Commit Graph

2392 Commits

Author SHA1 Message Date
Denys Vlasenko
1f272c06d0 whitespace fixes
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-11 23:03:27 +01:00
Denys Vlasenko
dda77e8376 libbb/sha1: revert last commit: pshufb is a SSSE3 insn, can't use it
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-11 14:53:26 +01:00
Denys Vlasenko
8154146be4 libbb/sha1: shrink unrolled x86-64 code
function                                             old     new   delta
sha1_process_block64                                3481    3384     -97

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-11 06:08:27 +01:00
Denys Vlasenko
6f56fa1713 libbb/sha: improve comments
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-10 15:38:10 +01:00
Denys Vlasenko
6a6c1c0ea9 whitespace fix
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-09 11:29:23 +01:00
Denys Vlasenko
caa9c4f707 libbb/sha256: code shrink in x86 assembly
function                                             old     new   delta
sha256_process_block64_shaNI 32-bit                  676     673      -3
sha256_process_block64_shaNI 64-bit                  680     677      -3

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-09 01:50:22 +01:00
Denys Vlasenko
11bcea7ac0 libbb/sha256: code shrink in 64-bit x86
function                                             old     new   delta
sha256_process_block64_shaNI                         701     680     -21

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-09 01:42:49 +01:00
Denys Vlasenko
461a994b09 libbb/sha256: code shrink in 32-bit x86
function                                             old     new   delta
sha256_process_block64_shaNI                         697     676     -21

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-09 01:30:23 +01:00
Denys Vlasenko
c0ff0d4528 libbb/sha256: code shrink in 32-bit x86
function                                             old     new   delta
sha256_process_block64_shaNI                         713     697     -16

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-09 00:33:39 +01:00
Denys Vlasenko
eb8d5f3b8f libbb/sha1: shrink x86 hardware accelerated hashing (32-bit)
function                                             old     new   delta
sha1_process_block64_shaNI                           511     507      -4

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-08 15:34:02 +01:00
Denys Vlasenko
eb52e7fa52 libbb/sha1: shrink x86 hardware accelerated hashing (32-bit)
function                                             old     new   delta
sha1_process_block64_shaNI                           517     511      -6

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-08 15:23:26 +01:00
Denys Vlasenko
71a1cccaad libbb/sha1: shrink x86 hardware accelerated hashing
function                                             old     new   delta
sha1_process_block64_shaNI 32-bit                    524     517      -7
sha1_process_block64_shaNI 64-bit                    510     508      -2

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-08 08:22:17 +01:00
Denys Vlasenko
4923f74e58 libbb/sha1: shrink unrolled x86-64 code
function                                             old     new   delta
sha1_process_block64                                3482    3481      -1
.rodata                                           108460  108412     -48
------------------------------------------------------------------------------
(add/remove: 1/4 grow/shrink: 0/2 up/down: 0/-49)             Total: -49 bytes

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-08 03:29:16 +01:00
Denys Vlasenko
c193cbd6df libbb/sha1: shrink and speed up unrolled x86-64 code
function                                             old     new   delta
sha1_process_block64                                3514    3482     -32

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-07 02:34:04 +01:00
Denys Vlasenko
987be932ed *: slap on a few ALIGN_PTR where appropriate
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-06 20:07:12 +01:00
Denys Vlasenko
ca466f385a *: slap on a few ALIGN* where appropriate
The result of looking at "grep -F -B2 '*fill*' busybox_unstripped.map"

function                                             old     new   delta
.rodata                                           108586  108460    -126
------------------------------------------------------------------------------
(add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-126)           Total: -126 bytes
   text	   data	    bss	    dec	    hex	filename
 970412	   4219	   1848	 976479	  ee65f	busybox_old
 970286	   4219	   1848	 976353	  ee5e1	busybox_unstripped

