- Linux-kselftest-mirror - lists.linaro.org

[PATCH v3] tools/nolibc: fix up size inflate regression

by Zhangjin Wu

As reported and suggested by Willy, the inline __sysret() helper introduces three types of conversions and increases the size: (1) the "unsigned long" argument to __sysret() forces a sign extension from all sys_* functions that used to return 'int' (2) the comparison with the error range now has to be performed on a 'unsigned long' instead of an 'int' (3) the return value from __sysret() is a 'long' (note, a signed long) which then has to be turned back to an 'int' before being returned by the caller to satisfy the caller's prototype. To fix up this, firstly, let's use macro instead of inline function to preserves the input type and avoids these useless conversions (1), (3). Secondly, comparison to -MAX_ERRNO inflicts on all integer returns where we could previously keep a simple sign comparison, let's use a new is_signed_type() macro from include/linux/compiler.h to limit the comparision to -MAX_ERRNO (2) only on demand and preserves a simple sign comparision for most of the cases as before. Thirdly, fix up the following warning by an explicit conversion and let __sysret() be able to accept the (void *) type of argument and return value with the same (void *) type: sysroot/powerpc/include/sys.h: In function 'sbrk': sysroot/powerpc/include/sys.h:104:16: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast] 104 | return (void *)__sysret(-ENOMEM); Fourthly, to further workaround the argument type with 'const', must use __auto_type for a new enough gcc versions and use 'long' for the old gcc versions as before. Here reports the size testing result with nolibc-test: before: // ppc64le $ size nolibc-test text data bss dec hex filename 27916 8 80 28004 6d64 nolibc-test // mips $ size nolibc-test text data bss dec hex filename 23276 64 64 23404 5b6c nolibc-test after: // ppc64le $ size nolibc-test text data bss dec hex filename 27736 8 80 27824 6cb0 nolibc-test // mips $ size nolibc-test text data bss dec hex filename 23036 64 64 23164 5a7c nolibc-test Suggested-by: Willy Tarreau <w(a)1wt.eu> Link: https://lore.kernel.org/lkml/20230806095846.GB10627@1wt.eu/ Link: https://lore.kernel.org/lkml/20230806134348.GA19145@1wt.eu/ Signed-off-by: Zhangjin Wu <falcon(a)tinylab.org> --- Hi, Willy To increase readability, v3 further defines a __GXX_HAS_AUTO_TYPE_WITH_CONST_SUPPORT macro for gcc >= 11.0 (ABI_VERSION >= 1016) who has __auto_type with 'const' support. When this macro is defined, provides a __sysret version with __auto_type, otherwise, use a fixed 'long' type as a fallback. Tested for all of the nolibc supported architectures with Arnd's 13.2.0 toolchains. and also for x86_64 with gcc-4.8 and gcc-9, no compile failures, no compile warnings, no running failures. Changes from v2 --> v3: * define a __GXX_HAS_AUTO_TYPE_WITH_CONST_SUPPORT for gcc >= 11.0 (ABI_VERSION >= 1016) * split __sysret() to two versions by the macro instead of a mixed unified and unreadable version * use shorter __ret instead of __sysret_arg Changes from v1 --> v2: * fix up argument with 'const' in the type * support "void *" argument v2: https://lore.kernel.org/lkml/95fe3e732f455fab653fe1427118d905e4d04257.16913… v1: https://lore.kernel.org/lkml/20230806131921.52453-1-falcon@tinylab.org/ --- tools/include/nolibc/sys.h | 66 +++++++++++++++++++++++++++++++------- 1 file changed, 55 insertions(+), 11 deletions(-) diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h index 56f63eb48a1b..b137f7771db9 100644 --- a/tools/include/nolibc/sys.h +++ b/tools/include/nolibc/sys.h @@ -35,15 +35,59 @@ * (src/internal/syscall_ret.c) and glibc (sysdeps/unix/sysv/linux/sysdep.h) */ -static __inline__ __attribute__((unused, always_inline)) -long __sysret(unsigned long ret) -{ - if (ret >= (unsigned long)-MAX_ERRNO) { - SET_ERRNO(-(long)ret); - return -1; - } - return ret; -} +/* + * Whether 'type' is a signed type or an unsigned type. Supports scalar types, + * bool and also pointer types. (from include/linux/compiler.h) + */ +#define __is_signed_type(type) (((type)(-1)) < (type)1) + +/* __auto_type is used instead of __typeof__ to workaround the build error + * 'error: assignment of read-only variable' when the argument has 'const' in + * the type, but __auto_type is a new feature from newer gcc version and it + * only works with 'const' from gcc 11.0 (__GXX_ABI_VERSION = 1016) + * https://gcc.gnu.org/legacy-ml/gcc-patches/2013-11/msg01378.html + */ + +#if __GXX_ABI_VERSION >= 1016 +#define __GXX_HAS_AUTO_TYPE_WITH_CONST_SUPPORT +#endif + +#ifdef __GXX_HAS_AUTO_TYPE_WITH_CONST_SUPPORT +#define __sysret(arg) \ +({ \ + __auto_type __ret = (arg); \ + if (__is_signed_type(__typeof__(arg))) { \ + if (__ret < 0) { \ + SET_ERRNO(-(long)__ret); \ + __ret = (__typeof__(arg))(-1L); \ + } \ + } else { \ + if ((unsigned long)__ret >= (unsigned long)-MAX_ERRNO) { \ + SET_ERRNO(-(long)__ret); \ + __ret = (__typeof__(arg))(-1L); \ + } \ + } \ + __ret; \ +}) + +#else /* ! __GXX_HAS_AUTO_TYPE_WITH_CONST_SUPPORT */ +#define __sysret(arg) \ +({ \ + long __ret = (long)(arg); \ + if (__is_signed_type(__typeof__(arg))) { \ + if (__ret < 0) { \ + SET_ERRNO(-__ret); \ + __ret = -1L; \ + } \ + } else { \ + if ((unsigned long)__ret >= (unsigned long)-MAX_ERRNO) { \ + SET_ERRNO(-__ret); \ + __ret = -1L; \ + } \ + } \ + (__typeof__(arg))__ret; \ +}) +#endif /* ! __GXX_HAS_AUTO_TYPE_WITH_CONST_SUPPORT */ /* Functions in this file only describe syscalls. They're declared static so * that the compiler usually decides to inline them while still being allowed @@ -94,7 +138,7 @@ void *sbrk(intptr_t inc) if (ret && sys_brk(ret + inc) == ret + inc) return ret + inc; - return (void *)__sysret(-ENOMEM); + return __sysret((void *)-ENOMEM); } @@ -682,7 +726,7 @@ void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd, static __attribute__((unused)) void *mmap(void *addr, size_t length, int prot, int flags, int fd, off_t offset) { - return (void *)__sysret((unsigned long)sys_mmap(addr, length, prot, flags, fd, offset)); + return __sysret(sys_mmap(addr, length, prot, flags, fd, offset)); } static __attribute__((unused)) -- 2.25.1

