diff --git a/Android.mk b/Android.mk new file mode 100644 index 0000000..5f13c04 --- /dev/null +++ b/Android.mk @@ -0,0 +1,24 @@ +LOCAL_PATH := $(call my-dir) + +include $(CLEAR_VARS) +LOCAL_MODULE := crt0 + +# Manually link the compiler runtime library +LOCAL_compiler_rt := $(shell $(TARGET_CC) -target $(LLVM_TRIPLE)$(TARGET_PLATFORM_LEVEL) --print-libgcc-file-name) + +LOCAL_EXPORT_LDFLAGS := -static -nostartfiles -nodefaultlibs $(LOCAL_compiler_rt) -Wl,--error-limit=0 +LOCAL_CFLAGS := -Wno-c99-designator + +LOCAL_SRC_FILES := \ + malloc.c \ + mem.c \ + misc.c \ + nolibc.c \ + stdio.c \ + syscall.c \ + bionic/dirent.cpp \ + bionic/strerror.cpp \ + bionic/syscall-$(TARGET_ARCH).S \ + tinystdio/tinystdio.c + +include $(BUILD_STATIC_LIBRARY) diff --git a/bionic/dirent.cpp b/bionic/dirent.cpp new file mode 100644 index 0000000..6d4c1bf --- /dev/null +++ b/bionic/dirent.cpp @@ -0,0 +1,168 @@ +/* + * Copyright (C) 2008 The Android Open Source Project + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE + * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, + * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, + * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS + * OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED + * AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, + * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT + * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#include + +#include +#include +#include +#include +#include +#include +#include + +#include "private/ErrnoRestorer.h" + +extern "C" int sys_getdents64(unsigned int, dirent*, unsigned int); + +// Apportable decided to copy the data structure from this file +// and use it in their own code, but they also call into readdir. +// In order to avoid a lockup, the structure must be maintained in +// the exact same order as in L and below. New structure members +// need to be added to the end of this structure. +// See b/21037208 for more details. +struct DIR { + int fd_; + size_t available_bytes_; + dirent* next_; + dirent buff_[15]; + long current_pos_; +}; + +static DIR* __allocate_DIR(int fd) { + DIR* d = reinterpret_cast(malloc(sizeof(DIR))); + if (d == nullptr) { + return nullptr; + } + d->fd_ = fd; + d->available_bytes_ = 0; + d->next_ = nullptr; + d->current_pos_ = 0L; + return d; +} + +int dirfd(DIR* d) { + return d->fd_; +} + +DIR* fdopendir(int fd) { + // Is 'fd' actually a directory? + struct stat sb; + if (fstat(fd, &sb) == -1) { + return nullptr; + } + if (!S_ISDIR(sb.st_mode)) { + errno = ENOTDIR; + return nullptr; + } + + return __allocate_DIR(fd); +} + +DIR* opendir(const char* path) { + int fd = open(path, O_CLOEXEC | O_DIRECTORY | O_RDONLY); + return (fd != -1) ? __allocate_DIR(fd) : nullptr; +} + +static bool __fill_DIR(DIR* d) { + int rc = TEMP_FAILURE_RETRY(sys_getdents64(d->fd_, d->buff_, sizeof(d->buff_))); + if (rc <= 0) { + return false; + } + d->available_bytes_ = rc; + d->next_ = d->buff_; + return true; +} + +static dirent* __readdir_locked(DIR* d) { + if (d->available_bytes_ == 0 && !__fill_DIR(d)) { + return nullptr; + } + + dirent* entry = d->next_; + d->next_ = reinterpret_cast(reinterpret_cast(entry) + entry->d_reclen); + d->available_bytes_ -= entry->d_reclen; + // The directory entry offset uses 0, 1, 2 instead of real file offset, + // so the value range of long type is enough. + d->current_pos_ = static_cast(entry->d_off); + return entry; +} + +dirent* readdir(DIR* d) { + return __readdir_locked(d); +} +__strong_alias(readdir64, readdir); + +int readdir_r(DIR* d, dirent* entry, dirent** result) { + ErrnoRestorer errno_restorer; + + *result = nullptr; + errno = 0; + + dirent* next = __readdir_locked(d); + if (errno != 0 && next == nullptr) { + return errno; + } + + if (next != nullptr) { + memcpy(entry, next, next->d_reclen); + *result = entry; + } + return 0; +} +__strong_alias(readdir64_r, readdir_r); + +int closedir(DIR* d) { + if (d == nullptr) { + errno = EINVAL; + return -1; + } + + int fd = d->fd_; + int rc = close(fd); + free(d); + return rc; +} + +void rewinddir(DIR* d) { + lseek(d->fd_, 0, SEEK_SET); + d->available_bytes_ = 0; + d->current_pos_ = 0L; +} + +void seekdir(DIR* d, long offset) { + off_t ret = lseek(d->fd_, offset, SEEK_SET); + if (ret != -1L) { + d->available_bytes_ = 0; + d->current_pos_ = ret; + } +} + +long telldir(DIR* d) { + return d->current_pos_; +} diff --git a/bionic/private/ErrnoRestorer.h b/bionic/private/ErrnoRestorer.h new file mode 100644 index 0000000..e698bb6 --- /dev/null +++ b/bionic/private/ErrnoRestorer.h @@ -0,0 +1,36 @@ +/* + * Copyright (C) 2013 The Android Open Source Project + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +#pragma once + +#include + +class ErrnoRestorer { + public: + explicit ErrnoRestorer() : saved_errno_(errno) { + } + + ~ErrnoRestorer() { + errno = saved_errno_; + } + + void override(int new_errno) { + saved_errno_ = new_errno; + } + + private: + int saved_errno_; +}; diff --git a/bionic/private/bionic_asm.h b/bionic/private/bionic_asm.h new file mode 100644 index 0000000..333f4fa --- /dev/null +++ b/bionic/private/bionic_asm.h @@ -0,0 +1,115 @@ +/* + * Copyright (C) 2013 The Android Open Source Project + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE + * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, + * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, + * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS + * OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED + * AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, + * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT + * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#pragma once + +#define __ASSEMBLY__ + +/* https://github.com/android/ndk/issues/1422 */ +#include + +#include /* For system call numbers. */ +#define MAX_ERRNO 4095 /* For recognizing system call error returns. */ + +#define __bionic_asm_custom_entry(f) +#define __bionic_asm_custom_end(f) +#define __bionic_asm_function_type @function +#define __bionic_asm_custom_note_gnu_section() + +#if defined(__aarch64__) +#include "bionic_asm_arm64.h" +#elif defined(__arm__) +#include "bionic_asm_arm.h" +#elif defined(__i386__) +#include "bionic_asm_x86.h" +#elif defined(__riscv) +#include "bionic_asm_riscv64.h" +#elif defined(__x86_64__) +#include "bionic_asm_x86_64.h" +#endif + +// Starts a normal assembler routine. +#define ENTRY(__f) __ENTRY_WITH_BINDING(__f, .globl) + +// Starts an assembler routine with hidden visibility. +#define ENTRY_PRIVATE(__f) \ + __ENTRY_WITH_BINDING(__f, .globl); \ + .hidden __f; + +// Starts an assembler routine that's weak so native bridges can override it. +#define ENTRY_WEAK_FOR_NATIVE_BRIDGE(__f) __ENTRY_WITH_BINDING(__f, .weak) + +// Starts an assembler routine with hidden visibility and no DWARF information. +// Only used for internal functions passed via sa_restorer. +// TODO: can't we just delete all those and let the kernel do its thing? +#define ENTRY_NO_DWARF_PRIVATE(__f) \ + __ENTRY_NO_DWARF(__f, .globl); \ + .hidden __f; + +// (Implementation detail.) +#define __ENTRY_NO_DWARF(__f, __binding) \ + .text; \ + __binding __f; \ + .balign __bionic_asm_align; \ + .type __f, __bionic_asm_function_type; \ + __f: \ + __bionic_asm_custom_entry(__f); + +// (Implementation detail.) +#define __ENTRY_WITH_BINDING(__f, __binding) \ + __ENTRY_NO_DWARF(__f, __binding); \ + .cfi_startproc; + +// Ends a normal assembler routine. +#define END(__f) \ + .cfi_endproc; \ + END_NO_DWARF(__f) + +// Ends an assembler routine with no DWARF information. +// Only used for internal functions passed via sa_restorer. +// TODO: can't we just delete all those and let the kernel do its thing? +#define END_NO_DWARF(__f) \ + .size __f, .- __f; \ + __bionic_asm_custom_end(__f) + +// Creates an alias `alias` for the symbol `original`. +#define ALIAS_SYMBOL(alias, original) \ + .globl alias; \ + .equ alias, original + +// Creates an alias `alias` for the symbol `original` that's weak so it can be +// separately overridden by native bridges. +#define ALIAS_SYMBOL_WEAK_FOR_NATIVE_BRIDGE(alias, original) \ + .weak alias; \ + .equ alias, original + +// Adds a GNU property ELF note. Important on arm64 to declare PAC/BTI support. +#define NOTE_GNU_PROPERTY() __bionic_asm_custom_note_gnu_section() + +// Gives local labels a more convenient and readable syntax. +#define L(__label) .L##__label diff --git a/bionic/private/bionic_asm_arm.h b/bionic/private/bionic_asm_arm.h new file mode 100644 index 0000000..d8381d3 --- /dev/null +++ b/bionic/private/bionic_asm_arm.h @@ -0,0 +1,48 @@ +/* $OpenBSD: asm.h,v 1.1 2004/02/01 05:09:49 drahn Exp $ */ +/* $NetBSD: asm.h,v 1.4 2001/07/16 05:43:32 matt Exp $ */ + +/* + * Copyright (c) 1990 The Regents of the University of California. + * All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * William Jolitz. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * from: @(#)asm.h 5.5 (Berkeley) 5/7/91 + */ + +#pragma once + +#define __bionic_asm_align 0 + +#undef __bionic_asm_custom_entry +#undef __bionic_asm_custom_end +#define __bionic_asm_custom_entry(f) .fnstart +#define __bionic_asm_custom_end(f) .fnend + +#undef __bionic_asm_function_type +#define __bionic_asm_function_type #function diff --git a/bionic/private/bionic_asm_arm64.h b/bionic/private/bionic_asm_arm64.h new file mode 100644 index 0000000..ffc7181 --- /dev/null +++ b/bionic/private/bionic_asm_arm64.h @@ -0,0 +1,79 @@ +/* $OpenBSD: asm.h,v 1.1 2004/02/01 05:09:49 drahn Exp $ */ +/* $NetBSD: asm.h,v 1.4 2001/07/16 05:43:32 matt Exp $ */ + +/* + * Copyright (c) 1990 The Regents of the University of California. + * All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * William Jolitz. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * from: @(#)asm.h 5.5 (Berkeley) 5/7/91 + */ + +#pragma once + +#define __bionic_asm_align 16 + +#undef __bionic_asm_function_type +#define __bionic_asm_function_type %function + +#if defined(__ARM_FEATURE_BTI_DEFAULT) +#define __bionic_asm_aarch64_feature_bti (1 << 0) +#undef __bionic_asm_custom_entry +#define __bionic_asm_custom_entry(f) bti c +#else +#define __bionic_asm_aarch64_feature_bti 0 +#endif + +#if defined(__ARM_FEATURE_PAC_DEFAULT) +#define __bionic_asm_aarch64_feature_pac (1 << 1) +#else +#define __bionic_asm_aarch64_feature_pac 0 +#endif + +#undef __bionic_asm_custom_note_gnu_section +#define __bionic_asm_custom_note_gnu_section() \ + .pushsection .note.gnu.property, "a"; \ + .balign 8; \ + .long 4; \ + .long 0x10; \ + .long 0x5; /* NT_GNU_PROPERTY_TYPE_0 */ \ + .asciz "GNU"; \ + .long 0xc0000000; /* GNU_PROPERTY_AARCH64_FEATURE_1_AND */ \ + .long 4; \ + .long (__bionic_asm_aarch64_feature_pac | \ + __bionic_asm_aarch64_feature_bti); \ + .long 0; \ + .popsection; + +#define NT_MEMTAG_LEVEL_MASK 3 +#define NT_MEMTAG_LEVEL_NONE 0 +#define NT_MEMTAG_LEVEL_ASYNC 1 +#define NT_MEMTAG_LEVEL_SYNC 2 +#define NT_MEMTAG_HEAP 4 +#define NT_MEMTAG_STACK 8 diff --git a/bionic/private/bionic_asm_riscv64.h b/bionic/private/bionic_asm_riscv64.h new file mode 100644 index 0000000..463ca31 --- /dev/null +++ b/bionic/private/bionic_asm_riscv64.h @@ -0,0 +1,43 @@ +/* $OpenBSD: asm.h,v 1.1 2004/02/01 05:09:49 drahn Exp $ */ +/* $NetBSD: asm.h,v 1.4 2001/07/16 05:43:32 matt Exp $ */ + +/* + * Copyright (c) 1990 The Regents of the University of California. + * All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * William Jolitz. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * from: @(#)asm.h 5.5 (Berkeley) 5/7/91 + */ + +#pragma once + +#define __bionic_asm_align 16 + +#undef __bionic_asm_function_type +#define __bionic_asm_function_type %function diff --git a/bionic/private/bionic_asm_x86.h b/bionic/private/bionic_asm_x86.h new file mode 100644 index 0000000..fcec40b --- /dev/null +++ b/bionic/private/bionic_asm_x86.h @@ -0,0 +1,51 @@ +/* $NetBSD: asm.h,v 1.40 2011/06/16 13:16:20 joerg Exp $ */ + +/*- + * Copyright (c) 1990 The Regents of the University of California. + * All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * William Jolitz. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * @(#)asm.h 5.5 (Berkeley) 5/7/91 + */ + +#pragma once + +#define PIC_PROLOGUE \ + pushl %ebx; \ + call 666f; \ +666: \ + popl %ebx; \ + addl $_GLOBAL_OFFSET_TABLE_+[.-666b], %ebx +#define PIC_EPILOGUE \ + popl %ebx +#define PIC_PLT(x) x@PLT +#define PIC_GOT(x) x@GOT(%ebx) +#define PIC_GOTOFF(x) x@GOTOFF(%ebx) + +#define __bionic_asm_align 16 diff --git a/bionic/private/bionic_asm_x86_64.h b/bionic/private/bionic_asm_x86_64.h new file mode 100644 index 0000000..c553b0c --- /dev/null +++ b/bionic/private/bionic_asm_x86_64.h @@ -0,0 +1,42 @@ +/* $NetBSD: asm.h,v 1.18 2013/09/12 15:36:17 joerg Exp $ */ + +/*- + * Copyright (c) 1990 The Regents of the University of California. + * All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * William Jolitz. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * @(#)asm.h 5.5 (Berkeley) 5/7/91 + */ + +#pragma once + +#define PIC_PLT(x) x@PLT +#define PIC_GOT(x) x@GOTPCREL(%rip) + +#define __bionic_asm_align 16 diff --git a/bionic/private/bionic_errdefs.h b/bionic/private/bionic_errdefs.h new file mode 100644 index 0000000..435d49b --- /dev/null +++ b/bionic/private/bionic_errdefs.h @@ -0,0 +1,171 @@ +/* + * Copyright (C) 2023 The Android Open Source Project + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE + * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, + * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, + * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS + * OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED + * AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, + * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT + * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +/* + * This header is used to define error constants and names; + * it might be included several times. + */ + +#ifndef __BIONIC_ERRDEF +#error __BIONIC_ERRDEF not defined +#endif + +__BIONIC_ERRDEF(0, "Success") +__BIONIC_ERRDEF(EPERM, "Operation not permitted") +__BIONIC_ERRDEF(ENOENT, "No such file or directory") +__BIONIC_ERRDEF(ESRCH, "No such process") +__BIONIC_ERRDEF(EINTR, "Interrupted system call") +__BIONIC_ERRDEF(EIO, "I/O error") +__BIONIC_ERRDEF(ENXIO, "No such device or address") +__BIONIC_ERRDEF(E2BIG, "Argument list too long") +__BIONIC_ERRDEF(ENOEXEC, "Exec format error") +__BIONIC_ERRDEF(EBADF, "Bad file descriptor") +__BIONIC_ERRDEF(ECHILD, "No child processes") +__BIONIC_ERRDEF(EAGAIN, "Try again") +__BIONIC_ERRDEF(ENOMEM, "Out of memory") +__BIONIC_ERRDEF(EACCES, "Permission denied") +__BIONIC_ERRDEF(EFAULT, "Bad address") +__BIONIC_ERRDEF(ENOTBLK, "Block device required") +__BIONIC_ERRDEF(EBUSY, "Device or resource busy") +__BIONIC_ERRDEF(EEXIST, "File exists") +__BIONIC_ERRDEF(EXDEV, "Cross-device link") +__BIONIC_ERRDEF(ENODEV, "No such device") +__BIONIC_ERRDEF(ENOTDIR, "Not a directory") +__BIONIC_ERRDEF(EISDIR, "Is a directory") +__BIONIC_ERRDEF(EINVAL, "Invalid argument") +__BIONIC_ERRDEF(ENFILE, "File table overflow") +__BIONIC_ERRDEF(EMFILE, "Too many open files") +__BIONIC_ERRDEF(ENOTTY, "Inappropriate ioctl for device") +__BIONIC_ERRDEF(ETXTBSY, "Text file busy") +__BIONIC_ERRDEF(EFBIG, "File too large") +__BIONIC_ERRDEF(ENOSPC, "No space left on device") +__BIONIC_ERRDEF(ESPIPE, "Illegal seek") +__BIONIC_ERRDEF(EROFS, "Read-only file system") +__BIONIC_ERRDEF(EMLINK, "Too many links") +__BIONIC_ERRDEF(EPIPE, "Broken pipe") +__BIONIC_ERRDEF(EDOM, "Math argument out of domain of func") +__BIONIC_ERRDEF(ERANGE, "Math result not representable") +__BIONIC_ERRDEF(EDEADLK, "Resource deadlock would occur") +__BIONIC_ERRDEF(ENAMETOOLONG, "File name too long") +__BIONIC_ERRDEF(ENOLCK, "No record locks available") +__BIONIC_ERRDEF(ENOSYS, "Function not implemented") +__BIONIC_ERRDEF(ENOTEMPTY, "Directory not empty") +__BIONIC_ERRDEF(ELOOP, "Too many symbolic links encountered") +__BIONIC_ERRDEF(ENOMSG, "No message of desired type") +__BIONIC_ERRDEF(EIDRM, "Identifier removed") +__BIONIC_ERRDEF(ECHRNG, "Channel number out of range") +__BIONIC_ERRDEF(EL2NSYNC, "Level 2 not synchronized") +__BIONIC_ERRDEF(EL3HLT, "Level 3 halted") +__BIONIC_ERRDEF(EL3RST, "Level 3 reset") +__BIONIC_ERRDEF(ELNRNG, "Link number out of range") +__BIONIC_ERRDEF(EUNATCH, "Protocol driver not attached") +__BIONIC_ERRDEF(ENOCSI, "No CSI structure available") +__BIONIC_ERRDEF(EL2HLT, "Level 2 halted") +__BIONIC_ERRDEF(EBADE, "Invalid exchange") +__BIONIC_ERRDEF(EBADR, "Invalid request descriptor") +__BIONIC_ERRDEF(EXFULL, "Exchange full") +__BIONIC_ERRDEF(ENOANO, "No anode") +__BIONIC_ERRDEF(EBADRQC, "Invalid request code") +__BIONIC_ERRDEF(EBADSLT, "Invalid slot") +__BIONIC_ERRDEF(EBFONT, "Bad font file format") +__BIONIC_ERRDEF(ENOSTR, "Device not a stream") +__BIONIC_ERRDEF(ENODATA, "No data available") +__BIONIC_ERRDEF(ETIME, "Timer expired") +__BIONIC_ERRDEF(ENOSR, "Out of streams resources") +__BIONIC_ERRDEF(ENONET, "Machine is not on the network") +__BIONIC_ERRDEF(ENOPKG, "Package not installed") +__BIONIC_ERRDEF(EREMOTE, "Object is remote") +__BIONIC_ERRDEF(ENOLINK, "Link has been severed") +__BIONIC_ERRDEF(EADV, "Advertise error") +__BIONIC_ERRDEF(ESRMNT, "Srmount error") +__BIONIC_ERRDEF(ECOMM, "Communication error on send") +__BIONIC_ERRDEF(EPROTO, "Protocol error") +__BIONIC_ERRDEF(EMULTIHOP, "Multihop attempted") +__BIONIC_ERRDEF(EDOTDOT, "RFS specific error") +__BIONIC_ERRDEF(EBADMSG, "Not a data message") +__BIONIC_ERRDEF(EOVERFLOW, "Value too large for defined data type") +__BIONIC_ERRDEF(ENOTUNIQ, "Name not unique on network") +__BIONIC_ERRDEF(EBADFD, "File descriptor in bad state") +__BIONIC_ERRDEF(EREMCHG, "Remote address changed") +__BIONIC_ERRDEF(ELIBACC, "Can not access a needed shared library") +__BIONIC_ERRDEF(ELIBBAD, "Accessing a corrupted shared library") +__BIONIC_ERRDEF(ELIBSCN, ".lib section in a.out corrupted") +__BIONIC_ERRDEF(ELIBMAX, "Attempting to link in too many shared libraries") +__BIONIC_ERRDEF(ELIBEXEC, "Cannot exec a shared library directly") +__BIONIC_ERRDEF(EILSEQ, "Illegal byte sequence") +__BIONIC_ERRDEF(ERESTART, "Interrupted system call should be restarted") +__BIONIC_ERRDEF(ESTRPIPE, "Streams pipe error") +__BIONIC_ERRDEF(EUSERS, "Too many users") +__BIONIC_ERRDEF(ENOTSOCK, "Socket operation on non-socket") +__BIONIC_ERRDEF(EDESTADDRREQ, "Destination address required") +__BIONIC_ERRDEF(EMSGSIZE, "Message too long") +__BIONIC_ERRDEF(EPROTOTYPE, "Protocol wrong type for socket") +__BIONIC_ERRDEF(ENOPROTOOPT, "Protocol not available") +__BIONIC_ERRDEF(EPROTONOSUPPORT, "Protocol not supported") +__BIONIC_ERRDEF(ESOCKTNOSUPPORT, "Socket type not supported") +__BIONIC_ERRDEF(EOPNOTSUPP, "Operation not supported on transport endpoint") +__BIONIC_ERRDEF(EPFNOSUPPORT, "Protocol family not supported") +__BIONIC_ERRDEF(EAFNOSUPPORT, "Address family not supported by protocol") +__BIONIC_ERRDEF(EADDRINUSE, "Address already in use") +__BIONIC_ERRDEF(EADDRNOTAVAIL, "Cannot assign requested address") +__BIONIC_ERRDEF(ENETDOWN, "Network is down") +__BIONIC_ERRDEF(ENETUNREACH, "Network is unreachable") +__BIONIC_ERRDEF(ENETRESET, "Network dropped connection because of reset") +__BIONIC_ERRDEF(ECONNABORTED, "Software caused connection abort") +__BIONIC_ERRDEF(ECONNRESET, "Connection reset by peer") +__BIONIC_ERRDEF(ENOBUFS, "No buffer space available") +__BIONIC_ERRDEF(EISCONN, "Transport endpoint is already connected") +__BIONIC_ERRDEF(ENOTCONN, "Transport endpoint is not connected") +__BIONIC_ERRDEF(ESHUTDOWN, "Cannot send after transport endpoint shutdown") +__BIONIC_ERRDEF(ETOOMANYREFS, "Too many references: cannot splice") +__BIONIC_ERRDEF(ETIMEDOUT, "Connection timed out") +__BIONIC_ERRDEF(ECONNREFUSED, "Connection refused") +__BIONIC_ERRDEF(EHOSTDOWN, "Host is down") +__BIONIC_ERRDEF(EHOSTUNREACH, "No route to host") +__BIONIC_ERRDEF(EALREADY, "Operation already in progress") +__BIONIC_ERRDEF(EINPROGRESS, "Operation now in progress") +__BIONIC_ERRDEF(ESTALE, "Stale NFS file handle") +__BIONIC_ERRDEF(EUCLEAN, "Structure needs cleaning") +__BIONIC_ERRDEF(ENOTNAM, "Not a XENIX named type file") +__BIONIC_ERRDEF(ENAVAIL, "No XENIX semaphores available") +__BIONIC_ERRDEF(EISNAM, "Is a named type file") +__BIONIC_ERRDEF(EREMOTEIO, "Remote I/O error") +__BIONIC_ERRDEF(EDQUOT, "Quota exceeded") +__BIONIC_ERRDEF(ENOMEDIUM, "No medium found") +__BIONIC_ERRDEF(EMEDIUMTYPE, "Wrong medium type") +__BIONIC_ERRDEF(ECANCELED, "Operation Canceled") +__BIONIC_ERRDEF(ENOKEY, "Required key not available") +__BIONIC_ERRDEF(EKEYEXPIRED, "Key has expired") +__BIONIC_ERRDEF(EKEYREVOKED, "Key has been revoked") +__BIONIC_ERRDEF(EKEYREJECTED, "Key was rejected by service") +__BIONIC_ERRDEF(EOWNERDEAD, "Owner died") +__BIONIC_ERRDEF(ENOTRECOVERABLE, "State not recoverable") +__BIONIC_ERRDEF(ERFKILL, "Operation not possible due to RF-kill") +__BIONIC_ERRDEF(EHWPOISON, "Memory page has hardware error") + +#undef __BIONIC_ERRDEF diff --git a/bionic/strerror.cpp b/bionic/strerror.cpp new file mode 100644 index 0000000..b6a8f5e --- /dev/null +++ b/bionic/strerror.cpp @@ -0,0 +1,100 @@ +/* + * Copyright (C) 2012 The Android Open Source Project + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE + * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, + * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, + * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS + * OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED + * AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, + * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT + * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +// -std=gnu++XX automatically defines _GNU_SOURCE, which then means that +// gives us the GNU variant, which is not what we're defining here. +#undef _GNU_SOURCE + +#include + +#include +#include + +#include "private/ErrnoRestorer.h" + +#include +#include + +// The arraysize(arr) macro returns the # of elements in an array arr. +// The expression is a compile-time constant, and therefore can be +// used in defining new arrays, for example. If you use arraysize on +// a pointer by mistake, you will get a compile-time error. +// +// One caveat is that arraysize() doesn't accept any array of an +// anonymous type or a type defined inside a function. +// +// This template function declaration is used in defining arraysize. +// Note that the function doesn't need an implementation, as we only +// use its type. +template +char (&ArraySizeHelper(T (&array)[N]))[N]; // NOLINT(readability/casting) + +#define arraysize(array) (sizeof(ArraySizeHelper(array))) + +static const char* __sys_error_descriptions[] = { +#define __BIONIC_ERRDEF(error_number, error_description) [error_number] = error_description, +#include "private/bionic_errdefs.h" +}; + +static inline const char* __strerror_lookup(int error_number) { + if (error_number < 0 || error_number >= static_cast(arraysize(__sys_error_descriptions))) { + return nullptr; + } + return __sys_error_descriptions[error_number]; +} + +int strerror_r(int error_number, char* buf, size_t buf_len) { + ErrnoRestorer errno_restorer; + size_t length; + + const char* error_name = __strerror_lookup(error_number); + if (error_name != nullptr) { + length = strlcpy(buf, error_name, buf_len); + } else { + length = snprintf(buf, buf_len, "Unknown error %d", error_number); + } + if (length >= buf_len) { + return ERANGE; + } + + return 0; +} + +char* strerror(int error_number) { + static char strerror_buf[NL_TEXTMAX]; + + // Just return the original constant in the easy cases. + char* result = const_cast(__strerror_lookup(error_number)); + if (result != nullptr) { + return result; + } + + result = strerror_buf; + strerror_r(error_number, result, sizeof(strerror_buf)); + return result; +} diff --git a/bionic/syscall-arm.S b/bionic/syscall-arm.S new file mode 100644 index 0000000..8b60383 --- /dev/null +++ b/bionic/syscall-arm.S @@ -0,0 +1,51 @@ +/* + * Copyright (C) 2008 The Android Open Source Project + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE + * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, + * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, + * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS + * OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED + * AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, + * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT + * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#include "private/bionic_asm.h" + +ENTRY(syscall) + mov ip, sp + stmfd sp!, {r4, r5, r6, r7} + .cfi_def_cfa_offset 16 + .cfi_rel_offset r4, 0 + .cfi_rel_offset r5, 4 + .cfi_rel_offset r6, 8 + .cfi_rel_offset r7, 12 + mov r7, r0 + mov r0, r1 + mov r1, r2 + mov r2, r3 + ldmfd ip, {r3, r4, r5, r6} + swi #0 + ldmfd sp!, {r4, r5, r6, r7} + .cfi_def_cfa_offset 0 + cmn r0, #(MAX_ERRNO + 1) + bxls lr + neg r0, r0 + b __set_errno_internal +END(syscall) diff --git a/bionic/syscall-arm64.S b/bionic/syscall-arm64.S new file mode 100644 index 0000000..acd2b42 --- /dev/null +++ b/bionic/syscall-arm64.S @@ -0,0 +1,51 @@ +/* + * Copyright (C) 2013 The Android Open Source Project + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE + * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, + * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, + * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS + * OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED + * AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, + * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT + * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#include "private/bionic_asm.h" + +ENTRY(syscall) + /* Move syscall No. from x0 to x8 */ + mov x8, x0 + /* Move syscall parameters from x1 thru x6 to x0 thru x5 */ + mov x0, x1 + mov x1, x2 + mov x2, x3 + mov x3, x4 + mov x4, x5 + mov x5, x6 + svc #0 + + /* check if syscall returned successfully */ + cmn x0, #(MAX_ERRNO + 1) + cneg x0, x0, hi + b.hi __set_errno_internal + + ret +END(syscall) + +NOTE_GNU_PROPERTY() diff --git a/bionic/syscall-x86.S b/bionic/syscall-x86.S new file mode 100644 index 0000000..c44ce36 --- /dev/null +++ b/bionic/syscall-x86.S @@ -0,0 +1,66 @@ +/* + * Generic syscall call. + * Upon entry: + * %eax: system call number - caller save + * %ebx: arg0 to system call - callee save + * %ecx: arg1 - caller save + * %edx: arg2 - caller save + * %esi: arg3 - callee save + * %edi: arg4 - callee save + * %ebp: arg5 - callee save + */ + +#include "private/bionic_asm.h" + +ENTRY(syscall) + # Push the callee save registers. + push %ebx + .cfi_adjust_cfa_offset 4 + .cfi_rel_offset ebx, 0 + push %esi + .cfi_adjust_cfa_offset 4 + .cfi_rel_offset esi, 0 + push %edi + .cfi_adjust_cfa_offset 4 + .cfi_rel_offset edi, 0 + push %ebp + .cfi_adjust_cfa_offset 4 + .cfi_rel_offset ebp, 0 + + # Load all the arguments from the calling frame. + # (Not all will be valid, depending on the syscall.) + mov 20(%esp),%eax + mov 24(%esp),%ebx + mov 28(%esp),%ecx + mov 32(%esp),%edx + mov 36(%esp),%esi + mov 40(%esp),%edi + mov 44(%esp),%ebp + + # Make the system call. + int $0x80 + + # Error? + cmpl $-MAX_ERRNO, %eax + jb 1f + # Yes, so set errno. + negl %eax + pushl %eax + call __set_errno_internal + addl $4, %esp +1: + # Restore the callee save registers. + pop %ebp + .cfi_adjust_cfa_offset -4 + .cfi_restore ebp + pop %edi + .cfi_adjust_cfa_offset -4 + .cfi_restore edi + pop %esi + .cfi_adjust_cfa_offset -4 + .cfi_restore esi + pop %ebx + .cfi_adjust_cfa_offset -4 + .cfi_restore ebx + ret +END(syscall) diff --git a/bionic/syscall-x86_64.S b/bionic/syscall-x86_64.S new file mode 100644 index 0000000..7a6f410 --- /dev/null +++ b/bionic/syscall-x86_64.S @@ -0,0 +1,63 @@ +/* + * Copyright (C) 2013 The Android Open Source Project + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE + * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, + * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, + * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS + * OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED + * AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, + * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT + * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +/* + * Generic syscall call. + * Upon entry: + * %rax: system call number + * %rdi: arg0 to system call + * %rsi: arg1 + * %rdx: arg2 + * %rcx: arg3 - syscall expects it at %r10 + * %r8: arg4 + * %r9: arg5 + */ + +#include "private/bionic_asm.h" + +ENTRY(syscall) + # All arguments are passed via registers. + # (Not all will be valid, depending on the syscall.) + mov %edi, %eax + mov %rsi, %rdi + mov %rdx, %rsi + mov %rcx, %rdx + mov %r8, %r10 + mov %r9, %r8 + mov 8(%rsp), %r9 + + # Make the system call. + syscall + cmpq $-MAX_ERRNO, %rax + jb 1f + negl %eax + movl %eax, %edi + call __set_errno_internal +1: + ret +END(syscall) diff --git a/dlmalloc/malloc.c b/dlmalloc/malloc.c new file mode 100644 index 0000000..b1495f4 --- /dev/null +++ b/dlmalloc/malloc.c @@ -0,0 +1,6291 @@ +/* +Copyright 2023 Doug Lea + +Permission is hereby granted, free of charge, to any person obtaining +a copy of this software and associated documentation files (the +"Software"), to deal in the Software without restriction, including +without limitation the rights to use, copy, modify, merge, publish, +distribute, sublicense, and/or sell copies of the Software, and to +permit persons to whom the Software is furnished to do so. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND +NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE +LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION +OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION +WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + +* Version 2.8.6 Wed Aug 29 06:57:58 2012 Doug Lea + Re-licensed 25 Sep 2023 with MIT-0 replacing obsolete CC0 + See https://opensource.org/license/mit-0/ + +* Quickstart + + This library is all in one file to simplify the most common usage: + ftp it, compile it (-O3), and link it into another program. All of + the compile-time options default to reasonable values for use on + most platforms. You might later want to step through various + compile-time and dynamic tuning options. + + For convenience, an include file for code using this malloc is at: + ftp://gee.cs.oswego.edu/pub/misc/malloc-2.8.6.h + You don't really need this .h file unless you call functions not + defined in your system include files. The .h file contains only the + excerpts from this file needed for using this malloc on ANSI C/C++ + systems, so long as you haven't changed compile-time options about + naming and tuning parameters. If you do, then you can create your + own malloc.h that does include all settings by cutting at the point + indicated below. Note that you may already by default be using a C + library containing a malloc that is based on some version of this + malloc (for example in linux). You might still want to use the one + in this file to customize settings or to avoid overheads associated + with library versions. + +* Vital statistics: + + Supported pointer/size_t representation: 4 or 8 bytes + size_t MUST be an unsigned type of the same width as + pointers. (If you are using an ancient system that declares + size_t as a signed type, or need it to be a different width + than pointers, you can use a previous release of this malloc + (e.g. 2.7.2) supporting these.) + + Alignment: 8 bytes (minimum) + This suffices for nearly all current machines and C compilers. + However, you can define MALLOC_ALIGNMENT to be wider than this + if necessary (up to 128bytes), at the expense of using more space. + + Minimum overhead per allocated chunk: 4 or 8 bytes (if 4byte sizes) + 8 or 16 bytes (if 8byte sizes) + Each malloced chunk has a hidden word of overhead holding size + and status information, and additional cross-check word + if FOOTERS is defined. + + Minimum allocated size: 4-byte ptrs: 16 bytes (including overhead) + 8-byte ptrs: 32 bytes (including overhead) + + Even a request for zero bytes (i.e., malloc(0)) returns a + pointer to something of the minimum allocatable size. + The maximum overhead wastage (i.e., number of extra bytes + allocated than were requested in malloc) is less than or equal + to the minimum size, except for requests >= mmap_threshold that + are serviced via mmap(), where the worst case wastage is about + 32 bytes plus the remainder from a system page (the minimal + mmap unit); typically 4096 or 8192 bytes. + + Security: static-safe; optionally more or less + The "security" of malloc refers to the ability of malicious + code to accentuate the effects of errors (for example, freeing + space that is not currently malloc'ed or overwriting past the + ends of chunks) in code that calls malloc. This malloc + guarantees not to modify any memory locations below the base of + heap, i.e., static variables, even in the presence of usage + errors. The routines additionally detect most improper frees + and reallocs. All this holds as long as the static bookkeeping + for malloc itself is not corrupted by some other means. This + is only one aspect of security -- these checks do not, and + cannot, detect all possible programming errors. + + If FOOTERS is defined nonzero, then each allocated chunk + carries an additional check word to verify that it was malloced + from its space. These check words are the same within each + execution of a program using malloc, but differ across + executions, so externally crafted fake chunks cannot be + freed. This improves security by rejecting frees/reallocs that + could corrupt heap memory, in addition to the checks preventing + writes to statics that are always on. This may further improve + security at the expense of time and space overhead. (Note that + FOOTERS may also be worth using with MSPACES.) + + By default detected errors cause the program to abort (calling + "abort()"). You can override this to instead proceed past + errors by defining PROCEED_ON_ERROR. In this case, a bad free + has no effect, and a malloc that encounters a bad address + caused by user overwrites will ignore the bad address by + dropping pointers and indices to all known memory. This may + be appropriate for programs that should continue if at all + possible in the face of programming errors, although they may + run out of memory because dropped memory is never reclaimed. + + If you don't like either of these options, you can define + CORRUPTION_ERROR_ACTION and USAGE_ERROR_ACTION to do anything + else. And if if you are sure that your program using malloc has + no errors or vulnerabilities, you can define INSECURE to 1, + which might (or might not) provide a small performance improvement. + + It is also possible to limit the maximum total allocatable + space, using malloc_set_footprint_limit. This is not + designed as a security feature in itself (calls to set limits + are not screened or privileged), but may be useful as one + aspect of a secure implementation. + + Thread-safety: NOT thread-safe unless USE_LOCKS defined non-zero + When USE_LOCKS is defined, each public call to malloc, free, + etc is surrounded with a lock. By default, this uses a plain + pthread mutex, win32 critical section, or a spin-lock if if + available for the platform and not disabled by setting + USE_SPIN_LOCKS=0. However, if USE_RECURSIVE_LOCKS is defined, + recursive versions are used instead (which are not required for + base functionality but may be needed in layered extensions). + Using a global lock is not especially fast, and can be a major + bottleneck. It is designed only to provide minimal protection + in concurrent environments, and to provide a basis for + extensions. If you are using malloc in a concurrent program, + consider instead using nedmalloc + (http://www.nedprod.com/programs/portable/nedmalloc/) or + ptmalloc (See http://www.malloc.de), which are derived from + versions of this malloc. + + System requirements: Any combination of MORECORE and/or MMAP/MUNMAP + This malloc can use unix sbrk or any emulation (invoked using + the CALL_MORECORE macro) and/or mmap/munmap or any emulation + (invoked using CALL_MMAP/CALL_MUNMAP) to get and release system + memory. On most unix systems, it tends to work best if both + MORECORE and MMAP are enabled. On Win32, it uses emulations + based on VirtualAlloc. It also uses common C library functions + like memset. + + Compliance: I believe it is compliant with the Single Unix Specification + (See http://www.unix.org). Also SVID/XPG, ANSI C, and probably + others as well. + +* Overview of algorithms + + This is not the fastest, most space-conserving, most portable, or + most tunable malloc ever written. However it is among the fastest + while also being among the most space-conserving, portable and + tunable. Consistent balance across these factors results in a good + general-purpose allocator for malloc-intensive programs. + + In most ways, this malloc is a best-fit allocator. Generally, it + chooses the best-fitting existing chunk for a request, with ties + broken in approximately least-recently-used order. (This strategy + normally maintains low fragmentation.) However, for requests less + than 256bytes, it deviates from best-fit when there is not an + exactly fitting available chunk by preferring to use space adjacent + to that used for the previous small request, as well as by breaking + ties in approximately most-recently-used order. (These enhance + locality of series of small allocations.) And for very large requests + (>= 256Kb by default), it relies on system memory mapping + facilities, if supported. (This helps avoid carrying around and + possibly fragmenting memory used only for large chunks.) + + All operations (except malloc_stats and mallinfo) have execution + times that are bounded by a constant factor of the number of bits in + a size_t, not counting any clearing in calloc or copying in realloc, + or actions surrounding MORECORE and MMAP that have times + proportional to the number of non-contiguous regions returned by + system allocation routines, which is often just 1. In real-time + applications, you can optionally suppress segment traversals using + NO_SEGMENT_TRAVERSAL, which assures bounded execution even when + system allocators return non-contiguous spaces, at the typical + expense of carrying around more memory and increased fragmentation. + + The implementation is not very modular and seriously overuses + macros. Perhaps someday all C compilers will do as good a job + inlining modular code as can now be done by brute-force expansion, + but now, enough of them seem not to. + + Some compilers issue a lot of warnings about code that is + dead/unreachable only on some platforms, and also about intentional + uses of negation on unsigned types. All known cases of each can be + ignored. + + For a longer but out of date high-level description, see + http://gee.cs.oswego.edu/dl/html/malloc.html + +* MSPACES + If MSPACES is defined, then in addition to malloc, free, etc., + this file also defines mspace_malloc, mspace_free, etc. These + are versions of malloc routines that take an "mspace" argument + obtained using create_mspace, to control all internal bookkeeping. + If ONLY_MSPACES is defined, only these versions are compiled. + So if you would like to use this allocator for only some allocations, + and your system malloc for others, you can compile with + ONLY_MSPACES and then do something like... + static mspace mymspace = create_mspace(0,0); // for example + #define mymalloc(bytes) mspace_malloc(mymspace, bytes) + + (Note: If you only need one instance of an mspace, you can instead + use "USE_DL_PREFIX" to relabel the global malloc.) + + You can similarly create thread-local allocators by storing + mspaces as thread-locals. For example: + static __thread mspace tlms = 0; + void* tlmalloc(size_t bytes) { + if (tlms == 0) tlms = create_mspace(0, 0); + return mspace_malloc(tlms, bytes); + } + void tlfree(void* mem) { mspace_free(tlms, mem); } + + Unless FOOTERS is defined, each mspace is completely independent. + You cannot allocate from one and free to another (although + conformance is only weakly checked, so usage errors are not always + caught). If FOOTERS is defined, then each chunk carries around a tag + indicating its originating mspace, and frees are directed to their + originating spaces. Normally, this requires use of locks. + + ------------------------- Compile-time options --------------------------- + +Be careful in setting #define values for numerical constants of type +size_t. On some systems, literal values are not automatically extended +to size_t precision unless they are explicitly casted. You can also +use the symbolic values MAX_SIZE_T, SIZE_T_ONE, etc below. + +WIN32 default: defined if _WIN32 defined + Defining WIN32 sets up defaults for MS environment and compilers. + Otherwise defaults are for unix. Beware that there seem to be some + cases where this malloc might not be a pure drop-in replacement for + Win32 malloc: Random-looking failures from Win32 GDI API's (eg; + SetDIBits()) may be due to bugs in some video driver implementations + when pixel buffers are malloc()ed, and the region spans more than + one VirtualAlloc()ed region. Because dlmalloc uses a small (64Kb) + default granularity, pixel buffers may straddle virtual allocation + regions more often than when using the Microsoft allocator. You can + avoid this by using VirtualAlloc() and VirtualFree() for all pixel + buffers rather than using malloc(). If this is not possible, + recompile this malloc with a larger DEFAULT_GRANULARITY. Note: + in cases where MSC and gcc (cygwin) are known to differ on WIN32, + conditions use _MSC_VER to distinguish them. + +DLMALLOC_EXPORT default: extern + Defines how public APIs are declared. If you want to export via a + Windows DLL, you might define this as + #define DLMALLOC_EXPORT extern __declspec(dllexport) + If you want a POSIX ELF shared object, you might use + #define DLMALLOC_EXPORT extern __attribute__((visibility("default"))) + +MALLOC_ALIGNMENT default: (size_t)(2 * sizeof(void *)) + Controls the minimum alignment for malloc'ed chunks. It must be a + power of two and at least 8, even on machines for which smaller + alignments would suffice. It may be defined as larger than this + though. Note however that code and data structures are optimized for + the case of 8-byte alignment. + +MSPACES default: 0 (false) + If true, compile in support for independent allocation spaces. + This is only supported if HAVE_MMAP is true. + +ONLY_MSPACES default: 0 (false) + If true, only compile in mspace versions, not regular versions. + +USE_LOCKS default: 0 (false) + Causes each call to each public routine to be surrounded with + pthread or WIN32 mutex lock/unlock. (If set true, this can be + overridden on a per-mspace basis for mspace versions.) If set to a + non-zero value other than 1, locks are used, but their + implementation is left out, so lock functions must be supplied manually, + as described below. + +USE_SPIN_LOCKS default: 1 iff USE_LOCKS and spin locks available + If true, uses custom spin locks for locking. This is currently + supported only gcc >= 4.1, older gccs on x86 platforms, and recent + MS compilers. Otherwise, posix locks or win32 critical sections are + used. + +USE_RECURSIVE_LOCKS default: not defined + If defined nonzero, uses recursive (aka reentrant) locks, otherwise + uses plain mutexes. This is not required for malloc proper, but may + be needed for layered allocators such as nedmalloc. + +LOCK_AT_FORK default: not defined + If defined nonzero, performs pthread_atfork upon initialization + to initialize child lock while holding parent lock. The implementation + assumes that pthread locks (not custom locks) are being used. In other + cases, you may need to customize the implementation. + +FOOTERS default: 0 + If true, provide extra checking and dispatching by placing + information in the footers of allocated chunks. This adds + space and time overhead. + +INSECURE default: 0 + If true, omit checks for usage errors and heap space overwrites. + +USE_DL_PREFIX default: NOT defined + Causes compiler to prefix all public routines with the string 'dl'. + This can be useful when you only want to use this malloc in one part + of a program, using your regular system malloc elsewhere. + +MALLOC_INSPECT_ALL default: NOT defined + If defined, compiles malloc_inspect_all and mspace_inspect_all, that + perform traversal of all heap space. Unless access to these + functions is otherwise restricted, you probably do not want to + include them in secure implementations. + +ABORT default: defined as abort() + Defines how to abort on failed checks. On most systems, a failed + check cannot die with an "assert" or even print an informative + message, because the underlying print routines in turn call malloc, + which will fail again. Generally, the best policy is to simply call + abort(). It's not very useful to do more than this because many + errors due to overwriting will show up as address faults (null, odd + addresses etc) rather than malloc-triggered checks, so will also + abort. Also, most compilers know that abort() does not return, so + can better optimize code conditionally calling it. + +PROCEED_ON_ERROR default: defined as 0 (false) + Controls whether detected bad addresses cause them to bypassed + rather than aborting. If set, detected bad arguments to free and + realloc are ignored. And all bookkeeping information is zeroed out + upon a detected overwrite of freed heap space, thus losing the + ability to ever return it from malloc again, but enabling the + application to proceed. If PROCEED_ON_ERROR is defined, the + static variable malloc_corruption_error_count is compiled in + and can be examined to see if errors have occurred. This option + generates slower code than the default abort policy. + +DEBUG default: NOT defined + The DEBUG setting is mainly intended for people trying to modify + this code or diagnose problems when porting to new platforms. + However, it may also be able to better isolate user errors than just + using runtime checks. The assertions in the check routines spell + out in more detail the assumptions and invariants underlying the + algorithms. The checking is fairly extensive, and will slow down + execution noticeably. Calling malloc_stats or mallinfo with DEBUG + set will attempt to check every non-mmapped allocated and free chunk + in the course of computing the summaries. + +ABORT_ON_ASSERT_FAILURE default: defined as 1 (true) + Debugging assertion failures can be nearly impossible if your + version of the assert macro causes malloc to be called, which will + lead to a cascade of further failures, blowing the runtime stack. + ABORT_ON_ASSERT_FAILURE cause assertions failures to call abort(), + which will usually make debugging easier. + +MALLOC_FAILURE_ACTION default: sets errno to ENOMEM, or no-op on win32 + The action to take before "return 0" when malloc fails to be able to + return memory because there is none available. + +HAVE_MORECORE default: 1 (true) unless win32 or ONLY_MSPACES + True if this system supports sbrk or an emulation of it. + +MORECORE default: sbrk + The name of the sbrk-style system routine to call to obtain more + memory. See below for guidance on writing custom MORECORE + functions. The type of the argument to sbrk/MORECORE varies across + systems. It cannot be size_t, because it supports negative + arguments, so it is normally the signed type of the same width as + size_t (sometimes declared as "intptr_t"). It doesn't much matter + though. Internally, we only call it with arguments less than half + the max value of a size_t, which should work across all reasonable + possibilities, although sometimes generating compiler warnings. + +MORECORE_CONTIGUOUS default: 1 (true) if HAVE_MORECORE + If true, take advantage of fact that consecutive calls to MORECORE + with positive arguments always return contiguous increasing + addresses. This is true of unix sbrk. It does not hurt too much to + set it true anyway, since malloc copes with non-contiguities. + Setting it false when definitely non-contiguous saves time + and possibly wasted space it would take to discover this though. + +MORECORE_CANNOT_TRIM default: NOT defined + True if MORECORE cannot release space back to the system when given + negative arguments. This is generally necessary only if you are + using a hand-crafted MORECORE function that cannot handle negative + arguments. + +NO_SEGMENT_TRAVERSAL default: 0 + If non-zero, suppresses traversals of memory segments + returned by either MORECORE or CALL_MMAP. This disables + merging of segments that are contiguous, and selectively + releasing them to the OS if unused, but bounds execution times. + +HAVE_MMAP default: 1 (true) + True if this system supports mmap or an emulation of it. If so, and + HAVE_MORECORE is not true, MMAP is used for all system + allocation. If set and HAVE_MORECORE is true as well, MMAP is + primarily used to directly allocate very large blocks. It is also + used as a backup strategy in cases where MORECORE fails to provide + space from system. Note: A single call to MUNMAP is assumed to be + able to unmap memory that may have be allocated using multiple calls + to MMAP, so long as they are adjacent. + +HAVE_MREMAP default: 1 on linux, else 0 + If true realloc() uses mremap() to re-allocate large blocks and + extend or shrink allocation spaces. + +MMAP_CLEARS default: 1 except on WINCE. + True if mmap clears memory so calloc doesn't need to. This is true + for standard unix mmap using /dev/zero and on WIN32 except for WINCE. + +USE_BUILTIN_FFS default: 0 (i.e., not used) + Causes malloc to use the builtin ffs() function to compute indices. + Some compilers may recognize and intrinsify ffs to be faster than the + supplied C version. Also, the case of x86 using gcc is special-cased + to an asm instruction, so is already as fast as it can be, and so + this setting has no effect. Similarly for Win32 under recent MS compilers. + (On most x86s, the asm version is only slightly faster than the C version.) + +malloc_getpagesize default: derive from system includes, or 4096. + The system page size. To the extent possible, this malloc manages + memory from the system in page-size units. This may be (and + usually is) a function rather than a constant. This is ignored + if WIN32, where page size is determined using getSystemInfo during + initialization. + +USE_DEV_RANDOM default: 0 (i.e., not used) + Causes malloc to use /dev/random to initialize secure magic seed for + stamping footers. Otherwise, the current time is used. + +NO_MALLINFO default: 0 + If defined, don't compile "mallinfo". This can be a simple way + of dealing with mismatches between system declarations and + those in this file. + +MALLINFO_FIELD_TYPE default: size_t + The type of the fields in the mallinfo struct. This was originally + defined as "int" in SVID etc, but is more usefully defined as + size_t. The value is used only if HAVE_USR_INCLUDE_MALLOC_H is not set + +NO_MALLOC_STATS default: 0 + If defined, don't compile "malloc_stats". This avoids calls to + fprintf and bringing in stdio dependencies you might not want. + +REALLOC_ZERO_BYTES_FREES default: not defined + This should be set if a call to realloc with zero bytes should + be the same as a call to free. Some people think it should. Otherwise, + since this malloc returns a unique pointer for malloc(0), so does + realloc(p, 0). + +LACKS_UNISTD_H, LACKS_FCNTL_H, LACKS_SYS_PARAM_H, LACKS_SYS_MMAN_H +LACKS_STRINGS_H, LACKS_STRING_H, LACKS_SYS_TYPES_H, LACKS_ERRNO_H +LACKS_STDLIB_H LACKS_SCHED_H LACKS_TIME_H default: NOT defined unless on WIN32 + Define these if your system does not have these header files. + You might need to manually insert some of the declarations they provide. + +DEFAULT_GRANULARITY default: page size if MORECORE_CONTIGUOUS, + system_info.dwAllocationGranularity in WIN32, + otherwise 64K. + Also settable using mallopt(M_GRANULARITY, x) + The unit for allocating and deallocating memory from the system. On + most systems with contiguous MORECORE, there is no reason to + make this more than a page. However, systems with MMAP tend to + either require or encourage larger granularities. You can increase + this value to prevent system allocation functions to be called so + often, especially if they are slow. The value must be at least one + page and must be a power of two. Setting to 0 causes initialization + to either page size or win32 region size. (Note: In previous + versions of malloc, the equivalent of this option was called + "TOP_PAD") + +DEFAULT_TRIM_THRESHOLD default: 2MB + Also settable using mallopt(M_TRIM_THRESHOLD, x) + The maximum amount of unused top-most memory to keep before + releasing via malloc_trim in free(). Automatic trimming is mainly + useful in long-lived programs using contiguous MORECORE. Because + trimming via sbrk can be slow on some systems, and can sometimes be + wasteful (in cases where programs immediately afterward allocate + more large chunks) the value should be high enough so that your + overall system performance would improve by releasing this much + memory. As a rough guide, you might set to a value close to the + average size of a process (program) running on your system. + Releasing this much memory would allow such a process to run in + memory. Generally, it is worth tuning trim thresholds when a + program undergoes phases where several large chunks are allocated + and released in ways that can reuse each other's storage, perhaps + mixed with phases where there are no such chunks at all. The trim + value must be greater than page size to have any useful effect. To + disable trimming completely, you can set to MAX_SIZE_T. Note that the trick + some people use of mallocing a huge space and then freeing it at + program startup, in an attempt to reserve system memory, doesn't + have the intended effect under automatic trimming, since that memory + will immediately be returned to the system. + +DEFAULT_MMAP_THRESHOLD default: 256K + Also settable using mallopt(M_MMAP_THRESHOLD, x) + The request size threshold for using MMAP to directly service a + request. Requests of at least this size that cannot be allocated + using already-existing space will be serviced via mmap. (If enough + normal freed space already exists it is used instead.) Using mmap + segregates relatively large chunks of memory so that they can be + individually obtained and released from the host system. A request + serviced through mmap is never reused by any other request (at least + not directly; the system may just so happen to remap successive + requests to the same locations). Segregating space in this way has + the benefits that: Mmapped space can always be individually released + back to the system, which helps keep the system level memory demands + of a long-lived program low. Also, mapped memory doesn't become + `locked' between other chunks, as can happen with normally allocated + chunks, which means that even trimming via malloc_trim would not + release them. However, it has the disadvantage that the space + cannot be reclaimed, consolidated, and then used to service later + requests, as happens with normal chunks. The advantages of mmap + nearly always outweigh disadvantages for "large" chunks, but the + value of "large" may vary across systems. The default is an + empirically derived value that works well in most systems. You can + disable mmap by setting to MAX_SIZE_T. + +MAX_RELEASE_CHECK_RATE default: 4095 unless not HAVE_MMAP + The number of consolidated frees between checks to release + unused segments when freeing. When using non-contiguous segments, + especially with multiple mspaces, checking only for topmost space + doesn't always suffice to trigger trimming. To compensate for this, + free() will, with a period of MAX_RELEASE_CHECK_RATE (or the + current number of segments, if greater) try to release unused + segments to the OS when freeing chunks that result in + consolidation. The best value for this parameter is a compromise + between slowing down frees with relatively costly checks that + rarely trigger versus holding on to unused memory. To effectively + disable, set to MAX_SIZE_T. This may lead to a very slight speed + improvement at the expense of carrying around more memory. +*/ + +/* Version identifier to allow people to support multiple versions */ +#ifndef DLMALLOC_VERSION +#define DLMALLOC_VERSION 20806 +#endif /* DLMALLOC_VERSION */ + +#ifndef DLMALLOC_EXPORT +#define DLMALLOC_EXPORT extern +#endif + +#ifndef WIN32 +#ifdef _WIN32 +#define WIN32 1 +#endif /* _WIN32 */ +#ifdef _WIN32_WCE +#define LACKS_FCNTL_H +#define WIN32 1 +#endif /* _WIN32_WCE */ +#endif /* WIN32 */ +#ifdef WIN32 +#define WIN32_LEAN_AND_MEAN +#include +#include +#define HAVE_MMAP 1 +#define HAVE_MORECORE 0 +#define LACKS_UNISTD_H +#define LACKS_SYS_PARAM_H +#define LACKS_SYS_MMAN_H +#define LACKS_STRING_H +#define LACKS_STRINGS_H +#define LACKS_SYS_TYPES_H +#define LACKS_ERRNO_H +#define LACKS_SCHED_H +#ifndef MALLOC_FAILURE_ACTION +#define MALLOC_FAILURE_ACTION +#endif /* MALLOC_FAILURE_ACTION */ +#ifndef MMAP_CLEARS +#ifdef _WIN32_WCE /* WINCE reportedly does not clear */ +#define MMAP_CLEARS 0 +#else +#define MMAP_CLEARS 1 +#endif /* _WIN32_WCE */ +#endif /*MMAP_CLEARS */ +#endif /* WIN32 */ + +#if defined(DARWIN) || defined(_DARWIN) +/* Mac OSX docs advise not to use sbrk; it seems better to use mmap */ +#ifndef HAVE_MORECORE +#define HAVE_MORECORE 0 +#define HAVE_MMAP 1 +/* OSX allocators provide 16 byte alignment */ +#ifndef MALLOC_ALIGNMENT +#define MALLOC_ALIGNMENT ((size_t)16U) +#endif +#endif /* HAVE_MORECORE */ +#endif /* DARWIN */ + +#ifndef LACKS_SYS_TYPES_H +#include /* For size_t */ +#endif /* LACKS_SYS_TYPES_H */ + +/* The maximum possible size_t value has all bits set */ +#define MAX_SIZE_T (~(size_t)0) + +#ifndef USE_LOCKS /* ensure true if spin or recursive locks set */ +#define USE_LOCKS ((defined(USE_SPIN_LOCKS) && USE_SPIN_LOCKS != 0) || \ + (defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0)) +#endif /* USE_LOCKS */ + +#if USE_LOCKS /* Spin locks for gcc >= 4.1, older gcc on x86, MSC >= 1310 */ +#if ((defined(__GNUC__) && \ + ((__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 1)) || \ + defined(__i386__) || defined(__x86_64__))) || \ + (defined(_MSC_VER) && _MSC_VER>=1310)) +#ifndef USE_SPIN_LOCKS +#define USE_SPIN_LOCKS 1 +#endif /* USE_SPIN_LOCKS */ +#elif USE_SPIN_LOCKS +#error "USE_SPIN_LOCKS defined without implementation" +#endif /* ... locks available... */ +#elif !defined(USE_SPIN_LOCKS) +#define USE_SPIN_LOCKS 0 +#endif /* USE_LOCKS */ + +#ifndef ONLY_MSPACES +#define ONLY_MSPACES 0 +#endif /* ONLY_MSPACES */ +#ifndef MSPACES +#if ONLY_MSPACES +#define MSPACES 1 +#else /* ONLY_MSPACES */ +#define MSPACES 0 +#endif /* ONLY_MSPACES */ +#endif /* MSPACES */ +#ifndef MALLOC_ALIGNMENT +#define MALLOC_ALIGNMENT ((size_t)(2 * sizeof(void *))) +#endif /* MALLOC_ALIGNMENT */ +#ifndef FOOTERS +#define FOOTERS 0 +#endif /* FOOTERS */ +#ifndef ABORT +#define ABORT abort() +#endif /* ABORT */ +#ifndef ABORT_ON_ASSERT_FAILURE +#define ABORT_ON_ASSERT_FAILURE 