- devel - example.com

[PATCH] GCC libgo compilation error
by Alex Potapenko 29 Sep '17

29 Sep '17

Hi all, I'm facing a compilation error while building GCC 7.2.0 libgo with uClibc-ng 1.0.26 with this error: runtime_sysinfo.go:418:17: error: use of undefined type ‘___uclibc_locale_struct’ Here is the relevant build output: https://pastebin.com/B7urxS2m The problematic runtime_sysinfo.go is created using -fdump-go-spec: it's used to automatically generate Go declarations from C code (see https://golang.org/doc/install/gccgo#Automatic_generation_of_Go_declaration…) The generated gen-sysinfo.go is indeed missing ___uclibc_locale_struct declaration. Looks like -fdump-go-spec generates types only from typedef declarations, ignoring structs, like "struct __uclibc_locale_struct;" in uClibc_locale.h. This simple change allows to build libgo fine: --- uClibc_locale.h.orig 2017-09-25 19:49:38.000000000 +0000 +++ uClibc_locale.h 2017-09-28 07:27:14.035517712 +0000 @@ -73,6 +73,7 @@ */ struct __uclibc_locale_struct; +typedef struct __uclibc_locale_struct __uclibc_locale_struct; typedef struct __uclibc_locale_struct *__locale_t; #endif /* !defined(__LOCALE_C_ONLY) */ Does this change look sane? Or should I patch GCC libgo/sysinfo.c instead to add "typedef struct __uclibc_locale_struct __uclibc_locale_struct;" there? Thanks, Alex

2 2

[PATCH] recvmmsg/sendmmsg: add recvmmsg sendmmsg support.
by Guo Ren 26 Sep '17

26 Sep '17

The recvmmsg and sendmmsg is very important for UDP stream application. If we only use recvmsg for UDP stream, it will only copy one mtu size of data in a syscall. And recvmmsg copy as many as you want in a syscall. So recvmmsg is more efficient,and some applications will depends on the recvmmsg and sendmmsg, eg: UDP media stream player. Signed-off-by: Guo Ren <ren_guo(a)c-sky.com> --- include/sys/socket.h | 30 ++++++++++++++++++++++++++++ libc/inet/Makefile.in | 3 ++- libc/inet/recvmmsg.c | 8 ++++++++ libc/inet/sendmmsg.c | 8 ++++++++ libc/inet/socketcalls.c | 48 +++++++++++++++++++++++++++++++++++++++++++++ libpthread/nptl/Makefile.in | 2 ++ 6 files changed, 98 insertions(+), 1 deletion(-) create mode 100644 libc/inet/recvmmsg.c create mode 100644 libc/inet/sendmmsg.c diff --git a/include/sys/socket.h b/include/sys/socket.h index 8642312..63dc4b9 100644 --- a/include/sys/socket.h +++ b/include/sys/socket.h @@ -97,6 +97,15 @@ typedef union { __SOCKADDR_ALLTYPES # undef __SOCKADDR_ONETYPE #endif +#ifdef __USE_GNU +/* For `recvmmsg' and `sendmmsg'. */ +struct mmsghdr + { + struct msghdr msg_hdr; /* Actual message header. */ + unsigned int msg_len; /* Number of received or sent bytes for the + entry. */ + }; +#endif /* Create a new socket of type TYPE in domain DOMAIN, using protocol PROTOCOL. If PROTOCOL is zero, one is chosen automatically. @@ -190,6 +199,17 @@ extern ssize_t sendmsg (int __fd, const struct msghdr *__message, int __flags); libc_hidden_proto(sendmsg) +#ifdef __USE_GNU +/* Send a VLEN messages as described by VMESSAGES to socket FD. + Returns the number of datagrams successfully written or -1 for errors. + + This function is a cancellation point and therefore not marked with + __THROW. */ +extern ssize_t sendmmsg (int __fd, struct mmsghdr *__vmessages, + size_t __vlen, int __flags); +libc_hidden_proto(sendmmsg) +#endif + /* Receive a message as described by MESSAGE from socket FD. Returns the number of bytes read or -1 for errors. @@ -198,6 +218,16 @@ libc_hidden_proto(sendmsg) extern ssize_t recvmsg (int __fd, struct msghdr *__message, int __flags); libc_hidden_proto(recvmsg) +#ifdef __USE_GNU +/* Receive up to VLEN messages as described by VMESSAGES from socket FD. + Returns the number of messages received or -1 for errors. + + This function is a cancellation point and therefore not marked with + __THROW. */ +extern ssize_t recvmmsg (int __fd, struct mmsghdr *__vmessages, + size_t vlen, int __flags, struct timespec *__tmo); +libc_hidden_proto(recvmmsg) +#endif /* Put the current value for socket FD's option OPTNAME at protocol level LEVEL into OPTVAL (which is *OPTLEN bytes long), and set *OPTLEN to the value's diff --git a/libc/inet/Makefile.in b/libc/inet/Makefile.in index 332e70e..bed76c3 100644 --- a/libc/inet/Makefile.in +++ b/libc/inet/Makefile.in @@ -47,7 +47,8 @@ CSRC-$(UCLIBC_HAS_RESOLVER_SUPPORT) += \ socketcalls_CSRC-y += \ accept.c bind.c connect.c getpeername.c getsockname.c \ getsockopt.c listen.c recv.c recvfrom.c recvmsg.c send.c sendmsg.c \ - sendto.c setsockopt.c shutdown.c socket.c socketpair.c + sendto.c setsockopt.c shutdown.c socket.c socketpair.c \ + recvmmsg.c sendmmsg.c socketcalls_CSRC-$(UCLIBC_LINUX_SPECIFIC) += accept4.c CSRC-$(UCLIBC_HAS_SOCKET) += $(socketcalls_CSRC-y) opensock.c diff --git a/libc/inet/recvmmsg.c b/libc/inet/recvmmsg.c new file mode 100644 index 0000000..003b5a6 --- /dev/null +++ b/libc/inet/recvmmsg.c @@ -0,0 +1,8 @@ +/* + * Copyright (C) 2000-2006 Erik Andersen <andersen(a)uclibc.org> + * + * Licensed under the LGPL v2.1, see the file COPYING.LIB in this tarball. + */ + +#define L_recvmmsg +#include "socketcalls.c" diff --git a/libc/inet/sendmmsg.c b/libc/inet/sendmmsg.c new file mode 100644 index 0000000..f1557fe --- /dev/null +++ b/libc/inet/sendmmsg.c @@ -0,0 +1,8 @@ +/* + * Copyright (C) 2000-2006 Erik Andersen <andersen(a)uclibc.org> + * + * Licensed under the LGPL v2.1, see the file COPYING.LIB in this tarball. + */ + +#define L_sendmmsg +#include "socketcalls.c" diff --git a/libc/inet/socketcalls.c b/libc/inet/socketcalls.c index 1fef810..83bad12 100644 --- a/libc/inet/socketcalls.c +++ b/libc/inet/socketcalls.c @@ -29,6 +29,8 @@ #define SYS_SENDMSG 16 #define SYS_RECVMSG 17 #define SYS_ACCEPT4 18 +#define SYS_RECVMMSG 19 +#define SYS_SENDMMSG 20 #endif /* exposed on x86 since Linux commit 9dea5dc921b5f4045a18c63eb92e84dc274d17eb */ @@ -283,6 +285,30 @@ CANCELLABLE_SYSCALL(ssize_t, recvmsg, (int sockfd, struct msghdr *msg, int flags lt_libc_hidden(recvmsg) #endif +#ifdef L_recvmmsg +static ssize_t __NC(recvmmsg)(int sockfd, struct mmsghdr *msg, size_t vlen, + int flags, struct timespec *tmo) +{ +# ifdef __NR_recvmmsg + return (ssize_t)INLINE_SYSCALL(recvmmsg, 5, sockfd, msg, vlen, flags, tmo); +# else + unsigned long args[5]; + + args[0] = sockfd; + args[1] = (unsigned long) msg; + args[2] = vlen; + args[3] = flags; + args[4] = (unsigned long) tmo; + return (ssize_t)__socketcall(SYS_RECVMMSG, args); +# endif +} +CANCELLABLE_SYSCALL(ssize_t, recvmmsg, + (int sockfd, struct mmsghdr *msg, size_t vlen, int flags, + struct timespec *tmo), + (sockfd, msg, vlen, flags, tmo)) +lt_libc_hidden(recvmmsg) +#endif + #ifdef L_send static ssize_t __NC(send)(int sockfd, const void *buffer, size_t len, int flags) { @@ -324,6 +350,28 @@ CANCELLABLE_SYSCALL(ssize_t, sendmsg, (int sockfd, const struct msghdr *msg, int lt_libc_hidden(sendmsg) #endif +#ifdef L_sendmmsg +static ssize_t __NC(sendmmsg)(int sockfd, struct mmsghdr *msg, size_t vlen, + int flags) +{ +# ifdef __NR_sendmmsg + return (ssize_t)INLINE_SYSCALL(recvmmsg, 4, sockfd, msg, vlen, flags); +# else + unsigned long args[4]; + + args[0] = sockfd; + args[1] = (unsigned long) msg; + args[2] = vlen; + args[3] = flags; + return (ssize_t)__socketcall(SYS_SENDMMSG, args); +# endif +} +CANCELLABLE_SYSCALL(ssize_t, sendmmsg, + (int sockfd, struct mmsghdr *msg, size_t vlen, int flags), + (sockfd, msg, vlen, flags)) +lt_libc_hidden(sendmmsg) +#endif + #ifdef L_sendto ssize_t __NC(sendto)(int sockfd, const void *buffer, size_t len, int flags, const struct sockaddr *to, socklen_t tolen) diff --git a/libpthread/nptl/Makefile.in b/libpthread/nptl/Makefile.in index 068eee4..a2f30ac 100644 --- a/libpthread/nptl/Makefile.in +++ b/libpthread/nptl/Makefile.in @@ -166,11 +166,13 @@ CFLAGS-readv.c = -fexceptions -fasynchronous-unwind-tables CFLAGS-recv.c = -fexceptions -fasynchronous-unwind-tables CFLAGS-recvfrom.c = -fexceptions -fasynchronous-unwind-tables CFLAGS-recvmsg.c = -fexceptions -fasynchronous-unwind-tables +CFLAGS-recvmmsg.c = -fexceptions -fasynchronous-unwind-tables CFLAGS-__rt_sigtimedwait.c = -fexceptions -fasynchronous-unwind-tables CFLAGS-__rt_sigwaitinfo.c = -fexceptions -fasynchronous-unwind-tables CFLAGS-select.c = -fexceptions -fasynchronous-unwind-tables CFLAGS-send.c = -fexceptions -fasynchronous-unwind-tables CFLAGS-sendmsg.c = -fexceptions -fasynchronous-unwind-tables +CFLAGS-sendmmsg.c = -fexceptions -fasynchronous-unwind-tables CFLAGS-sendto.c = -fexceptions -fasynchronous-unwind-tables CFLAGS-sigpause.c = -fexceptions CFLAGS-sigsuspend.c = -fexceptions -fasynchronous-unwind-tables -- 2.7.4

