Reference results of the experiments on TI OMAP3430 at 600 MHz
$ bench_strcmp -N "strcmp_1k" -s 1k -I 200
[original C code]
prc thr usecs/call samples errors cnt/samp size
strcmp_1k 1 1 10.38000 102 0 15000 1024
[ARM optimized code]
prc thr usecs/call samples errors cnt/samp size
strcmp_1k 1 1 3.08840 88 0 15000 1024
The work was derived from ARM Ltd, contributed to newlib, and reworked
for Android by Linaro.
Change-Id: Ib0d5755e1eb9adb07d80ef0252f57a5c4c57a425
Signed-off-by: Jim Huang <jserv@0xlab.org>
The kernel has supported this syscall for quite some time now,
but bionic did not. Now that there is a need for it, let's
add it to bionic.
Change-Id: Ifcef3e46f1438d79435b600c4e6063857ab16903
Used the new gensyscalls.py script to update the ARM syscalls with the
BEGIN(x) and END(x) macros to give size information for the code of the
syscall. Useful for valgrind.
Change-Id: I8c481c8928401ac110fd19b087f7d67e4db39326
Add a macro to annotate function end and start using both ENTRY and END
for each function. This allows valgrind (and presumably other debugging
tools) to use the debug symbols to trace the functions.
Change-Id: I5f09cef8e22fb356eb6f5cee952b031e567599b6
This patch improves the handling of 64-bit parameters in syscalls on ARM.
The ARM EABI mandates that 64-bit quantities be passed in even/odd register
pairs, which requires special treatment.
This allows us to simplify our implementations of pread() and pwrite()
and remove the C stubs for pread64() and pwrite64().
Also add ftruncate64() to <unistd.h>
Change-Id: I407e2fd223ba0093dd2d0b04c6152fadfc9ce3ef
Bug 3107933
This adds the cpu_set_t type definition and related functions
and macros used to handle CPU thread affinity.
sched_getcpu()
sched_setaffinity()
sched_getaffinity()
Change-Id: If382ecafde8926341a88478062b275553645065b
This elimates the makefile warning at the beginning of each build:
libc_common_intermediates/arch-arm/syscalls/eventfd.o' given more than once in the same rule.
Change-Id: I25cc0c373d55b5036dd17811a595c097fd6ca69a
The change explicitly isolates the assembly-only macros in header
<machine/cpu-features.h> in order to prevent mis-inclusion in C/C++
source files.
Change-Id: I0258e87c5ac3fd24944fb227290ac3b9cac4bfba
Merge commit 'bd8d987b3c3aa6d9d00cede2cb091f00bdb42204' into gingerbread-plus-aosp
* commit 'bd8d987b3c3aa6d9d00cede2cb091f00bdb42204':
libc: remove C++ comments from public headers.
Merge commit '3cf53d1a7814e1520df09d24b009c16f4f27db0d' into gingerbread-plus-aosp
* commit '3cf53d1a7814e1520df09d24b009c16f4f27db0d':
Fixes for the ARM-specific bswap_16, bswap_32, and bswap_64.
1. Make the feature test work by excluding known-deficient processors, so
we don't have to maintain a complete list of all the processors that support
REV and REV16.
2. Don't abuse 'register' to get an effect similar to GCC's +l constraint,
but which was unnecessarily restrictive.
3. Fix __swap64md so _x isn't clobbered, breaking 64-bit swaps.
4. Make <byteswap.h> (which declars bswap_16 and friends) use <endian.h>
rather than <sys/endian.h>, so we get the machine-dependent implementations.
Change-Id: I6a38fad7a9fbe394aff141489617eb3883e1e944
Merge commit '312be567a03aaf851707a268807ee666b12f8c74' into gingerbread-plus-aosp
* commit '312be567a03aaf851707a268807ee666b12f8c74':
Use ARMv6 instruction for handling byte order
Merge commit '3a1bbee36b773862e88c6f1895b607c0cd81b499' into gingerbread-plus-aosp
* commit '3a1bbee36b773862e88c6f1895b607c0cd81b499':
Add eventfd system call support
ARMv6 ISA has several instructions to handle data in different byte order.
For endian conversion (byte swapping) of single data words, it might be a
good idea to use the REV/REV16 instruction simply.
Change-Id: Ic4a5ed6254e082763e54aa70d428f59a0088636e
With this patch _and_ an upcoming build/ patch, the destruction
of static C++ objects contained in shared libraries will happen
properly when dlclose() is called.
Note that this change introduces crtbegin_so.S and crtend_so.S which
are currently ignored by the build system.
+ move definition of __dso_handle to the right place
(before that, all shared libraries used the __dso_handle
global variable from the C library).
Note that we keep a 'weak' __dso_handle in aeabi.c to avoid
breaking the build until the next patch to build/core/combo/
appears. We will be able to remove that later.
+ move bionic/aeabi.c to arch-arm/bionic/ (its proper location)
NOTE: The NDK will need to be modified to enable this feature in
the shared libraries that are generated through it.
Change-Id: I99cd801375bbaef0581175893d1aa0943211b9bc
With this patch, _and_ an upcoming build/ patch, the destruction
of static C++ objects contained in shared libraries will happen
properly when dlclose() is called.
Note that this change introduces crtbegin_so.S and crtend_so.S which
are currently ignored by the build system.
+ move definition of __dso_handle to the right place
(before that, all shared libraries used the __dso_handle
global variable from the C library).
