diff --git a/CMakeLists.txt b/CMakeLists.txt index 4f196d1e414..53021dbe666 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -118,16 +118,16 @@ endif () option (ENABLE_TESTS "Enables tests" ON) -if (CMAKE_SYSTEM_PROCESSOR MATCHES "amd64|x86_64") +if (ARCH_AMD64) option (USE_INTERNAL_MEMCPY "Use internal implementation of 'memcpy' function instead of provided by libc. Only for x86_64." ON) +endif () - if (OS_LINUX AND NOT UNBUNDLED AND MAKE_STATIC_LIBRARIES AND NOT SPLIT_SHARED_LIBRARIES AND CMAKE_VERSION VERSION_GREATER "3.9.0") - option (GLIBC_COMPATIBILITY "Set to TRUE to enable compatibility with older glibc libraries. Only for x86_64, Linux. Implies USE_INTERNAL_MEMCPY." ON) - endif () +if (OS_LINUX AND NOT UNBUNDLED AND MAKE_STATIC_LIBRARIES AND NOT SPLIT_SHARED_LIBRARIES AND CMAKE_VERSION VERSION_GREATER "3.9.0") + option (GLIBC_COMPATIBILITY "Set to TRUE to enable compatibility with older glibc libraries. Only for x86_64, Linux. Implies USE_INTERNAL_MEMCPY." ON) +endif () - if (NOT CMAKE_VERSION VERSION_GREATER "3.9.0") - message (WARNING "CMake version must be greater than 3.9.0 for production builds.") - endif () +if (NOT CMAKE_VERSION VERSION_GREATER "3.9.0") + message (WARNING "CMake version must be greater than 3.9.0 for production builds.") endif () # Make sure the final executable has symbols exported diff --git a/cmake/arch.cmake b/cmake/arch.cmake index deaa7a36eb4..f339236af64 100644 --- a/cmake/arch.cmake +++ b/cmake/arch.cmake @@ -1,3 +1,6 @@ +if (CMAKE_SYSTEM_PROCESSOR MATCHES "amd64|x86_64") + set (ARCH_AMD64 1) +endif () if (CMAKE_SYSTEM_PROCESSOR MATCHES "^(aarch64.*|AARCH64.*)") set (ARCH_AARCH64 1) endif () diff --git a/contrib/jemalloc-cmake/CMakeLists.txt b/contrib/jemalloc-cmake/CMakeLists.txt index 43875c9d07f..5b420246168 100644 --- a/contrib/jemalloc-cmake/CMakeLists.txt +++ b/contrib/jemalloc-cmake/CMakeLists.txt @@ -45,9 +45,15 @@ endif () add_library(jemalloc STATIC ${SRCS}) -target_include_directories(jemalloc PUBLIC - ${CMAKE_CURRENT_SOURCE_DIR}/include - ${CMAKE_CURRENT_SOURCE_DIR}/include_linux_x86_64) # jemalloc.h +target_include_directories(jemalloc PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/include) + +if (ARCH_AMD64) + target_include_directories(jemalloc PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/include_linux_x86_64) +elseif (ARCH_ARM) + target_include_directories(jemalloc PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/include_linux_aarch64) +else () + message (FATAL_ERROR "jemalloc can only be used on x86_64 or aarch64.") +endif () target_include_directories(jemalloc PRIVATE ${JEMALLOC_SOURCE_DIR}/include) diff --git a/contrib/jemalloc-cmake/include_linux_aarch64/README b/contrib/jemalloc-cmake/include_linux_aarch64/README new file mode 100644 index 00000000000..2ab582803a2 --- /dev/null +++ b/contrib/jemalloc-cmake/include_linux_aarch64/README @@ -0,0 +1,7 @@ +Here are pre-generated files from jemalloc on Linux aarch64. +You can obtain these files by running ./autogen.sh inside jemalloc source directory. + +Added #define GNU_SOURCE +Added JEMALLOC_OVERRIDE___POSIX_MEMALIGN because why not. +Removed JEMALLOC_HAVE_ATTR_FORMAT_GNU_PRINTF because it's non standard. +Removed JEMALLOC_PURGE_MADVISE_FREE because it's available only from Linux 4.5. diff --git a/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/internal/jemalloc_internal_defs.h b/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/internal/jemalloc_internal_defs.h new file mode 100644 index 00000000000..0e1cf49ad97 --- /dev/null +++ b/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/internal/jemalloc_internal_defs.h @@ -0,0 +1,382 @@ +/* include/jemalloc/internal/jemalloc_internal_defs.h. Generated from jemalloc_internal_defs.h.in by configure. */ +#ifndef JEMALLOC_INTERNAL_DEFS_H_ +#define JEMALLOC_INTERNAL_DEFS_H_ + + +#ifndef _GNU_SOURCE + #define _GNU_SOURCE +#endif + +/* + * If JEMALLOC_PREFIX is defined via --with-jemalloc-prefix, it will cause all + * public APIs to be prefixed. This makes it possible, with some care, to use + * multiple allocators simultaneously. + */ +/* #undef JEMALLOC_PREFIX */ +/* #undef JEMALLOC_CPREFIX */ + +/* + * Define overrides for non-standard allocator-related functions if they are + * present on the system. + */ +#define JEMALLOC_OVERRIDE___LIBC_CALLOC +#define JEMALLOC_OVERRIDE___LIBC_FREE +#define JEMALLOC_OVERRIDE___LIBC_MALLOC +#define JEMALLOC_OVERRIDE___LIBC_MEMALIGN +#define JEMALLOC_OVERRIDE___LIBC_REALLOC +#define JEMALLOC_OVERRIDE___LIBC_VALLOC +#define JEMALLOC_OVERRIDE___POSIX_MEMALIGN + +/* + * JEMALLOC_PRIVATE_NAMESPACE is used as a prefix for all library-private APIs. + * For shared libraries, symbol visibility