1 +#endif /* ABORT_ON_ASSERT_FAILURE */ +#ifndef PROCEED_ON_ERROR +#define PROCEED_ON_ERROR 0 +#endif /* PROCEED_ON_ERROR */ + +#ifndef INSECURE +#define INSECURE 0 +#endif /* INSECURE */ +#ifndef MALLOC_INSPECT_ALL +#define MALLOC_INSPECT_ALL 0 +#endif /* MALLOC_INSPECT_ALL */ +#ifndef HAVE_MMAP +#define HAVE_MMAP 1 +#endif /* HAVE_MMAP */ +#ifndef MMAP_CLEARS +#define MMAP_CLEARS 1 +#endif /* MMAP_CLEARS */ +#ifndef HAVE_MREMAP +#ifdef linux +#define HAVE_MREMAP 1 +#define _GNU_SOURCE /* Turns on mremap() definition */ +#else /* linux */ +#define HAVE_MREMAP 0 +#endif /* linux */ +#endif /* HAVE_MREMAP */ +#ifndef MALLOC_FAILURE_ACTION +#define MALLOC_FAILURE_ACTION errno = ENOMEM; +#endif /* MALLOC_FAILURE_ACTION */ +#ifndef HAVE_MORECORE +#if ONLY_MSPACES +#define HAVE_MORECORE 0 +#else /* ONLY_MSPACES */ +#define HAVE_MORECORE 1 +#endif /* ONLY_MSPACES */ +#endif /* HAVE_MORECORE */ +#if !HAVE_MORECORE +#define MORECORE_CONTIGUOUS 0 +#else /* !HAVE_MORECORE */ +#define MORECORE_DEFAULT sbrk +#ifndef MORECORE_CONTIGUOUS +#define MORECORE_CONTIGUOUS 1 +#endif /* MORECORE_CONTIGUOUS */ +#endif /* HAVE_MORECORE */ +#ifndef DEFAULT_GRANULARITY +#if (MORECORE_CONTIGUOUS || defined(WIN32)) +#define DEFAULT_GRANULARITY (0) /* 0 means to compute in init_mparams */ +#else /* MORECORE_CONTIGUOUS */ +#define DEFAULT_GRANULARITY ((size_t)64U * (size_t)1024U) +#endif /* MORECORE_CONTIGUOUS */ +#endif /* DEFAULT_GRANULARITY */ +#ifndef DEFAULT_TRIM_THRESHOLD +#ifndef MORECORE_CANNOT_TRIM +#define DEFAULT_TRIM_THRESHOLD ((size_t)2U * (size_t)1024U * (size_t)1024U) +#else /* MORECORE_CANNOT_TRIM */ +#define DEFAULT_TRIM_THRESHOLD MAX_SIZE_T +#endif /* MORECORE_CANNOT_TRIM */ +#endif /* DEFAULT_TRIM_THRESHOLD */ +#ifndef DEFAULT_MMAP_THRESHOLD +#if HAVE_MMAP +#define DEFAULT_MMAP_THRESHOLD ((size_t)256U * (size_t)1024U) +#else /* HAVE_MMAP */ +#define DEFAULT_MMAP_THRESHOLD MAX_SIZE_T +#endif /* HAVE_MMAP */ +#endif /* DEFAULT_MMAP_THRESHOLD */ +#ifndef MAX_RELEASE_CHECK_RATE +#if HAVE_MMAP +#define MAX_RELEASE_CHECK_RATE 4095 +#else +#define MAX_RELEASE_CHECK_RATE MAX_SIZE_T +#endif /* HAVE_MMAP */ +#endif /* MAX_RELEASE_CHECK_RATE */ +#ifndef USE_BUILTIN_FFS +#define USE_BUILTIN_FFS 0 +#endif /* USE_BUILTIN_FFS */ +#ifndef USE_DEV_RANDOM +#define USE_DEV_RANDOM 0 +#endif /* USE_DEV_RANDOM */ +#ifndef NO_MALLINFO +#define NO_MALLINFO 0 +#endif /* NO_MALLINFO */ +#ifndef MALLINFO_FIELD_TYPE +#define MALLINFO_FIELD_TYPE size_t +#endif /* MALLINFO_FIELD_TYPE */ +#ifndef NO_MALLOC_STATS +#define NO_MALLOC_STATS 0 +#endif /* NO_MALLOC_STATS */ +#ifndef NO_SEGMENT_TRAVERSAL +#define NO_SEGMENT_TRAVERSAL 0 +#endif /* NO_SEGMENT_TRAVERSAL */ + +/* + mallopt tuning options. SVID/XPG defines four standard parameter + numbers for mallopt, normally defined in malloc.h. None of these + are used in this malloc, so setting them has no effect. But this + malloc does support the following options. +*/ + +#define M_TRIM_THRESHOLD (-1) +#define M_GRANULARITY (-2) +#define M_MMAP_THRESHOLD (-3) + +/* ------------------------ Mallinfo declarations ------------------------ */ + +#if !NO_MALLINFO +/* + This version of malloc supports the standard SVID/XPG mallinfo + routine that returns a struct containing usage properties and + statistics. It should work on any system that has a + /usr/include/malloc.h defining struct mallinfo. The main + declaration needed is the mallinfo struct that is returned (by-copy) + by mallinfo(). The malloinfo struct contains a bunch of fields that + are not even meaningful in this version of malloc. These fields are + are instead filled by mallinfo() with other numbers that might be of + interest. + + HAVE_USR_INCLUDE_MALLOC_H should be set if you have a + /usr/include/malloc.h file that includes a declaration of struct + mallinfo. If so, it is included; else a compliant version is + declared below. These must be precisely the same for mallinfo() to + work. The original SVID version of this struct, defined on most + systems with mallinfo, declares all fields as ints. But some others + define as unsigned long. If your system defines the fields using a + type of different width than listed here, you MUST #include your + system version and #define HAVE_USR_INCLUDE_MALLOC_H. +*/ + +/* #define HAVE_USR_INCLUDE_MALLOC_H */ + +#ifdef HAVE_USR_INCLUDE_MALLOC_H +#include "/usr/include/malloc.h" +#else /* HAVE_USR_INCLUDE_MALLOC_H */ +#ifndef STRUCT_MALLINFO_DECLARED +/* HP-UX (and others?) redefines mallinfo unless _STRUCT_MALLINFO is defined */ +#define _STRUCT_MALLINFO +#define STRUCT_MALLINFO_DECLARED 1 +struct mallinfo { + MALLINFO_FIELD_TYPE arena; /* non-mmapped space allocated from system */ + MALLINFO_FIELD_TYPE ordblks; /* number of free chunks */ + MALLINFO_FIELD_TYPE smblks; /* always 0 */ + MALLINFO_FIELD_TYPE hblks; /* always 0 */ + MALLINFO_FIELD_TYPE hblkhd; /* space in mmapped regions */ + MALLINFO_FIELD_TYPE usmblks; /* maximum total allocated space */ + MALLINFO_FIELD_TYPE fsmblks; /* always 0 */ + MALLINFO_FIELD_TYPE uordblks; /* total allocated space */ + MALLINFO_FIELD_TYPE fordblks; /* total free space */ + MALLINFO_FIELD_TYPE keepcost; /* releasable (via malloc_trim) space */ +}; +#endif /* STRUCT_MALLINFO_DECLARED */ +#endif /* HAVE_USR_INCLUDE_MALLOC_H */ +#endif /* NO_MALLINFO */ + +/* + Try to persuade compilers to inline. The most critical functions for + inlining are defined as macros, so these aren't used for them. +*/ + +#ifndef FORCEINLINE + #if defined(__GNUC__) +#define FORCEINLINE __inline __attribute__ ((always_inline)) + #elif defined(_MSC_VER) + #define FORCEINLINE __forceinline + #endif +#endif +#ifndef NOINLINE + #if defined(__GNUC__) + #define NOINLINE __attribute__ ((noinline)) + #elif defined(_MSC_VER) + #define NOINLINE __declspec(noinline) + #else + #define NOINLINE + #endif +#endif + +#ifdef __cplusplus +extern "C" { +#ifndef FORCEINLINE + #define FORCEINLINE inline +#endif +#endif /* __cplusplus */ +#ifndef FORCEINLINE + #define FORCEINLINE +#endif + +#if !ONLY_MSPACES + +/* ------------------- Declarations of public routines ------------------- */ + +#ifndef USE_DL_PREFIX +#define dlcalloc calloc +#define dlfree free +#define dlmalloc malloc +#define dlmemalign memalign +#define dlposix_memalign posix_memalign +#define dlrealloc realloc +#define dlrealloc_in_place realloc_in_place +#define dlvalloc valloc +#define dlpvalloc pvalloc +#define dlmallinfo mallinfo +#define dlmallopt mallopt +#define dlmalloc_trim malloc_trim +#define dlmalloc_stats malloc_stats +// #define dlmalloc_usable_size malloc_usable_size +#define dlmalloc_footprint malloc_footprint +#define dlmalloc_max_footprint malloc_max_footprint +#define dlmalloc_footprint_limit malloc_footprint_limit +#define dlmalloc_set_footprint_limit malloc_set_footprint_limit +#define dlmalloc_inspect_all malloc_inspect_all +#define dlindependent_calloc independent_calloc +#define dlindependent_comalloc independent_comalloc +#define dlbulk_free bulk_free +#endif /* USE_DL_PREFIX */ + +/* + malloc(size_t n) + Returns a pointer to a newly allocated chunk of at least n bytes, or + null if no space is available, in which case errno is set to ENOMEM + on ANSI C systems. + + If n is zero, malloc returns a minimum-sized chunk. (The minimum + size is 16 bytes on most 32bit systems, and 32 bytes on 64bit + systems.) Note that size_t is an unsigned type, so calls with + arguments that would be negative if signed are interpreted as + requests for huge amounts of space, which will often fail. The + maximum supported value of n differs across systems, but is in all + cases less than the maximum representable value of a size_t. +*/ +DLMALLOC_EXPORT void* dlmalloc(size_t); + +/* + free(void* p) + Releases the chunk of memory pointed to by p, that had been previously + allocated using malloc or a related routine such as realloc. + It has no effect if p is null. If p was not malloced or already + freed, free(p) will by default cause the current program to abort. +*/ +DLMALLOC_EXPORT void dlfree(void*); + +/* + calloc(size_t n_elements, size_t element_size); + Returns a pointer to n_elements * element_size bytes, with all locations + set to zero. +*/ +DLMALLOC_EXPORT void* dlcalloc(size_t, size_t); + +/* + realloc(void* p, size_t n) + Returns a pointer to a chunk of size n that contains the same data + as does chunk p up to the minimum of (n, p's size) bytes, or null + if no space is available. + + The returned pointer may or may not be the same as p. The algorithm + prefers extending p in most cases when possible, otherwise it + employs the equivalent of a malloc-copy-free sequence. + + If p is null, realloc is equivalent to malloc. + + If space is not available, realloc returns null, errno is set (if on + ANSI) and p is NOT freed. + + if n is for fewer bytes than already held by p, the newly unused + space is lopped off and freed if possible. realloc with a size + argument of zero (re)allocates a minimum-sized chunk. + + The old unix realloc convention of allowing the last-free'd chunk + to be used as an argument to realloc is not supported. +*/ +DLMALLOC_EXPORT void* dlrealloc(void*, size_t); + +/* + realloc_in_place(void* p, size_t n) + Resizes the space allocated for p to size n, only if this can be + done without moving p (i.e., only if there is adjacent space + available if n is greater than p's current allocated size, or n is + less than or equal to p's size). This may be used instead of plain + realloc if an alternative allocation strategy is needed upon failure + to expand space; for example, reallocation of a buffer that must be + memory-aligned or cleared. You can use realloc_in_place to trigger + these alternatives only when needed. + + Returns p if successful; otherwise null. +*/ +DLMALLOC_EXPORT void* dlrealloc_in_place(void*, size_t); + +/* + memalign(size_t alignment, size_t n); + Returns a pointer to a newly allocated chunk of n bytes, aligned + in accord with the alignment argument. + + The alignment argument should be a power of two. If the argument is + not a power of two, the nearest greater power is used. + 8-byte alignment is guaranteed by normal malloc calls, so don't + bother calling memalign with an argument of 8 or less. + + Overreliance on memalign is a sure way to fragment space. +*/ +DLMALLOC_EXPORT void* dlmemalign(size_t, size_t); + +/* + int posix_memalign(void** pp, size_t alignment, size_t n); + Allocates a chunk of n bytes, aligned in accord with the alignment + argument. Differs from memalign only in that it (1) assigns the + allocated memory to *pp rather than returning it, (2) fails and + returns EINVAL if the alignment is not a power of two (3) fails and + returns ENOMEM if memory cannot be allocated. +*/ +DLMALLOC_EXPORT int dlposix_memalign(void**, size_t, size_t); + +/* + valloc(size_t n); + Equivalent to memalign(pagesize, n), where pagesize is the page + size of the system. If the pagesize is unknown, 4096 is used. +*/ +DLMALLOC_EXPORT void* dlvalloc(size_t); + +/* + mallopt(int parameter_number, int parameter_value) + Sets tunable parameters The format is to provide a + (parameter-number, parameter-value) pair. mallopt then sets the + corresponding parameter to the argument value if it can (i.e., so + long as the value is meaningful), and returns 1 if successful else + 0. To workaround the fact that mallopt is specified to use int, + not size_t parameters, the value -1 is specially treated as the + maximum unsigned size_t value. + + SVID/XPG/ANSI defines four standard param numbers for mallopt, + normally defined in malloc.h. None of these are use in this malloc, + so setting them has no effect. But this malloc also supports other + options in mallopt. See below for details. Briefly, supported + parameters are as follows (listed defaults are for "typical" + configurations). + + Symbol param # default allowed param values + M_TRIM_THRESHOLD -1 2*1024*1024 any (-1 disables) + M_GRANULARITY -2 page size any power of 2 >= page size + M_MMAP_THRESHOLD -3 256*1024 any (or 0 if no MMAP support) +*/ +DLMALLOC_EXPORT int dlmallopt(int, int); + +/* + malloc_footprint(); + Returns the number of bytes obtained from the system. The total + number of bytes allocated by malloc, realloc etc., is less than this + value. Unlike mallinfo, this function returns only a precomputed + result, so can be called frequently to monitor memory consumption. + Even if locks are otherwise defined, this function does not use them, + so results might not be up to date. +*/ +DLMALLOC_EXPORT size_t dlmalloc_footprint(void); + +/* + malloc_max_footprint(); + Returns the maximum number of bytes obtained from the system. This + value will be greater than current footprint if deallocated space + has been reclaimed by the system. The peak number of bytes allocated + by malloc, realloc etc., is less than this value. Unlike mallinfo, + this function returns only a precomputed result, so can be called + frequently to monitor memory consumption. Even if locks are + otherwise defined, this function does not use them, so results might + not be up to date. +*/ +DLMALLOC_EXPORT size_t dlmalloc_max_footprint(void); + +/* + malloc_footprint_limit(); + Returns the number of bytes that the heap is allowed to obtain from + the system, returning the last value returned by + malloc_set_footprint_limit, or the maximum size_t value if + never set. The returned value reflects a permission. There is no + guarantee that this number of bytes can actually be obtained from + the system. +*/ +DLMALLOC_EXPORT size_t dlmalloc_footprint_limit(); + +/* + malloc_set_footprint_limit(); + Sets the maximum number of bytes to obtain from the system, causing + failure returns from malloc and related functions upon attempts to + exceed this value. The argument value may be subject to page + rounding to an enforceable limit; this actual value is returned. + Using an argument of the maximum possible size_t effectively + disables checks. If the argument is less than or equal to the + current malloc_footprint, then all future allocations that require + additional system memory will fail. However, invocation cannot + retroactively deallocate existing used memory. +*/ +DLMALLOC_EXPORT size_t dlmalloc_set_footprint_limit(size_t bytes); + +#if MALLOC_INSPECT_ALL +/* + malloc_inspect_all(void(*handler)(void *start, + void *end, + size_t used_bytes, + void* callback_arg), + void* arg); + Traverses the heap and calls the given handler for each managed + region, skipping all bytes that are (or may be) used for bookkeeping + purposes. Traversal does not include include chunks that have been + directly memory mapped. Each reported region begins at the start + address, and continues up to but not including the end address. The + first used_bytes of the region contain allocated data. If + used_bytes is zero, the region is unallocated. The handler is + invoked with the given callback argument. If locks are defined, they + are held during the entire traversal. It is a bad idea to invoke + other malloc functions from within the handler. + + For example, to count the number of in-use chunks with size greater + than 1000, you could write: + static int count = 0; + void count_chunks(void* start, void* end, size_t used, void* arg) { + if (used >= 1000) ++count; + } + then: + malloc_inspect_all(count_chunks, NULL); + + malloc_inspect_all is compiled only if MALLOC_INSPECT_ALL is defined. +*/ +DLMALLOC_EXPORT void dlmalloc_inspect_all(void(*handler)(void*, void *, size_t, void*), + void* arg); + +#endif /* MALLOC_INSPECT_ALL */ + +#if !NO_MALLINFO +/* + mallinfo() + Returns (by copy) a struct containing various summary statistics: + + arena: current total non-mmapped bytes allocated from system + ordblks: the number of free chunks + smblks: always zero. + hblks: current number of mmapped regions + hblkhd: total bytes held in mmapped regions + usmblks: the maximum total allocated space. This will be greater + than current total if trimming has occurred. + fsmblks: always zero + uordblks: current total allocated space (normal or mmapped) + fordblks: total free space + keepcost: the maximum number of bytes that could ideally be released + back to system via malloc_trim. ("ideally" means that + it ignores page restrictions etc.) + + Because these fields are ints, but internal bookkeeping may + be kept as longs, the reported values may wrap around zero and + thus be inaccurate. +*/ +DLMALLOC_EXPORT struct mallinfo dlmallinfo(void); +#endif /* NO_MALLINFO */ + +/* + independent_calloc(size_t n_elements, size_t element_size, void* chunks[]); + + independent_calloc is similar to calloc, but instead of returning a + single cleared space, it returns an array of pointers to n_elements + independent elements that can hold contents of size elem_size, each + of which starts out cleared, and can be independently freed, + realloc'ed etc. The elements are guaranteed to be adjacently + allocated (this is not guaranteed to occur with multiple callocs or + mallocs), which may also improve cache locality in some + applications. + + The "chunks" argument is optional (i.e., may be null, which is + probably the most typical usage). If it is null, the returned array + is itself dynamically allocated and should also be freed when it is + no longer needed. Otherwise, the chunks array must be of at least + n_elements in length. It is filled in with the pointers to the + chunks. + + In either case, independent_calloc returns this pointer array, or + null if the allocation failed. If n_elements is zero and "chunks" + is null, it returns a chunk representing an array with zero elements + (which should be freed if not wanted). + + Each element must be freed when it is no longer needed. This can be + done all at once using bulk_free. + + independent_calloc simplifies and speeds up implementations of many + kinds of pools. It may also be useful when constructing large data + structures that initially have a fixed number of fixed-sized nodes, + but the number is not known at compile time, and some of the nodes + may later need to be freed. For example: + + struct Node { int item; struct Node* next; }; + + struct Node* build_list() { + struct Node** pool; + int n = read_number_of_nodes_needed(); + if (n <= 0) return 0; + pool = (struct Node**)(independent_calloc(n, sizeof(struct Node), 0); + if (pool == 0) die(); + // organize into a linked list... + struct Node* first = pool[0]; + for (i = 0; i < n-1; ++i) + pool[i]->next = pool[i+1]; + free(pool); // Can now free the array (or not, if it is needed later) + return first; + } +*/ +DLMALLOC_EXPORT void** dlindependent_calloc(size_t, size_t, void**); + +/* + independent_comalloc(size_t n_elements, size_t sizes[], void* chunks[]); + + independent_comalloc allocates, all at once, a set of n_elements + chunks with sizes indicated in the "sizes" array. It returns + an array of pointers to these elements, each of which can be + independently freed, realloc'ed etc. The elements are guaranteed to + be adjacently allocated (this is not guaranteed to occur with + multiple callocs or mallocs), which may also improve cache locality + in some applications. + + The "chunks" argument is optional (i.e., may be null). If it is null + the returned array is itself dynamically allocated and should also + be freed when it is no longer needed. Otherwise, the chunks array + must be of at least n_elements in length. It is filled in with the + pointers to the chunks. + + In either case, independent_comalloc returns this pointer array, or + null if the allocation failed. If n_elements is zero and chunks is + null, it returns a chunk representing an array with zero elements + (which should be freed if not wanted). + + Each element must be freed when it is no longer needed. This can be + done all at once using bulk_free. + + independent_comallac differs from independent_calloc in that each + element may have a different size, and also that it does not + automatically clear elements. + + independent_comalloc can be used to speed up allocation in cases + where several structs or objects must always be allocated at the + same time. For example: + + struct Head { ... } + struct Foot { ... } + + void send_message(char* msg) { + int msglen = strlen(msg); + size_t sizes[3] = { sizeof(struct Head), msglen, sizeof(struct Foot) }; + void* chunks[3]; + if (independent_comalloc(3, sizes, chunks) == 0) + die(); + struct Head* head = (struct Head*)(chunks[0]); + char* body = (char*)(chunks[1]); + struct Foot* foot = (struct Foot*)(chunks[2]); + // ... + } + + In general though, independent_comalloc is worth using only for + larger values of n_elements. For small values, you probably won't + detect enough difference from series of malloc calls to bother. + + Overuse of independent_comalloc can increase overall memory usage, + since it cannot reuse existing noncontiguous small chunks that + might be available for some of the elements. +*/ +DLMALLOC_EXPORT void** dlindependent_comalloc(size_t, size_t*, void**); + +/* + bulk_free(void* array[], size_t n_elements) + Frees and clears (sets to null) each non-null pointer in the given + array. This is likely to be faster than freeing them one-by-one. + If footers are used, pointers that have been allocated in different + mspaces are not freed or cleared, and the count of all such pointers + is returned. For large arrays of pointers with poor locality, it + may be worthwhile to sort this array before calling bulk_free. +*/ +DLMALLOC_EXPORT size_t dlbulk_free(void**, size_t n_elements); + +/* + pvalloc(size_t n); + Equivalent to valloc(minimum-page-that-holds(n)), that is, + round up n to nearest pagesize. + */ +DLMALLOC_EXPORT void* dlpvalloc(size_t); + +/* + malloc_trim(size_t pad); + + If possible, gives memory back to the system (via negative arguments + to sbrk) if there is unused memory at the `high' end of the malloc + pool or in unused MMAP segments. You can call this after freeing + large blocks of memory to potentially reduce the system-level memory + requirements of a program. However, it cannot guarantee to reduce + memory. Under some allocation patterns, some large free blocks of + memory will be locked between two used chunks, so they cannot be + given back to the system. + + The `pad' argument to malloc_trim represents the amount of free + trailing space to leave untrimmed. If this argument is zero, only + the minimum amount of memory to maintain internal data structures + will be left. Non-zero arguments can be supplied to maintain enough + trailing space to service future expected allocations without having + to re-obtain memory from the system. + + Malloc_trim returns 1 if it actually released any memory, else 0. +*/ +DLMALLOC_EXPORT int dlmalloc_trim(size_t); + +/* + malloc_stats(); + Prints on stderr the amount of space obtained from the system (both + via sbrk and mmap), the maximum amount (which may be more than + current if malloc_trim and/or munmap got called), and the current + number of bytes allocated via malloc (or realloc, etc) but not yet + freed. Note that this is the number of bytes allocated, not the + number requested. It will be larger than the number requested + because of alignment and bookkeeping overhead. Because it includes + alignment wastage as being in use, this figure may be greater than + zero even when no user-level chunks are allocated. + + The reported current and maximum system memory can be inaccurate if + a program makes other calls to system memory allocation functions + (normally sbrk) outside of malloc. + + malloc_stats prints only the most commonly interesting statistics. + More information can be obtained by calling mallinfo. +*/ +DLMALLOC_EXPORT void dlmalloc_stats(void); + +/* + malloc_usable_size(void* p); + + Returns the number of bytes you can actually use in + an allocated chunk, which may be more than you requested (although + often not) due to alignment and minimum size constraints. + You can use this many bytes without worrying about + overwriting other allocated objects. This is not a particularly great + programming practice. malloc_usable_size can be more useful in + debugging and assertions, for example: + + p = malloc(n); + assert(malloc_usable_size(p) >= 256); +*/ +size_t dlmalloc_usable_size(void*); + +#endif /* ONLY_MSPACES */ + +#if MSPACES + +/* + mspace is an opaque type representing an independent + region of space that supports mspace_malloc, etc. +*/ +typedef void* mspace; + +/* + create_mspace creates and returns a new independent space with the + given initial capacity, or, if 0, the default granularity size. It + returns null if there is no system memory available to create the + space. If argument locked is non-zero, the space uses a separate + lock to control access. The capacity of the space will grow + dynamically as needed to service mspace_malloc requests. You can + control the sizes of incremental increases of this space by + compiling with a different DEFAULT_GRANULARITY or dynamically + setting with mallopt(M_GRANULARITY, value). +*/ +DLMALLOC_EXPORT mspace create_mspace(size_t capacity, int locked); + +/* + destroy_mspace destroys the given space, and attempts to return all + of its memory back to the system, returning the total number of + bytes freed. After destruction, the results of access to all memory + used by the space become undefined. +*/ +DLMALLOC_EXPORT size_t destroy_mspace(mspace msp); + +/* + create_mspace_with_base uses the memory supplied as the initial base + of a new mspace. Part (less than 128*sizeof(size_t) bytes) of this + space is used for bookkeeping, so the capacity must be at least this + large. (Otherwise 0 is returned.) When this initial space is + exhausted, additional memory will be obtained from the system. + Destroying this space will deallocate all additionally allocated + space (if possible) but not the initial base. +*/ +DLMALLOC_EXPORT mspace create_mspace_with_base(void* base, size_t capacity, int locked); + +/* + mspace_track_large_chunks controls whether requests for large chunks + are allocated in their own untracked mmapped regions, separate from + others in this mspace. By default large chunks are not tracked, + which reduces fragmentation. However, such chunks are not + necessarily released to the system upon destroy_mspace. Enabling + tracking by setting to true may increase fragmentation, but avoids + leakage when relying on destroy_mspace to release all memory + allocated using this space. The function returns the previous + setting. +*/ +DLMALLOC_EXPORT int mspace_track_large_chunks(mspace msp, int enable); + + +/* + mspace_malloc behaves as malloc, but operates within + the given space. +*/ +DLMALLOC_EXPORT void* mspace_malloc(mspace msp, size_t bytes); + +/* + mspace_free behaves as free, but operates within + the given space. + + If compiled with FOOTERS==1, mspace_free is not actually needed. + free may be called instead of mspace_free because freed chunks from + any space are handled by their originating spaces. +*/ +DLMALLOC_EXPORT void mspace_free(mspace msp, void* mem); + +/* + mspace_realloc behaves as realloc, but operates within + the given space. + + If compiled with FOOTERS==1, mspace_realloc is not actually + needed. realloc may be called instead of mspace_realloc because + realloced chunks from any space are handled by their originating + spaces. +*/ +DLMALLOC_EXPORT void* mspace_realloc(mspace msp, void* mem, size_t newsize); + +/* + mspace_calloc behaves as calloc, but operates within + the given space. +*/ +DLMALLOC_EXPORT void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size); + +/* + mspace_memalign behaves as memalign, but operates within + the given space. +*/ +DLMALLOC_EXPORT void* mspace_memalign(mspace msp, size_t alignment, size_t bytes); + +/* + mspace_independent_calloc behaves as independent_calloc, but + operates within the given space. +*/ +DLMALLOC_EXPORT void** mspace_independent_calloc(mspace msp, size_t n_elements, + size_t elem_size, void* chunks[]); + +/* + mspace_independent_comalloc behaves as independent_comalloc, but + operates within the given space. +*/ +DLMALLOC_EXPORT void** mspace_independent_comalloc(mspace msp, size_t n_elements, + size_t sizes[], void* chunks[]); + +/* + mspace_footprint() returns the number of bytes obtained from the + system for this space. +*/ +DLMALLOC_EXPORT size_t mspace_footprint(mspace msp); + +/* + mspace_max_footprint() returns the peak number of bytes obtained from the + system for this space. +*/ +DLMALLOC_EXPORT size_t mspace_max_footprint(mspace msp); + + +#if !NO_MALLINFO +/* + mspace_mallinfo behaves as mallinfo, but reports properties of + the given space. +*/ +DLMALLOC_EXPORT struct mallinfo mspace_mallinfo(mspace msp); +#endif /* NO_MALLINFO */ + +/* + malloc_usable_size(void* p) behaves the same as malloc_usable_size; +*/ +DLMALLOC_EXPORT size_t mspace_usable_size(const void* mem); + +/* + mspace_malloc_stats behaves as malloc_stats, but reports + properties of the given space. +*/ +DLMALLOC_EXPORT void mspace_malloc_stats(mspace msp); + +/* + mspace_trim behaves as malloc_trim, but + operates within the given space. +*/ +DLMALLOC_EXPORT int mspace_trim(mspace msp, size_t pad); + +/* + An alias for mallopt. +*/ +DLMALLOC_EXPORT int mspace_mallopt(int, int); + +#endif /* MSPACES */ + +#ifdef __cplusplus +} /* end of extern "C" */ +#endif /* __cplusplus */ + +/* + ======================================================================== + To make a fully customizable malloc.h header file, cut everything + above this line, put into file malloc.h, edit to suit, and #include it + on the next line, as well as in programs that use this malloc. + ======================================================================== +*/ + +/* #include "malloc.h" */ + +/*------------------------------ internal #includes ---------------------- */ + +#ifdef _MSC_VER +#pragma warning( disable : 4146 ) /* no "unsigned" warnings */ +#endif /* _MSC_VER */ +#if !NO_MALLOC_STATS +#include /* for printing in malloc_stats */ +#endif /* NO_MALLOC_STATS */ +#ifndef LACKS_ERRNO_H +#include /* for MALLOC_FAILURE_ACTION */ +#endif /* LACKS_ERRNO_H */ +#ifdef DEBUG +#if ABORT_ON_ASSERT_FAILURE +#undef assert +#define assert(x) if(!(x)) ABORT +#else /* ABORT_ON_ASSERT_FAILURE */ +#include +#endif /* ABORT_ON_ASSERT_FAILURE */ +#else /* DEBUG */ +#ifndef assert +#define assert(x) +#endif +#define DEBUG 0 +#endif /* DEBUG */ +#if !defined(WIN32) && !defined(LACKS_TIME_H) +#include /* for magic initialization */ +#endif /* WIN32 */ +#ifndef LACKS_STDLIB_H +#include /* for abort() */ +#endif /* LACKS_STDLIB_H */ +#ifndef LACKS_STRING_H +#include /* for memset etc */ +#endif /* LACKS_STRING_H */ +#if USE_BUILTIN_FFS +#ifndef LACKS_STRINGS_H +#include /* for ffs */ +#endif /* LACKS_STRINGS_H */ +#endif /* USE_BUILTIN_FFS */ +#if HAVE_MMAP +#ifndef LACKS_SYS_MMAN_H +/* On some versions of linux, mremap decl in mman.h needs __USE_GNU set */ +#if (defined(linux) && !defined(__USE_GNU)) +#define __USE_GNU 1 +#include /* for mmap */ +#undef __USE_GNU +#else +#include /* for mmap */ +#endif /* linux */ +#endif /* LACKS_SYS_MMAN_H */ +#ifndef LACKS_FCNTL_H +#include +#endif /* LACKS_FCNTL_H */ +#endif /* HAVE_MMAP */ +#ifndef LACKS_UNISTD_H +#include /* for sbrk, sysconf */ +#else /* LACKS_UNISTD_H */ +#if !defined(__FreeBSD__) && !defined(__OpenBSD__) && !defined(__NetBSD__) +extern void* sbrk(ptrdiff_t); +#endif /* FreeBSD etc */ +#endif /* LACKS_UNISTD_H */ + +/* Declarations for locking */ +#if USE_LOCKS +#ifndef WIN32 +#if defined (__SVR4) && defined (__sun) /* solaris */ +#include +#elif !defined(LACKS_SCHED_H) +#include +#endif /* solaris or LACKS_SCHED_H */ +#if (defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0) || !USE_SPIN_LOCKS +#include +#endif /* USE_RECURSIVE_LOCKS ... */ +#elif defined(_MSC_VER) +#ifndef _M_AMD64 +/* These are already defined on AMD64 builds */ +#ifdef __cplusplus +extern "C" { +#endif /* __cplusplus */ +LONG __cdecl _InterlockedCompareExchange(LONG volatile *Dest, LONG Exchange, LONG Comp); +LONG __cdecl _InterlockedExchange(LONG volatile *Target, LONG Value); +#ifdef __cplusplus +} +#endif /* __cplusplus */ +#endif /* _M_AMD64 */ +#pragma intrinsic (_InterlockedCompareExchange) +#pragma intrinsic (_InterlockedExchange) +#define interlockedcompareexchange _InterlockedCompareExchange +#define interlockedexchange _InterlockedExchange +#elif defined(WIN32) && defined(__GNUC__) +#define interlockedcompareexchange(a, b, c) __sync_val_compare_and_swap(a, c, b) +#define interlockedexchange __sync_lock_test_and_set +#endif /* Win32 */ +#else /* USE_LOCKS */ +#endif /* USE_LOCKS */ + +#ifndef LOCK_AT_FORK +#define LOCK_AT_FORK 0 +#endif + +/* Declarations for bit scanning on win32 */ +#if defined(_MSC_VER) && _MSC_VER>=1300 +#ifndef BitScanForward /* Try to avoid pulling in WinNT.h */ +#ifdef __cplusplus +extern "C" { +#endif /* __cplusplus */ +unsigned char _BitScanForward(unsigned long *index, unsigned long mask); +unsigned char _BitScanReverse(unsigned long *index, unsigned long mask); +#ifdef __cplusplus +} +#endif /* __cplusplus */ + +#define BitScanForward _BitScanForward +#define BitScanReverse _BitScanReverse +#pragma intrinsic(_BitScanForward) +#pragma intrinsic(_BitScanReverse) +#endif /* BitScanForward */ +#endif /* defined(_MSC_VER) && _MSC_VER>=1300 */ + +#ifndef WIN32 +#ifndef malloc_getpagesize +# ifdef _SC_PAGESIZE /* some SVR4 systems omit an underscore */ +# ifndef _SC_PAGE_SIZE +# define _SC_PAGE_SIZE _SC_PAGESIZE +# endif +# endif +# ifdef _SC_PAGE_SIZE +# define malloc_getpagesize sysconf(_SC_PAGE_SIZE) +# else +# if defined(BSD) || defined(DGUX) || defined(HAVE_GETPAGESIZE) + extern size_t getpagesize(); +# define malloc_getpagesize getpagesize() +# else +# ifdef WIN32 /* use supplied emulation of getpagesize */ +# define malloc_getpagesize getpagesize() +# else +# ifndef LACKS_SYS_PARAM_H +# include +# endif +# ifdef EXEC_PAGESIZE +# define malloc_getpagesize EXEC_PAGESIZE +# else +# ifdef NBPG +# ifndef CLSIZE +# define malloc_getpagesize NBPG +# else +# define malloc_getpagesize (NBPG * CLSIZE) +# endif +# else +# ifdef NBPC +# define malloc_getpagesize NBPC +# else +# ifdef PAGESIZE +# define malloc_getpagesize PAGESIZE +# else /* just guess */ +# define malloc_getpagesize ((size_t)4096U) +# endif +# endif +# endif +# endif +# endif +# endif +# endif +#endif +#endif + +/* ------------------- size_t and alignment properties -------------------- */ + +/* The byte and bit size of a size_t */ +#define SIZE_T_SIZE (sizeof(size_t)) +#define SIZE_T_BITSIZE (sizeof(size_t) << 3) + +/* Some constants coerced to size_t */ +/* Annoying but necessary to avoid errors on some platforms */ +#define SIZE_T_ZERO ((size_t)0) +#define SIZE_T_ONE ((size_t)1) +#define SIZE_T_TWO ((size_t)2) +#define SIZE_T_FOUR ((size_t)4) +#define TWO_SIZE_T_SIZES (SIZE_T_SIZE<<1) +#define FOUR_SIZE_T_SIZES (SIZE_T_SIZE<<2) +#define SIX_SIZE_T_SIZES (FOUR_SIZE_T_SIZES+TWO_SIZE_T_SIZES) +#define HALF_MAX_SIZE_T (MAX_SIZE_T / 2U) + +/* The bit mask value corresponding to MALLOC_ALIGNMENT */ +#define CHUNK_ALIGN_MASK (MALLOC_ALIGNMENT - SIZE_T_ONE) + +/* True if address a has acceptable alignment */ +#define is_aligned(A) (((size_t)((A)) & (CHUNK_ALIGN_MASK)) == 0) + +/* the number of bytes to offset an address to align it */ +#define align_offset(A)\ + ((((size_t)(A) & CHUNK_ALIGN_MASK) == 0)? 0 :\ + ((MALLOC_ALIGNMENT - ((size_t)(A) & CHUNK_ALIGN_MASK)) & CHUNK_ALIGN_MASK)) + +/* -------------------------- MMAP preliminaries ------------------------- */ + +/* + If HAVE_MORECORE or HAVE_MMAP are false, we just define calls and + checks to fail so compiler optimizer can delete code rather than + using so many "#if"s. +*/ + + +/* MORECORE and MMAP must return MFAIL on failure */ +#define MFAIL ((void*)(MAX_SIZE_T)) +#define CMFAIL ((char*)(MFAIL)) /* defined for convenience */ + +#if HAVE_MMAP + +#ifndef WIN32 +#define MUNMAP_DEFAULT(a, s) munmap((a), (s)) +#define MMAP_PROT (PROT_READ|PROT_WRITE) +#if !defined(MAP_ANONYMOUS) && defined(MAP_ANON) +#define MAP_ANONYMOUS MAP_ANON +#endif /* MAP_ANON */ +#ifdef MAP_ANONYMOUS +#define MMAP_FLAGS (MAP_PRIVATE|MAP_ANONYMOUS) +#define MMAP_DEFAULT(s) mmap(0, (s), MMAP_PROT, MMAP_FLAGS, -1, 0) +#else /* MAP_ANONYMOUS */ +/* + Nearly all versions of mmap support MAP_ANONYMOUS, so the following + is unlikely to be needed, but is supplied just in case. +*/ +#define MMAP_FLAGS (MAP_PRIVATE) +static int dev_zero_fd = -1; /* Cached file descriptor for /dev/zero. */ +#define MMAP_DEFAULT(s) ((dev_zero_fd < 0) ? \ + (dev_zero_fd = open("/dev/zero", O_RDWR), \ + mmap(0, (s), MMAP_PROT, MMAP_FLAGS, dev_zero_fd, 0)) : \ + mmap(0, (s), MMAP_PROT, MMAP_FLAGS, dev_zero_fd, 0)) +#endif /* MAP_ANONYMOUS */ + +#define DIRECT_MMAP_DEFAULT(s) MMAP_DEFAULT(s) + +#else /* WIN32 */ + +/* Win32 MMAP via VirtualAlloc */ +static FORCEINLINE void* win32mmap(size_t size) { + void* ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT, PAGE_READWRITE); + return (ptr != 0)? ptr: MFAIL; +} + +/* For direct MMAP, use MEM_TOP_DOWN to minimize interference */ +static FORCEINLINE void* win32direct_mmap(size_t size) { + void* ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT|MEM_TOP_DOWN, + PAGE_READWRITE); + return (ptr != 0)? ptr: MFAIL; +} + +/* This function supports releasing coalesed segments */ +static FORCEINLINE int win32munmap(void* ptr, size_t size) { + MEMORY_BASIC_INFORMATION minfo; + char* cptr = (char*)ptr; + while (size) { + if (VirtualQuery(cptr, &minfo, sizeof(minfo)) == 0) + return -1; + if (minfo.BaseAddress != cptr || minfo.AllocationBase != cptr || + minfo.State != MEM_COMMIT || minfo.RegionSize > size) + return -1; + if (VirtualFree(cptr, 0, MEM_RELEASE) == 0) + return -1; + cptr += minfo.RegionSize; + size -= minfo.RegionSize; + } + return 0; +} + +#define MMAP_DEFAULT(s) win32mmap(s) +#define MUNMAP_DEFAULT(a, s) win32munmap((a), (s)) +#define DIRECT_MMAP_DEFAULT(s) win32direct_mmap(s) +#endif /* WIN32 */ +#endif /* HAVE_MMAP */ + +#if HAVE_MREMAP +#ifndef WIN32 +#define MREMAP_DEFAULT(addr, osz, nsz, mv) mremap((addr), (osz), (nsz), (mv)) +#endif /* WIN32 */ +#endif /* HAVE_MREMAP */ + +/** + * Define CALL_MORECORE + */ +#if HAVE_MORECORE + #ifdef MORECORE + #define CALL_MORECORE(S) MORECORE(S) + #else /* MORECORE */ + #define CALL_MORECORE(S) MORECORE_DEFAULT(S) + #endif /* MORECORE */ +#else /* HAVE_MORECORE */ + #define CALL_MORECORE(S) MFAIL +#endif /* HAVE_MORECORE */ + +/** + * Define CALL_MMAP/CALL_MUNMAP/CALL_DIRECT_MMAP + */ +#if HAVE_MMAP + #define USE_MMAP_BIT (SIZE_T_ONE) + + #ifdef MMAP + #define CALL_MMAP(s) MMAP(s) + #else /* MMAP */ + #define CALL_MMAP(s) MMAP_DEFAULT(s) + #endif /* MMAP */ + #ifdef MUNMAP + #define CALL_MUNMAP(a, s) MUNMAP((a), (s)) + #else /* MUNMAP */ + #define CALL_MUNMAP(a, s) MUNMAP_DEFAULT((a), (s)) + #endif /* MUNMAP */ + #ifdef DIRECT_MMAP + #define CALL_DIRECT_MMAP(s) DIRECT_MMAP(s) + #else /* DIRECT_MMAP */ + #define CALL_DIRECT_MMAP(s) DIRECT_MMAP_DEFAULT(s) + #endif /* DIRECT_MMAP */ +#else /* HAVE_MMAP */ + #define USE_MMAP_BIT (SIZE_T_ZERO) + + #define MMAP(s) MFAIL + #define MUNMAP(a, s) (-1) + #define DIRECT_MMAP(s) MFAIL + #define CALL_DIRECT_MMAP(s) DIRECT_MMAP(s) + #define CALL_MMAP(s) MMAP(s) + #define CALL_MUNMAP(a, s) MUNMAP((a), (s)) +#endif /* HAVE_MMAP */ + +/** + * Define CALL_MREMAP + */ +#if HAVE_MMAP && HAVE_MREMAP + #ifdef MREMAP + #define CALL_MREMAP(addr, osz, nsz, mv) MREMAP((addr), (osz), (nsz), (mv)) + #else /* MREMAP */ + #define CALL_MREMAP(addr, osz, nsz, mv) MREMAP_DEFAULT((addr), (osz), (nsz), (mv)) + #endif /* MREMAP */ +#else /* HAVE_MMAP && HAVE_MREMAP */ + #define CALL_MREMAP(addr, osz, nsz, mv) MFAIL +#endif /* HAVE_MMAP && HAVE_MREMAP */ + +/* mstate bit set if continguous morecore disabled or failed */ +#define USE_NONCONTIGUOUS_BIT (4U) + +/* segment bit set in create_mspace_with_base */ +#define EXTERN_BIT (8U) + + +/* --------------------------- Lock preliminaries ------------------------ */ + +/* + When locks are defined, there is one global lock, plus + one per-mspace lock. + + The global lock_ensures that mparams.magic and other unique + mparams values are initialized only once. It also protects + sequences of calls to MORECORE. In many cases sys_alloc requires + two calls, that should not be interleaved with calls by other + threads. This does not protect against direct calls to MORECORE + by other threads not using this lock, so there is still code to + cope the best we can on interference. + + Per-mspace locks surround calls to malloc, free, etc. + By default, locks are simple non-reentrant mutexes. + + Because lock-protected regions generally have bounded times, it is + OK to use the supplied simple spinlocks. Spinlocks are likely to + improve performance for lightly contended applications, but worsen + performance under heavy contention. + + If USE_LOCKS is > 1, the definitions of lock routines here are + bypassed, in which case you will need to define the type MLOCK_T, + and at least INITIAL_LOCK, DESTROY_LOCK, ACQUIRE_LOCK, RELEASE_LOCK + and TRY_LOCK. You must also declare a + static MLOCK_T malloc_global_mutex = { initialization values };. + +*/ + +#if !USE_LOCKS +#define USE_LOCK_BIT (0U) +#define INITIAL_LOCK(l) (0) +#define DESTROY_LOCK(l) (0) +#define ACQUIRE_MALLOC_GLOBAL_LOCK() +#define RELEASE_MALLOC_GLOBAL_LOCK() + +#else +#if USE_LOCKS > 1 +/* ----------------------- User-defined locks ------------------------ */ +/* Define your own lock implementation here */ +/* #define INITIAL_LOCK(lk) ... */ +/* #define DESTROY_LOCK(lk) ... */ +/* #define ACQUIRE_LOCK(lk) ... */ +/* #define RELEASE_LOCK(lk) ... */ +/* #define TRY_LOCK(lk) ... */ +/* static MLOCK_T malloc_global_mutex = ... */ + +#elif USE_SPIN_LOCKS + +/* First, define CAS_LOCK and CLEAR_LOCK on ints */ +/* Note CAS_LOCK defined to return 0 on success */ + +#if defined(__GNUC__)&& (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 1)) +#define CAS_LOCK(sl) __sync_lock_test_and_set(sl, 1) +#define CLEAR_LOCK(sl) __sync_lock_release(sl) + +#elif (defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))) +/* Custom spin locks for older gcc on x86 */ +static FORCEINLINE int x86_cas_lock(int *sl) { + int ret; + int val = 1; + int cmp = 0; + __asm__ __volatile__ ("lock; cmpxchgl %1, %2" + : "=a" (ret) + : "r" (val), "m" (*(sl)), "0"(cmp) + : "memory", "cc"); + return ret; +} + +static FORCEINLINE void x86_clear_lock(int* sl) { + assert(*sl != 0); + int prev = 0; + int ret; + __asm__ __volatile__ ("lock; xchgl %0, %1" + : "=r" (ret) + : "m" (*(sl)), "0"(prev) + : "memory"); +} + +#define CAS_LOCK(sl) x86_cas_lock(sl) +#define CLEAR_LOCK(sl) x86_clear_lock(sl) + +#else /* Win32 MSC */ +#define CAS_LOCK(sl) interlockedexchange(sl, (LONG)1) +#define CLEAR_LOCK(sl) interlockedexchange (sl, (LONG)0) + +#endif /* ... gcc spins locks ... */ + +/* How to yield for a spin lock */ +#define SPINS_PER_YIELD 63 +#if defined(_MSC_VER) +#define SLEEP_EX_DURATION 50 /* delay for yield/sleep */ +#define SPIN_LOCK_YIELD SleepEx(SLEEP_EX_DURATION, FALSE) +#elif defined (__SVR4) && defined (__sun) /* solaris */ +#define SPIN_LOCK_YIELD thr_yield(); +#elif !defined(LACKS_SCHED_H) +#define SPIN_LOCK_YIELD sched_yield(); +#else +#define SPIN_LOCK_YIELD +#endif /* ... yield ... */ + +#if !defined(USE_RECURSIVE_LOCKS) || USE_RECURSIVE_LOCKS == 0 +/* Plain spin locks use single word (embedded in malloc_states) */ +static int spin_acquire_lock(int *sl) { + int spins = 0; + while (*(volatile int *)sl != 0 || CAS_LOCK(sl)) { + if ((++spins & SPINS_PER_YIELD) == 0) { + SPIN_LOCK_YIELD; + } + } + return 0; +} + +#define MLOCK_T int +#define TRY_LOCK(sl) !CAS_LOCK(sl) +#define RELEASE_LOCK(sl) CLEAR_LOCK(sl) +#define ACQUIRE_LOCK(sl) (CAS_LOCK(sl)? spin_acquire_lock(sl) : 0) +#define INITIAL_LOCK(sl) (*sl = 0) +#define DESTROY_LOCK(sl) (0) +static MLOCK_T malloc_global_mutex = 0; + +#else /* USE_RECURSIVE_LOCKS */ +/* types for lock owners */ +#ifdef WIN32 +#define THREAD_ID_T DWORD +#define CURRENT_THREAD GetCurrentThreadId() +#define EQ_OWNER(X,Y) ((X) == (Y)) +#else +/* + Note: the following assume that pthread_t is a type that can be + initialized to (casted) zero. If this is not the case, you will need to + somehow redefine these or not use spin locks. +*/ +#define THREAD_ID_T pthread_t +#define CURRENT_THREAD pthread_self() +#define EQ_OWNER(X,Y) pthread_equal(X, Y) +#endif + +struct malloc_recursive_lock { + int sl; + unsigned int c; + THREAD_ID_T threadid; +}; + +#define MLOCK_T struct malloc_recursive_lock +static MLOCK_T malloc_global_mutex = { 0, 0, (THREAD_ID_T)0}; + +static FORCEINLINE void recursive_release_lock(MLOCK_T *lk) { + assert(lk->sl != 0); + if (--lk->c == 0) { + CLEAR_LOCK(&lk->sl); + } +} + +static FORCEINLINE int recursive_acquire_lock(MLOCK_T *lk) { + THREAD_ID_T mythreadid = CURRENT_THREAD; + int spins = 0; + for (;;) { + if (*((volatile int *)(&lk->sl)) == 0) { + if (!CAS_LOCK(&lk->sl)) { + lk->threadid = mythreadid; + lk->c = 1; + return 0; + } + } + else if (EQ_OWNER(lk->threadid, mythreadid)) { + ++lk->c; + return 0; + } + if ((++spins & SPINS_PER_YIELD) == 0) { + SPIN_LOCK_YIELD; + } + } +} + +static FORCEINLINE int recursive_try_lock(MLOCK_T *lk) { + THREAD_ID_T mythreadid = CURRENT_THREAD; + if (*((volatile int *)(&lk->sl)) == 0) { + if (!CAS_LOCK(&lk->sl)) { + lk->threadid = mythreadid; + lk->c = 1; + return 1; + } + } + else if (EQ_OWNER(lk->threadid, mythreadid)) { + ++lk->c; + return 1; + } + return 0; +} + +#define RELEASE_LOCK(lk) recursive_release_lock(lk) +#define TRY_LOCK(lk) recursive_try_lock(lk) +#define ACQUIRE_LOCK(lk) recursive_acquire_lock(lk) +#define INITIAL_LOCK(lk) ((lk)->threadid = (THREAD_ID_T)0, (lk)->sl = 0, (lk)->c = 0) +#define DESTROY_LOCK(lk) (0) +#endif /* USE_RECURSIVE_LOCKS */ + +#elif defined(WIN32) /* Win32 critical sections */ +#define MLOCK_T CRITICAL_SECTION +#define ACQUIRE_LOCK(lk) (EnterCriticalSection(lk), 0) +#define RELEASE_LOCK(lk) LeaveCriticalSection(lk) +#define TRY_LOCK(lk) TryEnterCriticalSection(lk) +#define INITIAL_LOCK(lk) (!InitializeCriticalSectionAndSpinCount((lk), 0x80000000|4000)) +#define DESTROY_LOCK(lk) (DeleteCriticalSection(lk), 0) +#define NEED_GLOBAL_LOCK_INIT + +static MLOCK_T malloc_global_mutex; +static volatile LONG malloc_global_mutex_status; + +/* Use spin loop to initialize global lock */ +static void init_malloc_global_mutex() { + for (;;) { + long stat = malloc_global_mutex_status; + if (stat > 0) + return; + /* transition to < 0 while initializing, then to > 0) */ + if (stat == 0 && + interlockedcompareexchange(&malloc_global_mutex_status, (LONG)-1, (LONG)0) == 0) { + InitializeCriticalSection(&malloc_global_mutex); + interlockedexchange(&malloc_global_mutex_status, (LONG)1); + return; + } + SleepEx(0, FALSE); + } +} + +#else /* pthreads-based locks */ +#define MLOCK_T pthread_mutex_t +#define ACQUIRE_LOCK(lk) pthread_mutex_lock(lk) +#define RELEASE_LOCK(lk) pthread_mutex_unlock(lk) +#define TRY_LOCK(lk) (!pthread_mutex_trylock(lk)) +#define INITIAL_LOCK(lk) pthread_init_lock(lk) +#define DESTROY_LOCK(lk) pthread_mutex_destroy(lk) + +#if defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0 && defined(linux) && !defined(PTHREAD_MUTEX_RECURSIVE) +/* Cope with old-style linux recursive lock initialization by adding */ +/* skipped internal declaration from pthread.h */ +extern int pthread_mutexattr_setkind_np __P ((pthread_mutexattr_t *__attr, + int __kind)); +#define PTHREAD_MUTEX_RECURSIVE PTHREAD_MUTEX_RECURSIVE_NP +#define pthread_mutexattr_settype(x,y) pthread_mutexattr_setkind_np(x,y) +#endif /* USE_RECURSIVE_LOCKS ... */ + +static MLOCK_T malloc_global_mutex = PTHREAD_MUTEX_INITIALIZER; + +static int pthread_init_lock (MLOCK_T *lk) { + pthread_mutexattr_t attr; + if (pthread_mutexattr_init(&attr)) return 1; +#if defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0 + if (pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_RECURSIVE)) return 1; +#endif + if (pthread_mutex_init(lk, &attr)) return 1; + if (pthread_mutexattr_destroy(&attr)) return 1; + return 0; +} + +#endif /* ... lock types ... */ + +/* Common code for all lock types */ +#define USE_LOCK_BIT (2U) + +#ifndef ACQUIRE_MALLOC_GLOBAL_LOCK +#define ACQUIRE_MALLOC_GLOBAL_LOCK() ACQUIRE_LOCK(&malloc_global_mutex); +#endif + +#ifndef RELEASE_MALLOC_GLOBAL_LOCK +#define RELEASE_MALLOC_GLOBAL_LOCK() RELEASE_LOCK(&malloc_global_mutex); +#endif + +#endif /* USE_LOCKS */ + +/* ----------------------- Chunk representations ------------------------ */ + +/* + (The following includes lightly edited explanations by Colin Plumb.) + + The malloc_chunk declaration below is misleading (but accurate and + necessary). It declares a "view" into memory allowing access to + necessary fields at known offsets from a given base. + + Chunks of memory are maintained using a `boundary tag' method as + originally described by Knuth. (See the paper by Paul Wilson + ftp://ftp.cs.utexas.edu/pub/garbage/allocsrv.ps for a survey of such + techniques.) Sizes of free chunks are stored both in the front of + each chunk and at the end. This makes consolidating fragmented + chunks into bigger chunks fast. The head fields also hold bits + representing whether chunks are free or in use. + + Here are some pictures to make it clearer. They are "exploded" to + show that the state of a chunk can be thought of as extending from + the high 31 bits of the head field of its header through the + prev_foot and PINUSE_BIT bit of the following chunk header. + + A chunk that's in use looks like: + + chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Size of previous chunk (if P = 0) | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |P| + | Size of this chunk 1| +-+ + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | | + +- -+ + | | + +- -+ + | : + +- size - sizeof(size_t) available payload bytes -+ + : | + chunk-> +- -+ + | | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |1| + | Size of next chunk (may or may not be in use) | +-+ + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + + And if it's free, it looks like this: + + chunk-> +- -+ + | User payload (must be in use, or we would have merged!) | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |P| + | Size of this chunk 0| +-+ + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Next pointer | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Prev pointer | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | : + +- size - sizeof(struct chunk) unused bytes -+ + : | + chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Size of this chunk | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |0| + | Size of next chunk (must be in use, or we would have merged)| +-+ + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | : + +- User payload -+ + : | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + |0| + +-+ + Note that since we always merge adjacent free chunks, the chunks + adjacent to a free chunk must be in use. + + Given a pointer to a chunk (which can be derived trivially from the + payload pointer) we can, in O(1) time, find out whether the adjacent + chunks are free, and if so, unlink them from the lists that they + are on and merge them with the current chunk. + + Chunks always begin on even word boundaries, so the mem portion + (which is returned to the user) is also on an even word boundary, and + thus at least double-word aligned. + + The P (PINUSE_BIT) bit, stored in the unused low-order bit of the + chunk size (which is always a multiple of two words), is an in-use + bit for the *previous* chunk. If that bit is *clear*, then the + word before the current chunk size contains the previous chunk + size, and can be used to find the front of the previous chunk. + The very first chunk allocated always has this bit set, preventing + access to non-existent (or non-owned) memory. If pinuse is set for + any given chunk, then you CANNOT determine the size of the + previous chunk, and might even get a memory addressing fault when + trying to do so. + + The C (CINUSE_BIT) bit, stored in the unused second-lowest bit of + the chunk size redundantly records whether the current chunk is + inuse (unless the chunk is mmapped). This redundancy enables usage + checks within free and realloc, and reduces indirection when freeing + and consolidating chunks. + + Each freshly allocated chunk must have both cinuse and pinuse set. + That is, each allocated chunk borders either a previously allocated + and still in-use chunk, or the base of its memory arena. This is + ensured by making all allocations from the `lowest' part of any + found chunk. Further, no free chunk physically borders another one, + so each free chunk is known to be preceded and followed by either + inuse chunks or the ends of memory. + + Note that the `foot' of the current chunk is actually represented + as the prev_foot of the NEXT chunk. This makes it easier to + deal with alignments etc but can be very confusing when trying + to extend or adapt this code. + + The exceptions to all this are + + 1. The special chunk `top' is the top-most available chunk (i.e., + the one bordering the end of available memory). It is treated + specially. Top is never included in any bin, is used only if + no other chunk is available, and is released back to the + system if it is very large (see M_TRIM_THRESHOLD). In effect, + the top chunk is treated as larger (and thus less well + fitting) than any other available chunk. The top chunk + doesn't update its trailing size field since there is no next + contiguous chunk that would have to index off it. However, + space is still allocated for it (TOP_FOOT_SIZE) to enable + separation or merging when space is extended. + + 3. Chunks allocated via mmap, have both cinuse and pinuse bits + cleared in their head fields. Because they are allocated + one-by-one, each must carry its own prev_foot field, which is + also used to hold the offset this chunk has within its mmapped + region, which is needed to preserve alignment. Each mmapped + chunk is trailed by the first two fields of a fake next-chunk + for sake of usage checks. + +*/ + +struct malloc_chunk { + size_t prev_foot; /* Size of previous chunk (if free). */ + size_t head; /* Size and inuse bits. */ + struct malloc_chunk* fd; /* double links -- used only if free. */ + struct malloc_chunk* bk; +}; + +typedef struct malloc_chunk mchunk; +typedef struct malloc_chunk* mchunkptr; +typedef struct malloc_chunk* sbinptr; /* The type of bins of chunks */ +typedef unsigned int bindex_t; /* Described below */ +typedef unsigned int binmap_t; /* Described below */ +typedef unsigned int flag_t; /* The type of various bit flag sets */ + +/* ------------------- Chunks sizes and alignments ----------------------- */ + +#define MCHUNK_SIZE (sizeof(mchunk)) + +#if FOOTERS +#define CHUNK_OVERHEAD (TWO_SIZE_T_SIZES) +#else /* FOOTERS */ +#define CHUNK_OVERHEAD (SIZE_T_SIZE) +#endif /* FOOTERS */ + +/* MMapped chunks need a second word of overhead ... */ +#define MMAP_CHUNK_OVERHEAD (TWO_SIZE_T_SIZES) +/* ... and additional padding for fake next-chunk at foot */ +#define MMAP_FOOT_PAD (FOUR_SIZE_T_SIZES) + +/* The smallest size we can malloc is an aligned minimal chunk */ +#define MIN_CHUNK_SIZE\ + ((MCHUNK_SIZE + CHUNK_ALIGN_MASK) & ~CHUNK_ALIGN_MASK) + +/* conversion from malloc headers to user pointers, and back */ +#define chunk2mem(p) ((void*)((char*)(p) + TWO_SIZE_T_SIZES)) +#define mem2chunk(mem) ((mchunkptr)((char*)(mem) - TWO_SIZE_T_SIZES)) +/* chunk associated with aligned address A */ +#define align_as_chunk(A) (mchunkptr)((A) + align_offset(chunk2mem(A))) + +/* Bounds on request (not chunk) sizes. */ +#define MAX_REQUEST ((-MIN_CHUNK_SIZE) << 2) +#define MIN_REQUEST (MIN_CHUNK_SIZE - CHUNK_OVERHEAD - SIZE_T_ONE) + +/* pad request bytes into a usable size */ +#define pad_request(req) \ + (((req) + CHUNK_OVERHEAD + CHUNK_ALIGN_MASK) & ~CHUNK_ALIGN_MASK) + +/* pad request, checking for minimum (but not maximum) */ +#define request2size(req) \ + (((req) < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(req)) + + +/* ------------------ Operations on head and foot fields ----------------- */ + +/* + The head field of a chunk is or'ed with PINUSE_BIT when previous + adjacent chunk in use, and or'ed with CINUSE_BIT if this chunk is in + use, unless mmapped, in which case both bits are cleared. + + FLAG4_BIT is not used by this malloc, but might be useful in extensions. +*/ + +#define PINUSE_BIT (SIZE_T_ONE) +#define CINUSE_BIT (SIZE_T_TWO) +#define FLAG4_BIT (SIZE_T_FOUR) +#define INUSE_BITS (PINUSE_BIT|CINUSE_BIT) +#define FLAG_BITS (PINUSE_BIT|CINUSE_BIT|FLAG4_BIT) + +/* Head value for fenceposts */ +#define FENCEPOST_HEAD (INUSE_BITS|SIZE_T_SIZE) + +/* extraction of fields from head words */ +#define cinuse(p) ((p)->head & CINUSE_BIT) +#define pinuse(p) ((p)->head & PINUSE_BIT) +#define flag4inuse(p) ((p)->head & FLAG4_BIT) +#define is_inuse(p) (((p)->head & INUSE_BITS) != PINUSE_BIT) +#define is_mmapped(p) (((p)->head & INUSE_BITS) == 0) + +#define chunksize(p) ((p)->head & ~(FLAG_BITS)) + +#define clear_pinuse(p) ((p)->head &= ~PINUSE_BIT) +#define set_flag4(p) ((p)->head |= FLAG4_BIT) +#define clear_flag4(p) ((p)->head &= ~FLAG4_BIT) + +/* Treat space at ptr +/- offset as a chunk */ +#define chunk_plus_offset(p, s) ((mchunkptr)(((char*)(p)) + (s))) +#define chunk_minus_offset(p, s) ((mchunkptr)(((char*)(p)) - (s))) + +/* Ptr to next or previous physical malloc_chunk. */ +#define next_chunk(p) ((mchunkptr)( ((char*)(p)) + ((p)->head & ~FLAG_BITS))) +#define prev_chunk(p) ((mchunkptr)( ((char*)(p)) - ((p)->prev_foot) )) + +/* extract next chunk's pinuse bit */ +#define next_pinuse(p) ((next_chunk(p)->head) & PINUSE_BIT) + +/* Get/set size at footer */ +#define get_foot(p, s) (((mchunkptr)((char*)(p) + (s)))->prev_foot) +#define set_foot(p, s) (((mchunkptr)((char*)(p) + (s)))->prev_foot = (s)) + +/* Set size, pinuse bit, and foot */ +#define set_size_and_pinuse_of_free_chunk(p, s)\ + ((p)->head = (s|PINUSE_BIT), set_foot(p, s)) + +/* Set size, pinuse bit, foot, and clear next pinuse */ +#define set_free_with_pinuse(p, s, n)\ + (clear_pinuse(n), set_size_and_pinuse_of_free_chunk(p, s)) + +/* Get the internal overhead associated with chunk p */ +#define overhead_for(p)\ + (is_mmapped(p)? MMAP_CHUNK_OVERHEAD : CHUNK_OVERHEAD) + +/* Return true if malloced space is not necessarily cleared */ +#if MMAP_CLEARS +#define calloc_must_clear(p) (!is_mmapped(p)) +#else /* MMAP_CLEARS */ +#define calloc_must_clear(p) (1) +#endif /* MMAP_CLEARS */ + +/* ---------------------- Overlaid data structures ----------------------- */ + +/* + When chunks are not in use, they are treated as nodes of either + lists or trees. + + "Small" chunks are stored in circular doubly-linked lists, and look + like this: + + chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Size of previous chunk | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + `head:' | Size of chunk, in bytes |P| + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Forward pointer to next chunk in list | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Back pointer to previous chunk in list | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Unused space (may