ARBITER_CONFIG_PA_CLNT_ENABLE); + if (!adreno_is_a20x(adreno_gpu)) + gpu_write(gpu, REG_A2XX_MH_CLNT_INTF_CTRL_CONFIG1, 0x00032f07); + + gpu_write(gpu, REG_A2XX_SQ_VS_PROGRAM, 0x00000000); + gpu_write(gpu, REG_A2XX_SQ_PS_PROGRAM, 0x00000000); + + gpu_write(gpu, REG_A2XX_RBBM_PM_OVERRIDE1, 0); /* 0x200 for msm8960? */ + gpu_write(gpu, REG_A2XX_RBBM_PM_OVERRIDE2, 0); /* 0x80/0x1a0 for a22x? */ + + /* note: gsl doesn't set this */ + gpu_write(gpu, REG_A2XX_RBBM_DEBUG, 0x00080000); + + gpu_write(gpu, REG_A2XX_RBBM_INT_CNTL, + A2XX_RBBM_INT_CNTL_RDERR_INT_MASK); + gpu_write(gpu, REG_AXXX_CP_INT_CNTL, + AXXX_CP_INT_CNTL_T0_PACKET_IN_IB_MASK | + AXXX_CP_INT_CNTL_OPCODE_ERROR_MASK | + AXXX_CP_INT_CNTL_PROTECTED_MODE_ERROR_MASK | + AXXX_CP_INT_CNTL_RESERVED_BIT_ERROR_MASK | + AXXX_CP_INT_CNTL_IB_ERROR_MASK | + AXXX_CP_INT_CNTL_IB1_INT_MASK | + AXXX_CP_INT_CNTL_RB_INT_MASK); + gpu_write(gpu, REG_A2XX_SQ_INT_CNTL, 0); + gpu_write(gpu, REG_A2XX_MH_INTERRUPT_MASK, + A2XX_MH_INTERRUPT_MASK_AXI_READ_ERROR | + A2XX_MH_INTERRUPT_MASK_AXI_WRITE_ERROR | + A2XX_MH_INTERRUPT_MASK_MMU_PAGE_FAULT); + + for (i = 3; i <= 5; i++) + if ((SZ_16K << i) == adreno_gpu->gmem) + break; + gpu_write(gpu, REG_A2XX_RB_EDRAM_INFO, i); + + ret = adreno_hw_init(gpu); + if (ret) + return ret; + + /* NOTE: PM4/micro-engine firmware registers look to be the same + * for a2xx and a3xx.. we could possibly push that part down to + * adreno_gpu base class. Or push both PM4 and PFP but + * parameterize the pfp ucode addr/data registers.. + */ + + /* Load PM4: */ + ptr = (uint32_t *)(adreno_gpu->fw[ADRENO_FW_PM4]->data); + len = adreno_gpu->fw[ADRENO_FW_PM4]->size / 4; + DBG("loading PM4 ucode version: %x", ptr[1]); + + gpu_write(gpu, REG_AXXX_CP_DEBUG, + AXXX_CP_DEBUG_MIU_128BIT_WRITE_ENABLE); + gpu_write(gpu, REG_AXXX_CP_ME_RAM_WADDR, 0); + for (i = 1; i < len; i++) + gpu_write(gpu, REG_AXXX_CP_ME_RAM_DATA, ptr[i]); + + /* Load PFP: */ + ptr = (uint32_t *)(adreno_gpu->fw[ADRENO_FW_PFP]->data); + len = adreno_gpu->fw[ADRENO_FW_PFP]->size / 4; + DBG("loading PFP ucode version: %x", ptr[5]); + + gpu_write(gpu, REG_A2XX_CP_PFP_UCODE_ADDR, 0); + for (i = 1; i < len; i++) + gpu_write(gpu, REG_A2XX_CP_PFP_UCODE_DATA, ptr[i]); + + gpu_write(gpu, REG_AXXX_CP_QUEUE_THRESHOLDS, 0x000C0804); + + /* clear ME_HALT to start micro engine */ + gpu_write(gpu, REG_AXXX_CP_ME_CNTL, 0); + + return a2xx_me_init(gpu) ? 0 : -EINVAL; +} + +static void a2xx_recover(struct msm_gpu *gpu) +{ + int i; + + adreno_dump_info(gpu); + + for (i = 0; i < 8; i++) { + printk("CP_SCRATCH_REG%d: %u\n", i, + gpu_read(gpu, REG_AXXX_CP_SCRATCH_REG0 + i)); + } + + /* dump registers before resetting gpu, if enabled: */ + if (hang_debug) + a2xx_dump(gpu); + + gpu_write(gpu, REG_A2XX_RBBM_SOFT_RESET, 1); + gpu_read(gpu, REG_A2XX_RBBM_SOFT_RESET); + gpu_write(gpu, REG_A2XX_RBBM_SOFT_RESET, 0); + adreno_recover(gpu); +} + +static void a2xx_destroy(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a2xx_gpu *a2xx_gpu = to_a2xx_gpu(adreno_gpu); + + DBG("%s", gpu->name); + + adreno_gpu_cleanup(adreno_gpu); + + kfree(a2xx_gpu); +} + +static bool a2xx_idle(struct msm_gpu *gpu) +{ + /* wait for ringbuffer to drain: */ + if (!adreno_idle(gpu, gpu->rb[0])) + return false; + + /* then wait for GPU to finish: */ + if (spin_until(!(gpu_read(gpu, REG_A2XX_RBBM_STATUS) & + A2XX_RBBM_STATUS_GUI_ACTIVE))) { + DRM_ERROR("%s: timeout waiting for GPU to idle!\n", gpu->name); + + /* TODO maybe we need to reset GPU here to recover from hang? */ + return false; + } + + return true; +} + +static irqreturn_t a2xx_irq(struct msm_gpu *gpu) +{ + uint32_t mstatus, status; + + mstatus = gpu_read(gpu, REG_A2XX_MASTER_INT_SIGNAL); + + if (mstatus & A2XX_MASTER_INT_SIGNAL_MH_INT_STAT) { + status = gpu_read(gpu, REG_A2XX_MH_INTERRUPT_STATUS); + + dev_warn(gpu->dev->dev, "MH_INT: %08X\n", status); + dev_warn(gpu->dev->dev, "MMU_PAGE_FAULT: %08X\n", + gpu_read(gpu, REG_A2XX_MH_MMU_PAGE_FAULT)); + + gpu_write(gpu, REG_A2XX_MH_INTERRUPT_CLEAR, status); + } + + if (mstatus & A2XX_MASTER_INT_SIGNAL_CP_INT_STAT) { + status = gpu_read(gpu, REG_AXXX_CP_INT_STATUS); + + /* only RB_INT is expected */ + if (status & ~AXXX_CP_INT_CNTL_RB_INT_MASK) + dev_warn(gpu->dev->dev, "CP_INT: %08X\n", status); + + gpu_write(gpu, REG_AXXX_CP_INT_ACK, status); + } + + if (mstatus & A2XX_MASTER_INT_SIGNAL_RBBM_INT_STAT) { + status = gpu_read(gpu, REG_A2XX_RBBM_INT_STATUS); + + dev_warn(gpu->dev->dev, "RBBM_INT: %08X\n", status); + + gpu_write(gpu, REG_A2XX_RBBM_INT_ACK, status); + } + + msm_gpu_retire(gpu); + + return IRQ_HANDLED; +} + +static const unsigned int a200_registers[] = { + 0x0000, 0x0002, 0x0004, 0x000B, 0x003B, 0x003D, 0x0040, 0x0044, + 0x0046, 0x0047, 0x01C0, 0x01C1, 0x01C3, 0x01C8, 0x01D5, 0x01D9, + 0x01DC, 0x01DD, 0x01EA, 0x01EA, 0x01EE, 0x01F3, 0x01F6, 0x01F7, + 0x01FC, 0x01FF, 0x0391, 0x0392, 0x039B, 0x039E, 0x03B2, 0x03B5, + 0x03B7, 0x03B7, 0x03F8, 0x03FB, 0x0440, 0x0440, 0x0443, 0x0444, + 0x044B, 0x044B, 0x044D, 0x044F, 0x0452, 0x0452, 0x0454, 0x045B, + 0x047F, 0x047F, 0x0578, 0x0587, 0x05C9, 0x05C9, 0x05D0, 0x05D0, + 0x0601, 0x0604, 0x0606, 0x0609, 0x060B, 0x060E, 0x0613, 0x0614, + 0x0A29, 0x0A2B, 0x0A2F, 0x0A31, 0x0A40, 0x0A43, 0x0A45, 0x0A45, + 0x0A4E, 0x0A4F, 0x0C2C, 0x0C2C, 0x0C30, 0x0C30, 0x0C38, 0x0C3C, + 0x0C40, 0x0C40, 0x0C44, 0x0C44, 0x0C80, 0x0C86, 0x0C88, 0x0C94, + 0x0C99, 0x0C9A, 0x0CA4, 0x0CA5, 0x0D00, 0x0D03, 0x0D06, 0x0D06, + 0x0D08, 0x0D0B, 0x0D34, 0x0D35, 0x0DAE, 0x0DC1, 0x0DC8, 0x0DD4, + 0x0DD8, 0x0DD9, 0x0E00, 0x0E00, 0x0E02, 0x0E04, 0x0E17, 0x0E1E, + 0x0EC0, 0x0EC9, 0x0ECB, 0x0ECC, 0x0ED0, 0x0ED0, 0x0ED4, 0x0ED7, + 0x0EE0, 0x0EE2, 0x0F01, 0x0F02, 0x0F0C, 0x0F0C, 0x0F0E, 0x0F12, + 0x0F26, 0x0F2A, 0x0F2C, 0x0F2C, 0x2000, 0x2002, 0x2006, 0x200F, + 0x2080, 0x2082, 0x2100, 0x2109, 0x210C, 0x2114, 0x2180, 0x2184, + 0x21F5, 0x21F7, 0x2200, 0x2208, 0x2280, 0x2283, 0x2293, 0x2294, + 0x2300, 0x2308, 0x2312, 0x2312, 0x2316, 0x231D, 0x2324, 0x2326, + 0x2380, 0x2383, 0x2400, 0x2402, 0x2406, 0x240F, 0x2480, 0x2482, + 0x2500, 0x2509, 0x250C, 0x2514, 0x2580, 0x2584, 0x25F5, 0x25F7, + 0x2600, 0x2608, 0x2680, 0x2683, 0x2693, 0x2694, 0x2700, 0x2708, + 0x2712, 0x2712, 0x2716, 0x271D, 0x2724, 0x2726, 0x2780, 0x2783, + 0x4000, 0x4003, 0x4800, 0x4805, 0x4900, 0x4900, 0x4908, 0x4908, + ~0 /* sentinel */ +}; + +static const unsigned int a220_registers[] = { + 0x0000, 0x0002, 0x0004, 0x000B, 0x003B, 0x003D, 0x0040, 0x0044, + 0x0046, 0x0047, 0x01C0, 0x01C1, 0x01C3, 0x01C8, 0x01D5, 0x01D9, + 0x01DC, 0x01DD, 0x01EA, 0x01EA, 0x01EE, 0x01F3, 0x01F6, 0x01F7, + 0x01FC, 0x01FF, 0x0391, 0x0392, 0x039B, 0x039E, 0x03B2, 0x03B5, + 0x03B7, 0x03B7, 0x03F8, 0x03FB, 0x0440, 0x0440, 0x0443, 0x0444, + 0x044B, 0x044B, 0x044D, 0x044F, 0x0452, 0x0452, 0x0454, 0x045B, + 0x047F, 0x047F, 0x0578, 0x0587, 0x05C9, 0x05C9, 0x05D0, 0x05D0, + 0x0601, 0x0604, 0x0606, 0x0609, 0x060B, 0x060E, 0x0613, 0x0614, + 0x0A29, 0x0A2B, 0x0A2F, 0x0A31, 0x0A40, 0x0A40, 0x0A42, 0x0A43, + 0x0A45, 0x0A45, 0x0A4E, 0x0A4F, 0x0C30, 0x0C30, 0x0C38, 0x0C39, + 0x0C3C, 0x0C3C, 0x0C80, 0x0C81, 0x0C88, 0x0C93, 0x0D00, 0x0D03, + 0x0D05, 0x0D06, 0x0D08, 0x0D0B, 0x0D34, 0x0D35, 0x0DAE, 0x0DC1, + 0x0DC8, 0x0DD4, 0x0DD8, 0x0DD9, 0x0E00, 0x0E00, 0x0E02, 0x0E04, + 0x0E17, 0x0E1E, 0x0EC0, 0x0EC9, 0x0ECB, 0x0ECC, 0x0ED0, 0x0ED0, + 0x0ED4, 0x0ED7, 0x0EE0, 0x0EE2, 0x0F01, 0x0F02, 0x2000, 0x2002, + 0x2006, 0x200F, 0x2080, 0x2082, 0x2100, 0x2102, 0x2104, 0x2109, + 0x210C, 0x2114, 0x2180, 0x2184, 0x21F5, 0x21F7, 0x2200, 0x2202, + 0x2204, 0x2204, 0x2208, 0x2208, 0x2280, 0x2282, 0x2294, 0x2294, + 0x2300, 0x2308, 0x2309, 0x230A, 0x2312, 0x2312, 0x2316, 0x2316, + 0x2318, 0x231D, 0x2324, 0x2326, 0x2380, 0x2383, 0x2400, 0x2402, + 0x2406, 0x240F, 0x2480, 0x2482, 0x2500, 0x2502, 0x2504, 0x2509, + 0x250C, 0x2514, 0x2580, 0x2584, 0x25F5, 0x25F7, 0x2600, 0x2602, + 0x2604, 0x2606, 0x2608, 0x2608, 0x2680, 0x2682, 0x2694, 0x2694, + 0x2700, 0x2708, 0x2712, 0x2712, 0x2716, 0x2716, 0x2718, 0x271D, + 0x2724, 0x2726, 0x2780, 0x2783, 0x4000, 0x4003, 0x4800, 0x4805, + 0x4900, 0x4900, 0x4908, 0x4908, + ~0 /* sentinel */ +}; + +static const unsigned int a225_registers[] = { + 0x0000, 0x0002, 0x0004, 0x000B, 0x003B, 0x003D, 0x0040, 0x0044, + 0x0046, 0x0047, 0x013C, 0x013C, 0x0140, 0x014F, 0x01C0, 0x01C1, + 0x01C3, 0x01C8, 0x01D5, 0x01D9, 0x01DC, 0x01DD, 0x01EA, 0x01EA, + 0x01EE, 0x01F3, 0x01F6, 0x01F7, 0x01FC, 0x01FF, 0x0391, 0x0392, + 0x039B, 0x039E, 0x03B2, 0x03B5, 0x03B7, 0x03B7, 0x03F8, 0x03FB, + 0x0440, 0x0440, 0x0443, 0x0444, 0x044B, 0x044B, 0x044D, 0x044F, + 0x0452, 0x0452, 0x0454, 0x045B, 0x047F, 0x047F, 0x0578, 0x0587, + 0x05C9, 0x05C9, 0x05D0, 0x05D0, 0x0601, 0x0604, 0x0606, 0x0609, + 0x060B, 0x060E, 0x0613, 0x0614, 0x0A29, 0x0A2B, 0x0A2F, 0x0A31, + 0x0A40, 0x0A40, 0x0A42, 0x0A43, 0x0A45, 0x0A45, 0x0A4E, 0x0A4F, + 0x0C01, 0x0C1D, 0x0C30, 0x0C30, 0x0C38, 0x0C39, 0x0C3C, 0x0C3C, + 0x0C80, 0x0C81, 0x0C88, 0x0C93, 0x0D00, 0x0D03, 0x0D05, 0x0D06, + 0x0D08, 0x0D0B, 0x0D34, 0x0D35, 0x0DAE, 0x0DC1, 0x0DC8, 0x0DD4, + 0x0DD8, 0x0DD9, 0x0E00, 0x0E00, 0x0E02, 0x0E04, 0x0E17, 0x0E1E, + 0x0EC0, 0x0EC9, 0x0ECB, 0x0ECC, 0x0ED0, 0x0ED0, 0x0ED4, 0x0ED7, + 0x0EE0, 0x0EE2, 0x0F01, 0x0F02, 0x2000, 0x200F, 0x2080, 0x2082, + 0x2100, 0x2109, 0x210C, 0x2114, 0x2180, 0x2184, 0x21F5, 0x21F7, + 0x2200, 0x2202, 0x2204, 0x2206, 0x2208, 0x2210, 0x2220, 0x2222, + 0x2280, 0x2282, 0x2294, 0x2294, 0x2297, 0x2297, 0x2300, 0x230A, + 0x2312, 0x2312, 0x2315, 0x2316, 0x2318, 0x231D, 0x2324, 0x2326, + 0x2340, 0x2357, 0x2360, 0x2360, 0x2380, 0x2383, 0x2400, 0x240F, + 0x2480, 0x2482, 0x2500, 0x2509, 0x250C, 0x2514, 0x2580, 0x2584, + 0x25F5, 0x25F7, 0x2600, 0x2602, 0x2604, 0x2606, 0x2608, 0x2610, + 0x2620, 0x2622, 0x2680, 0x2682, 0x2694, 0x2694, 0x2697, 0x2697, + 0x2700, 0x270A, 0x2712, 0x2712, 0x2715, 0x2716, 0x2718, 0x271D, + 0x2724, 0x2726, 0x2740, 0x2757, 0x2760, 0x2760, 0x2780, 0x2783, + 0x4000, 0x4003, 0x4800, 0x4806, 0x4808, 0x4808, 0x4900, 0x4900, + 0x4908, 0x4908, + ~0 /* sentinel */ +}; + +/* would be nice to not have to duplicate the _show() stuff with printk(): */ +static void a2xx_dump(struct msm_gpu *gpu) +{ + printk("status: %08x\n", + gpu_read(gpu, REG_A2XX_RBBM_STATUS)); + adreno_dump(gpu); +} + +static struct msm_gpu_state *a2xx_gpu_state_get(struct msm_gpu *gpu) +{ + struct msm_gpu_state *state = kzalloc(sizeof(*state), GFP_KERNEL); + + if (!state) + return ERR_PTR(-ENOMEM); + + adreno_gpu_state_get(gpu, state); + + state->rbbm_status = gpu_read(gpu, REG_A2XX_RBBM_STATUS); + + return state; +} + +/* Register offset defines for A2XX - copy of A3XX */ +static const unsigned int a2xx_register_offsets[REG_ADRENO_REGISTER_MAX] = { + REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE, REG_AXXX_CP_RB_BASE), + REG_ADRENO_SKIP(REG_ADRENO_CP_RB_BASE_HI), + REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR_ADDR, REG_AXXX_CP_RB_RPTR_ADDR), + REG_ADRENO_SKIP(REG_ADRENO_CP_RB_RPTR_ADDR_HI), + REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR, REG_AXXX_CP_RB_RPTR), + REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_WPTR, REG_AXXX_CP_RB_WPTR), + REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_AXXX_CP_RB_CNTL), +}; + +static const struct adreno_gpu_funcs funcs = { + .base = { + .get_param = adreno_get_param, + .hw_init = a2xx_hw_init, + .pm_suspend = msm_gpu_pm_suspend, + .pm_resume = msm_gpu_pm_resume, + .recover = a2xx_recover, + .submit = adreno_submit, + .flush = adreno_flush, + .active_ring = adreno_active_ring, + .irq = a2xx_irq, + .destroy = a2xx_destroy, +#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) + .show = adreno_show, +#endif + .gpu_state_get = a2xx_gpu_state_get, + .gpu_state_put = adreno_gpu_state_put, + }, +}; + +static const struct msm_gpu_perfcntr perfcntrs[] = { +/* TODO */ +}; + +struct msm_gpu *a2xx_gpu_init(struct drm_device *dev) +{ + struct a2xx_gpu *a2xx_gpu = NULL; + struct adreno_gpu *adreno_gpu; + struct msm_gpu *gpu; + struct msm_drm_private *priv = dev->dev_private; + struct platform_device *pdev = priv->gpu_pdev; + int ret; + + if (!pdev) { + dev_err(dev->dev, "no a2xx device\n"); + ret = -ENXIO; + goto fail; + } + + a2xx_gpu = kzalloc(sizeof(*a2xx_gpu), GFP_KERNEL); + if (!a2xx_gpu) { + ret = -ENOMEM; + goto fail; + } + + adreno_gpu = &a2xx_gpu->base; + gpu = &adreno_gpu->base; + + gpu->perfcntrs = perfcntrs; + gpu->num_perfcntrs = ARRAY_SIZE(perfcntrs); + + if (adreno_is_a20x(adreno_gpu)) + adreno_gpu->registers = a200_registers; + else if (adreno_is_a225(adreno_gpu)) + adreno_gpu->registers = a225_registers; + else + adreno_gpu->registers = a220_registers; + + adreno_gpu->reg_offsets = a2xx_register_offsets; + + ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); + if (ret) + goto fail; + + if (!gpu->aspace) { + dev_err(dev->dev, "No memory protection without MMU\n"); + ret = -ENXIO; + goto fail; + } + + return gpu; + +fail: + if (a2xx_gpu) + a2xx_destroy(&a2xx_gpu->base.base); + + return ERR_PTR(ret); +} diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.h b/drivers/gpu/drm/msm/adreno/a2xx_gpu.h new file mode 100644 index 000000000000..02fba2cb8932 --- /dev/null +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.h @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 The Linux Foundation. All rights reserved. */ + +#ifndef __A2XX_GPU_H__ +#define __A2XX_GPU_H__ + +#include "adreno_gpu.h" + +/* arrg, somehow fb.h is getting pulled in: */ +#undef ROP_COPY +#undef ROP_XOR + +#include "a2xx.xml.h" + +struct a2xx_gpu { + struct adreno_gpu base; + bool pm_enabled; +}; +#define to_a2xx_gpu(x) container_of(x, struct a2xx_gpu, base) + +#endif /* __A2XX_GPU_H__ */ diff --git a/drivers/gpu/drm/msm/adreno/a3xx.xml.h b/drivers/gpu/drm/msm/adreno/a3xx.xml.h index a89f7bb8b5cc..17059f242a98 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx.xml.h +++ b/drivers/gpu/drm/msm/adreno/a3xx.xml.h @@ -10,13 +10,13 @@ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: - /home/robclark/src/envytools/rnndb/adreno.xml ( 501 bytes, from 2018-07-03 19:37:13) - /home/robclark/src/envytools/rnndb/freedreno_copyright.xml ( 1572 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml ( 36805 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml ( 13634 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml ( 42585 bytes, from 2018-10-04 19:06:37) +- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml ( 42463 bytes, from 2018-11-19 13:44:03) +- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml ( 14201 bytes, from 2018-12-02 17:29:54) +- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml ( 43052 bytes, from 2018-12-02 17:29:54) - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml ( 83840 bytes, from 2018-07-03 19:37:13) - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml ( 112086 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml ( 147240 bytes, from 2018-10-04 19:06:37) -- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml ( 139581 bytes, from 2018-10-04 19:06:42) +- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml ( 147240 bytes, from 2018-12-02 17:29:54) +- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml ( 140790 bytes, from 2018-12-02 