mechanisms prevent these symbols + * from being exported, but for static libraries, naming collisions are a real + * possibility. + */ +#define JEMALLOC_PRIVATE_NAMESPACE je_ + +/* + * Hyper-threaded CPUs may need a special instruction inside spin loops in + * order to yield to another virtual CPU. + */ +#define CPU_SPINWAIT +/* 1 if CPU_SPINWAIT is defined, 0 otherwise. */ +#define HAVE_CPU_SPINWAIT 0 + +/* + * Number of significant bits in virtual addresses. This may be less than the + * total number of bits in a pointer, e.g. on x64, for which the uppermost 16 + * bits are the same as bit 47. + */ +#define LG_VADDR 48 + +/* Defined if C11 atomics are available. */ +#define JEMALLOC_C11_ATOMICS 1 + +/* Defined if GCC __atomic atomics are available. */ +#define JEMALLOC_GCC_ATOMIC_ATOMICS 1 + +/* Defined if GCC __sync atomics are available. */ +#define JEMALLOC_GCC_SYNC_ATOMICS 1 + +/* + * Defined if __sync_add_and_fetch(uint32_t *, uint32_t) and + * __sync_sub_and_fetch(uint32_t *, uint32_t) are available, despite + * __GCC_HAVE_SYNC_COMPARE_AND_SWAP_4 not being defined (which means the + * functions are defined in libgcc instead of being inlines). + */ +/* #undef JE_FORCE_SYNC_COMPARE_AND_SWAP_4 */ + +/* + * Defined if __sync_add_and_fetch(uint64_t *, uint64_t) and + * __sync_sub_and_fetch(uint64_t *, uint64_t) are available, despite + * __GCC_HAVE_SYNC_COMPARE_AND_SWAP_8 not being defined (which means the + * functions are defined in libgcc instead of being inlines). + */ +/* #undef JE_FORCE_SYNC_COMPARE_AND_SWAP_8 */ + +/* + * Defined if __builtin_clz() and __builtin_clzl() are available. + */ +#define JEMALLOC_HAVE_BUILTIN_CLZ + +/* + * Defined if os_unfair_lock_*() functions are available, as provided by Darwin. + */ +/* #undef JEMALLOC_OS_UNFAIR_LOCK */ + +/* + * Defined if OSSpin*() functions are available, as provided by Darwin, and + * documented in the spinlock(3) manual page. + */ +/* #undef JEMALLOC_OSSPIN */ + +/* Defined if syscall(2) is usable. */ +#define JEMALLOC_USE_SYSCALL + +/* + * Defined if secure_getenv(3) is available. + */ +#define JEMALLOC_HAVE_SECURE_GETENV + +/* + * Defined if issetugid(2) is available. + */ +/* #undef JEMALLOC_HAVE_ISSETUGID */ + +/* Defined if pthread_atfork(3) is available. */ +#define JEMALLOC_HAVE_PTHREAD_ATFORK + +/* Defined if pthread_setname_np(3) is available. */ +#define JEMALLOC_HAVE_PTHREAD_SETNAME_NP + +/* + * Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available. + */ +#define JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE 1 + +/* + * Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available. + */ +#define JEMALLOC_HAVE_CLOCK_MONOTONIC 1 + +/* + * Defined if mach_absolute_time() is available. + */ +/* #undef JEMALLOC_HAVE_MACH_ABSOLUTE_TIME */ + +/* + * Defined if _malloc_thread_cleanup() exists. At least in the case of + * FreeBSD, pthread_key_create() allocates, which if used during malloc + * bootstrapping will cause recursion into the pthreads library. Therefore, if + * _malloc_thread_cleanup() exists, use it as the basis for thread cleanup in + * malloc_tsd. + */ +/* #undef JEMALLOC_MALLOC_THREAD_CLEANUP */ + +/* + * Defined if threaded initialization is known to be safe on this platform. + * Among other things, it must be possible to initialize a mutex without + * triggering allocation in order for threaded allocation to be safe. + */ +#define JEMALLOC_THREADED_INIT + +/* + * Defined if the pthreads implementation defines + * _pthread_mutex_init_calloc_cb(), in which case the function is used in order + * to avoid recursive allocation during mutex initialization. + */ +/* #undef JEMALLOC_MUTEX_INIT_CB */ + +/* Non-empty if the tls_model attribute is supported. */ +#define JEMALLOC_TLS_MODEL __attribute__((tls_model("initial-exec"))) + +/* + * JEMALLOC_DEBUG enables assertions and other sanity checks, and disables + * inline functions. + */ +/* #undef JEMALLOC_DEBUG */ + +/* JEMALLOC_STATS enables statistics calculation. */ +#define JEMALLOC_STATS + +/* JEMALLOC_EXPERIMENTAL_SMALLOCX_API enables experimental smallocx API. */ +/* #undef JEMALLOC_EXPERIMENTAL_SMALLOCX_API */ + +/* JEMALLOC_PROF enables allocation profiling. */ +/* #undef JEMALLOC_PROF */ + +/* Use libunwind for profile backtracing if defined. */ +/* #undef JEMALLOC_PROF_LIBUNWIND */ + +/* Use libgcc for profile backtracing if defined. */ +/* #undef JEMALLOC_PROF_LIBGCC */ + +/* Use gcc intrinsics for profile backtracing if defined. */ +/* #undef JEMALLOC_PROF_GCC */ + +/* + * JEMALLOC_DSS enables use of sbrk(2) to allocate extents from the data storage + * segment (DSS). + */ +#define JEMALLOC_DSS + +/* Support memory filling (junk/zero). */ +#define