glibc/sysdeps/arm/atomic-machine.h
Adhemerval Zanella f9646d138f arm: Enable USE_ATOMIC_COMPILER_BUILTINS (BZ #24774)
As per other architectures.  I have checked on a armv8 hardware with
the following configurations:

  arm-linux-gnueabihf (gcc built with --with-float=hard --with-cpu=arm926ej-s)
  armv5-linux-gnueabihf (-march=armv5te -mfpu=vfpv3)
  armv7-linux-gnueabihf (-march=armv7-a -mfpu=vfpv3)
  armv7-thumb-linux-gnueabihf (-march=armv7-a -mfpu=vfpv3 -mthumb)
  armv7-neon-linux-gnueabihf (-march=armv7-a -mfpu=neon)
  armv7-neonhard-linux-gnueabihf (-march=armv7-a -mfpu=neon -mfloat-abi=hard)

Without any regression.

I haven't dig into the code, but since Linux atomic-machine.h handle
pre-ARMv6 and ARMv6 I expect the compiler might have some small room
to optimize.

The code size also improves is most of the configurations:

* master

   text    data     bss     dec     hex filename
1727801    9720   37928 1775449  1b1759	 arm-linux-gnueabihf/libc.so
1691729    9720   37928 1739377  1a8a71	 arm-linux-gnueabihf-armv7-disable-multi-arch/libc.so
1725509    9720   37928 1773157  1b0e65	 armv5-linux-gnueabihf/libc.so
1700757    9720   37928 1748405  1aadb5	 armv6-linux-gnueabihf/libc.so
1698973    9720   37928 1746621  1aa6bd	 armv6t2-linux-gnueabihf/libc.so
1695481    9752   37928 1743161  1a9939	 armv7-linux-gnueabihf/libc.so
1692917    9744   37928 1740589  1a8f2d	 armv7-neonhard-linux-gnueabihf/libc.so
1692917    9744   37928 1740589  1a8f2d	 armv7-neon-linux-gnueabihf/libc.so
1225353    9752   37928 1273033  136cc9	 armv7-thumb-linux-gnueabihf/libc.so

* patched

   text    data     bss     dec     hex filename
1726805    9720   37928 1774453  1b1375 arm-linux-gnueabihf/libc.so
1689321    9720   37928 1736969  1a8109	arm-linux-gnueabihf-armv7-disable-multi-arch/libc.so
1724433    9720   37928 1772081  1b0a31 armv5-linux-gnueabihf/libc.so
1698301    9720   37928 1745949  1aa41d armv6-linux-gnueabihf/libc.so
1696525    9720   37928 1744173  1a9d2d armv6t2-linux-gnueabihf/libc.so
1693009    9752   37928 1740689  1a8f91 armv7-linux-gnueabihf/libc.so
1690493    9744   37928 1738165  1a85b5 armv7-neonhard-linux-gnueabihf/libc.so
1690493    9744   37928 1738165  1a85b5 armv7-neon-linux-gnueabihf/libc.so
1223837    9752   37928 1271517  1366dd armv7-thumb-linux-gnueabihf/libc.so

The idea is eventually move all architectures to use compiler builtins.

Reviewed-by: Aurelien Jarno <aurelien@aurel32.net>
Tested-by: Aurelien Jarno <aurelien@aurel32.net>
2022-10-07 16:19:20 -03:00