1 year, 11 months

2
3
0 0

[PATCH] tools/nolibc: silence ppc64 compile warnings

by Zhangjin Wu

Silence the following warnings reported by the new -Wall -Wextra options with pure assembly code. In file included from sysroot/powerpc/include/stdio.h:13, from nolibc-test.c:13: sysroot/powerpc/include/arch.h: In function '_start': sysroot/powerpc/include/arch.h:192:32: warning: unused variable 'r2' [-Wunused-variable] 192 | register volatile long r2 __asm__ ("r2") = (void *)&TOC - (void *)_start; | ^~ sysroot/powerpc/include/arch.h:187:97: warning: optimization may eliminate reads and/or writes to register variables [-Wvolatile-register-var] 187 | void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void) | ^~~~~~ Since only elfv2 ABI requires to save the TOC/GOT pointer to r2 register, when using elfv1 ABI, the old C code is simply ignored by the compiler, but the compiler can not ignore the inline assembly code and will introduce build failure or running segfaults. So, let's further only add the new assembly code for elfv2 ABI with the checking of _CALL_ELF == 2. Link: https://refspecs.linuxfoundation.org/ELF/ppc64/PPC-elf64abi.pdf Link: https://www.llvm.org/devmtg/2014-04/PDFs/Talks/Euro-LLVM-2014-Weigand.pdf Signed-off-by: Zhangjin Wu <falcon(a)tinylab.org> --- Hi, Willy When rebase on latest 20230806-for-6.6-1 branch, -Wall -Wextra reported the above warnings. Here uses volatile inline assembly code instead of C code to silence the unused and optimization warnings. And since only elfv2 require to save TOC pointer to r2 register, this further only add the assembly code for elfv2. BR, Zhangjin --- tools/include/nolibc/arch-powerpc.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/tools/include/nolibc/arch-powerpc.h b/tools/include/nolibc/arch-powerpc.h index 76c3784f9dc7..ac212e6185b2 100644 --- a/tools/include/nolibc/arch-powerpc.h +++ b/tools/include/nolibc/arch-powerpc.h @@ -187,9 +187,17 @@ void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void) { #ifdef __powerpc64__ - /* On 64-bit PowerPC, save TOC/GOT pointer to r2 */ - extern char TOC __asm__ (".TOC."); - register volatile long r2 __asm__ ("r2") = (void *)&TOC - (void *)_start; +#if _CALL_ELF == 2 + /* with -mabi=elfv2, save TOC/GOT pointer to r2 + * r12 is global entry pointer, we use it to compute TOC from r12 + * https://www.llvm.org/devmtg/2014-04/PDFs/Talks/Euro-LLVM-2014-Weigand.pdf + * https://refspecs.linuxfoundation.org/ELF/ppc64/PPC-elf64abi.pdf + */ + __asm__ volatile ( + "addis 2, 12, .TOC. - _start@ha\n" + "addi 2, 2, .TOC. - _start@l\n" + ); +#endif /* _CALL_ELF == 2 */ __asm__ volatile ( "mr 3, 1\n" /* save stack pointer to r3, as arg1 of _start_c */ -- 2.25.1

1 year, 11 months

1
0
0 0

[PATCH v4 00/19] selftests/resctrl: Fixes and cleanups

by Ilpo Järvinen

Here is a series with some fixes and cleanups to resctrl selftests. Only has a minor change in code ordering in main() compared with v3. v4: - Move resctrlfs (unconditional) umount after resctrl fs support check v3: - Don't include rewritten CAT test into this series! - Tweak wildcard style in Makefile - Fix many changelog typos, remove some wrong claims, and generally improve them. - Add fix to PARENT_EXIT() to unmount resctrl FS - Add unmounting resctrl FS before starting any tests - Add fix for buf leak - Add fix for perf fd closing - Split mount/remount/umount patches differently - Use size_t and %zu for span - Keep MBM print as MB, only internally use span in bytes - Drop start_buf global from fill_buf v2 (was sent with CAT test rewrite which is no longer included in v3): - Rebased on top of next to solve the conflicts - Added 2 patches related to resctrl FS mount/umount (fix + cleanup) - Consistently use "alloc" in cache_alloc_size() - CAT test error handling tweaked - Remove a spurious newline change from the CAT patch - Small improvements to changelogs Ilpo Järvinen (19): selftests/resctrl: Add resctrl.h into build deps selftests/resctrl: Don't leak buffer in fill_cache() selftests/resctrl: Unmount resctrl FS if child fails to run benchmark selftests/resctrl: Close perf value read fd on errors selftests/resctrl: Unmount resctrl FS before starting the first test selftests/resctrl: Move resctrl FS mount/umount to higher level selftests/resctrl: Refactor remount_resctrl(bool mum_resctrlfs) to mount_resctrl() selftests/resctrl: Remove mum_resctrlfs from struct resctrl_val_param selftests/resctrl: Convert span to size_t selftests/resctrl: Express span internally in bytes selftests/resctrl: Remove duplicated preparation for span arg selftests/resctrl: Remove "malloc_and_init_memory" param from run_fill_buf() selftests/resctrl: Remove unnecessary startptr global from fill_buf selftests/resctrl: Improve parameter consistency in fill_buf selftests/resctrl: Don't pass test name to fill_buf selftests/resctrl: Don't use variable argument list for ->setup() selftests/resctrl: Move CAT/CMT test global vars to function they are used in selftests/resctrl: Pass the real number of tests to show_cache_info() selftests/resctrl: Remove test type checks from cat_val() tools/testing/selftests/resctrl/Makefile | 2 +- tools/testing/selftests/resctrl/cache.c | 64 +++++++------- tools/testing/selftests/resctrl/cat_test.c | 28 ++---- tools/testing/selftests/resctrl/cmt_test.c | 29 ++----- tools/testing/selftests/resctrl/fill_buf.c | 87 +++++++------------ tools/testing/selftests/resctrl/mba_test.c | 9 +- tools/testing/selftests/resctrl/mbm_test.c | 17 ++-- tools/testing/selftests/resctrl/resctrl.h | 17 ++-- .../testing/selftests/resctrl/resctrl_tests.c | 82 +++++++++++------ tools/testing/selftests/resctrl/resctrl_val.c | 7 +- tools/testing/selftests/resctrl/resctrlfs.c | 57 ++++++------ 11 files changed, 169 insertions(+), 230 deletions(-) -- 2.30.2