JEMALLOC_FILL + +/* Support utrace(2)-based tracing. */ +/* #undef JEMALLOC_UTRACE */ + +/* Support optional abort() on OOM. */ +/* #undef JEMALLOC_XMALLOC */ + +/* Support lazy locking (avoid locking unless a second thread is launched). */ +/* #undef JEMALLOC_LAZY_LOCK */ + +/* + * Minimum allocation alignment is 2^LG_QUANTUM bytes (ignoring tiny size + * classes). + */ +/* #undef LG_QUANTUM */ + +/* One page is 2^LG_PAGE bytes. */ +#define LG_PAGE 16 + +/* + * One huge page is 2^LG_HUGEPAGE bytes. Note that this is defined even if the + * system does not explicitly support huge pages; system calls that require + * explicit huge page support are separately configured. + */ +#define LG_HUGEPAGE 29 + +/* + * If defined, adjacent virtual memory mappings with identical attributes + * automatically coalesce, and they fragment when changes are made to subranges. + * This is the normal order of things for mmap()/munmap(), but on Windows + * VirtualAlloc()/VirtualFree() operations must be precisely matched, i.e. + * mappings do *not* coalesce/fragment. + */ +#define JEMALLOC_MAPS_COALESCE + +/* + * If defined, retain memory for later reuse by default rather than using e.g. + * munmap() to unmap freed extents. This is enabled on 64-bit Linux because + * common sequences of mmap()/munmap() calls will cause virtual memory map + * holes. + */ +#define JEMALLOC_RETAIN + +/* TLS is used to map arenas and magazine caches to threads. */ +#define JEMALLOC_TLS + +/* + * Used to mark unreachable code to quiet "end of non-void" compiler warnings. + * Don't use this directly; instead use unreachable() from util.h + */ +#define JEMALLOC_INTERNAL_UNREACHABLE __builtin_unreachable + +/* + * ffs*() functions to use for bitmapping. Don't use these directly; instead, + * use ffs_*() from util.h. + */ +#define JEMALLOC_INTERNAL_FFSLL __builtin_ffsll +#define JEMALLOC_INTERNAL_FFSL __builtin_ffsl +#define JEMALLOC_INTERNAL_FFS __builtin_ffs + +/* + * If defined, explicitly attempt to more uniformly distribute large allocation + * pointer alignments across all cache indices. + */ +#define JEMALLOC_CACHE_OBLIVIOUS + +/* + * If defined, enable logging facilities. We make this a configure option to + * avoid taking extra branches everywhere. + */ +/* #undef JEMALLOC_LOG */ + +/* + * If defined, use readlinkat() (instead of readlink()) to follow + * /etc/malloc_conf. + */ +/* #undef JEMALLOC_READLINKAT */ + +/* + * Darwin (OS X) uses zones to work around Mach-O symbol override shortcomings. + */ +/* #undef JEMALLOC_ZONE */ + +/* + * Methods for determining whether the OS overcommits. + * JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY: Linux's + * /proc/sys/vm.overcommit_memory file. + * JEMALLOC_SYSCTL_VM_OVERCOMMIT: FreeBSD's vm.overcommit sysctl. + */ +/* #undef JEMALLOC_SYSCTL_VM_OVERCOMMIT */ +#define JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY + +/* Defined if madvise(2) is available. */ +#define JEMALLOC_HAVE_MADVISE + +/* + * Defined if transparent huge pages are supported via the MADV_[NO]HUGEPAGE + * arguments to madvise(2). + */ +#define JEMALLOC_HAVE_MADVISE_HUGE + +/* + * Methods for purging unused pages differ between operating systems. + * + * madvise(..., MADV_FREE) : This marks pages as being unused, such that they + * will be discarded rather than swapped out. + * madvise(..., MADV_DONTNEED) : If JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS is + * defined, this immediately discards pages, + * such that new pages will be demand-zeroed if + * the address region is later touched; + * otherwise this behaves similarly to + * MADV_FREE, though typically with higher + * system overhead. + */ +#define JEMALLOC_PURGE_MADVISE_FREE +#define JEMALLOC_PURGE_MADVISE_DONTNEED +#define JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS + +/* Defined if madvise(2) is available but MADV_FREE is not (x86 Linux only). */ +/* #undef JEMALLOC_DEFINE_MADVISE_FREE */ + +/* + * Defined if MADV_DO[NT]DUMP is supported as an argument to madvise. + */ +#define JEMALLOC_MADVISE_DONTDUMP + +/* + * Defined if transparent huge pages (THPs) are supported via the + * MADV_[NO]HUGEPAGE arguments to madvise(2), and THP support is enabled. + */ +/* #undef JEMALLOC_THP */ + +/* Define if operating system has alloca.h header. */ +#define JEMALLOC_HAS_ALLOCA_H 1 + +/* C99 restrict keyword supported. */ +#define JEMALLOC_HAS_RESTRICT 1 + +/* For use by hash code. */ +/* #undef JEMALLOC_BIG_ENDIAN */ + +/* sizeof(int) == 2^LG_SIZEOF_INT. */ +#define LG_SIZEOF_INT 2 + +/* sizeof(long) == 2^LG_SIZEOF_LONG. */ +#define LG_SIZEOF_LONG 3 + +/* sizeof(long long) == 2^LG_SIZEOF_LONG_LONG. */ +#define LG_SIZEOF_LONG_LONG 3 + +/* sizeof(intmax_t) == 