17:29:54) - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml ( 10431 bytes, from 2018-09-14 13:03:07) - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml ( 1773 bytes, from 2018-07-03 19:37:13) diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c index 669c2d4b070d..c3b4bc6e4155 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c @@ -481,7 +481,7 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev) int ret; if (!pdev) { - dev_err(dev->dev, "no a3xx device\n"); + DRM_DEV_ERROR(dev->dev, "no a3xx device\n"); ret = -ENXIO; goto fail; } @@ -528,7 +528,7 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev) * to not be possible to restrict access, then we must * implement a cmdstream validator. */ - dev_err(dev->dev, "No memory protection without IOMMU\n"); + DRM_DEV_ERROR(dev->dev, "No memory protection without IOMMU\n"); ret = -ENXIO; goto fail; } diff --git a/drivers/gpu/drm/msm/adreno/a4xx.xml.h b/drivers/gpu/drm/msm/adreno/a4xx.xml.h index 858690f52854..9b51e25a9583 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx.xml.h +++ b/drivers/gpu/drm/msm/adreno/a4xx.xml.h @@ -10,13 +10,13 @@ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: - /home/robclark/src/envytools/rnndb/adreno.xml ( 501 bytes, from 2018-07-03 19:37:13) - /home/robclark/src/envytools/rnndb/freedreno_copyright.xml ( 1572 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml ( 36805 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml ( 13634 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml ( 42585 bytes, from 2018-10-04 19:06:37) +- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml ( 42463 bytes, from 2018-11-19 13:44:03) +- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml ( 14201 bytes, from 2018-12-02 17:29:54) +- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml ( 43052 bytes, from 2018-12-02 17:29:54) - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml ( 83840 bytes, from 2018-07-03 19:37:13) - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml ( 112086 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml ( 147240 bytes, from 2018-10-04 19:06:37) -- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml ( 139581 bytes, from 2018-10-04 19:06:42) +- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml ( 147240 bytes, from 2018-12-02 17:29:54) +- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml ( 140790 bytes, from 2018-12-02 17:29:54) - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml ( 10431 bytes, from 2018-09-14 13:03:07) - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml ( 1773 bytes, from 2018-07-03 19:37:13) diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c index 7c4e6dc1ed59..18f9a8e0bf3b 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c @@ -561,7 +561,7 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev) int ret; if (!pdev) { - dev_err(dev->dev, "no a4xx device\n"); + DRM_DEV_ERROR(dev->dev, "no a4xx device\n"); ret = -ENXIO; goto fail; } @@ -608,7 +608,7 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev) * to not be possible to restrict access, then we must * implement a cmdstream validator. */ - dev_err(dev->dev, "No memory protection without IOMMU\n"); + DRM_DEV_ERROR(dev->dev, "No memory protection without IOMMU\n"); ret = -ENXIO; goto fail; } diff --git a/drivers/gpu/drm/msm/adreno/a5xx.xml.h b/drivers/gpu/drm/msm/adreno/a5xx.xml.h index b4944cc0e62f..cf4fe14ddd6e 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx.xml.h +++ b/drivers/gpu/drm/msm/adreno/a5xx.xml.h @@ -10,13 +10,13 @@ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: - /home/robclark/src/envytools/rnndb/adreno.xml ( 501 bytes, from 2018-07-03 19:37:13) - /home/robclark/src/envytools/rnndb/freedreno_copyright.xml ( 1572 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml ( 36805 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml ( 13634 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml ( 42585 bytes, from 2018-10-04 19:06:37) +- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml ( 42463 bytes, from 2018-11-19 13:44:03) +- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml ( 14201 bytes, from 2018-12-02 17:29:54) +- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml ( 43052 bytes, from 2018-12-02 17:29:54) - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml ( 83840 bytes, from 2018-07-03 19:37:13) - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml ( 112086 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml ( 147240 bytes, from 2018-10-04 19:06:37) -- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml ( 139581 bytes, from 2018-10-04 19:06:42) +- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml ( 147240 bytes, from 2018-12-02 17:29:54) +- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml ( 140790 bytes, from 2018-12-02 17:29:54) - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml ( 10431 bytes, from 2018-09-14 13:03:07) - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml ( 1773 bytes, from 2018-07-03 19:37:13) diff --git a/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c b/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c index d2127b1c4ece..d9af3aff690f 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c @@ -130,15 +130,13 @@ reset_set(void *data, u64 val) adreno_gpu->fw[ADRENO_FW_PFP] = NULL; if (a5xx_gpu->pm4_bo) { - if (a5xx_gpu->pm4_iova) - msm_gem_put_iova(a5xx_gpu->pm4_bo, gpu->aspace); + msm_gem_unpin_iova(a5xx_gpu->pm4_bo, gpu->aspace); drm_gem_object_put(a5xx_gpu->pm4_bo); a5xx_gpu->pm4_bo = NULL; } if (a5xx_gpu->pfp_bo) { - if (a5xx_gpu->pfp_iova) - msm_gem_put_iova(a5xx_gpu->pfp_bo, gpu->aspace); + msm_gem_unpin_iova(a5xx_gpu->pfp_bo, gpu->aspace); drm_gem_object_put(a5xx_gpu->pfp_bo); a5xx_gpu->pfp_bo = NULL; } @@ -173,7 +171,7 @@ int a5xx_debugfs_init(struct msm_gpu *gpu, struct drm_minor *minor) minor->debugfs_root, minor); if (ret) { - dev_err(dev->dev, "could not install a5xx_debugfs_list\n"); + DRM_DEV_ERROR(dev->dev, "could not install a5xx_debugfs_list\n"); return ret; } diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 48b5304f460c..d5f5e56422f5 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -20,7 +20,6 @@ #include <linux/soc/qcom/mdt_loader.h> #include <linux/pm_opp.h> #include <linux/nvmem-consumer.h> -#include <linux/iopoll.h> #include <linux/slab.h> #include "msm_gem.h" #include "msm_mmu.h" @@ -511,13 +510,16 @@ static int a5xx_ucode_init(struct msm_gpu *gpu) a5xx_gpu->pm4_bo = adreno_fw_create_bo(gpu, adreno_gpu->fw[ADRENO_FW_PM4], &a5xx_gpu->pm4_iova); + if (IS_ERR(a5xx_gpu->pm4_bo)) { ret = PTR_ERR(a5xx_gpu->pm4_bo); a5xx_gpu->pm4_bo = NULL; - dev_err(gpu->dev->dev, "could not allocate PM4: %d\n", + DRM_DEV_ERROR(gpu->dev->dev, "could not allocate PM4: %d\n", ret); return ret; } + + msm_gem_object_set_name(a5xx_gpu->pm4_bo, "pm4fw"); } if (!a5xx_gpu->pfp_bo) { @@ -527,10 +529,12 @@ static int a5xx_ucode_init(struct msm_gpu *gpu) if (IS_ERR(a5xx_gpu->pfp_bo)) { ret = PTR_ERR(a5xx_gpu->pfp_bo); a5xx_gpu->pfp_bo = NULL; - dev_err(gpu->dev->dev, "could not allocate PFP: %d\n", + DRM_DEV_ERROR(gpu->dev->dev, "could not allocate PFP: %d\n", ret); return ret; } + + msm_gem_object_set_name(a5xx_gpu->pfp_bo, "pfpfw"); } gpu_write64(gpu, REG_A5XX_CP_ME_INSTR_BASE_LO, @@ -841,20 +845,17 @@ static void a5xx_destroy(struct msm_gpu *gpu) a5xx_preempt_fini(gpu); if (a5xx_gpu->pm4_bo) { - if (a5xx_gpu->pm4_iova) - msm_gem_put_iova(a5xx_gpu->pm4_bo, gpu->aspace); + msm_gem_unpin_iova(a5xx_gpu->pm4_bo, gpu->aspace); drm_gem_object_put_unlocked(a5xx_gpu->pm4_bo); } if (a5xx_gpu->pfp_bo) { - if (a5xx_gpu->pfp_iova) - msm_gem_put_iova(a5xx_gpu->pfp_bo, gpu->aspace); + msm_gem_unpin_iova(a5xx_gpu->pfp_bo, gpu->aspace); drm_gem_object_put_unlocked(a5xx_gpu->pfp_bo); } if (a5xx_gpu->gpmu_bo) { - if (a5xx_gpu->gpmu_iova) - msm_gem_put_iova(a5xx_gpu->gpmu_bo, gpu->aspace); + msm_gem_unpin_iova(a5xx_gpu->gpmu_bo, gpu->aspace); drm_gem_object_put_unlocked(a5xx_gpu->gpmu_bo); } @@ -1028,7 +1029,7 @@ static void a5xx_fault_detect_irq(struct msm_gpu *gpu) struct msm_drm_private *priv = dev->dev_private; struct msm_ringbuffer *ring = gpu->funcs->active_ring(gpu); - dev_err(dev->dev, "gpu fault ring %d fence %x status %8.8X rb %4.4x/%4.4x ib1 %16.16llX/%4.4x ib2 %16.16llX/%4.4x\n", + DRM_DEV_ERROR(dev->dev, "gpu fault ring %d fence %x status %8.8X rb %4.4x/%4.4x ib1 %16.16llX/%4.4x ib2 %16.16llX/%4.4x\n", ring ? ring->id : -1, ring ? ring->seqno : 0, gpu_read(gpu, REG_A5XX_RBBM_STATUS), gpu_read(gpu, REG_A5XX_CP_RB_RPTR), @@ -1134,7 +1135,7 @@ static const u32 a5xx_registers[] = { static void a5xx_dump(struct msm_gpu *gpu) { - dev_info(gpu->dev->dev, "status: %08x\n", + DRM_DEV_INFO(gpu->dev->dev, "status: %08x\n", gpu_read(gpu, REG_A5XX_RBBM_STATUS)); adreno_dump(gpu); } @@ -1211,10 +1212,6 @@ struct a5xx_gpu_state { u32 *hlsqregs; }; -#define gpu_poll_timeout(gpu, addr, val, cond, interval, timeout) \ - readl_poll_timeout((gpu)->mmio + ((addr) << 2), val, cond, \ - interval, timeout) - static int a5xx_crashdumper_init(struct msm_gpu *gpu, struct a5xx_crashdumper *dumper) { @@ -1222,19 +1219,10 @@ static int a5xx_crashdumper_init(struct msm_gpu *gpu, SZ_1M, MSM_BO_UNCACHED, gpu->aspace, &dumper->bo, &dumper->iova); - if (IS_ERR(dumper->ptr)) - return PTR_ERR(dumper->ptr); - - return 0; -} - -static void a5xx_crashdumper_free(struct msm_gpu *gpu, - struct a5xx_crashdumper *dumper) -{ - msm_gem_put_iova(dumper->bo, gpu->aspace); - msm_gem_put_vaddr(dumper->bo); + if (!IS_ERR(dumper->ptr)) + msm_gem_object_set_name(dumper->bo, "crashdump"); - drm_gem_object_put(dumper->bo); + return PTR_ERR_OR_ZERO(dumper->ptr); } static int a5xx_crashdumper_run(struct msm_gpu *gpu, @@ -1329,7 +1317,7 @@ static void a5xx_gpu_state_get_hlsq_regs(struct msm_gpu *gpu, if (a5xx_crashdumper_run(gpu, &dumper)) { kfree(a5xx_state->hlsqregs); - a5xx_crashdumper_free(gpu, &dumper); + msm_gem_kernel_put(dumper.bo, gpu->aspace, true); return; } @@ -1337,7 +1325,7 @@ static void a5xx_gpu_state_get_hlsq_regs(struct msm_gpu *gpu, memcpy(a5xx_state->hlsqregs, dumper.ptr + (256 * SZ_1K), count * sizeof(u32)); - a5xx_crashdumper_free(gpu, &dumper); + msm_gem_kernel_put(dumper.bo, gpu->aspace, true); } static struct msm_gpu_state *a5xx_gpu_state_get(struct msm_gpu *gpu) @@ -1508,7 +1496,7 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) int ret; if (!pdev) { - dev_err(dev->dev, "No A5XX device is defined\n"); + DRM_DEV_ERROR(dev->dev, "No A5XX device is defined\n"); return ERR_PTR(-ENXIO); } diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c index 7a41e1c147e4..70e65c94e525 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_power.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c @@ -298,7 +298,9 @@ void a5xx_gpmu_ucode_init(struct msm_gpu *gpu) MSM_BO_UNCACHED | MSM_BO_GPU_READONLY, gpu->aspace, &a5xx_gpu->gpmu_bo, &a5xx_gpu->gpmu_iova); if (IS_ERR(ptr)) - goto err; + return; + + msm_gem_object_set_name(a5xx_gpu->gpmu_bo, "gpmufw"); while (cmds_size > 0) { int i; @@ -317,15 +319,4 @@ void a5xx_gpmu_ucode_init(struct msm_gpu *gpu) msm_gem_put_vaddr(a5xx_gpu->gpmu_bo); a5xx_gpu->gpmu_dwords = dwords; - - return; -err: - if (a5xx_gpu->gpmu_iova) - msm_gem_put_iova(a5xx_gpu->gpmu_bo, gpu->aspace); - if (a5xx_gpu->gpmu_bo) - drm_gem_object_put(a5xx_gpu->gpmu_bo); - - a5xx_gpu->gpmu_bo = NULL; - a5xx_gpu->gpmu_iova = 0; - a5xx_gpu->gpmu_dwords = 0; } diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c index 4c357ead1be6..3d62310a535f 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c @@ -92,7 +92,7 @@ static void a5xx_preempt_timer(struct timer_list *t) if (!try_preempt_state(a5xx_gpu, PREEMPT_TRIGGERED, PREEMPT_FAULTED)) return; - dev_err(dev->dev, "%s: preemption timed out\n", gpu->name); + DRM_DEV_ERROR(dev->dev, "%s: preemption timed out\n", gpu->name); queue_work(priv->wq, &gpu->recover_work); } @@ -188,7 +188,7 @@ void a5xx_preempt_irq(struct msm_gpu *gpu) status = gpu_read(gpu, REG_A5XX_CP_CONTEXT_SWITCH_CNTL); if (unlikely(status)) { set_preempt_state(a5xx_gpu, PREEMPT_FAULTED); - dev_err(dev->dev, "%s: Preemption failed to complete\n", + DRM_DEV_ERROR(dev->dev, "%s: Preemption failed to complete\n", gpu->name); queue_work(priv->wq, &gpu->recover_work); return; @@ -245,6 +245,8 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu, if (IS_ERR(ptr)) return PTR_ERR(ptr); + msm_gem_object_set_name(bo, "preempt"); + a5xx_gpu->preempt_bo[ring->id] = bo; a5xx_gpu->preempt_iova[ring->id] = iova; a5xx_gpu->preempt[ring->id] = ptr; @@ -267,18 +269,8 @@ void a5xx_preempt_fini(struct msm_gpu *gpu) struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); int i; - for (i = 0; i < gpu->nr_rings; i++) { - if (!a5xx_gpu->preempt_bo[i]) - continue; - - msm_gem_put_vaddr(a5xx_gpu->preempt_bo[i]); - - if (a5xx_gpu->preempt_iova[i]) - msm_gem_put_iova(a5xx_gpu->preempt_bo[i], gpu->aspace); - - drm_gem_object_put(a5xx_gpu->preempt_bo[i]); - a5xx_gpu->preempt_bo[i] = NULL; - } + for (i = 0; i < gpu->nr_rings; i++) + msm_gem_kernel_put(a5xx_gpu->preempt_bo[i], gpu->aspace, true); } void a5xx_preempt_init(struct msm_gpu *gpu) diff --git a/drivers/gpu/drm/msm/adreno/a6xx.xml.h b/drivers/gpu/drm/msm/adreno/a6xx.xml.h index a6f7c40454a6..f44553ec3193 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx.xml.h +++ b/drivers/gpu/drm/msm/adreno/a6xx.xml.h @@ -10,13 +10,13 @@ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: - /home/robclark/src/envytools/rnndb/adreno.xml ( 501 bytes, from 2018-07-03 19:37:13) - /home/robclark/src/envytools/rnndb/freedreno_copyright.xml ( 1572 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml ( 36805 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml ( 13634 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml ( 42585 bytes, from 2018-10-04 19:06:37) +- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml ( 42463 bytes, from 2018-11-19 13:44:03) +- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml ( 14201 bytes, from 2018-12-02 17:29:54) +- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml ( 43052 bytes, from 2018-12-02 17:29:54) - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml ( 83840 bytes, from 2018-07-03 19:37:13) - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml ( 112086 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml ( 147240 bytes, from 2018-10-04 19:06:37) -- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml ( 139581 bytes, from 2018-10-04 19:06:42) +- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml ( 147240 bytes, from 2018-12-02 17:29:54) +- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml ( 140790 bytes, from 2018-12-02 17:29:54) - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml ( 10431 bytes, from 2018-09-14 13:03:07) - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml ( 1773 bytes, from 2018-07-03 19:37:13) @@ -501,7 +501,7 @@ enum a6xx_vfd_perfcounter_select { PERF_VFDP_VS_STAGE_WAVES = 22, }; -enum a6xx_hslq_perfcounter_select { +enum a6xx_hlsq_perfcounter_select { PERF_HLSQ_BUSY_CYCLES = 0, PERF_HLSQ_STALL_CYCLES_UCHE = 