139 lines
5.5 KiB
C

/* Atomic operations. Pure ARM version.
Copyright (C) 2002-2022 Free Software Foundation, Inc.
This file is part of the GNU C Library.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with the GNU C Library. If not, see
<https://www.gnu.org/licenses/>. */
#define __HAVE_64B_ATOMICS 0
#define USE_ATOMIC_COMPILER_BUILTINS 1
#define ATOMIC_EXCHANGE_USES_CAS 1
void __arm_link_error (void);
#ifdef __GCC_HAVE_SYNC_COMPARE_AND_SWAP_4
# define atomic_full_barrier() __sync_synchronize ()
#else
# define atomic_full_barrier() __arm_assisted_full_barrier ()
#endif
/* An OS-specific atomic-machine.h file will define this macro if
the OS can provide something. If not, we'll fail to build
with a compiler that doesn't supply the operation. */
#ifndef __arm_assisted_full_barrier
# define __arm_assisted_full_barrier() __arm_link_error()
#endif
/* Use the atomic builtins provided by GCC in case the backend provides
a pattern to do this efficiently. */
#ifdef __GCC_HAVE_SYNC_COMPARE_AND_SWAP_4
# define atomic_exchange_acq(mem, value) \
__atomic_val_bysize (__arch_exchange, int, mem, value, __ATOMIC_ACQUIRE)
# define atomic_exchange_rel(mem, value) \
__atomic_val_bysize (__arch_exchange, int, mem, value, __ATOMIC_RELEASE)
/* Atomic exchange (without compare). */
# define __arch_exchange_8_int(mem, newval, model) \
(__arm_link_error (), (typeof (*mem)) 0)
# define __arch_exchange_16_int(mem, newval, model) \
(__arm_link_error (), (typeof (*mem)) 0)
# define __arch_exchange_32_int(mem, newval, model) \
__atomic_exchange_n (mem, newval, model)
# define __arch_exchange_64_int(mem, newval, model) \
(__arm_link_error (), (typeof (*mem)) 0)
/* Compare and exchange with "acquire" semantics, ie barrier after. */
# define atomic_compare_and_exchange_bool_acq(mem, new, old) \
__atomic_bool_bysize (__arch_compare_and_exchange_bool, int, \
mem, new, old, __ATOMIC_ACQUIRE)
# define atomic_compare_and_exchange_val_acq(mem, new, old) \
__atomic_val_bysize (__arch_compare_and_exchange_val, int, \
mem, new, old, __ATOMIC_ACQUIRE)
/* Compare and exchange with "release" semantics, ie barrier before. */
# define atomic_compare_and_exchange_val_rel(mem, new, old) \
__atomic_val_bysize (__arch_compare_and_exchange_val, int, \
mem, new, old, __ATOMIC_RELEASE)
/* Compare and exchange.
For all "bool" routines, we return FALSE if exchange succesful. */
# define __arch_compare_and_exchange_bool_8_int(mem, newval, oldval, model) \
({__arm_link_error (); 0; })
# define __arch_compare_and_exchange_bool_16_int(mem, newval, oldval, model) \
({__arm_link_error (); 0; })
# define __arch_compare_and_exchange_bool_32_int(mem, newval, oldval, model) \
({ \
typeof (*mem) __oldval = (oldval); \
!__atomic_compare_exchange_n (mem, (void *) &__oldval, newval, 0, \
model, __ATOMIC_RELAXED); \
})
# define __arch_compare_and_exchange_bool_64_int(mem, newval, oldval, model) \
({__arm_link_error (); 0; })
# define __arch_compare_and_exchange_val_8_int(mem, newval, oldval, model) \
({__arm_link_error (); oldval; })
# define __arch_compare_and_exchange_val_16_int(mem, newval, oldval, model) \
({__arm_link_error (); oldval; })
# define __arch_compare_and_exchange_val_32_int(mem, newval, oldval, model) \
({ \
typeof (*mem) __oldval = (oldval); \
__atomic_compare_exchange_n (mem, (void *) &__oldval, newval, 0, \
model, __ATOMIC_RELAXED); \
__oldval; \
})
# define __arch_compare_and_exchange_val_64_int(mem, newval, oldval, model) \
({__arm_link_error (); oldval; })
#else
# define __arch_compare_and_exchange_val_32_acq(mem, newval, oldval) \
__arm_assisted_compare_and_exchange_val_32_acq ((mem), (newval), (oldval))
#endif
#ifndef __GCC_HAVE_SYNC_COMPARE_AND_SWAP_4
/* We don't support atomic operations on any non-word types.
So make them link errors. */
# define __arch_compare_and_exchange_val_8_acq(mem, newval, oldval) \
({ __arm_link_error (); oldval; })
# define __arch_compare_and_exchange_val_16_acq(mem, newval, oldval) \
({ __arm_link_error (); oldval; })
# define __arch_compare_and_exchange_val_64_acq(mem, newval, oldval) \
({ __arm_link_error (); oldval; })
#endif
/* An OS-specific atomic-machine.h file will define this macro if
the OS can provide something. If not, we'll fail to build
with a compiler that doesn't supply the operation. */
#ifndef __arm_assisted_compare_and_exchange_val_32_acq
# define __arm_assisted_compare_and_exchange_val_32_acq(mem, newval, oldval) \
({ __arm_link_error (); oldval; })
#endif