2^LG_SIZEOF_INTMAX_T. */ +#define LG_SIZEOF_INTMAX_T 3 + +/* glibc malloc hooks (__malloc_hook, __realloc_hook, __free_hook). */ +#define JEMALLOC_GLIBC_MALLOC_HOOK + +/* glibc memalign hook. */ +#define JEMALLOC_GLIBC_MEMALIGN_HOOK + +/* pthread support */ +#define JEMALLOC_HAVE_PTHREAD + +/* dlsym() support */ +#define JEMALLOC_HAVE_DLSYM + +/* Adaptive mutex support in pthreads. */ +#define JEMALLOC_HAVE_PTHREAD_MUTEX_ADAPTIVE_NP + +/* GNU specific sched_getcpu support */ +#define JEMALLOC_HAVE_SCHED_GETCPU + +/* GNU specific sched_setaffinity support */ +#define JEMALLOC_HAVE_SCHED_SETAFFINITY + +/* + * If defined, all the features necessary for background threads are present. + */ +#define JEMALLOC_BACKGROUND_THREAD 1 + +/* + * If defined, jemalloc symbols are not exported (doesn't work when + * JEMALLOC_PREFIX is not defined). + */ +/* #undef JEMALLOC_EXPORT */ + +/* config.malloc_conf options string. */ +#define JEMALLOC_CONFIG_MALLOC_CONF "" + +/* If defined, jemalloc takes the malloc/free/etc. symbol names. */ +#define JEMALLOC_IS_MALLOC 1 + +/* + * Defined if strerror_r returns char * if _GNU_SOURCE is defined. + */ +#define JEMALLOC_STRERROR_R_RETURNS_CHAR_WITH_GNU_SOURCE + +#endif /* JEMALLOC_INTERNAL_DEFS_H_ */ diff --git a/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/internal/jemalloc_preamble.h b/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/internal/jemalloc_preamble.h new file mode 100644 index 00000000000..c150785fb4a --- /dev/null +++ b/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/internal/jemalloc_preamble.h @@ -0,0 +1,194 @@ +#ifndef JEMALLOC_PREAMBLE_H +#define JEMALLOC_PREAMBLE_H + +#include "jemalloc_internal_defs.h" +#include "jemalloc/internal/jemalloc_internal_decls.h" + +#ifdef JEMALLOC_UTRACE +#include +#endif + +#define JEMALLOC_NO_DEMANGLE +#ifdef JEMALLOC_JET +# undef JEMALLOC_IS_MALLOC +# define JEMALLOC_N(n) jet_##n +# include "jemalloc/internal/public_namespace.h" +# define JEMALLOC_NO_RENAME +# include "jemalloc/jemalloc.h" +# undef JEMALLOC_NO_RENAME +#else +# define JEMALLOC_N(n) je_##n +# include "jemalloc/jemalloc.h" +#endif + +#if (defined(JEMALLOC_OSATOMIC) || defined(JEMALLOC_OSSPIN)) +#include +#endif + +#ifdef JEMALLOC_ZONE +#include +#include +#include +#endif + +#include "jemalloc/internal/jemalloc_internal_macros.h" + +/* + * Note that the ordering matters here; the hook itself is name-mangled. We + * want the inclusion of hooks to happen early, so that we hook as much as + * possible. + */ +#ifndef JEMALLOC_NO_PRIVATE_NAMESPACE +# ifndef JEMALLOC_JET +# include "jemalloc/internal/private_namespace.h" +# else +# include "jemalloc/internal/private_namespace_jet.h" +# endif +#endif +#include "jemalloc/internal/test_hooks.h" + +#ifdef JEMALLOC_DEFINE_MADVISE_FREE +# define JEMALLOC_MADV_FREE 8 +#endif + +static const bool config_debug = +#ifdef JEMALLOC_DEBUG + true +#else + false +#endif + ; +static const bool have_dss = +#ifdef JEMALLOC_DSS + true +#else + false +#endif + ; +static const bool have_madvise_huge = +#ifdef JEMALLOC_HAVE_MADVISE_HUGE + true +#else + false +#endif + ; +static const bool config_fill = +#ifdef JEMALLOC_FILL + true +#else + false +#endif + ; +static const bool config_lazy_lock = +#ifdef JEMALLOC_LAZY_LOCK + true +#else + false +#endif + ; +static const char * const config_malloc_conf = JEMALLOC_CONFIG_MALLOC_CONF; +static const bool config_prof = +#ifdef JEMALLOC_PROF + true +#else + false +#endif + ; +static const bool config_prof_libgcc = +#ifdef JEMALLOC_PROF_LIBGCC + true +#else + false +#endif + ; +static const bool config_prof_libunwind = +#ifdef JEMALLOC_PROF_LIBUNWIND + true +#else + false +#endif + ; +static const bool maps_coalesce = +#ifdef JEMALLOC_MAPS_COALESCE + true +#else + false +#endif + ; +static const bool config_stats = +#ifdef JEMALLOC_STATS + true +#else + false +#endif + ; +static const bool config_tls = +#ifdef JEMALLOC_TLS + true +#else + false +#endif + ; +static const bool config_utrace = +#ifdef JEMALLOC_UTRACE + true +#else + false +#endif + ; +static const bool config_xmalloc = +#ifdef JEMALLOC_XMALLOC + true +#else + false +#endif + ; +static const bool config_cache_oblivious = +#ifdef JEMALLOC_CACHE_OBLIVIOUS + true +#else + false +#endif + ; +/* + * Undocumented, for jemalloc development use only at the moment. See the note + * in jemalloc/internal/log.h. + */ +static const bool config_log = +#ifdef JEMALLOC_LOG + true +#else + false +#endif + ; +#ifdef JEMALLOC_HAVE_SCHED_GETCPU +/* Currently percpu_arena depends on sched_getcpu. */ +#define JEMALLOC_PERCPU_ARENA +#endif +static const bool have_percpu_arena = +#ifdef JEMALLOC_PERCPU_ARENA + true +#else + false +#endif + ; +/* + * Undocumented, and not recommended; the application should take full + * responsibility for tracking provenance. + */ +static const bool force_ivsalloc = +#ifdef JEMALLOC_FORCE_IVSALLOC + true +#else + false +#endif + ; +static const bool have_background_thread = +#ifdef JEMALLOC_BACKGROUND_THREAD + true +#else + false +#endif + ; + +#endif /* JEMALLOC_PREAMBLE_H */ diff --git a/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_defs.h b/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_defs.h new file mode 100644 index 00000000000..d1389237a77 --- /dev/null +++ b/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_defs.h @@ -0,0 +1,43 @@ +/* include/jemalloc/jemalloc_defs.h. Generated from jemalloc_defs.h.in by configure. */ +/* Defined if __attribute__((...)) syntax is supported. */ +#define JEMALLOC_HAVE_ATTR + +/* Defined if alloc_size attribute is supported. */ +#define JEMALLOC_HAVE_ATTR_ALLOC_SIZE + +/* Defined if format(printf, ...) attribute is supported. */ +#define JEMALLOC_HAVE_ATTR_FORMAT_PRINTF + +/* + * Define overrides for non-standard allocator-related functions if they are + * present on the system. + */ +#define JEMALLOC_OVERRIDE_MEMALIGN +#define JEMALLOC_OVERRIDE_VALLOC + +/* + * At least Linux omits the "const" in: + * + * size_t malloc_usable_size(const void *ptr); + * + * Match the operating system's prototype. + */ +#define JEMALLOC_USABLE_SIZE_CONST + +/* + * If defined, specify throw() for the public function prototypes when compiling + * with C++. The only justification for this is to match the prototypes that + * glibc defines. + */ +#define JEMALLOC_USE_CXX_THROW + +#ifdef _MSC_VER +# ifdef _WIN64 +# define LG_SIZEOF_PTR_WIN 3 +# else +# define LG_SIZEOF_PTR_WIN 2 +# endif +#endif + +/* sizeof(void *) == 2^LG_SIZEOF_PTR. */ +#define LG_SIZEOF_PTR 3 diff --git a/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_macros.h b/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_macros.h new file mode 100644 index 00000000000..79b13337fbb --- /dev/null +++ b/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_macros.h @@ -0,0 +1,123 @@ +#include +#include +#include +#include +#include + +#define JEMALLOC_VERSION "5.1.0-97-gcd2931ad9bbd78208565716ab102e86d858c2fff" +#define JEMALLOC_VERSION_MAJOR 5 +#define JEMALLOC_VERSION_MINOR 1 +#define JEMALLOC_VERSION_BUGFIX 0 +#define JEMALLOC_VERSION_NREV 97 +#define JEMALLOC_VERSION_GID "cd2931ad9bbd78208565716ab102e86d858c2fff" +#define JEMALLOC_VERSION_GID_IDENT cd2931ad9bbd78208565716ab102e86d858c2fff + +#define MALLOCX_LG_ALIGN(la) ((int)(la)) +#if LG_SIZEOF_PTR == 2 +# define MALLOCX_ALIGN(a) ((int)(ffs((int)(a))-1)) +#else +# define MALLOCX_ALIGN(a) \ + ((int)(((size_t)(a) < (size_t)INT_MAX) ? ffs((int)(a))-1 : \ + ffs((int)(((size_t)(a))>>32))+31)) +#endif +#define MALLOCX_ZERO ((int)0x40) +/* + * Bias tcache index bits so that 0 encodes "automatic tcache management", and 1 + * encodes MALLOCX_TCACHE_NONE. + */ +#define MALLOCX_TCACHE(tc) ((int)(((tc)+2) << 8)) +#define MALLOCX_TCACHE_NONE MALLOCX_TCACHE(-1) +/* + * Bias arena index bits so that 0 encodes "use an automatically chosen arena". + */ +#define MALLOCX_ARENA(a) ((((int)(a))+1) << 20) + +/* + * Use as arena index in "arena..{purge,decay,dss}" and + * "stats.arenas..*" mallctl interfaces to select all arenas. This + * definition is intentionally specified in raw decimal format to support + * cpp-based string concatenation, e.g. + * + * #define STRINGIFY_HELPER(x) #x + * #define STRINGIFY(x) STRINGIFY_HELPER(x) + * + * mallctl("arena." STRINGIFY(MALLCTL_ARENAS_ALL) ".purge", NULL, NULL, NULL, + * 0); + */ +#define MALLCTL_ARENAS_ALL 4096 +/* + * Use as arena index in "stats.arenas..*" mallctl interfaces to select + * destroyed arenas. + */ +#define MALLCTL_ARENAS_DESTROYED 4097 + +#if defined(__cplusplus) && defined(JEMALLOC_USE_CXX_THROW) +# define JEMALLOC_CXX_THROW throw() +#else +# define JEMALLOC_CXX_THROW +#endif + +#if defined(_MSC_VER) +# define JEMALLOC_ATTR(s) +# define JEMALLOC_ALIGNED(s) __declspec(align(s)) +# define JEMALLOC_ALLOC_SIZE(s) +# define JEMALLOC_ALLOC_SIZE2(s1, s2) +# ifndef JEMALLOC_EXPORT +# ifdef DLLEXPORT +# define JEMALLOC_EXPORT __declspec(dllexport) +# else +# define JEMALLOC_EXPORT __declspec(dllimport) +# endif +# endif +# define JEMALLOC_FORMAT_PRINTF(s, i) +# define JEMALLOC_NOINLINE __declspec(noinline) +# ifdef __cplusplus +# define JEMALLOC_NOTHROW __declspec(nothrow) +# else +# define JEMALLOC_NOTHROW +# endif +# define JEMALLOC_SECTION(s) __declspec(allocate(s)) +# define JEMALLOC_RESTRICT_RETURN __declspec(restrict) +# if _MSC_VER >= 1900 && !defined(__EDG__) +# define JEMALLOC_ALLOCATOR __declspec(allocator) +# else +# define JEMALLOC_ALLOCATOR +# endif +#elif defined(JEMALLOC_HAVE_ATTR) +# define JEMALLOC_ATTR(s) __attribute__((s)) +# define JEMALLOC_ALIGNED(s) JEMALLOC_ATTR(aligned(s)) +# ifdef JEMALLOC_HAVE_ATTR_ALLOC_SIZE +# define JEMALLOC_ALLOC_SIZE(s) JEMALLOC_ATTR(alloc_size(s)) +# define JEMALLOC_ALLOC_SIZE2(s1, s2) JEMALLOC_ATTR(alloc_size(s1, s2)) +# else +# define JEMALLOC_ALLOC_SIZE(s) +# define JEMALLOC_ALLOC_SIZE2(s1, s2) +# endif +# ifndef JEMALLOC_EXPORT +# define JEMALLOC_EXPORT JEMALLOC_ATTR(visibility("default")) +# endif +# ifdef JEMALLOC_HAVE_ATTR_FORMAT_GNU_PRINTF +# define JEMALLOC_FORMAT_PRINTF(s, i) JEMALLOC_ATTR(format(gnu_printf, s, i)) +# elif defined(JEMALLOC_HAVE_ATTR_FORMAT_PRINTF) +# define JEMALLOC_FORMAT_PRINTF(s, i) JEMALLOC_ATTR(format(printf, s, i)) +# else +# define JEMALLOC_FORMAT_PRINTF(s, i) +# endif +# define JEMALLOC_NOINLINE JEMALLOC_ATTR(noinline) +# define JEMALLOC_NOTHROW JEMALLOC_ATTR(nothrow) +# define JEMALLOC_SECTION(s) JEMALLOC_ATTR(section(s)) +# define JEMALLOC_RESTRICT_RETURN +# define JEMALLOC_ALLOCATOR +#else +# define JEMALLOC_ATTR(s) +# define JEMALLOC_ALIGNED(s) +# define JEMALLOC_ALLOC_SIZE(s) +# define JEMALLOC_ALLOC_SIZE2(s1, s2) +# define JEMALLOC_EXPORT +# define JEMALLOC_FORMAT_PRINTF(s, i) +# define JEMALLOC_NOINLINE +# define JEMALLOC_NOTHROW +# define JEMALLOC_SECTION(s) +# define JEMALLOC_RESTRICT_RETURN +# define JEMALLOC_ALLOCATOR +#endif diff --git a/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_protos.h b/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_protos.h new file mode 100644 index 00000000000..ff025e30fa7 --- /dev/null +++ b/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_protos.h @@ -0,0 +1,66 @@ +/* + * The je_ prefix on the following public symbol declarations is an artifact + * of namespace management, and should be omitted in application code unless + * JEMALLOC_NO_DEMANGLE is defined (see jemalloc_mangle.h). + */ +extern JEMALLOC_EXPORT const char *je_malloc_conf; +extern JEMALLOC_EXPORT void (*je_malloc_message)(void *cbopaque, + const char *s); + +JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN + void JEMALLOC_NOTHROW *je_malloc(size_t size) + JEMALLOC_CXX_THROW JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE(1); +JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN + void JEMALLOC_NOTHROW *je_calloc(size_t num, size_t size) + JEMALLOC_CXX_THROW JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE2(1, 2); +JEMALLOC_EXPORT int JEMALLOC_NOTHROW je_posix_memalign(void **memptr, + size_t alignment, size_t size) JEMALLOC_CXX_THROW JEMALLOC_ATTR(nonnull(1)); +JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN + void JEMALLOC_NOTHROW *je_aligned_alloc(size_t alignment, + size_t size) JEMALLOC_CXX_THROW JEMALLOC_ATTR(malloc) + JEMALLOC_ALLOC_SIZE(2); +JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN + void JEMALLOC_NOTHROW *je_realloc(void *ptr, size_t size) + JEMALLOC_CXX_THROW JEMALLOC_ALLOC_SIZE(2); +JEMALLOC_EXPORT void JEMALLOC_NOTHROW je_free(void *ptr) + JEMALLOC_CXX_THROW; + +JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN + void JEMALLOC_NOTHROW *je_mallocx(size_t size, int flags) + JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE(1); +JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN + void JEMALLOC_NOTHROW *je_rallocx(void *ptr, size_t size, + int flags) JEMALLOC_ALLOC_SIZE(2); +JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW je_xallocx(void *ptr, size_t size, + size_t extra, int flags); +JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW je_sallocx(const void *ptr, + int flags) JEMALLOC_ATTR(pure); +JEMALLOC_EXPORT void JEMALLOC_NOTHROW je_dallocx(void *ptr, int flags); +JEMALLOC_EXPORT void JEMALLOC_NOTHROW je_sdallocx(void *ptr, size_t size, + int flags); +JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW je_nallocx(size_t size, int flags) + JEMALLOC_ATTR(pure); + +JEMALLOC_EXPORT int JEMALLOC_NOTHROW je_mallctl(const char *name, + void *oldp, size_t *oldlenp, void *newp, size_t newlen); +JEMALLOC_EXPORT int JEMALLOC_NOTHROW je_mallctlnametomib(const char *name, + size_t *mibp, size_t *miblenp); +JEMALLOC_EXPORT int JEMALLOC_NOTHROW je_mallctlbymib(const size_t *mib, + size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen); +JEMALLOC_EXPORT void JEMALLOC_NOTHROW je_malloc_stats_print( + void (*write_cb)(void *, const char *), void *je_cbopaque, + const char *opts); +JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW je_malloc_usable_size( + JEMALLOC_USABLE_SIZE_CONST void *ptr) JEMALLOC_CXX_THROW; + +#ifdef JEMALLOC_OVERRIDE_MEMALIGN +JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN + void JEMALLOC_NOTHROW *je_memalign(size_t alignment, size_t size) + JEMALLOC_CXX_THROW JEMALLOC_ATTR(malloc); +#endif + +#ifdef JEMALLOC_OVERRIDE_VALLOC +JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN + void JEMALLOC_NOTHROW *je_valloc(size_t size) JEMALLOC_CXX_THROW + JEMALLOC_ATTR(malloc); +#endif diff --git a/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_typedefs.h b/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_typedefs.h new file mode 100644 index 00000000000..1a58874306e --- /dev/null +++ b/contrib/jemalloc-cmake/include_linux_aarch64/jemalloc/jemalloc_typedefs.h @@ -0,0 +1,77 @@ +typedef struct extent_hooks_s extent_hooks_t; + +/* + * void * + * extent_alloc(extent_hooks_t *extent_hooks, void *new_addr, size_t size, + * size_t alignment, bool *zero, bool *commit, unsigned arena_ind); + */ +typedef void *(extent_alloc_t)(extent_hooks_t *, void *, size_t, size_t, bool *, + bool *, unsigned); + +/* + * bool + * extent_dalloc(extent_hooks_t *extent_hooks, void *addr, size_t size, + * bool committed, unsigned arena_ind); + */ +typedef bool (extent_dalloc_t)(extent_hooks_t *, void *, size_t, bool, + unsigned); + +/* + * void + * extent_destroy(extent_hooks_t *extent_hooks, void *addr, size_t size, + * bool committed, unsigned arena_ind); + */ +typedef void (extent_destroy_t)(extent_hooks_t *, void *, size_t, bool, + unsigned); + +/* + * bool + * extent_commit(extent_hooks_t *extent_hooks, void *addr, size_t size, + * size_t offset, size_t length, unsigned arena_ind); + */ +typedef bool (extent_commit_t)(extent_hooks_t *, void *, size_t, size_t, size_t, + unsigned); + +/* + * bool + * extent_decommit(extent_hooks_t *extent_hooks, void *addr, size_t size, + * size_t offset, size_t length, unsigned arena_ind); + */ +typedef bool (extent_decommit_t)(extent_hooks_t *, void *, size_t, size_t, + size_t, unsigned); + +/* + * bool + * extent_purge(extent_hooks_t *extent_hooks, void *addr, size_t size, + * size_t offset, size_t length, unsigned arena_ind); + */ +typedef bool (extent_purge_t)(extent_hooks_t *, void *, size_t, size_t, size_t, + unsigned); + +/* + * bool + * extent_split(extent_hooks_t *extent_hooks, void *addr, size_t size, + * size_t size_a, size_t size_b, bool committed, unsigned arena_ind); + */ +typedef bool (extent_split_t)(extent_hooks_t *, void *, size_t, size_t, size_t, + bool, unsigned); + +/* + * bool + * extent_merge(extent_hooks_t *extent_hooks, void *addr_a, size_t size_a, + * void *addr_b, size_t size_b, bool committed, unsigned arena_ind); + */ +typedef bool (extent_merge_t)(extent_hooks_t *, void *, size_t, void *, size_t, + bool, unsigned); + +struct extent_hooks_s { + extent_alloc_t *alloc; + extent_dalloc_t *dalloc; + extent_destroy_t *destroy; + extent_commit_t *commit; + extent_decommit_t *decommit; + extent_purge_t *purge_lazy; + extent_purge_t *purge_forced; + extent_split_t *split; + extent_merge_t *merge; +}; diff --git a/libs/libcommon/cmake/find_jemalloc.cmake b/libs/libcommon/cmake/find_jemalloc.cmake index ec0841d1535..6508f1b675f 100644 --- a/libs/libcommon/cmake/find_jemalloc.cmake +++ b/libs/libcommon/cmake/find_jemalloc.cmake @@ -1,11 +1,11 @@ -if (OS_LINUX AND NOT SANITIZE AND NOT ARCH_ARM AND NOT ARCH_32 AND NOT ARCH_PPC64LE) +if (OS_LINUX AND NOT SANITIZE AND NOT ARCH_32 AND NOT ARCH_PPC64LE) set(ENABLE_JEMALLOC_DEFAULT ${ENABLE_LIBRARIES}) else () set(ENABLE_JEMALLOC_DEFAULT 0) endif () option (ENABLE_JEMALLOC "Set to TRUE to use jemalloc" ${ENABLE_JEMALLOC_DEFAULT}) -if (OS_LINUX AND NOT ARCH_ARM) +if (OS_LINUX) option (USE_INTERNAL_JEMALLOC_LIBRARY "Set to FALSE to use system jemalloc library instead of bundled" ${NOT_UNBUNDLED}) else() option (USE_INTERNAL_JEMALLOC_LIBRARY "Set to FALSE to use system jemalloc library instead of bundled" OFF) @@ -22,7 +22,7 @@ if (ENABLE_JEMALLOC) find_package (JeMalloc) endif () - if ((NOT JEMALLOC_LIBRARIES OR NOT JEMALLOC_INCLUDE_DIR) AND NOT MISSING_INTERNAL_JEMALLOC_LIBRARY AND NOT ARCH_ARM) + if ((NOT JEMALLOC_LIBRARIES OR NOT JEMALLOC_INCLUDE_DIR) AND NOT MISSING_INTERNAL_JEMALLOC_LIBRARY ) set (JEMALLOC_LIBRARIES "jemalloc") set (JEMALLOC_INCLUDE_DIR "${ClickHouse_SOURCE_DIR}/contrib/jemalloc-cmake/include" "${ClickHouse_SOURCE_DIR}/contrib/jemalloc-cmake/include_linux_x86_64") set (USE_INTERNAL_JEMALLOC_LIBRARY 1) diff --git a/libs/libglibc-compatibility/CMakeLists.txt b/libs/libglibc-compatibility/CMakeLists.txt index 9ceec6a8dee..2dbec5fa772 100644 --- a/libs/libglibc-compatibility/CMakeLists.txt +++ b/libs/libglibc-compatibility/CMakeLists.txt @@ -12,7 +12,15 @@ if (GLIBC_COMPATIBILITY) add_headers_and_sources(glibc_compatibility .) add_headers_and_sources(glibc_compatibility musl) - list(APPEND