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-06 19:53:10 +01:00
Denys Vlasenko
4f40735c87 libbb/sha256: code shrink in 32-bit x86
function                                             old     new   delta
sha256_process_block64_shaNI                         722     713      -9

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-06 00:56:13 +01:00
Denys Vlasenko
31c1c31077 libbb/sha256: code shrink in 64-bit x86
function                                             old     new   delta
sha256_process_block64_shaNI                         706     701      -5

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-06 00:33:42 +01:00
Denys Vlasenko
a1429fbb8c libbb/sha256: code shrink in 64-bit x86
function                                             old     new   delta
sha256_process_block64_shaNI                         730     706     -24

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-03 15:17:42 +01:00
Denys Vlasenko
de6cb4bed8 libbb/sha256: code shrink in 32-bit x86
function                                             old     new   delta
sha256_process_block64_shaNI                         747     722     -25

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-03 15:11:23 +01:00
Denys Vlasenko
6472ac9428 libbb/sha256: optional x86 hardware accelerated hashing
64 bit:
function                                             old     new   delta
sha256_process_block64_shaNI                           -     730    +730
.rodata                                           108314  108586    +272
sha256_begin                                          31      83     +52
------------------------------------------------------------------------------
(add/remove: 5/1 grow/shrink: 2/0 up/down: 1055/-1)          Total: 1054 bytes

32 bit:
function                                             old     new   delta
sha256_process_block64_shaNI                           -     747    +747
.rodata                                           104318  104590    +272
sha256_begin                                          29      84     +55
------------------------------------------------------------------------------
(add/remove: 5/1 grow/shrink: 2/0 up/down: 1075/-1)          Total: 1074 bytes

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-02-03 14:58:02 +01:00
Denys Vlasenko
205042c07a libbb/sha1: in unrolled x86-64 code, pass initial W[] in registers, not on stack
This can be faster on some CPUs.
On Skylake, evidently load latency from L1 (or store-to-load
forwarding in LSU) is fast enough to completely hide
memory reference latencies here.

function                                             old     new   delta
sha1_process_block64                                3495    3514     +19

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-25 17:21:45 +01:00
Denys Vlasenko
99e22d230d cut: build fix for FEATURE_CUT_REGEX
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-24 07:07:17 +01:00
Denys Vlasenko
39369ff460 libbb/sha1: use SSE2 in unrolled x86-64 code. ~10% faster
function                                             old     new   delta
.rodata                                           108241  108305     +64
sha1_process_block64                                3502    3495      -7
------------------------------------------------------------------------------
(add/remove: 5/0 grow/shrink: 1/1 up/down: 64/-7)              Total: 57 bytes

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-23 12:57:27 +01:00
Denys Vlasenko
1e825acf8d libbb: shrink lineedit_read_key()
function                                             old     new   delta
lineedit_read_key                                    237     231      -6

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-18 00:36:42 +01:00
Denys Vlasenko
12566e7f9b ash,hush: fix handling of SIGINT while waiting for interactive input
function                                             old     new   delta
lineedit_read_key                                    160     237     +77
__pgetc                                              522     589     +67
fgetc_interactive                                    244     309     +65
safe_read_key                                          -      39     +39
read_key                                             588     607     +19
record_pending_signo                                  23      32      +9
signal_handler                                        75      81      +6
.rodata                                           104312  104309      -3
------------------------------------------------------------------------------
(add/remove: 1/0 grow/shrink: 6/1 up/down: 282/-3)            Total: 279 bytes

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-17 11:46:23 +01:00
Denys Vlasenko
c2788f88f4 libbb: introduce and use chdir_or_warn()
function                                             old     new   delta
chdir_or_warn                                          -      37     +37
send_cgi_and_exit                                    720     711      -9
xchdir                                                27      15     -12
setup_environment                                    233     217     -16
fork_job                                             449     433     -16
------------------------------------------------------------------------------
(add/remove: 1/0 grow/shrink: 0/4 up/down: 37/-53)            Total: -16 bytes