1 0

[PATCH 1/1] statfs: bugfix statfs02 fstatfs02 failed in ltp-testsuite.
by Guo Ren 25 Sep '17

25 Sep '17

In the test-case of statfs from ltp-testsuite, it pass -1 to 2th argument. eg: fstatfs(fd , -1) When uclibc-ng parse the buf32 to buf will cause illegal address access, the kernel will signal the process with SIGSEV. If we pass the -1 directly to the syscall of statfs/fstatfs, kenrel use copy_to_user() to prevent the singal of SIGSEV and just return EVINAL. This is the ltp-testsuite expect. Signed-off-by: Guo Ren <ren_guo(a)c-sky.com> --- libc/misc/statfs/fstatfs64.c | 4 +++- libc/misc/statfs/statfs64.c | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/libc/misc/statfs/fstatfs64.c b/libc/misc/statfs/fstatfs64.c index 7221a0b..bb9ca30 100644 --- a/libc/misc/statfs/fstatfs64.c +++ b/libc/misc/statfs/fstatfs64.c @@ -33,9 +33,11 @@ int fstatfs64 (int fd, struct statfs64 *buf) { struct statfs buf32; - if (__libc_fstatfs (fd, &buf32) < 0) + if (__libc_fstatfs (fd, (struct statfs *)buf) < 0) return -1; + buf32 = *(struct statfs *)buf; + buf->f_type = buf32.f_type; buf->f_bsize = buf32.f_bsize; buf->f_blocks = buf32.f_blocks; diff --git a/libc/misc/statfs/statfs64.c b/libc/misc/statfs/statfs64.c index b1a33b7..7317870 100644 --- a/libc/misc/statfs/statfs64.c +++ b/libc/misc/statfs/statfs64.c @@ -31,9 +31,11 @@ int statfs64 (const char *file, struct statfs64 *buf) { struct statfs buf32; - if (__libc_statfs (file, &buf32) < 0) + if (__libc_statfs (file, (struct statfs *)buf) < 0) return -1; + buf32 = *(struct statfs *)buf; + buf->f_type = buf32.f_type; buf->f_bsize = buf32.f_bsize; buf->f_blocks = buf32.f_blocks; -- 2.7.4

