System calls can be pretty slow. This is mako, which has one of our
lowest latencies:
iterations ns/op
BM_unistd_getpid 10000000 209
BM_unistd_gettid 200000000 8
Bug: 15297299 (kernel panic from too many gettid calls)
Bug: 15315766 (excessive gettid overhead in liblogd)
Change-Id: I49656c0fc5b5d092390264a59e4f2c0d8a8b1aeb
The syscall generation always used 4 bytes for each push cfi directive.
However, the first push should always use an offset of 8 bytes, each
subsequent push after that is only 4 bytes though.
Change-Id: Ibaabd107f399ef67010b9a08213783957c2f74a9
There are no substantive changes to the data in this release. I'm applying
this just for completeness.
Change-Id: Ibe953969cb16db4d8d1ddb7dd3c943316e6e46b4
The problem with the original patch was that using syscall(3) means that
errno can be set, but pthread_create(3) was abusing the TLS errno slot as
a pthread_mutex_t for the thread startup handshake.
There was also a mistake in the check for syscall failures --- it should
have checked against -1 instead of 0 (not just because that's the default
idiom, but also here because futex(2) can legitimately return values > 0).
This patch stops abusing the TLS errno slot and adds a pthread_mutex_t to
pthread_internal_t instead. (Note that for LP64 sizeof(pthread_mutex_t) >
sizeof(uintptr_t), so we could potentially clobber other TLS slots too.)
I've also rewritten the LP32 compatibility stubs to directly reuse the
code from the .h file.
This reverts commit 75c55ff84e.
Bug: 15195455
Change-Id: I6ffb13e5cf6a35d8f59f692d94192aae9ab4593d
The comment used the phrase "normal case" when it more specifically refers to the "recursive case," so I changed it to that.
Change-Id: I8335cce4dee933c6a463aee653b28bd986b5b5e4
This reverts commit ced906c849.
Causes issues on art / dalvik due to a broken return value
check and other undiagnosed issues.
bug: 15195455
Change-Id: I5d6bbb389ecefb0e33a5237421a9d56d32a9317c
- removed extra padding from ucontex_t on x86, x86_64 and mips
- force ucontext_t struct to use 64 bits for the sigmask on all arches
(previsouly wrong since sigset_t on arm and x86 is only 32 bits)
- arm and arm64 continue to use padding to match glibc sigset_t
This brings Bionic on par with the kernel w.r.t ucontext padding.
Bug: 12828904
Change-Id: Ia8915ace694ecb4695603a334e697985f4c3e7aa
The LP64 has a duplicate copy of part of stdio, and relies
on bionic supplying this part. We should remove the hack from
the NDK, at least for LP64, and then revert this.
Bug: 15291317
Change-Id: I75e06e130188ca0aeb9d50dfe3a3e48a1d3968b7
The unwinder will end up on the parent thread's stack if the return
address register is not cleared.
Bug: 14270816
Bug: 15195760
Change-Id: Iebcdf5cc881cad245643bb193760de35eb7f8b19
typeof() is a gcc builtin and is not always available (such as clang when
-std=c*). Both gcc and clang always expose __typeof__(), so just use that.
Change-Id: I75e2a990acc35f6f39b2c353f6548100ec03c67f
The NDK apparently includes an android_support.a library that
refers to __srefill in its copy of the vsnprintf implementation.
Bug: 15249361
Change-Id: Ic2cf6f21290b3146c42fbe0624f5e4d54f6194b4
Anthony King <anthonydking@slimroms.net> reports that for Grouper the
Nvidia GL blobs need access to __swbuf. This is because the old <stdio.h>
had inline getc and putc implementations that directly referred to these
symbols.
Change-Id: I11a7b5550018ecc93d8f195c99857759669b2906
libmono from Unity still requires tkill(2).
Change-Id: I37a1994b08086c7fedb5c78ea0dadf2d72bc1463
Signed-off-by: Anthony King <anthonydking@slimroms.net>
Add optimized versions of bcopy and wmemmove for AArch64 based on the
memmove implementation
Change-Id: I82fbe8a7221ce224c567ffcfed7a94a53640fca8
Signed-off-by: Bernhard Rosenkraenzer <Bernhard.Rosenkranzer@linaro.org>
This reverts commit 8167dd7cb9.