1, PERF_HLSQ_STALL_CYCLES_SP_STATE = 2, @@ -2959,6 +2959,8 @@ static inline uint32_t A6XX_GRAS_SC_WINDOW_SCISSOR_BR_Y(uint32_t val) #define A6XX_GRAS_LRZ_CNTL_ENABLE 0x00000001 #define A6XX_GRAS_LRZ_CNTL_LRZ_WRITE 0x00000002 #define A6XX_GRAS_LRZ_CNTL_GREATER 0x00000004 +#define A6XX_GRAS_LRZ_CNTL_UNK3 0x00000008 +#define A6XX_GRAS_LRZ_CNTL_UNK4 0x00000010 #define REG_A6XX_GRAS_UNKNOWN_8101 0x00008101 @@ -2997,6 +2999,13 @@ static inline uint32_t A6XX_GRAS_LRZ_BUFFER_PITCH_ARRAY_PITCH(uint32_t val) #define REG_A6XX_GRAS_UNKNOWN_8110 0x00008110 #define REG_A6XX_GRAS_2D_BLIT_CNTL 0x00008400 +#define A6XX_GRAS_2D_BLIT_CNTL_COLOR_FORMAT__MASK 0x0000ff00 +#define A6XX_GRAS_2D_BLIT_CNTL_COLOR_FORMAT__SHIFT 8 +static inline uint32_t A6XX_GRAS_2D_BLIT_CNTL_COLOR_FORMAT(enum a6xx_color_fmt val) +{ + return ((val) << A6XX_GRAS_2D_BLIT_CNTL_COLOR_FORMAT__SHIFT) & A6XX_GRAS_2D_BLIT_CNTL_COLOR_FORMAT__MASK; +} +#define A6XX_GRAS_2D_BLIT_CNTL_SCISSOR 0x00010000 #define REG_A6XX_GRAS_2D_SRC_TL_X 0x00008401 #define A6XX_GRAS_2D_SRC_TL_X_X__MASK 0x00ffff00 @@ -3449,6 +3458,7 @@ static inline uint32_t A6XX_RB_BLEND_CNTL_ENABLE_BLEND(uint32_t val) return ((val) << A6XX_RB_BLEND_CNTL_ENABLE_BLEND__SHIFT) & A6XX_RB_BLEND_CNTL_ENABLE_BLEND__MASK; } #define A6XX_RB_BLEND_CNTL_INDEPENDENT_BLEND 0x00000100 +#define A6XX_RB_BLEND_CNTL_ALPHA_TO_COVERAGE 0x00000400 #define A6XX_RB_BLEND_CNTL_SAMPLE_MASK__MASK 0xffff0000 #define A6XX_RB_BLEND_CNTL_SAMPLE_MASK__SHIFT 16 static inline uint32_t A6XX_RB_BLEND_CNTL_SAMPLE_MASK(uint32_t val) @@ -3642,6 +3652,9 @@ static inline uint32_t A6XX_RB_WINDOW_OFFSET_Y(uint32_t val) #define REG_A6XX_RB_SAMPLE_COUNT_CONTROL 0x00008891 #define A6XX_RB_SAMPLE_COUNT_CONTROL_COPY 0x00000002 +#define REG_A6XX_RB_LRZ_CNTL 0x00008898 +#define A6XX_RB_LRZ_CNTL_ENABLE 0x00000001 + #define REG_A6XX_RB_UNKNOWN_88D0 0x000088d0 #define REG_A6XX_RB_BLIT_SCISSOR_TL 0x000088d1 @@ -3674,6 +3687,14 @@ static inline uint32_t A6XX_RB_BLIT_SCISSOR_BR_Y(uint32_t val) return ((val) << A6XX_RB_BLIT_SCISSOR_BR_Y__SHIFT) & A6XX_RB_BLIT_SCISSOR_BR_Y__MASK; } +#define REG_A6XX_RB_MSAA_CNTL 0x000088d5 +#define A6XX_RB_MSAA_CNTL_SAMPLES__MASK 0x00000018 +#define A6XX_RB_MSAA_CNTL_SAMPLES__SHIFT 3 +static inline uint32_t A6XX_RB_MSAA_CNTL_SAMPLES(enum a3xx_msaa_samples val) +{ + return ((val) << A6XX_RB_MSAA_CNTL_SAMPLES__SHIFT) & A6XX_RB_MSAA_CNTL_SAMPLES__MASK; +} + #define REG_A6XX_RB_BLIT_BASE_GMEM 0x000088d6 #define REG_A6XX_RB_BLIT_DST_INFO 0x000088d7 @@ -3684,6 +3705,12 @@ static inline uint32_t A6XX_RB_BLIT_DST_INFO_TILE_MODE(enum a6xx_tile_mode val) return ((val) << A6XX_RB_BLIT_DST_INFO_TILE_MODE__SHIFT) & A6XX_RB_BLIT_DST_INFO_TILE_MODE__MASK; } #define A6XX_RB_BLIT_DST_INFO_FLAGS 0x00000004 +#define A6XX_RB_BLIT_DST_INFO_SAMPLES__MASK 0x00000018 +#define A6XX_RB_BLIT_DST_INFO_SAMPLES__SHIFT 3 +static inline uint32_t A6XX_RB_BLIT_DST_INFO_SAMPLES(enum a3xx_msaa_samples val) +{ + return ((val) << A6XX_RB_BLIT_DST_INFO_SAMPLES__SHIFT) & A6XX_RB_BLIT_DST_INFO_SAMPLES__MASK; +} #define A6XX_RB_BLIT_DST_INFO_COLOR_FORMAT__MASK 0x00007f80 #define A6XX_RB_BLIT_DST_INFO_COLOR_FORMAT__SHIFT 7 static inline uint32_t A6XX_RB_BLIT_DST_INFO_COLOR_FORMAT(enum a6xx_color_fmt val) @@ -3780,6 +3807,9 @@ static inline uint32_t A6XX_RB_2D_BLIT_CNTL_COLOR_FORMAT(enum a6xx_color_fmt val { return ((val) << A6XX_RB_2D_BLIT_CNTL_COLOR_FORMAT__SHIFT) & A6XX_RB_2D_BLIT_CNTL_COLOR_FORMAT__MASK; } +#define A6XX_RB_2D_BLIT_CNTL_SCISSOR 0x00010000 + +#define REG_A6XX_RB_UNKNOWN_8C01 0x00008c01 #define REG_A6XX_RB_2D_DST_INFO 0x00008c17 #define A6XX_RB_2D_DST_INFO_COLOR_FORMAT__MASK 0x000000ff @@ -4465,6 +4495,7 @@ static inline uint32_t A6XX_SP_FS_CTRL_REG0_THREADSIZE(enum a3xx_threadsize val) #define REG_A6XX_SP_BLEND_CNTL 0x0000a989 #define A6XX_SP_BLEND_CNTL_ENABLED 0x00000001 #define A6XX_SP_BLEND_CNTL_UNK8 0x00000100 +#define A6XX_SP_BLEND_CNTL_ALPHA_TO_COVERAGE 0x00000400 #define REG_A6XX_SP_SRGB_CNTL 0x0000a98a #define A6XX_SP_SRGB_CNTL_SRGB_MRT0 0x00000001 @@ -4643,6 +4674,8 @@ static inline uint32_t A6XX_SP_FS_CONFIG_NSAMP(uint32_t val) #define REG_A6XX_SP_UNKNOWN_AB20 0x0000ab20 +#define REG_A6XX_SP_UNKNOWN_ACC0 0x0000acc0 + #define REG_A6XX_SP_UNKNOWN_AE00 0x0000ae00 #define REG_A6XX_SP_UNKNOWN_AE03 0x0000ae03 @@ -4700,11 +4733,34 @@ static inline uint32_t A6XX_SP_PS_2D_SRC_INFO_COLOR_SWAP(enum a3xx_color_swap va return ((val) << A6XX_SP_PS_2D_SRC_INFO_COLOR_SWAP__SHIFT) & A6XX_SP_PS_2D_SRC_INFO_COLOR_SWAP__MASK; } #define A6XX_SP_PS_2D_SRC_INFO_FLAGS 0x00001000 +#define A6XX_SP_PS_2D_SRC_INFO_FILTER 0x00010000 + +#define REG_A6XX_SP_PS_2D_SRC_SIZE 0x0000b4c1 +#define A6XX_SP_PS_2D_SRC_SIZE_WIDTH__MASK 0x00007fff +#define A6XX_SP_PS_2D_SRC_SIZE_WIDTH__SHIFT 0 +static inline uint32_t A6XX_SP_PS_2D_SRC_SIZE_WIDTH(uint32_t val) +{ + return ((val) << A6XX_SP_PS_2D_SRC_SIZE_WIDTH__SHIFT) & A6XX_SP_PS_2D_SRC_SIZE_WIDTH__MASK; +} +#define A6XX_SP_PS_2D_SRC_SIZE_HEIGHT__MASK 0x3fff8000 +#define A6XX_SP_PS_2D_SRC_SIZE_HEIGHT__SHIFT 15 +static inline uint32_t A6XX_SP_PS_2D_SRC_SIZE_HEIGHT(uint32_t val) +{ + return ((val) << A6XX_SP_PS_2D_SRC_SIZE_HEIGHT__SHIFT) & A6XX_SP_PS_2D_SRC_SIZE_HEIGHT__MASK; +} #define REG_A6XX_SP_PS_2D_SRC_LO 0x0000b4c2 #define REG_A6XX_SP_PS_2D_SRC_HI 0x0000b4c3 +#define REG_A6XX_SP_PS_2D_SRC_PITCH 0x0000b4c4 +#define A6XX_SP_PS_2D_SRC_PITCH_PITCH__MASK 0x01fffe00 +#define A6XX_SP_PS_2D_SRC_PITCH_PITCH__SHIFT 9 +static inline uint32_t A6XX_SP_PS_2D_SRC_PITCH_PITCH(uint32_t val) +{ + return ((val >> 6) << A6XX_SP_PS_2D_SRC_PITCH_PITCH__SHIFT) & A6XX_SP_PS_2D_SRC_PITCH_PITCH__MASK; +} + #define REG_A6XX_SP_PS_2D_SRC_FLAGS_LO 0x0000b4ca #define REG_A6XX_SP_PS_2D_SRC_FLAGS_HI 0x0000b4cb @@ -5033,6 +5089,12 @@ static inline uint32_t A6XX_TEX_CONST_0_MIPLVLS(uint32_t val) { return ((val) << A6XX_TEX_CONST_0_MIPLVLS__SHIFT) & A6XX_TEX_CONST_0_MIPLVLS__MASK; } +#define A6XX_TEX_CONST_0_SAMPLES__MASK 0x00300000 +#define A6XX_TEX_CONST_0_SAMPLES__SHIFT 20 +static inline uint32_t A6XX_TEX_CONST_0_SAMPLES(enum a3xx_msaa_samples val) +{ + return ((val) << A6XX_TEX_CONST_0_SAMPLES__SHIFT) & A6XX_TEX_CONST_0_SAMPLES__MASK; +} #define A6XX_TEX_CONST_0_FMT__MASK 0x3fc00000 #define A6XX_TEX_CONST_0_FMT__SHIFT 22 static inline uint32_t A6XX_TEX_CONST_0_FMT(enum a6xx_tex_fmt val) @@ -5365,5 +5427,9 @@ static inline uint32_t A6XX_CX_DBGC_CFG_DBGBUS_BYTEL_1_BYTEL15(uint32_t val) #define REG_A6XX_CX_DBGC_CFG_DBGBUS_TRACE_BUF2 0x00000030 +#define REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_0 0x00000001 + +#define REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_1 0x00000002 + #endif /* A6XX_XML */ diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index d4e98e5876bc..c58e953fefa3 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -51,10 +51,31 @@ static irqreturn_t a6xx_hfi_irq(int irq, void *data) return IRQ_HANDLED; } +bool a6xx_gmu_sptprac_is_on(struct a6xx_gmu *gmu) +{ + u32 val; + + /* This can be called from gpu state code so make sure GMU is valid */ + if (IS_ERR_OR_NULL(gmu->mmio)) + return false; + + val = gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS); + + return !(val & + (A6XX_GMU_SPTPRAC_PWR_CLK_STATUS_SPTPRAC_GDSC_POWER_OFF | + A6XX_GMU_SPTPRAC_PWR_CLK_STATUS_SP_CLOCK_OFF)); +} + /* Check to see if the GX rail is still powered */ -static bool a6xx_gmu_gx_is_on(struct a6xx_gmu *gmu) +bool a6xx_gmu_gx_is_on(struct a6xx_gmu *gmu) { - u32 val = gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS); + u32 val; + + /* This can be called from gpu state code so make sure GMU is valid */ + if (IS_ERR_OR_NULL(gmu->mmio)) + return false; + + val = gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS); return !(val & (A6XX_GMU_SPTPRAC_PWR_CLK_STATUS_GX_HM_GDSC_POWER_OFF | @@ -153,7 +174,7 @@ static int a6xx_gmu_start(struct a6xx_gmu *gmu) val == 0xbabeface, 100, 10000); if (ret) - dev_err(gmu->dev, "GMU firmware initialization timed out\n"); + DRM_DEV_ERROR(gmu->dev, "GMU firmware initialization timed out\n"); return ret; } @@ -168,7 +189,7 @@ static int a6xx_gmu_hfi_start(struct a6xx_gmu *gmu) ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_HFI_CTRL_STATUS, val, val & 1, 100, 10000); if (ret) - dev_err(gmu->dev, "Unable to start the HFI queues\n"); + DRM_DEV_ERROR(gmu->dev, "Unable to start the HFI queues\n"); return ret; } @@ -209,7 +230,7 @@ int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state) val & (1 << ack), 100, 10000); if (ret) - dev_err(gmu->dev, + DRM_DEV_ERROR(gmu->dev, "Timeout waiting for GMU OOB set %s: 0x%x\n", name, gmu_read(gmu, REG_A6XX_GMU_GMU2HOST_INTR_INFO)); @@ -251,7 +272,7 @@ static int a6xx_sptprac_enable(struct a6xx_gmu *gmu) (val & 0x38) == 0x28, 1, 100); if (ret) { - dev_err(gmu->dev, "Unable to power on SPTPRAC: 0x%x\n", + DRM_DEV_ERROR(gmu->dev, "Unable to power on SPTPRAC: 0x%x\n", gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS)); } @@ -273,7 +294,7 @@ static void a6xx_sptprac_disable(struct a6xx_gmu *gmu) (val & 0x04), 100, 10000); if (ret) - dev_err(gmu->dev, "failed to power off SPTPRAC: 0x%x\n", + DRM_DEV_ERROR(gmu->dev, "failed to power off SPTPRAC: 0x%x\n", gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS)); } @@ -317,7 +338,7 @@ static int a6xx_gmu_notify_slumber(struct a6xx_gmu *gmu) /* Check to see if the GMU really did slumber */ if (gmu_read(gmu, REG_A6XX_GPU_GMU_CX_GMU_RPMH_POWER_STATE) != 0x0f) { - dev_err(gmu->dev, "The GMU did not go into slumber\n"); + DRM_DEV_ERROR(gmu->dev, "The GMU did not go into slumber\n"); ret = -ETIMEDOUT; } } @@ -339,23 +360,27 @@ static int a6xx_rpmh_start(struct a6xx_gmu *gmu) ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_RSCC_CONTROL_ACK, val, val & (1 << 1), 100, 10000); if (ret) { - dev_err(gmu->dev, "Unable to power on the GPU RSC\n"); + DRM_DEV_ERROR(gmu->dev, "Unable to power on the GPU RSC\n"); return ret; } ret = gmu_poll_timeout(gmu, REG_A6XX_RSCC_SEQ_BUSY_DRV0, val, !val, 100, 10000); - if (!ret) { - gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, 0); - - /* Re-enable the power counter */ - gmu_write(gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_ENABLE, 1); - return 0; + if (ret) { + DRM_DEV_ERROR(gmu->dev, "GPU RSC sequence stuck while waking up the GPU\n"); + return ret; } - dev_err(gmu->dev, "GPU RSC sequence stuck while waking up the GPU\n"); - return ret; + gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, 0); + + /* Set up CX GMU counter 0 to count busy ticks */ + gmu_write(gmu, REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_MASK, 0xff000000); + gmu_rmw(gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_SELECT_0, 0xff, 0x20); + + /* Enable the power counter */ + gmu_write(gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_ENABLE, 1); + return 0; } static void a6xx_rpmh_stop(struct a6xx_gmu *gmu) @@ -368,7 +393,7 @@ static void a6xx_rpmh_stop(struct a6xx_gmu *gmu) ret = gmu_poll_timeout(gmu, REG_A6XX_GPU_RSCC_RSC_STATUS0_DRV0, val, val & (1 << 16), 100, 10000); if (ret) - dev_err(gmu->dev, "Unable to power off the GPU RSC\n"); + DRM_DEV_ERROR(gmu->dev, "Unable to power off the GPU RSC\n"); gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, 0); } @@ -520,7 +545,7 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state) /* Sanity check the size of the firmware that was loaded */ if (adreno_gpu->fw[ADRENO_FW_GMU]->size > 0x8000) { - dev_err(gmu->dev, + DRM_DEV_ERROR(gmu->dev, "GMU firmware is bigger than the available region\n"); return -EINVAL; } @@ -764,7 +789,7 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu) */ if (ret) - dev_err(gmu->dev, + DRM_DEV_ERROR(gmu->dev, "Unable to slumber GMU: status = 0%x/0%x\n", gmu_read(gmu, REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS), @@ -843,7 +868,7 @@ static struct a6xx_gmu_bo *a6xx_gmu_memory_alloc(struct a6xx_gmu *gmu, IOMMU_READ | IOMMU_WRITE); if (ret) { - dev_err(gmu->dev, "Unable to map GMU buffer object\n"); + DRM_DEV_ERROR(gmu->dev, "Unable to map GMU buffer object\n"); for (i = i - 1 ; i >= 0; i--) iommu_unmap(gmu->domain, @@ -969,12 +994,12 @@ static int a6xx_gmu_rpmh_arc_votes_init(struct device *dev, u32 *votes, } if (j == pri_count) { - dev_err(dev, + DRM_DEV_ERROR(dev, "Level %u not found in in the RPMh list\n", level); - dev_err(dev, "Available levels:\n"); + DRM_DEV_ERROR(dev, "Available levels:\n"); for (j = 0; j < pri_count; j++) - dev_err(dev, " %u\n", pri[j]); + DRM_DEV_ERROR(dev, " %u\n", pri[j]); return -EINVAL; } @@ -1081,7 +1106,7 @@ static int a6xx_gmu_pwrlevels_probe(struct a6xx_gmu *gmu) */ ret = dev_pm_opp_of_add_table(gmu->dev); if (ret) { - dev_err(gmu->dev, "Unable to set the OPP table for the GMU\n"); + DRM_DEV_ERROR(gmu->dev, "Unable to set the OPP table for the GMU\n"); return ret; } @@ -1122,13 +1147,13 @@ static void __iomem *a6xx_gmu_get_mmio(struct platform_device *pdev, IORESOURCE_MEM, name); if (!res) { - dev_err(&pdev->dev, "Unable to find the %s registers\n", name); + DRM_DEV_ERROR(&pdev->dev, "Unable to find the %s registers\n", name); return ERR_PTR(-EINVAL); } ret = devm_ioremap(&pdev->dev, res->start, resource_size(res)); if (!ret) { - dev_err(&pdev->dev, "Unable to map the %s registers\n", name); + DRM_DEV_ERROR(&pdev->dev, "Unable to map the %s registers\n", name); return ERR_PTR(-EINVAL); } @@ -1145,7 +1170,7 @@ static int a6xx_gmu_get_irq(struct a6xx_gmu *gmu, struct platform_device *pdev, ret = devm_request_irq(&pdev->dev, irq, handler, IRQF_TRIGGER_HIGH, name, gmu); if (ret) { - dev_err(&pdev->dev, "Unable to get interrupt %s\n", name); + DRM_DEV_ERROR(&pdev->dev, "Unable to get interrupt %s\n", name); return ret; } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h index 35f765afae45..c721d9165d8e 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h @@ -164,4 +164,7 @@ void a6xx_hfi_init(struct a6xx_gmu *gmu); int a6xx_hfi_start(struct a6xx_gmu *gmu, int boot_state); void a6xx_hfi_stop(struct a6xx_gmu *gmu); +bool a6xx_gmu_gx_is_on(struct a6xx_gmu *gmu); +bool a6xx_gmu_sptprac_is_on(struct a6xx_gmu *gmu); + #endif diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h index db56f263ed77..1cc1c135236b 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h @@ -10,13 +10,13 @@ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: - /home/robclark/src/envytools/rnndb/adreno.xml ( 501 bytes, from 2018-07-03 19:37:13) - /home/robclark/src/envytools/rnndb/freedreno_copyright.xml ( 1572 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml ( 36805 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml ( 13634 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml ( 42585 bytes, from 2018-10-04 19:06:37) +- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml ( 42463 bytes, from 2018-11-19 13:44:03) +- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml ( 14201 bytes, from 2018-12-02 17:29:54) +- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml ( 43052 bytes, from 2018-12-02 17:29:54) - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml ( 83840 bytes, from 2018-07-03 19:37:13) - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml ( 112086 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml ( 147240 bytes, from 2018-10-04 19:06:37) -- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml ( 139581 bytes, from 2018-10-04 19:06:42) +- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml ( 147240 bytes, from 2018-12-02 17:29:54) +- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml ( 140790 bytes, from 2018-12-02 17:29:54) - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml ( 10431 bytes, from 2018-09-14 13:03:07) - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml ( 1773 bytes, from 2018-07-03 19:37:13) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 631257c297fd..fefe773c989e 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -4,6 +4,7 @@ #include "msm_gem.h" #include "msm_mmu.h" +#include "msm_gpu_trace.h" #include "a6xx_gpu.h" #include "a6xx_gmu.xml.h" @@ -67,13 +68,36 @@ static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring) gpu_write(gpu, REG_A6XX_CP_RB_WPTR, wptr); } +static void get_stats_counter(struct msm_ringbuffer *ring, u32 counter, + u64 iova) +{ + OUT_PKT7(ring, CP_REG_TO_MEM, 3); + OUT_RING(ring, counter | (1 << 30) | (2 << 18)); + OUT_RING(ring, lower_32_bits(iova)); + OUT_RING(ring, upper_32_bits(iova)); +} + static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, struct msm_file_private *ctx) { + unsigned int index = submit->seqno % MSM_GPU_SUBMIT_STATS_COUNT; struct msm_drm_private *priv = gpu->dev->dev_private; + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); struct msm_ringbuffer *ring = submit->ring; unsigned int i; + get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP_0_LO, + rbmemptr_stats(ring, index, cpcycles_start)); + + /* + * For PM4 the GMU register offsets are calculated from the base of the + * GPU registers so we need to add 0x1a800 to the register value on A630 + * to get the right value from PM4. + */ + get_stats_counter(ring, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L + 0x1a800, + rbmemptr_stats(ring, index, alwayson_start)); + /* Invalidate CCU depth and color */ OUT_PKT7(ring, CP_EVENT_WRITE, 1); OUT_RING(ring, PC_CCU_INVALIDATE_DEPTH); @@ -98,6 +122,11 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, } } + get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP_0_LO, + rbmemptr_stats(ring, index, cpcycles_end)); + get_stats_counter(ring, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L + 0x1a800, + rbmemptr_stats(ring, index, alwayson_end)); + /* Write the fence to the scratch register */ OUT_PKT4(ring, REG_A6XX_CP_SCRATCH_REG(2), 1); OUT_RING(ring, submit->seqno); @@ -112,6 +141,10 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence))); OUT_RING(ring, submit->seqno); + trace_msm_gpu_submit_flush(submit, + gmu_read64(&a6xx_gpu->gmu, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L, + REG_A6XX_GMU_ALWAYS_ON_COUNTER_H)); + a6xx_flush(gpu, ring); } @@ -300,6 +333,8 @@ static int a6xx_ucode_init(struct msm_gpu *gpu) return ret; } + + msm_gem_object_set_name(a6xx_gpu->sqe_bo, "sqefw"); } gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE_LO, @@ -387,14 +422,6 @@ static int a6xx_hw_init(struct msm_gpu *gpu) /* Select CP0 to always count cycles */ gpu_write(gpu, REG_A6XX_CP_PERFCTR_CP_SEL_0, PERF_CP_ALWAYS_COUNT); - /* FIXME: not sure if this should live here or in a6xx_gmu.c */ - gmu_write(&a6xx_gpu->gmu, REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_MASK, - 0xff000000); - gmu_rmw(&a6xx_gpu->gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_SELECT_0, - 0xff, 0x20); - gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_ENABLE, - 0x01); - gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL, 2 << 1); gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, 2 << 1); gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, 2 << 1); @@ -481,7 +508,7 @@ out: static void a6xx_dump(struct msm_gpu *gpu) { - dev_info(&gpu->pdev->dev, "status: %08x\n", + DRM_DEV_INFO(&gpu->pdev->dev, "status: %08x\n", gpu_read(gpu, REG_A6XX_RBBM_STATUS)); adreno_dump(gpu); } @@ -498,7 +525,7 @@ static void a6xx_recover(struct msm_gpu *gpu) adreno_dump_info(gpu); for (i = 0; i < 8; i++) - dev_info(&gpu->pdev->dev, "CP_SCRATCH_REG%d: %u\n", i, + DRM_DEV_INFO(&gpu->pdev->dev, "CP_SCRATCH_REG%d: %u\n", i, gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(i))); if (hang_debug) @@ -645,33 +672,6 @@ static const u32 a6xx_register_offsets[REG_ADRENO_REGISTER_MAX] = { REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_A6XX_CP_RB_CNTL), }; -static const u32 a6xx_registers[] = { - 0x0000, 0x0002, 0x0010, 0x0010, 0x0012, 0x0012, 0x0018, 0x001b, - 0x001e, 0x0032, 0x0038, 0x003c, 0x0042, 0x0042, 0x0044, 0x0044, - 0x0047, 0x0047, 0x0056, 0x0056, 0x00ad, 0x00ae, 0x00b0, 0x00fb, - 0x0100, 0x011d, 0x0200, 0x020d, 0x0210, 0x0213, 0x0218, 0x023d, - 0x0400, 0x04f9, 0x0500, 0x0500, 0x0505, 0x050b, 0x050e, 0x0511, - 0x0533, 0x0533, 0x0540, 0x0555, 0x0800, 0x0808, 0x0810, 0x0813, - 0x0820, 0x0821, 0x0823, 0x0827, 0x0830, 0x0833, 0x0840, 0x0843, - 0x084f, 0x086f, 0x0880, 0x088a, 0x08a0, 0x08ab, 0x08c0, 0x08c4, - 0x08d0, 0x08dd, 0x08f0, 0x08f3, 0x0900, 0x0903, 0x0908, 0x0911, - 0x0928, 0x093e, 0x0942, 0x094d, 0x0980, 0x0984, 0x098d, 0x0996, - 0x0998, 0x099e, 0x09a0, 0x09a6, 0x09a8, 0x09ae, 0x09b0, 0x09b1, - 0x09c2, 0x09c8, 0x0a00, 0x0a03, 0x0c00, 0x0c04, 0x0c06, 0x0c06, - 0x0c10, 0x0cd9, 0x0e00, 0x0e0e, 0x0e10, 0x0e13, 0x0e17, 0x0e19, - 0x0e1c, 0x0e2b, 0x0e30, 0x0e32, 0x0e38, 0x0e39, 0x8600, 0x8601, - 0x8610, 0x861b, 0x8620, 0x8620, 0x8628, 0x862b, 0x8630, 0x8637, - 0x8e01, 0x8e01, 0x8e04, 0x8e05, 0x8e07, 0x8e08, 0x8e0c, 0x8e0c, - 0x8e10, 0x8e1c, 0x8e20, 0x8e25, 0x8e28, 0x8e28, 0x8e2c, 0x8e2f, - 0x8e3b, 0x8e3e, 0x8e40, 0x8e43, 0x8e50, 0x8e5e, 0x8e70, 0x8e77, - 0x9600, 0x9604, 0x9624, 0x9637, 0x9e00, 0x9e01, 0x9e03, 0x9e0e, - 0x9e11, 0x9e16, 0x9e19, 0x9e19, 0x9e1c, 0x9e1c, 0x9e20, 0x9e23, - 0x9e30, 0x9e31, 0x9e34, 0x9e34, 0x9e70, 0x9e72, 0x9e78, 0x9e79, - 0x9e80, 0x9fff, 0xa600, 0xa601, 0xa603, 0xa603, 0xa60a, 0xa60a, - 0xa610, 0xa617, 0xa630, 0xa630, - ~0 -}; - static int a6xx_pm_resume(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); @@ -724,14 +724,6 @@ static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) return 0; } -#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) -static void a6xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state, - struct drm_printer *p) -{ - adreno_show(gpu, state, p); -} -#endif - static struct msm_ringbuffer *a6xx_active_ring(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); @@ -746,8 +738,7 @@ static void a6xx_destroy(struct msm_gpu *gpu) struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); if (a6xx_gpu->sqe_bo) { - if (a6xx_gpu->sqe_iova) - msm_gem_put_iova(a6xx_gpu->sqe_bo, gpu->aspace); + msm_gem_unpin_iova(a6xx_gpu->sqe_bo, gpu->aspace); drm_gem_object_put_unlocked(a6xx_gpu->sqe_bo); } @@ -796,6 +787,8 @@ static const struct adreno_gpu_funcs funcs = { .gpu_busy = a6xx_gpu_busy, .gpu_get_freq = a6xx_gmu_get_freq, .gpu_set_freq = a6xx_gmu_set_freq, + .gpu_state_get = a6xx_gpu_state_get, + .gpu_state_put = a6xx_gpu_state_put, }, .get_timestamp = a6xx_get_timestamp, }; @@ -817,7 +810,7 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) adreno_gpu = &a6xx_gpu->base; gpu = &adreno_gpu->base; - adreno_gpu->registers = a6xx_registers; + adreno_gpu->registers = NULL; adreno_gpu->reg_offsets = a6xx_register_offsets; ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h index 4127dcebc202..528a4cfe07cd 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h @@ -56,6 +56,14 @@ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state); int a6xx_gmu_probe(struct a6xx_gpu *a6xx_gpu, struct device_node *node); void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu); + void a6xx_gmu_set_freq(struct msm_gpu *gpu, unsigned long freq); unsigned long a6xx_gmu_get_freq(struct msm_gpu *gpu); + +void a6xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state, + struct drm_printer *p); + +struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu); +int a6xx_gpu_state_put(struct msm_gpu_state *state); + #endif /* __A6XX_GPU_H__ */ diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c new file mode 100644 index 000000000000..e686331fa089 --- /dev/null +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -0,0 +1,1165 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 The Linux Foundation. All rights reserved. */ + +#include <linux/ascii85.h> +#include "msm_gem.h" +#include "a6xx_gpu.h" +#include "a6xx_gmu.h" +#include "a6xx_gpu_state.h" +#include "a6xx_gmu.xml.h" + +struct a6xx_gpu_state_obj { + const void *handle; + u32 *data; +}; + +struct a6xx_gpu_state { + struct msm_gpu_state base; + + struct a6xx_gpu_state_obj *gmu_registers; + int nr_gmu_registers; + + struct a6xx_gpu_state_obj *registers; + int nr_registers; + + struct a6xx_gpu_state_obj *shaders; + int nr_shaders; + + struct a6xx_gpu_state_obj *clusters; + int nr_clusters; + + struct a6xx_gpu_state_obj *dbgahb_clusters; + int nr_dbgahb_clusters; + + struct a6xx_gpu_state_obj *indexed_regs; + int nr_indexed_regs; + + struct a6xx_gpu_state_obj *debugbus; + int nr_debugbus; + + struct a6xx_gpu_state_obj *vbif_debugbus; + + struct a6xx_gpu_state_obj *cx_debugbus; + int nr_cx_debugbus; + + struct list_head objs; +}; + +static inline int CRASHDUMP_WRITE(u64 *in, u32 reg, u32 val) +{ + in[0] = val; + in[1] = (((u64) reg) << 44 | (1 << 21) | 1); + + return 2; +} + +static inline int CRASHDUMP_READ(u64 *in, u32 reg, u32 dwords, u64 target) +{ + in[0] = target; + in[1] = (((u64) reg) << 44 | dwords); + + return 2; +} + +static inline int CRASHDUMP_FINI(u64 *in) +{ + in[0] = 0; + in[1] = 0; + + return 2; +} + +struct a6xx_crashdumper { + void *ptr; + struct drm_gem_object *bo; + u64 iova; +}; + +struct a6xx_state_memobj { + struct list_head node; + unsigned long long data[]; +}; + +void *state_kcalloc(struct a6xx_gpu_state *a6xx_state, int nr, size_t objsize) +{ + struct a6xx_state_memobj *obj = + kzalloc((nr * objsize) + sizeof(*obj), GFP_KERNEL); + + if (!obj) + return NULL; + + list_add_tail(&obj->node, &a6xx_state->objs); + return &obj->data; +} + +void *state_kmemdup(struct a6xx_gpu_state *a6xx_state, void *src, + size_t size) +{ + void *dst = state_kcalloc(a6xx_state, 1, size); + + if (dst) + memcpy(dst, src, size); + return dst; +} + +/* + * Allocate 1MB for the crashdumper scratch region - 8k for the script and + * the rest for the data + */ +#define A6XX_CD_DATA_OFFSET 8192 +#define A6XX_CD_DATA_SIZE (SZ_1M - 8192) + +static int a6xx_crashdumper_init(struct msm_gpu *gpu, + struct a6xx_crashdumper *dumper) +{ + dumper->ptr = msm_gem_kernel_new_locked(gpu->dev, + SZ_1M, MSM_BO_UNCACHED, gpu->aspace, + &dumper->bo, &dumper->iova); + + if (!IS_ERR(dumper->ptr)) + msm_gem_object_set_name(dumper->bo, "crashdump"); + + return PTR_ERR_OR_ZERO(dumper->ptr); +} + +static int a6xx_crashdumper_run(struct msm_gpu *gpu, + struct a6xx_crashdumper *dumper) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + u32 val; + int ret; + + if (IS_ERR_OR_NULL(dumper->ptr)) + return -EINVAL; + + if (!a6xx_gmu_sptprac_is_on(&a6xx_gpu->gmu)) + return -EINVAL; + + /* Make sure all pending memory writes are posted */ + wmb(); + + gpu_write64(gpu, REG_A6XX_CP_CRASH_SCRIPT_BASE_LO, + REG_A6XX_CP_CRASH_SCRIPT_BASE_HI, dumper->iova); + + gpu_write(gpu, REG_A6XX_CP_CRASH_DUMP_CNTL, 1); + + ret = gpu_poll_timeout(gpu, REG_A6XX_CP_CRASH_DUMP_STATUS, val, + val & 0x02, 100, 10000); + + gpu_write(gpu, REG_A6XX_CP_CRASH_DUMP_CNTL, 0); + + return ret; +} + +/* read a value from the GX debug bus */ +static int debugbus_read(struct msm_gpu *gpu, u32 block, u32 offset, + u32 *data) +{ + u32 reg = A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) | + A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block); + + gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_A, reg); + gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_B, reg); + gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_C, reg); + gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_D, reg); + + /* Wait 1 us to make sure the data is flowing */ + udelay(1); + + data[0] = gpu_read(gpu, REG_A6XX_DBGC_CFG_DBGBUS_TRACE_BUF2); + data[1] = gpu_read(gpu, REG_A6XX_DBGC_CFG_DBGBUS_TRACE_BUF1); + + return 2; +} + +#define cxdbg_write(ptr, offset, val) \ + msm_writel((val), (ptr) + ((offset) << 2)) + +#define cxdbg_read(ptr, offset) \ + msm_readl((ptr) + ((offset) << 2)) + +/* read a value from the CX debug bus */ +static int cx_debugbus_read(void *__iomem cxdbg, u32 block, u32 offset, + u32 *data) +{ + u32 reg = A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) | + A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block); + + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_A, reg); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_B, reg); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_C, reg); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_D, reg); + + /* Wait 1 us to make sure the data is flowing */ + udelay(1); + + data[0] = cxdbg_read(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_TRACE_BUF2); + data[1] = cxdbg_read(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_TRACE_BUF1); + + return 2; +} + +/* Read a chunk of data from the VBIF debug bus */ +static int vbif_debugbus_read(struct msm_gpu *gpu, u32 ctrl0, u32 ctrl1, + u32 reg, int count, u32 *data) +{ + int i; + + gpu_write(gpu, ctrl0, reg); + + for (i = 0; i < count; i++) { + gpu_write(gpu, ctrl1, i); + data[i] = gpu_read(gpu, REG_A6XX_VBIF_TEST_BUS_OUT); + } + + return count; +} + +#define AXI_ARB_BLOCKS 2 +#define XIN_AXI_BLOCKS 5 +#define XIN_CORE_BLOCKS 4 + +#define VBIF_DEBUGBUS_BLOCK_SIZE \ + ((16 * AXI_ARB_BLOCKS) + \ + (18 * XIN_AXI_BLOCKS) + \ + (12 * XIN_CORE_BLOCKS)) + +static void a6xx_get_vbif_debugbus_block(struct msm_gpu *gpu, + struct a6xx_gpu_state *a6xx_state, + struct a6xx_gpu_state_obj *obj) +{ + u32 clk, *ptr; + int i; + + obj->data = state_kcalloc(a6xx_state, VBIF_DEBUGBUS_BLOCK_SIZE, + sizeof(u32)); + if (!obj->data) + return; + + obj->handle = NULL; + + /* Get the current clock setting */ + clk = gpu_read(gpu, REG_A6XX_VBIF_CLKON); + + /* Force on the bus so we can read it */ + gpu_write(gpu, REG_A6XX_VBIF_CLKON, + clk | A6XX_VBIF_CLKON_FORCE_ON_TESTBUS); + + /* We will read from BUS2 first, so disable BUS1 */ + gpu_write(gpu, REG_A6XX_VBIF_TEST_BUS1_CTRL0, 0); + + /* Enable the VBIF bus for reading */ + gpu_write(gpu, REG_A6XX_VBIF_TEST_BUS_OUT_CTRL, 1); + + ptr = obj->data; + + for (i = 0; i < AXI_ARB_BLOCKS; i++) + ptr += vbif_debugbus_read(gpu, + REG_A6XX_VBIF_TEST_BUS2_CTRL0, + REG_A6XX_VBIF_TEST_BUS2_CTRL1, + 1 << (i + 16), 16, ptr); + + for (i = 0; i < XIN_AXI_BLOCKS; i++) + ptr += vbif_debugbus_read(gpu, + REG_A6XX_VBIF_TEST_BUS2_CTRL0, + REG_A6XX_VBIF_TEST_BUS2_CTRL1, + 1 << i, 18, ptr); + + /* Stop BUS2 so we can turn on BUS1 */ + gpu_write(gpu, REG_A6XX_VBIF_TEST_BUS2_CTRL0, 0); + + for (i = 0; i < XIN_CORE_BLOCKS; i++) + ptr += vbif_debugbus_read(gpu, + REG_A6XX_VBIF_TEST_BUS1_CTRL0, + REG_A6XX_VBIF_TEST_BUS1_CTRL1, + 1 << i, 12, ptr); + + /* Restore the VBIF clock setting */ + gpu_write(gpu, REG_A6XX_VBIF_CLKON, clk); +} + +static void a6xx_get_debugbus_block(struct msm_gpu *gpu, + struct a6xx_gpu_state *a6xx_state, + const struct a6xx_debugbus_block *block, + struct a6xx_gpu_state_obj *obj) +{ + int i; + u32 *ptr; + + obj->data = state_kcalloc(a6xx_state, block->count, sizeof(u64)); + if (!obj->data) + return; + + obj->handle = block; + + for (ptr = obj->data, i = 0; i < block->count; i++) + ptr += debugbus_read(gpu, block->id, i, ptr); +} + +static void a6xx_get_cx_debugbus_block(void __iomem *cxdbg, + struct a6xx_gpu_state *a6xx_state, + const struct a6xx_debugbus_block *block, + struct a6xx_gpu_state_obj *obj) +{ + int i; + u32 *ptr; + + obj->data = state_kcalloc(a6xx_state, block->count, sizeof(u64)); + if (!obj->data) + return; + + obj->handle = block; + + for (ptr = obj->data, i = 0; i < block->count; i++) + ptr += cx_debugbus_read(cxdbg, block->id, i, ptr); +} + +static void a6xx_get_debugbus(struct msm_gpu *gpu, + struct a6xx_gpu_state *a6xx_state) +{ + struct resource *res; + void __iomem *cxdbg = NULL; + + /* Set up the GX debug bus */ + + gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_CNTLT, + A6XX_DBGC_CFG_DBGBUS_CNTLT_SEGT(0xf)); + + gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_CNTLM, + A6XX_DBGC_CFG_DBGBUS_CNTLM_ENABLE(0xf)); + + gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_0, 0); + gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_1, 0); + gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_2, 0); + gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_3, 0); + + gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_BYTEL_0, 0x76543210); + gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_BYTEL_1, 0xFEDCBA98); + + gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_0, 0); + gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_1, 0); + gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_2, 0); + gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_3, 0); + + /* Set up the CX debug bus - it lives elsewhere in the system so do a + * temporary ioremap for the registers + */ + res = platform_get_resource_byname(gpu->pdev, IORESOURCE_MEM, + "cx_dbgc"); + + if (res) + cxdbg = ioremap(res->start, resource_size(res)); + + if (cxdbg) { + cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_CNTLT, + A6XX_DBGC_CFG_DBGBUS_CNTLT_SEGT(0xf)); + + cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_CNTLM, + A6XX_DBGC_CFG_DBGBUS_CNTLM_ENABLE(0xf)); + + cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_0, 0); + cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_1, 0); + cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_2, 0); + cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_3, 0); + + cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_BYTEL_0, + 0x76543210); + cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_BYTEL_1, + 0xFEDCBA98); + + cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_0, 0); + cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_1, 0); + cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_2, 0); + cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_3, 0); + } + + a6xx_state->debugbus = state_kcalloc(a6xx_state, + ARRAY_SIZE(a6xx_debugbus_blocks), + sizeof(*a6xx_state->debugbus)); + + if (a6xx_state->debugbus) { + int i; + + for (i = 0; i < ARRAY_SIZE(a6xx_debugbus_blocks); i++) + a6xx_get_debugbus_block(gpu, + a6xx_state, + &a6xx_debugbus_blocks[i], + &a6xx_state->debugbus[i]); + + a6xx_state->nr_debugbus = ARRAY_SIZE(a6xx_debugbus_blocks); + } + + a6xx_state->vbif_debugbus = + state_kcalloc(a6xx_state, 1, + sizeof(*a6xx_state->vbif_debugbus)); + + if (a6xx_state->vbif_debugbus) + a6xx_get_vbif_debugbus_block(gpu, a6xx_state, + a6xx_state->vbif_debugbus); + + if (cxdbg) { + a6xx_state->cx_debugbus = + state_kcalloc(a6xx_state, + ARRAY_SIZE(a6xx_cx_debugbus_blocks), + sizeof(*a6xx_state->cx_debugbus)); + + if (a6xx_state->cx_debugbus) { + int i; + + for (i = 0; i < ARRAY_SIZE(a6xx_cx_debugbus_blocks); i++) + a6xx_get_cx_debugbus_block(cxdbg, + a6xx_state, + &a6xx_cx_debugbus_blocks[i], + &a6xx_state->cx_debugbus[i]); + + a6xx_state->nr_cx_debugbus = + ARRAY_SIZE(a6xx_cx_debugbus_blocks); + } + + iounmap(cxdbg); + } +} + +#define RANGE(reg, a) ((reg)[(a) + 1] - (reg)[(a)] + 1) + +/* Read a data cluster from behind the AHB aperture */ +static void a6xx_get_dbgahb_cluster(struct msm_gpu *gpu, + struct a6xx_gpu_state *a6xx_state, + const struct a6xx_dbgahb_cluster *dbgahb, + struct a6xx_gpu_state_obj *obj, + struct a6xx_crashdumper *dumper) +{ + u64 *in = dumper->ptr; + u64 out = dumper->iova + A6XX_CD_DATA_OFFSET; + size_t datasize; + int i, regcount = 0; + + for (i = 0; i < A6XX_NUM_CONTEXTS; i++) { + int j; + + in += CRASHDUMP_WRITE(in, REG_A6XX_HLSQ_DBG_READ_SEL, + (dbgahb->statetype + i * 2) << 8); + + for (j = 0; j < dbgahb->count; j += 2) { + int count = RANGE(dbgahb->registers, j); + u32 offset = REG_A6XX_HLSQ_DBG_AHB_READ_APERTURE + + dbgahb->registers[j] - (dbgahb->base >> 2); + + in += CRASHDUMP_READ(in, offset, count, out); + + out += count * sizeof(u32); + + if (i == 0) + regcount += count; + } + } + + CRASHDUMP_FINI(in); + + datasize = regcount * A6XX_NUM_CONTEXTS * sizeof(u32); + + if (WARN_ON(datasize > A6XX_CD_DATA_SIZE)) + return; + + if (a6xx_crashdumper_run(gpu, dumper)) + return; + + obj->handle = dbgahb; + obj->data = state_kmemdup(a6xx_state, dumper->ptr + A6XX_CD_DATA_OFFSET, + datasize); +} + +static void a6xx_get_dbgahb_clusters(struct msm_gpu *gpu, + struct a6xx_gpu_state *a6xx_state, + struct a6xx_crashdumper *dumper) +{ + int i; + + a6xx_state->dbgahb_clusters = state_kcalloc(a6xx_state, + ARRAY_SIZE(a6xx_dbgahb_clusters), + sizeof(*a6xx_state->dbgahb_clusters)); + + if (!a6xx_state->dbgahb_clusters) + return; + + a6xx_state->nr_dbgahb_clusters = ARRAY_SIZE(a6xx_dbgahb_clusters); + + for (i = 0; i < ARRAY_SIZE(a6xx_dbgahb_clusters); i++) + a6xx_get_dbgahb_cluster(gpu, a6xx_state, + &a6xx_dbgahb_clusters[i], + &a6xx_state->dbgahb_clusters[i], dumper); +} + +/* Read a data cluster from the CP aperture with the crashdumper */ +static void a6xx_get_cluster(struct msm_gpu *gpu, + struct a6xx_gpu_state *a6xx_state, + const struct a6xx_cluster *cluster, + struct a6xx_gpu_state_obj *obj, + struct a6xx_crashdumper *dumper) +{ + u64 *in = dumper->ptr; + u64 out = dumper->iova + A6XX_CD_DATA_OFFSET; + size_t datasize; + int i, regcount = 0; + + /* Some clusters need a selector register to be programmed too */ + if (cluster->sel_reg) + in += CRASHDUMP_WRITE(in, cluster->sel_reg, cluster->sel_val); + + for (i = 0; i < A6XX_NUM_CONTEXTS; i++) { + int j; + + in += CRASHDUMP_WRITE(in, REG_A6XX_CP_APERTURE_CNTL_CD, + (cluster->id << 8) | (i << 4) | i); + + for (j = 0; j < cluster->count; j += 2) { + int count = RANGE(cluster->registers, j); + + in += CRASHDUMP_READ(in, cluster->registers[j], + count, out); + + out += count * sizeof(u32); + + if (i == 0) + regcount += count; + } + } + + CRASHDUMP_FINI(in); + + datasize = regcount * A6XX_NUM_CONTEXTS * sizeof(u32); + + if (WARN_ON(datasize > A6XX_CD_DATA_SIZE)) + return; + + if (a6xx_crashdumper_run(gpu, dumper)) + return; + + obj->handle = cluster; + obj->data = state_kmemdup(a6xx_state, dumper->ptr + A6XX_CD_DATA_OFFSET, + datasize); +} + +static void a6xx_get_clusters(struct msm_gpu *gpu, + struct a6xx_gpu_state *a6xx_state, + struct a6xx_crashdumper *dumper) +{ + int i; + + a6xx_state->clusters = state_kcalloc(a6xx_state, + ARRAY_SIZE(a6xx_clusters), sizeof(*a6xx_state->clusters)); + + if (!a6xx_state->clusters) + return; + + a6xx_state->nr_clusters = ARRAY_SIZE(a6xx_clusters); + + for (i = 0; i < ARRAY_SIZE(a6xx_clusters); i++) + a6xx_get_cluster(gpu, a6xx_state, &a6xx_clusters[i], + &a6xx_state->clusters[i], dumper); +} + +/* Read a shader / debug block from the HLSQ aperture with the crashdumper */ +static void a6xx_get_shader_block(struct msm_gpu *gpu, + struct a6xx_gpu_state *a6xx_state, + const struct a6xx_shader_block *block, + struct a6xx_gpu_state_obj *obj, + struct a6xx_crashdumper *dumper) +{ + u64 *in = dumper->ptr; + size_t datasize = block->size * A6XX_NUM_SHADER_BANKS * sizeof(u32); + int i; + + if (WARN_ON(datasize > A6XX_CD_DATA_SIZE)) + return; + + for (i = 0; i < A6XX_NUM_SHADER_BANKS; i++) { + in += CRASHDUMP_WRITE(in, REG_A6XX_HLSQ_DBG_READ_SEL, + (block->type << 8) | i); + + in += CRASHDUMP_READ(in, REG_A6XX_HLSQ_DBG_AHB_READ_APERTURE, + block->size, dumper->iova + A6XX_CD_DATA_OFFSET); + } + + CRASHDUMP_FINI(in); + + if (a6xx_crashdumper_run(gpu, dumper)) + return; + + obj->handle = block; + obj->data = state_kmemdup(a6xx_state, dumper->ptr + A6XX_CD_DATA_OFFSET, + datasize); +} + +static void a6xx_get_shaders(struct msm_gpu *gpu, + struct a6xx_gpu_state *a6xx_state, + struct a6xx_crashdumper *dumper) +{ + int i; + + a6xx_state->shaders = state_kcalloc(a6xx_state, + ARRAY_SIZE(a6xx_shader_blocks), sizeof(*a6xx_state->shaders)); + + if (!a6xx_state->shaders) + return; + + a6xx_state->nr_shaders = ARRAY_SIZE(a6xx_shader_blocks); + + for (i = 0; i < ARRAY_SIZE(a6xx_shader_blocks); i++) + a6xx_get_shader_block(gpu, a6xx_state, &a6xx_shader_blocks[i], + &a6xx_state->shaders[i], dumper); +} + +/* Read registers from behind the HLSQ aperture with the crashdumper */ +static void a6xx_get_crashdumper_hlsq_registers(struct msm_gpu *gpu, + struct a6xx_gpu_state *a6xx_state, + const struct a6xx_registers *regs, + struct a6xx_gpu_state_obj *obj, + struct a6xx_crashdumper *dumper) + +{ + u64 *in = dumper->ptr; + u64 out = dumper->iova + A6XX_CD_DATA_OFFSET; + int i, regcount = 0; + + in += CRASHDUMP_WRITE(in, REG_A6XX_HLSQ_DBG_READ_SEL, regs->val1); + + for (i = 0; i < regs->count; i += 2) { + u32 count = RANGE(regs->registers, i); + u32 offset = REG_A6XX_HLSQ_DBG_AHB_READ_APERTURE + + regs->registers[i] - (regs->val0 >> 2); + + in += CRASHDUMP_READ(in, offset, count, out); + + out += count * sizeof(u32); + regcount += count; + } + + CRASHDUMP_FINI(in); + + if (WARN_ON((regcount * sizeof(u32)) > A6XX_CD_DATA_SIZE)) + return; + + if (a6xx_crashdumper_run(gpu, dumper)) + return; + + obj->handle = regs; + obj->data = state_kmemdup(a6xx_state, dumper->ptr + A6XX_CD_DATA_OFFSET, + regcount * sizeof(u32)); +} + +/* Read a block of registers using the crashdumper */ +static void a6xx_get_crashdumper_registers(struct msm_gpu *gpu, + struct a6xx_gpu_state *a6xx_state, + const struct a6xx_registers *regs, + struct a6xx_gpu_state_obj *obj, + struct a6xx_crashdumper *dumper) + +{ + u64 *in = dumper->ptr; + u64 out = dumper->iova + A6XX_CD_DATA_OFFSET; + int i, regcount = 0; + + /* Some blocks might need to program a selector register first */ + if (regs->val0) + in += CRASHDUMP_WRITE(in, regs->val0, regs->val1); + + for (i = 0; i < regs->count; i += 2) { + u32 count = RANGE(regs->registers, i); + + in += CRASHDUMP_READ(in, regs->registers[i], count, out); + + out += count * sizeof(u32); + regcount += count; + } + + CRASHDUMP_FINI(in); + + if (WARN_ON((regcount * sizeof(u32)) > A6XX_CD_DATA_SIZE)) + return; + + if (a6xx_crashdumper_run(gpu, dumper)) + return; + + obj->handle = regs; + obj->data = state_kmemdup(a6xx_state, dumper->ptr + A6XX_CD_DATA_OFFSET, + regcount * sizeof(u32)); +} + +/* Read a block of registers via AHB */ +static void a6xx_get_ahb_gpu_registers(struct msm_gpu *gpu, + struct a6xx_gpu_state *a6xx_state, + const struct a6xx_registers *regs, + struct a6xx_gpu_state_obj *obj) +{ + int i, regcount = 0, index = 0; + + for (i = 0; i < regs->count; i += 2) + regcount += RANGE(regs->registers, i); + + obj->handle = (const void *) regs; + obj->data = state_kcalloc(a6xx_state, regcount, sizeof(u32)); + if (!obj->data) + return; + + for (i = 0; i < regs->count; i += 2) { + u32 count = RANGE(regs->registers, i); + int j; + + for (j = 0; j < count; j++) + obj->data[index++] = gpu_read(gpu, + regs->registers[i] + j); + } +} + +/* Read a block of GMU registers */ +static void _a6xx_get_gmu_registers(struct msm_gpu *gpu, + struct a6xx_gpu_state *a6xx_state, + const struct a6xx_registers *regs, + struct a6xx_gpu_state_obj *obj) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + struct a6xx_gmu *gmu = &a6xx_gpu->gmu; + int i, regcount = 0, index = 0; + + for (i = 0; i < regs->count; i += 2) + regcount += RANGE(regs->registers, i); + + obj->handle = (const void *) regs; + obj->data = state_kcalloc(a6xx_state, regcount, sizeof(u32)); + if (!obj->data) + return; + + for (i = 0; i < regs->count; i += 2) { + u32 count = RANGE(regs->registers, i); + int j; + + for (j = 0; j < count; j++) + obj->data[index++] = gmu_read(gmu, + regs->registers[i] + j); + } +} + +static void a6xx_get_gmu_registers(struct msm_gpu *gpu, + struct a6xx_gpu_state *a6xx_state) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + + a6xx_state->gmu_registers = state_kcalloc(a6xx_state, + 2, sizeof(*a6xx_state->gmu_registers)); + + if (!a6xx_state->gmu_registers) + return; + + a6xx_state->nr_gmu_registers = 2; + + /* Get the CX GMU registers from AHB */ + _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[0], + &a6xx_state->gmu_registers[0]); + + if (!a6xx_gmu_gx_is_on(&a6xx_gpu->gmu)) + return; + + /* Set the fence to ALLOW mode so we can access the registers */ + gpu_write(gpu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, 0); + + _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[1], + &a6xx_state->gmu_registers[1]); +} + +static void a6xx_get_registers(struct msm_gpu *gpu, + struct a6xx_gpu_state *a6xx_state, + struct a6xx_crashdumper *dumper) +{ + int i, count = ARRAY_SIZE(a6xx_ahb_reglist) + + ARRAY_SIZE(a6xx_reglist) + + ARRAY_SIZE(a6xx_hlsq_reglist); + int index = 0; + + a6xx_state->registers = state_kcalloc(a6xx_state, + count, sizeof(*a6xx_state->registers)); + + if (!a6xx_state->registers) + return; + + a6xx_state->nr_registers = count; + + for (i = 0; i < ARRAY_SIZE(a6xx_ahb_reglist); i++) + a6xx_get_ahb_gpu_registers(gpu, + a6xx_state, &a6xx_ahb_reglist[i], + &a6xx_state->registers[index++]); + + for (i = 0; i < ARRAY_SIZE(a6xx_reglist); i++) + a6xx_get_crashdumper_registers(gpu, + a6xx_state, &a6xx_reglist[i], + &a6xx_state->registers[index++], + dumper); + + for (i = 0; i < ARRAY_SIZE(a6xx_hlsq_reglist); i++) + a6xx_get_crashdumper_hlsq_registers(gpu, + a6xx_state, &a6xx_hlsq_reglist[i], + &a6xx_state->registers[index++], + dumper); +} + +/* Read a block of data from an indexed register pair */ +static void a6xx_get_indexed_regs(struct msm_gpu *gpu, + struct a6xx_gpu_state *a6xx_state, + const struct a6xx_indexed_registers *indexed, + struct a6xx_gpu_state_obj *obj) +{ + int i; + + obj->handle = (const void *) indexed; + obj->data = state_kcalloc(a6xx_state, indexed->count, sizeof(u32)); + if (!obj->data) + return; + + /* All the indexed banks start at address 0 */ + gpu_write(gpu, indexed->addr, 0); + + /* Read the data - each read increments the internal address by 1 */ + for (i = 0; i < indexed->count; i++) + obj->data[i] = gpu_read(gpu, indexed->data); +} + +static void a6xx_get_indexed_registers(struct msm_gpu *gpu, + struct a6xx_gpu_state *a6xx_state) +{ + u32 mempool_size; + int