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 75c55ff84ebfa686c7ae2cc8ee431c6a33bd46b4.
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 ced906c849704f379d7191822f6d74993d4fa296.
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
