| Age | Commit message (Collapse) | Author |
|---|
|
This is necessary to place the libio vtables into the RELRO segment.
New tests elf/tst-relro-ldso and elf/tst-relro-libc are added to
verify that this is what actually happens.
The new tests fail on ia64 due to lack of (default) RELRO support
inbutils, so they are XFAILed there.
|
|
m68k is a non-PI_STATIC_AND_HIDDEN arch which uses a GOT relocation when
loading the address of a jump table. The GOT load may be reordered
before processing R_68K_RELATIVE relocations, leading to an
unrelocated/incorrect jump table, which will cause a crash.
The foolproof approach is to add an optimization barrier (e.g. calling
an non-inlinable function after relative relocations are resolved). That
is non-trivial given the current code structure, so just use the simple
approach to avoid the jump table: handle only the essential reloctions
for RTLD_BOOTSTRAP code.
This is based on Andreas Schwab's patch and fixed ld.so crash on m68k.
Reviewed-by: Adheemrval Zanella <adhemerval.zanella@linaro.org>
|
|
commit 8804157ad9da39631703b92315460808eac86b0c
Author: Noah Goldstein <goldstein.w.n@gmail.com>
Date: Fri Apr 15 12:27:59 2022 -0500
x86: Optimize memcmp SSE2 in memcmp.S
Only defined wmemcmp and missed __wmemcmp. This commit fixes that by
defining __wmemcmp and setting wmemcmp as a weak alias to __wmemcmp.
Both multiarch and disable-multiarch builds succeed and full xchecks
pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
After 73fc4e28b9464f0e13edc719a5372839970e7ddb,
__libc_enable_secure_decided is always 0 and a statically linked
executable may overwrite __libc_enable_secure without considering
AT_SECURE.
The __libc_enable_secure has been correctly initialized in _dl_aux_init,
so just remove __libc_enable_secure_decided and __libc_init_secure.
This allows us to remove some startup_get*id functions from
22b79ed7f413cd980a7af0cf258da5bf82b6d5e5.
Reviewed-by: Florian Weimer <fweimer@redhat.com>
|
|
Add missing support initially added by 4e8521333bea6e89fcef1020
(which missed n32 stat).
|
|
Old code was both inefficient and wasted code size. New code (-62
bytes) and comparable or better performance in the page cross case.
geometric_mean(N=20) of page cross cases New / Original: 0.960
size, align0, align1, ret, New Time/Old Time
1, 4095, 0, 0, 1.001
1, 4095, 0, 1, 0.999
1, 4095, 0, -1, 1.0
2, 4094, 0, 0, 1.0
2, 4094, 0, 1, 1.0
2, 4094, 0, -1, 1.0
3, 4093, 0, 0, 1.0
3, 4093, 0, 1, 1.0
3, 4093, 0, -1, 1.0
4, 4092, 0, 0, 0.987
4, 4092, 0, 1, 1.0
4, 4092, 0, -1, 1.0
5, 4091, 0, 0, 0.984
5, 4091, 0, 1, 1.002
5, 4091, 0, -1, 1.005
6, 4090, 0, 0, 0.993
6, 4090, 0, 1, 1.001
6, 4090, 0, -1, 1.003
7, 4089, 0, 0, 0.991
7, 4089, 0, 1, 1.0
7, 4089, 0, -1, 1.001
8, 4088, 0, 0, 0.875
8, 4088, 0, 1, 0.881
8, 4088, 0, -1, 0.888
9, 4087, 0, 0, 0.872
9, 4087, 0, 1, 0.879
9, 4087, 0, -1, 0.883
10, 4086, 0, 0, 0.878
10, 4086, 0, 1, 0.886
10, 4086, 0, -1, 0.873
11, 4085, 0, 0, 0.878
11, 4085, 0, 1, 0.881
11, 4085, 0, -1, 0.879
12, 4084, 0, 0, 0.873
12, 4084, 0, 1, 0.889
12, 4084, 0, -1, 0.875
13, 4083, 0, 0, 0.873
13, 4083, 0, 1, 0.863
13, 4083, 0, -1, 0.863
14, 4082, 0, 0, 0.838
14, 4082, 0, 1, 0.869
14, 4082, 0, -1, 0.877
15, 4081, 0, 0, 0.841
15, 4081, 0, 1, 0.869
15, 4081, 0, -1, 0.876
16, 4080, 0, 0, 0.988
16, 4080, 0, 1, 0.99
16, 4080, 0, -1, 0.989
17, 4079, 0, 0, 0.978
17, 4079, 0, 1, 0.981
17, 4079, 0, -1, 0.98
18, 4078, 0, 0, 0.981
18, 4078, 0, 1, 0.98
18, 4078, 0, -1, 0.985