count = ARRAY_SIZE(a6xx_indexed_reglist) + 1; + int i; + + a6xx_state->indexed_regs = state_kcalloc(a6xx_state, count, + sizeof(a6xx_state->indexed_regs)); + if (!a6xx_state->indexed_regs) + return; + + for (i = 0; i < ARRAY_SIZE(a6xx_indexed_reglist); i++) + a6xx_get_indexed_regs(gpu, a6xx_state, &a6xx_indexed_reglist[i], + &a6xx_state->indexed_regs[i]); + + /* Set the CP mempool size to 0 to stabilize it while dumping */ + mempool_size = gpu_read(gpu, REG_A6XX_CP_MEM_POOL_SIZE); + gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, 0); + + /* Get the contents of the CP mempool */ + a6xx_get_indexed_regs(gpu, a6xx_state, &a6xx_cp_mempool_indexed, + &a6xx_state->indexed_regs[i]); + + /* + * Offset 0x2000 in the mempool is the size - copy the saved size over + * so the data is consistent + */ + a6xx_state->indexed_regs[i].data[0x2000] = mempool_size; + + /* Restore the size in the hardware */ + gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, mempool_size); + + a6xx_state->nr_indexed_regs = count; +} + +struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu) +{ + struct a6xx_crashdumper dumper = { 0 }; + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + struct a6xx_gpu_state *a6xx_state = kzalloc(sizeof(*a6xx_state), + GFP_KERNEL); + + if (!a6xx_state) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&a6xx_state->objs); + + /* Get the generic state from the adreno core */ + adreno_gpu_state_get(gpu, &a6xx_state->base); + + a6xx_get_gmu_registers(gpu, a6xx_state); + + /* If GX isn't on the rest of the data isn't going to be accessible */ + if (!a6xx_gmu_gx_is_on(&a6xx_gpu->gmu)) + return &a6xx_state->base; + + /* Get the banks of indexed registers */ + a6xx_get_indexed_registers(gpu, a6xx_state); + + /* Try to initialize the crashdumper */ + if (!a6xx_crashdumper_init(gpu, &dumper)) { + a6xx_get_registers(gpu, a6xx_state, &dumper); + a6xx_get_shaders(gpu, a6xx_state, &dumper); + a6xx_get_clusters(gpu, a6xx_state, &dumper); + a6xx_get_dbgahb_clusters(gpu, a6xx_state, &dumper); + + msm_gem_kernel_put(dumper.bo, gpu->aspace, true); + } + + a6xx_get_debugbus(gpu, a6xx_state); + + return &a6xx_state->base; +} + +void a6xx_gpu_state_destroy(struct kref *kref) +{ + struct a6xx_state_memobj *obj, *tmp; + struct msm_gpu_state *state = container_of(kref, + struct msm_gpu_state, ref); + struct a6xx_gpu_state *a6xx_state = container_of(state, + struct a6xx_gpu_state, base); + + list_for_each_entry_safe(obj, tmp, &a6xx_state->objs, node) + kfree(obj); + + adreno_gpu_state_destroy(state); + kfree(a6xx_state); +} + +int a6xx_gpu_state_put(struct msm_gpu_state *state) +{ + if (IS_ERR_OR_NULL(state)) + return 1; + + return kref_put(&state->ref, a6xx_gpu_state_destroy); +} + +static void a6xx_show_registers(const u32 *registers, u32 *data, size_t count, + struct drm_printer *p) +{ + int i, index = 0; + + if (!data) + return; + + for (i = 0; i < count; i += 2) { + u32 count = RANGE(registers, i); + u32 offset = registers[i]; + int j; + + for (j = 0; j < count; index++, offset++, j++) { + if (data[index] == 0xdeafbead) + continue; + + drm_printf(p, " - { offset: 0x%06x, value: 0x%08x }\n", + offset << 2, data[index]); + } + } +} + +static void print_ascii85(struct drm_printer *p, size_t len, u32 *data) +{ + char out[ASCII85_BUFSZ]; + long i, l, datalen = 0; + + for (i = 0; i < len >> 2; i++) { + if (data[i]) + datalen = (i + 1) << 2; + } + + if (datalen == 0) + return; + + drm_puts(p, " data: !!ascii85 |\n"); + drm_puts(p, " "); + + + l = ascii85_encode_len(datalen); + + for (i = 0; i < l; i++) + drm_puts(p, ascii85_encode(data[i], out)); + + drm_puts(p, "\n"); +} + +static void print_name(struct drm_printer *p, const char *fmt, const char *name) +{ + drm_puts(p, fmt); + drm_puts(p, name); + drm_puts(p, "\n"); +} + +static void a6xx_show_shader(struct a6xx_gpu_state_obj *obj, + struct drm_printer *p) +{ + const struct a6xx_shader_block *block = obj->handle; + int i; + + if (!obj->handle) + return; + + print_name(p, " - type: ", block->name); + + for (i = 0; i < A6XX_NUM_SHADER_BANKS; i++) { + drm_printf(p, " - bank: %d\n", i); + drm_printf(p, " size: %d\n", block->size); + + if (!obj->data) + continue; + + print_ascii85(p, block->size << 2, + obj->data + (block->size * i)); + } +} + +static void a6xx_show_cluster_data(const u32 *registers, int size, u32 *data, + struct drm_printer *p) +{ + int ctx, index = 0; + + for (ctx = 0; ctx < A6XX_NUM_CONTEXTS; ctx++) { + int j; + + drm_printf(p, " - context: %d\n", ctx); + + for (j = 0; j < size; j += 2) { + u32 count = RANGE(registers, j); + u32 offset = registers[j]; + int k; + + for (k = 0; k < count; index++, offset++, k++) { + if (data[index] == 0xdeafbead) + continue; + + drm_printf(p, " - { offset: 0x%06x, value: 0x%08x }\n", + offset << 2, data[index]); + } + } + } +} + +static void a6xx_show_dbgahb_cluster(struct a6xx_gpu_state_obj *obj, + struct drm_printer *p) +{ + const struct a6xx_dbgahb_cluster *dbgahb = obj->handle; + + if (dbgahb) { + print_name(p, " - cluster-name: ", dbgahb->name); + a6xx_show_cluster_data(dbgahb->registers, dbgahb->count, + obj->data, p); + } +} + +static void a6xx_show_cluster(struct a6xx_gpu_state_obj *obj, + struct drm_printer *p) +{ + const struct a6xx_cluster *cluster = obj->handle; + + if (cluster) { + print_name(p, " - cluster-name: ", cluster->name); + a6xx_show_cluster_data(cluster->registers, cluster->count, + obj->data, p); + } +} + +static void a6xx_show_indexed_regs(struct a6xx_gpu_state_obj *obj, + struct drm_printer *p) +{ + const struct a6xx_indexed_registers *indexed = obj->handle; + + if (!indexed) + return; + + print_name(p, " - regs-name: ", indexed->name); + drm_printf(p, " dwords: %d\n", indexed->count); + + print_ascii85(p, indexed->count << 2, obj->data); +} + +static void a6xx_show_debugbus_block(const struct a6xx_debugbus_block *block, + u32 *data, struct drm_printer *p) +{ + if (block) { + print_name(p, " - debugbus-block: ", block->name); + + /* + * count for regular debugbus data is in quadwords, + * but print the size in dwords for consistency + */ + drm_printf(p, " count: %d\n", block->count << 1); + + print_ascii85(p, block->count << 3, data); + } +} + +static void a6xx_show_debugbus(struct a6xx_gpu_state *a6xx_state, + struct drm_printer *p) +{ + int i; + + for (i = 0; i < a6xx_state->nr_debugbus; i++) { + struct a6xx_gpu_state_obj *obj = &a6xx_state->debugbus[i]; + + a6xx_show_debugbus_block(obj->handle, obj->data, p); + } + + if (a6xx_state->vbif_debugbus) { + struct a6xx_gpu_state_obj *obj = a6xx_state->vbif_debugbus; + + drm_puts(p, " - debugbus-block: A6XX_DBGBUS_VBIF\n"); + drm_printf(p, " count: %d\n", VBIF_DEBUGBUS_BLOCK_SIZE); + + /* vbif debugbus data is in dwords. Confusing, huh? */ + print_ascii85(p, VBIF_DEBUGBUS_BLOCK_SIZE << 2, obj->data); + } + + for (i = 0; i < a6xx_state->nr_cx_debugbus; i++) { + struct a6xx_gpu_state_obj *obj = &a6xx_state->cx_debugbus[i]; + + a6xx_show_debugbus_block(obj->handle, obj->data, p); + } +} + +void a6xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state, + struct drm_printer *p) +{ + struct a6xx_gpu_state *a6xx_state = container_of(state, + struct a6xx_gpu_state, base); + int i; + + if (IS_ERR_OR_NULL(state)) + return; + + adreno_show(gpu, state, p); + + drm_puts(p, "registers:\n"); + for (i = 0; i < a6xx_state->nr_registers; i++) { + struct a6xx_gpu_state_obj *obj = &a6xx_state->registers[i]; + const struct a6xx_registers *regs = obj->handle; + + if (!obj->handle) + continue; + + a6xx_show_registers(regs->registers, obj->data, regs->count, p); + } + + drm_puts(p, "registers-gmu:\n"); + for (i = 0; i < a6xx_state->nr_gmu_registers; i++) { + struct a6xx_gpu_state_obj *obj = &a6xx_state->gmu_registers[i]; + const struct a6xx_registers *regs = obj->handle; + + if (!obj->handle) + continue; + + a6xx_show_registers(regs->registers, obj->data, regs->count, p); + } + + drm_puts(p, "indexed-registers:\n"); + for (i = 0; i < a6xx_state->nr_indexed_regs; i++) + a6xx_show_indexed_regs(&a6xx_state->indexed_regs[i], p); + + drm_puts(p, "shader-blocks:\n"); + for (i = 0; i < a6xx_state->nr_shaders; i++) + a6xx_show_shader(&a6xx_state->shaders[i], p); + + drm_puts(p, "clusters:\n"); + for (i = 0; i < a6xx_state->nr_clusters; i++) + a6xx_show_cluster(&a6xx_state->clusters[i], p); + + for (i = 0; i < a6xx_state->nr_dbgahb_clusters; i++) + a6xx_show_dbgahb_cluster(&a6xx_state->dbgahb_clusters[i], p); + + drm_puts(p, "debugbus:\n"); + a6xx_show_debugbus(a6xx_state, p); +} diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h new file mode 100644 index 000000000000..68cccfa2870a --- /dev/null +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h @@ -0,0 +1,430 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 The Linux Foundation. All rights reserved. */ + +#ifndef _A6XX_CRASH_DUMP_H_ +#define _A6XX_CRASH_DUMP_H_ + +#include "a6xx.xml.h" + +#define A6XX_NUM_CONTEXTS 2 +#define A6XX_NUM_SHADER_BANKS 3 + +static const u32 a6xx_gras_cluster[] = { + 0x8000, 0x8006, 0x8010, 0x8092, 0x8094, 0x809d, 0x80a0, 0x80a6, + 0x80af, 0x80f1, 0x8100, 0x8107, 0x8109, 0x8109, 0x8110, 0x8110, + 0x8400, 0x840b, +}; + +static const u32 a6xx_ps_cluster_rac[] = { + 0x8800, 0x8806, 0x8809, 0x8811, 0x8818, 0x881e, 0x8820, 0x8865, + 0x8870, 0x8879, 0x8880, 0x8889, 0x8890, 0x8891, 0x8898, 0x8898, + 0x88c0, 0x88c1, 0x88d0, 0x88e3, 0x8900, 0x890c, 0x890f, 0x891a, + 0x8c00, 0x8c01, 0x8c08, 0x8c10, 0x8c17, 0x8c1f, 0x8c26, 0x8c33, +}; + +static const u32 a6xx_ps_cluster_rbp[] = { + 0x88f0, 0x88f3, 0x890d, 0x890e, 0x8927, 0x8928, 0x8bf0, 0x8bf1, + 0x8c02, 0x8c07, 0x8c11, 0x8c16, 0x8c20, 0x8c25, +}; + +static const u32 a6xx_ps_cluster[] = { + 0x9200, 0x9216, 0x9218, 0x9236, 0x9300, 0x9306, +}; + +static const u32 a6xx_fe_cluster[] = { + 0x9300, 0x9306, 0x9800, 0x9806, 0x9b00, 0x9b07, 0xa000, 0xa009, + 0xa00e, 0xa0ef, 0xa0f8, 0xa0f8, +}; + +static const u32 a6xx_pc_vs_cluster[] = { + 0x9100, 0x9108, 0x9300, 0x9306, 0x9980, 0x9981, 0x9b00, 0x9b07, +}; + +#define CLUSTER_FE 0 +#define CLUSTER_SP_VS 1 +#define CLUSTER_PC_VS 2 +#define CLUSTER_GRAS 3 +#define CLUSTER_SP_PS 4 +#define CLUSTER_PS 5 + +#define CLUSTER(_id, _reg, _sel_reg, _sel_val) \ + { .id = _id, .name = #_id,\ + .registers = _reg, \ + .count = ARRAY_SIZE(_reg), \ + .sel_reg = _sel_reg, .sel_val = _sel_val } + +static const struct a6xx_cluster { + u32 id; + const char *name; + const u32 *registers; + size_t count; + u32 sel_reg; + u32 sel_val; +} a6xx_clusters[] = { + CLUSTER(CLUSTER_GRAS, a6xx_gras_cluster, 0, 0), + CLUSTER(CLUSTER_PS, a6xx_ps_cluster_rac, REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, 0x0), + CLUSTER(CLUSTER_PS, a6xx_ps_cluster_rbp, REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, 0x9), + CLUSTER(CLUSTER_PS, a6xx_ps_cluster, 0, 0), + CLUSTER(CLUSTER_FE, a6xx_fe_cluster, 0, 0), + CLUSTER(CLUSTER_PC_VS, a6xx_pc_vs_cluster, 0, 0), +}; + +static const u32 a6xx_sp_vs_hlsq_cluster[] = { + 0xb800, 0xb803, 0xb820, 0xb822, +}; + +static const u32 a6xx_sp_vs_sp_cluster[] = { + 0xa800, 0xa824, 0xa830, 0xa83c, 0xa840, 0xa864, 0xa870, 0xa895, + 0xa8a0, 0xa8af, 0xa8c0, 0xa8c3, +}; + +static const u32 a6xx_hlsq_duplicate_cluster[] = { + 0xbb10, 0xbb11, 0xbb20, 0xbb29, +}; + +static const u32 a6xx_hlsq_2d_duplicate_cluster[] = { + 0xbd80, 0xbd80, +}; + +static const u32 a6xx_sp_duplicate_cluster[] = { + 0xab00, 0xab00, 0xab04, 0xab05, 0xab10, 0xab1b, 0xab20, 0xab20, +}; + +static const u32 a6xx_tp_duplicate_cluster[] = { + 0xb300, 0xb307, 0xb309, 0xb309, 0xb380, 0xb382, +}; + +static const u32 a6xx_sp_ps_hlsq_cluster[] = { + 0xb980, 0xb980, 0xb982, 0xb987, 0xb990, 0xb99b, 0xb9a0, 0xb9a2, + 0xb9c0, 0xb9c9, +}; + +static const u32 a6xx_sp_ps_hlsq_2d_cluster[] = { + 0xbd80, 0xbd80, +}; + +static const u32 a6xx_sp_ps_sp_cluster[] = { + 0xa980, 0xa9a8, 0xa9b0, 0xa9bc, 0xa9d0, 0xa9d3, 0xa9e0, 0xa9f3, + 0xaa00, 0xaa00, 0xaa30, 0xaa31, +}; + +static const u32 a6xx_sp_ps_sp_2d_cluster[] = { + 0xacc0, 0xacc0, +}; + +static const u32 a6xx_sp_ps_tp_cluster[] = { + 0xb180, 0xb183, 0xb190, 0xb191, +}; + +static const u32 a6xx_sp_ps_tp_2d_cluster[] = { + 0xb4c0, 0xb4d1, +}; + +#define CLUSTER_DBGAHB(_id, _base, _type, _reg) \ + { .name = #_id, .statetype = _type, .base = _base, \ + .registers = _reg, .count = ARRAY_SIZE(_reg) } + +static const struct a6xx_dbgahb_cluster { + const char *name; + u32 statetype; + u32 base; + const u32 *registers; + size_t count; +} a6xx_dbgahb_clusters[] = { + CLUSTER_DBGAHB(CLUSTER_SP_VS, 0x0002e000, 0x41, a6xx_sp_vs_hlsq_cluster), + CLUSTER_DBGAHB(CLUSTER_SP_VS, 0x0002a000, 0x21, a6xx_sp_vs_sp_cluster), + CLUSTER_DBGAHB(CLUSTER_SP_VS, 0x0002e000, 0x41, a6xx_hlsq_duplicate_cluster), + CLUSTER_DBGAHB(CLUSTER_SP_VS, 0x0002f000, 0x45, a6xx_hlsq_2d_duplicate_cluster), + CLUSTER_DBGAHB(CLUSTER_SP_VS, 0x0002a000, 0x21, a6xx_sp_duplicate_cluster), + CLUSTER_DBGAHB(CLUSTER_SP_VS, 0x0002c000, 0x1, a6xx_tp_duplicate_cluster), + CLUSTER_DBGAHB(CLUSTER_SP_PS, 0x0002e000, 0x42, a6xx_sp_ps_hlsq_cluster), + CLUSTER_DBGAHB(CLUSTER_SP_PS, 0x0002f000, 0x46, a6xx_sp_ps_hlsq_2d_cluster), + CLUSTER_DBGAHB(CLUSTER_SP_PS, 0x0002a000, 0x22, a6xx_sp_ps_sp_cluster), + CLUSTER_DBGAHB(CLUSTER_SP_PS, 0x0002b000, 0x26, a6xx_sp_ps_sp_2d_cluster), + CLUSTER_DBGAHB(CLUSTER_SP_PS, 0x0002c000, 0x2, a6xx_sp_ps_tp_cluster), + CLUSTER_DBGAHB(CLUSTER_SP_PS, 0x0002d000, 0x6, a6xx_sp_ps_tp_2d_cluster), + CLUSTER_DBGAHB(CLUSTER_SP_PS, 0x0002e000, 0x42, a6xx_hlsq_duplicate_cluster), + CLUSTER_DBGAHB(CLUSTER_SP_PS, 0x0002a000, 0x22, a6xx_sp_duplicate_cluster), + CLUSTER_DBGAHB(CLUSTER_SP_PS, 0x0002c000, 0x2, a6xx_tp_duplicate_cluster), +}; + +static const u32 a6xx_hlsq_registers[] = { + 0xbe00, 0xbe01, 0xbe04, 0xbe05, 0xbe08, 0xbe09, 0xbe10, 0xbe15, + 0xbe20, 0xbe23, +}; + +static const u32 a6xx_sp_registers[] = { + 0xae00, 0xae04, 0xae0c, 0xae0c, 0xae0f, 0xae2b, 0xae30, 0xae32, + 0xae35, 0xae35, 0xae3a, 0xae3f, 0xae50, 0xae52, +}; + +static const u32 a6xx_tp_registers[] = { + 0xb600, 0xb601, 0xb604, 0xb605, 0xb610, 0xb61b, 0xb620, 0xb623, +}; + +struct a6xx_registers { + const u32 *registers; + size_t count; + u32 val0; + u32 val1; +}; + +#define HLSQ_DBG_REGS(_base, _type, _array) \ + { .val0 = _base, .val1 = _type, .registers = _array, \ + .count = ARRAY_SIZE(_array), } + +static const struct a6xx_registers a6xx_hlsq_reglist[] = { + HLSQ_DBG_REGS(0x0002F800, 0x40, a6xx_hlsq_registers), + HLSQ_DBG_REGS(0x0002B800, 0x20, a6xx_sp_registers), + HLSQ_DBG_REGS(0x0002D800, 0x0, a6xx_tp_registers), +}; + +#define SHADER(_type, _size) \ + { .type = _type, .name = #_type, .size = _size } + +static const struct a6xx_shader_block { + const char *name; + u32 type; + u32 size; +} a6xx_shader_blocks[] = { + SHADER(A6XX_TP0_TMO_DATA, 0x200), + SHADER(A6XX_TP0_SMO_DATA, 0x80), + SHADER(A6XX_TP0_MIPMAP_BASE_DATA, 0x3c0), + SHADER(A6XX_TP1_TMO_DATA, 0x200), + SHADER(A6XX_TP1_SMO_DATA, 0x80), + SHADER(A6XX_TP1_MIPMAP_BASE_DATA, 0x3c0), + SHADER(A6XX_SP_INST_DATA, 0x800), + SHADER(A6XX_SP_LB_0_DATA, 0x800), + SHADER(A6XX_SP_LB_1_DATA, 0x800), + SHADER(A6XX_SP_LB_2_DATA, 0x800), + SHADER(A6XX_SP_LB_3_DATA, 0x800), + SHADER(A6XX_SP_LB_4_DATA, 