src/lib/libc/aarch64/string, branch mainFreeBSD source treehttps://cgit-dev.freebsd.org/src/atom?h=main2026-02-03T17:11:51Zlibc/aarch64: Add memset for a 64 byte dc zva2026-02-03T17:11:51ZAndrew Turnerandrew@FreeBSD.org2026-02-03T14:01:32Zurn:sha1:32d1f18865abe94d351a6f178a93b7195595ec69
On arm64 we can use the "dc zva" instruction to zero memory. The CPU
tells software if the instruction is implemented, and if so the size
and alignment it will use.
When the size is 64-bytes the Arm Optimized Routines implementation of
memset can use dc zva to zero memory, and has a build flag to skip
checking.
Use this flag to build a version of memset that will be used when this
assumption is true.
Sponsored by: Arm Ltd
Differential Revision: https://reviews.freebsd.org/D54776
libc/aarch64: Split out the MOPS functions2026-02-03T17:11:50ZAndrew Turnerandrew@FreeBSD.org2026-02-03T14:01:07Zurn:sha1:f0516ed4652cfb7435f8c5a16b46dc067779a1a8
This allows static binaries to only include the functions they
reference.
Reviewed by: imp
Sponsored by: Arm Ltd
Differential Revision: https://reviews.freebsd.org/D54775
libc/aarch64: Add a Makefile.inc dependency2026-02-03T17:11:50ZAndrew Turnerandrew@FreeBSD.org2026-02-03T14:00:46Zurn:sha1:00f68392130cf597c7c76669c63dab26b31630c1
If we update Makefile.inc it may be to change the contents of these
files.
Reviewed by: imp
Sponsored by: Arm Ltd
Differential Revision: https://reviews.freebsd.org/D54774
libc/aarch64: Use MOPS implementations of memcpy/memmove/memset where availble2026-01-13T15:28:04ZSarah Walkersarah.walker2@arm.com2026-01-13T14:24:53Zurn:sha1:41ccf82b29f3b16fcd1ccb4987569c851222ef8d
Reviewed by: andrew
Sponsored by: Arm Ltd
Differential Revision: https://reviews.freebsd.org/D54560
libc/aarch64: fix ELF size of timingsafe_memcmp2025-09-26T09:04:54ZPaul Floydpjfloyd@wanadoo.fr2025-09-25T19:49:08Zurn:sha1:7feac79331bc8c77e2f8a3e71d6ea087fa17b61d
Looks like a copy and paste error.
The ELF size of 0 prevents Valgrind from redirecting this function.
PR: 289845
Reviewed by: fuz
Fixes: 3f224333af163d5fcd7547a20993dcf18f19076c
See also: https://bugs.kde.org/show_bug.cgi?id=509406
Pull Request: https://github.com/freebsd/freebsd-src/pull/1854
MFC after: 1 day
Event: EuroBSDcon 2025
libc: fix _FORTIFY_SOURCE build on aarch642025-03-04T19:53:34ZKyle Evanskevans@FreeBSD.org2025-03-04T19:53:34Zurn:sha1:429b03a00ba74ae0188cce3f3064cfac023e18c5
As with their amd64 counterparts, we need to undef these string funcs
that _FORTIFY_SOURCE will have defined macros for to avoid breaking the
build.
Fixes: bea89d038ac ("lib/libc/aarch64/string: add strlcat SIMD [...]")
Fixes: 3dc5429158c ("lib/libc/aarch64/string: add strncat SIMD [...]")
libc: Add include path for aarch64 memchr.S2025-01-17T16:23:56ZEd Masteemaste@FreeBSD.org2025-01-17T16:22:39Zurn:sha1:72f092ee019447c76ecb483c3f475313cf9dd5dd
Reported by: bapt
Sponsored by: The FreeBSD Foundation
Fixes: d355c28a0954 ("depend-cleanup: bea89d038ac5 also moved memchr")
depend-cleanup: bea89d038ac5 also moved memchr2025-01-17T15:17:45ZEd Masteemaste@FreeBSD.org2025-01-17T15:05:26Zurn:sha1:d355c28a0954de487e45c4349631c2b9449ba28d
Commit bea89d038ac5 added strlcat but also introduced a memchr wrapper
in the source tree rather than using the autogenerated one used for
AARCH64_STRING_FUNCS. Move memchr.S to MDSRS and add a cleanup rule for
the old wrapper.
Reviewed by: fuz
Sponsored by: The FreeBSD Foundation
Fixes: bea89d038ac5 ("lib/libc/aarch64/string: add strlcat SIMD implementation")
Differential Revision: https://reviews.freebsd.org/D48502
libc/aarch64: fix strlen() when flush-to-zero is set2025-01-16T01:20:30ZRobert Clauseckerfuz@FreeBSD.org2025-01-13T13:41:41Zurn:sha1:521c1fe0e2002dfd7d8db86eb7144b7865229912
Our SIMD-enhanced strlen() implementation for AArch64 uses
a floating-point comparison to compare a bit mask to zero.
This works fine under normal circumstances, but fails if
the FZ (flush-to-zero) flag is set in FPCR (the floating-point
control register) as then the CPU no longer distinguishes
denormals from zero.
This was not caught during testing; this flag is rarely set
and programs that do so rarely perform string manipulation.
Avoid this problem by using an integer comparison instead.
The performance impact seems to be small (about 0.5 %) on
the Windows 2023 Dev Kit, but seems to be more significant
(up to around 19%) on the RPi 5.
Reviewed by: getz
Fixes: 3863fec1ce2dc6033f094a085118605ea89db9e2
Differential Revision: https://reviews.freebsd.org/D48442
lib/libc/aarch64/string: add timingsafe_memcmp() assembly implementation2025-01-10T15:02:41ZRobert Clauseckerfuz@FreeBSD.org2024-12-09T09:50:00Zurn:sha1:3f224333af163d5fcd7547a20993dcf18f19076c
A port of the amd64 implementation with some slight changes due to
differences in instructions provided by aarch64.
No ASIMD for the same reason as the amd64 code: it's just not particularly
suitable for this application.
Event: EuroBSDcon 2024
Approved by: security (cperciva)
Reviewed by: getz, cperciva
Differential Revision: https://reviews.freebsd.org/D46758