BUG: Pahole does not create reorganization steps if structure is very large to analyze. #66
Description
@acmel, @alan-maguire,
bug preventing use pahole tool
$ ~/GIT/dwarves/build/pahole --reorganize -S --class_name=Dav1dFrameContext -j72 */*/*.o
libbpf: failed to find '.BTF' ELF section in src/libdav1d_bitdepth_16.a.p/cdef_apply_tmpl.c.o
pahole: src/libdav1d_bitdepth_16.a.p/cdef_apply_tmpl.c.o: Invalid argument
without class_name param
$ ~/GIT/dwarves/build/pahole --reorganize -S -j72 */*/*.o
struct Dav1dFrameContext {
Dav1dRef * seq_hdr_ref; /* 0 8 */
Dav1dSequenceHeader * seq_hdr; /* 8 8 */
Dav1dRef * frame_hdr_ref; /* 16 8 */
Dav1dFrameHeader * frame_hdr; /* 24 8 */
Dav1dThreadPicture refp[7]; /* 32 2072 */
/* --- cacheline 32 boundary (2048 bytes) was 56 bytes ago --- */
Dav1dPicture cur; /* 2104 272 */
/* --- cacheline 37 boundary (2368 bytes) was 8 bytes ago --- */
Dav1dThreadPicture sr_cur; /* 2376 296 */
/* --- cacheline 41 boundary (2624 bytes) was 48 bytes ago --- */
Dav1dRef * mvs_ref; /* 2672 8 */
refmvs_temporal_block * mvs; /* 2680 8 */
/* --- cacheline 42 boundary (2688 bytes) --- */
refmvs_temporal_block * ref_mvs[7]; /* 2688 56 */
Dav1dRef * ref_mvs_ref[7]; /* 2744 56 */
/* --- cacheline 43 boundary (2752 bytes) was 48 bytes ago --- */
Dav1dRef * cur_segmap_ref; /* 2800 8 */
Dav1dRef * prev_segmap_ref; /* 2808 8 */
/* --- cacheline 44 boundary (2816 bytes) --- */
uint8_t * cur_segmap; /* 2816 8 */
const uint8_t * prev_segmap; /* 2824 8 */
unsigned int refpoc[7]; /* 2832 28 */
unsigned int refrefpoc[7][7]; /* 2860 196 */
/* --- cacheline 47 boundary (3008 bytes) was 48 bytes ago --- */
CdfThreadContext in_cdf; /* 3056 24 */
/* --- cacheline 48 boundary (3072 bytes) was 8 bytes ago --- */
CdfThreadContext out_cdf; /* 3080 24 */
struct Dav1dTileGroup * tile; /* 3104 8 */
int n_tile_data_alloc; /* 3112 4 */
int n_tile_data; /* 3116 4 */
uint8_t gmv_warp_allowed[7]; /* 3120 7 */
/* XXX 1 byte hole, try to pack */
const Dav1dContext * c; /* 3128 8 */
/* --- cacheline 49 boundary (3136 bytes) --- */
Dav1dTileState * ts; /* 3136 8 */
const Dav1dDSPContext * dsp; /* 3144 8 */
struct {
recon_b_intra_fn recon_b_intra; /* 3152 8 */
recon_b_inter_fn recon_b_inter; /* 3160 8 */
filter_sbrow_fn filter_sbrow; /* 3168 8 */
filter_sbrow_fn filter_sbrow_deblock_cols; /* 3176 8 */
filter_sbrow_fn filter_sbrow_deblock_rows; /* 3184 8 */
void (*filter_sbrow_cdef)(Dav1dTaskContext *, int); /* 3192 8 */
/* --- cacheline 50 boundary (3200 bytes) --- */
filter_sbrow_fn filter_sbrow_resize; /* 3200 8 */
filter_sbrow_fn filter_sbrow_lr; /* 3208 8 */
backup_ipred_edge_fn backup_ipred_edge; /* 3216 8 */
read_coef_blocks_fn read_coef_blocks; /* 3224 8 */