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-13 12:56:10 +01:00
Denys Vlasenko
931c55f9e2 libbb: invert the meaning of SETUP_ENV_NO_CHDIR -> SETUP_ENV_CHDIR
Double negatives are hard to grok.

function                                             old     new   delta
login_main                                           986     988      +2
su_main                                              474     470      -4
------------------------------------------------------------------------------
(add/remove: 0/0 grow/shrink: 1/1 up/down: 2/-4)               Total: -2 bytes

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-13 12:50:48 +01:00
Denys Vlasenko
d162a7b978 sulogin: increase util-linux compatibility
Change to root's HOME. Set some envvars. Steal ctty if necessary and possible.

function                                             old     new   delta
sulogin_main                                         240     340    +100
setup_environment                                    225     233      +8
su_main                                              479     474      -5
------------------------------------------------------------------------------
(add/remove: 0/0 grow/shrink: 2/1 up/down: 108/-5)            Total: 103 bytes

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-12 23:19:11 +01:00
Denys Vlasenko
143356876b libbb/sha1: add a comment
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-08 22:43:24 +01:00
Denys Vlasenko
e7ff29402d libbb/sha1: simplify cpuid code
function                                             old     new   delta
sha1_begin                                           107     106      -1

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-08 01:25:23 +01:00
Denys Vlasenko
805ececa61 whitespace fix
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-08 00:41:09 +01:00
Denys Vlasenko
0bab5da37e libbb/sha1: tweak comments
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-07 14:55:31 +01:00
Denys Vlasenko
a96ccbefe4 libbb/sha1: optional i686 hardware accelerates hashing
function                                             old     new   delta
sha1_process_block64_shaNI                             -     524    +524
sha1_begin                                            57     114     +57
.rodata                                           104353  104369     +16
static.shaNI                                           -       1      +1
------------------------------------------------------------------------------
(add/remove: 4/0 grow/shrink: 2/0 up/down: 598/0)             Total: 598 bytes

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-07 01:32:13 +01:00
Denys Vlasenko
711e20ecb8 libbb/sha1: optional x86-64 hardware accelerates hashing
function                                             old     new   delta
sha1_process_block64_shaNI                             -     510    +510
sha1_begin                                            52     107     +55
.rodata                                           108285  108301     +16
static.shaNI                                           -       1      +1
------------------------------------------------------------------------------
(add/remove: 4/0 grow/shrink: 2/0 up/down: 582/0)             Total: 582 bytes

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-07 00:43:59 +01:00
Denys Vlasenko
6062c0d19b libbb: change xstrndup, xmemdup to take size_t as size parameter
Also, remove entirely usually-disabled paranoia check (was also using
wrong config option to enable itself).

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-05 23:03:54 +01:00
Denys Vlasenko
db5546ca10 libbb: code shrink: introduce and use [_]exit_SUCCESS()
function                                             old     new   delta
exit_SUCCESS                                           -       7      +7
_exit_SUCCESS                                          -       7      +7
run_pipe                                            1562    1567      +5
pseudo_exec_argv                                     399     400      +1
finish                                                86      87      +1
start_stop_daemon_main                              1109    1107      -2
shutdown_on_signal                                    38      36      -2
runsv_main                                          1662    1660      -2
redirect                                            1070    1068      -2
read_line                                             79      77      -2
pause_and_low_level_reboot                            54      52      -2
list_i2c_busses_and_exit                             483     481      -2
less_exit                                             12      10      -2
identify                                            4123    4121      -2
grep_file                                           1161    1159      -2
getty_main                                          1519    1517      -2
fsck_minix_main                                     2681    2679      -2
free_session                                         132     130      -2
fdisk_main                                          4739    4737      -2
clean_up_and_exit                                     53      51      -2
bsd_select                                          1566    1564      -2
bb_daemonize_or_rexec                                198     196      -2
------------------------------------------------------------------------------
(add/remove: 2/0 grow/shrink: 3/17 up/down: 21/-34)           Total: -13 bytes