1 year, 11 months

3
55
0 0

[PATCH v6 00/15] tools/nolibc: add a new syscall helper

by Zhangjin Wu

Hi, Willy Here is the v6 of the __sysret series [1], applies your suggestions. additionally, the sbrk() also uses the __sysret helper. These patches are tested (together with the coming v4 selftests/nolibc patches) for all of the supported architectures: arch/board | result ------------|------------ arm/vexpress-a9 | 142 test(s) passed, 1 skipped, 0 failed. arm/virt | 142 test(s) passed, 1 skipped, 0 failed. aarch64/virt | 142 test(s) passed, 1 skipped, 0 failed. ppc/g3beige | not supported ppc/ppce500 | not supported i386/pc | 142 test(s) passed, 1 skipped, 0 failed. x86_64/pc | 142 test(s) passed, 1 skipped, 0 failed. mipsel/malta | 142 test(s) passed, 1 skipped, 0 failed. loongarch64/virt | 142 test(s) passed, 1 skipped, 0 failed. riscv64/virt | 142 test(s) passed, 1 skipped, 0 failed. riscv32/virt | 0 test(s) passed, 0 skipped, 0 failed. s390x/s390-ccw-virtio | 142 test(s) passed, 1 skipped, 0 failed. Changes from v5 --> v6: * tools/nolibc: arch-*.h: fix up code indent errors toolc/nolibc: arch-*.h: clean up whitespaces after __asm__ Fix up the code indent errors and whitespaces between __asm__ and volatile. The post-whitespaces are reserved as before. * tools/nolibc: arch-loongarch.h: shrink with _NOLIBC_SYSCALL_CLOBBERLIST tools/nolibc: arch-mips.h: shrink with _NOLIBC_SYSCALL_CLOBBERLIST Add _NOLIBC_ prefix for SYSCALL_CLOBBERLIST. * tools/nolibc: add missing my_syscall6() for mips Use post-whitespaces instead of post-tab. The above 4 patches are preparation for this one. * tools/nolibc: __sysret: support syscalls who return a pointer Add comments about the new errno range [-MAX_ERRNOR, -1], add ref to the musl and glibc. * tools/nolibc: clean up mmap() routine Comment the MAP_FAILED return info. * tools/nolibc: clean up sbrk() routine New patch, applies __sysret() helper too and also fixes up an error reported by scripts/checkpatch.pl. * selftests/nolibc: export argv0 for some tests selftests/nolibc: prepare: create /dev/zero Prepare /dev/zero and argv0 for mmap test cases. * selftests/nolibc: add EXPECT_PTREQ, EXPECT_PTRNE and EXPECT_PTRER selftests/nolibc: add sbrk_0 to test current brk getting No change. * selftests/nolibc: add mmap_bad test case selftests/nolibc: add munmap_bad test case selftests/nolibc: add mmap_munmap_good test case Split the first two out to standalone patches. Add /dev/zero and argv0 to the file list and assigns a file_size manually for /dev/zero. Best regards, Zhangjin --- [1]: https://lore.kernel.org/lkml/cover.1687957589.git.falcon@tinylab.org/ Zhangjin Wu (15): tools/nolibc: arch-*.h: fix up code indent errors toolc/nolibc: arch-*.h: clean up whitespaces after __asm__ tools/nolibc: arch-loongarch.h: shrink with _NOLIBC_SYSCALL_CLOBBERLIST tools/nolibc: arch-mips.h: shrink with _NOLIBC_SYSCALL_CLOBBERLIST tools/nolibc: add missing my_syscall6() for mips tools/nolibc: __sysret: support syscalls who return a pointer tools/nolibc: clean up mmap() routine tools/nolibc: clean up sbrk() routine selftests/nolibc: export argv0 for some tests selftests/nolibc: prepare: create /dev/zero selftests/nolibc: add EXPECT_PTREQ, EXPECT_PTRNE and EXPECT_PTRER selftests/nolibc: add sbrk_0 to test current brk getting selftests/nolibc: add mmap_bad test case selftests/nolibc: add munmap_bad test case selftests/nolibc: add mmap_munmap_good test case tools/include/nolibc/arch-aarch64.h | 28 ++-- tools/include/nolibc/arch-arm.h | 28 ++-- tools/include/nolibc/arch-i386.h | 24 ++-- tools/include/nolibc/arch-loongarch.h | 37 +++--- tools/include/nolibc/arch-mips.h | 73 +++++++---- tools/include/nolibc/arch-riscv.h | 14 +- tools/include/nolibc/arch-s390.h | 14 +- tools/include/nolibc/arch-x86_64.h | 28 ++-- tools/include/nolibc/nolibc.h | 9 +- tools/include/nolibc/sys.h | 55 ++++---- tools/include/nolibc/types.h | 6 + tools/testing/selftests/nolibc/nolibc-test.c | 129 ++++++++++++++++++- 12 files changed, 292 insertions(+), 153 deletions(-) -- 2.25.1