glibc_compatibility_sources musl/syscall.s musl/longjmp.s) + if (ARCH_ARM) + list (APPEND glibc_compatibility_sources musl/aarch64/syscall.s musl/aarch64/longjmp.s) + set (musl_arch_include_dir musl/aarch64) + elseif (ARCH_AMD64) + list (APPEND glibc_compatibility_sources musl/x86_64/syscall.s musl/x86_64/longjmp.s) + set (musl_arch_include_dir musl/x86_64) + else () + message (FATAL_ERROR "glibc_compatibility can only be used on x86_64 or aarch64.") + endif () list(REMOVE_ITEM glibc_compatibility_sources musl/getentropy.c) if(HAVE_SYS_RANDOM_H) @@ -25,7 +33,7 @@ if (GLIBC_COMPATIBILITY) add_library(glibc-compatibility STATIC ${glibc_compatibility_sources}) - target_include_directories(glibc-compatibility PRIVATE libcxxabi) + target_include_directories(glibc-compatibility PRIVATE libcxxabi ${musl_arch_include_dir}) if (NOT USE_STATIC_LIBRARIES AND NOT MAKE_STATIC_LIBRARIES) target_compile_options(glibc-compatibility PRIVATE -fPIC) diff --git a/libs/libglibc-compatibility/musl/aarch64/atomic_arch.h b/libs/libglibc-compatibility/musl/aarch64/atomic_arch.h new file mode 100644 index 00000000000..40fefc25bb1 --- /dev/null +++ b/libs/libglibc-compatibility/musl/aarch64/atomic_arch.h @@ -0,0 +1,82 @@ +#define a_ll a_ll +static inline int a_ll(volatile int *p) +{ + int v; + __asm__ __volatile__ ("ldaxr %w0,%1" : "=r"(v) : "Q"(*p)); + return v; +} + +#define a_sc a_sc +static inline int a_sc(volatile int *p, int v) +{ + int r; + __asm__ __volatile__ ("stlxr %w0,%w2,%1" : "=&r"(r), "=Q"(*p) : "r"(v) : "memory"); + return !r; +} + +#define a_barrier a_barrier +static inline void a_barrier() +{ + __asm__ __volatile__ ("dmb ish" : : : "memory"); +} + +#define a_cas a_cas +static inline int a_cas(volatile int *p, int t, int s) +{ + int old; + do { + old = a_ll(p); + if (old != t) { + a_barrier(); + break; + } + } while (!a_sc(p, s)); + return old; +} + +#define a_ll_p a_ll_p +static inline void *a_ll_p(volatile void *p) +{ + void *v; + __asm__ __volatile__ ("ldaxr %0, %1" : "=r"(v) : "Q"(*(void *volatile *)p)); + return v; +} + +#define a_sc_p a_sc_p +static inline int a_sc_p(volatile int *p, void *v) +{ + int r; + __asm__ __volatile__ ("stlxr %w0,%2,%1" : "=&r"(r), "=Q"(*(void *volatile *)p) : "r"(v) : "memory"); + return !r; +} + +#define a_cas_p a_cas_p +static inline void *a_cas_p(volatile void *p, void *t, void *s) +{ + void *old; + do { + old = a_ll_p(p); + if (old != t) { + a_barrier(); + break; + } + } while (!a_sc_p(p, s)); + return old; +} + +#define a_ctz_64 a_ctz_64 +static inline int a_ctz_64(uint64_t x) +{ + __asm__( + " rbit %0, %1\n" + " clz %0, %0\n" + : "=r"(x) : "r"(x)); + return x; +} + +#define a_clz_64 a_clz_64 +static inline int a_clz_64(uint64_t x) +{ + __asm__("clz %0, %1" : "=r"(x) : "r"(x)); + return x; +} diff --git a/libs/libglibc-compatibility/musl/aarch64/longjmp.s b/libs/libglibc-compatibility/musl/aarch64/longjmp.s new file mode 100644 index 00000000000..19f04e7eebb --- /dev/null +++ b/libs/libglibc-compatibility/musl/aarch64/longjmp.s @@ -0,0 +1,21 @@ +.global musl_glibc_longjmp +.type musl_glibc_longjmp,@function +musl_glibc_longjmp: + // IHI0055B_aapcs64.pdf 5.1.1, 5.1.2 callee saved registers + ldp x19, x20, [x0,#0] + ldp x21, x22, [x0,#16] + ldp x23, x24, [x0,#32] + ldp x25, x26, [x0,#48] + ldp x27, x28, [x0,#64] + ldp x29, x30, [x0,#80] + ldr x2, [x0,#104] + mov sp, x2 + ldp d8 , d9, [x0,#112] + ldp d10, d11, [x0,#128] + ldp d12, d13, [x0,#144] + ldp d14, d15, [x0,#160] + + mov x0, x1 + cbnz x1, 1f + mov x0, #1 +1: br x30 diff --git a/libs/libglibc-compatibility/musl/aarch64/syscall.s b/libs/libglibc-compatibility/musl/aarch64/syscall.s new file mode 100644 index 00000000000..845986bf787 --- /dev/null +++ b/libs/libglibc-compatibility/musl/aarch64/syscall.s @@ -0,0 +1,14 @@ +.global __syscall +.hidden __syscall +.type __syscall,%function +__syscall: + uxtw x8,w0 + mov x0,x1 + mov x1,x2 + mov x2,x3 + mov x3,x4 + mov x4,x5 + mov x5,x6 + mov x6,x7 + svc 0 + ret diff --git a/libs/libglibc-compatibility/musl/atomic_arch.h b/libs/libglibc-compatibility/musl/x86_64/atomic_arch.h similarity index 100% rename from libs/libglibc-compatibility/musl/atomic_arch.h rename to libs/libglibc-compatibility/musl/x86_64/atomic_arch.h diff --git a/libs/libglibc-compatibility/musl/longjmp.s b/libs/libglibc-compatibility/musl/x86_64/longjmp.s similarity index 100% rename from libs/libglibc-compatibility/musl/longjmp.s rename to libs/libglibc-compatibility/musl/x86_64/longjmp.s diff --git a/libs/libglibc-compatibility/musl/syscall.s b/libs/libglibc-compatibility/musl/x86_64/syscall.s similarity index 100% rename from libs/libglibc-compatibility/musl/syscall.s rename to libs/libglibc-compatibility/musl/x86_64/syscall.s