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-05 22:16:06 +01:00
Denys Vlasenko
dfd8aafcf5 libbb: fflush_stdout_and_exit(0) still exits with _error_ (not 0!) if fflush fails
function                                             old     new   delta
fflush_stdout_and_exit                                36      40      +4

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-04 23:36:16 +01:00
Denys Vlasenko
31f45c1b36 libbb: factor out fflush_stdout_and_exit(EXIT_SUCCESS)
function                                             old     new   delta
fflush_stdout_and_exit_SUCCESS                         -       7      +7
xxd_main                                             890     888      -2
vlock_main                                           353     351      -2
uuencode_main                                        318     316      -2
uniq_main                                            427     425      -2
uname_main                                           250     248      -2
sort_main                                            853     851      -2
shuf_main                                            500     498      -2
route_main                                           238     236      -2
readlink_main                                        113     111      -2
nice_main                                            156     154      -2
last_main                                            957     955      -2
ipcs_main                                            960     958      -2
env_main                                             209     207      -2
chrt_main                                            464     462      -2
cal_main                                             921     919      -2
baseNUM_main                                         650     648      -2
------------------------------------------------------------------------------
(add/remove: 1/0 grow/shrink: 0/16 up/down: 7/-32)            Total: -25 bytes

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-04 23:31:58 +01:00
Denys Vlasenko
c3cfcc9242 libbb/sha1: x86_64 version: reorder prologue/epilogue insns
Not clear exactly why, but this increases hashing speed
on Skylake from 454 MB/s to 464 MB/s.

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-04 01:45:52 +01:00
Denys Vlasenko
7abb2bb96e libbb/sha1: x86_64 version: tidying up, no code changes
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-03 17:02:48 +01:00
Denys Vlasenko
4387077f8e typo fix
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-03 13:14:09 +01:00
Denys Vlasenko
947bef0dea libbb/sha1: x86_64 version: generate from a script, optimize a bit
function                                             old     new   delta
sha1_process_block64                                3569    3502     -67

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-03 13:10:30 +01:00
Denys Vlasenko
05fd13ebec libbb/sha1: x86_64 version: move to a separate .S file, no code changes
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-03 12:57:36 +01:00
Denys Vlasenko
5c0c558231 libbb/sha1: code shrink in medium-speed version
function                                             old     new   delta
sha1_process_block64                                 654     641     -13

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-02 01:56:35 +01:00
Denys Vlasenko
4d4f1f2096 libbb/sha1: x86_64 version: bswap in 64-bit chunks
function                                             old     new   delta
sha1_process_block64                                3562    3570      +8

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-01 15:42:15 +01:00
Denys Vlasenko
d643010fee libbb/sha1: shrink x86_64 version - use r8..15 for W[8..15]
function                                             old     new   delta
sha1_process_block64                                3683    3562    -121

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-01 15:01:53 +01:00
Denys Vlasenko
5f68170204 libbb/sha1: assembly versions for x86
32 bits:
function                                             old     new   delta
sha1_process_block64                                3950    3657    -293
64 bits:
sha1_process_block64                                4167    3683    -484

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2022-01-01 13:57:34 +01:00
Denys Vlasenko
f09d088fdf libbb/sha1: shrink and speed up fully unrolled version
function                                             old     new   delta
sha1_process_block64                                4149    3950    -199

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2021-12-31 17:07:47 +01:00
Denys Vlasenko
0b62a08777 libbb/sha1: add config-selectable partially unrolled version
function                                             old     new   delta
sha1_process_block64                                 364     732    +368
static.rconsts                                        16       -     -16
------------------------------------------------------------------------------
(add/remove: 0/1 grow/shrink: 1/0 up/down: 368/-16)           Total: 352 bytes

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2021-12-30 18:54:02 +01:00