Note that we keep a 'weak' __dso_handle in aeabi.c to avoid
breaking the build until the next patch to build/core/combo/
appears. We will be able to remove that later.
+ move bionic/aeabi.c to arch-arm/bionic/ (its proper location)
Change-Id: Ie771aa204e3acbdf02fd30ebd4150373a1398f39
NOTE: The NDK will need to be modified to enable this feature in
the shared libraries that are generated through it.
Update ARM atomic ops to use LDREX/STREX. Stripped out #if 0 chunk.
Insert explicit memory barriers in pthread and semaphore code.
For bug 2721865.
Change-Id: I0f153b797753a655702d8be41679273d1d5d6ae7
Added an underscore to _ARM_HAVE_LDREX_STREX to make it match the others.
Added __ARM_HAVE_DMB and __ARM_HAVE_LDREXD when appropriate.
Fixed some typos.
Change-Id: I2f55febcff4aeb7de572a514fb2cd2f820dca27c
GDB looks for specific opcode sequences when trying to recognize a stack
frame as a signal trampoline. The sequences it looks for happen to be those
created when SA_RESTORER is set, since glibc always sets a restorer. This
patch does the same here, so that the trampolines can be correctly identified.
Change-Id: I0ac574a68818cb24d939c3527f3aaeb04b853d04
This does not change the implementation of conditional variables
since we're waiting for other system components to properly use
pthread_condattr_init/setpshared before that.
Also remove an obsolete x86 source file.
Change-Id: Ia3e3fbac35b87a534fb04d4381c3c66b975bc8f7
Private futexes are a recent kernel addition: faster futexes that cannot be
shared between processes. This patch uses them by default, unless the PROCESS_SHARED
attribute flag is used when creating a mutex and/or conditional variable.
Also introduces pthread_condattr_init/destroy/setpshared/getpshared.
Change-Id: I3a0e2116f467072b046524cb5babc00e41057a53
Any of the setuid functions now updates /acct/uid/ with its own tid
before changing users. This is so we can properly account for cpu time
per uid.
Change-Id: I34186cf4d5228cac8439e582a9e26c01ef3011e4
Signed-off-by: Mike Chan <mike@android.com>
Only provide an implementation for ARM at the moment, since
it requires specific assembly fragments (the standard syscall
stubs cannot be used because the child returns in a different
stack).
Merge commit '76ef331cd6967ca8f5af779d25c8b634f8cdd2b6' into eclair-mr2-plus-aosp
* commit '76ef331cd6967ca8f5af779d25c8b634f8cdd2b6':
use local symbols in memset so it doesn't screw up profiling
Merge commit '7e7d6c48a064af82f0ec39f47b9eb803a6e1df4c' into eclair-plus-aosp
* commit '7e7d6c48a064af82f0ec39f47b9eb803a6e1df4c':
use local symbols in memset so it doesn't screw up profiling
Do not submit this patch before the one that modifies the Android emulator to
work-around a weird ARMv7 emulation issue. This is done to temporarily re-allow
the -user builds needed for QA.
This is required to work-around some corny bugs in ARMv7 emulation.
The emulation itself is required to run the dex pre-optimization pass
for -user builds.
Merge commit '7a9e06fa7e4e533074cde314f25dff3024f34a5d' into eclair-plus-aosp
* commit '7a9e06fa7e4e533074cde314f25dff3024f34a5d':
Fix ABI breakage in libc.so and libm.so between 1.6 and Eclair.
372 MB/s for large transfers, 440 MB/s for smaller ones down to 1KB. 130 MB/s for very small transfers ( < 32 bytes )
Performance is similar with non-congruent buffers.
For performance reasons, we don't call the kernel helper. Instead, we directly
access the TLS register on ARMv6 and higher. For ARMv5TE, keep using the hard-coded
address populated by the kernel on each task switch.
NOTE: Since we don't call the kernel helper, this must precisely match your
kernel configuration. This is controlled by setting the ARCH_ARM_HAVE_TLS_REGISTER
variable to 'true' in your board configuration file.
ARMv6 onwards. These architectures provide the load-linked, store-conditional pair of ldrex/strex whose use
is recommended in place of 'swp'. Also, the description of the 'swp' instruction in the ARMv6 reference
manual states that the swap operation does not include any memory barrier guarantees.This fix attempts to
address these issues by providing an atomic swap implementation using ldrex/strex under _ARM_HAVE_LDREX_STREX
macro. This Fix is verified on ST Ericsson's U8500 platform and Submitted on behalf of a third-party:
Surinder-pal SINGH from STMicroelectronics.
The problem was due to the fact that, in the case of dynamic executables,
the dynamic linker calls the DT_PREINIT_ARRAY, DT_INIT and DT_INIT_ARRAY
constructors when loading shared libraries and dynamic executables,
*before* calling the executable's entry point (i.e. arch-$ARCH/bionic/crtbegin_dynamic.c)
which in turns call __libc_init() in libc.so, as defined by bionic/libc_init_dynamic.c
The latter did call these constructors array again, mistakenly.
The patch also updates the documentation of many related functions.
Also adds a new section to linker/README.TXT explaining restrictions on
C library usage.
The patch has been tested on a Dream for stability issues with
proprietary blobs:
- H264 decoding works
- Camera + Video recording works
- GPS works
- Sensors work
The tests in system/extra/tests/bionic/libc/common/test_static_cpp_mutex.cpp has been
run and shows the static C++ constructor being called only once.