1 0

[PATCH 1/1] preadv/pwritev: bugfix preadv/pwritev syscall should be 5 args
by Guo Ren 25 Sep '17

25 Sep '17

The current uclibc-ng use 4 arguments, and this will cause ltp-testsuite's preadv/pwritev case failed. The syscall of preadv/pwritev in current linux-kernel is 5 arguments: linux/fs/read_write.c: SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) So just update to 5-args-syscall, and off_t could be 32bit or 64bit. Signed-off-by: Guo Ren <ren_guo(a)c-sky.com> --- libc/sysdeps/linux/common/preadv.c | 7 ++++++- libc/sysdeps/linux/common/pwritev.c | 7 ++++++- 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/libc/sysdeps/linux/common/preadv.c b/libc/sysdeps/linux/common/preadv.c index b90291b..fd9dde4 100644 --- a/libc/sysdeps/linux/common/preadv.c +++ b/libc/sysdeps/linux/common/preadv.c @@ -23,6 +23,11 @@ ssize_t preadv (int fd, const struct iovec *vector, int count, off_t offset) { - return INLINE_SYSCALL (preadv, 4, fd, vector, count, offset); + unsigned long pos_l, pos_h; + + pos_h = (unsigned long)((long long)offset >> 32); + pos_l = (unsigned long)((long long)offset); + + return INLINE_SYSCALL (preadv, 5, fd, vector, count, pos_l, pos_h); } #endif diff --git a/libc/sysdeps/linux/common/pwritev.c b/libc/sysdeps/linux/common/pwritev.c index a1880ed..bef5bcf 100644 --- a/libc/sysdeps/linux/common/pwritev.c +++ b/libc/sysdeps/linux/common/pwritev.c @@ -23,6 +23,11 @@ ssize_t pwritev (int fd, const struct iovec *vector, int count, off_t offset) { - return INLINE_SYSCALL (pwritev, 4, fd, vector, count, offset); + unsigned long pos_l, pos_h; + + pos_h = (unsigned long)((long long)offset >> 32); + pos_l = (unsigned long)((long long)offset); + + return INLINE_SYSCALL (pwritev, 5, fd, vector, count, pos_l, pos_h); } #endif -- 2.7.4

1 0

[PATCH] arc: Ensure that debugger can recognize sigrestorer
by Anton Kolesov 14 Sep '17

14 Sep '17

An issue has been found with current implementation of ARC signal restorer function in uClibc and how GDB handles it. When debugger information is not present, everything worked fine, because GDB would use a built-in logic to determine if function is a signal restorer. However when debugging information is present, debugger would rely solely on it and wouldn't use ARC-specific functions to detect signal handler frames. Because debug information for signal restorer is generated completely by the compiler, it lacks a marker, that identifies this as a signal frame that requires special handling. While it is possible to insert that marker via inline assembly, that still doesn't solve the whole problem, because some other expectations are not met by the debug information - there is no "nop" in front of the function, needed to fool debugger into thinking that this was a function call, and references to previous frame information need to be described manually. The simplest way to fix the problem is just to make sure that signal restorer function will not have any debug function at all, which can be done by writing it in assembly. Alternative, more complex solution, where debug information for signal frame is manually defined can be found in glibc/sysdeps/unix/sysv/linux/x86_64/sigaction.c [1]. [1] https://sourceware.org/git/?p=glibc.git;a=blob;f=sysdeps/unix/sysv/linux/x8… Signed-off-by: Anton Kolesov <Anton.Kolesov(a)synopsys.com> Anton

2 1

buildroot uclibc-ng-test package need update
by 郭任 29 Aug '17

29 Aug '17

Hi, Waldemar Could you help to update buildroot uclibc-ng-test package commit version? Our tst-malloc failed in that version. Thx & Best Regards ----------- Guo Ren, Software Engineer, C-SKY 3 XiDoumen Rd,BldgA,15F,Hangzhou,China P.C: 310012T: +86 13376814331M: ren_guo(a)c-sky.com http://www.c-sky.comhttps://c-sky.github.io

3 2

[PATCH] arc: Merge ARCv2 string routines in generic ARC .S files
by Alexey Brodkin 24 Aug '17