copy_pal_block_fn copy_pal_block_y; /* 3232 8 */
copy_pal_block_fn copy_pal_block_uv; /* 3240 8 */
read_pal_plane_fn read_pal_plane; /* 3248 8 */
read_pal_uv_fn read_pal_uv; /* 3256 8 */
} bd_fn; /* 3152 112 */
/* --- cacheline 51 boundary (3264 bytes) --- */
int n_ts; /* 3264 4 */
int ipred_edge_sz; /* 3268 4 */
pixel * ipred_edge[3]; /* 3272 24 */
ptrdiff_t b4_stride; /* 3296 8 */
int w4; /* 3304 4 */
int h4; /* 3308 4 */
int bw; /* 3312 4 */
int bh; /* 3316 4 */
int sb128w; /* 3320 4 */
int sb128h; /* 3324 4 */
/* --- cacheline 52 boundary (3328 bytes) --- */
int sbh; /* 3328 4 */
int sb_shift; /* 3332 4 */
int sb_step; /* 3336 4 */
int sr_sb128w; /* 3340 4 */
uint16_t dq[8][3][2]; /* 3344 96 */
/* --- cacheline 53 boundary (3392 bytes) was 48 bytes ago --- */
const uint8_t * qm[19][3]; /* 3440 456 */
/* --- cacheline 60 boundary (3840 bytes) was 56 bytes ago --- */
BlockContext * a; /* 3896 8 */
/* --- cacheline 61 boundary (3904 bytes) --- */
int a_sz; /* 3904 4 */
/* XXX 4 bytes hole, try to pack */
refmvs_frame rf; /* 3912 208 */
/* --- cacheline 64 boundary (4096 bytes) was 24 bytes ago --- */
uint8_t jnt_weights[7][7]; /* 4120 49 */
/* XXX 3 bytes hole, try to pack */
/* --- cacheline 65 boundary (4160 bytes) was 12 bytes ago --- */
int bitdepth_max; /* 4172 4 */
struct ScalableMotionParams svc[7][2]; /* 4176 112 */
/* --- cacheline 67 boundary (4288 bytes) --- */
int resize_step[2]; /* 4288 8 */
int resize_start[2]; /* 4296 8 */
struct {
int next_tile_row[2]; /* 4304 8 */
atomic_int entropy_progress; /* 4312 4 */
atomic_int deblock_progress; /* 4316 4 */
atomic_uint * frame_progress; /* 4320 8 */
atomic_uint * copy_lpf_progress; /* 4328 8 */
Av1Block * b; /* 4336 8 */
int16_t * cbi; /* 4344 8 */
/* --- cacheline 68 boundary (4352 bytes) --- */
pixel * pal; /* 4352 8 */
uint8_t * pal_idx; /* 4360 8 */
coef * cf; /* 4368 8 */
int prog_sz; /* 4376 4 */
int cbi_sz; /* 4380 4 */
int pal_sz; /* 4384 4 */
int pal_idx_sz; /* 4388 4 */
int cf_sz; /* 4392 4 */
/* XXX 4 bytes hole, try to pack */
unsigned int * tile_start_off; /* 4400 8 */
} frame_thread; /* 4304 104 */
/* XXX last struct has 1 hole */
/* XXX 8 bytes hole, try to pack */
/* --- cacheline 69 boundary (4416 bytes) --- */
struct {
uint8_t * level; /* 4416 8 */
Av1Filter * mask; /* 4424 8 */
Av1Restoration * lr_mask; /* 4432 8 */
int mask_sz; /* 4440 4 */
int lr_mask_sz; /* 4444 4 */
int cdef_buf_plane_sz[2]; /* 4448 8 */
int cdef_buf_sbh; /* 4456 4 */
int lr_buf_plane_sz[2]; /* 4460 8 */
int re_sz; /* 4468 4 */
/* XXX 8 bytes hole, try to pack */
/* --- cacheline 70 boundary (4480 bytes) --- */
Av1FilterLUT lim_lut __attribute__((__aligned__(16))); /* 4480 144 */