0x800), + SHADER(A6XX_SP_LB_5_DATA, 0x200), + SHADER(A6XX_SP_CB_BINDLESS_DATA, 0x2000), + SHADER(A6XX_SP_CB_LEGACY_DATA, 0x280), + SHADER(A6XX_SP_UAV_DATA, 0x80), + SHADER(A6XX_SP_INST_TAG, 0x80), + SHADER(A6XX_SP_CB_BINDLESS_TAG, 0x80), + SHADER(A6XX_SP_TMO_UMO_TAG, 0x80), + SHADER(A6XX_SP_SMO_TAG, 0x80), + SHADER(A6XX_SP_STATE_DATA, 0x3f), + SHADER(A6XX_HLSQ_CHUNK_CVS_RAM, 0x1c0), + SHADER(A6XX_HLSQ_CHUNK_CPS_RAM, 0x280), + SHADER(A6XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x40), + SHADER(A6XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x40), + SHADER(A6XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x4), + SHADER(A6XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x4), + SHADER(A6XX_HLSQ_CVS_MISC_RAM, 0x1c0), + SHADER(A6XX_HLSQ_CPS_MISC_RAM, 0x580), + SHADER(A6XX_HLSQ_INST_RAM, 0x800), + SHADER(A6XX_HLSQ_GFX_CVS_CONST_RAM, 0x800), + SHADER(A6XX_HLSQ_GFX_CPS_CONST_RAM, 0x800), + SHADER(A6XX_HLSQ_CVS_MISC_RAM_TAG, 0x8), + SHADER(A6XX_HLSQ_CPS_MISC_RAM_TAG, 0x4), + SHADER(A6XX_HLSQ_INST_RAM_TAG, 0x80), + SHADER(A6XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0xc), + SHADER(A6XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x10), + SHADER(A6XX_HLSQ_PWR_REST_RAM, 0x28), + SHADER(A6XX_HLSQ_PWR_REST_TAG, 0x14), + SHADER(A6XX_HLSQ_DATAPATH_META, 0x40), + SHADER(A6XX_HLSQ_FRONTEND_META, 0x40), + SHADER(A6XX_HLSQ_INDIRECT_META, 0x40), +}; + +static const u32 a6xx_rb_rac_registers[] = { + 0x8e04, 0x8e05, 0x8e07, 0x8e08, 0x8e10, 0x8e1c, 0x8e20, 0x8e25, + 0x8e28, 0x8e28, 0x8e2c, 0x8e2f, 0x8e50, 0x8e52, +}; + +static const u32 a6xx_rb_rbp_registers[] = { + 0x8e01, 0x8e01, 0x8e0c, 0x8e0c, 0x8e3b, 0x8e3e, 0x8e40, 0x8e43, + 0x8e53, 0x8e5f, 0x8e70, 0x8e77, +}; + +static const u32 a6xx_registers[] = { + /* RBBM */ + 0x0000, 0x0002, 0x0010, 0x0010, 0x0012, 0x0012, 0x0018, 0x001b, + 0x001e, 0x0032, 0x0038, 0x003c, 0x0042, 0x0042, 0x0044, 0x0044, + 0x0047, 0x0047, 0x0056, 0x0056, 0x00ad, 0x00ae, 0x00b0, 0x00fb, + 0x0100, 0x011d, 0x0200, 0x020d, 0x0218, 0x023d, 0x0400, 0x04f9, + 0x0500, 0x0500, 0x0505, 0x050b, 0x050e, 0x0511, 0x0533, 0x0533, + 0x0540, 0x0555, + /* CP */ + 0x0800, 0x0808, 0x0810, 0x0813, 0x0820, 0x0821, 0x0823, 0x0824, + 0x0826, 0x0827, 0x0830, 0x0833, 0x0840, 0x0843, 0x084f, 0x086f, + 0x0880, 0x088a, 0x08a0, 0x08ab, 0x08c0, 0x08c4, 0x08d0, 0x08dd, + 0x08f0, 0x08f3, 0x0900, 0x0903, 0x0908, 0x0911, 0x0928, 0x093e, + 0x0942, 0x094d, 0x0980, 0x0984, 0x098d, 0x0996, 0x0998, 0x099e, + 0x09a0, 0x09a6, 0x09a8, 0x09ae, 0x09b0, 0x09b1, 0x09c2, 0x09c8, + 0x0a00, 0x0a03, + /* VSC */ + 0x0c00, 0x0c04, 0x0c06, 0x0c06, 0x0c10, 0x0cd9, 0x0e00, 0x0e0e, + /* UCHE */ + 0x0e10, 0x0e13, 0x0e17, 0x0e19, 0x0e1c, 0x0e2b, 0x0e30, 0x0e32, + 0x0e38, 0x0e39, + /* GRAS */ + 0x8600, 0x8601, 0x8610, 0x861b, 0x8620, 0x8620, 0x8628, 0x862b, + 0x8630, 0x8637, + /* VPC */ + 0x9600, 0x9604, 0x9624, 0x9637, + /* PC */ + 0x9e00, 0x9e01, 0x9e03, 0x9e0e, 0x9e11, 0x9e16, 0x9e19, 0x9e19, + 0x9e1c, 0x9e1c, 0x9e20, 0x9e23, 0x9e30, 0x9e31, 0x9e34, 0x9e34, + 0x9e70, 0x9e72, 0x9e78, 0x9e79, 0x9e80, 0x9fff, + /* VFD */ + 0xa600, 0xa601, 0xa603, 0xa603, 0xa60a, 0xa60a, 0xa610, 0xa617, + 0xa630, 0xa630, +}; + +#define REGS(_array, _sel_reg, _sel_val) \ + { .registers = _array, .count = ARRAY_SIZE(_array), \ + .val0 = _sel_reg, .val1 = _sel_val } + +static const struct a6xx_registers a6xx_reglist[] = { + REGS(a6xx_registers, 0, 0), + REGS(a6xx_rb_rac_registers, REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, 0), + REGS(a6xx_rb_rbp_registers, REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, 9), +}; + +static const u32 a6xx_ahb_registers[] = { + /* RBBM_STATUS - RBBM_STATUS3 */ + 0x210, 0x213, + /* CP_STATUS_1 */ + 0x825, 0x825, +}; + +static const u32 a6xx_vbif_registers[] = { + 0x3000, 0x3007, 0x300c, 0x3014, 0x3018, 0x302d, 0x3030, 0x3031, + 0x3034, 0x3036, 0x303c, 0x303d, 0x3040, 0x3040, 0x3042, 0x3042, + 0x3049, 0x3049, 0x3058, 0x3058, 0x305a, 0x3061, 0x3064, 0x3068, + 0x306c, 0x306d, 0x3080, 0x3088, 0x308b, 0x308c, 0x3090, 0x3094, + 0x3098, 0x3098, 0x309c, 0x309c, 0x30c0, 0x30c0, 0x30c8, 0x30c8, + 0x30d0, 0x30d0, 0x30d8, 0x30d8, 0x30e0, 0x30e0, 0x3100, 0x3100, + 0x3108, 0x3108, 0x3110, 0x3110, 0x3118, 0x3118, 0x3120, 0x3120, + 0x3124, 0x3125, 0x3129, 0x3129, 0x3131, 0x3131, 0x3154, 0x3154, + 0x3156, 0x3156, 0x3158, 0x3158, 0x315a, 0x315a, 0x315c, 0x315c, + 0x315e, 0x315e, 0x3160, 0x3160, 0x3162, 0x3162, 0x340c, 0x340c, + 0x3410, 0x3410, 0x3800, 0x3801, +}; + +static const struct a6xx_registers a6xx_ahb_reglist[] = { + REGS(a6xx_ahb_registers, 0, 0), + REGS(a6xx_vbif_registers, 0, 0), +}; + +static const u32 a6xx_gmu_gx_registers[] = { + /* GMU GX */ + 0x0000, 0x0000, 0x0010, 0x0013, 0x0016, 0x0016, 0x0018, 0x001b, + 0x001e, 0x001e, 0x0020, 0x0023, 0x0026, 0x0026, 0x0028, 0x002b, + 0x002e, 0x002e, 0x0030, 0x0033, 0x0036, 0x0036, 0x0038, 0x003b, + 0x003e, 0x003e, 0x0040, 0x0043, 0x0046, 0x0046, 0x0080, 0x0084, + 0x0100, 0x012b, 0x0140, 0x0140, +}; + +static const u32 a6xx_gmu_cx_registers[] = { + /* GMU CX */ + 0x4c00, 0x4c07, 0x4c10, 0x4c12, 0x4d00, 0x4d00, 0x4d07, 0x4d0a, + 0x5000, 0x5004, 0x5007, 0x5008, 0x500b, 0x500c, 0x500f, 0x501c, + 0x5024, 0x502a, 0x502d, 0x5030, 0x5040, 0x5053, 0x5087, 0x5089, + 0x50a0, 0x50a2, 0x50a4, 0x50af, 0x50c0, 0x50c3, 0x50d0, 0x50d0, + 0x50e4, 0x50e4, 0x50e8, 0x50ec, 0x5100, 0x5103, 0x5140, 0x5140, + 0x5142, 0x5144, 0x514c, 0x514d, 0x514f, 0x5151, 0x5154, 0x5154, + 0x5157, 0x5158, 0x515d, 0x515d, 0x5162, 0x5162, 0x5164, 0x5165, + 0x5180, 0x5186, 0x5190, 0x519e, 0x51c0, 0x51c0, 0x51c5, 0x51cc, + 0x51e0, 0x51e2, 0x51f0, 0x51f0, 0x5200, 0x5201, + /* GPU RSCC */ + 0x8c8c, 0x8c8c, 0x8d01, 0x8d02, 0x8f40, 0x8f42, 0x8f44, 0x8f47, + 0x8f4c, 0x8f87, 0x8fec, 0x8fef, 0x8ff4, 0x902f, 0x9094, 0x9097, + 0x909c, 0x90d7, 0x913c, 0x913f, 0x9144, 0x917f, + /* GMU AO */ + 0x9300, 0x9316, 0x9400, 0x9400, + /* GPU CC */ + 0x9800, 0x9812, 0x9840, 0x9852, 0x9c00, 0x9c04, 0x9c07, 0x9c0b, + 0x9c15, 0x9c1c, 0x9c1e, 0x9c2d, 0x9c3c, 0x9c3d, 0x9c3f, 0x9c40, + 0x9c42, 0x9c49, 0x9c58, 0x9c5a, 0x9d40, 0x9d5e, 0xa000, 0xa002, + 0xa400, 0xa402, 0xac00, 0xac02, 0xb000, 0xb002, 0xb400, 0xb402, + 0xb800, 0xb802, + /* GPU CC ACD */ + 0xbc00, 0xbc16, 0xbc20, 0xbc27, +}; + +static const struct a6xx_registers a6xx_gmu_reglist[] = { + REGS(a6xx_gmu_cx_registers, 0, 0), + REGS(a6xx_gmu_gx_registers, 0, 0), +}; + +static const struct a6xx_indexed_registers { + const char *name; + u32 addr; + u32 data; + u32 count; +} a6xx_indexed_reglist[] = { + { "CP_SEQ_STAT", REG_A6XX_CP_SQE_STAT_ADDR, + REG_A6XX_CP_SQE_STAT_DATA, 0x33 }, + { "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR, + REG_A6XX_CP_DRAW_STATE_DATA, 0x100 }, + { "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, + REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x6000 }, + { "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR, + REG_A6XX_CP_ROQ_DBG_DATA, 0x400 }, +}; + +static const struct a6xx_indexed_registers a6xx_cp_mempool_indexed = { + "CP_MEMPOOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR, + REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2060, +}; + +#define DEBUGBUS(_id, _count) { .id = _id, .name = #_id, .count = _count } + +static const struct a6xx_debugbus_block { + const char *name; + u32 id; + u32 count; +} a6xx_debugbus_blocks[] = { + DEBUGBUS(A6XX_DBGBUS_CP, 0x100), + DEBUGBUS(A6XX_DBGBUS_RBBM, 0x100), + DEBUGBUS(A6XX_DBGBUS_HLSQ, 0x100), + DEBUGBUS(A6XX_DBGBUS_UCHE, 0x100), + DEBUGBUS(A6XX_DBGBUS_DPM, 0x100), + DEBUGBUS(A6XX_DBGBUS_TESS, 0x100), + DEBUGBUS(A6XX_DBGBUS_PC, 0x100), + DEBUGBUS(A6XX_DBGBUS_VFDP, 0x100), + DEBUGBUS(A6XX_DBGBUS_VPC, 0x100), + DEBUGBUS(A6XX_DBGBUS_TSE, 0x100), + DEBUGBUS(A6XX_DBGBUS_RAS, 0x100), + DEBUGBUS(A6XX_DBGBUS_VSC, 0x100), + DEBUGBUS(A6XX_DBGBUS_COM, 0x100), + DEBUGBUS(A6XX_DBGBUS_LRZ, 0x100), + DEBUGBUS(A6XX_DBGBUS_A2D, 0x100), + DEBUGBUS(A6XX_DBGBUS_CCUFCHE, 0x100), + DEBUGBUS(A6XX_DBGBUS_RBP, 0x100), + DEBUGBUS(A6XX_DBGBUS_DCS, 0x100), + DEBUGBUS(A6XX_DBGBUS_DBGC, 0x100), + DEBUGBUS(A6XX_DBGBUS_GMU_GX, 0x100), + DEBUGBUS(A6XX_DBGBUS_TPFCHE, 0x100), + DEBUGBUS(A6XX_DBGBUS_GPC, 0x100), + DEBUGBUS(A6XX_DBGBUS_LARC, 0x100), + DEBUGBUS(A6XX_DBGBUS_HLSQ_SPTP, 0x100), + DEBUGBUS(A6XX_DBGBUS_RB_0, 0x100), + DEBUGBUS(A6XX_DBGBUS_RB_1, 0x100), + DEBUGBUS(A6XX_DBGBUS_UCHE_WRAPPER, 0x100), + DEBUGBUS(A6XX_DBGBUS_CCU_0, 0x100), + DEBUGBUS(A6XX_DBGBUS_CCU_1, 0x100), + DEBUGBUS(A6XX_DBGBUS_VFD_0, 0x100), + DEBUGBUS(A6XX_DBGBUS_VFD_1, 0x100), + DEBUGBUS(A6XX_DBGBUS_VFD_2, 0x100), + DEBUGBUS(A6XX_DBGBUS_VFD_3, 0x100), + DEBUGBUS(A6XX_DBGBUS_SP_0, 0x100), + DEBUGBUS(A6XX_DBGBUS_SP_1, 0x100), + DEBUGBUS(A6XX_DBGBUS_TPL1_0, 0x100), + DEBUGBUS(A6XX_DBGBUS_TPL1_1, 0x100), + DEBUGBUS(A6XX_DBGBUS_TPL1_2, 0x100), + DEBUGBUS(A6XX_DBGBUS_TPL1_3, 0x100), +}; + +static const struct a6xx_debugbus_block a6xx_cx_debugbus_blocks[] = { + DEBUGBUS(A6XX_DBGBUS_GMU_CX, 0x100), + DEBUGBUS(A6XX_DBGBUS_CX, 0x100), +}; + +#endif diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c index 6ff9baec2658..eda11abc5f01 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c @@ -91,7 +91,7 @@ static int a6xx_hfi_wait_for_ack(struct a6xx_gmu *gmu, u32 id, u32 seqnum, val & A6XX_GMU_GMU2HOST_INTR_INFO_MSGQ, 100, 5000); if (ret) { - dev_err(gmu->dev, + DRM_DEV_ERROR(gmu->dev, "Message %s id %d timed out waiting for response\n", a6xx_hfi_msg_id[id], seqnum); return -ETIMEDOUT; @@ -110,7 +110,7 @@ static int a6xx_hfi_wait_for_ack(struct a6xx_gmu *gmu, u32 id, u32 seqnum, /* If the queue is empty our response never made it */ if (!ret) { - dev_err(gmu->dev, + DRM_DEV_ERROR(gmu->dev, "The HFI response queue is unexpectedly empty\n"); return -ENOENT; @@ -120,20 +120,20 @@ static int a6xx_hfi_wait_for_ack(struct a6xx_gmu *gmu, u32 id, u32 seqnum, struct a6xx_hfi_msg_error *error = (struct a6xx_hfi_msg_error *) &resp; - dev_err(gmu->dev, "GMU firmware error %d\n", + DRM_DEV_ERROR(gmu->dev, "GMU firmware error %d\n", error->code); continue; } if (seqnum != HFI_HEADER_SEQNUM(resp.ret_header)) { - dev_err(gmu->dev, + DRM_DEV_ERROR(gmu->dev, "Unexpected message id %d on the response queue\n", HFI_HEADER_SEQNUM(resp.ret_header)); continue; } if (resp.error) { - dev_err(gmu->dev, + DRM_DEV_ERROR(gmu->dev, "Message %s id %d returned error %d\n", a6xx_hfi_msg_id[id], seqnum, resp.error); return -EINVAL; @@ -163,7 +163,7 @@ static int a6xx_hfi_send_msg(struct a6xx_gmu *gmu, int id, ret = a6xx_hfi_queue_write(gmu, queue, data, dwords); if (ret) { - dev_err(gmu->dev, "Unable to send message %s id %d\n", + DRM_DEV_ERROR(gmu->dev, "Unable to send message %s id %d\n", a6xx_hfi_msg_id[id], seqnum); return ret; } @@ -317,7 +317,7 @@ void a6xx_hfi_stop(struct a6xx_gmu *gmu) continue; if (queue->header->read_index != queue->header->write_index) - dev_err(gmu->dev, "HFI queue %d is not empty\n", i); + DRM_DEV_ERROR(gmu->dev, "HFI queue %d is not empty\n", i); queue->header->read_index = 0; queue->header->write_index = 0; diff --git a/drivers/gpu/drm/msm/adreno/adreno_common.xml.h b/drivers/gpu/drm/msm/adreno/adreno_common.xml.h index 1318959d504d..641d3ba477b6 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_common.xml.h +++ b/drivers/gpu/drm/msm/adreno/adreno_common.xml.h @@ -10,13 +10,13 @@ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: - /home/robclark/src/envytools/rnndb/adreno.xml ( 501 bytes, from 2018-07-03 19:37:13) - /home/robclark/src/envytools/rnndb/freedreno_copyright.xml ( 1572 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml ( 36805 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml ( 13634 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml ( 42585 bytes, from 2018-10-04 19:06:37) +- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml ( 42463 bytes, from 2018-11-19 13:44:03) +- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml ( 14201 bytes, from 2018-12-02 17:29:54) +- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml ( 43052 bytes, from 2018-12-02 17:29:54) - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml ( 83840 bytes, from 2018-07-03 19:37:13) - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml ( 112086 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml ( 147240 bytes, from 2018-10-04 19:06:37) -- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml ( 139581 bytes, from 2018-10-04 19:06:42) +- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml ( 147240 bytes, from 2018-12-02 17:29:54) +- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml ( 140790 bytes, from 2018-12-02 17:29:54) - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml ( 10431 bytes, from 2018-09-14 13:03:07) - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml ( 1773 bytes, from 2018-07-03 19:37:13) @@ -339,6 +339,15 @@ static inline uint32_t AXXX_SCRATCH_UMSK_SWAP(uint32_t val) #define REG_AXXX_CP_STATE_DEBUG_DATA 0x000001ed #define REG_AXXX_CP_INT_CNTL 0x000001f2 +#define AXXX_CP_INT_CNTL_SW_INT_MASK 0x00080000 +#define AXXX_CP_INT_CNTL_T0_PACKET_IN_IB_MASK 0x00800000 +#define AXXX_CP_INT_CNTL_OPCODE_ERROR_MASK 0x01000000 +#define AXXX_CP_INT_CNTL_PROTECTED_MODE_ERROR_MASK 0x02000000 +#define AXXX_CP_INT_CNTL_RESERVED_BIT_ERROR_MASK 0x04000000 +#define AXXX_CP_INT_CNTL_IB_ERROR_MASK 0x08000000 +#define AXXX_CP_INT_CNTL_IB2_INT_MASK 0x20000000 +#define AXXX_CP_INT_CNTL_IB1_INT_MASK 0x40000000 +#define AXXX_CP_INT_CNTL_RB_INT_MASK 0x80000000 #define REG_AXXX_CP_INT_STATUS 0x000001f3 diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 86abdb2b3a9c..714ed6505e47 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -27,6 +27,39 @@ module_param_named(hang_debug, hang_debug, bool, 0600); static const struct adreno_info gpulist[] = { { + .rev = ADRENO_REV(2, 0, 0, 0), + .revn = 200, + .name = "A200", + .fw = { + [ADRENO_FW_PM4] = "yamato_pm4.fw", + [ADRENO_FW_PFP] = "yamato_pfp.fw", + }, + .gmem = SZ_256K, + .inactive_period = DRM_MSM_INACTIVE_PERIOD, + .init = a2xx_gpu_init, + }, { /* a200 on i.mx51 has only 128kib gmem */ + .rev = ADRENO_REV(2, 0, 0, 1), + .revn = 201, + .name = "A200", + .fw = { + [ADRENO_FW_PM4] = "yamato_pm4.fw", + [ADRENO_FW_PFP] = "yamato_pfp.fw", + }, + .gmem = SZ_128K, + .inactive_period = DRM_MSM_INACTIVE_PERIOD, + .init = a2xx_gpu_init, + }, { + .rev = ADRENO_REV(2, 2, 0, ANY_ID), + .revn = 220, + .name = "A220", + .fw = { + [ADRENO_FW_PM4] = "leia_pm4_470.fw", + [ADRENO_FW_PFP] = "leia_pfp_470.fw", + }, + .gmem = SZ_512K, + .inactive_period = DRM_MSM_INACTIVE_PERIOD, + .init = a2xx_gpu_init, + }, { .rev = ADRENO_REV(3, 0, 5, ANY_ID), .revn = 305, .name = "A305", @@ -196,7 +229,7 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev) ret = pm_runtime_get_sync(&pdev->dev); if (ret < 0) { - dev_err(dev->dev, "Couldn't power up the GPU: %d\n", ret); + DRM_DEV_ERROR(dev->dev, "Couldn't power up the GPU: %d\n", ret); return NULL; } @@ -205,7 +238,7 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev) mutex_unlock(&dev->struct_mutex); pm_runtime_put_autosuspend(&pdev->dev); if (ret) { - dev_err(dev->dev, "gpu hw init failed: %d\n", ret); + DRM_DEV_ERROR(dev->dev, "gpu hw init failed: %d\n", ret); return NULL; } @@ -238,7 +271,8 @@ static int find_chipid(struct device *dev, struct adreno_rev *rev) if (ret == 0) { unsigned int r, patch; - if (sscanf(compat, "qcom,adreno-%u.