24 Aug '17

In cde74b83f9b2 "ARC: remove special CFLAGS/LDFLAGS handling" we got rid of CONFIG_ARC_CPU_HS which was used to select ARCv2-specific implementation of optimized string routines. So now ARCv2-tuned memset/memcpy/strcmp are not used, instead those for ARC700 used for both ARC700 and ARCHS. Without uClibc config option we may only tell which CPU type we're targeting by built-in defines of GCC. I.e. no more conditional file inclusion in Makefiles. That leaves us only one option - merge both implementations in 1 file and use ifdefs. Signed-off-by: Alexey Brodkin <abrodkin(a)synopsys.com> --- FWIW I run that change through LMbench, LTP and uClibc-ng-testsuite and didn't see any significant differences or regressions. extra/Configs/Config.in | 1 - libc/string/arc/arcv2/memcpy.S | 236 ---------------------------------------- libc/string/arc/arcv2/memset.S | 115 -------------------- libc/string/arc/arcv2/strcmp.S | 83 -------------- libc/string/arc/memcpy.S | 238 ++++++++++++++++++++++++++++++++++++++++- libc/string/arc/memset.S | 115 +++++++++++++++++++- libc/string/arc/strcmp.S | 81 +++++++++++++- 7 files changed, 428 insertions(+), 441 deletions(-) delete mode 100644 libc/string/arc/arcv2/memcpy.S delete mode 100644 libc/string/arc/arcv2/memset.S delete mode 100644 libc/string/arc/arcv2/strcmp.S diff --git a/extra/Configs/Config.in b/extra/Configs/Config.in index 59ef31c47dec..ce832b55bcc7 100644 --- a/extra/Configs/Config.in +++ b/extra/Configs/Config.in @@ -250,7 +250,6 @@ config TARGET_SUBARCH default "i486" if CONFIG_486 default "i586" if CONFIG_586 default "i686" if CONFIG_686 - default "arcv2" if CONFIG_ARC_CPU_HS default "" source "extra/Configs/Config.in.arch" diff --git a/libc/string/arc/arcv2/memcpy.S b/libc/string/arc/arcv2/memcpy.S deleted file mode 100644 index ba29e8790721..000000000000 --- a/libc/string/arc/arcv2/memcpy.S +++ /dev/null @@ -1,236 +0,0 @@ -/* - * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) - * - * Licensed under the LGPL v2.1 or later, see the file COPYING.LIB in this tarball. - */ - -#include <features.h> -#include <sysdep.h> - -#ifdef __LITTLE_ENDIAN__ -# define SHIFT_1(RX,RY,IMM) asl RX, RY, IMM ; << -# define SHIFT_2(RX,RY,IMM) lsr RX, RY, IMM ; >> -# define MERGE_1(RX,RY,IMM) asl RX, RY, IMM -# define MERGE_2(RX,RY,IMM) -# define EXTRACT_1(RX,RY,IMM) and RX, RY, 0xFFFF -# define EXTRACT_2(RX,RY,IMM) lsr RX, RY, IMM -#else -# define SHIFT_1(RX,RY,IMM) lsr RX, RY, IMM ; >> -# define SHIFT_2(RX,RY,IMM) asl RX, RY, IMM ; << -# define MERGE_1(RX,RY,IMM) asl RX, RY, IMM ; << -# define MERGE_2(RX,RY,IMM) asl RX, RY, IMM ; << -# define EXTRACT_1(RX,RY,IMM) lsr RX, RY, IMM -# define EXTRACT_2(RX,RY,IMM) lsr RX, RY, 0x08 -#endif - -#if defined(__LL64__) || defined(__ARC_LL64__) -# define PREFETCH_READ(RX) prefetch [RX, 56] -# define PREFETCH_WRITE(RX) prefetchw [RX, 64] -# define LOADX(DST,RX) ldd.ab DST, [RX, 8] -# define STOREX(SRC,RX) std.ab SRC, [RX, 8] -# define ZOLSHFT 5 -# define ZOLAND 0x1F -#else -# define PREFETCH_READ(RX) prefetch [RX, 28] -# define PREFETCH_WRITE(RX) prefetchw [RX, 32] -# define LOADX(DST,RX) ld.ab DST, [RX, 4] -# define STOREX(SRC,RX) st.ab SRC, [RX, 4] -# define ZOLSHFT 4 -# define ZOLAND 0xF -#endif - -ENTRY(memcpy) - prefetch [r1] ; Prefetch the read location - prefetchw [r0] ; Prefetch the write location - mov.f 0, r2 -;;; if size is zero - jz.d [blink] - mov r3, r0 ; don't clobber ret val - -;;; if size <= 8 - cmp r2, 8 - bls.d @.Lsmallchunk - mov.f lp_count, r2 - - and.f r4, r0, 0x03 - rsub lp_count, r4, 4 - lpnz @.Laligndestination - ;; LOOP BEGIN - ldb.ab r5, [r1,1] - sub r2, r2, 1 - stb.ab r5, [r3,1] -.Laligndestination: - -;;; Check the alignment of the source - and.f r4, r1, 0x03 - bnz.d @.Lsourceunaligned - -;;; CASE 0: Both source and destination are 32bit aligned -;;; Convert len to Dwords, unfold x4 - lsr.f lp_count, r2, ZOLSHFT - lpnz @.Lcopy32_64bytes - ;; LOOP START - LOADX (r6, r1) - PREFETCH_READ (r1) - PREFETCH_WRITE (r3) - LOADX (r8, r1) - LOADX (r10, r1) - LOADX (r4, r1) - STOREX (r6, r3) - STOREX (r8, r3) - STOREX (r10, r3) - STOREX (r4, r3) -.Lcopy32_64bytes: - - and.f lp_count, r2, ZOLAND ;Last remaining 31 bytes -.Lsmallchunk: - lpnz @.Lcopyremainingbytes - ;; LOOP START - ldb.ab r5, [r1,1] - stb.ab r5, [r3,1] -.Lcopyremainingbytes: - - j [blink] -;;; END CASE 0 - -.Lsourceunaligned: - cmp r4, 2 - beq.d @.LunalignedOffby2 - sub r2, r2, 1 - - bhi.d @.LunalignedOffby3 - ldb.ab r5, [r1, 1] - -;;; CASE 1: The source is unaligned, off by 1 - ;; Hence I need to read 1 byte for a 16bit alignment - ;; and 2bytes to reach 32bit alignment - ldh.ab r6, [r1, 2] - sub r2, r2, 2 - ;; Convert to words, unfold x2 - lsr.f lp_count, r2, 3 - MERGE_1 (r6, r6, 8) - MERGE_2 (r5, r5, 24) - or r5, r5, r6 - - ;; Both src and dst are aligned - lpnz @.Lcopy8bytes_1 - ;; LOOP START - ld.ab r6, [r1, 4] - prefetch [r1, 28] ;Prefetch the next read location - ld.ab r8, [r1,4] - prefetchw [r3, 32] ;Prefetch the next write location - - SHIFT_1 (r7, r6, 24) - or r7, r7, r5 - SHIFT_2 (r5, r6, 8) - - SHIFT_1 (r9, r8, 24) - or r9, r9, r5 - SHIFT_2 (r5, r8, 8) - - st.ab r7, [r3, 4] - st.ab r9, [r3, 4] -.Lcopy8bytes_1: - - ;; Write back the remaining 16bits - EXTRACT_1 (r6, r5, 16) - sth.ab r6, [r3, 2] - ;; Write back the remaining 8bits - EXTRACT_2 (r5, r5, 16) - stb.ab r5, [r3, 1] - - and.f lp_count, r2, 0x07 ;Last 8bytes - lpnz @.Lcopybytewise_1 - ;; LOOP START - ldb.ab r6, [r1,1] - stb.ab r6, [r3,1] -.Lcopybytewise_1: - j [blink] - -.LunalignedOffby2: -;;; CASE 2: The source is unaligned, off