1 year, 11 months

3
22
0 0

[PATCH v4] tools/nolibc: fix up size inflate regression

by Zhangjin Wu

As reported and suggested by Willy, the inline __sysret() helper introduces three types of conversions and increases the size: (1) the "unsigned long" argument to __sysret() forces a sign extension from all sys_* functions that used to return 'int' (2) the comparison with the error range now has to be performed on a 'unsigned long' instead of an 'int' (3) the return value from __sysret() is a 'long' (note, a signed long) which then has to be turned back to an 'int' before being returned by the caller to satisfy the caller's prototype. To fix up this, firstly, let's use macro instead of inline function to preserves the input type and avoids these useless conversions (1), (3). Secondly, comparison to -MAX_ERRNO inflicts on all integer returns where we could previously keep a simple sign comparison, let's use a new is_signed_type() macro from include/linux/compiler.h to limit the comparision to -MAX_ERRNO (2) only on demand and preserves a simple sign comparision for most of the cases as before. Thirdly, fix up the following warning by an explicit conversion and let __sysret() be able to accept the (void *) type of argument: sysroot/powerpc/include/sys.h: In function 'sbrk': sysroot/powerpc/include/sys.h:104:16: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast] 104 | return (void *)__sysret(-ENOMEM); Fourthly, to further workaround the argument type with 'const', must use __auto_type in a new enough version or use 'long' as before. Here reports the size testing result of nolibc-test with gcc 13.2.0: before: // ppc64le with powerpc64-linux-gcc $ size nolibc-test text data bss dec hex filename 28004 8 80 28092 6dbc nolibc-test // mips with mips64-linux-gcc (CFLAGS="-mabi=32 -EL") $ size nolibc-test text data bss dec hex filename 23164 64 64 23292 5afc nolibc-test after: // ppc64le with powerpc64-linux-gcc $ size nolibc-test text data bss dec hex filename 27828 8 80 27916 6d0c nolibc-test // mips with mips64-linux-gcc (CFLAGS="-mabi=32 -EL") $ size nolibc-test text data bss dec hex filename 22924 64 64 23052 5a0c nolibc-test Suggested-by: Willy Tarreau <w(a)1wt.eu> Link: https://lore.kernel.org/lkml/20230806095846.GB10627@1wt.eu/ Link: https://lore.kernel.org/lkml/20230806134348.GA19145@1wt.eu/ Signed-off-by: Zhangjin Wu <falcon(a)tinylab.org> --- Hi, Willy v4 rebases on latest 20230806-for-6.6-1 and fixes up a warning reported by the new -Wall -Wextra options. Changes from v3 --> v4: * fix up a new warning about 'ret < 0' when the input arg type is (void *) Changes from v2 --> v3: * define a __GXX_HAS_AUTO_TYPE_WITH_CONST_SUPPORT for gcc >= 11.0 (ABI_VERSION >= 1016) * split __sysret() to two versions by the macro instead of a mixed unified and unreadable version * use shorter __ret instead of __sysret_arg Changes from v1 --> v2: * fix up argument with 'const' in the type * support "void *" argument v2: https://lore.kernel.org/lkml/95fe3e732f455fab653fe1427118d905e4d04257.16913… v1: https://lore.kernel.org/lkml/20230806131921.52453-1-falcon@tinylab.org/ --- tools/include/nolibc/sys.h | 66 +++++++++++++++++++++++++++++++------- 1 file changed, 55 insertions(+), 11 deletions(-) diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h index 833d6c5e86dc..565b4a295c11 100644 --- a/tools/include/nolibc/sys.h +++ b/tools/include/nolibc/sys.h @@ -35,15 +35,59 @@ * (src/internal/syscall_ret.c) and glibc (sysdeps/unix/sysv/linux/sysdep.h) */ -static __inline__ __attribute__((unused, always_inline)) -long __sysret(unsigned long ret) -{ - if (ret >= (unsigned long)-MAX_ERRNO) { - SET_ERRNO(-(long)ret); - return -1; - } - return ret; -} +/* + * Whether 'type' is a signed type or an unsigned type. Supports scalar types, + * bool and also pointer types. (from include/linux/compiler.h) + */ +#define __is_signed_type(type) (((type)(-1)) < (type)1) + +/* __auto_type is used instead of __typeof__ to workaround the build error + * 'error: assignment of read-only variable' when the argument has 'const' in + * the type, but __auto_type is a new feature from newer gcc version and it + * only works with 'const' from gcc 11.0 (__GXX_ABI_VERSION = 1016) + * https://gcc.gnu.org/legacy-ml/gcc-patches/2013-11/msg01378.html + */ + +#if __GXX_ABI_VERSION >= 1016 +#define __GXX_HAS_AUTO_TYPE_WITH_CONST_SUPPORT +#endif + +#ifdef __GXX_HAS_AUTO_TYPE_WITH_CONST_SUPPORT +#define __sysret(arg) \ +({ \ + __auto_type __ret = (arg); \ + if (__is_signed_type(__typeof__(arg))) { \ + if ((long)__ret < 0) { \ + SET_ERRNO(-(long)__ret); \ + __ret = (__typeof__(arg))(-1L); \ + } \ + } else { \ + if ((unsigned long)__ret >= (unsigned long)-MAX_ERRNO) { \ + SET_ERRNO(-(long)__ret); \ + __ret = (__typeof__(arg))(-1L); \ + } \ + } \ + __ret; \ +}) + +#else /* ! __GXX_HAS_AUTO_TYPE_WITH_CONST_SUPPORT */ +#define __sysret(arg) \ +({ \ + long __ret = (long)(arg); \ + if (__is_signed_type(__typeof__(arg))) { \ + if (__ret < 0) { \ + SET_ERRNO(-__ret); \ + __ret = -1L; \ + } \ + } else { \ + if ((unsigned long)__ret >= (unsigned long)-MAX_ERRNO) { \ + SET_ERRNO(-__ret); \ + __ret = -1L; \ + } \ + } \ + (__typeof__(arg))__ret; \ +}) +#endif /* ! __GXX_HAS_AUTO_TYPE_WITH_CONST_SUPPORT */ /* Functions in this file only describe syscalls. They're declared static so * that the compiler usually decides to inline them while still being allowed @@ -94,7 +138,7 @@ void *sbrk(intptr_t inc) if (ret && sys_brk(ret + inc) == ret + inc) return ret + inc; - return (void *)__sysret(-ENOMEM); + return __sysret((void *)-ENOMEM); } @@ -682,7 +726,7 @@ void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd, static __attribute__((unused)) void *mmap(void *addr, size_t length, int prot, int flags, int fd, off_t offset) { - return (void *)__sysret((unsigned long)sys_mmap(addr, length, prot, flags, fd, offset)); + return __sysret(sys_mmap(addr, length, prot, flags, fd, offset)); } static __attribute__((unused)) -- 2.25.1