%u", &r, &patch) == 2) { + if (sscanf(compat, "qcom,adreno-%u.%u", &r, &patch) == 2 || + sscanf(compat, "amd,imageon-%u.%u", &r, &patch) == 2) { rev->core = r / 100; r %= 100; rev->major = r / 10; @@ -253,7 +287,7 @@ static int find_chipid(struct device *dev, struct adreno_rev *rev) /* and if that fails, fall back to legacy "qcom,chipid" property: */ ret = of_property_read_u32(node, "qcom,chipid", &chipid); if (ret) { - dev_err(dev, "could not parse qcom,chipid: %d\n", ret); + DRM_DEV_ERROR(dev, "could not parse qcom,chipid: %d\n", ret); return ret; } @@ -274,6 +308,7 @@ static int adreno_bind(struct device *dev, struct device *master, void *data) static struct adreno_platform_config config = {}; const struct adreno_info *info; struct drm_device *drm = dev_get_drvdata(master); + struct msm_drm_private *priv = drm->dev_private; struct msm_gpu *gpu; int ret; @@ -296,6 +331,8 @@ static int adreno_bind(struct device *dev, struct device *master, void *data) DBG("Found GPU: %u.%u.%u.%u", config.rev.core, config.rev.major, config.rev.minor, config.rev.patchid); + priv->is_a2xx = config.rev.core == 2; + gpu = info->init(drm); if (IS_ERR(gpu)) { dev_warn(drm->dev, "failed to load adreno gpu\n"); @@ -323,9 +360,37 @@ static const struct component_ops a3xx_ops = { .unbind = adreno_unbind, }; +static void adreno_device_register_headless(void) +{ + /* on imx5, we don't have a top-level mdp/dpu node + * this creates a dummy node for the driver for that case + */ + struct platform_device_info dummy_info = { + .parent = NULL, + .name = "msm", + .id = -1, + .res = NULL, + .num_res = 0, + .data = NULL, + .size_data = 0, + .dma_mask = ~0, + }; + platform_device_register_full(&dummy_info); +} + static int adreno_probe(struct platform_device *pdev) { - return component_add(&pdev->dev, &a3xx_ops); + + int ret; + + ret = component_add(&pdev->dev, &a3xx_ops); + if (ret) + return ret; + + if (of_device_is_compatible(pdev->dev.of_node, "amd,imageon")) + adreno_device_register_headless(); + + return 0; } static int adreno_remove(struct platform_device *pdev) @@ -337,6 +402,8 @@ static int adreno_remove(struct platform_device *pdev) static const struct of_device_id dt_match[] = { { .compatible = "qcom,adreno" }, { .compatible = "qcom,adreno-3xx" }, + /* for compatibility with imx5 gpu: */ + { .compatible = "amd,imageon" }, /* for backwards compat w/ downstream kgsl DT files: */ { .compatible = "qcom,kgsl-3d0" }, {} diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 93d70f4a2154..2e4372ef17a3 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -89,12 +89,12 @@ adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname) ret = request_firmware_direct(&fw, newname, drm->dev); if (!ret) { - dev_info(drm->dev, "loaded %s from new location\n", + DRM_DEV_INFO(drm->dev, "loaded %s from new location\n", newname); adreno_gpu->fwloc = FW_LOCATION_NEW; goto out; } else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) { - dev_err(drm->dev, "failed to load %s: %d\n", + DRM_DEV_ERROR(drm->dev, "failed to load %s: %d\n", newname, ret); fw = ERR_PTR(ret); goto out; @@ -109,12 +109,12 @@ adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname) ret = request_firmware_direct(&fw, fwname, drm->dev); if (!ret) { - dev_info(drm->dev, "loaded %s from legacy location\n", + DRM_DEV_INFO(drm->dev, "loaded %s from legacy location\n", newname); adreno_gpu->fwloc = FW_LOCATION_LEGACY; goto out; } else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) { - dev_err(drm->dev, "failed to load %s: %d\n", + DRM_DEV_ERROR(drm->dev, "failed to load %s: %d\n", fwname, ret); fw = ERR_PTR(ret); goto out; @@ -130,19 +130,19 @@ adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname) ret = request_firmware(&fw, newname, drm->dev); if (!ret) { - dev_info(drm->dev, "loaded %s with helper\n", + DRM_DEV_INFO(drm->dev, "loaded %s with helper\n", newname); adreno_gpu->fwloc = FW_LOCATION_HELPER; goto out; } else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) { - dev_err(drm->dev, "failed to load %s: %d\n", + DRM_DEV_ERROR(drm->dev, "failed to load %s: %d\n", newname, ret); fw = ERR_PTR(ret); goto out; } } - dev_err(drm->dev, "failed to load %s\n", fwname); + DRM_DEV_ERROR(drm->dev, "failed to load %s\n", fwname); fw = ERR_PTR(-ENOENT); out: kfree(newname); @@ -209,14 +209,6 @@ int adreno_hw_init(struct msm_gpu *gpu) if (!ring) continue; - ret = msm_gem_get_iova(ring->bo, gpu->aspace, &ring->iova); - if (ret) { - ring->iova = 0; - dev_err(gpu->dev->dev, - "could not map ringbuffer %d: %d\n", i, ret); - return ret; - } - ring->cur = ring->start; ring->next = ring->start; @@ -277,7 +269,7 @@ void adreno_recover(struct msm_gpu *gpu) ret = msm_gpu_hw_init(gpu); if (ret) { - dev_err(dev->dev, "gpu hw init failed: %d\n", ret); + DRM_DEV_ERROR(dev->dev, "gpu hw init failed: %d\n", ret); /* hmm, oh well? */ } } @@ -319,16 +311,27 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, */ OUT_PKT3(ring, CP_EVENT_WRITE, 1); OUT_RING(ring, HLSQ_FLUSH); - - OUT_PKT3(ring, CP_WAIT_FOR_IDLE, 1); - OUT_RING(ring, 0x00000000); } - /* BIT(31) of CACHE_FLUSH_TS triggers CACHE_FLUSH_TS IRQ from GPU */ - OUT_PKT3(ring, CP_EVENT_WRITE, 3); - OUT_RING(ring, CACHE_FLUSH_TS | BIT(31)); - OUT_RING(ring, rbmemptr(ring, fence)); - OUT_RING(ring, submit->seqno); + /* wait for idle before cache flush/interrupt */ + OUT_PKT3(ring, CP_WAIT_FOR_IDLE, 1); + OUT_RING(ring, 0x00000000); + + if (!adreno_is_a2xx(adreno_gpu)) { + /* BIT(31) of CACHE_FLUSH_TS triggers CACHE_FLUSH_TS IRQ from GPU */ + OUT_PKT3(ring, CP_EVENT_WRITE, 3); + OUT_RING(ring, CACHE_FLUSH_TS | BIT(31)); + OUT_RING(ring, rbmemptr(ring, fence)); + OUT_RING(ring, submit->seqno); + } else { + /* BIT(31) means something else on a2xx */ + OUT_PKT3(ring, CP_EVENT_WRITE, 3); + OUT_RING(ring, CACHE_FLUSH_TS); + OUT_RING(ring, rbmemptr(ring, fence)); + OUT_RING(ring, submit->seqno); + OUT_PKT3(ring, CP_INTERRUPT, 1); + OUT_RING(ring, 0x80000000); + } #if 0 if (adreno_is_a3xx(adreno_gpu)) { @@ -406,7 +409,7 @@ int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state) size = j + 1; if (size) { - state->ring[i].data = kmalloc(size << 2, GFP_KERNEL); + state->ring[i].data = kvmalloc(size << 2, GFP_KERNEL); if (state->ring[i].data) { memcpy(state->ring[i].data, gpu->rb[i]->start, size << 2); state->ring[i].data_size = size << 2; @@ -414,6 +417,10 @@ int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state) } } + /* Some targets prefer to collect their own registers */ + if (!adreno_gpu->registers) + return 0; + /* Count the number of registers */ for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) count += adreno_gpu->registers[i + 1] - @@ -445,7 +452,7 @@ void adreno_gpu_state_destroy(struct msm_gpu_state *state) int i; for (i = 0; i < ARRAY_SIZE(state->ring); i++) - kfree(state->ring[i].data); + kvfree(state->ring[i].data); for (i = 0; state->bos && i < state->nr_bos; i++) kvfree(state->bos[i].data); @@ -475,34 +482,74 @@ int adreno_gpu_state_put(struct msm_gpu_state *state) #if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) -static void adreno_show_object(struct drm_printer *p, u32 *ptr, int len) +static char *adreno_gpu_ascii85_encode(u32 *src, size_t len) { + void *buf; + size_t buf_itr = 0, buffer_size; char out[ASCII85_BUFSZ]; - long l, datalen, i; + long l; + int i; - if (!ptr || !len) - return; + if (!src || !len) + return NULL; + + l = ascii85_encode_len(len); /* - * Only dump the non-zero part of the buffer - rarely will any data - * completely fill the entire allocated size of the buffer + * Ascii85 outputs either a 5 byte string or a 1 byte string. So we + * account for the worst case of 5 bytes per dword plus the 1 for '\0' */ - for (datalen = 0, i = 0; i < len >> 2; i++) { - if (ptr[i]) - datalen = (i << 2) + 1; - } + buffer_size = (l * 5) + 1; + + buf = kvmalloc(buffer_size, GFP_KERNEL); + if (!buf) + return NULL; + + for (i = 0; i < l; i++) + buf_itr += snprintf(buf + buf_itr, buffer_size - buf_itr, "%s", + ascii85_encode(src[i], out)); + + return buf; +} - /* Skip printing the object if it is empty */ - if (datalen == 0) +/* len is expected to be in bytes */ +static void adreno_show_object(struct drm_printer *p, void **ptr, int len, + bool *encoded) +{ + if (!*ptr || !len) return; - l = ascii85_encode_len(datalen); + if (!*encoded) { + long datalen, i; + u32 *buf = *ptr; + + /* + * Only dump the non-zero part of the buffer - rarely will + * any data completely fill the entire allocated size of + * the buffer. + */ + for (datalen = 0, i = 0; i < len >> 2; i++) + if (buf[i]) + datalen = ((i + 1) << 2); + + /* + * If we reach here, then the originally captured binary buffer + * will be replaced with the ascii85 encoded string + */ + *ptr = adreno_gpu_ascii85_encode(buf, datalen); + + kvfree(buf); + + *encoded = true; + } + + if (!*ptr) + return; drm_puts(p, " data: !!ascii85 |\n"); drm_puts(p, " "); - for (i = 0; i < l; i++) - drm_puts(p, ascii85_encode(ptr[i], out)); + drm_puts(p, *ptr); drm_puts(p, "\n"); } @@ -534,8 +581,8 @@ void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state, drm_printf(p, " wptr: %d\n", state->ring[i].wptr); drm_printf(p, " size: %d\n", MSM_GPU_RINGBUFFER_SZ); - adreno_show_object(p, state->ring[i].data, - state->ring[i].data_size); + adreno_show_object(p, &state->ring[i].data, + state->ring[i].data_size, &state->ring[i].encoded); } if (state->bos) { @@ -546,17 +593,19 @@ void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state, state->bos[i].iova); drm_printf(p, " size: %zd\n", state->bos[i].size); - adreno_show_object(p, state->bos[i].data, - state->bos[i].size); + adreno_show_object(p, &state->bos[i].data, + state->bos[i].size, &state->bos[i].encoded); } } - drm_puts(p, "registers:\n"); + if (state->nr_registers) { + drm_puts(p, "registers:\n"); - for (i = 0; i < state->nr_registers; i++) { - drm_printf(p, " - { offset: 0x%04x, value: 0x%08x }\n", - state->registers[i * 2] << 2, - state->registers[(i * 2) + 1]); + for (i = 0; i < state->nr_registers; i++) { + drm_printf(p, " - { offset: 0x%04x, value: 0x%08x }\n", + state->registers[i * 2] << 2, + state->registers[(i * 2) + 1]); + } } } #endif @@ -595,6 +644,9 @@ void adreno_dump(struct msm_gpu *gpu) struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); int i; + if (!adreno_gpu->registers) + return; + /* dump these out in a form that can be parsed by demsm: */ printk("IO:region %s 00000000 00020000\n", gpu->name); for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) { @@ -635,7 +687,7 @@ static int adreno_get_legacy_pwrlevels(struct device *dev) node = of_get_compatible_child(dev->of_node, "qcom,gpu-pwrlevels"); if (!node) { - dev_err(dev, "Could not find the GPU powerlevels\n"); + DRM_DEV_ERROR(dev, "Could not find the GPU powerlevels\n"); return -ENXIO; } @@ -674,7 +726,7 @@ static int adreno_get_pwrlevels(struct device *dev, else { ret = dev_pm_opp_of_add_table(dev); if (ret) - dev_err(dev, "Unable to set the OPP table\n"); + DRM_DEV_ERROR(dev, "Unable to set the OPP table\n"); } if (!ret) { @@ -717,6 +769,9 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, adreno_gpu_config.va_start = SZ_16M; adreno_gpu_config.va_end = 0xffffffff; + /* maximum range of a2xx mmu */ + if (adreno_is_a2xx(adreno_gpu)) + adreno_gpu_config.va_end = SZ_16M + 0xfff * SZ_64K; adreno_gpu_config.nr_rings = nr_rings; diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index de6e6ee42fba..5db459bc28a7 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -21,6 +21,7 @@ #define __ADRENO_GPU_H__ #include <linux/firmware.h> +#include <linux/iopoll.h> #include "msm_gpu.h" @@ -154,6 +155,20 @@ struct adreno_platform_config { __ret; \ }) +static inline bool adreno_is_a2xx(struct adreno_gpu *gpu) +{ + return (gpu->revn < 300); +} + +static inline bool adreno_is_a20x(struct adreno_gpu *gpu) +{ + return (gpu->revn < 210); +} + +static inline bool adreno_is_a225(struct adreno_gpu *gpu) +{ + return gpu->revn == 225; +} static inline bool adreno_is_a3xx(struct adreno_gpu *gpu) { @@ -334,6 +349,7 @@ static inline void adreno_gpu_write(struct adreno_gpu *gpu, gpu_write(&gpu->base, reg - 1, data); } +struct msm_gpu *a2xx_gpu_init(struct drm_device *dev); struct msm_gpu *a3xx_gpu_init(struct drm_device *dev); struct msm_gpu *a4xx_gpu_init(struct drm_device *dev); struct msm_gpu *a5xx_gpu_init(struct drm_device *dev); @@ -375,4 +391,9 @@ static inline uint32_t get_wptr(struct msm_ringbuffer *ring) ((1 << 29) \ ((ilog2((_len)) & 0x1F) << 24) | (((_reg) << 2) & 0xFFFFF)) + +#define gpu_poll_timeout(gpu, addr, val, cond, interval, timeout) \ + readl_poll_timeout((gpu)->mmio + ((addr) << 2), val, cond, \ + interval, timeout) + #endif /* __ADRENO_GPU_H__ */ diff --git a/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h b/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h index 15eb03bed984..79b907ac0b4b 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h +++ b/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h @@ -10,13 +10,13 @@ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: - /home/robclark/src/envytools/rnndb/adreno.xml ( 501 bytes, from 2018-07-03 19:37:13) - /home/robclark/src/envytools/rnndb/freedreno_copyright.xml ( 1572 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml ( 36805 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml ( 13634 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml ( 42585 bytes, from 2018-10-04 19:06:37) +- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml ( 42463 bytes, from 2018-11-19 13:44:03) +- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml ( 14201 bytes, from 2018-12-02 17:29:54) +- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml ( 43052 bytes, from 2018-12-02 17:29:54) - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml ( 83840 bytes, from 2018-07-03 19:37:13) - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml ( 112086 bytes, from 2018-07-03 19:37:13) -- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml ( 147240 bytes, from 2018-10-04 19:06:37) -- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml ( 139581 bytes, from 2018-10-04 19:06:42) +- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml ( 147240 bytes, from 2018-12-02 17:29:54) +- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml ( 140790 bytes, from 2018-12-02 17:29:54) - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml ( 10431 bytes, from 2018-09-14 13:03:07) - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml ( 1773 bytes, from 2018-07-03 19:37:13) @@ -108,6 +108,13 @@ enum pc_di_src_sel { DI_SRC_SEL_RESERVED = 3, }; +enum pc_di_face_cull_sel { + DI_FACE_CULL_NONE = 0, + DI_FACE_CULL_FETCH = 1, + DI_FACE_BACKFACE_CULL = 2, + DI_FACE_FRONTFACE_CULL = 3, +}; + enum pc_di_index_size { INDEX_SIZE_IGN = 0, INDEX_SIZE_16_BIT = 0, @@ -356,6 +363,7 @@ enum a6xx_render_mode { RM6_GMEM = 4, RM6_BLIT2D = 5, RM6_RESOLVE = 6, + RM6_BLIT2DSCALE = 12, }; enum pseudo_reg { |