by 2 - ldh.ab r5, [r1, 2] - sub r2, r2, 1 - - ;; Both src and dst are aligned - ;; Convert to words, unfold x2 - lsr.f lp_count, r2, 3 -#ifdef __BIG_ENDIAN__ - asl.nz r5, r5, 16 -#endif - lpnz @.Lcopy8bytes_2 - ;; LOOP START - ld.ab r6, [r1, 4] - prefetch [r1, 28] ;Prefetch the next read location - ld.ab r8, [r1,4] - prefetchw [r3, 32] ;Prefetch the next write location - - SHIFT_1 (r7, r6, 16) - or r7, r7, r5 - SHIFT_2 (r5, r6, 16) - - SHIFT_1 (r9, r8, 16) - or r9, r9, r5 - SHIFT_2 (r5, r8, 16) - - st.ab r7, [r3, 4] - st.ab r9, [r3, 4] -.Lcopy8bytes_2: - -#ifdef __BIG_ENDIAN__ - lsr.nz r5, r5, 16 -#endif - sth.ab r5, [r3, 2] - - and.f lp_count, r2, 0x07 ;Last 8bytes - lpnz @.Lcopybytewise_2 - ;; LOOP START - ldb.ab r6, [r1,1] - stb.ab r6, [r3,1] -.Lcopybytewise_2: - j [blink] - -.LunalignedOffby3: -;;; CASE 3: The source is unaligned, off by 3 -;;; Hence, I need to read 1byte for achieve the 32bit alignment - - ;; Both src and dst are aligned - ;; Convert to words, unfold x2 - lsr.f lp_count, r2, 3 -#ifdef __BIG_ENDIAN__ - asl.ne r5, r5, 24 -#endif - lpnz @.Lcopy8bytes_3 - ;; LOOP START - ld.ab r6, [r1, 4] - prefetch [r1, 28] ;Prefetch the next read location - ld.ab r8, [r1,4] - prefetchw [r3, 32] ;Prefetch the next write location - - SHIFT_1 (r7, r6, 8) - or r7, r7, r5 - SHIFT_2 (r5, r6, 24) - - SHIFT_1 (r9, r8, 8) - or r9, r9, r5 - SHIFT_2 (r5, r8, 24) - - st.ab r7, [r3, 4] - st.ab r9, [r3, 4] -.Lcopy8bytes_3: - -#ifdef __BIG_ENDIAN__ - lsr.nz r5, r5, 24 -#endif - stb.ab r5, [r3, 1] - - and.f lp_count, r2, 0x07 ;Last 8bytes - lpnz @.Lcopybytewise_3 - ;; LOOP START - ldb.ab r6, [r1,1] - stb.ab r6, [r3,1] -.Lcopybytewise_3: - j [blink] - -END(memcpy) -libc_hidden_def(memcpy) diff --git a/libc/string/arc/arcv2/memset.S b/libc/string/arc/arcv2/memset.S deleted file mode 100644 index 343cfaf81c6d..000000000000 --- a/libc/string/arc/arcv2/memset.S +++ /dev/null @@ -1,115 +0,0 @@ - -/* - * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) - * - * Licensed under the LGPL v2.1 or later, see the file COPYING.LIB in this tarball. - */ - -#include <features.h> -#include <sysdep.h> - -#ifdef DONT_USE_PREALLOC -#define PREWRITE(A,B) prefetchw [(A),(B)] -#else -#define PREWRITE(A,B) prealloc [(A),(B)] -#endif - -ENTRY(memset) - prefetchw [r0] ; Prefetch the write location - mov.f 0, r2 -;;; if size is zero - jz.d [blink] - mov r3, r0 ; don't clobber ret val - -;;; if length < 8 - brls.d.nt r2, 8, .Lsmallchunk - mov.f lp_count,r2 - - and.f r4, r0, 0x03 - rsub lp_count, r4, 4 - lpnz @.Laligndestination - ;; LOOP BEGIN - stb.ab r1, [r3,1] - sub r2, r2, 1 -.Laligndestination: - -;;; Destination is aligned - and r1, r1, 0xFF - asl r4, r1, 8 - or r4, r4, r1 - asl r5, r4, 16 - or r5, r5, r4 - mov r4, r5 - - sub3 lp_count, r2, 8 - cmp r2, 64 - bmsk.hi r2, r2, 5 - mov.ls lp_count, 0 - add3.hi r2, r2, 8 - -;;; Convert len to Dwords, unfold x8 - lsr.f lp_count, lp_count, 6 - lpnz @.Lset64bytes - ;; LOOP START - PREWRITE(r3, 64) ;Prefetch the next write location -#if defined(__LL64__) || defined(__ARC_LL64__) - std.ab r4, [r3, 8] - std.ab r4, [r3, 8] - std.ab r4, [r3, 8] - std.ab r4, [r3, 8] - std.ab r4, [r3, 8] - std.ab r4, [r3, 8] - std.ab r4, [r3, 8] - std.ab r4, [r3, 8] -#else - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] -#endif -.Lset64bytes: - - lsr.f lp_count, r2, 5 ;Last remaining max 124 bytes - lpnz .Lset32bytes - ;; LOOP START - prefetchw [r3, 32] ;Prefetch the next write location -#if defined(__LL64__) || defined(__ARC_LL64__) - std.ab r4, [r3, 8] - std.ab r4, [r3, 8] - std.ab r4, [r3, 8] - std.ab r4, [r3, 8] -#else - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] - st.ab r4, [r3, 4] -#endif -.Lset32bytes: - - and.f lp_count, r2, 0x1F ;Last remaining 31 bytes -.Lsmallchunk: - lpnz .Lcopy3bytes - ;; LOOP START - stb.ab r1, [r3, 1] -.Lcopy3bytes: - - j [blink] - -END(memset) -libc_hidden_def(memset) diff --git a/libc/string/arc/arcv2/strcmp.S b/libc/string/arc/arcv2/strcmp.S deleted file mode 100644 index 2e0e64a0c394..000000000000 --- a/libc/string/arc/arcv2/strcmp.S +++ /dev/null @@ -1,83 +0,0 @@ -/* - * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) - * - * Licensed under the LGPL v2.1 or later, see the file COPYING.LIB in this tarball. - */ - -#include <features.h> -#include <sysdep.h> - -ENTRY(strcmp) - or r2, r0, r1 - bmsk_s r2, r2, 1 - brne r2, 0, @.Lcharloop - -;;; s1 and s2 are word aligned - ld.ab r2, [r0, 4] - - mov_s r12, 0x01010101 - ror r11, r12 - .align 4 -.LwordLoop: - ld.ab r3, [r1, 4] - ;; Detect NULL char in str1 - sub r4, r2, r12 - ld.ab r5, [r0, 4] - bic r4, r4, r2 - and r4, r4, r11 - brne.d.nt r4, 0, .LfoundNULL - ;; Check if the read locations are the same - cmp r2, r3 - beq.d .LwordLoop - mov.eq r2, r5 - - ;; A match is found, spot it out -#ifdef __LITTLE_ENDIAN__ - swape r3, r3 - mov_s r0, 1 - swape r2, r2 -#else - mov_s r0, 1 -#endif - cmp_s r2, r3 - j_s.d [blink] - bset.lo r0, r0, 31 - - .align 4 -.LfoundNULL: -#ifdef __BIG_ENDIAN__ - swape r4, r4 - swape r2, r2 - swape r3, r3 -#endif - ;; Find null byte - ffs r0, r4 - bmsk r2, r2, r0 - bmsk r3, r3, r0 - swape r2, r2 - swape r3, r3 - ;; make the return value - sub.f r0, r2, r3 - mov.hi r0, 1 - j_s.d [blink] - bset.lo r0, r0, 31 - - .align 4 -.Lcharloop: - ldb.ab r2, [r0, 1] - ldb.ab r3, [r1, 1] - nop - breq r2, 0, .Lcmpend - breq r2, r3, .Lcharloop - - .align 4 -.Lcmpend: - j_s.d [blink] - sub r0, r2, r3 -END(strcmp) -libc_hidden_def(strcmp) - -#ifndef __UCLIBC_HAS_LOCALE__ -strong_alias(strcmp,strcoll) -libc_hidden_def(strcoll) -#endif diff --git