1 year, 11 months

1
0
0 0

[PATCH mptcp-next v12 0/5] bpf: Force to MPTCP

by Geliang Tang

As is described in the "How to use MPTCP?" section in MPTCP wiki [1]: "Your app should create sockets with IPPROTO_MPTCP as the proto: ( socket(AF_INET, SOCK_STREAM, IPPROTO_MPTCP); ). Legacy apps can be forced to create and use MPTCP sockets instead of TCP ones via the mptcpize command bundled with the mptcpd daemon." But the mptcpize (LD_PRELOAD technique) command has some limitations [2]: - it doesn't work if the application is not using libc (e.g. GoLang apps) - in some envs, it might not be easy to set env vars / change the way apps are launched, e.g. on Android - mptcpize needs to be launched with all apps that want MPTCP: we could have more control from BPF to enable MPTCP only for some apps or all the ones of a netns or a cgroup, etc. - it is not in BPF, we cannot talk about it at netdev conf. So this patchset attempts to use BPF to implement functions similer to mptcpize. The main idea is to add a hook in sys_socket() to change the protocol id from IPPROTO_TCP (or 0) to IPPROTO_MPTCP. [1] https://github.com/multipath-tcp/mptcp_net-next/wiki [2] https://github.com/multipath-tcp/mptcp_net-next/issues/79 v12: - update diag_* log of update_socket_protocol. - add 'ip netns show' after 'ip netns del' to check if there is a test did not clean up its netns. - return libbpf_get_error() instead of -EIO for the error from open_and_load(). - Use getsockopt(SOL_PROTOCOL) to verify mptcp protocol intead of using 'ss -tOni'. v11: - add comments about outputs of 'ss' and 'nstat'. - use "err = verify_mptcpify()" instead of using =+. v10: - drop "#ifdef CONFIG_BPF_JIT". - include vmlinux.h and bpf_tracing_net.h to avoid defining some macros. - drop unneeded checks for mptcp. v9: - update comment for 'update_socket_protocol'. v8: - drop the additional checks on the 'protocol' value after the 'update_socket_protocol()' call. v7: - add __weak and __diag_* for update_socket_protocol. v6: - add update_socket_protocol. v5: - add bpf_mptcpify helper. v4: - use lsm_cgroup/socket_create v3: - patch 8: char cmd[128]; -> char cmd[256]; v2: - Fix build selftests errors reported by CI Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/79 Geliang Tang (5): bpf: Add update_socket_protocol hook selftests/bpf: Use random netns name for mptcp selftests/bpf: Add two mptcp netns helpers selftests/bpf: Fix error checks of mptcp open_and_load selftests/bpf: Add mptcpify test net/mptcp/bpf.c | 15 ++ net/socket.c | 26 +++- .../testing/selftests/bpf/prog_tests/mptcp.c | 146 +++++++++++++++--- tools/testing/selftests/bpf/progs/mptcpify.c | 20 +++ 4 files changed, 186 insertions(+), 21 deletions(-) create mode 100644 tools/testing/selftests/bpf/progs/mptcpify.c -- 2.35.3

1 year, 11 months

1
5
0 0

[PATCH 0/1] Possible bug in zram on ppc64le on vfat

by Petr Vorel

Hi all, following bug is trying to workaround an error on ppc64le, where zram01.sh LTP test (there is also kernel selftest tools/testing/selftests/zram/zram01.sh, but LTP test got further updates) has often mem_used_total 0 although zram is already filled. Patch tries to repeatedly read /sys/block/zram*/mm_stat for 1 sec, waiting for mem_used_total > 0. The question if this is expected and should be workarounded or a bug which should be fixed. REPRODUCE THE ISSUE Quickest way to install only zram tests and their dependencies: make autotools && ./configure && for i in testcases/lib/ testcases/kernel/device-drivers/zram/; do cd $i && make -j$(getconf _NPROCESSORS_ONLN) && make install && cd -; done Run the test (only on vfat) PATH="/opt/ltp/testcases/bin:$PATH" LTP_SINGLE_FS_TYPE=vfat zram01.sh Petr Vorel (1): zram01.sh: Workaround division by 0 on vfat on ppc64le .../kernel/device-drivers/zram/zram01.sh | 27 +++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) -- 2.38.0