be 0 bytes long) . + . . + . | +nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + `foot:' | Size of chunk, in bytes | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + + Larger chunks are kept in a form of bitwise digital trees (aka + tries) keyed on chunksizes. Because malloc_tree_chunks are only for + free chunks greater than 256 bytes, their size doesn't impose any + constraints on user chunk sizes. Each node looks like: + + chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Size of previous chunk | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + `head:' | Size of chunk, in bytes |P| + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Forward pointer to next chunk of same size | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Back pointer to previous chunk of same size | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Pointer to left child (child[0]) | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Pointer to right child (child[1]) | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Pointer to parent | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | bin index of this chunk | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Unused space . + . | +nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + `foot:' | Size of chunk, in bytes | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + + Each tree holding treenodes is a tree of unique chunk sizes. Chunks + of the same size are arranged in a circularly-linked list, with only + the oldest chunk (the next to be used, in our FIFO ordering) + actually in the tree. (Tree members are distinguished by a non-null + parent pointer.) If a chunk with the same size an an existing node + is inserted, it is linked off the existing node using pointers that + work in the same way as fd/bk pointers of small chunks. + + Each tree contains a power of 2 sized range of chunk sizes (the + smallest is 0x100 <= x < 0x180), which is is divided in half at each + tree level, with the chunks in the smaller half of the range (0x100 + <= x < 0x140 for the top nose) in the left subtree and the larger + half (0x140 <= x < 0x180) in the right subtree. This is, of course, + done by inspecting individual bits. + + Using these rules, each node's left subtree contains all smaller + sizes than its right subtree. However, the node at the root of each + subtree has no particular ordering relationship to either. (The + dividing line between the subtree sizes is based on trie relation.) + If we remove the last chunk of a given size from the interior of the + tree, we need to replace it with a leaf node. The tree ordering + rules permit a node to be replaced by any leaf below it. + + The smallest chunk in a tree (a common operation in a best-fit + allocator) can be found by walking a path to the leftmost leaf in + the tree. Unlike a usual binary tree, where we follow left child + pointers until we reach a null, here we follow the right child + pointer any time the left one is null, until we reach a leaf with + both child pointers null. The smallest chunk in the tree will be + somewhere along that path. + + The worst case number of steps to add, find, or remove a node is + bounded by the number of bits differentiating chunks within + bins. Under current bin calculations, this ranges from 6 up to 21 + (for 32 bit sizes) or up to 53 (for 64 bit sizes). The typical case + is of course much better. +*/ + +struct malloc_tree_chunk { + /* The first four fields must be compatible with malloc_chunk */ + size_t prev_foot; + size_t head; + struct malloc_tree_chunk* fd; + struct malloc_tree_chunk* bk; + + struct malloc_tree_chunk* child[2]; + struct malloc_tree_chunk* parent; + bindex_t index; +}; + +typedef struct malloc_tree_chunk tchunk; +typedef struct malloc_tree_chunk* tchunkptr; +typedef struct malloc_tree_chunk* tbinptr; /* The type of bins of trees */ + +/* A little helper macro for trees */ +#define leftmost_child(t) ((t)->child[0] != 0? (t)->child[0] : (t)->child[1]) + +/* ----------------------------- Segments -------------------------------- */ + +/* + Each malloc space may include non-contiguous segments, held in a + list headed by an embedded malloc_segment record representing the + top-most space. Segments also include flags holding properties of + the space. Large chunks that are directly allocated by mmap are not + included in this list. They are instead independently created and + destroyed without otherwise keeping track of them. + + Segment management mainly comes into play for spaces allocated by + MMAP. Any call to MMAP might or might not return memory that is + adjacent to an existing segment. MORECORE normally contiguously + extends the current space, so this space is almost always adjacent, + which is simpler and faster to deal with. (This is why MORECORE is + used preferentially to MMAP when both are available -- see + sys_alloc.) When allocating using MMAP, we don't use any of the + hinting mechanisms (inconsistently) supported in various + implementations of unix mmap, or distinguish reserving from + committing memory. Instead, we just ask for space, and exploit + contiguity when we get it. It is probably possible to do + better than this on some systems, but no general scheme seems + to be significantly better. + + Management entails a simpler variant of the consolidation scheme + used for chunks to reduce fragmentation -- new adjacent memory is + normally prepended or appended to an existing segment. However, + there are limitations compared to chunk consolidation that mostly + reflect the fact that segment processing is relatively infrequent + (occurring only when getting memory from system) and that we + don't expect to have huge numbers of segments: + + * Segments are not indexed, so traversal requires linear scans. (It + would be possible to index these, but is not worth the extra + overhead and complexity for most programs on most platforms.) + * New segments are only appended to old ones when holding top-most + memory; if they cannot be prepended to others, they are held in + different segments. + + Except for the top-most segment of an mstate, each segment record + is kept at the tail of its segment. Segments are added by pushing + segment records onto the list headed by &mstate.seg for the + containing mstate. + + Segment flags control allocation/merge/deallocation policies: + * If EXTERN_BIT set, then we did not allocate this segment, + and so should not try to deallocate or merge with others. + (This currently holds only for the initial segment passed + into create_mspace_with_base.) + * If USE_MMAP_BIT set, the segment may be merged with + other surrounding mmapped segments and trimmed/de-allocated + using munmap. + * If neither bit is set, then the segment was obtained using + MORECORE so can be merged with surrounding MORECORE'd segments + and deallocated/trimmed using MORECORE with negative arguments. +*/ + +struct malloc_segment { + char* base; /* base address */ + size_t size; /* allocated size */ + struct malloc_segment* next; /* ptr to next segment */ + flag_t sflags; /* mmap and extern flag */ +}; + +#define is_mmapped_segment(S) ((S)->sflags & USE_MMAP_BIT) +#define is_extern_segment(S) ((S)->sflags & EXTERN_BIT) + +typedef struct malloc_segment msegment; +typedef struct malloc_segment* msegmentptr; + +/* ---------------------------- malloc_state ----------------------------- */ + +/* + A malloc_state holds all of the bookkeeping for a space. + The main fields are: + + Top + The topmost chunk of the currently active segment. Its size is + cached in topsize. The actual size of topmost space is + topsize+TOP_FOOT_SIZE, which includes space reserved for adding + fenceposts and segment records if necessary when getting more + space from the system. The size at which to autotrim top is + cached from mparams in trim_check, except that it is disabled if + an autotrim fails. + + Designated victim (dv) + This is the preferred chunk for servicing small requests that + don't have exact fits. It is normally the chunk split off most + recently to service another small request. Its size is cached in + dvsize. The link fields of this chunk are not maintained since it + is not kept in a bin. + + SmallBins + An array of bin headers for free chunks. These bins hold chunks + with sizes less than MIN_LARGE_SIZE bytes. Each bin contains + chunks of all the same size, spaced 8 bytes apart. To simplify + use in double-linked lists, each bin header acts as a malloc_chunk + pointing to the real first node, if it exists (else pointing to + itself). This avoids special-casing for headers. But to avoid + waste, we allocate only the fd/bk pointers of bins, and then use + repositioning tricks to treat these as the fields of a chunk. + + TreeBins + Treebins are pointers to the roots of trees holding a range of + sizes. There are 2 equally spaced treebins for each power of two + from TREE_SHIFT to TREE_SHIFT+16. The last bin holds anything + larger. + + Bin maps + There is one bit map for small bins ("smallmap") and one for + treebins ("treemap). Each bin sets its bit when non-empty, and + clears the bit when empty. Bit operations are then used to avoid + bin-by-bin searching -- nearly all "search" is done without ever + looking at bins that won't be selected. The bit maps + conservatively use 32 bits per map word, even if on 64bit system. + For a good description of some of the bit-based techniques used + here, see Henry S. Warren Jr's book "Hacker's Delight" (and + supplement at http://hackersdelight.org/). Many of these are + intended to reduce the branchiness of paths through malloc etc, as + well as to reduce the number of memory locations read or written. + + Segments + A list of segments headed by an embedded malloc_segment record + representing the initial space. + + Address check support + The least_addr field is the least address ever obtained from + MORECORE or MMAP. Attempted frees and reallocs of any address less + than this are trapped (unless INSECURE is defined). + + Magic tag + A cross-check field that should always hold same value as mparams.magic. + + Max allowed footprint + The maximum allowed bytes to allocate from system (zero means no limit) + + Flags + Bits recording whether to use MMAP, locks, or contiguous MORECORE + + Statistics + Each space keeps track of current and maximum system memory + obtained via MORECORE or MMAP. + + Trim support + Fields holding the amount of unused topmost memory that should trigger + trimming, and a counter to force periodic scanning to release unused + non-topmost segments. + + Locking + If USE_LOCKS is defined, the "mutex" lock is acquired and released + around every public call using this mspace. + + Extension support + A void* pointer and a size_t field that can be used to help implement + extensions to this malloc. +*/ + +/* Bin types, widths and sizes */ +#define NSMALLBINS (32U) +#define NTREEBINS (32U) +#define SMALLBIN_SHIFT (3U) +#define SMALLBIN_WIDTH (SIZE_T_ONE << SMALLBIN_SHIFT) +#define TREEBIN_SHIFT (8U) +#define MIN_LARGE_SIZE (SIZE_T_ONE << TREEBIN_SHIFT) +#define MAX_SMALL_SIZE (MIN_LARGE_SIZE - SIZE_T_ONE) +#define MAX_SMALL_REQUEST (MAX_SMALL_SIZE - CHUNK_ALIGN_MASK - CHUNK_OVERHEAD) + +struct malloc_state { + binmap_t smallmap; + binmap_t treemap; + size_t dvsize; + size_t topsize; + char* least_addr; + mchunkptr dv; + mchunkptr top; + size_t trim_check; + size_t release_checks; + size_t magic; + mchunkptr smallbins[(NSMALLBINS+1)*2]; + tbinptr treebins[NTREEBINS]; + size_t footprint; + size_t max_footprint; + size_t footprint_limit; /* zero means no limit */ + flag_t mflags; +#if USE_LOCKS + MLOCK_T mutex; /* locate lock among fields that rarely change */ +#endif /* USE_LOCKS */ + msegment seg; + void* extp; /* Unused but available for extensions */ + size_t exts; +}; + +typedef struct malloc_state* mstate; + +/* ------------- Global malloc_state and malloc_params ------------------- */ + +/* + malloc_params holds global properties, including those that can be + dynamically set using mallopt. There is a single instance, mparams, + initialized in init_mparams. Note that the non-zeroness of "magic" + also serves as an initialization flag. +*/ + +struct malloc_params { + size_t magic; + size_t page_size; + size_t granularity; + size_t mmap_threshold; + size_t trim_threshold; + flag_t default_mflags; +}; + +static struct malloc_params mparams; + +/* Ensure mparams initialized */ +#define ensure_initialization() (void)(mparams.magic != 0 || init_mparams()) + +#if !ONLY_MSPACES + +/* The global malloc_state used for all non-"mspace" calls */ +static struct malloc_state _gm_; +#define gm (&_gm_) +#define is_global(M) ((M) == &_gm_) + +#endif /* !ONLY_MSPACES */ + +#define is_initialized(M) ((M)->top != 0) + +/* -------------------------- system alloc setup ------------------------- */ + +/* Operations on mflags */ + +#define use_lock(M) ((M)->mflags & USE_LOCK_BIT) +#define enable_lock(M) ((M)->mflags |= USE_LOCK_BIT) +#if USE_LOCKS +#define disable_lock(M) ((M)->mflags &= ~USE_LOCK_BIT) +#else +#define disable_lock(M) +#endif + +#define use_mmap(M) ((M)->mflags & USE_MMAP_BIT) +#define enable_mmap(M) ((M)->mflags |= USE_MMAP_BIT) +#if HAVE_MMAP +#define disable_mmap(M) ((M)->mflags &= ~USE_MMAP_BIT) +#else +#define disable_mmap(M) +#endif + +#define use_noncontiguous(M) ((M)->mflags & USE_NONCONTIGUOUS_BIT) +#define disable_contiguous(M) ((M)->mflags |= USE_NONCONTIGUOUS_BIT) + +#define set_lock(M,L)\ + ((M)->mflags = (L)?\ + ((M)->mflags | USE_LOCK_BIT) :\ + ((M)->mflags & ~USE_LOCK_BIT)) + +/* page-align a size */ +#define page_align(S)\ + (((S) + (mparams.page_size - SIZE_T_ONE)) & ~(mparams.page_size - SIZE_T_ONE)) + +/* granularity-align a size */ +#define granularity_align(S)\ + (((S) + (mparams.granularity - SIZE_T_ONE))\ + & ~(mparams.granularity - SIZE_T_ONE)) + + +/* For mmap, use granularity alignment on windows, else page-align */ +#ifdef WIN32 +#define mmap_align(S) granularity_align(S) +#else +#define mmap_align(S) page_align(S) +#endif + +/* For sys_alloc, enough padding to ensure can malloc request on success */ +#define SYS_ALLOC_PADDING (TOP_FOOT_SIZE + MALLOC_ALIGNMENT) + +#define is_page_aligned(S)\ + (((size_t)(S) & (mparams.page_size - SIZE_T_ONE)) == 0) +#define is_granularity_aligned(S)\ + (((size_t)(S) & (mparams.granularity - SIZE_T_ONE)) == 0) + +/* True if segment S holds address A */ +#define segment_holds(S, A)\ + ((char*)(A) >= S->base && (char*)(A) < S->base + S->size) + +/* Return segment holding given address */ +static msegmentptr segment_holding(mstate m, char* addr) { + msegmentptr sp = &m->seg; + for (;;) { + if (addr >= sp->base && addr < sp->base + sp->size) + return sp; + if ((sp = sp->next) == 0) + return 0; + } +} + +/* Return true if segment contains a segment link */ +static int has_segment_link(mstate m, msegmentptr ss) { + msegmentptr sp = &m->seg; + for (;;) { + if ((char*)sp >= ss->base && (char*)sp < ss->base + ss->size) + return 1; + if ((sp = sp->next) == 0) + return 0; + } +} + +#ifndef MORECORE_CANNOT_TRIM +#define should_trim(M,s) ((s) > (M)->trim_check) +#else /* MORECORE_CANNOT_TRIM */ +#define should_trim(M,s) (0) +#endif /* MORECORE_CANNOT_TRIM */ + +/* + TOP_FOOT_SIZE is padding at the end of a segment, including space + that may be needed to place segment records and fenceposts when new + noncontiguous segments are added. +*/ +#define TOP_FOOT_SIZE\ + (align_offset(chunk2mem(0))+pad_request(sizeof(struct malloc_segment))+MIN_CHUNK_SIZE) + + +/* ------------------------------- Hooks -------------------------------- */ + +/* + PREACTION should be defined to return 0 on success, and nonzero on + failure. If you are not using locking, you can redefine these to do + anything you like. +*/ + +#if USE_LOCKS +#define PREACTION(M) ((use_lock(M))? ACQUIRE_LOCK(&(M)->mutex) : 0) +#define POSTACTION(M) { if (use_lock(M)) RELEASE_LOCK(&(M)->mutex); } +#else /* USE_LOCKS */ + +#ifndef PREACTION +#define PREACTION(M) (0) +#endif /* PREACTION */ + +#ifndef POSTACTION +#define POSTACTION(M) +#endif /* POSTACTION */ + +#endif /* USE_LOCKS */ + +/* + CORRUPTION_ERROR_ACTION is triggered upon detected bad addresses. + USAGE_ERROR_ACTION is triggered on detected bad frees and + reallocs. The argument p is an address that might have triggered the + fault. It is ignored by the two predefined actions, but might be + useful in custom actions that try to help diagnose errors. +*/ + +#if PROCEED_ON_ERROR + +/* A count of the number of corruption errors causing resets */ +int malloc_corruption_error_count; + +/* default corruption action */ +static void reset_on_error(mstate m); + +#define CORRUPTION_ERROR_ACTION(m) reset_on_error(m) +#define USAGE_ERROR_ACTION(m, p) + +#else /* PROCEED_ON_ERROR */ + +#ifndef CORRUPTION_ERROR_ACTION +#define CORRUPTION_ERROR_ACTION(m) ABORT +#endif /* CORRUPTION_ERROR_ACTION */ + +#ifndef USAGE_ERROR_ACTION +#define USAGE_ERROR_ACTION(m,p) ABORT +#endif /* USAGE_ERROR_ACTION */ + +#endif /* PROCEED_ON_ERROR */ + + +/* -------------------------- Debugging setup ---------------------------- */ + +#if ! DEBUG + +#define check_free_chunk(M,P) +#define check_inuse_chunk(M,P) +#define check_malloced_chunk(M,P,N) +#define check_mmapped_chunk(M,P) +#define check_malloc_state(M) +#define check_top_chunk(M,P) + +#else /* DEBUG */ +#define check_free_chunk(M,P) do_check_free_chunk(M,P) +#define check_inuse_chunk(M,P) do_check_inuse_chunk(M,P) +#define check_top_chunk(M,P) do_check_top_chunk(M,P) +#define check_malloced_chunk(M,P,N) do_check_malloced_chunk(M,P,N) +#define check_mmapped_chunk(M,P) do_check_mmapped_chunk(M,P) +#define check_malloc_state(M) do_check_malloc_state(M) + +static void do_check_any_chunk(mstate m, mchunkptr p); +static void do_check_top_chunk(mstate m, mchunkptr p); +static void do_check_mmapped_chunk(mstate m, mchunkptr p); +static void do_check_inuse_chunk(mstate m, mchunkptr p); +static void do_check_free_chunk(mstate m, mchunkptr p); +static void do_check_malloced_chunk(mstate m, void* mem, size_t s); +static void do_check_tree(mstate m, tchunkptr t); +static void do_check_treebin(mstate m, bindex_t i); +static void do_check_smallbin(mstate m, bindex_t i); +static void do_check_malloc_state(mstate m); +static int bin_find(mstate m, mchunkptr x); +static size_t traverse_and_check(mstate m); +#endif /* DEBUG */ + +/* ---------------------------- Indexing Bins ---------------------------- */ + +#define is_small(s) (((s) >> SMALLBIN_SHIFT) < NSMALLBINS) +#define small_index(s) (bindex_t)((s) >> SMALLBIN_SHIFT) +#define small_index2size(i) ((i) << SMALLBIN_SHIFT) +#define MIN_SMALL_INDEX (small_index(MIN_CHUNK_SIZE)) + +/* addressing by index. See above about smallbin repositioning */ +#define smallbin_at(M, i) ((sbinptr)((char*)&((M)->smallbins[(i)<<1]))) +#define treebin_at(M,i) (&((M)->treebins[i])) + +/* assign tree index for size S to variable I. Use x86 asm if possible */ +#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__)) +#define compute_tree_index(S, I)\ +{\ + unsigned int X = S >> TREEBIN_SHIFT;\ + if (X == 0)\ + I = 0;\ + else if (X > 0xFFFF)\ + I = NTREEBINS-1;\ + else {\ + unsigned int K = (unsigned) sizeof(X)*__CHAR_BIT__ - 1 - (unsigned) __builtin_clz(X); \ + I = (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\ + }\ +} + +#elif defined (__INTEL_COMPILER) +#define compute_tree_index(S, I)\ +{\ + size_t X = S >> TREEBIN_SHIFT;\ + if (X == 0)\ + I = 0;\ + else if (X > 0xFFFF)\ + I = NTREEBINS-1;\ + else {\ + unsigned int K = _bit_scan_reverse (X); \ + I = (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\ + }\ +} + +#elif defined(_MSC_VER) && _MSC_VER>=1300 +#define compute_tree_index(S, I)\ +{\ + size_t X = S >> TREEBIN_SHIFT;\ + if (X == 0)\ + I = 0;\ + else if (X > 0xFFFF)\ + I = NTREEBINS-1;\ + else {\ + unsigned int K;\ + _BitScanReverse((DWORD *) &K, (DWORD) X);\ + I = (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\ + }\ +} + +#else /* GNUC */ +#define compute_tree_index(S, I)\ +{\ + size_t X = S >> TREEBIN_SHIFT;\ + if (X == 0)\ + I = 0;\ + else if (X > 0xFFFF)\ + I = NTREEBINS-1;\ + else {\ + unsigned int Y = (unsigned int)X;\ + unsigned int N = ((Y - 0x100) >> 16) & 8;\ + unsigned int K = (((Y <<= N) - 0x1000) >> 16) & 4;\ + N += K;\ + N += K = (((Y <<= K) - 0x4000) >> 16) & 2;\ + K = 14 - N + ((Y <<= K) >> 15);\ + I = (K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1));\ + }\ +} +#endif /* GNUC */ + +/* Bit representing maximum resolved size in a treebin at i */ +#define bit_for_tree_index(i) \ + (i == NTREEBINS-1)? (SIZE_T_BITSIZE-1) : (((i) >> 1) + TREEBIN_SHIFT - 2) + +/* Shift placing maximum resolved bit in a treebin at i as sign bit */ +#define leftshift_for_tree_index(i) \ + ((i == NTREEBINS-1)? 0 : \ + ((SIZE_T_BITSIZE-SIZE_T_ONE) - (((i) >> 1) + TREEBIN_SHIFT - 2))) + +/* The size of the smallest chunk held in bin with index i */ +#define minsize_for_tree_index(i) \ + ((SIZE_T_ONE << (((i) >> 1) + TREEBIN_SHIFT)) | \ + (((size_t)((i) & SIZE_T_ONE)) << (((i) >> 1) + TREEBIN_SHIFT - 1))) + + +/* ------------------------ Operations on bin maps ----------------------- */ + +/* bit corresponding to given index */ +#define idx2bit(i) ((binmap_t)(1) << (i)) + +/* Mark/Clear bits with given index */ +#define mark_smallmap(M,i) ((M)->smallmap |= idx2bit(i)) +#define clear_smallmap(M,i) ((M)->smallmap &= ~idx2bit(i)) +#define smallmap_is_marked(M,i) ((M)->smallmap & idx2bit(i)) + +#define mark_treemap(M,i) ((M)->treemap |= idx2bit(i)) +#define clear_treemap(M,i) ((M)->treemap &= ~idx2bit(i)) +#define treemap_is_marked(M,i) ((M)->treemap & idx2bit(i)) + +/* isolate the least set bit of a bitmap */ +#define least_bit(x) ((x) & -(x)) + +/* mask with all bits to left of least bit of x on */ +#define left_bits(x) ((x<<1) | -(x<<1)) + +/* mask with all bits to left of or equal to least bit of x on */ +#define same_or_left_bits(x) ((x) | -(x)) + +/* index corresponding to given bit. Use x86 asm if possible */ + +#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__)) +#define compute_bit2idx(X, I)\ +{\ + unsigned int J;\ + J = __builtin_ctz(X); \ + I = (bindex_t)J;\ +} + +#elif defined (__INTEL_COMPILER) +#define compute_bit2idx(X, I)\ +{\ + unsigned int J;\ + J = _bit_scan_forward (X); \ + I = (bindex_t)J;\ +} + +#elif defined(_MSC_VER) && _MSC_VER>=1300 +#define compute_bit2idx(X, I)\ +{\ + unsigned int J;\ + _BitScanForward((DWORD *) &J, X);\ + I = (bindex_t)J;\ +} + +#elif USE_BUILTIN_FFS +#define compute_bit2idx(X, I) I = ffs(X)-1 + +#else +#define compute_bit2idx(X, I)\ +{\ + unsigned int Y = X - 1;\ + unsigned int K = Y >> (16-4) & 16;\ + unsigned int N = K; Y >>= K;\ + N += K = Y >> (8-3) & 8; Y >>= K;\ + N += K = Y >> (4-2) & 4; Y >>= K;\ + N += K = Y >> (2-1) & 2; Y >>= K;\ + N += K = Y >> (1-0) & 1; Y >>= K;\ + I = (bindex_t)(N + Y);\ +} +#endif /* GNUC */ + + +/* ----------------------- Runtime Check Support ------------------------- */ + +/* + For security, the main invariant is that malloc/free/etc never + writes to a static address other than malloc_state, unless static + malloc_state itself has been corrupted, which cannot occur via + malloc (because of these checks). In essence this means that we + believe all pointers, sizes, maps etc held in malloc_state, but + check all of those linked or offsetted from other embedded data + structures. These checks are interspersed with main code in a way + that tends to minimize their run-time cost. + + When FOOTERS is defined, in addition to range checking, we also + verify footer fields of inuse chunks, which can be used guarantee + that the mstate controlling malloc/free is intact. This is a + streamlined version of the approach described by William Robertson + et al in "Run-time Detection of Heap-based Overflows" LISA'03 + http://www.usenix.org/events/lisa03/tech/robertson.html The footer + of an inuse chunk holds the xor of its mstate and a random seed, + that is checked upon calls to free() and realloc(). This is + (probabalistically) unguessable from outside the program, but can be + computed by any code successfully malloc'ing any chunk, so does not + itself provide protection against code that has already broken + security through some other means. Unlike Robertson et al, we + always dynamically check addresses of all offset chunks (previous, + next, etc). This turns out to be cheaper than relying on hashes. +*/ + +#if !INSECURE +/* Check if address a is at least as high as any from MORECORE or MMAP */ +#define ok_address(M, a) ((char*)(a) >= (M)->least_addr) +/* Check if address of next chunk n is higher than base chunk p */ +#define ok_next(p, n) ((char*)(p) < (char*)(n)) +/* Check if p has inuse status */ +#define ok_inuse(p) is_inuse(p) +/* Check if p has its pinuse bit on */ +#define ok_pinuse(p) pinuse(p) + +#else /* !INSECURE */ +#define ok_address(M, a) (1) +#define ok_next(b, n) (1) +#define ok_inuse(p) (1) +#define ok_pinuse(p) (1) +#endif /* !INSECURE */ + +#if (FOOTERS && !INSECURE) +/* Check if (alleged) mstate m has expected magic field */ +#define ok_magic(M) ((M)->magic == mparams.magic) +#else /* (FOOTERS && !INSECURE) */ +#define ok_magic(M) (1) +#endif /* (FOOTERS && !INSECURE) */ + +/* In gcc, use __builtin_expect to minimize impact of checks */ +#if !INSECURE +#if defined(__GNUC__) && __GNUC__ >= 3 +#define RTCHECK(e) __builtin_expect(e, 1) +#else /* GNUC */ +#define RTCHECK(e) (e) +#endif /* GNUC */ +#else /* !INSECURE */ +#define RTCHECK(e) (1) +#endif /* !INSECURE */ + +/* macros to set up inuse chunks with or without footers */ + +#if !FOOTERS + +#define mark_inuse_foot(M,p,s) + +/* Macros for setting head/foot of non-mmapped chunks */ + +/* Set cinuse bit and pinuse bit of next chunk */ +#define set_inuse(M,p,s)\ + ((p)->head = (((p)->head & PINUSE_BIT)|s|CINUSE_BIT),\ + ((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT) + +/* Set cinuse and pinuse of this chunk and pinuse of next chunk */ +#define set_inuse_and_pinuse(M,p,s)\ + ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\ + ((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT) + +/* Set size, cinuse and pinuse bit of this chunk */ +#define set_size_and_pinuse_of_inuse_chunk(M, p, s)\ + ((p)->head = (s|PINUSE_BIT|CINUSE_BIT)) + +#else /* FOOTERS */ + +/* Set foot of inuse chunk to be xor of mstate and seed */ +#define mark_inuse_foot(M,p,s)\ + (((mchunkptr)((char*)(p) + (s)))->prev_foot = ((size_t)(M) ^ mparams.magic)) + +#define get_mstate_for(p)\ + ((mstate)(((mchunkptr)((char*)(p) +\ + (chunksize(p))))->prev_foot ^ mparams.magic)) + +#define set_inuse(M,p,s)\ + ((p)->head = (((p)->head & PINUSE_BIT)|s|CINUSE_BIT),\ + (((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT), \ + mark_inuse_foot(M,p,s)) + +#define set_inuse_and_pinuse(M,p,s)\ + ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\ + (((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT),\ + mark_inuse_foot(M,p,s)) + +#define set_size_and_pinuse_of_inuse_chunk(M, p, s)\ + ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\ + mark_inuse_foot(M, p, s)) + +#endif /* !FOOTERS */ + +/* ---------------------------- setting mparams -------------------------- */ + +#if LOCK_AT_FORK +static void pre_fork(void) { ACQUIRE_LOCK(&(gm)->mutex); } +static void post_fork_parent(void) { RELEASE_LOCK(&(gm)->mutex); } +static void post_fork_child(void) { INITIAL_LOCK(&(gm)->mutex); } +#endif /* LOCK_AT_FORK */ + +/* Initialize mparams */ +static int init_mparams(void) { +#ifdef NEED_GLOBAL_LOCK_INIT + if (malloc_global_mutex_status <= 0) + init_malloc_global_mutex(); +#endif + + ACQUIRE_MALLOC_GLOBAL_LOCK(); + if (mparams.magic == 0) { + size_t magic; + size_t psize; + size_t gsize; + +#ifndef WIN32 + psize = malloc_getpagesize; + gsize = ((DEFAULT_GRANULARITY != 0)? DEFAULT_GRANULARITY : psize); +#else /* WIN32 */ + { + SYSTEM_INFO system_info; + GetSystemInfo(&system_info); + psize = system_info.dwPageSize; + gsize = ((DEFAULT_GRANULARITY != 0)? + DEFAULT_GRANULARITY : system_info.dwAllocationGranularity); + } +#endif /* WIN32 */ + + /* Sanity-check configuration: + size_t must be unsigned and as wide as pointer type. + ints must be at least 4 bytes. + alignment must be at least 8. + Alignment, min chunk size, and page size must all be powers of 2. + */ + if ((sizeof(size_t) != sizeof(char*)) || + (MAX_SIZE_T < MIN_CHUNK_SIZE) || + (sizeof(int) < 4) || + (MALLOC_ALIGNMENT < (size_t)8U) || + ((MALLOC_ALIGNMENT & (MALLOC_ALIGNMENT-SIZE_T_ONE)) != 0) || + ((MCHUNK_SIZE & (MCHUNK_SIZE-SIZE_T_ONE)) != 0) || + ((gsize & (gsize-SIZE_T_ONE)) != 0) || + ((psize & (psize-SIZE_T_ONE)) != 0)) + ABORT; + mparams.granularity = gsize; + mparams.page_size = psize; + mparams.mmap_threshold = DEFAULT_MMAP_THRESHOLD; + mparams.trim_threshold = DEFAULT_TRIM_THRESHOLD; +#if MORECORE_CONTIGUOUS + mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT; +#else /* MORECORE_CONTIGUOUS */ + mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT|USE_NONCONTIGUOUS_BIT; +#endif /* MORECORE_CONTIGUOUS */ + +#if !ONLY_MSPACES + /* Set up lock for main malloc area */ + gm->mflags = mparams.default_mflags; + (void)INITIAL_LOCK(&gm->mutex); +#endif +#if LOCK_AT_FORK + pthread_atfork(&pre_fork, &post_fork_parent, &post_fork_child); +#endif + + { +#if USE_DEV_RANDOM + int fd; + unsigned char buf[sizeof(size_t)]; + /* Try to use /dev/urandom, else fall back on using time */ + if ((fd = open("/dev/urandom", O_RDONLY)) >= 0 && + read(fd, buf, sizeof(buf)) == sizeof(buf)) { + magic = *((size_t *) buf); + close(fd); + } + else +#endif /* USE_DEV_RANDOM */ +#ifdef WIN32 + magic = (size_t)(GetTickCount() ^ (size_t)0x55555555U); +#elif defined(LACKS_TIME_H) + magic = (size_t)&magic ^ (size_t)0x55555555U; +#else + magic = (size_t)(time(0) ^ (size_t)0x55555555U); +#endif + magic |= (size_t)8U; /* ensure nonzero */ + magic &= ~(size_t)7U; /* improve chances of fault for bad values */ + /* Until memory modes commonly available, use volatile-write */ + (*(volatile size_t *)(&(mparams.magic))) = magic; + } + } + + RELEASE_MALLOC_GLOBAL_LOCK(); + return 1; +} + +/* support for mallopt */ +static int change_mparam(int param_number, int value) { + size_t val; + ensure_initialization(); + val = (value == -1)? MAX_SIZE_T : (size_t)value; + switch(param_number) { + case M_TRIM_THRESHOLD: + mparams.trim_threshold = val; + return 1; + case M_GRANULARITY: + if (val >= mparams.page_size && ((val & (val-1)) == 0)) { + mparams.granularity = val; + return 1; + } + else + return 0; + case M_MMAP_THRESHOLD: + mparams.mmap_threshold = val; + return 1; + default: + return 0; + } +} + +#if DEBUG +/* ------------------------- Debugging Support --------------------------- */ + +/* Check properties of any chunk, whether free, inuse, mmapped etc */ +static void do_check_any_chunk(mstate m, mchunkptr p) { + assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD)); + assert(ok_address(m, p)); +} + +/* Check properties of top chunk */ +static void do_check_top_chunk(mstate m, mchunkptr p) { + msegmentptr sp = segment_holding(m, (char*)p); + size_t sz = p->head & ~INUSE_BITS; /* third-lowest bit can be set! */ + assert(sp != 0); + assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD)); + assert(ok_address(m, p)); + assert(sz == m->topsize); + assert(sz > 0); + assert(sz == ((sp->base + sp->size) - (char*)p) - TOP_FOOT_SIZE); + assert(pinuse(p)); + assert(!pinuse(chunk_plus_offset(p, sz))); +} + +/* Check properties of (inuse) mmapped chunks */ +static void do_check_mmapped_chunk(mstate m, mchunkptr p) { + size_t sz = chunksize(p); + size_t len = (sz + (p->prev_foot) + MMAP_FOOT_PAD); + assert(is_mmapped(p)); + assert(use_mmap(m)); + assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD)); + assert(ok_address(m, p)); + assert(!is_small(sz)); + assert((len & (mparams.page_size-SIZE_T_ONE)) == 0); + assert(chunk_plus_offset(p, sz)->head == FENCEPOST_HEAD); + assert(chunk_plus_offset(p, sz+SIZE_T_SIZE)->head == 0); +} + +/* Check properties of inuse chunks */ +static void do_check_inuse_chunk(mstate m, mchunkptr p) { + do_check_any_chunk(m, p); + assert(is_inuse(p)); + assert(next_pinuse(p)); + /* If not pinuse and not mmapped, previous chunk has OK offset */ + assert(is_mmapped(p) || pinuse(p) || next_chunk(prev_chunk(p)) == p); + if (is_mmapped(p)) + do_check_mmapped_chunk(m, p); +} + +/* Check properties of free chunks */ +static void do_check_free_chunk(mstate m, mchunkptr p) { + size_t sz = chunksize(p); + mchunkptr next = chunk_plus_offset(p, sz); + do_check_any_chunk(m, p); + assert(!is_inuse(p)); + assert(!next_pinuse(p)); + assert (!is_mmapped(p)); + if (p != m->dv && p != m->top) { + if (sz >= MIN_CHUNK_SIZE) { + assert((sz & CHUNK_ALIGN_MASK) == 0); + assert(is_aligned(chunk2mem(p))); + assert(next->prev_foot == sz); + assert(pinuse(p)); + assert (next == m->top || is_inuse(next)); + assert(p->fd->bk == p); + assert(p->bk->fd == p); + } + else /* markers are always of size SIZE_T_SIZE */ + assert(sz == SIZE_T_SIZE); + } +} + +/* Check properties of malloced chunks at the point they are malloced */ +static void do_check_malloced_chunk(mstate m, void* mem, size_t s) { + if (mem != 0) { + mchunkptr p = mem2chunk(mem); + size_t sz = p->head & ~INUSE_BITS; + do_check_inuse_chunk(m, p); + assert((sz & CHUNK_ALIGN_MASK) == 0); + assert(sz >= MIN_CHUNK_SIZE); + assert(sz >= s); + /* unless mmapped, size is less than MIN_CHUNK_SIZE more than request */ + assert(is_mmapped(p) || sz < (s + MIN_CHUNK_SIZE)); + } +} + +/* Check a tree and its subtrees. */ +static void do_check_tree(mstate m, tchunkptr t) { + tchunkptr head = 0; + tchunkptr u = t; + bindex_t tindex = t->index; + size_t tsize = chunksize(t); + bindex_t idx; + compute_tree_index(tsize, idx); + assert(tindex == idx); + assert(tsize >= MIN_LARGE_SIZE); + assert(tsize >= minsize_for_tree_index(idx)); + assert((idx == NTREEBINS-1) || (tsize < minsize_for_tree_index((idx+1)))); + + do { /* traverse through chain of same-sized nodes */ + do_check_any_chunk(m, ((mchunkptr)u)); + assert(u->index == tindex); + assert(chunksize(u) == tsize); + assert(!is_inuse(u)); + assert(!next_pinuse(u)); + assert(u->fd->bk == u); + assert(u->bk->fd == u); + if (u->parent == 0) { + assert(u->child[0] == 0); + assert(u->child[1] == 0); + } + else { + assert(head == 0); /* only one node on chain has parent */ + head = u; + assert(u->parent != u); + assert (u->parent->child[0] == u || + u->parent->child[1] == u || + *((tbinptr*)(u->parent)) == u); + if (u->child[0] != 0) { + assert(u->child[0]->parent == u); + assert(u->child[0] != u); + do_check_tree(m, u->child[0]); + } + if (u->child[1] != 0) { + assert(u->child[1]->parent == u); + assert(u->child[1] != u); + do_check_tree(m, u->child[1]); + } + if (u->child[0] != 0 && u->child[1] != 0) { + assert(chunksize(u->child[0]) < chunksize(u->child[1])); + } + } + u = u->fd; + } while (u != t); + assert(head != 0); +} + +/* Check all the chunks in a treebin. */ +static void do_check_treebin(mstate m, bindex_t i) { + tbinptr* tb = treebin_at(m, i); + tchunkptr t = *tb; + int empty = (m->treemap & (1U << i)) == 0; + if (t == 0) + assert(empty); + if (!empty) + do_check_tree(m, t); +} + +/* Check all the chunks in a smallbin. */ +static void do_check_smallbin(mstate m, bindex_t i) { + sbinptr b = smallbin_at(m, i); + mchunkptr p = b->bk; + unsigned int empty = (m->smallmap & (1U << i)) == 0; + if (p == b) + assert(empty); + if (!empty) { + for (; p != b; p = p->bk) { + size_t size = chunksize(p); + mchunkptr q; + /* each chunk claims to be free */ + do_check_free_chunk(m, p); + /* chunk belongs in bin */ + assert(small_index(size) == i); + assert(p->bk == b || chunksize(p->bk) == chunksize(p)); + /* chunk is followed by an inuse chunk */ + q = next_chunk(p); + if (q->head != FENCEPOST_HEAD) + do_check_inuse_chunk(m, q); + } + } +} + +/* Find x in a bin. Used in other check functions. */ +static int bin_find(mstate m, mchunkptr x) { + size_t size = chunksize(x); + if (is_small(size)) { + bindex_t sidx = small_index(size); + sbinptr b = smallbin_at(m, sidx); + if (smallmap_is_marked(m, sidx)) { + mchunkptr p = b; + do { + if (p == x) + return 1; + } while ((p = p->fd) != b); + } + } + else { + bindex_t tidx; + compute_tree_index(size, tidx); + if (treemap_is_marked(m, tidx)) { + tchunkptr t = *treebin_at(m, tidx); + size_t sizebits = size << leftshift_for_tree_index(tidx); + while (t != 0 && chunksize(t) != size) { + t = t->child[(sizebits >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]; + sizebits <<= 1; + } + if (t != 0) { + tchunkptr u = t; + do { + if (u == (tchunkptr)x) + return 1; + } while ((u = u->fd) != t); + } + } + } + return 0; +} + +/* Traverse each chunk and check it; return total */ +static size_t traverse_and_check(mstate m) { + size_t sum = 0; + if (is_initialized(m)) { + msegmentptr s = &m->seg; + sum += m->topsize + TOP_FOOT_SIZE; + while (s != 0) { + mchunkptr q = align_as_chunk(s->base); + mchunkptr lastq = 0; + assert(pinuse(q)); + while (segment_holds(s, q) && + q != m->top && q->head != FENCEPOST_HEAD) { + sum += chunksize(q); + if (is_inuse(q)) { + assert(!bin_find(m, q)); + do_check_inuse_chunk(m, q); + } + else { + assert(q == m->dv || bin_find(m, q)); + assert(lastq == 0 || is_inuse(lastq)); /* Not 2 consecutive free */ + do_check_free_chunk(m, q); + } + lastq = q; + q = next_chunk(q); + } + s = s->next; + } + } + return sum; +} + + +/* Check all properties of malloc_state. */ +static void do_check_malloc_state(mstate m) { + bindex_t i; + size_t total; + /* check bins */ + for (i = 0; i < NSMALLBINS; ++i) + do_check_smallbin(m, i); + for (i = 0; i < NTREEBINS; ++i) + do_check_treebin(m, i); + + if (m->dvsize != 0) { /* check dv chunk */ + do_check_any_chunk(m, m->dv); + assert(m->dvsize == chunksize(m->dv)); + assert(m->dvsize >= MIN_CHUNK_SIZE); + assert(bin_find(m, m->dv) == 0); + } + + if (m->top != 0) { /* check top chunk */ + do_check_top_chunk(m, m->top); + /*assert(m->topsize == chunksize(m->top)); redundant */ + assert(m->topsize > 0); + assert(bin_find(m, m->top) == 0); + } + + total = traverse_and_check(m); + assert(total <= m->footprint); + assert(m->footprint <= m->max_footprint); +} +#endif /* DEBUG */ + +/* ----------------------------- statistics ------------------------------ */ + +#if !NO_MALLINFO +static struct mallinfo internal_mallinfo(mstate m) { + struct mallinfo nm = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }; + ensure_initialization(); + if (!PREACTION(m)) { + check_malloc_state(m); + if (is_initialized(m)) { + size_t nfree = SIZE_T_ONE; /* top always free */ + size_t mfree = m->topsize + TOP_FOOT_SIZE; + size_t sum = mfree; + msegmentptr s = &m->seg; + while (s != 0) { + mchunkptr q = align_as_chunk(s->base); + while (segment_holds(s, q) && + q != m->top && q->head != FENCEPOST_HEAD) { + size_t sz = chunksize(q); + sum += sz; + if (!is_inuse(q)) { + mfree += sz; + ++nfree; + } + q = next_chunk(q); + } + s = s->next; + } + + nm.arena = sum; + nm.ordblks = nfree; + nm.hblkhd = m->footprint - sum; + nm.usmblks = m->max_footprint; + nm.uordblks = m->footprint - mfree; + nm.fordblks = mfree; + nm.keepcost = m->topsize; + } + + POSTACTION(m); + } + return nm; +} +#endif /* !NO_MALLINFO */ + +#if !NO_MALLOC_STATS +static void internal_malloc_stats(mstate m) { + ensure_initialization(); + if (!PREACTION(m)) { + size_t maxfp = 0; + size_t fp = 0; + size_t used = 0; + check_malloc_state(m); + if (is_initialized(m)) { + msegmentptr s = &m->seg; + maxfp = m->max_footprint; + fp = m->footprint; + used = fp - (m->topsize + TOP_FOOT_SIZE); + + while (s != 0) { + mchunkptr q = align_as_chunk(s->base); + while (segment_holds(s, q) && + q != m->top && q->head != FENCEPOST_HEAD) { + if (!is_inuse(q)) + used -= chunksize(q); + q = next_chunk(q); + } + s = s->next; + } + } + POSTACTION(m); /* drop lock */ + fprintf(stderr, "max system bytes = %10lu\n", (unsigned long)(maxfp)); + fprintf(stderr, "system bytes = %10lu\n", (unsigned long)(fp)); + fprintf(stderr, "in use bytes = %10lu\n", (unsigned long)(used)); + } +} +#endif /* NO_MALLOC_STATS */ + +/* ----------------------- Operations on smallbins ----------------------- */ + +/* + Various forms of linking and unlinking are defined as macros. Even + the ones for trees, which are very long but have very short typical + paths. This is ugly but reduces reliance on inlining support of + compilers. +*/ + +/* Link a free chunk into a smallbin */ +#define insert_small_chunk(M, P, S) {\ + bindex_t I = small_index(S);\ + mchunkptr B = smallbin_at(M, I);\ + mchunkptr F = B;\ + assert(S >= MIN_CHUNK_SIZE);\ + if (!smallmap_is_marked(M, I))\ + mark_smallmap(M, I);\ + else if (RTCHECK(ok_address(M, B->fd)))\ + F = B->fd;\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + B->fd = P;\ + F->bk = P;\ + P->fd = F;\ + P->bk = B;\ +} + +/* Unlink a chunk from a smallbin */ +#define unlink_small_chunk(M, P, S) {\ + mchunkptr F = P->fd;\ + mchunkptr B = P->bk;\ + bindex_t I = small_index(S);\ + assert(P != B);\ + assert(P != F);\ + assert(chunksize(P) == small_index2size(I));\ + if (RTCHECK(F == smallbin_at(M,I) || (ok_address(M, F) && F->bk == P))) { \ + if (B == F) {\ + clear_smallmap(M, I);\ + }\ + else if (RTCHECK(B == smallbin_at(M,I) ||\ + (ok_address(M, B) && B->fd == P))) {\ + F->bk = B;\ + B->fd = F;\ + }\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + }\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ +} + +/* Unlink the first chunk from a smallbin */ +#define unlink_first_small_chunk(M, B, P, I) {\ + mchunkptr F = P->fd;\ + assert(P != B);\ + assert(P != F);\ + assert(chunksize(P) == small_index2size(I));\ + if (B == F) {\ + clear_smallmap(M, I);\ + }\ + else if (RTCHECK(ok_address(M, F) && F->bk == P)) {\ + F->bk = B;\ + B->fd = F;\ + }\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ +} + +/* Replace dv node, binning the old one */ +/* Used only when dvsize known to be small */ +#define replace_dv(M, P, S) {\ + size_t DVS = M->dvsize;\ + assert(is_small(DVS));\ + if (DVS != 0) {\ + mchunkptr DV = M->dv;\ + insert_small_chunk(M, DV, DVS);\ + }\ + M->dvsize = S;\ + M->dv = P;\ +} + +/* ------------------------- Operations on trees ------------------------- */ + +/* Insert chunk into tree */ +#define insert_large_chunk(M, X, S) {\ + tbinptr* H;\ + bindex_t I;\ + compute_tree_index(S, I);\ + H = treebin_at(M, I);\ + X->index = I;\ + X->child[0] = X->child[1] = 0;\ + if (!treemap_is_marked(M, I)) {\ + mark_treemap(M, I);\ + *H = X;\ + X->parent = (tchunkptr)H;\ + X->fd = X->bk = X;\ + }\ + else {\ + tchunkptr T = *H;\ + size_t K = S << leftshift_for_tree_index(I);\ + for (;;) {\ + if (chunksize(T) != S) {\ + tchunkptr* C = &(T->child[(K >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]);\ + K <<= 1;\ + if (*C != 0)\ + T = *C;\ + else if (RTCHECK(ok_address(M, C))) {\ + *C = X;\ + X->parent = T;\ + X->fd = X->bk = X;\ + break;\ + }\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + break;\ + }\ + }\ + else {\ + tchunkptr F = T->fd;\ + if (RTCHECK(ok_address(M, T) && ok_address(M, F))) {\ + T->fd = F->bk = X;\ + X->fd = F;\ + X->bk = T;\ + X->parent = 0;\ + break;\ + }\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + break;\ + }\ + }\ + }\ + }\ +} + +/* + Unlink steps: + + 1. If x is a chained node, unlink it from its same-sized fd/bk links + and choose its bk node as its replacement. + 2. If x was the last node of its size, but not a leaf node, it must + be replaced with a leaf node (not merely one with an open left or + right), to make sure that lefts and rights of descendents + correspond properly to bit masks. We use the rightmost descendent + of x. We could use any other leaf, but this is easy to locate and + tends to counteract removal of leftmosts elsewhere, and so keeps + paths shorter than minimally guaranteed. This doesn't loop much + because on average a node in a tree is near the bottom. + 3. If x is the base of a chain (i.e., has parent links) relink + x's parent and children to x's replacement (or null if none). +*/ + +#define unlink_large_chunk(M, X) {\ + tchunkptr XP = X->parent;\ + tchunkptr R;\ + if (X->bk != X) {\ + tchunkptr F = X->fd;\ + R = X->bk;\ + if (RTCHECK(ok_address(M, F) && F->bk == X && R->fd == X)) {\ + F->bk = R;\ + R->fd = F;\ + }\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + }\ + else {\ + tchunkptr* RP;\ + if (((R = *(RP = &(X->child[1]))) != 0) ||\ + ((R = *(RP = &(X->child[0]))) != 0)) {\ + tchunkptr* CP;\ + while ((*(CP = &(R->child[1])) != 0) ||\ + (*(CP = &(R->child[0])) != 0)) {\ + R = *(RP = CP);\ + }\ + if (RTCHECK(ok_address(M, RP)))\ + *RP = 0;\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + }\ + }\ + if (XP != 0) {\ + tbinptr* H = treebin_at(M, X->index);\ + if (X == *H) {\ + if ((*H = R) == 0) \ + clear_treemap(M, X->index);\ + }\ + else if (RTCHECK(ok_address(M, XP))) {\ + if (XP->child[0] == X) \ + XP->child[0] = R;\ + else \ + XP->child[1] = R;\ + }\ + else\ + CORRUPTION_ERROR_ACTION(M);\ + if (R != 0) {\ + if (RTCHECK(ok_address(M, R))) {\ + tchunkptr C0, C1;\ + R->parent = XP;\ + if ((C0 = X->child[0]) != 0) {\ + if (RTCHECK(ok_address(M, C0))) {\ + R->child[0] = C0;\ + C0->parent = R;\ + }\ + else\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + if ((C1 = X->child[1]) != 0) {\ + if (RTCHECK(ok_address(M, C1))) {\ + R->child[1] = C1;\ + C1->parent = R;\ + }\ + else\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + }\ + else\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + }\ +} + +/* Relays to large vs small bin operations */ + +#define insert_chunk(M, P, S)\ + if (is_small(S)) insert_small_chunk(M, P, S)\ + else { tchunkptr TP = (tchunkptr)(P); insert_large_chunk(M, TP, S); } + +#define unlink_chunk(M, P, S)\ + if (is_small(S)) unlink_small_chunk(M, P, S)\ + else { tchunkptr TP = (tchunkptr)(P); unlink_large_chunk(M, TP); } + + +/* Relays to internal calls to malloc/free from realloc, memalign etc */ + +#if ONLY_MSPACES +#define internal_malloc(m, b) mspace_malloc(m, b) +#define internal_free(m, mem) mspace_free(m,mem); +#else /* ONLY_MSPACES */ +#if MSPACES +#define internal_malloc(m, b)\ + ((m == gm)? dlmalloc(b) : mspace_malloc(m, b)) +#define internal_free(m, mem)\ + if (m == gm) dlfree(mem); else mspace_free(m,mem); +#else /* MSPACES */ +#define internal_malloc(m, b) dlmalloc(b) +#define internal_free(m, mem) dlfree(mem) +#endif /* MSPACES */ +#endif /* ONLY_MSPACES */ + +/* ----------------------- Direct-mmapping chunks ----------------------- */ + +/* + Directly mmapped chunks are set up with an offset to the start of + the mmapped region stored in the prev_foot field of the chunk. This + allows reconstruction of the required argument to MUNMAP when freed, + and also allows adjustment of the returned chunk to meet alignment + requirements (especially in memalign). +*/ + +/* Malloc using mmap */ +static void* mmap_alloc(mstate m, size_t nb) { + size_t mmsize = mmap_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK); + if (m->footprint_limit != 0) { + size_t fp = m->footprint + mmsize; + if (fp <= m->footprint || fp > m->footprint_limit) + return 0; + } + if (mmsize > nb) { /* Check for wrap around 0 */ + char* mm = (char*)(CALL_DIRECT_MMAP(mmsize)); + if (mm != CMFAIL) { + size_t offset = align_offset(chunk2mem(mm)); + size_t psize = mmsize - offset - MMAP_FOOT_PAD; + mchunkptr p = (mchunkptr)(mm + offset); + p->prev_foot = offset; + p->head = psize; + mark_inuse_foot(m, p, psize); + chunk_plus_offset(p, psize)->head = FENCEPOST_HEAD; + chunk_plus_offset(p, psize+SIZE_T_SIZE)->head = 0; + + if (m->least_addr == 0 || mm < m->least_addr) + m->least_addr = mm; + if ((m->footprint += mmsize) > m->max_footprint) + m->max_footprint = m->footprint; + assert(is_aligned(chunk2mem(p))); + check_mmapped_chunk(m, p); + return chunk2mem(p); + } + } + return 0; +} + +/* Realloc using mmap */ +static mchunkptr mmap_resize(mstate m, mchunkptr oldp, size_t nb, int flags) { + size_t oldsize = chunksize(oldp); + (void)flags; /* placate people compiling -Wunused */ + if (is_small(nb)) /* Can't shrink mmap regions below small size */ + return 0; + /* Keep old chunk if big enough but not too big */ + if (oldsize >= nb + SIZE_T_SIZE && + (oldsize - nb) <= (mparams.granularity << 1)) + return oldp; + else { + size_t offset = oldp->prev_foot; + size_t oldmmsize = oldsize + offset + MMAP_FOOT_PAD; + size_t newmmsize = mmap_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK); + char* cp = (char*)CALL_MREMAP((char*)oldp - offset, + oldmmsize, newmmsize, flags); + if (cp != CMFAIL) { + mchunkptr newp = (mchunkptr)(cp + offset); + size_t psize = newmmsize - offset - MMAP_FOOT_PAD; + newp->head = psize; + mark_inuse_foot(m, newp, psize); + chunk_plus_offset(newp, psize)->head = FENCEPOST_HEAD; + chunk_plus_offset(newp, psize+SIZE_T_SIZE)->head = 0; + + if (cp < m->least_addr) + m->least_addr = cp; + if ((m->footprint += newmmsize - oldmmsize) > m->max_footprint) + m->max_footprint = m->footprint; + check_mmapped_chunk(m, newp); + return newp; + } + } + return 0; +} + + +/* -------------------------- mspace management -------------------------- */ + +/* Initialize top chunk and its size */ +static void init_top(mstate m, mchunkptr p, size_t psize) { + /* Ensure alignment */ + size_t offset = align_offset(chunk2mem(p)); + p = (mchunkptr)((char*)p + offset); + psize -= offset; + + m->top = p; + m->topsize = psize; + p->head = psize | PINUSE_BIT; + /* set size of fake trailing chunk holding overhead space only once */ + chunk_plus_offset(p, psize)->head = TOP_FOOT_SIZE; + m->trim_check = mparams.trim_threshold; /* reset on each update */ +} + +/* Initialize bins for a new mstate that is otherwise zeroed out */ +static void init_bins(mstate m) { + /* Establish circular links for smallbins */ + bindex_t i; + for (i = 0; i < NSMALLBINS; ++i) { + sbinptr bin = smallbin_at(m,i); + bin->fd = bin->bk = bin; + } +} + +#if PROCEED_ON_ERROR + +/* default corruption action */ +static void reset_on_error(mstate m) { + int i; + ++malloc_corruption_error_count; + /* Reinitialize fields to forget about all memory */ + m->smallmap = m->treemap = 0; + m->dvsize = m->topsize = 0; + m->seg.base = 0; + m->seg.size = 0; + m->seg.next = 0; + m->top = m->dv = 0; + for (i = 0; i < NTREEBINS; ++i) + *treebin_at(m, i) = 0; + init_bins(m); +} +#endif /* PROCEED_ON_ERROR */ + +/* Allocate chunk and prepend remainder with chunk in successor base. */ +static void* prepend_alloc(mstate m, char* newbase, char* oldbase, + size_t nb) { + mchunkptr p = align_as_chunk(newbase); + mchunkptr oldfirst = align_as_chunk(oldbase); + size_t psize = (char*)oldfirst - (char*)p; + mchunkptr q = chunk_plus_offset(p, nb); + size_t qsize = psize - nb; + set_size_and_pinuse_of_inuse_chunk(m, p, nb); + + assert((char*)oldfirst > (char*)q); + assert(pinuse(oldfirst)); + assert(qsize >= MIN_CHUNK_SIZE); + + /* consolidate remainder with first chunk of old base */ + if (oldfirst == m->top) { + size_t tsize = m->topsize += qsize; + m->top = q; + q->head = tsize | PINUSE_BIT; + check_top_chunk(m, q); + } + else if (oldfirst == m->dv) { + size_t dsize = m->dvsize += qsize; + m->dv = q; + set_size_and_pinuse_of_free_chunk(q, dsize); + } + else { + if (!is_inuse(oldfirst)) { + size_t nsize = chunksize(oldfirst); + unlink_chunk(m, oldfirst, nsize); + oldfirst = chunk_plus_offset(oldfirst, nsize); + qsize += nsize; + } + set_free_with_pinuse(q, qsize, oldfirst); + insert_chunk(m, q, qsize); + check_free_chunk(m, q); + } + + check_malloced_chunk(m, chunk2mem(p), nb); + return chunk2mem(p); +} + +/* Add a segment to hold a new noncontiguous region */ +static void add_segment(mstate m, char* tbase, size_t tsize, flag_t mmapped) { + /* Determine locations and sizes of segment, fenceposts, old top */ + char* old_top = (char*)m->top; + msegmentptr oldsp = segment_holding(m, old_top); + char* old_end = oldsp->base + oldsp->size; + size_t ssize = pad_request(sizeof(struct malloc_segment)); + char* rawsp = old_end - (ssize + FOUR_SIZE_T_SIZES + CHUNK_ALIGN_MASK); + size_t offset = align_offset(chunk2mem(rawsp)); + char* asp = rawsp + offset; + char* csp = (asp < (old_top + MIN_CHUNK_SIZE))? old_top : asp; + mchunkptr sp = (mchunkptr)csp; + msegmentptr ss = (msegmentptr)(chunk2mem(sp)); + mchunkptr tnext = chunk_plus_offset(sp, ssize); + mchunkptr p = tnext; + int nfences = 0; + + /* reset top to new space */ + init_top(m, (mchunkptr)tbase, tsize - TOP_FOOT_SIZE); + + /* Set up segment record */ + assert(is_aligned(ss)); + set_size_and_pinuse_of_inuse_chunk(m, sp, ssize); + *ss = m->seg; /* Push current record */ + m->seg.base = tbase; + m->seg.size = tsize; + m->seg.sflags = mmapped; + m->seg.next = ss; + + /* Insert trailing fenceposts */ + for (;;) { + mchunkptr nextp = chunk_plus_offset(p, SIZE_T_SIZE); + p->head = FENCEPOST_HEAD; + ++nfences; + if ((char*)(&(nextp->head)) < old_end) + p = nextp; + else + break; + } + assert(nfences >= 2); + + /* Insert the rest of old top into a bin as an ordinary free chunk */ + if (csp != old_top) { + mchunkptr q = (mchunkptr)old_top; + size_t psize = csp - old_top; + mchunkptr tn = chunk_plus_offset(q, psize); + set_free_with_pinuse(q, psize, tn); + insert_chunk(m, q, psize); + } + + check_top_chunk(m, m->top); +} + +/* -------------------------- System allocation -------------------------- */ + +/* Get memory from system using MORECORE or MMAP */ +static void* sys_alloc(mstate m, size_t nb) { + char* tbase = CMFAIL; + size_t tsize = 0; + flag_t mmap_flag = 0; + size_t asize; /* allocation size */ + + ensure_initialization(); + + /* Directly map large chunks, but only if already initialized */ + if (use_mmap(m) && nb >= mparams.mmap_threshold && m->topsize != 0) { + void* mem = mmap_alloc(m, nb); + if (mem != 0) + return mem; + } + + asize = granularity_align(nb + SYS_ALLOC_PADDING); + if (asize <= nb) + return 0; /* wraparound */ + if (m->footprint_limit != 0) { + size_t fp = m->footprint + asize; + if (fp <= m->footprint || fp > m->footprint_limit) + return 0; + } + + /* + Try getting memory in any of three ways (in most-preferred to + least-preferred order): + 1. A call to MORECORE that can normally contiguously extend memory. + (disabled if not MORECORE_CONTIGUOUS or not HAVE_MORECORE or + or main space is mmapped or a previous contiguous call failed) + 2. A call to MMAP new space (disabled if not HAVE_MMAP). + Note that under the default settings, if MORECORE is unable to + fulfill a request, and HAVE_MMAP is true, then mmap is + used as a noncontiguous system allocator. This is a useful backup + strategy for systems with holes in address spaces -- in this case + sbrk cannot contiguously expand the heap, but mmap may be able to + find space. + 3. A call to MORECORE that cannot usually contiguously extend memory. + (disabled if not HAVE_MORECORE) + + In all cases, we need to request enough bytes from system to ensure + we can malloc nb bytes upon success, so pad with enough space for + top_foot, plus alignment-pad to make sure we don't lose bytes if + not on boundary, and round this up to a granularity unit. + */ + + if (MORECORE_CONTIGUOUS && !use_noncontiguous(m)) { + char* br = CMFAIL; + size_t ssize = asize; /* sbrk call size */ + msegmentptr ss = (m->top == 0)? 0 : segment_holding(m, (char*)m->top); + ACQUIRE_MALLOC_GLOBAL_LOCK(); + + if (ss == 0) { /* First time through or recovery */ + char* base = (char*)CALL_MORECORE(0); + if (base != CMFAIL) { + size_t fp; + /* Adjust to end on a page boundary */ + if (!is_page_aligned(base)) + ssize += (page_align((size_t)base) - (size_t)base); + fp = m->footprint + ssize; /* recheck limits */ + if (ssize > nb && ssize < HALF_MAX_SIZE_T && + (m->footprint_limit == 0 || + (fp > m->footprint && fp <= m->footprint_limit)) && + (br = (char*)(CALL_MORECORE(ssize))) == base) { + tbase = base; + tsize = ssize; + } + } + } + else { + /* Subtract out existing available top space from MORECORE request. */ + ssize = granularity_align(nb - m->topsize + SYS_ALLOC_PADDING); + /* Use mem here only if it did continuously extend old space */ + if (ssize < HALF_MAX_SIZE_T && + (br = (char*)(CALL_MORECORE(ssize))) == ss->base+ss->size) { + tbase = br; + tsize = ssize; + } + } + + if (tbase == CMFAIL) { /* Cope with partial failure */ + if (br != CMFAIL) { /* Try to use/extend the space we did get */ + if (ssize < HALF_MAX_SIZE_T && + ssize < nb + SYS_ALLOC_PADDING) { + size_t esize = granularity_align(nb + SYS_ALLOC_PADDING - ssize); + if (esize < HALF_MAX_SIZE_T) { + char* end = (char*)CALL_MORECORE(esize); + if (end != CMFAIL) + ssize += esize; + else { /* Can't use; try to release */ + (void) CALL_MORECORE(-ssize); + br = CMFAIL; + } + } + } + } + if (br != CMFAIL) { /* Use the space we did get */ + tbase = br; + tsize = ssize; + } + else + disable_contiguous(m); /* Don't try contiguous path in the future */ + } + + RELEASE_MALLOC_GLOBAL_LOCK(); + } + + if (HAVE_MMAP && tbase == CMFAIL) { /* Try MMAP */ + char* mp = (char*)(CALL_MMAP(asize)); + if (mp != CMFAIL) { + tbase = mp; + tsize = asize; + mmap_flag = USE_MMAP_BIT; + } + } + + if (HAVE_MORECORE && tbase == CMFAIL) { /* Try noncontiguous MORECORE */ + if (asize < HALF_MAX_SIZE_T) { + char* br = CMFAIL; + char* end = CMFAIL; + ACQUIRE_MALLOC_GLOBAL_LOCK(); + br = (char*)(CALL_MORECORE(asize)); + end = (char*)(CALL_MORECORE(0)); + RELEASE_MALLOC_GLOBAL_LOCK(); + if (br != CMFAIL && end != CMFAIL && br < end) { + size_t ssize = end - br; + if (ssize > nb + TOP_FOOT_SIZE) { + tbase = br; + tsize = ssize; + } + } + } + } + + if (tbase != CMFAIL) { + + if ((m->footprint += tsize) > m->max_footprint) + m->max_footprint = m->footprint; + + if (!is_initialized(m)) { /* first-time initialization */ + if (m->least_addr == 0 || tbase < m->least_addr) + m->least_addr = tbase; + m->seg.base = tbase; + m->seg.size = tsize; + m->seg.sflags = mmap_flag; + m->magic = mparams.magic; + m->release_checks = MAX_RELEASE_CHECK_RATE; + init_bins(m); +#if !ONLY_MSPACES + if (is_global(m)) + init_top(m, (mchunkptr)tbase, tsize - TOP_FOOT_SIZE); + else +#endif + { + /* Offset top by embedded malloc_state */ + mchunkptr mn = next_chunk(mem2chunk(m)); + init_top(m, mn, (size_t)((tbase + tsize) - (char*)mn) -TOP_FOOT_SIZE); + } + } + + else { + /* Try to merge with an existing segment */ + msegmentptr sp = &m->seg; + /* Only consider most recent segment if traversal suppressed */ + while (sp != 0 && tbase != sp->base + sp->size) + sp = (NO_SEGMENT_TRAVERSAL) ? 0 : sp->next; + if (sp != 0 && + !is_extern_segment(sp) && + (sp->sflags & USE_MMAP_BIT) == mmap_flag && + segment_holds(sp, m->top)) { /* append */ + sp->size += tsize; + init_top(m, m->top, m->topsize + tsize); + } + else { + if (tbase < m->least_addr) + m->least_addr = tbase; + sp = &m->seg; + while (sp != 0 && sp->base != tbase + tsize) + sp = (NO_SEGMENT_TRAVERSAL) ? 