/* --- cacheline 72 boundary (4608 bytes) was 16 bytes ago --- */
uint8_t lvl[8][4][8][2] __attribute__((__aligned__(16))); /* 4624 512 */
/* --- cacheline 80 boundary (5120 bytes) was 16 bytes ago --- */
int last_sharpness; /* 5136 4 */
/* XXX 4 bytes hole, try to pack */
uint8_t * tx_lpf_right_edge[2]; /* 5144 16 */
uint8_t * cdef_line_buf; /* 5160 8 */
uint8_t * lr_line_buf; /* 5168 8 */
pixel * cdef_line[2][3]; /* 5176 48 */
/* --- cacheline 81 boundary (5184 bytes) was 40 bytes ago --- */
pixel * cdef_lpf_line[3]; /* 5224 24 */
/* --- cacheline 82 boundary (5248 bytes) --- */
pixel * lr_lpf_line[3]; /* 5248 24 */
uint8_t * start_of_tile_row; /* 5272 8 */
int start_of_tile_row_sz; /* 5280 4 */
int need_cdef_lpf_copy; /* 5284 4 */
pixel * p[3]; /* 5288 24 */
/* --- cacheline 83 boundary (5312 bytes) --- */
pixel * sr_p[3]; /* 5312 24 */
int restore_planes; /* 5336 4 */
} __attribute__((__aligned__(16))) lf __attribute__((__aligned__(16))); /* 4416 928 */
/* XXX last struct has 4 bytes of padding, 2 holes */
struct {
pthread_mutex_t lock; /* 5344 40 */
/* --- cacheline 84 boundary (5376 bytes) was 8 bytes ago --- */
pthread_cond_t cond; /* 5384 48 */
struct TaskThreadData * ttd; /* 5432 8 */
/* --- cacheline 85 boundary (5440 bytes) --- */
struct Dav1dTask * tasks; /* 5440 8 */
struct Dav1dTask * tile_tasks[2]; /* 5448 16 */
struct Dav1dTask init_task; /* 5464 32 */
int num_tasks; /* 5496 4 */
int num_tile_tasks; /* 5500 4 */
/* --- cacheline 86 boundary (5504 bytes) --- */
atomic_int init_done; /* 5504 4 */
atomic_int done[2]; /* 5508 8 */
int retval; /* 5516 4 */
int update_set; /* 5520 4 */
atomic_int error; /* 5524 4 */
atomic_int task_counter; /* 5528 4 */
/* XXX 4 bytes hole, try to pack */
struct Dav1dTask * task_head; /* 5536 8 */
struct Dav1dTask * task_tail; /* 5544 8 */
struct Dav1dTask * task_cur_prev; /* 5552 8 */
struct {
atomic_int merge; /* 5560 4 */
/* XXX 4 bytes hole, try to pack */
/* --- cacheline 87 boundary (5568 bytes) --- */
pthread_mutex_t lock; /* 5568 40 */
Dav1dTask * head; /* 5608 8 */
Dav1dTask * tail; /* 5616 8 */
} pending_tasks; /* 5560 64 */
/* XXX last struct has 1 hole */
} task_thread; /* 5344 280 */
/* XXX last struct has 1 hole */
struct FrameTileThreadData tile_thread; /* 5624 16 */
/* XXX last struct has 4 bytes of padding */
/* size: 5648, cachelines: 89, members: 55 */
/* sum members: 5624, holes: 4, sum holes: 16 */
/* padding: 8 */
/* member types with holes: 3, total: 4 */
/* paddings: 2, sum paddings: 8 */
/* forced alignments: 1, forced holes: 1, sum forced holes: 8 */
/* last cacheline: 16 bytes */
} __attribute__((__aligned__(16)));