For some reason I thought the bcopy change was bzero. The bcopy code doesn't pass our tests, so reverting until I can figure out what's wrong.
Change-Id: Id89fe959ea5105cd58dff6bba8d91a30cc4bcb07
Add optimized versions of bcopy and wmemmove for AArch64 based on the
memmove implementation
Change-Id: Ie43d0ff4f8ec4edba5b4fb5ccacd941f81ac6557
Signed-off-by: Bernhard Rosenkraenzer <Bernhard.Rosenkranzer@linaro.org>
Since __bionic_clone uses tail-call to invoke __bionic_clone_entry,
at runtime the unwinder will reach the stack of the clone() function,
which belongs to the parent thread, if the link register is not cleared.
BUG: 14270816
Change-Id: Ia3711c87f8b619debe73748c28b9fb8691ea698e
I've left __sF exposed since that's how the OpenBSD stdin, stdout, stderr
are implemented. Other BSDs and glibc use a separate global for each instead
of an array.
Bug: 11156955
Change-Id: I9f3d2d4314a8d4a78c3197b9acd9258820c5f150
- used underscore_style_for_vars
- extracted time related functionality into a function
- cleaned up style
- removed unused fields from pthread_rwlock_t on LP64
- changed reservation in pthread_rwlock_t so that the size of the
structure equals glibc version
Bug: 8133149
Change-Id: I84ad3918678dc7f5e6b3db9b7e9b0899d3abe9cd
glibc doesn't have tkill or tgkill and says "use syscall(3) instead".
I've left tgkill since it's quite widely used, but there's no reason
to have tkill as well.
Bug: 11156955
Change-Id: Ifc0af750320086f829bc9914551c172b501f3b60
Also hide part of the system properties compatibility code, since
we needed to touch that to keep it building.
I'll remove __futex_syscall4 and futex in a later patch.
Bug: 11156955
Change-Id: Ibbf42414c5bb07fb9f1c4a169922844778e4eeae
Fix syscall generator to add cfi directives and add the directives
for all arm64 assembler.
Bug: 15138290
Change-Id: I7f0e4a16c141ac624e5276917a3a1ed45778e057
There's no need to expose gregset_t and fpregset_t when they
are not used in ucontext_t.
Bug: 12828904
Change-Id: Ieda1edf0ab18015f444c4d385fe9c41c4544017f
This was accidentally added at a time when you couldn't add a constant
to <syscall.h> without generating an assembly stub! (You no longer need
to add the constants at all.)
Bug: 11156955
Change-Id: I053c17879138787976c744a5ecf7d30ee51dc48f
To use jemalloc, add MALLOC_IMPL = jemalloc in a board config file
and you get the new version automatically.
Update the pthread_create_key tests since jemalloc uses a few keys.
Add a new test to verify memalign works as expected.
Bug: 981363
Change-Id: I16eb152b291a95bd2499e90492fc6b4bd7053836
The update-tzdata.py tool now uses downloaded Olson data
to update ICU (*new*) at the same time as it updates Bionic
data.
Change-Id: I7efbd6f453fe2b3e71f564121ff0f64a74289d86
If libnetd_client can't be found, operate as before and use the default netId
potentially overriden by a more specific netId passed in to
android_get*fornet().
(cherry picked from commit 559c7842cc)
Change-Id: I42ef3293172651870fb46d2de22464c4f03e8e0b
Our type_info stub implementation is incompatible with the libc++ headers. Since
we don't need this support internally and anyone that wants RTTI support will
have to use libc++ anyway, this can be safely removed.
Change-Id: Ied8b67a0d86a4eb0e31191a50cceba0e39a16a6d
+ Name the dispatch header correctly (NetdClientDispatch.h).
+ Hide the global dispatch variable (__netdClientDispatch).
+ Explain why it's okay to read the variable without locking.
+ Use quotes instead of angle-brackets for non-system includes.
+ Add necessary declarations for C compiles (and not just C++).
Change-Id: Id0932165e71d81da5fce77a684f40c2263f58e61
I cleaned up most of our warnings last week but forgot to turn on -Werror,
so of course we're getting new warnings already. I've left -Werror commented
out in those places where we still have warnings to deal with before we can
turn on -Werror.
Change-Id: Ia58ff8b8c1ada4bf81eec6f19ec1d34e133cf4b1