a/libc/string/arc/memcpy.S b/libc/string/arc/memcpy.S index 1c11951e40d2..69d7220b8a7e 100644 --- a/libc/string/arc/memcpy.S +++ b/libc/string/arc/memcpy.S @@ -1,5 +1,5 @@ /* - * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com) + * Copyright (C) 2013, 2014-2015, 2017 Synopsys, Inc. (www.synopsys.com) * Copyright (C) 2007 ARC International (UK) LTD * * Licensed under the LGPL v2.1 or later, see the file COPYING.LIB in this tarball. @@ -7,12 +7,18 @@ #include <sysdep.h> +#if !defined(__ARC700__) && !defined(__ARCHS__) +#error "Neither ARC700 nor ARCHS is defined!" +#endif + +ENTRY(memcpy) + +#ifdef __ARC700__ /* This memcpy implementation does not support objects of 1GB or larger - the check for alignment does not work then. */ /* We assume that most sources and destinations are aligned, and that also lengths are mostly a multiple of four, although to a lesser extent. */ -ENTRY(memcpy) or r3,r0,r1 asl_s r3,r3,30 mov_s r5,r0 @@ -67,5 +73,233 @@ ENTRY(memcpy) .Lendbloop: j_s.d [blink] stb r12,[r5,0] +#endif /* __ARC700__ */ + +#ifdef __ARCHS__ +#ifdef __LITTLE_ENDIAN__ +# define SHIFT_1(RX,RY,IMM) asl RX, RY, IMM ; << +# define SHIFT_2(RX,RY,IMM) lsr RX, RY, IMM ; >> +# define MERGE_1(RX,RY,IMM) asl RX, RY, IMM +# define MERGE_2(RX,RY,IMM) +# define EXTRACT_1(RX,RY,IMM) and RX, RY, 0xFFFF +# define EXTRACT_2(RX,RY,IMM) lsr RX, RY, IMM +#else +# define SHIFT_1(RX,RY,IMM) lsr RX, RY, IMM ; >> +# define SHIFT_2(RX,RY,IMM) asl RX, RY, IMM ; << +# define MERGE_1(RX,RY,IMM) asl RX, RY, IMM ; << +# define MERGE_2(RX,RY,IMM) asl RX, RY, IMM ; << +# define EXTRACT_1(RX,RY,IMM) lsr RX, RY, IMM +# define EXTRACT_2(RX,RY,IMM) lsr RX, RY, 0x08 +#endif + +#if defined(__LL64__) || defined(__ARC_LL64__) +# define PREFETCH_READ(RX) prefetch [RX, 56] +# define PREFETCH_WRITE(RX) prefetchw [RX, 64] +# define LOADX(DST,RX) ldd.ab DST, [RX, 8] +# define STOREX(SRC,RX) std.ab SRC, [RX, 8] +# define ZOLSHFT 5 +# define ZOLAND 0x1F +#else +# define PREFETCH_READ(RX) prefetch [RX, 28] +# define PREFETCH_WRITE(RX) prefetchw [RX, 32] +# define LOADX(DST,RX) ld.ab DST, [RX, 4] +# define STOREX(SRC,RX) st.ab SRC, [RX, 4] +# define ZOLSHFT 4 +# define ZOLAND 0xF +#endif + + prefetch [r1] ; Prefetch the read location + prefetchw [r0] ; Prefetch the write location + mov.f 0, r2 +;;; if size is zero + jz.d [blink] + mov r3, r0 ; don't clobber ret val + +;;; if size <= 8 + cmp r2, 8 + bls.d @.Lsmallchunk + mov.f lp_count, r2 + + and.f r4, r0, 0x03 + rsub lp_count, r4, 4 + lpnz @.Laligndestination + ;; LOOP BEGIN + ldb.ab r5, [r1,1] + sub r2, r2, 1 + stb.ab r5, [r3,1] +.Laligndestination: + +;;; Check the alignment of the source + and.f r4, r1, 0x03 + bnz.d @.Lsourceunaligned + +;;; CASE 0: Both source and destination are 32bit aligned +;;; Convert len to Dwords, unfold x4 + lsr.f lp_count, r2, ZOLSHFT + lpnz @.Lcopy32_64bytes + ;; LOOP START + LOADX (r6, r1) + PREFETCH_READ (r1) + PREFETCH_WRITE (r3) + LOADX (r8, r1) + LOADX (r10, r1) + LOADX (r4, r1) + STOREX (r6, r3) + STOREX (r8, r3) + STOREX (r10, r3) + STOREX (r4, r3) +.Lcopy32_64bytes: + + and.f lp_count, r2, ZOLAND ;Last remaining 31 bytes +.Lsmallchunk: + lpnz @.Lcopyremainingbytes + ;; LOOP START + ldb.ab r5, [r1,1] + stb.ab r5, [r3,1] +.Lcopyremainingbytes: + + j [blink] +;;; END CASE 0 + +.Lsourceunaligned: + cmp r4, 2 + beq.d @.LunalignedOffby2 + sub r2, r2, 1 + + bhi.d @.LunalignedOffby3 + ldb.ab r5, [r1, 1] + +;;; CASE 1: The source is unaligned, off by 1 + ;; Hence I need to read 1 byte for a 16bit alignment + ;; and 2bytes to reach 32bit alignment + ldh.ab r6, [r1, 2] + sub r2, r2, 2 + ;; Convert to words, unfold x2 + lsr.f lp_count, r2, 3 + MERGE_1 (r6, r6, 8) + MERGE_2 (r5, r5, 24) + or r5, r5, r6 + + ;; Both src and dst are aligned + lpnz @.Lcopy8bytes_1 + ;; LOOP START + ld.ab r6, [r1, 4] + prefetch [r1, 28] ;Prefetch the next read location + ld.ab r8, [r1,4] + prefetchw [r3, 32] ;Prefetch the next write location + + SHIFT_1 (r7, r6, 24) + or r7, r7, r5 + SHIFT_2 (r5, r6, 8) + + SHIFT_1 (r9, r8, 24) + or r9, r9, r5 + SHIFT_2 (r5, r8, 8) + + st.ab r7, [r3, 4] + st.ab r9, [r3, 4] +.Lcopy8bytes_1: + + ;; Write back the remaining 16bits + EXTRACT_1 (r6, r5, 16) + sth.ab r6, [r3, 2] + ;; Write back the remaining 8bits + EXTRACT_2 (r5, r5, 16) + stb.ab r5, [r3, 1] + + and.f lp_count, r2, 0x07 ;Last 8bytes + lpnz @.Lcopybytewise_1 + ;; LOOP START + ldb.ab r6, [r1,1] + stb.ab r6, [r3,1] +.Lcopybytewise_1: + j [blink] + +.LunalignedOffby2: +;;; CASE 2: The source is unaligned, off by 2 + ldh.ab r5, [r1, 2] + sub r2, r2, 1 + + ;; Both src and dst are aligned + ;; Convert to words, unfold x2 + lsr.f lp_count, r2, 3 +#ifdef __BIG_ENDIAN__ + asl.nz r5, r5, 16 +#endif + lpnz @.Lcopy8bytes_2 + ;; LOOP START + ld.ab r6, [r1, 4] + prefetch [r1, 28] ;Prefetch the next read location + ld.ab r8, [r1,4] + prefetchw [r3, 32] ;Prefetch the next write location + + SHIFT_1 (r7, r6, 16) + or r7, r7, r5 + SHIFT_2 (r5, r6, 16) + + SHIFT_1 (r9, r8, 16) + or r9, r9, r5 + SHIFT_2 (r5, r8, 16) + + st.ab r7, [r3, 4] + st.ab r9, [r3, 4] +.Lcopy8bytes_2: + +#ifdef __BIG_ENDIAN__ + lsr.nz r5, r5, 16 +#endif + sth.ab r5, [r3, 2] + + and.f lp_count, r2, 0x07 ;Last 8bytes + lpnz @.Lcopybytewise_2 + ;; LOOP START + ldb.ab r6, [r1,1] + stb.ab r6, [r3,1] +.Lcopybytewise_2: + j [blink] + +.LunalignedOffby3: +;;; CASE 3: The source is unaligned, off by 3 +;;; Hence, I need to read 1byte for achieve the 32bit alignment + + ;; Both src and dst are aligned + ;; Convert to words, unfold x2 + lsr.f lp_count, r2, 3 +#ifdef __BIG_ENDIAN__ + asl.ne r5, r5, 24 +#endif + lpnz @.Lcopy8bytes_3 + ;; LOOP START + ld.ab r6, [r1, 4] + prefetch [r1, 28] ;Prefetch the next read location + ld.ab r8, [r1,4] + prefetchw [r3, 32] ;Prefetch the next write location + + SHIFT_1 (r7, r6, 8) + or r7, r7, r5 + SHIFT_2 (r5, r6, 24) + + SHIFT_1 (r9, r8, 8) + or r9, r9, r5 + SHIFT_2 (r5, r8, 24) + + st.ab r7, [r3, 4] + st.ab r9, [r3, 4] +.Lcopy8bytes_3: + +#ifdef __BIG_ENDIAN__ + lsr.nz r5, r5, 24 +#endif + stb.ab r5, [r3, 1] + + and.f lp_count, r2, 0x07 ;Last 8bytes + lpnz @.Lcopybytewise_3 + ;; LOOP START + ldb.ab r6, [r1,1] + stb.ab r6, [r3,1] +.Lcopybytewise_3: + j [blink] +#endif /* __ARCHS__ */ + END(memcpy) libc_hidden_def(memcpy) diff --git a/libc/string/arc/memset.S b/libc/string/arc/memset.S index f4048455a433..0b74ddc7fca8 100644 --- a/libc/string/arc/memset.S +++ b/libc/string/arc/memset.S @@ -1,5 +1,5 @@ /* - * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com) + * Copyright (C) 2013, 2014-2015, 2017 Synopsys, Inc. (www.synopsys.com) * Copyright (C) 2007 ARC International (UK) LTD * * Licensed under the LGPL v2.1 or later, see the file COPYING.LIB in this tarball. @@ -7,10 +7,15 @@ #include <sysdep.h> -#define SMALL 7 /* Must be at least 6 to deal with alignment/loop issues. */ +#if !defined(__ARC700__) && !defined(__ARCHS__) +#error "Neither ARC700 nor ARCHS is defined!" +#endif ENTRY(memset) +#ifdef __ARC700__ +#define SMALL 7 /* Must be at least 6 to deal with alignment/loop issues. */ + mov_s r4,r0 or r12,r0,r2 bmsk.f r12,r12,1 @@ -47,5 +52,111 @@ ENTRY(memset) stb.ab r1,[r4,1] .Ltiny_end: j_s [blink] +#endif /* __ARC700__ */ + +#ifdef __ARCHS__ +#ifdef DONT_USE_PREALLOC +#define PREWRITE(A,B) prefetchw [(A),(B)] +#else +#define PREWRITE(A,B) prealloc [(A),(B)] +#endif + + prefetchw [r0] ; Prefetch the write location + mov.f 0, r2 +;;; if size is zero + jz.d [blink] + mov r3, r0 ; don't clobber ret val + +;;; if length < 8 + brls.d.nt r2, 8, .Lsmallchunk + mov.f lp_count,r2 + + and.f r4, r0, 0x03 + rsub lp_count, r4, 4 + lpnz @.Laligndestination + ;; LOOP BEGIN + stb.ab r1, [r3,1] + sub r2, r2, 1 +.Laligndestination: + +;;; Destination is aligned + and r1, r1, 0xFF + asl r4, r1, 8 + or r4, r4, r1 + asl r5, r4, 16 + or r5, r5, r4 + mov r4, r5 + + sub3 lp_count, r2, 8 + cmp r2, 64 + bmsk.hi r2, r2, 5 + mov.ls lp_count, 0 + add3.hi r2, r2, 8 + +;;; Convert len to Dwords, unfold x8 + lsr.f lp_count, lp_count, 6 + lpnz @.Lset64bytes + ;; LOOP START + PREWRITE(r3, 64) ;Prefetch the next write location +#if defined(__LL64__) || defined(__ARC_LL64__) + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] +#else + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] +#endif +.Lset64bytes: + + lsr.f lp_count, r2, 5 ;Last remaining max 124 bytes + lpnz .Lset32bytes + ;; LOOP START + prefetchw [r3, 32] ;Prefetch the next write location +#if defined(__LL64__) || defined(__ARC_LL64__) + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] + std.ab r4, [r3, 8] +#else + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] +#endif +.Lset32bytes: + + and.f lp_count, r2, 0x1F ;Last remaining 31 bytes +.Lsmallchunk: + lpnz .Lcopy3bytes + ;; LOOP START + stb.ab r1, [r3, 1] +.Lcopy3bytes: + + j [blink] +#endif /* __ARCHS__ */ + END(memset) libc_hidden_def(memset) diff --git a/libc/string/arc/strcmp.S b/libc/string/arc/strcmp.S index 5a0e56045c44..ad38d9e00c8a 100644 --- a/libc/string/arc/strcmp.S +++ b/libc/string/arc/strcmp.S @@ -1,5 +1,5 @@ /* - * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com) + * Copyright (C) 2013, 2014-2015, 2017 Synopsys, Inc. (www.synopsys.com) * Copyright (C) 2007 ARC International (UK) LTD * * Licensed under the LGPL v2.1 or later, see the file COPYING.LIB in this tarball. @@ -8,6 +8,13 @@ #include <features.h> #include <sysdep.h> +#if !defined(__ARC700__) && !defined(__ARCHS__) +#error "Neither ARC700 nor ARCHS is defined!" +#endif + +ENTRY(strcmp) + +#ifdef __ARC700__ /* This is optimized primarily for the ARC700. It would be possible to speed up the loops by one cycle / word respective one cycle / byte by forcing double source 1 alignment, unrolling @@ -15,7 +22,6 @@ source 1; however, that would increase the overhead for loop setup / finish, and strcmp might often terminate early. */ -ENTRY(strcmp) or r2,r0,r1 bmsk_s r2,r2,1 brne r2,0,.Lcharloop @@ -93,6 +99,77 @@ ENTRY(strcmp) .Lcmpend: j_s.d [blink] sub r0,r2,r3 +#endif /* __ARC700__ */ + +#ifdef __ARCHS__ + or r2, r0, r1 + bmsk_s r2, r2, 1 + brne r2, 0, @.Lcharloop + +;;; s1 and s2 are word aligned + ld.ab r2, [r0, 4] + + mov_s r12, 0x01010101 + ror r11, r12 + .align 4 +.LwordLoop: + ld.ab r3, [r1, 4] + ;; Detect NULL char in str1 + sub r4, r2, r12 + ld.ab r5, [r0, 4] + bic r4, r4, r2 + and r4, r4, r11 + brne.d.nt r4, 0, .LfoundNULL + ;; Check if the read locations are the same + cmp r2, r3 + beq.d .LwordLoop + mov.eq r2, r5 + + ;; A match is found, spot it out +#ifdef __LITTLE_ENDIAN__ + swape r3, r3 + mov_s r0, 1 + swape r2, r2 +#else + mov_s r0, 1 +#endif + cmp_s r2, r3 + j_s.d [blink] + bset.lo r0, r0, 31 + + .align 4 +.LfoundNULL: +#ifdef __BIG_ENDIAN__ + swape r4, r4 + swape r2, r2 + swape r3, r3 +#endif + ;; Find null byte + ffs r0, r4 + bmsk r2, r2, r0 + bmsk r3, r3, r0 + swape r2, r2 + swape r3, r3 + ;; make the return value + sub.f r0, r2, r3 + mov.hi r0, 1 + j_s.d [blink] + bset.lo r0, r0, 31 + + .align 4 +.Lcharloop: + ldb.ab r2, [r0, 1] + ldb.ab r3, [r1, 1] + nop + breq r2, 0, .Lcmpend + breq r2, r3, .Lcharloop + + .align 4 +.Lcmpend: + j_s.d [blink] + sub r0, r2, r3 +#endif /* __ARCHS__ */ + END(strcmp) libc_hidden_def(strcmp) -- 2.7.5