0 : sp->next; + if (sp != 0 && + !is_extern_segment(sp) && + (sp->sflags & USE_MMAP_BIT) == mmap_flag) { + char* oldbase = sp->base; + sp->base = tbase; + sp->size += tsize; + return prepend_alloc(m, tbase, oldbase, nb); + } + else + add_segment(m, tbase, tsize, mmap_flag); + } + } + + if (nb < m->topsize) { /* Allocate from new or extended top space */ + size_t rsize = m->topsize -= nb; + mchunkptr p = m->top; + mchunkptr r = m->top = chunk_plus_offset(p, nb); + r->head = rsize | PINUSE_BIT; + set_size_and_pinuse_of_inuse_chunk(m, p, nb); + check_top_chunk(m, m->top); + check_malloced_chunk(m, chunk2mem(p), nb); + return chunk2mem(p); + } + } + + MALLOC_FAILURE_ACTION; + return 0; +} + +/* ----------------------- system deallocation -------------------------- */ + +/* Unmap and unlink any mmapped segments that don't contain used chunks */ +static size_t release_unused_segments(mstate m) { + size_t released = 0; + int nsegs = 0; + msegmentptr pred = &m->seg; + msegmentptr sp = pred->next; + while (sp != 0) { + char* base = sp->base; + size_t size = sp->size; + msegmentptr next = sp->next; + ++nsegs; + if (is_mmapped_segment(sp) && !is_extern_segment(sp)) { + mchunkptr p = align_as_chunk(base); + size_t psize = chunksize(p); + /* Can unmap if first chunk holds entire segment and not pinned */ + if (!is_inuse(p) && (char*)p + psize >= base + size - TOP_FOOT_SIZE) { + tchunkptr tp = (tchunkptr)p; + assert(segment_holds(sp, (char*)sp)); + if (p == m->dv) { + m->dv = 0; + m->dvsize = 0; + } + else { + unlink_large_chunk(m, tp); + } + if (CALL_MUNMAP(base, size) == 0) { + released += size; + m->footprint -= size; + /* unlink obsoleted record */ + sp = pred; + sp->next = next; + } + else { /* back out if cannot unmap */ + insert_large_chunk(m, tp, psize); + } + } + } + if (NO_SEGMENT_TRAVERSAL) /* scan only first segment */ + break; + pred = sp; + sp = next; + } + /* Reset check counter */ + m->release_checks = (((size_t) nsegs > (size_t) MAX_RELEASE_CHECK_RATE)? + (size_t) nsegs : (size_t) MAX_RELEASE_CHECK_RATE); + return released; +} + +static int sys_trim(mstate m, size_t pad) { + size_t released = 0; + ensure_initialization(); + if (pad < MAX_REQUEST && is_initialized(m)) { + pad += TOP_FOOT_SIZE; /* ensure enough room for segment overhead */ + + if (m->topsize > pad) { + /* Shrink top space in granularity-size units, keeping at least one */ + size_t unit = mparams.granularity; + size_t extra = ((m->topsize - pad + (unit - SIZE_T_ONE)) / unit - + SIZE_T_ONE) * unit; + msegmentptr sp = segment_holding(m, (char*)m->top); + + if (!is_extern_segment(sp)) { + if (is_mmapped_segment(sp)) { + if (HAVE_MMAP && + sp->size >= extra && + !has_segment_link(m, sp)) { /* can't shrink if pinned */ + size_t newsize = sp->size - extra; + (void)newsize; /* placate people compiling -Wunused-variable */ + /* Prefer mremap, fall back to munmap */ + if ((CALL_MREMAP(sp->base, sp->size, newsize, 0) != MFAIL) || + (CALL_MUNMAP(sp->base + newsize, extra) == 0)) { + released = extra; + } + } + } + else if (HAVE_MORECORE) { + if (extra >= HALF_MAX_SIZE_T) /* Avoid wrapping negative */ + extra = (HALF_MAX_SIZE_T) + SIZE_T_ONE - unit; + ACQUIRE_MALLOC_GLOBAL_LOCK(); + { + /* Make sure end of memory is where we last set it. */ + char* old_br = (char*)(CALL_MORECORE(0)); + if (old_br == sp->base + sp->size) { + char* rel_br = (char*)(CALL_MORECORE(-extra)); + char* new_br = (char*)(CALL_MORECORE(0)); + if (rel_br != CMFAIL && new_br < old_br) + released = old_br - new_br; + } + } + RELEASE_MALLOC_GLOBAL_LOCK(); + } + } + + if (released != 0) { + sp->size -= released; + m->footprint -= released; + init_top(m, m->top, m->topsize - released); + check_top_chunk(m, m->top); + } + } + + /* Unmap any unused mmapped segments */ + if (HAVE_MMAP) + released += release_unused_segments(m); + + /* On failure, disable autotrim to avoid repeated failed future calls */ + if (released == 0 && m->topsize > m->trim_check) + m->trim_check = MAX_SIZE_T; + } + + return (released != 0)? 1 : 0; +} + +/* Consolidate and bin a chunk. Differs from exported versions + of free mainly in that the chunk need not be marked as inuse. +*/ +static void dispose_chunk(mstate m, mchunkptr p, size_t psize) { + mchunkptr next = chunk_plus_offset(p, psize); + if (!pinuse(p)) { + mchunkptr prev; + size_t prevsize = p->prev_foot; + if (is_mmapped(p)) { + psize += prevsize + MMAP_FOOT_PAD; + if (CALL_MUNMAP((char*)p - prevsize, psize) == 0) + m->footprint -= psize; + return; + } + prev = chunk_minus_offset(p, prevsize); + psize += prevsize; + p = prev; + if (RTCHECK(ok_address(m, prev))) { /* consolidate backward */ + if (p != m->dv) { + unlink_chunk(m, p, prevsize); + } + else if ((next->head & INUSE_BITS) == INUSE_BITS) { + m->dvsize = psize; + set_free_with_pinuse(p, psize, next); + return; + } + } + else { + CORRUPTION_ERROR_ACTION(m); + return; + } + } + if (RTCHECK(ok_address(m, next))) { + if (!cinuse(next)) { /* consolidate forward */ + if (next == m->top) { + size_t tsize = m->topsize += psize; + m->top = p; + p->head = tsize | PINUSE_BIT; + if (p == m->dv) { + m->dv = 0; + m->dvsize = 0; + } + return; + } + else if (next == m->dv) { + size_t dsize = m->dvsize += psize; + m->dv = p; + set_size_and_pinuse_of_free_chunk(p, dsize); + return; + } + else { + size_t nsize = chunksize(next); + psize += nsize; + unlink_chunk(m, next, nsize); + set_size_and_pinuse_of_free_chunk(p, psize); + if (p == m->dv) { + m->dvsize = psize; + return; + } + } + } + else { + set_free_with_pinuse(p, psize, next); + } + insert_chunk(m, p, psize); + } + else { + CORRUPTION_ERROR_ACTION(m); + } +} + +/* ---------------------------- malloc --------------------------- */ + +/* allocate a large request from the best fitting chunk in a treebin */ +static void* tmalloc_large(mstate m, size_t nb) { + tchunkptr v = 0; + size_t rsize = -nb; /* Unsigned negation */ + tchunkptr t; + bindex_t idx; + compute_tree_index(nb, idx); + if ((t = *treebin_at(m, idx)) != 0) { + /* Traverse tree for this bin looking for node with size == nb */ + size_t sizebits = nb << leftshift_for_tree_index(idx); + tchunkptr rst = 0; /* The deepest untaken right subtree */ + for (;;) { + tchunkptr rt; + size_t trem = chunksize(t) - nb; + if (trem < rsize) { + v = t; + if ((rsize = trem) == 0) + break; + } + rt = t->child[1]; + t = t->child[(sizebits >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]; + if (rt != 0 && rt != t) + rst = rt; + if (t == 0) { + t = rst; /* set t to least subtree holding sizes > nb */ + break; + } + sizebits <<= 1; + } + } + if (t == 0 && v == 0) { /* set t to root of next non-empty treebin */ + binmap_t leftbits = left_bits(idx2bit(idx)) & m->treemap; + if (leftbits != 0) { + bindex_t i; + binmap_t leastbit = least_bit(leftbits); + compute_bit2idx(leastbit, i); + t = *treebin_at(m, i); + } + } + + while (t != 0) { /* find smallest of tree or subtree */ + size_t trem = chunksize(t) - nb; + if (trem < rsize) { + rsize = trem; + v = t; + } + t = leftmost_child(t); + } + + /* If dv is a better fit, return 0 so malloc will use it */ + if (v != 0 && rsize < (size_t)(m->dvsize - nb)) { + if (RTCHECK(ok_address(m, v))) { /* split */ + mchunkptr r = chunk_plus_offset(v, nb); + assert(chunksize(v) == rsize + nb); + if (RTCHECK(ok_next(v, r))) { + unlink_large_chunk(m, v); + if (rsize < MIN_CHUNK_SIZE) + set_inuse_and_pinuse(m, v, (rsize + nb)); + else { + set_size_and_pinuse_of_inuse_chunk(m, v, nb); + set_size_and_pinuse_of_free_chunk(r, rsize); + insert_chunk(m, r, rsize); + } + return chunk2mem(v); + } + } + CORRUPTION_ERROR_ACTION(m); + } + return 0; +} + +/* allocate a small request from the best fitting chunk in a treebin */ +static void* tmalloc_small(mstate m, size_t nb) { + tchunkptr t, v; + size_t rsize; + bindex_t i; + binmap_t leastbit = least_bit(m->treemap); + compute_bit2idx(leastbit, i); + v = t = *treebin_at(m, i); + rsize = chunksize(t) - nb; + + while ((t = leftmost_child(t)) != 0) { + size_t trem = chunksize(t) - nb; + if (trem < rsize) { + rsize = trem; + v = t; + } + } + + if (RTCHECK(ok_address(m, v))) { + mchunkptr r = chunk_plus_offset(v, nb); + assert(chunksize(v) == rsize + nb); + if (RTCHECK(ok_next(v, r))) { + unlink_large_chunk(m, v); + if (rsize < MIN_CHUNK_SIZE) + set_inuse_and_pinuse(m, v, (rsize + nb)); + else { + set_size_and_pinuse_of_inuse_chunk(m, v, nb); + set_size_and_pinuse_of_free_chunk(r, rsize); + replace_dv(m, r, rsize); + } + return chunk2mem(v); + } + } + + CORRUPTION_ERROR_ACTION(m); + return 0; +} + +#if !ONLY_MSPACES + +void* dlmalloc(size_t bytes) { + /* + Basic algorithm: + If a small request (< 256 bytes minus per-chunk overhead): + 1. If one exists, use a remainderless chunk in associated smallbin. + (Remainderless means that there are too few excess bytes to + represent as a chunk.) + 2. If it is big enough, use the dv chunk, which is normally the + chunk adjacent to the one used for the most recent small request. + 3. If one exists, split the smallest available chunk in a bin, + saving remainder in dv. + 4. If it is big enough, use the top chunk. + 5. If available, get memory from system and use it + Otherwise, for a large request: + 1. Find the smallest available binned chunk that fits, and use it + if it is better fitting than dv chunk, splitting if necessary. + 2. If better fitting than any binned chunk, use the dv chunk. + 3. If it is big enough, use the top chunk. + 4. If request size >= mmap threshold, try to directly mmap this chunk. + 5. If available, get memory from system and use it + + The ugly goto's here ensure that postaction occurs along all paths. + */ + +#if USE_LOCKS + ensure_initialization(); /* initialize in sys_alloc if not using locks */ +#endif + + if (!PREACTION(gm)) { + void* mem; + size_t nb; + if (bytes <= MAX_SMALL_REQUEST) { + bindex_t idx; + binmap_t smallbits; + nb = (bytes < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(bytes); + idx = small_index(nb); + smallbits = gm->smallmap >> idx; + + if ((smallbits & 0x3U) != 0) { /* Remainderless fit to a smallbin. */ + mchunkptr b, p; + idx += ~smallbits & 1; /* Uses next bin if idx empty */ + b = smallbin_at(gm, idx); + p = b->fd; + assert(chunksize(p) == small_index2size(idx)); + unlink_first_small_chunk(gm, b, p, idx); + set_inuse_and_pinuse(gm, p, small_index2size(idx)); + mem = chunk2mem(p); + check_malloced_chunk(gm, mem, nb); + goto postaction; + } + + else if (nb > gm->dvsize) { + if (smallbits != 0) { /* Use chunk in next nonempty smallbin */ + mchunkptr b, p, r; + size_t rsize; + bindex_t i; + binmap_t leftbits = (smallbits << idx) & left_bits(idx2bit(idx)); + binmap_t leastbit = least_bit(leftbits); + compute_bit2idx(leastbit, i); + b = smallbin_at(gm, i); + p = b->fd; + assert(chunksize(p) == small_index2size(i)); + unlink_first_small_chunk(gm, b, p, i); + rsize = small_index2size(i) - nb; + /* Fit here cannot be remainderless if 4byte sizes */ + if (SIZE_T_SIZE != 4 && rsize < MIN_CHUNK_SIZE) + set_inuse_and_pinuse(gm, p, small_index2size(i)); + else { + set_size_and_pinuse_of_inuse_chunk(gm, p, nb); + r = chunk_plus_offset(p, nb); + set_size_and_pinuse_of_free_chunk(r, rsize); + replace_dv(gm, r, rsize); + } + mem = chunk2mem(p); + check_malloced_chunk(gm, mem, nb); + goto postaction; + } + + else if (gm->treemap != 0 && (mem = tmalloc_small(gm, nb)) != 0) { + check_malloced_chunk(gm, mem, nb); + goto postaction; + } + } + } + else if (bytes >= MAX_REQUEST) + nb = MAX_SIZE_T; /* Too big to allocate. Force failure (in sys alloc) */ + else { + nb = pad_request(bytes); + if (gm->treemap != 0 && (mem = tmalloc_large(gm, nb)) != 0) { + check_malloced_chunk(gm, mem, nb); + goto postaction; + } + } + + if (nb <= gm->dvsize) { + size_t rsize = gm->dvsize - nb; + mchunkptr p = gm->dv; + if (rsize >= MIN_CHUNK_SIZE) { /* split dv */ + mchunkptr r = gm->dv = chunk_plus_offset(p, nb); + gm->dvsize = rsize; + set_size_and_pinuse_of_free_chunk(r, rsize); + set_size_and_pinuse_of_inuse_chunk(gm, p, nb); + } + else { /* exhaust dv */ + size_t dvs = gm->dvsize; + gm->dvsize = 0; + gm->dv = 0; + set_inuse_and_pinuse(gm, p, dvs); + } + mem = chunk2mem(p); + check_malloced_chunk(gm, mem, nb); + goto postaction; + } + + else if (nb < gm->topsize) { /* Split top */ + size_t rsize = gm->topsize -= nb; + mchunkptr p = gm->top; + mchunkptr r = gm->top = chunk_plus_offset(p, nb); + r->head = rsize | PINUSE_BIT; + set_size_and_pinuse_of_inuse_chunk(gm, p, nb); + mem = chunk2mem(p); + check_top_chunk(gm, gm->top); + check_malloced_chunk(gm, mem, nb); + goto postaction; + } + + mem = sys_alloc(gm, nb); + + postaction: + POSTACTION(gm); + return mem; + } + + return 0; +} + +/* ---------------------------- free --------------------------- */ + +void dlfree(void* mem) { + /* + Consolidate freed chunks with preceeding or succeeding bordering + free chunks, if they exist, and then place in a bin. Intermixed + with special cases for top, dv, mmapped chunks, and usage errors. + */ + + if (mem != 0) { + mchunkptr p = mem2chunk(mem); +#if FOOTERS + mstate fm = get_mstate_for(p); + if (!ok_magic(fm)) { + USAGE_ERROR_ACTION(fm, p); + return; + } +#else /* FOOTERS */ +#define fm gm +#endif /* FOOTERS */ + if (!PREACTION(fm)) { + check_inuse_chunk(fm, p); + if (RTCHECK(ok_address(fm, p) && ok_inuse(p))) { + size_t psize = chunksize(p); + mchunkptr next = chunk_plus_offset(p, psize); + if (!pinuse(p)) { + size_t prevsize = p->prev_foot; + if (is_mmapped(p)) { + psize += prevsize + MMAP_FOOT_PAD; + if (CALL_MUNMAP((char*)p - prevsize, psize) == 0) + fm->footprint -= psize; + goto postaction; + } + else { + mchunkptr prev = chunk_minus_offset(p, prevsize); + psize += prevsize; + p = prev; + if (RTCHECK(ok_address(fm, prev))) { /* consolidate backward */ + if (p != fm->dv) { + unlink_chunk(fm, p, prevsize); + } + else if ((next->head & INUSE_BITS) == INUSE_BITS) { + fm->dvsize = psize; + set_free_with_pinuse(p, psize, next); + goto postaction; + } + } + else + goto erroraction; + } + } + + if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) { + if (!cinuse(next)) { /* consolidate forward */ + if (next == fm->top) { + size_t tsize = fm->topsize += psize; + fm->top = p; + p->head = tsize | PINUSE_BIT; + if (p == fm->dv) { + fm->dv = 0; + fm->dvsize = 0; + } + if (should_trim(fm, tsize)) + sys_trim(fm, 0); + goto postaction; + } + else if (next == fm->dv) { + size_t dsize = fm->dvsize += psize; + fm->dv = p; + set_size_and_pinuse_of_free_chunk(p, dsize); + goto postaction; + } + else { + size_t nsize = chunksize(next); + psize += nsize; + unlink_chunk(fm, next, nsize); + set_size_and_pinuse_of_free_chunk(p, psize); + if (p == fm->dv) { + fm->dvsize = psize; + goto postaction; + } + } + } + else + set_free_with_pinuse(p, psize, next); + + if (is_small(psize)) { + insert_small_chunk(fm, p, psize); + check_free_chunk(fm, p); + } + else { + tchunkptr tp = (tchunkptr)p; + insert_large_chunk(fm, tp, psize); + check_free_chunk(fm, p); + if (--fm->release_checks == 0) + release_unused_segments(fm); + } + goto postaction; + } + } + erroraction: + USAGE_ERROR_ACTION(fm, p); + postaction: + POSTACTION(fm); + } + } +#if !FOOTERS +#undef fm +#endif /* FOOTERS */ +} + +void* dlcalloc(size_t n_elements, size_t elem_size) { + void* mem; + size_t req = 0; + if (n_elements != 0) { + req = n_elements * elem_size; + if (((n_elements | elem_size) & ~(size_t)0xffff) && + (req / n_elements != elem_size)) + req = MAX_SIZE_T; /* force downstream failure on overflow */ + } + mem = dlmalloc(req); + if (mem != 0 && calloc_must_clear(mem2chunk(mem))) + memset(mem, 0, req); + return mem; +} + +#endif /* !ONLY_MSPACES */ + +/* ------------ Internal support for realloc, memalign, etc -------------- */ + +/* Try to realloc; only in-place unless can_move true */ +static mchunkptr try_realloc_chunk(mstate m, mchunkptr p, size_t nb, + int can_move) { + mchunkptr newp = 0; + size_t oldsize = chunksize(p); + mchunkptr next = chunk_plus_offset(p, oldsize); + if (RTCHECK(ok_address(m, p) && ok_inuse(p) && + ok_next(p, next) && ok_pinuse(next))) { + if (is_mmapped(p)) { + newp = mmap_resize(m, p, nb, can_move); + } + else if (oldsize >= nb) { /* already big enough */ + size_t rsize = oldsize - nb; + if (rsize >= MIN_CHUNK_SIZE) { /* split off remainder */ + mchunkptr r = chunk_plus_offset(p, nb); + set_inuse(m, p, nb); + set_inuse(m, r, rsize); + dispose_chunk(m, r, rsize); + } + newp = p; + } + else if (next == m->top) { /* extend into top */ + if (oldsize + m->topsize > nb) { + size_t newsize = oldsize + m->topsize; + size_t newtopsize = newsize - nb; + mchunkptr newtop = chunk_plus_offset(p, nb); + set_inuse(m, p, nb); + newtop->head = newtopsize |PINUSE_BIT; + m->top = newtop; + m->topsize = newtopsize; + newp = p; + } + } + else if (next == m->dv) { /* extend into dv */ + size_t dvs = m->dvsize; + if (oldsize + dvs >= nb) { + size_t dsize = oldsize + dvs - nb; + if (dsize >= MIN_CHUNK_SIZE) { + mchunkptr r = chunk_plus_offset(p, nb); + mchunkptr n = chunk_plus_offset(r, dsize); + set_inuse(m, p, nb); + set_size_and_pinuse_of_free_chunk(r, dsize); + clear_pinuse(n); + m->dvsize = dsize; + m->dv = r; + } + else { /* exhaust dv */ + size_t newsize = oldsize + dvs; + set_inuse(m, p, newsize); + m->dvsize = 0; + m->dv = 0; + } + newp = p; + } + } + else if (!cinuse(next)) { /* extend into next free chunk */ + size_t nextsize = chunksize(next); + if (oldsize + nextsize >= nb) { + size_t rsize = oldsize + nextsize - nb; + unlink_chunk(m, next, nextsize); + if (rsize < MIN_CHUNK_SIZE) { + size_t newsize = oldsize + nextsize; + set_inuse(m, p, newsize); + } + else { + mchunkptr r = chunk_plus_offset(p, nb); + set_inuse(m, p, nb); + set_inuse(m, r, rsize); + dispose_chunk(m, r, rsize); + } + newp = p; + } + } + } + else { + USAGE_ERROR_ACTION(m, chunk2mem(p)); + } + return newp; +} + +static void* internal_memalign(mstate m, size_t alignment, size_t bytes) { + void* mem = 0; + if (alignment < MIN_CHUNK_SIZE) /* must be at least a minimum chunk size */ + alignment = MIN_CHUNK_SIZE; + if ((alignment & (alignment-SIZE_T_ONE)) != 0) {/* Ensure a power of 2 */ + size_t a = MALLOC_ALIGNMENT << 1; + while (a < alignment) a <<= 1; + alignment = a; + } + if (bytes >= MAX_REQUEST - alignment) { + if (m != 0) { /* Test isn't needed but avoids compiler warning */ + MALLOC_FAILURE_ACTION; + } + } + else { + size_t nb = request2size(bytes); + size_t req = nb + alignment + MIN_CHUNK_SIZE - CHUNK_OVERHEAD; + mem = internal_malloc(m, req); + if (mem != 0) { + mchunkptr p = mem2chunk(mem); + if (PREACTION(m)) + return 0; + if ((((size_t)(mem)) & (alignment - 1)) != 0) { /* misaligned */ + /* + Find an aligned spot inside chunk. Since we need to give + back leading space in a chunk of at least MIN_CHUNK_SIZE, if + the first calculation places us at a spot with less than + MIN_CHUNK_SIZE leader, we can move to the next aligned spot. + We've allocated enough total room so that this is always + possible. + */ + char* br = (char*)mem2chunk((size_t)(((size_t)((char*)mem + alignment - + SIZE_T_ONE)) & + -alignment)); + char* pos = ((size_t)(br - (char*)(p)) >= MIN_CHUNK_SIZE)? + br : br+alignment; + mchunkptr newp = (mchunkptr)pos; + size_t leadsize = pos - (char*)(p); + size_t newsize = chunksize(p) - leadsize; + + if (is_mmapped(p)) { /* For mmapped chunks, just adjust offset */ + newp->prev_foot = p->prev_foot + leadsize; + newp->head = newsize; + } + else { /* Otherwise, give back leader, use the rest */ + set_inuse(m, newp, newsize); + set_inuse(m, p, leadsize); + dispose_chunk(m, p, leadsize); + } + p = newp; + } + + /* Give back spare room at the end */ + if (!is_mmapped(p)) { + size_t size = chunksize(p); + if (size > nb + MIN_CHUNK_SIZE) { + size_t remainder_size = size - nb; + mchunkptr remainder = chunk_plus_offset(p, nb); + set_inuse(m, p, nb); + set_inuse(m, remainder, remainder_size); + dispose_chunk(m, remainder, remainder_size); + } + } + + mem = chunk2mem(p); + assert (chunksize(p) >= nb); + assert(((size_t)mem & (alignment - 1)) == 0); + check_inuse_chunk(m, p); + POSTACTION(m); + } + } + return mem; +} + +/* + Common support for independent_X routines, handling + all of the combinations that can result. + The opts arg has: + bit 0 set if all elements are same size (using sizes[0]) + bit 1 set if elements should be zeroed +*/ +static void** ialloc(mstate m, + size_t n_elements, + size_t* sizes, + int opts, + void* chunks[]) { + + size_t element_size; /* chunksize of each element, if all same */ + size_t contents_size; /* total size of elements */ + size_t array_size; /* request size of pointer array */ + void* mem; /* malloced aggregate space */ + mchunkptr p; /* corresponding chunk */ + size_t remainder_size; /* remaining bytes while splitting */ + void** marray; /* either "chunks" or malloced ptr array */ + mchunkptr array_chunk; /* chunk for malloced ptr array */ + flag_t was_enabled; /* to disable mmap */ + size_t size; + size_t i; + + ensure_initialization(); + /* compute array length, if needed */ + if (chunks != 0) { + if (n_elements == 0) + return chunks; /* nothing to do */ + marray = chunks; + array_size = 0; + } + else { + /* if empty req, must still return chunk representing empty array */ + if (n_elements == 0) + return (void**)internal_malloc(m, 0); + marray = 0; + array_size = request2size(n_elements * (sizeof(void*))); + } + + /* compute total element size */ + if (opts & 0x1) { /* all-same-size */ + element_size = request2size(*sizes); + contents_size = n_elements * element_size; + } + else { /* add up all the sizes */ + element_size = 0; + contents_size = 0; + for (i = 0; i != n_elements; ++i) + contents_size += request2size(sizes[i]); + } + + size = contents_size + array_size; + + /* + Allocate the aggregate chunk. First disable direct-mmapping so + malloc won't use it, since we would not be able to later + free/realloc space internal to a segregated mmap region. + */ + was_enabled = use_mmap(m); + disable_mmap(m); + mem = internal_malloc(m, size - CHUNK_OVERHEAD); + if (was_enabled) + enable_mmap(m); + if (mem == 0) + return 0; + + if (PREACTION(m)) return 0; + p = mem2chunk(mem); + remainder_size = chunksize(p); + + assert(!is_mmapped(p)); + + if (opts & 0x2) { /* optionally clear the elements */ + memset((size_t*)mem, 0, remainder_size - SIZE_T_SIZE - array_size); + } + + /* If not provided, allocate the pointer array as final part of chunk */ + if (marray == 0) { + size_t array_chunk_size; + array_chunk = chunk_plus_offset(p, contents_size); + array_chunk_size = remainder_size - contents_size; + marray = (void**) (chunk2mem(array_chunk)); + set_size_and_pinuse_of_inuse_chunk(m, array_chunk, array_chunk_size); + remainder_size = contents_size; + } + + /* split out elements */ + for (i = 0; ; ++i) { + marray[i] = chunk2mem(p); + if (i != n_elements-1) { + if (element_size != 0) + size = element_size; + else + size = request2size(sizes[i]); + remainder_size -= size; + set_size_and_pinuse_of_inuse_chunk(m, p, size); + p = chunk_plus_offset(p, size); + } + else { /* the final element absorbs any overallocation slop */ + set_size_and_pinuse_of_inuse_chunk(m, p, remainder_size); + break; + } + } + +#if DEBUG + if (marray != chunks) { + /* final element must have exactly exhausted chunk */ + if (element_size != 0) { + assert(remainder_size == element_size); + } + else { + assert(remainder_size == request2size(sizes[i])); + } + check_inuse_chunk(m, mem2chunk(marray)); + } + for (i = 0; i != n_elements; ++i) + check_inuse_chunk(m, mem2chunk(marray[i])); + +#endif /* DEBUG */ + + POSTACTION(m); + return marray; +} + +/* Try to free all pointers in the given array. + Note: this could be made faster, by delaying consolidation, + at the price of disabling some user integrity checks, We + still optimize some consolidations by combining adjacent + chunks before freeing, which will occur often if allocated + with ialloc or the array is sorted. +*/ +static size_t internal_bulk_free(mstate m, void* array[], size_t nelem) { + size_t unfreed = 0; + if (!PREACTION(m)) { + void** a; + void** fence = &(array[nelem]); + for (a = array; a != fence; ++a) { + void* mem = *a; + if (mem != 0) { + mchunkptr p = mem2chunk(mem); + size_t psize = chunksize(p); +#if FOOTERS + if (get_mstate_for(p) != m) { + ++unfreed; + continue; + } +#endif + check_inuse_chunk(m, p); + *a = 0; + if (RTCHECK(ok_address(m, p) && ok_inuse(p))) { + void ** b = a + 1; /* try to merge with next chunk */ + mchunkptr next = next_chunk(p); + if (b != fence && *b == chunk2mem(next)) { + size_t newsize = chunksize(next) + psize; + set_inuse(m, p, newsize); + *b = chunk2mem(p); + } + else + dispose_chunk(m, p, psize); + } + else { + CORRUPTION_ERROR_ACTION(m); + break; + } + } + } + if (should_trim(m, m->topsize)) + sys_trim(m, 0); + POSTACTION(m); + } + return unfreed; +} + +/* Traversal */ +#if MALLOC_INSPECT_ALL +static void internal_inspect_all(mstate m, + void(*handler)(void *start, + void *end, + size_t used_bytes, + void* callback_arg), + void* arg) { + if (is_initialized(m)) { + mchunkptr top = m->top; + msegmentptr s; + for (s = &m->seg; s != 0; s = s->next) { + mchunkptr q = align_as_chunk(s->base); + while (segment_holds(s, q) && q->head != FENCEPOST_HEAD) { + mchunkptr next = next_chunk(q); + size_t sz = chunksize(q); + size_t used; + void* start; + if (is_inuse(q)) { + used = sz - CHUNK_OVERHEAD; /* must not be mmapped */ + start = chunk2mem(q); + } + else { + used = 0; + if (is_small(sz)) { /* offset by possible bookkeeping */ + start = (void*)((char*)q + sizeof(struct malloc_chunk)); + } + else { + start = (void*)((char*)q + sizeof(struct malloc_tree_chunk)); + } + } + if (start < (void*)next) /* skip if all space is bookkeeping */ + handler(start, next, used, arg); + if (q == top) + break; + q = next; + } + } + } +} +#endif /* MALLOC_INSPECT_ALL */ + +/* ------------------ Exported realloc, memalign, etc -------------------- */ + +#if !ONLY_MSPACES + +void* dlrealloc(void* oldmem, size_t bytes) { + void* mem = 0; + if (oldmem == 0) { + mem = dlmalloc(bytes); + } + else if (bytes >= MAX_REQUEST) { + MALLOC_FAILURE_ACTION; + } +#ifdef REALLOC_ZERO_BYTES_FREES + else if (bytes == 0) { + dlfree(oldmem); + } +#endif /* REALLOC_ZERO_BYTES_FREES */ + else { + size_t nb = request2size(bytes); + mchunkptr oldp = mem2chunk(oldmem); +#if ! FOOTERS + mstate m = gm; +#else /* FOOTERS */ + mstate m = get_mstate_for(oldp); + if (!ok_magic(m)) { + USAGE_ERROR_ACTION(m, oldmem); + return 0; + } +#endif /* FOOTERS */ + if (!PREACTION(m)) { + mchunkptr newp = try_realloc_chunk(m, oldp, nb, 1); + POSTACTION(m); + if (newp != 0) { + check_inuse_chunk(m, newp); + mem = chunk2mem(newp); + } + else { + mem = internal_malloc(m, bytes); + if (mem != 0) { + size_t oc = chunksize(oldp) - overhead_for(oldp); + memcpy(mem, oldmem, (oc < bytes)? oc : bytes); + internal_free(m, oldmem); + } + } + } + } + return mem; +} + +void* dlrealloc_in_place(void* oldmem, size_t bytes) { + void* mem = 0; + if (oldmem != 0) { + if (bytes >= MAX_REQUEST) { + MALLOC_FAILURE_ACTION; + } + else { + size_t nb = request2size(bytes); + mchunkptr oldp = mem2chunk(oldmem); +#if ! FOOTERS + mstate m = gm; +#else /* FOOTERS */ + mstate m = get_mstate_for(oldp); + if (!ok_magic(m)) { + USAGE_ERROR_ACTION(m, oldmem); + return 0; + } +#endif /* FOOTERS */ + if (!PREACTION(m)) { + mchunkptr newp = try_realloc_chunk(m, oldp, nb, 0); + POSTACTION(m); + if (newp == oldp) { + check_inuse_chunk(m, newp); + mem = oldmem; + } + } + } + } + return mem; +} + +void* dlmemalign(size_t alignment, size_t bytes) { + if (alignment <= MALLOC_ALIGNMENT) { + return dlmalloc(bytes); + } + return internal_memalign(gm, alignment, bytes); +} + +int dlposix_memalign(void** pp, size_t alignment, size_t bytes) { + void* mem = 0; + if (alignment == MALLOC_ALIGNMENT) + mem = dlmalloc(bytes); + else { + size_t d = alignment / sizeof(void*); + size_t r = alignment % sizeof(void*); + if (r != 0 || d == 0 || (d & (d-SIZE_T_ONE)) != 0) + return EINVAL; + else if (bytes <= MAX_REQUEST - alignment) { + if (alignment < MIN_CHUNK_SIZE) + alignment = MIN_CHUNK_SIZE; + mem = internal_memalign(gm, alignment, bytes); + } + } + if (mem == 0) + return ENOMEM; + else { + *pp = mem; + return 0; + } +} + +void* dlvalloc(size_t bytes) { + size_t pagesz; + ensure_initialization(); + pagesz = mparams.page_size; + return dlmemalign(pagesz, bytes); +} + +void* dlpvalloc(size_t bytes) { + size_t pagesz; + ensure_initialization(); + pagesz = mparams.page_size; + return dlmemalign(pagesz, (bytes + pagesz - SIZE_T_ONE) & ~(pagesz - SIZE_T_ONE)); +} + +void** dlindependent_calloc(size_t n_elements, size_t elem_size, + void* chunks[]) { + size_t sz = elem_size; /* serves as 1-element array */ + return ialloc(gm, n_elements, &sz, 3, chunks); +} + +void** dlindependent_comalloc(size_t n_elements, size_t sizes[], + void* chunks[]) { + return ialloc(gm, n_elements, sizes, 0, chunks); +} + +size_t dlbulk_free(void* array[], size_t nelem) { + return internal_bulk_free(gm, array, nelem); +} + +#if MALLOC_INSPECT_ALL +void dlmalloc_inspect_all(void(*handler)(void *start, + void *end, + size_t used_bytes, + void* callback_arg), + void* arg) { + ensure_initialization(); + if (!PREACTION(gm)) { + internal_inspect_all(gm, handler, arg); + POSTACTION(gm); + } +} +#endif /* MALLOC_INSPECT_ALL */ + +int dlmalloc_trim(size_t pad) { + int result = 0; + ensure_initialization(); + if (!PREACTION(gm)) { + result = sys_trim(gm, pad); + POSTACTION(gm); + } + return result; +} + +size_t dlmalloc_footprint(void) { + return gm->footprint; +} + +size_t dlmalloc_max_footprint(void) { + return gm->max_footprint; +} + +size_t dlmalloc_footprint_limit(void) { + size_t maf = gm->footprint_limit; + return maf == 0 ? MAX_SIZE_T : maf; +} + +size_t dlmalloc_set_footprint_limit(size_t bytes) { + size_t result; /* invert sense of 0 */ + if (bytes == 0) + result = granularity_align(1); /* Use minimal size */ + if (bytes == MAX_SIZE_T) + result = 0; /* disable */ + else + result = granularity_align(bytes); + return gm->footprint_limit = result; +} + +#if !NO_MALLINFO +struct mallinfo dlmallinfo(void) { + return internal_mallinfo(gm); +} +#endif /* NO_MALLINFO */ + +#if !NO_MALLOC_STATS +void dlmalloc_stats() { + internal_malloc_stats(gm); +} +#endif /* NO_MALLOC_STATS */ + +int dlmallopt(int param_number, int value) { + return change_mparam(param_number, value); +} + +size_t dlmalloc_usable_size(void* mem) { + if (mem != 0) { + mchunkptr p = mem2chunk(mem); + if (is_inuse(p)) + return chunksize(p) - overhead_for(p); + } + return 0; +} + +#endif /* !ONLY_MSPACES */ + +/* ----------------------------- user mspaces ---------------------------- */ + +#if MSPACES + +static mstate init_user_mstate(char* tbase, size_t tsize) { + size_t msize = pad_request(sizeof(struct malloc_state)); + mchunkptr mn; + mchunkptr msp = align_as_chunk(tbase); + mstate m = (mstate)(chunk2mem(msp)); + memset(m, 0, msize); + (void)INITIAL_LOCK(&m->mutex); + msp->head = (msize|INUSE_BITS); + m->seg.base = m->least_addr = tbase; + m->seg.size = m->footprint = m->max_footprint = tsize; + m->magic = mparams.magic; + m->release_checks = MAX_RELEASE_CHECK_RATE; + m->mflags = mparams.default_mflags; + m->extp = 0; + m->exts = 0; + disable_contiguous(m); + init_bins(m); + mn = next_chunk(mem2chunk(m)); + init_top(m, mn, (size_t)((tbase + tsize) - (char*)mn) - TOP_FOOT_SIZE); + check_top_chunk(m, m->top); + return m; +} + +mspace create_mspace(size_t capacity, int locked) { + mstate m = 0; + size_t msize; + ensure_initialization(); + msize = pad_request(sizeof(struct malloc_state)); + if (capacity < (size_t) -(msize + TOP_FOOT_SIZE + mparams.page_size)) { + size_t rs = ((capacity == 0)? mparams.granularity : + (capacity + TOP_FOOT_SIZE + msize)); + size_t tsize = granularity_align(rs); + char* tbase = (char*)(CALL_MMAP(tsize)); + if (tbase != CMFAIL) { + m = init_user_mstate(tbase, tsize); + m->seg.sflags = USE_MMAP_BIT; + set_lock(m, locked); + } + } + return (mspace)m; +} + +mspace create_mspace_with_base(void* base, size_t capacity, int locked) { + mstate m = 0; + size_t msize; + ensure_initialization(); + msize = pad_request(sizeof(struct malloc_state)); + if (capacity > msize + TOP_FOOT_SIZE && + capacity < (size_t) -(msize + TOP_FOOT_SIZE + mparams.page_size)) { + m = init_user_mstate((char*)base, capacity); + m->seg.sflags = EXTERN_BIT; + set_lock(m, locked); + } + return (mspace)m; +} + +int mspace_track_large_chunks(mspace msp, int enable) { + int ret = 0; + mstate ms = (mstate)msp; + if (!PREACTION(ms)) { + if (!use_mmap(ms)) { + ret = 1; + } + if (!enable) { + enable_mmap(ms); + } else { + disable_mmap(ms); + } + POSTACTION(ms); + } + return ret; +} + +size_t destroy_mspace(mspace msp) { + size_t freed = 0; + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + msegmentptr sp = &ms->seg; + (void)DESTROY_LOCK(&ms->mutex); /* destroy before unmapped */ + while (sp != 0) { + char* base = sp->base; + size_t size = sp->size; + flag_t flag = sp->sflags; + (void)base; /* placate people compiling -Wunused-variable */ + sp = sp->next; + if ((flag & USE_MMAP_BIT) && !(flag & EXTERN_BIT) && + CALL_MUNMAP(base, size) == 0) + freed += size; + } + } + else { + USAGE_ERROR_ACTION(ms,ms); + } + return freed; +} + +/* + mspace versions of routines are near-clones of the global + versions. This is not so nice but better than the alternatives. +*/ + +void* mspace_malloc(mspace msp, size_t bytes) { + mstate ms = (mstate)msp; + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + return 0; + } + if (!PREACTION(ms)) { + void* mem; + size_t nb; + if (bytes <= MAX_SMALL_REQUEST) { + bindex_t idx; + binmap_t smallbits; + nb = (bytes < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(bytes); + idx = small_index(nb); + smallbits = ms->smallmap >> idx; + + if ((smallbits & 0x3U) != 0) { /* Remainderless fit to a smallbin. */ + mchunkptr b, p; + idx += ~smallbits & 1; /* Uses next bin if idx empty */ + b = smallbin_at(ms, idx); + p = b->fd; + assert(chunksize(p) == small_index2size(idx)); + unlink_first_small_chunk(ms, b, p, idx); + set_inuse_and_pinuse(ms, p, small_index2size(idx)); + mem = chunk2mem(p); + check_malloced_chunk(ms, mem, nb); + goto postaction; + } + + else if (nb > ms->dvsize) { + if (smallbits != 0) { /* Use chunk in next nonempty smallbin */ + mchunkptr b, p, r; + size_t rsize; + bindex_t i; + binmap_t leftbits = (smallbits << idx) & left_bits(idx2bit(idx)); + binmap_t leastbit = least_bit(leftbits); + compute_bit2idx(leastbit, i); + b = smallbin_at(ms, i); + p = b->fd; + assert(chunksize(p) == small_index2size(i)); + unlink_first_small_chunk(ms, b, p, i); + rsize = small_index2size(i) - nb; + /* Fit here cannot be remainderless if 4byte sizes */ + if (SIZE_T_SIZE != 4 && rsize < MIN_CHUNK_SIZE) + set_inuse_and_pinuse(ms, p, small_index2size(i)); + else { + set_size_and_pinuse_of_inuse_chunk(ms, p, nb); + r = chunk_plus_offset(p, nb); + set_size_and_pinuse_of_free_chunk(r, rsize); + replace_dv(ms, r, rsize); + } + mem = chunk2mem(p); + check_malloced_chunk(ms, mem, nb); + goto postaction; + } + + else if (ms->treemap != 0 && (mem = tmalloc_small(ms, nb)) != 0) { + check_malloced_chunk(ms, mem, nb); + goto postaction; + } + } + } + else if (bytes >= MAX_REQUEST) + nb = MAX_SIZE_T; /* Too big to allocate. Force failure (in sys alloc) */ + else { + nb = pad_request(bytes); + if (ms->treemap != 0 && (mem = tmalloc_large(ms, nb)) != 0) { + check_malloced_chunk(ms, mem, nb); + goto postaction; + } + } + + if (nb <= ms->dvsize) { + size_t rsize = ms->dvsize - nb; + mchunkptr p = ms->dv; + if (rsize >= MIN_CHUNK_SIZE) { /* split dv */ + mchunkptr r = ms->dv = chunk_plus_offset(p, nb); + ms->dvsize = rsize; + set_size_and_pinuse_of_free_chunk(r, rsize); + set_size_and_pinuse_of_inuse_chunk(ms, p, nb); + } + else { /* exhaust dv */ + size_t dvs = ms->dvsize; + ms->dvsize = 0; + ms->dv = 0; + set_inuse_and_pinuse(ms, p, dvs); + } + mem = chunk2mem(p); + check_malloced_chunk(ms, mem, nb); + goto postaction; + } + + else if (nb < ms->topsize) { /* Split top */ + size_t rsize = ms->topsize -= nb; + mchunkptr p = ms->top; + mchunkptr r = ms->top = chunk_plus_offset(p, nb); + r->head = rsize | PINUSE_BIT; + set_size_and_pinuse_of_inuse_chunk(ms, p, nb); + mem = chunk2mem(p); + check_top_chunk(ms, ms->top); + check_malloced_chunk(ms, mem, nb); + goto postaction; + } + + mem = sys_alloc(ms, nb); + + postaction: + POSTACTION(ms); + return mem; + } + + return 0; +} + +void mspace_free(mspace msp, void* mem) { + if (mem != 0) { + mchunkptr p = mem2chunk(mem); +#if FOOTERS + mstate fm = get_mstate_for(p); + (void)msp; /* placate people compiling -Wunused */ +#else /* FOOTERS */ + mstate fm = (mstate)msp; +#endif /* FOOTERS */ + if (!ok_magic(fm)) { + USAGE_ERROR_ACTION(fm, p); + return; + } + if (!PREACTION(fm)) { + check_inuse_chunk(fm, p); + if (RTCHECK(ok_address(fm, p) && ok_inuse(p))) { + size_t psize = chunksize(p); + mchunkptr next = chunk_plus_offset(p, psize); + if (!pinuse(p)) { + size_t prevsize = p->prev_foot; + if (is_mmapped(p)) { + psize += prevsize + MMAP_FOOT_PAD; + if (CALL_MUNMAP((char*)p - prevsize, psize) == 0) + fm->footprint -= psize; + goto postaction; + } + else { + mchunkptr prev = chunk_minus_offset(p, prevsize); + psize += prevsize; + p = prev; + if (RTCHECK(ok_address(fm, prev))) { /* consolidate backward */ + if (p != fm->dv) { + unlink_chunk(fm, p, prevsize); + } + else if ((next->head & INUSE_BITS) == INUSE_BITS) { + fm->dvsize = psize; + set_free_with_pinuse(p, psize, next); + goto postaction; + } + } + else + goto erroraction; + } + } + + if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) { + if (!cinuse(next)) { /* consolidate forward */ + if (next == fm->top) { + size_t tsize = fm->topsize += psize; + fm->top = p; + p->head = tsize | PINUSE_BIT; + if (p == fm->dv) { + fm->dv = 0; + fm->dvsize = 0; + } + if (should_trim(fm, tsize)) + sys_trim(fm, 0); + goto postaction; + } + else if (next == fm->dv) { + size_t dsize = fm->dvsize += psize; + fm->dv = p; + set_size_and_pinuse_of_free_chunk(p, dsize); + goto postaction; + } + else { + size_t nsize = chunksize(next); + psize += nsize; + unlink_chunk(fm, next, nsize); + set_size_and_pinuse_of_free_chunk(p, psize); + if (p == fm->dv) { + fm->dvsize = psize; + goto postaction; + } + } + } + else + set_free_with_pinuse(p, psize, next); + + if (is_small(psize)) { + insert_small_chunk(fm, p, psize); + check_free_chunk(fm, p); + } + else { + tchunkptr tp = (tchunkptr)p; + insert_large_chunk(fm, tp, psize); + check_free_chunk(fm, p); + if (--fm->release_checks == 0) + release_unused_segments(fm); + } + goto postaction; + } + } + erroraction: + USAGE_ERROR_ACTION(fm, p); + postaction: + POSTACTION(fm); + } + } +} + +void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size) { + void* mem; + size_t req = 0; + mstate ms = (mstate)msp; + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + return 0; + } + if (n_elements != 0) { + req = n_elements * elem_size; + if (((n_elements | elem_size) & ~(size_t)0xffff) && + (req / n_elements != elem_size)) + req = MAX_SIZE_T; /* force downstream failure on overflow */ + } + mem = internal_malloc(ms, req); + if (mem != 0 && calloc_must_clear(mem2chunk(mem))) + memset(mem, 0, req); + return mem; +} + +void* mspace_realloc(mspace msp, void* oldmem, size_t bytes) { + void* mem = 0; + if (oldmem == 0) { + mem = mspace_malloc(msp, bytes); + } + else if (bytes >= MAX_REQUEST) { + MALLOC_FAILURE_ACTION; + } +#ifdef REALLOC_ZERO_BYTES_FREES + else if (bytes == 0) { + mspace_free(msp, oldmem); + } +#endif /* REALLOC_ZERO_BYTES_FREES */ + else { + size_t nb = request2size(bytes); + mchunkptr oldp = mem2chunk(oldmem); +#if ! FOOTERS + mstate m = (mstate)msp; +#else /* FOOTERS */ + mstate m = get_mstate_for(oldp); + if (!ok_magic(m)) { + USAGE_ERROR_ACTION(m, oldmem); + return 0; + } +#endif /* FOOTERS */ + if (!PREACTION(m)) { + mchunkptr newp = try_realloc_chunk(m, oldp, nb, 1); + POSTACTION(m); + if (newp != 0) { + check_inuse_chunk(m, newp); + mem = chunk2mem(newp); + } + else { + mem = mspace_malloc(m, bytes); + if (mem != 0) { + size_t oc = chunksize(oldp) - overhead_for(oldp); + memcpy(mem, oldmem, (oc < bytes)? oc : bytes); + mspace_free(m, oldmem); + } + } + } + } + return mem; +} + +void* mspace_realloc_in_place(mspace msp, void* oldmem, size_t bytes) { + void* mem = 0; + if (oldmem != 0) { + if (bytes >= MAX_REQUEST) { + MALLOC_FAILURE_ACTION; + } + else { + size_t nb = request2size(bytes); + mchunkptr oldp = mem2chunk(oldmem); +#if ! FOOTERS + mstate m = (mstate)msp; +#else /* FOOTERS */ + mstate m = get_mstate_for(oldp); + (void)msp; /* placate people compiling -Wunused */ + if (!ok_magic(m)) { + USAGE_ERROR_ACTION(m, oldmem); + return 0; + } +#endif /* FOOTERS */ + if (!PREACTION(m)) { + mchunkptr newp = try_realloc_chunk(m, oldp, nb, 0); + POSTACTION(m); + if (newp == oldp) { + check_inuse_chunk(m, newp); + mem = oldmem; + } + } + } + } + return mem; +} + +void* mspace_memalign(mspace msp, size_t alignment, size_t bytes) { + mstate ms = (mstate)msp; + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + return 0; + } + if (alignment <= MALLOC_ALIGNMENT) + return mspace_malloc(msp, bytes); + return internal_memalign(ms, alignment, bytes); +} + +void** mspace_independent_calloc(mspace msp, size_t n_elements, + size_t elem_size, void* chunks[]) { + size_t sz = elem_size; /* serves as 1-element array */ + mstate ms = (mstate)msp; + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + return 0; + } + return ialloc(ms, n_elements, &sz, 3, chunks); +} + +void** mspace_independent_comalloc(mspace msp, size_t n_elements, + size_t sizes[], void* chunks[]) { + mstate ms = (mstate)msp; + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + return 0; + } + return ialloc(ms, n_elements, sizes, 0, chunks); +} + +size_t mspace_bulk_free(mspace msp, void* array[], size_t nelem) { + return internal_bulk_free((mstate)msp, array, nelem); +} + +#if MALLOC_INSPECT_ALL +void mspace_inspect_all(mspace msp, + void(*handler)(void *start, + void *end, + size_t used_bytes, + void* callback_arg), + void* arg) { + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + if (!PREACTION(ms)) { + internal_inspect_all(ms, handler, arg); + POSTACTION(ms); + } + } + else { + USAGE_ERROR_ACTION(ms,ms); + } +} +#endif /* MALLOC_INSPECT_ALL */ + +int mspace_trim(mspace msp, size_t pad) { + int result = 0; + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + if (!PREACTION(ms)) { + result = sys_trim(ms, pad); + POSTACTION(ms); + } + } + else { + USAGE_ERROR_ACTION(ms,ms); + } + return result; +} + +#if !NO_MALLOC_STATS +void mspace_malloc_stats(mspace msp) { + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + internal_malloc_stats(ms); + } + else { + USAGE_ERROR_ACTION(ms,ms); + } +} +#endif /* NO_MALLOC_STATS */ + +size_t mspace_footprint(mspace msp) { + size_t result = 0; + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + result = ms->footprint; + } + else { + USAGE_ERROR_ACTION(ms,ms); + } + return result; +} + +size_t mspace_max_footprint(mspace msp) { + size_t result = 0; + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + result = ms->max_footprint; + } + else { + USAGE_ERROR_ACTION(ms,ms); + } + return result; +} + +size_t mspace_footprint_limit(mspace msp) { + size_t result = 0; + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + size_t maf = ms->footprint_limit; + result = (maf == 0) ? MAX_SIZE_T : maf; + } + else { + USAGE_ERROR_ACTION(ms,ms); + } + return result; +} + +size_t mspace_set_footprint_limit(mspace msp, size_t bytes) { + size_t result = 0; + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + if (bytes == 0) + result = granularity_align(1); /* Use minimal size */ + if (bytes == MAX_SIZE_T) + result = 0; /* disable */ + else + result = granularity_align(bytes); + ms->footprint_limit = result; + } + else { + USAGE_ERROR_ACTION(ms,ms); + } + return result; +} + +#if !NO_MALLINFO +struct mallinfo mspace_mallinfo(mspace msp) { + mstate ms = (mstate)msp; + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + } + return internal_mallinfo(ms); +} +#endif /* NO_MALLINFO */ + +size_t mspace_usable_size(const void* mem) { + if (mem != 0) { + mchunkptr p = mem2chunk(mem); + if (is_inuse(p)) + return chunksize(p) - overhead_for(p); + } + return 0; +} + +int mspace_mallopt(int param_number, int value) { + return change_mparam(param_number, value); +} + +#endif /* MSPACES */ + + +/* -------------------- Alternative MORECORE functions ------------------- */ + +/* + Guidelines for creating a custom version of MORECORE: + + * For best performance, MORECORE should allocate in multiples of pagesize. + * MORECORE may allocate more memory than requested. (Or even less, + but this will usually result in a malloc failure.) + * MORECORE must not allocate memory when given argument zero, but + instead return one past the end address of memory from previous + nonzero call. + * For best performance, consecutive calls to MORECORE with positive + arguments should return increasing addresses, indicating that + space has been contiguously extended. + * Even though consecutive calls to MORECORE need not return contiguous + addresses, it must be OK for malloc'ed chunks to span multiple + regions in those cases where they do happen to be contiguous. + * MORECORE need not handle negative arguments -- it may instead + just return MFAIL when given negative arguments. + Negative arguments are always multiples of pagesize. MORECORE + must not misinterpret negative args as large positive unsigned + args. You can suppress all such calls from even occurring by defining + MORECORE_CANNOT_TRIM, + + As an example alternative MORECORE, here is a custom allocator + kindly contributed for pre-OSX macOS. It uses virtually but not + necessarily physically contiguous non-paged memory (locked in, + present and won't get swapped out). You can use it by uncommenting + this section, adding some #includes, and setting up the appropriate + defines above: + + #define MORECORE osMoreCore + + There is also a shutdown routine that should somehow be called for + cleanup upon program exit. + + #define MAX_POOL_ENTRIES 100 + #define MINIMUM_MORECORE_SIZE (64 * 1024U) + static int next_os_pool; + void *our_os_pools[MAX_POOL_ENTRIES]; + + void *osMoreCore(int size) + { + void *ptr = 0; + static void *sbrk_top = 0; + + if (size > 0) + { + if (size < MINIMUM_MORECORE_SIZE) + size = MINIMUM_MORECORE_SIZE; + if (CurrentExecutionLevel() == kTaskLevel) + ptr = PoolAllocateResident(size + RM_PAGE_SIZE, 0); + if (ptr == 0) + { + return (void *) MFAIL; + } + // save ptrs so they can be freed during cleanup + our_os_pools[next_os_pool] = ptr; + next_os_pool++; + ptr = (void *) ((((size_t) ptr) + RM_PAGE_MASK) & ~RM_PAGE_MASK); + sbrk_top = (char *) ptr + size; + return ptr; + } + else if (size < 0) + { + // we don't currently support shrink behavior + return (void *) MFAIL; + } + else + { + return sbrk_top; + } + } + + // cleanup any allocated memory pools + // called as last thing before shutting down driver + + void osCleanupMem(void) + { + void **ptr; + + for (ptr = our_os_pools; ptr < &our_os_pools[MAX_POOL_ENTRIES]; ptr++) + if (*ptr) + { + PoolDeallocate(*ptr); + *ptr = 0; + } + } + +*/ + + +/* ----------------------------------------------------------------------- +History: + v2.8.6 Wed Aug 29 06:57:58 2012 Doug Lea + * fix bad comparison in dlposix_memalign + * don't reuse adjusted asize in sys_alloc + * add LOCK_AT_FORK -- thanks to Kirill Artamonov for the suggestion + * reduce compiler warnings -- thanks to all who reported/suggested these + + v2.8.5 Sun May 22 10:26:02 2011 Doug Lea (dl at gee) + * Always perform unlink checks unless INSECURE + * Add posix_memalign. + * Improve realloc to expand in more cases; expose realloc_in_place. + Thanks to Peter Buhr for the suggestion. + * Add footprint_limit, inspect_all, bulk_free. Thanks + to Barry Hayes and others for the suggestions. + * Internal refactorings to avoid calls while holding locks + * Use non-reentrant locks by default. Thanks to Roland McGrath + for the suggestion. + * Small fixes to mspace_destroy, reset_on_error. + * Various configuration extensions/changes. Thanks + to all who contributed these. + + V2.8.4a Thu Apr 28 14:39:43 2011 (dl at gee.cs.oswego.edu) + * Update Creative Commons URL + + V2.8.4 Wed May 27 09:56:23 2009 Doug Lea (dl at gee) + * Use zeros instead of prev foot for is_mmapped + * Add mspace_track_large_chunks; thanks to Jean Brouwers + * Fix set_inuse in internal_realloc; thanks to Jean Brouwers + * Fix insufficient sys_alloc padding when using 16byte alignment + * Fix bad error check in mspace_footprint + * Adaptations for ptmalloc; thanks to Wolfram Gloger. + * Reentrant spin locks; thanks to Earl Chew and others + * Win32 improvements; thanks to Niall Douglas and Earl Chew + * Add NO_SEGMENT_TRAVERSAL and MAX_RELEASE_CHECK_RATE options + * Extension hook in malloc_state + * Various small adjustments to reduce warnings on some compilers + * Various configuration extensions/changes for more platforms. Thanks + to all who contributed these. + + V2.8.3 Thu Sep 22 11:16:32 2005 Doug Lea (dl at gee) + * Add max_footprint functions + * Ensure all appropriate literals are size_t + * Fix conditional compilation problem for some #define settings + * Avoid concatenating segments with the one provided + in create_mspace_with_base + * Rename some variables to avoid compiler shadowing warnings + * Use explicit lock initialization. + * Better handling of sbrk interference. + * Simplify and fix segment insertion, trimming and mspace_destroy + * Reinstate REALLOC_ZERO_BYTES_FREES option from 2.7.x + * Thanks especially to Dennis Flanagan for help on these. + + V2.8.2 Sun Jun 12 16:01:10 2005 Doug Lea (dl at gee) + * Fix memalign brace error. + + V2.8.1 Wed Jun 8 16:11:46 2005 Doug Lea (dl at gee) + * Fix improper #endif nesting in C++ + * Add explicit casts needed for C++ + + V2.8.0 Mon May 30 14:09:02 2005 Doug Lea (dl at gee) + * Use trees for large bins + * Support mspaces + * Use segments to unify sbrk-based and mmap-based system allocation, + removing need for emulation on most platforms without sbrk. + * Default safety checks + * Optional footer checks. Thanks to William Robertson for the idea. + * Internal code refactoring + * Incorporate suggestions and platform-specific changes. + Thanks to Dennis Flanagan, Colin Plumb, Niall Douglas, + Aaron Bachmann, Emery Berger, and others. + * Speed up non-fastbin processing enough to remove fastbins. + * Remove useless cfree() to avoid conflicts with other apps. + * Remove internal memcpy, memset. Compilers handle builtins better. + * Remove some options that no one ever used and rename others. + + V2.7.2 Sat Aug 17 09:07:30 2002 Doug Lea (dl at gee) + * Fix malloc_state bitmap array misdeclaration + + V2.7.1 Thu Jul 25 10:58:03 2002 Doug Lea (dl at gee) + * Allow tuning of FIRST_SORTED_BIN_SIZE + * Use PTR_UINT as type for all ptr->int casts. Thanks to John Belmonte. + * Better detection and support for non-contiguousness of MORECORE. + Thanks to Andreas Mueller, Conal Walsh, and Wolfram Gloger + * Bypass most of malloc if no frees. Thanks To Emery Berger. + * Fix freeing of old top non-contiguous chunk im sysmalloc. + * Raised default trim and map thresholds to 256K. + * Fix mmap-related #defines. Thanks to Lubos Lunak. + * Fix copy macros; added LACKS_FCNTL_H. Thanks to Neal Walfield. + * Branch-free bin calculation + * Default trim and mmap thresholds now 256K. + + V2.7.0 Sun Mar 11 14:14:06 2001 Doug Lea (dl at gee) + * Introduce independent_comalloc and independent_calloc. + Thanks to Michael Pachos for motivation and help. + * Make optional .h file available + * Allow > 2GB requests on 32bit systems. + * new WIN32 sbrk, mmap, munmap, lock code from . + Thanks also to Andreas Mueller , + and Anonymous. + * Allow override of MALLOC_ALIGNMENT (Thanks to Ruud Waij for + helping test this.) + * memalign: check alignment arg + * realloc: don't try to shift chunks backwards, since this + leads to more fragmentation in some programs and doesn't + seem to help in any others. + * Collect all cases in malloc requiring system memory into sysmalloc + * Use mmap as backup to sbrk + * Place all internal state in malloc_state + * Introduce fastbins (although similar to 2.5.1) + * Many minor tunings and cosmetic improvements + * Introduce USE_PUBLIC_MALLOC_WRAPPERS, USE_MALLOC_LOCK + * Introduce MALLOC_FAILURE_ACTION, MORECORE_CONTIGUOUS + Thanks to Tony E. Bennett and others. + * Include errno.h to support default failure action. + + V2.6.6 Sun Dec 5 07:42:19 1999 Doug Lea (dl at gee) + * return null for negative arguments + * Added Several WIN32 cleanups from Martin C. Fong + * Add 'LACKS_SYS_PARAM_H' for those systems without 'sys/param.h' + (e.g. WIN32 platforms) + * Cleanup header file inclusion for WIN32 platforms + * Cleanup code to avoid Microsoft Visual C++ compiler complaints + * Add 'USE_DL_PREFIX' to quickly allow co-existence with existing + memory allocation routines + * Set 'malloc_getpagesize' for WIN32 platforms (needs more work) + * Use 'assert' rather than 'ASSERT' in WIN32 code to conform to + usage of 'assert' in non-WIN32 code + * Improve WIN32 'sbrk()' emulation's 'findRegion()' routine to + avoid infinite loop + * Always call 'fREe()' rather than 'free()' + + V2.6.5 Wed Jun 17 15:57:31 1998 Doug Lea (dl at gee) + * Fixed ordering problem with boundary-stamping + + V2.6.3 Sun May 19 08:17:58 1996 Doug Lea (dl at gee) + * Added pvalloc, as recommended by H.J. Liu + * Added 64bit pointer support mainly from Wolfram Gloger + * Added anonymously donated WIN32 sbrk emulation + * Malloc, calloc, getpagesize: add optimizations from Raymond Nijssen + * malloc_extend_top: fix mask error that caused wastage after + foreign sbrks + * Add linux mremap support code from HJ Liu + + V2.6.2 Tue Dec 5 06:52:55 1995 Doug Lea (dl at gee) + * Integrated most documentation with the code. + * Add support for mmap, with help from + Wolfram Gloger (Gloger@lrz.uni-muenchen.de). + * Use last_remainder in more cases. + * Pack bins using idea from colin@nyx10.cs.du.edu + * Use ordered bins instead of best-fit threshhold + * Eliminate block-local decls to simplify tracing and debugging. + * Support another case of realloc via move into top + * Fix error occuring when initial sbrk_base not word-aligned. + * Rely on page size for units instead of SBRK_UNIT to + avoid surprises about sbrk alignment conventions. + * Add mallinfo, mallopt. Thanks to Raymond Nijssen + (raymond@es.ele.tue.nl) for the suggestion. + * Add `pad' argument to malloc_trim and top_pad mallopt parameter. + * More precautions for cases where other routines call sbrk, + courtesy of Wolfram Gloger (Gloger@lrz.uni-muenchen.de). + * Added macros etc., allowing use in linux libc from + H.J. Lu (hjl@gnu.ai.mit.edu) + * Inverted this history list + + V2.6.1 Sat Dec 2 14:10:57 1995 Doug Lea (dl at gee) + * Re-tuned and fixed to behave more nicely with V2.6.0 changes. + * Removed all preallocation code since under current scheme + the work required to undo bad preallocations exceeds + the work saved in good cases for most test programs. + * No longer use return list or unconsolidated bins since + no scheme using them consistently outperforms those that don't + given above changes. + * Use best fit for very large chunks to prevent some worst-cases. + * Added some support for debugging + + V2.6.0 Sat Nov 4 07:05:23 1995 Doug Lea (dl at gee) + * Removed footers when chunks are in use. Thanks to + Paul Wilson (wilson@cs.texas.edu) for the suggestion. + + V2.5.4 Wed Nov 1 07:54:51 1995 Doug Lea (dl at gee) + * Added malloc_trim, with help from Wolfram Gloger + (wmglo@Dent.MED.Uni-Muenchen.DE). + + V2.5.3 Tue Apr 26 10:16:01 1994 Doug Lea (dl at g) + + V2.5.2 Tue Apr 5 16:20:40 1994 Doug Lea (dl at g) + * realloc: try to expand in both directions + * malloc: swap order of clean-bin strategy; + * realloc: only conditionally expand backwards + * Try not to scavenge used bins + * Use bin counts as a guide to preallocation + * Occasionally bin return list chunks in first scan + * Add a few optimizations from colin@nyx10.cs.du.edu + + V2.5.1 Sat Aug 14 15:40:43 1993 Doug Lea (dl at g) + * faster bin computation & slightly different binning + * merged all consolidations to one part of malloc proper + (eliminating old malloc_find_space & malloc_clean_bin) + * Scan 2 returns chunks (not just 1) + * Propagate failure in realloc if malloc returns 0 + * Add stuff to allow compilation on non-ANSI compilers + from kpv@research.att.com + + V2.5 Sat Aug 7 07:41:59 1993 Doug Lea (dl at g.oswego.edu) + * removed potential for odd address access in prev_chunk + * removed dependency on getpagesize.h + * misc cosmetics and a bit more internal documentation + * anticosmetics: mangled names in macros to evade debugger strangeness + * tested on sparc, hp-700, dec-mips, rs6000 + with gcc & native cc (hp, dec only) allowing + Detlefs & Zorn comparison study (in SIGPLAN Notices.) + + Trial version Fri Aug 28 13:14:29 1992 Doug Lea (dl at g.oswego.edu) + * Based loosely on libg++-1.2X malloc. (It retains some of the overall + structure of old version, but most details differ.) + +*/ diff --git a/dlmalloc/malloc.h b/dlmalloc/malloc.h new file mode 100644 index 0000000..877d28f --- /dev/null +++ b/dlmalloc/malloc.h @@ -0,0 +1,637 @@ +/* +Copyright 2023 Doug Lea + +Permission is hereby granted, free of charge, to any person obtaining +a copy of this software and associated documentation files (the +"Software"), to deal in the Software without restriction, including +without limitation the rights to use, copy, modify, merge, publish, +distribute, sublicense, and/or sell copies of the Software, and to +permit persons to whom the Software is furnished to do so. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND +NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE +LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION +OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION +WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + + Default header file for malloc-2.8.x + Re-licensed 25 Sep 2023 with MIT-0 replacing obsolete CC0 + See https://opensource.org/license/mit-0/ + + This header is for ANSI C/C++ only. You can set any of + the following #defines before including: + + * If USE_DL_PREFIX is defined, it is assumed that malloc.c + was also compiled with this option, so all routines + have names starting with "dl". + + * If HAVE_USR_INCLUDE_MALLOC_H is defined, it is assumed that this + file will be #included AFTER . This is needed only if + your system defines a struct mallinfo that is incompatible with the + standard one declared here. Otherwise, you can include this file + INSTEAD of your system system . At least on ANSI, all + declarations should be compatible with system versions + + * If MSPACES is defined, declarations for mspace versions are included. +*/ + +#ifndef MALLOC_280_H +#define MALLOC_280_H + +#ifdef __cplusplus +extern "C" { +#endif + +#include /* for size_t */ + +#ifndef ONLY_MSPACES +#define ONLY_MSPACES 0 /* define to a value */ +#elif ONLY_MSPACES != 0 +#define ONLY_MSPACES 1 +#endif /* ONLY_MSPACES */ +#ifndef NO_MALLINFO +#define NO_MALLINFO 0 +#endif /* NO_MALLINFO */ + +#ifndef MSPACES +#if ONLY_MSPACES +#define MSPACES 1 +#else /* ONLY_MSPACES */ +#define MSPACES 0 +#endif /* ONLY_MSPACES */ +#endif /* MSPACES */ + +#if !ONLY_MSPACES + +#ifndef USE_DL_PREFIX +#define dlcalloc calloc +#define dlfree free +#define dlmalloc malloc +#define dlmemalign memalign +#define dlposix_memalign posix_memalign +#define dlrealloc realloc +#define dlvalloc valloc +#define dlpvalloc pvalloc +#define dlmallinfo mallinfo +#define dlmallopt mallopt +#define dlmalloc_trim malloc_trim +#define dlmalloc_stats malloc_stats +#define dlmalloc_usable_size malloc_usable_size +#define dlmalloc_footprint malloc_footprint +#define dlmalloc_max_footprint malloc_max_footprint +#define dlmalloc_footprint_limit malloc_footprint_limit +#define dlmalloc_set_footprint_limit malloc_set_footprint_limit +#define dlmalloc_inspect_all malloc_inspect_all +#define dlindependent_calloc independent_calloc +#define dlindependent_comalloc independent_comalloc +#define dlbulk_free bulk_free +#endif /* USE_DL_PREFIX */ + +#if !NO_MALLINFO +#ifndef HAVE_USR_INCLUDE_MALLOC_H +#ifndef _MALLOC_H +#ifndef MALLINFO_FIELD_TYPE +#define MALLINFO_FIELD_TYPE size_t +#endif /* MALLINFO_FIELD_TYPE */ +#ifndef STRUCT_MALLINFO_DECLARED +#define STRUCT_MALLINFO_DECLARED 1 +struct mallinfo { + MALLINFO_FIELD_TYPE arena; /* non-mmapped space allocated from system */ + MALLINFO_FIELD_TYPE ordblks; /* number of free chunks */ + MALLINFO_FIELD_TYPE smblks; /* always 0 */ + MALLINFO_FIELD_TYPE hblks; /* always 0 */ + MALLINFO_FIELD_TYPE hblkhd; /* space in mmapped regions */ + MALLINFO_FIELD_TYPE usmblks; /* maximum total allocated space */ + MALLINFO_FIELD_TYPE fsmblks; /* always 0 */ + MALLINFO_FIELD_TYPE uordblks; /* total allocated space */ + MALLINFO_FIELD_TYPE fordblks; /* total free space */ + MALLINFO_FIELD_TYPE keepcost; /* releasable (via malloc_trim) space */ +}; +#endif /* STRUCT_MALLINFO_DECLARED */ +#endif /* _MALLOC_H */ +#endif /* HAVE_USR_INCLUDE_MALLOC_H */ +#endif /* !NO_MALLINFO */ + +/* + malloc(size_t n) + Returns a pointer to a newly allocated chunk of at least n bytes, or + null if no space is available, in which case errno is set to ENOMEM + on ANSI C systems. + + If n is zero, malloc returns a minimum-sized chunk. (The minimum + size is 16 bytes on most 32bit systems, and 32 bytes on 64bit + systems.) Note that size_t is an unsigned type, so calls with + arguments that would be negative if signed are interpreted as + requests for huge amounts of space, which will often fail. The + maximum supported value of n differs across systems, but is in all + cases less than the maximum representable value of a size_t. +*/ +void* dlmalloc(size_t); + +/* + free(void* p) + Releases the chunk of memory pointed to by p, that had been previously + allocated using malloc or a related routine such as realloc. + It has no effect if p is null. If p was not malloced or already + freed, free(p) will by default cuase the current program to abort. +*/ +void dlfree(void*); + +/* + calloc(size_t n_elements, size_t element_size); + Returns a pointer to n_elements * element_size bytes, with all locations + set to zero. +*/ +void* dlcalloc(size_t, size_t); + +/* + realloc(void* p, size_t n) + Returns a pointer to a chunk of size n that contains the same data + as does chunk p up to the minimum of (n, p's size) bytes, or null + if no space is available. + + The returned pointer may or may not be the same as p. The algorithm + prefers extending p in most cases when possible, otherwise it + employs the equivalent of a malloc-copy-free sequence. + + If p is null, realloc is equivalent to malloc. + + If space is not available, realloc returns null, errno is set (if on + ANSI) and p is NOT freed. + + if n is for fewer bytes than already held by p, the newly unused + space is lopped off and freed if possible. realloc with a size + argument of zero (re)allocates a minimum-sized chunk. + + The old unix realloc convention of allowing the last-free'd chunk + to be used as an argument to realloc is not supported. +*/ +void* dlrealloc(void*, size_t); + +/* + realloc_in_place(void* p, size_t n) + Resizes the space allocated for p to size n, only if this can be + done without moving p (i.e., only if there is adjacent space + available if n is greater than p's current allocated size, or n is + less than or equal to p's size). This may be used instead of plain + realloc if an alternative allocation strategy is needed upon failure + to expand space; for example, reallocation of a buffer that must be + memory-aligned or cleared. You can use realloc_in_place to trigger + these alternatives only when needed. + + Returns p if successful; otherwise null. +*/ +void* dlrealloc_in_place(void*, size_t); + +/* + memalign(size_t alignment, size_t n); + Returns a pointer to a newly allocated chunk of n bytes, aligned + in accord with the alignment argument. + + The alignment argument should be a power of two. If the argument is + not a power of two, the nearest greater power is used. + 8-byte alignment is guaranteed by normal malloc calls, so don't + bother calling memalign with an argument of 8 or less. + + Overreliance on memalign is a sure way to fragment space. +*/ +void* dlmemalign(size_t, size_t); + +/* + int posix_memalign(void** pp, size_t alignment, size_t n); + Allocates a chunk of n bytes, aligned in accord with the alignment + argument. Differs from memalign only in that it (1) assigns the + allocated memory to *pp rather than returning it, (2) fails and + returns EINVAL if the alignment is not a power of two (3) fails and + returns ENOMEM if memory cannot be allocated. +*/ +int dlposix_memalign(void**, size_t, size_t); + +/* + valloc(size_t n); + Equivalent to memalign(pagesize, n), where pagesize is the page + size of the system. If the pagesize is unknown, 4096 is used. +*/ +void* dlvalloc(size_t); + +/* + mallopt(int parameter_number, int parameter_value) + Sets tunable parameters The format is to provide a + (parameter-number, parameter-value) pair. mallopt then sets the + corresponding parameter to the argument value if it can (i.e., so + long as the value is meaningful), and returns 1 if successful else + 0. SVID/XPG/ANSI defines four standard param numbers for mallopt, + normally defined in malloc.h. None of these are use in this malloc, + so setting them has no effect. But this malloc also supports other + options in mallopt: + + Symbol param # default allowed param values + M_TRIM_THRESHOLD -1 2*1024*1024 any (-1U disables trimming) + M_GRANULARITY -2 page size any power of 2 >= page size + M_MMAP_THRESHOLD -3 256*1024 any (or 0 if no MMAP support) +*/ +int dlmallopt(int, int); + +#define M_TRIM_THRESHOLD (-1) +#define M_GRANULARITY (-2) +#define M_MMAP_THRESHOLD (-3) + + +/* + malloc_footprint(); + Returns the number of bytes obtained from the system. The total + number of bytes allocated by malloc, realloc etc., is less than this + value. Unlike mallinfo, this function returns only a precomputed + result, so can be called frequently to monitor memory consumption. + Even if locks are otherwise defined, this function does not use them, + so results might not be up to date. +*/ +size_t dlmalloc_footprint(void); + +/* + malloc_max_footprint(); + Returns the maximum number of bytes obtained from the system. This + value will be greater than current footprint if deallocated space + has been reclaimed by the system. The peak number of bytes allocated + by malloc, realloc etc., is less than this value. Unlike mallinfo, + this function returns only a precomputed result, so can be called + frequently to monitor memory consumption. Even if locks are + otherwise defined, this function does not use them, so results might + not be up to date. +*/ +size_t dlmalloc_max_footprint(void); + +/* + malloc_footprint_limit(); + Returns the number of bytes that the heap is allowed to obtain from + the system, returning the last value returned by + malloc_set_footprint_limit, or the maximum size_t value if + never set. The returned value reflects a permission. There is no + guarantee that this number of bytes can actually be obtained from + the system. +*/ +size_t dlmalloc_footprint_limit(void); + +/* + malloc_set_footprint_limit(); + Sets the maximum number of bytes to obtain from the system, causing + failure returns from malloc and related functions upon attempts to + exceed this value. The argument value may be subject to page + rounding to an enforceable limit; this actual value is returned. + Using an argument of the maximum possible size_t effectively + disables checks. If the argument is less than or equal to the + current malloc_footprint, then all future allocations that require + additional system memory will fail. However, invocation cannot + retroactively deallocate existing used memory. +*/ +size_t dlmalloc_set_footprint_limit(size_t bytes); + +/* + malloc_inspect_all(void(*handler)(void *start, + void *end, + size_t used_bytes, + void* callback_arg), + void* arg); + Traverses the heap and calls the given handler for each managed + region, skipping all bytes that are (or may be) used for bookkeeping + purposes. Traversal does not include include chunks that have been + directly memory mapped. Each reported region begins at the start + address, and continues up to but not including the end address. The + first used_bytes of the region contain allocated data. If + used_bytes is zero, the region is unallocated. The handler is + invoked with the given callback argument. If locks are defined, they + are held during the entire traversal. It is a bad idea to invoke + other malloc functions from within the handler. + + For example, to count the number of in-use chunks with size greater + than 1000, you could write: + static int count = 0; + void count_chunks(void* start, void* end, size_t used, void* arg) { + if (used >= 1000) ++count; + } + then: + malloc_inspect_all(count_chunks, NULL); + + malloc_inspect_all is compiled only if MALLOC_INSPECT_ALL is defined. +*/ +void dlmalloc_inspect_all(void(*handler)(void*, void *, size_t, void*), + void* arg); + +#if !NO_MALLINFO +/* + mallinfo() + Returns (by copy) a struct containing various summary statistics: + + arena: current total non-mmapped bytes allocated from system + ordblks: the number of free chunks + smblks: always zero. + hblks: current number of mmapped regions + hblkhd: total bytes held in mmapped regions + usmblks: the maximum total allocated space. This will be greater + than current total if trimming has occurred. + fsmblks: always zero + uordblks: current total allocated space (normal or mmapped) + fordblks: total free space + keepcost: the maximum number of bytes that could ideally be released + back to system via malloc_trim. ("ideally" means that + it ignores page restrictions etc.) + + Because these fields are ints, but internal bookkeeping may + be kept as longs, the reported values may wrap around zero and + thus be inaccurate. +*/ + +struct mallinfo dlmallinfo(void); +#endif /* NO_MALLINFO */ + +/* + independent_calloc(size_t n_elements, size_t element_size, void* chunks[]); + + independent_calloc is similar to calloc, but instead of returning a + single cleared space, it returns an array of pointers to n_elements + independent elements that can hold contents of size elem_size, each + of which starts out cleared, and can be independently freed, + realloc'ed etc. The elements are guaranteed to be adjacently + allocated (this is not guaranteed to occur with multiple callocs or + mallocs), which may also improve cache locality in some + applications. + + The "chunks" argument is optional (i.e., may be null, which is + probably the most typical usage). If it is null, the returned array + is itself dynamically allocated and should also be freed when it is + no longer needed. Otherwise, the chunks array must be of at least + n_elements in length. It is filled in with the pointers to the + chunks. + + In either case, independent_calloc returns this pointer array, or + null if the allocation failed. If n_elements is zero and "chunks" + is null, it returns a chunk representing an array with zero elements + (which should be freed if not wanted). + + Each element must be freed when it is no longer needed. This can be + done all at once using bulk_free. + + independent_calloc simplifies and speeds up implementations of many + kinds of pools. It may also be useful when constructing large data + structures that initially have a fixed number of fixed-sized nodes, + but the number is not known at compile time, and some of the nodes + may later need to be freed. For example: + + struct Node { int item; struct Node* next; }; + + struct Node* build_list() { + struct Node** pool; + int n = read_number_of_nodes_needed(); + if (n <= 0) return 0; + pool = (struct Node**)(independent_calloc(n, sizeof(struct Node), 0); + if (pool == 0) die(); + // organize into a linked list... + struct Node* first = pool[0]; + for (i = 0; i < n-1; ++i) + pool[i]->next = pool[i+1]; + free(pool); // Can now free the array (or not, if it is needed later) + return first; + } +*/ +void** dlindependent_calloc(size_t, size_t, void**); + +/* + independent_comalloc(size_t n_elements, size_t sizes[], void* chunks[]); + + independent_comalloc allocates, all at once, a set of n_elements + chunks with sizes indicated in the "sizes" array. It returns + an array of pointers to these elements, each of which can be + independently freed, realloc'ed etc. The elements are guaranteed to + be adjacently allocated (this is not guaranteed to occur with + multiple callocs or mallocs), which may also improve cache locality + in some applications. + + The "chunks" argument is optional (i.e., may be null). If it is null + the returned array is itself dynamically allocated and should also + be freed when it is no longer needed. Otherwise, the chunks array + must be of at least n_elements in length. It is filled in with the + pointers to the chunks. + + In either case, independent_comalloc returns this pointer array, or + null if the allocation failed. If n_elements is zero and chunks is + null, it returns a chunk representing an array with zero elements + (which should be freed if not wanted). + + Each element must be freed when it is no longer needed. This can be + done all at once using bulk_free. + + independent_comallac differs from independent_calloc in that each + element may have a different size, and also that it does not + automatically clear elements. + + independent_comalloc can be used to speed up allocation in cases + where several structs or objects must always be allocated at the + same time. For example: + + struct Head { ... } + struct Foot { ... } + + void send_message(char* msg) { + int msglen = strlen(msg); + size_t sizes[3] = { sizeof(struct Head), msglen, sizeof(struct Foot) }; + void* chunks[3]; + if (independent_comalloc(3, sizes, chunks) == 0) + die(); + struct Head* head = (struct Head*)(chunks[0]); + char* body = (char*)(chunks[1]); + struct Foot* foot = (struct Foot*)(chunks[2]); + // ... + } + + In general though, independent_comalloc is worth using only for + larger values of n_elements. For small values, you probably won't + detect enough difference from series of malloc calls to bother. + + Overuse of independent_comalloc can increase overall memory usage, + since it cannot reuse existing noncontiguous small chunks that + might be available for some of the elements. +*/ +void** dlindependent_comalloc(size_t, size_t*, void**); + +/* + bulk_free(void* array[], size_t n_elements) + Frees and clears (sets to null) each non-null pointer in the given + array. This is likely to be faster than freeing them one-by-one. + If footers are used, pointers that have been allocated in different + mspaces are not freed or cleared, and the count of all such pointers + is returned. For large arrays of pointers with poor locality, it + may be worthwhile to sort this array before calling bulk_free. +*/ +size_t dlbulk_free(void**, size_t n_elements); + +/* + pvalloc(size_t n); + Equivalent to valloc(minimum-page-that-holds(n)), that is, + round up n to nearest pagesize. + */ +void* dlpvalloc(size_t); + +/* + malloc_trim(size_t pad); + + If possible, gives memory back to the system (via negative arguments + to sbrk) if there is unused memory at the `high' end of the malloc + pool or in unused MMAP segments. You can call this after freeing + large blocks of memory to potentially reduce the system-level memory + requirements of a program. However, it cannot guarantee to reduce + memory. Under some allocation patterns, some large free blocks of + memory will be locked between two used chunks, so they cannot be + given back to the system. + + The `pad' argument to malloc_trim represents the amount of free + trailing space to leave untrimmed. If this argument is zero, only + the minimum amount of memory to maintain internal data structures + will be left. Non-zero arguments can be supplied to maintain enough + trailing space to service future expected allocations without having + to re-obtain memory from the system. + + Malloc_trim returns 1 if it actually released any memory, else 0. +*/ +int dlmalloc_trim(size_t); + +/* + malloc_stats(); + Prints on stderr the amount of space obtained from the system (both + via sbrk and mmap), the maximum amount (which may be more than + current if malloc_trim and/or munmap got called), and the current + number of bytes allocated via malloc (or realloc, etc) but not yet + freed. Note that this is the number of bytes allocated, not the + number requested. It will be larger than the number requested + because of alignment and bookkeeping overhead. Because it includes + alignment wastage as being in use, this figure may be greater than + zero even when no user-level chunks are allocated. + + The reported current and maximum system memory can be inaccurate if + a program makes other calls to system memory allocation functions + (normally sbrk) outside of malloc. + + malloc_stats prints only the most commonly interesting statistics. + More information can be obtained by calling mallinfo. + + malloc_stats is not compiled if NO_MALLOC_STATS is defined. +*/ +void dlmalloc_stats(void); + +#endif /* !ONLY_MSPACES */ + +/* + malloc_usable_size(void* p); + + Returns the number of bytes you can actually use in + an allocated chunk, which may be more than you requested (although + often not) due to alignment and minimum size constraints. + You can use this many bytes without worrying about + overwriting other allocated objects. This is not a particularly great + programming practice. malloc_usable_size can be more useful in + debugging and assertions, for example: + + p = malloc(n); + assert(malloc_usable_size(p) >= 256); +*/ +size_t dlmalloc_usable_size(const void*); + +#if MSPACES + +/* + mspace is an opaque type representing an independent + region of space that supports mspace_malloc, etc. +*/ +typedef void* mspace; + +/* + create_mspace creates and returns a new independent space with the + given initial capacity, or, if 0, the default granularity size. It + returns null if there is no system memory available to create the + space. If argument locked is non-zero, the space uses a separate + lock to control access. The capacity of the space will grow + dynamically as needed to service mspace_malloc requests. You can + control the sizes of incremental increases of this space by + compiling with a different DEFAULT_GRANULARITY or dynamically + setting with mallopt(M_GRANULARITY, value). +*/ +mspace create_mspace(size_t capacity, int locked); + +/* + destroy_mspace destroys the given space, and attempts to return all + of its memory back to the system, returning the total number of + bytes freed. After destruction, the results of access to all memory + used by the space become undefined. +*/ +size_t destroy_mspace(mspace msp); + +/* + create_mspace_with_base uses the memory supplied as the initial base + of a new mspace. Part (less than 128*sizeof(size_t) bytes) of this + space is used for bookkeeping, so the capacity must be at least this + large. (Otherwise 0 is returned.) When this initial space is + exhausted, additional memory will be obtained from the system. + Destroying this space will deallocate all additionally allocated + space (if possible) but not the initial base. +*/ +mspace create_mspace_with_base(void* base, size_t capacity, int locked); + +/* + mspace_track_large_chunks controls whether requests for large chunks + are allocated in their own untracked mmapped regions, separate from + others in this mspace. By default large chunks are not tracked, + which reduces fragmentation. However, such chunks are not + necessarily released to the system upon destroy_mspace. Enabling + tracking by setting to true may increase fragmentation, but avoids + leakage when relying on destroy_mspace to release all memory + allocated using this space. The function returns the previous + setting. +*/ +int mspace_track_large_chunks(mspace msp, int enable); + +#if !NO_MALLINFO +/* + mspace_mallinfo behaves as mallinfo, but reports properties of + the given space. +*/ +struct mallinfo mspace_mallinfo(mspace msp); +#endif /* NO_MALLINFO */ + +/* + An alias for mallopt. +*/ +int mspace_mallopt(int, int); + +/* + The following operate identically to their malloc counterparts + but operate only for the given mspace argument +*/ +void* mspace_malloc(mspace msp, size_t bytes); +void mspace_free(mspace msp, void* mem); +void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size); +void* mspace_realloc(mspace msp, void* mem, size_t newsize); +void* mspace_realloc_in_place(mspace msp, void* mem, size_t newsize); +void* mspace_memalign(mspace msp, size_t alignment, size_t bytes); +void** mspace_independent_calloc(mspace msp, size_t n_elements, + size_t elem_size, void* chunks[]); +void** mspace_independent_comalloc(mspace msp, size_t n_elements, + size_t sizes[], void* chunks[]); +size_t mspace_bulk_free(mspace msp, void**, size_t n_elements); +size_t mspace_usable_size(const void* mem); +void mspace_malloc_stats(mspace msp); +int mspace_trim(mspace msp, size_t pad); +size_t mspace_footprint(mspace msp); +size_t mspace_max_footprint(mspace msp); +size_t mspace_footprint_limit(mspace msp); +size_t mspace_set_footprint_limit(mspace msp, size_t bytes); +void mspace_inspect_all(mspace msp, + void(*handler)(void *, void *, size_t, void*), + void* arg); +#endif /* MSPACES */ + +#ifdef __cplusplus +}; /* end of extern "C" */ +#endif + +#endif /* MALLOC_280_H */ diff --git a/linux_syscall_support.h b/linux_syscall_support.h new file mode 100644 index 0000000..c80fbfd --- /dev/null +++ b/linux_syscall_support.h @@ -0,0 +1,5375 @@ +/* Copyright 2005-2011 Google LLC + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are + * met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following disclaimer + * in the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Google LLC nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * --- + * Author: Markus Gutschke + */ + +/* This file includes Linux-specific support functions common to the + * coredumper and the thread lister; primarily, this is a collection + * of direct system calls, and a couple of symbols missing from + * standard header files. + * There are a few options that the including file can set to control + * the behavior of this file: + * + * SYS_CPLUSPLUS: + * The entire header file will normally be wrapped in 'extern "C" { }", + * making it suitable for compilation as both C and C++ source. If you + * do not want to do this, you can set the SYS_CPLUSPLUS macro to inhibit + * the wrapping. N.B. doing so will suppress inclusion of all prerequisite + * system header files, too. It is the caller's responsibility to provide + * the necessary definitions. + * + * SYS_ERRNO: + * All system calls will update "errno" unless overridden by setting the + * SYS_ERRNO macro prior to including this file. SYS_ERRNO should be + * an l-value. + * + * SYS_INLINE: + * New symbols will be defined "static inline", unless overridden by + * the SYS_INLINE macro. + * + * SYS_LINUX_SYSCALL_SUPPORT_H + * This macro is used to avoid multiple inclusions of this header file. + * If you need to include this file more than once, make sure to + * unset SYS_LINUX_SYSCALL_SUPPORT_H before each inclusion. + * + * SYS_PREFIX: + * New system calls will have a prefix of "sys_" unless overridden by + * the SYS_PREFIX macro. Valid values for this macro are [0..9] which + * results in prefixes "sys[0..9]_". It is also possible to set this + * macro to -1, which avoids all prefixes. + * + * SYS_SYSCALL_ENTRYPOINT: + * Some applications (such as sandboxes that filter system calls), need + * to be able to run custom-code each time a system call is made. If this + * macro is defined, it expands to the name of a "common" symbol. If + * this symbol is assigned a non-NULL pointer value, it is used as the + * address of the system call entrypoint. + * A pointer to this symbol can be obtained by calling + * get_syscall_entrypoint() + * + * This file defines a few internal symbols that all start with "LSS_". + * Do not access these symbols from outside this file. They are not part + * of the supported API. + */ +#ifndef SYS_LINUX_SYSCALL_SUPPORT_H +#define SYS_LINUX_SYSCALL_SUPPORT_H + +/* We currently only support x86-32, x86-64, ARM, MIPS, PPC, s390 and s390x + * on Linux. + * Porting to other related platforms should not be difficult. + */ +#if (defined(__i386__) || defined(__x86_64__) || defined(__ARM_ARCH_3__) || \ + defined(__mips__) || defined(__PPC__) || defined(__ARM_EABI__) || \ + defined(__aarch64__) || defined(__s390__) || defined(__e2k__) || \ + (defined(__riscv) && __riscv_xlen == 64) || defined(__loongarch_lp64)) \ + && (defined(__linux) || defined(__ANDROID__)) + +#ifndef SYS_CPLUSPLUS +#ifdef __cplusplus +/* Some system header files in older versions of gcc neglect to properly + * handle being included from C++. As it appears to be harmless to have + * multiple nested 'extern "C"' blocks, just add another one here. + */ +extern "C" { +#endif + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef __mips__ +/* Include definitions of the ABI currently in use. */ +#ifdef __ANDROID__ +/* Android doesn't have sgidefs.h, but does have asm/sgidefs.h, + * which has the definitions we need. + */ +#include +#else +#include +#endif +#endif +#endif + +/* Some libcs, for example Android NDK and musl, #define these + * macros as aliases to their non-64 counterparts. To avoid naming + * conflict, remove them. + * + * These are restored by the corresponding #pragma pop_macro near + * the end of this file. + */ +#pragma push_macro("stat64") +#pragma push_macro("fstat64") +#pragma push_macro("lstat64") +#pragma push_macro("pread64") +#pragma push_macro("pwrite64") +#pragma push_macro("getdents64") +#undef stat64 +#undef fstat64 +#undef lstat64 +#undef pread64 +#undef pwrite64 +#undef getdents64 + +#if defined(__ANDROID__) && defined(__x86_64__) +// A number of x86_64 syscalls are blocked by seccomp on recent Android; +// undefine them so that modern alternatives will be used instead where +// possible. +// The alternative syscalls have been sanity checked against linux-3.4+; +// older versions might not work. +# undef __NR_getdents +# undef __NR_dup2 +# undef __NR_fork +# undef __NR_getpgrp +# undef __NR_open +# undef __NR_poll +# undef __NR_readlink +# undef __NR_stat +# undef __NR_unlink +# undef __NR_pipe +#endif + +#if defined(__ANDROID__) +// waitpid is blocked by seccomp on all architectures on recent Android. +# undef __NR_waitpid +#endif + +/* As glibc often provides subtly incompatible data structures (and implicit + * wrapper functions that convert them), we provide our own kernel data + * structures for use by the system calls. + * These structures have been developed by using Linux 2.6.23 headers for + * reference. Note though, we do not care about exact API compatibility + * with the kernel, and in fact the kernel often does not have a single + * API that works across architectures. Instead, we try to mimic the glibc + * API where reasonable, and only guarantee ABI compatibility with the + * kernel headers. + * Most notably, here are a few changes that were made to the structures + * defined by kernel headers: + * + * - we only define structures, but not symbolic names for kernel data + * types. For the latter, we directly use the native C datatype + * (i.e. "unsigned" instead of "mode_t"). + * - in a few cases, it is possible to define identical structures for + * both 32bit (e.g. i386) and 64bit (e.g. x86-64) platforms by + * standardizing on the 64bit version of the data types. In particular, + * this means that we use "unsigned" where the 32bit headers say + * "unsigned long". + * - overall, we try to minimize the number of cases where we need to + * conditionally define different structures. + * - the "struct kernel_sigaction" class of structures have been + * modified to more closely mimic glibc's API by introducing an + * anonymous union for the function pointer. + * - a small number of field names had to have an underscore appended to + * them, because glibc defines a global macro by the same name. + */ + +/* include/linux/dirent.h */ +struct kernel_dirent64 { + unsigned long long d_ino; + long long d_off; + unsigned short d_reclen; + unsigned char d_type; + char d_name[256]; +}; + +/* include/linux/dirent.h */ +#if !defined(__NR_getdents) +// when getdents is not available, getdents64 is used for both. +#define kernel_dirent kernel_dirent64 +#else +struct kernel_dirent { + long d_ino; + long d_off; + unsigned short d_reclen; + char d_name[256]; +}; +#endif + +/* include/linux/uio.h */ +struct kernel_iovec { + void *iov_base; + unsigned long iov_len; +}; + +/* include/linux/socket.h */ +struct kernel_msghdr { + void *msg_name; + int msg_namelen; + struct kernel_iovec*msg_iov; + unsigned long msg_iovlen; + void *msg_control; + unsigned long msg_controllen; + unsigned msg_flags; +}; + +/* include/asm-generic/poll.h */ +struct kernel_pollfd { + int fd; + short events; + short revents; +}; + +/* include/linux/resource.h */ +struct kernel_rlimit { + unsigned long rlim_cur; + unsigned long rlim_max; +}; + +/* include/linux/time.h */ +struct kernel_timespec { + long tv_sec; + long tv_nsec; +}; + +/* include/linux/time.h */ +struct kernel_timeval { + long tv_sec; + long tv_usec; +}; + +/* include/linux/time.h */ +struct kernel_itimerval { + struct kernel_timeval it_interval; + struct kernel_timeval it_value; +}; + +/* include/linux/resource.h */ +struct kernel_rusage { + struct kernel_timeval ru_utime; + struct kernel_timeval ru_stime; + long ru_maxrss; + long ru_ixrss; + long ru_idrss; + long ru_isrss; + long ru_minflt; + long ru_majflt; + long ru_nswap; + long ru_inblock; + long ru_oublock; + long ru_msgsnd; + long ru_msgrcv; + long ru_nsignals; + long ru_nvcsw; + long ru_nivcsw; +}; + +#if defined(__i386__) || defined(__ARM_EABI__) || defined(__ARM_ARCH_3__) \ + || defined(__PPC__) || (defined(__s390__) && !defined(__s390x__)) \ + || defined(__e2k__) + +/* include/asm-{arm,i386,mips,ppc}/signal.h */ +struct kernel_old_sigaction { + union { + void (*sa_handler_)(int); + void (*sa_sigaction_)(int, siginfo_t *, void *); + }; + unsigned long sa_mask; + unsigned long sa_flags; + void (*sa_restorer)(void); +} __attribute__((packed,aligned(4))); +#elif (defined(__mips__) && _MIPS_SIM == _MIPS_SIM_ABI32) + #define kernel_old_sigaction kernel_sigaction +#elif defined(__aarch64__) || defined(__riscv) || defined(__loongarch_lp64) + // No kernel_old_sigaction defined for arm64 riscv and loongarch64. +#endif + +/* Some kernel functions (e.g. sigaction() in 2.6.23) require that the + * exactly match the size of the signal set, even though the API was + * intended to be extensible. We define our own KERNEL_NSIG to deal with + * this. + * Please note that glibc provides signals [1.._NSIG-1], whereas the + * kernel (and this header) provides the range [1..KERNEL_NSIG]. The + * actual number of signals is obviously the same, but the constants + * differ by one. + */ +#ifdef __mips__ +#define KERNEL_NSIG 128 +#else +#define KERNEL_NSIG 64 +#endif + +/* include/asm-{arm,aarch64,i386,mips,x86_64}/signal.h */ +struct kernel_sigset_t { + unsigned long sig[(KERNEL_NSIG + 8*sizeof(unsigned long) - 1)/ + (8*sizeof(unsigned long))]; +}; + +/* include/asm-{arm,i386,mips,x86_64,ppc}/signal.h */ +struct kernel_sigaction { +#ifdef __mips__ + unsigned long sa_flags; + union { + void (*sa_handler_)(int); + void (*sa_sigaction_)(int, siginfo_t *, void *); + }; + struct kernel_sigset_t sa_mask; +#else + union { + void (*sa_handler_)(int); + void (*sa_sigaction_)(int, siginfo_t *, void *); + }; + unsigned long sa_flags; +#if !defined(__riscv) && !defined(__loongarch_lp64) + void (*sa_restorer)(void); +#endif + struct kernel_sigset_t sa_mask; +#endif +}; + +/* include/linux/socket.h */ +struct kernel_sockaddr { + unsigned short sa_family; + char sa_data[14]; +}; + +/* include/asm-{arm,aarch64,i386,mips,ppc,s390}/stat.h */ +#ifdef __mips__ +#if _MIPS_SIM == _MIPS_SIM_ABI64 +typedef unsigned long long kernel_blkcnt_t; +typedef unsigned kernel_blksize_t; +typedef unsigned kernel_dev_t; +typedef unsigned kernel_gid_t; +typedef unsigned long long kernel_ino_t; +typedef unsigned kernel_mode_t; +typedef unsigned kernel_nlink_t; +typedef long long kernel_off_t; +typedef unsigned kernel_time_t; +typedef unsigned kernel_uid_t; +struct kernel_stat { +#else +struct kernel_stat64 { +#endif + unsigned st_dev; + unsigned __pad0[3]; + unsigned long long st_ino; + unsigned st_mode; + unsigned st_nlink; + unsigned st_uid; + unsigned st_gid; + unsigned st_rdev; + unsigned __pad1[3]; + long long st_size; + unsigned st_atime_; + unsigned st_atime_nsec_; + unsigned st_mtime_; + unsigned st_mtime_nsec_; + unsigned st_ctime_; + unsigned st_ctime_nsec_; + unsigned st_blksize; + unsigned __pad2; + unsigned long long st_blocks; +}; +#elif defined __PPC__ +struct kernel_stat64 { + unsigned long long st_dev; + unsigned long long st_ino; + unsigned st_mode; + unsigned st_nlink; + unsigned st_uid; + unsigned st_gid; + unsigned long long st_rdev; + unsigned short int __pad2; + long long st_size; + long st_blksize; + long long st_blocks; + long st_atime_; + unsigned long st_atime_nsec_; + long st_mtime_; + unsigned long st_mtime_nsec_; + long st_ctime_; + unsigned long st_ctime_nsec_; + unsigned long __unused4; + unsigned long __unused5; +}; +#elif defined(__e2k__) +struct kernel_stat64 { + unsigned long long st_dev; + unsigned long long st_ino; + unsigned int st_mode; + unsigned int st_nlink; + unsigned int st_uid; + unsigned int st_gid; + unsigned long long st_rdev; + long long st_size; + int st_blksize; + int __pad2; + unsigned long long st_blocks; + int st_atime_; + unsigned int st_atime_nsec_; + int st_mtime_; + unsigned int st_mtime_nsec_; + int st_ctime_; + unsigned int st_ctime_nsec_; + unsigned int __unused4; + unsigned int __unused5; +}; +#else +struct kernel_stat64 { + unsigned long long st_dev; + unsigned char __pad0[4]; + unsigned __st_ino; + unsigned st_mode; + unsigned st_nlink; + unsigned st_uid; + unsigned st_gid; + unsigned long long st_rdev; + unsigned char __pad3[4]; + long long st_size; + unsigned st_blksize; + unsigned long long st_blocks; + unsigned st_atime_; + unsigned st_atime_nsec_; + unsigned st_mtime_; + unsigned st_mtime_nsec_; + unsigned st_ctime_; + unsigned st_ctime_nsec_; + unsigned long long st_ino; +}; +#endif + +/* include/asm-{arm,aarch64,i386,mips,x86_64,ppc,s390}/stat.h */ +#if defined(__i386__) || defined(__ARM_ARCH_3__) || defined(__ARM_EABI__) +typedef unsigned kernel_blkcnt_t; +typedef unsigned kernel_blksize_t; +typedef unsigned short kernel_dev_t; +typedef unsigned short kernel_gid_t; +typedef unsigned kernel_ino_t; +typedef unsigned short kernel_mode_t; +typedef unsigned short kernel_nlink_t; +typedef unsigned kernel_off_t; +typedef unsigned kernel_time_t; +typedef unsigned short kernel_uid_t; +struct kernel_stat { + /* The kernel headers suggest that st_dev and st_rdev should be 32bit + * quantities encoding 12bit major and 20bit minor numbers in an interleaved + * format. In reality, we do not see useful data in the top bits. So, + * we'll leave the padding in here, until we find a better solution. + */ + kernel_dev_t st_dev; + short pad1; + kernel_ino_t st_ino; + kernel_mode_t st_mode; + kernel_nlink_t st_nlink; + kernel_uid_t st_uid; + kernel_gid_t st_gid; + kernel_dev_t st_rdev; + short pad2; + kernel_off_t st_size; + kernel_blksize_t st_blksize; + kernel_blkcnt_t st_blocks; + kernel_time_t st_atime_; + unsigned st_atime_nsec_; + kernel_time_t st_mtime_; + unsigned st_mtime_nsec_; + kernel_time_t st_ctime_; + unsigned st_ctime_nsec_; + unsigned __unused4; + unsigned __unused5; +}; +#elif defined(__x86_64__) +typedef int64_t kernel_blkcnt_t; +typedef int64_t kernel_blksize_t; +typedef uint64_t kernel_dev_t; +typedef unsigned kernel_gid_t; +typedef uint64_t kernel_ino_t; +typedef unsigned kernel_mode_t; +typedef uint64_t kernel_nlink_t; +typedef int64_t kernel_off_t; +typedef uint64_t kernel_time_t; +typedef unsigned kernel_uid_t; +struct kernel_stat { + kernel_dev_t st_dev; + kernel_ino_t st_ino; + kernel_nlink_t st_nlink; + kernel_mode_t st_mode; + kernel_uid_t st_uid; + kernel_gid_t st_gid; + unsigned __pad0; + kernel_dev_t st_rdev; + kernel_off_t st_size; + kernel_blksize_t st_blksize; + kernel_blkcnt_t st_blocks; + kernel_time_t st_atime_; + uint64_t st_atime_nsec_; + kernel_time_t st_mtime_; + uint64_t st_mtime_nsec_; + kernel_time_t st_ctime_; + uint64_t st_ctime_nsec_; + int64_t __unused4[3]; +}; +#elif defined(__PPC__) +typedef unsigned long kernel_blkcnt_t; +typedef unsigned long kernel_blksize_t; +typedef unsigned kernel_dev_t; +typedef unsigned kernel_gid_t; +typedef unsigned long kernel_ino_t; +typedef unsigned long kernel_mode_t; +typedef unsigned short kernel_nlink_t; +typedef long kernel_off_t; +typedef unsigned long kernel_time_t; +typedef unsigned kernel_uid_t; +struct kernel_stat { + kernel_dev_t st_dev; + kernel_ino_t st_ino; + kernel_mode_t st_mode; + kernel_nlink_t st_nlink; + kernel_gid_t st_uid; + kernel_uid_t st_gid; + kernel_dev_t st_rdev; + kernel_off_t st_size; + kernel_blksize_t st_blksize; + kernel_blkcnt_t st_blocks; + kernel_time_t st_atime_; + unsigned long st_atime_nsec_; + kernel_time_t st_mtime_; + unsigned long st_mtime_nsec_; + kernel_time_t st_ctime_; + unsigned long st_ctime_nsec_; + unsigned long __unused4; + unsigned long __unused5; +}; +#elif (defined(__mips__) && _MIPS_SIM != _MIPS_SIM_ABI64) +typedef int kernel_blkcnt_t; +typedef int kernel_blksize_t; +typedef unsigned kernel_dev_t; +typedef unsigned kernel_gid_t; +typedef unsigned kernel_ino_t; +typedef unsigned kernel_mode_t; +typedef unsigned kernel_nlink_t; +typedef long kernel_off_t; +typedef long kernel_time_t; +typedef unsigned kernel_uid_t; +struct kernel_stat { + kernel_dev_t st_dev; + int st_pad1[3]; + kernel_ino_t st_ino; + kernel_mode_t st_mode; + kernel_nlink_t st_nlink; + kernel_uid_t st_uid; + kernel_gid_t st_gid; + kernel_dev_t st_rdev; + int st_pad2[2]; + kernel_off_t st_size; + int st_pad3; + kernel_time_t st_atime_; + long st_atime_nsec_; + kernel_time_t st_mtime_; + long st_mtime_nsec_; + kernel_time_t st_ctime_; + long st_ctime_nsec_; + kernel_blksize_t st_blksize; + kernel_blkcnt_t st_blocks; + int st_pad4[14]; +}; +#elif defined(__aarch64__) || defined(__riscv) || defined(__loongarch_lp64) +typedef long kernel_blkcnt_t; +typedef int kernel_blksize_t; +typedef unsigned long kernel_dev_t; +typedef unsigned int kernel_gid_t; +typedef unsigned long kernel_ino_t; +typedef unsigned int kernel_mode_t; +typedef unsigned int kernel_nlink_t; +typedef long kernel_off_t; +typedef long kernel_time_t; +typedef unsigned int kernel_uid_t; +struct kernel_stat { + kernel_dev_t st_dev; + kernel_ino_t st_ino; + kernel_mode_t st_mode; + kernel_nlink_t st_nlink; + kernel_uid_t st_uid; + kernel_gid_t st_gid; + kernel_dev_t st_rdev; + unsigned long __pad1; + kernel_off_t st_size; + kernel_blksize_t st_blksize; + int __pad2; + kernel_blkcnt_t st_blocks; + kernel_time_t st_atime_; + unsigned long st_atime_nsec_; + kernel_time_t st_mtime_; + unsigned long st_mtime_nsec_; + kernel_time_t st_ctime_; + unsigned long st_ctime_nsec_; + unsigned int __unused4; + unsigned int __unused5; +}; +#elif defined(__s390x__) +typedef long kernel_blkcnt_t; +typedef unsigned long kernel_blksize_t; +typedef unsigned long kernel_dev_t; +typedef unsigned int kernel_gid_t; +typedef unsigned long kernel_ino_t; +typedef unsigned int kernel_mode_t; +typedef unsigned long kernel_nlink_t; +typedef unsigned long kernel_off_t; +typedef unsigned long kernel_time_t; +typedef unsigned int kernel_uid_t; +struct kernel_stat { + kernel_dev_t st_dev; + kernel_ino_t st_ino; + kernel_nlink_t st_nlink; + kernel_mode_t st_mode; + kernel_uid_t st_uid; + kernel_gid_t st_gid; + unsigned int __pad1; + kernel_dev_t st_rdev; + kernel_off_t st_size; + kernel_time_t st_atime_; + unsigned long st_atime_nsec_; + kernel_time_t st_mtime_; + unsigned long st_mtime_nsec_; + kernel_time_t st_ctime_; + unsigned long st_ctime_nsec_; + kernel_blksize_t st_blksize; + kernel_blkcnt_t st_blocks; + unsigned long __unused[3]; +}; +#elif defined(__s390__) +typedef unsigned long kernel_blkcnt_t; +typedef unsigned long kernel_blksize_t; +typedef unsigned short kernel_dev_t; +typedef unsigned short kernel_gid_t; +typedef unsigned long kernel_ino_t; +typedef unsigned short kernel_mode_t; +typedef unsigned short kernel_nlink_t; +typedef unsigned long kernel_off_t; +typedef unsigned long kernel_time_t; +typedef unsigned short kernel_uid_t; +struct kernel_stat { + kernel_dev_t st_dev; + unsigned short __pad1; + kernel_ino_t st_ino; + kernel_mode_t st_mode; + kernel_nlink_t st_nlink; + kernel_uid_t st_uid; + kernel_gid_t st_gid; + kernel_dev_t st_rdev; + unsigned short __pad2; + kernel_off_t st_size; + kernel_blksize_t st_blksize; + kernel_blkcnt_t st_blocks; + kernel_time_t st_atime_; + unsigned long st_atime_nsec_; + kernel_time_t st_mtime_; + unsigned long st_mtime_nsec_; + kernel_time_t st_ctime_; + unsigned long st_ctime_nsec_; + unsigned long __unused4; + unsigned long __unused5; +}; +#elif defined(__e2k__) +typedef unsigned long kernel_blkcnt_t; +typedef unsigned long kernel_blksize_t; +typedef unsigned long kernel_dev_t; +typedef unsigned int kernel_gid_t; +typedef unsigned long kernel_ino_t; +typedef unsigned int kernel_mode_t; +typedef unsigned long kernel_nlink_t; +typedef unsigned long kernel_off_t; +typedef unsigned long kernel_time_t; +typedef unsigned int kernel_uid_t; +struct kernel_stat { + kernel_dev_t st_dev; + kernel_ino_t st_ino; + kernel_mode_t st_mode; + kernel_nlink_t st_nlink; + kernel_uid_t st_uid; + kernel_gid_t st_gid; + kernel_dev_t st_rdev; + kernel_off_t st_size; + kernel_blksize_t st_blksize; + kernel_blkcnt_t st_blocks; + kernel_time_t st_atime_; + unsigned long st_atime_nsec_; + kernel_time_t st_mtime_; + unsigned long st_mtime_nsec_; + kernel_time_t st_ctime_; + unsigned long st_ctime_nsec_; +}; +#endif + +/* include/asm-{arm,aarch64,i386,mips,x86_64,ppc,s390}/statfs.h */ +#ifdef __mips__ +#if _MIPS_SIM != _MIPS_SIM_ABI64 +struct kernel_statfs64 { + unsigned long f_type; + unsigned long f_bsize; + unsigned long f_frsize; + unsigned long __pad; + unsigned long long f_blocks; + unsigned long long f_bfree; + unsigned long long f_files; + unsigned long long f_ffree; + unsigned long long f_bavail; + struct { int val[2]; } f_fsid; + unsigned long f_namelen; + unsigned long f_spare[6]; +}; +#endif +#elif defined(__s390__) +/* See also arch/s390/include/asm/compat.h */ +struct kernel_statfs64 { + unsigned int f_type; + unsigned int f_bsize; + unsigned long long f_blocks; + unsigned long long f_bfree; + unsigned long long f_bavail; + unsigned long long f_files; + unsigned long long f_ffree; + struct { int val[2]; } f_fsid; + unsigned int f_namelen; + unsigned int f_frsize; + unsigned int f_flags; + unsigned int f_spare[4]; +}; +#elif !defined(__x86_64__) +struct kernel_statfs64 { + unsigned long f_type; + unsigned long f_bsize; + unsigned long long f_blocks; + unsigned long long f_bfree; + unsigned long long f_bavail; + unsigned long long f_files; + unsigned long long f_ffree; + struct { int val[2]; } f_fsid; + unsigned long f_namelen; + unsigned long f_frsize; + unsigned long f_spare[5]; +}; +#endif + +/* include/asm-{arm,i386,mips,x86_64,ppc,generic,s390}/statfs.h */ +#ifdef __mips__ +struct kernel_statfs { + long f_type; + long f_bsize; + long f_frsize; + long f_blocks; + long f_bfree; + long f_files; + long f_ffree; + long f_bavail; + struct { int val[2]; } f_fsid; + long f_namelen; + long f_spare[6]; +}; +#elif defined(__x86_64__) +struct kernel_statfs { + /* x86_64 actually defines all these fields as signed, whereas all other */ + /* platforms define them as unsigned. Leaving them at unsigned should not */ + /* cause any problems. Make sure these are 64-bit even on x32. */ + uint64_t f_type; + uint64_t f_bsize; + uint64_t f_blocks; + uint64_t f_bfree; + uint64_t f_bavail; + uint64_t f_files; + uint64_t f_ffree; + struct { int val[2]; } f_fsid; + uint64_t f_namelen; + uint64_t f_frsize; + uint64_t f_spare[5]; +}; +#elif defined(__s390__) +struct kernel_statfs { + unsigned int f_type; + unsigned int f_bsize; + unsigned long f_blocks; + unsigned long f_bfree; + unsigned long f_bavail; + unsigned long f_files; + unsigned long f_ffree; + struct { int val[2]; } f_fsid; + unsigned int f_namelen; + unsigned int f_frsize; + unsigned int f_flags; + unsigned int f_spare[4]; +}; +#else +struct kernel_statfs { + unsigned long f_type; + unsigned long f_bsize; + unsigned long f_blocks; + unsigned long f_bfree; + unsigned long f_bavail; + unsigned long f_files; + unsigned long f_ffree; + struct { int val[2]; } f_fsid; + unsigned long f_namelen; + unsigned long f_frsize; + unsigned long f_spare[5]; +}; +#endif + +struct kernel_statx_timestamp { + int64_t tv_sec; + uint32_t tv_nsec; + int32_t __reserved; +}; + +struct kernel_statx { + uint32_t stx_mask; + uint32_t stx_blksize; + uint64_t stx_attributes; + uint32_t stx_nlink; + uint32_t stx_uid; + uint32_t stx_gid; + uint16_t stx_mode; + uint16_t __spare0[1]; + uint64_t stx_ino; + uint64_t stx_size; + uint64_t stx_blocks; + uint64_t stx_attributes_mask; + struct kernel_statx_timestamp stx_atime; + struct kernel_statx_timestamp stx_btime; + struct kernel_statx_timestamp stx_ctime; + struct kernel_statx_timestamp stx_mtime; + uint32_t stx_rdev_major; + uint32_t stx_rdev_minor; + uint32_t stx_dev_major; + uint32_t stx_dev_minor; + uint64_t stx_mnt_id; + uint64_t __spare2; + uint64_t __spare3[12]; +}; + +/* Definitions missing from the standard header files */ +#ifndef O_DIRECTORY +#if defined(__ARM_ARCH_3__) || defined(__ARM_EABI__) || defined(__aarch64__) +#define O_DIRECTORY 0040000 +#else +#define O_DIRECTORY 0200000 +#endif +#endif +#ifndef NT_PRXFPREG +#define NT_PRXFPREG 0x46e62b7f +#endif +#ifndef PTRACE_GETFPXREGS +#define PTRACE_GETFPXREGS ((enum __ptrace_request)18) +#endif +#ifndef PR_GET_DUMPABLE +#define PR_GET_DUMPABLE 3 +#endif +#ifndef PR_SET_DUMPABLE +#define PR_SET_DUMPABLE 4 +#endif +#ifndef PR_GET_SECCOMP +#define PR_GET_SECCOMP 21 +#endif +#ifndef PR_SET_SECCOMP +#define PR_SET_SECCOMP 22 +#endif +#ifndef AT_FDCWD +#define AT_FDCWD (-100) +#endif +#ifndef AT_SYMLINK_NOFOLLOW +#define AT_SYMLINK_NOFOLLOW 0x100 +#endif +#ifndef AT_REMOVEDIR +#define AT_REMOVEDIR 0x200 +#endif +#ifndef AT_NO_AUTOMOUNT +#define AT_NO_AUTOMOUNT 0x800 +#endif +#ifndef AT_EMPTY_PATH +#define AT_EMPTY_PATH 0x1000 +#endif +#ifndef STATX_BASIC_STATS +#define STATX_BASIC_STATS 0x000007ffU +#endif +#ifndef AT_STATX_SYNC_AS_STAT +#define AT_STATX_SYNC_AS_STAT 0x0000 +#endif +#ifndef MREMAP_FIXED +#define MREMAP_FIXED 2 +#endif +#ifndef SA_RESTORER +#define SA_RESTORER 0x04000000 +#endif +#ifndef CPUCLOCK_PROF +#define CPUCLOCK_PROF 0 +#endif +#ifndef CPUCLOCK_VIRT +#define CPUCLOCK_VIRT 1 +#endif +#ifndef CPUCLOCK_SCHED +#define CPUCLOCK_SCHED 2 +#endif +#ifndef CPUCLOCK_PERTHREAD_MASK +#define CPUCLOCK_PERTHREAD_MASK 4 +#endif +#ifndef MAKE_PROCESS_CPUCLOCK +#define MAKE_PROCESS_CPUCLOCK(pid, clock) \ + ((int)(~(unsigned)(pid) << 3) | (int)(clock)) +#endif +#ifndef MAKE_THREAD_CPUCLOCK +#define MAKE_THREAD_CPUCLOCK(tid, clock) \ + ((int)(~(unsigned)(tid) << 3) | \ + (int)((clock) | CPUCLOCK_PERTHREAD_MASK)) +#endif + +#ifndef FUTEX_WAIT +#define FUTEX_WAIT 0 +#endif +#ifndef FUTEX_WAKE +#define FUTEX_WAKE 1 +#endif +#ifndef FUTEX_FD +#define FUTEX_FD 2 +#endif +#ifndef FUTEX_REQUEUE +#define FUTEX_REQUEUE 3 +#endif +#ifndef FUTEX_CMP_REQUEUE +#define FUTEX_CMP_REQUEUE 4 +#endif +#ifndef FUTEX_WAKE_OP +#define FUTEX_WAKE_OP 5 +#endif +#ifndef FUTEX_LOCK_PI +#define FUTEX_LOCK_PI 6 +#endif +#ifndef FUTEX_UNLOCK_PI +#define FUTEX_UNLOCK_PI 7 +#endif +#ifndef FUTEX_TRYLOCK_PI +#define FUTEX_TRYLOCK_PI 8 +#endif +#ifndef FUTEX_PRIVATE_FLAG +#define FUTEX_PRIVATE_FLAG 128 +#endif +#ifndef FUTEX_CMD_MASK +#define FUTEX_CMD_MASK ~FUTEX_PRIVATE_FLAG +#endif +#ifndef FUTEX_WAIT_PRIVATE +#define FUTEX_WAIT_PRIVATE (FUTEX_WAIT | FUTEX_PRIVATE_FLAG) +#endif +#ifndef FUTEX_WAKE_PRIVATE +#define FUTEX_WAKE_PRIVATE (FUTEX_WAKE | FUTEX_PRIVATE_FLAG) +#endif +#ifndef FUTEX_REQUEUE_PRIVATE +#define FUTEX_REQUEUE_PRIVATE (FUTEX_REQUEUE | FUTEX_PRIVATE_FLAG) +#endif +#ifndef FUTEX_CMP_REQUEUE_PRIVATE +#define FUTEX_CMP_REQUEUE_PRIVATE (FUTEX_CMP_REQUEUE | FUTEX_PRIVATE_FLAG) +#endif +#ifndef FUTEX_WAKE_OP_PRIVATE +#define FUTEX_WAKE_OP_PRIVATE (FUTEX_WAKE_OP | FUTEX_PRIVATE_FLAG) +#endif +#ifndef FUTEX_LOCK_PI_PRIVATE +#define FUTEX_LOCK_PI_PRIVATE (FUTEX_LOCK_PI | FUTEX_PRIVATE_FLAG) +#endif +#ifndef FUTEX_UNLOCK_PI_PRIVATE +#define FUTEX_UNLOCK_PI_PRIVATE (FUTEX_UNLOCK_PI | FUTEX_PRIVATE_FLAG) +#endif +#ifndef FUTEX_TRYLOCK_PI_PRIVATE +#define FUTEX_TRYLOCK_PI_PRIVATE (FUTEX_TRYLOCK_PI | FUTEX_PRIVATE_FLAG) +#endif + + +#if defined(__x86_64__) +#ifndef ARCH_SET_GS +#define ARCH_SET_GS 0x1001 +#endif +#ifndef ARCH_GET_GS +#define ARCH_GET_GS 0x1004 +#endif +#endif + +#if defined(__i386__) +#ifndef __NR_quotactl +#define __NR_quotactl 131 +#endif +#ifndef __NR_setresuid +#define __NR_setresuid 164 +#define __NR_getresuid 165 +#define __NR_setresgid 170 +#define __NR_getresgid 171 +#endif +#ifndef __NR_rt_sigaction +#define __NR_rt_sigreturn 173 +#define __NR_rt_sigaction 174 +#define __NR_rt_sigprocmask 175 +#define __NR_rt_sigpending 176 +#define __NR_rt_sigsuspend 179 +#endif +#ifndef __NR_pread64 +#define __NR_pread64 180 +#endif +#ifndef __NR_pwrite64 +#define __NR_pwrite64 181 +#endif +#ifndef __NR_ugetrlimit +#define __NR_ugetrlimit 191 +#endif +#ifndef __NR_stat64 +#define __NR_stat64 195 +#endif +#ifndef __NR_fstat64 +#define __NR_fstat64 197 +#endif +#ifndef __NR_setresuid32 +#define __NR_setresuid32 208 +#define __NR_getresuid32 209 +#define __NR_setresgid32 210 +#define __NR_getresgid32 211 +#endif +#ifndef __NR_setfsuid32 +#define __NR_setfsuid32 215 +#define __NR_setfsgid32 216 +#endif +#ifndef __NR_getdents64 +#define __NR_getdents64 220 +#endif +#ifndef __NR_gettid +#define __NR_gettid 224 +#endif +#ifndef __NR_readahead +#define __NR_readahead 225 +#endif +#ifndef __NR_setxattr +#define __NR_setxattr 226 +#endif +#ifndef __NR_lsetxattr +#define __NR_lsetxattr 227 +#endif +#ifndef __NR_getxattr +#define __NR_getxattr 229 +#endif +#ifndef __NR_lgetxattr +#define __NR_lgetxattr 230 +#endif +#ifndef __NR_listxattr +#define __NR_listxattr 232 +#endif +#ifndef __NR_llistxattr +#define __NR_llistxattr 233 +#endif +#ifndef __NR_tkill +#define __NR_tkill 238 +#endif +#ifndef __NR_futex +#define __NR_futex 240 +#endif +#ifndef __NR_sched_setaffinity +#define __NR_sched_setaffinity 241 +#define __NR_sched_getaffinity 242 +#endif +#ifndef __NR_set_tid_address +#define __NR_set_tid_address 258 +#endif +#ifndef __NR_clock_gettime +#define __NR_clock_gettime 265 +#endif +#ifndef __NR_clock_getres +#define __NR_clock_getres 266 +#endif +#ifndef __NR_statfs64 +#define __NR_statfs64 268 +#endif +#ifndef __NR_fstatfs64 +#define __NR_fstatfs64 269 +#endif +#ifndef __NR_fadvise64_64 +#define __NR_fadvise64_64 272 +#endif +#ifndef __NR_ioprio_set +#define __NR_ioprio_set 289 +#endif +#ifndef __NR_ioprio_get +#define __NR_ioprio_get 290 +#endif +#ifndef __NR_openat +#define __NR_openat 295 +#endif +#ifndef __NR_fstatat64 +#define __NR_fstatat64 300 +#endif +#ifndef __NR_unlinkat +#define __NR_unlinkat 301 +#endif +#ifndef __NR_move_pages +#define __NR_move_pages 317 +#endif +#ifndef __NR_getcpu +#define __NR_getcpu 318 +#endif +#ifndef __NR_fallocate +#define __NR_fallocate 324 +#endif +#ifndef __NR_getrandom +#define __NR_getrandom 355 +#endif +/* End of i386 definitions */ +#elif defined(__ARM_ARCH_3__) || defined(__ARM_EABI__) +#ifndef __NR_setresuid +#define __NR_setresuid (__NR_SYSCALL_BASE + 164) +#define __NR_getresuid (__NR_SYSCALL_BASE + 165) +#define __NR_setresgid (__NR_SYSCALL_BASE + 170) +#define __NR_getresgid (__NR_SYSCALL_BASE + 171) +#endif +#ifndef __NR_rt_sigaction +#define __NR_rt_sigreturn (__NR_SYSCALL_BASE + 173) +#define __NR_rt_sigaction (__NR_SYSCALL_BASE + 174) +#define __NR_rt_sigprocmask (__NR_SYSCALL_BASE + 175) +#define __NR_rt_sigpending (__NR_SYSCALL_BASE + 176) +#define __NR_rt_sigsuspend (__NR_SYSCALL_BASE + 179) +#endif +#ifndef __NR_pread64 +#define __NR_pread64 (__NR_SYSCALL_BASE + 180) +#endif +#ifndef __NR_pwrite64 +#define __NR_pwrite64 (__NR_SYSCALL_BASE + 181) +#endif +#ifndef __NR_ugetrlimit +#define __NR_ugetrlimit (__NR_SYSCALL_BASE + 191) +#endif +#ifndef __NR_stat64 +#define __NR_stat64 (__NR_SYSCALL_BASE + 195) +#endif +#ifndef __NR_fstat64 +#define __NR_fstat64 (__NR_SYSCALL_BASE + 197) +#endif +#ifndef __NR_setresuid32 +#define __NR_setresuid32 (__NR_SYSCALL_BASE + 208) +#define __NR_getresuid32 (__NR_SYSCALL_BASE + 209) +#define __NR_setresgid32 (__NR_SYSCALL_BASE + 210) +#define __NR_getresgid32 (__NR_SYSCALL_BASE + 211) +#endif +#ifndef __NR_setfsuid32 +#define __NR_setfsuid32 (__NR_SYSCALL_BASE + 215) +#define __NR_setfsgid32 (__NR_SYSCALL_BASE + 216) +#endif +#ifndef __NR_getdents64 +#define __NR_getdents64 (__NR_SYSCALL_BASE + 217) +#endif +#ifndef __NR_gettid +#define __NR_gettid (__NR_SYSCALL_BASE + 224) +#endif +#ifndef __NR_readahead +#define __NR_readahead (__NR_SYSCALL_BASE + 225) +#endif +#ifndef __NR_setxattr +#define __NR_setxattr (__NR_SYSCALL_BASE + 226) +#endif +#ifndef __NR_lsetxattr +#define __NR_lsetxattr (__NR_SYSCALL_BASE + 227) +#endif +#ifndef __NR_getxattr +#define __NR_getxattr (__NR_SYSCALL_BASE + 229) +#endif +#ifndef __NR_lgetxattr +#define __NR_lgetxattr (__NR_SYSCALL_BASE + 230) +#endif +#ifndef __NR_listxattr +#define __NR_listxattr (__NR_SYSCALL_BASE + 232) +#endif +#ifndef __NR_llistxattr +#define __NR_llistxattr (__NR_SYSCALL_BASE + 233) +#endif +#ifndef __NR_tkill +#define __NR_tkill (__NR_SYSCALL_BASE + 238) +#endif +#ifndef __NR_futex +#define __NR_futex (__NR_SYSCALL_BASE + 240) +#endif +#ifndef __NR_sched_setaffinity +#define __NR_sched_setaffinity (__NR_SYSCALL_BASE + 241) +#define __NR_sched_getaffinity (__NR_SYSCALL_BASE + 242) +#endif +#ifndef __NR_set_tid_address +#define __NR_set_tid_address (__NR_SYSCALL_BASE + 256) +#endif +#ifndef __NR_clock_gettime +#define __NR_clock_gettime (__NR_SYSCALL_BASE + 263) +#endif +#ifndef __NR_clock_getres +#define __NR_clock_getres (__NR_SYSCALL_BASE + 264) +#endif +#ifndef __NR_statfs64 +#define __NR_statfs64 (__NR_SYSCALL_BASE + 266) +#endif +#ifndef __NR_fstatfs64 +#define __NR_fstatfs64 (__NR_SYSCALL_BASE + 267) +#endif +#ifndef __NR_ioprio_set +#define __NR_ioprio_set (__NR_SYSCALL_BASE + 314) +#endif +#ifndef __NR_ioprio_get +#define __NR_ioprio_get (__NR_SYSCALL_BASE + 315) +#endif +#ifndef __NR_fstatat64 +#define __NR_fstatat64 (__NR_SYSCALL_BASE + 327) +#endif +#ifndef __NR_move_pages +#define __NR_move_pages (__NR_SYSCALL_BASE + 344) +#endif +#ifndef __NR_getcpu +#define __NR_getcpu (__NR_SYSCALL_BASE + 345) +#endif +#ifndef __NR_getrandom +#define __NR_getrandom (__NR_SYSCALL_BASE + 384) +#endif +/* End of ARM 3/EABI definitions */ +#elif defined(__aarch64__) || defined(__riscv) || defined(__loongarch_lp64) +#ifndef __NR_setxattr +#define __NR_setxattr 5 +#endif +#ifndef __NR_lsetxattr +#define __NR_lsetxattr 6 +#endif +#ifndef __NR_getxattr +#define __NR_getxattr 8 +#endif +#ifndef __NR_lgetxattr +#define __NR_lgetxattr 9 +#endif +#ifndef __NR_listxattr +#define __NR_listxattr 11 +#endif +#ifndef __NR_llistxattr +#define __NR_llistxattr 12 +#endif +#ifndef __NR_ioprio_set +#define __NR_ioprio_set 30 +#endif +#ifndef __NR_ioprio_get +#define __NR_ioprio_get 31 +#endif +#ifndef __NR_unlinkat +#define __NR_unlinkat 35 +#endif +#ifndef __NR_fallocate +#define __NR_fallocate 47 +#endif +#ifndef __NR_openat +#define __NR_openat 56 +#endif +#ifndef __NR_quotactl +#define __NR_quotactl 60 +#endif +#ifndef __NR_getdents64 +#define __NR_getdents64 61 +#endif +#ifndef __NR_getdents +// when getdents is not available, getdents64 is used for both. +#define __NR_getdents __NR_getdents64 +#endif +#ifndef __NR_pread64 +#define __NR_pread64 67 +#endif +#ifndef __NR_pwrite64 +#define __NR_pwrite64 68 +#endif +#ifndef __NR_ppoll +#define __NR_ppoll 73 +#endif +#ifndef __NR_readlinkat +#define __NR_readlinkat 78 +#endif +#if !defined(__loongarch_lp64) +#ifndef __NR_newfstatat +#define __NR_newfstatat 79 +#endif +#endif +#ifndef __NR_set_tid_address +#define __NR_set_tid_address 96 +#endif +#ifndef __NR_futex +#define __NR_futex 98 +#endif +#ifndef __NR_clock_gettime +#define __NR_clock_gettime 113 +#endif +#ifndef __NR_clock_getres +#define __NR_clock_getres 114 +#endif +#ifndef __NR_sched_setaffinity +#define __NR_sched_setaffinity 122 +#define __NR_sched_getaffinity 123 +#endif +#ifndef __NR_tkill +#define __NR_tkill 130 +#endif +#ifndef __NR_setresuid +#define __NR_setresuid 147 +#define __NR_getresuid 148 +#define __NR_setresgid 149 +#define __NR_getresgid 150 +#endif +#ifndef __NR_gettid +#define __NR_gettid 178 +#endif +#ifndef __NR_readahead +#define __NR_readahead 213 +#endif +#ifndef __NR_fadvise64 +#define __NR_fadvise64 223 +#endif +#ifndef __NR_move_pages +#define __NR_move_pages 239 +#endif +#ifndef __NR_getrandom +#define __NR_getrandom 278 +#endif +#ifndef __NR_statx +#define __NR_statx 291 +#endif +#elif defined(__x86_64__) +#ifndef __NR_pread64 +#define __NR_pread64 17 +#endif +#ifndef __NR_pwrite64 +#define __NR_pwrite64 18 +#endif +#ifndef __NR_setresuid +#define __NR_setresuid 117 +#define __NR_getresuid 118 +#define __NR_setresgid 119 +#define __NR_getresgid 120 +#endif +#ifndef __NR_quotactl +#define __NR_quotactl 179 +#endif +#ifndef __NR_gettid +#define __NR_gettid 186 +#endif +#ifndef __NR_readahead +#define __NR_readahead 187 +#endif +#ifndef __NR_setxattr +#define __NR_setxattr 188 +#endif +#ifndef __NR_lsetxattr +#define __NR_lsetxattr 189 +#endif +#ifndef __NR_getxattr +#define __NR_getxattr 191 +#endif +#ifndef __NR_lgetxattr +#define __NR_lgetxattr 192 +#endif +#ifndef __NR_listxattr +#define __NR_listxattr 194 +#endif +#ifndef __NR_llistxattr +#define __NR_llistxattr 195 +#endif +#ifndef __NR_tkill +#define __NR_tkill 200 +#endif +#ifndef __NR_futex +#define __NR_futex 202 +#endif +#ifndef __NR_sched_setaffinity +#define __NR_sched_setaffinity 203 +#define __NR_sched_getaffinity 204 +#endif +#ifndef __NR_getdents64 +#define __NR_getdents64 217 +#endif +#ifndef __NR_getdents +// when getdents is not available, getdents64 is used for both. +#define __NR_getdents __NR_getdents64 +#endif +#ifndef __NR_set_tid_address +#define __NR_set_tid_address 218 +#endif +#ifndef __NR_fadvise64 +#define __NR_fadvise64 221 +#endif +#ifndef __NR_clock_gettime +#define __NR_clock_gettime 228 +#endif +#ifndef __NR_clock_getres +#define __NR_clock_getres 229 +#endif +#ifndef __NR_ioprio_set +#define __NR_ioprio_set 251 +#endif +#ifndef __NR_ioprio_get +#define __NR_ioprio_get 252 +#endif +#ifndef __NR_openat +#define __NR_openat 257 +#endif +#ifndef __NR_newfstatat +#define __NR_newfstatat 262 +#endif +#ifndef __NR_unlinkat +#define __NR_unlinkat 263 +#endif +#ifndef __NR_move_pages +#define __NR_move_pages 279 +#endif +#ifndef __NR_fallocate +#define __NR_fallocate 285 +#endif +#ifndef __NR_getrandom +#define __NR_getrandom 318 +#endif +/* End of x86-64 definitions */ +#elif defined(__mips__) +#if _MIPS_SIM == _MIPS_SIM_ABI32 +#ifndef __NR_setresuid +#define __NR_setresuid (__NR_Linux + 185) +#define __NR_getresuid (__NR_Linux + 186) +#define __NR_setresgid (__NR_Linux + 190) +#define __NR_getresgid (__NR_Linux + 191) +#endif +#ifndef __NR_rt_sigaction +#define __NR_rt_sigreturn (__NR_Linux + 193) +#define __NR_rt_sigaction (__NR_Linux + 194) +#define __NR_rt_sigprocmask (__NR_Linux + 195) +#define __NR_rt_sigpending (__NR_Linux + 196) +#define __NR_rt_sigsuspend (__NR_Linux + 199) +#endif +#ifndef __NR_pread64 +#define __NR_pread64 (__NR_Linux + 200) +#endif +#ifndef __NR_pwrite64 +#define __NR_pwrite64 (__NR_Linux + 201) +#endif +#ifndef __NR_stat64 +#define __NR_stat64 (__NR_Linux + 213) +#endif +#ifndef __NR_fstat64 +#define __NR_fstat64 (__NR_Linux + 215) +#endif +#ifndef __NR_getdents64 +#define __NR_getdents64 (__NR_Linux + 219) +#endif +#ifndef __NR_gettid +#define __NR_gettid (__NR_Linux + 222) +#endif +#ifndef __NR_readahead +#define __NR_readahead (__NR_Linux + 223) +#endif +#ifndef __NR_setxattr +#define __NR_setxattr (__NR_Linux + 224) +#endif +#ifndef __NR_lsetxattr +#define __NR_lsetxattr (__NR_Linux + 225) +#endif +#ifndef __NR_getxattr +#define __NR_getxattr (__NR_Linux + 227) +#endif +#ifndef __NR_lgetxattr +#define __NR_lgetxattr (__NR_Linux + 228) +#endif +#ifndef __NR_listxattr +#define __NR_listxattr (__NR_Linux + 230) +#endif +#ifndef __NR_llistxattr +#define __NR_llistxattr (__NR_Linux + 231) +#endif +#ifndef __NR_tkill +#define __NR_tkill (__NR_Linux + 236) +#endif +#ifndef __NR_futex +#define __NR_futex (__NR_Linux + 238) +#endif +#ifndef __NR_sched_setaffinity +#define __NR_sched_setaffinity (__NR_Linux + 239) +#define __NR_sched_getaffinity (__NR_Linux + 240) +#endif +#ifndef __NR_set_tid_address +#define __NR_set_tid_address (__NR_Linux + 252) +#endif +#ifndef __NR_statfs64 +#define __NR_statfs64 (__NR_Linux + 255) +#endif +#ifndef __NR_fstatfs64 +#define __NR_fstatfs64 (__NR_Linux + 256) +#endif +#ifndef __NR_clock_gettime +#define __NR_clock_gettime (__NR_Linux + 263) +#endif +#ifndef __NR_clock_getres +#define __NR_clock_getres (__NR_Linux + 264) +#endif +#ifndef __NR_openat +#define __NR_openat (__NR_Linux + 288) +#endif +#ifndef __NR_fstatat +#define __NR_fstatat (__NR_Linux + 293) +#endif +#ifndef __NR_unlinkat +#define __NR_unlinkat (__NR_Linux + 294) +#endif +#ifndef __NR_move_pages +#define __NR_move_pages (__NR_Linux + 308) +#endif +#ifndef __NR_getcpu +#define __NR_getcpu (__NR_Linux + 312) +#endif +#ifndef __NR_ioprio_set +#define __NR_ioprio_set (__NR_Linux + 314) +#endif +#ifndef __NR_ioprio_get +#define __NR_ioprio_get (__NR_Linux + 315) +#endif +#ifndef __NR_getrandom +#define __NR_getrandom (__NR_Linux + 353) +#endif +/* End of MIPS (old 32bit API) definitions */ +#elif _MIPS_SIM == _MIPS_SIM_ABI64 +#ifndef __NR_pread64 +#define __NR_pread64 (__NR_Linux + 16) +#endif +#ifndef __NR_pwrite64 +#define __NR_pwrite64 (__NR_Linux + 17) +#endif +#ifndef __NR_setresuid +#define __NR_setresuid (__NR_Linux + 115) +#define __NR_getresuid (__NR_Linux + 116) +#define __NR_setresgid (__NR_Linux + 117) +#define __NR_getresgid (__NR_Linux + 118) +#endif +#ifndef __NR_gettid +#define __NR_gettid (__NR_Linux + 178) +#endif +#ifndef __NR_readahead +#define __NR_readahead (__NR_Linux + 179) +#endif +#ifndef __NR_setxattr +#define __NR_setxattr (__NR_Linux + 180) +#endif +#ifndef __NR_lsetxattr +#define __NR_lsetxattr (__NR_Linux + 181) +#endif +#ifndef __NR_getxattr +#define __NR_getxattr (__NR_Linux + 183) +#endif +#ifndef __NR_lgetxattr +#define __NR_lgetxattr (__NR_Linux + 184) +#endif +#ifndef __NR_listxattr +#define __NR_listxattr (__NR_Linux + 186) +#endif +#ifndef __NR_llistxattr +#define __NR_llistxattr (__NR_Linux + 187) +#endif +#ifndef __NR_tkill +#define __NR_tkill (__NR_Linux + 192) +#endif +#ifndef __NR_futex +#define __NR_futex (__NR_Linux + 194) +#endif +#ifndef __NR_sched_setaffinity +#define __NR_sched_setaffinity (__NR_Linux + 195) +#define __NR_sched_getaffinity (__NR_Linux + 196) +#endif +#ifndef __NR_set_tid_address +#define __NR_set_tid_address (__NR_Linux + 212) +#endif +#ifndef __NR_clock_gettime +#define __NR_clock_gettime (__NR_Linux + 222) +#endif +#ifndef __NR_clock_getres +#define __NR_clock_getres (__NR_Linux + 223) +#endif +#ifndef __NR_openat +#define __NR_openat (__NR_Linux + 247) +#endif +#ifndef __NR_fstatat +#define __NR_fstatat (__NR_Linux + 252) +#endif +#ifndef __NR_unlinkat +#define __NR_unlinkat (__NR_Linux + 253) +#endif +#ifndef __NR_move_pages +#define __NR_move_pages (__NR_Linux + 267) +#endif +#ifndef __NR_getcpu +#define __NR_getcpu (__NR_Linux + 271) +#endif +#ifndef __NR_ioprio_set +#define __NR_ioprio_set (__NR_Linux + 273) +#endif +#ifndef __NR_ioprio_get +#define __NR_ioprio_get (__NR_Linux + 274) +#endif +#ifndef __NR_getrandom +#define __NR_getrandom (__NR_Linux + 313) +#endif +/* End of MIPS (64bit API) definitions */ +#else +#ifndef __NR_setresuid +#define __NR_setresuid (__NR_Linux + 115) +#define __NR_getresuid (__NR_Linux + 116) +#define __NR_setresgid (__NR_Linux + 117) +#define __NR_getresgid (__NR_Linux + 118) +#endif +#ifndef __NR_gettid +#define __NR_gettid (__NR_Linux + 178) +#endif +#ifndef __NR_readahead +#define __NR_readahead (__NR_Linux + 179) +#endif +#ifndef __NR_setxattr +#define __NR_setxattr (__NR_Linux + 180) +#endif +#ifndef __NR_lsetxattr +#define __NR_lsetxattr (__NR_Linux + 181) +#endif +#ifndef __NR_getxattr +#define __NR_getxattr (__NR_Linux + 183) +#endif +#ifndef __NR_lgetxattr +#define __NR_lgetxattr (__NR_Linux + 184) +#endif +#ifndef __NR_listxattr +#define __NR_listxattr (__NR_Linux + 186) +#endif +#ifndef __NR_llistxattr +#define __NR_llistxattr (__NR_Linux + 187) +#endif +#ifndef __NR_tkill +#define __NR_tkill (__NR_Linux + 192) +#endif +#ifndef __NR_futex +#define __NR_futex (__NR_Linux + 194) +#endif +#ifndef __NR_sched_setaffinity +#define __NR_sched_setaffinity (__NR_Linux + 195) +#define __NR_sched_getaffinity (__NR_Linux + 196) +#endif +#ifndef __NR_set_tid_address +#define __NR_set_tid_address (__NR_Linux + 213) +#endif +#ifndef __NR_statfs64 +#define __NR_statfs64 (__NR_Linux + 217) +#endif +#ifndef __NR_fstatfs64 +#define __NR_fstatfs64 (__NR_Linux + 218) +#endif +#ifndef __NR_clock_gettime +#define __NR_clock_gettime (__NR_Linux + 226) +#endif +#ifndef __NR_clock_getres +#define __NR_clock_getres (__NR_Linux + 227) +#endif +#ifndef __NR_openat +#define __NR_openat (__NR_Linux + 251) +#endif +#ifndef __NR_fstatat +#define __NR_fstatat (__NR_Linux + 256) +#endif +#ifndef __NR_unlinkat +#define __NR_unlinkat (__NR_Linux + 257) +#endif +#ifndef __NR_move_pages +#define __NR_move_pages (__NR_Linux + 271) +#endif +#ifndef __NR_getcpu +#define __NR_getcpu (__NR_Linux + 275) +#endif +#ifndef __NR_ioprio_set +#define __NR_ioprio_set (__NR_Linux + 277) +#endif +#ifndef __NR_ioprio_get +#define __NR_ioprio_get (__NR_Linux + 278) +#endif +/* End of MIPS (new 32bit API) definitions */ +#endif +/* End of MIPS definitions */ +#elif defined(__PPC__) +#ifndef __NR_setfsuid +#define __NR_setfsuid 138 +#define __NR_setfsgid 139 +#endif +#ifndef __NR_setresuid +#define __NR_setresuid 164 +#define __NR_getresuid 165 +#define __NR_setresgid 169 +#define __NR_getresgid 170 +#endif +#ifndef __NR_rt_sigaction +#define __NR_rt_sigreturn 172 +#define __NR_rt_sigaction 173 +#define __NR_rt_sigprocmask 174 +#define __NR_rt_sigpending 175 +#define __NR_rt_sigsuspend 178 +#endif +#ifndef __NR_pread64 +#define __NR_pread64 179 +#endif +#ifndef __NR_pwrite64 +#define __NR_pwrite64 180 +#endif +#ifndef __NR_ugetrlimit +#define __NR_ugetrlimit 190 +#endif +#ifndef __NR_readahead +#define __NR_readahead 191 +#endif +#ifndef __NR_stat64 +#define __NR_stat64 195 +#endif +#ifndef __NR_fstat64 +#define __NR_fstat64 197 +#endif +#ifndef __NR_getdents64 +#define __NR_getdents64 202 +#endif +#ifndef __NR_gettid +#define __NR_gettid 207 +#endif +#ifndef __NR_tkill +#define __NR_tkill 208 +#endif +#ifndef __NR_setxattr +#define __NR_setxattr 209 +#endif +#ifndef __NR_lsetxattr +#define __NR_lsetxattr 210 +#endif +#ifndef __NR_getxattr +#define __NR_getxattr 212 +#endif +#ifndef __NR_lgetxattr +#define __NR_lgetxattr 213 +#endif +#ifndef __NR_listxattr +#define __NR_listxattr 215 +#endif +#ifndef __NR_llistxattr +#define __NR_llistxattr 216 +#endif +#ifndef __NR_futex +#define __NR_futex 221 +#endif +#ifndef __NR_sched_setaffinity +#define __NR_sched_setaffinity 222 +#define __NR_sched_getaffinity 223 +#endif +#ifndef __NR_set_tid_address +#define __NR_set_tid_address 232 +#endif +#ifndef __NR_clock_gettime +#define __NR_clock_gettime 246 +#endif +#ifndef __NR_clock_getres +#define __NR_clock_getres 247 +#endif +#ifndef __NR_statfs64 +#define __NR_statfs64 252 +#endif +#ifndef __NR_fstatfs64 +#define __NR_fstatfs64 253 +#endif +#ifndef __NR_fadvise64_64 +#define __NR_fadvise64_64 254 +#endif +#ifndef __NR_ioprio_set +#define __NR_ioprio_set 273 +#endif +#ifndef __NR_ioprio_get +#define __NR_ioprio_get 274 +#endif +#ifndef __NR_openat +#define __NR_openat 286 +#endif +#ifndef __NR_fstatat64 +#define __NR_fstatat64 291 +#endif +#ifndef __NR_unlinkat +#define __NR_unlinkat 292 +#endif +#ifndef __NR_move_pages +#define __NR_move_pages 301 +#endif +#ifndef __NR_getcpu +#define __NR_getcpu 302 +#endif +/* End of powerpc definitions */ +#elif defined(__s390__) +#ifndef __NR_quotactl +#define __NR_quotactl 131 +#endif +#ifndef __NR_rt_sigreturn +#define __NR_rt_sigreturn 173 +#endif +#ifndef __NR_rt_sigaction +#define __NR_rt_sigaction 174 +#endif +#ifndef __NR_rt_sigprocmask +#define __NR_rt_sigprocmask 175 +#endif +#ifndef __NR_rt_sigpending +#define __NR_rt_sigpending 176 +#endif +#ifndef __NR_rt_sigsuspend +#define __NR_rt_sigsuspend 179 +#endif +#ifndef __NR_pread64 +#define __NR_pread64 180 +#endif +#ifndef __NR_pwrite64 +#define __NR_pwrite64 181 +#endif +#ifndef __NR_getdents64 +#define __NR_getdents64 220 +#endif +#ifndef __NR_readahead +#define __NR_readahead 222 +#endif +#ifndef __NR_setxattr +#define __NR_setxattr 224 +#endif +#ifndef __NR_lsetxattr +#define __NR_lsetxattr 225 +#endif +#ifndef __NR_getxattr +#define __NR_getxattr 227 +#endif +#ifndef __NR_lgetxattr +#define __NR_lgetxattr 228 +#endif +#ifndef __NR_listxattr +#define __NR_listxattr 230 +#endif +#ifndef __NR_llistxattr +#define __NR_llistxattr 231 +#endif +#ifndef __NR_gettid +#define __NR_gettid 236 +#endif +#ifndef __NR_tkill +#define __NR_tkill 237 +#endif +#ifndef __NR_futex +#define __NR_futex 238 +#endif +#ifndef __NR_sched_setaffinity +#define __NR_sched_setaffinity 239 +#endif +#ifndef __NR_sched_getaffinity +#define __NR_sched_getaffinity 240 +#endif +#ifndef __NR_set_tid_address +#define __NR_set_tid_address 252 +#endif +#ifndef __NR_clock_gettime +#define __NR_clock_gettime 260 +#endif +#ifndef __NR_clock_getres +#define __NR_clock_getres 261 +#endif +#ifndef __NR_statfs64 +#define __NR_statfs64 265 +#endif +#ifndef __NR_fstatfs64 +#define __NR_fstatfs64 266 +#endif +#ifndef __NR_ioprio_set +#define __NR_ioprio_set 282 +#endif +#ifndef __NR_ioprio_get +#define __NR_ioprio_get 283 +#endif +#ifndef __NR_openat +#define __NR_openat 288 +#endif +#ifndef __NR_unlinkat +#define __NR_unlinkat 294 +#endif +#ifndef __NR_move_pages +#define __NR_move_pages 310 +#endif +#ifndef __NR_getcpu +#define __NR_getcpu 311 +#endif +#ifndef __NR_fallocate +#define __NR_fallocate 314 +#endif +/* Some syscalls are named/numbered differently between s390 and s390x. */ +#ifdef __s390x__ +# ifndef __NR_getrlimit +# define __NR_getrlimit 191 +# endif +# ifndef __NR_setresuid +# define __NR_setresuid 208 +# endif +# ifndef __NR_getresuid +# define __NR_getresuid 209 +# endif +# ifndef __NR_setresgid +# define __NR_setresgid 210 +# endif +# ifndef __NR_getresgid +# define __NR_getresgid 211 +# endif +# ifndef __NR_setfsuid +# define __NR_setfsuid 215 +# endif +# ifndef __NR_setfsgid +# define __NR_setfsgid 216 +# endif +# ifndef __NR_fadvise64 +# define __NR_fadvise64 253 +# endif +# ifndef __NR_newfstatat +# define __NR_newfstatat 293 +# endif +#else /* __s390x__ */ +# ifndef __NR_getrlimit +# define __NR_getrlimit 76 +# endif +# ifndef __NR_setfsuid +# define __NR_setfsuid 138 +# endif +# ifndef __NR_setfsgid +# define __NR_setfsgid 139 +# endif +# ifndef __NR_setresuid +# define __NR_setresuid 164 +# endif +# ifndef __NR_getresuid +# define __NR_getresuid 165 +# endif +# ifndef __NR_setresgid +# define __NR_setresgid 170 +# endif +# ifndef __NR_getresgid +# define __NR_getresgid 171 +# endif +# ifndef __NR_ugetrlimit +# define __NR_ugetrlimit 191 +# endif +# ifndef __NR_mmap2 +# define __NR_mmap2 192 +# endif +# ifndef __NR_setresuid32 +# define __NR_setresuid32 208 +# endif +# ifndef __NR_getresuid32 +# define __NR_getresuid32 209 +# endif +# ifndef __NR_setresgid32 +# define __NR_setresgid32 210 +# endif +# ifndef __NR_getresgid32 +# define __NR_getresgid32 211 +# endif +# ifndef __NR_setfsuid32 +# define __NR_setfsuid32 215 +# endif +# ifndef __NR_setfsgid32 +# define __NR_setfsgid32 216 +# endif +# ifndef __NR_fadvise64_64 +# define __NR_fadvise64_64 264 +# endif +# ifndef __NR_fstatat64 +# define __NR_fstatat64 293 +# endif +#endif /* __s390__ */ +/* End of s390/s390x definitions */ +#endif + + +/* After forking, we must make sure to only call system calls. */ +#if defined(__BOUNDED_POINTERS__) + #error "Need to port invocations of syscalls for bounded ptrs" +#else + /* The core dumper and the thread lister get executed after threads + * have been suspended. As a consequence, we cannot call any functions + * that acquire locks. Unfortunately, libc wraps most system calls + * (e.g. in order to implement pthread_atfork, and to make calls + * cancellable), which means we cannot call these functions. Instead, + * we have to call syscall() directly. + */ + #undef LSS_ERRNO + #ifdef SYS_ERRNO + /* Allow the including file to override the location of errno. This can + * be useful when using clone() with the CLONE_VM option. + */ + #define LSS_ERRNO SYS_ERRNO + #else + #define LSS_ERRNO errno + #endif + + #undef LSS_INLINE + #ifdef SYS_INLINE + #define LSS_INLINE SYS_INLINE + #else + #define LSS_INLINE static inline + #endif + + /* Allow the including file to override the prefix used for all new + * system calls. By default, it will be set to "sys_". + */ + #undef LSS_NAME + #ifndef SYS_PREFIX + #define LSS_NAME(name) sys_##name + #elif defined(SYS_PREFIX) && SYS_PREFIX < 0 + #define LSS_NAME(name) name + #elif defined(SYS_PREFIX) && SYS_PREFIX == 0 + #define LSS_NAME(name) sys0_##name + #elif defined(SYS_PREFIX) && SYS_PREFIX == 1 + #define LSS_NAME(name) sys1_##name + #elif defined(SYS_PREFIX) && SYS_PREFIX == 2 + #define LSS_NAME(name) sys2_##name + #elif defined(SYS_PREFIX) && SYS_PREFIX == 3 + #define LSS_NAME(name) sys3_##name + #elif defined(SYS_PREFIX) && SYS_PREFIX == 4 + #define LSS_NAME(name) sys4_##name + #elif defined(SYS_PREFIX) && SYS_PREFIX == 5 + #define LSS_NAME(name) sys5_##name + #elif defined(SYS_PREFIX) && SYS_PREFIX == 6 + #define LSS_NAME(name) sys6_##name + #elif defined(SYS_PREFIX) && SYS_PREFIX == 7 + #define LSS_NAME(name) sys7_##name + #elif defined(SYS_PREFIX) && SYS_PREFIX == 8 + #define LSS_NAME(name) sys8_##name + #elif defined(SYS_PREFIX) && SYS_PREFIX == 9 + #define LSS_NAME(name) sys9_##name + #endif + + #undef LSS_RETURN + #if defined(__i386__) || defined(__x86_64__) || defined(__ARM_ARCH_3__) \ + || defined(__ARM_EABI__) || defined(__aarch64__) || defined(__s390__) \ + || defined(__e2k__) || defined(__riscv) || defined(__loongarch_lp64) + /* Failing system calls return a negative result in the range of + * -1..-4095. These are "errno" values with the sign inverted. + */ + #define LSS_RETURN(type, res) \ + do { \ + if ((unsigned long)(res) >= (unsigned long)(-4095)) { \ + LSS_ERRNO = (int)(-(res)); \ + res = -1; \ + } \ + return (type) (res); \ + } while (0) + #elif defined(__mips__) + /* On MIPS, failing system calls return -1, and set errno in a + * separate CPU register. + */ + #define LSS_RETURN(type, res, err) \ + do { \ + if (err) { \ + unsigned long __errnovalue = (res); \ + LSS_ERRNO = __errnovalue; \ + res = -1; \ + } \ + return (type) (res); \ + } while (0) + #elif defined(__PPC__) + /* On PPC, failing system calls return -1, and set errno in a + * separate CPU register. See linux/unistd.h. + */ + #define LSS_RETURN(type, res, err) \ + do { \ + if (err & 0x10000000 ) { \ + LSS_ERRNO = (res); \ + res = -1; \ + } \ + return (type) (res); \ + } while (0) + #endif + #if defined(__i386__) + /* In PIC mode (e.g. when building shared libraries), gcc for i386 + * reserves ebx. Unfortunately, most distribution ship with implementations + * of _syscallX() which clobber ebx. + * Also, most definitions of _syscallX() neglect to mark "memory" as being + * clobbered. This causes problems with compilers, that do a better job + * at optimizing across __asm__ calls. + * So, we just have to redefine all of the _syscallX() macros. + */ + #undef LSS_ENTRYPOINT + #ifdef SYS_SYSCALL_ENTRYPOINT + static inline void (**LSS_NAME(get_syscall_entrypoint)(void))(void) { + void (**entrypoint)(void); + asm volatile(".bss\n" + ".align 8\n" + ".globl " SYS_SYSCALL_ENTRYPOINT "\n" + ".common " SYS_SYSCALL_ENTRYPOINT ",8,8\n" + ".previous\n" + /* This logically does 'lea "SYS_SYSCALL_ENTRYPOINT", %0' */ + "call 0f\n" + "0:pop %0\n" + "add $_GLOBAL_OFFSET_TABLE_+[.-0b], %0\n" + "mov " SYS_SYSCALL_ENTRYPOINT "@GOT(%0), %0\n" + : "=r"(entrypoint)); + return entrypoint; + } + + #define LSS_ENTRYPOINT ".bss\n" \ + ".align 8\n" \ + ".globl " SYS_SYSCALL_ENTRYPOINT "\n" \ + ".common " SYS_SYSCALL_ENTRYPOINT ",8,8\n" \ + ".previous\n" \ + /* Check the SYS_SYSCALL_ENTRYPOINT vector */ \ + "push %%eax\n" \ + "call 10000f\n" \ + "10000:pop %%eax\n" \ + "add $_GLOBAL_OFFSET_TABLE_+[.-10000b], %%eax\n" \ + "mov " SYS_SYSCALL_ENTRYPOINT \ + "@GOT(%%eax), %%eax\n" \ + "mov 0(%%eax), %%eax\n" \ + "test %%eax, %%eax\n" \ + "jz 10002f\n" \ + "push %%eax\n" \ + "call 10001f\n" \ + "10001:pop %%eax\n" \ + "add $(10003f-10001b), %%eax\n" \ + "xchg 4(%%esp), %%eax\n" \ + "ret\n" \ + "10002:pop %%eax\n" \ + "int $0x80\n" \ + "10003:\n" + #else + #define LSS_ENTRYPOINT "int $0x80\n" + #endif + #undef LSS_BODY + #define LSS_BODY(type,args...) \ + long __res; \ + __asm__ __volatile__("push %%ebx\n" \ + "movl %2,%%ebx\n" \ + LSS_ENTRYPOINT \ + "pop %%ebx" \ + args \ + : "memory"); \ + LSS_RETURN(type,__res) + #undef _syscall0 + #define _syscall0(type,name) \ + type LSS_NAME(name)(void) { \ + long __res; \ + __asm__ volatile(LSS_ENTRYPOINT \ + : "=a" (__res) \ + : "0" (__NR_##name) \ + : "memory"); \ + LSS_RETURN(type,__res); \ + } + #undef _syscall1 + #define _syscall1(type,name,type1,arg1) \ + type LSS_NAME(name)(type1 arg1) { \ + LSS_BODY(type, \ + : "=a" (__res) \ + : "0" (__NR_##name), "ri" ((long)(arg1))); \ + } + #undef _syscall2 + #define _syscall2(type,name,type1,arg1,type2,arg2) \ + type LSS_NAME(name)(type1 arg1,type2 arg2) { \ + LSS_BODY(type, \ + : "=a" (__res) \ + : "0" (__NR_##name),"ri" ((long)(arg1)), "c" ((long)(arg2))); \ + } + #undef _syscall3 + #define _syscall3(type,name,type1,arg1,type2,arg2,type3,arg3) \ + type LSS_NAME(name)(type1 arg1,type2 arg2,type3 arg3) { \ + LSS_BODY(type, \ + : "=a" (__res) \ + : "0" (__NR_##name), "ri" ((long)(arg1)), "c" ((long)(arg2)), \ + "d" ((long)(arg3))); \ + } + #undef _syscall4 + #define _syscall4(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4) { \ + LSS_BODY(type, \ + : "=a" (__res) \ + : "0" (__NR_##name), "ri" ((long)(arg1)), "c" ((long)(arg2)), \ + "d" ((long)(arg3)),"S" ((long)(arg4))); \ + } + #undef _syscall5 + #define _syscall5(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \ + type5,arg5) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5) { \ + long __res; \ + __asm__ __volatile__("push %%ebx\n" \ + "movl %2,%%ebx\n" \ + "movl %1,%%eax\n" \ + LSS_ENTRYPOINT \ + "pop %%ebx" \ + : "=a" (__res) \ + : "i" (__NR_##name), "ri" ((long)(arg1)), \ + "c" ((long)(arg2)), "d" ((long)(arg3)), \ + "S" ((long)(arg4)), "D" ((long)(arg5)) \ + : "memory"); \ + LSS_RETURN(type,__res); \ + } + #undef _syscall6 + #define _syscall6(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \ + type5,arg5,type6,arg6) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5, type6 arg6) { \ + long __res; \ + struct { long __a1; long __a6; } __s = { (long)arg1, (long) arg6 }; \ + __asm__ __volatile__("push %%ebp\n" \ + "push %%ebx\n" \ + "movl 4(%2),%%ebp\n" \ + "movl 0(%2), %%ebx\n" \ + "movl %1,%%eax\n" \ + LSS_ENTRYPOINT \ + "pop %%ebx\n" \ + "pop %%ebp" \ + : "=a" (__res) \ + : "i" (__NR_##name), "0" ((long)(&__s)), \ + "c" ((long)(arg2)), "d" ((long)(arg3)), \ + "S" ((long)(arg4)), "D" ((long)(arg5)) \ + : "memory"); \ + LSS_RETURN(type,__res); \ + } + LSS_INLINE int LSS_NAME(clone)(int (*fn)(void *), void *child_stack, + int flags, void *arg, int *parent_tidptr, + void *newtls, int *child_tidptr) { + long __res; + __asm__ __volatile__(/* if (fn == NULL) + * return -EINVAL; + */ + "movl %3,%%ecx\n" + "jecxz 1f\n" + + /* if (child_stack == NULL) + * return -EINVAL; + */ + "movl %4,%%ecx\n" + "jecxz 1f\n" + + /* Set up alignment of the child stack: + * child_stack = (child_stack & ~0xF) - 20; + */ + "andl $-16,%%ecx\n" + "subl $20,%%ecx\n" + + /* Push "arg" and "fn" onto the stack that will be + * used by the child. + */ + "movl %6,%%eax\n" + "movl %%eax,4(%%ecx)\n" + "movl %3,%%eax\n" + "movl %%eax,(%%ecx)\n" + + /* %eax = syscall(%eax = __NR_clone, + * %ebx = flags, + * %ecx = child_stack, + * %edx = parent_tidptr, + * %esi = newtls, + * %edi = child_tidptr) + * Also, make sure that %ebx gets preserved as it is + * used in PIC mode. + */ + "movl %8,%%esi\n" + "movl %7,%%edx\n" + "movl %5,%%eax\n" + "movl %9,%%edi\n" + "pushl %%ebx\n" + "movl %%eax,%%ebx\n" + "movl %2,%%eax\n" + LSS_ENTRYPOINT + + /* In the parent: restore %ebx + * In the child: move "fn" into %ebx + */ + "popl %%ebx\n" + + /* if (%eax != 0) + * return %eax; + */ + "test %%eax,%%eax\n" + "jnz 1f\n" + + /* In the child, now. Terminate frame pointer chain. + */ + "movl $0,%%ebp\n" + + /* Call "fn". "arg" is already on the stack. + */ + "call *%%ebx\n" + + /* Call _exit(%ebx). Unfortunately older versions + * of gcc restrict the number of arguments that can + * be passed to asm(). So, we need to hard-code the + * system call number. + */ + "movl %%eax,%%ebx\n" + "movl $1,%%eax\n" + LSS_ENTRYPOINT + + /* Return to parent. + */ + "1:\n" + : "=a" (__res) + : "0"(-EINVAL), "i"(__NR_clone), + "m"(fn), "m"(child_stack), "m"(flags), "m"(arg), + "m"(parent_tidptr), "m"(newtls), "m"(child_tidptr) + : "memory", "ecx", "edx", "esi", "edi"); + LSS_RETURN(int, __res); + } + + LSS_INLINE _syscall1(int, set_thread_area, void *, u) + LSS_INLINE _syscall1(int, get_thread_area, void *, u) + + LSS_INLINE void (*LSS_NAME(restore_rt)(void))(void) { + /* On i386, the kernel does not know how to return from a signal + * handler. Instead, it relies on user space to provide a + * restorer function that calls the {rt_,}sigreturn() system call. + * Unfortunately, we cannot just reference the glibc version of this + * function, as glibc goes out of its way to make it inaccessible. + */ + void (*res)(void); + __asm__ __volatile__("call 2f\n" + "0:.align 16\n" + "1:movl %1,%%eax\n" + LSS_ENTRYPOINT + "2:popl %0\n" + "addl $(1b-0b),%0\n" + : "=a" (res) + : "i" (__NR_rt_sigreturn)); + return res; + } + LSS_INLINE void (*LSS_NAME(restore)(void))(void) { + /* On i386, the kernel does not know how to return from a signal + * handler. Instead, it relies on user space to provide a + * restorer function that calls the {rt_,}sigreturn() system call. + * Unfortunately, we cannot just reference the glibc version of this + * function, as glibc goes out of its way to make it inaccessible. + */ + void (*res)(void); + __asm__ __volatile__("call 2f\n" + "0:.align 16\n" + "1:pop %%eax\n" + "movl %1,%%eax\n" + LSS_ENTRYPOINT + "2:popl %0\n" + "addl $(1b-0b),%0\n" + : "=a" (res) + : "i" (__NR_sigreturn)); + return res; + } + #elif defined(__x86_64__) + /* There are no known problems with any of the _syscallX() macros + * currently shipping for x86_64, but we still need to be able to define + * our own version so that we can override the location of the errno + * location (e.g. when using the clone() system call with the CLONE_VM + * option). + */ + #undef LSS_ENTRYPOINT + #ifdef SYS_SYSCALL_ENTRYPOINT + static inline void (**LSS_NAME(get_syscall_entrypoint)(void))(void) { + void (**entrypoint)(void); + asm volatile(".bss\n" + ".align 8\n" + ".globl " SYS_SYSCALL_ENTRYPOINT "\n" + ".common " SYS_SYSCALL_ENTRYPOINT ",8,8\n" + ".previous\n" + "mov " SYS_SYSCALL_ENTRYPOINT "@GOTPCREL(%%rip), %0\n" + : "=r"(entrypoint)); + return entrypoint; + } + + #define LSS_ENTRYPOINT \ + ".bss\n" \ + ".align 8\n" \ + ".globl " SYS_SYSCALL_ENTRYPOINT "\n" \ + ".common " SYS_SYSCALL_ENTRYPOINT ",8,8\n" \ + ".previous\n" \ + "mov " SYS_SYSCALL_ENTRYPOINT "@GOTPCREL(%%rip), %%rcx\n" \ + "mov 0(%%rcx), %%rcx\n" \ + "test %%rcx, %%rcx\n" \ + "jz 10001f\n" \ + "call *%%rcx\n" \ + "jmp 10002f\n" \ + "10001:syscall\n" \ + "10002:\n" + + #else + #define LSS_ENTRYPOINT "syscall\n" + #endif + + /* The x32 ABI has 32 bit longs, but the syscall interface is 64 bit. + * We need to explicitly cast to an unsigned 64 bit type to avoid implicit + * sign extension. We can't cast pointers directly because those are + * 32 bits, and gcc will dump ugly warnings about casting from a pointer + * to an integer of a different size. + */ + #undef LSS_SYSCALL_ARG + #define LSS_SYSCALL_ARG(a) ((uint64_t)(uintptr_t)(a)) + #undef _LSS_RETURN + #define _LSS_RETURN(type, res, cast) \ + do { \ + if ((uint64_t)(res) >= (uint64_t)(-4095)) { \ + LSS_ERRNO = (int)(-(res)); \ + res = -1; \ + } \ + return (type)(cast)(res); \ + } while (0) + #undef LSS_RETURN + #define LSS_RETURN(type, res) _LSS_RETURN(type, res, uintptr_t) + + #undef _LSS_BODY + #define _LSS_BODY(nr, type, name, cast, ...) \ + long long __res; \ + __asm__ __volatile__(LSS_BODY_ASM##nr LSS_ENTRYPOINT \ + : "=a" (__res) \ + : "0" (__NR_##name) LSS_BODY_ARG##nr(__VA_ARGS__) \ + : LSS_BODY_CLOBBER##nr "r11", "rcx", "memory"); \ + _LSS_RETURN(type, __res, cast) + #undef LSS_BODY + #define LSS_BODY(nr, type, name, args...) \ + _LSS_BODY(nr, type, name, uintptr_t, ## args) + + #undef LSS_BODY_ASM0 + #undef LSS_BODY_ASM1 + #undef LSS_BODY_ASM2 + #undef LSS_BODY_ASM3 + #undef LSS_BODY_ASM4 + #undef LSS_BODY_ASM5 + #undef LSS_BODY_ASM6 + #define LSS_BODY_ASM0 + #define LSS_BODY_ASM1 LSS_BODY_ASM0 + #define LSS_BODY_ASM2 LSS_BODY_ASM1 + #define LSS_BODY_ASM3 LSS_BODY_ASM2 + #define LSS_BODY_ASM4 LSS_BODY_ASM3 "movq %5,%%r10;" + #define LSS_BODY_ASM5 LSS_BODY_ASM4 "movq %6,%%r8;" + #define LSS_BODY_ASM6 LSS_BODY_ASM5 "movq %7,%%r9;" + + #undef LSS_BODY_CLOBBER0 + #undef LSS_BODY_CLOBBER1 + #undef LSS_BODY_CLOBBER2 + #undef LSS_BODY_CLOBBER3 + #undef LSS_BODY_CLOBBER4 + #undef LSS_BODY_CLOBBER5 + #undef LSS_BODY_CLOBBER6 + #define LSS_BODY_CLOBBER0 + #define LSS_BODY_CLOBBER1 LSS_BODY_CLOBBER0 + #define LSS_BODY_CLOBBER2 LSS_BODY_CLOBBER1 + #define LSS_BODY_CLOBBER3 LSS_BODY_CLOBBER2 + #define LSS_BODY_CLOBBER4 LSS_BODY_CLOBBER3 "r10", + #define LSS_BODY_CLOBBER5 LSS_BODY_CLOBBER4 "r8", + #define LSS_BODY_CLOBBER6 LSS_BODY_CLOBBER5 "r9", + + #undef LSS_BODY_ARG0 + #undef LSS_BODY_ARG1 + #undef LSS_BODY_ARG2 + #undef LSS_BODY_ARG3 + #undef LSS_BODY_ARG4 + #undef LSS_BODY_ARG5 + #undef LSS_BODY_ARG6 + #define LSS_BODY_ARG0() + #define LSS_BODY_ARG1(arg1) \ + LSS_BODY_ARG0(), "D" (arg1) + #define LSS_BODY_ARG2(arg1, arg2) \ + LSS_BODY_ARG1(arg1), "S" (arg2) + #define LSS_BODY_ARG3(arg1, arg2, arg3) \ + LSS_BODY_ARG2(arg1, arg2), "d" (arg3) + #define LSS_BODY_ARG4(arg1, arg2, arg3, arg4) \ + LSS_BODY_ARG3(arg1, arg2, arg3), "r" (arg4) + #define LSS_BODY_ARG5(arg1, arg2, arg3, arg4, arg5) \ + LSS_BODY_ARG4(arg1, arg2, arg3, arg4), "r" (arg5) + #define LSS_BODY_ARG6(arg1, arg2, arg3, arg4, arg5, arg6) \ + LSS_BODY_ARG5(arg1, arg2, arg3, arg4, arg5), "r" (arg6) + + #undef _syscall0 + #define _syscall0(type,name) \ + type LSS_NAME(name)(void) { \ + LSS_BODY(0, type, name); \ + } + #undef _syscall1 + #define _syscall1(type,name,type1,arg1) \ + type LSS_NAME(name)(type1 arg1) { \ + LSS_BODY(1, type, name, LSS_SYSCALL_ARG(arg1)); \ + } + #undef _syscall2 + #define _syscall2(type,name,type1,arg1,type2,arg2) \ + type LSS_NAME(name)(type1 arg1, type2 arg2) { \ + LSS_BODY(2, type, name, LSS_SYSCALL_ARG(arg1), LSS_SYSCALL_ARG(arg2));\ + } + #undef _syscall3 + #define _syscall3(type,name,type1,arg1,type2,arg2,type3,arg3) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3) { \ + LSS_BODY(3, type, name, LSS_SYSCALL_ARG(arg1), LSS_SYSCALL_ARG(arg2), \ + LSS_SYSCALL_ARG(arg3)); \ + } + #undef _syscall4 + #define _syscall4(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4) { \ + LSS_BODY(4, type, name, LSS_SYSCALL_ARG(arg1), LSS_SYSCALL_ARG(arg2), \ + LSS_SYSCALL_ARG(arg3), LSS_SYSCALL_ARG(arg4));\ + } + #undef _syscall5 + #define _syscall5(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \ + type5,arg5) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5) { \ + LSS_BODY(5, type, name, LSS_SYSCALL_ARG(arg1), LSS_SYSCALL_ARG(arg2), \ + LSS_SYSCALL_ARG(arg3), LSS_SYSCALL_ARG(arg4), \ + LSS_SYSCALL_ARG(arg5)); \ + } + #undef _syscall6 + #define _syscall6(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \ + type5,arg5,type6,arg6) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5, type6 arg6) { \ + LSS_BODY(6, type, name, LSS_SYSCALL_ARG(arg1), LSS_SYSCALL_ARG(arg2), \ + LSS_SYSCALL_ARG(arg3), LSS_SYSCALL_ARG(arg4), \ + LSS_SYSCALL_ARG(arg5), LSS_SYSCALL_ARG(arg6));\ + } + LSS_INLINE int LSS_NAME(clone)(int (*fn)(void *), void *child_stack, + int flags, void *arg, int *parent_tidptr, + void *newtls, int *child_tidptr) { + long long __res; + { + __asm__ __volatile__(/* if (fn == NULL) + * return -EINVAL; + */ + "testq %4,%4\n" + "jz 1f\n" + + /* if (child_stack == NULL) + * return -EINVAL; + */ + "testq %5,%5\n" + "jz 1f\n" + + /* childstack -= 2*sizeof(void *); + */ + "subq $16,%5\n" + + /* Push "arg" and "fn" onto the stack that will be + * used by the child. + */ + "movq %7,8(%5)\n" + "movq %4,0(%5)\n" + + /* %rax = syscall(%rax = __NR_clone, + * %rdi = flags, + * %rsi = child_stack, + * %rdx = parent_tidptr, + * %r8 = new_tls, + * %r10 = child_tidptr) + */ + "movq %2,%%rax\n" + "movq %9,%%r8\n" + "movq %10,%%r10\n" + LSS_ENTRYPOINT + + /* if (%rax != 0) + * return; + */ + "testq %%rax,%%rax\n" + "jnz 1f\n" + + /* In the child. Terminate frame pointer chain. + */ + "xorq %%rbp,%%rbp\n" + + /* Call "fn(arg)". + */ + "popq %%rax\n" + "popq %%rdi\n" + "call *%%rax\n" + + /* Call _exit(%ebx). + */ + "movq %%rax,%%rdi\n" + "movq %3,%%rax\n" + LSS_ENTRYPOINT + + /* Return to parent. + */ + "1:\n" + : "=a" (__res) + : "0"(-EINVAL), "i"(__NR_clone), "i"(__NR_exit), + "r"(LSS_SYSCALL_ARG(fn)), + "S"(LSS_SYSCALL_ARG(child_stack)), + "D"(LSS_SYSCALL_ARG(flags)), + "r"(LSS_SYSCALL_ARG(arg)), + "d"(LSS_SYSCALL_ARG(parent_tidptr)), + "r"(LSS_SYSCALL_ARG(newtls)), + "r"(LSS_SYSCALL_ARG(child_tidptr)) + : "memory", "r8", "r10", "r11", "rcx"); + } + LSS_RETURN(int, __res); + } + LSS_INLINE _syscall2(int, arch_prctl, int, c, void *, a) + + LSS_INLINE void (*LSS_NAME(restore_rt)(void))(void) { + /* On x86-64, the kernel does not know how to return from + * a signal handler. Instead, it relies on user space to provide a + * restorer function that calls the rt_sigreturn() system call. + * Unfortunately, we cannot just reference the glibc version of this + * function, as glibc goes out of its way to make it inaccessible. + */ + long long res; + __asm__ __volatile__("jmp 2f\n" + ".align 16\n" + "1:movq %1,%%rax\n" + LSS_ENTRYPOINT + "2:leaq 1b(%%rip),%0\n" + : "=r" (res) + : "i" (__NR_rt_sigreturn)); + return (void (*)(void))(uintptr_t)res; + } + #elif defined(__ARM_ARCH_3__) + /* Most definitions of _syscallX() neglect to mark "memory" as being + * clobbered. This causes problems with compilers, that do a better job + * at optimizing across __asm__ calls. + * So, we just have to redefine all of the _syscallX() macros. + */ + #undef LSS_REG + #define LSS_REG(r,a) register long __r##r __asm__("r"#r) = (long)a + #undef LSS_BODY + #define LSS_BODY(type,name,args...) \ + register long __res_r0 __asm__("r0"); \ + long __res; \ + __asm__ __volatile__ (__syscall(name) \ + : "=r"(__res_r0) : args : "lr", "memory"); \ + __res = __res_r0; \ + LSS_RETURN(type, __res) + #undef _syscall0 + #define _syscall0(type, name) \ + type LSS_NAME(name)(void) { \ + LSS_BODY(type, name); \ + } + #undef _syscall1 + #define _syscall1(type, name, type1, arg1) \ + type LSS_NAME(name)(type1 arg1) { \ + LSS_REG(0, arg1); LSS_BODY(type, name, "r"(__r0)); \ + } + #undef _syscall2 + #define _syscall2(type, name, type1, arg1, type2, arg2) \ + type LSS_NAME(name)(type1 arg1, type2 arg2) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1)); \ + } + #undef _syscall3 + #define _syscall3(type, name, type1, arg1, type2, arg2, type3, arg3) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2)); \ + } + #undef _syscall4 + #define _syscall4(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_REG(3, arg4); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2), "r"(__r3)); \ + } + #undef _syscall5 + #define _syscall5(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \ + type5,arg5) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_REG(3, arg4); LSS_REG(4, arg5); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2), "r"(__r3), \ + "r"(__r4)); \ + } + #undef _syscall6 + #define _syscall6(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \ + type5,arg5,type6,arg6) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5, type6 arg6) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_REG(3, arg4); LSS_REG(4, arg5); LSS_REG(5, arg6); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2), "r"(__r3), \ + "r"(__r4), "r"(__r5)); \ + } + LSS_INLINE int LSS_NAME(clone)(int (*fn)(void *), void *child_stack, + int flags, void *arg, int *parent_tidptr, + void *newtls, int *child_tidptr) { + long __res; + { + register int __flags __asm__("r0") = flags; + register void *__stack __asm__("r1") = child_stack; + register void *__ptid __asm__("r2") = parent_tidptr; + register void *__tls __asm__("r3") = newtls; + register int *__ctid __asm__("r4") = child_tidptr; + __asm__ __volatile__(/* if (fn == NULL || child_stack == NULL) + * return -EINVAL; + */ + "cmp %2,#0\n" + "cmpne %3,#0\n" + "moveq %0,%1\n" + "beq 1f\n" + + /* Push "arg" and "fn" onto the stack that will be + * used by the child. + */ + "str %5,[%3,#-4]!\n" + "str %2,[%3,#-4]!\n" + + /* %r0 = syscall(%r0 = flags, + * %r1 = child_stack, + * %r2 = parent_tidptr, + * %r3 = newtls, + * %r4 = child_tidptr) + */ + __syscall(clone)"\n" + + /* if (%r0 != 0) + * return %r0; + */ + "movs %0,r0\n" + "bne 1f\n" + + /* In the child, now. Call "fn(arg)". + */ + "ldr r0,[sp, #4]\n" + "mov lr,pc\n" + "ldr pc,[sp]\n" + + /* Call _exit(%r0). + */ + __syscall(exit)"\n" + "1:\n" + : "=r" (__res) + : "i"(-EINVAL), + "r"(fn), "r"(__stack), "r"(__flags), "r"(arg), + "r"(__ptid), "r"(__tls), "r"(__ctid) + : "cc", "lr", "memory"); + } + LSS_RETURN(int, __res); + } + #elif defined(__ARM_EABI__) + /* Most definitions of _syscallX() neglect to mark "memory" as being + * clobbered. This causes problems with compilers, that do a better job + * at optimizing across __asm__ calls. + * So, we just have to redefine all fo the _syscallX() macros. + */ + #undef LSS_REG + #define LSS_REG(r,a) register long __r##r __asm__("r"#r) = (long)a + #undef LSS_BODY + #define LSS_BODY(type,name,args...) \ + register long __res_r0 __asm__("r0"); \ + long __res; \ + __asm__ __volatile__ ("push {r7}\n" \ + "mov r7, %1\n" \ + "swi 0x0\n" \ + "pop {r7}\n" \ + : "=r"(__res_r0) \ + : "i"(__NR_##name) , ## args \ + : "lr", "memory"); \ + __res = __res_r0; \ + LSS_RETURN(type, __res) + #undef _syscall0 + #define _syscall0(type, name) \ + type LSS_NAME(name)(void) { \ + LSS_BODY(type, name); \ + } + #undef _syscall1 + #define _syscall1(type, name, type1, arg1) \ + type LSS_NAME(name)(type1 arg1) { \ + LSS_REG(0, arg1); LSS_BODY(type, name, "r"(__r0)); \ + } + #undef _syscall2 + #define _syscall2(type, name, type1, arg1, type2, arg2) \ + type LSS_NAME(name)(type1 arg1, type2 arg2) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1)); \ + } + #undef _syscall3 + #define _syscall3(type, name, type1, arg1, type2, arg2, type3, arg3) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2)); \ + } + #undef _syscall4 + #define _syscall4(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_REG(3, arg4); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2), "r"(__r3)); \ + } + #undef _syscall5 + #define _syscall5(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \ + type5,arg5) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_REG(3, arg4); LSS_REG(4, arg5); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2), "r"(__r3), \ + "r"(__r4)); \ + } + #undef _syscall6 + #define _syscall6(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \ + type5,arg5,type6,arg6) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5, type6 arg6) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_REG(3, arg4); LSS_REG(4, arg5); LSS_REG(5, arg6); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2), "r"(__r3), \ + "r"(__r4), "r"(__r5)); \ + } + LSS_INLINE int LSS_NAME(clone)(int (*fn)(void *), void *child_stack, + int flags, void *arg, int *parent_tidptr, + void *newtls, int *child_tidptr) { + long __res; + if (fn == NULL || child_stack == NULL) { + __res = -EINVAL; + LSS_RETURN(int, __res); + } + + /* Push "arg" and "fn" onto the stack that will be + * used by the child. + */ + { + uintptr_t* cstack = (uintptr_t*)child_stack - 2; + cstack[0] = (uintptr_t)fn; + cstack[1] = (uintptr_t)arg; + child_stack = cstack; + } + { + register int __flags __asm__("r0") = flags; + register void *__stack __asm__("r1") = child_stack; + register void *__ptid __asm__("r2") = parent_tidptr; + register void *__tls __asm__("r3") = newtls; + register int *__ctid __asm__("r4") = child_tidptr; + __asm__ __volatile__( +#ifdef __thumb2__ + "push {r7}\n" +#endif + /* %r0 = syscall(%r0 = flags, + * %r1 = child_stack, + * %r2 = parent_tidptr, + * %r3 = newtls, + * %r4 = child_tidptr) + */ + "mov r7, %6\n" + "swi 0x0\n" + + /* if (%r0 != 0) + * return %r0; + */ + "cmp r0, #0\n" + "bne 1f\n" + + /* In the child, now. Call "fn(arg)". + */ + "ldr r0,[sp, #4]\n" + + "ldr lr,[sp]\n" + "blx lr\n" + + /* Call _exit(%r0). + */ + "mov r7, %7\n" + "swi 0x0\n" + /* Unreachable */ + "bkpt #0\n" + "1:\n" +#ifdef __thumb2__ + "pop {r7}\n" +#endif + "movs %0,r0\n" + : "=r"(__res) + : "r"(__stack), "r"(__flags), "r"(__ptid), "r"(__tls), "r"(__ctid), + "i"(__NR_clone), "i"(__NR_exit) + : "cc", "lr", "memory" +#ifndef __thumb2__ + , "r7" +#endif + ); + } + LSS_RETURN(int, __res); + } + #elif defined(__aarch64__) + /* Most definitions of _syscallX() neglect to mark "memory" as being + * clobbered. This causes problems with compilers, that do a better job + * at optimizing across __asm__ calls. + * So, we just have to redefine all of the _syscallX() macros. + */ + #undef LSS_REG + #define LSS_REG(r,a) register int64_t __r##r __asm__("x"#r) = (int64_t)a + #undef LSS_BODY + #define LSS_BODY(type,name,args...) \ + register int64_t __res_x0 __asm__("x0"); \ + int64_t __res; \ + __asm__ __volatile__ ("mov x8, %1\n" \ + "svc 0x0\n" \ + : "=r"(__res_x0) \ + : "i"(__NR_##name) , ## args \ + : "x8", "memory"); \ + __res = __res_x0; \ + LSS_RETURN(type, __res) + #undef _syscall0 + #define _syscall0(type, name) \ + type LSS_NAME(name)(void) { \ + LSS_BODY(type, name); \ + } + #undef _syscall1 + #define _syscall1(type, name, type1, arg1) \ + type LSS_NAME(name)(type1 arg1) { \ + LSS_REG(0, arg1); LSS_BODY(type, name, "r"(__r0)); \ + } + #undef _syscall2 + #define _syscall2(type, name, type1, arg1, type2, arg2) \ + type LSS_NAME(name)(type1 arg1, type2 arg2) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1)); \ + } + #undef _syscall3 + #define _syscall3(type, name, type1, arg1, type2, arg2, type3, arg3) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2)); \ + } + #undef _syscall4 + #define _syscall4(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_REG(3, arg4); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2), "r"(__r3)); \ + } + #undef _syscall5 + #define _syscall5(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \ + type5,arg5) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_REG(3, arg4); LSS_REG(4, arg5); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2), "r"(__r3), \ + "r"(__r4)); \ + } + #undef _syscall6 + #define _syscall6(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \ + type5,arg5,type6,arg6) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5, type6 arg6) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_REG(3, arg4); LSS_REG(4, arg5); LSS_REG(5, arg6); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2), "r"(__r3), \ + "r"(__r4), "r"(__r5)); \ + } + + LSS_INLINE int LSS_NAME(clone)(int (*fn)(void *), void *child_stack, + int flags, void *arg, int *parent_tidptr, + void *newtls, int *child_tidptr) { + int64_t __res; + { + register uint64_t __flags __asm__("x0") = (uint64_t)flags; + register void *__stack __asm__("x1") = child_stack; + register void *__ptid __asm__("x2") = parent_tidptr; + register void *__tls __asm__("x3") = newtls; + register int *__ctid __asm__("x4") = child_tidptr; + __asm__ __volatile__(/* Push "arg" and "fn" onto the stack that will be + * used by the child. + */ + "stp %1, %4, [%2, #-16]!\n" + + /* %x0 = syscall(%x0 = flags, + * %x1 = child_stack, + * %x2 = parent_tidptr, + * %x3 = newtls, + * %x4 = child_tidptr) + */ + "mov x8, %8\n" + "svc 0x0\n" + + /* if (%r0 != 0) + * return %r0; + */ + "mov %0, x0\n" + "cbnz x0, 1f\n" + + /* In the child, now. Call "fn(arg)". + */ + "ldp x1, x0, [sp], #16\n" + "blr x1\n" + + /* Call _exit(%r0). + */ + "mov x8, %9\n" + "svc 0x0\n" + "1:\n" + : "=r" (__res) + : "r"(fn), "r"(__stack), "r"(__flags), "r"(arg), + "r"(__ptid), "r"(__tls), "r"(__ctid), + "i"(__NR_clone), "i"(__NR_exit) + : "cc", "x8", "memory"); + } + LSS_RETURN(int, __res); + } + LSS_INLINE void (*LSS_NAME(restore_rt)(void))(void) { + /* On aarch64, the kernel does not know how to return from + * a signal handler. Instead, it relies on user space to provide a + * restorer function that calls the rt_sigreturn() system call. + * Unfortunately, we cannot just reference the glibc version of this + * function, as glibc goes out of its way to make it inaccessible. + * + * This is simular to __kernel_rt_sigreturn(). + */ + long long res; + __asm__ __volatile__("b 2f\n" + "1:\n" + /* NOP required by some unwinder. For details. + * see aarch64's vdso/sigreturn.S in the kernel. + */ + "nop\n" + /* Some system softwares recognize this instruction + * sequence to unwind from * signal handlers. Do not + * modify the next two instructions. + */ + "mov x8, %1\n" + "svc 0x0\n" + "2:\n" + "adr %0, 1b\n" + : "=r" (res) + : "i" (__NR_rt_sigreturn)); + return (void (*)(void))(uintptr_t)res; + } + #elif defined(__mips__) + #undef LSS_REG + #define LSS_REG(r,a) register unsigned long __r##r __asm__("$"#r) = \ + (unsigned long)(a) + #undef LSS_BODY + #undef LSS_SYSCALL_CLOBBERS + #if _MIPS_SIM == _MIPS_SIM_ABI32 + #define LSS_SYSCALL_CLOBBERS "$1", "$3", "$8", "$9", "$10", \ + "$11", "$12", "$13", "$14", "$15", \ + "$24", "$25", "hi", "lo", "memory" + #else + #define LSS_SYSCALL_CLOBBERS "$1", "$3", "$10", "$11", "$12", \ + "$13", "$14", "$15", "$24", "$25", \ + "hi", "lo", "memory" + #endif + #define LSS_BODY(type,name,r7,...) \ + register unsigned long __v0 __asm__("$2") = __NR_##name; \ + __asm__ __volatile__ ("syscall\n" \ + : "=r"(__v0), r7 (__r7) \ + : "0"(__v0), ##__VA_ARGS__ \ + : LSS_SYSCALL_CLOBBERS); \ + LSS_RETURN(type, __v0, __r7) + #undef _syscall0 + #define _syscall0(type, name) \ + type LSS_NAME(name)(void) { \ + register unsigned long __r7 __asm__("$7"); \ + LSS_BODY(type, name, "=r"); \ + } + #undef _syscall1 + #define _syscall1(type, name, type1, arg1) \ + type LSS_NAME(name)(type1 arg1) { \ + register unsigned long __r7 __asm__("$7"); \ + LSS_REG(4, arg1); LSS_BODY(type, name, "=r", "r"(__r4)); \ + } + #undef _syscall2 + #define _syscall2(type, name, type1, arg1, type2, arg2) \ + type LSS_NAME(name)(type1 arg1, type2 arg2) { \ + register unsigned long __r7 __asm__("$7"); \ + LSS_REG(4, arg1); LSS_REG(5, arg2); \ + LSS_BODY(type, name, "=r", "r"(__r4), "r"(__r5)); \ + } + #undef _syscall3 + #define _syscall3(type, name, type1, arg1, type2, arg2, type3, arg3) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3) { \ + register unsigned long __r7 __asm__("$7"); \ + LSS_REG(4, arg1); LSS_REG(5, arg2); LSS_REG(6, arg3); \ + LSS_BODY(type, name, "=r", "r"(__r4), "r"(__r5), "r"(__r6)); \ + } + #undef _syscall4 + #define _syscall4(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4) { \ + LSS_REG(4, arg1); LSS_REG(5, arg2); LSS_REG(6, arg3); \ + LSS_REG(7, arg4); \ + LSS_BODY(type, name, "+r", "r"(__r4), "r"(__r5), "r"(__r6)); \ + } + #undef _syscall5 + #if _MIPS_SIM == _MIPS_SIM_ABI32 + /* The old 32bit MIPS system call API passes the fifth and sixth argument + * on the stack, whereas the new APIs use registers "r8" and "r9". + */ + #define _syscall5(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \ + type5,arg5) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5) { \ + LSS_REG(4, arg1); LSS_REG(5, arg2); LSS_REG(6, arg3); \ + LSS_REG(7, arg4); \ + register unsigned long __v0 __asm__("$2") = __NR_##name; \ + __asm__ __volatile__ (".set noreorder\n" \ + "subu $29, 32\n" \ + "sw %5, 16($29)\n" \ + "syscall\n" \ + "addiu $29, 32\n" \ + ".set reorder\n" \ + : "+r"(__v0), "+r" (__r7) \ + : "r"(__r4), "r"(__r5), \ + "r"(__r6), "r" ((unsigned long)arg5) \ + : "$8", "$9", "$10", "$11", "$12", \ + "$13", "$14", "$15", "$24", "$25", \ + "memory"); \ + LSS_RETURN(type, __v0, __r7); \ + } + #else + #define _syscall5(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \ + type5,arg5) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5) { \ + LSS_REG(4, arg1); LSS_REG(5, arg2); LSS_REG(6, arg3); \ + LSS_REG(7, arg4); LSS_REG(8, arg5); \ + LSS_BODY(type, name, "+r", "r"(__r4), "r"(__r5), "r"(__r6), \ + "r"(__r8)); \ + } + #endif + #undef _syscall6 + #if _MIPS_SIM == _MIPS_SIM_ABI32 + /* The old 32bit MIPS system call API passes the fifth and sixth argument + * on the stack, whereas the new APIs use registers "r8" and "r9". + */ + #define _syscall6(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \ + type5,arg5,type6,arg6) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5, type6 arg6) { \ + LSS_REG(4, arg1); LSS_REG(5, arg2); LSS_REG(6, arg3); \ + LSS_REG(7, arg4); \ + register unsigned long __v0 __asm__("$2") = __NR_##name; \ + __asm__ __volatile__ (".set noreorder\n" \ + "subu $29, 32\n" \ + "sw %5, 16($29)\n" \ + "sw %6, 20($29)\n" \ + "syscall\n" \ + "addiu $29, 32\n" \ + ".set reorder\n" \ + : "+r"(__v0), "+r" (__r7) \ + : "r"(__r4), "r"(__r5), \ + "r"(__r6), "r" ((unsigned long)arg5), \ + "r" ((unsigned long)arg6) \ + : "$8", "$9", "$10", "$11", "$12", \ + "$13", "$14", "$15", "$24", "$25", \ + "memory"); \ + LSS_RETURN(type, __v0, __r7); \ + } + #else + #define _syscall6(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \ + type5,arg5,type6,arg6) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5,type6 arg6) { \ + LSS_REG(4, arg1); LSS_REG(5, arg2); LSS_REG(6, arg3); \ + LSS_REG(7, arg4); LSS_REG(8, arg5); LSS_REG(9, arg6); \ + LSS_BODY(type, name, "+r", "r"(__r4), "r"(__r5), "r"(__r6), \ + "r"(__r8), "r"(__r9)); \ + } + #endif + LSS_INLINE int LSS_NAME(clone)(int (*fn)(void *), void *child_stack, + int flags, void *arg, int *parent_tidptr, + void *newtls, int *child_tidptr) { + register unsigned long __v0 __asm__("$2") = -EINVAL; + register unsigned long __r7 __asm__("$7") = (unsigned long)newtls; + { + register int __flags __asm__("$4") = flags; + register void *__stack __asm__("$5") = child_stack; + register void *__ptid __asm__("$6") = parent_tidptr; + register int *__ctid __asm__("$8") = child_tidptr; + __asm__ __volatile__( + #if _MIPS_SIM == _MIPS_SIM_ABI32 && _MIPS_SZPTR == 32 + "subu $29,24\n" + #elif _MIPS_SIM == _MIPS_SIM_NABI32 + "sub $29,16\n" + #else + "dsubu $29,16\n" + #endif + + /* if (fn == NULL || child_stack == NULL) + * return -EINVAL; + */ + "beqz %4,1f\n" + "beqz %5,1f\n" + + /* Push "arg" and "fn" onto the stack that will be + * used by the child. + */ + #if _MIPS_SIM == _MIPS_SIM_ABI32 && _MIPS_SZPTR == 32 + "subu %5,32\n" + "sw %4,0(%5)\n" + "sw %7,4(%5)\n" + #elif _MIPS_SIM == _MIPS_SIM_NABI32 + "sub %5,32\n" + "sw %4,0(%5)\n" + "sw %7,8(%5)\n" + #else + "dsubu %5,32\n" + "sd %4,0(%5)\n" + "sd %7,8(%5)\n" + #endif + + /* $7 = syscall($4 = flags, + * $5 = child_stack, + * $6 = parent_tidptr, + * $7 = newtls, + * $8 = child_tidptr) + */ + "li $2,%2\n" + "syscall\n" + + /* if ($7 != 0) + * return $2; + */ + "bnez $7,1f\n" + "bnez $2,1f\n" + + /* In the child, now. Call "fn(arg)". + */ + #if _MIPS_SIM == _MIPS_SIM_ABI32 && _MIPS_SZPTR == 32 + "lw $25,0($29)\n" + "lw $4,4($29)\n" + #elif _MIPS_SIM == _MIPS_SIM_NABI32 + "lw $25,0($29)\n" + "lw $4,8($29)\n" + #else + "ld $25,0($29)\n" + "ld $4,8($29)\n" + #endif + "jalr $25\n" + + /* Call _exit($2) + */ + "move $4,$2\n" + "li $2,%3\n" + "syscall\n" + + "1:\n" + #if _MIPS_SIM == _MIPS_SIM_ABI32 && _MIPS_SZPTR == 32 + "addu $29, 24\n" + #elif _MIPS_SIM == _MIPS_SIM_NABI32 + "add $29, 16\n" + #else + "daddu $29,16\n" + #endif + : "+r" (__v0), "+r" (__r7) + : "i"(__NR_clone), "i"(__NR_exit), "r"(fn), + "r"(__stack), "r"(__flags), "r"(arg), + "r"(__ptid), "r"(__ctid) + : "$9", "$10", "$11", "$12", "$13", "$14", "$15", + "$24", "$25", "memory"); + } + LSS_RETURN(int, __v0, __r7); + } + #elif defined (__PPC__) + #undef LSS_LOADARGS_0 + #define LSS_LOADARGS_0(name, dummy...) \ + __sc_0 = __NR_##name + #undef LSS_LOADARGS_1 + #define LSS_LOADARGS_1(name, arg1) \ + LSS_LOADARGS_0(name); \ + __sc_3 = (unsigned long) (arg1) + #undef LSS_LOADARGS_2 + #define LSS_LOADARGS_2(name, arg1, arg2) \ + LSS_LOADARGS_1(name, arg1); \ + __sc_4 = (unsigned long) (arg2) + #undef LSS_LOADARGS_3 + #define LSS_LOADARGS_3(name, arg1, arg2, arg3) \ + LSS_LOADARGS_2(name, arg1, arg2); \ + __sc_5 = (unsigned long) (arg3) + #undef LSS_LOADARGS_4 + #define LSS_LOADARGS_4(name, arg1, arg2, arg3, arg4) \ + LSS_LOADARGS_3(name, arg1, arg2, arg3); \ + __sc_6 = (unsigned long) (arg4) + #undef LSS_LOADARGS_5 + #define LSS_LOADARGS_5(name, arg1, arg2, arg3, arg4, arg5) \ + LSS_LOADARGS_4(name, arg1, arg2, arg3, arg4); \ + __sc_7 = (unsigned long) (arg5) + #undef LSS_LOADARGS_6 + #define LSS_LOADARGS_6(name, arg1, arg2, arg3, arg4, arg5, arg6) \ + LSS_LOADARGS_5(name, arg1, arg2, arg3, arg4, arg5); \ + __sc_8 = (unsigned long) (arg6) + #undef LSS_ASMINPUT_0 + #define LSS_ASMINPUT_0 "0" (__sc_0) + #undef LSS_ASMINPUT_1 + #define LSS_ASMINPUT_1 LSS_ASMINPUT_0, "1" (__sc_3) + #undef LSS_ASMINPUT_2 + #define LSS_ASMINPUT_2 LSS_ASMINPUT_1, "2" (__sc_4) + #undef LSS_ASMINPUT_3 + #define LSS_ASMINPUT_3 LSS_ASMINPUT_2, "3" (__sc_5) + #undef LSS_ASMINPUT_4 + #define LSS_ASMINPUT_4 LSS_ASMINPUT_3, "4" (__sc_6) + #undef LSS_ASMINPUT_5 + #define LSS_ASMINPUT_5 LSS_ASMINPUT_4, "5" (__sc_7) + #undef LSS_ASMINPUT_6 + #define LSS_ASMINPUT_6 LSS_ASMINPUT_5, "6" (__sc_8) + #undef LSS_BODY + #define LSS_BODY(nr, type, name, args...) \ + long __sc_ret, __sc_err; \ + { \ + register unsigned long __sc_0 __asm__ ("r0"); \ + register unsigned long __sc_3 __asm__ ("r3"); \ + register unsigned long __sc_4 __asm__ ("r4"); \ + register unsigned long __sc_5 __asm__ ("r5"); \ + register unsigned long __sc_6 __asm__ ("r6"); \ + register unsigned long __sc_7 __asm__ ("r7"); \ + register unsigned long __sc_8 __asm__ ("r8"); \ + \ + LSS_LOADARGS_##nr(name, args); \ + __asm__ __volatile__ \ + ("sc\n\t" \ + "mfcr %0" \ + : "=&r" (__sc_0), \ + "=&r" (__sc_3), "=&r" (__sc_4), \ + "=&r" (__sc_5), "=&r" (__sc_6), \ + "=&r" (__sc_7), "=&r" (__sc_8) \ + : LSS_ASMINPUT_##nr \ + : "cr0", "ctr", "memory", \ + "r9", "r10", "r11", "r12"); \ + __sc_ret = __sc_3; \ + __sc_err = __sc_0; \ + } \ + LSS_RETURN(type, __sc_ret, __sc_err) + #undef _syscall0 + #define _syscall0(type, name) \ + type LSS_NAME(name)(void) { \ + LSS_BODY(0, type, name); \ + } + #undef _syscall1 + #define _syscall1(type, name, type1, arg1) \ + type LSS_NAME(name)(type1 arg1) { \ + LSS_BODY(1, type, name, arg1); \ + } + #undef _syscall2 + #define _syscall2(type, name, type1, arg1, type2, arg2) \ + type LSS_NAME(name)(type1 arg1, type2 arg2) { \ + LSS_BODY(2, type, name, arg1, arg2); \ + } + #undef _syscall3 + #define _syscall3(type, name, type1, arg1, type2, arg2, type3, arg3) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3) { \ + LSS_BODY(3, type, name, arg1, arg2, arg3); \ + } + #undef _syscall4 + #define _syscall4(type, name, type1, arg1, type2, arg2, type3, arg3, \ + type4, arg4) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4) { \ + LSS_BODY(4, type, name, arg1, arg2, arg3, arg4); \ + } + #undef _syscall5 + #define _syscall5(type, name, type1, arg1, type2, arg2, type3, arg3, \ + type4, arg4, type5, arg5) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5) { \ + LSS_BODY(5, type, name, arg1, arg2, arg3, arg4, arg5); \ + } + #undef _syscall6 + #define _syscall6(type, name, type1, arg1, type2, arg2, type3, arg3, \ + type4, arg4, type5, arg5, type6, arg6) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5, type6 arg6) { \ + LSS_BODY(6, type, name, arg1, arg2, arg3, arg4, arg5, arg6); \ + } + /* clone function adapted from glibc 2.3.6 clone.S */ + /* TODO(csilvers): consider wrapping some args up in a struct, like we + * do for i386's _syscall6, so we can compile successfully on gcc 2.95 + */ + LSS_INLINE int LSS_NAME(clone)(int (*fn)(void *), void *child_stack, + int flags, void *arg, int *parent_tidptr, + void *newtls, int *child_tidptr) { + long __ret, __err; + { + register int (*__fn)(void *) __asm__ ("r8") = fn; + register void *__cstack __asm__ ("r4") = child_stack; + register int __flags __asm__ ("r3") = flags; + register void * __arg __asm__ ("r9") = arg; + register int * __ptidptr __asm__ ("r5") = parent_tidptr; + register void * __newtls __asm__ ("r6") = newtls; + register int * __ctidptr __asm__ ("r7") = child_tidptr; + __asm__ __volatile__( + /* check for fn == NULL + * and child_stack == NULL + */ + "cmpwi cr0, %6, 0\n\t" + "cmpwi cr1, %7, 0\n\t" + "cror cr0*4+eq, cr1*4+eq, cr0*4+eq\n\t" + "beq- cr0, 1f\n\t" + + /* set up stack frame for child */ + "clrrwi %7, %7, 4\n\t" + "li 0, 0\n\t" + "stwu 0, -16(%7)\n\t" + + /* fn, arg, child_stack are saved across the syscall: r28-30 */ + "mr 28, %6\n\t" + "mr 29, %7\n\t" + "mr 27, %9\n\t" + + /* syscall */ + "li 0, %4\n\t" + /* flags already in r3 + * child_stack already in r4 + * ptidptr already in r5 + * newtls already in r6 + * ctidptr already in r7 + */ + "sc\n\t" + + /* Test if syscall was successful */ + "cmpwi cr1, 3, 0\n\t" + "crandc cr1*4+eq, cr1*4+eq, cr0*4+so\n\t" + "bne- cr1, 1f\n\t" + + /* Do the function call */ + "mtctr 28\n\t" + "mr 3, 27\n\t" + "bctrl\n\t" + + /* Call _exit(r3) */ + "li 0, %5\n\t" + "sc\n\t" + + /* Return to parent */ + "1:\n" + "mfcr %1\n\t" + "mr %0, 3\n\t" + : "=r" (__ret), "=r" (__err) + : "0" (-1), "1" (EINVAL), + "i" (__NR_clone), "i" (__NR_exit), + "r" (__fn), "r" (__cstack), "r" (__flags), + "r" (__arg), "r" (__ptidptr), "r" (__newtls), + "r" (__ctidptr) + : "cr0", "cr1", "memory", "ctr", + "r0", "r29", "r27", "r28"); + } + LSS_RETURN(int, __ret, __err); + } + #elif defined(__s390__) + #undef LSS_REG + #define LSS_REG(r, a) register unsigned long __r##r __asm__("r"#r) = (unsigned long) a + #undef LSS_BODY + #define LSS_BODY(type, name, args...) \ + register unsigned long __nr __asm__("r1") \ + = (unsigned long)(__NR_##name); \ + register long __res_r2 __asm__("r2"); \ + long __res; \ + __asm__ __volatile__ \ + ("svc 0\n\t" \ + : "=d"(__res_r2) \ + : "d"(__nr), ## args \ + : "memory"); \ + __res = __res_r2; \ + LSS_RETURN(type, __res) + #undef _syscall0 + #define _syscall0(type, name) \ + type LSS_NAME(name)(void) { \ + LSS_BODY(type, name); \ + } + #undef _syscall1 + #define _syscall1(type, name, type1, arg1) \ + type LSS_NAME(name)(type1 arg1) { \ + LSS_REG(2, arg1); \ + LSS_BODY(type, name, "0"(__r2)); \ + } + #undef _syscall2 + #define _syscall2(type, name, type1, arg1, type2, arg2) \ + type LSS_NAME(name)(type1 arg1, type2 arg2) { \ + LSS_REG(2, arg1); LSS_REG(3, arg2); \ + LSS_BODY(type, name, "0"(__r2), "d"(__r3)); \ + } + #undef _syscall3 + #define _syscall3(type, name, type1, arg1, type2, arg2, type3, arg3) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3) { \ + LSS_REG(2, arg1); LSS_REG(3, arg2); LSS_REG(4, arg3); \ + LSS_BODY(type, name, "0"(__r2), "d"(__r3), "d"(__r4)); \ + } + #undef _syscall4 + #define _syscall4(type, name, type1, arg1, type2, arg2, type3, arg3, \ + type4, arg4) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, \ + type4 arg4) { \ + LSS_REG(2, arg1); LSS_REG(3, arg2); LSS_REG(4, arg3); \ + LSS_REG(5, arg4); \ + LSS_BODY(type, name, "0"(__r2), "d"(__r3), "d"(__r4), \ + "d"(__r5)); \ + } + #undef _syscall5 + #define _syscall5(type, name, type1, arg1, type2, arg2, type3, arg3, \ + type4, arg4, type5, arg5) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, \ + type4 arg4, type5 arg5) { \ + LSS_REG(2, arg1); LSS_REG(3, arg2); LSS_REG(4, arg3); \ + LSS_REG(5, arg4); LSS_REG(6, arg5); \ + LSS_BODY(type, name, "0"(__r2), "d"(__r3), "d"(__r4), \ + "d"(__r5), "d"(__r6)); \ + } + #undef _syscall6 + #define _syscall6(type, name, type1, arg1, type2, arg2, type3, arg3, \ + type4, arg4, type5, arg5, type6, arg6) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, \ + type4 arg4, type5 arg5, type6 arg6) { \ + LSS_REG(2, arg1); LSS_REG(3, arg2); LSS_REG(4, arg3); \ + LSS_REG(5, arg4); LSS_REG(6, arg5); LSS_REG(7, arg6); \ + LSS_BODY(type, name, "0"(__r2), "d"(__r3), "d"(__r4), \ + "d"(__r5), "d"(__r6), "d"(__r7)); \ + } + LSS_INLINE int LSS_NAME(clone)(int (*fn)(void *), void *child_stack, + int flags, void *arg, int *parent_tidptr, + void *newtls, int *child_tidptr) { + long __ret; + { + register int (*__fn)(void *) __asm__ ("r1") = fn; + register void *__cstack __asm__ ("r2") = child_stack; + register int __flags __asm__ ("r3") = flags; + register void *__arg __asm__ ("r0") = arg; + register int *__ptidptr __asm__ ("r4") = parent_tidptr; + register void *__newtls __asm__ ("r6") = newtls; + register int *__ctidptr __asm__ ("r5") = child_tidptr; + __asm__ __volatile__ ( + #ifndef __s390x__ + /* arg