1 year, 11 months

5
19
0 0

[PATCH v26 0/5] Implement IOCTL to get and optionally clear info about PTEs

by Muhammad Usama Anjum

*Changes in v26:* - Code re-structurring and API changes in PAGEMAP_IOCTL *Changes in v25*: - Do proper filtering on hole as well (hole got missed earlier) *Changes in v24*: - Rebase on top of next-20230710 - Place WP markers in case of hole as well *Changes in v23*: - Set vec_buf_index in loop only when vec_buf_index is set - Return -EFAULT instead of -EINVAL if vec is NULL - Correctly return the walk ending address to the page granularity *Changes in v22*: - Interface change: - Replace [start start + len) with [start, end) - Return the ending address of the address walk in start *Changes in v21*: - Abort walk instead of returning error if WP is to be performed on partial hugetlb *Changes in v20* - Correct PAGE_IS_FILE and add PAGE_IS_PFNZERO *Changes in v19* - Minor changes and interface updates *Changes in v18* - Rebase on top of next-20230613 - Minor updates *Changes in v17* - Rebase on top of next-20230606 - Minor improvements in PAGEMAP_SCAN IOCTL patch *Changes in v16* - Fix a corner case - Add exclusive PM_SCAN_OP_WP back *Changes in v15* - Build fix (Add missed build fix in RESEND) *Changes in v14* - Fix build error caused by #ifdef added at last minute in some configs *Changes in v13* - Rebase on top of next-20230414 - Give-up on using uffd_wp_range() and write new helpers, flush tlb only once *Changes in v12* - Update and other memory types to UFFD_FEATURE_WP_ASYNC - Rebaase on top of next-20230406 - Review updates *Changes in v11* - Rebase on top of next-20230307 - Base patches on UFFD_FEATURE_WP_UNPOPULATED - Do a lot of cosmetic changes and review updates - Remove ENGAGE_WP + !GET operation as it can be performed with UFFDIO_WRITEPROTECT *Changes in v10* - Add specific condition to return error if hugetlb is used with wp async - Move changes in tools/include/uapi/linux/fs.h to separate patch - Add documentation *Changes in v9:* - Correct fault resolution for userfaultfd wp async - Fix build warnings and errors which were happening on some configs - Simplify pagemap ioctl's code *Changes in v8:* - Update uffd async wp implementation - Improve PAGEMAP_IOCTL implementation *Changes in v7:* - Add uffd wp async - Update the IOCTL to use uffd under the hood instead of soft-dirty flags *Motivation* The real motivation for adding PAGEMAP_SCAN IOCTL is to emulate Windows GetWriteWatch() and ResetWriteWatch() syscalls [1]. The GetWriteWatch() retrieves the addresses of the pages that are written to in a region of virtual memory. This syscall is used in Windows applications and games etc. This syscall is being emulated in pretty slow manner in userspace. Our purpose is to enhance the kernel such that we translate it efficiently in a better way. Currently some out of tree hack patches are being used to efficiently emulate it in some kernels. We intend to replace those with these patches. So the whole gaming on Linux can effectively get benefit from this. It means there would be tons of users of this code. CRIU use case [2] was mentioned by Andrei and Danylo: > Use cases for migrating sparse VMAs are binaries sanitized with ASAN, > MSAN or TSAN [3]. All of these sanitizers produce sparse mappings of > shadow memory [4]. Being able to migrate such binaries allows to highly > reduce the amount of work needed to identify and fix post-migration > crashes, which happen constantly. Andrei's defines the following uses of this code: * it is more granular and allows us to track changed pages more effectively. The current interface can clear dirty bits for the entire process only. In addition, reading info about pages is a separate operation. It means we must freeze the process to read information about all its pages, reset dirty bits, only then we can start dumping pages. The information about pages becomes more and more outdated, while we are processing pages. The new interface solves both these downsides. First, it allows us to read pte bits and clear the soft-dirty bit atomically. It means that CRIU will not need to freeze processes to pre-dump their memory. Second, it clears soft-dirty bits for a specified region of memory. It means CRIU will have actual info about pages to the moment of dumping them. * The new interface has to be much faster because basic page filtering is happening in the kernel. With the old interface, we have to read pagemap for each page. *Implementation Evolution (Short Summary)* From the definition of GetWriteWatch(), we feel like kernel's soft-dirty feature can be used under the hood with some additions like: * reset soft-dirty flag for only a specific region of memory instead of clearing the flag for the entire process * get and clear soft-dirty flag for a specific region atomically So we decided to use ioctl on pagemap file to read or/and reset soft-dirty flag. But using soft-dirty flag, sometimes we get extra pages which weren't even written. They had become soft-dirty because of VMA merging and VM_SOFTDIRTY flag. This breaks the definition of GetWriteWatch(). We were able to by-pass this short coming by ignoring VM_SOFTDIRTY until David reported that mprotect etc messes up the soft-dirty flag while ignoring VM_SOFTDIRTY [5]. This wasn't happening until [6] got introduced. We discussed if we can revert these patches. But we could not reach to any conclusion. So at this point, I made couple of tries to solve this whole VM_SOFTDIRTY issue by correcting the soft-dirty implementation: * [7] Correct the bug fixed wrongly back in 2014. It had potential to cause regression. We left it behind. * [8] Keep a list of soft-dirty part of a VMA across splits and merges. I got the reply don't increase the size of the VMA by 8 bytes. At this point, we left soft-dirty considering it is too much delicate and userfaultfd [9] seemed like the only way forward. From there onward, we have been basing soft-dirty emulation on userfaultfd wp feature where kernel resolves the faults itself when WP_ASYNC feature is used. It was straight forward to add WP_ASYNC feature in userfautlfd. Now we get only those pages dirty or written-to which are really written in reality. (PS There is another WP_UNPOPULATED userfautfd feature is required which is needed to avoid pre-faulting memory before write-protecting [9].) All the different masks were added on the request of CRIU devs to create interface more generic and better. [1] https://learn.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-… [2] https://lore.kernel.org/all/20221014134802.1361436-1-mdanylo@google.com [3] https://github.com/google/sanitizers [4] https://github.com/google/sanitizers/wiki/AddressSanitizerAlgorithm#64-bit [5] https://lore.kernel.org/all/bfcae708-db21-04b4-0bbe-712badd03071@redhat.com [6] https://lore.kernel.org/all/20220725142048.30450-1-peterx@redhat.com/ [7] https://lore.kernel.org/all/20221122115007.2787017-1-usama.anjum@collabora.… [8] https://lore.kernel.org/all/20221220162606.1595355-1-usama.anjum@collabora.… [9] https://lore.kernel.org/all/20230306213925.617814-1-peterx@redhat.com [10] https://lore.kernel.org/all/20230125144529.1630917-1-mdanylo@google.com * Original Cover letter from v8* Hello, Note: Soft-dirty pages and pages which have been written-to are synonyms. As kernel already has soft-dirty feature inside which we have given up to use, we are using written-to terminology while using UFFD async WP under the hood. It is possible to find and clear soft-dirty pages entirely in userspace. But it isn't efficient: - The mprotect and SIGSEGV handler for bookkeeping - The userfaultfd wp (synchronous) with the handler for bookkeeping Some benchmarks can be seen here[1]. This series adds features that weren't present earlier: - There is no atomic get soft-dirty/Written-to status and clear present in the kernel. - The pages which have been written-to can not be found in accurate way. (Kernel's soft-dirty PTE bit + sof_dirty VMA bit shows more soft-dirty pages than there actually are.) Historically, soft-dirty PTE bit tracking has been used in the CRIU project. The procfs interface is enough for finding the soft-dirty bit status and clearing the soft-dirty bit of all the pages of a process. We have the use case where we need to track the soft-dirty PTE bit for only specific pages on-demand. We need this tracking and clear mechanism of a region of memory while the process is running to emulate the getWriteWatch() syscall of Windows. *(Moved to using UFFD instead of soft-dirty feature to find pages which have been written-to from v7 patch series)*: Stop using the soft-dirty flags for finding which pages have been written to. It is too delicate and wrong as it shows more soft-dirty pages than the actual soft-dirty pages. There is no interest in correcting it [2][3] as this is how the feature was written years ago. It shouldn't be updated to changed behaviour. Peter Xu has suggested using the async version of the UFFD WP [4] as it is based inherently on the PTEs. So in this patch series, I've added a new mode to the UFFD which is asynchronous version of the write protect. When this variant of the UFFD WP is used, the page faults are resolved automatically by the kernel. The pages which have been written-to can be found by reading pagemap file (!PM_UFFD_WP). This feature can be used successfully to find which pages have been written to from the time the pages were write protected. This works just like the soft-dirty flag without showing any extra pages which aren't soft-dirty in reality. The information related to pages if the page is file mapped, present and swapped is required for the CRIU project [5][6]. The addition of the required mask, any mask, excluded mask and return masks are also required for the CRIU project [5]. The IOCTL returns the addresses of the pages which match the specific masks. The page addresses are returned in struct page_region in a compact form. The max_pages is needed to support a use case where user only wants to get a specific number of pages. So there is no need to find all the pages of interest in the range when max_pages is specified. The IOCTL returns when the maximum number of the pages are found. The max_pages is optional. If max_pages is specified, it must be equal or greater than the vec_size. This restriction is needed to handle worse case when one page_region only contains info of one page and it cannot be compacted. This is needed to emulate the Windows getWriteWatch() syscall. The patch series include the detailed selftest which can be used as an example for the uffd async wp test and PAGEMAP_IOCTL. It shows the interface usages as well. [1] https://lore.kernel.org/lkml/54d4c322-cd6e-eefd-b161-2af2b56aae24@collabora… [2] https://lore.kernel.org/all/20221220162606.1595355-1-usama.anjum@collabora.… [3] https://lore.kernel.org/all/20221122115007.2787017-1-usama.anjum@collabora.… [4] https://lore.kernel.org/all/Y6Hc2d+7eTKs7AiH@x1n [5] https://lore.kernel.org/all/YyiDg79flhWoMDZB@gmail.com/ [6] https://lore.kernel.org/all/20221014134802.1361436-1-mdanylo@google.com/ Regards, Muhammad Usama Anjum Muhammad Usama Anjum (4): fs/proc/task_mmu: Implement IOCTL to get and optionally clear info about PTEs tools headers UAPI: Update linux/fs.h with the kernel sources mm/pagemap: add documentation of PAGEMAP_SCAN IOCTL selftests: mm: add pagemap ioctl tests Peter Xu (1): userfaultfd: UFFD_FEATURE_WP_ASYNC Documentation/admin-guide/mm/pagemap.rst | 64 + Documentation/admin-guide/mm/userfaultfd.rst | 35 + fs/proc/task_mmu.c | 653 ++++++++ fs/userfaultfd.c | 26 +- include/linux/hugetlb.h | 1 + include/linux/userfaultfd_k.h | 21 +- include/uapi/linux/fs.h | 58 + include/uapi/linux/userfaultfd.h | 9 +- mm/hugetlb.c | 34 +- mm/memory.c | 27 +- tools/include/uapi/linux/fs.h | 58 + tools/testing/selftests/mm/.gitignore | 2 + tools/testing/selftests/mm/Makefile | 3 +- tools/testing/selftests/mm/config | 1 + tools/testing/selftests/mm/pagemap_ioctl.c | 1485 ++++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 4 + 16 files changed, 2457 insertions(+), 24 deletions(-) create mode 100644 tools/testing/selftests/mm/pagemap_ioctl.c -- 2.39.2