4 4

Compile fix when debugging is enabled
by Bogdan Harjoc 19 Aug '17

19 Aug '17

Pthread pid caching was removed recently but an assert is still present which checks pthread->pid, and this breaks the build when debugging is enabled: http://repo.or.cz/uclibc-ng.git/commit/bddde5860ffb8a78587854cc8e3e914bd692… http://repo.or.cz/uclibc-ng.git/blob/HEAD:/libpthread/nptl/pthread_getattr_… Line 69 should be removed from pthread_getattr_np.c . Cheers, Bogdan

2 1

buildroot uClibc-ng build failure
by Waldemar Brodkorb 10 Aug '17

10 Aug '17

Hi André, we are seeing a build error on your machine when locales in uClibc-ng are enabled: http://autobuild.buildroot.net/results/d5b/d5ba81eea9223569ba5b363551c4a2f7… Can you show us locale -a from your machine? For a working tolower(), the uClibc-ng code needs to use setlocale on the host. But it seems only these are tried to use: en_US en_US en_GB best regards Waldemar

6 12

[PATCH] towlower and locales
by Eugene Yudin 02 Aug '17

02 Aug '17

Hi, The function towlower doesn't work with locales diffrent from C. Issue was introduced in this commit: https://cgit.openadk.org/cgi/cgit/uclibc-ng.git/commit/?id= 8cde3a9bf2856dcb9a759dec7ecb04a68e712254 Call to setlocale is needed for correct generation of the table uplow_diff. I received the compile time error "range assumption error" after uncommenting the call. Similar problem described here: http://lists.uclibc.org/pipermail/uclibc/2015-March/048852.html The attached patch fix the problem by using int32_t values. Test program: $ cat test.c #include <locale.h> #include <stdio.h> #include <wchar.h> #include <wctype.h> int main(int argc, char *argv[]) { int i = 0; wchar_t str[] = L"ТЕСТОВАЯ СТРОКА"; wchar_t c; setlocale(LC_ALL, "ru_RU.utf-8"); wprintf(L"Input:\t\"%ls\"\n", str); wprintf(L"Output:\t\""); while (str[i]) { c = str[i]; putwchar(towlower(c)); i++; } wprintf(L"\"\n"); return 0; } Output (without patch): $ ./test Input: "ТЕСТОВАЯ СТРОКА" Output: "ТЕСТОВАЯ СТРОКА" Output (with patch): $ ./test Input: "ТЕСТОВАЯ СТРОКА" Output: "тестовая строка" -- Best regards, Eugene

3 4