already in r0 */ + "ltr %4, %4\n\t" /* check fn, which is already in r1 */ + "jz 1f\n\t" /* NULL function pointer, return -EINVAL */ + "ltr %5, %5\n\t" /* check child_stack, which is already in r2 */ + "jz 1f\n\t" /* NULL stack pointer, return -EINVAL */ + /* flags already in r3 */ + /* parent_tidptr already in r4 */ + /* child_tidptr already in r5 */ + /* newtls already in r6 */ + "svc %2\n\t" /* invoke clone syscall */ + "ltr %0,%%r2\n\t" /* load return code into __ret and test */ + "jnz 1f\n\t" /* return to parent if non-zero */ + /* start child thread */ + "lr %%r2, %7\n\t" /* set first parameter to void *arg */ + "ahi %%r15, -96\n\t" /* make room on the stack for the save area */ + "xc 0(4,%%r15), 0(%%r15)\n\t" + "basr %%r14, %4\n\t" /* jump to fn */ + "svc %3\n" /* invoke exit syscall */ + "1:\n" + #else + /* arg already in r0 */ + "ltgr %4, %4\n\t" /* check fn, which is already in r1 */ + "jz 1f\n\t" /* NULL function pointer, return -EINVAL */ + "ltgr %5, %5\n\t" /* check child_stack, which is already in r2 */ + "jz 1f\n\t" /* NULL stack pointer, return -EINVAL */ + /* flags already in r3 */ + /* parent_tidptr already in r4 */ + /* child_tidptr already in r5 */ + /* newtls already in r6 */ + "svc %2\n\t" /* invoke clone syscall */ + "ltgr %0, %%r2\n\t" /* load return code into __ret and test */ + "jnz 1f\n\t" /* return to parent if non-zero */ + /* start child thread */ + "lgr %%r2, %7\n\t" /* set first parameter to void *arg */ + "aghi %%r15, -160\n\t" /* make room on the stack for the save area */ + "xc 0(8,%%r15), 0(%%r15)\n\t" + "basr %%r14, %4\n\t" /* jump to fn */ + "svc %3\n" /* invoke exit syscall */ + "1:\n" + #endif + : "=r" (__ret) + : "0" (-EINVAL), "i" (__NR_clone), "i" (__NR_exit), + "d" (__fn), "d" (__cstack), "d" (__flags), "d" (__arg), + "d" (__ptidptr), "d" (__newtls), "d" (__ctidptr) + : "cc", "r14", "memory" + ); + } + LSS_RETURN(int, __ret); + } + #elif defined(__riscv) && __riscv_xlen == 64 + #undef LSS_REG + #define LSS_REG(r,a) register int64_t __r##r __asm__("a"#r) = (int64_t)a + #undef LSS_BODY + #define LSS_BODY(type,name,args...) \ + register int64_t __res_a0 __asm__("a0"); \ + register int64_t __a7 __asm__("a7") = __NR_##name; \ + int64_t __res; \ + __asm__ __volatile__ ("scall\n" \ + : "=r"(__res_a0) \ + : "r"(__a7) , ## args \ + : "memory"); \ + __res = __res_a0; \ + LSS_RETURN(type, __res) + #undef _syscall0 + #define _syscall0(type, name) \ + type LSS_NAME(name)(void) { \ + LSS_BODY(type, name); \ + } + #undef _syscall1 + #define _syscall1(type, name, type1, arg1) \ + type LSS_NAME(name)(type1 arg1) { \ + LSS_REG(0, arg1); LSS_BODY(type, name, "r"(__r0)); \ + } + #undef _syscall2 + #define _syscall2(type, name, type1, arg1, type2, arg2) \ + type LSS_NAME(name)(type1 arg1, type2 arg2) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1)); \ + } + #undef _syscall3 + #define _syscall3(type, name, type1, arg1, type2, arg2, type3, arg3) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2)); \ + } + #undef _syscall4 + #define _syscall4(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_REG(3, arg4); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2), "r"(__r3)); \ + } + #undef _syscall5 + #define _syscall5(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \ + type5,arg5) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_REG(3, arg4); LSS_REG(4, arg5); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2), "r"(__r3), \ + "r"(__r4)); \ + } + #undef _syscall6 + #define _syscall6(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \ + type5,arg5,type6,arg6) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5, type6 arg6) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_REG(3, arg4); LSS_REG(4, arg5); LSS_REG(5, arg6); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2), "r"(__r3), \ + "r"(__r4), "r"(__r5)); \ + } + + LSS_INLINE int LSS_NAME(clone)(int (*fn)(void *), void *child_stack, + int flags, void *arg, int *parent_tidptr, + void *newtls, int *child_tidptr) { + int64_t __res; + { + register int64_t __res_a0 __asm__("a0"); + register uint64_t __flags __asm__("a0") = (uint64_t)flags; + register void *__stack __asm__("a1") = child_stack; + register void *__ptid __asm__("a2") = parent_tidptr; + register void *__tls __asm__("a3") = newtls; + register int *__ctid __asm__("a4") = child_tidptr; + __asm__ __volatile__(/* Push "arg" and "fn" onto the stack that will be + * used by the child. + */ + "addi %2,%2,-16\n" + "sd %1, 0(%2)\n" + "sd %4, 8(%2)\n" + + /* %a0 = syscall(%a0 = flags, + * %a1 = child_stack, + * %a2 = parent_tidptr, + * %a3 = newtls, + * %a4 = child_tidptr) + */ + "li a7, %8\n" + "scall\n" + + /* if (%a0 != 0) + * return %a0; + */ + "bnez %0, 1f\n" + + /* In the child, now. Call "fn(arg)". + */ + "ld a1, 0(sp)\n" + "ld a0, 8(sp)\n" + "jalr a1\n" + + /* Call _exit(%a0). + */ + "li a7, %9\n" + "scall\n" + "1:\n" + : "=r" (__res_a0) + : "r"(fn), "r"(__stack), "r"(__flags), "r"(arg), + "r"(__ptid), "r"(__tls), "r"(__ctid), + "i"(__NR_clone), "i"(__NR_exit) + : "cc", "memory"); + __res = __res_a0; + } + LSS_RETURN(int, __res); + } + #elif defined(__e2k__) + + #undef _LSS_BODY + #define _LSS_BODY(nr, type, name, ...) \ + register unsigned long long __res; \ + __asm__ __volatile__ \ + ( \ + "{\n\t" \ + " sdisp %%ctpr1, 0x3\n\t" \ + " addd, s 0x0, %[sys_num], %%b[0]\n\t" \ + LSS_BODY_ASM##nr \ + "}\n\t" \ + "{\n\t" \ + " call %%ctpr1, wbs = %#\n\t" \ + "}\n\t" \ + "{\n\t" \ + " addd, s 0x0, %%b[0], %[res]\n\t" \ + "}\n\t" \ + : [res] "=r" (__res) \ + : \ + LSS_BODY_ARG##nr(__VA_ARGS__) \ + [sys_num] "ri" (__NR_##name) \ + : "ctpr1", "ctpr2", "ctpr3", \ + "b[0]", "b[1]", "b[2]", "b[3]", \ + "b[4]", "b[5]", "b[6]", "b[7]" \ + ); \ + LSS_RETURN(type, __res); + + #undef LSS_BODY + #define LSS_BODY(nr, type, name, args...) \ + _LSS_BODY(nr, type, name, ## args) + + #undef LSS_BODY_ASM0 + #undef LSS_BODY_ASM1 + #undef LSS_BODY_ASM2 + #undef LSS_BODY_ASM3 + #undef LSS_BODY_ASM4 + #undef LSS_BODY_ASM5 + #undef LSS_BODY_ASM6 + + #define LSS_BODY_ASM0 + #define LSS_BODY_ASM1 LSS_BODY_ASM0 \ + " addd, s 0x0, %[arg1], %%b[1]\n\t" + #define LSS_BODY_ASM2 LSS_BODY_ASM1 \ + " addd, s 0x0, %[arg2], %%b[2]\n\t" + #define LSS_BODY_ASM3 LSS_BODY_ASM2 \ + " addd, s 0x0, %[arg3], %%b[3]\n\t" + #define LSS_BODY_ASM4 LSS_BODY_ASM3 \ + " addd, s 0x0, %[arg4], %%b[4]\n\t" + #define LSS_BODY_ASM5 LSS_BODY_ASM4 \ + " addd, s 0x0, %[arg5], %%b[5]\n\t" + #define LSS_BODY_ASM6 LSS_BODY_ASM5 \ + "}\n\t" \ + "{\n\t" \ + " addd, s 0x0, %[arg6], %%b[6]\n\t" + + #undef LSS_SYSCALL_ARG + #define LSS_SYSCALL_ARG(a) ((unsigned long long)(uintptr_t)(a)) + + #undef LSS_BODY_ARG0 + #undef LSS_BODY_ARG1 + #undef LSS_BODY_ARG2 + #undef LSS_BODY_ARG3 + #undef LSS_BODY_ARG4 + #undef LSS_BODY_ARG5 + #undef LSS_BODY_ARG6 + + #define LSS_BODY_ARG0() + #define LSS_BODY_ARG1(_arg1) \ + [arg1] "ri" LSS_SYSCALL_ARG(_arg1), + #define LSS_BODY_ARG2(_arg1, _arg2) \ + LSS_BODY_ARG1(_arg1) \ + [arg2] "ri" LSS_SYSCALL_ARG(_arg2), + #define LSS_BODY_ARG3(_arg1, _arg2, _arg3) \ + LSS_BODY_ARG2(_arg1, _arg2) \ + [arg3] "ri" LSS_SYSCALL_ARG(_arg3), + #define LSS_BODY_ARG4(_arg1, _arg2, _arg3, _arg4) \ + LSS_BODY_ARG3(_arg1, _arg2, _arg3) \ + [arg4] "ri" LSS_SYSCALL_ARG(_arg4), + #define LSS_BODY_ARG5(_arg1, _arg2, _arg3, _arg4, _arg5) \ + LSS_BODY_ARG4(_arg1, _arg2, _arg3, _arg4) \ + [arg5] "ri" LSS_SYSCALL_ARG(_arg5), + #define LSS_BODY_ARG6(_arg1, _arg2, _arg3, _arg4, _arg5, _arg6) \ + LSS_BODY_ARG5(_arg1, _arg2, _arg3, _arg4, _arg5) \ + [arg6] "ri" LSS_SYSCALL_ARG(_arg6), + + #undef _syscall0 + #define _syscall0(type, name) \ + type LSS_NAME(name)(void) { \ + LSS_BODY(0, type, name); \ + } + + #undef _syscall1 + #define _syscall1(type, name, type1, arg1) \ + type LSS_NAME(name)(type1 arg1) { \ + LSS_BODY(1, type, name, arg1) \ + } + + #undef _syscall2 + #define _syscall2(type, name, type1, arg1, type2, arg2) \ + type LSS_NAME(name)(type1 arg1, type2 arg2) { \ + LSS_BODY(2, type, name, arg1, arg2) \ + } + + #undef _syscall3 + #define _syscall3(type, name, type1, arg1, type2, arg2, type3, arg3) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3) { \ + LSS_BODY(3, type, name, arg1, arg2, arg3) \ + } + + #undef _syscall4 + #define _syscall4(type, name, type1, arg1, type2, arg2, type3, arg3, \ + type4, arg4) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4) { \ + LSS_BODY(4, type, name, arg1, arg2, arg3, arg4) \ + } + + #undef _syscall5 + #define _syscall5(type, name, type1, arg1, type2, arg2, type3, arg3, \ + type4, arg4, type5, arg5) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5) { \ + LSS_BODY(5, type, name, arg1, arg2, arg3, arg4, arg5) \ + } + + #undef _syscall6 + #define _syscall6(type, name, type1, arg1, type2, arg2, type3, arg3, \ + type4, arg4, type5, arg5, type6, arg6) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5, type6 arg6) { \ + LSS_BODY(6, type, name, arg1, arg2, arg3, arg4, arg5, arg6) \ + } + + LSS_INLINE int LSS_NAME(clone)(int (*fn)(void *), void *child_stack, + int flags, void *arg, int *parent_tidptr, + void *newtls, int *child_tidptr) { + unsigned long long __res; + + __asm__ __volatile__ ( + "{\n\t" + " addd,s 0x0, %[nr_clone], %%b[0]\n\t" + " addd,s 0x0, %[flags], %%db[1]\n\t" + " addd,s 0x0, %[child_stack], %%db[2]\n\t" + " addd,s 0x0, %[parent_tidptr], %%db[3]\n\t" + " addd,s 0x0, %[child_tidptr], %%db[4]\n\t" + " addd,s 0x0, %[newtls], %%db[5]\n\t" + "}\n\t" + /* if (fn == NULL) + * return -EINVAL; + */ + + "{\n\t" + " disp %%ctpr1, .L1\n\t" + "}\n\t" + "{\n\t" + " cmpesb,s 0x0, %[fn], %%pred0\n\t" + "}\n\t" + "{\n\t" + " ct %%ctpr1 ? %%pred0\n\t" + "}\n\t" + + /* if (child_stack == NULL) + * return -EINVAL; + */ + "{\n\t" + " cmpesb,s 0x0, %%db[2], %%pred0\n\t" + "}\n\t" + "{\n\t" + " ct %%ctpr1 ? %%pred0\n\t" + "}\n\t" + + /* b[0] = syscall(%b[0] = __NR_clone, + * %db[1] = flags, + * %db[2] = child_stack, + * %db[3] = parent_tidptr, + * %db[4] = child_tidptr, + * %db[5] = newtls) + */ + "{\n\t" + " sdisp %%ctpr1, 0x3\n\t" + "}\n\t" + "{\n\t" + " call %%ctpr1, wbs = %#\n\t" + "}\n\t" + + /* if (%[b0] != 0) + * return %b[0]; + */ + "{\n\t" + " disp %%ctpr1, .L2\n\t" + " cmpesb,s 0x0, %%b[0], %%pred0\n\t" + "}\n\t" + "{\n\t" + " ct %%ctpr1 ? ~%%pred0\n\t" + "}\n\t" + /* In the child, now. Call "fn(arg)". + */ + + "{\n\t" + " movtd,s %[fn], %%ctpr1\n\t" + "}\n\t" + "{\n\t" + " addd,s 0x0, %[arg], %%db[0]\n\t" + "}\n\t" + "{\n\t" + " call %%ctpr1, wbs = %#\n\t" + "}\n\t" + /* Call _exit(%b[0]). + */ + + "{\n\t" + " sdisp %%ctpr1, 0x3\n\t" + " addd,s 0x0, %%b[0], %%b[1]\n\t" + "}\n\t" + "{\n\t" + " addd,s 0x0, %[nr_exit], %%b[0]\n\t" + "}\n\t" + "{\n\t" + " call %%ctpr1, wbs = %#\n\t" + "}\n\t" + "{\n\t" + " disp %%ctpr1, .L2\n\t" + " adds,s 0x0, 0x0, %%b[0]\n\t" + "}\n\t" + "{\n\t" + " ct %%ctpr1\n\t" + "}\n\t" + ".L1:\n\t" + "{\n\t" + " addd,s 0x0, %[einval], %%b[0]\n\t" + "}\n\t" + ".L2:\n\t" + "{\n\t" + " addd,s 0x0, %%b[0], %[res]\n\t" + "}\n\t" + : [res] "=r" LSS_SYSCALL_ARG(__res) + : [nr_clone] "ri" LSS_SYSCALL_ARG(__NR_clone) + [arg] "ri" LSS_SYSCALL_ARG(arg) + [nr_exit] "ri" LSS_SYSCALL_ARG(__NR_exit) + [flags] "ri" LSS_SYSCALL_ARG(flags) + [child_stack] "ri" LSS_SYSCALL_ARG(child_stack) + [parent_tidptr] "ri" + LSS_SYSCALL_ARG(parent_tidptr) + [newtls] "ri" LSS_SYSCALL_ARG(newtls) + [child_tidptr] "ri" + LSS_SYSCALL_ARG(child_tidptr) + [fn] "ri" LSS_SYSCALL_ARG(fn) + [einval] "ri" LSS_SYSCALL_ARG(-EINVAL) + : "ctpr1", "b[0]", "b[1]", "b[2]", "b[3]", + "b[4]", "b[5]", "pred0"); + LSS_RETURN(int, __res); + } + #elif defined(__loongarch_lp64) + /* Most definitions of _syscallX() neglect to mark "memory" as being + * clobbered. This causes problems with compilers, that do a better job + * at optimizing across __asm__ calls. + * So, we just have to redefine all of the _syscallX() macros. + */ + #undef LSS_REG + #define LSS_REG(ar,a) register int64_t __r##ar __asm__("a"#ar) = (int64_t)a + /* syscall is like subroutine calls, all caller-saved registers may be + * clobbered, we should add them to the |Clobbers| list. + * a0 is not included because it's in the output list. + */ + #define LSS_SYSCALL_CLOBBERS "t0", "t1", "t2", "t3", "t4", "t5", "t6", \ + "t7", "t8", "memory" + #undef LSS_BODY + #define LSS_BODY(type,name,args...) \ + register int64_t __res_a0 __asm__("a0"); \ + register int64_t __a7 __asm__("a7") = __NR_##name; \ + int64_t __res; \ + __asm__ __volatile__ ("syscall 0x0\n" \ + : "=r"(__res_a0) \ + : "r"(__a7), ## args \ + : LSS_SYSCALL_CLOBBERS); \ + __res = __res_a0; \ + LSS_RETURN(type, __res) + #undef _syscall0 + #define _syscall0(type, name) \ + type LSS_NAME(name)(void) { \ + LSS_BODY(type, name); \ + } + #undef _syscall1 + #define _syscall1(type, name, type1, arg1) \ + type LSS_NAME(name)(type1 arg1) { \ + LSS_REG(0, arg1); LSS_BODY(type, name, "r"(__r0)); \ + } + #undef _syscall2 + #define _syscall2(type, name, type1, arg1, type2, arg2) \ + type LSS_NAME(name)(type1 arg1, type2 arg2) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1)); \ + } + #undef _syscall3 + #define _syscall3(type, name, type1, arg1, type2, arg2, type3, arg3) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2)); \ + } + #undef _syscall4 + #define _syscall4(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_REG(3, arg4); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2), "r"(__r3)); \ + } + #undef _syscall5 + #define _syscall5(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \ + type5,arg5) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_REG(3, arg4); LSS_REG(4, arg5); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2), "r"(__r3), \ + "r"(__r4)); \ + } + #undef _syscall6 + #define _syscall6(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \ + type5,arg5,type6,arg6) \ + type LSS_NAME(name)(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \ + type5 arg5, type6 arg6) { \ + LSS_REG(0, arg1); LSS_REG(1, arg2); LSS_REG(2, arg3); \ + LSS_REG(3, arg4); LSS_REG(4, arg5); LSS_REG(5, arg6); \ + LSS_BODY(type, name, "r"(__r0), "r"(__r1), "r"(__r2), "r"(__r3), \ + "r"(__r4), "r"(__r5)); \ + } + + LSS_INLINE int LSS_NAME(clone)(int (*fn)(void *), void *child_stack, + int flags, void *arg, int *parent_tidptr, + void *newtls, int *child_tidptr) { + int64_t __res; + { + register int64_t __res_a0 __asm__("a0"); + register uint64_t __flags __asm__("a0") = flags; + register void *__stack __asm__("a1") = child_stack; + register void *__ptid __asm__("a2") = parent_tidptr; + register void *__tls __asm__("a3") = newtls; + register int *__ctid __asm__("a4") = child_tidptr; + __asm__ __volatile__(/* Push "arg" and "fn" onto the stack that will be + * used by the child. + */ + "addi.d %2, %2, -16\n" + "st.d %1, %2, 8\n" + "st.d %4, %2, 0\n" + + /* %a0 = syscall(%a0 = flags, + * %a1 = child_stack, + * %a2 = parent_tidptr, + * %a3 = newtls, + * %a4 = child_tidptr) + */ + "li.d $a7, %8\n" + "syscall 0x0\n" + + /* if (%a0 != 0) + * return %a0; + */ + "bnez $a0, 1f\n" + + /* In the child, now. Call "fn(arg)". + */ + "ld.d $a0, $sp, 0\n" + "ld.d $a1, $sp, 8\n" + "addi.d $sp, $sp, 16\n" + "jirl $ra, $a1, 0\n" + + /* Call _exit(%a0). + */ + "li.d $a7, %9\n" + "syscall 0x0\n" + "1:\n" + : "=r" (__res_a0) + : "r"(fn), "r"(__stack), "r"(__flags), "r"(arg), + "r"(__ptid), "r"(__tls), "r"(__ctid), + "i"(__NR_clone), "i"(__NR_exit) + : "a7", LSS_SYSCALL_CLOBBERS); + __res = __res_a0; + } + LSS_RETURN(int, __res); + } + + #endif + #define __NR__exit __NR_exit + #define __NR__gettid __NR_gettid + #define __NR__mremap __NR_mremap + LSS_INLINE _syscall1(void *, brk, void *, e) + LSS_INLINE _syscall1(int, chdir, const char *,p) + LSS_INLINE _syscall1(int, close, int, f) + LSS_INLINE _syscall2(int, clock_getres, int, c, + struct kernel_timespec*, t) + LSS_INLINE _syscall2(int, clock_gettime, int, c, + struct kernel_timespec*, t) + LSS_INLINE _syscall1(int, dup, int, f) + #if defined(__NR_dup2) + // dup2 is polyfilled below when not available. + LSS_INLINE _syscall2(int, dup2, int, s, + int, d) + #endif + #if defined(__NR_dup3) + LSS_INLINE _syscall3(int, dup3, int, s, int, d, int, f) + #endif + LSS_INLINE _syscall3(int, execve, const char*, f, + const char*const*,a,const char*const*, e) + LSS_INLINE _syscall1(int, _exit, int, e) + LSS_INLINE _syscall1(int, exit_group, int, e) + LSS_INLINE _syscall3(int, fcntl, int, f, + int, c, long, a) + #if defined(__NR_fork) + // fork is polyfilled below when not available. + LSS_INLINE _syscall0(pid_t, fork) + #endif + #if defined(__NR_fstat) + LSS_INLINE _syscall2(int, fstat, int, f, + struct kernel_stat*, b) + #endif + LSS_INLINE _syscall2(int, fstatfs, int, f, + struct kernel_statfs*, b) + #if defined(__x86_64__) + /* Need to make sure off_t isn't truncated to 32-bits under x32. */ + LSS_INLINE int LSS_NAME(ftruncate)(int f, off_t l) { + LSS_BODY(2, int, ftruncate, LSS_SYSCALL_ARG(f), (uint64_t)(l)); + } + #else + LSS_INLINE _syscall2(int, ftruncate, int, f, + off_t, l) + #endif + LSS_INLINE _syscall6(int, futex, int*, u, + int, o, int, v, + struct kernel_timespec*, t, + int*, u2, int, v2) + LSS_INLINE _syscall3(int, getdents, int, f, + struct kernel_dirent*, d, int, c) + LSS_INLINE _syscall3(int, getdents64, int, f, + struct kernel_dirent64*, d, int, c) + LSS_INLINE _syscall0(gid_t, getegid) + LSS_INLINE _syscall0(uid_t, geteuid) + LSS_INLINE _syscall2(int, getitimer, int, w, + struct kernel_itimerval*, c) + #if defined(__NR_getpgrp) + LSS_INLINE _syscall0(pid_t, getpgrp) + #endif + LSS_INLINE _syscall0(pid_t, getpid) + LSS_INLINE _syscall0(pid_t, getppid) + LSS_INLINE _syscall2(int, getpriority, int, a, + int, b) + LSS_INLINE _syscall3(int, getresgid, gid_t *, r, + gid_t *, e, gid_t *, s) + LSS_INLINE _syscall3(int, getresuid, uid_t *, r, + uid_t *, e, uid_t *, s) + #if defined(__NR_getrlimit) + LSS_INLINE _syscall2(int, getrlimit, int, r, + struct kernel_rlimit*, l) + #endif + LSS_INLINE _syscall1(pid_t, getsid, pid_t, p) + LSS_INLINE _syscall0(pid_t, _gettid) + LSS_INLINE _syscall2(pid_t, gettimeofday, struct kernel_timeval*, t, + void*, tz) + LSS_INLINE _syscall5(int, setxattr, const char *,p, + const char *, n, const void *,v, + size_t, s, int, f) + LSS_INLINE _syscall5(int, lsetxattr, const char *,p, + const char *, n, const void *,v, + size_t, s, int, f) + LSS_INLINE _syscall4(ssize_t, getxattr, const char *,p, + const char *, n, void *, v, size_t, s) + LSS_INLINE _syscall4(ssize_t, lgetxattr, const char *,p, + const char *, n, void *, v, size_t, s) + LSS_INLINE _syscall3(ssize_t, listxattr, const char *,p, + char *, l, size_t, s) + LSS_INLINE _syscall3(ssize_t, llistxattr, const char *,p, + char *, l, size_t, s) + LSS_INLINE _syscall3(int, ioctl, int, d, + int, r, void *, a) + LSS_INLINE _syscall2(int, ioprio_get, int, which, + int, who) + LSS_INLINE _syscall3(int, ioprio_set, int, which, + int, who, int, ioprio) + LSS_INLINE _syscall2(int, kill, pid_t, p, + int, s) + #if defined(__x86_64__) + /* Need to make sure off_t isn't truncated to 32-bits under x32. */ + LSS_INLINE off_t LSS_NAME(lseek)(int f, off_t o, int w) { + _LSS_BODY(3, off_t, lseek, off_t, LSS_SYSCALL_ARG(f), (uint64_t)(o), + LSS_SYSCALL_ARG(w)); + } + #else + LSS_INLINE _syscall3(off_t, lseek, int, f, + off_t, o, int, w) + #endif + LSS_INLINE _syscall2(int, munmap, void*, s, + size_t, l) + LSS_INLINE _syscall6(long, move_pages, pid_t, p, + unsigned long, n, void **,g, int *, d, + int *, s, int, f) + LSS_INLINE _syscall3(int, mprotect, const void *,a, + size_t, l, int, p) + LSS_INLINE _syscall5(void*, _mremap, void*, o, + size_t, os, size_t, ns, + unsigned long, f, void *, a) + #if defined(__NR_open) + // open is polyfilled below when not available. + LSS_INLINE _syscall3(int, open, const char*, p, + int, f, int, m) + #endif + #if defined(__NR_poll) + // poll is polyfilled below when not available. + LSS_INLINE _syscall3(int, poll, struct kernel_pollfd*, u, + unsigned int, n, int, t) + #endif + #if defined(__NR_ppoll) + LSS_INLINE _syscall5(int, ppoll, struct kernel_pollfd *, u, + unsigned int, n, const struct kernel_timespec *, t, + const struct kernel_sigset_t *, sigmask, size_t, s) + #endif + LSS_INLINE _syscall5(int, prctl, int, option, + unsigned long, arg2, + unsigned long, arg3, + unsigned long, arg4, + unsigned long, arg5) + LSS_INLINE _syscall4(long, ptrace, int, r, + pid_t, p, void *, a, void *, d) + #if defined(__NR_quotactl) + // Defined on x86_64 / i386 only + LSS_INLINE _syscall4(int, quotactl, int, cmd, const char *, special, + int, id, caddr_t, addr) + #endif + LSS_INLINE _syscall3(ssize_t, read, int, f, + void *, b, size_t, c) + #if defined(__NR_readlink) + // readlink is polyfilled below when not available. + LSS_INLINE _syscall3(int, readlink, const char*, p, + char*, b, size_t, s) + #endif + #if defined(__NR_readlinkat) + LSS_INLINE _syscall4(int, readlinkat, int, d, const char *, p, char *, b, + size_t, s) + #endif + LSS_INLINE _syscall4(int, rt_sigaction, int, s, + const struct kernel_sigaction*, a, + struct kernel_sigaction*, o, size_t, c) + LSS_INLINE _syscall2(int, rt_sigpending, struct kernel_sigset_t *, s, + size_t, c) + LSS_INLINE _syscall4(int, rt_sigprocmask, int, h, + const struct kernel_sigset_t*, s, + struct kernel_sigset_t*, o, size_t, c) + LSS_INLINE _syscall2(int, rt_sigsuspend, + const struct kernel_sigset_t*, s, size_t, c) + LSS_INLINE _syscall4(int, rt_sigtimedwait, const struct kernel_sigset_t*, s, + siginfo_t*, i, const struct timespec*, t, size_t, c) + LSS_INLINE _syscall3(int, sched_getaffinity,pid_t, p, + unsigned int, l, unsigned long *, m) + LSS_INLINE _syscall3(int, sched_setaffinity,pid_t, p, + unsigned int, l, unsigned long *, m) + LSS_INLINE _syscall0(int, sched_yield) + LSS_INLINE _syscall1(long, set_tid_address, int *, t) + LSS_INLINE _syscall1(int, setfsgid, gid_t, g) + LSS_INLINE _syscall1(int, setfsuid, uid_t, u) + LSS_INLINE _syscall1(int, setuid, uid_t, u) + LSS_INLINE _syscall1(int, setgid, gid_t, g) + LSS_INLINE _syscall3(int, setitimer, int, w, + const struct kernel_itimerval*, n, + struct kernel_itimerval*, o) + LSS_INLINE _syscall2(int, setpgid, pid_t, p, + pid_t, g) + LSS_INLINE _syscall3(int, setpriority, int, a, + int, b, int, p) + LSS_INLINE _syscall3(int, setresgid, gid_t, r, + gid_t, e, gid_t, s) + LSS_INLINE _syscall3(int, setresuid, uid_t, r, + uid_t, e, uid_t, s) + #if defined(__NR_setrlimit) + LSS_INLINE _syscall2(int, setrlimit, int, r, + const struct kernel_rlimit*, l) + #endif + LSS_INLINE _syscall0(pid_t, setsid) + LSS_INLINE _syscall2(int, sigaltstack, const stack_t*, s, + const stack_t*, o) + #if defined(__NR_sigreturn) + LSS_INLINE _syscall1(int, sigreturn, unsigned long, u) + #endif + #if defined(__NR_stat) + // stat and lstat are polyfilled below when not available. + LSS_INLINE _syscall2(int, stat, const char*, f, + struct kernel_stat*, b) + #endif + #if defined(__NR_lstat) + LSS_INLINE _syscall2(int, lstat, const char*, f, + struct kernel_stat*, b) + #endif + LSS_INLINE _syscall2(int, statfs, const char*, f, + struct kernel_statfs*, b) + LSS_INLINE _syscall3(int, tgkill, pid_t, p, + pid_t, t, int, s) + LSS_INLINE _syscall2(int, tkill, pid_t, p, + int, s) + #if defined(__NR_unlink) + // unlink is polyfilled below when not available. + LSS_INLINE _syscall1(int, unlink, const char*, f) + #endif + LSS_INLINE _syscall3(ssize_t, write, int, f, + const void *, b, size_t, c) + LSS_INLINE _syscall3(ssize_t, writev, int, f, + const struct kernel_iovec*, v, size_t, c) + #if defined(__NR_getcpu) + LSS_INLINE _syscall3(long, getcpu, unsigned *, cpu, + unsigned *, node, void *, unused) + #endif + #if defined(__NR_fadvise64) + #if defined(__x86_64__) + /* Need to make sure loff_t isn't truncated to 32-bits under x32. */ + LSS_INLINE int LSS_NAME(fadvise64)(int fd, loff_t offset, loff_t len, + int advice) { + LSS_BODY(4, int, fadvise64, LSS_SYSCALL_ARG(fd), (uint64_t)(offset), + (uint64_t)(len), LSS_SYSCALL_ARG(advice)); + } + #else + LSS_INLINE _syscall4(int, fadvise64, + int, fd, loff_t, offset, loff_t, len, int, advice) + #endif + #elif defined(__i386__) + #define __NR__fadvise64_64 __NR_fadvise64_64 + LSS_INLINE _syscall6(int, _fadvise64_64, int, fd, + unsigned, offset_lo, unsigned, offset_hi, + unsigned, len_lo, unsigned, len_hi, + int, advice) + + LSS_INLINE int LSS_NAME(fadvise64)(int fd, loff_t offset, + loff_t len, int advice) { + return LSS_NAME(_fadvise64_64)(fd, + (unsigned)offset, (unsigned)(offset >>32), + (unsigned)len, (unsigned)(len >> 32), + advice); + } + + #elif defined(__s390__) && !defined(__s390x__) + #define __NR__fadvise64_64 __NR_fadvise64_64 + struct kernel_fadvise64_64_args { + int fd; + long long offset; + long long len; + int advice; + }; + + LSS_INLINE _syscall1(int, _fadvise64_64, + struct kernel_fadvise64_64_args *args) + + LSS_INLINE int LSS_NAME(fadvise64)(int fd, loff_t offset, + loff_t len, int advice) { + struct kernel_fadvise64_64_args args = { fd, offset, len, advice }; + return LSS_NAME(_fadvise64_64)(&args); + } + #endif + #if defined(__NR_fallocate) + #if defined(__x86_64__) + /* Need to make sure loff_t isn't truncated to 32-bits under x32. */ + LSS_INLINE int LSS_NAME(fallocate)(int f, int mode, loff_t offset, + loff_t len) { + LSS_BODY(4, int, fallocate, LSS_SYSCALL_ARG(f), LSS_SYSCALL_ARG(mode), + (uint64_t)(offset), (uint64_t)(len)); + } + #elif (defined(__i386__) || (defined(__s390__) && !defined(__s390x__)) \ + || defined(__ARM_ARCH_3__) || defined(__ARM_EABI__) \ + || (defined(__mips__) && _MIPS_SIM == _MIPS_SIM_ABI32) \ + || defined(__PPC__)) + #define __NR__fallocate __NR_fallocate + LSS_INLINE _syscall6(int, _fallocate, int, fd, + int, mode, + unsigned, offset_lo, unsigned, offset_hi, + unsigned, len_lo, unsigned, len_hi) + + LSS_INLINE int LSS_NAME(fallocate)(int fd, int mode, + loff_t offset, loff_t len) { + union { loff_t off; unsigned w[2]; } o = { offset }, l = { len }; + return LSS_NAME(_fallocate)(fd, mode, o.w[0], o.w[1], l.w[0], l.w[1]); + } + #else + LSS_INLINE _syscall4(int, fallocate, + int, f, int, mode, loff_t, offset, loff_t, len) + #endif + #endif + #if defined(__NR_getrandom) + LSS_INLINE _syscall3(ssize_t, getrandom, void*, buffer, size_t, length, + unsigned int, flags) + #endif + #if defined(__NR_newfstatat) + LSS_INLINE _syscall4(int, newfstatat, int, d, + const char *, p, + struct kernel_stat*, b, int, f) + #endif + #if defined(__NR_statx) + LSS_INLINE _syscall5(int, statx, int, d, + const char *, p, + int, f, int, m, + struct kernel_statx*, b) + #endif + #if defined(__x86_64__) || defined(__s390x__) + LSS_INLINE int LSS_NAME(getresgid32)(gid_t *rgid, + gid_t *egid, + gid_t *sgid) { + return LSS_NAME(getresgid)(rgid, egid, sgid); + } + + LSS_INLINE int LSS_NAME(getresuid32)(uid_t *ruid, + uid_t *euid, + uid_t *suid) { + return LSS_NAME(getresuid)(ruid, euid, suid); + } + + LSS_INLINE int LSS_NAME(setfsgid32)(gid_t gid) { + return LSS_NAME(setfsgid)(gid); + } + + LSS_INLINE int LSS_NAME(setfsuid32)(uid_t uid) { + return LSS_NAME(setfsuid)(uid); + } + + LSS_INLINE int LSS_NAME(setresgid32)(gid_t rgid, gid_t egid, gid_t sgid) { + return LSS_NAME(setresgid)(rgid, egid, sgid); + } + + LSS_INLINE int LSS_NAME(setresuid32)(uid_t ruid, uid_t euid, uid_t suid) { + return LSS_NAME(setresuid)(ruid, euid, suid); + } + + LSS_INLINE int LSS_NAME(sigaction)(int signum, + const struct kernel_sigaction *act, + struct kernel_sigaction *oldact) { + #if defined(__x86_64__) + /* On x86_64, the kernel requires us to always set our own + * SA_RESTORER in order to be able to return from a signal handler. + * This function must have a "magic" signature that the "gdb" + * (and maybe the kernel?) can recognize. + */ + if (act != NULL && !(act->sa_flags & SA_RESTORER)) { + struct kernel_sigaction a = *act; + a.sa_flags |= SA_RESTORER; + a.sa_restorer = LSS_NAME(restore_rt)(); + return LSS_NAME(rt_sigaction)(signum, &a, oldact, + (KERNEL_NSIG+7)/8); + } else + #endif + return LSS_NAME(rt_sigaction)(signum, act, oldact, + (KERNEL_NSIG+7)/8); + } + LSS_INLINE int LSS_NAME(sigpending)(struct kernel_sigset_t *set) { + return LSS_NAME(rt_sigpending)(set, (KERNEL_NSIG+7)/8); + } + LSS_INLINE int LSS_NAME(sigsuspend)(const struct kernel_sigset_t *set) { + return LSS_NAME(rt_sigsuspend)(set, (KERNEL_NSIG+7)/8); + } + #endif + #if defined(__aarch64__) + LSS_INLINE int LSS_NAME(sigaction)(int signum, + const struct kernel_sigaction *act, + struct kernel_sigaction *oldact) { + /* On aarch64, the kernel requires us to always set our own + * SA_RESTORER in order to be able to return from a signal handler. + * This function must have a known "magic" instruction sequence + * that system softwares like a stack unwinder can recognize. + */ + if (act != NULL && !(act->sa_flags & SA_RESTORER)) { + struct kernel_sigaction a = *act; + a.sa_flags |= SA_RESTORER; + a.sa_restorer = LSS_NAME(restore_rt)(); + return LSS_NAME(rt_sigaction)(signum, &a, oldact, + (KERNEL_NSIG+7)/8); + } else + return LSS_NAME(rt_sigaction)(signum, act, oldact, + (KERNEL_NSIG+7)/8); + } + #endif + #if defined(__NR_rt_sigprocmask) + LSS_INLINE int LSS_NAME(sigprocmask)(int how, + const struct kernel_sigset_t *set, + struct kernel_sigset_t *oldset) { + return LSS_NAME(rt_sigprocmask)(how, set, oldset, (KERNEL_NSIG+7)/8); + } + #endif + #if defined(__NR_rt_sigtimedwait) + LSS_INLINE int LSS_NAME(sigtimedwait)(const struct kernel_sigset_t *set, + siginfo_t *info, + const struct timespec *timeout) { + return LSS_NAME(rt_sigtimedwait)(set, info, timeout, (KERNEL_NSIG+7)/8); + } + #endif + #if defined(__NR_wait4) + LSS_INLINE _syscall4(pid_t, wait4, pid_t, p, + int*, s, int, o, + struct kernel_rusage*, r) + #endif + #if defined(__NR_openat) + LSS_INLINE _syscall4(int, openat, int, d, const char *, p, int, f, int, m) + #endif + #if defined(__NR_unlinkat) + LSS_INLINE _syscall3(int, unlinkat, int, d, const char *, p, int, f) + #endif + #if defined(__i386__) || defined(__ARM_ARCH_3__) || defined(__ARM_EABI__) || \ + (defined(__s390__) && !defined(__s390x__)) + #define __NR__getresgid32 __NR_getresgid32 + #define __NR__getresuid32 __NR_getresuid32 + #define __NR__setfsgid32 __NR_setfsgid32 + #define __NR__setfsuid32 __NR_setfsuid32 + #define __NR__setresgid32 __NR_setresgid32 + #define __NR__setresuid32 __NR_setresuid32 +#if defined(__ARM_EABI__) + LSS_INLINE _syscall2(int, ugetrlimit, int, r, + struct kernel_rlimit*, l) +#endif + LSS_INLINE _syscall3(int, _getresgid32, gid_t *, r, + gid_t *, e, gid_t *, s) + LSS_INLINE _syscall3(int, _getresuid32, uid_t *, r, + uid_t *, e, uid_t *, s) + LSS_INLINE _syscall1(int, _setfsgid32, gid_t, f) + LSS_INLINE _syscall1(int, _setfsuid32, uid_t, f) + LSS_INLINE _syscall3(int, _setresgid32, gid_t, r, + gid_t, e, gid_t, s) + LSS_INLINE _syscall3(int, _setresuid32, uid_t, r, + uid_t, e, uid_t, s) + + LSS_INLINE int LSS_NAME(getresgid32)(gid_t *rgid, + gid_t *egid, + gid_t *sgid) { + int rc; + if ((rc = LSS_NAME(_getresgid32)(rgid, egid, sgid)) < 0 && + LSS_ERRNO == ENOSYS) { + if ((rgid == NULL) || (egid == NULL) || (sgid == NULL)) { + return EFAULT; + } + // Clear the high bits first, since getresgid only sets 16 bits + *rgid = *egid = *sgid = 0; + rc = LSS_NAME(getresgid)(rgid, egid, sgid); + } + return rc; + } + + LSS_INLINE int LSS_NAME(getresuid32)(uid_t *ruid, + uid_t *euid, + uid_t *suid) { + int rc; + if ((rc = LSS_NAME(_getresuid32)(ruid, euid, suid)) < 0 && + LSS_ERRNO == ENOSYS) { + if ((ruid == NULL) || (euid == NULL) || (suid == NULL)) { + return EFAULT; + } + // Clear the high bits first, since getresuid only sets 16 bits + *ruid = *euid = *suid = 0; + rc = LSS_NAME(getresuid)(ruid, euid, suid); + } + return rc; + } + + LSS_INLINE int LSS_NAME(setfsgid32)(gid_t gid) { + int rc; + if ((rc = LSS_NAME(_setfsgid32)(gid)) < 0 && + LSS_ERRNO == ENOSYS) { + if ((unsigned int)gid & ~0xFFFFu) { + rc = EINVAL; + } else { + rc = LSS_NAME(setfsgid)(gid); + } + } + return rc; + } + + LSS_INLINE int LSS_NAME(setfsuid32)(uid_t uid) { + int rc; + if ((rc = LSS_NAME(_setfsuid32)(uid)) < 0 && + LSS_ERRNO == ENOSYS) { + if ((unsigned int)uid & ~0xFFFFu) { + rc = EINVAL; + } else { + rc = LSS_NAME(setfsuid)(uid); + } + } + return rc; + } + + LSS_INLINE int LSS_NAME(setresgid32)(gid_t rgid, gid_t egid, gid_t sgid) { + int rc; + if ((rc = LSS_NAME(_setresgid32)(rgid, egid, sgid)) < 0 && + LSS_ERRNO == ENOSYS) { + if ((unsigned int)rgid & ~0xFFFFu || + (unsigned int)egid & ~0xFFFFu || + (unsigned int)sgid & ~0xFFFFu) { + rc = EINVAL; + } else { + rc = LSS_NAME(setresgid)(rgid, egid, sgid); + } + } + return rc; + } + + LSS_INLINE int LSS_NAME(setresuid32)(uid_t ruid, uid_t euid, uid_t suid) { + int rc; + if ((rc = LSS_NAME(_setresuid32)(ruid, euid, suid)) < 0 && + LSS_ERRNO == ENOSYS) { + if ((unsigned int)ruid & ~0xFFFFu || + (unsigned int)euid & ~0xFFFFu || + (unsigned int)suid & ~0xFFFFu) { + rc = EINVAL; + } else { + rc = LSS_NAME(setresuid)(ruid, euid, suid); + } + } + return rc; + } + #endif + LSS_INLINE int LSS_NAME(sigemptyset)(struct kernel_sigset_t *set) { + memset(&set->sig, 0, sizeof(set->sig)); + return 0; + } + + LSS_INLINE int LSS_NAME(sigfillset)(struct kernel_sigset_t *set) { + memset(&set->sig, -1, sizeof(set->sig)); + return 0; + } + + LSS_INLINE int LSS_NAME(sigaddset)(struct kernel_sigset_t *set, + int signum) { + if (signum < 1 || (size_t)signum > (8*sizeof(set->sig))) { + LSS_ERRNO = EINVAL; + return -1; + } else { + set->sig[(size_t)(signum - 1)/(8*sizeof(set->sig[0]))] + |= 1UL << ((size_t)(signum - 1) % (8*sizeof(set->sig[0]))); + return 0; + } + } + + LSS_INLINE int LSS_NAME(sigdelset)(struct kernel_sigset_t *set, + int signum) { + if (signum < 1 || (size_t)signum > (8*sizeof(set->sig))) { + LSS_ERRNO = EINVAL; + return -1; + } else { + set->sig[(size_t)(signum - 1)/(8*sizeof(set->sig[0]))] + &= ~(1UL << ((size_t)(signum - 1) % (8*sizeof(set->sig[0])))); + return 0; + } + } + + LSS_INLINE int LSS_NAME(sigismember)(struct kernel_sigset_t *set, + int signum) { + if (signum < 1 || (size_t)signum > (8*sizeof(set->sig))) { + LSS_ERRNO = EINVAL; + return -1; + } else { + return !!(set->sig[(size_t)(signum - 1)/(8*sizeof(set->sig[0]))] & + (1UL << ((size_t)(signum - 1) % (8*sizeof(set->sig[0]))))); + } + } + #if defined(__i386__) || \ + defined(__ARM_ARCH_3__) || defined(__ARM_EABI__) || \ + (defined(__mips__) && _MIPS_SIM == _MIPS_SIM_ABI32) || \ + defined(__PPC__) || \ + (defined(__s390__) && !defined(__s390x__)) || defined(__e2k__) + #define __NR__sigaction __NR_sigaction + #define __NR__sigpending __NR_sigpending + #define __NR__sigsuspend __NR_sigsuspend + #define __NR__socketcall __NR_socketcall + LSS_INLINE _syscall2(int, fstat64, int, f, + struct kernel_stat64 *, b) + LSS_INLINE _syscall5(int, _llseek, uint, fd, + unsigned long, hi, unsigned long, lo, + loff_t *, res, uint, wh) +#if defined(__s390__) && !defined(__s390x__) + /* On s390, mmap2() arguments are passed in memory. */ + LSS_INLINE void* LSS_NAME(_mmap2)(void *s, size_t l, int p, int f, int d, + off_t o) { + unsigned long buf[6] = { (unsigned long) s, (unsigned long) l, + (unsigned long) p, (unsigned long) f, + (unsigned long) d, (unsigned long) o }; + LSS_REG(2, buf); + LSS_BODY(void*, mmap2, "0"(__r2)); + } +#elif defined(__NR_mmap2) + #define __NR__mmap2 __NR_mmap2 + LSS_INLINE _syscall6(void*, _mmap2, void*, s, + size_t, l, int, p, + int, f, int, d, + off_t, o) +#endif + LSS_INLINE _syscall3(int, _sigaction, int, s, + const struct kernel_old_sigaction*, a, + struct kernel_old_sigaction*, o) + LSS_INLINE _syscall1(int, _sigpending, unsigned long*, s) + #ifdef __PPC__ + LSS_INLINE _syscall1(int, _sigsuspend, unsigned long, s) + #else + LSS_INLINE _syscall3(int, _sigsuspend, const void*, a, + int, b, + unsigned long, s) + #endif + LSS_INLINE _syscall2(int, stat64, const char *, p, + struct kernel_stat64 *, b) + + LSS_INLINE int LSS_NAME(sigaction)(int signum, + const struct kernel_sigaction *act, + struct kernel_sigaction *oldact) { + int old_errno = LSS_ERRNO; + int rc; + struct kernel_sigaction a; + if (act != NULL) { + a = *act; + #ifdef __i386__ + /* On i386, the kernel requires us to always set our own + * SA_RESTORER when using realtime signals. Otherwise, it does not + * know how to return from a signal handler. This function must have + * a "magic" signature that the "gdb" (and maybe the kernel?) can + * recognize. + * Apparently, a SA_RESTORER is implicitly set by the kernel, when + * using non-realtime signals. + * + * TODO: Test whether ARM needs a restorer + */ + if (!(a.sa_flags & SA_RESTORER)) { + a.sa_flags |= SA_RESTORER; + a.sa_restorer = (a.sa_flags & SA_SIGINFO) + ? LSS_NAME(restore_rt)() : LSS_NAME(restore)(); + } + #endif + } + rc = LSS_NAME(rt_sigaction)(signum, act ? &a : act, oldact, + (KERNEL_NSIG+7)/8); + if (rc < 0 && LSS_ERRNO == ENOSYS) { + struct kernel_old_sigaction oa, ooa, *ptr_a = &oa, *ptr_oa = &ooa; + if (!act) { + ptr_a = NULL; + } else { + oa.sa_handler_ = act->sa_handler_; + memcpy(&oa.sa_mask, &act->sa_mask, sizeof(oa.sa_mask)); + #ifndef __mips__ + oa.sa_restorer = act->sa_restorer; + #endif + oa.sa_flags = act->sa_flags; + } + if (!oldact) { + ptr_oa = NULL; + } + LSS_ERRNO = old_errno; + rc = LSS_NAME(_sigaction)(signum, ptr_a, ptr_oa); + if (rc == 0 && oldact) { + if (act) { + memcpy(oldact, act, sizeof(*act)); + } else { + memset(oldact, 0, sizeof(*oldact)); + } + oldact->sa_handler_ = ptr_oa->sa_handler_; + oldact->sa_flags = ptr_oa->sa_flags; + memcpy(&oldact->sa_mask, &ptr_oa->sa_mask, sizeof(ptr_oa->sa_mask)); + #ifndef __mips__ + oldact->sa_restorer = ptr_oa->sa_restorer; + #endif + } + } + return rc; + } + + LSS_INLINE int LSS_NAME(sigpending)(struct kernel_sigset_t *set) { + int old_errno = LSS_ERRNO; + int rc = LSS_NAME(rt_sigpending)(set, (KERNEL_NSIG+7)/8); + if (rc < 0 && LSS_ERRNO == ENOSYS) { + LSS_ERRNO = old_errno; + LSS_NAME(sigemptyset)(set); + rc = LSS_NAME(_sigpending)(&set->sig[0]); + } + return rc; + } + + LSS_INLINE int LSS_NAME(sigsuspend)(const struct kernel_sigset_t *set) { + int olderrno = LSS_ERRNO; + int rc = LSS_NAME(rt_sigsuspend)(set, (KERNEL_NSIG+7)/8); + if (rc < 0 && LSS_ERRNO == ENOSYS) { + LSS_ERRNO = olderrno; + rc = LSS_NAME(_sigsuspend)( + #ifndef __PPC__ + set, 0, + #endif + set->sig[0]); + } + return rc; + } + #endif + #if defined(__s390x__) + /* On s390x, mmap() arguments are passed in memory. */ + LSS_INLINE void* LSS_NAME(mmap)(void *s, size_t l, int p, int f, int d, + int64_t o) { + unsigned long buf[6] = { (unsigned long) s, (unsigned long) l, + (unsigned long) p, (unsigned long) f, + (unsigned long) d, (unsigned long) o }; + LSS_REG(2, buf); + LSS_BODY(void*, mmap, "0"(__r2)); + } + #elif defined(__x86_64__) + /* Need to make sure __off64_t isn't truncated to 32-bits under x32. */ + LSS_INLINE void* LSS_NAME(mmap)(void *s, size_t l, int p, int f, int d, + int64_t o) { + LSS_BODY(6, void*, mmap, LSS_SYSCALL_ARG(s), LSS_SYSCALL_ARG(l), + LSS_SYSCALL_ARG(p), LSS_SYSCALL_ARG(f), + LSS_SYSCALL_ARG(d), (uint64_t)(o)); + } + #elif defined(__NR_mmap2) + /* On these architectures, implement mmap() with mmap2(). */ + LSS_INLINE void* LSS_NAME(mmap)(void *s, size_t l, int p, int f, int d, + int64_t o) { + if (o % 4096) { + LSS_ERRNO = EINVAL; + return (void *) -1; + } + return LSS_NAME(_mmap2)(s, l, p, f, d, (o / 4096)); + } + #else + /* Remaining 64-bit architectures. */ + LSS_INLINE _syscall6(void*, mmap, void*, addr, size_t, length, int, prot, + int, flags, int, fd, int64_t, offset) + #endif + #if defined(__PPC__) + #undef LSS_SC_LOADARGS_0 + #define LSS_SC_LOADARGS_0(dummy...) + #undef LSS_SC_LOADARGS_1 + #define LSS_SC_LOADARGS_1(arg1) \ + __sc_4 = (unsigned long) (arg1) + #undef LSS_SC_LOADARGS_2 + #define LSS_SC_LOADARGS_2(arg1, arg2) \ + LSS_SC_LOADARGS_1(arg1); \ + __sc_5 = (unsigned long) (arg2) + #undef LSS_SC_LOADARGS_3 + #define LSS_SC_LOADARGS_3(arg1, arg2, arg3) \ + LSS_SC_LOADARGS_2(arg1, arg2); \ + __sc_6 = (unsigned long) (arg3) + #undef LSS_SC_LOADARGS_4 + #define LSS_SC_LOADARGS_4(arg1, arg2, arg3, arg4) \ + LSS_SC_LOADARGS_3(arg1, arg2, arg3); \ + __sc_7 = (unsigned long) (arg4) + #undef LSS_SC_LOADARGS_5 + #define LSS_SC_LOADARGS_5(arg1, arg2, arg3, arg4, arg5) \ + LSS_SC_LOADARGS_4(arg1, arg2, arg3, arg4); \ + __sc_8 = (unsigned long) (arg5) + #undef LSS_SC_BODY + #define LSS_SC_BODY(nr, type, opt, args...) \ + long __sc_ret, __sc_err; \ + { \ + register unsigned long __sc_0 __asm__ ("r0") = __NR_socketcall; \ + register unsigned long __sc_3 __asm__ ("r3") = opt; \ + register unsigned long __sc_4 __asm__ ("r4"); \ + register unsigned long __sc_5 __asm__ ("r5"); \ + register unsigned long __sc_6 __asm__ ("r6"); \ + register unsigned long __sc_7 __asm__ ("r7"); \ + register unsigned long __sc_8 __asm__ ("r8"); \ + LSS_SC_LOADARGS_##nr(args); \ + __asm__ __volatile__ \ + ("stwu 1, -48(1)\n\t" \ + "stw 4, 20(1)\n\t" \ + "stw 5, 24(1)\n\t" \ + "stw 6, 28(1)\n\t" \ + "stw 7, 32(1)\n\t" \ + "stw 8, 36(1)\n\t" \ + "addi 4, 1, 20\n\t" \ + "sc\n\t" \ + "mfcr %0" \ + : "=&r" (__sc_0), \ + "=&r" (__sc_3), "=&r" (__sc_4), \ + "=&r" (__sc_5), "=&r" (__sc_6), \ + "=&r" (__sc_7), "=&r" (__sc_8) \ + : LSS_ASMINPUT_##nr \ + : "cr0", "ctr", "memory"); \ + __sc_ret = __sc_3; \ + __sc_err = __sc_0; \ + } \ + LSS_RETURN(type, __sc_ret, __sc_err) + + LSS_INLINE ssize_t LSS_NAME(recvmsg)(int s,struct kernel_msghdr *msg, + int flags){ + LSS_SC_BODY(3, ssize_t, 17, s, msg, flags); + } + + LSS_INLINE ssize_t LSS_NAME(sendmsg)(int s, + const struct kernel_msghdr *msg, + int flags) { + LSS_SC_BODY(3, ssize_t, 16, s, msg, flags); + } + + // TODO(csilvers): why is this ifdef'ed out? +#if 0 + LSS_INLINE ssize_t LSS_NAME(sendto)(int s, const void *buf, size_t len, + int flags, + const struct kernel_sockaddr *to, + unsigned int tolen) { + LSS_BODY(6, ssize_t, 11, s, buf, len, flags, to, tolen); + } +#endif + + LSS_INLINE int LSS_NAME(shutdown)(int s, int how) { + LSS_SC_BODY(2, int, 13, s, how); + } + + LSS_INLINE int LSS_NAME(socket)(int domain, int type, int protocol) { + LSS_SC_BODY(3, int, 1, domain, type, protocol); + } + + LSS_INLINE int LSS_NAME(socketpair)(int d, int type, int protocol, + int sv[2]) { + LSS_SC_BODY(4, int, 8, d, type, protocol, sv); + } + #endif + #if defined(__NR_recvmsg) + LSS_INLINE _syscall3(ssize_t, recvmsg, int, s, struct kernel_msghdr*, msg, + int, flags) + #endif + #if defined(__NR_sendmsg) + LSS_INLINE _syscall3(ssize_t, sendmsg, int, s, const struct kernel_msghdr*, + msg, int, flags) + #endif + #if defined(__NR_sendto) + LSS_INLINE _syscall6(ssize_t, sendto, int, s, const void*, buf, size_t,len, + int, flags, const struct kernel_sockaddr*, to, + unsigned int, tolen) + #endif + #if defined(__NR_shutdown) + LSS_INLINE _syscall2(int, shutdown, int, s, int, how) + #endif + #if defined(__NR_socket) + LSS_INLINE _syscall3(int, socket, int, domain, int, type, int, protocol) + #endif + #if defined(__NR_socketpair) + LSS_INLINE _syscall4(int, socketpair, int, d, int, type, int, protocol, + int*, sv) + #endif + + #if defined(__NR_socketcall) + LSS_INLINE _syscall2(int, _socketcall, int, c, + va_list, a) + LSS_INLINE int LSS_NAME(socketcall)(int op, ...) { + int rc; + va_list ap; + va_start(ap, op); + rc = LSS_NAME(_socketcall)(op, ap); + va_end(ap); + return rc; + } + + # if !defined(__NR_recvmsg) + LSS_INLINE ssize_t LSS_NAME(recvmsg)(int s,struct kernel_msghdr *msg, + int flags){ + return (ssize_t)LSS_NAME(socketcall)(17, s, msg, flags); + } + # endif + # if !defined(__NR_sendmsg) + LSS_INLINE ssize_t LSS_NAME(sendmsg)(int s, + const struct kernel_msghdr *msg, + int flags) { + return (ssize_t)LSS_NAME(socketcall)(16, s, msg, flags); + } + # endif + # if !defined(__NR_sendto) + LSS_INLINE ssize_t LSS_NAME(sendto)(int s, const void *buf, size_t len, + int flags, + const struct kernel_sockaddr *to, + unsigned int tolen) { + return (ssize_t)LSS_NAME(socketcall)(11, s, buf, len, flags, to, tolen); + } + # endif + # if !defined(__NR_shutdown) + LSS_INLINE int LSS_NAME(shutdown)(int s, int how) { + return LSS_NAME(socketcall)(13, s, how); + } + # endif + # if !defined(__NR_socket) + LSS_INLINE int LSS_NAME(socket)(int domain, int type, int protocol) { + return LSS_NAME(socketcall)(1, domain, type, protocol); + } + # endif + # if !defined(__NR_socketpair) + LSS_INLINE int LSS_NAME(socketpair)(int d, int type, int protocol, + int sv[2]) { + return LSS_NAME(socketcall)(8, d, type, protocol, sv); + } + # endif + #endif + #if defined(__NR_fstatat64) + LSS_INLINE _syscall4(int, fstatat64, int, d, + const char *, p, + struct kernel_stat64 *, b, int, f) + #endif + #if defined(__NR_waitpid) + // waitpid is polyfilled below when not available. + LSS_INLINE _syscall3(pid_t, waitpid, pid_t, p, + int*, s, int, o) + #endif + #if defined(__mips__) + /* sys_pipe() on MIPS has non-standard calling conventions, as it returns + * both file handles through CPU registers. + */ + LSS_INLINE int LSS_NAME(pipe)(int *p) { + register unsigned long __v0 __asm__("$2") = __NR_pipe; + register unsigned long __v1 __asm__("$3"); + register unsigned long __r7 __asm__("$7"); + __asm__ __volatile__ ("syscall\n" + : "=r"(__v0), "=r"(__v1), "=r" (__r7) + : "0"(__v0) + : "$8", "$9", "$10", "$11", "$12", + "$13", "$14", "$15", "$24", "$25", "memory"); + if (__r7) { + unsigned long __errnovalue = __v0; + LSS_ERRNO = __errnovalue; + return -1; + } else { + p[0] = __v0; + p[1] = __v1; + return 0; + } + } + #elif defined(__NR_pipe) + // pipe is polyfilled below when not available. + LSS_INLINE _syscall1(int, pipe, int *, p) + #endif + #if defined(__NR_pipe2) + LSS_INLINE _syscall2(int, pipe2, int *, pipefd, int, flags) + #endif + /* TODO(csilvers): see if ppc can/should support this as well */ + #if defined(__i386__) || defined(__ARM_ARCH_3__) || \ + defined(__ARM_EABI__) || \ + (defined(__mips__) && _MIPS_SIM != _MIPS_SIM_ABI64) || \ + (defined(__s390__) && !defined(__s390x__)) + #define __NR__statfs64 __NR_statfs64 + #define __NR__fstatfs64 __NR_fstatfs64 + LSS_INLINE _syscall3(int, _statfs64, const char*, p, + size_t, s,struct kernel_statfs64*, b) + LSS_INLINE _syscall3(int, _fstatfs64, int, f, + size_t, s,struct kernel_statfs64*, b) + LSS_INLINE int LSS_NAME(statfs64)(const char *p, + struct kernel_statfs64 *b) { + return LSS_NAME(_statfs64)(p, sizeof(*b), b); + } + LSS_INLINE int LSS_NAME(fstatfs64)(int f,struct kernel_statfs64 *b) { + return LSS_NAME(_fstatfs64)(f, sizeof(*b), b); + } + #endif + + LSS_INLINE int LSS_NAME(execv)(const char *path, const char *const argv[]) { + extern char **environ; + return LSS_NAME(execve)(path, argv, (const char *const *)environ); + } + + LSS_INLINE pid_t LSS_NAME(gettid)(void) { + pid_t tid = LSS_NAME(_gettid)(); + if (tid != -1) { + return tid; + } + return LSS_NAME(getpid)(); + } + + LSS_INLINE void *LSS_NAME(mremap)(void *old_address, size_t old_size, + size_t new_size, int flags, ...) { + va_list ap; + void *new_address, *rc; + va_start(ap, flags); + new_address = va_arg(ap, void *); + rc = LSS_NAME(_mremap)(old_address, old_size, new_size, + (unsigned long)flags, new_address); + va_end(ap); + return rc; + } + + LSS_INLINE long LSS_NAME(ptrace_detach)(pid_t pid) { + /* PTRACE_DETACH can sometimes forget to wake up the tracee and it + * then sends job control signals to the real parent, rather than to + * the tracer. We reduce the risk of this happening by starting a + * whole new time slice, and then quickly sending a SIGCONT signal + * right after detaching from the tracee. + * + * We use tkill to ensure that we only issue a wakeup for the thread being + * detached. Large multi threaded apps can take a long time in the kernel + * processing SIGCONT. + */ + long rc; + int err; + LSS_NAME(sched_yield)(); + rc = LSS_NAME(ptrace)(PTRACE_DETACH, pid, (void *)0, (void *)0); + err = LSS_ERRNO; + LSS_NAME(tkill)(pid, SIGCONT); + /* Old systems don't have tkill */ + if (LSS_ERRNO == ENOSYS) + LSS_NAME(kill)(pid, SIGCONT); + LSS_ERRNO = err; + return rc; + } + + LSS_INLINE int LSS_NAME(raise)(int sig) { + return LSS_NAME(kill)(LSS_NAME(getpid)(), sig); + } + + LSS_INLINE int LSS_NAME(setpgrp)(void) { + return LSS_NAME(setpgid)(0, 0); + } + + #if defined(__x86_64__) + /* Need to make sure loff_t isn't truncated to 32-bits under x32. */ + LSS_INLINE ssize_t LSS_NAME(pread64)(int f, void *b, size_t c, loff_t o) { + LSS_BODY(4, ssize_t, pread64, LSS_SYSCALL_ARG(f), LSS_SYSCALL_ARG(b), + LSS_SYSCALL_ARG(c), (uint64_t)(o)); + } + + LSS_INLINE ssize_t LSS_NAME(pwrite64)(int f, const void *b, size_t c, + loff_t o) { + LSS_BODY(4, ssize_t, pwrite64, LSS_SYSCALL_ARG(f), LSS_SYSCALL_ARG(b), + LSS_SYSCALL_ARG(c), (uint64_t)(o)); + } + + LSS_INLINE int LSS_NAME(readahead)(int f, loff_t o, size_t c) { + LSS_BODY(3, int, readahead, LSS_SYSCALL_ARG(f), (uint64_t)(o), + LSS_SYSCALL_ARG(c)); + } + #elif defined(__mips__) && _MIPS_SIM == _MIPS_SIM_ABI64 + LSS_INLINE _syscall4(ssize_t, pread64, int, f, + void *, b, size_t, c, + loff_t, o) + LSS_INLINE _syscall4(ssize_t, pwrite64, int, f, + const void *, b, size_t, c, + loff_t, o) + LSS_INLINE _syscall3(int, readahead, int, f, + loff_t, o, unsigned, c) + #else + #define __NR__pread64 __NR_pread64 + #define __NR__pwrite64 __NR_pwrite64 + #define __NR__readahead __NR_readahead + #if defined(__ARM_EABI__) || defined(__mips__) + /* On ARM and MIPS, a 64-bit parameter has to be in an even-odd register + * pair. Hence these calls ignore their fourth argument (r3) so that their + * fifth and sixth make such a pair (r4,r5). + */ + #define LSS_LLARG_PAD 0, + LSS_INLINE _syscall6(ssize_t, _pread64, int, f, + void *, b, size_t, c, + unsigned, skip, unsigned, o1, unsigned, o2) + LSS_INLINE _syscall6(ssize_t, _pwrite64, int, f, + const void *, b, size_t, c, + unsigned, skip, unsigned, o1, unsigned, o2) + LSS_INLINE _syscall5(int, _readahead, int, f, + unsigned, skip, + unsigned, o1, unsigned, o2, size_t, c) + #else + #define LSS_LLARG_PAD + LSS_INLINE _syscall5(ssize_t, _pread64, int, f, + void *, b, size_t, c, unsigned, o1, + unsigned, o2) + LSS_INLINE _syscall5(ssize_t, _pwrite64, int, f, + const void *, b, size_t, c, unsigned, o1, + unsigned, o2) + LSS_INLINE _syscall4(int, _readahead, int, f, + unsigned, o1, unsigned, o2, size_t, c) + #endif + /* We force 64bit-wide parameters onto the stack, then access each + * 32-bit component individually. This guarantees that we build the + * correct parameters independent of the native byte-order of the + * underlying architecture. + */ + LSS_INLINE ssize_t LSS_NAME(pread64)(int fd, void *buf, size_t count, + loff_t off) { + union { loff_t off; unsigned arg[2]; } o = { off }; + return LSS_NAME(_pread64)(fd, buf, count, + LSS_LLARG_PAD o.arg[0], o.arg[1]); + } + LSS_INLINE ssize_t LSS_NAME(pwrite64)(int fd, const void *buf, + size_t count, loff_t off) { + union { loff_t off; unsigned arg[2]; } o = { off }; + return LSS_NAME(_pwrite64)(fd, buf, count, + LSS_LLARG_PAD o.arg[0], o.arg[1]); + } + LSS_INLINE int LSS_NAME(readahead)(int fd, loff_t off, size_t count) { + union { loff_t off; unsigned arg[2]; } o = { off }; + return LSS_NAME(_readahead)(fd, LSS_LLARG_PAD o.arg[0], o.arg[1], count); + } + #endif +#endif + +/* + * Polyfills for deprecated syscalls. + */ + +#if !defined(__NR_dup2) + LSS_INLINE int LSS_NAME(dup2)(int s, int d) { + return LSS_NAME(dup3)(s, d, 0); + } +#endif + +#if !defined(__NR_open) + LSS_INLINE int LSS_NAME(open)(const char *pathname, int flags, int mode) { + return LSS_NAME(openat)(AT_FDCWD, pathname, flags, mode); + } +#endif + +#if !defined(__NR_unlink) + LSS_INLINE int LSS_NAME(unlink)(const char *pathname) { + return LSS_NAME(unlinkat)(AT_FDCWD, pathname, 0); + } +#endif + +#if !defined(__NR_readlink) + LSS_INLINE int LSS_NAME(readlink)(const char *pathname, char *buffer, + size_t size) { + return LSS_NAME(readlinkat)(AT_FDCWD, pathname, buffer, size); + } +#endif + +#if !defined(__NR_pipe) + LSS_INLINE int LSS_NAME(pipe)(int *pipefd) { + return LSS_NAME(pipe2)(pipefd, 0); + } +#endif + +#if !defined(__NR_poll) + LSS_INLINE int LSS_NAME(poll)(struct kernel_pollfd *fds, unsigned int nfds, + int timeout) { + struct kernel_timespec timeout_ts; + struct kernel_timespec *timeout_ts_p = NULL; + + if (timeout >= 0) { + timeout_ts.tv_sec = timeout / 1000; + timeout_ts.tv_nsec = (timeout % 1000) * 1000000; + timeout_ts_p = &timeout_ts; + } + return LSS_NAME(ppoll)(fds, nfds, timeout_ts_p, NULL, 0); + } +#endif + +#if defined(__NR_statx) + /* copy the contents of kernel_statx to the kernel_stat structure. */ + LSS_INLINE void LSS_NAME(cp_stat_statx)(struct kernel_stat *to, + struct kernel_statx *from) { + memset(to, 0, sizeof(struct kernel_stat)); + to->st_dev = (kernel_dev_t)((from->stx_dev_minor & 0xff) | + ((from->stx_dev_major & 0xfff) << 8) | + ((from->stx_dev_minor & ~0xffu) << 12)); + to->st_rdev = (kernel_dev_t)((from->stx_rdev_minor & 0xff) | + ((from->stx_rdev_major & 0xfff) << 8) | + ((from->stx_rdev_minor & ~0xffu) << 12)); + to->st_ino = (kernel_ino_t)from->stx_ino; + to->st_mode = (kernel_mode_t)from->stx_mode; + to->st_nlink = (kernel_nlink_t)from->stx_nlink; + to->st_uid = (kernel_uid_t)from->stx_uid; + to->st_gid = (kernel_gid_t)from->stx_gid; + to->st_atime_ = (kernel_time_t)(from->stx_atime.tv_sec); + to->st_atime_nsec_ = from->stx_atime.tv_nsec; + to->st_mtime_ = (kernel_time_t)(from->stx_mtime.tv_sec); + to->st_mtime_nsec_ = from->stx_mtime.tv_nsec; + to->st_ctime_ = (kernel_time_t)(from->stx_ctime.tv_sec); + to->st_ctime_nsec_ = from->stx_ctime.tv_nsec; + to->st_size = (kernel_off_t)(from->stx_size); + to->st_blocks = (kernel_blkcnt_t)(from->stx_blocks); + to->st_blksize = (kernel_blksize_t)from->stx_blksize; + } +#endif + +#if !defined(__NR_fstat) + LSS_INLINE int LSS_NAME(fstat)(int fd, + struct kernel_stat *buf) { + #if defined(__NR_newfstatat) + return LSS_NAME(newfstatat)(fd, "", buf, AT_EMPTY_PATH); + #elif defined(__NR_statx) + struct kernel_statx stx; + int flags = AT_NO_AUTOMOUNT | AT_EMPTY_PATH; + int mask = STATX_BASIC_STATS; + int res = LSS_NAME(statx)(fd, "", flags, mask, &stx); + LSS_NAME(cp_stat_statx)(buf, &stx); + return res; + #endif + } +#endif + +#if !defined(__NR_stat) + LSS_INLINE int LSS_NAME(stat)(const char *pathname, + struct kernel_stat *buf) { + #if defined(__NR_newfstatat) + return LSS_NAME(newfstatat)(AT_FDCWD, pathname, buf, 0); + #elif defined(__NR_statx) + struct kernel_statx stx; + int flags = AT_NO_AUTOMOUNT | AT_STATX_SYNC_AS_STAT; + int mask = STATX_BASIC_STATS; + int res = LSS_NAME(statx)(AT_FDCWD, pathname, flags, mask, &stx); + LSS_NAME(cp_stat_statx)(buf, &stx); + return res; + #endif + } +#endif + +#if !defined(__NR_lstat) + LSS_INLINE int LSS_NAME(lstat)(const char *pathname, + struct kernel_stat *buf) { + #if defined(__NR_newfstatat) + return LSS_NAME(newfstatat)(AT_FDCWD, pathname, buf, AT_SYMLINK_NOFOLLOW); + #elif defined(__NR_statx) + struct kernel_statx stx; + int flags = AT_NO_AUTOMOUNT | AT_SYMLINK_NOFOLLOW; + int mask = STATX_BASIC_STATS; + int res = LSS_NAME(statx)(AT_FDCWD, pathname, flags, mask, &stx); + LSS_NAME(cp_stat_statx)(buf, &stx); + return res; + #endif + } +#endif + +#if !defined(__NR_waitpid) + LSS_INLINE pid_t LSS_NAME(waitpid)(pid_t pid, int *status, int options) { + return LSS_NAME(wait4)(pid, status, options, 0); + } +#endif + +#if !defined(__NR_fork) +// TODO: define this in an arch-independant way instead of inlining the clone +// syscall body. + +# if defined(__aarch64__) || defined(__riscv) || defined(__loongarch_lp64) + LSS_INLINE pid_t LSS_NAME(fork)(void) { + // No fork syscall on aarch64 - implement by means of the clone syscall. + // Note that this does not reset glibc's cached view of the PID/TID, so + // some glibc interfaces might go wrong in the forked subprocess. + int flags = SIGCHLD; + void *child_stack = NULL; + void *parent_tidptr = NULL; + void *newtls = NULL; + void *child_tidptr = NULL; + + LSS_REG(0, flags); + LSS_REG(1, child_stack); + LSS_REG(2, parent_tidptr); + LSS_REG(3, newtls); + LSS_REG(4, child_tidptr); + LSS_BODY(pid_t, clone, "r"(__r0), "r"(__r1), "r"(__r2), "r"(__r3), + "r"(__r4)); + } +# elif defined(__x86_64__) + LSS_INLINE pid_t LSS_NAME(fork)(void) { + // Android disallows the fork syscall on x86_64 - implement by means of the + // clone syscall as above for aarch64. + int flags = SIGCHLD; + void *child_stack = NULL; + void *parent_tidptr = NULL; + void *newtls = NULL; + void *child_tidptr = NULL; + + LSS_BODY(5, pid_t, clone, LSS_SYSCALL_ARG(flags), + LSS_SYSCALL_ARG(child_stack), LSS_SYSCALL_ARG(parent_tidptr), + LSS_SYSCALL_ARG(newtls), LSS_SYSCALL_ARG(child_tidptr)); + } +# else +# error missing fork polyfill for this architecture +# endif +#endif + +/* These restore the original values of these macros saved by the + * corresponding #pragma push_macro near the top of this file. */ +#pragma pop_macro("stat64") +#pragma pop_macro("fstat64") +#pragma pop_macro("lstat64") +#pragma pop_macro("pread64") +#pragma pop_macro("pwrite64") +#pragma pop_macro("getdents64") + +#if defined(__cplusplus) && !defined(SYS_CPLUSPLUS) +} +#endif + +#endif +#endif diff --git a/malloc.c b/malloc.c new file mode 100644 index 0000000..14d7661 --- /dev/null +++ b/malloc.c @@ -0,0 +1,16 @@ +// Configure dlmalloc + +#define USE_LOCKS 0 +#define INSECURE 1 +#define HAVE_MORECORE 0 +#define NO_MALLINFO 1 +#define NO_MALLOC_STATS 1 +#define LACKS_TIME_H 1 +#define malloc_getpagesize 4096 + +#pragma clang diagnostic push +#pragma clang diagnostic ignored "-Wunused-but-set-variable" + +#include "dlmalloc/malloc.c" + +#pragma clang diagnostic pop diff --git a/mem.c b/mem.c new file mode 100644 index 0000000..cc17d5f --- /dev/null +++ b/mem.c @@ -0,0 +1,361 @@ +#include +#include + +void *memset(void *dst, int ch, size_t n) { + uint8_t *d = dst; + uint8_t c = ch; + while (n--) + (*d++) = c; + return dst; +} + +void *memmove(void *dst, const void *src, size_t n) { + return memcpy(dst, src, n); +} + +void *memcpy(void *dst, const void *src, size_t n) { + uint8_t *d = dst; + const uint8_t *s = src; + while (n--) + *d++ = *s++; + return dst; +} + +int memcmp(const void *lhs, const void *rhs, size_t n) { + const uint8_t *l = lhs; + const uint8_t *r = rhs; + while (n--) { + if (*l != *r) { + return *l - *r; + } else { + l++; + r++; + } + } + return 0; +} + +void *memchr(const void *ptr, int ch, size_t n) { + const uint8_t *p = ptr; + uint8_t c = ch; + while (n--) { + if (*p != c) + ++p; + else + return (void *) p; + } + return NULL; +} + +char *strchr(const char *s, int ch) { + char c = ch; + while (*s != c) + if (!*s++) + return NULL; + return (char *) s; +} + +int strcmp(const char *lhs, const char *rhs) { + while (*lhs && (*lhs == *rhs)) { + ++lhs; + ++rhs; + } + return *(uint8_t *)lhs - *(uint8_t *)rhs; +} + +size_t strlen(const char *str) { + size_t l = 0; + while (str[l]) + ++l; + return l; +} + +char *strcpy(char *restrict dest, const char *restrict src) { + char *ret = dest; + while ((*dest++ = *src++)) {} + return ret; +} + +char *strdup(const char *str) { + size_t siz; + char *copy; + siz = strlen(str) + 1; + if ((copy = malloc(siz)) == NULL) + return NULL; + memcpy(copy, str, siz); + return copy; +} + +// memmem source: bionic/libc/upstream-openbsd/lib/libc/string/memmem.c + +static char *twobyte_memmem(const unsigned char *h, size_t k, const unsigned char *n) { + uint16_t nw = n[0]<<8 | n[1], hw = h[0]<<8 | h[1]; + for (h+=2, k-=2; k; k--, hw = hw<<8 | *h++) + if (hw == nw) return (char *)h-2; + return hw == nw ? (char *)h-2 : 0; +} + +static char *threebyte_memmem(const unsigned char *h, size_t k, const unsigned char *n) { + uint32_t nw = n[0]<<24 | n[1]<<16 | n[2]<<8; + uint32_t hw = h[0]<<24 | h[1]<<16 | h[2]<<8; + for (h+=3, k-=3; k; k--, hw = (hw|*h++)<<8) + if (hw == nw) return (char *)h-3; + return hw == nw ? (char *)h-3 : 0; +} + +static char *fourbyte_memmem(const unsigned char *h, size_t k, const unsigned char *n) { + uint32_t nw = n[0]<<24 | n[1]<<16 | n[2]<<8 | n[3]; + uint32_t hw = h[0]<<24 | h[1]<<16 | h[2]<<8 | h[3]; + for (h+=4, k-=4; k; k--, hw = hw<<8 | *h++) + if (hw == nw) return (char *)h-4; + return hw == nw ? (char *)h-4 : 0; +} + +#define MAX(a,b) ((a)>(b)?