19, 4077, 0, 0, 0.977
19, 4077, 0, 1, 0.979
19, 4077, 0, -1, 0.986
20, 4076, 0, 0, 0.977
20, 4076, 0, 1, 0.986
20, 4076, 0, -1, 0.984
21, 4075, 0, 0, 0.977
21, 4075, 0, 1, 0.983
21, 4075, 0, -1, 0.988
22, 4074, 0, 0, 0.983
22, 4074, 0, 1, 0.994
22, 4074, 0, -1, 0.993
23, 4073, 0, 0, 0.98
23, 4073, 0, 1, 0.992
23, 4073, 0, -1, 0.995
24, 4072, 0, 0, 0.989
24, 4072, 0, 1, 0.989
24, 4072, 0, -1, 0.991
25, 4071, 0, 0, 0.99
25, 4071, 0, 1, 0.999
25, 4071, 0, -1, 0.996
26, 4070, 0, 0, 0.993
26, 4070, 0, 1, 0.995
26, 4070, 0, -1, 0.998
27, 4069, 0, 0, 0.993
27, 4069, 0, 1, 0.999
27, 4069, 0, -1, 1.0
28, 4068, 0, 0, 0.997
28, 4068, 0, 1, 1.0
28, 4068, 0, -1, 0.999
29, 4067, 0, 0, 0.996
29, 4067, 0, 1, 0.999
29, 4067, 0, -1, 0.999
30, 4066, 0, 0, 0.991
30, 4066, 0, 1, 1.001
30, 4066, 0, -1, 0.999
31, 4065, 0, 0, 0.988
31, 4065, 0, 1, 0.998
31, 4065, 0, -1, 0.998
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
Code didn't actually use any sse4 instructions since `ptest` was
removed in:
commit 2f9062d7171850451e6044ef78d91ff8c017b9c0
Author: Noah Goldstein <goldstein.w.n@gmail.com>
Date: Wed Nov 10 16:18:56 2021 -0600
x86: Shrink memcmp-sse4.S code size
The new memcmp-sse2 implementation is also faster.
geometric_mean(N=20) of page cross cases SSE2 / SSE4: 0.905
Note there are two regressions preferring SSE2 for Size = 1 and Size =
65.
Size = 1:
size, align0, align1, ret, New Time/Old Time
1, 1, 1, 0, 1.2
1, 1, 1, 1, 1.197
1, 1, 1, -1, 1.2
This is intentional. Size == 1 is significantly less hot based on
profiles of GCC11 and Python3 than sizes [4, 8] (which is made
hotter).
Python3 Size = 1 -> 13.64%
Python3 Size = [4, 8] -> 60.92%
GCC11 Size = 1 -> 1.29%
GCC11 Size = [4, 8] -> 33.86%
size, align0, align1, ret, New Time/Old Time
4, 4, 4, 0, 0.622
4, 4, 4, 1, 0.797
4, 4, 4, -1, 0.805
5, 5, 5, 0, 0.623
5, 5, 5, 1, 0.777
5, 5, 5, -1, 0.802
6, 6, 6, 0, 0.625
6, 6, 6, 1, 0.813
6, 6, 6, -1, 0.788
7, 7, 7, 0, 0.625
7, 7, 7, 1, 0.799
7, 7, 7, -1, 0.795
8, 8, 8, 0, 0.625
8, 8, 8, 1, 0.848
8, 8, 8, -1, 0.914
9, 9, 9, 0, 0.625
Size = 65:
size, align0, align1, ret, New Time/Old Time
65, 0, 0, 0, 1.103
65, 0, 0, 1, 1.216
65, 0, 0, -1, 1.227
65, 65, 0, 0, 1.091
65, 0, 65, 1, 1.19
65, 65, 65, -1, 1.215
This is because A) the checks in range [65, 96] are now unrolled 2x
and B) because smaller values <= 16 are now given a hotter path. By
contrast the SSE4 version has a branch for Size = 80. The unrolled
version has get better performance for returns which need both
comparisons.
size, align0, align1, ret, New Time/Old Time
128, 4, 8, 0, 0.858
128, 4, 8, 1, 0.879
128, 4, 8, -1, 0.888
As well, out of microbenchmark environments that are not full
predictable the branch will have a real-cost.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
New code save size (-303 bytes) and has significantly better
performance.
geometric_mean(N=20) of page cross cases New / Original: 0.634
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
The loader does not need to pull all __get_errlist definitions
and its size is decreased:
Before:
$ size elf/ld.so
text data bss dec hex filename
197774 11024 456 209254 33166 elf/ld.so
After:
$ size elf/ld.so
text data bss dec hex filename
191510 9936 456 201902 314ae elf/ld.so
Checked on x86_64-linux-gnu.
|
|
The goal is to remove most SSSE3 function as SSE4, AVX2, and EVEX are
generally preferable. memcpy/memmove is one exception where avoiding
unaligned loads with `palignr` is important for some targets.