1 year, 11 months

4
19
0 0

[PATCH v2] tools/nolibc: fix up size inflate regression

by Zhangjin Wu

As reported and suggested by Willy, the inline __sysret() helper introduces three types of conversions and increases the size: (1) the "unsigned long" argument to __sysret() forces a sign extension from all sys_* functions that used to return 'int' (2) the comparison with the error range now has to be performed on a 'unsigned long' instead of an 'int' (3) the return value from __sysret() is a 'long' (note, a signed long) which then has to be turned back to an 'int' before being returned by the caller to satisfy the caller's prototype. To fix up this, firstly, let's use macro instead of inline function to preserves the input type and avoids these useless conversions (1), (3). Secondly, comparison to -MAX_ERRNO inflicts on all integer returns where we could previously keep a simple sign comparison, let's use a new is_signed_type() macro from include/linux/compiler.h to limit the comparision to -MAX_ERRNO (2) only on demand and preserves a simple sign comparision for most of the cases as before. Thirdly, fix up the following warning by an explicit conversion and let __sysret() be able to accept the (void *) type of argument: sysroot/powerpc/include/sys.h: In function 'sbrk': sysroot/powerpc/include/sys.h:104:16: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast] 104 | return (void *)__sysret(-ENOMEM); Fourthly, to further workaround the argument type with 'const', must use __auto_type in a new enough version or use 'long' as before. Here reports the size testing result with nolibc-test: before: // ppc64le $ size nolibc-test text data bss dec hex filename 27916 8 80 28004 6d64 nolibc-test // mips $ size nolibc-test text data bss dec hex filename 23276 64 64 23404 5b6c nolibc-test after: // ppc64le $ size nolibc-test text data bss dec hex filename 27736 8 80 27824 6cb0 nolibc-test // mips $ size nolibc-test text data bss dec hex filename 23036 64 64 23164 5a7c nolibc-test Suggested-by: Willy Tarreau <w(a)1wt.eu> Link: https://lore.kernel.org/lkml/20230806095846.GB10627@1wt.eu/ Link: https://lore.kernel.org/lkml/20230806134348.GA19145@1wt.eu/ Signed-off-by: Zhangjin Wu <falcon(a)tinylab.org> --- v2 here is further fix up argument with 'const' in the type and also support "void *" argument, v1 is [1]. Tested on many architectures (i386, x86_64, mips, ppc64) and gcc version (from gcc 4.8-13.1.0), compiles well without any warning and errors and also with smaller size. [1]: https://lore.kernel.org/lkml/20230806131921.52453-1-falcon@tinylab.org/ --- tools/include/nolibc/sys.h | 52 ++++++++++++++++++++++++++++++-------- 1 file changed, 41 insertions(+), 11 deletions(-) diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h index 56f63eb48a1b..9c7448ae19e2 100644 --- a/tools/include/nolibc/sys.h +++ b/tools/include/nolibc/sys.h @@ -35,15 +35,45 @@ * (src/internal/syscall_ret.c) and glibc (sysdeps/unix/sysv/linux/sysdep.h) */ -static __inline__ __attribute__((unused, always_inline)) -long __sysret(unsigned long ret) -{ - if (ret >= (unsigned long)-MAX_ERRNO) { - SET_ERRNO(-(long)ret); - return -1; - } - return ret; -} +/* + * Whether 'type' is a signed type or an unsigned type. Supports scalar types, + * bool and also pointer types. (from include/linux/compiler.h) + */ +#define __is_signed_type(type) (((type)(-1)) < (type)1) + +/* __auto_type is used instead of __typeof__ to workaround the build error + * 'error: assignment of read-only variable' when the argument has 'const' in + * the type, but __auto_type is a new feature from newer version and it only + * work with 'const' from gcc 11.0 (__GXX_ABI_VERSION = 1016) + * https://gcc.gnu.org/legacy-ml/gcc-patches/2013-11/msg01378.html + */ + +#if __GXX_ABI_VERSION < 1016 +#define __typeofdecl(arg) long +#define __typeofconv1(arg) (long) +#define __typeofconv2(arg) (long) +#else +#define __typeofdecl(arg) __auto_type +#define __typeofconv1(arg) +#define __typeofconv2(arg) (__typeof__(arg)) +#endif + +#define __sysret(arg) \ +({ \ + __typeofdecl(arg) __sysret_arg = __typeofconv1(arg)(arg); \ + if (__is_signed_type(__typeof__(arg))) { \ + if (__sysret_arg < 0) { \ + SET_ERRNO(-(long)__sysret_arg); \ + __sysret_arg = __typeofconv2(arg)(-1L); \ + } \ + } else { \ + if ((unsigned long)__sysret_arg >= (unsigned long)-MAX_ERRNO) { \ + SET_ERRNO(-(long)__sysret_arg); \ + __sysret_arg = __typeofconv2(arg)(-1L); \ + } \ + } \ + (__typeof__(arg))__sysret_arg; \ +}) /* Functions in this file only describe syscalls. They're declared static so * that the compiler usually decides to inline them while still being allowed @@ -94,7 +124,7 @@ void *sbrk(intptr_t inc) if (ret && sys_brk(ret + inc) == ret + inc) return ret + inc; - return (void *)__sysret(-ENOMEM); + return __sysret((void *)-ENOMEM); } @@ -682,7 +712,7 @@ void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd, static __attribute__((unused)) void *mmap(void *addr, size_t length, int prot, int flags, int fd, off_t offset) { - return (void *)__sysret((unsigned long)sys_mmap(addr, length, prot, flags, fd, offset)); + return __sysret(sys_mmap(addr, length, prot, flags, fd, offset)); } static __attribute__((unused)) -- 2.25.1