(a):(b)) +#define MIN(a,b) ((a)<(b)?(a):(b)) + +#define BITOP(a,b,op) \ + ((a)[(size_t)(b)/(8*sizeof *(a))] op (size_t)1<<((size_t)(b)%(8*sizeof *(a)))) + +/* + * Maxime Crochemore and Dominique Perrin, Two-way string-matching, + * Journal of the ACM, 38(3):651-675, July 1991. + * + */ +static char *twoway_memmem( + const unsigned char *h, const unsigned char *z, const unsigned char *n, size_t l) { + size_t i, ip, jp, k, p, ms, p0, mem, mem0; + size_t byteset[32 / sizeof(size_t)] = { 0 }; + size_t shift[256]; + + /* Computing length of needle and fill shift table */ + for (i=0; i n[jp+k]) { + jp += k; + k = 1; + p = jp - ip; + } else { + ip = jp++; + k = p = 1; + } + } + ms = ip; + p0 = p; + + /* And with the opposite comparison */ + ip = -1; jp = 0; k = p = 1; + while (jp+k ms+1) ms = ip; + else p = p0; + + /* Periodic needle? */ + if (memcmp(n, n+p, ms+1)) { + mem0 = 0; + p = MAX(ms, l-ms-1) + 1; + } else mem0 = l-p; + mem = 0; + + /* Search loop */ + for (;;) { + /* If remainder of haystack is shorter than needle, done */ + if (z-h < l) return 0; + + /* Check last byte first; advance by shift on mismatch */ + if (BITOP(byteset, h[l-1], &)) { + k = l-shift[h[l-1]]; + if (k) { + if (k < mem) k = mem; + h += k; + mem = 0; + continue; + } + } else { + h += l; + mem = 0; + continue; + } + + /* Compare right half */ + for (k=MAX(ms+1,mem); kmem && n[k-1] == h[k-1]; k--); + if (k <= mem) return (char *)h; + h += p; + mem = mem0; + } +} + +void *memmem(const void *h0, size_t k, const void *n0, size_t l) { + const unsigned char *h = h0, *n = n0; + + /* Return immediately on empty needle */ + if (!l) return (void *)h; + + /* Return immediately when needle is longer than haystack */ + if (k +#include +#include +#include +#include +#include + +// Source: bionic/libc/upstream-openbsd/lib/libc/stdlib/getenv.c +static char *__findenv(const char *name, int len, int *offset) { + int i; + const char *np; + char **p, *cp; + + if (name == NULL || environ == NULL) + return (NULL); + for (p = environ + *offset; (cp = *p) != NULL; ++p) { + for (np = name, i = len; i && *cp; i--) + if (*cp++ != *np++) + break; + if (i == 0 && *cp++ == '=') { + *offset = p - environ; + return (cp); + } + } + return (NULL); +} + +// Source: bionic/libc/upstream-openbsd/lib/libc/stdlib/setenv.c +int setenv(const char *name, const char *value, int rewrite) { + static char **lastenv; + + char *C, **P; + const char *np; + int l_value, offset = 0; + + if (!name || !*name) { + errno = EINVAL; + return (-1); + } + for (np = name; *np && *np != '='; ++np) + ; + if (*np) { + errno = EINVAL; + return (-1); /* has `=' in name */ + } + + l_value = strlen(value); + if ((C = __findenv(name, (int)(np - name), &offset)) != NULL) { + int tmpoff = offset + 1; + if (!rewrite) + return (0); +#if 0 /* XXX - existing entry may not be writable */ + if (strlen(C) >= l_value) { /* old larger; copy over */ + while ((*C++ = *value++)) + ; + return (0); + } +#endif + /* could be set multiple times */ + while (__findenv(name, (int)(np - name), &tmpoff)) { + for (P = &environ[tmpoff];; ++P) + if (!(*P = *(P + 1))) + break; + } + } else { /* create new slot */ + size_t cnt = 0; + + if (environ != NULL) { + for (P = environ; *P != NULL; P++) + ; + cnt = P - environ; + } + size_t new_size; + if (__builtin_mul_overflow(cnt + 2, sizeof(char *), &new_size)) { + errno = ENOMEM; + return (-1); + } + P = realloc(lastenv, new_size); + if (!P) + return (-1); + if (lastenv != environ && environ != NULL) + memcpy(P, environ, cnt * sizeof(char *)); + lastenv = environ = P; + offset = cnt; + environ[cnt + 1] = NULL; + } + if (!(environ[offset] = /* name + `=' + value */ + malloc((int)(np - name) + l_value + 2))) + return (-1); + for (C = environ[offset]; (*C = *name++) && *C != '='; ++C) + ; + for (*C++ = '='; (*C++ = *value++); ) + ; + return (0); +} + +// Source: bionic/libc/bionic/libgen.cpp +static int __basename_r(const char *path, char* buffer, size_t buffer_size) { + const char *startp = NULL; + const char *endp = NULL; + int len; + int result; + + // Empty or NULL string gets treated as ".". + if (path == NULL || *path == '\0') { + startp = "."; + len = 1; + goto Exit; + } + + // Strip trailing slashes. + endp = path + strlen(path) - 1; + while (endp > path && *endp == '/') { + endp--; + } + + // All slashes becomes "/". + if (endp == path && *endp == '/') { + startp = "/"; + len = 1; + goto Exit; + } + + // Find the start of the base. + startp = endp; + while (startp > path && *(startp - 1) != '/') { + startp--; + } + + len = endp - startp +1; + +Exit: + result = len; + if (buffer == NULL) { + return result; + } + if (len > (int) buffer_size - 1) { + len = buffer_size - 1; + result = -1; + errno = ERANGE; + } + + if (len >= 0) { + memcpy(buffer, startp, len); + buffer[len] = 0; + } + return result; +} + +char *basename(const char *path) { + static char buf[4069]; + int rc = __basename_r(path, buf, sizeof(buf)); + return (rc < 0) ? NULL : buf; +} + +// Simply just abort when abort_message is called +void __wrap_abort_message(const char* format, ...) { + abort(); +} + +// Don't care about C++ global destructors +int __cxa_atexit(void (*func) (void *), void * arg, void * dso_handle) { + return 0; +} + +// Emulate pthread functions + +static pthread_key_t g_counter = 0; +static void **g_key_values = NULL; + +int pthread_key_create(pthread_key_t *key_ptr, void (*dtor)(void*)) { + *key_ptr = g_counter++; + g_key_values = realloc(g_key_values, g_counter * sizeof(void*)); + return 0; +} + +int pthread_key_delete(pthread_key_t key) { + if (key < g_counter) { + g_key_values[key] = NULL; + } + return 0; +} + +void *pthread_getspecific(pthread_key_t key) { + return key < g_counter ? g_key_values[key] : NULL; +} + +int pthread_setspecific(pthread_key_t key, const void *value) { + if (key < g_counter) { + g_key_values[key] = (void *) value; + } + return 0; +} + +// Workaround LTO bug: https://github.com/llvm/llvm-project/issues/61101 +#if defined(__i386__) +extern long *_GLOBAL_OFFSET_TABLE_; +long unused() { + return *_GLOBAL_OFFSET_TABLE_; +} +#endif diff --git a/nolibc.c b/nolibc.c new file mode 100644 index 0000000..9df3cbf --- /dev/null +++ b/nolibc.c @@ -0,0 +1,15 @@ +#include "nolibc/crt.h" +#include "nolibc/arch.h" + +// errno + +static int g_errno = 0; + +int *__errno(void) { + return &g_errno; +} + +long __set_errno_internal(int n) { + g_errno = n; + return -1; +} diff --git a/nolibc/arch-aarch64.h b/nolibc/arch-aarch64.h new file mode 100644 index 0000000..73ff481 --- /dev/null +++ b/nolibc/arch-aarch64.h @@ -0,0 +1,159 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * AARCH64 specific definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau + */ + +#ifndef _NOLIBC_ARCH_AARCH64_H +#define _NOLIBC_ARCH_AARCH64_H + +/* Syscalls for AARCH64 : + * - registers are 64-bit + * - stack is 16-byte aligned + * - syscall number is passed in x8 + * - arguments are in x0, x1, x2, x3, x4, x5 + * - the system call is performed by calling svc 0 + * - syscall return comes in x0. + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + * + * On aarch64, select() is not implemented so we have to use pselect6(). + */ +#define __ARCH_WANT_SYS_PSELECT6 + +#define my_syscall0(num) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0"); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + register long _arg2 __asm__ ("x1") = (long)(arg2); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + register long _arg2 __asm__ ("x1") = (long)(arg2); \ + register long _arg3 __asm__ ("x2") = (long)(arg3); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + register long _arg2 __asm__ ("x1") = (long)(arg2); \ + register long _arg3 __asm__ ("x2") = (long)(arg3); \ + register long _arg4 __asm__ ("x3") = (long)(arg4); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + register long _arg2 __asm__ ("x1") = (long)(arg2); \ + register long _arg3 __asm__ ("x2") = (long)(arg3); \ + register long _arg4 __asm__ ("x3") = (long)(arg4); \ + register long _arg5 __asm__ ("x4") = (long)(arg5); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r" (_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + register long _arg2 __asm__ ("x1") = (long)(arg2); \ + register long _arg3 __asm__ ("x2") = (long)(arg3); \ + register long _arg4 __asm__ ("x3") = (long)(arg4); \ + register long _arg5 __asm__ ("x4") = (long)(arg5); \ + register long _arg6 __asm__ ("x5") = (long)(arg6); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r" (_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_arg6), "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#ifdef _NOLIBC_CRT_H + +/* startup code */ +void __attribute__((noreturn)) _start(void) +{ + __asm__ volatile ( + "mov x0, sp\n" /* save stack pointer to x0, as arg1 of _start_c */ + "and sp, x0, -16\n" /* sp must be 16-byte aligned in the callee */ + "bl _start_c\n" /* transfer to c runtime */ + ); + __builtin_unreachable(); +} + +#endif /* _NOLIBC_CRT_H */ + +#endif /* _NOLIBC_ARCH_AARCH64_H */ diff --git a/nolibc/arch-arm.h b/nolibc/arch-arm.h new file mode 100644 index 0000000..82a1a62 --- /dev/null +++ b/nolibc/arch-arm.h @@ -0,0 +1,200 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * ARM specific definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau + */ + +#ifndef _NOLIBC_ARCH_ARM_H +#define _NOLIBC_ARCH_ARM_H + +/* Syscalls for ARM in ARM or Thumb modes : + * - registers are 32-bit + * - stack is 8-byte aligned + * ( http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.faqs/ka4127.html) + * - syscall number is passed in r7 + * - arguments are in r0, r1, r2, r3, r4, r5 + * - the system call is performed by calling svc #0 + * - syscall return comes in r0. + * - only lr is clobbered. + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + * - the syscall number is always specified last in order to allow to force + * some registers before (gcc refuses a %-register at the last position). + * - in thumb mode without -fomit-frame-pointer, r7 is also used to store the + * frame pointer, and we cannot directly assign it as a register variable, + * nor can we clobber it. Instead we assign the r6 register and swap it + * with r7 before calling svc, and r6 is marked as clobbered. + * We're just using any regular register which we assign to r7 after saving + * it. + * + * Also, ARM supports the old_select syscall if newselect is not available + */ +#define __ARCH_WANT_SYS_OLD_SELECT + +#if (defined(__THUMBEB__) || defined(__THUMBEL__)) && \ + !defined(NOLIBC_OMIT_FRAME_POINTER) +/* swap r6,r7 needed in Thumb mode since we can't use nor clobber r7 */ +#define _NOLIBC_SYSCALL_REG "r6" +#define _NOLIBC_THUMB_SET_R7 "eor r7, r6\neor r6, r7\neor r7, r6\n" +#define _NOLIBC_THUMB_RESTORE_R7 "mov r7, r6\n" + +#else /* we're in ARM mode */ +/* in Arm mode we can directly use r7 */ +#define _NOLIBC_SYSCALL_REG "r7" +#define _NOLIBC_THUMB_SET_R7 "" +#define _NOLIBC_THUMB_RESTORE_R7 "" + +#endif /* end THUMB */ + +#define my_syscall0(num) \ +({ \ + register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \ + register long _arg1 __asm__ ("r0"); \ + \ + __asm__ volatile ( \ + _NOLIBC_THUMB_SET_R7 \ + "svc #0\n" \ + _NOLIBC_THUMB_RESTORE_R7 \ + : "=r"(_arg1), "=r"(_num) \ + : "r"(_arg1), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \ + register long _arg1 __asm__ ("r0") = (long)(arg1); \ + \ + __asm__ volatile ( \ + _NOLIBC_THUMB_SET_R7 \ + "svc #0\n" \ + _NOLIBC_THUMB_RESTORE_R7 \ + : "=r"(_arg1), "=r" (_num) \ + : "r"(_arg1), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \ + register long _arg1 __asm__ ("r0") = (long)(arg1); \ + register long _arg2 __asm__ ("r1") = (long)(arg2); \ + \ + __asm__ volatile ( \ + _NOLIBC_THUMB_SET_R7 \ + "svc #0\n" \ + _NOLIBC_THUMB_RESTORE_R7 \ + : "=r"(_arg1), "=r" (_num) \ + : "r"(_arg1), "r"(_arg2), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \ + register long _arg1 __asm__ ("r0") = (long)(arg1); \ + register long _arg2 __asm__ ("r1") = (long)(arg2); \ + register long _arg3 __asm__ ("r2") = (long)(arg3); \ + \ + __asm__ volatile ( \ + _NOLIBC_THUMB_SET_R7 \ + "svc #0\n" \ + _NOLIBC_THUMB_RESTORE_R7 \ + : "=r"(_arg1), "=r" (_num) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \ + register long _arg1 __asm__ ("r0") = (long)(arg1); \ + register long _arg2 __asm__ ("r1") = (long)(arg2); \ + register long _arg3 __asm__ ("r2") = (long)(arg3); \ + register long _arg4 __asm__ ("r3") = (long)(arg4); \ + \ + __asm__ volatile ( \ + _NOLIBC_THUMB_SET_R7 \ + "svc #0\n" \ + _NOLIBC_THUMB_RESTORE_R7 \ + : "=r"(_arg1), "=r" (_num) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \ + register long _arg1 __asm__ ("r0") = (long)(arg1); \ + register long _arg2 __asm__ ("r1") = (long)(arg2); \ + register long _arg3 __asm__ ("r2") = (long)(arg3); \ + register long _arg4 __asm__ ("r3") = (long)(arg4); \ + register long _arg5 __asm__ ("r4") = (long)(arg5); \ + \ + __asm__ volatile ( \ + _NOLIBC_THUMB_SET_R7 \ + "svc #0\n" \ + _NOLIBC_THUMB_RESTORE_R7 \ + : "=r"(_arg1), "=r" (_num) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \ + register long _arg1 __asm__ ("r0") = (long)(arg1); \ + register long _arg2 __asm__ ("r1") = (long)(arg2); \ + register long _arg3 __asm__ ("r2") = (long)(arg3); \ + register long _arg4 __asm__ ("r3") = (long)(arg4); \ + register long _arg5 __asm__ ("r4") = (long)(arg5); \ + register long _arg6 __asm__ ("r5") = (long)(arg6); \ + \ + __asm__ volatile ( \ + _NOLIBC_THUMB_SET_R7 \ + "svc #0\n" \ + _NOLIBC_THUMB_RESTORE_R7 \ + : "=r"(_arg1), "=r" (_num) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_arg6), "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#ifdef _NOLIBC_CRT_H + +/* startup code */ +void __attribute__((noreturn)) _start(void) +{ + __asm__ volatile ( + "mov r0, sp\n" /* save stack pointer to %r0, as arg1 of _start_c */ + "and ip, r0, #-8\n" /* sp must be 8-byte aligned in the callee */ + "mov sp, ip\n" + "bl _start_c\n" /* transfer to c runtime */ + ); + __builtin_unreachable(); +} + +#endif /* _NOLIBC_CRT_H */ + +#endif /* _NOLIBC_ARCH_ARM_H */ diff --git a/nolibc/arch-i386.h b/nolibc/arch-i386.h new file mode 100644 index 0000000..4870ed2 --- /dev/null +++ b/nolibc/arch-i386.h @@ -0,0 +1,179 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * i386 specific definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau + */ + +#ifndef _NOLIBC_ARCH_I386_H +#define _NOLIBC_ARCH_I386_H + +/* Syscalls for i386 : + * - mostly similar to x86_64 + * - registers are 32-bit + * - syscall number is passed in eax + * - arguments are in ebx, ecx, edx, esi, edi, ebp respectively + * - all registers are preserved (except eax of course) + * - the system call is performed by calling int $0x80 + * - syscall return comes in eax + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + * - the syscall number is always specified last in order to allow to force + * some registers before (gcc refuses a %-register at the last position). + * + * Also, i386 supports the old_select syscall if newselect is not available + */ +#define __ARCH_WANT_SYS_OLD_SELECT + +#define my_syscall0(num) \ +({ \ + long _ret; \ + register long _num __asm__ ("eax") = (num); \ + \ + __asm__ volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + long _ret; \ + register long _num __asm__ ("eax") = (num); \ + register long _arg1 __asm__ ("ebx") = (long)(arg1); \ + \ + __asm__ volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + long _ret; \ + register long _num __asm__ ("eax") = (num); \ + register long _arg1 __asm__ ("ebx") = (long)(arg1); \ + register long _arg2 __asm__ ("ecx") = (long)(arg2); \ + \ + __asm__ volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), "r"(_arg2), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + long _ret; \ + register long _num __asm__ ("eax") = (num); \ + register long _arg1 __asm__ ("ebx") = (long)(arg1); \ + register long _arg2 __asm__ ("ecx") = (long)(arg2); \ + register long _arg3 __asm__ ("edx") = (long)(arg3); \ + \ + __asm__ volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + long _ret; \ + register long _num __asm__ ("eax") = (num); \ + register long _arg1 __asm__ ("ebx") = (long)(arg1); \ + register long _arg2 __asm__ ("ecx") = (long)(arg2); \ + register long _arg3 __asm__ ("edx") = (long)(arg3); \ + register long _arg4 __asm__ ("esi") = (long)(arg4); \ + \ + __asm__ volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + long _ret; \ + register long _num __asm__ ("eax") = (num); \ + register long _arg1 __asm__ ("ebx") = (long)(arg1); \ + register long _arg2 __asm__ ("ecx") = (long)(arg2); \ + register long _arg3 __asm__ ("edx") = (long)(arg3); \ + register long _arg4 __asm__ ("esi") = (long)(arg4); \ + register long _arg5 __asm__ ("edi") = (long)(arg5); \ + \ + __asm__ volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + long _eax = (long)(num); \ + long _arg6 = (long)(arg6); /* Always in memory */ \ + __asm__ volatile ( \ + "pushl %[_arg6]\n\t" \ + "pushl %%ebp\n\t" \ + "movl 4(%%esp),%%ebp\n\t" \ + "int $0x80\n\t" \ + "popl %%ebp\n\t" \ + "addl $4,%%esp\n\t" \ + : "+a"(_eax) /* %eax */ \ + : "b"(arg1), /* %ebx */ \ + "c"(arg2), /* %ecx */ \ + "d"(arg3), /* %edx */ \ + "S"(arg4), /* %esi */ \ + "D"(arg5), /* %edi */ \ + [_arg6]"m"(_arg6) /* memory */ \ + : "memory", "cc" \ + ); \ + _eax; \ +}) + +#ifdef _NOLIBC_CRT_H + +/* startup code */ +/* + * i386 System V ABI mandates: + * 1) last pushed argument must be 16-byte aligned. + * 2) The deepest stack frame should be set to zero + * + */ +void __attribute__((noreturn)) _start(void) +{ + __asm__ volatile ( + "xor %ebp, %ebp\n" /* zero the stack frame */ + "mov %esp, %eax\n" /* save stack pointer to %eax, as arg1 of _start_c */ + "and $-16, %esp\n" /* last pushed argument must be 16-byte aligned */ + "push %eax\n" /* push arg1 on stack to support plain stack modes too */ + "call _start_c\n" /* transfer to c runtime */ + "hlt\n" /* ensure it does not return */ + ); + __builtin_unreachable(); +} + +#endif /* _NOLIBC_CRT_H */ + +#endif /* _NOLIBC_ARCH_I386_H */ diff --git a/nolibc/arch-x86_64.h b/nolibc/arch-x86_64.h new file mode 100644 index 0000000..eb92010 --- /dev/null +++ b/nolibc/arch-x86_64.h @@ -0,0 +1,177 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * x86_64 specific definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau + */ + +#ifndef _NOLIBC_ARCH_X86_64_H +#define _NOLIBC_ARCH_X86_64_H + +/* Syscalls for x86_64 : + * - registers are 64-bit + * - syscall number is passed in rax + * - arguments are in rdi, rsi, rdx, r10, r8, r9 respectively + * - the system call is performed by calling the syscall instruction + * - syscall return comes in rax + * - rcx and r11 are clobbered, others are preserved. + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + * - the syscall number is always specified last in order to allow to force + * some registers before (gcc refuses a %-register at the last position). + * - see also x86-64 ABI section A.2 AMD64 Linux Kernel Conventions, A.2.1 + * Calling Conventions. + * + * Link x86-64 ABI: https://gitlab.com/x86-psABIs/x86-64-ABI/-/wikis/home + * + */ + +#define my_syscall0(num) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + register long _arg1 __asm__ ("rdi") = (long)(arg1); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), \ + "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + register long _arg1 __asm__ ("rdi") = (long)(arg1); \ + register long _arg2 __asm__ ("rsi") = (long)(arg2); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), "r"(_arg2), \ + "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + register long _arg1 __asm__ ("rdi") = (long)(arg1); \ + register long _arg2 __asm__ ("rsi") = (long)(arg2); \ + register long _arg3 __asm__ ("rdx") = (long)(arg3); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ + "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + register long _arg1 __asm__ ("rdi") = (long)(arg1); \ + register long _arg2 __asm__ ("rsi") = (long)(arg2); \ + register long _arg3 __asm__ ("rdx") = (long)(arg3); \ + register long _arg4 __asm__ ("r10") = (long)(arg4); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + register long _arg1 __asm__ ("rdi") = (long)(arg1); \ + register long _arg2 __asm__ ("rsi") = (long)(arg2); \ + register long _arg3 __asm__ ("rdx") = (long)(arg3); \ + register long _arg4 __asm__ ("r10") = (long)(arg4); \ + register long _arg5 __asm__ ("r8") = (long)(arg5); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + register long _arg1 __asm__ ("rdi") = (long)(arg1); \ + register long _arg2 __asm__ ("rsi") = (long)(arg2); \ + register long _arg3 __asm__ ("rdx") = (long)(arg3); \ + register long _arg4 __asm__ ("r10") = (long)(arg4); \ + register long _arg5 __asm__ ("r8") = (long)(arg5); \ + register long _arg6 __asm__ ("r9") = (long)(arg6); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_arg6), "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#ifdef _NOLIBC_CRT_H + +/* startup code */ +/* + * x86-64 System V ABI mandates: + * 1) %rsp must be 16-byte aligned right before the function call. + * 2) The deepest stack frame should be zero (the %rbp). + * + */ +void __attribute__((noreturn)) _start(void) +{ + __asm__ volatile ( + "xor %ebp, %ebp\n" /* zero the stack frame */ + "mov %rsp, %rdi\n" /* save stack pointer to %rdi, as arg1 of _start_c */ + "and $-16, %rsp\n" /* %rsp must be 16-byte aligned before call */ + "call _start_c\n" /* transfer to c runtime */ + "hlt\n" /* ensure it does not return */ + ); + __builtin_unreachable(); +} + +#endif /* _NOLIBC_CRT_H */ + +#endif /* _NOLIBC_ARCH_X86_64_H */ diff --git a/nolibc/arch.h b/nolibc/arch.h new file mode 100644 index 0000000..b7ee2a6 --- /dev/null +++ b/nolibc/arch.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * Copyright (C) 2017-2022 Willy Tarreau + */ + +/* Below comes the architecture-specific code. For each architecture, we have + * the syscall declarations and the _start code definition. This is the only + * global part. On all architectures the kernel puts everything in the stack + * before jumping to _start just above us, without any return address (_start + * is not a function but an entry point). So at the stack pointer we find argc. + * Then argv[] begins, and ends at the first NULL. Then we have envp which + * starts and ends with a NULL as well. So envp=argv+argc+1. + */ + +#ifndef _NOLIBC_ARCH_H +#define _NOLIBC_ARCH_H + +#if defined(__x86_64__) +#include "arch-x86_64.h" +#elif defined(__i386__) || defined(__i486__) || defined(__i586__) || defined(__i686__) +#include "arch-i386.h" +#elif defined(__ARM_EABI__) +#include "arch-arm.h" +#elif defined(__aarch64__) +#include "arch-aarch64.h" +#endif + +#endif /* _NOLIBC_ARCH_H */ diff --git a/nolibc/crt.h b/nolibc/crt.h new file mode 100644 index 0000000..ccbe2ea --- /dev/null +++ b/nolibc/crt.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * C Run Time support for NOLIBC + * Copyright (C) 2023 Zhangjin Wu + */ + +#ifndef _NOLIBC_CRT_H +#define _NOLIBC_CRT_H + +char **environ; +const unsigned long *_auxv; +void _exit(int); +void __init_stdio(void); + +typedef void init_func_t(int, char*[], char*[]); +typedef void fini_func_t(void); + +extern init_func_t *__preinit_array_start[]; +extern init_func_t *__preinit_array_end[]; +extern init_func_t *__init_array_start[]; +extern init_func_t *__init_array_end[]; +extern fini_func_t *__fini_array_start[]; +extern fini_func_t *__fini_array_end[]; + +static void call_array(init_func_t **start, init_func_t **end, int argc, char *argv[], char *envp[]) { + unsigned long count = end - start; + while (count-- > 0) { + init_func_t* function = *start++; + (*function)(argc, argv, envp); + } +} + +void __attribute__((used)) _start_c(long *sp) +{ + long argc; + char **argv; + char **envp; + const unsigned long *auxv; + /* silence potential warning: conflicting types for 'main' */ + int _nolibc_main(int, char **, char **) __asm__ ("main"); + + /* + * sp : argc <-- argument count, required by main() + * argv: argv[0] <-- argument vector, required by main() + * argv[1] + * ... + * argv[argc-1] + * null + * environ: environ[0] <-- environment variables, required by main() and getenv() + * environ[1] + * ... + * null + * _auxv: _auxv[0] <-- auxiliary vector, required by getauxval() + * _auxv[1] + * ... + * null + */ + + /* assign argc and argv */ + argc = *sp; + argv = (void *)(sp + 1); + + /* find environ */ + environ = envp = argv + argc + 1; + + /* find _auxv */ + for (auxv = (void *)envp; *auxv++;) + ; + _auxv = auxv; + + /* call preinit and init */ + __init_stdio(); + call_array(__preinit_array_start, __preinit_array_end, argc, argv, envp); + call_array(__init_array_start, __init_array_end, argc, argv, envp); + + /* go to application */ + _exit(_nolibc_main(argc, argv, envp)); +} + +#endif /* _NOLIBC_CRT_H */ diff --git a/stdio.c b/stdio.c new file mode 100644 index 0000000..2e78aa7 --- /dev/null +++ b/stdio.c @@ -0,0 +1,222 @@ +#include +#include +#include +#include + +typedef struct file_ptr_t { + int fd; + void *cookie; + int (*read_fn)(void*, char*, int); + int (*write_fn)(void*, const char*, int); + int (*close_fn)(void*); +} file_ptr_t; + +static int fp_read_fn(void *p, char *buf, int sz) { + intptr_t fd = (intptr_t) p; + return read(fd, buf, sz); +} + +static int fp_write_fn(void *p, const char *buf, int sz) { + intptr_t fd = (intptr_t) p; + return write(fd, buf, sz); +} + +static int fp_close_fn(void *p) { + intptr_t fd = (intptr_t) p; + return close(fd); +} + +static void set_fp_fd(file_ptr_t *fp, int fd) { + fp->fd = fd; + fp->cookie = NULL; + fp->read_fn = fp_read_fn; + fp->write_fn = fp_write_fn; + fp->close_fn = fp_close_fn; +} + +static file_ptr_t __stdio_fp[3]; + +FILE* stdin = (FILE *) &__stdio_fp[0]; +FILE* stdout = (FILE *) &__stdio_fp[1]; +FILE* stderr = (FILE *) &__stdio_fp[2]; + +void __init_stdio(void) { + set_fp_fd((file_ptr_t *) stdin, 0); + set_fp_fd((file_ptr_t *) stdout, 1); + set_fp_fd((file_ptr_t *) stderr, 2); +} + +FILE *fdopen(int fd, const char *mode __attribute__((unused))) { + file_ptr_t *fp = malloc(sizeof(file_ptr_t)); + set_fp_fd(fp, fd); + return (FILE *) fp; +} + +FILE *funopen(const void* cookie, + int (*read_fn)(void*, char*, int), + int (*write_fn)(void*, const char*, int), + fpos_t (*seek_fn)(void*, fpos_t, int), + int (*close_fn)(void*)) { + file_ptr_t *fp = malloc(sizeof(file_ptr_t)); + fp->fd = -1; + fp->cookie = (void *) cookie; + fp->read_fn = read_fn; + fp->write_fn = write_fn; + fp->close_fn = close_fn; + return (FILE *) fp; +} + +#define fn_arg (fp->fd < 0 ? fp->cookie : ((void*)(intptr_t) fp->fd)) + +int fclose(FILE *stream) { + file_ptr_t *fp = (file_ptr_t *) stream; + int ret = fp->close_fn(fn_arg); + free(fp); + return ret; +} + +int fileno(FILE *stream) { + file_ptr_t *fp = (file_ptr_t *) stream; + return fp->fd; +} + +int fputc(int ch, FILE *stream) { + char c = ch; + file_ptr_t *fp = (file_ptr_t *) stream; + return fp->write_fn(fn_arg, &c, 1) >= 0 ? 0 : EOF; +} + +size_t fwrite(const void* buf, size_t size, size_t count, FILE* stream) { + file_ptr_t *fp = (file_ptr_t *) stream; + int len = size * count; + int ret = fp->write_fn(fn_arg, buf, len); + return ret == len ? count : 0; +} + +int fputs(const char* s, FILE* stream) { + file_ptr_t *fp = (file_ptr_t *) stream; + size_t length = strlen(s); + return fp->write_fn(fn_arg, s, length) == length ? 0 : EOF; +} + +int fgetc(FILE *stream) { + char ch; + file_ptr_t *fp = (file_ptr_t *) stream; + if (fp->read_fn(fn_arg, &ch, 1) == 1) { + return ch; + } + return -1; +} + +size_t fread(void *buf, size_t size, size_t count, FILE* stream) { + file_ptr_t *fp = (file_ptr_t *) stream; + int len = size * count; + int ret = fp->read_fn(fn_arg, buf, len); + return ret == len ? count : 0; +} + +void setbuf(FILE* fp, char* buf) {} + +#include "tinystdio/tinystdio.c" + +struct file_putp { + FILE *fp; + int len; +}; + +static void file_putc(void *data, char ch) { + struct file_putp *putp = data; + int r = write(fileno(putp->fp), &ch, 1); + if (r >= 0) + putp->len += r; +} + +int vfprintf(FILE *stream, const char *format, va_list arg) { + struct file_putp data; + data.fp = stream; + data.len = 0; + tfp_format(&data, &file_putc, format, arg); + return data.len; +} + +int vasprintf(char **strp, const char *fmt, va_list ap) { + int size = vsnprintf(NULL, 0, fmt, ap); + if (size >= 0) { + *strp = malloc(size + 1); + vsnprintf(*strp, size, fmt, ap); + } + return size; +} + +int vprintf(const char *fmt, va_list args) { + return vfprintf(stdout, fmt, args); +} + +int fprintf(FILE *stream, const char *fmt, ...) { + va_list args; + int ret; + + va_start(args, fmt); + ret = vfprintf(stream, fmt, args); + va_end(args); + return ret; +} + +int printf(const char *fmt, ...) { + va_list args; + int ret; + + va_start(args, fmt); + ret = vfprintf(stdout, fmt, args); + va_end(args); + return ret; +} + +int sscanf(const char *str, const char *format, ...) { + va_list ap; + int retval; + + va_start(ap, format); + retval = tfp_vsscanf(str, format, ap); + va_end(ap); + return retval; +} + +// Original source: https://github.com/freebsd/freebsd/blob/master/contrib/file/src/getline.c +// License: BSD, full copyright notice please check original source +ssize_t getdelim(char **buf, size_t *bufsiz, int delimiter, FILE *fp) { + char *ptr, *eptr; + + if (*buf == NULL || *bufsiz == 0) { + *bufsiz = BUFSIZ; + if ((*buf = (char *) malloc(*bufsiz)) == NULL) + return -1; + } + + for (ptr = *buf, eptr = *buf + *bufsiz;;) { + int c = fgetc(fp); + if (c == -1) { + return ptr == *buf ? -1 : ptr - *buf; + } + *ptr++ = c; + if (c == delimiter) { + *ptr = '\0'; + return ptr - *buf; + } + if (ptr + 2 >= eptr) { + char *nbuf; + size_t nbufsiz = *bufsiz * 2; + ssize_t d = ptr - *buf; + if ((nbuf = (char *) realloc(*buf, nbufsiz)) == NULL) + return -1; + *buf = nbuf; + *bufsiz = nbufsiz; + eptr = nbuf + nbufsiz; + ptr = nbuf + d; + } + } +} + +ssize_t getline(char **buf, size_t *bufsiz, FILE *fp) { + return getdelim(buf, bufsiz, '\n', fp); +} diff --git a/syscall.c b/syscall.c new file mode 100644 index 0000000..1f10a50 --- /dev/null +++ b/syscall.c @@ -0,0 +1,221 @@ +#define SYS_INLINE + +#include "linux_syscall_support.h" + +// Some missing declarations +static inline _syscall3(int, faccessat, int, f, const char *, p, int, m) +_syscall2(int, umount2, const char *, t, int, f) +_syscall4(int, renameat, int, o, const char *, op, int, n, const char *, np) +_syscall1(mode_t, umask, mode_t, mask) +_syscall1(int, chroot, const char *, path) +_syscall2(int, nanosleep, const struct kernel_timespec *, req, struct kernel_timespec *, rem) +_syscall5(int, mount, const char *, s, const char *, t, + const char *, fs, unsigned long, f, const void *, d) +_syscall3(int, symlinkat, const char *, t, int, fd, const char *, l) +_syscall3(int, mkdirat, int, dirfd, const char *, pathname, mode_t, mode) +_syscall4(ssize_t, sendfile, int, out_fd, int, in_fd, off_t *, offset, size_t, count) +_syscall5(int, linkat, int, o, const char *, op, int, n, const char *, np, int, f) +_syscall4(int, mknodat, int, dirfd, const char *, pathname, mode_t, mode, dev_t, dev) +_syscall2(int, fchmod, int, fd, mode_t, mode) +_syscall4(int, fchmodat, int, dirfd, const char *, pathname, mode_t, mode, int, flags) +_syscall5(int, fchownat, int, dirfd, const char *, p, uid_t, owner, gid_t, group, int, flags) +_syscall3(ssize_t, readv, int, fd, const struct kernel_iovec*, v, size_t, c) + +#define SYMBOL_ALIAS(from, to) \ +__asm__(".global " #from " \n " #from " = " #to) + +#define EXPORT_SYMBOL(name) \ +SYMBOL_ALIAS(name, sys_##name) + +EXPORT_SYMBOL(_exit); +EXPORT_SYMBOL(openat); +EXPORT_SYMBOL(close); +EXPORT_SYMBOL(read); +EXPORT_SYMBOL(symlink); +EXPORT_SYMBOL(write); +EXPORT_SYMBOL(writev); +EXPORT_SYMBOL(unlink); +EXPORT_SYMBOL(mmap); +EXPORT_SYMBOL(munmap); +EXPORT_SYMBOL(mremap); +EXPORT_SYMBOL(readlink); +EXPORT_SYMBOL(unlinkat); +EXPORT_SYMBOL(getpid); +EXPORT_SYMBOL(chdir); +EXPORT_SYMBOL(umount2); +EXPORT_SYMBOL(readlinkat); +EXPORT_SYMBOL(renameat); +EXPORT_SYMBOL(umask); +EXPORT_SYMBOL(chroot); +EXPORT_SYMBOL(mount); +EXPORT_SYMBOL(symlinkat); +EXPORT_SYMBOL(stat); +EXPORT_SYMBOL(lstat); +EXPORT_SYMBOL(statfs); +EXPORT_SYMBOL(mkdirat); +EXPORT_SYMBOL(ioctl); +EXPORT_SYMBOL(fork); +EXPORT_SYMBOL(sendfile); +EXPORT_SYMBOL(ftruncate); +EXPORT_SYMBOL(linkat); +EXPORT_SYMBOL(mknodat); +EXPORT_SYMBOL(fchmod); +EXPORT_SYMBOL(fchmodat); +EXPORT_SYMBOL(fchownat); +EXPORT_SYMBOL(readv); +EXPORT_SYMBOL(lseek); +EXPORT_SYMBOL(execve); +EXPORT_SYMBOL(getdents64); + +SYMBOL_ALIAS(exit, _exit); + +#if defined(__LP64__) + +EXPORT_SYMBOL(fstat); +EXPORT_SYMBOL(newfstatat); +SYMBOL_ALIAS(fstatat, newfstatat); + +#else + +EXPORT_SYMBOL(fstat64); +EXPORT_SYMBOL(fstatat64); +SYMBOL_ALIAS(fstat, fstat64); +SYMBOL_ALIAS(fstatat, fstatat64); + +#endif + +int fchown(int fd, uid_t owner, gid_t group) { + return fchownat(fd, "", owner, group, AT_EMPTY_PATH); +} + +int lchown(const char* path, uid_t uid, gid_t gid) { + return fchownat(AT_FDCWD, path, uid, gid, AT_SYMLINK_NOFOLLOW); +} + +int chown(const char* path, uid_t uid, gid_t gid) { + return fchownat(AT_FDCWD, path, uid, gid, 0); +} + +int chmod(const char* path, mode_t mode) { + return sys_fchmodat(AT_FDCWD, path, mode, 0); +} + +int mkfifoat(int fd, const char* path, mode_t mode) { + return sys_mknodat(fd, path, (mode & ~S_IFMT) | S_IFIFO, 0); +} + +int mkfifo(const char* path, mode_t mode) { + return mkfifoat(AT_FDCWD, path, mode); +} + +int mknod(const char* path, mode_t mode, dev_t dev) { + return sys_mknodat(AT_FDCWD, path, mode, dev); +} + +int link(const char *oldpath, const char *newpath) { + return sys_linkat(AT_FDCWD, oldpath, AT_FDCWD, newpath, 0); +} + +int rmdir(const char *path) { + return sys_unlinkat(AT_FDCWD, path, AT_REMOVEDIR); +} + +int mkdir(const char *pathname, mode_t mode) { + return sys_mkdirat(AT_FDCWD, pathname, mode); +} + +int symlink(const char *target, const char *linkpath) { + return sys_symlinkat(target, AT_FDCWD, linkpath); +} + +int rename(const char *oldpath, const char *newpath) { + return sys_renameat(AT_FDCWD, oldpath, AT_FDCWD, newpath); +} + +int access(const char* path, int mode) { + return faccessat(AT_FDCWD, path, mode, 0); +} + +int remove(const char *path) { + int r = sys_unlinkat(AT_FDCWD, path, 0); + if (r < 0 && errno == EISDIR) { + r = sys_unlinkat(AT_FDCWD, path, AT_REMOVEDIR); + } + return r; +} + +// Source: bionic/libc/bionic/abort.cpp +void abort() { + // Don't block SIGABRT to give any signal handler a chance; we ignore + // any errors -- X311J doesn't allow abort to return anyway. + struct kernel_sigset_t mask; + sys_sigfillset(&mask); + sys_sigdelset(&mask, SIGABRT); + + sys_sigprocmask(SIG_SETMASK, &mask, NULL); + sys_raise(SIGABRT); + + // If SIGABRT is ignored or it's caught and the handler returns, + // remove the SIGABRT signal handler and raise SIGABRT again. + struct kernel_sigaction sa = { .sa_handler_ = SIG_DFL, .sa_flags = SA_RESTART }; + sys_sigaction(SIGABRT, &sa, NULL); + + sys_sigprocmask(SIG_SETMASK, &mask, NULL); + sys_raise(SIGABRT); + + // If we get this far, just exit. + _exit(127); +} + +// Source: bionic/libc/bionic/usleep.cpp +int usleep(useconds_t us) { + struct kernel_timespec ts; + ts.tv_sec = us / 1000000; + ts.tv_nsec = (us % 1000000) * 1000; + return sys_nanosleep(&ts, NULL); +} + +// Source: bionic/libc/bionic/faccessat.cpp +int faccessat(int dirfd, const char *pathname, int mode, int flags) { + // "The mode specifies the accessibility check(s) to be performed, + // and is either the value F_OK, or a mask consisting of the + // bitwise OR of one or more of R_OK, W_OK, and X_OK." + if ((mode != F_OK) && ((mode & ~(R_OK | W_OK | X_OK)) != 0) && + ((mode & (R_OK | W_OK | X_OK)) == 0)) { + errno = EINVAL; + return -1; + } + + if (flags != 0) { + // We deliberately don't support AT_SYMLINK_NOFOLLOW, a glibc + // only feature which is error prone and dangerous. + // More details at http://permalink.gmane.org/gmane.linux.lib.musl.general/6952 + // + // AT_EACCESS isn't supported either. Android doesn't have setuid + // programs, and never runs code with euid!=uid. + // + // We could use faccessat2(2) from Linux 5.8, but since we don't want the + // first feature and don't need the second, we just reject such requests. + errno = EINVAL; + return -1; + } + + return sys_faccessat(dirfd, pathname, mode); +} + +int open(const char *pathname, int flags, ...) { + int mode = 0; + + if (((flags & O_CREAT) == O_CREAT) || ((flags & O_TMPFILE) == O_TMPFILE)) { + va_list args; + va_start(args, flags); + mode = va_arg(args, int); + va_end(args); + } + +#if !defined(__LP64__) + flags |= O_LARGEFILE; +#endif + + return sys_openat(AT_FDCWD, pathname, flags, mode); +} diff --git a/tinystdio/tinystdio.c b/tinystdio/tinystdio.c new file mode 100644 index 0000000..b9b1f7c --- /dev/null +++ b/tinystdio/tinystdio.c @@ -0,0 +1,834 @@ +/* +File: tinyprintf.c + +Copyright (C) 2004 Kustaa Nyholm + +This library is free software; you can redistribute it and/or +modify it under the terms of the GNU Lesser General Public +License as published by the Free Software Foundation; either +version 2.1 of the License, or (at your option) any later version. + +This library is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +Lesser General Public License for more details. + +You should have received a copy of the GNU Lesser General Public +License along with this library; if not, write to the Free Software +Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + +*/ + +#include + +#include "tinystdio.h" + + +/* + * Configuration + */ + +/* Enable long int support */ +#define PRINTF_LONG_SUPPORT + +/* Enable long long int support (implies long int support) */ +#define PRINTF_LONG_LONG_SUPPORT + +/* Enable %z (size_t) support */ +#define PRINTF_SIZE_T_SUPPORT + + +/* + * Configuration adjustments + */ +#ifdef PRINTF_SIZE_T_SUPPORT +#include +#endif + +#ifdef PRINTF_LONG_LONG_SUPPORT +# define PRINTF_LONG_SUPPORT +#endif + +/* __SIZEOF___ defined at least by gcc */ +#ifdef __SIZEOF_POINTER__ +# define SIZEOF_POINTER __SIZEOF_POINTER__ +#endif +#ifdef __SIZEOF_LONG_LONG__ +# define SIZEOF_LONG_LONG __SIZEOF_LONG_LONG__ +#endif +#ifdef __SIZEOF_LONG__ +# define SIZEOF_LONG __SIZEOF_LONG__ +#endif +#ifdef __SIZEOF_INT__ +# define SIZEOF_INT __SIZEOF_INT__ +#endif + +#ifdef __GNUC__ +# define _TFP_GCC_NO_INLINE_ __attribute__ ((noinline)) +#else +# define _TFP_GCC_NO_INLINE_ +#endif + +/* + * Implementation + */ +struct param { + bool lz; /**< Leading zeros */ + bool alt; /**< alternate form */ + bool uc; /**< Upper case (for base16 only) */ + bool align_left; /**< 0 == align right (default), 1 == align left */ + int width; /**< field width */ + char sign; /**< The sign to display (if any) */ + unsigned int base; /**< number base (e.g.: 8, 10, 16) */ + char *bf; /**< Buffer to output */ + char prec; /**< Floating point precision */ +}; + + +#ifdef PRINTF_LONG_LONG_SUPPORT +static void _TFP_GCC_NO_INLINE_ ulli2a( + unsigned long long int num, struct param *p) +{ + int n = 0; + unsigned long long int d = 1; + char *bf = p->bf; + while (num / d >= p->base) + d *= p->base; + while (d != 0) { + int dgt = num / d; + num %= d; + d /= p->base; + if (n || dgt > 0 || d == 0) { + *bf++ = dgt + (dgt < 10 ? '0' : (p->uc ? 'A' : 'a') - 10); + ++n; + } + } + *bf = 0; +} + +static void lli2a(long long int num, struct param *p) +{ + if (num < 0) { + num = -num; + p->sign = '-'; + } + ulli2a(num, p); +} +#endif + +#ifdef PRINTF_LONG_SUPPORT +static void uli2a(unsigned long int num, struct param *p) +{ + int n = 0; + unsigned long int d = 1; + char *bf = p->bf; + while (num / d >= p->base) + d *= p->base; + while (d != 0) { + int dgt = num / d; + num %= d; + d /= p->base; + if (n || dgt > 0 || d == 0) { + *bf++ = dgt + (dgt < 10 ? '0' : (p->uc ? 'A' : 'a') - 10); + ++n; + } + } + *bf = 0; +} + +static void li2a(long num, struct param *p) +{ + if (num < 0) { + num = -num; + p->sign = '-'; + } + uli2a(num, p); +} +#endif + +static void ui2a(unsigned int num, struct param *p) +{ + int n = 0; + unsigned int d = 1; + char *bf = p->bf; + while (num / d >= p->base) + d *= p->base; + while (d != 0) { + int dgt = num / d; + num %= d; + d /= p->base; + if (n || dgt > 0 || d == 0) { + *bf++ = dgt + (dgt < 10 ? '0' : (p->uc ? 'A' : 'a') - 10); + ++n; + } + } + *bf = 0; +} + +static void i2a(int num, struct param *p) +{ + if (num < 0) { + num = -num; + p->sign = '-'; + } + ui2a(num, p); +} + +static int a2d(char ch) +{ + if (ch >= '0' && ch <= '9') + return ch - '0'; + else if (ch >= 'a' && ch <= 'f') + return ch - 'a' + 10; + else if (ch >= 'A' && ch <= 'F') + return ch - 'A' + 10; + else + return -1; +} + +static char a2u(char ch, const char **src, int base, int *nump) +{ + const char *p = *src; + int num = 0; + int digit; + while ((digit = a2d(ch)) >= 0) { + if (digit > base) + break; + num = num * base + digit; + ch = *p++; + } + *src = p; + *nump = num; + return ch; +} + +static void putchw(void *putp, putcf putf, struct param *p) +{ + char ch; + int n = p->width; + char *bf = p->bf; + + /* Number of filling characters */ + while (*bf++ && n > 0) + n--; + if (p->sign) + n--; + if (p->alt && p->base == 16) + n -= 2; + else if (p->alt && p->base == 8) + n--; + + /* Fill with space to align to the right, before alternate or sign */ + if (!p->lz && !p->align_left) { + while (n-- > 0) + putf(putp, ' '); + } + + /* print sign */ + if (p->sign) + putf(putp, p->sign); + + /* Alternate */ + if (p->alt && p->base == 16) { + putf(putp, '0'); + putf(putp, (p->uc ? 'X' : 'x')); + } else if (p->alt && p->base == 8) { + putf(putp, '0'); + } + + /* Fill with zeros, after alternate or sign */ + if (p->lz) { + while (n-- > 0) + putf(putp, '0'); + } + + /* Put actual buffer */ + bf = p->bf; + while ((ch = *bf++)) + putf(putp, ch); + + /* Fill with space to align to the left, after string */ + if (!p->lz && p->align_left) { + while (n-- > 0) + putf(putp, ' '); + } +} + +void tfp_format(void *putp, putcf putf, const char *fmt, va_list va) +{ + struct param p; + double fval; + int temp_buffer[16]; + int fpart; + int fiter; + int ffactor; + int sign; +#ifdef PRINTF_LONG_SUPPORT + char bf[23]; /* long = 64b on some architectures */ +#else + char bf[12]; /* int = 32b on some architectures */ +#endif + char ch; + p.bf = bf; + + while ((ch = *(fmt++))) { + if (ch != '%') { + putf(putp, ch); + } else { +#ifdef PRINTF_LONG_SUPPORT + char lng = 0; /* 1 for long, 2 for long long */ +#endif + /* Init parameter struct */ + p.lz = 0; + p.alt = 0; + p.width = 0; + p.align_left = 0; + p.sign = 0; + p.prec = TINY_PRINTF_FP_PRECISION; + + /* Flags */ + while ((ch = *(fmt++))) { + switch (ch) { + case '-': + p.align_left = 1; + continue; + case '0': + p.lz = 1; + continue; + case '#': + p.alt = 1; + continue; + case '+': + p.sign = 1; + continue; + default: + break; + } + break; + } + + /* Width */ + if (ch >= '0' && ch <= '9') { + ch = a2u(ch, &fmt, 10, &(p.width)); + } + + /* We accept 'x.y' format but don't support it completely: + * we ignore the 'y' digit => this ignores 0-fill + * size and makes it == width (ie. 'x') */ + if (ch == '.') { + //p.lz = 1; /* zero-padding */ + /* ignore actual 0-fill size: */ + ch = *(fmt++); + if (ch >= '0' && ch <= '9') + p.prec = ch - '0'; + do + { + ch = *(fmt++); + } while (ch >= '0' && ch <= '9'); + + } + +#ifdef PRINTF_SIZE_T_SUPPORT +# ifdef PRINTF_LONG_SUPPORT + if (ch == 'z') { + ch = *(fmt++); + if (sizeof(size_t) == sizeof(unsigned long int)) + lng = 1; +# ifdef PRINTF_LONG_LONG_SUPPORT + else if (sizeof(size_t) == sizeof(unsigned long long int)) + lng = 2; +# endif + } else +# endif +#endif + +#ifdef PRINTF_LONG_SUPPORT + if (ch == 'l') { + ch = *(fmt++); + lng = 1; +#ifdef PRINTF_LONG_LONG_SUPPORT + if (ch == 'l') { + ch = *(fmt++); + lng = 2; + } +#endif + } +#endif + switch (ch) { + case 0: + goto abort; + case 'u': + p.base = 10; +#ifdef PRINTF_LONG_SUPPORT +#ifdef PRINTF_LONG_LONG_SUPPORT + if (2 == lng) + ulli2a(va_arg(va, unsigned long long int), &p); + else +#endif + if (1 == lng) + uli2a(va_arg(va, unsigned long int), &p); + else +#endif + ui2a(va_arg(va, unsigned int), &p); + putchw(putp, putf, &p); + break; + case 'd': + case 'i': + p.base = 10; +#ifdef PRINTF_LONG_SUPPORT +#ifdef PRINTF_LONG_LONG_SUPPORT + if (2 == lng) + lli2a(va_arg(va, long long int), &p); + else +#endif + if (1 == lng) + li2a(va_arg(va, long int), &p); + else +#endif + i2a(va_arg(va, int), &p); + putchw(putp, putf, &p); + break; +#ifdef SIZEOF_POINTER + case 'p': + p.alt = 1; +# if defined(SIZEOF_INT) && SIZEOF_POINTER <= SIZEOF_INT + lng = 0; +# elif defined(SIZEOF_LONG) && SIZEOF_POINTER <= SIZEOF_LONG + lng = 1; +# elif defined(SIZEOF_LONG_LONG) && SIZEOF_POINTER <= SIZEOF_LONG_LONG + lng = 2; +# endif +#endif + case 'x': + case 'X': + p.base = 16; + p.uc = (ch == 'X')?1:0; +#ifdef PRINTF_LONG_SUPPORT +#ifdef PRINTF_LONG_LONG_SUPPORT + if (2 == lng) + ulli2a(va_arg(va, unsigned long long int), &p); + else +#endif + if (1 == lng) + uli2a(va_arg(va, unsigned long int), &p); + else +#endif + ui2a(va_arg(va, unsigned int), &p); + putchw(putp, putf, &p); + break; + case 'o': + p.base = 8; + ui2a(va_arg(va, unsigned int), &p); + putchw(putp, putf, &p); + break; + case 'c': + putf(putp, (char)(va_arg(va, int))); + break; + case 's': + p.bf = va_arg(va, char *); + putchw(putp, putf, &p); + p.bf = bf; + break; + case '%': + putf(putp, ch); + break; + case 'f': + case 'F': + fval = va_arg(va, double); + sign = 0; + if (fval < 0) + { + sign = 1; + p.width--; + fval = - fval; + } + else if (p.sign) { + sign = 2; + p.width--; + } + + fpart = (int)fval; + + fiter = 0; + while (fpart != 0) + { + temp_buffer[fiter++] = fpart % 10; + fpart = fpart / 10; + + } + fiter--; + if (fiter == -1) + p.width--; + /* Leading zeros */ + if (p.lz) { + + if (sign == 1) + putf(putp, '-'); + else if (sign == 2) + putf(putp, '+'); + + while (p.width-- > p.prec + fiter + 2) + { + putf(putp, '0'); + } + } + else + { + + while (p.width-- > p.prec + fiter + 2) + { + putf(putp, ' '); + } + + if (sign == 1) + putf(putp, '-'); + else if (sign == 2) + putf(putp, '+'); + + } + + if (fiter == -1) + putf(putp, '0'); + while (fiter > -1) + { + putf(putp, '0' + (temp_buffer[fiter--])); + } + + putf(putp, '.'); + ffactor = 1; + while (p.prec-- > 0) + { + ffactor *= 10; + fpart = (int)((fval - (int)fval)*ffactor); + if (fpart == 0) + putf(putp, '0'); + } + fiter = 0; + while (fpart != 0) + { + temp_buffer[fiter++] = fpart % 10; + fpart = fpart / 10; + + } + fiter--; + while (fiter > -1) + { + putf(putp, '0' + (temp_buffer[fiter--])); + } + break; + default: + break; + } + } + } + abort:; +} + + +#if TINYPRINTF_DEFINE_TFP_PRINTF +static putcf stdout_putf; +static void *stdout_putp; + +void init_printf(void *putp, putcf putf) +{ + stdout_putf = putf; + stdout_putp = putp; +} + +void tfp_printf(char *fmt, ...) +{ + va_list va; + va_start(va, fmt); + tfp_format(stdout_putp, stdout_putf, fmt, va); + va_end(va); +} +#endif + +#if TINYPRINTF_DEFINE_TFP_SPRINTF +struct _vsnprintf_putcf_data +{ + size_t dest_capacity; + char *dest; + size_t num_chars; +}; + +static void _vsnprintf_putcf(void *p, char c) +{ + struct _vsnprintf_putcf_data *data = (struct _vsnprintf_putcf_data*)p; + if (data->num_chars < data->dest_capacity) + data->dest[data->num_chars] = c; + data->num_chars ++; +} + +int tfp_vsnprintf(char *str, size_t size, const char *format, va_list ap) +{ + struct _vsnprintf_putcf_data data; + + data.dest = str; + data.dest_capacity = size ? size - 1 : 0; + data.num_chars = 0; + tfp_format(&data, _vsnprintf_putcf, format, ap); + + if (data.num_chars < data.dest_capacity) + data.dest[data.num_chars] = '\0'; + else if (size) + data.dest[data.dest_capacity] = '\0'; + + return data.num_chars; +} + +int tfp_snprintf(char *str, size_t size, const char *format, ...) +{ + va_list ap; + int retval; + + va_start(ap, format); + retval = tfp_vsnprintf(str, size, format, ap); + va_end(ap); + return retval; +} + +struct _vsprintf_putcf_data +{ + char *dest; + size_t num_chars; +}; + +static void _vsprintf_putcf(void *p, char c) +{ + struct _vsprintf_putcf_data *data = (struct _vsprintf_putcf_data*)p; + data->dest[data->num_chars++] = c; +} + +int tfp_vsprintf(char *str, const char *format, va_list ap) +{ + struct _vsprintf_putcf_data data; + data.dest = str; + data.num_chars = 0; + tfp_format(&data, _vsprintf_putcf, format, ap); + data.dest[data.num_chars] = '\0'; + return data.num_chars; +} + +int tfp_sprintf(char *str, const char *format, ...) +{ + va_list ap; + int retval; + + va_start(ap, format); + retval = tfp_vsprintf(str, format, ap); + va_end(ap); + return retval; +} + +#endif + +int tfp_vsscanf(const char* str, const char* format, va_list ap) +{ + int value, tmp; + float fvalue; + double Fvalue; + int count = 0; + int pos; + char neg, fmt_code; + + for (count = 0; *format != 0 && *str != 0; format++, str++) + { + while (*format == ' ' && *format != 0) format++; + + if (*format == 0) + break; + + while (*str == ' ' && *str != 0) str++; + + if (*str == 0) + break; + + if (*format == '%') + { + format++; + if (*format == 'n') + { + if (str[0] == '0' && (str[1] == 'x' || str[1] == 'X')) + { + fmt_code = 'x'; + str += 2; + } + else + if (str[0] == 'b') + { + fmt_code = 'b'; + str++; + } + else + fmt_code = 'd'; + } + else + fmt_code = *format; + + switch (fmt_code) + { + case 'x': + case 'X': + for (value = 0, pos = 0; *str != 0; str++, pos++) + { + if ('0' <= *str && *str <= '9') + tmp = *str - '0'; + else + if ('a' <= *str && *str <= 'f') + tmp = *str - 'a' + 10; + else + if ('A' <= *str && *str <= 'F') + tmp = *str - 'A' + 10; + else + break; + + value *= 16; + value += tmp; + } + if (pos == 0) + return count; + *(va_arg(ap, int*)) = value; + count++; + break; + + case 'b': + for (value = 0, pos = 0; *str != 0; str++, pos++) + { + if (*str != '0' && *str != '1') + break; + + value *= 2; + value += *str - '0'; + } + + if (pos == 0) + return count; + + *(va_arg(ap, int*)) = value; + count++; + break; + + case 'd': + if (*str == '-') + { + neg = 1; + str++; + } + else + neg = 0; + for (value = 0, pos = 0; *str != 0; str++, pos++) + { + if ('0' <= *str && *str <= '9') + value = value*10 + (int)(*str - '0'); + else + break; + } + if (pos == 0) + return count; + *(va_arg(ap, int*)) = neg ? -value : value; + count++; + break; + + case 'f': + if (*str == '-') + { + neg = 1; + str++; + } + else + neg = 0; + + int point_flag = 0; + int exp = 0; + for (fvalue = 0, pos = 0; *str != 0 ; str++, pos++) + { + if (*str == '.') + { + point_flag = 1; + str++; + } + if ('0' <= *str && *str <= '9') + fvalue = fvalue*10 + (int)(*str - '0'); + else + break; + + if (point_flag == 1) + exp++; + + } + + if (pos == 0) + return count; + + for (pos = 0; pos < exp; pos++) + fvalue = fvalue/10.0; + + *(va_arg(ap, float*)) = neg ? -fvalue : fvalue; + count++; + break; + + case 'F': + if (*str == '-') + { + neg = 1; + str++; + } + else + neg = 0; + + int Fpoint_flag = 0; + int Fexp = 0; + for (Fvalue = 0, pos = 0; *str != 0 ; str++, pos++) + { + + if (*str == '.') + { + Fpoint_flag = 1; + str++; + } + if ('0' <= *str && *str <= '9') + Fvalue = Fvalue*10 + (int)(*str - '0'); + else + break; + + if (Fpoint_flag == 1) + Fexp++; + + } + + if (pos == 0) + return count; + for (pos = 0; pos < Fexp; pos++) + Fvalue = Fvalue/10.0; + *(va_arg(ap, double*)) = neg ? -Fvalue : Fvalue; + count++; + break; + + case 'c': + *(va_arg(ap, char*)) = *str; + count++; + break; + + case 's': + pos = 0; + char* tab = va_arg(ap, char*); + while (*str != ' ' && *str != 0) + *(tab++) = *str++; + *tab = 0; + count++; + break; + + default: + return count; + } + } + else + { + if (*format != *str) + break; + } + } + + return count; +} diff --git a/tinystdio/tinystdio.h b/tinystdio/tinystdio.h new file mode 100644 index 0000000..89de5dc --- /dev/null +++ b/tinystdio/tinystdio.h @@ -0,0 +1,204 @@ +/* +File: tinyprintf.h + +Copyright (C) 2004 Kustaa Nyholm + +This library is free software; you can redistribute it and/or +modify it under the terms of the GNU Lesser General Public +License as published by the Free Software Foundation; either +version 2.1 of the License, or (at your option) any later version. + +This library is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +Lesser General Public License for more details. + +You should have received a copy of the GNU Lesser General Public +License along with this library; if not, write to the Free Software +Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + +This library is really just two files: 'tinyprintf.h' and 'tinyprintf.c'. + +They provide a simple and small (+400 loc) printf functionality to +be used in embedded systems. + +I've found them so useful in debugging that I do not bother with a +debugger at all. + +They are distributed in source form, so to use them, just compile them +into your project. + +Two printf variants are provided: printf and the 'sprintf' family of +functions ('snprintf', 'sprintf', 'vsnprintf', 'vsprintf'). + +The formats supported by this implementation are: +'c' 'd' 'i' 'o' 'p' 'u' 's' 'x' 'X'. + +Zero padding and field width are also supported. + +If the library is compiled with 'PRINTF_SUPPORT_LONG' defined, then +the long specifier is also supported. Note that this will pull in some +long math routines (pun intended!) and thus make your executable +noticeably longer. Likewise with 'PRINTF_LONG_LONG_SUPPORT' for the +long long specifier, and with 'PRINTF_SIZE_T_SUPPORT' for the size_t +specifier. + +The memory footprint of course depends on the target CPU, compiler and +compiler options, but a rough guesstimate (based on a H8S target) is about +1.4 kB for code and some twenty 'int's and 'char's, say 60 bytes of stack space. +Not too bad. Your mileage may vary. By hacking the source code you can +get rid of some hundred bytes, I'm sure, but personally I feel the balance of +functionality and flexibility versus code size is close to optimal for +many embedded systems. + +To use the printf, you need to supply your own character output function, +something like : + +void putc ( void* p, char c) +{ + while (!SERIAL_PORT_EMPTY) ; + SERIAL_PORT_TX_REGISTER = c; +} + +Before you can call printf, you need to initialize it to use your +character output function with something like: + +init_printf(NULL,putc); + +Notice the 'NULL' in 'init_printf' and the parameter 'void* p' in 'putc', +the NULL (or any pointer) you pass into the 'init_printf' will eventually be +passed to your 'putc' routine. This allows you to pass some storage space (or +anything really) to the character output function, if necessary. +This is not often needed but it was implemented like that because it made +implementing the sprintf function so neat (look at the source code). + +The code is re-entrant, except for the 'init_printf' function, so it is safe +to call it from interrupts too, although this may result in mixed output. +If you rely on re-entrancy, take care that your 'putc' function is re-entrant! + +The printf and sprintf functions are actually macros that translate to +'tfp_printf' and 'tfp_sprintf' when 'TINYPRINTF_OVERRIDE_LIBC' is set +(default). Setting it to 0 makes it possible to use them along with +'stdio.h' printf's in a single source file. When +'TINYPRINTF_OVERRIDE_LIBC' is set, please note that printf/sprintf are +not function-like macros, so if you have variables or struct members +with these names, things will explode in your face. Without variadic +macros this is the best we can do to wrap these function. If it is a +problem, just give up the macros and use the functions directly, or +rename them. + +It is also possible to avoid defining tfp_printf and/or tfp_sprintf by +clearing 'TINYPRINTF_DEFINE_TFP_PRINTF' and/or +'TINYPRINTF_DEFINE_TFP_SPRINTF' to 0. This allows for example to +export only tfp_format, which is at the core of all the other +functions. + +For further details see source code. + +regs Kusti, 23.10.2004 + + +31.01.2015 +Update from Cebotari Vladislav + cebotari.vladislav@gmail.com + +- Added floating point support with different precision in x.y format + also with leading zeros possibility (like standard printf function). + Floating point printf is tested on tiva launchpad (tm4c123gh6pm TI mcu) +- Also vsscanf for floats and double %f - float, %F - double + +*/ + +#ifndef __TFP_PRINTF__ +#define __TFP_PRINTF__ + +#include + +/* Global configuration */ + + +/* Set this to 0 if you do not want to provide tfp_printf */ +#ifndef TINYPRINTF_DEFINE_TFP_PRINTF +# define TINYPRINTF_DEFINE_TFP_PRINTF 0 +#endif + +/* Set this to 0 if you do not want to provide + tfp_sprintf/snprintf/vsprintf/vsnprintf */ +#ifndef TINYPRINTF_DEFINE_TFP_SPRINTF +# define TINYPRINTF_DEFINE_TFP_SPRINTF 1 +#endif + +/* Set this to 0 if you do not want tfp_printf and + tfp_{vsn,sn,vs,s}printf to be also available as + printf/{vsn,sn,vs,s}printf */ +#ifndef TINYPRINTF_OVERRIDE_LIBC +# define TINYPRINTF_OVERRIDE_LIBC 1 +#endif + +# define TINY_PRINTF_FP_PRECISION 6 + +/* Optional external types dependencies */ + +#if TINYPRINTF_DEFINE_TFP_SPRINTF +# include /* size_t */ +#endif + +/* Declarations */ + +#ifdef __GNUC__ +# define _TFP_SPECIFY_PRINTF_FMT(fmt_idx,arg1_idx) \ + __attribute__((format (printf, fmt_idx, arg1_idx))) +#else +# define _TFP_SPECIFY_PRINTF_FMT(fmt_idx,arg1_idx) +#endif + +#ifdef __cplusplus +extern "C" { +#endif + +typedef void (*putcf) (void *, char); + +/* + 'tfp_format' really is the central function for all tinyprintf. For + each output character after formatting, the 'putf' callback is + called with 2 args: + - an arbitrary void* 'putp' param defined by the user and + passed unmodified from 'tfp_format', + - the character. + The 'tfp_printf' and 'tfp_sprintf' functions simply define their own + callback and pass to it the right 'putp' it is expecting. +*/ +void tfp_format(void *putp, putcf putf, const char *fmt, va_list va); +# if TINYPRINTF_OVERRIDE_LIBC +# define tfp_vsscanf vsscanf +# endif +int tfp_vsscanf(const char* str, const char* format, va_list va); + +#if TINYPRINTF_DEFINE_TFP_SPRINTF +# if TINYPRINTF_OVERRIDE_LIBC +# define tfp_vsnprintf vsnprintf +# define tfp_snprintf snprintf +# define tfp_vsprintf vsprintf +# define tfp_sprintf sprintf +# endif +int tfp_vsnprintf(char *str, size_t size, const char *fmt, va_list ap); +int tfp_snprintf(char *str, size_t size, const char *fmt, ...) \ + _TFP_SPECIFY_PRINTF_FMT(3, 4); +int tfp_vsprintf(char *str, const char *fmt, va_list ap); +int tfp_sprintf(char *str, const char *fmt, ...) \ + _TFP_SPECIFY_PRINTF_FMT(2, 3); +#endif + +#if TINYPRINTF_DEFINE_TFP_PRINTF +# if TINYPRINTF_OVERRIDE_LIBC +# define tfp_printf printf +# endif +void init_printf(void *putp, putcf putf); +void tfp_printf(char *fmt, ...) _TFP_SPECIFY_PRINTF_FMT(1, 2); +#endif + +#ifdef __cplusplus +} +#endif + +#endif