This commit replaces memmove-ssse3 with a better optimized are lower
code footprint verion. As well it aliases memcpy to memmove.
Aside from this function all other SSSE3 functions should be safe to
remove.
The performance is not changed drastically although shows overall
improvements without any major regressions or gains.
bench-memcpy geometric_mean(N=50) New / Original: 0.957
bench-memcpy-random geometric_mean(N=50) New / Original: 0.912
bench-memcpy-large geometric_mean(N=50) New / Original: 0.892
Benchmarks where run on Zhaoxin KX-6840@2000MHz See attached numbers
for all results.
More important this saves 7246 bytes of code size in memmove an
additional 10741 bytes by reusing memmove code for memcpy (total 17987
bytes saves). As well an additional 896 bytes of rodata for the jump
table entries.
|
|
With SSE2, SSE4.1, AVX2, and EVEX versions very few targets prefer
SSSE3. As a result it is no longer worth it to keep the SSSE3
versions given the code size cost.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
With SSE2, SSE4.1, AVX2, and EVEX versions very few targets prefer
SSSE3. As a result it is no longer worth it to keep the SSSE3
versions given the code size cost.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
With SSE2, SSE4.1, AVX2, and EVEX versions very few targets prefer
SSSE3. As a result it is no longer worth it to keep the SSSE3
versions given the code size cost.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
With SSE2, SSE4.1, AVX2, and EVEX versions very few targets prefer
SSSE3. As a result it is no longer worth it to keep the SSSE3
versions given the code size cost.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
With SSE2, SSE4.1, AVX2, and EVEX versions very few targets prefer
SSSE3. As a result it is no longer worth it to keep the SSSE3
versions given the code size cost.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
Some Linux interfaces never restart after being interrupted by a signal
handler, regardless of the use of SA_RESTART [1]. It means that for
pthread cancellation, if the target thread disables cancellation with
pthread_setcancelstate and calls such interfaces (like poll or select),
it should not see spurious EINTR failures due the internal SIGCANCEL.
However recent changes made pthread_cancel to always sent the internal
signal, regardless of the target thread cancellation status or type.
To fix it, the previous semantic is restored, where the cancel signal
is only sent if the target thread has cancelation enabled in
asynchronous mode.
The cancel state and cancel type is moved back to cancelhandling
and atomic operation are used to synchronize between threads. The
patch essentially revert the following commits:
8c1c0aae20 nptl: Move cancel type out of cancelhandling
2b51742531 nptl: Move cancel state out of cancelhandling
26cfbb7162 nptl: Remove CANCELING_BITMASK
However I changed the atomic operation to follow the internal C11
semantic and removed the MACRO usage, it simplifies a bit the
resulting code (and removes another usage of the old atomic macros).
Checked on x86_64-linux-gnu, i686-linux-gnu, aarch64-linux-gnu,
and powerpc64-linux-gnu.
[1] https://man7.org/linux/man-pages/man7/signal.7.html
Reviewed-by: Florian Weimer <fweimer@redhat.com>
Tested-by: Aurelien Jarno <aurelien@aurel32.net>
|
|
The new IBM z16 is added to platform string array.
The macro _DL_PLATFORMS_COUNT is incremented.
_dl_hwcaps_subdir is extended by "z16" if HWCAP_S390_VXRS_PDE2
is set. HWCAP_S390_NNPA is not tested in _dl_hwcaps_subdirs_active
as those instructions may be replaced or removed in future.
tst-glibc-hwcaps.c is extended in order to test z16 via new marker5.
A fatal glibc error is dumped if glibc was build with architecture
level set for z16, but run on an older machine. (See dl-hwcap-check.h)
|
|
On 32-bit machines this has no affect. On 64-bit machines
{u}int_fast{16|32} are set as {u}int64_t which is often not
ideal. Particularly x86_64 this change both saves code size and
may save instruction cost.
Full xcheck passes on x86_64.
|
|
So we can implement it in the exec server.
|
|
It does not seem to be used.
Reviewed-by: Florian Weimer <fweimer@redhat.com>
|
|
The 32-bit and 64-bit variants of RISC-V share the same name - "RISC-V"
- when generating the libm error table for the info pages. This
collision, and the way how the table is generated, mean that the values
in the final table for "RISC-V" may be either for the 32- or 64-bit
variant, with no indication as to which.
As an additional side-effect, this makes the build non-reproducible, as
the error table generated is dependent upon the host filesystem
implementation.
To solve this issue, the libm-test-ulps-name files for both variants
have been modified to include their word size, so as to remove the
collision and provide more accurate information in the table.
An alternative proposed was to merge the two variants' ULP values into a
single file, but this would mean that information about error values is
lost, as the two variants are not identical. Some differences are
considerable, notably the values for the exp() function are large.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
|
|
start_addresses in sysdeps/powerpc/powerpc64/start.S is historical
baggage that should disappear. Until someone does that, relocating
stinfo->main by hand is one solution to the fact that the field may be
unrelocated at the time it is accessed. This is similar to what is
done for dynamic tags via the D_PTR macro. stinfo->init and
stinfo->fini are zero in both powerpc64/start.S and powerpc32/start.S,
so make it a little more obvious they are unused by passing NULLs to
LIBC_START_MAIN. The makefile change is needed to pick up
elf/dl-static-tls.h from dl-machine.h.
Reviewed-by: Tulio Magno Quites Machado Filho <tuliom@linux.ibm.com>
|
|
libgcc ifunc resolvers that access hwcap via a field in the tcb can't
be called until the thread pointer is set up. Other ifunc resolvers
might need access to at_platform. This patch sets up a fake thread
pointer early to a copy of tcbhead_t. hwcapinfo.c already had local
variables for hwcap and at_platform, replace them with an entire
tcbhead_t. It's not that large and this way we easily ensure hwcap
and at_platform are at the same relative offsets as they are in the
real thread block.
The patch also conditionally disables part of tst-tlsifunc-static,
"bar address read from IFUNC resolver is incorrect". We can't get a
proper address for a thread variable before glibc initialises tls.
Reviewed-by: Tulio Magno Quites Machado Filho <tuliom@linux.ibm.com>
|
|
The PowerPC64 linker edits medium model toc-indirect code to toc-pointer
relative:
addis r9,r2,tc_entry_for_var@toc@ha
ld r9,tc_entry_for_var@toc@l(r9)
becomes
addis r9,r2,(var-.TOC.)@ha
addi r9,r9,(var-.TOC.)@l
when "var" is known to be local to the binary. This isn't done for
small-model toc-indirect code, because "var" is almost guaranteed to
be too far away from .TOC. for a 16-bit signed offset. And, because
the analysis of which .toc entry can be removed becomes much more
complicated in objects that mix code models, they aren't removed if
any small-model toc sequence appears in an object file.
Unfortunately, glibc's build of ld.so smashes the needed objects
together in a ld -r linking stage. This means the GOT/TOC is left
with a whole lot of relative relocations which is untidy, but in
itself is not a serious problem. However, static-pie on powerpc64
bombs due to a segfault caused by one of the small-model accesses
before _dl_relocate_static_pie. (The very first one in rcrt1.o
passing start_addresses in r8 to __libc_start_main.)
So this patch makes all the toc/got accesses in assembly medium code
model, and a couple of functions hidden. By itself this is not
enough to give us working static-pie, but it is useful in isolation to
enable better linker optimisation.
There's a serious problem in libgcc too. libgcc ifuncs access the
AT_HWCAP words stored in the tcb with an offset from the thread
pointer (r13), but r13 isn't set at the time _dl_relocate_static_pie.
A followup patch will fix that.
Reviewed-by: Tulio Magno Quites Machado Filho <tuliom@linux.ibm.com>
|
|
Compilers may decide to put the rfv variable in .data rather than on
the stack. It's slightly better to put it in .data.rel.ro.local
instead. Regardles of that, making it const may enable further
optimisations. Found when examining relative relocations (GOT ones
in particular) as part of enabling static-pie for PowerPC64.
|
|
The builtin from generic code generates similar compliant sequence.
Checked on sparc64-linux-gnu.
|
|
The generic code already uses builtins.
|
|
All architectures that uses it (x86, ia64, m68k) implement the
builtin.
Checked on x86_64-linux-gnu and ia64-linux-gnu.
|
|
The builtin used by generic code generates similar code.
Checked on ia64-linux-gnu.
|
|
The builtin used by generic code generates similar code.
Checked on x86_64-linux-gnu and i686-linux-gnu.
|
|
The builtin and generic implementation from generic files are suffice.
Checked on powerpc64-linux-gnu and powerpc-linux-gnu.
|
|
Checked on x86_64-linux-gnu.
|
|
The __closefrom_fallback tries to get a available file descriptor
if the initial open ("/proc/self/fd/", ...) fails. It assumes the
failure would be only if procfs is not mount (ENOENT), however if
the the proc file is not accessible (due some other kernel filtering
such apparmor) it will iterate over a potentially large file set
issuing close calls.
It should only try the close fallback if open returns EMFILE,
ENFILE, or ENOMEM.
Checked on x86_64-linux-gnu.
|
|
-z combreloc has been the default regadless of the architecture since
binutils commit f4d733664aabd7bd78c82895e030ec9779a92809 (2002). The
configure check added in commit fdde83499a05 (2001) has long been
unneeded.
We can therefore treat HAVE_Z_COMBRELOC as always 1 and delete dead code
paths in dl-machine.h files (many were copied from commit a711b01d34ca
and ee0cb67ec238).
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
|
|
For sparc64 is the same as the generic implementation, while for
sparc32 the builtin generates the same code.
Checked on sparc64-linux-gnu and sparcv9-linux-gnu.
|
|
The generic implementation fixes 5 fabs tests on ia64-linux-gnu:
math/test-double-fabs
math/test-float-fabs
math/test-float32-fabs
math/test-float32x-fabs
math/test-float64-fabs
Checked on ia64-linux-gnu.
|
|
For x86_64 is the same as the generic implementation, while for i686
the builtin generates the same code.
|
|
The generic implementation already uses builtins.
|
|
Just a few QOL changes.
1. Prefer `add` > `lea` as it has high execution units it can run
on.
2. Don't break macro-fusion between `test` and `jcc`
3. Reduce code size by removing gratuitous padding bytes (-90
bytes).
geometric_mean(N=20) of all benchmarks New / Original: 0.959
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
Just a few small QOL changes.
1. Prefer `add` > `lea` as it has high execution units it can run
on.
2. Don't break macro-fusion between `test` and `jcc`
geometric_mean(N=20) of all benchmarks New / Original: 0.973
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
Add the new HWCAP2_AFP and HWCAP2_RPRES constants from Linux 5.17.
Tested with build-many-glibcs.py for aarch64-linux-gnu.
|
|
The rational is:
1. SSE42 has nearly identical logic so any benefit is minimal (3.4%
regression on Tigerlake using SSE42 versus AVX across the
benchtest suite).
2. AVX2 version covers the majority of targets that previously
prefered it.
3. The targets where AVX would still be best (SnB and IVB) are
becoming outdated.
All in all the saving the code size is worth it.
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
geometric_mean(N=40) of all benchmarks EVEX / SSE42: .621
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
geometric_mean(N=40) of all benchmarks AVX2 / SSE42: .702
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
Slightly faster method of doing TOLOWER that saves an
instruction.
Also replace the hard coded 5-byte no with .p2align 4. On builds with
CET enabled this misaligned entry to strcasecmp.
geometric_mean(N=40) of all benchmarks New / Original: .920
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
Slightly faster method of doing TOLOWER that saves an
instruction.
Also replace the hard coded 5-byte no with .p2align 4. On builds with
CET enabled this misaligned entry to strcasecmp.
geometric_mean(N=40) of all benchmarks New / Original: .894
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
Overflow case for __wcsncmp_avx2_rtm should be __wcscmp_avx2_rtm not
__wcscmp_avx2.
commit ddf0992cf57a93200e0c782e2a94d0733a5a0b87
Author: Noah Goldstein <goldstein.w.n@gmail.com>
Date: Sun Jan 9 16:02:21 2022 -0600
x86: Fix __wcsncmp_avx2 in strcmp-avx2.S [BZ# 28755]
Set the wrong fallback function for `__wcsncmp_avx2_rtm`. It was set
to fallback on to `__wcscmp_avx2` instead of `__wcscmp_avx2_rtm` which
can cause spurious aborts.
This change will need to be backported.
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
The generic implementation is faster.
geometric_mean(N=20) of all benchmarks New / Original: .710
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
The generic implementation is faster (see strcspn commit).
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
The generic implementation is faster.
geometric_mean(N=20) of all benchmarks New / Original: .678
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