1 year, 11 months

1
1
0 0

[PATCH] tools/nolibc: fix up size inflate regression

by Zhangjin Wu

As reported and suggested by Willy, the inline __sysret() helper introduces three types of conversions and increases the size: (1) the "unsigned long" argument to __sysret() forces a sign extension from all sys_* functions that used to return 'int' (2) the comparison with the error range now has to be performed on a 'unsigned long' instead of an 'int' (3) the return value from __sysret() is a 'long' (note, a signed long) which then has to be turned back to an 'int' before being returned by the caller to satisfy the caller's prototype. To fix up this, firstly, let's use macro instead of inline function to preserves the input type and avoids these useless conversions (1), (3). Secondly, comparison to -MAX_ERRNO inflicts on all integer returns where we could previously keep a simple sign comparison, let's use a new is_signed_type() macro from include/linux/compiler.h to limit the comparision to -MAX_ERRNO (2) only on demand and preserves a simple sign comparision for most of the cases as before. Thirdly, fix up the following warning by an explicit conversion: sysroot/powerpc/include/sys.h: In function 'sbrk': sysroot/powerpc/include/sys.h:104:16: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast] 104 | return (void *)__sysret(-ENOMEM); Here reports the size testing result with nolibc-test: before: // ppc64le $ size nolibc-test text data bss dec hex filename 27916 8 80 28004 6d64 nolibc-test // mips $ size nolibc-test text data bss dec hex filename 23276 64 64 23404 5b6c nolibc-test after: // ppc64le $ size nolibc-test text data bss dec hex filename 27736 8 80 27824 6cb0 nolibc-test // mips $ size nolibc-test text data bss dec hex filename 23036 64 64 23164 5a7c nolibc-test Suggested-by: Willy Tarreau <w(a)1wt.eu> Link: https://lore.kernel.org/lkml/20230806095846.GB10627@1wt.eu/#R Signed-off-by: Zhangjin Wu <falcon(a)tinylab.org> --- tools/include/nolibc/compiler.h | 9 +++++++++ tools/include/nolibc/sys.h | 27 +++++++++++++++++---------- 2 files changed, 26 insertions(+), 10 deletions(-) diff --git a/tools/include/nolibc/compiler.h b/tools/include/nolibc/compiler.h index beddc3665d69..360dfc533814 100644 --- a/tools/include/nolibc/compiler.h +++ b/tools/include/nolibc/compiler.h @@ -22,4 +22,13 @@ # define __no_stack_protector __attribute__((__optimize__("-fno-stack-protector"))) #endif /* defined(__has_attribute) */ +/* + * from include/linux/compiler.h + * + * Whether 'type' is a signed type or an unsigned type. Supports scalar types, + * bool and also pointer types. + */ +#define is_signed_type(type) (((type)(-1)) < (type)1) +#define is_unsigned_type(type) (!is_signed_type(type)) + #endif /* _NOLIBC_COMPILER_H */ diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h index 56f63eb48a1b..8271302f79c4 100644 --- a/tools/include/nolibc/sys.h +++ b/tools/include/nolibc/sys.h @@ -35,15 +35,22 @@ * (src/internal/syscall_ret.c) and glibc (sysdeps/unix/sysv/linux/sysdep.h) */ -static __inline__ __attribute__((unused, always_inline)) -long __sysret(unsigned long ret) -{ - if (ret >= (unsigned long)-MAX_ERRNO) { - SET_ERRNO(-(long)ret); - return -1; - } - return ret; -} +#define __sysret(arg) \ +({ \ + __typeof__(arg) __sysret_arg = (arg); \ + if (is_signed_type(__typeof__(arg))) { \ + if (__sysret_arg < 0) { \ + SET_ERRNO(-(int)__sysret_arg); \ + __sysret_arg = -1L; \ + } \ + } else { \ + if ((unsigned long)__sysret_arg >= (unsigned long)-MAX_ERRNO) { \ + SET_ERRNO(-(int)__sysret_arg); \ + __sysret_arg = -1L; \ + } \ + } \ + __sysret_arg; \ +}) /* Functions in this file only describe syscalls. They're declared static so * that the compiler usually decides to inline them while still being allowed @@ -94,7 +101,7 @@ void *sbrk(intptr_t inc) if (ret && sys_brk(ret + inc) == ret + inc) return ret + inc; - return (void *)__sysret(-ENOMEM); + return (void *)__sysret((unsigned long)-ENOMEM); } -- 2.25.1

1 year, 11 months

2
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror