Index: head/contrib/jemalloc/COPYING =================================================================== --- head/contrib/jemalloc/COPYING (revision 360232) +++ head/contrib/jemalloc/COPYING (revision 360233) @@ -1,27 +1,27 @@ Unless otherwise specified, files in the jemalloc source distribution are subject to the following license: -------------------------------------------------------------------------------- -Copyright (C) 2002-2018 Jason Evans . +Copyright (C) 2002-present Jason Evans . All rights reserved. Copyright (C) 2007-2012 Mozilla Foundation. All rights reserved. -Copyright (C) 2009-2018 Facebook, Inc. All rights reserved. +Copyright (C) 2009-present Facebook, Inc. All rights reserved. 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(s), this list of conditions and the following disclaimer. 2. Redistributions in binary form must reproduce the above copyright notice(s), 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 HOLDER(S) ``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 HOLDER(S) 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. -------------------------------------------------------------------------------- Index: head/contrib/jemalloc/ChangeLog =================================================================== --- head/contrib/jemalloc/ChangeLog (revision 360232) +++ head/contrib/jemalloc/ChangeLog (revision 360233) @@ -1,1382 +1,1518 @@ Following are change highlights associated with official releases. Important bug fixes are all mentioned, but some internal enhancements are omitted here for brevity. Much more detail can be found in the git revision history: https://github.com/jemalloc/jemalloc -* 5.1.0 (May 4th, 2018) +* 5.2.1 (August 5, 2019) + + This release is primarily about Windows. A critical virtual memory leak is + resolved on all Windows platforms. The regression was present in all releases + since 5.0.0. + + Bug fixes: + - Fix a severe virtual memory leak on Windows. This regression was first + released in 5.0.0. (@Ignition, @j0t, @frederik-h, @davidtgoldblatt, + @interwq) + - Fix size 0 handling in posix_memalign(). This regression was first released + in 5.2.0. (@interwq) + - Fix the prof_log unit test which may observe unexpected backtraces from + compiler optimizations. The test was first added in 5.2.0. (@marxin, + @gnzlbg, @interwq) + - Fix the declaration of the extent_avail tree. This regression was first + released in 5.1.0. (@zoulasc) + - Fix an incorrect reference in jeprof. This functionality was first released + in 3.0.0. (@prehistoric-penguin) + - Fix an assertion on the deallocation fast-path. This regression was first + released in 5.2.0. (@yinan1048576) + - Fix the TLS_MODEL attribute in headers. This regression was first released + in 5.0.0. (@zoulasc, @interwq) + + Optimizations and refactors: + - Implement opt.retain on Windows and enable by default on 64-bit. (@interwq, + @davidtgoldblatt) + - Optimize away a branch on the operator delete[] path. (@mgrice) + - Add format annotation to the format generator function. (@zoulasc) + - Refactor and improve the size class header generation. (@yinan1048576) + - Remove best fit. (@djwatson) + - Avoid blocking on background thread locks for stats. (@oranagra, @interwq) + +* 5.2.0 (April 2, 2019) + + This release includes a few notable improvements, which are summarized below: + 1) improved fast-path performance from the optimizations by @djwatson; 2) + reduced virtual memory fragmentation and metadata usage; and 3) bug fixes on + setting the number of background threads. In addition, peak / spike memory + usage is improved with certain allocation patterns. As usual, the release and + prior dev versions have gone through large-scale production testing. + + New features: + - Implement oversize_threshold, which uses a dedicated arena for allocations + crossing the specified threshold to reduce fragmentation. (@interwq) + - Add extents usage information to stats. (@tyleretzel) + - Log time information for sampled allocations. (@tyleretzel) + - Support 0 size in sdallocx. (@djwatson) + - Output rate for certain counters in malloc_stats. (@zinoale) + - Add configure option --enable-readlinkat, which allows the use of readlinkat + over readlink. (@davidtgoldblatt) + - Add configure options --{enable,disable}-{static,shared} to allow not + building unwanted libraries. (@Ericson2314) + - Add configure option --disable-libdl to enable fully static builds. + (@interwq) + - Add mallctl interfaces: + + opt.oversize_threshold (@interwq) + + stats.arenas..extent_avail (@tyleretzel) + + stats.arenas..extents..n{dirty,muzzy,retained} (@tyleretzel) + + stats.arenas..extents..{dirty,muzzy,retained}_bytes + (@tyleretzel) + + Portability improvements: + - Update MSVC builds. (@maksqwe, @rustyx) + - Workaround a compiler optimizer bug on s390x. (@rkmisra) + - Make use of pthread_set_name_np(3) on FreeBSD. (@trasz) + - Implement malloc_getcpu() to enable percpu_arena for windows. (@santagada) + - Link against -pthread instead of -lpthread. (@paravoid) + - Make background_thread not dependent on libdl. (@interwq) + - Add stringify to fix a linker directive issue on MSVC. (@daverigby) + - Detect and fall back when 8-bit atomics are unavailable. (@interwq) + - Fall back to the default pthread_create if dlsym(3) fails. (@interwq) + + Optimizations and refactors: + - Refactor the TSD module. (@davidtgoldblatt) + - Avoid taking extents_muzzy mutex when muzzy is disabled. (@interwq) + - Avoid taking large_mtx for auto arenas on the tcache flush path. (@interwq) + - Optimize ixalloc by avoiding a size lookup. (@interwq) + - Implement opt.oversize_threshold which uses a dedicated arena for requests + crossing the threshold, also eagerly purges the oversize extents. Default + the threshold to 8 MiB. (@interwq) + - Clean compilation with -Wextra. (@gnzlbg, @jasone) + - Refactor the size class module. (@davidtgoldblatt) + - Refactor the stats emitter. (@tyleretzel) + - Optimize pow2_ceil. (@rkmisra) + - Avoid runtime detection of lazy purging on FreeBSD. (@trasz) + - Optimize mmap(2) alignment handling on FreeBSD. (@trasz) + - Improve error handling for THP state initialization. (@jsteemann) + - Rework the malloc() fast path. (@djwatson) + - Rework the free() fast path. (@djwatson) + - Refactor and optimize the tcache fill / flush paths. (@djwatson) + - Optimize sync / lwsync on PowerPC. (@chmeeedalf) + - Bypass extent_dalloc() when retain is enabled. (@interwq) + - Optimize the locking on large deallocation. (@interwq) + - Reduce the number of pages committed from sanity checking in debug build. + (@trasz, @interwq) + - Deprecate OSSpinLock. (@interwq) + - Lower the default number of background threads to 4 (when the feature + is enabled). (@interwq) + - Optimize the trylock spin wait. (@djwatson) + - Use arena index for arena-matching checks. (@interwq) + - Avoid forced decay on thread termination when using background threads. + (@interwq) + - Disable muzzy decay by default. (@djwatson, @interwq) + - Only initialize libgcc unwinder when profiling is enabled. (@paravoid, + @interwq) + + Bug fixes (all only relevant to jemalloc 5.x): + - Fix background thread index issues with max_background_threads. (@djwatson, + @interwq) + - Fix stats output for opt.lg_extent_max_active_fit. (@interwq) + - Fix opt.prof_prefix initialization. (@davidtgoldblatt) + - Properly trigger decay on tcache destroy. (@interwq, @amosbird) + - Fix tcache.flush. (@interwq) + - Detect whether explicit extent zero out is necessary with huge pages or + custom extent hooks, which may change the purge semantics. (@interwq) + - Fix a side effect caused by extent_max_active_fit combined with decay-based + purging, where freed extents can accumulate and not be reused for an + extended period of time. (@interwq, @mpghf) + - Fix a missing unlock on extent register error handling. (@zoulasc) + + Testing: + - Simplify the Travis script output. (@gnzlbg) + - Update the test scripts for FreeBSD. (@devnexen) + - Add unit tests for the producer-consumer pattern. (@interwq) + - Add Cirrus-CI config for FreeBSD builds. (@jasone) + - Add size-matching sanity checks on tcache flush. (@davidtgoldblatt, + @interwq) + + Incompatible changes: + - Remove --with-lg-page-sizes. (@davidtgoldblatt) + + Documentation: + - Attempt to build docs by default, however skip doc building when xsltproc + is missing. (@interwq, @cmuellner) + +* 5.1.0 (May 4, 2018) This release is primarily about fine-tuning, ranging from several new features to numerous notable performance and portability enhancements. The release and prior dev versions have been running in multiple large scale applications for months, and the cumulative improvements are substantial in many cases. Given the long and successful production runs, this release is likely a good candidate for applications to upgrade, from both jemalloc 5.0 and before. For performance-critical applications, the newly added TUNING.md provides guidelines on jemalloc tuning. New features: - Implement transparent huge page support for internal metadata. (@interwq) - Add opt.thp to allow enabling / disabling transparent huge pages for all mappings. (@interwq) - Add maximum background thread count option. (@djwatson) - Allow prof_active to control opt.lg_prof_interval and prof.gdump. (@interwq) - Allow arena index lookup based on allocation addresses via mallctl. (@lionkov) - Allow disabling initial-exec TLS model. (@davidtgoldblatt, @KenMacD) - Add opt.lg_extent_max_active_fit to set the max ratio between the size of the active extent selected (to split off from) and the size of the requested allocation. (@interwq, @davidtgoldblatt) - Add retain_grow_limit to set the max size when growing virtual address space. (@interwq) - Add mallctl interfaces: + arena..retain_grow_limit (@interwq) + arenas.lookup (@lionkov) + max_background_threads (@djwatson) + opt.lg_extent_max_active_fit (@interwq) + opt.max_background_threads (@djwatson) + opt.metadata_thp (@interwq) + opt.thp (@interwq) + stats.metadata_thp (@interwq) Portability improvements: - Support GNU/kFreeBSD configuration. (@paravoid) - Support m68k, nios2 and SH3 architectures. (@paravoid) - Fall back to FD_CLOEXEC when O_CLOEXEC is unavailable. (@zonyitoo) - Fix symbol listing for cross-compiling. (@tamird) - Fix high bits computation on ARM. (@davidtgoldblatt, @paravoid) - Disable the CPU_SPINWAIT macro for Power. (@davidtgoldblatt, @marxin) - Fix MSVC 2015 & 2017 builds. (@rustyx) - Improve RISC-V support. (@EdSchouten) - Set name mangling script in strict mode. (@nicolov) - Avoid MADV_HUGEPAGE on ARM. (@marxin) - Modify configure to determine return value of strerror_r. (@davidtgoldblatt, @cferris1000) - Make sure CXXFLAGS is tested with CPP compiler. (@nehaljwani) - Fix 32-bit build on MSVC. (@rustyx) - Fix external symbol on MSVC. (@maksqwe) - Avoid a printf format specifier warning. (@jasone) - Add configure option --disable-initial-exec-tls which can allow jemalloc to be dynamically loaded after program startup. (@davidtgoldblatt, @KenMacD) - AArch64: Add ILP32 support. (@cmuellner) - Add --with-lg-vaddr configure option to support cross compiling. (@cmuellner, @davidtgoldblatt) Optimizations and refactors: - Improve active extent fit with extent_max_active_fit. This considerably reduces fragmentation over time and improves virtual memory and metadata usage. (@davidtgoldblatt, @interwq) - Eagerly coalesce large extents to reduce fragmentation. (@interwq) - sdallocx: only read size info when page aligned (i.e. possibly sampled), which speeds up the sized deallocation path significantly. (@interwq) - Avoid attempting new mappings for in place expansion with retain, since it rarely succeeds in practice and causes high overhead. (@interwq) - Refactor OOM handling in newImpl. (@wqfish) - Add internal fine-grained logging functionality for debugging use. (@davidtgoldblatt) - Refactor arena / tcache interactions. (@davidtgoldblatt) - Refactor extent management with dumpable flag. (@davidtgoldblatt) - Add runtime detection of lazy purging. (@interwq) - Use pairing heap instead of red-black tree for extents_avail. (@djwatson) - Use sysctl on startup in FreeBSD. (@trasz) - Use thread local prng state instead of atomic. (@djwatson) - Make decay to always purge one more extent than before, because in practice large extents are usually the ones that cross the decay threshold. Purging the additional extent helps save memory as well as reduce VM fragmentation. (@interwq) - Fast division by dynamic values. (@davidtgoldblatt) - Improve the fit for aligned allocation. (@interwq, @edwinsmith) - Refactor extent_t bitpacking. (@rkmisra) - Optimize the generated assembly for ticker operations. (@davidtgoldblatt) - Convert stats printing to use a structured text emitter. (@davidtgoldblatt) - Remove preserve_lru feature for extents management. (@djwatson) - Consolidate two memory loads into one on the fast deallocation path. (@davidtgoldblatt, @interwq) Bug fixes (most of the issues are only relevant to jemalloc 5.0): - Fix deadlock with multithreaded fork in OS X. (@davidtgoldblatt) - Validate returned file descriptor before use. (@zonyitoo) - Fix a few background thread initialization and shutdown issues. (@interwq) - Fix an extent coalesce + decay race by taking both coalescing extents off the LRU list. (@interwq) - Fix potentially unbound increase during decay, caused by one thread keep stashing memory to purge while other threads generating new pages. The number of pages to purge is checked to prevent this. (@interwq) - Fix a FreeBSD bootstrap assertion. (@strejda, @interwq) - Handle 32 bit mutex counters. (@rkmisra) - Fix a indexing bug when creating background threads. (@davidtgoldblatt, @binliu19) - Fix arguments passed to extent_init. (@yuleniwo, @interwq) - Fix addresses used for ordering mutexes. (@rkmisra) - Fix abort_conf processing during bootstrap. (@interwq) - Fix include path order for out-of-tree builds. (@cmuellner) Incompatible changes: - Remove --disable-thp. (@interwq) - Remove mallctl interfaces: + config.thp (@interwq) Documentation: - Add TUNING.md. (@interwq, @davidtgoldblatt, @djwatson) * 5.0.1 (July 1, 2017) This bugfix release fixes several issues, most of which are obscure enough that typical applications are not impacted. Bug fixes: - Update decay->nunpurged before purging, in order to avoid potential update races and subsequent incorrect purging volume. (@interwq) - Only abort on dlsym(3) error if the failure impacts an enabled feature (lazy locking and/or background threads). This mitigates an initialization failure bug for which we still do not have a clear reproduction test case. (@interwq) - Modify tsd management so that it neither crashes nor leaks if a thread's only allocation activity is to call free() after TLS destructors have been executed. This behavior was observed when operating with GNU libc, and is unlikely to be an issue with other libc implementations. (@interwq) - Mask signals during background thread creation. This prevents signals from being inadvertently delivered to background threads. (@jasone, @davidtgoldblatt, @interwq) - Avoid inactivity checks within background threads, in order to prevent recursive mutex acquisition. (@interwq) - Fix extent_grow_retained() to use the specified hooks when the arena..extent_hooks mallctl is used to override the default hooks. (@interwq) - Add missing reentrancy support for custom extent hooks which allocate. (@interwq) - Post-fork(2), re-initialize the list of tcaches associated with each arena to contain no tcaches except the forking thread's. (@interwq) - Add missing post-fork(2) mutex reinitialization for extent_grow_mtx. This fixes potential deadlocks after fork(2). (@interwq) - Enforce minimum autoconf version (currently 2.68), since 2.63 is known to generate corrupt configure scripts. (@jasone) - Ensure that the configured page size (--with-lg-page) is no larger than the configured huge page size (--with-lg-hugepage). (@jasone) * 5.0.0 (June 13, 2017) Unlike all previous jemalloc releases, this release does not use naturally aligned "chunks" for virtual memory management, and instead uses page-aligned "extents". This change has few externally visible effects, but the internal impacts are... extensive. Many other internal changes combine to make this the most cohesively designed version of jemalloc so far, with ample opportunity for further enhancements. Continuous integration is now an integral aspect of development thanks to the efforts of @davidtgoldblatt, and the dev branch tends to remain reasonably stable on the tested platforms (Linux, FreeBSD, macOS, and Windows). As a side effect the official release frequency may decrease over time. New features: - Implement optional per-CPU arena support; threads choose which arena to use based on current CPU rather than on fixed thread-->arena associations. (@interwq) - Implement two-phase decay of unused dirty pages. Pages transition from dirty-->muzzy-->clean, where the first phase transition relies on madvise(... MADV_FREE) semantics, and the second phase transition discards pages such that they are replaced with demand-zeroed pages on next access. (@jasone) - Increase decay time resolution from seconds to milliseconds. (@jasone) - Implement opt-in per CPU background threads, and use them for asynchronous decay-driven unused dirty page purging. (@interwq) - Add mutex profiling, which collects a variety of statistics useful for diagnosing overhead/contention issues. (@interwq) - Add C++ new/delete operator bindings. (@djwatson) - Support manually created arena destruction, such that all data and metadata are discarded. Add MALLCTL_ARENAS_DESTROYED for accessing merged stats associated with destroyed arenas. (@jasone) - Add MALLCTL_ARENAS_ALL as a fixed index for use in accessing merged/destroyed arena statistics via mallctl. (@jasone) - Add opt.abort_conf to optionally abort if invalid configuration options are detected during initialization. (@interwq) - Add opt.stats_print_opts, so that e.g. JSON output can be selected for the stats dumped during exit if opt.stats_print is true. (@jasone) - Add --with-version=VERSION for use when embedding jemalloc into another project's git repository. (@jasone) - Add --disable-thp to support cross compiling. (@jasone) - Add --with-lg-hugepage to support cross compiling. (@jasone) - Add mallctl interfaces (various authors): + background_thread + opt.abort_conf + opt.retain + opt.percpu_arena + opt.background_thread + opt.{dirty,muzzy}_decay_ms + opt.stats_print_opts + arena..initialized + arena..destroy + arena..{dirty,muzzy}_decay_ms + arena..extent_hooks + arenas.{dirty,muzzy}_decay_ms + arenas.bin..slab_size + arenas.nlextents + arenas.lextent..size + arenas.create + stats.background_thread.{num_threads,num_runs,run_interval} + stats.mutexes.{ctl,background_thread,prof,reset}. {num_ops,num_spin_acq,num_wait,max_wait_time,total_wait_time,max_num_thds, num_owner_switch} + stats.arenas..{dirty,muzzy}_decay_ms + stats.arenas..uptime + stats.arenas..{pmuzzy,base,internal,resident} + stats.arenas..{dirty,muzzy}_{npurge,nmadvise,purged} + stats.arenas..bins..{nslabs,reslabs,curslabs} + stats.arenas..bins..mutex. {num_ops,num_spin_acq,num_wait,max_wait_time,total_wait_time,max_num_thds, num_owner_switch} + stats.arenas..lextents..{nmalloc,ndalloc,nrequests,curlextents} + stats.arenas.i.mutexes.{large,extent_avail,extents_dirty,extents_muzzy, extents_retained,decay_dirty,decay_muzzy,base,tcache_list}. {num_ops,num_spin_acq,num_wait,max_wait_time,total_wait_time,max_num_thds, num_owner_switch} Portability improvements: - Improve reentrant allocation support, such that deadlock is less likely if e.g. a system library call in turn allocates memory. (@davidtgoldblatt, @interwq) - Support static linking of jemalloc with glibc. (@djwatson) Optimizations and refactors: - Organize virtual memory as "extents" of virtual memory pages, rather than as naturally aligned "chunks", and store all metadata in arbitrarily distant locations. This reduces virtual memory external fragmentation, and will interact better with huge pages (not yet explicitly supported). (@jasone) - Fold large and huge size classes together; only small and large size classes remain. (@jasone) - Unify the allocation paths, and merge most fast-path branching decisions. (@davidtgoldblatt, @interwq) - Embed per thread automatic tcache into thread-specific data, which reduces conditional branches and dereferences. Also reorganize tcache to increase fast-path data locality. (@interwq) - Rewrite atomics to closely model the C11 API, convert various synchronization from mutex-based to atomic, and use the explicit memory ordering control to resolve various hypothetical races without increasing synchronization overhead. (@davidtgoldblatt) - Extensively optimize rtree via various methods: + Add multiple layers of rtree lookup caching, since rtree lookups are now part of fast-path deallocation. (@interwq) + Determine rtree layout at compile time. (@jasone) + Make the tree shallower for common configurations. (@jasone) + Embed the root node in the top-level rtree data structure, thus avoiding one level of indirection. (@jasone) + Further specialize leaf elements as compared to internal node elements, and directly embed extent metadata needed for fast-path deallocation. (@jasone) + Ignore leading always-zero address bits (architecture-specific). (@jasone) - Reorganize headers (ongoing work) to make them hermetic, and disentangle various module dependencies. (@davidtgoldblatt) - Convert various internal data structures such as size class metadata from boot-time-initialized to compile-time-initialized. Propagate resulting data structure simplifications, such as making arena metadata fixed-size. (@jasone) - Simplify size class lookups when constrained to size classes that are multiples of the page size. This speeds lookups, but the primary benefit is complexity reduction in code that was the source of numerous regressions. (@jasone) - Lock individual extents when possible for localized extent operations, rather than relying on a top-level arena lock. (@davidtgoldblatt, @jasone) - Use first fit layout policy instead of best fit, in order to improve packing. (@jasone) - If munmap(2) is not in use, use an exponential series to grow each arena's virtual memory, so that the number of disjoint virtual memory mappings remains low. (@jasone) - Implement per arena base allocators, so that arenas never share any virtual memory pages. (@jasone) - Automatically generate private symbol name mangling macros. (@jasone) Incompatible changes: - Replace chunk hooks with an expanded/normalized set of extent hooks. (@jasone) - Remove ratio-based purging. (@jasone) - Remove --disable-tcache. (@jasone) - Remove --disable-tls. (@jasone) - Remove --enable-ivsalloc. (@jasone) - Remove --with-lg-size-class-group. (@jasone) - Remove --with-lg-tiny-min. (@jasone) - Remove --disable-cc-silence. (@jasone) - Remove --enable-code-coverage. (@jasone) - Remove --disable-munmap (replaced by opt.retain). (@jasone) - Remove Valgrind support. (@jasone) - Remove quarantine support. (@jasone) - Remove redzone support. (@jasone) - Remove mallctl interfaces (various authors): + config.munmap + config.tcache + config.tls + config.valgrind + opt.lg_chunk + opt.purge + opt.lg_dirty_mult + opt.decay_time + opt.quarantine + opt.redzone + opt.thp + arena..lg_dirty_mult + arena..decay_time + arena..chunk_hooks + arenas.initialized + arenas.lg_dirty_mult + arenas.decay_time + arenas.bin..run_size + arenas.nlruns + arenas.lrun..size + arenas.nhchunks + arenas.hchunk..size + arenas.extend + stats.cactive + stats.arenas..lg_dirty_mult + stats.arenas..decay_time + stats.arenas..metadata.{mapped,allocated} + stats.arenas..{npurge,nmadvise,purged} + stats.arenas..huge.{allocated,nmalloc,ndalloc,nrequests} + stats.arenas..bins..{nruns,reruns,curruns} + stats.arenas..lruns..{nmalloc,ndalloc,nrequests,curruns} + stats.arenas..hchunks..{nmalloc,ndalloc,nrequests,curhchunks} Bug fixes: - Improve interval-based profile dump triggering to dump only one profile when a single allocation's size exceeds the interval. (@jasone) - Use prefixed function names (as controlled by --with-jemalloc-prefix) when pruning backtrace frames in jeprof. (@jasone) * 4.5.0 (February 28, 2017) This is the first release to benefit from much broader continuous integration testing, thanks to @davidtgoldblatt. Had we had this testing infrastructure in place for prior releases, it would have caught all of the most serious regressions fixed by this release. New features: - Add --disable-thp and the opt.thp mallctl to provide opt-out mechanisms for transparent huge page integration. (@jasone) - Update zone allocator integration to work with macOS 10.12. (@glandium) - Restructure *CFLAGS configuration, so that CFLAGS behaves typically, and EXTRA_CFLAGS provides a way to specify e.g. -Werror during building, but not during configuration. (@jasone, @ronawho) Bug fixes: - Fix DSS (sbrk(2)-based) allocation. This regression was first released in 4.3.0. (@jasone) - Handle race in per size class utilization computation. This functionality was first released in 4.0.0. (@interwq) - Fix lock order reversal during gdump. (@jasone) - Fix/refactor tcache synchronization. This regression was first released in 4.0.0. (@jasone) - Fix various JSON-formatted malloc_stats_print() bugs. This functionality was first released in 4.3.0. (@jasone) - Fix huge-aligned allocation. This regression was first released in 4.4.0. (@jasone) - When transparent huge page integration is enabled, detect what state pages start in according to the kernel's current operating mode, and only convert arena chunks to non-huge during purging if that is not their initial state. This functionality was first released in 4.4.0. (@jasone) - Fix lg_chunk clamping for the --enable-cache-oblivious --disable-fill case. This regression was first released in 4.0.0. (@jasone, @428desmo) - Properly detect sparc64 when building for Linux. (@glaubitz) * 4.4.0 (December 3, 2016) New features: - Add configure support for *-*-linux-android. (@cferris1000, @jasone) - Add the --disable-syscall configure option, for use on systems that place security-motivated limitations on syscall(2). (@jasone) - Add support for Debian GNU/kFreeBSD. (@thesam) Optimizations: - Add extent serial numbers and use them where appropriate as a sort key that is higher priority than address, so that the allocation policy prefers older extents. This tends to improve locality (decrease fragmentation) when memory grows downward. (@jasone) - Refactor madvise(2) configuration so that MADV_FREE is detected and utilized on Linux 4.5 and newer. (@jasone) - Mark partially purged arena chunks as non-huge-page. This improves interaction with Linux's transparent huge page functionality. (@jasone) Bug fixes: - Fix size class computations for edge conditions involving extremely large allocations. This regression was first released in 4.0.0. (@jasone, @ingvarha) - Remove overly restrictive assertions related to the cactive statistic. This regression was first released in 4.1.0. (@jasone) - Implement a more reliable detection scheme for os_unfair_lock on macOS. (@jszakmeister) * 4.3.1 (November 7, 2016) Bug fixes: - Fix a severe virtual memory leak. This regression was first released in 4.3.0. (@interwq, @jasone) - Refactor atomic and prng APIs to restore support for 32-bit platforms that use pre-C11 toolchains, e.g. FreeBSD's mips. (@jasone) * 4.3.0 (November 4, 2016) This is the first release that passes the test suite for multiple Windows configurations, thanks in large part to @glandium setting up continuous integration via AppVeyor (and Travis CI for Linux and OS X). New features: - Add "J" (JSON) support to malloc_stats_print(). (@jasone) - Add Cray compiler support. (@ronawho) Optimizations: - Add/use adaptive spinning for bootstrapping and radix tree node initialization. (@jasone) Bug fixes: - Fix large allocation to search starting in the optimal size class heap, which can substantially reduce virtual memory churn and fragmentation. This regression was first released in 4.0.0. (@mjp41, @jasone) - Fix stats.arenas..nthreads accounting. (@interwq) - Fix and simplify decay-based purging. (@jasone) - Make DSS (sbrk(2)-related) operations lockless, which resolves potential deadlocks during thread exit. (@jasone) - Fix over-sized allocation of radix tree leaf nodes. (@mjp41, @ogaun, @jasone) - Fix over-sized allocation of arena_t (plus associated stats) data structures. (@jasone, @interwq) - Fix EXTRA_CFLAGS to not affect configuration. (@jasone) - Fix a Valgrind integration bug. (@ronawho) - Disallow 0x5a junk filling when running in Valgrind. (@jasone) - Fix a file descriptor leak on Linux. This regression was first released in 4.2.0. (@vsarunas, @jasone) - Fix static linking of jemalloc with glibc. (@djwatson) - Use syscall(2) rather than {open,read,close}(2) during boot on Linux. This works around other libraries' system call wrappers performing reentrant allocation. (@kspinka, @Whissi, @jasone) - Fix OS X default zone replacement to work with OS X 10.12. (@glandium, @jasone) - Fix cached memory management to avoid needless commit/decommit operations during purging, which resolves permanent virtual memory map fragmentation issues on Windows. (@mjp41, @jasone) - Fix TSD fetches to avoid (recursive) allocation. This is relevant to non-TLS and Windows configurations. (@jasone) - Fix malloc_conf overriding to work on Windows. (@jasone) - Forcibly disable lazy-lock on Windows (was forcibly *enabled*). (@jasone) * 4.2.1 (June 8, 2016) Bug fixes: - Fix bootstrapping issues for configurations that require allocation during tsd initialization (e.g. --disable-tls). (@cferris1000, @jasone) - Fix gettimeofday() version of nstime_update(). (@ronawho) - Fix Valgrind regressions in calloc() and chunk_alloc_wrapper(). (@ronawho) - Fix potential VM map fragmentation regression. (@jasone) - Fix opt_zero-triggered in-place huge reallocation zeroing. (@jasone) - Fix heap profiling context leaks in reallocation edge cases. (@jasone) * 4.2.0 (May 12, 2016) New features: - Add the arena..reset mallctl, which makes it possible to discard all of an arena's allocations in a single operation. (@jasone) - Add the stats.retained and stats.arenas..retained statistics. (@jasone) - Add the --with-version configure option. (@jasone) - Support --with-lg-page values larger than actual page size. (@jasone) Optimizations: - Use pairing heaps rather than red-black trees for various hot data structures. (@djwatson, @jasone) - Streamline fast paths of rtree operations. (@jasone) - Optimize the fast paths of calloc() and [m,d,sd]allocx(). (@jasone) - Decommit unused virtual memory if the OS does not overcommit. (@jasone) - Specify MAP_NORESERVE on Linux if [heuristic] overcommit is active, in order to avoid unfortunate interactions during fork(2). (@jasone) Bug fixes: - Fix chunk accounting related to triggering gdump profiles. (@jasone) - Link against librt for clock_gettime(2) if glibc < 2.17. (@jasone) - Scale leak report summary according to sampling probability. (@jasone) * 4.1.1 (May 3, 2016) This bugfix release resolves a variety of mostly minor issues, though the bitmap fix is critical for 64-bit Windows. Bug fixes: - Fix the linear scan version of bitmap_sfu() to shift by the proper amount even when sizeof(long) is not the same as sizeof(void *), as on 64-bit Windows. (@jasone) - Fix hashing functions to avoid unaligned memory accesses (and resulting crashes). This is relevant at least to some ARM-based platforms. (@rkmisra) - Fix fork()-related lock rank ordering reversals. These reversals were unlikely to cause deadlocks in practice except when heap profiling was enabled and active. (@jasone) - Fix various chunk leaks in OOM code paths. (@jasone) - Fix malloc_stats_print() to print opt.narenas correctly. (@jasone) - Fix MSVC-specific build/test issues. (@rustyx, @yuslepukhin) - Fix a variety of test failures that were due to test fragility rather than core bugs. (@jasone) * 4.1.0 (February 28, 2016) This release is primarily about optimizations, but it also incorporates a lot of portability-motivated refactoring and enhancements. Many people worked on this release, to an extent that even with the omission here of minor changes (see git revision history), and of the people who reported and diagnosed issues, so much of the work was contributed that starting with this release, changes are annotated with author credits to help reflect the collaborative effort involved. New features: - Implement decay-based unused dirty page purging, a major optimization with mallctl API impact. This is an alternative to the existing ratio-based unused dirty page purging, and is intended to eventually become the sole purging mechanism. New mallctls: + opt.purge + opt.decay_time + arena..decay + arena..decay_time + arenas.decay_time + stats.arenas..decay_time (@jasone, @cevans87) - Add --with-malloc-conf, which makes it possible to embed a default options string during configuration. This was motivated by the desire to specify --with-malloc-conf=purge:decay , since the default must remain purge:ratio until the 5.0.0 release. (@jasone) - Add MS Visual Studio 2015 support. (@rustyx, @yuslepukhin) - Make *allocx() size class overflow behavior defined. The maximum size class is now less than PTRDIFF_MAX to protect applications against numerical overflow, and all allocation functions are guaranteed to indicate errors rather than potentially crashing if the request size exceeds the maximum size class. (@jasone) - jeprof: + Add raw heap profile support. (@jasone) + Add --retain and --exclude for backtrace symbol filtering. (@jasone) Optimizations: - Optimize the fast path to combine various bootstrapping and configuration checks and execute more streamlined code in the common case. (@interwq) - Use linear scan for small bitmaps (used for small object tracking). In addition to speeding up bitmap operations on 64-bit systems, this reduces allocator metadata overhead by approximately 0.2%. (@djwatson) - Separate arena_avail trees, which substantially speeds up run tree operations. (@djwatson) - Use memoization (boot-time-computed table) for run quantization. Separate arena_avail trees reduced the importance of this optimization. (@jasone) - Attempt mmap-based in-place huge reallocation. This can dramatically speed up incremental huge reallocation. (@jasone) Incompatible changes: - Make opt.narenas unsigned rather than size_t. (@jasone) Bug fixes: - Fix stats.cactive accounting regression. (@rustyx, @jasone) - Handle unaligned keys in hash(). This caused problems for some ARM systems. (@jasone, @cferris1000) - Refactor arenas array. In addition to fixing a fork-related deadlock, this makes arena lookups faster and simpler. (@jasone) - Move retained memory allocation out of the default chunk allocation function, to a location that gets executed even if the application installs a custom chunk allocation function. This resolves a virtual memory leak. (@buchgr) - Fix a potential tsd cleanup leak. (@cferris1000, @jasone) - Fix run quantization. In practice this bug had no impact unless applications requested memory with alignment exceeding one page. (@jasone, @djwatson) - Fix LinuxThreads-specific bootstrapping deadlock. (Cosmin Paraschiv) - jeprof: + Don't discard curl options if timeout is not defined. (@djwatson) + Detect failed profile fetches. (@djwatson) - Fix stats.arenas..{dss,lg_dirty_mult,decay_time,pactive,pdirty} for --disable-stats case. (@jasone) * 4.0.4 (October 24, 2015) This bugfix release fixes another xallocx() regression. No other regressions have come to light in over a month, so this is likely a good starting point for people who prefer to wait for "dot one" releases with all the major issues shaken out. Bug fixes: - Fix xallocx(..., MALLOCX_ZERO to zero the last full trailing page of large allocations that have been randomly assigned an offset of 0 when --enable-cache-oblivious configure option is enabled. * 4.0.3 (September 24, 2015) This bugfix release continues the trend of xallocx() and heap profiling fixes. Bug fixes: - Fix xallocx(..., MALLOCX_ZERO) to zero all trailing bytes of large allocations when --enable-cache-oblivious configure option is enabled. - Fix xallocx(..., MALLOCX_ZERO) to zero trailing bytes of huge allocations when resizing from/to a size class that is not a multiple of the chunk size. - Fix prof_tctx_dump_iter() to filter out nodes that were created after heap profile dumping started. - Work around a potentially bad thread-specific data initialization interaction with NPTL (glibc's pthreads implementation). * 4.0.2 (September 21, 2015) This bugfix release addresses a few bugs specific to heap profiling. Bug fixes: - Fix ixallocx_prof_sample() to never modify nor create sampled small allocations. xallocx() is in general incapable of moving small allocations, so this fix removes buggy code without loss of generality. - Fix irallocx_prof_sample() to always allocate large regions, even when alignment is non-zero. - Fix prof_alloc_rollback() to read tdata from thread-specific data rather than dereferencing a potentially invalid tctx. * 4.0.1 (September 15, 2015) This is a bugfix release that is somewhat high risk due to the amount of refactoring required to address deep xallocx() problems. As a side effect of these fixes, xallocx() now tries harder to partially fulfill requests for optional extra space. Note that a couple of minor heap profiling optimizations are included, but these are better thought of as performance fixes that were integral to discovering most of the other bugs. Optimizations: - Avoid a chunk metadata read in arena_prof_tctx_set(), since it is in the fast path when heap profiling is enabled. Additionally, split a special case out into arena_prof_tctx_reset(), which also avoids chunk metadata reads. - Optimize irallocx_prof() to optimistically update the sampler state. The prior implementation appears to have been a holdover from when rallocx()/xallocx() functionality was combined as rallocm(). Bug fixes: - Fix TLS configuration such that it is enabled by default for platforms on which it works correctly. - Fix arenas_cache_cleanup() and arena_get_hard() to handle allocation/deallocation within the application's thread-specific data cleanup functions even after arenas_cache is torn down. - Fix xallocx() bugs related to size+extra exceeding HUGE_MAXCLASS. - Fix chunk purge hook calls for in-place huge shrinking reallocation to specify the old chunk size rather than the new chunk size. This bug caused no correctness issues for the default chunk purge function, but was visible to custom functions set via the "arena..chunk_hooks" mallctl. - Fix heap profiling bugs: + Fix heap profiling to distinguish among otherwise identical sample sites with interposed resets (triggered via the "prof.reset" mallctl). This bug could cause data structure corruption that would most likely result in a segfault. + Fix irealloc_prof() to prof_alloc_rollback() on OOM. + Make one call to prof_active_get_unlocked() per allocation event, and use the result throughout the relevant functions that handle an allocation event. Also add a missing check in prof_realloc(). These fixes protect allocation events against concurrent prof_active changes. + Fix ixallocx_prof() to pass usize_max and zero to ixallocx_prof_sample() in the correct order. + Fix prof_realloc() to call prof_free_sampled_object() after calling prof_malloc_sample_object(). Prior to this fix, if tctx and old_tctx were the same, the tctx could have been prematurely destroyed. - Fix portability bugs: + Don't bitshift by negative amounts when encoding/decoding run sizes in chunk header maps. This affected systems with page sizes greater than 8 KiB. + Rename index_t to szind_t to avoid an existing type on Solaris. + Add JEMALLOC_CXX_THROW to the memalign() function prototype, in order to match glibc and avoid compilation errors when including both jemalloc/jemalloc.h and malloc.h in C++ code. + Don't assume that /bin/sh is appropriate when running size_classes.sh during configuration. + Consider __sparcv9 a synonym for __sparc64__ when defining LG_QUANTUM. + Link tests to librt if it contains clock_gettime(2). * 4.0.0 (August 17, 2015) This version contains many speed and space optimizations, both minor and major. The major themes are generalization, unification, and simplification. Although many of these optimizations cause no visible behavior change, their cumulative effect is substantial. New features: - Normalize size class spacing to be consistent across the complete size range. By default there are four size classes per size doubling, but this is now configurable via the --with-lg-size-class-group option. Also add the --with-lg-page, --with-lg-page-sizes, --with-lg-quantum, and --with-lg-tiny-min options, which can be used to tweak page and size class settings. Impacts: + Worst case performance for incrementally growing/shrinking reallocation is improved because there are far fewer size classes, and therefore copying happens less often. + Internal fragmentation is limited to 20% for all but the smallest size classes (those less than four times the quantum). (1B + 4 KiB) and (1B + 4 MiB) previously suffered nearly 50% internal fragmentation. + Chunk fragmentation tends to be lower because there are fewer distinct run sizes to pack. - Add support for explicit tcaches. The "tcache.create", "tcache.flush", and "tcache.destroy" mallctls control tcache lifetime and flushing, and the MALLOCX_TCACHE(tc) and MALLOCX_TCACHE_NONE flags to the *allocx() API control which tcache is used for each operation. - Implement per thread heap profiling, as well as the ability to enable/disable heap profiling on a per thread basis. Add the "prof.reset", "prof.lg_sample", "thread.prof.name", "thread.prof.active", "opt.prof_thread_active_init", "prof.thread_active_init", and "thread.prof.active" mallctls. - Add support for per arena application-specified chunk allocators, configured via the "arena..chunk_hooks" mallctl. - Refactor huge allocation to be managed by arenas, so that arenas now function as general purpose independent allocators. This is important in the context of user-specified chunk allocators, aside from the scalability benefits. Related new statistics: + The "stats.arenas..huge.allocated", "stats.arenas..huge.nmalloc", "stats.arenas..huge.ndalloc", and "stats.arenas..huge.nrequests" mallctls provide high level per arena huge allocation statistics. + The "arenas.nhchunks", "arenas.hchunk..size", "stats.arenas..hchunks..nmalloc", "stats.arenas..hchunks..ndalloc", "stats.arenas..hchunks..nrequests", and "stats.arenas..hchunks..curhchunks" mallctls provide per size class statistics. - Add the 'util' column to malloc_stats_print() output, which reports the proportion of available regions that are currently in use for each small size class. - Add "alloc" and "free" modes for for junk filling (see the "opt.junk" mallctl), so that it is possible to separately enable junk filling for allocation versus deallocation. - Add the jemalloc-config script, which provides information about how jemalloc was configured, and how to integrate it into application builds. - Add metadata statistics, which are accessible via the "stats.metadata", "stats.arenas..metadata.mapped", and "stats.arenas..metadata.allocated" mallctls. - Add the "stats.resident" mallctl, which reports the upper limit of physically resident memory mapped by the allocator. - Add per arena control over unused dirty page purging, via the "arenas.lg_dirty_mult", "arena..lg_dirty_mult", and "stats.arenas..lg_dirty_mult" mallctls. - Add the "prof.gdump" mallctl, which makes it possible to toggle the gdump feature on/off during program execution. - Add sdallocx(), which implements sized deallocation. The primary optimization over dallocx() is the removal of a metadata read, which often suffers an L1 cache miss. - Add missing header includes in jemalloc/jemalloc.h, so that applications only have to #include . - Add support for additional platforms: + Bitrig + Cygwin + DragonFlyBSD + iOS + OpenBSD + OpenRISC/or1k Optimizations: - Maintain dirty runs in per arena LRUs rather than in per arena trees of dirty-run-containing chunks. In practice this change significantly reduces dirty page purging volume. - Integrate whole chunks into the unused dirty page purging machinery. This reduces the cost of repeated huge allocation/deallocation, because it effectively introduces a cache of chunks. - Split the arena chunk map into two separate arrays, in order to increase cache locality for the frequently accessed bits. - Move small run metadata out of runs, into arena chunk headers. This reduces run fragmentation, smaller runs reduce external fragmentation for small size classes, and packed (less uniformly aligned) metadata layout improves CPU cache set distribution. - Randomly distribute large allocation base pointer alignment relative to page boundaries in order to more uniformly utilize CPU cache sets. This can be disabled via the --disable-cache-oblivious configure option, and queried via the "config.cache_oblivious" mallctl. - Micro-optimize the fast paths for the public API functions. - Refactor thread-specific data to reside in a single structure. This assures that only a single TLS read is necessary per call into the public API. - Implement in-place huge allocation growing and shrinking. - Refactor rtree (radix tree for chunk lookups) to be lock-free, and make additional optimizations that reduce maximum lookup depth to one or two levels. This resolves what was a concurrency bottleneck for per arena huge allocation, because a global data structure is critical for determining which arenas own which huge allocations. Incompatible changes: - Replace --enable-cc-silence with --disable-cc-silence to suppress spurious warnings by default. - Assure that the constness of malloc_usable_size()'s return type matches that of the system implementation. - Change the heap profile dump format to support per thread heap profiling, rename pprof to jeprof, and enhance it with the --thread= option. As a result, the bundled jeprof must now be used rather than the upstream (gperftools) pprof. - Disable "opt.prof_final" by default, in order to avoid atexit(3), which can internally deadlock on some platforms. - Change the "arenas.nlruns" mallctl type from size_t to unsigned. - Replace the "stats.arenas..bins..allocated" mallctl with "stats.arenas..bins..curregs". - Ignore MALLOC_CONF in set{uid,gid,cap} binaries. - Ignore MALLOCX_ARENA(a) in dallocx(), in favor of using the MALLOCX_TCACHE(tc) and MALLOCX_TCACHE_NONE flags to control tcache usage. Removed features: - Remove the *allocm() API, which is superseded by the *allocx() API. - Remove the --enable-dss options, and make dss non-optional on all platforms which support sbrk(2). - Remove the "arenas.purge" mallctl, which was obsoleted by the "arena..purge" mallctl in 3.1.0. - Remove the unnecessary "opt.valgrind" mallctl; jemalloc automatically detects whether it is running inside Valgrind. - Remove the "stats.huge.allocated", "stats.huge.nmalloc", and "stats.huge.ndalloc" mallctls. - Remove the --enable-mremap option. - Remove the "stats.chunks.current", "stats.chunks.total", and "stats.chunks.high" mallctls. Bug fixes: - Fix the cactive statistic to decrease (rather than increase) when active memory decreases. This regression was first released in 3.5.0. - Fix OOM handling in memalign() and valloc(). A variant of this bug existed in all releases since 2.0.0, which introduced these functions. - Fix an OOM-related regression in arena_tcache_fill_small(), which could cause cache corruption on OOM. This regression was present in all releases from 2.2.0 through 3.6.0. - Fix size class overflow handling for malloc(), posix_memalign(), memalign(), calloc(), and realloc() when profiling is enabled. - Fix the "arena..dss" mallctl to return an error if "primary" or "secondary" precedence is specified, but sbrk(2) is not supported. - Fix fallback lg_floor() implementations to handle extremely large inputs. - Ensure the default purgeable zone is after the default zone on OS X. - Fix latent bugs in atomic_*(). - Fix the "arena..dss" mallctl to handle read-only calls. - Fix tls_model configuration to enable the initial-exec model when possible. - Mark malloc_conf as a weak symbol so that the application can override it. - Correctly detect glibc's adaptive pthread mutexes. - Fix the --without-export configure option. * 3.6.0 (March 31, 2014) This version contains a critical bug fix for a regression present in 3.5.0 and 3.5.1. Bug fixes: - Fix a regression in arena_chunk_alloc() that caused crashes during small/large allocation if chunk allocation failed. In the absence of this bug, chunk allocation failure would result in allocation failure, e.g. NULL return from malloc(). This regression was introduced in 3.5.0. - Fix backtracing for gcc intrinsics-based backtracing by specifying -fno-omit-frame-pointer to gcc. Note that the application (and all the libraries it links to) must also be compiled with this option for backtracing to be reliable. - Use dss allocation precedence for huge allocations as well as small/large allocations. - Fix test assertion failure message formatting. This bug did not manifest on x86_64 systems because of implementation subtleties in va_list. - Fix inconsequential test failures for hash and SFMT code. New features: - Support heap profiling on FreeBSD. This feature depends on the proc filesystem being mounted during heap profile dumping. * 3.5.1 (February 25, 2014) This version primarily addresses minor bugs in test code. Bug fixes: - Configure Solaris/Illumos to use MADV_FREE. - Fix junk filling for mremap(2)-based huge reallocation. This is only relevant if configuring with the --enable-mremap option specified. - Avoid compilation failure if 'restrict' C99 keyword is not supported by the compiler. - Add a configure test for SSE2 rather than assuming it is usable on i686 systems. This fixes test compilation errors, especially on 32-bit Linux systems. - Fix mallctl argument size mismatches (size_t vs. uint64_t) in the stats unit test. - Fix/remove flawed alignment-related overflow tests. - Prevent compiler optimizations that could change backtraces in the prof_accum unit test. * 3.5.0 (January 22, 2014) This version focuses on refactoring and automated testing, though it also includes some non-trivial heap profiling optimizations not mentioned below. New features: - Add the *allocx() API, which is a successor to the experimental *allocm() API. The *allocx() functions are slightly simpler to use because they have fewer parameters, they directly return the results of primary interest, and mallocx()/rallocx() avoid the strict aliasing pitfall that allocm()/rallocm() share with posix_memalign(). Note that *allocm() is slated for removal in the next non-bugfix release. - Add support for LinuxThreads. Bug fixes: - Unless heap profiling is enabled, disable floating point code and don't link with libm. This, in combination with e.g. EXTRA_CFLAGS=-mno-sse on x64 systems, makes it possible to completely disable floating point register use. Some versions of glibc neglect to save/restore caller-saved floating point registers during dynamic lazy symbol loading, and the symbol loading code uses whatever malloc the application happens to have linked/loaded with, the result being potential floating point register corruption. - Report ENOMEM rather than EINVAL if an OOM occurs during heap profiling backtrace creation in imemalign(). This bug impacted posix_memalign() and aligned_alloc(). - Fix a file descriptor leak in a prof_dump_maps() error path. - Fix prof_dump() to close the dump file descriptor for all relevant error paths. - Fix rallocm() to use the arena specified by the ALLOCM_ARENA(s) flag for allocation, not just deallocation. - Fix a data race for large allocation stats counters. - Fix a potential infinite loop during thread exit. This bug occurred on Solaris, and could affect other platforms with similar pthreads TSD implementations. - Don't junk-fill reallocations unless usable size changes. This fixes a violation of the *allocx()/*allocm() semantics. - Fix growing large reallocation to junk fill new space. - Fix huge deallocation to junk fill when munmap is disabled. - Change the default private namespace prefix from empty to je_, and change --with-private-namespace-prefix so that it prepends an additional prefix rather than replacing je_. This reduces the likelihood of applications which statically link jemalloc experiencing symbol name collisions. - Add missing private namespace mangling (relevant when --with-private-namespace is specified). - Add and use JEMALLOC_INLINE_C so that static inline functions are marked as static even for debug builds. - Add a missing mutex unlock in a malloc_init_hard() error path. In practice this error path is never executed. - Fix numerous bugs in malloc_strotumax() error handling/reporting. These bugs had no impact except for malformed inputs. - Fix numerous bugs in malloc_snprintf(). These bugs were not exercised by existing calls, so they had no impact. * 3.4.1 (October 20, 2013) Bug fixes: - Fix a race in the "arenas.extend" mallctl that could cause memory corruption of internal data structures and subsequent crashes. - Fix Valgrind integration flaws that caused Valgrind warnings about reads of uninitialized memory in: + arena chunk headers + internal zero-initialized data structures (relevant to tcache and prof code) - Preserve errno during the first allocation. A readlink(2) call during initialization fails unless /etc/malloc.conf exists, so errno was typically set during the first allocation prior to this fix. - Fix compilation warnings reported by gcc 4.8.1. * 3.4.0 (June 2, 2013) This version is essentially a small bugfix release, but the addition of aarch64 support requires that the minor version be incremented. Bug fixes: - Fix race-triggered deadlocks in chunk_record(). These deadlocks were typically triggered by multiple threads concurrently deallocating huge objects. New features: - Add support for the aarch64 architecture. * 3.3.1 (March 6, 2013) This version fixes bugs that are typically encountered only when utilizing custom run-time options. Bug fixes: - Fix a locking order bug that could cause deadlock during fork if heap profiling were enabled. - Fix a chunk recycling bug that could cause the allocator to lose track of whether a chunk was zeroed. On FreeBSD, NetBSD, and OS X, it could cause corruption if allocating via sbrk(2) (unlikely unless running with the "dss:primary" option specified). This was completely harmless on Linux unless using mlockall(2) (and unlikely even then, unless the --disable-munmap configure option or the "dss:primary" option was specified). This regression was introduced in 3.1.0 by the mlockall(2)/madvise(2) interaction fix. - Fix TLS-related memory corruption that could occur during thread exit if the thread never allocated memory. Only the quarantine and prof facilities were susceptible. - Fix two quarantine bugs: + Internal reallocation of the quarantined object array leaked the old array. + Reallocation failure for internal reallocation of the quarantined object array (very unlikely) resulted in memory corruption. - Fix Valgrind integration to annotate all internally allocated memory in a way that keeps Valgrind happy about internal data structure access. - Fix building for s390 systems. * 3.3.0 (January 23, 2013) This version includes a few minor performance improvements in addition to the listed new features and bug fixes. New features: - Add clipping support to lg_chunk option processing. - Add the --enable-ivsalloc option. - Add the --without-export option. - Add the --disable-zone-allocator option. Bug fixes: - Fix "arenas.extend" mallctl to output the number of arenas. - Fix chunk_recycle() to unconditionally inform Valgrind that returned memory is undefined. - Fix build break on FreeBSD related to alloca.h. * 3.2.0 (November 9, 2012) In addition to a couple of bug fixes, this version modifies page run allocation and dirty page purging algorithms in order to better control page-level virtual memory fragmentation. Incompatible changes: - Change the "opt.lg_dirty_mult" default from 5 to 3 (32:1 to 8:1). Bug fixes: - Fix dss/mmap allocation precedence code to use recyclable mmap memory only after primary dss allocation fails. - Fix deadlock in the "arenas.purge" mallctl. This regression was introduced in 3.1.0 by the addition of the "arena..purge" mallctl. * 3.1.0 (October 16, 2012) New features: - Auto-detect whether running inside Valgrind, thus removing the need to manually specify MALLOC_CONF=valgrind:true. - Add the "arenas.extend" mallctl, which allows applications to create manually managed arenas. - Add the ALLOCM_ARENA() flag for {,r,d}allocm(). - Add the "opt.dss", "arena..dss", and "stats.arenas..dss" mallctls, which provide control over dss/mmap precedence. - Add the "arena..purge" mallctl, which obsoletes "arenas.purge". - Define LG_QUANTUM for hppa. Incompatible changes: - Disable tcache by default if running inside Valgrind, in order to avoid making unallocated objects appear reachable to Valgrind. - Drop const from malloc_usable_size() argument on Linux. Bug fixes: - Fix heap profiling crash if sampled object is freed via realloc(p, 0). - Remove const from __*_hook variable declarations, so that glibc can modify them during process forking. - Fix mlockall(2)/madvise(2) interaction. - Fix fork(2)-related deadlocks. - Fix error return value for "thread.tcache.enabled" mallctl. * 3.0.0 (May 11, 2012) Although this version adds some major new features, the primary focus is on internal code cleanup that facilitates maintainability and portability, most of which is not reflected in the ChangeLog. This is the first release to incorporate substantial contributions from numerous other developers, and the result is a more broadly useful allocator (see the git revision history for contribution details). Note that the license has been unified, thanks to Facebook granting a license under the same terms as the other copyright holders (see COPYING). New features: - Implement Valgrind support, redzones, and quarantine. - Add support for additional platforms: + FreeBSD + Mac OS X Lion + MinGW + Windows (no support yet for replacing the system malloc) - Add support for additional architectures: + MIPS + SH4 + Tilera - Add support for cross compiling. - Add nallocm(), which rounds a request size up to the nearest size class without actually allocating. - Implement aligned_alloc() (blame C11). - Add the "thread.tcache.enabled" mallctl. - Add the "opt.prof_final" mallctl. - Update pprof (from gperftools 2.0). - Add the --with-mangling option. - Add the --disable-experimental option. - Add the --disable-munmap option, and make it the default on Linux. - Add the --enable-mremap option, which disables use of mremap(2) by default. Incompatible changes: - Enable stats by default. - Enable fill by default. - Disable lazy locking by default. - Rename the "tcache.flush" mallctl to "thread.tcache.flush". - Rename the "arenas.pagesize" mallctl to "arenas.page". - Change the "opt.lg_prof_sample" default from 0 to 19 (1 B to 512 KiB). - Change the "opt.prof_accum" default from true to false. Removed features: - Remove the swap feature, including the "config.swap", "swap.avail", "swap.prezeroed", "swap.nfds", and "swap.fds" mallctls. - Remove highruns statistics, including the "stats.arenas..bins..highruns" and "stats.arenas..lruns..highruns" mallctls. - As part of small size class refactoring, remove the "opt.lg_[qc]space_max", "arenas.cacheline", "arenas.subpage", "arenas.[tqcs]space_{min,max}", and "arenas.[tqcs]bins" mallctls. - Remove the "arenas.chunksize" mallctl. - Remove the "opt.lg_prof_tcmax" option. - Remove the "opt.lg_prof_bt_max" option. - Remove the "opt.lg_tcache_gc_sweep" option. - Remove the --disable-tiny option, including the "config.tiny" mallctl. - Remove the --enable-dynamic-page-shift configure option. - Remove the --enable-sysv configure option. Bug fixes: - Fix a statistics-related bug in the "thread.arena" mallctl that could cause invalid statistics and crashes. - Work around TLS deallocation via free() on Linux. This bug could cause write-after-free memory corruption. - Fix a potential deadlock that could occur during interval- and growth-triggered heap profile dumps. - Fix large calloc() zeroing bugs due to dropping chunk map unzeroed flags. - Fix chunk_alloc_dss() to stop claiming memory is zeroed. This bug could cause memory corruption and crashes with --enable-dss specified. - Fix fork-related bugs that could cause deadlock in children between fork and exec. - Fix malloc_stats_print() to honor 'b' and 'l' in the opts parameter. - Fix realloc(p, 0) to act like free(p). - Do not enforce minimum alignment in memalign(). - Check for NULL pointer in malloc_usable_size(). - Fix an off-by-one heap profile statistics bug that could be observed in interval- and growth-triggered heap profiles. - Fix the "epoch" mallctl to update cached stats even if the passed in epoch is 0. - Fix bin->runcur management to fix a layout policy bug. This bug did not affect correctness. - Fix a bug in choose_arena_hard() that potentially caused more arenas to be initialized than necessary. - Add missing "opt.lg_tcache_max" mallctl implementation. - Use glibc allocator hooks to make mixed allocator usage less likely. - Fix build issues for --disable-tcache. - Don't mangle pthread_create() when --with-private-namespace is specified. * 2.2.5 (November 14, 2011) Bug fixes: - Fix huge_ralloc() race when using mremap(2). This is a serious bug that could cause memory corruption and/or crashes. - Fix huge_ralloc() to maintain chunk statistics. - Fix malloc_stats_print(..., "a") output. * 2.2.4 (November 5, 2011) Bug fixes: - Initialize arenas_tsd before using it. This bug existed for 2.2.[0-3], as well as for --disable-tls builds in earlier releases. - Do not assume a 4 KiB page size in test/rallocm.c. * 2.2.3 (August 31, 2011) This version fixes numerous bugs related to heap profiling. Bug fixes: - Fix a prof-related race condition. This bug could cause memory corruption, but only occurred in non-default configurations (prof_accum:false). - Fix off-by-one backtracing issues (make sure that prof_alloc_prep() is excluded from backtraces). - Fix a prof-related bug in realloc() (only triggered by OOM errors). - Fix prof-related bugs in allocm() and rallocm(). - Fix prof_tdata_cleanup() for --disable-tls builds. - Fix a relative include path, to fix objdir builds. * 2.2.2 (July 30, 2011) Bug fixes: - Fix a build error for --disable-tcache. - Fix assertions in arena_purge() (for real this time). - Add the --with-private-namespace option. This is a workaround for symbol conflicts that can inadvertently arise when using static libraries. * 2.2.1 (March 30, 2011) Bug fixes: - Implement atomic operations for x86/x64. This fixes compilation failures for versions of gcc that are still in wide use. - Fix an assertion in arena_purge(). * 2.2.0 (March 22, 2011) This version incorporates several improvements to algorithms and data structures that tend to reduce fragmentation and increase speed. New features: - Add the "stats.cactive" mallctl. - Update pprof (from google-perftools 1.7). - Improve backtracing-related configuration logic, and add the --disable-prof-libgcc option. Bug fixes: - Change default symbol visibility from "internal", to "hidden", which decreases the overhead of library-internal function calls. - Fix symbol visibility so that it is also set on OS X. - Fix a build dependency regression caused by the introduction of the .pic.o suffix for PIC object files. - Add missing checks for mutex initialization failures. - Don't use libgcc-based backtracing except on x64, where it is known to work. - Fix deadlocks on OS X that were due to memory allocation in pthread_mutex_lock(). - Heap profiling-specific fixes: + Fix memory corruption due to integer overflow in small region index computation, when using a small enough sample interval that profiling context pointers are stored in small run headers. + Fix a bootstrap ordering bug that only occurred with TLS disabled. + Fix a rallocm() rsize bug. + Fix error detection bugs for aligned memory allocation. * 2.1.3 (March 14, 2011) Bug fixes: - Fix a cpp logic regression (due to the "thread.{de,}allocatedp" mallctl fix for OS X in 2.1.2). - Fix a "thread.arena" mallctl bug. - Fix a thread cache stats merging bug. * 2.1.2 (March 2, 2011) Bug fixes: - Fix "thread.{de,}allocatedp" mallctl for OS X. - Add missing jemalloc.a to build system. * 2.1.1 (January 31, 2011) Bug fixes: - Fix aligned huge reallocation (affected allocm()). - Fix the ALLOCM_LG_ALIGN macro definition. - Fix a heap dumping deadlock. - Fix a "thread.arena" mallctl bug. * 2.1.0 (December 3, 2010) This version incorporates some optimizations that can't quite be considered bug fixes. New features: - Use Linux's mremap(2) for huge object reallocation when possible. - Avoid locking in mallctl*() when possible. - Add the "thread.[de]allocatedp" mallctl's. - Convert the manual page source from roff to DocBook, and generate both roff and HTML manuals. Bug fixes: - Fix a crash due to incorrect bootstrap ordering. This only impacted --enable-debug --enable-dss configurations. - Fix a minor statistics bug for mallctl("swap.avail", ...). * 2.0.1 (October 29, 2010) Bug fixes: - Fix a race condition in heap profiling that could cause undefined behavior if "opt.prof_accum" were disabled. - Add missing mutex unlocks for some OOM error paths in the heap profiling code. - Fix a compilation error for non-C99 builds. * 2.0.0 (October 24, 2010) This version focuses on the experimental *allocm() API, and on improved run-time configuration/introspection. Nonetheless, numerous performance improvements are also included. New features: - Implement the experimental {,r,s,d}allocm() API, which provides a superset of the functionality available via malloc(), calloc(), posix_memalign(), realloc(), malloc_usable_size(), and free(). These functions can be used to allocate/reallocate aligned zeroed memory, ask for optional extra memory during reallocation, prevent object movement during reallocation, etc. - Replace JEMALLOC_OPTIONS/JEMALLOC_PROF_PREFIX with MALLOC_CONF, which is more human-readable, and more flexible. For example: JEMALLOC_OPTIONS=AJP is now: MALLOC_CONF=abort:true,fill:true,stats_print:true - Port to Apple OS X. Sponsored by Mozilla. - Make it possible for the application to control thread-->arena mappings via the "thread.arena" mallctl. - Add compile-time support for all TLS-related functionality via pthreads TSD. This is mainly of interest for OS X, which does not support TLS, but has a TSD implementation with similar performance. - Override memalign() and valloc() if they are provided by the system. - Add the "arenas.purge" mallctl, which can be used to synchronously purge all dirty unused pages. - Make cumulative heap profiling data optional, so that it is possible to limit the amount of memory consumed by heap profiling data structures. - Add per thread allocation counters that can be accessed via the "thread.allocated" and "thread.deallocated" mallctls. Incompatible changes: - Remove JEMALLOC_OPTIONS and malloc_options (see MALLOC_CONF above). - Increase default backtrace depth from 4 to 128 for heap profiling. - Disable interval-based profile dumps by default. Bug fixes: - Remove bad assertions in fork handler functions. These assertions could cause aborts for some combinations of configure settings. - Fix strerror_r() usage to deal with non-standard semantics in GNU libc. - Fix leak context reporting. This bug tended to cause the number of contexts to be underreported (though the reported number of objects and bytes were correct). - Fix a realloc() bug for large in-place growing reallocation. This bug could cause memory corruption, but it was hard to trigger. - Fix an allocation bug for small allocations that could be triggered if multiple threads raced to create a new run of backing pages. - Enhance the heap profiler to trigger samples based on usable size, rather than request size. - Fix a heap profiling bug due to sometimes losing track of requested object size for sampled objects. * 1.0.3 (August 12, 2010) Bug fixes: - Fix the libunwind-based implementation of stack backtracing (used for heap profiling). This bug could cause zero-length backtraces to be reported. - Add a missing mutex unlock in library initialization code. If multiple threads raced to initialize malloc, some of them could end up permanently blocked. * 1.0.2 (May 11, 2010) Bug fixes: - Fix junk filling of large objects, which could cause memory corruption. - Add MAP_NORESERVE support for chunk mapping, because otherwise virtual memory limits could cause swap file configuration to fail. Contributed by Jordan DeLong. * 1.0.1 (April 14, 2010) Bug fixes: - Fix compilation when --enable-fill is specified. - Fix threads-related profiling bugs that affected accuracy and caused memory to be leaked during thread exit. - Fix dirty page purging race conditions that could cause crashes. - Fix crash in tcache flushing code during thread destruction. * 1.0.0 (April 11, 2010) This release focuses on speed and run-time introspection. Numerous algorithmic improvements make this release substantially faster than its predecessors. New features: - Implement autoconf-based configuration system. - Add mallctl*(), for the purposes of introspection and run-time configuration. - Make it possible for the application to manually flush a thread's cache, via the "tcache.flush" mallctl. - Base maximum dirty page count on proportion of active memory. - Compute various additional run-time statistics, including per size class statistics for large objects. - Expose malloc_stats_print(), which can be called repeatedly by the application. - Simplify the malloc_message() signature to only take one string argument, and incorporate an opaque data pointer argument for use by the application in combination with malloc_stats_print(). - Add support for allocation backed by one or more swap files, and allow the application to disable over-commit if swap files are in use. - Implement allocation profiling and leak checking. Removed features: - Remove the dynamic arena rebalancing code, since thread-specific caching reduces its utility. Bug fixes: - Modify chunk allocation to work when address space layout randomization (ASLR) is in use. - Fix thread cleanup bugs related to TLS destruction. - Handle 0-size allocation requests in posix_memalign(). - Fix a chunk leak. The leaked chunks were never touched, so this impacted virtual memory usage, but not physical memory usage. * linux_2008082[78]a (August 27/28, 2008) These snapshot releases are the simple result of incorporating Linux-specific support into the FreeBSD malloc sources. -------------------------------------------------------------------------------- vim:filetype=text:textwidth=80 Index: head/contrib/jemalloc/FREEBSD-Xlist =================================================================== --- head/contrib/jemalloc/FREEBSD-Xlist (revision 360232) +++ head/contrib/jemalloc/FREEBSD-Xlist (revision 360233) @@ -1,59 +1,60 @@ $FreeBSD$ .appveyor.yml .autom4te.cfg +.cirrus.yml .git* .travis.yml FREEBSD-* INSTALL.md Makefile* README TUNING.md autogen.sh autom4te.cache/ bin/ build-aux/ config.* configure* doc/*.in doc/*.xml doc/*.xsl doc/*.html include/jemalloc/internal/atomic_msvc.h include/jemalloc/internal/jemalloc_internal_defs.h.in include/jemalloc/internal/jemalloc_preamble.h.in include/jemalloc/internal/private_namespace.sh include/jemalloc/internal/private_symbols_jet.awk include/jemalloc/internal/private_symbols.awk include/jemalloc/internal/private_symbols.sh include/jemalloc/internal/public_namespace.sh include/jemalloc/internal/public_symbols.txt include/jemalloc/internal/public_unnamespace.h include/jemalloc/internal/public_unnamespace.sh include/jemalloc/internal/size_classes.sh include/jemalloc/internal/smoothstep.sh include/jemalloc/internal/tsd_win.h include/jemalloc/jemalloc.h.in include/jemalloc/jemalloc.sh include/jemalloc/jemalloc_defs.h include/jemalloc/jemalloc_defs.h.in include/jemalloc/jemalloc_macros.h include/jemalloc/jemalloc_macros.h.in include/jemalloc/jemalloc_mangle_jet.h include/jemalloc/jemalloc_mangle.sh include/jemalloc/jemalloc_mangle.h include/jemalloc/jemalloc_protos_jet.h include/jemalloc/jemalloc_protos.h include/jemalloc/jemalloc_protos.h.in include/jemalloc/jemalloc_rename.h include/jemalloc/jemalloc_rename.sh include/jemalloc/jemalloc_typedefs.h.in include/msvc_compat/ install-sh jemalloc.pc* m4/ msvc/ run_tests.sh scripts/ src/jemalloc_cpp.cpp src/zone.c test/ Index: head/contrib/jemalloc/FREEBSD-diffs =================================================================== --- head/contrib/jemalloc/FREEBSD-diffs (revision 360232) +++ head/contrib/jemalloc/FREEBSD-diffs (revision 360233) @@ -1,541 +1,582 @@ diff --git a/doc/jemalloc.xml.in b/doc/jemalloc.xml.in -index 1e12fd3a..c42a7e10 100644 +index 7fecda7c..d5ca5e86 100644 --- a/doc/jemalloc.xml.in +++ b/doc/jemalloc.xml.in @@ -53,11 +53,22 @@ This manual describes jemalloc @jemalloc_version@. More information can be found at the jemalloc website. + + The following configuration options are enabled in libc's built-in + jemalloc: , + , , + , , and + . + Additionally, is enabled in development + versions of FreeBSD (controlled by the + MALLOC_PRODUCTION make variable). + SYNOPSIS - #include <jemalloc/jemalloc.h> + #include <stdlib.h> +#include <malloc_np.h> Standard API -@@ -3376,4 +3387,18 @@ malloc_conf = "narenas:1";]]> +@@ -3510,4 +3521,18 @@ malloc_conf = "narenas:1";]]> The posix_memalign() function conforms to IEEE Std 1003.1-2001 (POSIX.1). + + HISTORY + The malloc_usable_size() and + posix_memalign() functions first appeared in FreeBSD + 7.0. + + The aligned_alloc(), + malloc_stats_print(), and + mallctl*() functions first appeared in FreeBSD + 10.0. + + The *allocx() functions first appeared in FreeBSD + 11.0. + -diff --git a/include/jemalloc/internal/hooks.h b/include/jemalloc/internal/hooks.h -index cd49afcb..85e2a991 100644 ---- a/include/jemalloc/internal/hooks.h -+++ b/include/jemalloc/internal/hooks.h -@@ -6,13 +6,6 @@ extern JEMALLOC_EXPORT void (*hooks_libc_hook)(); - - #define JEMALLOC_HOOK(fn, hook) ((void)(hook != NULL && (hook(), 0)), fn) - --#define open JEMALLOC_HOOK(open, hooks_libc_hook) --#define read JEMALLOC_HOOK(read, hooks_libc_hook) --#define write JEMALLOC_HOOK(write, hooks_libc_hook) --#define readlink JEMALLOC_HOOK(readlink, hooks_libc_hook) --#define close JEMALLOC_HOOK(close, hooks_libc_hook) --#define creat JEMALLOC_HOOK(creat, hooks_libc_hook) --#define secure_getenv JEMALLOC_HOOK(secure_getenv, hooks_libc_hook) - /* Note that this is undef'd and re-define'd in src/prof.c. */ - #define _Unwind_Backtrace JEMALLOC_HOOK(_Unwind_Backtrace, hooks_libc_hook) - diff --git a/include/jemalloc/internal/jemalloc_internal_decls.h b/include/jemalloc/internal/jemalloc_internal_decls.h -index be70df51..84cd70da 100644 +index 7d6053e2..a0e4f5af 100644 --- a/include/jemalloc/internal/jemalloc_internal_decls.h +++ b/include/jemalloc/internal/jemalloc_internal_decls.h @@ -1,6 +1,9 @@ #ifndef JEMALLOC_INTERNAL_DECLS_H #define JEMALLOC_INTERNAL_DECLS_H +#include "libc_private.h" +#include "namespace.h" + #include #ifdef _WIN32 # include +diff --git a/include/jemalloc/internal/jemalloc_internal_defs_FreeBSD.h b/include/jemalloc/internal/jemalloc_internal_defs_FreeBSD.h +new file mode 100644 +index 00000000..0dab1296 +--- /dev/null ++++ b/include/jemalloc/internal/jemalloc_internal_defs_FreeBSD.h +@@ -0,0 +1,9 @@ ++#ifndef __clang__ ++# undef JEMALLOC_INTERNAL_UNREACHABLE ++# define JEMALLOC_INTERNAL_UNREACHABLE abort ++ ++# undef JEMALLOC_C11_ATOMICS ++# undef JEMALLOC_GCC_ATOMIC_ATOMICS ++# undef JEMALLOC_GCC_U8_ATOMIC_ATOMICS ++# undef JEMALLOC_GCC_U8_SYNC_ATOMICS ++#endif diff --git a/include/jemalloc/internal/jemalloc_preamble.h.in b/include/jemalloc/internal/jemalloc_preamble.h.in -index e621fbc8..dbdd5d6b 100644 +index 3418cbfa..53e30dc4 100644 --- a/include/jemalloc/internal/jemalloc_preamble.h.in +++ b/include/jemalloc/internal/jemalloc_preamble.h.in @@ -8,6 +8,9 @@ #include #endif +#include "un-namespace.h" +#include "libc_private.h" + #define JEMALLOC_NO_DEMANGLE #ifdef JEMALLOC_JET # undef JEMALLOC_IS_MALLOC @@ -79,13 +82,7 @@ static const bool config_fill = false #endif ; -static const bool config_lazy_lock = -#ifdef JEMALLOC_LAZY_LOCK - true -#else - false -#endif - ; +static const bool config_lazy_lock = true; static const char * const config_malloc_conf = JEMALLOC_CONFIG_MALLOC_CONF; static const bool config_prof = #ifdef JEMALLOC_PROF diff --git a/include/jemalloc/internal/mutex.h b/include/jemalloc/internal/mutex.h -index 6520c251..0013cbe9 100644 +index 7c24f072..94af1618 100644 --- a/include/jemalloc/internal/mutex.h +++ b/include/jemalloc/internal/mutex.h -@@ -121,9 +121,6 @@ struct malloc_mutex_s { +@@ -135,9 +135,6 @@ struct malloc_mutex_s { #ifdef JEMALLOC_LAZY_LOCK extern bool isthreaded; -#else -# undef isthreaded /* Undo private_namespace.h definition. */ -# define isthreaded true #endif bool malloc_mutex_init(malloc_mutex_t *mutex, const char *name, -@@ -131,6 +128,7 @@ bool malloc_mutex_init(malloc_mutex_t *mutex, const char *name, +@@ -145,6 +142,7 @@ bool malloc_mutex_init(malloc_mutex_t *mutex, const char *name, void malloc_mutex_prefork(tsdn_t *tsdn, malloc_mutex_t *mutex); void malloc_mutex_postfork_parent(tsdn_t *tsdn, malloc_mutex_t *mutex); void malloc_mutex_postfork_child(tsdn_t *tsdn, malloc_mutex_t *mutex); +bool malloc_mutex_first_thread(void); bool malloc_mutex_boot(void); void malloc_mutex_prof_data_reset(tsdn_t *tsdn, malloc_mutex_t *mutex); +diff --git a/include/jemalloc/internal/test_hooks.h b/include/jemalloc/internal/test_hooks.h +index a6351e59..0780c52f 100644 +--- a/include/jemalloc/internal/test_hooks.h ++++ b/include/jemalloc/internal/test_hooks.h +@@ -6,13 +6,6 @@ extern JEMALLOC_EXPORT void (*test_hooks_libc_hook)(); + + #define JEMALLOC_HOOK(fn, hook) ((void)(hook != NULL && (hook(), 0)), fn) + +-#define open JEMALLOC_HOOK(open, test_hooks_libc_hook) +-#define read JEMALLOC_HOOK(read, test_hooks_libc_hook) +-#define write JEMALLOC_HOOK(write, test_hooks_libc_hook) +-#define readlink JEMALLOC_HOOK(readlink, test_hooks_libc_hook) +-#define close JEMALLOC_HOOK(close, test_hooks_libc_hook) +-#define creat JEMALLOC_HOOK(creat, test_hooks_libc_hook) +-#define secure_getenv JEMALLOC_HOOK(secure_getenv, test_hooks_libc_hook) + /* Note that this is undef'd and re-define'd in src/prof.c. */ + #define _Unwind_Backtrace JEMALLOC_HOOK(_Unwind_Backtrace, test_hooks_libc_hook) + diff --git a/include/jemalloc/internal/tsd.h b/include/jemalloc/internal/tsd.h -index 0b9841aa..f03eee61 100644 +index 9ba26004..ecfda5d6 100644 --- a/include/jemalloc/internal/tsd.h +++ b/include/jemalloc/internal/tsd.h -@@ -122,7 +122,8 @@ struct tsd_s { - t use_a_getter_or_setter_instead_##n; +@@ -198,7 +198,8 @@ struct tsd_s { + t TSD_MANGLE(n); MALLOC_TSD #undef O -}; +/* AddressSanitizer requires TLS data to be aligned to at least 8 bytes. */ +} JEMALLOC_ALIGNED(16); - /* - * Wrapper around tsd_t that makes it possible to avoid implicit conversion + JEMALLOC_ALWAYS_INLINE uint8_t + tsd_state_get(tsd_t *tsd) { diff --git a/include/jemalloc/jemalloc_FreeBSD.h b/include/jemalloc/jemalloc_FreeBSD.h new file mode 100644 index 00000000..b752b0e7 --- /dev/null +++ b/include/jemalloc/jemalloc_FreeBSD.h @@ -0,0 +1,185 @@ +/* + * Override settings that were generated in jemalloc_defs.h as necessary. + */ + +#undef JEMALLOC_OVERRIDE_VALLOC + +#ifndef MALLOC_PRODUCTION +#define JEMALLOC_DEBUG +#endif + +#undef JEMALLOC_DSS + +#undef JEMALLOC_BACKGROUND_THREAD + +/* + * The following are architecture-dependent, so conditionally define them for + * each supported architecture. + */ +#undef JEMALLOC_TLS_MODEL +#undef LG_PAGE +#undef LG_VADDR +#undef LG_SIZEOF_PTR +#undef LG_SIZEOF_INT +#undef LG_SIZEOF_LONG +#undef LG_SIZEOF_INTMAX_T + +#ifdef __i386__ +# define LG_VADDR 32 +# define LG_SIZEOF_PTR 2 +# define JEMALLOC_TLS_MODEL __attribute__((tls_model("initial-exec"))) +#endif +#ifdef __ia64__ +# define LG_VADDR 64 +# define LG_SIZEOF_PTR 3 +#endif +#ifdef __sparc64__ +# define LG_VADDR 64 +# define LG_SIZEOF_PTR 3 +# define JEMALLOC_TLS_MODEL __attribute__((tls_model("initial-exec"))) +#endif +#ifdef __amd64__ +# define LG_VADDR 48 +# define LG_SIZEOF_PTR 3 +# define JEMALLOC_TLS_MODEL __attribute__((tls_model("initial-exec"))) +#endif +#ifdef __arm__ +# define LG_VADDR 32 +# define LG_SIZEOF_PTR 2 +#endif +#ifdef __aarch64__ +# define LG_VADDR 48 +# define LG_SIZEOF_PTR 3 +#endif +#ifdef __mips__ +#ifdef __mips_n64 +# define LG_VADDR 64 +# define LG_SIZEOF_PTR 3 +#else +# define LG_VADDR 32 +# define LG_SIZEOF_PTR 2 +#endif +#endif +#ifdef __powerpc64__ +# define LG_VADDR 64 +# define LG_SIZEOF_PTR 3 +#elif defined(__powerpc__) +# define LG_VADDR 32 +# define LG_SIZEOF_PTR 2 +#endif +#ifdef __riscv +# define LG_VADDR 64 +# define LG_SIZEOF_PTR 3 +#endif + +#ifndef JEMALLOC_TLS_MODEL +# define JEMALLOC_TLS_MODEL /* Default. */ +#endif + +#define LG_PAGE PAGE_SHIFT +#define LG_SIZEOF_INT 2 +#define LG_SIZEOF_LONG LG_SIZEOF_PTR +#define LG_SIZEOF_INTMAX_T 3 + +#undef CPU_SPINWAIT +#include +#include +#define CPU_SPINWAIT cpu_spinwait() + +/* Disable lazy-lock machinery, mangle isthreaded, and adjust its type. */ +#undef JEMALLOC_LAZY_LOCK +extern int __isthreaded; +#define isthreaded ((bool)__isthreaded) + +/* Mangle. */ +#undef je_malloc +#undef je_calloc +#undef je_posix_memalign +#undef je_aligned_alloc +#undef je_realloc +#undef je_free +#undef je_malloc_usable_size +#undef je_mallocx +#undef je_rallocx +#undef je_xallocx +#undef je_sallocx +#undef je_dallocx +#undef je_sdallocx +#undef je_nallocx +#undef je_mallctl +#undef je_mallctlnametomib +#undef je_mallctlbymib +#undef je_malloc_stats_print +#undef je_allocm +#undef je_rallocm +#undef je_sallocm +#undef je_dallocm +#undef je_nallocm +#define je_malloc __malloc +#define je_calloc __calloc +#define je_posix_memalign __posix_memalign +#define je_aligned_alloc __aligned_alloc +#define je_realloc __realloc +#define je_free __free +#define je_malloc_usable_size __malloc_usable_size +#define je_mallocx __mallocx +#define je_rallocx __rallocx +#define je_xallocx __xallocx +#define je_sallocx __sallocx +#define je_dallocx __dallocx +#define je_sdallocx __sdallocx +#define je_nallocx __nallocx +#define je_mallctl __mallctl +#define je_mallctlnametomib __mallctlnametomib +#define je_mallctlbymib __mallctlbymib +#define je_malloc_stats_print __malloc_stats_print +#define je_allocm __allocm +#define je_rallocm __rallocm +#define je_sallocm __sallocm +#define je_dallocm __dallocm +#define je_nallocm __nallocm +#define open _open +#define read _read +#define write _write +#define close _close +#define pthread_join _pthread_join +#define pthread_once _pthread_once +#define pthread_self _pthread_self +#define pthread_equal _pthread_equal +#define pthread_mutex_lock _pthread_mutex_lock +#define pthread_mutex_trylock _pthread_mutex_trylock +#define pthread_mutex_unlock _pthread_mutex_unlock +#define pthread_cond_init _pthread_cond_init +#define pthread_cond_wait _pthread_cond_wait +#define pthread_cond_timedwait _pthread_cond_timedwait +#define pthread_cond_signal _pthread_cond_signal + +#ifdef JEMALLOC_C_ +/* + * Define 'weak' symbols so that an application can have its own versions + * of malloc, calloc, realloc, free, et al. + */ +__weak_reference(__malloc, malloc); +__weak_reference(__calloc, calloc); +__weak_reference(__posix_memalign, posix_memalign); +__weak_reference(__aligned_alloc, aligned_alloc); +__weak_reference(__realloc, realloc); +__weak_reference(__free, free); +__weak_reference(__malloc_usable_size, malloc_usable_size); +__weak_reference(__mallocx, mallocx); +__weak_reference(__rallocx, rallocx); +__weak_reference(__xallocx, xallocx); +__weak_reference(__sallocx, sallocx); +__weak_reference(__dallocx, dallocx); +__weak_reference(__sdallocx, sdallocx); +__weak_reference(__nallocx, nallocx); +__weak_reference(__mallctl, mallctl); +__weak_reference(__mallctlnametomib, mallctlnametomib); +__weak_reference(__mallctlbymib, mallctlbymib); +__weak_reference(__malloc_stats_print, malloc_stats_print); +__weak_reference(__allocm, allocm); +__weak_reference(__rallocm, rallocm); +__weak_reference(__sallocm, sallocm); +__weak_reference(__dallocm, dallocm); +__weak_reference(__nallocm, nallocm); +#endif diff --git a/include/jemalloc/jemalloc_rename.sh b/include/jemalloc/jemalloc_rename.sh index f9438912..47d032c1 100755 --- a/include/jemalloc/jemalloc_rename.sh +++ b/include/jemalloc/jemalloc_rename.sh @@ -19,4 +19,6 @@ done cat <: */ +const char *__malloc_options_1_0 = NULL; +__sym_compat(_malloc_options, __malloc_options_1_0, FBSD_1.0); + /* Runtime configuration options. */ const char *je_malloc_conf #ifndef _WIN32 -@@ -3160,6 +3164,103 @@ je_malloc_usable_size(JEMALLOC_USABLE_SIZE_CONST void *ptr) { +@@ -2660,25 +2664,6 @@ je_realloc(void *ptr, size_t arg_size) { + LOG("core.realloc.entry", "ptr: %p, size: %zu\n", ptr, size); + + if (unlikely(size == 0)) { +- if (ptr != NULL) { +- /* realloc(ptr, 0) is equivalent to free(ptr). */ +- UTRACE(ptr, 0, 0); +- tcache_t *tcache; +- tsd_t *tsd = tsd_fetch(); +- if (tsd_reentrancy_level_get(tsd) == 0) { +- tcache = tcache_get(tsd); +- } else { +- tcache = NULL; +- } +- +- uintptr_t args[3] = {(uintptr_t)ptr, size}; +- hook_invoke_dalloc(hook_dalloc_realloc, ptr, args); +- +- ifree(tsd, ptr, tcache, true); +- +- LOG("core.realloc.exit", "result: %p", NULL); +- return NULL; +- } + size = 1; + } + +@@ -3750,6 +3735,103 @@ je_malloc_usable_size(JEMALLOC_USABLE_SIZE_CONST void *ptr) { + * End non-standard functions. */ /******************************************************************************/ - /* ++/* + * Begin compatibility functions. + */ + +#define ALLOCM_LG_ALIGN(la) (la) +#define ALLOCM_ALIGN(a) (ffsl(a)-1) +#define ALLOCM_ZERO ((int)0x40) +#define ALLOCM_NO_MOVE ((int)0x80) + +#define ALLOCM_SUCCESS 0 +#define ALLOCM_ERR_OOM 1 +#define ALLOCM_ERR_NOT_MOVED 2 + +int +je_allocm(void **ptr, size_t *rsize, size_t size, int flags) { + assert(ptr != NULL); + + void *p = je_mallocx(size, flags); + if (p == NULL) { + return (ALLOCM_ERR_OOM); + } + if (rsize != NULL) { + *rsize = isalloc(tsdn_fetch(), p); + } + *ptr = p; + return ALLOCM_SUCCESS; +} + +int +je_rallocm(void **ptr, size_t *rsize, size_t size, size_t extra, int flags) { + assert(ptr != NULL); + assert(*ptr != NULL); + assert(size != 0); + assert(SIZE_T_MAX - size >= extra); + + int ret; + bool no_move = flags & ALLOCM_NO_MOVE; + + if (no_move) { + size_t usize = je_xallocx(*ptr, size, extra, flags); + ret = (usize >= size) ? ALLOCM_SUCCESS : ALLOCM_ERR_NOT_MOVED; + if (rsize != NULL) { + *rsize = usize; + } + } else { + void *p = je_rallocx(*ptr, size+extra, flags); + if (p != NULL) { + *ptr = p; + ret = ALLOCM_SUCCESS; + } else { + ret = ALLOCM_ERR_OOM; + } + if (rsize != NULL) { + *rsize = isalloc(tsdn_fetch(), *ptr); + } + } + return ret; +} + +int +je_sallocm(const void *ptr, size_t *rsize, int flags) { + assert(rsize != NULL); + *rsize = je_sallocx(ptr, flags); + return ALLOCM_SUCCESS; +} + +int +je_dallocm(void *ptr, int flags) { + je_dallocx(ptr, flags); + return ALLOCM_SUCCESS; +} + +int +je_nallocm(size_t *rsize, size_t size, int flags) { + size_t usize = je_nallocx(size, flags); + if (usize == 0) { + return ALLOCM_ERR_OOM; + } + if (rsize != NULL) { + *rsize = usize; + } + return ALLOCM_SUCCESS; +} + +#undef ALLOCM_LG_ALIGN +#undef ALLOCM_ALIGN +#undef ALLOCM_ZERO +#undef ALLOCM_NO_MOVE + +#undef ALLOCM_SUCCESS +#undef ALLOCM_ERR_OOM +#undef ALLOCM_ERR_NOT_MOVED + +/* + * End compatibility functions. + */ +/******************************************************************************/ -+/* + /* * The following functions are used by threading libraries for protection of * malloc during fork(). - */ -@@ -3323,4 +3424,11 @@ jemalloc_postfork_child(void) { +@@ -3919,4 +4001,11 @@ jemalloc_postfork_child(void) { ctl_postfork_child(tsd_tsdn(tsd)); } +void +_malloc_first_thread(void) +{ + + (void)malloc_mutex_first_thread(); +} + /******************************************************************************/ diff --git a/src/malloc_io.c b/src/malloc_io.c -index 7bdc13f9..c8802c70 100644 +index d7cb0f52..cda589c4 100644 --- a/src/malloc_io.c +++ b/src/malloc_io.c @@ -75,6 +75,20 @@ wrtmessage(void *cbopaque, const char *s) { JEMALLOC_EXPORT void (*je_malloc_message)(void *, const char *s); +JEMALLOC_ATTR(visibility("hidden")) +void +wrtmessage_1_0(const char *s1, const char *s2, const char *s3, const char *s4) { + + wrtmessage(NULL, s1); + wrtmessage(NULL, s2); + wrtmessage(NULL, s3); + wrtmessage(NULL, s4); +} + +void (*__malloc_message_1_0)(const char *s1, const char *s2, const char *s3, + const char *s4) = wrtmessage_1_0; +__sym_compat(_malloc_message, __malloc_message_1_0, FBSD_1.0); + /* * Wrapper around malloc_message() that avoids the need for * je_malloc_message(...) throughout the code. diff --git a/src/mutex.c b/src/mutex.c -index 30222b3e..b2c36283 100644 +index 3f920f5b..88a7730c 100644 --- a/src/mutex.c +++ b/src/mutex.c @@ -41,6 +41,17 @@ pthread_create(pthread_t *__restrict thread, #ifdef JEMALLOC_MUTEX_INIT_CB JEMALLOC_EXPORT int _pthread_mutex_init_calloc_cb(pthread_mutex_t *mutex, void *(calloc_cb)(size_t, size_t)); + +#pragma weak _pthread_mutex_init_calloc_cb +int +_pthread_mutex_init_calloc_cb(pthread_mutex_t *mutex, + void *(calloc_cb)(size_t, size_t)) +{ + + return (((int (*)(pthread_mutex_t *, void *(*)(size_t, size_t))) + __libc_interposing[INTERPOS__pthread_mutex_init_calloc_cb])(mutex, + calloc_cb)); +} #endif void @@ -131,6 +142,16 @@ mutex_addr_comp(const witness_t *witness1, void *mutex1, + } } - bool ++bool +malloc_mutex_first_thread(void) { + +#ifndef JEMALLOC_MUTEX_INIT_CB + return (malloc_mutex_first_thread()); +#else + return (false); +#endif +} + -+bool + bool malloc_mutex_init(malloc_mutex_t *mutex, const char *name, witness_rank_t rank, malloc_mutex_lock_order_t lock_order) { - mutex_prof_data_init(&mutex->prof_data); Index: head/contrib/jemalloc/VERSION =================================================================== --- head/contrib/jemalloc/VERSION (revision 360232) +++ head/contrib/jemalloc/VERSION (revision 360233) @@ -1 +1 @@ -5.1.0-0-g61efbda7098de6fe64c362d309824864308c36d4 +5.2.1-0-gea6b3e973b477b8061e0076bb257dbd7f3faa756 Index: head/contrib/jemalloc/doc/jemalloc.3 =================================================================== --- head/contrib/jemalloc/doc/jemalloc.3 (revision 360232) +++ head/contrib/jemalloc/doc/jemalloc.3 (revision 360233) @@ -1,2497 +1,2560 @@ '\" t .\" Title: JEMALLOC .\" Author: Jason Evans -.\" Generator: DocBook XSL Stylesheets v1.76.1 -.\" Date: 05/08/2018 +.\" Generator: DocBook XSL Stylesheets v1.79.1 +.\" Date: 11/10/2019 .\" Manual: User Manual -.\" Source: jemalloc 5.1.0-0-g61efbda7098de6fe64c362d309824864308c36d4 +.\" Source: jemalloc 5.2.1-0-gea6b3e973b477b8061e0076bb257dbd7f3faa756 .\" Language: English .\" -.TH "JEMALLOC" "3" "05/08/2018" "jemalloc 5.1.0-0-g61efbda7098d" "User Manual" +.TH "JEMALLOC" "3" "11/10/2019" "jemalloc 5.2.1-0-gea6b3e973b47" "User Manual" .\" ----------------------------------------------------------------- .\" * Define some portability stuff .\" ----------------------------------------------------------------- .\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ .\" http://bugs.debian.org/507673 .\" http://lists.gnu.org/archive/html/groff/2009-02/msg00013.html .\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ .ie \n(.g .ds Aq \(aq .el .ds Aq ' .\" ----------------------------------------------------------------- .\" * set default formatting .\" ----------------------------------------------------------------- .\" disable hyphenation .nh .\" disable justification (adjust text to left margin only) .ad l .\" ----------------------------------------------------------------- .\" * MAIN CONTENT STARTS HERE * .\" ----------------------------------------------------------------- .SH "NAME" jemalloc \- general purpose memory allocation functions .SH "LIBRARY" .PP -This manual describes jemalloc 5\&.1\&.0\-0\-g61efbda7098de6fe64c362d309824864308c36d4\&. More information can be found at the +This manual describes jemalloc 5\&.2\&.1\-0\-gea6b3e973b477b8061e0076bb257dbd7f3faa756\&. More information can be found at the \m[blue]\fBjemalloc website\fR\m[]\&\s-2\u[1]\d\s+2\&. .PP The following configuration options are enabled in libc\*(Aqs built\-in jemalloc: \fB\-\-enable\-fill\fR, \fB\-\-enable\-lazy\-lock\fR, \fB\-\-enable\-stats\fR, \fB\-\-enable\-utrace\fR, \fB\-\-enable\-xmalloc\fR, and \fB\-\-with\-malloc\-conf=abort_conf:false\fR\&. Additionally, \fB\-\-enable\-debug\fR is enabled in development versions of FreeBSD (controlled by the \fBMALLOC_PRODUCTION\fR make variable)\&. .SH "SYNOPSIS" .sp .ft B .nf #include #include .fi .ft .SS "Standard API" .HP \w'void\ *malloc('u .BI "void *malloc(size_t\ " "size" ");" .HP \w'void\ *calloc('u .BI "void *calloc(size_t\ " "number" ", size_t\ " "size" ");" .HP \w'int\ posix_memalign('u .BI "int posix_memalign(void\ **" "ptr" ", size_t\ " "alignment" ", size_t\ " "size" ");" .HP \w'void\ *aligned_alloc('u .BI "void *aligned_alloc(size_t\ " "alignment" ", size_t\ " "size" ");" .HP \w'void\ *realloc('u .BI "void *realloc(void\ *" "ptr" ", size_t\ " "size" ");" .HP \w'void\ free('u .BI "void free(void\ *" "ptr" ");" .SS "Non\-standard API" .HP \w'void\ *mallocx('u .BI "void *mallocx(size_t\ " "size" ", int\ " "flags" ");" .HP \w'void\ *rallocx('u .BI "void *rallocx(void\ *" "ptr" ", size_t\ " "size" ", int\ " "flags" ");" .HP \w'size_t\ xallocx('u .BI "size_t xallocx(void\ *" "ptr" ", size_t\ " "size" ", size_t\ " "extra" ", int\ " "flags" ");" .HP \w'size_t\ sallocx('u .BI "size_t sallocx(void\ *" "ptr" ", int\ " "flags" ");" .HP \w'void\ dallocx('u .BI "void dallocx(void\ *" "ptr" ", int\ " "flags" ");" .HP \w'void\ sdallocx('u .BI "void sdallocx(void\ *" "ptr" ", size_t\ " "size" ", int\ " "flags" ");" .HP \w'size_t\ nallocx('u .BI "size_t nallocx(size_t\ " "size" ", int\ " "flags" ");" .HP \w'int\ mallctl('u .BI "int mallctl(const\ char\ *" "name" ", void\ *" "oldp" ", size_t\ *" "oldlenp" ", void\ *" "newp" ", size_t\ " "newlen" ");" .HP \w'int\ mallctlnametomib('u .BI "int mallctlnametomib(const\ char\ *" "name" ", size_t\ *" "mibp" ", size_t\ *" "miblenp" ");" .HP \w'int\ mallctlbymib('u .BI "int mallctlbymib(const\ size_t\ *" "mib" ", size_t\ " "miblen" ", void\ *" "oldp" ", size_t\ *" "oldlenp" ", void\ *" "newp" ", size_t\ " "newlen" ");" .HP \w'void\ malloc_stats_print('u .BI "void malloc_stats_print(void\ " "(*write_cb)" "\ (void\ *,\ const\ char\ *), void\ *" "cbopaque" ", const\ char\ *" "opts" ");" .HP \w'size_t\ malloc_usable_size('u .BI "size_t malloc_usable_size(const\ void\ *" "ptr" ");" .HP \w'void\ (*malloc_message)('u .BI "void (*malloc_message)(void\ *" "cbopaque" ", const\ char\ *" "s" ");" .PP const char *\fImalloc_conf\fR; .SH "DESCRIPTION" .SS "Standard API" .PP The malloc() function allocates \fIsize\fR bytes of uninitialized memory\&. The allocated space is suitably aligned (after possible pointer coercion) for storage of any type of object\&. .PP The calloc() function allocates space for \fInumber\fR objects, each \fIsize\fR bytes in length\&. The result is identical to calling malloc() with an argument of \fInumber\fR * \fIsize\fR, with the exception that the allocated memory is explicitly initialized to zero bytes\&. .PP The posix_memalign() function allocates \fIsize\fR bytes of memory such that the allocation\*(Aqs base address is a multiple of \fIalignment\fR, and returns the allocation in the value pointed to by \fIptr\fR\&. The requested \fIalignment\fR must be a power of 2 at least as large as sizeof(\fBvoid *\fR)\&. .PP The aligned_alloc() function allocates \fIsize\fR bytes of memory such that the allocation\*(Aqs base address is a multiple of \fIalignment\fR\&. The requested \fIalignment\fR must be a power of 2\&. Behavior is undefined if \fIsize\fR is not an integral multiple of \fIalignment\fR\&. .PP The realloc() function changes the size of the previously allocated memory referenced by \fIptr\fR to \fIsize\fR bytes\&. The contents of the memory are unchanged up to the lesser of the new and old sizes\&. If the new size is larger, the contents of the newly allocated portion of the memory are undefined\&. Upon success, the memory referenced by \fIptr\fR is freed and a pointer to the newly allocated memory is returned\&. Note that realloc() may move the memory allocation, resulting in a different return value than \fIptr\fR\&. If \fIptr\fR is \fBNULL\fR, the realloc() function behaves identically to malloc() for the specified size\&. .PP The free() function causes the allocated memory referenced by \fIptr\fR to be made available for future allocations\&. If \fIptr\fR is \fBNULL\fR, no action occurs\&. .SS "Non\-standard API" .PP The mallocx(), rallocx(), xallocx(), sallocx(), dallocx(), sdallocx(), and nallocx() functions all have a \fIflags\fR argument that can be used to specify options\&. The functions only check the options that are contextually relevant\&. Use bitwise or (|) operations to specify one or more of the following: .PP \fBMALLOCX_LG_ALIGN(\fR\fB\fIla\fR\fR\fB) \fR .RS 4 Align the memory allocation to start at an address that is a multiple of (1 << \fIla\fR)\&. This macro does not validate that \fIla\fR is within the valid range\&. .RE .PP \fBMALLOCX_ALIGN(\fR\fB\fIa\fR\fR\fB) \fR .RS 4 Align the memory allocation to start at an address that is a multiple of \fIa\fR, where \fIa\fR is a power of two\&. This macro does not validate that \fIa\fR is a power of 2\&. .RE .PP \fBMALLOCX_ZERO\fR .RS 4 Initialize newly allocated memory to contain zero bytes\&. In the growing reallocation case, the real size prior to reallocation defines the boundary between untouched bytes and those that are initialized to contain zero bytes\&. If this macro is absent, newly allocated memory is uninitialized\&. .RE .PP \fBMALLOCX_TCACHE(\fR\fB\fItc\fR\fR\fB) \fR .RS 4 Use the thread\-specific cache (tcache) specified by the identifier \fItc\fR, which must have been acquired via the tcache\&.create mallctl\&. This macro does not validate that \fItc\fR specifies a valid identifier\&. .RE .PP \fBMALLOCX_TCACHE_NONE\fR .RS 4 Do not use a thread\-specific cache (tcache)\&. Unless \fBMALLOCX_TCACHE(\fR\fB\fItc\fR\fR\fB)\fR or \fBMALLOCX_TCACHE_NONE\fR is specified, an automatically managed tcache will be used under many circumstances\&. This macro cannot be used in the same \fIflags\fR argument as \fBMALLOCX_TCACHE(\fR\fB\fItc\fR\fR\fB)\fR\&. .RE .PP \fBMALLOCX_ARENA(\fR\fB\fIa\fR\fR\fB) \fR .RS 4 Use the arena specified by the index \fIa\fR\&. This macro has no effect for regions that were allocated via an arena other than the one specified\&. This macro does not validate that \fIa\fR specifies an arena index in the valid range\&. .RE .PP The mallocx() function allocates at least \fIsize\fR bytes of memory, and returns a pointer to the base address of the allocation\&. Behavior is undefined if \fIsize\fR is \fB0\fR\&. .PP The rallocx() function resizes the allocation at \fIptr\fR to be at least \fIsize\fR bytes, and returns a pointer to the base address of the resulting allocation, which may or may not have moved from its original location\&. Behavior is undefined if \fIsize\fR is \fB0\fR\&. .PP The xallocx() function resizes the allocation at \fIptr\fR in place to be at least \fIsize\fR bytes, and returns the real size of the allocation\&. If \fIextra\fR is non\-zero, an attempt is made to resize the allocation to be at least (\fIsize\fR + \fIextra\fR) bytes, though inability to allocate the extra byte(s) will not by itself result in failure to resize\&. Behavior is undefined if \fIsize\fR is \fB0\fR, or if (\fIsize\fR + \fIextra\fR > \fBSIZE_T_MAX\fR)\&. .PP The sallocx() function returns the real size of the allocation at \fIptr\fR\&. .PP The dallocx() function causes the memory referenced by \fIptr\fR to be made available for future allocations\&. .PP The sdallocx() function is an extension of dallocx() with a \fIsize\fR parameter to allow the caller to pass in the allocation size as an optimization\&. The minimum valid input size is the original requested size of the allocation, and the maximum valid input size is the corresponding value returned by nallocx() or sallocx()\&. .PP The nallocx() function allocates no memory, but it performs the same size computation as the mallocx() function, and returns the real size of the allocation that would result from the equivalent mallocx() function call, or \fB0\fR if the inputs exceed the maximum supported size class and/or alignment\&. Behavior is undefined if \fIsize\fR is \fB0\fR\&. .PP The mallctl() function provides a general interface for introspecting the memory allocator, as well as setting modifiable parameters and triggering actions\&. The period\-separated \fIname\fR argument specifies a location in a tree\-structured namespace; see the MALLCTL NAMESPACE section for documentation on the tree contents\&. To read a value, pass a pointer via \fIoldp\fR to adequate space to contain the value, and a pointer to its length via \fIoldlenp\fR; otherwise pass \fBNULL\fR and \fBNULL\fR\&. Similarly, to write a value, pass a pointer to the value via \fInewp\fR, and its length via \fInewlen\fR; otherwise pass \fBNULL\fR and \fB0\fR\&. .PP The mallctlnametomib() function provides a way to avoid repeated name lookups for applications that repeatedly query the same portion of the namespace, by translating a name to a \(lqManagement Information Base\(rq (MIB) that can be passed repeatedly to mallctlbymib()\&. Upon successful return from mallctlnametomib(), \fImibp\fR contains an array of \fI*miblenp\fR integers, where \fI*miblenp\fR is the lesser of the number of components in \fIname\fR and the input value of \fI*miblenp\fR\&. Thus it is possible to pass a \fI*miblenp\fR that is smaller than the number of period\-separated name components, which results in a partial MIB that can be used as the basis for constructing a complete MIB\&. For name components that are integers (e\&.g\&. the 2 in arenas\&.bin\&.2\&.size), the corresponding MIB component will always be that integer\&. Therefore, it is legitimate to construct code like the following: .sp .if n \{\ .RS 4 .\} .nf unsigned nbins, i; size_t mib[4]; size_t len, miblen; len = sizeof(nbins); mallctl("arenas\&.nbins", &nbins, &len, NULL, 0); miblen = 4; mallctlnametomib("arenas\&.bin\&.0\&.size", mib, &miblen); for (i = 0; i < nbins; i++) { size_t bin_size; mib[2] = i; len = sizeof(bin_size); mallctlbymib(mib, miblen, (void *)&bin_size, &len, NULL, 0); /* Do something with bin_size\&.\&.\&. */ } .fi .if n \{\ .RE .\} .PP .RS 4 .RE .PP The malloc_stats_print() function writes summary statistics via the \fIwrite_cb\fR callback function pointer and \fIcbopaque\fR data passed to \fIwrite_cb\fR, or malloc_message() if \fIwrite_cb\fR is \fBNULL\fR\&. The statistics are presented in human\-readable form unless \(lqJ\(rq is specified as a character within the \fIopts\fR string, in which case the statistics are presented in \m[blue]\fBJSON format\fR\m[]\&\s-2\u[2]\d\s+2\&. This function can be called repeatedly\&. General information that never changes during execution can be omitted by specifying \(lqg\(rq as a character within the \fIopts\fR string\&. Note that -malloc_message() +malloc_stats_print() uses the mallctl*() functions internally, so inconsistent statistics can be reported if multiple threads use these functions simultaneously\&. If \fB\-\-enable\-stats\fR is specified during configuration, \(lqm\(rq, \(lqd\(rq, and \(lqa\(rq can be specified to omit merged arena, destroyed merged arena, and per arena statistics, respectively; \(lqb\(rq and \(lql\(rq can be specified to omit per size class statistics for bins and large objects, respectively; \(lqx\(rq -can be specified to omit all mutex statistics\&. Unrecognized characters are silently ignored\&. Note that thread caching may prevent some statistics from being completely up to date, since extra locking would be required to merge counters that track thread cache operations\&. +can be specified to omit all mutex statistics; +\(lqe\(rq +can be used to omit extent statistics\&. Unrecognized characters are silently ignored\&. Note that thread caching may prevent some statistics from being completely up to date, since extra locking would be required to merge counters that track thread cache operations\&. .PP The malloc_usable_size() function returns the usable size of the allocation pointed to by \fIptr\fR\&. The return value may be larger than the size that was requested during allocation\&. The malloc_usable_size() function is not a mechanism for in\-place realloc(); rather it is provided solely as a tool for introspection purposes\&. Any discrepancy between the requested allocation size and the size reported by malloc_usable_size() should not be depended on, since such behavior is entirely implementation\-dependent\&. .SH "TUNING" .PP Once, when the first call is made to one of the memory allocation routines, the allocator initializes its internals based in part on various options that can be specified at compile\- or run\-time\&. .PP The string specified via \fB\-\-with\-malloc\-conf\fR, the string pointed to by the global variable \fImalloc_conf\fR, the \(lqname\(rq of the file referenced by the symbolic link named /etc/malloc\&.conf, and the value of the environment variable \fBMALLOC_CONF\fR, will be interpreted, in that order, from left to right as options\&. Note that \fImalloc_conf\fR may be read before main() is entered, so the declaration of \fImalloc_conf\fR should specify an initializer that contains the final value to be read by jemalloc\&. \fB\-\-with\-malloc\-conf\fR and \fImalloc_conf\fR are compile\-time mechanisms, whereas /etc/malloc\&.conf and \fBMALLOC_CONF\fR can be safely set any time prior to program invocation\&. .PP An options string is a comma\-separated list of option:value pairs\&. There is one key corresponding to each opt\&.* mallctl (see the MALLCTL NAMESPACE section for options documentation)\&. For example, abort:true,narenas:1 sets the opt\&.abort and opt\&.narenas options\&. Some options have boolean values (true/false), others have integer values (base 8, 10, or 16, depending on prefix), and yet others have raw string values\&. .SH "IMPLEMENTATION NOTES" .PP Traditionally, allocators have used \fBsbrk\fR(2) to obtain memory, which is suboptimal for several reasons, including race conditions, increased fragmentation, and artificial limitations on maximum usable memory\&. If \fBsbrk\fR(2) is supported by the operating system, this allocator uses both \fBmmap\fR(2) and \fBsbrk\fR(2), in that order of preference; otherwise only \fBmmap\fR(2) is used\&. .PP This allocator uses multiple arenas in order to reduce lock contention for threaded programs on multi\-processor systems\&. This works well with regard to threading scalability, but incurs some costs\&. There is a small fixed per\-arena overhead, and additionally, arenas manage memory completely independently of each other, which means a small fixed increase in overall memory fragmentation\&. These overheads are not generally an issue, given the number of arenas normally used\&. Note that using substantially more arenas than the default is not likely to improve performance, mainly due to reduced cache performance\&. However, it may make sense to reduce the number of arenas if an application does not make much use of the allocation functions\&. .PP In addition to multiple arenas, this allocator supports thread\-specific caching, in order to make it possible to completely avoid synchronization for most allocation requests\&. Such caching allows very fast allocation in the common case, but it increases memory usage and fragmentation, since a bounded number of objects can remain allocated in each thread cache\&. .PP Memory is conceptually broken into extents\&. Extents are always aligned to multiples of the page size\&. This alignment makes it possible to find metadata for user objects quickly\&. User objects are broken into two categories according to size: small and large\&. Contiguous small objects comprise a slab, which resides within a single extent, whereas large objects each have their own extents backing them\&. .PP Small objects are managed in groups by slabs\&. Each slab maintains a bitmap to track which regions are in use\&. Allocation requests that are no more than half the quantum (8 or 16, depending on architecture) are rounded up to the nearest power of two that is at least sizeof(\fBdouble\fR)\&. All other object size classes are multiples of the quantum, spaced such that there are four size classes for each doubling in size, which limits internal fragmentation to approximately 20% for all but the smallest size classes\&. Small size classes are smaller than four times the page size, and large size classes extend from four times the page size up to the largest size class that does not exceed \fBPTRDIFF_MAX\fR\&. .PP Allocations are packed tightly together, which can be an issue for multi\-threaded applications\&. If you need to assure that allocations do not suffer from cacheline sharing, round your allocation requests up to the nearest multiple of the cacheline size, or specify cacheline alignment when allocating\&. .PP The realloc(), rallocx(), and xallocx() functions may resize allocations without moving them under limited circumstances\&. Unlike the *allocx() API, the standard API does not officially round up the usable size of an allocation to the nearest size class, so technically it is necessary to call realloc() to grow e\&.g\&. a 9\-byte allocation to 16 bytes, or shrink a 16\-byte allocation to 9 bytes\&. Growth and shrinkage trivially succeeds in place as long as the pre\-size and post\-size both round up to the same size class\&. No other API guarantees are made regarding in\-place resizing, but the current implementation also tries to resize large allocations in place, as long as the pre\-size and post\-size are both large\&. For shrinkage to succeed, the extent allocator must support splitting (see arena\&.\&.extent_hooks)\&. Growth only succeeds if the trailing memory is currently available, and the extent allocator supports merging\&. .PP Assuming 4 KiB pages and a 16\-byte quantum on a 64\-bit system, the size classes in each category are as shown in Table 1\&. .sp .it 1 an-trap .nr an-no-space-flag 1 .nr an-break-flag 1 .br .B Table\ \&1.\ \&Size classes .TS allbox tab(:); lB rB lB. T{ Category T}:T{ Spacing T}:T{ Size T} .T& l r l ^ r l ^ r l ^ r l ^ r l ^ r l ^ r l ^ r l ^ r l l r l ^ r l ^ r l ^ r l ^ r l ^ r l ^ r l ^ r l ^ r l ^ r l ^ r l ^ r l ^ r l ^ r l ^ r l ^ r l. T{ Small T}:T{ lg T}:T{ [8] T} :T{ 16 T}:T{ [16, 32, 48, 64, 80, 96, 112, 128] T} :T{ 32 T}:T{ [160, 192, 224, 256] T} :T{ 64 T}:T{ [320, 384, 448, 512] T} :T{ 128 T}:T{ [640, 768, 896, 1024] T} :T{ 256 T}:T{ [1280, 1536, 1792, 2048] T} :T{ 512 T}:T{ [2560, 3072, 3584, 4096] T} :T{ 1 KiB T}:T{ [5 KiB, 6 KiB, 7 KiB, 8 KiB] T} :T{ 2 KiB T}:T{ [10 KiB, 12 KiB, 14 KiB] T} T{ Large T}:T{ 2 KiB T}:T{ [16 KiB] T} :T{ 4 KiB T}:T{ [20 KiB, 24 KiB, 28 KiB, 32 KiB] T} :T{ 8 KiB T}:T{ [40 KiB, 48 KiB, 54 KiB, 64 KiB] T} :T{ 16 KiB T}:T{ [80 KiB, 96 KiB, 112 KiB, 128 KiB] T} :T{ 32 KiB T}:T{ [160 KiB, 192 KiB, 224 KiB, 256 KiB] T} :T{ 64 KiB T}:T{ [320 KiB, 384 KiB, 448 KiB, 512 KiB] T} :T{ 128 KiB T}:T{ [640 KiB, 768 KiB, 896 KiB, 1 MiB] T} :T{ 256 KiB T}:T{ [1280 KiB, 1536 KiB, 1792 KiB, 2 MiB] T} :T{ 512 KiB T}:T{ [2560 KiB, 3 MiB, 3584 KiB, 4 MiB] T} :T{ 1 MiB T}:T{ [5 MiB, 6 MiB, 7 MiB, 8 MiB] T} :T{ 2 MiB T}:T{ [10 MiB, 12 MiB, 14 MiB, 16 MiB] T} :T{ 4 MiB T}:T{ [20 MiB, 24 MiB, 28 MiB, 32 MiB] T} :T{ 8 MiB T}:T{ [40 MiB, 48 MiB, 56 MiB, 64 MiB] T} :T{ \&.\&.\&. T}:T{ \&.\&.\&. T} :T{ 512 PiB T}:T{ [2560 PiB, 3 EiB, 3584 PiB, 4 EiB] T} :T{ 1 EiB T}:T{ [5 EiB, 6 EiB, 7 EiB] T} .TE .sp 1 .SH "MALLCTL NAMESPACE" .PP The following names are defined in the namespace accessible via the mallctl*() functions\&. Value types are specified in parentheses, their readable/writable statuses are encoded as rw, r\-, \-w, or \-\-, and required build configuration flags follow, if any\&. A name element encoded as or indicates an integer component, where the integer varies from 0 to some upper value that must be determined via introspection\&. In the case of stats\&.arenas\&.\&.* and arena\&.\&.{initialized,purge,decay,dss}, equal to \fBMALLCTL_ARENAS_ALL\fR can be used to operate on all arenas or access the summation of statistics from all arenas; similarly equal to \fBMALLCTL_ARENAS_DESTROYED\fR can be used to access the summation of statistics from all destroyed arenas\&. These constants can be utilized either via mallctlnametomib() followed by mallctlbymib(), or via code such as the following: .sp .if n \{\ .RS 4 .\} .nf #define STRINGIFY_HELPER(x) #x #define STRINGIFY(x) STRINGIFY_HELPER(x) mallctl("arena\&." STRINGIFY(MALLCTL_ARENAS_ALL) "\&.decay", NULL, NULL, NULL, 0); .fi .if n \{\ .RE .\} .sp Take special note of the epoch mallctl, which controls refreshing of cached dynamic statistics\&. .PP version (\fBconst char *\fR) r\- .RS 4 Return the jemalloc version string\&. .RE .PP epoch (\fBuint64_t\fR) rw .RS 4 If a value is passed in, refresh the data from which the mallctl*() functions report values, and increment the epoch\&. Return the current epoch\&. This is useful for detecting whether another thread caused a refresh\&. .RE .PP background_thread (\fBbool\fR) rw .RS 4 Enable/disable internal background worker threads\&. When set to true, background threads are created on demand (the number of background threads will be no more than the number of CPUs or active arenas)\&. Threads run periodically, and handle purging asynchronously\&. When switching off, background threads are terminated synchronously\&. Note that after \fBfork\fR(2) function, the state in the child process will be disabled regardless the state in parent process\&. See stats\&.background_thread for related stats\&. opt\&.background_thread can be used to set the default option\&. This option is only available on selected pthread\-based platforms\&. .RE .PP max_background_threads (\fBsize_t\fR) rw .RS 4 Maximum number of background worker threads that will be created\&. This value is capped at opt\&.max_background_threads at startup\&. .RE .PP config\&.cache_oblivious (\fBbool\fR) r\- .RS 4 \fB\-\-enable\-cache\-oblivious\fR was specified during build configuration\&. .RE .PP config\&.debug (\fBbool\fR) r\- .RS 4 \fB\-\-enable\-debug\fR was specified during build configuration\&. .RE .PP config\&.fill (\fBbool\fR) r\- .RS 4 \fB\-\-enable\-fill\fR was specified during build configuration\&. .RE .PP config\&.lazy_lock (\fBbool\fR) r\- .RS 4 \fB\-\-enable\-lazy\-lock\fR was specified during build configuration\&. .RE .PP config\&.malloc_conf (\fBconst char *\fR) r\- .RS 4 Embedded configure\-time\-specified run\-time options string, empty unless \fB\-\-with\-malloc\-conf\fR was specified during build configuration\&. .RE .PP config\&.prof (\fBbool\fR) r\- .RS 4 \fB\-\-enable\-prof\fR was specified during build configuration\&. .RE .PP config\&.prof_libgcc (\fBbool\fR) r\- .RS 4 \fB\-\-disable\-prof\-libgcc\fR was not specified during build configuration\&. .RE .PP config\&.prof_libunwind (\fBbool\fR) r\- .RS 4 \fB\-\-enable\-prof\-libunwind\fR was specified during build configuration\&. .RE .PP config\&.stats (\fBbool\fR) r\- .RS 4 \fB\-\-enable\-stats\fR was specified during build configuration\&. .RE .PP config\&.utrace (\fBbool\fR) r\- .RS 4 \fB\-\-enable\-utrace\fR was specified during build configuration\&. .RE .PP config\&.xmalloc (\fBbool\fR) r\- .RS 4 \fB\-\-enable\-xmalloc\fR was specified during build configuration\&. .RE .PP opt\&.abort (\fBbool\fR) r\- .RS 4 Abort\-on\-warning enabled/disabled\&. If true, most warnings are fatal\&. Note that runtime option warnings are not included (see opt\&.abort_conf for that)\&. The process will call \fBabort\fR(3) in these cases\&. This option is disabled by default unless \fB\-\-enable\-debug\fR is specified during configuration, in which case it is enabled by default\&. .RE .PP +opt\&.confirm_conf (\fBbool\fR) r\- +.RS 4 +Confirm\-runtime\-options\-when\-program\-starts enabled/disabled\&. If true, the string specified via +\fB\-\-with\-malloc\-conf\fR, the string pointed to by the global variable +\fImalloc_conf\fR, the +\(lqname\(rq +of the file referenced by the symbolic link named +/etc/malloc\&.conf, and the value of the environment variable +\fBMALLOC_CONF\fR, will be printed in order\&. Then, each option being set will be individually printed\&. This option is disabled by default\&. +.RE +.PP opt\&.abort_conf (\fBbool\fR) r\- .RS 4 Abort\-on\-invalid\-configuration enabled/disabled\&. If true, invalid runtime options are fatal\&. The process will call \fBabort\fR(3) in these cases\&. This option is disabled by default unless \fB\-\-enable\-debug\fR is specified during configuration, in which case it is enabled by default\&. .RE .PP opt\&.metadata_thp (\fBconst char *\fR) r\- .RS 4 Controls whether to allow jemalloc to use transparent huge page (THP) for internal metadata (see stats\&.metadata)\&. \(lqalways\(rq allows such usage\&. \(lqauto\(rq uses no THP initially, but may begin to do so when metadata usage reaches certain level\&. The default is \(lqdisabled\(rq\&. .RE .PP opt\&.retain (\fBbool\fR) r\- .RS 4 If true, retain unused virtual memory for later reuse rather than discarding it by calling \fBmunmap\fR(2) or equivalent (see stats\&.retained -for related details)\&. This option is disabled by default unless discarding virtual memory is known to trigger platform\-specific performance problems, e\&.g\&. for [64\-bit] Linux, which has a quirk in its virtual memory allocation algorithm that causes semi\-permanent VM map holes under normal jemalloc operation\&. Although -\fBmunmap\fR(2) -causes issues on 32\-bit Linux as well, retaining virtual memory for 32\-bit Linux is disabled by default due to the practical possibility of address space exhaustion\&. +for related details)\&. It also makes jemalloc use +\fBmmap\fR(2) +or equivalent in a more greedy way, mapping larger chunks in one go\&. This option is disabled by default unless discarding virtual memory is known to trigger platform\-specific performance problems, namely 1) for [64\-bit] Linux, which has a quirk in its virtual memory allocation algorithm that causes semi\-permanent VM map holes under normal jemalloc operation; and 2) for [64\-bit] Windows, which disallows split / merged regions with +\fI\fBMEM_RELEASE\fR\fR\&. Although the same issues may present on 32\-bit platforms as well, retaining virtual memory for 32\-bit Linux and Windows is disabled by default due to the practical possibility of address space exhaustion\&. .RE .PP opt\&.dss (\fBconst char *\fR) r\- .RS 4 dss (\fBsbrk\fR(2)) allocation precedence as related to \fBmmap\fR(2) allocation\&. The following settings are supported if \fBsbrk\fR(2) is supported by the operating system: \(lqdisabled\(rq, \(lqprimary\(rq, and \(lqsecondary\(rq; otherwise only \(lqdisabled\(rq is supported\&. The default is \(lqsecondary\(rq if \fBsbrk\fR(2) is supported by the operating system; \(lqdisabled\(rq otherwise\&. .RE .PP opt\&.narenas (\fBunsigned\fR) r\- .RS 4 Maximum number of arenas to use for automatic multiplexing of threads and arenas\&. The default is four times the number of CPUs, or one if there is a single CPU\&. .RE .PP +opt\&.oversize_threshold (\fBsize_t\fR) r\- +.RS 4 +The threshold in bytes of which requests are considered oversize\&. Allocation requests with greater sizes are fulfilled from a dedicated arena (automatically managed, however not within +narenas), in order to reduce fragmentation by not mixing huge allocations with small ones\&. In addition, the decay API guarantees on the extents greater than the specified threshold may be overridden\&. Note that requests with arena index specified via +\fBMALLOCX_ARENA\fR, or threads associated with explicit arenas will not be considered\&. The default threshold is 8MiB\&. Values not within large size classes disables this feature\&. +.RE +.PP opt\&.percpu_arena (\fBconst char *\fR) r\- .RS 4 Per CPU arena mode\&. Use the \(lqpercpu\(rq setting to enable this feature, which uses number of CPUs to determine number of arenas, and bind threads to arenas dynamically based on the CPU the thread runs on currently\&. \(lqphycpu\(rq setting uses one arena per physical CPU, which means the two hyper threads on the same CPU share one arena\&. Note that no runtime checking regarding the availability of hyper threading is done at the moment\&. When set to \(lqdisabled\(rq, narenas and thread to arena association will not be impacted by this option\&. The default is \(lqdisabled\(rq\&. .RE .PP -opt\&.background_thread (\fBconst bool\fR) r\- +opt\&.background_thread (\fBbool\fR) r\- .RS 4 Internal background worker threads enabled/disabled\&. Because of potential circular dependencies, enabling background thread using this option may cause crash or deadlock during initialization\&. For a reliable way to use this feature, see background_thread for dynamic control options and details\&. This option is disabled by default\&. .RE .PP -opt\&.max_background_threads (\fBconst size_t\fR) r\- +opt\&.max_background_threads (\fBsize_t\fR) r\- .RS 4 Maximum number of background threads that will be created if background_thread is set\&. Defaults to number of cpus\&. .RE .PP opt\&.dirty_decay_ms (\fBssize_t\fR) r\- .RS 4 Approximate time in milliseconds from the creation of a set of unused dirty pages until an equivalent set of unused dirty pages is purged (i\&.e\&. converted to muzzy via e\&.g\&. madvise(\fI\&.\&.\&.\fR\fI\fBMADV_FREE\fR\fR) if supported by the operating system, or converted to clean otherwise) and/or reused\&. Dirty pages are defined as previously having been potentially written to by the application, and therefore consuming physical memory, yet having no current use\&. The pages are incrementally purged according to a sigmoidal decay curve that starts and ends with zero purge rate\&. A decay time of 0 causes all unused dirty pages to be purged immediately upon creation\&. A decay time of \-1 disables purging\&. The default decay time is 10 seconds\&. See arenas\&.dirty_decay_ms and arena\&.\&.dirty_decay_ms for related dynamic control options\&. See opt\&.muzzy_decay_ms -for a description of muzzy pages\&. +for a description of muzzy pages\&.for a description of muzzy pages\&. Note that when the +oversize_threshold +feature is enabled, the arenas reserved for oversize requests may have its own default decay settings\&. .RE .PP opt\&.muzzy_decay_ms (\fBssize_t\fR) r\- .RS 4 Approximate time in milliseconds from the creation of a set of unused muzzy pages until an equivalent set of unused muzzy pages is purged (i\&.e\&. converted to clean) and/or reused\&. Muzzy pages are defined as previously having been unused dirty pages that were subsequently purged in a manner that left them subject to the reclamation whims of the operating system (e\&.g\&. madvise(\fI\&.\&.\&.\fR\fI\fBMADV_FREE\fR\fR)), and therefore in an indeterminate state\&. The pages are incrementally purged according to a sigmoidal decay curve that starts and ends with zero purge rate\&. A decay time of 0 causes all unused muzzy pages to be purged immediately upon creation\&. A decay time of \-1 disables purging\&. The default decay time is 10 seconds\&. See arenas\&.muzzy_decay_ms and arena\&.\&.muzzy_decay_ms for related dynamic control options\&. .RE .PP opt\&.lg_extent_max_active_fit (\fBsize_t\fR) r\- .RS 4 When reusing dirty extents, this determines the (log base 2 of the) maximum ratio between the size of the active extent selected (to split off from) and the size of the requested allocation\&. This prevents the splitting of large active extents for smaller allocations, which can reduce fragmentation over the long run (especially for non\-active extents)\&. Lower value may reduce fragmentation, at the cost of extra active extents\&. The default value is 6, which gives a maximum ratio of 64 (2^6)\&. .RE .PP opt\&.stats_print (\fBbool\fR) r\- .RS 4 Enable/disable statistics printing at exit\&. If enabled, the malloc_stats_print() function is called at program exit via an \fBatexit\fR(3) function\&. opt\&.stats_print_opts can be combined to specify output options\&. If \fB\-\-enable\-stats\fR is specified during configuration, this has the potential to cause deadlock for a multi\-threaded process that exits while one or more threads are executing in the memory allocation functions\&. Furthermore, atexit() may allocate memory during application initialization and then deadlock internally when jemalloc in turn calls atexit(), so this option is not universally usable (though the application can register its own atexit() function with equivalent functionality)\&. Therefore, this option should only be used with care; it is primarily intended as a performance tuning aid during application development\&. This option is disabled by default\&. .RE .PP opt\&.stats_print_opts (\fBconst char *\fR) r\- .RS 4 Options (the \fIopts\fR string) to pass to the malloc_stats_print() at exit (enabled through opt\&.stats_print)\&. See available options in malloc_stats_print()\&. Has no effect unless opt\&.stats_print is enabled\&. The default is \(lq\(rq\&. .RE .PP opt\&.junk (\fBconst char *\fR) r\- [\fB\-\-enable\-fill\fR] .RS 4 Junk filling\&. If set to \(lqalloc\(rq, each byte of uninitialized allocated memory will be initialized to 0xa5\&. If set to \(lqfree\(rq, all deallocated memory will be initialized to 0x5a\&. If set to \(lqtrue\(rq, both allocated and deallocated memory will be initialized, and if set to \(lqfalse\(rq, junk filling be disabled entirely\&. This is intended for debugging and will impact performance negatively\&. This option is \(lqfalse\(rq by default unless \fB\-\-enable\-debug\fR is specified during configuration, in which case it is \(lqtrue\(rq by default\&. .RE .PP opt\&.zero (\fBbool\fR) r\- [\fB\-\-enable\-fill\fR] .RS 4 Zero filling enabled/disabled\&. If enabled, each byte of uninitialized allocated memory will be initialized to 0\&. Note that this initialization only happens once for each byte, so realloc() and rallocx() calls do not zero memory that was previously allocated\&. This is intended for debugging and will impact performance negatively\&. This option is disabled by default\&. .RE .PP opt\&.utrace (\fBbool\fR) r\- [\fB\-\-enable\-utrace\fR] .RS 4 Allocation tracing based on \fButrace\fR(2) enabled/disabled\&. This option is disabled by default\&. .RE .PP opt\&.xmalloc (\fBbool\fR) r\- [\fB\-\-enable\-xmalloc\fR] .RS 4 Abort\-on\-out\-of\-memory enabled/disabled\&. If enabled, rather than returning failure for any allocation function, display a diagnostic message on \fBSTDERR_FILENO\fR and cause the program to drop core (using \fBabort\fR(3))\&. If an application is designed to depend on this behavior, set the option at compile time by including the following in the source code: .sp .if n \{\ .RS 4 .\} .nf malloc_conf = "xmalloc:true"; .fi .if n \{\ .RE .\} .sp This option is disabled by default\&. .RE .PP opt\&.tcache (\fBbool\fR) r\- .RS 4 Thread\-specific caching (tcache) enabled/disabled\&. When there are multiple threads, each thread uses a tcache for objects up to a certain size\&. Thread\-specific caching allows many allocations to be satisfied without performing any thread synchronization, at the cost of increased memory use\&. See the opt\&.lg_tcache_max option for related tuning information\&. This option is enabled by default\&. .RE .PP opt\&.lg_tcache_max (\fBsize_t\fR) r\- .RS 4 Maximum size class (log base 2) to cache in the thread\-specific cache (tcache)\&. At a minimum, all small size classes are cached, and at a maximum all large size classes are cached\&. The default maximum is 32 KiB (2^15)\&. .RE .PP opt\&.thp (\fBconst char *\fR) r\- .RS 4 Transparent hugepage (THP) mode\&. Settings "always", "never" and "default" are available if THP is supported by the operating system\&. The "always" setting enables transparent hugepage for all user memory mappings with \fI\fBMADV_HUGEPAGE\fR\fR; "never" ensures no transparent hugepage with \fI\fBMADV_NOHUGEPAGE\fR\fR; the default setting "default" makes no changes\&. Note that: this option does not affect THP for jemalloc internal metadata (see opt\&.metadata_thp); in addition, for arenas with customized extent_hooks, this option is bypassed as it is implemented as part of the default extent hooks\&. .RE .PP opt\&.prof (\fBbool\fR) r\- [\fB\-\-enable\-prof\fR] .RS 4 Memory profiling enabled/disabled\&. If enabled, profile memory allocation activity\&. See the opt\&.prof_active option for on\-the\-fly activation/deactivation\&. See the opt\&.lg_prof_sample option for probabilistic sampling control\&. See the opt\&.prof_accum option for control of cumulative sample reporting\&. See the opt\&.lg_prof_interval option for information on interval\-triggered profile dumping, the opt\&.prof_gdump option for information on high\-water\-triggered profile dumping, and the opt\&.prof_final option for final profile dumping\&. Profile output is compatible with the \fBjeprof\fR command, which is based on the \fBpprof\fR that is developed as part of the \m[blue]\fBgperftools package\fR\m[]\&\s-2\u[3]\d\s+2\&. See HEAP PROFILE FORMAT for heap profile format documentation\&. .RE .PP opt\&.prof_prefix (\fBconst char *\fR) r\- [\fB\-\-enable\-prof\fR] .RS 4 Filename prefix for profile dumps\&. If the prefix is set to the empty string, no automatic dumps will occur; this is primarily useful for disabling the automatic final heap dump (which also disables leak reporting, if enabled)\&. The default prefix is jeprof\&. .RE .PP opt\&.prof_active (\fBbool\fR) r\- [\fB\-\-enable\-prof\fR] .RS 4 Profiling activated/deactivated\&. This is a secondary control mechanism that makes it possible to start the application with profiling enabled (see the opt\&.prof option) but inactive, then toggle profiling at any time during program execution with the prof\&.active mallctl\&. This option is enabled by default\&. .RE .PP opt\&.prof_thread_active_init (\fBbool\fR) r\- [\fB\-\-enable\-prof\fR] .RS 4 Initial setting for thread\&.prof\&.active in newly created threads\&. The initial setting for newly created threads can also be changed during execution via the prof\&.thread_active_init mallctl\&. This option is enabled by default\&. .RE .PP opt\&.lg_prof_sample (\fBsize_t\fR) r\- [\fB\-\-enable\-prof\fR] .RS 4 Average interval (log base 2) between allocation samples, as measured in bytes of allocation activity\&. Increasing the sampling interval decreases profile fidelity, but also decreases the computational overhead\&. The default sample interval is 512 KiB (2^19 B)\&. .RE .PP opt\&.prof_accum (\fBbool\fR) r\- [\fB\-\-enable\-prof\fR] .RS 4 Reporting of cumulative object/byte counts in profile dumps enabled/disabled\&. If this option is enabled, every unique backtrace must be stored for the duration of execution\&. Depending on the application, this can impose a large memory overhead, and the cumulative counts are not always of interest\&. This option is disabled by default\&. .RE .PP opt\&.lg_prof_interval (\fBssize_t\fR) r\- [\fB\-\-enable\-prof\fR] .RS 4 Average interval (log base 2) between memory profile dumps, as measured in bytes of allocation activity\&. The actual interval between dumps may be sporadic because decentralized allocation counters are used to avoid synchronization bottlenecks\&. Profiles are dumped to files named according to the pattern \&.\&.\&.i\&.heap, where is controlled by the opt\&.prof_prefix option\&. By default, interval\-triggered profile dumping is disabled (encoded as \-1)\&. .RE .PP opt\&.prof_gdump (\fBbool\fR) r\- [\fB\-\-enable\-prof\fR] .RS 4 Set the initial state of prof\&.gdump, which when enabled triggers a memory profile dump every time the total virtual memory exceeds the previous maximum\&. This option is disabled by default\&. .RE .PP opt\&.prof_final (\fBbool\fR) r\- [\fB\-\-enable\-prof\fR] .RS 4 Use an \fBatexit\fR(3) function to dump final memory usage to a file named according to the pattern \&.\&.\&.f\&.heap, where is controlled by the opt\&.prof_prefix option\&. Note that atexit() may allocate memory during application initialization and then deadlock internally when jemalloc in turn calls atexit(), so this option is not universally usable (though the application can register its own atexit() function with equivalent functionality)\&. This option is disabled by default\&. .RE .PP opt\&.prof_leak (\fBbool\fR) r\- [\fB\-\-enable\-prof\fR] .RS 4 Leak reporting enabled/disabled\&. If enabled, use an \fBatexit\fR(3) function to report memory leaks detected by allocation sampling\&. See the opt\&.prof option for information on analyzing heap profile output\&. This option is disabled by default\&. .RE .PP thread\&.arena (\fBunsigned\fR) rw .RS 4 Get or set the arena associated with the calling thread\&. If the specified arena was not initialized beforehand (see the arena\&.i\&.initialized mallctl), it will be automatically initialized as a side effect of calling this interface\&. .RE .PP thread\&.allocated (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Get the total number of bytes ever allocated by the calling thread\&. This counter has the potential to wrap around; it is up to the application to appropriately interpret the counter in such cases\&. .RE .PP thread\&.allocatedp (\fBuint64_t *\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Get a pointer to the the value that is returned by the thread\&.allocated mallctl\&. This is useful for avoiding the overhead of repeated mallctl*() calls\&. .RE .PP thread\&.deallocated (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Get the total number of bytes ever deallocated by the calling thread\&. This counter has the potential to wrap around; it is up to the application to appropriately interpret the counter in such cases\&. .RE .PP thread\&.deallocatedp (\fBuint64_t *\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Get a pointer to the the value that is returned by the thread\&.deallocated mallctl\&. This is useful for avoiding the overhead of repeated mallctl*() calls\&. .RE .PP thread\&.tcache\&.enabled (\fBbool\fR) rw .RS 4 Enable/disable calling thread\*(Aqs tcache\&. The tcache is implicitly flushed as a side effect of becoming disabled (see thread\&.tcache\&.flush)\&. .RE .PP thread\&.tcache\&.flush (\fBvoid\fR) \-\- .RS 4 Flush calling thread\*(Aqs thread\-specific cache (tcache)\&. This interface releases all cached objects and internal data structures associated with the calling thread\*(Aqs tcache\&. Ordinarily, this interface need not be called, since automatic periodic incremental garbage collection occurs, and the thread cache is automatically discarded when a thread exits\&. However, garbage collection is triggered by allocation activity, so it is possible for a thread that stops allocating/deallocating to retain its cache indefinitely, in which case the developer may find manual flushing useful\&. .RE .PP thread\&.prof\&.name (\fBconst char *\fR) r\- or \-w [\fB\-\-enable\-prof\fR] .RS 4 Get/set the descriptive name associated with the calling thread in memory profile dumps\&. An internal copy of the name string is created, so the input string need not be maintained after this interface completes execution\&. The output string of this interface should be copied for non\-ephemeral uses, because multiple implementation details can cause asynchronous string deallocation\&. Furthermore, each invocation of this interface can only read or write; simultaneous read/write is not supported due to string lifetime limitations\&. The name string must be nil\-terminated and comprised only of characters in the sets recognized by \fBisgraph\fR(3) and \fBisblank\fR(3)\&. .RE .PP thread\&.prof\&.active (\fBbool\fR) rw [\fB\-\-enable\-prof\fR] .RS 4 Control whether sampling is currently active for the calling thread\&. This is an activation mechanism in addition to prof\&.active; both must be active for the calling thread to sample\&. This flag is enabled by default\&. .RE .PP tcache\&.create (\fBunsigned\fR) r\- .RS 4 Create an explicit thread\-specific cache (tcache) and return an identifier that can be passed to the \fBMALLOCX_TCACHE(\fR\fB\fItc\fR\fR\fB)\fR macro to explicitly use the specified cache rather than the automatically managed one that is used by default\&. Each explicit cache can be used by only one thread at a time; the application must assure that this constraint holds\&. .RE .PP tcache\&.flush (\fBunsigned\fR) \-w .RS 4 Flush the specified thread\-specific cache (tcache)\&. The same considerations apply to this interface as to thread\&.tcache\&.flush, except that the tcache will never be automatically discarded\&. .RE .PP tcache\&.destroy (\fBunsigned\fR) \-w .RS 4 Flush the specified thread\-specific cache (tcache) and make the identifier available for use during a future tcache creation\&. .RE .PP arena\&.\&.initialized (\fBbool\fR) r\- .RS 4 Get whether the specified arena\*(Aqs statistics are initialized (i\&.e\&. the arena was initialized prior to the current epoch)\&. This interface can also be nominally used to query whether the merged statistics corresponding to \fBMALLCTL_ARENAS_ALL\fR are initialized (always true)\&. .RE .PP arena\&.\&.decay (\fBvoid\fR) \-\- .RS 4 Trigger decay\-based purging of unused dirty/muzzy pages for arena , or for all arenas if equals \fBMALLCTL_ARENAS_ALL\fR\&. The proportion of unused dirty/muzzy pages to be purged depends on the current time; see opt\&.dirty_decay_ms and opt\&.muzy_decay_ms for details\&. .RE .PP arena\&.\&.purge (\fBvoid\fR) \-\- .RS 4 Purge all unused dirty pages for arena , or for all arenas if equals \fBMALLCTL_ARENAS_ALL\fR\&. .RE .PP arena\&.\&.reset (\fBvoid\fR) \-\- .RS 4 Discard all of the arena\*(Aqs extant allocations\&. This interface can only be used with arenas explicitly created via arenas\&.create\&. None of the arena\*(Aqs discarded/cached allocations may accessed afterward\&. As part of this requirement, all thread caches which were used to allocate/deallocate in conjunction with the arena must be flushed beforehand\&. .RE .PP arena\&.\&.destroy (\fBvoid\fR) \-\- .RS 4 Destroy the arena\&. Discard all of the arena\*(Aqs extant allocations using the same mechanism as for arena\&.\&.reset (with all the same constraints and side effects), merge the arena stats into those accessible at arena index \fBMALLCTL_ARENAS_DESTROYED\fR, and then completely discard all metadata associated with the arena\&. Future calls to arenas\&.create may recycle the arena index\&. Destruction will fail if any threads are currently associated with the arena as a result of calls to thread\&.arena\&. .RE .PP arena\&.\&.dss (\fBconst char *\fR) rw .RS 4 Set the precedence of dss allocation as related to mmap allocation for arena , or for all arenas if equals \fBMALLCTL_ARENAS_ALL\fR\&. See opt\&.dss for supported settings\&. .RE .PP arena\&.\&.dirty_decay_ms (\fBssize_t\fR) rw .RS 4 Current per\-arena approximate time in milliseconds from the creation of a set of unused dirty pages until an equivalent set of unused dirty pages is purged and/or reused\&. Each time this interface is set, all currently unused dirty pages are considered to have fully decayed, which causes immediate purging of all unused dirty pages unless the decay time is set to \-1 (i\&.e\&. purging disabled)\&. See opt\&.dirty_decay_ms for additional information\&. .RE .PP arena\&.\&.muzzy_decay_ms (\fBssize_t\fR) rw .RS 4 Current per\-arena approximate time in milliseconds from the creation of a set of unused muzzy pages until an equivalent set of unused muzzy pages is purged and/or reused\&. Each time this interface is set, all currently unused muzzy pages are considered to have fully decayed, which causes immediate purging of all unused muzzy pages unless the decay time is set to \-1 (i\&.e\&. purging disabled)\&. See opt\&.muzzy_decay_ms for additional information\&. .RE .PP arena\&.\&.retain_grow_limit (\fBsize_t\fR) rw .RS 4 Maximum size to grow retained region (only relevant when opt\&.retain is enabled)\&. This controls the maximum increment to expand virtual memory, or allocation through arena\&.extent_hooks\&. In particular, if customized extent hooks reserve physical memory (e\&.g\&. 1G huge pages), this is useful to control the allocation hook\*(Aqs input size\&. The default is no limit\&. .RE .PP arena\&.\&.extent_hooks (\fBextent_hooks_t *\fR) rw .RS 4 Get or set the extent management hook functions for arena \&. The functions must be capable of operating on all extant extents associated with arena , usually by passing unknown extents to the replaced functions\&. In practice, it is feasible to control allocation for arenas explicitly created via arenas\&.create -such that all extents originate from an application\-supplied extent allocator (by specifying the custom extent hook functions during arena creation), but the automatically created arenas will have already created extents prior to the application having an opportunity to take over extent allocation\&. +such that all extents originate from an application\-supplied extent allocator (by specifying the custom extent hook functions during arena creation)\&. However, the API guarantees for the automatically created arenas may be relaxed \-\- hooks set there may be called in a "best effort" fashion; in addition there may be extents created prior to the application having an opportunity to take over extent allocation\&. .sp .if n \{\ .RS 4 .\} .nf typedef extent_hooks_s extent_hooks_t; 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; }; .fi .if n \{\ .RE .\} .sp The \fBextent_hooks_t\fR structure comprises function pointers which are described individually below\&. jemalloc uses these functions to manage extent lifetime, which starts off with allocation of mapped committed memory, in the simplest case followed by deallocation\&. However, there are performance and platform reasons to retain extents for later reuse\&. Cleanup attempts cascade from deallocation to decommit to forced purging to lazy purging, which gives the extent management functions opportunities to reject the most permanent cleanup operations in favor of less permanent (and often less costly) operations\&. All operations except allocation can be universally opted out of by setting the hook pointers to \fBNULL\fR, or selectively opted out of by returning failure\&. Note that once the extent hook is set, the structure is accessed directly by the associated arenas, so it must remain valid for the entire lifetime of the arenas\&. .HP \w'typedef\ void\ *(extent_alloc_t)('u .BI "typedef void *(extent_alloc_t)(extent_hooks_t\ *" "extent_hooks" ", void\ *" "new_addr" ", size_t\ " "size" ", size_t\ " "alignment" ", bool\ *" "zero" ", bool\ *" "commit" ", unsigned\ " "arena_ind" ");" .sp .if n \{\ .RS 4 .\} .nf .fi .if n \{\ .RE .\} .sp An extent allocation function conforms to the \fBextent_alloc_t\fR type and upon success returns a pointer to \fIsize\fR bytes of mapped memory on behalf of arena \fIarena_ind\fR such that the extent\*(Aqs base address is a multiple of \fIalignment\fR, as well as setting \fI*zero\fR to indicate whether the extent is zeroed and \fI*commit\fR to indicate whether the extent is committed\&. Upon error the function returns \fBNULL\fR and leaves \fI*zero\fR and \fI*commit\fR unmodified\&. The \fIsize\fR parameter is always a multiple of the page size\&. The \fIalignment\fR parameter is always a power of two at least as large as the page size\&. Zeroing is mandatory if \fI*zero\fR is true upon function entry\&. Committing is mandatory if \fI*commit\fR is true upon function entry\&. If \fInew_addr\fR is not \fBNULL\fR, the returned pointer must be \fInew_addr\fR on success or \fBNULL\fR on error\&. Committed memory may be committed in absolute terms as on a system that does not overcommit, or in implicit terms as on a system that overcommits and satisfies physical memory needs on demand via soft page faults\&. Note that replacing the default extent allocation function makes the arena\*(Aqs arena\&.\&.dss setting irrelevant\&. .HP \w'typedef\ bool\ (extent_dalloc_t)('u .BI "typedef bool (extent_dalloc_t)(extent_hooks_t\ *" "extent_hooks" ", void\ *" "addr" ", size_t\ " "size" ", bool\ " "committed" ", unsigned\ " "arena_ind" ");" .sp .if n \{\ .RS 4 .\} .nf .fi .if n \{\ .RE .\} .sp An extent deallocation function conforms to the \fBextent_dalloc_t\fR type and deallocates an extent at given \fIaddr\fR and \fIsize\fR with \fIcommitted\fR/decommited memory as indicated, on behalf of arena \fIarena_ind\fR, returning false upon success\&. If the function returns true, this indicates opt\-out from deallocation; the virtual memory mapping associated with the extent remains mapped, in the same commit state, and available for future use, in which case it will be automatically retained for later reuse\&. .HP \w'typedef\ void\ (extent_destroy_t)('u .BI "typedef void (extent_destroy_t)(extent_hooks_t\ *" "extent_hooks" ", void\ *" "addr" ", size_t\ " "size" ", bool\ " "committed" ", unsigned\ " "arena_ind" ");" .sp .if n \{\ .RS 4 .\} .nf .fi .if n \{\ .RE .\} .sp An extent destruction function conforms to the \fBextent_destroy_t\fR type and unconditionally destroys an extent at given \fIaddr\fR and \fIsize\fR with \fIcommitted\fR/decommited memory as indicated, on behalf of arena \fIarena_ind\fR\&. This function may be called to destroy retained extents during arena destruction (see arena\&.\&.destroy)\&. .HP \w'typedef\ bool\ (extent_commit_t)('u .BI "typedef bool (extent_commit_t)(extent_hooks_t\ *" "extent_hooks" ", void\ *" "addr" ", size_t\ " "size" ", size_t\ " "offset" ", size_t\ " "length" ", unsigned\ " "arena_ind" ");" .sp .if n \{\ .RS 4 .\} .nf .fi .if n \{\ .RE .\} .sp An extent commit function conforms to the \fBextent_commit_t\fR type and commits zeroed physical memory to back pages within an extent at given \fIaddr\fR and \fIsize\fR at \fIoffset\fR bytes, extending for \fIlength\fR on behalf of arena \fIarena_ind\fR, returning false upon success\&. Committed memory may be committed in absolute terms as on a system that does not overcommit, or in implicit terms as on a system that overcommits and satisfies physical memory needs on demand via soft page faults\&. If the function returns true, this indicates insufficient physical memory to satisfy the request\&. .HP \w'typedef\ bool\ (extent_decommit_t)('u .BI "typedef bool (extent_decommit_t)(extent_hooks_t\ *" "extent_hooks" ", void\ *" "addr" ", size_t\ " "size" ", size_t\ " "offset" ", size_t\ " "length" ", unsigned\ " "arena_ind" ");" .sp .if n \{\ .RS 4 .\} .nf .fi .if n \{\ .RE .\} .sp An extent decommit function conforms to the \fBextent_decommit_t\fR type and decommits any physical memory that is backing pages within an extent at given \fIaddr\fR and \fIsize\fR at \fIoffset\fR bytes, extending for \fIlength\fR on behalf of arena \fIarena_ind\fR, returning false upon success, in which case the pages will be committed via the extent commit function before being reused\&. If the function returns true, this indicates opt\-out from decommit; the memory remains committed and available for future use, in which case it will be automatically retained for later reuse\&. .HP \w'typedef\ bool\ (extent_purge_t)('u .BI "typedef bool (extent_purge_t)(extent_hooks_t\ *" "extent_hooks" ", void\ *" "addr" ", size_t\ " "size" ", size_t\ " "offset" ", size_t\ " "length" ", unsigned\ " "arena_ind" ");" .sp .if n \{\ .RS 4 .\} .nf .fi .if n \{\ .RE .\} .sp An extent purge function conforms to the \fBextent_purge_t\fR type and discards physical pages within the virtual memory mapping associated with an extent at given \fIaddr\fR and \fIsize\fR at \fIoffset\fR bytes, extending for \fIlength\fR on behalf of arena \fIarena_ind\fR\&. A lazy extent purge function (e\&.g\&. implemented via madvise(\fI\&.\&.\&.\fR\fI\fBMADV_FREE\fR\fR)) can delay purging indefinitely and leave the pages within the purged virtual memory range in an indeterminite state, whereas a forced extent purge function immediately purges, and the pages within the virtual memory range will be zero\-filled the next time they are accessed\&. If the function returns true, this indicates failure to purge\&. .HP \w'typedef\ bool\ (extent_split_t)('u .BI "typedef bool (extent_split_t)(extent_hooks_t\ *" "extent_hooks" ", void\ *" "addr" ", size_t\ " "size" ", size_t\ " "size_a" ", size_t\ " "size_b" ", bool\ " "committed" ", unsigned\ " "arena_ind" ");" .sp .if n \{\ .RS 4 .\} .nf .fi .if n \{\ .RE .\} .sp An extent split function conforms to the \fBextent_split_t\fR type and optionally splits an extent at given \fIaddr\fR and \fIsize\fR into two adjacent extents, the first of \fIsize_a\fR bytes, and the second of \fIsize_b\fR bytes, operating on \fIcommitted\fR/decommitted memory as indicated, on behalf of arena \fIarena_ind\fR, returning false upon success\&. If the function returns true, this indicates that the extent remains unsplit and therefore should continue to be operated on as a whole\&. .HP \w'typedef\ bool\ (extent_merge_t)('u .BI "typedef bool (extent_merge_t)(extent_hooks_t\ *" "extent_hooks" ", void\ *" "addr_a" ", size_t\ " "size_a" ", void\ *" "addr_b" ", size_t\ " "size_b" ", bool\ " "committed" ", unsigned\ " "arena_ind" ");" .sp .if n \{\ .RS 4 .\} .nf .fi .if n \{\ .RE .\} .sp An extent merge function conforms to the \fBextent_merge_t\fR type and optionally merges adjacent extents, at given \fIaddr_a\fR and \fIsize_a\fR with given \fIaddr_b\fR and \fIsize_b\fR into one contiguous extent, operating on \fIcommitted\fR/decommitted memory as indicated, on behalf of arena \fIarena_ind\fR, returning false upon success\&. If the function returns true, this indicates that the extents remain distinct mappings and therefore should continue to be operated on independently\&. .RE .PP arenas\&.narenas (\fBunsigned\fR) r\- .RS 4 Current limit on number of arenas\&. .RE .PP arenas\&.dirty_decay_ms (\fBssize_t\fR) rw .RS 4 Current default per\-arena approximate time in milliseconds from the creation of a set of unused dirty pages until an equivalent set of unused dirty pages is purged and/or reused, used to initialize arena\&.\&.dirty_decay_ms during arena creation\&. See opt\&.dirty_decay_ms for additional information\&. .RE .PP arenas\&.muzzy_decay_ms (\fBssize_t\fR) rw .RS 4 Current default per\-arena approximate time in milliseconds from the creation of a set of unused muzzy pages until an equivalent set of unused muzzy pages is purged and/or reused, used to initialize arena\&.\&.muzzy_decay_ms during arena creation\&. See opt\&.muzzy_decay_ms for additional information\&. .RE .PP arenas\&.quantum (\fBsize_t\fR) r\- .RS 4 Quantum size\&. .RE .PP arenas\&.page (\fBsize_t\fR) r\- .RS 4 Page size\&. .RE .PP arenas\&.tcache_max (\fBsize_t\fR) r\- .RS 4 Maximum thread\-cached size class\&. .RE .PP arenas\&.nbins (\fBunsigned\fR) r\- .RS 4 Number of bin size classes\&. .RE .PP arenas\&.nhbins (\fBunsigned\fR) r\- .RS 4 Total number of thread cache bin size classes\&. .RE .PP arenas\&.bin\&.\&.size (\fBsize_t\fR) r\- .RS 4 Maximum size supported by size class\&. .RE .PP arenas\&.bin\&.\&.nregs (\fBuint32_t\fR) r\- .RS 4 Number of regions per slab\&. .RE .PP arenas\&.bin\&.\&.slab_size (\fBsize_t\fR) r\- .RS 4 Number of bytes per slab\&. .RE .PP arenas\&.nlextents (\fBunsigned\fR) r\- .RS 4 Total number of large size classes\&. .RE .PP arenas\&.lextent\&.\&.size (\fBsize_t\fR) r\- .RS 4 Maximum size supported by this large size class\&. .RE .PP arenas\&.create (\fBunsigned\fR, \fBextent_hooks_t *\fR) rw .RS 4 Explicitly create a new arena outside the range of automatically managed arenas, with optionally specified extent hooks, and return the new arena index\&. .RE .PP arenas\&.lookup (\fBunsigned\fR, \fBvoid*\fR) rw .RS 4 Index of the arena to which an allocation belongs to\&. .RE .PP prof\&.thread_active_init (\fBbool\fR) rw [\fB\-\-enable\-prof\fR] .RS 4 Control the initial setting for thread\&.prof\&.active in newly created threads\&. See the opt\&.prof_thread_active_init option for additional information\&. .RE .PP prof\&.active (\fBbool\fR) rw [\fB\-\-enable\-prof\fR] .RS 4 Control whether sampling is currently active\&. See the opt\&.prof_active option for additional information, as well as the interrelated thread\&.prof\&.active mallctl\&. .RE .PP prof\&.dump (\fBconst char *\fR) \-w [\fB\-\-enable\-prof\fR] .RS 4 Dump a memory profile to the specified file, or if NULL is specified, to a file according to the pattern \&.\&.\&.m\&.heap, where is controlled by the opt\&.prof_prefix option\&. .RE .PP prof\&.gdump (\fBbool\fR) rw [\fB\-\-enable\-prof\fR] .RS 4 When enabled, trigger a memory profile dump every time the total virtual memory exceeds the previous maximum\&. Profiles are dumped to files named according to the pattern \&.\&.\&.u\&.heap, where is controlled by the opt\&.prof_prefix option\&. .RE .PP prof\&.reset (\fBsize_t\fR) \-w [\fB\-\-enable\-prof\fR] .RS 4 Reset all memory profile statistics, and optionally update the sample rate (see opt\&.lg_prof_sample and prof\&.lg_sample)\&. .RE .PP prof\&.lg_sample (\fBsize_t\fR) r\- [\fB\-\-enable\-prof\fR] .RS 4 Get the current sample rate (see opt\&.lg_prof_sample)\&. .RE .PP prof\&.interval (\fBuint64_t\fR) r\- [\fB\-\-enable\-prof\fR] .RS 4 Average number of bytes allocated between interval\-based profile dumps\&. See the opt\&.lg_prof_interval option for additional information\&. .RE .PP stats\&.allocated (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Total number of bytes allocated by the application\&. .RE .PP stats\&.active (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Total number of bytes in active pages allocated by the application\&. This is a multiple of the page size, and greater than or equal to stats\&.allocated\&. This does not include stats\&.arenas\&.\&.pdirty, stats\&.arenas\&.\&.pmuzzy, nor pages entirely devoted to allocator metadata\&. .RE .PP stats\&.metadata (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Total number of bytes dedicated to metadata, which comprise base allocations used for bootstrap\-sensitive allocator metadata structures (see stats\&.arenas\&.\&.base) and internal allocations (see stats\&.arenas\&.\&.internal)\&. Transparent huge page (enabled with opt\&.metadata_thp) usage is not considered\&. .RE .PP stats\&.metadata_thp (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Number of transparent huge pages (THP) used for metadata\&. See stats\&.metadata and opt\&.metadata_thp) for details\&. .RE .PP stats\&.resident (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Maximum number of bytes in physically resident data pages mapped by the allocator, comprising all pages dedicated to allocator metadata, pages backing active allocations, and unused dirty pages\&. This is a maximum rather than precise because pages may not actually be physically resident if they correspond to demand\-zeroed virtual memory that has not yet been touched\&. This is a multiple of the page size, and is larger than stats\&.active\&. .RE .PP stats\&.mapped (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Total number of bytes in active extents mapped by the allocator\&. This is larger than stats\&.active\&. This does not include inactive extents, even those that contain unused dirty pages, which means that there is no strict ordering between this and stats\&.resident\&. .RE .PP stats\&.retained (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Total number of bytes in virtual memory mappings that were retained rather than being returned to the operating system via e\&.g\&. \fBmunmap\fR(2) or similar\&. Retained virtual memory is typically untouched, decommitted, or purged, so it has no strongly associated physical memory (see extent hooks for details)\&. Retained memory is excluded from mapped memory statistics, e\&.g\&. stats\&.mapped\&. .RE .PP stats\&.background_thread\&.num_threads (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Number of background threads running currently\&. .RE .PP stats\&.background_thread\&.num_runs (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Total number of runs from all background threads\&. .RE .PP stats\&.background_thread\&.run_interval (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Average run interval in nanoseconds of background threads\&. .RE .PP stats\&.mutexes\&.ctl\&.{counter}; (\fBcounter specific type\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Statistics on \fIctl\fR mutex (global scope; mallctl related)\&. {counter} is one of the counters below: .PP .RS 4 \fInum_ops\fR (\fBuint64_t\fR): Total number of lock acquisition operations on this mutex\&. .sp \fInum_spin_acq\fR (\fBuint64_t\fR): Number of times the mutex was spin\-acquired\&. When the mutex is currently locked and cannot be acquired immediately, a short period of spin\-retry within jemalloc will be performed\&. Acquired through spin generally means the contention was lightweight and not causing context switches\&. .sp \fInum_wait\fR (\fBuint64_t\fR): Number of times the mutex was wait\-acquired, which means the mutex contention was not solved by spin\-retry, and blocking operation was likely involved in order to acquire the mutex\&. This event generally implies higher cost / longer delay, and should be investigated if it happens often\&. .sp \fImax_wait_time\fR (\fBuint64_t\fR): Maximum length of time in nanoseconds spent on a single wait\-acquired lock operation\&. Note that to avoid profiling overhead on the common path, this does not consider spin\-acquired cases\&. .sp \fItotal_wait_time\fR (\fBuint64_t\fR): Cumulative time in nanoseconds spent on wait\-acquired lock operations\&. Similarly, spin\-acquired cases are not considered\&. .sp \fImax_num_thds\fR (\fBuint32_t\fR): Maximum number of threads waiting on this mutex simultaneously\&. Similarly, spin\-acquired cases are not considered\&. .sp \fInum_owner_switch\fR (\fBuint64_t\fR): Number of times the current mutex owner is different from the previous one\&. This event does not generally imply an issue; rather it is an indicator of how often the protected data are accessed by different threads\&. .RE .RE .PP stats\&.mutexes\&.background_thread\&.{counter} (\fBcounter specific type\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Statistics on \fIbackground_thread\fR mutex (global scope; background_thread related)\&. {counter} is one of the counters in mutex profiling counters\&. .RE .PP stats\&.mutexes\&.prof\&.{counter} (\fBcounter specific type\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Statistics on \fIprof\fR mutex (global scope; profiling related)\&. {counter} is one of the counters in mutex profiling counters\&. .RE .PP stats\&.mutexes\&.reset (\fBvoid\fR) \-\- [\fB\-\-enable\-stats\fR] .RS 4 Reset all mutex profile statistics, including global mutexes, arena mutexes and bin mutexes\&. .RE .PP stats\&.arenas\&.\&.dss (\fBconst char *\fR) r\- .RS 4 dss (\fBsbrk\fR(2)) allocation precedence as related to \fBmmap\fR(2) allocation\&. See opt\&.dss for details\&. .RE .PP stats\&.arenas\&.\&.dirty_decay_ms (\fBssize_t\fR) r\- .RS 4 Approximate time in milliseconds from the creation of a set of unused dirty pages until an equivalent set of unused dirty pages is purged and/or reused\&. See opt\&.dirty_decay_ms for details\&. .RE .PP stats\&.arenas\&.\&.muzzy_decay_ms (\fBssize_t\fR) r\- .RS 4 Approximate time in milliseconds from the creation of a set of unused muzzy pages until an equivalent set of unused muzzy pages is purged and/or reused\&. See opt\&.muzzy_decay_ms for details\&. .RE .PP stats\&.arenas\&.\&.nthreads (\fBunsigned\fR) r\- .RS 4 Number of threads currently assigned to arena\&. .RE .PP stats\&.arenas\&.\&.uptime (\fBuint64_t\fR) r\- .RS 4 Time elapsed (in nanoseconds) since the arena was created\&. If equals \fB0\fR or \fBMALLCTL_ARENAS_ALL\fR, this is the uptime since malloc initialization\&. .RE .PP stats\&.arenas\&.\&.pactive (\fBsize_t\fR) r\- .RS 4 Number of pages in active extents\&. .RE .PP stats\&.arenas\&.\&.pdirty (\fBsize_t\fR) r\- .RS 4 Number of pages within unused extents that are potentially dirty, and for which madvise() or similar has not been called\&. See opt\&.dirty_decay_ms for a description of dirty pages\&. .RE .PP stats\&.arenas\&.\&.pmuzzy (\fBsize_t\fR) r\- .RS 4 Number of pages within unused extents that are muzzy\&. See opt\&.muzzy_decay_ms for a description of muzzy pages\&. .RE .PP stats\&.arenas\&.\&.mapped (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Number of mapped bytes\&. .RE .PP stats\&.arenas\&.\&.retained (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Number of retained bytes\&. See stats\&.retained for details\&. .RE .PP +stats\&.arenas\&.\&.extent_avail (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] +.RS 4 +Number of allocated (but unused) extent structs in this arena\&. +.RE +.PP stats\&.arenas\&.\&.base (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Number of bytes dedicated to bootstrap\-sensitive allocator metadata structures\&. .RE .PP stats\&.arenas\&.\&.internal (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Number of bytes dedicated to internal allocations\&. Internal allocations differ from application\-originated allocations in that they are for internal use, and that they are omitted from heap profiles\&. .RE .PP stats\&.arenas\&.\&.metadata_thp (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Number of transparent huge pages (THP) used for metadata\&. See opt\&.metadata_thp for details\&. .RE .PP stats\&.arenas\&.\&.resident (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Maximum number of bytes in physically resident data pages mapped by the arena, comprising all pages dedicated to allocator metadata, pages backing active allocations, and unused dirty pages\&. This is a maximum rather than precise because pages may not actually be physically resident if they correspond to demand\-zeroed virtual memory that has not yet been touched\&. This is a multiple of the page size\&. .RE .PP stats\&.arenas\&.\&.dirty_npurge (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Number of dirty page purge sweeps performed\&. .RE .PP stats\&.arenas\&.\&.dirty_nmadvise (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Number of madvise() or similar calls made to purge dirty pages\&. .RE .PP stats\&.arenas\&.\&.dirty_purged (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Number of dirty pages purged\&. .RE .PP stats\&.arenas\&.\&.muzzy_npurge (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Number of muzzy page purge sweeps performed\&. .RE .PP stats\&.arenas\&.\&.muzzy_nmadvise (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Number of madvise() or similar calls made to purge muzzy pages\&. .RE .PP stats\&.arenas\&.\&.muzzy_purged (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Number of muzzy pages purged\&. .RE .PP stats\&.arenas\&.\&.small\&.allocated (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Number of bytes currently allocated by small objects\&. .RE .PP stats\&.arenas\&.\&.small\&.nmalloc (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Cumulative number of times a small allocation was requested from the arena\*(Aqs bins, whether to fill the relevant tcache if opt\&.tcache is enabled, or to directly satisfy an allocation request otherwise\&. .RE .PP stats\&.arenas\&.\&.small\&.ndalloc (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Cumulative number of times a small allocation was returned to the arena\*(Aqs bins, whether to flush the relevant tcache if opt\&.tcache is enabled, or to directly deallocate an allocation otherwise\&. .RE .PP stats\&.arenas\&.\&.small\&.nrequests (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Cumulative number of allocation requests satisfied by all bin size classes\&. .RE .PP +stats\&.arenas\&.\&.small\&.nfills (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] +.RS 4 +Cumulative number of tcache fills by all small size classes\&. +.RE +.PP +stats\&.arenas\&.\&.small\&.nflushes (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] +.RS 4 +Cumulative number of tcache flushes by all small size classes\&. +.RE +.PP stats\&.arenas\&.\&.large\&.allocated (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Number of bytes currently allocated by large objects\&. .RE .PP stats\&.arenas\&.\&.large\&.nmalloc (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Cumulative number of times a large extent was allocated from the arena, whether to fill the relevant tcache if opt\&.tcache is enabled and the size class is within the range being cached, or to directly satisfy an allocation request otherwise\&. .RE .PP stats\&.arenas\&.\&.large\&.ndalloc (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Cumulative number of times a large extent was returned to the arena, whether to flush the relevant tcache if opt\&.tcache is enabled and the size class is within the range being cached, or to directly deallocate an allocation otherwise\&. .RE .PP stats\&.arenas\&.\&.large\&.nrequests (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Cumulative number of allocation requests satisfied by all large size classes\&. .RE .PP +stats\&.arenas\&.\&.large\&.nfills (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] +.RS 4 +Cumulative number of tcache fills by all large size classes\&. +.RE +.PP +stats\&.arenas\&.\&.large\&.nflushes (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] +.RS 4 +Cumulative number of tcache flushes by all large size classes\&. +.RE +.PP stats\&.arenas\&.\&.bins\&.\&.nmalloc (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Cumulative number of times a bin region of the corresponding size class was allocated from the arena, whether to fill the relevant tcache if opt\&.tcache is enabled, or to directly satisfy an allocation request otherwise\&. .RE .PP stats\&.arenas\&.\&.bins\&.\&.ndalloc (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Cumulative number of times a bin region of the corresponding size class was returned to the arena, whether to flush the relevant tcache if opt\&.tcache is enabled, or to directly deallocate an allocation otherwise\&. .RE .PP stats\&.arenas\&.\&.bins\&.\&.nrequests (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Cumulative number of allocation requests satisfied by bin regions of the corresponding size class\&. .RE .PP stats\&.arenas\&.\&.bins\&.\&.curregs (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Current number of regions for this size class\&. .RE .PP stats\&.arenas\&.\&.bins\&.\&.nfills (\fBuint64_t\fR) r\- .RS 4 Cumulative number of tcache fills\&. .RE .PP stats\&.arenas\&.\&.bins\&.\&.nflushes (\fBuint64_t\fR) r\- .RS 4 Cumulative number of tcache flushes\&. .RE .PP stats\&.arenas\&.\&.bins\&.\&.nslabs (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Cumulative number of slabs created\&. .RE .PP stats\&.arenas\&.\&.bins\&.\&.nreslabs (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Cumulative number of times the current slab from which to allocate changed\&. .RE .PP stats\&.arenas\&.\&.bins\&.\&.curslabs (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Current number of slabs\&. .RE .PP +stats\&.arenas\&.\&.bins\&.\&.nonfull_slabs (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] +.RS 4 +Current number of nonfull slabs\&. +.RE +.PP stats\&.arenas\&.\&.bins\&.\&.mutex\&.{counter} (\fBcounter specific type\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Statistics on \fIarena\&.\&.bins\&.\fR mutex (arena bin scope; bin operation related)\&. {counter} is one of the counters in mutex profiling counters\&. +.RE +.PP +stats\&.arenas\&.\&.extents\&.\&.n{extent_type} (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] +.RS 4 +Number of extents of the given type in this arena in the bucket corresponding to page size index \&. The extent type is one of dirty, muzzy, or retained\&. +.RE +.PP +stats\&.arenas\&.\&.extents\&.\&.{extent_type}_bytes (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] +.RS 4 +Sum of the bytes managed by extents of the given type in this arena in the bucket corresponding to page size index \&. The extent type is one of dirty, muzzy, or retained\&. .RE .PP stats\&.arenas\&.\&.lextents\&.\&.nmalloc (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Cumulative number of times a large extent of the corresponding size class was allocated from the arena, whether to fill the relevant tcache if opt\&.tcache is enabled and the size class is within the range being cached, or to directly satisfy an allocation request otherwise\&. .RE .PP stats\&.arenas\&.\&.lextents\&.\&.ndalloc (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Cumulative number of times a large extent of the corresponding size class was returned to the arena, whether to flush the relevant tcache if opt\&.tcache is enabled and the size class is within the range being cached, or to directly deallocate an allocation otherwise\&. .RE .PP stats\&.arenas\&.\&.lextents\&.\&.nrequests (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Cumulative number of allocation requests satisfied by large extents of the corresponding size class\&. .RE .PP stats\&.arenas\&.\&.lextents\&.\&.curlextents (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Current number of large allocations for this size class\&. .RE .PP stats\&.arenas\&.\&.mutexes\&.large\&.{counter} (\fBcounter specific type\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Statistics on \fIarena\&.\&.large\fR mutex (arena scope; large allocation related)\&. {counter} is one of the counters in mutex profiling counters\&. .RE .PP stats\&.arenas\&.\&.mutexes\&.extent_avail\&.{counter} (\fBcounter specific type\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Statistics on \fIarena\&.\&.extent_avail \fR mutex (arena scope; extent avail related)\&. {counter} is one of the counters in mutex profiling counters\&. .RE .PP stats\&.arenas\&.\&.mutexes\&.extents_dirty\&.{counter} (\fBcounter specific type\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Statistics on \fIarena\&.\&.extents_dirty \fR mutex (arena scope; dirty extents related)\&. {counter} is one of the counters in mutex profiling counters\&. .RE .PP stats\&.arenas\&.\&.mutexes\&.extents_muzzy\&.{counter} (\fBcounter specific type\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Statistics on \fIarena\&.\&.extents_muzzy \fR mutex (arena scope; muzzy extents related)\&. {counter} is one of the counters in mutex profiling counters\&. .RE .PP stats\&.arenas\&.\&.mutexes\&.extents_retained\&.{counter} (\fBcounter specific type\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Statistics on \fIarena\&.\&.extents_retained \fR mutex (arena scope; retained extents related)\&. {counter} is one of the counters in mutex profiling counters\&. .RE .PP stats\&.arenas\&.\&.mutexes\&.decay_dirty\&.{counter} (\fBcounter specific type\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Statistics on \fIarena\&.\&.decay_dirty \fR mutex (arena scope; decay for dirty pages related)\&. {counter} is one of the counters in mutex profiling counters\&. .RE .PP stats\&.arenas\&.\&.mutexes\&.decay_muzzy\&.{counter} (\fBcounter specific type\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Statistics on \fIarena\&.\&.decay_muzzy \fR mutex (arena scope; decay for muzzy pages related)\&. {counter} is one of the counters in mutex profiling counters\&. .RE .PP stats\&.arenas\&.\&.mutexes\&.base\&.{counter} (\fBcounter specific type\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Statistics on \fIarena\&.\&.base\fR mutex (arena scope; base allocator related)\&. {counter} is one of the counters in mutex profiling counters\&. .RE .PP stats\&.arenas\&.\&.mutexes\&.tcache_list\&.{counter} (\fBcounter specific type\fR) r\- [\fB\-\-enable\-stats\fR] .RS 4 Statistics on \fIarena\&.\&.tcache_list\fR mutex (arena scope; tcache to arena association related)\&. This mutex is expected to be accessed less often\&. {counter} is one of the counters in mutex profiling counters\&. .RE .SH "HEAP PROFILE FORMAT" .PP Although the heap profiling functionality was originally designed to be compatible with the \fBpprof\fR command that is developed as part of the \m[blue]\fBgperftools package\fR\m[]\&\s-2\u[3]\d\s+2, the addition of per thread heap profiling functionality required a different heap profile format\&. The \fBjeprof\fR command is derived from \fBpprof\fR, with enhancements to support the heap profile format described here\&. .PP In the following hypothetical heap profile, \fB[\&.\&.\&.]\fR indicates elision for the sake of compactness\&. .sp .if n \{\ .RS 4 .\} .nf heap_v2/524288 t*: 28106: 56637512 [0: 0] [\&.\&.\&.] t3: 352: 16777344 [0: 0] [\&.\&.\&.] t99: 17754: 29341640 [0: 0] [\&.\&.\&.] @ 0x5f86da8 0x5f5a1dc [\&.\&.\&.] 0x29e4d4e 0xa200316 0xabb2988 [\&.\&.\&.] t*: 13: 6688 [0: 0] t3: 12: 6496 [0: ] t99: 1: 192 [0: 0] [\&.\&.\&.] MAPPED_LIBRARIES: [\&.\&.\&.] .fi .if n \{\ .RE .\} .sp The following matches the above heap profile, but most tokens are replaced with \fB\fR to indicate descriptions of the corresponding fields\&. .sp .if n \{\ .RS 4 .\} .nf / : : [: ] [\&.\&.\&.] : : [: ] [\&.\&.\&.] : : [: ] [\&.\&.\&.] @ [\&.\&.\&.] [\&.\&.\&.] : : [: ] : : [: ] : : [: ] [\&.\&.\&.] MAPPED_LIBRARIES: /maps> .fi .if n \{\ .RE .\} .SH "DEBUGGING MALLOC PROBLEMS" .PP When debugging, it is a good idea to configure/build jemalloc with the \fB\-\-enable\-debug\fR and \fB\-\-enable\-fill\fR options, and recompile the program with suitable options and symbols for debugger support\&. When so configured, jemalloc incorporates a wide variety of run\-time assertions that catch application errors such as double\-free, write\-after\-free, etc\&. .PP Programs often accidentally depend on \(lquninitialized\(rq memory actually being filled with zero bytes\&. Junk filling (see the opt\&.junk option) tends to expose such bugs in the form of obviously incorrect results and/or coredumps\&. Conversely, zero filling (see the opt\&.zero option) eliminates the symptoms of such bugs\&. Between these two options, it is usually possible to quickly detect, diagnose, and eliminate such bugs\&. .PP This implementation does not provide much detail about the problems it detects, because the performance impact for storing such information would be prohibitive\&. .SH "DIAGNOSTIC MESSAGES" .PP If any of the memory allocation/deallocation functions detect an error or warning condition, a message will be printed to file descriptor \fBSTDERR_FILENO\fR\&. Errors will result in the process dumping core\&. If the opt\&.abort option is set, most warnings are treated as errors\&. .PP The \fImalloc_message\fR variable allows the programmer to override the function which emits the text strings forming the errors and warnings if for some reason the \fBSTDERR_FILENO\fR file descriptor is not suitable for this\&. malloc_message() takes the \fIcbopaque\fR pointer argument that is \fBNULL\fR unless overridden by the arguments in a call to malloc_stats_print(), followed by a string pointer\&. Please note that doing anything which tries to allocate memory in this function is likely to result in a crash or deadlock\&. .PP All messages are prefixed by \(lq: \(rq\&. .SH "RETURN VALUES" .SS "Standard API" .PP The malloc() and calloc() functions return a pointer to the allocated memory if successful; otherwise a \fBNULL\fR pointer is returned and \fIerrno\fR is set to ENOMEM\&. .PP The posix_memalign() function returns the value 0 if successful; otherwise it returns an error value\&. The posix_memalign() function will fail if: .PP EINVAL .RS 4 The \fIalignment\fR parameter is not a power of 2 at least as large as sizeof(\fBvoid *\fR)\&. .RE .PP ENOMEM .RS 4 Memory allocation error\&. .RE .PP The aligned_alloc() function returns a pointer to the allocated memory if successful; otherwise a \fBNULL\fR pointer is returned and \fIerrno\fR is set\&. The aligned_alloc() function will fail if: .PP EINVAL .RS 4 The \fIalignment\fR parameter is not a power of 2\&. .RE .PP ENOMEM .RS 4 Memory allocation error\&. .RE .PP The realloc() function returns a pointer, possibly identical to \fIptr\fR, to the allocated memory if successful; otherwise a \fBNULL\fR pointer is returned, and \fIerrno\fR is set to ENOMEM if the error was the result of an allocation failure\&. The realloc() function always leaves the original buffer intact when an error occurs\&. .PP The free() function returns no value\&. .SS "Non\-standard API" .PP The mallocx() and rallocx() functions return a pointer to the allocated memory if successful; otherwise a \fBNULL\fR pointer is returned to indicate insufficient contiguous memory was available to service the allocation request\&. .PP The xallocx() function returns the real size of the resulting resized allocation pointed to by \fIptr\fR, which is a value less than \fIsize\fR if the allocation could not be adequately grown in place\&. .PP The sallocx() function returns the real size of the allocation pointed to by \fIptr\fR\&. .PP The nallocx() returns the real size that would result from a successful equivalent mallocx() function call, or zero if insufficient memory is available to perform the size computation\&. .PP The mallctl(), mallctlnametomib(), and mallctlbymib() functions return 0 on success; otherwise they return an error value\&. The functions will fail if: .PP EINVAL .RS 4 \fInewp\fR is not \fBNULL\fR, and \fInewlen\fR is too large or too small\&. Alternatively, \fI*oldlenp\fR is too large or too small; in this case as much data as possible are read despite the error\&. .RE .PP ENOENT .RS 4 \fIname\fR or \fImib\fR specifies an unknown/invalid value\&. .RE .PP EPERM .RS 4 Attempt to read or write void value, or attempt to write read\-only value\&. .RE .PP EAGAIN .RS 4 A memory allocation failure occurred\&. .RE .PP EFAULT .RS 4 An interface with side effects failed in some way not directly related to mallctl*() read/write processing\&. .RE .PP The malloc_usable_size() function returns the usable size of the allocation pointed to by \fIptr\fR\&. .SH "ENVIRONMENT" .PP The following environment variable affects the execution of the allocation functions: .PP \fBMALLOC_CONF\fR .RS 4 If the environment variable \fBMALLOC_CONF\fR is set, the characters it contains will be interpreted as options\&. .RE .SH "EXAMPLES" .PP To dump core whenever a problem occurs: .sp .if n \{\ .RS 4 .\} .nf ln \-s \*(Aqabort:true\*(Aq /etc/malloc\&.conf .fi .if n \{\ .RE .\} .PP To specify in the source that only one arena should be automatically created: .sp .if n \{\ .RS 4 .\} .nf malloc_conf = "narenas:1"; .fi .if n \{\ .RE .\} .SH "SEE ALSO" .PP \fBmadvise\fR(2), \fBmmap\fR(2), \fBsbrk\fR(2), \fButrace\fR(2), \fBalloca\fR(3), \fBatexit\fR(3), \fBgetpagesize\fR(3) .SH "STANDARDS" .PP The malloc(), calloc(), realloc(), and free() functions conform to ISO/IEC 9899:1990 (\(lqISO C90\(rq)\&. .PP The posix_memalign() function conforms to IEEE Std 1003\&.1\-2001 (\(lqPOSIX\&.1\(rq)\&. .SH "HISTORY" .PP The malloc_usable_size() and posix_memalign() functions first appeared in FreeBSD 7\&.0\&. .PP The aligned_alloc(), malloc_stats_print(), and mallctl*() functions first appeared in FreeBSD 10\&.0\&. .PP The *allocx() functions first appeared in FreeBSD 11\&.0\&. .SH "AUTHOR" .PP \fBJason Evans\fR .RS 4 .RE .SH "NOTES" .IP " 1." 4 jemalloc website .RS 4 \%http://jemalloc.net/ .RE .IP " 2." 4 JSON format .RS 4 \%http://www.json.org/ .RE .IP " 3." 4 gperftools package .RS 4 \%http://code.google.com/p/gperftools/ .RE Index: head/contrib/jemalloc/include/jemalloc/internal/size_classes.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/size_classes.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/size_classes.h (nonexistent) @@ -1,5556 +0,0 @@ -#ifndef JEMALLOC_INTERNAL_SIZE_CLASSES_H -#define JEMALLOC_INTERNAL_SIZE_CLASSES_H - -/* This file was automatically generated by size_classes.sh. */ - -#include "jemalloc/internal/jemalloc_internal_types.h" - -/* - * This header file defines: - * - * LG_SIZE_CLASS_GROUP: Lg of size class count for each size doubling. - * LG_TINY_MIN: Lg of minimum size class to support. - * SIZE_CLASSES: Complete table of SC(index, lg_grp, lg_delta, ndelta, psz, - * bin, pgs, lg_delta_lookup) tuples. - * index: Size class index. - * lg_grp: Lg group base size (no deltas added). - * lg_delta: Lg delta to previous size class. - * ndelta: Delta multiplier. size == 1< 256) -# error "Too many small size classes" -#endif - -#endif /* JEMALLOC_INTERNAL_SIZE_CLASSES_H */ Property changes on: head/contrib/jemalloc/include/jemalloc/internal/size_classes.h ___________________________________________________________________ Deleted: svn:eol-style ## -1 +0,0 ## -native \ No newline at end of property Deleted: svn:keywords ## -1 +0,0 ## -FreeBSD=%H \ No newline at end of property Deleted: svn:mime-type ## -1 +0,0 ## -text/plain \ No newline at end of property Index: head/contrib/jemalloc/include/jemalloc/internal/hooks.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/hooks.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/hooks.h (nonexistent) @@ -1,12 +0,0 @@ -#ifndef JEMALLOC_INTERNAL_HOOKS_H -#define JEMALLOC_INTERNAL_HOOKS_H - -extern JEMALLOC_EXPORT void (*hooks_arena_new_hook)(); -extern JEMALLOC_EXPORT void (*hooks_libc_hook)(); - -#define JEMALLOC_HOOK(fn, hook) ((void)(hook != NULL && (hook(), 0)), fn) - -/* Note that this is undef'd and re-define'd in src/prof.c. */ -#define _Unwind_Backtrace JEMALLOC_HOOK(_Unwind_Backtrace, hooks_libc_hook) - -#endif /* JEMALLOC_INTERNAL_HOOKS_H */ Property changes on: head/contrib/jemalloc/include/jemalloc/internal/hooks.h ___________________________________________________________________ Deleted: svn:eol-style ## -1 +0,0 ## -native \ No newline at end of property Deleted: svn:keywords ## -1 +0,0 ## -FreeBSD=%H \ No newline at end of property Deleted: svn:mime-type ## -1 +0,0 ## -text/plain \ No newline at end of property Index: head/contrib/jemalloc/include/jemalloc/internal/arena_externs.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/arena_externs.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/arena_externs.h (revision 360233) @@ -1,94 +1,104 @@ #ifndef JEMALLOC_INTERNAL_ARENA_EXTERNS_H #define JEMALLOC_INTERNAL_ARENA_EXTERNS_H #include "jemalloc/internal/bin.h" #include "jemalloc/internal/extent_dss.h" +#include "jemalloc/internal/hook.h" #include "jemalloc/internal/pages.h" -#include "jemalloc/internal/size_classes.h" #include "jemalloc/internal/stats.h" extern ssize_t opt_dirty_decay_ms; extern ssize_t opt_muzzy_decay_ms; extern percpu_arena_mode_t opt_percpu_arena; extern const char *percpu_arena_mode_names[]; extern const uint64_t h_steps[SMOOTHSTEP_NSTEPS]; extern malloc_mutex_t arenas_lock; +extern size_t opt_oversize_threshold; +extern size_t oversize_threshold; + void arena_basic_stats_merge(tsdn_t *tsdn, arena_t *arena, unsigned *nthreads, const char **dss, ssize_t *dirty_decay_ms, ssize_t *muzzy_decay_ms, size_t *nactive, size_t *ndirty, size_t *nmuzzy); void arena_stats_merge(tsdn_t *tsdn, arena_t *arena, unsigned *nthreads, const char **dss, ssize_t *dirty_decay_ms, ssize_t *muzzy_decay_ms, size_t *nactive, size_t *ndirty, size_t *nmuzzy, arena_stats_t *astats, - bin_stats_t *bstats, arena_stats_large_t *lstats); + bin_stats_t *bstats, arena_stats_large_t *lstats, + arena_stats_extents_t *estats); void arena_extents_dirty_dalloc(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent); #ifdef JEMALLOC_JET size_t arena_slab_regind(extent_t *slab, szind_t binind, const void *ptr); #endif extent_t *arena_extent_alloc_large(tsdn_t *tsdn, arena_t *arena, size_t usize, size_t alignment, bool *zero); void arena_extent_dalloc_large_prep(tsdn_t *tsdn, arena_t *arena, extent_t *extent); void arena_extent_ralloc_large_shrink(tsdn_t *tsdn, arena_t *arena, extent_t *extent, size_t oldsize); void arena_extent_ralloc_large_expand(tsdn_t *tsdn, arena_t *arena, extent_t *extent, size_t oldsize); ssize_t arena_dirty_decay_ms_get(arena_t *arena); bool arena_dirty_decay_ms_set(tsdn_t *tsdn, arena_t *arena, ssize_t decay_ms); ssize_t arena_muzzy_decay_ms_get(arena_t *arena); bool arena_muzzy_decay_ms_set(tsdn_t *tsdn, arena_t *arena, ssize_t decay_ms); void arena_decay(tsdn_t *tsdn, arena_t *arena, bool is_background_thread, bool all); void arena_reset(tsd_t *tsd, arena_t *arena); void arena_destroy(tsd_t *tsd, arena_t *arena); void arena_tcache_fill_small(tsdn_t *tsdn, arena_t *arena, tcache_t *tcache, cache_bin_t *tbin, szind_t binind, uint64_t prof_accumbytes); void arena_alloc_junk_small(void *ptr, const bin_info_t *bin_info, bool zero); typedef void (arena_dalloc_junk_small_t)(void *, const bin_info_t *); extern arena_dalloc_junk_small_t *JET_MUTABLE arena_dalloc_junk_small; void *arena_malloc_hard(tsdn_t *tsdn, arena_t *arena, size_t size, szind_t ind, bool zero); void *arena_palloc(tsdn_t *tsdn, arena_t *arena, size_t usize, size_t alignment, bool zero, tcache_t *tcache); -void arena_prof_promote(tsdn_t *tsdn, const void *ptr, size_t usize); +void arena_prof_promote(tsdn_t *tsdn, void *ptr, size_t usize); void arena_dalloc_promoted(tsdn_t *tsdn, void *ptr, tcache_t *tcache, bool slow_path); -void arena_dalloc_bin_junked_locked(tsdn_t *tsdn, arena_t *arena, - extent_t *extent, void *ptr); +void arena_dalloc_bin_junked_locked(tsdn_t *tsdn, arena_t *arena, bin_t *bin, + szind_t binind, extent_t *extent, void *ptr); void arena_dalloc_small(tsdn_t *tsdn, void *ptr); bool arena_ralloc_no_move(tsdn_t *tsdn, void *ptr, size_t oldsize, size_t size, - size_t extra, bool zero); + size_t extra, bool zero, size_t *newsize); void *arena_ralloc(tsdn_t *tsdn, arena_t *arena, void *ptr, size_t oldsize, - size_t size, size_t alignment, bool zero, tcache_t *tcache); + size_t size, size_t alignment, bool zero, tcache_t *tcache, + hook_ralloc_args_t *hook_args); dss_prec_t arena_dss_prec_get(arena_t *arena); bool arena_dss_prec_set(arena_t *arena, dss_prec_t dss_prec); ssize_t arena_dirty_decay_ms_default_get(void); bool arena_dirty_decay_ms_default_set(ssize_t decay_ms); ssize_t arena_muzzy_decay_ms_default_get(void); bool arena_muzzy_decay_ms_default_set(ssize_t decay_ms); bool arena_retain_grow_limit_get_set(tsd_t *tsd, arena_t *arena, size_t *old_limit, size_t *new_limit); unsigned arena_nthreads_get(arena_t *arena, bool internal); void arena_nthreads_inc(arena_t *arena, bool internal); void arena_nthreads_dec(arena_t *arena, bool internal); size_t arena_extent_sn_next(arena_t *arena); arena_t *arena_new(tsdn_t *tsdn, unsigned ind, extent_hooks_t *extent_hooks); -void arena_boot(void); +bool arena_init_huge(void); +bool arena_is_huge(unsigned arena_ind); +arena_t *arena_choose_huge(tsd_t *tsd); +bin_t *arena_bin_choose_lock(tsdn_t *tsdn, arena_t *arena, szind_t binind, + unsigned *binshard); +void arena_boot(sc_data_t *sc_data); void arena_prefork0(tsdn_t *tsdn, arena_t *arena); void arena_prefork1(tsdn_t *tsdn, arena_t *arena); void arena_prefork2(tsdn_t *tsdn, arena_t *arena); void arena_prefork3(tsdn_t *tsdn, arena_t *arena); void arena_prefork4(tsdn_t *tsdn, arena_t *arena); void arena_prefork5(tsdn_t *tsdn, arena_t *arena); void arena_prefork6(tsdn_t *tsdn, arena_t *arena); void arena_prefork7(tsdn_t *tsdn, arena_t *arena); void arena_postfork_parent(tsdn_t *tsdn, arena_t *arena); void arena_postfork_child(tsdn_t *tsdn, arena_t *arena); #endif /* JEMALLOC_INTERNAL_ARENA_EXTERNS_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/arena_inlines_b.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/arena_inlines_b.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/arena_inlines_b.h (revision 360233) @@ -1,354 +1,427 @@ #ifndef JEMALLOC_INTERNAL_ARENA_INLINES_B_H #define JEMALLOC_INTERNAL_ARENA_INLINES_B_H #include "jemalloc/internal/jemalloc_internal_types.h" #include "jemalloc/internal/mutex.h" #include "jemalloc/internal/rtree.h" -#include "jemalloc/internal/size_classes.h" +#include "jemalloc/internal/sc.h" #include "jemalloc/internal/sz.h" #include "jemalloc/internal/ticker.h" +JEMALLOC_ALWAYS_INLINE bool +arena_has_default_hooks(arena_t *arena) { + return (extent_hooks_get(arena) == &extent_hooks_default); +} + +JEMALLOC_ALWAYS_INLINE arena_t * +arena_choose_maybe_huge(tsd_t *tsd, arena_t *arena, size_t size) { + if (arena != NULL) { + return arena; + } + + /* + * For huge allocations, use the dedicated huge arena if both are true: + * 1) is using auto arena selection (i.e. arena == NULL), and 2) the + * thread is not assigned to a manual arena. + */ + if (unlikely(size >= oversize_threshold)) { + arena_t *tsd_arena = tsd_arena_get(tsd); + if (tsd_arena == NULL || arena_is_auto(tsd_arena)) { + return arena_choose_huge(tsd); + } + } + + return arena_choose(tsd, NULL); +} + JEMALLOC_ALWAYS_INLINE prof_tctx_t * arena_prof_tctx_get(tsdn_t *tsdn, const void *ptr, alloc_ctx_t *alloc_ctx) { cassert(config_prof); assert(ptr != NULL); /* Static check. */ if (alloc_ctx == NULL) { const extent_t *extent = iealloc(tsdn, ptr); if (unlikely(!extent_slab_get(extent))) { return large_prof_tctx_get(tsdn, extent); } } else { if (unlikely(!alloc_ctx->slab)) { return large_prof_tctx_get(tsdn, iealloc(tsdn, ptr)); } } return (prof_tctx_t *)(uintptr_t)1U; } JEMALLOC_ALWAYS_INLINE void -arena_prof_tctx_set(tsdn_t *tsdn, const void *ptr, UNUSED size_t usize, +arena_prof_tctx_set(tsdn_t *tsdn, const void *ptr, size_t usize, alloc_ctx_t *alloc_ctx, prof_tctx_t *tctx) { cassert(config_prof); assert(ptr != NULL); /* Static check. */ if (alloc_ctx == NULL) { extent_t *extent = iealloc(tsdn, ptr); if (unlikely(!extent_slab_get(extent))) { large_prof_tctx_set(tsdn, extent, tctx); } } else { if (unlikely(!alloc_ctx->slab)) { large_prof_tctx_set(tsdn, iealloc(tsdn, ptr), tctx); } } } static inline void -arena_prof_tctx_reset(tsdn_t *tsdn, const void *ptr, UNUSED prof_tctx_t *tctx) { +arena_prof_tctx_reset(tsdn_t *tsdn, const void *ptr, prof_tctx_t *tctx) { cassert(config_prof); assert(ptr != NULL); extent_t *extent = iealloc(tsdn, ptr); assert(!extent_slab_get(extent)); large_prof_tctx_reset(tsdn, extent); } +JEMALLOC_ALWAYS_INLINE nstime_t +arena_prof_alloc_time_get(tsdn_t *tsdn, const void *ptr, + alloc_ctx_t *alloc_ctx) { + cassert(config_prof); + assert(ptr != NULL); + + extent_t *extent = iealloc(tsdn, ptr); + /* + * Unlike arena_prof_prof_tctx_{get, set}, we only call this once we're + * sure we have a sampled allocation. + */ + assert(!extent_slab_get(extent)); + return large_prof_alloc_time_get(extent); +} + JEMALLOC_ALWAYS_INLINE void +arena_prof_alloc_time_set(tsdn_t *tsdn, const void *ptr, alloc_ctx_t *alloc_ctx, + nstime_t t) { + cassert(config_prof); + assert(ptr != NULL); + + extent_t *extent = iealloc(tsdn, ptr); + assert(!extent_slab_get(extent)); + large_prof_alloc_time_set(extent, t); +} + +JEMALLOC_ALWAYS_INLINE void arena_decay_ticks(tsdn_t *tsdn, arena_t *arena, unsigned nticks) { tsd_t *tsd; ticker_t *decay_ticker; if (unlikely(tsdn_null(tsdn))) { return; } tsd = tsdn_tsd(tsdn); decay_ticker = decay_ticker_get(tsd, arena_ind_get(arena)); if (unlikely(decay_ticker == NULL)) { return; } if (unlikely(ticker_ticks(decay_ticker, nticks))) { arena_decay(tsdn, arena, false, false); } } JEMALLOC_ALWAYS_INLINE void arena_decay_tick(tsdn_t *tsdn, arena_t *arena) { malloc_mutex_assert_not_owner(tsdn, &arena->decay_dirty.mtx); malloc_mutex_assert_not_owner(tsdn, &arena->decay_muzzy.mtx); arena_decay_ticks(tsdn, arena, 1); } +/* Purge a single extent to retained / unmapped directly. */ +JEMALLOC_ALWAYS_INLINE void +arena_decay_extent(tsdn_t *tsdn,arena_t *arena, extent_hooks_t **r_extent_hooks, + extent_t *extent) { + size_t extent_size = extent_size_get(extent); + extent_dalloc_wrapper(tsdn, arena, + r_extent_hooks, extent); + if (config_stats) { + /* Update stats accordingly. */ + arena_stats_lock(tsdn, &arena->stats); + arena_stats_add_u64(tsdn, &arena->stats, + &arena->decay_dirty.stats->nmadvise, 1); + arena_stats_add_u64(tsdn, &arena->stats, + &arena->decay_dirty.stats->purged, extent_size >> LG_PAGE); + arena_stats_sub_zu(tsdn, &arena->stats, &arena->stats.mapped, + extent_size); + arena_stats_unlock(tsdn, &arena->stats); + } +} + JEMALLOC_ALWAYS_INLINE void * arena_malloc(tsdn_t *tsdn, arena_t *arena, size_t size, szind_t ind, bool zero, tcache_t *tcache, bool slow_path) { assert(!tsdn_null(tsdn) || tcache == NULL); - assert(size != 0); if (likely(tcache != NULL)) { - if (likely(size <= SMALL_MAXCLASS)) { + if (likely(size <= SC_SMALL_MAXCLASS)) { return tcache_alloc_small(tsdn_tsd(tsdn), arena, tcache, size, ind, zero, slow_path); } if (likely(size <= tcache_maxclass)) { return tcache_alloc_large(tsdn_tsd(tsdn), arena, tcache, size, ind, zero, slow_path); } /* (size > tcache_maxclass) case falls through. */ assert(size > tcache_maxclass); } return arena_malloc_hard(tsdn, arena, size, ind, zero); } JEMALLOC_ALWAYS_INLINE arena_t * arena_aalloc(tsdn_t *tsdn, const void *ptr) { return extent_arena_get(iealloc(tsdn, ptr)); } JEMALLOC_ALWAYS_INLINE size_t arena_salloc(tsdn_t *tsdn, const void *ptr) { assert(ptr != NULL); rtree_ctx_t rtree_ctx_fallback; rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); szind_t szind = rtree_szind_read(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr, true); - assert(szind != NSIZES); + assert(szind != SC_NSIZES); return sz_index2size(szind); } JEMALLOC_ALWAYS_INLINE size_t arena_vsalloc(tsdn_t *tsdn, const void *ptr) { /* * Return 0 if ptr is not within an extent managed by jemalloc. This * function has two extra costs relative to isalloc(): * - The rtree calls cannot claim to be dependent lookups, which induces * rtree lookup load dependencies. * - The lookup may fail, so there is an extra branch to check for * failure. */ rtree_ctx_t rtree_ctx_fallback; rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); extent_t *extent; szind_t szind; if (rtree_extent_szind_read(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr, false, &extent, &szind)) { return 0; } if (extent == NULL) { return 0; } assert(extent_state_get(extent) == extent_state_active); /* Only slab members should be looked up via interior pointers. */ assert(extent_addr_get(extent) == ptr || extent_slab_get(extent)); - assert(szind != NSIZES); + assert(szind != SC_NSIZES); return sz_index2size(szind); } static inline void +arena_dalloc_large_no_tcache(tsdn_t *tsdn, void *ptr, szind_t szind) { + if (config_prof && unlikely(szind < SC_NBINS)) { + arena_dalloc_promoted(tsdn, ptr, NULL, true); + } else { + extent_t *extent = iealloc(tsdn, ptr); + large_dalloc(tsdn, extent); + } +} + +static inline void arena_dalloc_no_tcache(tsdn_t *tsdn, void *ptr) { assert(ptr != NULL); rtree_ctx_t rtree_ctx_fallback; rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); szind_t szind; bool slab; rtree_szind_slab_read(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr, true, &szind, &slab); if (config_debug) { extent_t *extent = rtree_extent_read(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr, true); assert(szind == extent_szind_get(extent)); - assert(szind < NSIZES); + assert(szind < SC_NSIZES); assert(slab == extent_slab_get(extent)); } if (likely(slab)) { /* Small allocation. */ arena_dalloc_small(tsdn, ptr); } else { + arena_dalloc_large_no_tcache(tsdn, ptr, szind); + } +} + +JEMALLOC_ALWAYS_INLINE void +arena_dalloc_large(tsdn_t *tsdn, void *ptr, tcache_t *tcache, szind_t szind, + bool slow_path) { + if (szind < nhbins) { + if (config_prof && unlikely(szind < SC_NBINS)) { + arena_dalloc_promoted(tsdn, ptr, tcache, slow_path); + } else { + tcache_dalloc_large(tsdn_tsd(tsdn), tcache, ptr, szind, + slow_path); + } + } else { extent_t *extent = iealloc(tsdn, ptr); large_dalloc(tsdn, extent); } } JEMALLOC_ALWAYS_INLINE void arena_dalloc(tsdn_t *tsdn, void *ptr, tcache_t *tcache, alloc_ctx_t *alloc_ctx, bool slow_path) { assert(!tsdn_null(tsdn) || tcache == NULL); assert(ptr != NULL); if (unlikely(tcache == NULL)) { arena_dalloc_no_tcache(tsdn, ptr); return; } szind_t szind; bool slab; rtree_ctx_t *rtree_ctx; if (alloc_ctx != NULL) { szind = alloc_ctx->szind; slab = alloc_ctx->slab; - assert(szind != NSIZES); + assert(szind != SC_NSIZES); } else { rtree_ctx = tsd_rtree_ctx(tsdn_tsd(tsdn)); rtree_szind_slab_read(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr, true, &szind, &slab); } if (config_debug) { rtree_ctx = tsd_rtree_ctx(tsdn_tsd(tsdn)); extent_t *extent = rtree_extent_read(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr, true); assert(szind == extent_szind_get(extent)); - assert(szind < NSIZES); + assert(szind < SC_NSIZES); assert(slab == extent_slab_get(extent)); } if (likely(slab)) { /* Small allocation. */ tcache_dalloc_small(tsdn_tsd(tsdn), tcache, ptr, szind, slow_path); } else { - if (szind < nhbins) { - if (config_prof && unlikely(szind < NBINS)) { - arena_dalloc_promoted(tsdn, ptr, tcache, - slow_path); - } else { - tcache_dalloc_large(tsdn_tsd(tsdn), tcache, ptr, - szind, slow_path); - } - } else { - extent_t *extent = iealloc(tsdn, ptr); - large_dalloc(tsdn, extent); - } + arena_dalloc_large(tsdn, ptr, tcache, szind, slow_path); } } static inline void arena_sdalloc_no_tcache(tsdn_t *tsdn, void *ptr, size_t size) { assert(ptr != NULL); - assert(size <= LARGE_MAXCLASS); + assert(size <= SC_LARGE_MAXCLASS); szind_t szind; bool slab; if (!config_prof || !opt_prof) { /* * There is no risk of being confused by a promoted sampled * object, so base szind and slab on the given size. */ szind = sz_size2index(size); - slab = (szind < NBINS); + slab = (szind < SC_NBINS); } if ((config_prof && opt_prof) || config_debug) { rtree_ctx_t rtree_ctx_fallback; rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); rtree_szind_slab_read(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr, true, &szind, &slab); assert(szind == sz_size2index(size)); - assert((config_prof && opt_prof) || slab == (szind < NBINS)); + assert((config_prof && opt_prof) || slab == (szind < SC_NBINS)); if (config_debug) { extent_t *extent = rtree_extent_read(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr, true); assert(szind == extent_szind_get(extent)); assert(slab == extent_slab_get(extent)); } } if (likely(slab)) { /* Small allocation. */ arena_dalloc_small(tsdn, ptr); } else { - extent_t *extent = iealloc(tsdn, ptr); - large_dalloc(tsdn, extent); + arena_dalloc_large_no_tcache(tsdn, ptr, szind); } } JEMALLOC_ALWAYS_INLINE void arena_sdalloc(tsdn_t *tsdn, void *ptr, size_t size, tcache_t *tcache, alloc_ctx_t *alloc_ctx, bool slow_path) { assert(!tsdn_null(tsdn) || tcache == NULL); assert(ptr != NULL); - assert(size <= LARGE_MAXCLASS); + assert(size <= SC_LARGE_MAXCLASS); if (unlikely(tcache == NULL)) { arena_sdalloc_no_tcache(tsdn, ptr, size); return; } szind_t szind; bool slab; - UNUSED alloc_ctx_t local_ctx; + alloc_ctx_t local_ctx; if (config_prof && opt_prof) { if (alloc_ctx == NULL) { /* Uncommon case and should be a static check. */ rtree_ctx_t rtree_ctx_fallback; rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); rtree_szind_slab_read(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr, true, &local_ctx.szind, &local_ctx.slab); assert(local_ctx.szind == sz_size2index(size)); alloc_ctx = &local_ctx; } slab = alloc_ctx->slab; szind = alloc_ctx->szind; } else { /* * There is no risk of being confused by a promoted sampled * object, so base szind and slab on the given size. */ szind = sz_size2index(size); - slab = (szind < NBINS); + slab = (szind < SC_NBINS); } if (config_debug) { rtree_ctx_t *rtree_ctx = tsd_rtree_ctx(tsdn_tsd(tsdn)); rtree_szind_slab_read(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr, true, &szind, &slab); extent_t *extent = rtree_extent_read(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr, true); assert(szind == extent_szind_get(extent)); assert(slab == extent_slab_get(extent)); } if (likely(slab)) { /* Small allocation. */ tcache_dalloc_small(tsdn_tsd(tsdn), tcache, ptr, szind, slow_path); } else { - if (szind < nhbins) { - if (config_prof && unlikely(szind < NBINS)) { - arena_dalloc_promoted(tsdn, ptr, tcache, - slow_path); - } else { - tcache_dalloc_large(tsdn_tsd(tsdn), - tcache, ptr, szind, slow_path); - } - } else { - extent_t *extent = iealloc(tsdn, ptr); - large_dalloc(tsdn, extent); - } + arena_dalloc_large(tsdn, ptr, tcache, szind, slow_path); } } #endif /* JEMALLOC_INTERNAL_ARENA_INLINES_B_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/arena_stats.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/arena_stats.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/arena_stats.h (revision 360233) @@ -1,237 +1,271 @@ #ifndef JEMALLOC_INTERNAL_ARENA_STATS_H #define JEMALLOC_INTERNAL_ARENA_STATS_H #include "jemalloc/internal/atomic.h" #include "jemalloc/internal/mutex.h" #include "jemalloc/internal/mutex_prof.h" -#include "jemalloc/internal/size_classes.h" +#include "jemalloc/internal/sc.h" +JEMALLOC_DIAGNOSTIC_DISABLE_SPURIOUS + /* * In those architectures that support 64-bit atomics, we use atomic updates for * our 64-bit values. Otherwise, we use a plain uint64_t and synchronize * externally. */ #ifdef JEMALLOC_ATOMIC_U64 typedef atomic_u64_t arena_stats_u64_t; #else /* Must hold the arena stats mutex while reading atomically. */ typedef uint64_t arena_stats_u64_t; #endif typedef struct arena_stats_large_s arena_stats_large_t; struct arena_stats_large_s { /* * Total number of allocation/deallocation requests served directly by * the arena. */ arena_stats_u64_t nmalloc; arena_stats_u64_t ndalloc; /* * Number of allocation requests that correspond to this size class. * This includes requests served by tcache, though tcache only * periodically merges into this counter. */ arena_stats_u64_t nrequests; /* Partially derived. */ + /* + * Number of tcache fills / flushes for large (similarly, periodically + * merged). Note that there is no large tcache batch-fill currently + * (i.e. only fill 1 at a time); however flush may be batched. + */ + arena_stats_u64_t nfills; /* Partially derived. */ + arena_stats_u64_t nflushes; /* Partially derived. */ /* Current number of allocations of this size class. */ size_t curlextents; /* Derived. */ }; typedef struct arena_stats_decay_s arena_stats_decay_t; struct arena_stats_decay_s { /* Total number of purge sweeps. */ arena_stats_u64_t npurge; /* Total number of madvise calls made. */ arena_stats_u64_t nmadvise; /* Total number of pages purged. */ arena_stats_u64_t purged; }; +typedef struct arena_stats_extents_s arena_stats_extents_t; +struct arena_stats_extents_s { + /* + * Stats for a given index in the range [0, SC_NPSIZES] in an extents_t. + * We track both bytes and # of extents: two extents in the same bucket + * may have different sizes if adjacent size classes differ by more than + * a page, so bytes cannot always be derived from # of extents. + */ + atomic_zu_t ndirty; + atomic_zu_t dirty_bytes; + atomic_zu_t nmuzzy; + atomic_zu_t muzzy_bytes; + atomic_zu_t nretained; + atomic_zu_t retained_bytes; +}; + /* * Arena stats. Note that fields marked "derived" are not directly maintained * within the arena code; rather their values are derived during stats merge * requests. */ typedef struct arena_stats_s arena_stats_t; struct arena_stats_s { #ifndef JEMALLOC_ATOMIC_U64 malloc_mutex_t mtx; #endif /* Number of bytes currently mapped, excluding retained memory. */ atomic_zu_t mapped; /* Partially derived. */ /* * Number of unused virtual memory bytes currently retained. Retained * bytes are technically mapped (though always decommitted or purged), * but they are excluded from the mapped statistic (above). */ atomic_zu_t retained; /* Derived. */ + /* Number of extent_t structs allocated by base, but not being used. */ + atomic_zu_t extent_avail; + arena_stats_decay_t decay_dirty; arena_stats_decay_t decay_muzzy; atomic_zu_t base; /* Derived. */ atomic_zu_t internal; atomic_zu_t resident; /* Derived. */ atomic_zu_t metadata_thp; atomic_zu_t allocated_large; /* Derived. */ arena_stats_u64_t nmalloc_large; /* Derived. */ arena_stats_u64_t ndalloc_large; /* Derived. */ + arena_stats_u64_t nfills_large; /* Derived. */ + arena_stats_u64_t nflushes_large; /* Derived. */ arena_stats_u64_t nrequests_large; /* Derived. */ + /* VM space had to be leaked (undocumented). Normally 0. */ + atomic_zu_t abandoned_vm; + /* Number of bytes cached in tcache associated with this arena. */ atomic_zu_t tcache_bytes; /* Derived. */ mutex_prof_data_t mutex_prof_data[mutex_prof_num_arena_mutexes]; /* One element for each large size class. */ - arena_stats_large_t lstats[NSIZES - NBINS]; + arena_stats_large_t lstats[SC_NSIZES - SC_NBINS]; /* Arena uptime. */ nstime_t uptime; }; static inline bool -arena_stats_init(UNUSED tsdn_t *tsdn, arena_stats_t *arena_stats) { +arena_stats_init(tsdn_t *tsdn, arena_stats_t *arena_stats) { if (config_debug) { for (size_t i = 0; i < sizeof(arena_stats_t); i++) { assert(((char *)arena_stats)[i] == 0); } } #ifndef JEMALLOC_ATOMIC_U64 if (malloc_mutex_init(&arena_stats->mtx, "arena_stats", WITNESS_RANK_ARENA_STATS, malloc_mutex_rank_exclusive)) { return true; } #endif /* Memory is zeroed, so there is no need to clear stats. */ return false; } static inline void arena_stats_lock(tsdn_t *tsdn, arena_stats_t *arena_stats) { #ifndef JEMALLOC_ATOMIC_U64 malloc_mutex_lock(tsdn, &arena_stats->mtx); #endif } static inline void arena_stats_unlock(tsdn_t *tsdn, arena_stats_t *arena_stats) { #ifndef JEMALLOC_ATOMIC_U64 malloc_mutex_unlock(tsdn, &arena_stats->mtx); #endif } static inline uint64_t arena_stats_read_u64(tsdn_t *tsdn, arena_stats_t *arena_stats, arena_stats_u64_t *p) { #ifdef JEMALLOC_ATOMIC_U64 return atomic_load_u64(p, ATOMIC_RELAXED); #else malloc_mutex_assert_owner(tsdn, &arena_stats->mtx); return *p; #endif } static inline void arena_stats_add_u64(tsdn_t *tsdn, arena_stats_t *arena_stats, arena_stats_u64_t *p, uint64_t x) { #ifdef JEMALLOC_ATOMIC_U64 atomic_fetch_add_u64(p, x, ATOMIC_RELAXED); #else malloc_mutex_assert_owner(tsdn, &arena_stats->mtx); *p += x; #endif } -UNUSED static inline void +static inline void arena_stats_sub_u64(tsdn_t *tsdn, arena_stats_t *arena_stats, arena_stats_u64_t *p, uint64_t x) { #ifdef JEMALLOC_ATOMIC_U64 - UNUSED uint64_t r = atomic_fetch_sub_u64(p, x, ATOMIC_RELAXED); + uint64_t r = atomic_fetch_sub_u64(p, x, ATOMIC_RELAXED); assert(r - x <= r); #else malloc_mutex_assert_owner(tsdn, &arena_stats->mtx); *p -= x; assert(*p + x >= *p); #endif } /* * Non-atomically sets *dst += src. *dst needs external synchronization. * This lets us avoid the cost of a fetch_add when its unnecessary (note that * the types here are atomic). */ static inline void arena_stats_accum_u64(arena_stats_u64_t *dst, uint64_t src) { #ifdef JEMALLOC_ATOMIC_U64 uint64_t cur_dst = atomic_load_u64(dst, ATOMIC_RELAXED); atomic_store_u64(dst, src + cur_dst, ATOMIC_RELAXED); #else *dst += src; #endif } static inline size_t -arena_stats_read_zu(tsdn_t *tsdn, arena_stats_t *arena_stats, atomic_zu_t *p) { +arena_stats_read_zu(tsdn_t *tsdn, arena_stats_t *arena_stats, + atomic_zu_t *p) { #ifdef JEMALLOC_ATOMIC_U64 return atomic_load_zu(p, ATOMIC_RELAXED); #else malloc_mutex_assert_owner(tsdn, &arena_stats->mtx); return atomic_load_zu(p, ATOMIC_RELAXED); #endif } static inline void -arena_stats_add_zu(tsdn_t *tsdn, arena_stats_t *arena_stats, atomic_zu_t *p, - size_t x) { +arena_stats_add_zu(tsdn_t *tsdn, arena_stats_t *arena_stats, + atomic_zu_t *p, size_t x) { #ifdef JEMALLOC_ATOMIC_U64 atomic_fetch_add_zu(p, x, ATOMIC_RELAXED); #else malloc_mutex_assert_owner(tsdn, &arena_stats->mtx); size_t cur = atomic_load_zu(p, ATOMIC_RELAXED); atomic_store_zu(p, cur + x, ATOMIC_RELAXED); #endif } static inline void -arena_stats_sub_zu(tsdn_t *tsdn, arena_stats_t *arena_stats, atomic_zu_t *p, - size_t x) { +arena_stats_sub_zu(tsdn_t *tsdn, arena_stats_t *arena_stats, + atomic_zu_t *p, size_t x) { #ifdef JEMALLOC_ATOMIC_U64 - UNUSED size_t r = atomic_fetch_sub_zu(p, x, ATOMIC_RELAXED); + size_t r = atomic_fetch_sub_zu(p, x, ATOMIC_RELAXED); assert(r - x <= r); #else malloc_mutex_assert_owner(tsdn, &arena_stats->mtx); size_t cur = atomic_load_zu(p, ATOMIC_RELAXED); atomic_store_zu(p, cur - x, ATOMIC_RELAXED); #endif } /* Like the _u64 variant, needs an externally synchronized *dst. */ static inline void arena_stats_accum_zu(atomic_zu_t *dst, size_t src) { size_t cur_dst = atomic_load_zu(dst, ATOMIC_RELAXED); atomic_store_zu(dst, src + cur_dst, ATOMIC_RELAXED); } static inline void -arena_stats_large_nrequests_add(tsdn_t *tsdn, arena_stats_t *arena_stats, +arena_stats_large_flush_nrequests_add(tsdn_t *tsdn, arena_stats_t *arena_stats, szind_t szind, uint64_t nrequests) { arena_stats_lock(tsdn, arena_stats); - arena_stats_add_u64(tsdn, arena_stats, &arena_stats->lstats[szind - - NBINS].nrequests, nrequests); + arena_stats_large_t *lstats = &arena_stats->lstats[szind - SC_NBINS]; + arena_stats_add_u64(tsdn, arena_stats, &lstats->nrequests, nrequests); + arena_stats_add_u64(tsdn, arena_stats, &lstats->nflushes, 1); arena_stats_unlock(tsdn, arena_stats); } static inline void arena_stats_mapped_add(tsdn_t *tsdn, arena_stats_t *arena_stats, size_t size) { arena_stats_lock(tsdn, arena_stats); arena_stats_add_zu(tsdn, arena_stats, &arena_stats->mapped, size); arena_stats_unlock(tsdn, arena_stats); } - #endif /* JEMALLOC_INTERNAL_ARENA_STATS_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/arena_structs_b.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/arena_structs_b.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/arena_structs_b.h (revision 360233) @@ -1,229 +1,232 @@ #ifndef JEMALLOC_INTERNAL_ARENA_STRUCTS_B_H #define JEMALLOC_INTERNAL_ARENA_STRUCTS_B_H #include "jemalloc/internal/arena_stats.h" #include "jemalloc/internal/atomic.h" #include "jemalloc/internal/bin.h" #include "jemalloc/internal/bitmap.h" #include "jemalloc/internal/extent_dss.h" #include "jemalloc/internal/jemalloc_internal_types.h" #include "jemalloc/internal/mutex.h" #include "jemalloc/internal/nstime.h" #include "jemalloc/internal/ql.h" -#include "jemalloc/internal/size_classes.h" +#include "jemalloc/internal/sc.h" #include "jemalloc/internal/smoothstep.h" #include "jemalloc/internal/ticker.h" struct arena_decay_s { /* Synchronizes all non-atomic fields. */ malloc_mutex_t mtx; /* * True if a thread is currently purging the extents associated with * this decay structure. */ bool purging; /* * Approximate time in milliseconds from the creation of a set of unused * dirty pages until an equivalent set of unused dirty pages is purged * and/or reused. */ atomic_zd_t time_ms; /* time / SMOOTHSTEP_NSTEPS. */ nstime_t interval; /* * Time at which the current decay interval logically started. We do * not actually advance to a new epoch until sometime after it starts * because of scheduling and computation delays, and it is even possible * to completely skip epochs. In all cases, during epoch advancement we * merge all relevant activity into the most recently recorded epoch. */ nstime_t epoch; /* Deadline randomness generator. */ uint64_t jitter_state; /* * Deadline for current epoch. This is the sum of interval and per * epoch jitter which is a uniform random variable in [0..interval). * Epochs always advance by precise multiples of interval, but we * randomize the deadline to reduce the likelihood of arenas purging in * lockstep. */ nstime_t deadline; /* * Number of unpurged pages at beginning of current epoch. During epoch * advancement we use the delta between arena->decay_*.nunpurged and * extents_npages_get(&arena->extents_*) to determine how many dirty * pages, if any, were generated. */ size_t nunpurged; /* * Trailing log of how many unused dirty pages were generated during * each of the past SMOOTHSTEP_NSTEPS decay epochs, where the last * element is the most recent epoch. Corresponding epoch times are * relative to epoch. */ size_t backlog[SMOOTHSTEP_NSTEPS]; /* * Pointer to associated stats. These stats are embedded directly in * the arena's stats due to how stats structures are shared between the * arena and ctl code. * * Synchronization: Same as associated arena's stats field. */ arena_stats_decay_t *stats; /* Peak number of pages in associated extents. Used for debug only. */ uint64_t ceil_npages; }; struct arena_s { /* * Number of threads currently assigned to this arena. Each thread has * two distinct assignments, one for application-serving allocation, and * the other for internal metadata allocation. Internal metadata must * not be allocated from arenas explicitly created via the arenas.create * mallctl, because the arena..reset mallctl indiscriminately * discards all allocations for the affected arena. * * 0: Application allocation. * 1: Internal metadata allocation. * * Synchronization: atomic. */ atomic_u_t nthreads[2]; + /* Next bin shard for binding new threads. Synchronization: atomic. */ + atomic_u_t binshard_next; + /* * When percpu_arena is enabled, to amortize the cost of reading / * updating the current CPU id, track the most recent thread accessing * this arena, and only read CPU if there is a mismatch. */ tsdn_t *last_thd; /* Synchronization: internal. */ arena_stats_t stats; /* * Lists of tcaches and cache_bin_array_descriptors for extant threads * associated with this arena. Stats from these are merged * incrementally, and at exit if opt_stats_print is enabled. * * Synchronization: tcache_ql_mtx. */ ql_head(tcache_t) tcache_ql; ql_head(cache_bin_array_descriptor_t) cache_bin_array_descriptor_ql; malloc_mutex_t tcache_ql_mtx; /* Synchronization: internal. */ prof_accum_t prof_accum; - uint64_t prof_accumbytes; /* * PRNG state for cache index randomization of large allocation base * pointers. * * Synchronization: atomic. */ atomic_zu_t offset_state; /* * Extent serial number generator state. * * Synchronization: atomic. */ atomic_zu_t extent_sn_next; /* * Represents a dss_prec_t, but atomically. * * Synchronization: atomic. */ atomic_u_t dss_prec; /* * Number of pages in active extents. * * Synchronization: atomic. */ atomic_zu_t nactive; /* * Extant large allocations. * * Synchronization: large_mtx. */ extent_list_t large; /* Synchronizes all large allocation/update/deallocation. */ malloc_mutex_t large_mtx; /* * Collections of extents that were previously allocated. These are * used when allocating extents, in an attempt to re-use address space. * * Synchronization: internal. */ extents_t extents_dirty; extents_t extents_muzzy; extents_t extents_retained; /* * Decay-based purging state, responsible for scheduling extent state * transitions. * * Synchronization: internal. */ arena_decay_t decay_dirty; /* dirty --> muzzy */ arena_decay_t decay_muzzy; /* muzzy --> retained */ /* * Next extent size class in a growing series to use when satisfying a * request via the extent hooks (only if opt_retain). This limits the * number of disjoint virtual memory ranges so that extent merging can * be effective even if multiple arenas' extent allocation requests are * highly interleaved. * * retain_grow_limit is the max allowed size ind to expand (unless the * required size is greater). Default is no limit, and controlled * through mallctl only. * * Synchronization: extent_grow_mtx */ pszind_t extent_grow_next; pszind_t retain_grow_limit; malloc_mutex_t extent_grow_mtx; /* * Available extent structures that were allocated via * base_alloc_extent(). * * Synchronization: extent_avail_mtx. */ extent_tree_t extent_avail; + atomic_zu_t extent_avail_cnt; malloc_mutex_t extent_avail_mtx; /* * bins is used to store heaps of free regions. * * Synchronization: internal. */ - bin_t bins[NBINS]; + bins_t bins[SC_NBINS]; /* * Base allocator, from which arena metadata are allocated. * * Synchronization: internal. */ base_t *base; /* Used to determine uptime. Read-only after initialization. */ nstime_t create_time; }; /* Used in conjunction with tsd for fast arena-related context lookup. */ struct arena_tdata_s { ticker_t decay_ticker; }; /* Used to pass rtree lookup context down the path. */ struct alloc_ctx_s { szind_t szind; bool slab; }; #endif /* JEMALLOC_INTERNAL_ARENA_STRUCTS_B_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/arena_types.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/arena_types.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/arena_types.h (revision 360233) @@ -1,43 +1,51 @@ #ifndef JEMALLOC_INTERNAL_ARENA_TYPES_H #define JEMALLOC_INTERNAL_ARENA_TYPES_H +#include "jemalloc/internal/sc.h" + /* Maximum number of regions in one slab. */ -#define LG_SLAB_MAXREGS (LG_PAGE - LG_TINY_MIN) +#define LG_SLAB_MAXREGS (LG_PAGE - SC_LG_TINY_MIN) #define SLAB_MAXREGS (1U << LG_SLAB_MAXREGS) /* Default decay times in milliseconds. */ #define DIRTY_DECAY_MS_DEFAULT ZD(10 * 1000) -#define MUZZY_DECAY_MS_DEFAULT ZD(10 * 1000) +#define MUZZY_DECAY_MS_DEFAULT (0) /* Number of event ticks between time checks. */ #define DECAY_NTICKS_PER_UPDATE 1000 typedef struct arena_slab_data_s arena_slab_data_t; typedef struct arena_decay_s arena_decay_t; typedef struct arena_s arena_t; typedef struct arena_tdata_s arena_tdata_t; typedef struct alloc_ctx_s alloc_ctx_t; typedef enum { percpu_arena_mode_names_base = 0, /* Used for options processing. */ /* * *_uninit are used only during bootstrapping, and must correspond * to initialized variant plus percpu_arena_mode_enabled_base. */ percpu_arena_uninit = 0, per_phycpu_arena_uninit = 1, /* All non-disabled modes must come after percpu_arena_disabled. */ percpu_arena_disabled = 2, percpu_arena_mode_names_limit = 3, /* Used for options processing. */ percpu_arena_mode_enabled_base = 3, percpu_arena = 3, per_phycpu_arena = 4 /* Hyper threads share arena. */ } percpu_arena_mode_t; #define PERCPU_ARENA_ENABLED(m) ((m) >= percpu_arena_mode_enabled_base) #define PERCPU_ARENA_DEFAULT percpu_arena_disabled + +/* + * When allocation_size >= oversize_threshold, use the dedicated huge arena + * (unless have explicitly spicified arena index). 0 disables the feature. + */ +#define OVERSIZE_THRESHOLD_DEFAULT (8 << 20) #endif /* JEMALLOC_INTERNAL_ARENA_TYPES_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/atomic.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/atomic.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/atomic.h (revision 360233) @@ -1,77 +1,86 @@ #ifndef JEMALLOC_INTERNAL_ATOMIC_H #define JEMALLOC_INTERNAL_ATOMIC_H -#define ATOMIC_INLINE static inline +#define ATOMIC_INLINE JEMALLOC_ALWAYS_INLINE +#define JEMALLOC_U8_ATOMICS #if defined(JEMALLOC_GCC_ATOMIC_ATOMICS) # include "jemalloc/internal/atomic_gcc_atomic.h" +# if !defined(JEMALLOC_GCC_U8_ATOMIC_ATOMICS) +# undef JEMALLOC_U8_ATOMICS +# endif #elif defined(JEMALLOC_GCC_SYNC_ATOMICS) # include "jemalloc/internal/atomic_gcc_sync.h" +# if !defined(JEMALLOC_GCC_U8_SYNC_ATOMICS) +# undef JEMALLOC_U8_ATOMICS +# endif #elif defined(_MSC_VER) # include "jemalloc/internal/atomic_msvc.h" #elif defined(JEMALLOC_C11_ATOMICS) # include "jemalloc/internal/atomic_c11.h" #else # error "Don't have atomics implemented on this platform." #endif /* * This header gives more or less a backport of C11 atomics. The user can write * JEMALLOC_GENERATE_ATOMICS(type, short_type, lg_sizeof_type); to generate * counterparts of the C11 atomic functions for type, as so: * JEMALLOC_GENERATE_ATOMICS(int *, pi, 3); * and then write things like: * int *some_ptr; * atomic_pi_t atomic_ptr_to_int; * atomic_store_pi(&atomic_ptr_to_int, some_ptr, ATOMIC_RELAXED); * int *prev_value = atomic_exchange_pi(&ptr_to_int, NULL, ATOMIC_ACQ_REL); * assert(some_ptr == prev_value); * and expect things to work in the obvious way. * * Also included (with naming differences to avoid conflicts with the standard * library): * atomic_fence(atomic_memory_order_t) (mimics C11's atomic_thread_fence). * ATOMIC_INIT (mimics C11's ATOMIC_VAR_INIT). */ /* * Pure convenience, so that we don't have to type "atomic_memory_order_" * quite so often. */ #define ATOMIC_RELAXED atomic_memory_order_relaxed #define ATOMIC_ACQUIRE atomic_memory_order_acquire #define ATOMIC_RELEASE atomic_memory_order_release #define ATOMIC_ACQ_REL atomic_memory_order_acq_rel #define ATOMIC_SEQ_CST atomic_memory_order_seq_cst /* * Not all platforms have 64-bit atomics. If we do, this #define exposes that * fact. */ #if (LG_SIZEOF_PTR == 3 || LG_SIZEOF_INT == 3) # define JEMALLOC_ATOMIC_U64 #endif JEMALLOC_GENERATE_ATOMICS(void *, p, LG_SIZEOF_PTR) /* * There's no actual guarantee that sizeof(bool) == 1, but it's true on the only * platform that actually needs to know the size, MSVC. */ JEMALLOC_GENERATE_ATOMICS(bool, b, 0) JEMALLOC_GENERATE_INT_ATOMICS(unsigned, u, LG_SIZEOF_INT) JEMALLOC_GENERATE_INT_ATOMICS(size_t, zu, LG_SIZEOF_PTR) JEMALLOC_GENERATE_INT_ATOMICS(ssize_t, zd, LG_SIZEOF_PTR) + +JEMALLOC_GENERATE_INT_ATOMICS(uint8_t, u8, 0) JEMALLOC_GENERATE_INT_ATOMICS(uint32_t, u32, 2) #ifdef JEMALLOC_ATOMIC_U64 JEMALLOC_GENERATE_INT_ATOMICS(uint64_t, u64, 3) #endif #undef ATOMIC_INLINE #endif /* JEMALLOC_INTERNAL_ATOMIC_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/atomic_gcc_atomic.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/atomic_gcc_atomic.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/atomic_gcc_atomic.h (revision 360233) @@ -1,127 +1,129 @@ #ifndef JEMALLOC_INTERNAL_ATOMIC_GCC_ATOMIC_H #define JEMALLOC_INTERNAL_ATOMIC_GCC_ATOMIC_H #include "jemalloc/internal/assert.h" #define ATOMIC_INIT(...) {__VA_ARGS__} typedef enum { atomic_memory_order_relaxed, atomic_memory_order_acquire, atomic_memory_order_release, atomic_memory_order_acq_rel, atomic_memory_order_seq_cst } atomic_memory_order_t; ATOMIC_INLINE int atomic_enum_to_builtin(atomic_memory_order_t mo) { switch (mo) { case atomic_memory_order_relaxed: return __ATOMIC_RELAXED; case atomic_memory_order_acquire: return __ATOMIC_ACQUIRE; case atomic_memory_order_release: return __ATOMIC_RELEASE; case atomic_memory_order_acq_rel: return __ATOMIC_ACQ_REL; case atomic_memory_order_seq_cst: return __ATOMIC_SEQ_CST; } /* Can't happen; the switch is exhaustive. */ not_reached(); } ATOMIC_INLINE void atomic_fence(atomic_memory_order_t mo) { __atomic_thread_fence(atomic_enum_to_builtin(mo)); } #define JEMALLOC_GENERATE_ATOMICS(type, short_type, \ /* unused */ lg_size) \ typedef struct { \ type repr; \ } atomic_##short_type##_t; \ \ ATOMIC_INLINE type \ atomic_load_##short_type(const atomic_##short_type##_t *a, \ atomic_memory_order_t mo) { \ type result; \ __atomic_load(&a->repr, &result, atomic_enum_to_builtin(mo)); \ return result; \ } \ \ ATOMIC_INLINE void \ atomic_store_##short_type(atomic_##short_type##_t *a, type val, \ atomic_memory_order_t mo) { \ __atomic_store(&a->repr, &val, atomic_enum_to_builtin(mo)); \ } \ \ ATOMIC_INLINE type \ atomic_exchange_##short_type(atomic_##short_type##_t *a, type val, \ atomic_memory_order_t mo) { \ type result; \ __atomic_exchange(&a->repr, &val, &result, \ atomic_enum_to_builtin(mo)); \ return result; \ } \ \ ATOMIC_INLINE bool \ atomic_compare_exchange_weak_##short_type(atomic_##short_type##_t *a, \ - type *expected, type desired, atomic_memory_order_t success_mo, \ + UNUSED type *expected, type desired, \ + atomic_memory_order_t success_mo, \ atomic_memory_order_t failure_mo) { \ return __atomic_compare_exchange(&a->repr, expected, &desired, \ true, atomic_enum_to_builtin(success_mo), \ atomic_enum_to_builtin(failure_mo)); \ } \ \ ATOMIC_INLINE bool \ atomic_compare_exchange_strong_##short_type(atomic_##short_type##_t *a, \ - type *expected, type desired, atomic_memory_order_t success_mo, \ + UNUSED type *expected, type desired, \ + atomic_memory_order_t success_mo, \ atomic_memory_order_t failure_mo) { \ return __atomic_compare_exchange(&a->repr, expected, &desired, \ false, \ atomic_enum_to_builtin(success_mo), \ atomic_enum_to_builtin(failure_mo)); \ } #define JEMALLOC_GENERATE_INT_ATOMICS(type, short_type, \ /* unused */ lg_size) \ JEMALLOC_GENERATE_ATOMICS(type, short_type, /* unused */ lg_size) \ \ ATOMIC_INLINE type \ atomic_fetch_add_##short_type(atomic_##short_type##_t *a, type val, \ atomic_memory_order_t mo) { \ return __atomic_fetch_add(&a->repr, val, \ atomic_enum_to_builtin(mo)); \ } \ \ ATOMIC_INLINE type \ atomic_fetch_sub_##short_type(atomic_##short_type##_t *a, type val, \ atomic_memory_order_t mo) { \ return __atomic_fetch_sub(&a->repr, val, \ atomic_enum_to_builtin(mo)); \ } \ \ ATOMIC_INLINE type \ atomic_fetch_and_##short_type(atomic_##short_type##_t *a, type val, \ atomic_memory_order_t mo) { \ return __atomic_fetch_and(&a->repr, val, \ atomic_enum_to_builtin(mo)); \ } \ \ ATOMIC_INLINE type \ atomic_fetch_or_##short_type(atomic_##short_type##_t *a, type val, \ atomic_memory_order_t mo) { \ return __atomic_fetch_or(&a->repr, val, \ atomic_enum_to_builtin(mo)); \ } \ \ ATOMIC_INLINE type \ atomic_fetch_xor_##short_type(atomic_##short_type##_t *a, type val, \ atomic_memory_order_t mo) { \ return __atomic_fetch_xor(&a->repr, val, \ atomic_enum_to_builtin(mo)); \ } #endif /* JEMALLOC_INTERNAL_ATOMIC_GCC_ATOMIC_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/atomic_gcc_sync.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/atomic_gcc_sync.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/atomic_gcc_sync.h (revision 360233) @@ -1,191 +1,195 @@ #ifndef JEMALLOC_INTERNAL_ATOMIC_GCC_SYNC_H #define JEMALLOC_INTERNAL_ATOMIC_GCC_SYNC_H #define ATOMIC_INIT(...) {__VA_ARGS__} typedef enum { atomic_memory_order_relaxed, atomic_memory_order_acquire, atomic_memory_order_release, atomic_memory_order_acq_rel, atomic_memory_order_seq_cst } atomic_memory_order_t; ATOMIC_INLINE void atomic_fence(atomic_memory_order_t mo) { /* Easy cases first: no barrier, and full barrier. */ if (mo == atomic_memory_order_relaxed) { asm volatile("" ::: "memory"); return; } if (mo == atomic_memory_order_seq_cst) { asm volatile("" ::: "memory"); __sync_synchronize(); asm volatile("" ::: "memory"); return; } asm volatile("" ::: "memory"); # if defined(__i386__) || defined(__x86_64__) /* This is implicit on x86. */ -# elif defined(__ppc__) +# elif defined(__ppc64__) asm volatile("lwsync"); +# elif defined(__ppc__) + asm volatile("sync"); # elif defined(__sparc__) && defined(__arch64__) if (mo == atomic_memory_order_acquire) { asm volatile("membar #LoadLoad | #LoadStore"); } else if (mo == atomic_memory_order_release) { asm volatile("membar #LoadStore | #StoreStore"); } else { asm volatile("membar #LoadLoad | #LoadStore | #StoreStore"); } # else __sync_synchronize(); # endif asm volatile("" ::: "memory"); } /* * A correct implementation of seq_cst loads and stores on weakly ordered * architectures could do either of the following: * 1. store() is weak-fence -> store -> strong fence, load() is load -> * strong-fence. * 2. store() is strong-fence -> store, load() is strong-fence -> load -> * weak-fence. * The tricky thing is, load() and store() above can be the load or store * portions of a gcc __sync builtin, so we have to follow GCC's lead, which * means going with strategy 2. * On strongly ordered architectures, the natural strategy is to stick a strong * fence after seq_cst stores, and have naked loads. So we want the strong * fences in different places on different architectures. * atomic_pre_sc_load_fence and atomic_post_sc_store_fence allow us to * accomplish this. */ ATOMIC_INLINE void atomic_pre_sc_load_fence() { # if defined(__i386__) || defined(__x86_64__) || \ (defined(__sparc__) && defined(__arch64__)) atomic_fence(atomic_memory_order_relaxed); # else atomic_fence(atomic_memory_order_seq_cst); # endif } ATOMIC_INLINE void atomic_post_sc_store_fence() { # if defined(__i386__) || defined(__x86_64__) || \ (defined(__sparc__) && defined(__arch64__)) atomic_fence(atomic_memory_order_seq_cst); # else atomic_fence(atomic_memory_order_relaxed); # endif } #define JEMALLOC_GENERATE_ATOMICS(type, short_type, \ /* unused */ lg_size) \ typedef struct { \ type volatile repr; \ } atomic_##short_type##_t; \ \ ATOMIC_INLINE type \ atomic_load_##short_type(const atomic_##short_type##_t *a, \ atomic_memory_order_t mo) { \ if (mo == atomic_memory_order_seq_cst) { \ atomic_pre_sc_load_fence(); \ } \ type result = a->repr; \ if (mo != atomic_memory_order_relaxed) { \ atomic_fence(atomic_memory_order_acquire); \ } \ return result; \ } \ \ ATOMIC_INLINE void \ atomic_store_##short_type(atomic_##short_type##_t *a, \ type val, atomic_memory_order_t mo) { \ if (mo != atomic_memory_order_relaxed) { \ atomic_fence(atomic_memory_order_release); \ } \ a->repr = val; \ if (mo == atomic_memory_order_seq_cst) { \ atomic_post_sc_store_fence(); \ } \ } \ \ ATOMIC_INLINE type \ -atomic_exchange_##short_type(atomic_##short_type##_t *a, type val, \ - atomic_memory_order_t mo) { \ +atomic_exchange_##short_type(atomic_##short_type##_t *a, type val, \ + atomic_memory_order_t mo) { \ /* \ * Because of FreeBSD, we care about gcc 4.2, which doesn't have\ * an atomic exchange builtin. We fake it with a CAS loop. \ */ \ while (true) { \ type old = a->repr; \ if (__sync_bool_compare_and_swap(&a->repr, old, val)) { \ return old; \ } \ } \ } \ \ ATOMIC_INLINE bool \ atomic_compare_exchange_weak_##short_type(atomic_##short_type##_t *a, \ - type *expected, type desired, atomic_memory_order_t success_mo, \ - atomic_memory_order_t failure_mo) { \ + type *expected, type desired, \ + atomic_memory_order_t success_mo, \ + atomic_memory_order_t failure_mo) { \ type prev = __sync_val_compare_and_swap(&a->repr, *expected, \ desired); \ if (prev == *expected) { \ return true; \ } else { \ *expected = prev; \ return false; \ } \ } \ ATOMIC_INLINE bool \ atomic_compare_exchange_strong_##short_type(atomic_##short_type##_t *a, \ - type *expected, type desired, atomic_memory_order_t success_mo, \ - atomic_memory_order_t failure_mo) { \ + type *expected, type desired, \ + atomic_memory_order_t success_mo, \ + atomic_memory_order_t failure_mo) { \ type prev = __sync_val_compare_and_swap(&a->repr, *expected, \ desired); \ if (prev == *expected) { \ return true; \ } else { \ *expected = prev; \ return false; \ } \ } #define JEMALLOC_GENERATE_INT_ATOMICS(type, short_type, \ /* unused */ lg_size) \ JEMALLOC_GENERATE_ATOMICS(type, short_type, /* unused */ lg_size) \ \ ATOMIC_INLINE type \ atomic_fetch_add_##short_type(atomic_##short_type##_t *a, type val, \ atomic_memory_order_t mo) { \ return __sync_fetch_and_add(&a->repr, val); \ } \ \ ATOMIC_INLINE type \ atomic_fetch_sub_##short_type(atomic_##short_type##_t *a, type val, \ atomic_memory_order_t mo) { \ return __sync_fetch_and_sub(&a->repr, val); \ } \ \ ATOMIC_INLINE type \ atomic_fetch_and_##short_type(atomic_##short_type##_t *a, type val, \ atomic_memory_order_t mo) { \ return __sync_fetch_and_and(&a->repr, val); \ } \ \ ATOMIC_INLINE type \ atomic_fetch_or_##short_type(atomic_##short_type##_t *a, type val, \ atomic_memory_order_t mo) { \ return __sync_fetch_and_or(&a->repr, val); \ } \ \ ATOMIC_INLINE type \ atomic_fetch_xor_##short_type(atomic_##short_type##_t *a, type val, \ atomic_memory_order_t mo) { \ return __sync_fetch_and_xor(&a->repr, val); \ } #endif /* JEMALLOC_INTERNAL_ATOMIC_GCC_SYNC_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/background_thread_externs.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/background_thread_externs.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/background_thread_externs.h (revision 360233) @@ -1,33 +1,32 @@ #ifndef JEMALLOC_INTERNAL_BACKGROUND_THREAD_EXTERNS_H #define JEMALLOC_INTERNAL_BACKGROUND_THREAD_EXTERNS_H extern bool opt_background_thread; extern size_t opt_max_background_threads; extern malloc_mutex_t background_thread_lock; extern atomic_b_t background_thread_enabled_state; extern size_t n_background_threads; extern size_t max_background_threads; extern background_thread_info_t *background_thread_info; -extern bool can_enable_background_thread; bool background_thread_create(tsd_t *tsd, unsigned arena_ind); bool background_threads_enable(tsd_t *tsd); bool background_threads_disable(tsd_t *tsd); void background_thread_interval_check(tsdn_t *tsdn, arena_t *arena, arena_decay_t *decay, size_t npages_new); void background_thread_prefork0(tsdn_t *tsdn); void background_thread_prefork1(tsdn_t *tsdn); void background_thread_postfork_parent(tsdn_t *tsdn); void background_thread_postfork_child(tsdn_t *tsdn); bool background_thread_stats_read(tsdn_t *tsdn, background_thread_stats_t *stats); void background_thread_ctl_init(tsdn_t *tsdn); #ifdef JEMALLOC_PTHREAD_CREATE_WRAPPER extern int pthread_create_wrapper(pthread_t *__restrict, const pthread_attr_t *, void *(*)(void *), void *__restrict); #endif bool background_thread_boot0(void); bool background_thread_boot1(tsdn_t *tsdn); #endif /* JEMALLOC_INTERNAL_BACKGROUND_THREAD_EXTERNS_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/background_thread_inlines.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/background_thread_inlines.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/background_thread_inlines.h (revision 360233) @@ -1,57 +1,62 @@ #ifndef JEMALLOC_INTERNAL_BACKGROUND_THREAD_INLINES_H #define JEMALLOC_INTERNAL_BACKGROUND_THREAD_INLINES_H JEMALLOC_ALWAYS_INLINE bool background_thread_enabled(void) { return atomic_load_b(&background_thread_enabled_state, ATOMIC_RELAXED); } JEMALLOC_ALWAYS_INLINE void background_thread_enabled_set(tsdn_t *tsdn, bool state) { malloc_mutex_assert_owner(tsdn, &background_thread_lock); atomic_store_b(&background_thread_enabled_state, state, ATOMIC_RELAXED); } JEMALLOC_ALWAYS_INLINE background_thread_info_t * arena_background_thread_info_get(arena_t *arena) { unsigned arena_ind = arena_ind_get(arena); - return &background_thread_info[arena_ind % ncpus]; + return &background_thread_info[arena_ind % max_background_threads]; +} + +JEMALLOC_ALWAYS_INLINE background_thread_info_t * +background_thread_info_get(size_t ind) { + return &background_thread_info[ind % max_background_threads]; } JEMALLOC_ALWAYS_INLINE uint64_t background_thread_wakeup_time_get(background_thread_info_t *info) { uint64_t next_wakeup = nstime_ns(&info->next_wakeup); assert(atomic_load_b(&info->indefinite_sleep, ATOMIC_ACQUIRE) == (next_wakeup == BACKGROUND_THREAD_INDEFINITE_SLEEP)); return next_wakeup; } JEMALLOC_ALWAYS_INLINE void background_thread_wakeup_time_set(tsdn_t *tsdn, background_thread_info_t *info, uint64_t wakeup_time) { malloc_mutex_assert_owner(tsdn, &info->mtx); atomic_store_b(&info->indefinite_sleep, wakeup_time == BACKGROUND_THREAD_INDEFINITE_SLEEP, ATOMIC_RELEASE); nstime_init(&info->next_wakeup, wakeup_time); } JEMALLOC_ALWAYS_INLINE bool background_thread_indefinite_sleep(background_thread_info_t *info) { return atomic_load_b(&info->indefinite_sleep, ATOMIC_ACQUIRE); } JEMALLOC_ALWAYS_INLINE void arena_background_thread_inactivity_check(tsdn_t *tsdn, arena_t *arena, bool is_background_thread) { if (!background_thread_enabled() || is_background_thread) { return; } background_thread_info_t *info = arena_background_thread_info_get(arena); if (background_thread_indefinite_sleep(info)) { background_thread_interval_check(tsdn, arena, &arena->decay_dirty, 0); } } #endif /* JEMALLOC_INTERNAL_BACKGROUND_THREAD_INLINES_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/background_thread_structs.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/background_thread_structs.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/background_thread_structs.h (revision 360233) @@ -1,53 +1,54 @@ #ifndef JEMALLOC_INTERNAL_BACKGROUND_THREAD_STRUCTS_H #define JEMALLOC_INTERNAL_BACKGROUND_THREAD_STRUCTS_H /* This file really combines "structs" and "types", but only transitionally. */ #if defined(JEMALLOC_BACKGROUND_THREAD) || defined(JEMALLOC_LAZY_LOCK) # define JEMALLOC_PTHREAD_CREATE_WRAPPER #endif #define BACKGROUND_THREAD_INDEFINITE_SLEEP UINT64_MAX #define MAX_BACKGROUND_THREAD_LIMIT MALLOCX_ARENA_LIMIT +#define DEFAULT_NUM_BACKGROUND_THREAD 4 typedef enum { background_thread_stopped, background_thread_started, /* Thread waits on the global lock when paused (for arena_reset). */ background_thread_paused, } background_thread_state_t; struct background_thread_info_s { #ifdef JEMALLOC_BACKGROUND_THREAD /* Background thread is pthread specific. */ pthread_t thread; pthread_cond_t cond; #endif malloc_mutex_t mtx; background_thread_state_t state; /* When true, it means no wakeup scheduled. */ atomic_b_t indefinite_sleep; /* Next scheduled wakeup time (absolute time in ns). */ nstime_t next_wakeup; /* * Since the last background thread run, newly added number of pages * that need to be purged by the next wakeup. This is adjusted on * epoch advance, and is used to determine whether we should signal the * background thread to wake up earlier. */ size_t npages_to_purge_new; /* Stats: total number of runs since started. */ uint64_t tot_n_runs; /* Stats: total sleep time since started. */ nstime_t tot_sleep_time; }; typedef struct background_thread_info_s background_thread_info_t; struct background_thread_stats_s { size_t num_threads; uint64_t num_runs; nstime_t run_interval; }; typedef struct background_thread_stats_s background_thread_stats_t; #endif /* JEMALLOC_INTERNAL_BACKGROUND_THREAD_STRUCTS_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/base_structs.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/base_structs.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/base_structs.h (revision 360233) @@ -1,59 +1,59 @@ #ifndef JEMALLOC_INTERNAL_BASE_STRUCTS_H #define JEMALLOC_INTERNAL_BASE_STRUCTS_H #include "jemalloc/internal/jemalloc_internal_types.h" #include "jemalloc/internal/mutex.h" -#include "jemalloc/internal/size_classes.h" +#include "jemalloc/internal/sc.h" /* Embedded at the beginning of every block of base-managed virtual memory. */ struct base_block_s { /* Total size of block's virtual memory mapping. */ size_t size; /* Next block in list of base's blocks. */ base_block_t *next; /* Tracks unused trailing space. */ extent_t extent; }; struct base_s { /* Associated arena's index within the arenas array. */ unsigned ind; /* * User-configurable extent hook functions. Points to an * extent_hooks_t. */ atomic_p_t extent_hooks; /* Protects base_alloc() and base_stats_get() operations. */ malloc_mutex_t mtx; /* Using THP when true (metadata_thp auto mode). */ bool auto_thp_switched; /* * Most recent size class in the series of increasingly large base * extents. Logarithmic spacing between subsequent allocations ensures * that the total number of distinct mappings remains small. */ pszind_t pind_last; /* Serial number generation state. */ size_t extent_sn_next; /* Chain of all blocks associated with base. */ base_block_t *blocks; /* Heap of extents that track unused trailing space within blocks. */ - extent_heap_t avail[NSIZES]; + extent_heap_t avail[SC_NSIZES]; /* Stats, only maintained if config_stats. */ size_t allocated; size_t resident; size_t mapped; /* Number of THP regions touched. */ size_t n_thp; }; #endif /* JEMALLOC_INTERNAL_BASE_STRUCTS_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/bin.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/bin.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/bin.h (revision 360233) @@ -1,106 +1,123 @@ #ifndef JEMALLOC_INTERNAL_BIN_H #define JEMALLOC_INTERNAL_BIN_H +#include "jemalloc/internal/bin_stats.h" +#include "jemalloc/internal/bin_types.h" #include "jemalloc/internal/extent_types.h" #include "jemalloc/internal/extent_structs.h" #include "jemalloc/internal/mutex.h" -#include "jemalloc/internal/bin_stats.h" +#include "jemalloc/internal/sc.h" /* * A bin contains a set of extents that are currently being used for slab * allocations. */ /* * Read-only information associated with each element of arena_t's bins array * is stored separately, partly to reduce memory usage (only one copy, rather * than one per arena), but mainly to avoid false cacheline sharing. * * Each slab has the following layout: * * /--------------------\ * | region 0 | * |--------------------| * | region 1 | * |--------------------| * | ... | * | ... | * | ... | * |--------------------| * | region nregs-1 | * \--------------------/ */ typedef struct bin_info_s bin_info_t; struct bin_info_s { /* Size of regions in a slab for this bin's size class. */ size_t reg_size; /* Total size of a slab for this bin's size class. */ size_t slab_size; /* Total number of regions in a slab for this bin's size class. */ uint32_t nregs; + /* Number of sharded bins in each arena for this size class. */ + uint32_t n_shards; + /* * Metadata used to manipulate bitmaps for slabs associated with this * bin. */ bitmap_info_t bitmap_info; }; -extern const bin_info_t bin_infos[NBINS]; +extern bin_info_t bin_infos[SC_NBINS]; - typedef struct bin_s bin_t; struct bin_s { /* All operations on bin_t fields require lock ownership. */ malloc_mutex_t lock; /* * Current slab being used to service allocations of this bin's size * class. slabcur is independent of slabs_{nonfull,full}; whenever * slabcur is reassigned, the previous slab must be deallocated or * inserted into slabs_{nonfull,full}. */ extent_t *slabcur; /* * Heap of non-full slabs. This heap is used to assure that new * allocations come from the non-full slab that is oldest/lowest in * memory. */ extent_heap_t slabs_nonfull; /* List used to track full slabs. */ extent_list_t slabs_full; /* Bin statistics. */ bin_stats_t stats; }; +/* A set of sharded bins of the same size class. */ +typedef struct bins_s bins_t; +struct bins_s { + /* Sharded bins. Dynamically sized. */ + bin_t *bin_shards; +}; + +void bin_shard_sizes_boot(unsigned bin_shards[SC_NBINS]); +bool bin_update_shard_size(unsigned bin_shards[SC_NBINS], size_t start_size, + size_t end_size, size_t nshards); +void bin_boot(sc_data_t *sc_data, unsigned bin_shard_sizes[SC_NBINS]); + /* Initializes a bin to empty. Returns true on error. */ bool bin_init(bin_t *bin); /* Forking. */ void bin_prefork(tsdn_t *tsdn, bin_t *bin); void bin_postfork_parent(tsdn_t *tsdn, bin_t *bin); void bin_postfork_child(tsdn_t *tsdn, bin_t *bin); /* Stats. */ static inline void bin_stats_merge(tsdn_t *tsdn, bin_stats_t *dst_bin_stats, bin_t *bin) { malloc_mutex_lock(tsdn, &bin->lock); - malloc_mutex_prof_read(tsdn, &dst_bin_stats->mutex_data, &bin->lock); + malloc_mutex_prof_accum(tsdn, &dst_bin_stats->mutex_data, &bin->lock); dst_bin_stats->nmalloc += bin->stats.nmalloc; dst_bin_stats->ndalloc += bin->stats.ndalloc; dst_bin_stats->nrequests += bin->stats.nrequests; dst_bin_stats->curregs += bin->stats.curregs; dst_bin_stats->nfills += bin->stats.nfills; dst_bin_stats->nflushes += bin->stats.nflushes; dst_bin_stats->nslabs += bin->stats.nslabs; dst_bin_stats->reslabs += bin->stats.reslabs; dst_bin_stats->curslabs += bin->stats.curslabs; + dst_bin_stats->nonfull_slabs += bin->stats.nonfull_slabs; malloc_mutex_unlock(tsdn, &bin->lock); } #endif /* JEMALLOC_INTERNAL_BIN_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/bin_stats.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/bin_stats.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/bin_stats.h (revision 360233) @@ -1,51 +1,54 @@ #ifndef JEMALLOC_INTERNAL_BIN_STATS_H #define JEMALLOC_INTERNAL_BIN_STATS_H #include "jemalloc/internal/mutex_prof.h" typedef struct bin_stats_s bin_stats_t; struct bin_stats_s { /* * Total number of allocation/deallocation requests served directly by * the bin. Note that tcache may allocate an object, then recycle it * many times, resulting many increments to nrequests, but only one * each to nmalloc and ndalloc. */ uint64_t nmalloc; uint64_t ndalloc; /* * Number of allocation requests that correspond to the size of this * bin. This includes requests served by tcache, though tcache only * periodically merges into this counter. */ uint64_t nrequests; /* * Current number of regions of this size class, including regions * currently cached by tcache. */ size_t curregs; /* Number of tcache fills from this bin. */ uint64_t nfills; /* Number of tcache flushes to this bin. */ uint64_t nflushes; /* Total number of slabs created for this bin's size class. */ uint64_t nslabs; /* * Total number of slabs reused by extracting them from the slabs heap * for this bin's size class. */ uint64_t reslabs; /* Current number of slabs in this bin. */ size_t curslabs; + /* Current size of nonfull slabs heap in this bin. */ + size_t nonfull_slabs; + mutex_prof_data_t mutex_data; }; #endif /* JEMALLOC_INTERNAL_BIN_STATS_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/bin_types.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/bin_types.h (nonexistent) +++ head/contrib/jemalloc/include/jemalloc/internal/bin_types.h (revision 360233) @@ -0,0 +1,17 @@ +#ifndef JEMALLOC_INTERNAL_BIN_TYPES_H +#define JEMALLOC_INTERNAL_BIN_TYPES_H + +#include "jemalloc/internal/sc.h" + +#define BIN_SHARDS_MAX (1 << EXTENT_BITS_BINSHARD_WIDTH) +#define N_BIN_SHARDS_DEFAULT 1 + +/* Used in TSD static initializer only. Real init in arena_bind(). */ +#define TSD_BINSHARDS_ZERO_INITIALIZER {{UINT8_MAX}} + +typedef struct tsd_binshards_s tsd_binshards_t; +struct tsd_binshards_s { + uint8_t binshard[SC_NBINS]; +}; + +#endif /* JEMALLOC_INTERNAL_BIN_TYPES_H */ Property changes on: head/contrib/jemalloc/include/jemalloc/internal/bin_types.h ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/jemalloc/include/jemalloc/internal/bit_util.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/bit_util.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/bit_util.h (revision 360233) @@ -1,165 +1,239 @@ #ifndef JEMALLOC_INTERNAL_BIT_UTIL_H #define JEMALLOC_INTERNAL_BIT_UTIL_H #include "jemalloc/internal/assert.h" #define BIT_UTIL_INLINE static inline /* Sanity check. */ #if !defined(JEMALLOC_INTERNAL_FFSLL) || !defined(JEMALLOC_INTERNAL_FFSL) \ || !defined(JEMALLOC_INTERNAL_FFS) # error JEMALLOC_INTERNAL_FFS{,L,LL} should have been defined by configure #endif BIT_UTIL_INLINE unsigned ffs_llu(unsigned long long bitmap) { return JEMALLOC_INTERNAL_FFSLL(bitmap); } BIT_UTIL_INLINE unsigned ffs_lu(unsigned long bitmap) { return JEMALLOC_INTERNAL_FFSL(bitmap); } BIT_UTIL_INLINE unsigned ffs_u(unsigned bitmap) { return JEMALLOC_INTERNAL_FFS(bitmap); } +#ifdef JEMALLOC_INTERNAL_POPCOUNTL BIT_UTIL_INLINE unsigned +popcount_lu(unsigned long bitmap) { + return JEMALLOC_INTERNAL_POPCOUNTL(bitmap); +} +#endif + +/* + * Clears first unset bit in bitmap, and returns + * place of bit. bitmap *must not* be 0. + */ + +BIT_UTIL_INLINE size_t +cfs_lu(unsigned long* bitmap) { + size_t bit = ffs_lu(*bitmap) - 1; + *bitmap ^= ZU(1) << bit; + return bit; +} + +BIT_UTIL_INLINE unsigned ffs_zu(size_t bitmap) { #if LG_SIZEOF_PTR == LG_SIZEOF_INT return ffs_u(bitmap); #elif LG_SIZEOF_PTR == LG_SIZEOF_LONG return ffs_lu(bitmap); #elif LG_SIZEOF_PTR == LG_SIZEOF_LONG_LONG return ffs_llu(bitmap); #else #error No implementation for size_t ffs() #endif } BIT_UTIL_INLINE unsigned ffs_u64(uint64_t bitmap) { #if LG_SIZEOF_LONG == 3 return ffs_lu(bitmap); #elif LG_SIZEOF_LONG_LONG == 3 return ffs_llu(bitmap); #else #error No implementation for 64-bit ffs() #endif } BIT_UTIL_INLINE unsigned ffs_u32(uint32_t bitmap) { #if LG_SIZEOF_INT == 2 return ffs_u(bitmap); #else #error No implementation for 32-bit ffs() #endif return ffs_u(bitmap); } BIT_UTIL_INLINE uint64_t pow2_ceil_u64(uint64_t x) { +#if (defined(__amd64__) || defined(__x86_64__) || defined(JEMALLOC_HAVE_BUILTIN_CLZ)) + if(unlikely(x <= 1)) { + return x; + } + size_t msb_on_index; +#if (defined(__amd64__) || defined(__x86_64__)) + asm ("bsrq %1, %0" + : "=r"(msb_on_index) // Outputs. + : "r"(x-1) // Inputs. + ); +#elif (defined(JEMALLOC_HAVE_BUILTIN_CLZ)) + msb_on_index = (63 ^ __builtin_clzll(x - 1)); +#endif + assert(msb_on_index < 63); + return 1ULL << (msb_on_index + 1); +#else x--; x |= x >> 1; x |= x >> 2; x |= x >> 4; x |= x >> 8; x |= x >> 16; x |= x >> 32; x++; return x; +#endif } BIT_UTIL_INLINE uint32_t pow2_ceil_u32(uint32_t x) { +#if ((defined(__i386__) || defined(JEMALLOC_HAVE_BUILTIN_CLZ)) && (!defined(__s390__))) + if(unlikely(x <= 1)) { + return x; + } + size_t msb_on_index; +#if (defined(__i386__)) + asm ("bsr %1, %0" + : "=r"(msb_on_index) // Outputs. + : "r"(x-1) // Inputs. + ); +#elif (defined(JEMALLOC_HAVE_BUILTIN_CLZ)) + msb_on_index = (31 ^ __builtin_clz(x - 1)); +#endif + assert(msb_on_index < 31); + return 1U << (msb_on_index + 1); +#else x--; x |= x >> 1; x |= x >> 2; x |= x >> 4; x |= x >> 8; x |= x >> 16; x++; return x; +#endif } /* Compute the smallest power of 2 that is >= x. */ BIT_UTIL_INLINE size_t pow2_ceil_zu(size_t x) { #if (LG_SIZEOF_PTR == 3) return pow2_ceil_u64(x); #else return pow2_ceil_u32(x); #endif } #if (defined(__i386__) || defined(__amd64__) || defined(__x86_64__)) BIT_UTIL_INLINE unsigned lg_floor(size_t x) { size_t ret; assert(x != 0); asm ("bsr %1, %0" : "=r"(ret) // Outputs. : "r"(x) // Inputs. ); assert(ret < UINT_MAX); return (unsigned)ret; } #elif (defined(_MSC_VER)) BIT_UTIL_INLINE unsigned lg_floor(size_t x) { unsigned long ret; assert(x != 0); #if (LG_SIZEOF_PTR == 3) _BitScanReverse64(&ret, x); #elif (LG_SIZEOF_PTR == 2) _BitScanReverse(&ret, x); #else # error "Unsupported type size for lg_floor()" #endif assert(ret < UINT_MAX); return (unsigned)ret; } #elif (defined(JEMALLOC_HAVE_BUILTIN_CLZ)) BIT_UTIL_INLINE unsigned lg_floor(size_t x) { assert(x != 0); #if (LG_SIZEOF_PTR == LG_SIZEOF_INT) return ((8 << LG_SIZEOF_PTR) - 1) - __builtin_clz(x); #elif (LG_SIZEOF_PTR == LG_SIZEOF_LONG) return ((8 << LG_SIZEOF_PTR) - 1) - __builtin_clzl(x); #else # error "Unsupported type size for lg_floor()" #endif } #else BIT_UTIL_INLINE unsigned lg_floor(size_t x) { assert(x != 0); x |= (x >> 1); x |= (x >> 2); x |= (x >> 4); x |= (x >> 8); x |= (x >> 16); #if (LG_SIZEOF_PTR == 3) x |= (x >> 32); #endif if (x == SIZE_T_MAX) { return (8 << LG_SIZEOF_PTR) - 1; } x++; return ffs_zu(x) - 2; } #endif +BIT_UTIL_INLINE unsigned +lg_ceil(size_t x) { + return lg_floor(x) + ((x & (x - 1)) == 0 ? 0 : 1); +} + #undef BIT_UTIL_INLINE + +/* A compile-time version of lg_floor and lg_ceil. */ +#define LG_FLOOR_1(x) 0 +#define LG_FLOOR_2(x) (x < (1ULL << 1) ? LG_FLOOR_1(x) : 1 + LG_FLOOR_1(x >> 1)) +#define LG_FLOOR_4(x) (x < (1ULL << 2) ? LG_FLOOR_2(x) : 2 + LG_FLOOR_2(x >> 2)) +#define LG_FLOOR_8(x) (x < (1ULL << 4) ? LG_FLOOR_4(x) : 4 + LG_FLOOR_4(x >> 4)) +#define LG_FLOOR_16(x) (x < (1ULL << 8) ? LG_FLOOR_8(x) : 8 + LG_FLOOR_8(x >> 8)) +#define LG_FLOOR_32(x) (x < (1ULL << 16) ? LG_FLOOR_16(x) : 16 + LG_FLOOR_16(x >> 16)) +#define LG_FLOOR_64(x) (x < (1ULL << 32) ? LG_FLOOR_32(x) : 32 + LG_FLOOR_32(x >> 32)) +#if LG_SIZEOF_PTR == 2 +# define LG_FLOOR(x) LG_FLOOR_32((x)) +#else +# define LG_FLOOR(x) LG_FLOOR_64((x)) +#endif + +#define LG_CEIL(x) (LG_FLOOR(x) + (((x) & ((x) - 1)) == 0 ? 0 : 1)) #endif /* JEMALLOC_INTERNAL_BIT_UTIL_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/bitmap.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/bitmap.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/bitmap.h (revision 360233) @@ -1,369 +1,369 @@ #ifndef JEMALLOC_INTERNAL_BITMAP_H #define JEMALLOC_INTERNAL_BITMAP_H #include "jemalloc/internal/arena_types.h" #include "jemalloc/internal/bit_util.h" -#include "jemalloc/internal/size_classes.h" +#include "jemalloc/internal/sc.h" typedef unsigned long bitmap_t; #define LG_SIZEOF_BITMAP LG_SIZEOF_LONG /* Maximum bitmap bit count is 2^LG_BITMAP_MAXBITS. */ -#if LG_SLAB_MAXREGS > LG_CEIL_NSIZES +#if LG_SLAB_MAXREGS > LG_CEIL(SC_NSIZES) /* Maximum bitmap bit count is determined by maximum regions per slab. */ # define LG_BITMAP_MAXBITS LG_SLAB_MAXREGS #else /* Maximum bitmap bit count is determined by number of extent size classes. */ -# define LG_BITMAP_MAXBITS LG_CEIL_NSIZES +# define LG_BITMAP_MAXBITS LG_CEIL(SC_NSIZES) #endif #define BITMAP_MAXBITS (ZU(1) << LG_BITMAP_MAXBITS) /* Number of bits per group. */ #define LG_BITMAP_GROUP_NBITS (LG_SIZEOF_BITMAP + 3) #define BITMAP_GROUP_NBITS (1U << LG_BITMAP_GROUP_NBITS) #define BITMAP_GROUP_NBITS_MASK (BITMAP_GROUP_NBITS-1) /* * Do some analysis on how big the bitmap is before we use a tree. For a brute * force linear search, if we would have to call ffs_lu() more than 2^3 times, * use a tree instead. */ #if LG_BITMAP_MAXBITS - LG_BITMAP_GROUP_NBITS > 3 # define BITMAP_USE_TREE #endif /* Number of groups required to store a given number of bits. */ #define BITMAP_BITS2GROUPS(nbits) \ (((nbits) + BITMAP_GROUP_NBITS_MASK) >> LG_BITMAP_GROUP_NBITS) /* * Number of groups required at a particular level for a given number of bits. */ #define BITMAP_GROUPS_L0(nbits) \ BITMAP_BITS2GROUPS(nbits) #define BITMAP_GROUPS_L1(nbits) \ BITMAP_BITS2GROUPS(BITMAP_BITS2GROUPS(nbits)) #define BITMAP_GROUPS_L2(nbits) \ BITMAP_BITS2GROUPS(BITMAP_BITS2GROUPS(BITMAP_BITS2GROUPS((nbits)))) #define BITMAP_GROUPS_L3(nbits) \ BITMAP_BITS2GROUPS(BITMAP_BITS2GROUPS(BITMAP_BITS2GROUPS( \ BITMAP_BITS2GROUPS((nbits))))) #define BITMAP_GROUPS_L4(nbits) \ BITMAP_BITS2GROUPS(BITMAP_BITS2GROUPS(BITMAP_BITS2GROUPS( \ BITMAP_BITS2GROUPS(BITMAP_BITS2GROUPS((nbits)))))) /* * Assuming the number of levels, number of groups required for a given number * of bits. */ #define BITMAP_GROUPS_1_LEVEL(nbits) \ BITMAP_GROUPS_L0(nbits) #define BITMAP_GROUPS_2_LEVEL(nbits) \ (BITMAP_GROUPS_1_LEVEL(nbits) + BITMAP_GROUPS_L1(nbits)) #define BITMAP_GROUPS_3_LEVEL(nbits) \ (BITMAP_GROUPS_2_LEVEL(nbits) + BITMAP_GROUPS_L2(nbits)) #define BITMAP_GROUPS_4_LEVEL(nbits) \ (BITMAP_GROUPS_3_LEVEL(nbits) + BITMAP_GROUPS_L3(nbits)) #define BITMAP_GROUPS_5_LEVEL(nbits) \ (BITMAP_GROUPS_4_LEVEL(nbits) + BITMAP_GROUPS_L4(nbits)) /* * Maximum number of groups required to support LG_BITMAP_MAXBITS. */ #ifdef BITMAP_USE_TREE #if LG_BITMAP_MAXBITS <= LG_BITMAP_GROUP_NBITS # define BITMAP_GROUPS(nbits) BITMAP_GROUPS_1_LEVEL(nbits) # define BITMAP_GROUPS_MAX BITMAP_GROUPS_1_LEVEL(BITMAP_MAXBITS) #elif LG_BITMAP_MAXBITS <= LG_BITMAP_GROUP_NBITS * 2 # define BITMAP_GROUPS(nbits) BITMAP_GROUPS_2_LEVEL(nbits) # define BITMAP_GROUPS_MAX BITMAP_GROUPS_2_LEVEL(BITMAP_MAXBITS) #elif LG_BITMAP_MAXBITS <= LG_BITMAP_GROUP_NBITS * 3 # define BITMAP_GROUPS(nbits) BITMAP_GROUPS_3_LEVEL(nbits) # define BITMAP_GROUPS_MAX BITMAP_GROUPS_3_LEVEL(BITMAP_MAXBITS) #elif LG_BITMAP_MAXBITS <= LG_BITMAP_GROUP_NBITS * 4 # define BITMAP_GROUPS(nbits) BITMAP_GROUPS_4_LEVEL(nbits) # define BITMAP_GROUPS_MAX BITMAP_GROUPS_4_LEVEL(BITMAP_MAXBITS) #elif LG_BITMAP_MAXBITS <= LG_BITMAP_GROUP_NBITS * 5 # define BITMAP_GROUPS(nbits) BITMAP_GROUPS_5_LEVEL(nbits) # define BITMAP_GROUPS_MAX BITMAP_GROUPS_5_LEVEL(BITMAP_MAXBITS) #else # error "Unsupported bitmap size" #endif /* * Maximum number of levels possible. This could be statically computed based * on LG_BITMAP_MAXBITS: * * #define BITMAP_MAX_LEVELS \ * (LG_BITMAP_MAXBITS / LG_SIZEOF_BITMAP) \ * + !!(LG_BITMAP_MAXBITS % LG_SIZEOF_BITMAP) * * However, that would not allow the generic BITMAP_INFO_INITIALIZER() macro, so * instead hardcode BITMAP_MAX_LEVELS to the largest number supported by the * various cascading macros. The only additional cost this incurs is some * unused trailing entries in bitmap_info_t structures; the bitmaps themselves * are not impacted. */ #define BITMAP_MAX_LEVELS 5 #define BITMAP_INFO_INITIALIZER(nbits) { \ /* nbits. */ \ nbits, \ /* nlevels. */ \ (BITMAP_GROUPS_L0(nbits) > BITMAP_GROUPS_L1(nbits)) + \ (BITMAP_GROUPS_L1(nbits) > BITMAP_GROUPS_L2(nbits)) + \ (BITMAP_GROUPS_L2(nbits) > BITMAP_GROUPS_L3(nbits)) + \ (BITMAP_GROUPS_L3(nbits) > BITMAP_GROUPS_L4(nbits)) + 1, \ /* levels. */ \ { \ {0}, \ {BITMAP_GROUPS_L0(nbits)}, \ {BITMAP_GROUPS_L1(nbits) + BITMAP_GROUPS_L0(nbits)}, \ {BITMAP_GROUPS_L2(nbits) + BITMAP_GROUPS_L1(nbits) + \ BITMAP_GROUPS_L0(nbits)}, \ {BITMAP_GROUPS_L3(nbits) + BITMAP_GROUPS_L2(nbits) + \ BITMAP_GROUPS_L1(nbits) + BITMAP_GROUPS_L0(nbits)}, \ {BITMAP_GROUPS_L4(nbits) + BITMAP_GROUPS_L3(nbits) + \ BITMAP_GROUPS_L2(nbits) + BITMAP_GROUPS_L1(nbits) \ + BITMAP_GROUPS_L0(nbits)} \ } \ } #else /* BITMAP_USE_TREE */ #define BITMAP_GROUPS(nbits) BITMAP_BITS2GROUPS(nbits) #define BITMAP_GROUPS_MAX BITMAP_BITS2GROUPS(BITMAP_MAXBITS) #define BITMAP_INFO_INITIALIZER(nbits) { \ /* nbits. */ \ nbits, \ /* ngroups. */ \ BITMAP_BITS2GROUPS(nbits) \ } #endif /* BITMAP_USE_TREE */ typedef struct bitmap_level_s { /* Offset of this level's groups within the array of groups. */ size_t group_offset; } bitmap_level_t; typedef struct bitmap_info_s { /* Logical number of bits in bitmap (stored at bottom level). */ size_t nbits; #ifdef BITMAP_USE_TREE /* Number of levels necessary for nbits. */ unsigned nlevels; /* * Only the first (nlevels+1) elements are used, and levels are ordered * bottom to top (e.g. the bottom level is stored in levels[0]). */ bitmap_level_t levels[BITMAP_MAX_LEVELS+1]; #else /* BITMAP_USE_TREE */ /* Number of groups necessary for nbits. */ size_t ngroups; #endif /* BITMAP_USE_TREE */ } bitmap_info_t; void bitmap_info_init(bitmap_info_t *binfo, size_t nbits); void bitmap_init(bitmap_t *bitmap, const bitmap_info_t *binfo, bool fill); size_t bitmap_size(const bitmap_info_t *binfo); static inline bool bitmap_full(bitmap_t *bitmap, const bitmap_info_t *binfo) { #ifdef BITMAP_USE_TREE size_t rgoff = binfo->levels[binfo->nlevels].group_offset - 1; bitmap_t rg = bitmap[rgoff]; /* The bitmap is full iff the root group is 0. */ return (rg == 0); #else size_t i; for (i = 0; i < binfo->ngroups; i++) { if (bitmap[i] != 0) { return false; } } return true; #endif } static inline bool bitmap_get(bitmap_t *bitmap, const bitmap_info_t *binfo, size_t bit) { size_t goff; bitmap_t g; assert(bit < binfo->nbits); goff = bit >> LG_BITMAP_GROUP_NBITS; g = bitmap[goff]; return !(g & (ZU(1) << (bit & BITMAP_GROUP_NBITS_MASK))); } static inline void bitmap_set(bitmap_t *bitmap, const bitmap_info_t *binfo, size_t bit) { size_t goff; bitmap_t *gp; bitmap_t g; assert(bit < binfo->nbits); assert(!bitmap_get(bitmap, binfo, bit)); goff = bit >> LG_BITMAP_GROUP_NBITS; gp = &bitmap[goff]; g = *gp; assert(g & (ZU(1) << (bit & BITMAP_GROUP_NBITS_MASK))); g ^= ZU(1) << (bit & BITMAP_GROUP_NBITS_MASK); *gp = g; assert(bitmap_get(bitmap, binfo, bit)); #ifdef BITMAP_USE_TREE /* Propagate group state transitions up the tree. */ if (g == 0) { unsigned i; for (i = 1; i < binfo->nlevels; i++) { bit = goff; goff = bit >> LG_BITMAP_GROUP_NBITS; gp = &bitmap[binfo->levels[i].group_offset + goff]; g = *gp; assert(g & (ZU(1) << (bit & BITMAP_GROUP_NBITS_MASK))); g ^= ZU(1) << (bit & BITMAP_GROUP_NBITS_MASK); *gp = g; if (g != 0) { break; } } } #endif } /* ffu: find first unset >= bit. */ static inline size_t bitmap_ffu(const bitmap_t *bitmap, const bitmap_info_t *binfo, size_t min_bit) { assert(min_bit < binfo->nbits); #ifdef BITMAP_USE_TREE size_t bit = 0; for (unsigned level = binfo->nlevels; level--;) { size_t lg_bits_per_group = (LG_BITMAP_GROUP_NBITS * (level + 1)); bitmap_t group = bitmap[binfo->levels[level].group_offset + (bit >> lg_bits_per_group)]; unsigned group_nmask = (unsigned)(((min_bit > bit) ? (min_bit - bit) : 0) >> (lg_bits_per_group - LG_BITMAP_GROUP_NBITS)); assert(group_nmask <= BITMAP_GROUP_NBITS); bitmap_t group_mask = ~((1LU << group_nmask) - 1); bitmap_t group_masked = group & group_mask; if (group_masked == 0LU) { if (group == 0LU) { return binfo->nbits; } /* * min_bit was preceded by one or more unset bits in * this group, but there are no other unset bits in this * group. Try again starting at the first bit of the * next sibling. This will recurse at most once per * non-root level. */ size_t sib_base = bit + (ZU(1) << lg_bits_per_group); assert(sib_base > min_bit); assert(sib_base > bit); if (sib_base >= binfo->nbits) { return binfo->nbits; } return bitmap_ffu(bitmap, binfo, sib_base); } bit += ((size_t)(ffs_lu(group_masked) - 1)) << (lg_bits_per_group - LG_BITMAP_GROUP_NBITS); } assert(bit >= min_bit); assert(bit < binfo->nbits); return bit; #else size_t i = min_bit >> LG_BITMAP_GROUP_NBITS; bitmap_t g = bitmap[i] & ~((1LU << (min_bit & BITMAP_GROUP_NBITS_MASK)) - 1); size_t bit; do { bit = ffs_lu(g); if (bit != 0) { return (i << LG_BITMAP_GROUP_NBITS) + (bit - 1); } i++; g = bitmap[i]; } while (i < binfo->ngroups); return binfo->nbits; #endif } /* sfu: set first unset. */ static inline size_t bitmap_sfu(bitmap_t *bitmap, const bitmap_info_t *binfo) { size_t bit; bitmap_t g; unsigned i; assert(!bitmap_full(bitmap, binfo)); #ifdef BITMAP_USE_TREE i = binfo->nlevels - 1; g = bitmap[binfo->levels[i].group_offset]; bit = ffs_lu(g) - 1; while (i > 0) { i--; g = bitmap[binfo->levels[i].group_offset + bit]; bit = (bit << LG_BITMAP_GROUP_NBITS) + (ffs_lu(g) - 1); } #else i = 0; g = bitmap[0]; while ((bit = ffs_lu(g)) == 0) { i++; g = bitmap[i]; } bit = (i << LG_BITMAP_GROUP_NBITS) + (bit - 1); #endif bitmap_set(bitmap, binfo, bit); return bit; } static inline void bitmap_unset(bitmap_t *bitmap, const bitmap_info_t *binfo, size_t bit) { size_t goff; bitmap_t *gp; bitmap_t g; UNUSED bool propagate; assert(bit < binfo->nbits); assert(bitmap_get(bitmap, binfo, bit)); goff = bit >> LG_BITMAP_GROUP_NBITS; gp = &bitmap[goff]; g = *gp; propagate = (g == 0); assert((g & (ZU(1) << (bit & BITMAP_GROUP_NBITS_MASK))) == 0); g ^= ZU(1) << (bit & BITMAP_GROUP_NBITS_MASK); *gp = g; assert(!bitmap_get(bitmap, binfo, bit)); #ifdef BITMAP_USE_TREE /* Propagate group state transitions up the tree. */ if (propagate) { unsigned i; for (i = 1; i < binfo->nlevels; i++) { bit = goff; goff = bit >> LG_BITMAP_GROUP_NBITS; gp = &bitmap[binfo->levels[i].group_offset + goff]; g = *gp; propagate = (g == 0); assert((g & (ZU(1) << (bit & BITMAP_GROUP_NBITS_MASK))) == 0); g ^= ZU(1) << (bit & BITMAP_GROUP_NBITS_MASK); *gp = g; if (!propagate) { break; } } } #endif /* BITMAP_USE_TREE */ } #endif /* JEMALLOC_INTERNAL_BITMAP_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/cache_bin.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/cache_bin.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/cache_bin.h (revision 360233) @@ -1,114 +1,131 @@ #ifndef JEMALLOC_INTERNAL_CACHE_BIN_H #define JEMALLOC_INTERNAL_CACHE_BIN_H #include "jemalloc/internal/ql.h" /* * The cache_bins are the mechanism that the tcache and the arena use to * communicate. The tcache fills from and flushes to the arena by passing a * cache_bin_t to fill/flush. When the arena needs to pull stats from the * tcaches associated with it, it does so by iterating over its * cache_bin_array_descriptor_t objects and reading out per-bin stats it * contains. This makes it so that the arena need not know about the existence * of the tcache at all. */ /* * The count of the number of cached allocations in a bin. We make this signed * so that negative numbers can encode "invalid" states (e.g. a low water mark * of -1 for a cache that has been depleted). */ typedef int32_t cache_bin_sz_t; typedef struct cache_bin_stats_s cache_bin_stats_t; struct cache_bin_stats_s { /* * Number of allocation requests that corresponded to the size of this * bin. */ uint64_t nrequests; }; /* * Read-only information associated with each element of tcache_t's tbins array * is stored separately, mainly to reduce memory usage. */ typedef struct cache_bin_info_s cache_bin_info_t; struct cache_bin_info_s { /* Upper limit on ncached. */ cache_bin_sz_t ncached_max; }; typedef struct cache_bin_s cache_bin_t; struct cache_bin_s { /* Min # cached since last GC. */ cache_bin_sz_t low_water; /* # of cached objects. */ cache_bin_sz_t ncached; /* * ncached and stats are both modified frequently. Let's keep them * close so that they have a higher chance of being on the same * cacheline, thus less write-backs. */ cache_bin_stats_t tstats; /* * Stack of available objects. * * To make use of adjacent cacheline prefetch, the items in the avail * stack goes to higher address for newer allocations. avail points * just above the available space, which means that * avail[-ncached, ... -1] are available items and the lowest item will * be allocated first. */ void **avail; }; typedef struct cache_bin_array_descriptor_s cache_bin_array_descriptor_t; struct cache_bin_array_descriptor_s { /* * The arena keeps a list of the cache bins associated with it, for * stats collection. */ ql_elm(cache_bin_array_descriptor_t) link; /* Pointers to the tcache bins. */ cache_bin_t *bins_small; cache_bin_t *bins_large; }; static inline void cache_bin_array_descriptor_init(cache_bin_array_descriptor_t *descriptor, cache_bin_t *bins_small, cache_bin_t *bins_large) { ql_elm_new(descriptor, link); descriptor->bins_small = bins_small; descriptor->bins_large = bins_large; } JEMALLOC_ALWAYS_INLINE void * cache_bin_alloc_easy(cache_bin_t *bin, bool *success) { void *ret; - if (unlikely(bin->ncached == 0)) { - bin->low_water = -1; - *success = false; - return NULL; + bin->ncached--; + + /* + * Check for both bin->ncached == 0 and ncached < low_water + * in a single branch. + */ + if (unlikely(bin->ncached <= bin->low_water)) { + bin->low_water = bin->ncached; + if (bin->ncached == -1) { + bin->ncached = 0; + *success = false; + return NULL; + } } + /* * success (instead of ret) should be checked upon the return of this * function. We avoid checking (ret == NULL) because there is never a * null stored on the avail stack (which is unknown to the compiler), * and eagerly checking ret would cause pipeline stall (waiting for the * cacheline). */ *success = true; - ret = *(bin->avail - bin->ncached); - bin->ncached--; + ret = *(bin->avail - (bin->ncached + 1)); - if (unlikely(bin->ncached < bin->low_water)) { - bin->low_water = bin->ncached; + return ret; +} + +JEMALLOC_ALWAYS_INLINE bool +cache_bin_dalloc_easy(cache_bin_t *bin, cache_bin_info_t *bin_info, void *ptr) { + if (unlikely(bin->ncached == bin_info->ncached_max)) { + return false; } + assert(bin->ncached < bin_info->ncached_max); + bin->ncached++; + *(bin->avail - bin->ncached) = ptr; - return ret; + return true; } #endif /* JEMALLOC_INTERNAL_CACHE_BIN_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/ctl.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/ctl.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/ctl.h (revision 360233) @@ -1,131 +1,134 @@ #ifndef JEMALLOC_INTERNAL_CTL_H #define JEMALLOC_INTERNAL_CTL_H #include "jemalloc/internal/jemalloc_internal_types.h" #include "jemalloc/internal/malloc_io.h" #include "jemalloc/internal/mutex_prof.h" #include "jemalloc/internal/ql.h" -#include "jemalloc/internal/size_classes.h" +#include "jemalloc/internal/sc.h" #include "jemalloc/internal/stats.h" /* Maximum ctl tree depth. */ #define CTL_MAX_DEPTH 7 typedef struct ctl_node_s { bool named; } ctl_node_t; typedef struct ctl_named_node_s { ctl_node_t node; const char *name; /* If (nchildren == 0), this is a terminal node. */ size_t nchildren; const ctl_node_t *children; int (*ctl)(tsd_t *, const size_t *, size_t, void *, size_t *, void *, size_t); } ctl_named_node_t; typedef struct ctl_indexed_node_s { struct ctl_node_s node; const ctl_named_node_t *(*index)(tsdn_t *, const size_t *, size_t, size_t); } ctl_indexed_node_t; typedef struct ctl_arena_stats_s { arena_stats_t astats; /* Aggregate stats for small size classes, based on bin stats. */ size_t allocated_small; uint64_t nmalloc_small; uint64_t ndalloc_small; uint64_t nrequests_small; + uint64_t nfills_small; + uint64_t nflushes_small; - bin_stats_t bstats[NBINS]; - arena_stats_large_t lstats[NSIZES - NBINS]; + bin_stats_t bstats[SC_NBINS]; + arena_stats_large_t lstats[SC_NSIZES - SC_NBINS]; + arena_stats_extents_t estats[SC_NPSIZES]; } ctl_arena_stats_t; typedef struct ctl_stats_s { size_t allocated; size_t active; size_t metadata; size_t metadata_thp; size_t resident; size_t mapped; size_t retained; background_thread_stats_t background_thread; mutex_prof_data_t mutex_prof_data[mutex_prof_num_global_mutexes]; } ctl_stats_t; typedef struct ctl_arena_s ctl_arena_t; struct ctl_arena_s { unsigned arena_ind; bool initialized; ql_elm(ctl_arena_t) destroyed_link; /* Basic stats, supported even if !config_stats. */ unsigned nthreads; const char *dss; ssize_t dirty_decay_ms; ssize_t muzzy_decay_ms; size_t pactive; size_t pdirty; size_t pmuzzy; /* NULL if !config_stats. */ ctl_arena_stats_t *astats; }; typedef struct ctl_arenas_s { uint64_t epoch; unsigned narenas; ql_head(ctl_arena_t) destroyed; /* * Element 0 corresponds to merged stats for extant arenas (accessed via * MALLCTL_ARENAS_ALL), element 1 corresponds to merged stats for * destroyed arenas (accessed via MALLCTL_ARENAS_DESTROYED), and the * remaining MALLOCX_ARENA_LIMIT elements correspond to arenas. */ ctl_arena_t *arenas[2 + MALLOCX_ARENA_LIMIT]; } ctl_arenas_t; int ctl_byname(tsd_t *tsd, const char *name, void *oldp, size_t *oldlenp, void *newp, size_t newlen); int ctl_nametomib(tsd_t *tsd, const char *name, size_t *mibp, size_t *miblenp); int ctl_bymib(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen); bool ctl_boot(void); void ctl_prefork(tsdn_t *tsdn); void ctl_postfork_parent(tsdn_t *tsdn); void ctl_postfork_child(tsdn_t *tsdn); #define xmallctl(name, oldp, oldlenp, newp, newlen) do { \ if (je_mallctl(name, oldp, oldlenp, newp, newlen) \ != 0) { \ malloc_printf( \ ": Failure in xmallctl(\"%s\", ...)\n", \ name); \ abort(); \ } \ } while (0) #define xmallctlnametomib(name, mibp, miblenp) do { \ if (je_mallctlnametomib(name, mibp, miblenp) != 0) { \ malloc_printf(": Failure in " \ "xmallctlnametomib(\"%s\", ...)\n", name); \ abort(); \ } \ } while (0) #define xmallctlbymib(mib, miblen, oldp, oldlenp, newp, newlen) do { \ if (je_mallctlbymib(mib, miblen, oldp, oldlenp, newp, \ newlen) != 0) { \ malloc_write( \ ": Failure in xmallctlbymib()\n"); \ abort(); \ } \ } while (0) #endif /* JEMALLOC_INTERNAL_CTL_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/emitter.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/emitter.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/emitter.h (revision 360233) @@ -1,435 +1,486 @@ #ifndef JEMALLOC_INTERNAL_EMITTER_H #define JEMALLOC_INTERNAL_EMITTER_H #include "jemalloc/internal/ql.h" typedef enum emitter_output_e emitter_output_t; enum emitter_output_e { emitter_output_json, emitter_output_table }; typedef enum emitter_justify_e emitter_justify_t; enum emitter_justify_e { emitter_justify_left, emitter_justify_right, /* Not for users; just to pass to internal functions. */ emitter_justify_none }; typedef enum emitter_type_e emitter_type_t; enum emitter_type_e { emitter_type_bool, emitter_type_int, emitter_type_unsigned, emitter_type_uint32, emitter_type_uint64, emitter_type_size, emitter_type_ssize, emitter_type_string, /* * A title is a column title in a table; it's just a string, but it's * not quoted. */ emitter_type_title, }; typedef struct emitter_col_s emitter_col_t; struct emitter_col_s { /* Filled in by the user. */ emitter_justify_t justify; int width; emitter_type_t type; union { bool bool_val; int int_val; unsigned unsigned_val; uint32_t uint32_val; + uint32_t uint32_t_val; uint64_t uint64_val; + uint64_t uint64_t_val; size_t size_val; ssize_t ssize_val; const char *str_val; }; /* Filled in by initialization. */ ql_elm(emitter_col_t) link; }; typedef struct emitter_row_s emitter_row_t; struct emitter_row_s { ql_head(emitter_col_t) cols; }; -static inline void -emitter_row_init(emitter_row_t *row) { - ql_new(&row->cols); -} - -static inline void -emitter_col_init(emitter_col_t *col, emitter_row_t *row) { - ql_elm_new(col, link); - ql_tail_insert(&row->cols, col, link); -} - typedef struct emitter_s emitter_t; struct emitter_s { emitter_output_t output; /* The output information. */ void (*write_cb)(void *, const char *); void *cbopaque; int nesting_depth; /* True if we've already emitted a value at the given depth. */ bool item_at_depth; + /* True if we emitted a key and will emit corresponding value next. */ + bool emitted_key; }; -static inline void -emitter_init(emitter_t *emitter, emitter_output_t emitter_output, - void (*write_cb)(void *, const char *), void *cbopaque) { - emitter->output = emitter_output; - emitter->write_cb = write_cb; - emitter->cbopaque = cbopaque; - emitter->item_at_depth = false; - emitter->nesting_depth = 0; -} - /* Internal convenience function. Write to the emitter the given string. */ JEMALLOC_FORMAT_PRINTF(2, 3) static inline void emitter_printf(emitter_t *emitter, const char *format, ...) { va_list ap; va_start(ap, format); malloc_vcprintf(emitter->write_cb, emitter->cbopaque, format, ap); va_end(ap); } -/* Write to the emitter the given string, but only in table mode. */ -JEMALLOC_FORMAT_PRINTF(2, 3) -static inline void -emitter_table_printf(emitter_t *emitter, const char *format, ...) { - if (emitter->output == emitter_output_table) { - va_list ap; - va_start(ap, format); - malloc_vcprintf(emitter->write_cb, emitter->cbopaque, format, ap); - va_end(ap); - } -} - -static inline void +static inline const char * JEMALLOC_FORMAT_ARG(3) emitter_gen_fmt(char *out_fmt, size_t out_size, const char *fmt_specifier, emitter_justify_t justify, int width) { size_t written; + fmt_specifier++; if (justify == emitter_justify_none) { written = malloc_snprintf(out_fmt, out_size, "%%%s", fmt_specifier); } else if (justify == emitter_justify_left) { written = malloc_snprintf(out_fmt, out_size, "%%-%d%s", width, fmt_specifier); } else { written = malloc_snprintf(out_fmt, out_size, "%%%d%s", width, fmt_specifier); } /* Only happens in case of bad format string, which *we* choose. */ assert(written < out_size); + return out_fmt; } /* * Internal. Emit the given value type in the relevant encoding (so that the * bool true gets mapped to json "true", but the string "true" gets mapped to * json "\"true\"", for instance. * * Width is ignored if justify is emitter_justify_none. */ static inline void emitter_print_value(emitter_t *emitter, emitter_justify_t justify, int width, emitter_type_t value_type, const void *value) { size_t str_written; #define BUF_SIZE 256 #define FMT_SIZE 10 /* * We dynamically generate a format string to emit, to let us use the * snprintf machinery. This is kinda hacky, but gets the job done * quickly without having to think about the various snprintf edge * cases. */ char fmt[FMT_SIZE]; char buf[BUF_SIZE]; #define EMIT_SIMPLE(type, format) \ - emitter_gen_fmt(fmt, FMT_SIZE, format, justify, width); \ - emitter_printf(emitter, fmt, *(const type *)value); \ + emitter_printf(emitter, \ + emitter_gen_fmt(fmt, FMT_SIZE, format, justify, width), \ + *(const type *)value); switch (value_type) { case emitter_type_bool: - emitter_gen_fmt(fmt, FMT_SIZE, "s", justify, width); - emitter_printf(emitter, fmt, *(const bool *)value ? - "true" : "false"); + emitter_printf(emitter, + emitter_gen_fmt(fmt, FMT_SIZE, "%s", justify, width), + *(const bool *)value ? "true" : "false"); break; case emitter_type_int: - EMIT_SIMPLE(int, "d") + EMIT_SIMPLE(int, "%d") break; case emitter_type_unsigned: - EMIT_SIMPLE(unsigned, "u") + EMIT_SIMPLE(unsigned, "%u") break; case emitter_type_ssize: - EMIT_SIMPLE(ssize_t, "zd") + EMIT_SIMPLE(ssize_t, "%zd") break; case emitter_type_size: - EMIT_SIMPLE(size_t, "zu") + EMIT_SIMPLE(size_t, "%zu") break; case emitter_type_string: str_written = malloc_snprintf(buf, BUF_SIZE, "\"%s\"", *(const char *const *)value); /* * We control the strings we output; we shouldn't get anything * anywhere near the fmt size. */ assert(str_written < BUF_SIZE); - emitter_gen_fmt(fmt, FMT_SIZE, "s", justify, width); - emitter_printf(emitter, fmt, buf); + emitter_printf(emitter, + emitter_gen_fmt(fmt, FMT_SIZE, "%s", justify, width), buf); break; case emitter_type_uint32: - EMIT_SIMPLE(uint32_t, FMTu32) + EMIT_SIMPLE(uint32_t, "%" FMTu32) break; case emitter_type_uint64: - EMIT_SIMPLE(uint64_t, FMTu64) + EMIT_SIMPLE(uint64_t, "%" FMTu64) break; case emitter_type_title: - EMIT_SIMPLE(char *const, "s"); + EMIT_SIMPLE(char *const, "%s"); break; default: unreachable(); } #undef BUF_SIZE #undef FMT_SIZE } /* Internal functions. In json mode, tracks nesting state. */ static inline void emitter_nest_inc(emitter_t *emitter) { emitter->nesting_depth++; emitter->item_at_depth = false; } static inline void emitter_nest_dec(emitter_t *emitter) { emitter->nesting_depth--; emitter->item_at_depth = true; } static inline void emitter_indent(emitter_t *emitter) { int amount = emitter->nesting_depth; const char *indent_str; if (emitter->output == emitter_output_json) { indent_str = "\t"; } else { amount *= 2; indent_str = " "; } for (int i = 0; i < amount; i++) { emitter_printf(emitter, "%s", indent_str); } } static inline void emitter_json_key_prefix(emitter_t *emitter) { + if (emitter->emitted_key) { + emitter->emitted_key = false; + return; + } emitter_printf(emitter, "%s\n", emitter->item_at_depth ? "," : ""); emitter_indent(emitter); } +/******************************************************************************/ +/* Public functions for emitter_t. */ + static inline void -emitter_begin(emitter_t *emitter) { - if (emitter->output == emitter_output_json) { - assert(emitter->nesting_depth == 0); - emitter_printf(emitter, "{"); - emitter_nest_inc(emitter); - } else { - // tabular init - emitter_printf(emitter, "%s", ""); - } +emitter_init(emitter_t *emitter, emitter_output_t emitter_output, + void (*write_cb)(void *, const char *), void *cbopaque) { + emitter->output = emitter_output; + emitter->write_cb = write_cb; + emitter->cbopaque = cbopaque; + emitter->item_at_depth = false; + emitter->emitted_key = false; + emitter->nesting_depth = 0; } +/******************************************************************************/ +/* JSON public API. */ + +/* + * Emits a key (e.g. as appears in an object). The next json entity emitted will + * be the corresponding value. + */ static inline void -emitter_end(emitter_t *emitter) { +emitter_json_key(emitter_t *emitter, const char *json_key) { if (emitter->output == emitter_output_json) { - assert(emitter->nesting_depth == 1); - emitter_nest_dec(emitter); - emitter_printf(emitter, "\n}\n"); + emitter_json_key_prefix(emitter); + emitter_printf(emitter, "\"%s\": ", json_key); + emitter->emitted_key = true; } } -/* - * Note emits a different kv pair as well, but only in table mode. Omits the - * note if table_note_key is NULL. - */ static inline void -emitter_kv_note(emitter_t *emitter, const char *json_key, const char *table_key, - emitter_type_t value_type, const void *value, - const char *table_note_key, emitter_type_t table_note_value_type, - const void *table_note_value) { +emitter_json_value(emitter_t *emitter, emitter_type_t value_type, + const void *value) { if (emitter->output == emitter_output_json) { - assert(emitter->nesting_depth > 0); emitter_json_key_prefix(emitter); - emitter_printf(emitter, "\"%s\": ", json_key); emitter_print_value(emitter, emitter_justify_none, -1, value_type, value); - } else { - emitter_indent(emitter); - emitter_printf(emitter, "%s: ", table_key); - emitter_print_value(emitter, emitter_justify_none, -1, - value_type, value); - if (table_note_key != NULL) { - emitter_printf(emitter, " (%s: ", table_note_key); - emitter_print_value(emitter, emitter_justify_none, -1, - table_note_value_type, table_note_value); - emitter_printf(emitter, ")"); - } - emitter_printf(emitter, "\n"); + emitter->item_at_depth = true; } - emitter->item_at_depth = true; } +/* Shorthand for calling emitter_json_key and then emitter_json_value. */ static inline void -emitter_kv(emitter_t *emitter, const char *json_key, const char *table_key, +emitter_json_kv(emitter_t *emitter, const char *json_key, emitter_type_t value_type, const void *value) { - emitter_kv_note(emitter, json_key, table_key, value_type, value, NULL, - emitter_type_bool, NULL); + emitter_json_key(emitter, json_key); + emitter_json_value(emitter, value_type, value); } static inline void -emitter_json_kv(emitter_t *emitter, const char *json_key, - emitter_type_t value_type, const void *value) { +emitter_json_array_begin(emitter_t *emitter) { if (emitter->output == emitter_output_json) { - emitter_kv(emitter, json_key, NULL, value_type, value); + emitter_json_key_prefix(emitter); + emitter_printf(emitter, "["); + emitter_nest_inc(emitter); } } +/* Shorthand for calling emitter_json_key and then emitter_json_array_begin. */ static inline void -emitter_table_kv(emitter_t *emitter, const char *table_key, - emitter_type_t value_type, const void *value) { - if (emitter->output == emitter_output_table) { - emitter_kv(emitter, NULL, table_key, value_type, value); +emitter_json_array_kv_begin(emitter_t *emitter, const char *json_key) { + emitter_json_key(emitter, json_key); + emitter_json_array_begin(emitter); +} + +static inline void +emitter_json_array_end(emitter_t *emitter) { + if (emitter->output == emitter_output_json) { + assert(emitter->nesting_depth > 0); + emitter_nest_dec(emitter); + emitter_printf(emitter, "\n"); + emitter_indent(emitter); + emitter_printf(emitter, "]"); } } static inline void -emitter_dict_begin(emitter_t *emitter, const char *json_key, - const char *table_header) { +emitter_json_object_begin(emitter_t *emitter) { if (emitter->output == emitter_output_json) { emitter_json_key_prefix(emitter); - emitter_printf(emitter, "\"%s\": {", json_key); + emitter_printf(emitter, "{"); emitter_nest_inc(emitter); - } else { - emitter_indent(emitter); - emitter_printf(emitter, "%s\n", table_header); - emitter_nest_inc(emitter); } } +/* Shorthand for calling emitter_json_key and then emitter_json_object_begin. */ static inline void -emitter_dict_end(emitter_t *emitter) { +emitter_json_object_kv_begin(emitter_t *emitter, const char *json_key) { + emitter_json_key(emitter, json_key); + emitter_json_object_begin(emitter); +} + +static inline void +emitter_json_object_end(emitter_t *emitter) { if (emitter->output == emitter_output_json) { assert(emitter->nesting_depth > 0); emitter_nest_dec(emitter); emitter_printf(emitter, "\n"); emitter_indent(emitter); emitter_printf(emitter, "}"); - } else { - emitter_nest_dec(emitter); } } + +/******************************************************************************/ +/* Table public API. */ + static inline void -emitter_json_dict_begin(emitter_t *emitter, const char *json_key) { - if (emitter->output == emitter_output_json) { - emitter_dict_begin(emitter, json_key, NULL); +emitter_table_dict_begin(emitter_t *emitter, const char *table_key) { + if (emitter->output == emitter_output_table) { + emitter_indent(emitter); + emitter_printf(emitter, "%s\n", table_key); + emitter_nest_inc(emitter); } } static inline void -emitter_json_dict_end(emitter_t *emitter) { - if (emitter->output == emitter_output_json) { - emitter_dict_end(emitter); +emitter_table_dict_end(emitter_t *emitter) { + if (emitter->output == emitter_output_table) { + emitter_nest_dec(emitter); } } static inline void -emitter_table_dict_begin(emitter_t *emitter, const char *table_key) { +emitter_table_kv_note(emitter_t *emitter, const char *table_key, + emitter_type_t value_type, const void *value, + const char *table_note_key, emitter_type_t table_note_value_type, + const void *table_note_value) { if (emitter->output == emitter_output_table) { - emitter_dict_begin(emitter, NULL, table_key); + emitter_indent(emitter); + emitter_printf(emitter, "%s: ", table_key); + emitter_print_value(emitter, emitter_justify_none, -1, + value_type, value); + if (table_note_key != NULL) { + emitter_printf(emitter, " (%s: ", table_note_key); + emitter_print_value(emitter, emitter_justify_none, -1, + table_note_value_type, table_note_value); + emitter_printf(emitter, ")"); + } + emitter_printf(emitter, "\n"); } + emitter->item_at_depth = true; } static inline void -emitter_table_dict_end(emitter_t *emitter) { +emitter_table_kv(emitter_t *emitter, const char *table_key, + emitter_type_t value_type, const void *value) { + emitter_table_kv_note(emitter, table_key, value_type, value, NULL, + emitter_type_bool, NULL); +} + + +/* Write to the emitter the given string, but only in table mode. */ +JEMALLOC_FORMAT_PRINTF(2, 3) +static inline void +emitter_table_printf(emitter_t *emitter, const char *format, ...) { if (emitter->output == emitter_output_table) { - emitter_dict_end(emitter); + va_list ap; + va_start(ap, format); + malloc_vcprintf(emitter->write_cb, emitter->cbopaque, format, ap); + va_end(ap); } } static inline void -emitter_json_arr_begin(emitter_t *emitter, const char *json_key) { - if (emitter->output == emitter_output_json) { - emitter_json_key_prefix(emitter); - emitter_printf(emitter, "\"%s\": [", json_key); - emitter_nest_inc(emitter); +emitter_table_row(emitter_t *emitter, emitter_row_t *row) { + if (emitter->output != emitter_output_table) { + return; } + emitter_col_t *col; + ql_foreach(col, &row->cols, link) { + emitter_print_value(emitter, col->justify, col->width, + col->type, (const void *)&col->bool_val); + } + emitter_table_printf(emitter, "\n"); } static inline void -emitter_json_arr_end(emitter_t *emitter) { +emitter_row_init(emitter_row_t *row) { + ql_new(&row->cols); +} + +static inline void +emitter_col_init(emitter_col_t *col, emitter_row_t *row) { + ql_elm_new(col, link); + ql_tail_insert(&row->cols, col, link); +} + + +/******************************************************************************/ +/* + * Generalized public API. Emits using either JSON or table, according to + * settings in the emitter_t. */ + +/* + * Note emits a different kv pair as well, but only in table mode. Omits the + * note if table_note_key is NULL. + */ +static inline void +emitter_kv_note(emitter_t *emitter, const char *json_key, const char *table_key, + emitter_type_t value_type, const void *value, + const char *table_note_key, emitter_type_t table_note_value_type, + const void *table_note_value) { if (emitter->output == emitter_output_json) { - assert(emitter->nesting_depth > 0); - emitter_nest_dec(emitter); - emitter_printf(emitter, "\n"); - emitter_indent(emitter); - emitter_printf(emitter, "]"); + emitter_json_key(emitter, json_key); + emitter_json_value(emitter, value_type, value); + } else { + emitter_table_kv_note(emitter, table_key, value_type, value, + table_note_key, table_note_value_type, table_note_value); } + emitter->item_at_depth = true; } static inline void -emitter_json_arr_obj_begin(emitter_t *emitter) { +emitter_kv(emitter_t *emitter, const char *json_key, const char *table_key, + emitter_type_t value_type, const void *value) { + emitter_kv_note(emitter, json_key, table_key, value_type, value, NULL, + emitter_type_bool, NULL); +} + +static inline void +emitter_dict_begin(emitter_t *emitter, const char *json_key, + const char *table_header) { if (emitter->output == emitter_output_json) { - emitter_json_key_prefix(emitter); - emitter_printf(emitter, "{"); - emitter_nest_inc(emitter); + emitter_json_key(emitter, json_key); + emitter_json_object_begin(emitter); + } else { + emitter_table_dict_begin(emitter, table_header); } } static inline void -emitter_json_arr_obj_end(emitter_t *emitter) { +emitter_dict_end(emitter_t *emitter) { if (emitter->output == emitter_output_json) { - assert(emitter->nesting_depth > 0); - emitter_nest_dec(emitter); - emitter_printf(emitter, "\n"); - emitter_indent(emitter); - emitter_printf(emitter, "}"); + emitter_json_object_end(emitter); + } else { + emitter_table_dict_end(emitter); } } static inline void -emitter_json_arr_value(emitter_t *emitter, emitter_type_t value_type, - const void *value) { +emitter_begin(emitter_t *emitter) { if (emitter->output == emitter_output_json) { - emitter_json_key_prefix(emitter); - emitter_print_value(emitter, emitter_justify_none, -1, - value_type, value); + assert(emitter->nesting_depth == 0); + emitter_printf(emitter, "{"); + emitter_nest_inc(emitter); + } else { + /* + * This guarantees that we always call write_cb at least once. + * This is useful if some invariant is established by each call + * to write_cb, but doesn't hold initially: e.g., some buffer + * holds a null-terminated string. + */ + emitter_printf(emitter, "%s", ""); } } static inline void -emitter_table_row(emitter_t *emitter, emitter_row_t *row) { - if (emitter->output != emitter_output_table) { - return; +emitter_end(emitter_t *emitter) { + if (emitter->output == emitter_output_json) { + assert(emitter->nesting_depth == 1); + emitter_nest_dec(emitter); + emitter_printf(emitter, "\n}\n"); } - emitter_col_t *col; - ql_foreach(col, &row->cols, link) { - emitter_print_value(emitter, col->justify, col->width, - col->type, (const void *)&col->bool_val); - } - emitter_table_printf(emitter, "\n"); } #endif /* JEMALLOC_INTERNAL_EMITTER_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/extent_externs.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/extent_externs.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/extent_externs.h (revision 360233) @@ -1,73 +1,83 @@ #ifndef JEMALLOC_INTERNAL_EXTENT_EXTERNS_H #define JEMALLOC_INTERNAL_EXTENT_EXTERNS_H #include "jemalloc/internal/mutex.h" #include "jemalloc/internal/mutex_pool.h" #include "jemalloc/internal/ph.h" #include "jemalloc/internal/rtree.h" extern size_t opt_lg_extent_max_active_fit; extern rtree_t extents_rtree; extern const extent_hooks_t extent_hooks_default; extern mutex_pool_t extent_mutex_pool; extent_t *extent_alloc(tsdn_t *tsdn, arena_t *arena); void extent_dalloc(tsdn_t *tsdn, arena_t *arena, extent_t *extent); extent_hooks_t *extent_hooks_get(arena_t *arena); extent_hooks_t *extent_hooks_set(tsd_t *tsd, arena_t *arena, extent_hooks_t *extent_hooks); #ifdef JEMALLOC_JET size_t extent_size_quantize_floor(size_t size); size_t extent_size_quantize_ceil(size_t size); #endif -rb_proto(, extent_avail_, extent_tree_t, extent_t) +ph_proto(, extent_avail_, extent_tree_t, extent_t) ph_proto(, extent_heap_, extent_heap_t, extent_t) bool extents_init(tsdn_t *tsdn, extents_t *extents, extent_state_t state, bool delay_coalesce); extent_state_t extents_state_get(const extents_t *extents); size_t extents_npages_get(extents_t *extents); +/* Get the number of extents in the given page size index. */ +size_t extents_nextents_get(extents_t *extents, pszind_t ind); +/* Get the sum total bytes of the extents in the given page size index. */ +size_t extents_nbytes_get(extents_t *extents, pszind_t ind); extent_t *extents_alloc(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extents_t *extents, void *new_addr, size_t size, size_t pad, size_t alignment, bool slab, szind_t szind, bool *zero, bool *commit); void extents_dalloc(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extents_t *extents, extent_t *extent); extent_t *extents_evict(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extents_t *extents, size_t npages_min); void extents_prefork(tsdn_t *tsdn, extents_t *extents); void extents_postfork_parent(tsdn_t *tsdn, extents_t *extents); void extents_postfork_child(tsdn_t *tsdn, extents_t *extents); extent_t *extent_alloc_wrapper(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, void *new_addr, size_t size, size_t pad, size_t alignment, bool slab, szind_t szind, bool *zero, bool *commit); void extent_dalloc_gap(tsdn_t *tsdn, arena_t *arena, extent_t *extent); void extent_dalloc_wrapper(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent); void extent_destroy_wrapper(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent); bool extent_commit_wrapper(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset, size_t length); bool extent_decommit_wrapper(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset, size_t length); bool extent_purge_lazy_wrapper(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset, size_t length); bool extent_purge_forced_wrapper(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset, size_t length); extent_t *extent_split_wrapper(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent, size_t size_a, szind_t szind_a, bool slab_a, size_t size_b, szind_t szind_b, bool slab_b); bool extent_merge_wrapper(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *a, extent_t *b); bool extent_boot(void); + +void extent_util_stats_get(tsdn_t *tsdn, const void *ptr, + size_t *nfree, size_t *nregs, size_t *size); +void extent_util_stats_verbose_get(tsdn_t *tsdn, const void *ptr, + size_t *nfree, size_t *nregs, size_t *size, + size_t *bin_nfree, size_t *bin_nregs, void **slabcur_addr); #endif /* JEMALLOC_INTERNAL_EXTENT_EXTERNS_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/extent_inlines.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/extent_inlines.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/extent_inlines.h (revision 360233) @@ -1,433 +1,501 @@ #ifndef JEMALLOC_INTERNAL_EXTENT_INLINES_H #define JEMALLOC_INTERNAL_EXTENT_INLINES_H #include "jemalloc/internal/mutex.h" #include "jemalloc/internal/mutex_pool.h" #include "jemalloc/internal/pages.h" #include "jemalloc/internal/prng.h" #include "jemalloc/internal/ql.h" +#include "jemalloc/internal/sc.h" #include "jemalloc/internal/sz.h" static inline void extent_lock(tsdn_t *tsdn, extent_t *extent) { assert(extent != NULL); mutex_pool_lock(tsdn, &extent_mutex_pool, (uintptr_t)extent); } static inline void extent_unlock(tsdn_t *tsdn, extent_t *extent) { assert(extent != NULL); mutex_pool_unlock(tsdn, &extent_mutex_pool, (uintptr_t)extent); } static inline void extent_lock2(tsdn_t *tsdn, extent_t *extent1, extent_t *extent2) { assert(extent1 != NULL && extent2 != NULL); mutex_pool_lock2(tsdn, &extent_mutex_pool, (uintptr_t)extent1, (uintptr_t)extent2); } static inline void extent_unlock2(tsdn_t *tsdn, extent_t *extent1, extent_t *extent2) { assert(extent1 != NULL && extent2 != NULL); mutex_pool_unlock2(tsdn, &extent_mutex_pool, (uintptr_t)extent1, (uintptr_t)extent2); } -static inline arena_t * -extent_arena_get(const extent_t *extent) { +static inline unsigned +extent_arena_ind_get(const extent_t *extent) { unsigned arena_ind = (unsigned)((extent->e_bits & EXTENT_BITS_ARENA_MASK) >> EXTENT_BITS_ARENA_SHIFT); - /* - * The following check is omitted because we should never actually read - * a NULL arena pointer. - */ - if (false && arena_ind >= MALLOCX_ARENA_LIMIT) { - return NULL; - } assert(arena_ind < MALLOCX_ARENA_LIMIT); + + return arena_ind; +} + +static inline arena_t * +extent_arena_get(const extent_t *extent) { + unsigned arena_ind = extent_arena_ind_get(extent); + return (arena_t *)atomic_load_p(&arenas[arena_ind], ATOMIC_ACQUIRE); } static inline szind_t extent_szind_get_maybe_invalid(const extent_t *extent) { szind_t szind = (szind_t)((extent->e_bits & EXTENT_BITS_SZIND_MASK) >> EXTENT_BITS_SZIND_SHIFT); - assert(szind <= NSIZES); + assert(szind <= SC_NSIZES); return szind; } static inline szind_t extent_szind_get(const extent_t *extent) { szind_t szind = extent_szind_get_maybe_invalid(extent); - assert(szind < NSIZES); /* Never call when "invalid". */ + assert(szind < SC_NSIZES); /* Never call when "invalid". */ return szind; } static inline size_t extent_usize_get(const extent_t *extent) { return sz_index2size(extent_szind_get(extent)); } +static inline unsigned +extent_binshard_get(const extent_t *extent) { + unsigned binshard = (unsigned)((extent->e_bits & + EXTENT_BITS_BINSHARD_MASK) >> EXTENT_BITS_BINSHARD_SHIFT); + assert(binshard < bin_infos[extent_szind_get(extent)].n_shards); + return binshard; +} + static inline size_t extent_sn_get(const extent_t *extent) { return (size_t)((extent->e_bits & EXTENT_BITS_SN_MASK) >> EXTENT_BITS_SN_SHIFT); } static inline extent_state_t extent_state_get(const extent_t *extent) { return (extent_state_t)((extent->e_bits & EXTENT_BITS_STATE_MASK) >> EXTENT_BITS_STATE_SHIFT); } static inline bool extent_zeroed_get(const extent_t *extent) { return (bool)((extent->e_bits & EXTENT_BITS_ZEROED_MASK) >> EXTENT_BITS_ZEROED_SHIFT); } static inline bool extent_committed_get(const extent_t *extent) { return (bool)((extent->e_bits & EXTENT_BITS_COMMITTED_MASK) >> EXTENT_BITS_COMMITTED_SHIFT); } static inline bool extent_dumpable_get(const extent_t *extent) { return (bool)((extent->e_bits & EXTENT_BITS_DUMPABLE_MASK) >> EXTENT_BITS_DUMPABLE_SHIFT); } static inline bool extent_slab_get(const extent_t *extent) { return (bool)((extent->e_bits & EXTENT_BITS_SLAB_MASK) >> EXTENT_BITS_SLAB_SHIFT); } static inline unsigned extent_nfree_get(const extent_t *extent) { assert(extent_slab_get(extent)); return (unsigned)((extent->e_bits & EXTENT_BITS_NFREE_MASK) >> EXTENT_BITS_NFREE_SHIFT); } static inline void * extent_base_get(const extent_t *extent) { assert(extent->e_addr == PAGE_ADDR2BASE(extent->e_addr) || !extent_slab_get(extent)); return PAGE_ADDR2BASE(extent->e_addr); } static inline void * extent_addr_get(const extent_t *extent) { assert(extent->e_addr == PAGE_ADDR2BASE(extent->e_addr) || !extent_slab_get(extent)); return extent->e_addr; } static inline size_t extent_size_get(const extent_t *extent) { return (extent->e_size_esn & EXTENT_SIZE_MASK); } static inline size_t extent_esn_get(const extent_t *extent) { return (extent->e_size_esn & EXTENT_ESN_MASK); } static inline size_t extent_bsize_get(const extent_t *extent) { return extent->e_bsize; } static inline void * extent_before_get(const extent_t *extent) { return (void *)((uintptr_t)extent_base_get(extent) - PAGE); } static inline void * extent_last_get(const extent_t *extent) { return (void *)((uintptr_t)extent_base_get(extent) + extent_size_get(extent) - PAGE); } static inline void * extent_past_get(const extent_t *extent) { return (void *)((uintptr_t)extent_base_get(extent) + extent_size_get(extent)); } static inline arena_slab_data_t * extent_slab_data_get(extent_t *extent) { assert(extent_slab_get(extent)); return &extent->e_slab_data; } static inline const arena_slab_data_t * extent_slab_data_get_const(const extent_t *extent) { assert(extent_slab_get(extent)); return &extent->e_slab_data; } static inline prof_tctx_t * extent_prof_tctx_get(const extent_t *extent) { return (prof_tctx_t *)atomic_load_p(&extent->e_prof_tctx, ATOMIC_ACQUIRE); } +static inline nstime_t +extent_prof_alloc_time_get(const extent_t *extent) { + return extent->e_alloc_time; +} + static inline void extent_arena_set(extent_t *extent, arena_t *arena) { unsigned arena_ind = (arena != NULL) ? arena_ind_get(arena) : ((1U << MALLOCX_ARENA_BITS) - 1); extent->e_bits = (extent->e_bits & ~EXTENT_BITS_ARENA_MASK) | ((uint64_t)arena_ind << EXTENT_BITS_ARENA_SHIFT); } static inline void +extent_binshard_set(extent_t *extent, unsigned binshard) { + /* The assertion assumes szind is set already. */ + assert(binshard < bin_infos[extent_szind_get(extent)].n_shards); + extent->e_bits = (extent->e_bits & ~EXTENT_BITS_BINSHARD_MASK) | + ((uint64_t)binshard << EXTENT_BITS_BINSHARD_SHIFT); +} + +static inline void extent_addr_set(extent_t *extent, void *addr) { extent->e_addr = addr; } static inline void -extent_addr_randomize(UNUSED tsdn_t *tsdn, extent_t *extent, size_t alignment) { +extent_addr_randomize(tsdn_t *tsdn, extent_t *extent, size_t alignment) { assert(extent_base_get(extent) == extent_addr_get(extent)); if (alignment < PAGE) { unsigned lg_range = LG_PAGE - lg_floor(CACHELINE_CEILING(alignment)); size_t r; if (!tsdn_null(tsdn)) { tsd_t *tsd = tsdn_tsd(tsdn); r = (size_t)prng_lg_range_u64( tsd_offset_statep_get(tsd), lg_range); } else { r = prng_lg_range_zu( &extent_arena_get(extent)->offset_state, lg_range, true); } uintptr_t random_offset = ((uintptr_t)r) << (LG_PAGE - lg_range); extent->e_addr = (void *)((uintptr_t)extent->e_addr + random_offset); assert(ALIGNMENT_ADDR2BASE(extent->e_addr, alignment) == extent->e_addr); } } static inline void extent_size_set(extent_t *extent, size_t size) { assert((size & ~EXTENT_SIZE_MASK) == 0); extent->e_size_esn = size | (extent->e_size_esn & ~EXTENT_SIZE_MASK); } static inline void extent_esn_set(extent_t *extent, size_t esn) { extent->e_size_esn = (extent->e_size_esn & ~EXTENT_ESN_MASK) | (esn & EXTENT_ESN_MASK); } static inline void extent_bsize_set(extent_t *extent, size_t bsize) { extent->e_bsize = bsize; } static inline void extent_szind_set(extent_t *extent, szind_t szind) { - assert(szind <= NSIZES); /* NSIZES means "invalid". */ + assert(szind <= SC_NSIZES); /* SC_NSIZES means "invalid". */ extent->e_bits = (extent->e_bits & ~EXTENT_BITS_SZIND_MASK) | ((uint64_t)szind << EXTENT_BITS_SZIND_SHIFT); } static inline void extent_nfree_set(extent_t *extent, unsigned nfree) { assert(extent_slab_get(extent)); extent->e_bits = (extent->e_bits & ~EXTENT_BITS_NFREE_MASK) | ((uint64_t)nfree << EXTENT_BITS_NFREE_SHIFT); } static inline void +extent_nfree_binshard_set(extent_t *extent, unsigned nfree, unsigned binshard) { + /* The assertion assumes szind is set already. */ + assert(binshard < bin_infos[extent_szind_get(extent)].n_shards); + extent->e_bits = (extent->e_bits & + (~EXTENT_BITS_NFREE_MASK & ~EXTENT_BITS_BINSHARD_MASK)) | + ((uint64_t)binshard << EXTENT_BITS_BINSHARD_SHIFT) | + ((uint64_t)nfree << EXTENT_BITS_NFREE_SHIFT); +} + +static inline void extent_nfree_inc(extent_t *extent) { assert(extent_slab_get(extent)); extent->e_bits += ((uint64_t)1U << EXTENT_BITS_NFREE_SHIFT); } static inline void extent_nfree_dec(extent_t *extent) { assert(extent_slab_get(extent)); extent->e_bits -= ((uint64_t)1U << EXTENT_BITS_NFREE_SHIFT); } static inline void +extent_nfree_sub(extent_t *extent, uint64_t n) { + assert(extent_slab_get(extent)); + extent->e_bits -= (n << EXTENT_BITS_NFREE_SHIFT); +} + +static inline void extent_sn_set(extent_t *extent, size_t sn) { extent->e_bits = (extent->e_bits & ~EXTENT_BITS_SN_MASK) | ((uint64_t)sn << EXTENT_BITS_SN_SHIFT); } static inline void extent_state_set(extent_t *extent, extent_state_t state) { extent->e_bits = (extent->e_bits & ~EXTENT_BITS_STATE_MASK) | ((uint64_t)state << EXTENT_BITS_STATE_SHIFT); } static inline void extent_zeroed_set(extent_t *extent, bool zeroed) { extent->e_bits = (extent->e_bits & ~EXTENT_BITS_ZEROED_MASK) | ((uint64_t)zeroed << EXTENT_BITS_ZEROED_SHIFT); } static inline void extent_committed_set(extent_t *extent, bool committed) { extent->e_bits = (extent->e_bits & ~EXTENT_BITS_COMMITTED_MASK) | ((uint64_t)committed << EXTENT_BITS_COMMITTED_SHIFT); } static inline void extent_dumpable_set(extent_t *extent, bool dumpable) { extent->e_bits = (extent->e_bits & ~EXTENT_BITS_DUMPABLE_MASK) | ((uint64_t)dumpable << EXTENT_BITS_DUMPABLE_SHIFT); } static inline void extent_slab_set(extent_t *extent, bool slab) { extent->e_bits = (extent->e_bits & ~EXTENT_BITS_SLAB_MASK) | ((uint64_t)slab << EXTENT_BITS_SLAB_SHIFT); } static inline void extent_prof_tctx_set(extent_t *extent, prof_tctx_t *tctx) { atomic_store_p(&extent->e_prof_tctx, tctx, ATOMIC_RELEASE); } static inline void +extent_prof_alloc_time_set(extent_t *extent, nstime_t t) { + nstime_copy(&extent->e_alloc_time, &t); +} + +static inline bool +extent_is_head_get(extent_t *extent) { + if (maps_coalesce) { + not_reached(); + } + + return (bool)((extent->e_bits & EXTENT_BITS_IS_HEAD_MASK) >> + EXTENT_BITS_IS_HEAD_SHIFT); +} + +static inline void +extent_is_head_set(extent_t *extent, bool is_head) { + if (maps_coalesce) { + not_reached(); + } + + extent->e_bits = (extent->e_bits & ~EXTENT_BITS_IS_HEAD_MASK) | + ((uint64_t)is_head << EXTENT_BITS_IS_HEAD_SHIFT); +} + +static inline void extent_init(extent_t *extent, arena_t *arena, void *addr, size_t size, bool slab, szind_t szind, size_t sn, extent_state_t state, bool zeroed, - bool committed, bool dumpable) { + bool committed, bool dumpable, extent_head_state_t is_head) { assert(addr == PAGE_ADDR2BASE(addr) || !slab); extent_arena_set(extent, arena); extent_addr_set(extent, addr); extent_size_set(extent, size); extent_slab_set(extent, slab); extent_szind_set(extent, szind); extent_sn_set(extent, sn); extent_state_set(extent, state); extent_zeroed_set(extent, zeroed); extent_committed_set(extent, committed); extent_dumpable_set(extent, dumpable); ql_elm_new(extent, ql_link); + if (!maps_coalesce) { + extent_is_head_set(extent, (is_head == EXTENT_IS_HEAD) ? true : + false); + } if (config_prof) { extent_prof_tctx_set(extent, NULL); } } static inline void extent_binit(extent_t *extent, void *addr, size_t bsize, size_t sn) { extent_arena_set(extent, NULL); extent_addr_set(extent, addr); extent_bsize_set(extent, bsize); extent_slab_set(extent, false); - extent_szind_set(extent, NSIZES); + extent_szind_set(extent, SC_NSIZES); extent_sn_set(extent, sn); extent_state_set(extent, extent_state_active); extent_zeroed_set(extent, true); extent_committed_set(extent, true); extent_dumpable_set(extent, true); } static inline void extent_list_init(extent_list_t *list) { ql_new(list); } static inline extent_t * extent_list_first(const extent_list_t *list) { return ql_first(list); } static inline extent_t * extent_list_last(const extent_list_t *list) { return ql_last(list, ql_link); } static inline void extent_list_append(extent_list_t *list, extent_t *extent) { ql_tail_insert(list, extent, ql_link); } static inline void extent_list_prepend(extent_list_t *list, extent_t *extent) { ql_head_insert(list, extent, ql_link); } static inline void extent_list_replace(extent_list_t *list, extent_t *to_remove, extent_t *to_insert) { ql_after_insert(to_remove, to_insert, ql_link); ql_remove(list, to_remove, ql_link); } static inline void extent_list_remove(extent_list_t *list, extent_t *extent) { ql_remove(list, extent, ql_link); } static inline int extent_sn_comp(const extent_t *a, const extent_t *b) { size_t a_sn = extent_sn_get(a); size_t b_sn = extent_sn_get(b); return (a_sn > b_sn) - (a_sn < b_sn); } static inline int extent_esn_comp(const extent_t *a, const extent_t *b) { size_t a_esn = extent_esn_get(a); size_t b_esn = extent_esn_get(b); return (a_esn > b_esn) - (a_esn < b_esn); } static inline int extent_ad_comp(const extent_t *a, const extent_t *b) { uintptr_t a_addr = (uintptr_t)extent_addr_get(a); uintptr_t b_addr = (uintptr_t)extent_addr_get(b); return (a_addr > b_addr) - (a_addr < b_addr); } static inline int extent_ead_comp(const extent_t *a, const extent_t *b) { uintptr_t a_eaddr = (uintptr_t)a; uintptr_t b_eaddr = (uintptr_t)b; return (a_eaddr > b_eaddr) - (a_eaddr < b_eaddr); } static inline int extent_snad_comp(const extent_t *a, const extent_t *b) { int ret; ret = extent_sn_comp(a, b); if (ret != 0) { return ret; } ret = extent_ad_comp(a, b); return ret; } static inline int extent_esnead_comp(const extent_t *a, const extent_t *b) { int ret; ret = extent_esn_comp(a, b); if (ret != 0) { return ret; } ret = extent_ead_comp(a, b); return ret; } #endif /* JEMALLOC_INTERNAL_EXTENT_INLINES_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/extent_structs.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/extent_structs.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/extent_structs.h (revision 360233) @@ -1,219 +1,256 @@ #ifndef JEMALLOC_INTERNAL_EXTENT_STRUCTS_H #define JEMALLOC_INTERNAL_EXTENT_STRUCTS_H #include "jemalloc/internal/atomic.h" +#include "jemalloc/internal/bit_util.h" #include "jemalloc/internal/bitmap.h" #include "jemalloc/internal/mutex.h" #include "jemalloc/internal/ql.h" #include "jemalloc/internal/ph.h" -#include "jemalloc/internal/size_classes.h" +#include "jemalloc/internal/sc.h" typedef enum { extent_state_active = 0, extent_state_dirty = 1, extent_state_muzzy = 2, extent_state_retained = 3 } extent_state_t; /* Extent (span of pages). Use accessor functions for e_* fields. */ struct extent_s { /* * Bitfield containing several fields: * * a: arena_ind * b: slab * c: committed * d: dumpable * z: zeroed * t: state * i: szind * f: nfree + * s: bin_shard * n: sn * - * nnnnnnnn ... nnnnffff ffffffii iiiiiitt zdcbaaaa aaaaaaaa + * nnnnnnnn ... nnnnnnss ssssffff ffffffii iiiiiitt zdcbaaaa aaaaaaaa * * arena_ind: Arena from which this extent came, or all 1 bits if * unassociated. * * slab: The slab flag indicates whether the extent is used for a slab * of small regions. This helps differentiate small size classes, * and it indicates whether interior pointers can be looked up via * iealloc(). * * committed: The committed flag indicates whether physical memory is * committed to the extent, whether explicitly or implicitly * as on a system that overcommits and satisfies physical * memory needs on demand via soft page faults. * * dumpable: The dumpable flag indicates whether or not we've set the * memory in question to be dumpable. Note that this * interacts somewhat subtly with user-specified extent hooks, * since we don't know if *they* are fiddling with * dumpability (in which case, we don't want to undo whatever * they're doing). To deal with this scenario, we: * - Make dumpable false only for memory allocated with the * default hooks. * - Only allow memory to go from non-dumpable to dumpable, * and only once. * - Never make the OS call to allow dumping when the * dumpable bit is already set. * These three constraints mean that we will never * accidentally dump user memory that the user meant to set * nondumpable with their extent hooks. * * * zeroed: The zeroed flag is used by extent recycling code to track * whether memory is zero-filled. * * state: The state flag is an extent_state_t. * * szind: The szind flag indicates usable size class index for * allocations residing in this extent, regardless of whether the * extent is a slab. Extent size and usable size often differ * even for non-slabs, either due to sz_large_pad or promotion of * sampled small regions. * * nfree: Number of free regions in slab. * + * bin_shard: the shard of the bin from which this extent came. + * * sn: Serial number (potentially non-unique). * * Serial numbers may wrap around if !opt_retain, but as long as * comparison functions fall back on address comparison for equal * serial numbers, stable (if imperfect) ordering is maintained. * * Serial numbers may not be unique even in the absence of * wrap-around, e.g. when splitting an extent and assigning the same * serial number to both resulting adjacent extents. */ uint64_t e_bits; #define MASK(CURRENT_FIELD_WIDTH, CURRENT_FIELD_SHIFT) ((((((uint64_t)0x1U) << (CURRENT_FIELD_WIDTH)) - 1)) << (CURRENT_FIELD_SHIFT)) #define EXTENT_BITS_ARENA_WIDTH MALLOCX_ARENA_BITS #define EXTENT_BITS_ARENA_SHIFT 0 #define EXTENT_BITS_ARENA_MASK MASK(EXTENT_BITS_ARENA_WIDTH, EXTENT_BITS_ARENA_SHIFT) #define EXTENT_BITS_SLAB_WIDTH 1 #define EXTENT_BITS_SLAB_SHIFT (EXTENT_BITS_ARENA_WIDTH + EXTENT_BITS_ARENA_SHIFT) #define EXTENT_BITS_SLAB_MASK MASK(EXTENT_BITS_SLAB_WIDTH, EXTENT_BITS_SLAB_SHIFT) #define EXTENT_BITS_COMMITTED_WIDTH 1 #define EXTENT_BITS_COMMITTED_SHIFT (EXTENT_BITS_SLAB_WIDTH + EXTENT_BITS_SLAB_SHIFT) #define EXTENT_BITS_COMMITTED_MASK MASK(EXTENT_BITS_COMMITTED_WIDTH, EXTENT_BITS_COMMITTED_SHIFT) #define EXTENT_BITS_DUMPABLE_WIDTH 1 #define EXTENT_BITS_DUMPABLE_SHIFT (EXTENT_BITS_COMMITTED_WIDTH + EXTENT_BITS_COMMITTED_SHIFT) #define EXTENT_BITS_DUMPABLE_MASK MASK(EXTENT_BITS_DUMPABLE_WIDTH, EXTENT_BITS_DUMPABLE_SHIFT) #define EXTENT_BITS_ZEROED_WIDTH 1 #define EXTENT_BITS_ZEROED_SHIFT (EXTENT_BITS_DUMPABLE_WIDTH + EXTENT_BITS_DUMPABLE_SHIFT) #define EXTENT_BITS_ZEROED_MASK MASK(EXTENT_BITS_ZEROED_WIDTH, EXTENT_BITS_ZEROED_SHIFT) #define EXTENT_BITS_STATE_WIDTH 2 #define EXTENT_BITS_STATE_SHIFT (EXTENT_BITS_ZEROED_WIDTH + EXTENT_BITS_ZEROED_SHIFT) #define EXTENT_BITS_STATE_MASK MASK(EXTENT_BITS_STATE_WIDTH, EXTENT_BITS_STATE_SHIFT) -#define EXTENT_BITS_SZIND_WIDTH LG_CEIL_NSIZES +#define EXTENT_BITS_SZIND_WIDTH LG_CEIL(SC_NSIZES) #define EXTENT_BITS_SZIND_SHIFT (EXTENT_BITS_STATE_WIDTH + EXTENT_BITS_STATE_SHIFT) #define EXTENT_BITS_SZIND_MASK MASK(EXTENT_BITS_SZIND_WIDTH, EXTENT_BITS_SZIND_SHIFT) #define EXTENT_BITS_NFREE_WIDTH (LG_SLAB_MAXREGS + 1) #define EXTENT_BITS_NFREE_SHIFT (EXTENT_BITS_SZIND_WIDTH + EXTENT_BITS_SZIND_SHIFT) #define EXTENT_BITS_NFREE_MASK MASK(EXTENT_BITS_NFREE_WIDTH, EXTENT_BITS_NFREE_SHIFT) -#define EXTENT_BITS_SN_SHIFT (EXTENT_BITS_NFREE_WIDTH + EXTENT_BITS_NFREE_SHIFT) +#define EXTENT_BITS_BINSHARD_WIDTH 6 +#define EXTENT_BITS_BINSHARD_SHIFT (EXTENT_BITS_NFREE_WIDTH + EXTENT_BITS_NFREE_SHIFT) +#define EXTENT_BITS_BINSHARD_MASK MASK(EXTENT_BITS_BINSHARD_WIDTH, EXTENT_BITS_BINSHARD_SHIFT) + +#define EXTENT_BITS_IS_HEAD_WIDTH 1 +#define EXTENT_BITS_IS_HEAD_SHIFT (EXTENT_BITS_BINSHARD_WIDTH + EXTENT_BITS_BINSHARD_SHIFT) +#define EXTENT_BITS_IS_HEAD_MASK MASK(EXTENT_BITS_IS_HEAD_WIDTH, EXTENT_BITS_IS_HEAD_SHIFT) + +#define EXTENT_BITS_SN_SHIFT (EXTENT_BITS_IS_HEAD_WIDTH + EXTENT_BITS_IS_HEAD_SHIFT) #define EXTENT_BITS_SN_MASK (UINT64_MAX << EXTENT_BITS_SN_SHIFT) /* Pointer to the extent that this structure is responsible for. */ void *e_addr; union { /* * Extent size and serial number associated with the extent * structure (different than the serial number for the extent at * e_addr). * * ssssssss [...] ssssssss ssssnnnn nnnnnnnn */ size_t e_size_esn; #define EXTENT_SIZE_MASK ((size_t)~(PAGE-1)) #define EXTENT_ESN_MASK ((size_t)PAGE-1) /* Base extent size, which may not be a multiple of PAGE. */ size_t e_bsize; }; /* * List linkage, used by a variety of lists: * - bin_t's slabs_full * - extents_t's LRU * - stashed dirty extents * - arena's large allocations */ ql_elm(extent_t) ql_link; /* * Linkage for per size class sn/address-ordered heaps, and * for extent_avail */ phn(extent_t) ph_link; union { /* Small region slab metadata. */ arena_slab_data_t e_slab_data; - /* - * Profile counters, used for large objects. Points to a - * prof_tctx_t. - */ - atomic_p_t e_prof_tctx; + /* Profiling data, used for large objects. */ + struct { + /* Time when this was allocated. */ + nstime_t e_alloc_time; + /* Points to a prof_tctx_t. */ + atomic_p_t e_prof_tctx; + }; }; }; typedef ql_head(extent_t) extent_list_t; typedef ph(extent_t) extent_tree_t; typedef ph(extent_t) extent_heap_t; /* Quantized collection of extents, with built-in LRU queue. */ struct extents_s { malloc_mutex_t mtx; /* * Quantized per size class heaps of extents. * * Synchronization: mtx. */ - extent_heap_t heaps[NPSIZES+1]; + extent_heap_t heaps[SC_NPSIZES + 1]; + atomic_zu_t nextents[SC_NPSIZES + 1]; + atomic_zu_t nbytes[SC_NPSIZES + 1]; /* * Bitmap for which set bits correspond to non-empty heaps. * * Synchronization: mtx. */ - bitmap_t bitmap[BITMAP_GROUPS(NPSIZES+1)]; + bitmap_t bitmap[BITMAP_GROUPS(SC_NPSIZES + 1)]; /* * LRU of all extents in heaps. * * Synchronization: mtx. */ extent_list_t lru; /* * Page sum for all extents in heaps. * * The synchronization here is a little tricky. Modifications to npages * must hold mtx, but reads need not (though, a reader who sees npages * without holding the mutex can't assume anything about the rest of the * state of the extents_t). */ atomic_zu_t npages; /* All stored extents must be in the same state. */ extent_state_t state; /* * If true, delay coalescing until eviction; otherwise coalesce during * deallocation. */ bool delay_coalesce; +}; + +/* + * The following two structs are for experimental purposes. See + * experimental_utilization_query_ctl and + * experimental_utilization_batch_query_ctl in src/ctl.c. + */ + +struct extent_util_stats_s { + size_t nfree; + size_t nregs; + size_t size; +}; + +struct extent_util_stats_verbose_s { + void *slabcur_addr; + size_t nfree; + size_t nregs; + size_t size; + size_t bin_nfree; + size_t bin_nregs; }; #endif /* JEMALLOC_INTERNAL_EXTENT_STRUCTS_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/extent_types.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/extent_types.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/extent_types.h (revision 360233) @@ -1,17 +1,23 @@ #ifndef JEMALLOC_INTERNAL_EXTENT_TYPES_H #define JEMALLOC_INTERNAL_EXTENT_TYPES_H typedef struct extent_s extent_t; typedef struct extents_s extents_t; +typedef struct extent_util_stats_s extent_util_stats_t; +typedef struct extent_util_stats_verbose_s extent_util_stats_verbose_t; + #define EXTENT_HOOKS_INITIALIZER NULL -#define EXTENT_GROW_MAX_PIND (NPSIZES - 1) - /* * When reuse (and split) an active extent, (1U << opt_lg_extent_max_active_fit) * is the max ratio between the size of the active extent and the new extent. */ #define LG_EXTENT_MAX_ACTIVE_FIT_DEFAULT 6 + +typedef enum { + EXTENT_NOT_HEAD, + EXTENT_IS_HEAD /* Only relevant for Windows && opt.retain. */ +} extent_head_state_t; #endif /* JEMALLOC_INTERNAL_EXTENT_TYPES_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/hash.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/hash.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/hash.h (revision 360233) @@ -1,318 +1,319 @@ #ifndef JEMALLOC_INTERNAL_HASH_H #define JEMALLOC_INTERNAL_HASH_H #include "jemalloc/internal/assert.h" /* * The following hash function is based on MurmurHash3, placed into the public * domain by Austin Appleby. See https://github.com/aappleby/smhasher for * details. */ /******************************************************************************/ /* Internal implementation. */ static inline uint32_t hash_rotl_32(uint32_t x, int8_t r) { return ((x << r) | (x >> (32 - r))); } static inline uint64_t hash_rotl_64(uint64_t x, int8_t r) { return ((x << r) | (x >> (64 - r))); } static inline uint32_t hash_get_block_32(const uint32_t *p, int i) { /* Handle unaligned read. */ if (unlikely((uintptr_t)p & (sizeof(uint32_t)-1)) != 0) { uint32_t ret; memcpy(&ret, (uint8_t *)(p + i), sizeof(uint32_t)); return ret; } return p[i]; } static inline uint64_t hash_get_block_64(const uint64_t *p, int i) { /* Handle unaligned read. */ if (unlikely((uintptr_t)p & (sizeof(uint64_t)-1)) != 0) { uint64_t ret; memcpy(&ret, (uint8_t *)(p + i), sizeof(uint64_t)); return ret; } return p[i]; } static inline uint32_t hash_fmix_32(uint32_t h) { h ^= h >> 16; h *= 0x85ebca6b; h ^= h >> 13; h *= 0xc2b2ae35; h ^= h >> 16; return h; } static inline uint64_t hash_fmix_64(uint64_t k) { k ^= k >> 33; k *= KQU(0xff51afd7ed558ccd); k ^= k >> 33; k *= KQU(0xc4ceb9fe1a85ec53); k ^= k >> 33; return k; } static inline uint32_t hash_x86_32(const void *key, int len, uint32_t seed) { const uint8_t *data = (const uint8_t *) key; const int nblocks = len / 4; uint32_t h1 = seed; const uint32_t c1 = 0xcc9e2d51; const uint32_t c2 = 0x1b873593; /* body */ { const uint32_t *blocks = (const uint32_t *) (data + nblocks*4); int i; for (i = -nblocks; i; i++) { uint32_t k1 = hash_get_block_32(blocks, i); k1 *= c1; k1 = hash_rotl_32(k1, 15); k1 *= c2; h1 ^= k1; h1 = hash_rotl_32(h1, 13); h1 = h1*5 + 0xe6546b64; } } /* tail */ { const uint8_t *tail = (const uint8_t *) (data + nblocks*4); uint32_t k1 = 0; switch (len & 3) { - case 3: k1 ^= tail[2] << 16; - case 2: k1 ^= tail[1] << 8; + case 3: k1 ^= tail[2] << 16; JEMALLOC_FALLTHROUGH + case 2: k1 ^= tail[1] << 8; JEMALLOC_FALLTHROUGH case 1: k1 ^= tail[0]; k1 *= c1; k1 = hash_rotl_32(k1, 15); k1 *= c2; h1 ^= k1; } } /* finalization */ h1 ^= len; h1 = hash_fmix_32(h1); return h1; } -UNUSED static inline void +static inline void hash_x86_128(const void *key, const int len, uint32_t seed, uint64_t r_out[2]) { const uint8_t * data = (const uint8_t *) key; const int nblocks = len / 16; uint32_t h1 = seed; uint32_t h2 = seed; uint32_t h3 = seed; uint32_t h4 = seed; const uint32_t c1 = 0x239b961b; const uint32_t c2 = 0xab0e9789; const uint32_t c3 = 0x38b34ae5; const uint32_t c4 = 0xa1e38b93; /* body */ { const uint32_t *blocks = (const uint32_t *) (data + nblocks*16); int i; for (i = -nblocks; i; i++) { uint32_t k1 = hash_get_block_32(blocks, i*4 + 0); uint32_t k2 = hash_get_block_32(blocks, i*4 + 1); uint32_t k3 = hash_get_block_32(blocks, i*4 + 2); uint32_t k4 = hash_get_block_32(blocks, i*4 + 3); k1 *= c1; k1 = hash_rotl_32(k1, 15); k1 *= c2; h1 ^= k1; h1 = hash_rotl_32(h1, 19); h1 += h2; h1 = h1*5 + 0x561ccd1b; k2 *= c2; k2 = hash_rotl_32(k2, 16); k2 *= c3; h2 ^= k2; h2 = hash_rotl_32(h2, 17); h2 += h3; h2 = h2*5 + 0x0bcaa747; k3 *= c3; k3 = hash_rotl_32(k3, 17); k3 *= c4; h3 ^= k3; h3 = hash_rotl_32(h3, 15); h3 += h4; h3 = h3*5 + 0x96cd1c35; k4 *= c4; k4 = hash_rotl_32(k4, 18); k4 *= c1; h4 ^= k4; h4 = hash_rotl_32(h4, 13); h4 += h1; h4 = h4*5 + 0x32ac3b17; } } /* tail */ { const uint8_t *tail = (const uint8_t *) (data + nblocks*16); uint32_t k1 = 0; uint32_t k2 = 0; uint32_t k3 = 0; uint32_t k4 = 0; switch (len & 15) { - case 15: k4 ^= tail[14] << 16; - case 14: k4 ^= tail[13] << 8; + case 15: k4 ^= tail[14] << 16; JEMALLOC_FALLTHROUGH + case 14: k4 ^= tail[13] << 8; JEMALLOC_FALLTHROUGH case 13: k4 ^= tail[12] << 0; k4 *= c4; k4 = hash_rotl_32(k4, 18); k4 *= c1; h4 ^= k4; - - case 12: k3 ^= tail[11] << 24; - case 11: k3 ^= tail[10] << 16; - case 10: k3 ^= tail[ 9] << 8; + JEMALLOC_FALLTHROUGH + case 12: k3 ^= tail[11] << 24; JEMALLOC_FALLTHROUGH + case 11: k3 ^= tail[10] << 16; JEMALLOC_FALLTHROUGH + case 10: k3 ^= tail[ 9] << 8; JEMALLOC_FALLTHROUGH case 9: k3 ^= tail[ 8] << 0; k3 *= c3; k3 = hash_rotl_32(k3, 17); k3 *= c4; h3 ^= k3; - - case 8: k2 ^= tail[ 7] << 24; - case 7: k2 ^= tail[ 6] << 16; - case 6: k2 ^= tail[ 5] << 8; + JEMALLOC_FALLTHROUGH + case 8: k2 ^= tail[ 7] << 24; JEMALLOC_FALLTHROUGH + case 7: k2 ^= tail[ 6] << 16; JEMALLOC_FALLTHROUGH + case 6: k2 ^= tail[ 5] << 8; JEMALLOC_FALLTHROUGH case 5: k2 ^= tail[ 4] << 0; k2 *= c2; k2 = hash_rotl_32(k2, 16); k2 *= c3; h2 ^= k2; - - case 4: k1 ^= tail[ 3] << 24; - case 3: k1 ^= tail[ 2] << 16; - case 2: k1 ^= tail[ 1] << 8; + JEMALLOC_FALLTHROUGH + case 4: k1 ^= tail[ 3] << 24; JEMALLOC_FALLTHROUGH + case 3: k1 ^= tail[ 2] << 16; JEMALLOC_FALLTHROUGH + case 2: k1 ^= tail[ 1] << 8; JEMALLOC_FALLTHROUGH case 1: k1 ^= tail[ 0] << 0; k1 *= c1; k1 = hash_rotl_32(k1, 15); k1 *= c2; h1 ^= k1; + break; } } /* finalization */ h1 ^= len; h2 ^= len; h3 ^= len; h4 ^= len; h1 += h2; h1 += h3; h1 += h4; h2 += h1; h3 += h1; h4 += h1; h1 = hash_fmix_32(h1); h2 = hash_fmix_32(h2); h3 = hash_fmix_32(h3); h4 = hash_fmix_32(h4); h1 += h2; h1 += h3; h1 += h4; h2 += h1; h3 += h1; h4 += h1; r_out[0] = (((uint64_t) h2) << 32) | h1; r_out[1] = (((uint64_t) h4) << 32) | h3; } -UNUSED static inline void +static inline void hash_x64_128(const void *key, const int len, const uint32_t seed, uint64_t r_out[2]) { const uint8_t *data = (const uint8_t *) key; const int nblocks = len / 16; uint64_t h1 = seed; uint64_t h2 = seed; const uint64_t c1 = KQU(0x87c37b91114253d5); const uint64_t c2 = KQU(0x4cf5ad432745937f); /* body */ { const uint64_t *blocks = (const uint64_t *) (data); int i; for (i = 0; i < nblocks; i++) { uint64_t k1 = hash_get_block_64(blocks, i*2 + 0); uint64_t k2 = hash_get_block_64(blocks, i*2 + 1); k1 *= c1; k1 = hash_rotl_64(k1, 31); k1 *= c2; h1 ^= k1; h1 = hash_rotl_64(h1, 27); h1 += h2; h1 = h1*5 + 0x52dce729; k2 *= c2; k2 = hash_rotl_64(k2, 33); k2 *= c1; h2 ^= k2; h2 = hash_rotl_64(h2, 31); h2 += h1; h2 = h2*5 + 0x38495ab5; } } /* tail */ { const uint8_t *tail = (const uint8_t*)(data + nblocks*16); uint64_t k1 = 0; uint64_t k2 = 0; switch (len & 15) { - case 15: k2 ^= ((uint64_t)(tail[14])) << 48; /* falls through */ - case 14: k2 ^= ((uint64_t)(tail[13])) << 40; /* falls through */ - case 13: k2 ^= ((uint64_t)(tail[12])) << 32; /* falls through */ - case 12: k2 ^= ((uint64_t)(tail[11])) << 24; /* falls through */ - case 11: k2 ^= ((uint64_t)(tail[10])) << 16; /* falls through */ - case 10: k2 ^= ((uint64_t)(tail[ 9])) << 8; /* falls through */ + case 15: k2 ^= ((uint64_t)(tail[14])) << 48; JEMALLOC_FALLTHROUGH + case 14: k2 ^= ((uint64_t)(tail[13])) << 40; JEMALLOC_FALLTHROUGH + case 13: k2 ^= ((uint64_t)(tail[12])) << 32; JEMALLOC_FALLTHROUGH + case 12: k2 ^= ((uint64_t)(tail[11])) << 24; JEMALLOC_FALLTHROUGH + case 11: k2 ^= ((uint64_t)(tail[10])) << 16; JEMALLOC_FALLTHROUGH + case 10: k2 ^= ((uint64_t)(tail[ 9])) << 8; JEMALLOC_FALLTHROUGH case 9: k2 ^= ((uint64_t)(tail[ 8])) << 0; k2 *= c2; k2 = hash_rotl_64(k2, 33); k2 *= c1; h2 ^= k2; - /* falls through */ - case 8: k1 ^= ((uint64_t)(tail[ 7])) << 56; /* falls through */ - case 7: k1 ^= ((uint64_t)(tail[ 6])) << 48; /* falls through */ - case 6: k1 ^= ((uint64_t)(tail[ 5])) << 40; /* falls through */ - case 5: k1 ^= ((uint64_t)(tail[ 4])) << 32; /* falls through */ - case 4: k1 ^= ((uint64_t)(tail[ 3])) << 24; /* falls through */ - case 3: k1 ^= ((uint64_t)(tail[ 2])) << 16; /* falls through */ - case 2: k1 ^= ((uint64_t)(tail[ 1])) << 8; /* falls through */ + JEMALLOC_FALLTHROUGH + case 8: k1 ^= ((uint64_t)(tail[ 7])) << 56; JEMALLOC_FALLTHROUGH + case 7: k1 ^= ((uint64_t)(tail[ 6])) << 48; JEMALLOC_FALLTHROUGH + case 6: k1 ^= ((uint64_t)(tail[ 5])) << 40; JEMALLOC_FALLTHROUGH + case 5: k1 ^= ((uint64_t)(tail[ 4])) << 32; JEMALLOC_FALLTHROUGH + case 4: k1 ^= ((uint64_t)(tail[ 3])) << 24; JEMALLOC_FALLTHROUGH + case 3: k1 ^= ((uint64_t)(tail[ 2])) << 16; JEMALLOC_FALLTHROUGH + case 2: k1 ^= ((uint64_t)(tail[ 1])) << 8; JEMALLOC_FALLTHROUGH case 1: k1 ^= ((uint64_t)(tail[ 0])) << 0; k1 *= c1; k1 = hash_rotl_64(k1, 31); k1 *= c2; h1 ^= k1; } } /* finalization */ h1 ^= len; h2 ^= len; h1 += h2; h2 += h1; h1 = hash_fmix_64(h1); h2 = hash_fmix_64(h2); h1 += h2; h2 += h1; r_out[0] = h1; r_out[1] = h2; } /******************************************************************************/ /* API. */ static inline void hash(const void *key, size_t len, const uint32_t seed, size_t r_hash[2]) { assert(len <= INT_MAX); /* Unfortunate implementation limitation. */ #if (LG_SIZEOF_PTR == 3 && !defined(JEMALLOC_BIG_ENDIAN)) hash_x64_128(key, (int)len, seed, (uint64_t *)r_hash); #else { uint64_t hashes[2]; hash_x86_128(key, (int)len, seed, hashes); r_hash[0] = (size_t)hashes[0]; r_hash[1] = (size_t)hashes[1]; } #endif } #endif /* JEMALLOC_INTERNAL_HASH_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/hook.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/hook.h (nonexistent) +++ head/contrib/jemalloc/include/jemalloc/internal/hook.h (revision 360233) @@ -0,0 +1,163 @@ +#ifndef JEMALLOC_INTERNAL_HOOK_H +#define JEMALLOC_INTERNAL_HOOK_H + +#include "jemalloc/internal/tsd.h" + +/* + * This API is *extremely* experimental, and may get ripped out, changed in API- + * and ABI-incompatible ways, be insufficiently or incorrectly documented, etc. + * + * It allows hooking the stateful parts of the API to see changes as they + * happen. + * + * Allocation hooks are called after the allocation is done, free hooks are + * called before the free is done, and expand hooks are called after the + * allocation is expanded. + * + * For realloc and rallocx, if the expansion happens in place, the expansion + * hook is called. If it is moved, then the alloc hook is called on the new + * location, and then the free hook is called on the old location (i.e. both + * hooks are invoked in between the alloc and the dalloc). + * + * If we return NULL from OOM, then usize might not be trustworthy. Calling + * realloc(NULL, size) only calls the alloc hook, and calling realloc(ptr, 0) + * only calls the free hook. (Calling realloc(NULL, 0) is treated as malloc(0), + * and only calls the alloc hook). + * + * Reentrancy: + * Reentrancy is guarded against from within the hook implementation. If you + * call allocator functions from within a hook, the hooks will not be invoked + * again. + * Threading: + * The installation of a hook synchronizes with all its uses. If you can + * prove the installation of a hook happens-before a jemalloc entry point, + * then the hook will get invoked (unless there's a racing removal). + * + * Hook insertion appears to be atomic at a per-thread level (i.e. if a thread + * allocates and has the alloc hook invoked, then a subsequent free on the + * same thread will also have the free hook invoked). + * + * The *removal* of a hook does *not* block until all threads are done with + * the hook. Hook authors have to be resilient to this, and need some + * out-of-band mechanism for cleaning up any dynamically allocated memory + * associated with their hook. + * Ordering: + * Order of hook execution is unspecified, and may be different than insertion + * order. + */ + +#define HOOK_MAX 4 + +enum hook_alloc_e { + hook_alloc_malloc, + hook_alloc_posix_memalign, + hook_alloc_aligned_alloc, + hook_alloc_calloc, + hook_alloc_memalign, + hook_alloc_valloc, + hook_alloc_mallocx, + + /* The reallocating functions have both alloc and dalloc variants */ + hook_alloc_realloc, + hook_alloc_rallocx, +}; +/* + * We put the enum typedef after the enum, since this file may get included by + * jemalloc_cpp.cpp, and C++ disallows enum forward declarations. + */ +typedef enum hook_alloc_e hook_alloc_t; + +enum hook_dalloc_e { + hook_dalloc_free, + hook_dalloc_dallocx, + hook_dalloc_sdallocx, + + /* + * The dalloc halves of reallocation (not called if in-place expansion + * happens). + */ + hook_dalloc_realloc, + hook_dalloc_rallocx, +}; +typedef enum hook_dalloc_e hook_dalloc_t; + + +enum hook_expand_e { + hook_expand_realloc, + hook_expand_rallocx, + hook_expand_xallocx, +}; +typedef enum hook_expand_e hook_expand_t; + +typedef void (*hook_alloc)( + void *extra, hook_alloc_t type, void *result, uintptr_t result_raw, + uintptr_t args_raw[3]); + +typedef void (*hook_dalloc)( + void *extra, hook_dalloc_t type, void *address, uintptr_t args_raw[3]); + +typedef void (*hook_expand)( + void *extra, hook_expand_t type, void *address, size_t old_usize, + size_t new_usize, uintptr_t result_raw, uintptr_t args_raw[4]); + +typedef struct hooks_s hooks_t; +struct hooks_s { + hook_alloc alloc_hook; + hook_dalloc dalloc_hook; + hook_expand expand_hook; + void *extra; +}; + +/* + * Begin implementation details; everything above this point might one day live + * in a public API. Everything below this point never will. + */ + +/* + * The realloc pathways haven't gotten any refactoring love in a while, and it's + * fairly difficult to pass information from the entry point to the hooks. We + * put the informaiton the hooks will need into a struct to encapsulate + * everything. + * + * Much of these pathways are force-inlined, so that the compiler can avoid + * materializing this struct until we hit an extern arena function. For fairly + * goofy reasons, *many* of the realloc paths hit an extern arena function. + * These paths are cold enough that it doesn't matter; eventually, we should + * rewrite the realloc code to make the expand-in-place and the + * free-then-realloc paths more orthogonal, at which point we don't need to + * spread the hook logic all over the place. + */ +typedef struct hook_ralloc_args_s hook_ralloc_args_t; +struct hook_ralloc_args_s { + /* I.e. as opposed to rallocx. */ + bool is_realloc; + /* + * The expand hook takes 4 arguments, even if only 3 are actually used; + * we add an extra one in case the user decides to memcpy without + * looking too closely at the hooked function. + */ + uintptr_t args[4]; +}; + +/* + * Returns an opaque handle to be used when removing the hook. NULL means that + * we couldn't install the hook. + */ +bool hook_boot(); + +void *hook_install(tsdn_t *tsdn, hooks_t *hooks); +/* Uninstalls the hook with the handle previously returned from hook_install. */ +void hook_remove(tsdn_t *tsdn, void *opaque); + +/* Hooks */ + +void hook_invoke_alloc(hook_alloc_t type, void *result, uintptr_t result_raw, + uintptr_t args_raw[3]); + +void hook_invoke_dalloc(hook_dalloc_t type, void *address, + uintptr_t args_raw[3]); + +void hook_invoke_expand(hook_expand_t type, void *address, size_t old_usize, + size_t new_usize, uintptr_t result_raw, uintptr_t args_raw[4]); + +#endif /* JEMALLOC_INTERNAL_HOOK_H */ Property changes on: head/contrib/jemalloc/include/jemalloc/internal/hook.h ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_decls.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_decls.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_decls.h (revision 360233) @@ -1,94 +1,97 @@ #ifndef JEMALLOC_INTERNAL_DECLS_H #define JEMALLOC_INTERNAL_DECLS_H #include "libc_private.h" #include "namespace.h" #include #ifdef _WIN32 # include # include "msvc_compat/windows_extra.h" # ifdef _WIN64 # if LG_VADDR <= 32 # error Generate the headers using x64 vcargs # endif # else # if LG_VADDR > 32 # undef LG_VADDR # define LG_VADDR 32 # endif # endif #else # include # include # if !defined(__pnacl__) && !defined(__native_client__) # include # if !defined(SYS_write) && defined(__NR_write) # define SYS_write __NR_write # endif # if defined(SYS_open) && defined(__aarch64__) /* Android headers may define SYS_open to __NR_open even though * __NR_open may not exist on AArch64 (superseded by __NR_openat). */ # undef SYS_open # endif # include # endif # include +# ifdef __FreeBSD__ +# include +# endif # include # ifdef JEMALLOC_OS_UNFAIR_LOCK # include # endif # ifdef JEMALLOC_GLIBC_MALLOC_HOOK # include # endif # include # include # include # ifdef JEMALLOC_HAVE_MACH_ABSOLUTE_TIME # include # endif #endif #include #include #ifndef SIZE_T_MAX # define SIZE_T_MAX SIZE_MAX #endif #ifndef SSIZE_MAX # define SSIZE_MAX ((ssize_t)(SIZE_T_MAX >> 1)) #endif #include #include #include #include #include #include #ifndef offsetof # define offsetof(type, member) ((size_t)&(((type *)NULL)->member)) #endif #include #include #include #ifdef _MSC_VER # include typedef intptr_t ssize_t; # define PATH_MAX 1024 # define STDERR_FILENO 2 # define __func__ __FUNCTION__ # ifdef JEMALLOC_HAS_RESTRICT # define restrict __restrict # endif /* Disable warnings about deprecated system functions. */ # pragma warning(disable: 4996) #if _MSC_VER < 1800 static int isblank(int c) { return (c == '\t' || c == ' '); } #endif #else # include #endif #include #endif /* JEMALLOC_INTERNAL_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_defs.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_defs.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_defs.h (revision 360233) @@ -1,367 +1,367 @@ /* 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_ /* * 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. */ /* #undef JEMALLOC_OVERRIDE___LIBC_CALLOC */ /* #undef JEMALLOC_OVERRIDE___LIBC_FREE */ /* #undef JEMALLOC_OVERRIDE___LIBC_MALLOC */ /* #undef JEMALLOC_OVERRIDE___LIBC_MEMALIGN */ /* #undef JEMALLOC_OVERRIDE___LIBC_REALLOC */ /* #undef 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 __asm__ volatile("pause") /* 1 if CPU_SPINWAIT is defined, 0 otherwise. */ #define HAVE_CPU_SPINWAIT 1 /* * 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. */ -/* #undef JEMALLOC_C11_ATOMICS */ +#define JEMALLOC_C11_ATOMICS 1 /* Defined if GCC __atomic atomics are available. */ -/* #undef JEMALLOC_GCC_ATOMIC_ATOMICS */ +#define JEMALLOC_GCC_ATOMIC_ATOMICS 1 +/* and the 8-bit variant support. */ +#define JEMALLOC_GCC_U8_ATOMIC_ATOMICS 1 /* Defined if GCC __sync atomics are available. */ #define JEMALLOC_GCC_SYNC_ATOMICS 1 +/* and the 8-bit variant support. */ +#define JEMALLOC_GCC_U8_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). - */ -#define 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). - */ -#define 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. */ /* #undef JEMALLOC_HAVE_SECURE_GETENV */ /* * Defined if issetugid(2) is available. */ #define JEMALLOC_HAVE_ISSETUGID /* Defined if pthread_atfork(3) is available. */ #define JEMALLOC_HAVE_PTHREAD_ATFORK /* Defined if pthread_setname_np(3) is available. */ /* #undef JEMALLOC_HAVE_PTHREAD_SETNAME_NP */ /* * Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available. */ /* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */ /* * 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. */ #define 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. */ /* #undef 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. */ #define JEMALLOC_MUTEX_INIT_CB 1 /* 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. */ #define JEMALLOC_UTRACE /* Support optional abort() on OOM. */ #define JEMALLOC_XMALLOC /* Support lazy locking (avoid locking unless a second thread is launched). */ #define 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 12 /* * 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 21 /* * 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. */ /* #undef 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 abort +#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 /* + * popcount*() functions to use for bitmapping. + */ +#define JEMALLOC_INTERNAL_POPCOUNTL __builtin_popcountl +#define JEMALLOC_INTERNAL_POPCOUNT __builtin_popcount + +/* * 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. */ #define JEMALLOC_SYSCTL_VM_OVERCOMMIT /* #undef 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). */ /* #undef 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 /* #undef 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. */ /* #undef 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. */ /* #undef JEMALLOC_HAS_ALLOCA_H */ /* 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). */ /* #undef JEMALLOC_GLIBC_MALLOC_HOOK */ /* glibc memalign hook. */ /* #undef 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 */ /* #undef JEMALLOC_HAVE_SCHED_GETCPU */ /* GNU specific sched_setaffinity support */ /* #undef 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 "abort_conf:false" /* 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. */ /* #undef JEMALLOC_STRERROR_R_RETURNS_CHAR_WITH_GNU_SOURCE */ + +/* Performs additional safety checks when defined. */ +/* #undef JEMALLOC_OPT_SAFETY_CHECKS */ #endif /* JEMALLOC_INTERNAL_DEFS_H_ */ Index: head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_defs_FreeBSD.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_defs_FreeBSD.h (nonexistent) +++ head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_defs_FreeBSD.h (revision 360233) @@ -0,0 +1,9 @@ +#ifndef __clang__ +# undef JEMALLOC_INTERNAL_UNREACHABLE +# define JEMALLOC_INTERNAL_UNREACHABLE abort + +# undef JEMALLOC_C11_ATOMICS +# undef JEMALLOC_GCC_ATOMIC_ATOMICS +# undef JEMALLOC_GCC_U8_ATOMIC_ATOMICS +# undef JEMALLOC_GCC_U8_SYNC_ATOMICS +#endif Property changes on: head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_defs_FreeBSD.h ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_externs.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_externs.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_externs.h (revision 360233) @@ -1,53 +1,57 @@ #ifndef JEMALLOC_INTERNAL_EXTERNS_H #define JEMALLOC_INTERNAL_EXTERNS_H #include "jemalloc/internal/atomic.h" -#include "jemalloc/internal/size_classes.h" #include "jemalloc/internal/tsd_types.h" /* TSD checks this to set thread local slow state accordingly. */ extern bool malloc_slow; /* Run-time options. */ extern bool opt_abort; extern bool opt_abort_conf; +extern bool opt_confirm_conf; extern const char *opt_junk; extern bool opt_junk_alloc; extern bool opt_junk_free; extern bool opt_utrace; extern bool opt_xmalloc; extern bool opt_zero; extern unsigned opt_narenas; /* Number of CPUs. */ extern unsigned ncpus; /* Number of arenas used for automatic multiplexing of threads and arenas. */ extern unsigned narenas_auto; +/* Base index for manual arenas. */ +extern unsigned manual_arena_base; + /* * Arenas that are used to service external requests. Not all elements of the * arenas array are necessarily used; arenas are created lazily as needed. */ extern atomic_p_t arenas[]; void *a0malloc(size_t size); void a0dalloc(void *ptr); void *bootstrap_malloc(size_t size); void *bootstrap_calloc(size_t num, size_t size); void bootstrap_free(void *ptr); void arena_set(unsigned ind, arena_t *arena); unsigned narenas_total_get(void); arena_t *arena_init(tsdn_t *tsdn, unsigned ind, extent_hooks_t *extent_hooks); arena_tdata_t *arena_tdata_get_hard(tsd_t *tsd, unsigned ind); arena_t *arena_choose_hard(tsd_t *tsd, bool internal); void arena_migrate(tsd_t *tsd, unsigned oldind, unsigned newind); void iarena_cleanup(tsd_t *tsd); void arena_cleanup(tsd_t *tsd); void arenas_tdata_cleanup(tsd_t *tsd); void jemalloc_prefork(void); void jemalloc_postfork_parent(void); void jemalloc_postfork_child(void); bool malloc_initialized(void); +void je_sdallocx_noflags(void *ptr, size_t size); #endif /* JEMALLOC_INTERNAL_EXTERNS_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_a.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_a.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_a.h (revision 360233) @@ -1,172 +1,174 @@ #ifndef JEMALLOC_INTERNAL_INLINES_A_H #define JEMALLOC_INTERNAL_INLINES_A_H #include "jemalloc/internal/atomic.h" #include "jemalloc/internal/bit_util.h" #include "jemalloc/internal/jemalloc_internal_types.h" -#include "jemalloc/internal/size_classes.h" +#include "jemalloc/internal/sc.h" #include "jemalloc/internal/ticker.h" JEMALLOC_ALWAYS_INLINE malloc_cpuid_t malloc_getcpu(void) { assert(have_percpu_arena); -#if defined(JEMALLOC_HAVE_SCHED_GETCPU) +#if defined(_WIN32) + return GetCurrentProcessorNumber(); +#elif defined(JEMALLOC_HAVE_SCHED_GETCPU) return (malloc_cpuid_t)sched_getcpu(); #else not_reached(); return -1; #endif } /* Return the chosen arena index based on current cpu. */ JEMALLOC_ALWAYS_INLINE unsigned percpu_arena_choose(void) { assert(have_percpu_arena && PERCPU_ARENA_ENABLED(opt_percpu_arena)); malloc_cpuid_t cpuid = malloc_getcpu(); assert(cpuid >= 0); unsigned arena_ind; if ((opt_percpu_arena == percpu_arena) || ((unsigned)cpuid < ncpus / 2)) { arena_ind = cpuid; } else { assert(opt_percpu_arena == per_phycpu_arena); /* Hyper threads on the same physical CPU share arena. */ arena_ind = cpuid - ncpus / 2; } return arena_ind; } /* Return the limit of percpu auto arena range, i.e. arenas[0...ind_limit). */ JEMALLOC_ALWAYS_INLINE unsigned percpu_arena_ind_limit(percpu_arena_mode_t mode) { assert(have_percpu_arena && PERCPU_ARENA_ENABLED(mode)); if (mode == per_phycpu_arena && ncpus > 1) { if (ncpus % 2) { /* This likely means a misconfig. */ return ncpus / 2 + 1; } return ncpus / 2; } else { return ncpus; } } static inline arena_tdata_t * arena_tdata_get(tsd_t *tsd, unsigned ind, bool refresh_if_missing) { arena_tdata_t *tdata; arena_tdata_t *arenas_tdata = tsd_arenas_tdata_get(tsd); if (unlikely(arenas_tdata == NULL)) { /* arenas_tdata hasn't been initialized yet. */ return arena_tdata_get_hard(tsd, ind); } if (unlikely(ind >= tsd_narenas_tdata_get(tsd))) { /* * ind is invalid, cache is old (too small), or tdata to be * initialized. */ return (refresh_if_missing ? arena_tdata_get_hard(tsd, ind) : NULL); } tdata = &arenas_tdata[ind]; if (likely(tdata != NULL) || !refresh_if_missing) { return tdata; } return arena_tdata_get_hard(tsd, ind); } static inline arena_t * arena_get(tsdn_t *tsdn, unsigned ind, bool init_if_missing) { arena_t *ret; assert(ind < MALLOCX_ARENA_LIMIT); ret = (arena_t *)atomic_load_p(&arenas[ind], ATOMIC_ACQUIRE); if (unlikely(ret == NULL)) { if (init_if_missing) { ret = arena_init(tsdn, ind, (extent_hooks_t *)&extent_hooks_default); } } return ret; } static inline ticker_t * decay_ticker_get(tsd_t *tsd, unsigned ind) { arena_tdata_t *tdata; tdata = arena_tdata_get(tsd, ind, true); if (unlikely(tdata == NULL)) { return NULL; } return &tdata->decay_ticker; } JEMALLOC_ALWAYS_INLINE cache_bin_t * tcache_small_bin_get(tcache_t *tcache, szind_t binind) { - assert(binind < NBINS); + assert(binind < SC_NBINS); return &tcache->bins_small[binind]; } JEMALLOC_ALWAYS_INLINE cache_bin_t * tcache_large_bin_get(tcache_t *tcache, szind_t binind) { - assert(binind >= NBINS &&binind < nhbins); - return &tcache->bins_large[binind - NBINS]; + assert(binind >= SC_NBINS &&binind < nhbins); + return &tcache->bins_large[binind - SC_NBINS]; } JEMALLOC_ALWAYS_INLINE bool tcache_available(tsd_t *tsd) { /* * Thread specific auto tcache might be unavailable if: 1) during tcache * initialization, or 2) disabled through thread.tcache.enabled mallctl * or config options. This check covers all cases. */ if (likely(tsd_tcache_enabled_get(tsd))) { /* Associated arena == NULL implies tcache init in progress. */ assert(tsd_tcachep_get(tsd)->arena == NULL || tcache_small_bin_get(tsd_tcachep_get(tsd), 0)->avail != NULL); return true; } return false; } JEMALLOC_ALWAYS_INLINE tcache_t * tcache_get(tsd_t *tsd) { if (!tcache_available(tsd)) { return NULL; } return tsd_tcachep_get(tsd); } static inline void pre_reentrancy(tsd_t *tsd, arena_t *arena) { /* arena is the current context. Reentry from a0 is not allowed. */ assert(arena != arena_get(tsd_tsdn(tsd), 0, false)); bool fast = tsd_fast(tsd); assert(tsd_reentrancy_level_get(tsd) < INT8_MAX); ++*tsd_reentrancy_levelp_get(tsd); if (fast) { /* Prepare slow path for reentrancy. */ tsd_slow_update(tsd); - assert(tsd->state == tsd_state_nominal_slow); + assert(tsd_state_get(tsd) == tsd_state_nominal_slow); } } static inline void post_reentrancy(tsd_t *tsd) { int8_t *reentrancy_level = tsd_reentrancy_levelp_get(tsd); assert(*reentrancy_level > 0); if (--*reentrancy_level == 0) { tsd_slow_update(tsd); } } #endif /* JEMALLOC_INTERNAL_INLINES_A_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_b.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_b.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_b.h (revision 360233) @@ -1,86 +1,87 @@ #ifndef JEMALLOC_INTERNAL_INLINES_B_H #define JEMALLOC_INTERNAL_INLINES_B_H #include "jemalloc/internal/rtree.h" /* Choose an arena based on a per-thread value. */ static inline arena_t * arena_choose_impl(tsd_t *tsd, arena_t *arena, bool internal) { arena_t *ret; if (arena != NULL) { return arena; } /* During reentrancy, arena 0 is the safest bet. */ if (unlikely(tsd_reentrancy_level_get(tsd) > 0)) { return arena_get(tsd_tsdn(tsd), 0, true); } ret = internal ? tsd_iarena_get(tsd) : tsd_arena_get(tsd); if (unlikely(ret == NULL)) { ret = arena_choose_hard(tsd, internal); assert(ret); if (tcache_available(tsd)) { tcache_t *tcache = tcache_get(tsd); if (tcache->arena != NULL) { /* See comments in tcache_data_init().*/ assert(tcache->arena == arena_get(tsd_tsdn(tsd), 0, false)); if (tcache->arena != ret) { tcache_arena_reassociate(tsd_tsdn(tsd), tcache, ret); } } else { tcache_arena_associate(tsd_tsdn(tsd), tcache, ret); } } } /* * Note that for percpu arena, if the current arena is outside of the * auto percpu arena range, (i.e. thread is assigned to a manually * managed arena), then percpu arena is skipped. */ if (have_percpu_arena && PERCPU_ARENA_ENABLED(opt_percpu_arena) && !internal && (arena_ind_get(ret) < percpu_arena_ind_limit(opt_percpu_arena)) && (ret->last_thd != tsd_tsdn(tsd))) { unsigned ind = percpu_arena_choose(); if (arena_ind_get(ret) != ind) { percpu_arena_update(tsd, ind); ret = tsd_arena_get(tsd); } ret->last_thd = tsd_tsdn(tsd); } return ret; } static inline arena_t * arena_choose(tsd_t *tsd, arena_t *arena) { return arena_choose_impl(tsd, arena, false); } static inline arena_t * arena_ichoose(tsd_t *tsd, arena_t *arena) { return arena_choose_impl(tsd, arena, true); } static inline bool arena_is_auto(arena_t *arena) { assert(narenas_auto > 0); - return (arena_ind_get(arena) < narenas_auto); + + return (arena_ind_get(arena) < manual_arena_base); } JEMALLOC_ALWAYS_INLINE extent_t * iealloc(tsdn_t *tsdn, const void *ptr) { rtree_ctx_t rtree_ctx_fallback; rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); return rtree_extent_read(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr, true); } #endif /* JEMALLOC_INTERNAL_INLINES_B_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_c.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_c.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_c.h (revision 360233) @@ -1,218 +1,222 @@ #ifndef JEMALLOC_INTERNAL_INLINES_C_H #define JEMALLOC_INTERNAL_INLINES_C_H +#include "jemalloc/internal/hook.h" #include "jemalloc/internal/jemalloc_internal_types.h" #include "jemalloc/internal/sz.h" #include "jemalloc/internal/witness.h" /* * Translating the names of the 'i' functions: * Abbreviations used in the first part of the function name (before * alloc/dalloc) describe what that function accomplishes: * a: arena (query) * s: size (query, or sized deallocation) * e: extent (query) * p: aligned (allocates) * vs: size (query, without knowing that the pointer is into the heap) * r: rallocx implementation * x: xallocx implementation * Abbreviations used in the second part of the function name (after * alloc/dalloc) describe the arguments it takes * z: whether to return zeroed memory * t: accepts a tcache_t * parameter * m: accepts an arena_t * parameter */ JEMALLOC_ALWAYS_INLINE arena_t * iaalloc(tsdn_t *tsdn, const void *ptr) { assert(ptr != NULL); return arena_aalloc(tsdn, ptr); } JEMALLOC_ALWAYS_INLINE size_t isalloc(tsdn_t *tsdn, const void *ptr) { assert(ptr != NULL); return arena_salloc(tsdn, ptr); } JEMALLOC_ALWAYS_INLINE void * iallocztm(tsdn_t *tsdn, size_t size, szind_t ind, bool zero, tcache_t *tcache, bool is_internal, arena_t *arena, bool slow_path) { void *ret; - assert(size != 0); assert(!is_internal || tcache == NULL); assert(!is_internal || arena == NULL || arena_is_auto(arena)); if (!tsdn_null(tsdn) && tsd_reentrancy_level_get(tsdn_tsd(tsdn)) == 0) { witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); } ret = arena_malloc(tsdn, arena, size, ind, zero, tcache, slow_path); if (config_stats && is_internal && likely(ret != NULL)) { arena_internal_add(iaalloc(tsdn, ret), isalloc(tsdn, ret)); } return ret; } JEMALLOC_ALWAYS_INLINE void * ialloc(tsd_t *tsd, size_t size, szind_t ind, bool zero, bool slow_path) { return iallocztm(tsd_tsdn(tsd), size, ind, zero, tcache_get(tsd), false, NULL, slow_path); } JEMALLOC_ALWAYS_INLINE void * ipallocztm(tsdn_t *tsdn, size_t usize, size_t alignment, bool zero, tcache_t *tcache, bool is_internal, arena_t *arena) { void *ret; assert(usize != 0); assert(usize == sz_sa2u(usize, alignment)); assert(!is_internal || tcache == NULL); assert(!is_internal || arena == NULL || arena_is_auto(arena)); witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); ret = arena_palloc(tsdn, arena, usize, alignment, zero, tcache); assert(ALIGNMENT_ADDR2BASE(ret, alignment) == ret); if (config_stats && is_internal && likely(ret != NULL)) { arena_internal_add(iaalloc(tsdn, ret), isalloc(tsdn, ret)); } return ret; } JEMALLOC_ALWAYS_INLINE void * ipalloct(tsdn_t *tsdn, size_t usize, size_t alignment, bool zero, tcache_t *tcache, arena_t *arena) { return ipallocztm(tsdn, usize, alignment, zero, tcache, false, arena); } JEMALLOC_ALWAYS_INLINE void * ipalloc(tsd_t *tsd, size_t usize, size_t alignment, bool zero) { return ipallocztm(tsd_tsdn(tsd), usize, alignment, zero, tcache_get(tsd), false, NULL); } JEMALLOC_ALWAYS_INLINE size_t ivsalloc(tsdn_t *tsdn, const void *ptr) { return arena_vsalloc(tsdn, ptr); } JEMALLOC_ALWAYS_INLINE void idalloctm(tsdn_t *tsdn, void *ptr, tcache_t *tcache, alloc_ctx_t *alloc_ctx, bool is_internal, bool slow_path) { assert(ptr != NULL); assert(!is_internal || tcache == NULL); assert(!is_internal || arena_is_auto(iaalloc(tsdn, ptr))); witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); if (config_stats && is_internal) { arena_internal_sub(iaalloc(tsdn, ptr), isalloc(tsdn, ptr)); } if (!is_internal && !tsdn_null(tsdn) && tsd_reentrancy_level_get(tsdn_tsd(tsdn)) != 0) { assert(tcache == NULL); } arena_dalloc(tsdn, ptr, tcache, alloc_ctx, slow_path); } JEMALLOC_ALWAYS_INLINE void idalloc(tsd_t *tsd, void *ptr) { idalloctm(tsd_tsdn(tsd), ptr, tcache_get(tsd), NULL, false, true); } JEMALLOC_ALWAYS_INLINE void isdalloct(tsdn_t *tsdn, void *ptr, size_t size, tcache_t *tcache, alloc_ctx_t *alloc_ctx, bool slow_path) { witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); arena_sdalloc(tsdn, ptr, size, tcache, alloc_ctx, slow_path); } JEMALLOC_ALWAYS_INLINE void * iralloct_realign(tsdn_t *tsdn, void *ptr, size_t oldsize, size_t size, - size_t extra, size_t alignment, bool zero, tcache_t *tcache, - arena_t *arena) { + size_t alignment, bool zero, tcache_t *tcache, arena_t *arena, + hook_ralloc_args_t *hook_args) { witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); void *p; size_t usize, copysize; - usize = sz_sa2u(size + extra, alignment); - if (unlikely(usize == 0 || usize > LARGE_MAXCLASS)) { + usize = sz_sa2u(size, alignment); + if (unlikely(usize == 0 || usize > SC_LARGE_MAXCLASS)) { return NULL; } p = ipalloct(tsdn, usize, alignment, zero, tcache, arena); if (p == NULL) { - if (extra == 0) { - return NULL; - } - /* Try again, without extra this time. */ - usize = sz_sa2u(size, alignment); - if (unlikely(usize == 0 || usize > LARGE_MAXCLASS)) { - return NULL; - } - p = ipalloct(tsdn, usize, alignment, zero, tcache, arena); - if (p == NULL) { - return NULL; - } + return NULL; } /* * Copy at most size bytes (not size+extra), since the caller has no * expectation that the extra bytes will be reliably preserved. */ copysize = (size < oldsize) ? size : oldsize; memcpy(p, ptr, copysize); + hook_invoke_alloc(hook_args->is_realloc + ? hook_alloc_realloc : hook_alloc_rallocx, p, (uintptr_t)p, + hook_args->args); + hook_invoke_dalloc(hook_args->is_realloc + ? hook_dalloc_realloc : hook_dalloc_rallocx, ptr, hook_args->args); isdalloct(tsdn, ptr, oldsize, tcache, NULL, true); return p; } +/* + * is_realloc threads through the knowledge of whether or not this call comes + * from je_realloc (as opposed to je_rallocx); this ensures that we pass the + * correct entry point into any hooks. + * Note that these functions are all force-inlined, so no actual bool gets + * passed-around anywhere. + */ JEMALLOC_ALWAYS_INLINE void * iralloct(tsdn_t *tsdn, void *ptr, size_t oldsize, size_t size, size_t alignment, - bool zero, tcache_t *tcache, arena_t *arena) { + bool zero, tcache_t *tcache, arena_t *arena, hook_ralloc_args_t *hook_args) +{ assert(ptr != NULL); assert(size != 0); witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); if (alignment != 0 && ((uintptr_t)ptr & ((uintptr_t)alignment-1)) != 0) { /* * Existing object alignment is inadequate; allocate new space * and copy. */ - return iralloct_realign(tsdn, ptr, oldsize, size, 0, alignment, - zero, tcache, arena); + return iralloct_realign(tsdn, ptr, oldsize, size, alignment, + zero, tcache, arena, hook_args); } return arena_ralloc(tsdn, arena, ptr, oldsize, size, alignment, zero, - tcache); + tcache, hook_args); } JEMALLOC_ALWAYS_INLINE void * iralloc(tsd_t *tsd, void *ptr, size_t oldsize, size_t size, size_t alignment, - bool zero) { + bool zero, hook_ralloc_args_t *hook_args) { return iralloct(tsd_tsdn(tsd), ptr, oldsize, size, alignment, zero, - tcache_get(tsd), NULL); + tcache_get(tsd), NULL, hook_args); } JEMALLOC_ALWAYS_INLINE bool ixalloc(tsdn_t *tsdn, void *ptr, size_t oldsize, size_t size, size_t extra, - size_t alignment, bool zero) { + size_t alignment, bool zero, size_t *newsize) { assert(ptr != NULL); assert(size != 0); witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); if (alignment != 0 && ((uintptr_t)ptr & ((uintptr_t)alignment-1)) != 0) { /* Existing object alignment is inadequate. */ + *newsize = oldsize; return true; } - return arena_ralloc_no_move(tsdn, ptr, oldsize, size, extra, zero); + return arena_ralloc_no_move(tsdn, ptr, oldsize, size, extra, zero, + newsize); } #endif /* JEMALLOC_INTERNAL_INLINES_C_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_macros.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_macros.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_macros.h (revision 360233) @@ -1,43 +1,114 @@ #ifndef JEMALLOC_INTERNAL_MACROS_H #define JEMALLOC_INTERNAL_MACROS_H #ifdef JEMALLOC_DEBUG # define JEMALLOC_ALWAYS_INLINE static inline #else # define JEMALLOC_ALWAYS_INLINE JEMALLOC_ATTR(always_inline) static inline #endif #ifdef _MSC_VER # define inline _inline #endif #define UNUSED JEMALLOC_ATTR(unused) #define ZU(z) ((size_t)z) #define ZD(z) ((ssize_t)z) #define QU(q) ((uint64_t)q) #define QD(q) ((int64_t)q) #define KZU(z) ZU(z##ULL) #define KZD(z) ZD(z##LL) #define KQU(q) QU(q##ULL) #define KQD(q) QI(q##LL) #ifndef __DECONST # define __DECONST(type, var) ((type)(uintptr_t)(const void *)(var)) #endif #if !defined(JEMALLOC_HAS_RESTRICT) || defined(__cplusplus) # define restrict #endif -/* Various function pointers are statick and immutable except during testing. */ +/* Various function pointers are static and immutable except during testing. */ #ifdef JEMALLOC_JET # define JET_MUTABLE #else # define JET_MUTABLE const #endif #define JEMALLOC_VA_ARGS_HEAD(head, ...) head #define JEMALLOC_VA_ARGS_TAIL(head, ...) __VA_ARGS__ + +#if (defined(__GNUC__) || defined(__GNUG__)) && !defined(__clang__) \ + && defined(JEMALLOC_HAVE_ATTR) && (__GNUC__ >= 7) +#define JEMALLOC_FALLTHROUGH JEMALLOC_ATTR(fallthrough); +#else +#define JEMALLOC_FALLTHROUGH /* falls through */ +#endif + +/* Diagnostic suppression macros */ +#if defined(_MSC_VER) && !defined(__clang__) +# define JEMALLOC_DIAGNOSTIC_PUSH __pragma(warning(push)) +# define JEMALLOC_DIAGNOSTIC_POP __pragma(warning(pop)) +# define JEMALLOC_DIAGNOSTIC_IGNORE(W) __pragma(warning(disable:W)) +# define JEMALLOC_DIAGNOSTIC_IGNORE_MISSING_STRUCT_FIELD_INITIALIZERS +# define JEMALLOC_DIAGNOSTIC_IGNORE_TYPE_LIMITS +# define JEMALLOC_DIAGNOSTIC_IGNORE_ALLOC_SIZE_LARGER_THAN +# define JEMALLOC_DIAGNOSTIC_DISABLE_SPURIOUS +/* #pragma GCC diagnostic first appeared in gcc 4.6. */ +#elif (defined(__GNUC__) && ((__GNUC__ > 4) || ((__GNUC__ == 4) && \ + (__GNUC_MINOR__ > 5)))) || defined(__clang__) +/* + * The JEMALLOC_PRAGMA__ macro is an implementation detail of the GCC and Clang + * diagnostic suppression macros and should not be used anywhere else. + */ +# define JEMALLOC_PRAGMA__(X) _Pragma(#X) +# define JEMALLOC_DIAGNOSTIC_PUSH JEMALLOC_PRAGMA__(GCC diagnostic push) +# define JEMALLOC_DIAGNOSTIC_POP JEMALLOC_PRAGMA__(GCC diagnostic pop) +# define JEMALLOC_DIAGNOSTIC_IGNORE(W) \ + JEMALLOC_PRAGMA__(GCC diagnostic ignored W) + +/* + * The -Wmissing-field-initializers warning is buggy in GCC versions < 5.1 and + * all clang versions up to version 7 (currently trunk, unreleased). This macro + * suppresses the warning for the affected compiler versions only. + */ +# if ((defined(__GNUC__) && !defined(__clang__)) && (__GNUC__ < 5)) || \ + defined(__clang__) +# define JEMALLOC_DIAGNOSTIC_IGNORE_MISSING_STRUCT_FIELD_INITIALIZERS \ + JEMALLOC_DIAGNOSTIC_IGNORE("-Wmissing-field-initializers") +# else +# define JEMALLOC_DIAGNOSTIC_IGNORE_MISSING_STRUCT_FIELD_INITIALIZERS +# endif + +# define JEMALLOC_DIAGNOSTIC_IGNORE_TYPE_LIMITS \ + JEMALLOC_DIAGNOSTIC_IGNORE("-Wtype-limits") +# define JEMALLOC_DIAGNOSTIC_IGNORE_UNUSED_PARAMETER \ + JEMALLOC_DIAGNOSTIC_IGNORE("-Wunused-parameter") +# if defined(__GNUC__) && !defined(__clang__) && (__GNUC__ >= 7) +# define JEMALLOC_DIAGNOSTIC_IGNORE_ALLOC_SIZE_LARGER_THAN \ + JEMALLOC_DIAGNOSTIC_IGNORE("-Walloc-size-larger-than=") +# else +# define JEMALLOC_DIAGNOSTIC_IGNORE_ALLOC_SIZE_LARGER_THAN +# endif +# define JEMALLOC_DIAGNOSTIC_DISABLE_SPURIOUS \ + JEMALLOC_DIAGNOSTIC_PUSH \ + JEMALLOC_DIAGNOSTIC_IGNORE_UNUSED_PARAMETER +#else +# define JEMALLOC_DIAGNOSTIC_PUSH +# define JEMALLOC_DIAGNOSTIC_POP +# define JEMALLOC_DIAGNOSTIC_IGNORE(W) +# define JEMALLOC_DIAGNOSTIC_IGNORE_MISSING_STRUCT_FIELD_INITIALIZERS +# define JEMALLOC_DIAGNOSTIC_IGNORE_TYPE_LIMITS +# define JEMALLOC_DIAGNOSTIC_IGNORE_ALLOC_SIZE_LARGER_THAN +# define JEMALLOC_DIAGNOSTIC_DISABLE_SPURIOUS +#endif + +/* + * Disables spurious diagnostics for all headers. Since these headers are not + * included by users directly, it does not affect their diagnostic settings. + */ +JEMALLOC_DIAGNOSTIC_DISABLE_SPURIOUS #endif /* JEMALLOC_INTERNAL_MACROS_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_types.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_types.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/jemalloc_internal_types.h (revision 360233) @@ -1,185 +1,114 @@ #ifndef JEMALLOC_INTERNAL_TYPES_H #define JEMALLOC_INTERNAL_TYPES_H +#include "jemalloc/internal/quantum.h" + /* Page size index type. */ typedef unsigned pszind_t; /* Size class index type. */ typedef unsigned szind_t; /* Processor / core id type. */ typedef int malloc_cpuid_t; /* * Flags bits: * * a: arena * t: tcache * 0: unused * z: zero * n: alignment * * aaaaaaaa aaaatttt tttttttt 0znnnnnn */ #define MALLOCX_ARENA_BITS 12 #define MALLOCX_TCACHE_BITS 12 #define MALLOCX_LG_ALIGN_BITS 6 #define MALLOCX_ARENA_SHIFT 20 #define MALLOCX_TCACHE_SHIFT 8 #define MALLOCX_ARENA_MASK \ (((1 << MALLOCX_ARENA_BITS) - 1) << MALLOCX_ARENA_SHIFT) /* NB: Arena index bias decreases the maximum number of arenas by 1. */ #define MALLOCX_ARENA_LIMIT ((1 << MALLOCX_ARENA_BITS) - 1) #define MALLOCX_TCACHE_MASK \ (((1 << MALLOCX_TCACHE_BITS) - 1) << MALLOCX_TCACHE_SHIFT) #define MALLOCX_TCACHE_MAX ((1 << MALLOCX_TCACHE_BITS) - 3) #define MALLOCX_LG_ALIGN_MASK ((1 << MALLOCX_LG_ALIGN_BITS) - 1) /* Use MALLOCX_ALIGN_GET() if alignment may not be specified in flags. */ #define MALLOCX_ALIGN_GET_SPECIFIED(flags) \ (ZU(1) << (flags & MALLOCX_LG_ALIGN_MASK)) #define MALLOCX_ALIGN_GET(flags) \ (MALLOCX_ALIGN_GET_SPECIFIED(flags) & (SIZE_T_MAX-1)) #define MALLOCX_ZERO_GET(flags) \ ((bool)(flags & MALLOCX_ZERO)) #define MALLOCX_TCACHE_GET(flags) \ (((unsigned)((flags & MALLOCX_TCACHE_MASK) >> MALLOCX_TCACHE_SHIFT)) - 2) #define MALLOCX_ARENA_GET(flags) \ (((unsigned)(((unsigned)flags) >> MALLOCX_ARENA_SHIFT)) - 1) /* Smallest size class to support. */ #define TINY_MIN (1U << LG_TINY_MIN) - -/* - * Minimum allocation alignment is 2^LG_QUANTUM bytes (ignoring tiny size - * classes). - */ -#ifndef LG_QUANTUM -# if (defined(__i386__) || defined(_M_IX86)) -# define LG_QUANTUM 4 -# endif -# ifdef __ia64__ -# define LG_QUANTUM 4 -# endif -# ifdef __alpha__ -# define LG_QUANTUM 4 -# endif -# if (defined(__sparc64__) || defined(__sparcv9) || defined(__sparc_v9__)) -# define LG_QUANTUM 4 -# endif -# if (defined(__amd64__) || defined(__x86_64__) || defined(_M_X64)) -# define LG_QUANTUM 4 -# endif -# ifdef __arm__ -# define LG_QUANTUM 3 -# endif -# ifdef __aarch64__ -# define LG_QUANTUM 4 -# endif -# ifdef __hppa__ -# define LG_QUANTUM 4 -# endif -# ifdef __m68k__ -# define LG_QUANTUM 3 -# endif -# ifdef __mips__ -# define LG_QUANTUM 3 -# endif -# ifdef __nios2__ -# define LG_QUANTUM 3 -# endif -# ifdef __or1k__ -# define LG_QUANTUM 3 -# endif -# ifdef __powerpc__ -# define LG_QUANTUM 4 -# endif -# if defined(__riscv) || defined(__riscv__) -# define LG_QUANTUM 4 -# endif -# ifdef __s390__ -# define LG_QUANTUM 4 -# endif -# if (defined (__SH3E__) || defined(__SH4_SINGLE__) || defined(__SH4__) || \ - defined(__SH4_SINGLE_ONLY__)) -# define LG_QUANTUM 4 -# endif -# ifdef __tile__ -# define LG_QUANTUM 4 -# endif -# ifdef __le32__ -# define LG_QUANTUM 4 -# endif -# ifndef LG_QUANTUM -# error "Unknown minimum alignment for architecture; specify via " - "--with-lg-quantum" -# endif -#endif - -#define QUANTUM ((size_t)(1U << LG_QUANTUM)) -#define QUANTUM_MASK (QUANTUM - 1) - -/* Return the smallest quantum multiple that is >= a. */ -#define QUANTUM_CEILING(a) \ - (((a) + QUANTUM_MASK) & ~QUANTUM_MASK) #define LONG ((size_t)(1U << LG_SIZEOF_LONG)) #define LONG_MASK (LONG - 1) /* Return the smallest long multiple that is >= a. */ #define LONG_CEILING(a) \ (((a) + LONG_MASK) & ~LONG_MASK) #define SIZEOF_PTR (1U << LG_SIZEOF_PTR) #define PTR_MASK (SIZEOF_PTR - 1) /* Return the smallest (void *) multiple that is >= a. */ #define PTR_CEILING(a) \ (((a) + PTR_MASK) & ~PTR_MASK) /* * Maximum size of L1 cache line. This is used to avoid cache line aliasing. * In addition, this controls the spacing of cacheline-spaced size classes. * * CACHELINE cannot be based on LG_CACHELINE because __declspec(align()) can * only handle raw constants. */ #define LG_CACHELINE 6 #define CACHELINE 64 #define CACHELINE_MASK (CACHELINE - 1) /* Return the smallest cacheline multiple that is >= s. */ #define CACHELINE_CEILING(s) \ (((s) + CACHELINE_MASK) & ~CACHELINE_MASK) /* Return the nearest aligned address at or below a. */ #define ALIGNMENT_ADDR2BASE(a, alignment) \ ((void *)((uintptr_t)(a) & ((~(alignment)) + 1))) /* Return the offset between a and the nearest aligned address at or below a. */ #define ALIGNMENT_ADDR2OFFSET(a, alignment) \ ((size_t)((uintptr_t)(a) & (alignment - 1))) /* Return the smallest alignment multiple that is >= s. */ #define ALIGNMENT_CEILING(s, alignment) \ (((s) + (alignment - 1)) & ((~(alignment)) + 1)) /* Declare a variable-length array. */ #if __STDC_VERSION__ < 199901L # ifdef _MSC_VER # include # define alloca _alloca # else # ifdef JEMALLOC_HAS_ALLOCA_H # include # else # include # endif # endif # define VARIABLE_ARRAY(type, name, count) \ type *name = alloca(sizeof(type) * (count)) #else # define VARIABLE_ARRAY(type, name, count) type name[(count)] #endif #endif /* JEMALLOC_INTERNAL_TYPES_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/jemalloc_preamble.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/jemalloc_preamble.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/jemalloc_preamble.h (revision 360233) @@ -1,191 +1,210 @@ #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 #include "un-namespace.h" #include "libc_private.h" #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.h" # undef JEMALLOC_NO_RENAME #else # define JEMALLOC_N(n) __je_##n # include "../jemalloc.h" #endif -#if (defined(JEMALLOC_OSATOMIC) || defined(JEMALLOC_OSSPIN)) +#if defined(JEMALLOC_OSATOMIC) #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/hooks.h" +#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 = true; 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 +/* + * Are extra safety checks enabled; things like checking the size of sized + * deallocations, double-frees, etc. + */ +static const bool config_opt_safety_checks = +#ifdef JEMALLOC_OPT_SAFETY_CHECKS + true +#elif defined(JEMALLOC_DEBUG) + /* + * This lets us only guard safety checks by one flag instead of two; fast + * checks can guard solely by config_opt_safety_checks and run in debug mode + * too. + */ + true +#else + false +#endif + ; + +#if defined(_WIN32) || defined(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 */ Index: head/contrib/jemalloc/include/jemalloc/internal/large_externs.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/large_externs.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/large_externs.h (revision 360233) @@ -1,26 +1,32 @@ #ifndef JEMALLOC_INTERNAL_LARGE_EXTERNS_H #define JEMALLOC_INTERNAL_LARGE_EXTERNS_H +#include "jemalloc/internal/hook.h" + void *large_malloc(tsdn_t *tsdn, arena_t *arena, size_t usize, bool zero); void *large_palloc(tsdn_t *tsdn, arena_t *arena, size_t usize, size_t alignment, bool zero); bool large_ralloc_no_move(tsdn_t *tsdn, extent_t *extent, size_t usize_min, size_t usize_max, bool zero); -void *large_ralloc(tsdn_t *tsdn, arena_t *arena, extent_t *extent, size_t usize, - size_t alignment, bool zero, tcache_t *tcache); +void *large_ralloc(tsdn_t *tsdn, arena_t *arena, void *ptr, size_t usize, + size_t alignment, bool zero, tcache_t *tcache, + hook_ralloc_args_t *hook_args); typedef void (large_dalloc_junk_t)(void *, size_t); extern large_dalloc_junk_t *JET_MUTABLE large_dalloc_junk; typedef void (large_dalloc_maybe_junk_t)(void *, size_t); extern large_dalloc_maybe_junk_t *JET_MUTABLE large_dalloc_maybe_junk; void large_dalloc_prep_junked_locked(tsdn_t *tsdn, extent_t *extent); void large_dalloc_finish(tsdn_t *tsdn, extent_t *extent); void large_dalloc(tsdn_t *tsdn, extent_t *extent); size_t large_salloc(tsdn_t *tsdn, const extent_t *extent); prof_tctx_t *large_prof_tctx_get(tsdn_t *tsdn, const extent_t *extent); void large_prof_tctx_set(tsdn_t *tsdn, extent_t *extent, prof_tctx_t *tctx); void large_prof_tctx_reset(tsdn_t *tsdn, extent_t *extent); + +nstime_t large_prof_alloc_time_get(const extent_t *extent); +void large_prof_alloc_time_set(extent_t *extent, nstime_t time); #endif /* JEMALLOC_INTERNAL_LARGE_EXTERNS_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/malloc_io.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/malloc_io.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/malloc_io.h (revision 360233) @@ -1,102 +1,102 @@ #ifndef JEMALLOC_INTERNAL_MALLOC_IO_H #define JEMALLOC_INTERNAL_MALLOC_IO_H #ifdef _WIN32 # ifdef _WIN64 # define FMT64_PREFIX "ll" # define FMTPTR_PREFIX "ll" # else # define FMT64_PREFIX "ll" # define FMTPTR_PREFIX "" # endif # define FMTd32 "d" # define FMTu32 "u" # define FMTx32 "x" # define FMTd64 FMT64_PREFIX "d" # define FMTu64 FMT64_PREFIX "u" # define FMTx64 FMT64_PREFIX "x" # define FMTdPTR FMTPTR_PREFIX "d" # define FMTuPTR FMTPTR_PREFIX "u" # define FMTxPTR FMTPTR_PREFIX "x" #else # include # define FMTd32 PRId32 # define FMTu32 PRIu32 # define FMTx32 PRIx32 # define FMTd64 PRId64 # define FMTu64 PRIu64 # define FMTx64 PRIx64 # define FMTdPTR PRIdPTR # define FMTuPTR PRIuPTR # define FMTxPTR PRIxPTR #endif /* Size of stack-allocated buffer passed to buferror(). */ #define BUFERROR_BUF 64 /* * Size of stack-allocated buffer used by malloc_{,v,vc}printf(). This must be * large enough for all possible uses within jemalloc. */ #define MALLOC_PRINTF_BUFSIZE 4096 int buferror(int err, char *buf, size_t buflen); uintmax_t malloc_strtoumax(const char *restrict nptr, char **restrict endptr, int base); void malloc_write(const char *s); /* * malloc_vsnprintf() supports a subset of snprintf(3) that avoids floating * point math. */ size_t malloc_vsnprintf(char *str, size_t size, const char *format, va_list ap); size_t malloc_snprintf(char *str, size_t size, const char *format, ...) JEMALLOC_FORMAT_PRINTF(3, 4); /* - * The caller can set write_cb and cbopaque to null to choose to print with the + * The caller can set write_cb to null to choose to print with the * je_malloc_message hook. */ void malloc_vcprintf(void (*write_cb)(void *, const char *), void *cbopaque, const char *format, va_list ap); void malloc_cprintf(void (*write_cb)(void *, const char *), void *cbopaque, const char *format, ...) JEMALLOC_FORMAT_PRINTF(3, 4); void malloc_printf(const char *format, ...) JEMALLOC_FORMAT_PRINTF(1, 2); static inline ssize_t malloc_write_fd(int fd, const void *buf, size_t count) { #if defined(JEMALLOC_USE_SYSCALL) && defined(SYS_write) /* * Use syscall(2) rather than write(2) when possible in order to avoid * the possibility of memory allocation within libc. This is necessary * on FreeBSD; most operating systems do not have this problem though. * * syscall() returns long or int, depending on platform, so capture the * result in the widest plausible type to avoid compiler warnings. */ long result = syscall(SYS_write, fd, buf, count); #else ssize_t result = (ssize_t)write(fd, buf, #ifdef _WIN32 (unsigned int) #endif count); #endif return (ssize_t)result; } static inline ssize_t malloc_read_fd(int fd, void *buf, size_t count) { #if defined(JEMALLOC_USE_SYSCALL) && defined(SYS_read) long result = syscall(SYS_read, fd, buf, count); #else ssize_t result = read(fd, buf, #ifdef _WIN32 (unsigned int) #endif count); #endif return (ssize_t)result; } #endif /* JEMALLOC_INTERNAL_MALLOC_IO_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/mutex.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/mutex.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/mutex.h (revision 360233) @@ -1,246 +1,286 @@ #ifndef JEMALLOC_INTERNAL_MUTEX_H #define JEMALLOC_INTERNAL_MUTEX_H #include "jemalloc/internal/atomic.h" #include "jemalloc/internal/mutex_prof.h" #include "jemalloc/internal/tsd.h" #include "jemalloc/internal/witness.h" typedef enum { /* Can only acquire one mutex of a given witness rank at a time. */ malloc_mutex_rank_exclusive, /* * Can acquire multiple mutexes of the same witness rank, but in * address-ascending order only. */ malloc_mutex_address_ordered } malloc_mutex_lock_order_t; typedef struct malloc_mutex_s malloc_mutex_t; struct malloc_mutex_s { union { struct { /* * prof_data is defined first to reduce cacheline * bouncing: the data is not touched by the mutex holder * during unlocking, while might be modified by * contenders. Having it before the mutex itself could * avoid prefetching a modified cacheline (for the * unlocking thread). */ mutex_prof_data_t prof_data; #ifdef _WIN32 # if _WIN32_WINNT >= 0x0600 SRWLOCK lock; # else CRITICAL_SECTION lock; # endif #elif (defined(JEMALLOC_OS_UNFAIR_LOCK)) os_unfair_lock lock; -#elif (defined(JEMALLOC_OSSPIN)) - OSSpinLock lock; #elif (defined(JEMALLOC_MUTEX_INIT_CB)) pthread_mutex_t lock; malloc_mutex_t *postponed_next; #else pthread_mutex_t lock; #endif + /* + * Hint flag to avoid exclusive cache line contention + * during spin waiting + */ + atomic_b_t locked; }; /* * We only touch witness when configured w/ debug. However we * keep the field in a union when !debug so that we don't have * to pollute the code base with #ifdefs, while avoid paying the * memory cost. */ #if !defined(JEMALLOC_DEBUG) witness_t witness; malloc_mutex_lock_order_t lock_order; #endif }; #if defined(JEMALLOC_DEBUG) witness_t witness; malloc_mutex_lock_order_t lock_order; #endif }; /* * Based on benchmark results, a fixed spin with this amount of retries works * well for our critical sections. */ #define MALLOC_MUTEX_MAX_SPIN 250 #ifdef _WIN32 # if _WIN32_WINNT >= 0x0600 # define MALLOC_MUTEX_LOCK(m) AcquireSRWLockExclusive(&(m)->lock) # define MALLOC_MUTEX_UNLOCK(m) ReleaseSRWLockExclusive(&(m)->lock) # define MALLOC_MUTEX_TRYLOCK(m) (!TryAcquireSRWLockExclusive(&(m)->lock)) # else # define MALLOC_MUTEX_LOCK(m) EnterCriticalSection(&(m)->lock) # define MALLOC_MUTEX_UNLOCK(m) LeaveCriticalSection(&(m)->lock) # define MALLOC_MUTEX_TRYLOCK(m) (!TryEnterCriticalSection(&(m)->lock)) # endif #elif (defined(JEMALLOC_OS_UNFAIR_LOCK)) # define MALLOC_MUTEX_LOCK(m) os_unfair_lock_lock(&(m)->lock) # define MALLOC_MUTEX_UNLOCK(m) os_unfair_lock_unlock(&(m)->lock) # define MALLOC_MUTEX_TRYLOCK(m) (!os_unfair_lock_trylock(&(m)->lock)) -#elif (defined(JEMALLOC_OSSPIN)) -# define MALLOC_MUTEX_LOCK(m) OSSpinLockLock(&(m)->lock) -# define MALLOC_MUTEX_UNLOCK(m) OSSpinLockUnlock(&(m)->lock) -# define MALLOC_MUTEX_TRYLOCK(m) (!OSSpinLockTry(&(m)->lock)) #else # define MALLOC_MUTEX_LOCK(m) pthread_mutex_lock(&(m)->lock) # define MALLOC_MUTEX_UNLOCK(m) pthread_mutex_unlock(&(m)->lock) # define MALLOC_MUTEX_TRYLOCK(m) (pthread_mutex_trylock(&(m)->lock) != 0) #endif #define LOCK_PROF_DATA_INITIALIZER \ {NSTIME_ZERO_INITIALIZER, NSTIME_ZERO_INITIALIZER, 0, 0, 0, \ ATOMIC_INIT(0), 0, NULL, 0} #ifdef _WIN32 # define MALLOC_MUTEX_INITIALIZER #elif (defined(JEMALLOC_OS_UNFAIR_LOCK)) -# define MALLOC_MUTEX_INITIALIZER \ - {{{LOCK_PROF_DATA_INITIALIZER, OS_UNFAIR_LOCK_INIT}}, \ +# if defined(JEMALLOC_DEBUG) +# define MALLOC_MUTEX_INITIALIZER \ + {{{LOCK_PROF_DATA_INITIALIZER, OS_UNFAIR_LOCK_INIT, ATOMIC_INIT(false)}}, \ + WITNESS_INITIALIZER("mutex", WITNESS_RANK_OMIT), 0} +# else +# define MALLOC_MUTEX_INITIALIZER \ + {{{LOCK_PROF_DATA_INITIALIZER, OS_UNFAIR_LOCK_INIT, ATOMIC_INIT(false)}}, \ WITNESS_INITIALIZER("mutex", WITNESS_RANK_OMIT)} -#elif (defined(JEMALLOC_OSSPIN)) -# define MALLOC_MUTEX_INITIALIZER \ - {{{LOCK_PROF_DATA_INITIALIZER, 0}}, \ - WITNESS_INITIALIZER("mutex", WITNESS_RANK_OMIT)} +# endif #elif (defined(JEMALLOC_MUTEX_INIT_CB)) -# define MALLOC_MUTEX_INITIALIZER \ - {{{LOCK_PROF_DATA_INITIALIZER, PTHREAD_MUTEX_INITIALIZER, NULL}}, \ - WITNESS_INITIALIZER("mutex", WITNESS_RANK_OMIT)} +# if (defined(JEMALLOC_DEBUG)) +# define MALLOC_MUTEX_INITIALIZER \ + {{{LOCK_PROF_DATA_INITIALIZER, PTHREAD_MUTEX_INITIALIZER, NULL, ATOMIC_INIT(false)}}, \ + WITNESS_INITIALIZER("mutex", WITNESS_RANK_OMIT), 0} +# else +# define MALLOC_MUTEX_INITIALIZER \ + {{{LOCK_PROF_DATA_INITIALIZER, PTHREAD_MUTEX_INITIALIZER, NULL, ATOMIC_INIT(false)}}, \ + WITNESS_INITIALIZER("mutex", WITNESS_RANK_OMIT)} +# endif + #else # define MALLOC_MUTEX_TYPE PTHREAD_MUTEX_DEFAULT +# if defined(JEMALLOC_DEBUG) # define MALLOC_MUTEX_INITIALIZER \ - {{{LOCK_PROF_DATA_INITIALIZER, PTHREAD_MUTEX_INITIALIZER}}, \ - WITNESS_INITIALIZER("mutex", WITNESS_RANK_OMIT)} + {{{LOCK_PROF_DATA_INITIALIZER, PTHREAD_MUTEX_INITIALIZER, ATOMIC_INIT(false)}}, \ + WITNESS_INITIALIZER("mutex", WITNESS_RANK_OMIT), 0} +# else +# define MALLOC_MUTEX_INITIALIZER \ + {{{LOCK_PROF_DATA_INITIALIZER, PTHREAD_MUTEX_INITIALIZER, ATOMIC_INIT(false)}}, \ + WITNESS_INITIALIZER("mutex", WITNESS_RANK_OMIT)} +# endif #endif #ifdef JEMALLOC_LAZY_LOCK extern bool isthreaded; #endif bool malloc_mutex_init(malloc_mutex_t *mutex, const char *name, witness_rank_t rank, malloc_mutex_lock_order_t lock_order); void malloc_mutex_prefork(tsdn_t *tsdn, malloc_mutex_t *mutex); void malloc_mutex_postfork_parent(tsdn_t *tsdn, malloc_mutex_t *mutex); void malloc_mutex_postfork_child(tsdn_t *tsdn, malloc_mutex_t *mutex); bool malloc_mutex_first_thread(void); bool malloc_mutex_boot(void); void malloc_mutex_prof_data_reset(tsdn_t *tsdn, malloc_mutex_t *mutex); void malloc_mutex_lock_slow(malloc_mutex_t *mutex); static inline void malloc_mutex_lock_final(malloc_mutex_t *mutex) { MALLOC_MUTEX_LOCK(mutex); + atomic_store_b(&mutex->locked, true, ATOMIC_RELAXED); } static inline bool malloc_mutex_trylock_final(malloc_mutex_t *mutex) { return MALLOC_MUTEX_TRYLOCK(mutex); } static inline void mutex_owner_stats_update(tsdn_t *tsdn, malloc_mutex_t *mutex) { if (config_stats) { mutex_prof_data_t *data = &mutex->prof_data; data->n_lock_ops++; if (data->prev_owner != tsdn) { data->prev_owner = tsdn; data->n_owner_switches++; } } } /* Trylock: return false if the lock is successfully acquired. */ static inline bool malloc_mutex_trylock(tsdn_t *tsdn, malloc_mutex_t *mutex) { witness_assert_not_owner(tsdn_witness_tsdp_get(tsdn), &mutex->witness); if (isthreaded) { if (malloc_mutex_trylock_final(mutex)) { + atomic_store_b(&mutex->locked, true, ATOMIC_RELAXED); return true; } mutex_owner_stats_update(tsdn, mutex); } witness_lock(tsdn_witness_tsdp_get(tsdn), &mutex->witness); return false; } /* Aggregate lock prof data. */ static inline void malloc_mutex_prof_merge(mutex_prof_data_t *sum, mutex_prof_data_t *data) { nstime_add(&sum->tot_wait_time, &data->tot_wait_time); if (nstime_compare(&sum->max_wait_time, &data->max_wait_time) < 0) { nstime_copy(&sum->max_wait_time, &data->max_wait_time); } sum->n_wait_times += data->n_wait_times; sum->n_spin_acquired += data->n_spin_acquired; if (sum->max_n_thds < data->max_n_thds) { sum->max_n_thds = data->max_n_thds; } uint32_t cur_n_waiting_thds = atomic_load_u32(&sum->n_waiting_thds, ATOMIC_RELAXED); uint32_t new_n_waiting_thds = cur_n_waiting_thds + atomic_load_u32( &data->n_waiting_thds, ATOMIC_RELAXED); atomic_store_u32(&sum->n_waiting_thds, new_n_waiting_thds, ATOMIC_RELAXED); sum->n_owner_switches += data->n_owner_switches; sum->n_lock_ops += data->n_lock_ops; } static inline void malloc_mutex_lock(tsdn_t *tsdn, malloc_mutex_t *mutex) { witness_assert_not_owner(tsdn_witness_tsdp_get(tsdn), &mutex->witness); if (isthreaded) { if (malloc_mutex_trylock_final(mutex)) { malloc_mutex_lock_slow(mutex); + atomic_store_b(&mutex->locked, true, ATOMIC_RELAXED); } mutex_owner_stats_update(tsdn, mutex); } witness_lock(tsdn_witness_tsdp_get(tsdn), &mutex->witness); } static inline void malloc_mutex_unlock(tsdn_t *tsdn, malloc_mutex_t *mutex) { + atomic_store_b(&mutex->locked, false, ATOMIC_RELAXED); witness_unlock(tsdn_witness_tsdp_get(tsdn), &mutex->witness); if (isthreaded) { MALLOC_MUTEX_UNLOCK(mutex); } } static inline void malloc_mutex_assert_owner(tsdn_t *tsdn, malloc_mutex_t *mutex) { witness_assert_owner(tsdn_witness_tsdp_get(tsdn), &mutex->witness); } static inline void malloc_mutex_assert_not_owner(tsdn_t *tsdn, malloc_mutex_t *mutex) { witness_assert_not_owner(tsdn_witness_tsdp_get(tsdn), &mutex->witness); } /* Copy the prof data from mutex for processing. */ static inline void malloc_mutex_prof_read(tsdn_t *tsdn, mutex_prof_data_t *data, malloc_mutex_t *mutex) { mutex_prof_data_t *source = &mutex->prof_data; /* Can only read holding the mutex. */ malloc_mutex_assert_owner(tsdn, mutex); /* * Not *really* allowed (we shouldn't be doing non-atomic loads of * atomic data), but the mutex protection makes this safe, and writing * a member-for-member copy is tedious for this situation. */ *data = *source; /* n_wait_thds is not reported (modified w/o locking). */ atomic_store_u32(&data->n_waiting_thds, 0, ATOMIC_RELAXED); +} + +static inline void +malloc_mutex_prof_accum(tsdn_t *tsdn, mutex_prof_data_t *data, + malloc_mutex_t *mutex) { + mutex_prof_data_t *source = &mutex->prof_data; + /* Can only read holding the mutex. */ + malloc_mutex_assert_owner(tsdn, mutex); + + nstime_add(&data->tot_wait_time, &source->tot_wait_time); + if (nstime_compare(&source->max_wait_time, &data->max_wait_time) > 0) { + nstime_copy(&data->max_wait_time, &source->max_wait_time); + } + data->n_wait_times += source->n_wait_times; + data->n_spin_acquired += source->n_spin_acquired; + if (data->max_n_thds < source->max_n_thds) { + data->max_n_thds = source->max_n_thds; + } + /* n_wait_thds is not reported. */ + atomic_store_u32(&data->n_waiting_thds, 0, ATOMIC_RELAXED); + data->n_owner_switches += source->n_owner_switches; + data->n_lock_ops += source->n_lock_ops; } #endif /* JEMALLOC_INTERNAL_MUTEX_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/mutex_prof.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/mutex_prof.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/mutex_prof.h (revision 360233) @@ -1,99 +1,108 @@ #ifndef JEMALLOC_INTERNAL_MUTEX_PROF_H #define JEMALLOC_INTERNAL_MUTEX_PROF_H #include "jemalloc/internal/atomic.h" #include "jemalloc/internal/nstime.h" #include "jemalloc/internal/tsd_types.h" #define MUTEX_PROF_GLOBAL_MUTEXES \ OP(background_thread) \ OP(ctl) \ OP(prof) typedef enum { #define OP(mtx) global_prof_mutex_##mtx, MUTEX_PROF_GLOBAL_MUTEXES #undef OP mutex_prof_num_global_mutexes } mutex_prof_global_ind_t; #define MUTEX_PROF_ARENA_MUTEXES \ OP(large) \ OP(extent_avail) \ OP(extents_dirty) \ OP(extents_muzzy) \ OP(extents_retained) \ OP(decay_dirty) \ OP(decay_muzzy) \ OP(base) \ OP(tcache_list) typedef enum { #define OP(mtx) arena_prof_mutex_##mtx, MUTEX_PROF_ARENA_MUTEXES #undef OP mutex_prof_num_arena_mutexes } mutex_prof_arena_ind_t; +/* + * The forth parameter is a boolean value that is true for derived rate counters + * and false for real ones. + */ #define MUTEX_PROF_UINT64_COUNTERS \ - OP(num_ops, uint64_t, "n_lock_ops") \ - OP(num_wait, uint64_t, "n_waiting") \ - OP(num_spin_acq, uint64_t, "n_spin_acq") \ - OP(num_owner_switch, uint64_t, "n_owner_switch") \ - OP(total_wait_time, uint64_t, "total_wait_ns") \ - OP(max_wait_time, uint64_t, "max_wait_ns") + OP(num_ops, uint64_t, "n_lock_ops", false, num_ops) \ + OP(num_ops_ps, uint64_t, "(#/sec)", true, num_ops) \ + OP(num_wait, uint64_t, "n_waiting", false, num_wait) \ + OP(num_wait_ps, uint64_t, "(#/sec)", true, num_wait) \ + OP(num_spin_acq, uint64_t, "n_spin_acq", false, num_spin_acq) \ + OP(num_spin_acq_ps, uint64_t, "(#/sec)", true, num_spin_acq) \ + OP(num_owner_switch, uint64_t, "n_owner_switch", false, num_owner_switch) \ + OP(num_owner_switch_ps, uint64_t, "(#/sec)", true, num_owner_switch) \ + OP(total_wait_time, uint64_t, "total_wait_ns", false, total_wait_time) \ + OP(total_wait_time_ps, uint64_t, "(#/sec)", true, total_wait_time) \ + OP(max_wait_time, uint64_t, "max_wait_ns", false, max_wait_time) #define MUTEX_PROF_UINT32_COUNTERS \ - OP(max_num_thds, uint32_t, "max_n_thds") + OP(max_num_thds, uint32_t, "max_n_thds", false, max_num_thds) #define MUTEX_PROF_COUNTERS \ MUTEX_PROF_UINT64_COUNTERS \ MUTEX_PROF_UINT32_COUNTERS -#define OP(counter, type, human) mutex_counter_##counter, +#define OP(counter, type, human, derived, base_counter) mutex_counter_##counter, #define COUNTER_ENUM(counter_list, t) \ typedef enum { \ counter_list \ mutex_prof_num_##t##_counters \ } mutex_prof_##t##_counter_ind_t; COUNTER_ENUM(MUTEX_PROF_UINT64_COUNTERS, uint64_t) COUNTER_ENUM(MUTEX_PROF_UINT32_COUNTERS, uint32_t) #undef COUNTER_ENUM #undef OP typedef struct { /* * Counters touched on the slow path, i.e. when there is lock * contention. We update them once we have the lock. */ /* Total time (in nano seconds) spent waiting on this mutex. */ nstime_t tot_wait_time; /* Max time (in nano seconds) spent on a single lock operation. */ nstime_t max_wait_time; /* # of times have to wait for this mutex (after spinning). */ uint64_t n_wait_times; /* # of times acquired the mutex through local spinning. */ uint64_t n_spin_acquired; /* Max # of threads waiting for the mutex at the same time. */ uint32_t max_n_thds; /* Current # of threads waiting on the lock. Atomic synced. */ atomic_u32_t n_waiting_thds; /* * Data touched on the fast path. These are modified right after we * grab the lock, so it's placed closest to the end (i.e. right before * the lock) so that we have a higher chance of them being on the same * cacheline. */ /* # of times the mutex holder is different than the previous one. */ uint64_t n_owner_switches; /* Previous mutex holder, to facilitate n_owner_switches. */ tsdn_t *prev_owner; /* # of lock() operations in total. */ uint64_t n_lock_ops; } mutex_prof_data_t; #endif /* JEMALLOC_INTERNAL_MUTEX_PROF_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/private_namespace.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/private_namespace.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/private_namespace.h (revision 360233) @@ -1,376 +1,420 @@ #define a0dalloc JEMALLOC_N(a0dalloc) #define a0malloc JEMALLOC_N(a0malloc) #define arena_choose_hard JEMALLOC_N(arena_choose_hard) #define arena_cleanup JEMALLOC_N(arena_cleanup) #define arena_init JEMALLOC_N(arena_init) #define arena_migrate JEMALLOC_N(arena_migrate) #define arena_set JEMALLOC_N(arena_set) #define arena_tdata_get_hard JEMALLOC_N(arena_tdata_get_hard) #define arenas JEMALLOC_N(arenas) #define arenas_lock JEMALLOC_N(arenas_lock) #define arenas_tdata_cleanup JEMALLOC_N(arenas_tdata_cleanup) #define bootstrap_calloc JEMALLOC_N(bootstrap_calloc) #define bootstrap_free JEMALLOC_N(bootstrap_free) #define bootstrap_malloc JEMALLOC_N(bootstrap_malloc) +#define free_default JEMALLOC_N(free_default) #define iarena_cleanup JEMALLOC_N(iarena_cleanup) +#define je_sdallocx_noflags JEMALLOC_N(je_sdallocx_noflags) #define jemalloc_postfork_child JEMALLOC_N(jemalloc_postfork_child) +#define malloc_default JEMALLOC_N(malloc_default) #define malloc_initialized JEMALLOC_N(malloc_initialized) #define malloc_slow JEMALLOC_N(malloc_slow) +#define manual_arena_base JEMALLOC_N(manual_arena_base) #define narenas_auto JEMALLOC_N(narenas_auto) #define narenas_total_get JEMALLOC_N(narenas_total_get) #define ncpus JEMALLOC_N(ncpus) #define opt_abort JEMALLOC_N(opt_abort) #define opt_abort_conf JEMALLOC_N(opt_abort_conf) +#define opt_confirm_conf JEMALLOC_N(opt_confirm_conf) #define opt_junk JEMALLOC_N(opt_junk) #define opt_junk_alloc JEMALLOC_N(opt_junk_alloc) #define opt_junk_free JEMALLOC_N(opt_junk_free) #define opt_narenas JEMALLOC_N(opt_narenas) #define opt_utrace JEMALLOC_N(opt_utrace) #define opt_xmalloc JEMALLOC_N(opt_xmalloc) #define opt_zero JEMALLOC_N(opt_zero) +#define sdallocx_default JEMALLOC_N(sdallocx_default) #define arena_alloc_junk_small JEMALLOC_N(arena_alloc_junk_small) #define arena_basic_stats_merge JEMALLOC_N(arena_basic_stats_merge) +#define arena_bin_choose_lock JEMALLOC_N(arena_bin_choose_lock) #define arena_boot JEMALLOC_N(arena_boot) +#define arena_choose_huge JEMALLOC_N(arena_choose_huge) #define arena_dalloc_bin_junked_locked JEMALLOC_N(arena_dalloc_bin_junked_locked) #define arena_dalloc_junk_small JEMALLOC_N(arena_dalloc_junk_small) #define arena_dalloc_promoted JEMALLOC_N(arena_dalloc_promoted) #define arena_dalloc_small JEMALLOC_N(arena_dalloc_small) #define arena_decay JEMALLOC_N(arena_decay) #define arena_destroy JEMALLOC_N(arena_destroy) #define arena_dirty_decay_ms_default_get JEMALLOC_N(arena_dirty_decay_ms_default_get) #define arena_dirty_decay_ms_default_set JEMALLOC_N(arena_dirty_decay_ms_default_set) #define arena_dirty_decay_ms_get JEMALLOC_N(arena_dirty_decay_ms_get) #define arena_dirty_decay_ms_set JEMALLOC_N(arena_dirty_decay_ms_set) #define arena_dss_prec_get JEMALLOC_N(arena_dss_prec_get) #define arena_dss_prec_set JEMALLOC_N(arena_dss_prec_set) #define arena_extent_alloc_large JEMALLOC_N(arena_extent_alloc_large) #define arena_extent_dalloc_large_prep JEMALLOC_N(arena_extent_dalloc_large_prep) #define arena_extent_ralloc_large_expand JEMALLOC_N(arena_extent_ralloc_large_expand) #define arena_extent_ralloc_large_shrink JEMALLOC_N(arena_extent_ralloc_large_shrink) #define arena_extent_sn_next JEMALLOC_N(arena_extent_sn_next) #define arena_extents_dirty_dalloc JEMALLOC_N(arena_extents_dirty_dalloc) +#define arena_init_huge JEMALLOC_N(arena_init_huge) +#define arena_is_huge JEMALLOC_N(arena_is_huge) #define arena_malloc_hard JEMALLOC_N(arena_malloc_hard) #define arena_muzzy_decay_ms_default_get JEMALLOC_N(arena_muzzy_decay_ms_default_get) #define arena_muzzy_decay_ms_default_set JEMALLOC_N(arena_muzzy_decay_ms_default_set) #define arena_muzzy_decay_ms_get JEMALLOC_N(arena_muzzy_decay_ms_get) #define arena_muzzy_decay_ms_set JEMALLOC_N(arena_muzzy_decay_ms_set) #define arena_new JEMALLOC_N(arena_new) #define arena_nthreads_dec JEMALLOC_N(arena_nthreads_dec) #define arena_nthreads_get JEMALLOC_N(arena_nthreads_get) #define arena_nthreads_inc JEMALLOC_N(arena_nthreads_inc) #define arena_palloc JEMALLOC_N(arena_palloc) #define arena_postfork_child JEMALLOC_N(arena_postfork_child) #define arena_postfork_parent JEMALLOC_N(arena_postfork_parent) #define arena_prefork0 JEMALLOC_N(arena_prefork0) #define arena_prefork1 JEMALLOC_N(arena_prefork1) #define arena_prefork2 JEMALLOC_N(arena_prefork2) #define arena_prefork3 JEMALLOC_N(arena_prefork3) #define arena_prefork4 JEMALLOC_N(arena_prefork4) #define arena_prefork5 JEMALLOC_N(arena_prefork5) #define arena_prefork6 JEMALLOC_N(arena_prefork6) #define arena_prefork7 JEMALLOC_N(arena_prefork7) #define arena_prof_promote JEMALLOC_N(arena_prof_promote) #define arena_ralloc JEMALLOC_N(arena_ralloc) #define arena_ralloc_no_move JEMALLOC_N(arena_ralloc_no_move) #define arena_reset JEMALLOC_N(arena_reset) #define arena_retain_grow_limit_get_set JEMALLOC_N(arena_retain_grow_limit_get_set) #define arena_stats_merge JEMALLOC_N(arena_stats_merge) #define arena_tcache_fill_small JEMALLOC_N(arena_tcache_fill_small) #define h_steps JEMALLOC_N(h_steps) #define opt_dirty_decay_ms JEMALLOC_N(opt_dirty_decay_ms) #define opt_muzzy_decay_ms JEMALLOC_N(opt_muzzy_decay_ms) +#define opt_oversize_threshold JEMALLOC_N(opt_oversize_threshold) #define opt_percpu_arena JEMALLOC_N(opt_percpu_arena) +#define oversize_threshold JEMALLOC_N(oversize_threshold) #define percpu_arena_mode_names JEMALLOC_N(percpu_arena_mode_names) #define background_thread_boot0 JEMALLOC_N(background_thread_boot0) #define background_thread_boot1 JEMALLOC_N(background_thread_boot1) #define background_thread_create JEMALLOC_N(background_thread_create) #define background_thread_ctl_init JEMALLOC_N(background_thread_ctl_init) #define background_thread_enabled_state JEMALLOC_N(background_thread_enabled_state) #define background_thread_info JEMALLOC_N(background_thread_info) #define background_thread_interval_check JEMALLOC_N(background_thread_interval_check) #define background_thread_lock JEMALLOC_N(background_thread_lock) #define background_thread_postfork_child JEMALLOC_N(background_thread_postfork_child) #define background_thread_postfork_parent JEMALLOC_N(background_thread_postfork_parent) #define background_thread_prefork0 JEMALLOC_N(background_thread_prefork0) #define background_thread_prefork1 JEMALLOC_N(background_thread_prefork1) #define background_thread_stats_read JEMALLOC_N(background_thread_stats_read) #define background_threads_disable JEMALLOC_N(background_threads_disable) #define background_threads_enable JEMALLOC_N(background_threads_enable) -#define can_enable_background_thread JEMALLOC_N(can_enable_background_thread) #define max_background_threads JEMALLOC_N(max_background_threads) #define n_background_threads JEMALLOC_N(n_background_threads) #define opt_background_thread JEMALLOC_N(opt_background_thread) #define opt_max_background_threads JEMALLOC_N(opt_max_background_threads) #define pthread_create_wrapper JEMALLOC_N(pthread_create_wrapper) #define b0get JEMALLOC_N(b0get) #define base_alloc JEMALLOC_N(base_alloc) #define base_alloc_extent JEMALLOC_N(base_alloc_extent) #define base_boot JEMALLOC_N(base_boot) #define base_delete JEMALLOC_N(base_delete) #define base_extent_hooks_get JEMALLOC_N(base_extent_hooks_get) #define base_extent_hooks_set JEMALLOC_N(base_extent_hooks_set) #define base_new JEMALLOC_N(base_new) #define base_postfork_child JEMALLOC_N(base_postfork_child) #define base_postfork_parent JEMALLOC_N(base_postfork_parent) #define base_prefork JEMALLOC_N(base_prefork) #define base_stats_get JEMALLOC_N(base_stats_get) #define metadata_thp_mode_names JEMALLOC_N(metadata_thp_mode_names) #define opt_metadata_thp JEMALLOC_N(opt_metadata_thp) +#define bin_boot JEMALLOC_N(bin_boot) #define bin_infos JEMALLOC_N(bin_infos) #define bin_init JEMALLOC_N(bin_init) #define bin_postfork_child JEMALLOC_N(bin_postfork_child) #define bin_postfork_parent JEMALLOC_N(bin_postfork_parent) #define bin_prefork JEMALLOC_N(bin_prefork) +#define bin_shard_sizes_boot JEMALLOC_N(bin_shard_sizes_boot) +#define bin_update_shard_size JEMALLOC_N(bin_update_shard_size) #define bitmap_info_init JEMALLOC_N(bitmap_info_init) #define bitmap_init JEMALLOC_N(bitmap_init) #define bitmap_size JEMALLOC_N(bitmap_size) #define ckh_count JEMALLOC_N(ckh_count) #define ckh_delete JEMALLOC_N(ckh_delete) #define ckh_insert JEMALLOC_N(ckh_insert) #define ckh_iter JEMALLOC_N(ckh_iter) #define ckh_new JEMALLOC_N(ckh_new) #define ckh_pointer_hash JEMALLOC_N(ckh_pointer_hash) #define ckh_pointer_keycomp JEMALLOC_N(ckh_pointer_keycomp) #define ckh_remove JEMALLOC_N(ckh_remove) #define ckh_search JEMALLOC_N(ckh_search) #define ckh_string_hash JEMALLOC_N(ckh_string_hash) #define ckh_string_keycomp JEMALLOC_N(ckh_string_keycomp) #define ctl_boot JEMALLOC_N(ctl_boot) #define ctl_bymib JEMALLOC_N(ctl_bymib) #define ctl_byname JEMALLOC_N(ctl_byname) #define ctl_nametomib JEMALLOC_N(ctl_nametomib) #define ctl_postfork_child JEMALLOC_N(ctl_postfork_child) #define ctl_postfork_parent JEMALLOC_N(ctl_postfork_parent) #define ctl_prefork JEMALLOC_N(ctl_prefork) #define div_init JEMALLOC_N(div_init) #define extent_alloc JEMALLOC_N(extent_alloc) #define extent_alloc_wrapper JEMALLOC_N(extent_alloc_wrapper) #define extent_avail_any JEMALLOC_N(extent_avail_any) #define extent_avail_empty JEMALLOC_N(extent_avail_empty) #define extent_avail_first JEMALLOC_N(extent_avail_first) #define extent_avail_insert JEMALLOC_N(extent_avail_insert) #define extent_avail_new JEMALLOC_N(extent_avail_new) #define extent_avail_remove JEMALLOC_N(extent_avail_remove) #define extent_avail_remove_any JEMALLOC_N(extent_avail_remove_any) #define extent_avail_remove_first JEMALLOC_N(extent_avail_remove_first) #define extent_boot JEMALLOC_N(extent_boot) #define extent_commit_wrapper JEMALLOC_N(extent_commit_wrapper) #define extent_dalloc JEMALLOC_N(extent_dalloc) #define extent_dalloc_gap JEMALLOC_N(extent_dalloc_gap) #define extent_dalloc_wrapper JEMALLOC_N(extent_dalloc_wrapper) #define extent_decommit_wrapper JEMALLOC_N(extent_decommit_wrapper) #define extent_destroy_wrapper JEMALLOC_N(extent_destroy_wrapper) #define extent_heap_any JEMALLOC_N(extent_heap_any) #define extent_heap_empty JEMALLOC_N(extent_heap_empty) #define extent_heap_first JEMALLOC_N(extent_heap_first) #define extent_heap_insert JEMALLOC_N(extent_heap_insert) #define extent_heap_new JEMALLOC_N(extent_heap_new) #define extent_heap_remove JEMALLOC_N(extent_heap_remove) #define extent_heap_remove_any JEMALLOC_N(extent_heap_remove_any) #define extent_heap_remove_first JEMALLOC_N(extent_heap_remove_first) #define extent_hooks_default JEMALLOC_N(extent_hooks_default) #define extent_hooks_get JEMALLOC_N(extent_hooks_get) #define extent_hooks_set JEMALLOC_N(extent_hooks_set) #define extent_merge_wrapper JEMALLOC_N(extent_merge_wrapper) #define extent_mutex_pool JEMALLOC_N(extent_mutex_pool) #define extent_purge_forced_wrapper JEMALLOC_N(extent_purge_forced_wrapper) #define extent_purge_lazy_wrapper JEMALLOC_N(extent_purge_lazy_wrapper) #define extent_split_wrapper JEMALLOC_N(extent_split_wrapper) +#define extent_util_stats_get JEMALLOC_N(extent_util_stats_get) +#define extent_util_stats_verbose_get JEMALLOC_N(extent_util_stats_verbose_get) #define extents_alloc JEMALLOC_N(extents_alloc) #define extents_dalloc JEMALLOC_N(extents_dalloc) #define extents_evict JEMALLOC_N(extents_evict) #define extents_init JEMALLOC_N(extents_init) +#define extents_nbytes_get JEMALLOC_N(extents_nbytes_get) +#define extents_nextents_get JEMALLOC_N(extents_nextents_get) #define extents_npages_get JEMALLOC_N(extents_npages_get) #define extents_postfork_child JEMALLOC_N(extents_postfork_child) #define extents_postfork_parent JEMALLOC_N(extents_postfork_parent) #define extents_prefork JEMALLOC_N(extents_prefork) #define extents_rtree JEMALLOC_N(extents_rtree) #define extents_state_get JEMALLOC_N(extents_state_get) #define opt_lg_extent_max_active_fit JEMALLOC_N(opt_lg_extent_max_active_fit) #define dss_prec_names JEMALLOC_N(dss_prec_names) #define extent_alloc_dss JEMALLOC_N(extent_alloc_dss) #define extent_dss_boot JEMALLOC_N(extent_dss_boot) #define extent_dss_mergeable JEMALLOC_N(extent_dss_mergeable) #define extent_dss_prec_get JEMALLOC_N(extent_dss_prec_get) #define extent_dss_prec_set JEMALLOC_N(extent_dss_prec_set) #define extent_in_dss JEMALLOC_N(extent_in_dss) #define opt_dss JEMALLOC_N(opt_dss) #define extent_alloc_mmap JEMALLOC_N(extent_alloc_mmap) #define extent_dalloc_mmap JEMALLOC_N(extent_dalloc_mmap) #define opt_retain JEMALLOC_N(opt_retain) -#define hooks_arena_new_hook JEMALLOC_N(hooks_arena_new_hook) -#define hooks_libc_hook JEMALLOC_N(hooks_libc_hook) +#define hook_boot JEMALLOC_N(hook_boot) +#define hook_install JEMALLOC_N(hook_install) +#define hook_invoke_alloc JEMALLOC_N(hook_invoke_alloc) +#define hook_invoke_dalloc JEMALLOC_N(hook_invoke_dalloc) +#define hook_invoke_expand JEMALLOC_N(hook_invoke_expand) +#define hook_remove JEMALLOC_N(hook_remove) #define large_dalloc JEMALLOC_N(large_dalloc) #define large_dalloc_finish JEMALLOC_N(large_dalloc_finish) #define large_dalloc_junk JEMALLOC_N(large_dalloc_junk) #define large_dalloc_maybe_junk JEMALLOC_N(large_dalloc_maybe_junk) #define large_dalloc_prep_junked_locked JEMALLOC_N(large_dalloc_prep_junked_locked) #define large_malloc JEMALLOC_N(large_malloc) #define large_palloc JEMALLOC_N(large_palloc) +#define large_prof_alloc_time_get JEMALLOC_N(large_prof_alloc_time_get) +#define large_prof_alloc_time_set JEMALLOC_N(large_prof_alloc_time_set) #define large_prof_tctx_get JEMALLOC_N(large_prof_tctx_get) #define large_prof_tctx_reset JEMALLOC_N(large_prof_tctx_reset) #define large_prof_tctx_set JEMALLOC_N(large_prof_tctx_set) #define large_ralloc JEMALLOC_N(large_ralloc) #define large_ralloc_no_move JEMALLOC_N(large_ralloc_no_move) #define large_salloc JEMALLOC_N(large_salloc) #define log_init_done JEMALLOC_N(log_init_done) #define log_var_names JEMALLOC_N(log_var_names) #define log_var_update_state JEMALLOC_N(log_var_update_state) #define buferror JEMALLOC_N(buferror) #define malloc_cprintf JEMALLOC_N(malloc_cprintf) #define malloc_printf JEMALLOC_N(malloc_printf) #define malloc_snprintf JEMALLOC_N(malloc_snprintf) #define malloc_strtoumax JEMALLOC_N(malloc_strtoumax) #define malloc_vcprintf JEMALLOC_N(malloc_vcprintf) #define malloc_vsnprintf JEMALLOC_N(malloc_vsnprintf) #define malloc_write JEMALLOC_N(malloc_write) #define malloc_mutex_boot JEMALLOC_N(malloc_mutex_boot) #define malloc_mutex_init JEMALLOC_N(malloc_mutex_init) #define malloc_mutex_lock_slow JEMALLOC_N(malloc_mutex_lock_slow) #define malloc_mutex_postfork_child JEMALLOC_N(malloc_mutex_postfork_child) #define malloc_mutex_postfork_parent JEMALLOC_N(malloc_mutex_postfork_parent) #define malloc_mutex_prefork JEMALLOC_N(malloc_mutex_prefork) #define malloc_mutex_prof_data_reset JEMALLOC_N(malloc_mutex_prof_data_reset) #define mutex_pool_init JEMALLOC_N(mutex_pool_init) #define nstime_add JEMALLOC_N(nstime_add) #define nstime_compare JEMALLOC_N(nstime_compare) #define nstime_copy JEMALLOC_N(nstime_copy) #define nstime_divide JEMALLOC_N(nstime_divide) #define nstime_iadd JEMALLOC_N(nstime_iadd) #define nstime_idivide JEMALLOC_N(nstime_idivide) #define nstime_imultiply JEMALLOC_N(nstime_imultiply) #define nstime_init JEMALLOC_N(nstime_init) #define nstime_init2 JEMALLOC_N(nstime_init2) #define nstime_isubtract JEMALLOC_N(nstime_isubtract) #define nstime_monotonic JEMALLOC_N(nstime_monotonic) #define nstime_msec JEMALLOC_N(nstime_msec) #define nstime_ns JEMALLOC_N(nstime_ns) #define nstime_nsec JEMALLOC_N(nstime_nsec) #define nstime_sec JEMALLOC_N(nstime_sec) #define nstime_subtract JEMALLOC_N(nstime_subtract) #define nstime_update JEMALLOC_N(nstime_update) #define init_system_thp_mode JEMALLOC_N(init_system_thp_mode) #define opt_thp JEMALLOC_N(opt_thp) #define pages_boot JEMALLOC_N(pages_boot) #define pages_commit JEMALLOC_N(pages_commit) #define pages_decommit JEMALLOC_N(pages_decommit) #define pages_dodump JEMALLOC_N(pages_dodump) #define pages_dontdump JEMALLOC_N(pages_dontdump) #define pages_huge JEMALLOC_N(pages_huge) #define pages_map JEMALLOC_N(pages_map) #define pages_nohuge JEMALLOC_N(pages_nohuge) #define pages_purge_forced JEMALLOC_N(pages_purge_forced) #define pages_purge_lazy JEMALLOC_N(pages_purge_lazy) #define pages_set_thp_state JEMALLOC_N(pages_set_thp_state) #define pages_unmap JEMALLOC_N(pages_unmap) #define thp_mode_names JEMALLOC_N(thp_mode_names) #define bt2gctx_mtx JEMALLOC_N(bt2gctx_mtx) #define bt_init JEMALLOC_N(bt_init) #define lg_prof_sample JEMALLOC_N(lg_prof_sample) #define opt_lg_prof_interval JEMALLOC_N(opt_lg_prof_interval) #define opt_lg_prof_sample JEMALLOC_N(opt_lg_prof_sample) #define opt_prof JEMALLOC_N(opt_prof) #define opt_prof_accum JEMALLOC_N(opt_prof_accum) #define opt_prof_active JEMALLOC_N(opt_prof_active) #define opt_prof_final JEMALLOC_N(opt_prof_final) #define opt_prof_gdump JEMALLOC_N(opt_prof_gdump) #define opt_prof_leak JEMALLOC_N(opt_prof_leak) +#define opt_prof_log JEMALLOC_N(opt_prof_log) #define opt_prof_prefix JEMALLOC_N(opt_prof_prefix) #define opt_prof_thread_active_init JEMALLOC_N(opt_prof_thread_active_init) #define prof_accum_init JEMALLOC_N(prof_accum_init) #define prof_active JEMALLOC_N(prof_active) #define prof_active_get JEMALLOC_N(prof_active_get) #define prof_active_set JEMALLOC_N(prof_active_set) #define prof_alloc_rollback JEMALLOC_N(prof_alloc_rollback) #define prof_backtrace JEMALLOC_N(prof_backtrace) #define prof_boot0 JEMALLOC_N(prof_boot0) #define prof_boot1 JEMALLOC_N(prof_boot1) #define prof_boot2 JEMALLOC_N(prof_boot2) #define prof_dump_header JEMALLOC_N(prof_dump_header) #define prof_dump_open JEMALLOC_N(prof_dump_open) #define prof_free_sampled_object JEMALLOC_N(prof_free_sampled_object) #define prof_gdump JEMALLOC_N(prof_gdump) #define prof_gdump_get JEMALLOC_N(prof_gdump_get) #define prof_gdump_set JEMALLOC_N(prof_gdump_set) #define prof_gdump_val JEMALLOC_N(prof_gdump_val) #define prof_idump JEMALLOC_N(prof_idump) #define prof_interval JEMALLOC_N(prof_interval) +#define prof_log_start JEMALLOC_N(prof_log_start) +#define prof_log_stop JEMALLOC_N(prof_log_stop) +#define prof_logging_state JEMALLOC_N(prof_logging_state) #define prof_lookup JEMALLOC_N(prof_lookup) #define prof_malloc_sample_object JEMALLOC_N(prof_malloc_sample_object) #define prof_mdump JEMALLOC_N(prof_mdump) #define prof_postfork_child JEMALLOC_N(prof_postfork_child) #define prof_postfork_parent JEMALLOC_N(prof_postfork_parent) #define prof_prefork0 JEMALLOC_N(prof_prefork0) #define prof_prefork1 JEMALLOC_N(prof_prefork1) #define prof_reset JEMALLOC_N(prof_reset) #define prof_sample_threshold_update JEMALLOC_N(prof_sample_threshold_update) #define prof_tdata_cleanup JEMALLOC_N(prof_tdata_cleanup) #define prof_tdata_init JEMALLOC_N(prof_tdata_init) #define prof_tdata_reinit JEMALLOC_N(prof_tdata_reinit) #define prof_thread_active_get JEMALLOC_N(prof_thread_active_get) #define prof_thread_active_init_get JEMALLOC_N(prof_thread_active_init_get) #define prof_thread_active_init_set JEMALLOC_N(prof_thread_active_init_set) #define prof_thread_active_set JEMALLOC_N(prof_thread_active_set) #define prof_thread_name_get JEMALLOC_N(prof_thread_name_get) #define prof_thread_name_set JEMALLOC_N(prof_thread_name_set) #define rtree_ctx_data_init JEMALLOC_N(rtree_ctx_data_init) #define rtree_leaf_alloc JEMALLOC_N(rtree_leaf_alloc) #define rtree_leaf_dalloc JEMALLOC_N(rtree_leaf_dalloc) #define rtree_leaf_elm_lookup_hard JEMALLOC_N(rtree_leaf_elm_lookup_hard) #define rtree_new JEMALLOC_N(rtree_new) #define rtree_node_alloc JEMALLOC_N(rtree_node_alloc) #define rtree_node_dalloc JEMALLOC_N(rtree_node_dalloc) +#define safety_check_fail JEMALLOC_N(safety_check_fail) +#define safety_check_set_abort JEMALLOC_N(safety_check_set_abort) #define arena_mutex_names JEMALLOC_N(arena_mutex_names) #define global_mutex_names JEMALLOC_N(global_mutex_names) #define opt_stats_print JEMALLOC_N(opt_stats_print) #define opt_stats_print_opts JEMALLOC_N(opt_stats_print_opts) #define stats_print JEMALLOC_N(stats_print) +#define sc_boot JEMALLOC_N(sc_boot) +#define sc_data_global JEMALLOC_N(sc_data_global) +#define sc_data_init JEMALLOC_N(sc_data_init) +#define sc_data_update_slab_size JEMALLOC_N(sc_data_update_slab_size) +#define sz_boot JEMALLOC_N(sz_boot) #define sz_index2size_tab JEMALLOC_N(sz_index2size_tab) #define sz_pind2sz_tab JEMALLOC_N(sz_pind2sz_tab) #define sz_size2index_tab JEMALLOC_N(sz_size2index_tab) #define nhbins JEMALLOC_N(nhbins) #define opt_lg_tcache_max JEMALLOC_N(opt_lg_tcache_max) #define opt_tcache JEMALLOC_N(opt_tcache) #define tcache_alloc_small_hard JEMALLOC_N(tcache_alloc_small_hard) #define tcache_arena_associate JEMALLOC_N(tcache_arena_associate) #define tcache_arena_reassociate JEMALLOC_N(tcache_arena_reassociate) #define tcache_bin_flush_large JEMALLOC_N(tcache_bin_flush_large) #define tcache_bin_flush_small JEMALLOC_N(tcache_bin_flush_small) #define tcache_bin_info JEMALLOC_N(tcache_bin_info) #define tcache_boot JEMALLOC_N(tcache_boot) #define tcache_cleanup JEMALLOC_N(tcache_cleanup) #define tcache_create_explicit JEMALLOC_N(tcache_create_explicit) #define tcache_event_hard JEMALLOC_N(tcache_event_hard) #define tcache_flush JEMALLOC_N(tcache_flush) #define tcache_maxclass JEMALLOC_N(tcache_maxclass) #define tcache_postfork_child JEMALLOC_N(tcache_postfork_child) #define tcache_postfork_parent JEMALLOC_N(tcache_postfork_parent) #define tcache_prefork JEMALLOC_N(tcache_prefork) #define tcache_salloc JEMALLOC_N(tcache_salloc) #define tcache_stats_merge JEMALLOC_N(tcache_stats_merge) #define tcaches JEMALLOC_N(tcaches) #define tcaches_create JEMALLOC_N(tcaches_create) #define tcaches_destroy JEMALLOC_N(tcaches_destroy) #define tcaches_flush JEMALLOC_N(tcaches_flush) #define tsd_tcache_data_init JEMALLOC_N(tsd_tcache_data_init) #define tsd_tcache_enabled_data_init JEMALLOC_N(tsd_tcache_enabled_data_init) +#define test_hooks_arena_new_hook JEMALLOC_N(test_hooks_arena_new_hook) +#define test_hooks_libc_hook JEMALLOC_N(test_hooks_libc_hook) #define malloc_tsd_boot0 JEMALLOC_N(malloc_tsd_boot0) #define malloc_tsd_boot1 JEMALLOC_N(malloc_tsd_boot1) #define malloc_tsd_cleanup_register JEMALLOC_N(malloc_tsd_cleanup_register) #define malloc_tsd_dalloc JEMALLOC_N(malloc_tsd_dalloc) #define malloc_tsd_malloc JEMALLOC_N(malloc_tsd_malloc) #define tsd_booted JEMALLOC_N(tsd_booted) #define tsd_cleanup JEMALLOC_N(tsd_cleanup) #define tsd_fetch_slow JEMALLOC_N(tsd_fetch_slow) +#define tsd_global_slow JEMALLOC_N(tsd_global_slow) +#define tsd_global_slow_dec JEMALLOC_N(tsd_global_slow_dec) +#define tsd_global_slow_inc JEMALLOC_N(tsd_global_slow_inc) #define tsd_initialized JEMALLOC_N(tsd_initialized) +#define tsd_postfork_child JEMALLOC_N(tsd_postfork_child) +#define tsd_postfork_parent JEMALLOC_N(tsd_postfork_parent) +#define tsd_prefork JEMALLOC_N(tsd_prefork) #define tsd_slow_update JEMALLOC_N(tsd_slow_update) +#define tsd_state_set JEMALLOC_N(tsd_state_set) #define tsd_tls JEMALLOC_N(tsd_tls) #define witness_depth_error JEMALLOC_N(witness_depth_error) #define witness_init JEMALLOC_N(witness_init) #define witness_lock_error JEMALLOC_N(witness_lock_error) #define witness_not_owner_error JEMALLOC_N(witness_not_owner_error) #define witness_owner_error JEMALLOC_N(witness_owner_error) #define witness_postfork_child JEMALLOC_N(witness_postfork_child) #define witness_postfork_parent JEMALLOC_N(witness_postfork_parent) #define witness_prefork JEMALLOC_N(witness_prefork) #define witnesses_cleanup JEMALLOC_N(witnesses_cleanup) Index: head/contrib/jemalloc/include/jemalloc/internal/prof_externs.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/prof_externs.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/prof_externs.h (revision 360233) @@ -1,92 +1,105 @@ #ifndef JEMALLOC_INTERNAL_PROF_EXTERNS_H #define JEMALLOC_INTERNAL_PROF_EXTERNS_H #include "jemalloc/internal/mutex.h" extern malloc_mutex_t bt2gctx_mtx; extern bool opt_prof; extern bool opt_prof_active; extern bool opt_prof_thread_active_init; extern size_t opt_lg_prof_sample; /* Mean bytes between samples. */ extern ssize_t opt_lg_prof_interval; /* lg(prof_interval). */ extern bool opt_prof_gdump; /* High-water memory dumping. */ extern bool opt_prof_final; /* Final profile dumping. */ extern bool opt_prof_leak; /* Dump leak summary at exit. */ extern bool opt_prof_accum; /* Report cumulative bytes. */ +extern bool opt_prof_log; /* Turn logging on at boot. */ extern char opt_prof_prefix[ /* Minimize memory bloat for non-prof builds. */ #ifdef JEMALLOC_PROF PATH_MAX + #endif 1]; /* Accessed via prof_active_[gs]et{_unlocked,}(). */ extern bool prof_active; /* Accessed via prof_gdump_[gs]et{_unlocked,}(). */ extern bool prof_gdump_val; /* * Profile dump interval, measured in bytes allocated. Each arena triggers a * profile dump when it reaches this threshold. The effect is that the * interval between profile dumps averages prof_interval, though the actual * interval between dumps will tend to be sporadic, and the interval will be a * maximum of approximately (prof_interval * narenas). */ extern uint64_t prof_interval; /* * Initialized as opt_lg_prof_sample, and potentially modified during profiling * resets. */ extern size_t lg_prof_sample; void prof_alloc_rollback(tsd_t *tsd, prof_tctx_t *tctx, bool updated); void prof_malloc_sample_object(tsdn_t *tsdn, const void *ptr, size_t usize, prof_tctx_t *tctx); -void prof_free_sampled_object(tsd_t *tsd, size_t usize, prof_tctx_t *tctx); +void prof_free_sampled_object(tsd_t *tsd, const void *ptr, size_t usize, + prof_tctx_t *tctx); void bt_init(prof_bt_t *bt, void **vec); void prof_backtrace(prof_bt_t *bt); prof_tctx_t *prof_lookup(tsd_t *tsd, prof_bt_t *bt); #ifdef JEMALLOC_JET size_t prof_tdata_count(void); size_t prof_bt_count(void); #endif typedef int (prof_dump_open_t)(bool, const char *); extern prof_dump_open_t *JET_MUTABLE prof_dump_open; typedef bool (prof_dump_header_t)(tsdn_t *, bool, const prof_cnt_t *); extern prof_dump_header_t *JET_MUTABLE prof_dump_header; #ifdef JEMALLOC_JET void prof_cnt_all(uint64_t *curobjs, uint64_t *curbytes, uint64_t *accumobjs, uint64_t *accumbytes); #endif bool prof_accum_init(tsdn_t *tsdn, prof_accum_t *prof_accum); void prof_idump(tsdn_t *tsdn); bool prof_mdump(tsd_t *tsd, const char *filename); void prof_gdump(tsdn_t *tsdn); prof_tdata_t *prof_tdata_init(tsd_t *tsd); prof_tdata_t *prof_tdata_reinit(tsd_t *tsd, prof_tdata_t *tdata); void prof_reset(tsd_t *tsd, size_t lg_sample); void prof_tdata_cleanup(tsd_t *tsd); bool prof_active_get(tsdn_t *tsdn); bool prof_active_set(tsdn_t *tsdn, bool active); const char *prof_thread_name_get(tsd_t *tsd); int prof_thread_name_set(tsd_t *tsd, const char *thread_name); bool prof_thread_active_get(tsd_t *tsd); bool prof_thread_active_set(tsd_t *tsd, bool active); bool prof_thread_active_init_get(tsdn_t *tsdn); bool prof_thread_active_init_set(tsdn_t *tsdn, bool active_init); bool prof_gdump_get(tsdn_t *tsdn); bool prof_gdump_set(tsdn_t *tsdn, bool active); void prof_boot0(void); void prof_boot1(void); bool prof_boot2(tsd_t *tsd); void prof_prefork0(tsdn_t *tsdn); void prof_prefork1(tsdn_t *tsdn); void prof_postfork_parent(tsdn_t *tsdn); void prof_postfork_child(tsdn_t *tsdn); void prof_sample_threshold_update(prof_tdata_t *tdata); + +bool prof_log_start(tsdn_t *tsdn, const char *filename); +bool prof_log_stop(tsdn_t *tsdn); +#ifdef JEMALLOC_JET +size_t prof_log_bt_count(void); +size_t prof_log_alloc_count(void); +size_t prof_log_thr_count(void); +bool prof_log_is_logging(void); +bool prof_log_rep_check(void); +void prof_log_dummy_set(bool new_value); +#endif #endif /* JEMALLOC_INTERNAL_PROF_EXTERNS_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/prof_inlines_a.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/prof_inlines_a.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/prof_inlines_a.h (revision 360233) @@ -1,83 +1,85 @@ #ifndef JEMALLOC_INTERNAL_PROF_INLINES_A_H #define JEMALLOC_INTERNAL_PROF_INLINES_A_H #include "jemalloc/internal/mutex.h" static inline bool -prof_accum_add(tsdn_t *tsdn, prof_accum_t *prof_accum, uint64_t accumbytes) { +prof_accum_add(tsdn_t *tsdn, prof_accum_t *prof_accum, + uint64_t accumbytes) { cassert(config_prof); bool overflow; uint64_t a0, a1; /* * If the application allocates fast enough (and/or if idump is slow * enough), extreme overflow here (a1 >= prof_interval * 2) can cause * idump trigger coalescing. This is an intentional mechanism that * avoids rate-limiting allocation. */ #ifdef JEMALLOC_ATOMIC_U64 a0 = atomic_load_u64(&prof_accum->accumbytes, ATOMIC_RELAXED); do { a1 = a0 + accumbytes; assert(a1 >= a0); overflow = (a1 >= prof_interval); if (overflow) { a1 %= prof_interval; } } while (!atomic_compare_exchange_weak_u64(&prof_accum->accumbytes, &a0, a1, ATOMIC_RELAXED, ATOMIC_RELAXED)); #else malloc_mutex_lock(tsdn, &prof_accum->mtx); a0 = prof_accum->accumbytes; a1 = a0 + accumbytes; overflow = (a1 >= prof_interval); if (overflow) { a1 %= prof_interval; } prof_accum->accumbytes = a1; malloc_mutex_unlock(tsdn, &prof_accum->mtx); #endif return overflow; } static inline void -prof_accum_cancel(tsdn_t *tsdn, prof_accum_t *prof_accum, size_t usize) { +prof_accum_cancel(tsdn_t *tsdn, prof_accum_t *prof_accum, + size_t usize) { cassert(config_prof); /* * Cancel out as much of the excessive prof_accumbytes increase as * possible without underflowing. Interval-triggered dumps occur * slightly more often than intended as a result of incomplete * canceling. */ uint64_t a0, a1; #ifdef JEMALLOC_ATOMIC_U64 a0 = atomic_load_u64(&prof_accum->accumbytes, ATOMIC_RELAXED); do { - a1 = (a0 >= LARGE_MINCLASS - usize) ? a0 - (LARGE_MINCLASS - - usize) : 0; + a1 = (a0 >= SC_LARGE_MINCLASS - usize) + ? a0 - (SC_LARGE_MINCLASS - usize) : 0; } while (!atomic_compare_exchange_weak_u64(&prof_accum->accumbytes, &a0, a1, ATOMIC_RELAXED, ATOMIC_RELAXED)); #else malloc_mutex_lock(tsdn, &prof_accum->mtx); a0 = prof_accum->accumbytes; - a1 = (a0 >= LARGE_MINCLASS - usize) ? a0 - (LARGE_MINCLASS - usize) : - 0; + a1 = (a0 >= SC_LARGE_MINCLASS - usize) + ? a0 - (SC_LARGE_MINCLASS - usize) : 0; prof_accum->accumbytes = a1; malloc_mutex_unlock(tsdn, &prof_accum->mtx); #endif } JEMALLOC_ALWAYS_INLINE bool prof_active_get_unlocked(void) { /* * Even if opt_prof is true, sampling can be temporarily disabled by * setting prof_active to false. No locking is used when reading * prof_active in the fast path, so there are no guarantees regarding * how long it will take for all threads to notice state changes. */ return prof_active; } #endif /* JEMALLOC_INTERNAL_PROF_INLINES_A_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/prof_inlines_b.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/prof_inlines_b.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/prof_inlines_b.h (revision 360233) @@ -1,206 +1,250 @@ #ifndef JEMALLOC_INTERNAL_PROF_INLINES_B_H #define JEMALLOC_INTERNAL_PROF_INLINES_B_H +#include "jemalloc/internal/safety_check.h" #include "jemalloc/internal/sz.h" JEMALLOC_ALWAYS_INLINE bool prof_gdump_get_unlocked(void) { /* * No locking is used when reading prof_gdump_val in the fast path, so * there are no guarantees regarding how long it will take for all * threads to notice state changes. */ return prof_gdump_val; } JEMALLOC_ALWAYS_INLINE prof_tdata_t * prof_tdata_get(tsd_t *tsd, bool create) { prof_tdata_t *tdata; cassert(config_prof); tdata = tsd_prof_tdata_get(tsd); if (create) { if (unlikely(tdata == NULL)) { if (tsd_nominal(tsd)) { tdata = prof_tdata_init(tsd); tsd_prof_tdata_set(tsd, tdata); } } else if (unlikely(tdata->expired)) { tdata = prof_tdata_reinit(tsd, tdata); tsd_prof_tdata_set(tsd, tdata); } assert(tdata == NULL || tdata->attached); } return tdata; } JEMALLOC_ALWAYS_INLINE prof_tctx_t * prof_tctx_get(tsdn_t *tsdn, const void *ptr, alloc_ctx_t *alloc_ctx) { cassert(config_prof); assert(ptr != NULL); return arena_prof_tctx_get(tsdn, ptr, alloc_ctx); } JEMALLOC_ALWAYS_INLINE void prof_tctx_set(tsdn_t *tsdn, const void *ptr, size_t usize, alloc_ctx_t *alloc_ctx, prof_tctx_t *tctx) { cassert(config_prof); assert(ptr != NULL); arena_prof_tctx_set(tsdn, ptr, usize, alloc_ctx, tctx); } JEMALLOC_ALWAYS_INLINE void prof_tctx_reset(tsdn_t *tsdn, const void *ptr, prof_tctx_t *tctx) { cassert(config_prof); assert(ptr != NULL); arena_prof_tctx_reset(tsdn, ptr, tctx); } +JEMALLOC_ALWAYS_INLINE nstime_t +prof_alloc_time_get(tsdn_t *tsdn, const void *ptr, alloc_ctx_t *alloc_ctx) { + cassert(config_prof); + assert(ptr != NULL); + + return arena_prof_alloc_time_get(tsdn, ptr, alloc_ctx); +} + +JEMALLOC_ALWAYS_INLINE void +prof_alloc_time_set(tsdn_t *tsdn, const void *ptr, alloc_ctx_t *alloc_ctx, + nstime_t t) { + cassert(config_prof); + assert(ptr != NULL); + + arena_prof_alloc_time_set(tsdn, ptr, alloc_ctx, t); +} + JEMALLOC_ALWAYS_INLINE bool +prof_sample_check(tsd_t *tsd, size_t usize, bool update) { + ssize_t check = update ? 0 : usize; + + int64_t bytes_until_sample = tsd_bytes_until_sample_get(tsd); + if (update) { + bytes_until_sample -= usize; + if (tsd_nominal(tsd)) { + tsd_bytes_until_sample_set(tsd, bytes_until_sample); + } + } + if (likely(bytes_until_sample >= check)) { + return true; + } + + return false; +} + +JEMALLOC_ALWAYS_INLINE bool prof_sample_accum_update(tsd_t *tsd, size_t usize, bool update, - prof_tdata_t **tdata_out) { + prof_tdata_t **tdata_out) { prof_tdata_t *tdata; cassert(config_prof); + /* Fastpath: no need to load tdata */ + if (likely(prof_sample_check(tsd, usize, update))) { + return true; + } + + bool booted = tsd_prof_tdata_get(tsd); tdata = prof_tdata_get(tsd, true); if (unlikely((uintptr_t)tdata <= (uintptr_t)PROF_TDATA_STATE_MAX)) { tdata = NULL; } if (tdata_out != NULL) { *tdata_out = tdata; } if (unlikely(tdata == NULL)) { return true; } - if (likely(tdata->bytes_until_sample >= usize)) { - if (update) { - tdata->bytes_until_sample -= usize; - } + /* + * If this was the first creation of tdata, then + * prof_tdata_get() reset bytes_until_sample, so decrement and + * check it again + */ + if (!booted && prof_sample_check(tsd, usize, update)) { return true; - } else { - if (tsd_reentrancy_level_get(tsd) > 0) { - return true; - } - /* Compute new sample threshold. */ - if (update) { - prof_sample_threshold_update(tdata); - } - return !tdata->active; } + + if (tsd_reentrancy_level_get(tsd) > 0) { + return true; + } + /* Compute new sample threshold. */ + if (update) { + prof_sample_threshold_update(tdata); + } + return !tdata->active; } JEMALLOC_ALWAYS_INLINE prof_tctx_t * prof_alloc_prep(tsd_t *tsd, size_t usize, bool prof_active, bool update) { prof_tctx_t *ret; prof_tdata_t *tdata; prof_bt_t bt; assert(usize == sz_s2u(usize)); if (!prof_active || likely(prof_sample_accum_update(tsd, usize, update, &tdata))) { ret = (prof_tctx_t *)(uintptr_t)1U; } else { bt_init(&bt, tdata->vec); prof_backtrace(&bt); ret = prof_lookup(tsd, &bt); } return ret; } JEMALLOC_ALWAYS_INLINE void prof_malloc(tsdn_t *tsdn, const void *ptr, size_t usize, alloc_ctx_t *alloc_ctx, prof_tctx_t *tctx) { cassert(config_prof); assert(ptr != NULL); assert(usize == isalloc(tsdn, ptr)); if (unlikely((uintptr_t)tctx > (uintptr_t)1U)) { prof_malloc_sample_object(tsdn, ptr, usize, tctx); } else { prof_tctx_set(tsdn, ptr, usize, alloc_ctx, (prof_tctx_t *)(uintptr_t)1U); } } JEMALLOC_ALWAYS_INLINE void prof_realloc(tsd_t *tsd, const void *ptr, size_t usize, prof_tctx_t *tctx, bool prof_active, bool updated, const void *old_ptr, size_t old_usize, prof_tctx_t *old_tctx) { bool sampled, old_sampled, moved; cassert(config_prof); assert(ptr != NULL || (uintptr_t)tctx <= (uintptr_t)1U); if (prof_active && !updated && ptr != NULL) { assert(usize == isalloc(tsd_tsdn(tsd), ptr)); if (prof_sample_accum_update(tsd, usize, true, NULL)) { /* * Don't sample. The usize passed to prof_alloc_prep() * was larger than what actually got allocated, so a * backtrace was captured for this allocation, even * though its actual usize was insufficient to cross the * sample threshold. */ prof_alloc_rollback(tsd, tctx, true); tctx = (prof_tctx_t *)(uintptr_t)1U; } } sampled = ((uintptr_t)tctx > (uintptr_t)1U); old_sampled = ((uintptr_t)old_tctx > (uintptr_t)1U); moved = (ptr != old_ptr); if (unlikely(sampled)) { prof_malloc_sample_object(tsd_tsdn(tsd), ptr, usize, tctx); } else if (moved) { prof_tctx_set(tsd_tsdn(tsd), ptr, usize, NULL, (prof_tctx_t *)(uintptr_t)1U); } else if (unlikely(old_sampled)) { /* * prof_tctx_set() would work for the !moved case as well, but * prof_tctx_reset() is slightly cheaper, and the proper thing * to do here in the presence of explicit knowledge re: moved * state. */ prof_tctx_reset(tsd_tsdn(tsd), ptr, tctx); } else { assert((uintptr_t)prof_tctx_get(tsd_tsdn(tsd), ptr, NULL) == (uintptr_t)1U); } /* * The prof_free_sampled_object() call must come after the * prof_malloc_sample_object() call, because tctx and old_tctx may be * the same, in which case reversing the call order could cause the tctx * to be prematurely destroyed as a side effect of momentarily zeroed * counters. */ if (unlikely(old_sampled)) { - prof_free_sampled_object(tsd, old_usize, old_tctx); + prof_free_sampled_object(tsd, ptr, old_usize, old_tctx); } } JEMALLOC_ALWAYS_INLINE void prof_free(tsd_t *tsd, const void *ptr, size_t usize, alloc_ctx_t *alloc_ctx) { prof_tctx_t *tctx = prof_tctx_get(tsd_tsdn(tsd), ptr, alloc_ctx); cassert(config_prof); assert(usize == isalloc(tsd_tsdn(tsd), ptr)); if (unlikely((uintptr_t)tctx > (uintptr_t)1U)) { - prof_free_sampled_object(tsd, usize, tctx); + prof_free_sampled_object(tsd, ptr, usize, tctx); } } #endif /* JEMALLOC_INTERNAL_PROF_INLINES_B_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/prof_structs.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/prof_structs.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/prof_structs.h (revision 360233) @@ -1,201 +1,200 @@ #ifndef JEMALLOC_INTERNAL_PROF_STRUCTS_H #define JEMALLOC_INTERNAL_PROF_STRUCTS_H #include "jemalloc/internal/ckh.h" #include "jemalloc/internal/mutex.h" #include "jemalloc/internal/prng.h" #include "jemalloc/internal/rb.h" struct prof_bt_s { /* Backtrace, stored as len program counters. */ void **vec; unsigned len; }; #ifdef JEMALLOC_PROF_LIBGCC /* Data structure passed to libgcc _Unwind_Backtrace() callback functions. */ typedef struct { prof_bt_t *bt; unsigned max; } prof_unwind_data_t; #endif struct prof_accum_s { #ifndef JEMALLOC_ATOMIC_U64 malloc_mutex_t mtx; uint64_t accumbytes; #else atomic_u64_t accumbytes; #endif }; struct prof_cnt_s { /* Profiling counters. */ uint64_t curobjs; uint64_t curbytes; uint64_t accumobjs; uint64_t accumbytes; }; typedef enum { prof_tctx_state_initializing, prof_tctx_state_nominal, prof_tctx_state_dumping, prof_tctx_state_purgatory /* Dumper must finish destroying. */ } prof_tctx_state_t; struct prof_tctx_s { /* Thread data for thread that performed the allocation. */ prof_tdata_t *tdata; /* * Copy of tdata->thr_{uid,discrim}, necessary because tdata may be * defunct during teardown. */ uint64_t thr_uid; uint64_t thr_discrim; /* Profiling counters, protected by tdata->lock. */ prof_cnt_t cnts; /* Associated global context. */ prof_gctx_t *gctx; /* * UID that distinguishes multiple tctx's created by the same thread, * but coexisting in gctx->tctxs. There are two ways that such * coexistence can occur: * - A dumper thread can cause a tctx to be retained in the purgatory * state. * - Although a single "producer" thread must create all tctx's which * share the same thr_uid, multiple "consumers" can each concurrently * execute portions of prof_tctx_destroy(). prof_tctx_destroy() only * gets called once each time cnts.cur{objs,bytes} drop to 0, but this * threshold can be hit again before the first consumer finishes * executing prof_tctx_destroy(). */ uint64_t tctx_uid; /* Linkage into gctx's tctxs. */ rb_node(prof_tctx_t) tctx_link; /* * True during prof_alloc_prep()..prof_malloc_sample_object(), prevents * sample vs destroy race. */ bool prepared; /* Current dump-related state, protected by gctx->lock. */ prof_tctx_state_t state; /* * Copy of cnts snapshotted during early dump phase, protected by * dump_mtx. */ prof_cnt_t dump_cnts; }; typedef rb_tree(prof_tctx_t) prof_tctx_tree_t; struct prof_gctx_s { /* Protects nlimbo, cnt_summed, and tctxs. */ malloc_mutex_t *lock; /* * Number of threads that currently cause this gctx to be in a state of * limbo due to one of: * - Initializing this gctx. * - Initializing per thread counters associated with this gctx. * - Preparing to destroy this gctx. * - Dumping a heap profile that includes this gctx. * nlimbo must be 1 (single destroyer) in order to safely destroy the * gctx. */ unsigned nlimbo; /* * Tree of profile counters, one for each thread that has allocated in * this context. */ prof_tctx_tree_t tctxs; /* Linkage for tree of contexts to be dumped. */ rb_node(prof_gctx_t) dump_link; /* Temporary storage for summation during dump. */ prof_cnt_t cnt_summed; /* Associated backtrace. */ prof_bt_t bt; /* Backtrace vector, variable size, referred to by bt. */ void *vec[1]; }; typedef rb_tree(prof_gctx_t) prof_gctx_tree_t; struct prof_tdata_s { malloc_mutex_t *lock; /* Monotonically increasing unique thread identifier. */ uint64_t thr_uid; /* * Monotonically increasing discriminator among tdata structures * associated with the same thr_uid. */ uint64_t thr_discrim; /* Included in heap profile dumps if non-NULL. */ char *thread_name; bool attached; bool expired; rb_node(prof_tdata_t) tdata_link; /* * Counter used to initialize prof_tctx_t's tctx_uid. No locking is * necessary when incrementing this field, because only one thread ever * does so. */ uint64_t tctx_uid_next; /* * Hash of (prof_bt_t *)-->(prof_tctx_t *). Each thread tracks * backtraces for which it has non-zero allocation/deallocation counters * associated with thread-specific prof_tctx_t objects. Other threads * may write to prof_tctx_t contents when freeing associated objects. */ ckh_t bt2tctx; /* Sampling state. */ uint64_t prng_state; - uint64_t bytes_until_sample; /* State used to avoid dumping while operating on prof internals. */ bool enq; bool enq_idump; bool enq_gdump; /* * Set to true during an early dump phase for tdata's which are * currently being dumped. New threads' tdata's have this initialized * to false so that they aren't accidentally included in later dump * phases. */ bool dumping; /* * True if profiling is active for this tdata's thread * (thread.prof.active mallctl). */ bool active; /* Temporary storage for summation during dump. */ prof_cnt_t cnt_summed; /* Backtrace vector, used for calls to prof_backtrace(). */ void *vec[PROF_BT_MAX]; }; typedef rb_tree(prof_tdata_t) prof_tdata_tree_t; #endif /* JEMALLOC_INTERNAL_PROF_STRUCTS_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/public_namespace.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/public_namespace.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/public_namespace.h (revision 360233) @@ -1,21 +1,22 @@ #define je_aligned_alloc JEMALLOC_N(aligned_alloc) #define je_calloc JEMALLOC_N(calloc) #define je_dallocx JEMALLOC_N(dallocx) #define je_free JEMALLOC_N(free) #define je_mallctl JEMALLOC_N(mallctl) #define je_mallctlbymib JEMALLOC_N(mallctlbymib) #define je_mallctlnametomib JEMALLOC_N(mallctlnametomib) #define je_malloc JEMALLOC_N(malloc) #define je_malloc_conf JEMALLOC_N(malloc_conf) #define je_malloc_message JEMALLOC_N(malloc_message) #define je_malloc_stats_print JEMALLOC_N(malloc_stats_print) #define je_malloc_usable_size JEMALLOC_N(malloc_usable_size) #define je_mallocx JEMALLOC_N(mallocx) +#define je_smallocx_ea6b3e973b477b8061e0076bb257dbd7f3faa756 JEMALLOC_N(smallocx_ea6b3e973b477b8061e0076bb257dbd7f3faa756) #define je_nallocx JEMALLOC_N(nallocx) #define je_posix_memalign JEMALLOC_N(posix_memalign) #define je_rallocx JEMALLOC_N(rallocx) #define je_realloc JEMALLOC_N(realloc) #define je_sallocx JEMALLOC_N(sallocx) #define je_sdallocx JEMALLOC_N(sdallocx) #define je_xallocx JEMALLOC_N(xallocx) #define je_valloc JEMALLOC_N(valloc) Index: head/contrib/jemalloc/include/jemalloc/internal/quantum.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/quantum.h (nonexistent) +++ head/contrib/jemalloc/include/jemalloc/internal/quantum.h (revision 360233) @@ -0,0 +1,77 @@ +#ifndef JEMALLOC_INTERNAL_QUANTUM_H +#define JEMALLOC_INTERNAL_QUANTUM_H + +/* + * Minimum allocation alignment is 2^LG_QUANTUM bytes (ignoring tiny size + * classes). + */ +#ifndef LG_QUANTUM +# if (defined(__i386__) || defined(_M_IX86)) +# define LG_QUANTUM 4 +# endif +# ifdef __ia64__ +# define LG_QUANTUM 4 +# endif +# ifdef __alpha__ +# define LG_QUANTUM 4 +# endif +# if (defined(__sparc64__) || defined(__sparcv9) || defined(__sparc_v9__)) +# define LG_QUANTUM 4 +# endif +# if (defined(__amd64__) || defined(__x86_64__) || defined(_M_X64)) +# define LG_QUANTUM 4 +# endif +# ifdef __arm__ +# define LG_QUANTUM 3 +# endif +# ifdef __aarch64__ +# define LG_QUANTUM 4 +# endif +# ifdef __hppa__ +# define LG_QUANTUM 4 +# endif +# ifdef __m68k__ +# define LG_QUANTUM 3 +# endif +# ifdef __mips__ +# define LG_QUANTUM 3 +# endif +# ifdef __nios2__ +# define LG_QUANTUM 3 +# endif +# ifdef __or1k__ +# define LG_QUANTUM 3 +# endif +# ifdef __powerpc__ +# define LG_QUANTUM 4 +# endif +# if defined(__riscv) || defined(__riscv__) +# define LG_QUANTUM 4 +# endif +# ifdef __s390__ +# define LG_QUANTUM 4 +# endif +# if (defined (__SH3E__) || defined(__SH4_SINGLE__) || defined(__SH4__) || \ + defined(__SH4_SINGLE_ONLY__)) +# define LG_QUANTUM 4 +# endif +# ifdef __tile__ +# define LG_QUANTUM 4 +# endif +# ifdef __le32__ +# define LG_QUANTUM 4 +# endif +# ifndef LG_QUANTUM +# error "Unknown minimum alignment for architecture; specify via " + "--with-lg-quantum" +# endif +#endif + +#define QUANTUM ((size_t)(1U << LG_QUANTUM)) +#define QUANTUM_MASK (QUANTUM - 1) + +/* Return the smallest quantum multiple that is >= a. */ +#define QUANTUM_CEILING(a) \ + (((a) + QUANTUM_MASK) & ~QUANTUM_MASK) + +#endif /* JEMALLOC_INTERNAL_QUANTUM_H */ Property changes on: head/contrib/jemalloc/include/jemalloc/internal/quantum.h ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/jemalloc/include/jemalloc/internal/rtree.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/rtree.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/rtree.h (revision 360233) @@ -1,492 +1,528 @@ #ifndef JEMALLOC_INTERNAL_RTREE_H #define JEMALLOC_INTERNAL_RTREE_H #include "jemalloc/internal/atomic.h" #include "jemalloc/internal/mutex.h" #include "jemalloc/internal/rtree_tsd.h" -#include "jemalloc/internal/size_classes.h" +#include "jemalloc/internal/sc.h" #include "jemalloc/internal/tsd.h" /* * This radix tree implementation is tailored to the singular purpose of * associating metadata with extents that are currently owned by jemalloc. * ******************************************************************************* */ /* Number of high insignificant bits. */ #define RTREE_NHIB ((1U << (LG_SIZEOF_PTR+3)) - LG_VADDR) /* Number of low insigificant bits. */ #define RTREE_NLIB LG_PAGE /* Number of significant bits. */ #define RTREE_NSB (LG_VADDR - RTREE_NLIB) /* Number of levels in radix tree. */ #if RTREE_NSB <= 10 # define RTREE_HEIGHT 1 #elif RTREE_NSB <= 36 # define RTREE_HEIGHT 2 #elif RTREE_NSB <= 52 # define RTREE_HEIGHT 3 #else # error Unsupported number of significant virtual address bits #endif /* Use compact leaf representation if virtual address encoding allows. */ -#if RTREE_NHIB >= LG_CEIL_NSIZES +#if RTREE_NHIB >= LG_CEIL(SC_NSIZES) # define RTREE_LEAF_COMPACT #endif /* Needed for initialization only. */ #define RTREE_LEAFKEY_INVALID ((uintptr_t)1) typedef struct rtree_node_elm_s rtree_node_elm_t; struct rtree_node_elm_s { atomic_p_t child; /* (rtree_{node,leaf}_elm_t *) */ }; struct rtree_leaf_elm_s { #ifdef RTREE_LEAF_COMPACT /* * Single pointer-width field containing all three leaf element fields. * For example, on a 64-bit x64 system with 48 significant virtual * memory address bits, the index, extent, and slab fields are packed as * such: * * x: index * e: extent * b: slab * * 00000000 xxxxxxxx eeeeeeee [...] eeeeeeee eeee000b */ atomic_p_t le_bits; #else atomic_p_t le_extent; /* (extent_t *) */ atomic_u_t le_szind; /* (szind_t) */ atomic_b_t le_slab; /* (bool) */ #endif }; typedef struct rtree_level_s rtree_level_t; struct rtree_level_s { /* Number of key bits distinguished by this level. */ unsigned bits; /* * Cumulative number of key bits distinguished by traversing to * corresponding tree level. */ unsigned cumbits; }; typedef struct rtree_s rtree_t; struct rtree_s { malloc_mutex_t init_lock; /* Number of elements based on rtree_levels[0].bits. */ #if RTREE_HEIGHT > 1 rtree_node_elm_t root[1U << (RTREE_NSB/RTREE_HEIGHT)]; #else rtree_leaf_elm_t root[1U << (RTREE_NSB/RTREE_HEIGHT)]; #endif }; /* * Split the bits into one to three partitions depending on number of * significant bits. It the number of bits does not divide evenly into the * number of levels, place one remainder bit per level starting at the leaf * level. */ static const rtree_level_t rtree_levels[] = { #if RTREE_HEIGHT == 1 {RTREE_NSB, RTREE_NHIB + RTREE_NSB} #elif RTREE_HEIGHT == 2 {RTREE_NSB/2, RTREE_NHIB + RTREE_NSB/2}, {RTREE_NSB/2 + RTREE_NSB%2, RTREE_NHIB + RTREE_NSB} #elif RTREE_HEIGHT == 3 {RTREE_NSB/3, RTREE_NHIB + RTREE_NSB/3}, {RTREE_NSB/3 + RTREE_NSB%3/2, RTREE_NHIB + RTREE_NSB/3*2 + RTREE_NSB%3/2}, {RTREE_NSB/3 + RTREE_NSB%3 - RTREE_NSB%3/2, RTREE_NHIB + RTREE_NSB} #else # error Unsupported rtree height #endif }; bool rtree_new(rtree_t *rtree, bool zeroed); typedef rtree_node_elm_t *(rtree_node_alloc_t)(tsdn_t *, rtree_t *, size_t); extern rtree_node_alloc_t *JET_MUTABLE rtree_node_alloc; typedef rtree_leaf_elm_t *(rtree_leaf_alloc_t)(tsdn_t *, rtree_t *, size_t); extern rtree_leaf_alloc_t *JET_MUTABLE rtree_leaf_alloc; typedef void (rtree_node_dalloc_t)(tsdn_t *, rtree_t *, rtree_node_elm_t *); extern rtree_node_dalloc_t *JET_MUTABLE rtree_node_dalloc; typedef void (rtree_leaf_dalloc_t)(tsdn_t *, rtree_t *, rtree_leaf_elm_t *); extern rtree_leaf_dalloc_t *JET_MUTABLE rtree_leaf_dalloc; #ifdef JEMALLOC_JET void rtree_delete(tsdn_t *tsdn, rtree_t *rtree); #endif rtree_leaf_elm_t *rtree_leaf_elm_lookup_hard(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx, uintptr_t key, bool dependent, bool init_missing); JEMALLOC_ALWAYS_INLINE uintptr_t rtree_leafkey(uintptr_t key) { unsigned ptrbits = ZU(1) << (LG_SIZEOF_PTR+3); unsigned cumbits = (rtree_levels[RTREE_HEIGHT-1].cumbits - rtree_levels[RTREE_HEIGHT-1].bits); unsigned maskbits = ptrbits - cumbits; uintptr_t mask = ~((ZU(1) << maskbits) - 1); return (key & mask); } JEMALLOC_ALWAYS_INLINE size_t rtree_cache_direct_map(uintptr_t key) { unsigned ptrbits = ZU(1) << (LG_SIZEOF_PTR+3); unsigned cumbits = (rtree_levels[RTREE_HEIGHT-1].cumbits - rtree_levels[RTREE_HEIGHT-1].bits); unsigned maskbits = ptrbits - cumbits; return (size_t)((key >> maskbits) & (RTREE_CTX_NCACHE - 1)); } JEMALLOC_ALWAYS_INLINE uintptr_t rtree_subkey(uintptr_t key, unsigned level) { unsigned ptrbits = ZU(1) << (LG_SIZEOF_PTR+3); unsigned cumbits = rtree_levels[level].cumbits; unsigned shiftbits = ptrbits - cumbits; unsigned maskbits = rtree_levels[level].bits; uintptr_t mask = (ZU(1) << maskbits) - 1; return ((key >> shiftbits) & mask); } /* * Atomic getters. * * dependent: Reading a value on behalf of a pointer to a valid allocation * is guaranteed to be a clean read even without synchronization, * because the rtree update became visible in memory before the * pointer came into existence. * !dependent: An arbitrary read, e.g. on behalf of ivsalloc(), may not be * dependent on a previous rtree write, which means a stale read * could result if synchronization were omitted here. */ # ifdef RTREE_LEAF_COMPACT JEMALLOC_ALWAYS_INLINE uintptr_t -rtree_leaf_elm_bits_read(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *elm, - bool dependent) { +rtree_leaf_elm_bits_read(tsdn_t *tsdn, rtree_t *rtree, + rtree_leaf_elm_t *elm, bool dependent) { return (uintptr_t)atomic_load_p(&elm->le_bits, dependent ? ATOMIC_RELAXED : ATOMIC_ACQUIRE); } JEMALLOC_ALWAYS_INLINE extent_t * rtree_leaf_elm_bits_extent_get(uintptr_t bits) { # ifdef __aarch64__ /* * aarch64 doesn't sign extend the highest virtual address bit to set * the higher ones. Instead, the high bits gets zeroed. */ uintptr_t high_bit_mask = ((uintptr_t)1 << LG_VADDR) - 1; /* Mask off the slab bit. */ uintptr_t low_bit_mask = ~(uintptr_t)1; uintptr_t mask = high_bit_mask & low_bit_mask; return (extent_t *)(bits & mask); # else /* Restore sign-extended high bits, mask slab bit. */ return (extent_t *)((uintptr_t)((intptr_t)(bits << RTREE_NHIB) >> RTREE_NHIB) & ~((uintptr_t)0x1)); # endif } JEMALLOC_ALWAYS_INLINE szind_t rtree_leaf_elm_bits_szind_get(uintptr_t bits) { return (szind_t)(bits >> LG_VADDR); } JEMALLOC_ALWAYS_INLINE bool rtree_leaf_elm_bits_slab_get(uintptr_t bits) { return (bool)(bits & (uintptr_t)0x1); } # endif JEMALLOC_ALWAYS_INLINE extent_t * -rtree_leaf_elm_extent_read(UNUSED tsdn_t *tsdn, UNUSED rtree_t *rtree, +rtree_leaf_elm_extent_read(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *elm, bool dependent) { #ifdef RTREE_LEAF_COMPACT uintptr_t bits = rtree_leaf_elm_bits_read(tsdn, rtree, elm, dependent); return rtree_leaf_elm_bits_extent_get(bits); #else extent_t *extent = (extent_t *)atomic_load_p(&elm->le_extent, dependent ? ATOMIC_RELAXED : ATOMIC_ACQUIRE); return extent; #endif } JEMALLOC_ALWAYS_INLINE szind_t -rtree_leaf_elm_szind_read(UNUSED tsdn_t *tsdn, UNUSED rtree_t *rtree, +rtree_leaf_elm_szind_read(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *elm, bool dependent) { #ifdef RTREE_LEAF_COMPACT uintptr_t bits = rtree_leaf_elm_bits_read(tsdn, rtree, elm, dependent); return rtree_leaf_elm_bits_szind_get(bits); #else return (szind_t)atomic_load_u(&elm->le_szind, dependent ? ATOMIC_RELAXED : ATOMIC_ACQUIRE); #endif } JEMALLOC_ALWAYS_INLINE bool -rtree_leaf_elm_slab_read(UNUSED tsdn_t *tsdn, UNUSED rtree_t *rtree, +rtree_leaf_elm_slab_read(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *elm, bool dependent) { #ifdef RTREE_LEAF_COMPACT uintptr_t bits = rtree_leaf_elm_bits_read(tsdn, rtree, elm, dependent); return rtree_leaf_elm_bits_slab_get(bits); #else return atomic_load_b(&elm->le_slab, dependent ? ATOMIC_RELAXED : ATOMIC_ACQUIRE); #endif } static inline void -rtree_leaf_elm_extent_write(UNUSED tsdn_t *tsdn, UNUSED rtree_t *rtree, +rtree_leaf_elm_extent_write(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *elm, extent_t *extent) { #ifdef RTREE_LEAF_COMPACT uintptr_t old_bits = rtree_leaf_elm_bits_read(tsdn, rtree, elm, true); uintptr_t bits = ((uintptr_t)rtree_leaf_elm_bits_szind_get(old_bits) << LG_VADDR) | ((uintptr_t)extent & (((uintptr_t)0x1 << LG_VADDR) - 1)) | ((uintptr_t)rtree_leaf_elm_bits_slab_get(old_bits)); atomic_store_p(&elm->le_bits, (void *)bits, ATOMIC_RELEASE); #else atomic_store_p(&elm->le_extent, extent, ATOMIC_RELEASE); #endif } static inline void -rtree_leaf_elm_szind_write(UNUSED tsdn_t *tsdn, UNUSED rtree_t *rtree, +rtree_leaf_elm_szind_write(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *elm, szind_t szind) { - assert(szind <= NSIZES); + assert(szind <= SC_NSIZES); #ifdef RTREE_LEAF_COMPACT uintptr_t old_bits = rtree_leaf_elm_bits_read(tsdn, rtree, elm, true); uintptr_t bits = ((uintptr_t)szind << LG_VADDR) | ((uintptr_t)rtree_leaf_elm_bits_extent_get(old_bits) & (((uintptr_t)0x1 << LG_VADDR) - 1)) | ((uintptr_t)rtree_leaf_elm_bits_slab_get(old_bits)); atomic_store_p(&elm->le_bits, (void *)bits, ATOMIC_RELEASE); #else atomic_store_u(&elm->le_szind, szind, ATOMIC_RELEASE); #endif } static inline void -rtree_leaf_elm_slab_write(UNUSED tsdn_t *tsdn, UNUSED rtree_t *rtree, +rtree_leaf_elm_slab_write(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *elm, bool slab) { #ifdef RTREE_LEAF_COMPACT uintptr_t old_bits = rtree_leaf_elm_bits_read(tsdn, rtree, elm, true); uintptr_t bits = ((uintptr_t)rtree_leaf_elm_bits_szind_get(old_bits) << LG_VADDR) | ((uintptr_t)rtree_leaf_elm_bits_extent_get(old_bits) & (((uintptr_t)0x1 << LG_VADDR) - 1)) | ((uintptr_t)slab); atomic_store_p(&elm->le_bits, (void *)bits, ATOMIC_RELEASE); #else atomic_store_b(&elm->le_slab, slab, ATOMIC_RELEASE); #endif } static inline void -rtree_leaf_elm_write(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *elm, - extent_t *extent, szind_t szind, bool slab) { +rtree_leaf_elm_write(tsdn_t *tsdn, rtree_t *rtree, + rtree_leaf_elm_t *elm, extent_t *extent, szind_t szind, bool slab) { #ifdef RTREE_LEAF_COMPACT uintptr_t bits = ((uintptr_t)szind << LG_VADDR) | ((uintptr_t)extent & (((uintptr_t)0x1 << LG_VADDR) - 1)) | ((uintptr_t)slab); atomic_store_p(&elm->le_bits, (void *)bits, ATOMIC_RELEASE); #else rtree_leaf_elm_slab_write(tsdn, rtree, elm, slab); rtree_leaf_elm_szind_write(tsdn, rtree, elm, szind); /* * Write extent last, since the element is atomically considered valid * as soon as the extent field is non-NULL. */ rtree_leaf_elm_extent_write(tsdn, rtree, elm, extent); #endif } static inline void rtree_leaf_elm_szind_slab_update(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *elm, szind_t szind, bool slab) { - assert(!slab || szind < NBINS); + assert(!slab || szind < SC_NBINS); /* * The caller implicitly assures that it is the only writer to the szind * and slab fields, and that the extent field cannot currently change. */ rtree_leaf_elm_slab_write(tsdn, rtree, elm, slab); rtree_leaf_elm_szind_write(tsdn, rtree, elm, szind); } JEMALLOC_ALWAYS_INLINE rtree_leaf_elm_t * rtree_leaf_elm_lookup(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx, uintptr_t key, bool dependent, bool init_missing) { assert(key != 0); assert(!dependent || !init_missing); size_t slot = rtree_cache_direct_map(key); uintptr_t leafkey = rtree_leafkey(key); assert(leafkey != RTREE_LEAFKEY_INVALID); /* Fast path: L1 direct mapped cache. */ if (likely(rtree_ctx->cache[slot].leafkey == leafkey)) { rtree_leaf_elm_t *leaf = rtree_ctx->cache[slot].leaf; assert(leaf != NULL); uintptr_t subkey = rtree_subkey(key, RTREE_HEIGHT-1); return &leaf[subkey]; } /* * Search the L2 LRU cache. On hit, swap the matching element into the * slot in L1 cache, and move the position in L2 up by 1. */ #define RTREE_CACHE_CHECK_L2(i) do { \ if (likely(rtree_ctx->l2_cache[i].leafkey == leafkey)) { \ rtree_leaf_elm_t *leaf = rtree_ctx->l2_cache[i].leaf; \ assert(leaf != NULL); \ if (i > 0) { \ /* Bubble up by one. */ \ rtree_ctx->l2_cache[i].leafkey = \ rtree_ctx->l2_cache[i - 1].leafkey; \ rtree_ctx->l2_cache[i].leaf = \ rtree_ctx->l2_cache[i - 1].leaf; \ rtree_ctx->l2_cache[i - 1].leafkey = \ rtree_ctx->cache[slot].leafkey; \ rtree_ctx->l2_cache[i - 1].leaf = \ rtree_ctx->cache[slot].leaf; \ } else { \ rtree_ctx->l2_cache[0].leafkey = \ rtree_ctx->cache[slot].leafkey; \ rtree_ctx->l2_cache[0].leaf = \ rtree_ctx->cache[slot].leaf; \ } \ rtree_ctx->cache[slot].leafkey = leafkey; \ rtree_ctx->cache[slot].leaf = leaf; \ uintptr_t subkey = rtree_subkey(key, RTREE_HEIGHT-1); \ return &leaf[subkey]; \ } \ } while (0) /* Check the first cache entry. */ RTREE_CACHE_CHECK_L2(0); /* Search the remaining cache elements. */ for (unsigned i = 1; i < RTREE_CTX_NCACHE_L2; i++) { RTREE_CACHE_CHECK_L2(i); } #undef RTREE_CACHE_CHECK_L2 return rtree_leaf_elm_lookup_hard(tsdn, rtree, rtree_ctx, key, dependent, init_missing); } static inline bool rtree_write(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx, uintptr_t key, extent_t *extent, szind_t szind, bool slab) { /* Use rtree_clear() to set the extent to NULL. */ assert(extent != NULL); rtree_leaf_elm_t *elm = rtree_leaf_elm_lookup(tsdn, rtree, rtree_ctx, key, false, true); if (elm == NULL) { return true; } assert(rtree_leaf_elm_extent_read(tsdn, rtree, elm, false) == NULL); rtree_leaf_elm_write(tsdn, rtree, elm, extent, szind, slab); return false; } JEMALLOC_ALWAYS_INLINE rtree_leaf_elm_t * rtree_read(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx, uintptr_t key, bool dependent) { rtree_leaf_elm_t *elm = rtree_leaf_elm_lookup(tsdn, rtree, rtree_ctx, key, dependent, false); if (!dependent && elm == NULL) { return NULL; } assert(elm != NULL); return elm; } JEMALLOC_ALWAYS_INLINE extent_t * rtree_extent_read(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx, uintptr_t key, bool dependent) { rtree_leaf_elm_t *elm = rtree_read(tsdn, rtree, rtree_ctx, key, dependent); if (!dependent && elm == NULL) { return NULL; } return rtree_leaf_elm_extent_read(tsdn, rtree, elm, dependent); } JEMALLOC_ALWAYS_INLINE szind_t rtree_szind_read(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx, uintptr_t key, bool dependent) { rtree_leaf_elm_t *elm = rtree_read(tsdn, rtree, rtree_ctx, key, dependent); if (!dependent && elm == NULL) { - return NSIZES; + return SC_NSIZES; } return rtree_leaf_elm_szind_read(tsdn, rtree, elm, dependent); } /* * rtree_slab_read() is intentionally omitted because slab is always read in * conjunction with szind, which makes rtree_szind_slab_read() a better choice. */ JEMALLOC_ALWAYS_INLINE bool rtree_extent_szind_read(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx, uintptr_t key, bool dependent, extent_t **r_extent, szind_t *r_szind) { rtree_leaf_elm_t *elm = rtree_read(tsdn, rtree, rtree_ctx, key, dependent); if (!dependent && elm == NULL) { return true; } *r_extent = rtree_leaf_elm_extent_read(tsdn, rtree, elm, dependent); *r_szind = rtree_leaf_elm_szind_read(tsdn, rtree, elm, dependent); return false; } +/* + * Try to read szind_slab from the L1 cache. Returns true on a hit, + * and fills in r_szind and r_slab. Otherwise returns false. + * + * Key is allowed to be NULL in order to save an extra branch on the + * fastpath. returns false in this case. + */ JEMALLOC_ALWAYS_INLINE bool +rtree_szind_slab_read_fast(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx, + uintptr_t key, szind_t *r_szind, bool *r_slab) { + rtree_leaf_elm_t *elm; + + size_t slot = rtree_cache_direct_map(key); + uintptr_t leafkey = rtree_leafkey(key); + assert(leafkey != RTREE_LEAFKEY_INVALID); + + if (likely(rtree_ctx->cache[slot].leafkey == leafkey)) { + rtree_leaf_elm_t *leaf = rtree_ctx->cache[slot].leaf; + assert(leaf != NULL); + uintptr_t subkey = rtree_subkey(key, RTREE_HEIGHT-1); + elm = &leaf[subkey]; + +#ifdef RTREE_LEAF_COMPACT + uintptr_t bits = rtree_leaf_elm_bits_read(tsdn, rtree, + elm, true); + *r_szind = rtree_leaf_elm_bits_szind_get(bits); + *r_slab = rtree_leaf_elm_bits_slab_get(bits); +#else + *r_szind = rtree_leaf_elm_szind_read(tsdn, rtree, elm, true); + *r_slab = rtree_leaf_elm_slab_read(tsdn, rtree, elm, true); +#endif + return true; + } else { + return false; + } +} +JEMALLOC_ALWAYS_INLINE bool rtree_szind_slab_read(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx, uintptr_t key, bool dependent, szind_t *r_szind, bool *r_slab) { rtree_leaf_elm_t *elm = rtree_read(tsdn, rtree, rtree_ctx, key, dependent); if (!dependent && elm == NULL) { return true; } #ifdef RTREE_LEAF_COMPACT uintptr_t bits = rtree_leaf_elm_bits_read(tsdn, rtree, elm, dependent); *r_szind = rtree_leaf_elm_bits_szind_get(bits); *r_slab = rtree_leaf_elm_bits_slab_get(bits); #else *r_szind = rtree_leaf_elm_szind_read(tsdn, rtree, elm, dependent); *r_slab = rtree_leaf_elm_slab_read(tsdn, rtree, elm, dependent); #endif return false; } static inline void rtree_szind_slab_update(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx, uintptr_t key, szind_t szind, bool slab) { - assert(!slab || szind < NBINS); + assert(!slab || szind < SC_NBINS); rtree_leaf_elm_t *elm = rtree_read(tsdn, rtree, rtree_ctx, key, true); rtree_leaf_elm_szind_slab_update(tsdn, rtree, elm, szind, slab); } static inline void rtree_clear(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx, uintptr_t key) { rtree_leaf_elm_t *elm = rtree_read(tsdn, rtree, rtree_ctx, key, true); assert(rtree_leaf_elm_extent_read(tsdn, rtree, elm, false) != NULL); - rtree_leaf_elm_write(tsdn, rtree, elm, NULL, NSIZES, false); + rtree_leaf_elm_write(tsdn, rtree, elm, NULL, SC_NSIZES, false); } #endif /* JEMALLOC_INTERNAL_RTREE_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/rtree_tsd.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/rtree_tsd.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/rtree_tsd.h (revision 360233) @@ -1,50 +1,50 @@ #ifndef JEMALLOC_INTERNAL_RTREE_CTX_H #define JEMALLOC_INTERNAL_RTREE_CTX_H /* * Number of leafkey/leaf pairs to cache in L1 and L2 level respectively. Each * entry supports an entire leaf, so the cache hit rate is typically high even * with a small number of entries. In rare cases extent activity will straddle * the boundary between two leaf nodes. Furthermore, an arena may use a * combination of dss and mmap. Note that as memory usage grows past the amount * that this cache can directly cover, the cache will become less effective if * locality of reference is low, but the consequence is merely cache misses * while traversing the tree nodes. * * The L1 direct mapped cache offers consistent and low cost on cache hit. * However collision could affect hit rate negatively. This is resolved by * combining with a L2 LRU cache, which requires linear search and re-ordering * on access but suffers no collision. Note that, the cache will itself suffer * cache misses if made overly large, plus the cost of linear search in the LRU * cache. */ #define RTREE_CTX_LG_NCACHE 4 #define RTREE_CTX_NCACHE (1 << RTREE_CTX_LG_NCACHE) #define RTREE_CTX_NCACHE_L2 8 /* * Zero initializer required for tsd initialization only. Proper initialization * done via rtree_ctx_data_init(). */ -#define RTREE_CTX_ZERO_INITIALIZER {{{0}}, {{0}}} +#define RTREE_CTX_ZERO_INITIALIZER {{{0, 0}}, {{0, 0}}} typedef struct rtree_leaf_elm_s rtree_leaf_elm_t; typedef struct rtree_ctx_cache_elm_s rtree_ctx_cache_elm_t; struct rtree_ctx_cache_elm_s { uintptr_t leafkey; rtree_leaf_elm_t *leaf; }; typedef struct rtree_ctx_s rtree_ctx_t; struct rtree_ctx_s { /* Direct mapped cache. */ rtree_ctx_cache_elm_t cache[RTREE_CTX_NCACHE]; /* L2 LRU cache. */ rtree_ctx_cache_elm_t l2_cache[RTREE_CTX_NCACHE_L2]; }; void rtree_ctx_data_init(rtree_ctx_t *ctx); #endif /* JEMALLOC_INTERNAL_RTREE_CTX_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/safety_check.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/safety_check.h (nonexistent) +++ head/contrib/jemalloc/include/jemalloc/internal/safety_check.h (revision 360233) @@ -0,0 +1,26 @@ +#ifndef JEMALLOC_INTERNAL_SAFETY_CHECK_H +#define JEMALLOC_INTERNAL_SAFETY_CHECK_H + +void safety_check_fail(const char *format, ...); +/* Can set to NULL for a default. */ +void safety_check_set_abort(void (*abort_fn)()); + +JEMALLOC_ALWAYS_INLINE void +safety_check_set_redzone(void *ptr, size_t usize, size_t bumped_usize) { + assert(usize < bumped_usize); + for (size_t i = usize; i < bumped_usize && i < usize + 32; ++i) { + *((unsigned char *)ptr + i) = 0xBC; + } +} + +JEMALLOC_ALWAYS_INLINE void +safety_check_verify_redzone(const void *ptr, size_t usize, size_t bumped_usize) +{ + for (size_t i = usize; i < bumped_usize && i < usize + 32; ++i) { + if (unlikely(*((unsigned char *)ptr + i) != 0xBC)) { + safety_check_fail("Use after free error\n"); + } + } +} + +#endif /*JEMALLOC_INTERNAL_SAFETY_CHECK_H */ Property changes on: head/contrib/jemalloc/include/jemalloc/internal/safety_check.h ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/jemalloc/include/jemalloc/internal/sc.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/sc.h (nonexistent) +++ head/contrib/jemalloc/include/jemalloc/internal/sc.h (revision 360233) @@ -0,0 +1,333 @@ +#ifndef JEMALLOC_INTERNAL_SC_H +#define JEMALLOC_INTERNAL_SC_H + +#include "jemalloc/internal/jemalloc_internal_types.h" + +/* + * Size class computations: + * + * These are a little tricky; we'll first start by describing how things + * generally work, and then describe some of the details. + * + * Ignore the first few size classes for a moment. We can then split all the + * remaining size classes into groups. The size classes in a group are spaced + * such that they cover allocation request sizes in a power-of-2 range. The + * power of two is called the base of the group, and the size classes in it + * satisfy allocations in the half-open range (base, base * 2]. There are + * SC_NGROUP size classes in each group, equally spaced in the range, so that + * each one covers allocations for base / SC_NGROUP possible allocation sizes. + * We call that value (base / SC_NGROUP) the delta of the group. Each size class + * is delta larger than the one before it (including the initial size class in a + * group, which is delta larger than base, the largest size class in the + * previous group). + * To make the math all work out nicely, we require that SC_NGROUP is a power of + * two, and define it in terms of SC_LG_NGROUP. We'll often talk in terms of + * lg_base and lg_delta. For each of these groups then, we have that + * lg_delta == lg_base - SC_LG_NGROUP. + * The size classes in a group with a given lg_base and lg_delta (which, recall, + * can be computed from lg_base for these groups) are therefore: + * base + 1 * delta + * which covers allocations in (base, base + 1 * delta] + * base + 2 * delta + * which covers allocations in (base + 1 * delta, base + 2 * delta]. + * base + 3 * delta + * which covers allocations in (base + 2 * delta, base + 3 * delta]. + * ... + * base + SC_NGROUP * delta ( == 2 * base) + * which covers allocations in (base + (SC_NGROUP - 1) * delta, 2 * base]. + * (Note that currently SC_NGROUP is always 4, so the "..." is empty in + * practice.) + * Note that the last size class in the group is the next power of two (after + * base), so that we've set up the induction correctly for the next group's + * selection of delta. + * + * Now, let's start considering the first few size classes. Two extra constants + * come into play here: LG_QUANTUM and SC_LG_TINY_MIN. LG_QUANTUM ensures + * correct platform alignment; all objects of size (1 << LG_QUANTUM) or larger + * are at least (1 << LG_QUANTUM) aligned; this can be used to ensure that we + * never return improperly aligned memory, by making (1 << LG_QUANTUM) equal the + * highest required alignment of a platform. For allocation sizes smaller than + * (1 << LG_QUANTUM) though, we can be more relaxed (since we don't support + * platforms with types with alignment larger than their size). To allow such + * allocations (without wasting space unnecessarily), we introduce tiny size + * classes; one per power of two, up until we hit the quantum size. There are + * therefore LG_QUANTUM - SC_LG_TINY_MIN such size classes. + * + * Next, we have a size class of size (1 << LG_QUANTUM). This can't be the + * start of a group in the sense we described above (covering a power of two + * range) since, if we divided into it to pick a value of delta, we'd get a + * delta smaller than (1 << LG_QUANTUM) for sizes >= (1 << LG_QUANTUM), which + * is against the rules. + * + * The first base we can divide by SC_NGROUP while still being at least + * (1 << LG_QUANTUM) is SC_NGROUP * (1 << LG_QUANTUM). We can get there by + * having SC_NGROUP size classes, spaced (1 << LG_QUANTUM) apart. These size + * classes are: + * 1 * (1 << LG_QUANTUM) + * 2 * (1 << LG_QUANTUM) + * 3 * (1 << LG_QUANTUM) + * ... (although, as above, this "..." is empty in practice) + * SC_NGROUP * (1 << LG_QUANTUM). + * + * There are SC_NGROUP of these size classes, so we can regard it as a sort of + * pseudo-group, even though it spans multiple powers of 2, is divided + * differently, and both starts and ends on a power of 2 (as opposed to just + * ending). SC_NGROUP is itself a power of two, so the first group after the + * pseudo-group has the power-of-two base SC_NGROUP * (1 << LG_QUANTUM), for a + * lg_base of LG_QUANTUM + SC_LG_NGROUP. We can divide this base into SC_NGROUP + * sizes without violating our LG_QUANTUM requirements, so we can safely set + * lg_delta = lg_base - SC_LG_GROUP (== LG_QUANTUM). + * + * So, in order, the size classes are: + * + * Tiny size classes: + * - Count: LG_QUANTUM - SC_LG_TINY_MIN. + * - Sizes: + * 1 << SC_LG_TINY_MIN + * 1 << (SC_LG_TINY_MIN + 1) + * 1 << (SC_LG_TINY_MIN + 2) + * ... + * 1 << (LG_QUANTUM - 1) + * + * Initial pseudo-group: + * - Count: SC_NGROUP + * - Sizes: + * 1 * (1 << LG_QUANTUM) + * 2 * (1 << LG_QUANTUM) + * 3 * (1 << LG_QUANTUM) + * ... + * SC_NGROUP * (1 << LG_QUANTUM) + * + * Regular group 0: + * - Count: SC_NGROUP + * - Sizes: + * (relative to lg_base of LG_QUANTUM + SC_LG_NGROUP and lg_delta of + * lg_base - SC_LG_NGROUP) + * (1 << lg_base) + 1 * (1 << lg_delta) + * (1 << lg_base) + 2 * (1 << lg_delta) + * (1 << lg_base) + 3 * (1 << lg_delta) + * ... + * (1 << lg_base) + SC_NGROUP * (1 << lg_delta) [ == (1 << (lg_base + 1)) ] + * + * Regular group 1: + * - Count: SC_NGROUP + * - Sizes: + * (relative to lg_base of LG_QUANTUM + SC_LG_NGROUP + 1 and lg_delta of + * lg_base - SC_LG_NGROUP) + * (1 << lg_base) + 1 * (1 << lg_delta) + * (1 << lg_base) + 2 * (1 << lg_delta) + * (1 << lg_base) + 3 * (1 << lg_delta) + * ... + * (1 << lg_base) + SC_NGROUP * (1 << lg_delta) [ == (1 << (lg_base + 1)) ] + * + * ... + * + * Regular group N: + * - Count: SC_NGROUP + * - Sizes: + * (relative to lg_base of LG_QUANTUM + SC_LG_NGROUP + N and lg_delta of + * lg_base - SC_LG_NGROUP) + * (1 << lg_base) + 1 * (1 << lg_delta) + * (1 << lg_base) + 2 * (1 << lg_delta) + * (1 << lg_base) + 3 * (1 << lg_delta) + * ... + * (1 << lg_base) + SC_NGROUP * (1 << lg_delta) [ == (1 << (lg_base + 1)) ] + * + * + * Representation of metadata: + * To make the math easy, we'll mostly work in lg quantities. We record lg_base, + * lg_delta, and ndelta (i.e. number of deltas above the base) on a + * per-size-class basis, and maintain the invariant that, across all size + * classes, size == (1 << lg_base) + ndelta * (1 << lg_delta). + * + * For regular groups (i.e. those with lg_base >= LG_QUANTUM + SC_LG_NGROUP), + * lg_delta is lg_base - SC_LG_NGROUP, and ndelta goes from 1 to SC_NGROUP. + * + * For the initial tiny size classes (if any), lg_base is lg(size class size). + * lg_delta is lg_base for the first size class, and lg_base - 1 for all + * subsequent ones. ndelta is always 0. + * + * For the pseudo-group, if there are no tiny size classes, then we set + * lg_base == LG_QUANTUM, lg_delta == LG_QUANTUM, and have ndelta range from 0 + * to SC_NGROUP - 1. (Note that delta == base, so base + (SC_NGROUP - 1) * delta + * is just SC_NGROUP * base, or (1 << (SC_LG_NGROUP + LG_QUANTUM)), so we do + * indeed get a power of two that way). If there *are* tiny size classes, then + * the first size class needs to have lg_delta relative to the largest tiny size + * class. We therefore set lg_base == LG_QUANTUM - 1, + * lg_delta == LG_QUANTUM - 1, and ndelta == 1, keeping the rest of the + * pseudo-group the same. + * + * + * Other terminology: + * "Small" size classes mean those that are allocated out of bins, which is the + * same as those that are slab allocated. + * "Large" size classes are those that are not small. The cutoff for counting as + * large is page size * group size. + */ + +/* + * Size class N + (1 << SC_LG_NGROUP) twice the size of size class N. + */ +#define SC_LG_NGROUP 2 +#define SC_LG_TINY_MIN 3 + +#if SC_LG_TINY_MIN == 0 +/* The div module doesn't support division by 1, which this would require. */ +#error "Unsupported LG_TINY_MIN" +#endif + +/* + * The definitions below are all determined by the above settings and system + * characteristics. + */ +#define SC_NGROUP (1ULL << SC_LG_NGROUP) +#define SC_PTR_BITS ((1ULL << LG_SIZEOF_PTR) * 8) +#define SC_NTINY (LG_QUANTUM - SC_LG_TINY_MIN) +#define SC_LG_TINY_MAXCLASS (LG_QUANTUM > SC_LG_TINY_MIN ? LG_QUANTUM - 1 : -1) +#define SC_NPSEUDO SC_NGROUP +#define SC_LG_FIRST_REGULAR_BASE (LG_QUANTUM + SC_LG_NGROUP) +/* + * We cap allocations to be less than 2 ** (ptr_bits - 1), so the highest base + * we need is 2 ** (ptr_bits - 2). (This also means that the last group is 1 + * size class shorter than the others). + * We could probably save some space in arenas by capping this at LG_VADDR size. + */ +#define SC_LG_BASE_MAX (SC_PTR_BITS - 2) +#define SC_NREGULAR (SC_NGROUP * \ + (SC_LG_BASE_MAX - SC_LG_FIRST_REGULAR_BASE + 1) - 1) +#define SC_NSIZES (SC_NTINY + SC_NPSEUDO + SC_NREGULAR) + +/* The number of size classes that are a multiple of the page size. */ +#define SC_NPSIZES ( \ + /* Start with all the size classes. */ \ + SC_NSIZES \ + /* Subtract out those groups with too small a base. */ \ + - (LG_PAGE - 1 - SC_LG_FIRST_REGULAR_BASE) * SC_NGROUP \ + /* And the pseudo-group. */ \ + - SC_NPSEUDO \ + /* And the tiny group. */ \ + - SC_NTINY \ + /* Sizes where ndelta*delta is not a multiple of the page size. */ \ + - (SC_LG_NGROUP * SC_NGROUP)) +/* + * Note that the last line is computed as the sum of the second column in the + * following table: + * lg(base) | count of sizes to exclude + * ------------------------------|----------------------------- + * LG_PAGE - 1 | SC_NGROUP - 1 + * LG_PAGE | SC_NGROUP - 1 + * LG_PAGE + 1 | SC_NGROUP - 2 + * LG_PAGE + 2 | SC_NGROUP - 4 + * ... | ... + * LG_PAGE + (SC_LG_NGROUP - 1) | SC_NGROUP - (SC_NGROUP / 2) + */ + +/* + * We declare a size class is binnable if size < page size * group. Or, in other + * words, lg(size) < lg(page size) + lg(group size). + */ +#define SC_NBINS ( \ + /* Sub-regular size classes. */ \ + SC_NTINY + SC_NPSEUDO \ + /* Groups with lg_regular_min_base <= lg_base <= lg_base_max */ \ + + SC_NGROUP * (LG_PAGE + SC_LG_NGROUP - SC_LG_FIRST_REGULAR_BASE) \ + /* Last SC of the last group hits the bound exactly; exclude it. */ \ + - 1) + +/* + * The size2index_tab lookup table uses uint8_t to encode each bin index, so we + * cannot support more than 256 small size classes. + */ +#if (SC_NBINS > 256) +# error "Too many small size classes" +#endif + +/* The largest size class in the lookup table. */ +#define SC_LOOKUP_MAXCLASS ((size_t)1 << 12) + +/* Internal, only used for the definition of SC_SMALL_MAXCLASS. */ +#define SC_SMALL_MAX_BASE ((size_t)1 << (LG_PAGE + SC_LG_NGROUP - 1)) +#define SC_SMALL_MAX_DELTA ((size_t)1 << (LG_PAGE - 1)) + +/* The largest size class allocated out of a slab. */ +#define SC_SMALL_MAXCLASS (SC_SMALL_MAX_BASE \ + + (SC_NGROUP - 1) * SC_SMALL_MAX_DELTA) + +/* The smallest size class not allocated out of a slab. */ +#define SC_LARGE_MINCLASS ((size_t)1ULL << (LG_PAGE + SC_LG_NGROUP)) +#define SC_LG_LARGE_MINCLASS (LG_PAGE + SC_LG_NGROUP) + +/* Internal; only used for the definition of SC_LARGE_MAXCLASS. */ +#define SC_MAX_BASE ((size_t)1 << (SC_PTR_BITS - 2)) +#define SC_MAX_DELTA ((size_t)1 << (SC_PTR_BITS - 2 - SC_LG_NGROUP)) + +/* The largest size class supported. */ +#define SC_LARGE_MAXCLASS (SC_MAX_BASE + (SC_NGROUP - 1) * SC_MAX_DELTA) + +typedef struct sc_s sc_t; +struct sc_s { + /* Size class index, or -1 if not a valid size class. */ + int index; + /* Lg group base size (no deltas added). */ + int lg_base; + /* Lg delta to previous size class. */ + int lg_delta; + /* Delta multiplier. size == 1<data) / sizeof(size_t)]; \ + buf[sizeof(buf) / sizeof(size_t) - 1] = 0; \ + memcpy(buf, src, sizeof(type)); \ + size_t old_seq = atomic_load_zu(&dst->seq, ATOMIC_RELAXED); \ + atomic_store_zu(&dst->seq, old_seq + 1, ATOMIC_RELAXED); \ + atomic_fence(ATOMIC_RELEASE); \ + for (size_t i = 0; i < sizeof(buf) / sizeof(size_t); i++) { \ + atomic_store_zu(&dst->data[i], buf[i], ATOMIC_RELAXED); \ + } \ + atomic_store_zu(&dst->seq, old_seq + 2, ATOMIC_RELEASE); \ +} \ + \ +/* Returns whether or not the read was consistent. */ \ +static inline bool \ +seq_try_load_##short_type(type *dst, seq_##short_type##_t *src) { \ + size_t buf[sizeof(src->data) / sizeof(size_t)]; \ + size_t seq1 = atomic_load_zu(&src->seq, ATOMIC_ACQUIRE); \ + if (seq1 % 2 != 0) { \ + return false; \ + } \ + for (size_t i = 0; i < sizeof(buf) / sizeof(size_t); i++) { \ + buf[i] = atomic_load_zu(&src->data[i], ATOMIC_RELAXED); \ + } \ + atomic_fence(ATOMIC_ACQUIRE); \ + size_t seq2 = atomic_load_zu(&src->seq, ATOMIC_RELAXED); \ + if (seq1 != seq2) { \ + return false; \ + } \ + memcpy(dst, buf, sizeof(type)); \ + return true; \ +} + +#endif /* JEMALLOC_INTERNAL_SEQ_H */ Property changes on: head/contrib/jemalloc/include/jemalloc/internal/seq.h ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/jemalloc/include/jemalloc/internal/stats.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/stats.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/stats.h (revision 360233) @@ -1,30 +1,31 @@ #ifndef JEMALLOC_INTERNAL_STATS_H #define JEMALLOC_INTERNAL_STATS_H /* OPTION(opt, var_name, default, set_value_to) */ #define STATS_PRINT_OPTIONS \ OPTION('J', json, false, true) \ OPTION('g', general, true, false) \ OPTION('m', merged, config_stats, false) \ OPTION('d', destroyed, config_stats, false) \ OPTION('a', unmerged, config_stats, false) \ OPTION('b', bins, true, false) \ OPTION('l', large, true, false) \ - OPTION('x', mutex, true, false) + OPTION('x', mutex, true, false) \ + OPTION('e', extents, true, false) enum { #define OPTION(o, v, d, s) stats_print_option_num_##v, STATS_PRINT_OPTIONS #undef OPTION stats_print_tot_num_options }; /* Options for stats_print. */ extern bool opt_stats_print; extern char opt_stats_print_opts[stats_print_tot_num_options+1]; /* Implements je_malloc_stats_print. */ void stats_print(void (*write_cb)(void *, const char *), void *cbopaque, const char *opts); #endif /* JEMALLOC_INTERNAL_STATS_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/sz.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/sz.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/sz.h (revision 360233) @@ -1,317 +1,318 @@ #ifndef JEMALLOC_INTERNAL_SIZE_H #define JEMALLOC_INTERNAL_SIZE_H #include "jemalloc/internal/bit_util.h" #include "jemalloc/internal/pages.h" -#include "jemalloc/internal/size_classes.h" +#include "jemalloc/internal/sc.h" #include "jemalloc/internal/util.h" /* * sz module: Size computations. * * Some abbreviations used here: * p: Page * ind: Index * s, sz: Size * u: Usable size * a: Aligned * * These are not always used completely consistently, but should be enough to * interpret function names. E.g. sz_psz2ind converts page size to page size * index; sz_sa2u converts a (size, alignment) allocation request to the usable * size that would result from such an allocation. */ /* * sz_pind2sz_tab encodes the same information as could be computed by * sz_pind2sz_compute(). */ -extern size_t const sz_pind2sz_tab[NPSIZES+1]; +extern size_t sz_pind2sz_tab[SC_NPSIZES + 1]; /* * sz_index2size_tab encodes the same information as could be computed (at * unacceptable cost in some code paths) by sz_index2size_compute(). */ -extern size_t const sz_index2size_tab[NSIZES]; +extern size_t sz_index2size_tab[SC_NSIZES]; /* * sz_size2index_tab is a compact lookup table that rounds request sizes up to * size classes. In order to reduce cache footprint, the table is compressed, * and all accesses are via sz_size2index(). */ -extern uint8_t const sz_size2index_tab[]; +extern uint8_t sz_size2index_tab[]; static const size_t sz_large_pad = #ifdef JEMALLOC_CACHE_OBLIVIOUS PAGE #else 0 #endif ; +extern void sz_boot(const sc_data_t *sc_data); + JEMALLOC_ALWAYS_INLINE pszind_t sz_psz2ind(size_t psz) { - if (unlikely(psz > LARGE_MAXCLASS)) { - return NPSIZES; + if (unlikely(psz > SC_LARGE_MAXCLASS)) { + return SC_NPSIZES; } - { - pszind_t x = lg_floor((psz<<1)-1); - pszind_t shift = (x < LG_SIZE_CLASS_GROUP + LG_PAGE) ? 0 : x - - (LG_SIZE_CLASS_GROUP + LG_PAGE); - pszind_t grp = shift << LG_SIZE_CLASS_GROUP; + pszind_t x = lg_floor((psz<<1)-1); + pszind_t shift = (x < SC_LG_NGROUP + LG_PAGE) ? + 0 : x - (SC_LG_NGROUP + LG_PAGE); + pszind_t grp = shift << SC_LG_NGROUP; - pszind_t lg_delta = (x < LG_SIZE_CLASS_GROUP + LG_PAGE + 1) ? - LG_PAGE : x - LG_SIZE_CLASS_GROUP - 1; + pszind_t lg_delta = (x < SC_LG_NGROUP + LG_PAGE + 1) ? + LG_PAGE : x - SC_LG_NGROUP - 1; - size_t delta_inverse_mask = ZU(-1) << lg_delta; - pszind_t mod = ((((psz-1) & delta_inverse_mask) >> lg_delta)) & - ((ZU(1) << LG_SIZE_CLASS_GROUP) - 1); + size_t delta_inverse_mask = ZU(-1) << lg_delta; + pszind_t mod = ((((psz-1) & delta_inverse_mask) >> lg_delta)) & + ((ZU(1) << SC_LG_NGROUP) - 1); - pszind_t ind = grp + mod; - return ind; - } + pszind_t ind = grp + mod; + return ind; } static inline size_t sz_pind2sz_compute(pszind_t pind) { - if (unlikely(pind == NPSIZES)) { - return LARGE_MAXCLASS + PAGE; + if (unlikely(pind == SC_NPSIZES)) { + return SC_LARGE_MAXCLASS + PAGE; } - { - size_t grp = pind >> LG_SIZE_CLASS_GROUP; - size_t mod = pind & ((ZU(1) << LG_SIZE_CLASS_GROUP) - 1); + size_t grp = pind >> SC_LG_NGROUP; + size_t mod = pind & ((ZU(1) << SC_LG_NGROUP) - 1); - size_t grp_size_mask = ~((!!grp)-1); - size_t grp_size = ((ZU(1) << (LG_PAGE + - (LG_SIZE_CLASS_GROUP-1))) << grp) & grp_size_mask; + size_t grp_size_mask = ~((!!grp)-1); + size_t grp_size = ((ZU(1) << (LG_PAGE + (SC_LG_NGROUP-1))) << grp) + & grp_size_mask; - size_t shift = (grp == 0) ? 1 : grp; - size_t lg_delta = shift + (LG_PAGE-1); - size_t mod_size = (mod+1) << lg_delta; + size_t shift = (grp == 0) ? 1 : grp; + size_t lg_delta = shift + (LG_PAGE-1); + size_t mod_size = (mod+1) << lg_delta; - size_t sz = grp_size + mod_size; - return sz; - } + size_t sz = grp_size + mod_size; + return sz; } static inline size_t sz_pind2sz_lookup(pszind_t pind) { size_t ret = (size_t)sz_pind2sz_tab[pind]; assert(ret == sz_pind2sz_compute(pind)); return ret; } static inline size_t sz_pind2sz(pszind_t pind) { - assert(pind < NPSIZES+1); + assert(pind < SC_NPSIZES + 1); return sz_pind2sz_lookup(pind); } static inline size_t sz_psz2u(size_t psz) { - if (unlikely(psz > LARGE_MAXCLASS)) { - return LARGE_MAXCLASS + PAGE; + if (unlikely(psz > SC_LARGE_MAXCLASS)) { + return SC_LARGE_MAXCLASS + PAGE; } - { - size_t x = lg_floor((psz<<1)-1); - size_t lg_delta = (x < LG_SIZE_CLASS_GROUP + LG_PAGE + 1) ? - LG_PAGE : x - LG_SIZE_CLASS_GROUP - 1; - size_t delta = ZU(1) << lg_delta; - size_t delta_mask = delta - 1; - size_t usize = (psz + delta_mask) & ~delta_mask; - return usize; - } + size_t x = lg_floor((psz<<1)-1); + size_t lg_delta = (x < SC_LG_NGROUP + LG_PAGE + 1) ? + LG_PAGE : x - SC_LG_NGROUP - 1; + size_t delta = ZU(1) << lg_delta; + size_t delta_mask = delta - 1; + size_t usize = (psz + delta_mask) & ~delta_mask; + return usize; } static inline szind_t sz_size2index_compute(size_t size) { - if (unlikely(size > LARGE_MAXCLASS)) { - return NSIZES; + if (unlikely(size > SC_LARGE_MAXCLASS)) { + return SC_NSIZES; } -#if (NTBINS != 0) - if (size <= (ZU(1) << LG_TINY_MAXCLASS)) { - szind_t lg_tmin = LG_TINY_MAXCLASS - NTBINS + 1; + + if (size == 0) { + return 0; + } +#if (SC_NTINY != 0) + if (size <= (ZU(1) << SC_LG_TINY_MAXCLASS)) { + szind_t lg_tmin = SC_LG_TINY_MAXCLASS - SC_NTINY + 1; szind_t lg_ceil = lg_floor(pow2_ceil_zu(size)); return (lg_ceil < lg_tmin ? 0 : lg_ceil - lg_tmin); } #endif { szind_t x = lg_floor((size<<1)-1); - szind_t shift = (x < LG_SIZE_CLASS_GROUP + LG_QUANTUM) ? 0 : - x - (LG_SIZE_CLASS_GROUP + LG_QUANTUM); - szind_t grp = shift << LG_SIZE_CLASS_GROUP; + szind_t shift = (x < SC_LG_NGROUP + LG_QUANTUM) ? 0 : + x - (SC_LG_NGROUP + LG_QUANTUM); + szind_t grp = shift << SC_LG_NGROUP; - szind_t lg_delta = (x < LG_SIZE_CLASS_GROUP + LG_QUANTUM + 1) - ? LG_QUANTUM : x - LG_SIZE_CLASS_GROUP - 1; + szind_t lg_delta = (x < SC_LG_NGROUP + LG_QUANTUM + 1) + ? LG_QUANTUM : x - SC_LG_NGROUP - 1; size_t delta_inverse_mask = ZU(-1) << lg_delta; szind_t mod = ((((size-1) & delta_inverse_mask) >> lg_delta)) & - ((ZU(1) << LG_SIZE_CLASS_GROUP) - 1); + ((ZU(1) << SC_LG_NGROUP) - 1); - szind_t index = NTBINS + grp + mod; + szind_t index = SC_NTINY + grp + mod; return index; } } JEMALLOC_ALWAYS_INLINE szind_t sz_size2index_lookup(size_t size) { - assert(size <= LOOKUP_MAXCLASS); - { - szind_t ret = (sz_size2index_tab[(size-1) >> LG_TINY_MIN]); - assert(ret == sz_size2index_compute(size)); - return ret; - } + assert(size <= SC_LOOKUP_MAXCLASS); + szind_t ret = (sz_size2index_tab[(size + (ZU(1) << SC_LG_TINY_MIN) - 1) + >> SC_LG_TINY_MIN]); + assert(ret == sz_size2index_compute(size)); + return ret; } JEMALLOC_ALWAYS_INLINE szind_t sz_size2index(size_t size) { - assert(size > 0); - if (likely(size <= LOOKUP_MAXCLASS)) { + if (likely(size <= SC_LOOKUP_MAXCLASS)) { return sz_size2index_lookup(size); } return sz_size2index_compute(size); } static inline size_t sz_index2size_compute(szind_t index) { -#if (NTBINS > 0) - if (index < NTBINS) { - return (ZU(1) << (LG_TINY_MAXCLASS - NTBINS + 1 + index)); +#if (SC_NTINY > 0) + if (index < SC_NTINY) { + return (ZU(1) << (SC_LG_TINY_MAXCLASS - SC_NTINY + 1 + index)); } #endif { - size_t reduced_index = index - NTBINS; - size_t grp = reduced_index >> LG_SIZE_CLASS_GROUP; - size_t mod = reduced_index & ((ZU(1) << LG_SIZE_CLASS_GROUP) - + size_t reduced_index = index - SC_NTINY; + size_t grp = reduced_index >> SC_LG_NGROUP; + size_t mod = reduced_index & ((ZU(1) << SC_LG_NGROUP) - 1); size_t grp_size_mask = ~((!!grp)-1); size_t grp_size = ((ZU(1) << (LG_QUANTUM + - (LG_SIZE_CLASS_GROUP-1))) << grp) & grp_size_mask; + (SC_LG_NGROUP-1))) << grp) & grp_size_mask; size_t shift = (grp == 0) ? 1 : grp; size_t lg_delta = shift + (LG_QUANTUM-1); size_t mod_size = (mod+1) << lg_delta; size_t usize = grp_size + mod_size; return usize; } } JEMALLOC_ALWAYS_INLINE size_t sz_index2size_lookup(szind_t index) { size_t ret = (size_t)sz_index2size_tab[index]; assert(ret == sz_index2size_compute(index)); return ret; } JEMALLOC_ALWAYS_INLINE size_t sz_index2size(szind_t index) { - assert(index < NSIZES); + assert(index < SC_NSIZES); return sz_index2size_lookup(index); } JEMALLOC_ALWAYS_INLINE size_t sz_s2u_compute(size_t size) { - if (unlikely(size > LARGE_MAXCLASS)) { + if (unlikely(size > SC_LARGE_MAXCLASS)) { return 0; } -#if (NTBINS > 0) - if (size <= (ZU(1) << LG_TINY_MAXCLASS)) { - size_t lg_tmin = LG_TINY_MAXCLASS - NTBINS + 1; + + if (size == 0) { + size++; + } +#if (SC_NTINY > 0) + if (size <= (ZU(1) << SC_LG_TINY_MAXCLASS)) { + size_t lg_tmin = SC_LG_TINY_MAXCLASS - SC_NTINY + 1; size_t lg_ceil = lg_floor(pow2_ceil_zu(size)); return (lg_ceil < lg_tmin ? (ZU(1) << lg_tmin) : (ZU(1) << lg_ceil)); } #endif { size_t x = lg_floor((size<<1)-1); - size_t lg_delta = (x < LG_SIZE_CLASS_GROUP + LG_QUANTUM + 1) - ? LG_QUANTUM : x - LG_SIZE_CLASS_GROUP - 1; + size_t lg_delta = (x < SC_LG_NGROUP + LG_QUANTUM + 1) + ? LG_QUANTUM : x - SC_LG_NGROUP - 1; size_t delta = ZU(1) << lg_delta; size_t delta_mask = delta - 1; size_t usize = (size + delta_mask) & ~delta_mask; return usize; } } JEMALLOC_ALWAYS_INLINE size_t sz_s2u_lookup(size_t size) { size_t ret = sz_index2size_lookup(sz_size2index_lookup(size)); assert(ret == sz_s2u_compute(size)); return ret; } /* * Compute usable size that would result from allocating an object with the * specified size. */ JEMALLOC_ALWAYS_INLINE size_t sz_s2u(size_t size) { - assert(size > 0); - if (likely(size <= LOOKUP_MAXCLASS)) { + if (likely(size <= SC_LOOKUP_MAXCLASS)) { return sz_s2u_lookup(size); } return sz_s2u_compute(size); } /* * Compute usable size that would result from allocating an object with the * specified size and alignment. */ JEMALLOC_ALWAYS_INLINE size_t sz_sa2u(size_t size, size_t alignment) { size_t usize; assert(alignment != 0 && ((alignment - 1) & alignment) == 0); /* Try for a small size class. */ - if (size <= SMALL_MAXCLASS && alignment < PAGE) { + if (size <= SC_SMALL_MAXCLASS && alignment < PAGE) { /* * Round size up to the nearest multiple of alignment. * * This done, we can take advantage of the fact that for each * small size class, every object is aligned at the smallest * power of two that is non-zero in the base two representation * of the size. For example: * * Size | Base 2 | Minimum alignment * -----+----------+------------------ * 96 | 1100000 | 32 * 144 | 10100000 | 32 * 192 | 11000000 | 64 */ usize = sz_s2u(ALIGNMENT_CEILING(size, alignment)); - if (usize < LARGE_MINCLASS) { + if (usize < SC_LARGE_MINCLASS) { return usize; } } /* Large size class. Beware of overflow. */ - if (unlikely(alignment > LARGE_MAXCLASS)) { + if (unlikely(alignment > SC_LARGE_MAXCLASS)) { return 0; } /* Make sure result is a large size class. */ - if (size <= LARGE_MINCLASS) { - usize = LARGE_MINCLASS; + if (size <= SC_LARGE_MINCLASS) { + usize = SC_LARGE_MINCLASS; } else { usize = sz_s2u(size); if (usize < size) { /* size_t overflow. */ return 0; } } /* * Calculate the multi-page mapping that large_palloc() would need in * order to guarantee the alignment. */ if (usize + sz_large_pad + PAGE_CEILING(alignment) - PAGE < usize) { /* size_t overflow. */ return 0; } return usize; } #endif /* JEMALLOC_INTERNAL_SIZE_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/tcache_externs.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/tcache_externs.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/tcache_externs.h (revision 360233) @@ -1,55 +1,53 @@ #ifndef JEMALLOC_INTERNAL_TCACHE_EXTERNS_H #define JEMALLOC_INTERNAL_TCACHE_EXTERNS_H -#include "jemalloc/internal/size_classes.h" - extern bool opt_tcache; extern ssize_t opt_lg_tcache_max; extern cache_bin_info_t *tcache_bin_info; /* - * Number of tcache bins. There are NBINS small-object bins, plus 0 or more + * Number of tcache bins. There are SC_NBINS small-object bins, plus 0 or more * large-object bins. */ extern unsigned nhbins; /* Maximum cached size class. */ extern size_t tcache_maxclass; /* * Explicit tcaches, managed via the tcache.{create,flush,destroy} mallctls and * usable via the MALLOCX_TCACHE() flag. The automatic per thread tcaches are * completely disjoint from this data structure. tcaches starts off as a sparse * array, so it has no physical memory footprint until individual pages are * touched. This allows the entire array to be allocated the first time an * explicit tcache is created without a disproportionate impact on memory usage. */ extern tcaches_t *tcaches; size_t tcache_salloc(tsdn_t *tsdn, const void *ptr); void tcache_event_hard(tsd_t *tsd, tcache_t *tcache); void *tcache_alloc_small_hard(tsdn_t *tsdn, arena_t *arena, tcache_t *tcache, cache_bin_t *tbin, szind_t binind, bool *tcache_success); void tcache_bin_flush_small(tsd_t *tsd, tcache_t *tcache, cache_bin_t *tbin, szind_t binind, unsigned rem); void tcache_bin_flush_large(tsd_t *tsd, cache_bin_t *tbin, szind_t binind, unsigned rem, tcache_t *tcache); void tcache_arena_reassociate(tsdn_t *tsdn, tcache_t *tcache, arena_t *arena); tcache_t *tcache_create_explicit(tsd_t *tsd); void tcache_cleanup(tsd_t *tsd); void tcache_stats_merge(tsdn_t *tsdn, tcache_t *tcache, arena_t *arena); bool tcaches_create(tsd_t *tsd, unsigned *r_ind); void tcaches_flush(tsd_t *tsd, unsigned ind); void tcaches_destroy(tsd_t *tsd, unsigned ind); bool tcache_boot(tsdn_t *tsdn); void tcache_arena_associate(tsdn_t *tsdn, tcache_t *tcache, arena_t *arena); void tcache_prefork(tsdn_t *tsdn); void tcache_postfork_parent(tsdn_t *tsdn); void tcache_postfork_child(tsdn_t *tsdn); void tcache_flush(tsd_t *tsd); bool tsd_tcache_data_init(tsd_t *tsd); bool tsd_tcache_enabled_data_init(tsd_t *tsd); #endif /* JEMALLOC_INTERNAL_TCACHE_EXTERNS_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/tcache_inlines.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/tcache_inlines.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/tcache_inlines.h (revision 360233) @@ -1,223 +1,227 @@ #ifndef JEMALLOC_INTERNAL_TCACHE_INLINES_H #define JEMALLOC_INTERNAL_TCACHE_INLINES_H #include "jemalloc/internal/bin.h" #include "jemalloc/internal/jemalloc_internal_types.h" -#include "jemalloc/internal/size_classes.h" +#include "jemalloc/internal/sc.h" #include "jemalloc/internal/sz.h" #include "jemalloc/internal/ticker.h" #include "jemalloc/internal/util.h" static inline bool tcache_enabled_get(tsd_t *tsd) { return tsd_tcache_enabled_get(tsd); } static inline void tcache_enabled_set(tsd_t *tsd, bool enabled) { bool was_enabled = tsd_tcache_enabled_get(tsd); if (!was_enabled && enabled) { tsd_tcache_data_init(tsd); } else if (was_enabled && !enabled) { tcache_cleanup(tsd); } /* Commit the state last. Above calls check current state. */ tsd_tcache_enabled_set(tsd, enabled); tsd_slow_update(tsd); } JEMALLOC_ALWAYS_INLINE void tcache_event(tsd_t *tsd, tcache_t *tcache) { if (TCACHE_GC_INCR == 0) { return; } if (unlikely(ticker_tick(&tcache->gc_ticker))) { tcache_event_hard(tsd, tcache); } } JEMALLOC_ALWAYS_INLINE void * tcache_alloc_small(tsd_t *tsd, arena_t *arena, tcache_t *tcache, - UNUSED size_t size, szind_t binind, bool zero, bool slow_path) { + size_t size, szind_t binind, bool zero, bool slow_path) { void *ret; cache_bin_t *bin; bool tcache_success; size_t usize JEMALLOC_CC_SILENCE_INIT(0); - assert(binind < NBINS); + assert(binind < SC_NBINS); bin = tcache_small_bin_get(tcache, binind); ret = cache_bin_alloc_easy(bin, &tcache_success); assert(tcache_success == (ret != NULL)); if (unlikely(!tcache_success)) { bool tcache_hard_success; arena = arena_choose(tsd, arena); if (unlikely(arena == NULL)) { return NULL; } ret = tcache_alloc_small_hard(tsd_tsdn(tsd), arena, tcache, bin, binind, &tcache_hard_success); if (tcache_hard_success == false) { return NULL; } } assert(ret); /* * Only compute usize if required. The checks in the following if * statement are all static. */ if (config_prof || (slow_path && config_fill) || unlikely(zero)) { usize = sz_index2size(binind); assert(tcache_salloc(tsd_tsdn(tsd), ret) == usize); } if (likely(!zero)) { if (slow_path && config_fill) { if (unlikely(opt_junk_alloc)) { arena_alloc_junk_small(ret, &bin_infos[binind], false); } else if (unlikely(opt_zero)) { memset(ret, 0, usize); } } } else { if (slow_path && config_fill && unlikely(opt_junk_alloc)) { arena_alloc_junk_small(ret, &bin_infos[binind], true); } memset(ret, 0, usize); } if (config_stats) { bin->tstats.nrequests++; } if (config_prof) { tcache->prof_accumbytes += usize; } tcache_event(tsd, tcache); return ret; } JEMALLOC_ALWAYS_INLINE void * tcache_alloc_large(tsd_t *tsd, arena_t *arena, tcache_t *tcache, size_t size, szind_t binind, bool zero, bool slow_path) { void *ret; cache_bin_t *bin; bool tcache_success; - assert(binind >= NBINS &&binind < nhbins); + assert(binind >= SC_NBINS &&binind < nhbins); bin = tcache_large_bin_get(tcache, binind); ret = cache_bin_alloc_easy(bin, &tcache_success); assert(tcache_success == (ret != NULL)); if (unlikely(!tcache_success)) { /* * Only allocate one large object at a time, because it's quite * expensive to create one and not use it. */ arena = arena_choose(tsd, arena); if (unlikely(arena == NULL)) { return NULL; } ret = large_malloc(tsd_tsdn(tsd), arena, sz_s2u(size), zero); if (ret == NULL) { return NULL; } } else { size_t usize JEMALLOC_CC_SILENCE_INIT(0); /* Only compute usize on demand */ if (config_prof || (slow_path && config_fill) || unlikely(zero)) { usize = sz_index2size(binind); assert(usize <= tcache_maxclass); } if (likely(!zero)) { if (slow_path && config_fill) { if (unlikely(opt_junk_alloc)) { memset(ret, JEMALLOC_ALLOC_JUNK, usize); } else if (unlikely(opt_zero)) { memset(ret, 0, usize); } } } else { memset(ret, 0, usize); } if (config_stats) { bin->tstats.nrequests++; } if (config_prof) { tcache->prof_accumbytes += usize; } } tcache_event(tsd, tcache); return ret; } JEMALLOC_ALWAYS_INLINE void tcache_dalloc_small(tsd_t *tsd, tcache_t *tcache, void *ptr, szind_t binind, bool slow_path) { cache_bin_t *bin; cache_bin_info_t *bin_info; - assert(tcache_salloc(tsd_tsdn(tsd), ptr) <= SMALL_MAXCLASS); + assert(tcache_salloc(tsd_tsdn(tsd), ptr) + <= SC_SMALL_MAXCLASS); if (slow_path && config_fill && unlikely(opt_junk_free)) { arena_dalloc_junk_small(ptr, &bin_infos[binind]); } bin = tcache_small_bin_get(tcache, binind); bin_info = &tcache_bin_info[binind]; - if (unlikely(bin->ncached == bin_info->ncached_max)) { + if (unlikely(!cache_bin_dalloc_easy(bin, bin_info, ptr))) { tcache_bin_flush_small(tsd, tcache, bin, binind, (bin_info->ncached_max >> 1)); + bool ret = cache_bin_dalloc_easy(bin, bin_info, ptr); + assert(ret); } - assert(bin->ncached < bin_info->ncached_max); - bin->ncached++; - *(bin->avail - bin->ncached) = ptr; tcache_event(tsd, tcache); } JEMALLOC_ALWAYS_INLINE void tcache_dalloc_large(tsd_t *tsd, tcache_t *tcache, void *ptr, szind_t binind, bool slow_path) { cache_bin_t *bin; cache_bin_info_t *bin_info; - assert(tcache_salloc(tsd_tsdn(tsd), ptr) > SMALL_MAXCLASS); + assert(tcache_salloc(tsd_tsdn(tsd), ptr) + > SC_SMALL_MAXCLASS); assert(tcache_salloc(tsd_tsdn(tsd), ptr) <= tcache_maxclass); if (slow_path && config_fill && unlikely(opt_junk_free)) { large_dalloc_junk(ptr, sz_index2size(binind)); } bin = tcache_large_bin_get(tcache, binind); bin_info = &tcache_bin_info[binind]; if (unlikely(bin->ncached == bin_info->ncached_max)) { tcache_bin_flush_large(tsd, bin, binind, (bin_info->ncached_max >> 1), tcache); } assert(bin->ncached < bin_info->ncached_max); bin->ncached++; *(bin->avail - bin->ncached) = ptr; tcache_event(tsd, tcache); } JEMALLOC_ALWAYS_INLINE tcache_t * tcaches_get(tsd_t *tsd, unsigned ind) { tcaches_t *elm = &tcaches[ind]; if (unlikely(elm->tcache == NULL)) { + malloc_printf(": invalid tcache id (%u).\n", ind); + abort(); + } else if (unlikely(elm->tcache == TCACHES_ELM_NEED_REINIT)) { elm->tcache = tcache_create_explicit(tsd); } return elm->tcache; } #endif /* JEMALLOC_INTERNAL_TCACHE_INLINES_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/tcache_structs.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/tcache_structs.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/tcache_structs.h (revision 360233) @@ -1,61 +1,70 @@ #ifndef JEMALLOC_INTERNAL_TCACHE_STRUCTS_H #define JEMALLOC_INTERNAL_TCACHE_STRUCTS_H -#include "jemalloc/internal/ql.h" -#include "jemalloc/internal/size_classes.h" #include "jemalloc/internal/cache_bin.h" +#include "jemalloc/internal/ql.h" +#include "jemalloc/internal/sc.h" #include "jemalloc/internal/ticker.h" +#include "jemalloc/internal/tsd_types.h" +/* Various uses of this struct need it to be a named type. */ +typedef ql_elm(tsd_t) tsd_link_t; + struct tcache_s { /* * To minimize our cache-footprint, we put the frequently accessed data * together at the start of this struct. */ /* Cleared after arena_prof_accum(). */ uint64_t prof_accumbytes; /* Drives incremental GC. */ ticker_t gc_ticker; /* * The pointer stacks associated with bins follow as a contiguous array. * During tcache initialization, the avail pointer in each element of * tbins is initialized to point to the proper offset within this array. */ - cache_bin_t bins_small[NBINS]; + cache_bin_t bins_small[SC_NBINS]; /* * This data is less hot; we can be a little less careful with our * footprint here. */ /* Lets us track all the tcaches in an arena. */ ql_elm(tcache_t) link; + + /* Logically scoped to tsd, but put here for cache layout reasons. */ + ql_elm(tsd_t) tsd_link; + bool in_hook; + /* * The descriptor lets the arena find our cache bins without seeing the * tcache definition. This enables arenas to aggregate stats across * tcaches without having a tcache dependency. */ cache_bin_array_descriptor_t cache_bin_array_descriptor; /* The arena this tcache is associated with. */ arena_t *arena; /* Next bin to GC. */ szind_t next_gc_bin; /* For small bins, fill (ncached_max >> lg_fill_div). */ - uint8_t lg_fill_div[NBINS]; + uint8_t lg_fill_div[SC_NBINS]; /* * We put the cache bins for large size classes at the end of the * struct, since some of them might not get used. This might end up * letting us avoid touching an extra page if we don't have to. */ - cache_bin_t bins_large[NSIZES-NBINS]; + cache_bin_t bins_large[SC_NSIZES-SC_NBINS]; }; /* Linkage for list of available (previously used) explicit tcache IDs. */ struct tcaches_s { union { tcache_t *tcache; tcaches_t *next; }; }; #endif /* JEMALLOC_INTERNAL_TCACHE_STRUCTS_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/tcache_types.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/tcache_types.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/tcache_types.h (revision 360233) @@ -1,56 +1,59 @@ #ifndef JEMALLOC_INTERNAL_TCACHE_TYPES_H #define JEMALLOC_INTERNAL_TCACHE_TYPES_H -#include "jemalloc/internal/size_classes.h" +#include "jemalloc/internal/sc.h" typedef struct tcache_s tcache_t; typedef struct tcaches_s tcaches_t; /* * tcache pointers close to NULL are used to encode state information that is * used for two purposes: preventing thread caching on a per thread basis and * cleaning up during thread shutdown. */ #define TCACHE_STATE_DISABLED ((tcache_t *)(uintptr_t)1) #define TCACHE_STATE_REINCARNATED ((tcache_t *)(uintptr_t)2) #define TCACHE_STATE_PURGATORY ((tcache_t *)(uintptr_t)3) #define TCACHE_STATE_MAX TCACHE_STATE_PURGATORY /* * Absolute minimum number of cache slots for each small bin. */ #define TCACHE_NSLOTS_SMALL_MIN 20 /* * Absolute maximum number of cache slots for each small bin in the thread * cache. This is an additional constraint beyond that imposed as: twice the * number of regions per slab for this size class. * * This constant must be an even number. */ #define TCACHE_NSLOTS_SMALL_MAX 200 /* Number of cache slots for large size classes. */ #define TCACHE_NSLOTS_LARGE 20 /* (1U << opt_lg_tcache_max) is used to compute tcache_maxclass. */ #define LG_TCACHE_MAXCLASS_DEFAULT 15 /* * TCACHE_GC_SWEEP is the approximate number of allocation events between * full GC sweeps. Integer rounding may cause the actual number to be * slightly higher, since GC is performed incrementally. */ #define TCACHE_GC_SWEEP 8192 /* Number of tcache allocation/deallocation events between incremental GCs. */ #define TCACHE_GC_INCR \ - ((TCACHE_GC_SWEEP / NBINS) + ((TCACHE_GC_SWEEP / NBINS == 0) ? 0 : 1)) + ((TCACHE_GC_SWEEP / SC_NBINS) + ((TCACHE_GC_SWEEP / SC_NBINS == 0) ? 0 : 1)) /* Used in TSD static initializer only. Real init in tcache_data_init(). */ #define TCACHE_ZERO_INITIALIZER {0} /* Used in TSD static initializer only. Will be initialized to opt_tcache. */ #define TCACHE_ENABLED_ZERO_INITIALIZER false + +/* Used for explicit tcache only. Means flushed but not destroyed. */ +#define TCACHES_ELM_NEED_REINIT ((tcache_t *)(uintptr_t)1) #endif /* JEMALLOC_INTERNAL_TCACHE_TYPES_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/test_hooks.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/test_hooks.h (nonexistent) +++ head/contrib/jemalloc/include/jemalloc/internal/test_hooks.h (revision 360233) @@ -0,0 +1,12 @@ +#ifndef JEMALLOC_INTERNAL_TEST_HOOKS_H +#define JEMALLOC_INTERNAL_TEST_HOOKS_H + +extern JEMALLOC_EXPORT void (*test_hooks_arena_new_hook)(); +extern JEMALLOC_EXPORT void (*test_hooks_libc_hook)(); + +#define JEMALLOC_HOOK(fn, hook) ((void)(hook != NULL && (hook(), 0)), fn) + +/* Note that this is undef'd and re-define'd in src/prof.c. */ +#define _Unwind_Backtrace JEMALLOC_HOOK(_Unwind_Backtrace, test_hooks_libc_hook) + +#endif /* JEMALLOC_INTERNAL_TEST_HOOKS_H */ Property changes on: head/contrib/jemalloc/include/jemalloc/internal/test_hooks.h ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/jemalloc/include/jemalloc/internal/ticker.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/ticker.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/ticker.h (revision 360233) @@ -1,78 +1,91 @@ #ifndef JEMALLOC_INTERNAL_TICKER_H #define JEMALLOC_INTERNAL_TICKER_H #include "jemalloc/internal/util.h" /** * A ticker makes it easy to count-down events until some limit. You * ticker_init the ticker to trigger every nticks events. You then notify it * that an event has occurred with calls to ticker_tick (or that nticks events * have occurred with a call to ticker_ticks), which will return true (and reset * the counter) if the countdown hit zero. */ typedef struct { int32_t tick; int32_t nticks; } ticker_t; static inline void ticker_init(ticker_t *ticker, int32_t nticks) { ticker->tick = nticks; ticker->nticks = nticks; } static inline void ticker_copy(ticker_t *ticker, const ticker_t *other) { *ticker = *other; } static inline int32_t ticker_read(const ticker_t *ticker) { return ticker->tick; } /* * Not intended to be a public API. Unfortunately, on x86, neither gcc nor * clang seems smart enough to turn * ticker->tick -= nticks; * if (unlikely(ticker->tick < 0)) { * fixup ticker * return true; * } * return false; * into * subq %nticks_reg, (%ticker_reg) * js fixup ticker * * unless we force "fixup ticker" out of line. In that case, gcc gets it right, * but clang now does worse than before. So, on x86 with gcc, we force it out * of line, but otherwise let the inlining occur. Ordinarily this wouldn't be * worth the hassle, but this is on the fast path of both malloc and free (via * tcache_event). */ #if defined(__GNUC__) && !defined(__clang__) \ && (defined(__x86_64__) || defined(__i386__)) JEMALLOC_NOINLINE #endif static bool ticker_fixup(ticker_t *ticker) { ticker->tick = ticker->nticks; return true; } static inline bool ticker_ticks(ticker_t *ticker, int32_t nticks) { ticker->tick -= nticks; if (unlikely(ticker->tick < 0)) { return ticker_fixup(ticker); } return false; } static inline bool ticker_tick(ticker_t *ticker) { return ticker_ticks(ticker, 1); } +/* + * Try to tick. If ticker would fire, return true, but rely on + * slowpath to reset ticker. + */ +static inline bool +ticker_trytick(ticker_t *ticker) { + --ticker->tick; + if (unlikely(ticker->tick < 0)) { + return true; + } + return false; +} + #endif /* JEMALLOC_INTERNAL_TICKER_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/tsd.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/tsd.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/tsd.h (revision 360233) @@ -1,327 +1,416 @@ #ifndef JEMALLOC_INTERNAL_TSD_H #define JEMALLOC_INTERNAL_TSD_H #include "jemalloc/internal/arena_types.h" #include "jemalloc/internal/assert.h" +#include "jemalloc/internal/bin_types.h" #include "jemalloc/internal/jemalloc_internal_externs.h" #include "jemalloc/internal/prof_types.h" #include "jemalloc/internal/ql.h" #include "jemalloc/internal/rtree_tsd.h" #include "jemalloc/internal/tcache_types.h" #include "jemalloc/internal/tcache_structs.h" #include "jemalloc/internal/util.h" #include "jemalloc/internal/witness.h" /* * Thread-Specific-Data layout * --- data accessed on tcache fast path: state, rtree_ctx, stats, prof --- * s: state * e: tcache_enabled * m: thread_allocated (config_stats) * f: thread_deallocated (config_stats) * p: prof_tdata (config_prof) * c: rtree_ctx (rtree cache accessed on deallocation) * t: tcache * --- data not accessed on tcache fast path: arena-related fields --- * d: arenas_tdata_bypass * r: reentrancy_level * x: narenas_tdata * i: iarena * a: arena * o: arenas_tdata * Loading TSD data is on the critical path of basically all malloc operations. * In particular, tcache and rtree_ctx rely on hot CPU cache to be effective. * Use a compact layout to reduce cache footprint. * +--- 64-bit and 64B cacheline; 1B each letter; First byte on the left. ---+ * |---------------------------- 1st cacheline ----------------------------| * | sedrxxxx mmmmmmmm ffffffff pppppppp [c * 32 ........ ........ .......] | * |---------------------------- 2nd cacheline ----------------------------| * | [c * 64 ........ ........ ........ ........ ........ ........ .......] | * |---------------------------- 3nd cacheline ----------------------------| * | [c * 32 ........ ........ .......] iiiiiiii aaaaaaaa oooooooo [t...... | * +-------------------------------------------------------------------------+ * Note: the entire tcache is embedded into TSD and spans multiple cachelines. * * The last 3 members (i, a and o) before tcache isn't really needed on tcache * fast path. However we have a number of unused tcache bins and witnesses * (never touched unless config_debug) at the end of tcache, so we place them * there to avoid breaking the cachelines and possibly paging in an extra page. */ #ifdef JEMALLOC_JET typedef void (*test_callback_t)(int *); # define MALLOC_TSD_TEST_DATA_INIT 0x72b65c10 # define MALLOC_TEST_TSD \ O(test_data, int, int) \ O(test_callback, test_callback_t, int) # define MALLOC_TEST_TSD_INITIALIZER , MALLOC_TSD_TEST_DATA_INIT, NULL #else # define MALLOC_TEST_TSD # define MALLOC_TEST_TSD_INITIALIZER #endif /* O(name, type, nullable type */ #define MALLOC_TSD \ O(tcache_enabled, bool, bool) \ O(arenas_tdata_bypass, bool, bool) \ O(reentrancy_level, int8_t, int8_t) \ O(narenas_tdata, uint32_t, uint32_t) \ O(offset_state, uint64_t, uint64_t) \ O(thread_allocated, uint64_t, uint64_t) \ O(thread_deallocated, uint64_t, uint64_t) \ + O(bytes_until_sample, int64_t, int64_t) \ O(prof_tdata, prof_tdata_t *, prof_tdata_t *) \ O(rtree_ctx, rtree_ctx_t, rtree_ctx_t) \ O(iarena, arena_t *, arena_t *) \ O(arena, arena_t *, arena_t *) \ O(arenas_tdata, arena_tdata_t *, arena_tdata_t *)\ + O(binshards, tsd_binshards_t, tsd_binshards_t)\ O(tcache, tcache_t, tcache_t) \ O(witness_tsd, witness_tsd_t, witness_tsdn_t) \ MALLOC_TEST_TSD #define TSD_INITIALIZER { \ - tsd_state_uninitialized, \ + ATOMIC_INIT(tsd_state_uninitialized), \ TCACHE_ENABLED_ZERO_INITIALIZER, \ false, \ 0, \ 0, \ 0, \ 0, \ 0, \ + 0, \ NULL, \ RTREE_CTX_ZERO_INITIALIZER, \ NULL, \ NULL, \ NULL, \ + TSD_BINSHARDS_ZERO_INITIALIZER, \ TCACHE_ZERO_INITIALIZER, \ WITNESS_TSD_INITIALIZER \ MALLOC_TEST_TSD_INITIALIZER \ } +void *malloc_tsd_malloc(size_t size); +void malloc_tsd_dalloc(void *wrapper); +void malloc_tsd_cleanup_register(bool (*f)(void)); +tsd_t *malloc_tsd_boot0(void); +void malloc_tsd_boot1(void); +void tsd_cleanup(void *arg); +tsd_t *tsd_fetch_slow(tsd_t *tsd, bool internal); +void tsd_state_set(tsd_t *tsd, uint8_t new_state); +void tsd_slow_update(tsd_t *tsd); +void tsd_prefork(tsd_t *tsd); +void tsd_postfork_parent(tsd_t *tsd); +void tsd_postfork_child(tsd_t *tsd); + +/* + * Call ..._inc when your module wants to take all threads down the slow paths, + * and ..._dec when it no longer needs to. + */ +void tsd_global_slow_inc(tsdn_t *tsdn); +void tsd_global_slow_dec(tsdn_t *tsdn); +bool tsd_global_slow(); + enum { - tsd_state_nominal = 0, /* Common case --> jnz. */ - tsd_state_nominal_slow = 1, /* Initialized but on slow path. */ - /* the above 2 nominal states should be lower values. */ - tsd_state_nominal_max = 1, /* used for comparison only. */ - tsd_state_minimal_initialized = 2, - tsd_state_purgatory = 3, - tsd_state_reincarnated = 4, - tsd_state_uninitialized = 5 + /* Common case --> jnz. */ + tsd_state_nominal = 0, + /* Initialized but on slow path. */ + tsd_state_nominal_slow = 1, + /* + * Some thread has changed global state in such a way that all nominal + * threads need to recompute their fast / slow status the next time they + * get a chance. + * + * Any thread can change another thread's status *to* recompute, but + * threads are the only ones who can change their status *from* + * recompute. + */ + tsd_state_nominal_recompute = 2, + /* + * The above nominal states should be lower values. We use + * tsd_nominal_max to separate nominal states from threads in the + * process of being born / dying. + */ + tsd_state_nominal_max = 2, + + /* + * A thread might free() during its death as its only allocator action; + * in such scenarios, we need tsd, but set up in such a way that no + * cleanup is necessary. + */ + tsd_state_minimal_initialized = 3, + /* States during which we know we're in thread death. */ + tsd_state_purgatory = 4, + tsd_state_reincarnated = 5, + /* + * What it says on the tin; tsd that hasn't been initialized. Note + * that even when the tsd struct lives in TLS, when need to keep track + * of stuff like whether or not our pthread destructors have been + * scheduled, so this really truly is different than the nominal state. + */ + tsd_state_uninitialized = 6 }; -/* Manually limit tsd_state_t to a single byte. */ -typedef uint8_t tsd_state_t; +/* + * Some TSD accesses can only be done in a nominal state. To enforce this, we + * wrap TSD member access in a function that asserts on TSD state, and mangle + * field names to prevent touching them accidentally. + */ +#define TSD_MANGLE(n) cant_access_tsd_items_directly_use_a_getter_or_setter_##n +#ifdef JEMALLOC_U8_ATOMICS +# define tsd_state_t atomic_u8_t +# define tsd_atomic_load atomic_load_u8 +# define tsd_atomic_store atomic_store_u8 +# define tsd_atomic_exchange atomic_exchange_u8 +#else +# define tsd_state_t atomic_u32_t +# define tsd_atomic_load atomic_load_u32 +# define tsd_atomic_store atomic_store_u32 +# define tsd_atomic_exchange atomic_exchange_u32 +#endif + /* The actual tsd. */ struct tsd_s { /* * The contents should be treated as totally opaque outside the tsd * module. Access any thread-local state through the getters and * setters below. */ - tsd_state_t state; + + /* + * We manually limit the state to just a single byte. Unless the 8-bit + * atomics are unavailable (which is rare). + */ + tsd_state_t state; #define O(n, t, nt) \ - t use_a_getter_or_setter_instead_##n; + t TSD_MANGLE(n); MALLOC_TSD #undef O /* AddressSanitizer requires TLS data to be aligned to at least 8 bytes. */ } JEMALLOC_ALIGNED(16); +JEMALLOC_ALWAYS_INLINE uint8_t +tsd_state_get(tsd_t *tsd) { + /* + * This should be atomic. Unfortunately, compilers right now can't tell + * that this can be done as a memory comparison, and forces a load into + * a register that hurts fast-path performance. + */ + /* return atomic_load_u8(&tsd->state, ATOMIC_RELAXED); */ + return *(uint8_t *)&tsd->state; +} + /* * Wrapper around tsd_t that makes it possible to avoid implicit conversion * between tsd_t and tsdn_t, where tsdn_t is "nullable" and has to be * explicitly converted to tsd_t, which is non-nullable. */ struct tsdn_s { tsd_t tsd; }; #define TSDN_NULL ((tsdn_t *)0) JEMALLOC_ALWAYS_INLINE tsdn_t * tsd_tsdn(tsd_t *tsd) { return (tsdn_t *)tsd; } JEMALLOC_ALWAYS_INLINE bool tsdn_null(const tsdn_t *tsdn) { return tsdn == NULL; } JEMALLOC_ALWAYS_INLINE tsd_t * tsdn_tsd(tsdn_t *tsdn) { assert(!tsdn_null(tsdn)); return &tsdn->tsd; } -void *malloc_tsd_malloc(size_t size); -void malloc_tsd_dalloc(void *wrapper); -void malloc_tsd_cleanup_register(bool (*f)(void)); -tsd_t *malloc_tsd_boot0(void); -void malloc_tsd_boot1(void); -void tsd_cleanup(void *arg); -tsd_t *tsd_fetch_slow(tsd_t *tsd, bool internal); -void tsd_slow_update(tsd_t *tsd); - /* * We put the platform-specific data declarations and inlines into their own * header files to avoid cluttering this file. They define tsd_boot0, * tsd_boot1, tsd_boot, tsd_booted_get, tsd_get_allocates, tsd_get, and tsd_set. */ #ifdef JEMALLOC_MALLOC_THREAD_CLEANUP #include "jemalloc/internal/tsd_malloc_thread_cleanup.h" #elif (defined(JEMALLOC_TLS)) #include "jemalloc/internal/tsd_tls.h" #elif (defined(_WIN32)) #include "jemalloc/internal/tsd_win.h" #else #include "jemalloc/internal/tsd_generic.h" #endif /* * tsd_foop_get_unsafe(tsd) returns a pointer to the thread-local instance of * foo. This omits some safety checks, and so can be used during tsd * initialization and cleanup. */ #define O(n, t, nt) \ JEMALLOC_ALWAYS_INLINE t * \ tsd_##n##p_get_unsafe(tsd_t *tsd) { \ - return &tsd->use_a_getter_or_setter_instead_##n; \ + return &tsd->TSD_MANGLE(n); \ } MALLOC_TSD #undef O /* tsd_foop_get(tsd) returns a pointer to the thread-local instance of foo. */ #define O(n, t, nt) \ JEMALLOC_ALWAYS_INLINE t * \ tsd_##n##p_get(tsd_t *tsd) { \ - assert(tsd->state == tsd_state_nominal || \ - tsd->state == tsd_state_nominal_slow || \ - tsd->state == tsd_state_reincarnated || \ - tsd->state == tsd_state_minimal_initialized); \ + /* \ + * Because the state might change asynchronously if it's \ + * nominal, we need to make sure that we only read it once. \ + */ \ + uint8_t state = tsd_state_get(tsd); \ + assert(state == tsd_state_nominal || \ + state == tsd_state_nominal_slow || \ + state == tsd_state_nominal_recompute || \ + state == tsd_state_reincarnated || \ + state == tsd_state_minimal_initialized); \ return tsd_##n##p_get_unsafe(tsd); \ } MALLOC_TSD #undef O /* * tsdn_foop_get(tsdn) returns either the thread-local instance of foo (if tsdn * isn't NULL), or NULL (if tsdn is NULL), cast to the nullable pointer type. */ #define O(n, t, nt) \ JEMALLOC_ALWAYS_INLINE nt * \ tsdn_##n##p_get(tsdn_t *tsdn) { \ if (tsdn_null(tsdn)) { \ return NULL; \ } \ tsd_t *tsd = tsdn_tsd(tsdn); \ return (nt *)tsd_##n##p_get(tsd); \ } MALLOC_TSD #undef O /* tsd_foo_get(tsd) returns the value of the thread-local instance of foo. */ #define O(n, t, nt) \ JEMALLOC_ALWAYS_INLINE t \ tsd_##n##_get(tsd_t *tsd) { \ return *tsd_##n##p_get(tsd); \ } MALLOC_TSD #undef O /* tsd_foo_set(tsd, val) updates the thread-local instance of foo to be val. */ #define O(n, t, nt) \ JEMALLOC_ALWAYS_INLINE void \ tsd_##n##_set(tsd_t *tsd, t val) { \ - assert(tsd->state != tsd_state_reincarnated && \ - tsd->state != tsd_state_minimal_initialized); \ + assert(tsd_state_get(tsd) != tsd_state_reincarnated && \ + tsd_state_get(tsd) != tsd_state_minimal_initialized); \ *tsd_##n##p_get(tsd) = val; \ } MALLOC_TSD #undef O JEMALLOC_ALWAYS_INLINE void tsd_assert_fast(tsd_t *tsd) { + /* + * Note that our fastness assertion does *not* include global slowness + * counters; it's not in general possible to ensure that they won't + * change asynchronously from underneath us. + */ assert(!malloc_slow && tsd_tcache_enabled_get(tsd) && tsd_reentrancy_level_get(tsd) == 0); } JEMALLOC_ALWAYS_INLINE bool tsd_fast(tsd_t *tsd) { - bool fast = (tsd->state == tsd_state_nominal); + bool fast = (tsd_state_get(tsd) == tsd_state_nominal); if (fast) { tsd_assert_fast(tsd); } return fast; } JEMALLOC_ALWAYS_INLINE tsd_t * tsd_fetch_impl(bool init, bool minimal) { tsd_t *tsd = tsd_get(init); if (!init && tsd_get_allocates() && tsd == NULL) { return NULL; } assert(tsd != NULL); - if (unlikely(tsd->state != tsd_state_nominal)) { + if (unlikely(tsd_state_get(tsd) != tsd_state_nominal)) { return tsd_fetch_slow(tsd, minimal); } assert(tsd_fast(tsd)); tsd_assert_fast(tsd); return tsd; } /* Get a minimal TSD that requires no cleanup. See comments in free(). */ JEMALLOC_ALWAYS_INLINE tsd_t * tsd_fetch_min(void) { return tsd_fetch_impl(true, true); } /* For internal background threads use only. */ JEMALLOC_ALWAYS_INLINE tsd_t * tsd_internal_fetch(void) { tsd_t *tsd = tsd_fetch_min(); /* Use reincarnated state to prevent full initialization. */ - tsd->state = tsd_state_reincarnated; + tsd_state_set(tsd, tsd_state_reincarnated); return tsd; } JEMALLOC_ALWAYS_INLINE tsd_t * tsd_fetch(void) { return tsd_fetch_impl(true, false); } static inline bool tsd_nominal(tsd_t *tsd) { - return (tsd->state <= tsd_state_nominal_max); + return (tsd_state_get(tsd) <= tsd_state_nominal_max); } JEMALLOC_ALWAYS_INLINE tsdn_t * tsdn_fetch(void) { if (!tsd_booted_get()) { return NULL; } return tsd_tsdn(tsd_fetch_impl(false, false)); } JEMALLOC_ALWAYS_INLINE rtree_ctx_t * tsd_rtree_ctx(tsd_t *tsd) { return tsd_rtree_ctxp_get(tsd); } JEMALLOC_ALWAYS_INLINE rtree_ctx_t * tsdn_rtree_ctx(tsdn_t *tsdn, rtree_ctx_t *fallback) { /* * If tsd cannot be accessed, initialize the fallback rtree_ctx and * return a pointer to it. */ if (unlikely(tsdn_null(tsdn))) { rtree_ctx_data_init(fallback); return fallback; } return tsd_rtree_ctx(tsdn_tsd(tsdn)); } #endif /* JEMALLOC_INTERNAL_TSD_H */ Index: head/contrib/jemalloc/include/jemalloc/internal/tsd_generic.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/tsd_generic.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/tsd_generic.h (revision 360233) @@ -1,157 +1,163 @@ #ifdef JEMALLOC_INTERNAL_TSD_GENERIC_H #error This file should be included only once, by tsd.h. #endif #define JEMALLOC_INTERNAL_TSD_GENERIC_H typedef struct tsd_init_block_s tsd_init_block_t; struct tsd_init_block_s { ql_elm(tsd_init_block_t) link; pthread_t thread; void *data; }; /* Defined in tsd.c, to allow the mutex headers to have tsd dependencies. */ typedef struct tsd_init_head_s tsd_init_head_t; typedef struct { bool initialized; tsd_t val; } tsd_wrapper_t; void *tsd_init_check_recursion(tsd_init_head_t *head, tsd_init_block_t *block); void tsd_init_finish(tsd_init_head_t *head, tsd_init_block_t *block); extern pthread_key_t tsd_tsd; extern tsd_init_head_t tsd_init_head; extern tsd_wrapper_t tsd_boot_wrapper; extern bool tsd_booted; /* Initialization/cleanup. */ JEMALLOC_ALWAYS_INLINE void tsd_cleanup_wrapper(void *arg) { tsd_wrapper_t *wrapper = (tsd_wrapper_t *)arg; if (wrapper->initialized) { wrapper->initialized = false; tsd_cleanup(&wrapper->val); if (wrapper->initialized) { /* Trigger another cleanup round. */ if (pthread_setspecific(tsd_tsd, (void *)wrapper) != 0) { malloc_write(": Error setting TSD\n"); if (opt_abort) { abort(); } } return; } } malloc_tsd_dalloc(wrapper); } JEMALLOC_ALWAYS_INLINE void tsd_wrapper_set(tsd_wrapper_t *wrapper) { if (pthread_setspecific(tsd_tsd, (void *)wrapper) != 0) { malloc_write(": Error setting TSD\n"); abort(); } } JEMALLOC_ALWAYS_INLINE tsd_wrapper_t * tsd_wrapper_get(bool init) { tsd_wrapper_t *wrapper = (tsd_wrapper_t *)pthread_getspecific(tsd_tsd); if (init && unlikely(wrapper == NULL)) { tsd_init_block_t block; wrapper = (tsd_wrapper_t *) tsd_init_check_recursion(&tsd_init_head, &block); if (wrapper) { return wrapper; } wrapper = (tsd_wrapper_t *) malloc_tsd_malloc(sizeof(tsd_wrapper_t)); block.data = (void *)wrapper; if (wrapper == NULL) { malloc_write(": Error allocating TSD\n"); abort(); } else { wrapper->initialized = false; + JEMALLOC_DIAGNOSTIC_PUSH + JEMALLOC_DIAGNOSTIC_IGNORE_MISSING_STRUCT_FIELD_INITIALIZERS tsd_t initializer = TSD_INITIALIZER; + JEMALLOC_DIAGNOSTIC_POP wrapper->val = initializer; } tsd_wrapper_set(wrapper); tsd_init_finish(&tsd_init_head, &block); } return wrapper; } JEMALLOC_ALWAYS_INLINE bool tsd_boot0(void) { if (pthread_key_create(&tsd_tsd, tsd_cleanup_wrapper) != 0) { return true; } tsd_wrapper_set(&tsd_boot_wrapper); tsd_booted = true; return false; } JEMALLOC_ALWAYS_INLINE void tsd_boot1(void) { tsd_wrapper_t *wrapper; wrapper = (tsd_wrapper_t *)malloc_tsd_malloc(sizeof(tsd_wrapper_t)); if (wrapper == NULL) { malloc_write(": Error allocating TSD\n"); abort(); } tsd_boot_wrapper.initialized = false; tsd_cleanup(&tsd_boot_wrapper.val); wrapper->initialized = false; + JEMALLOC_DIAGNOSTIC_PUSH + JEMALLOC_DIAGNOSTIC_IGNORE_MISSING_STRUCT_FIELD_INITIALIZERS tsd_t initializer = TSD_INITIALIZER; + JEMALLOC_DIAGNOSTIC_POP wrapper->val = initializer; tsd_wrapper_set(wrapper); } JEMALLOC_ALWAYS_INLINE bool tsd_boot(void) { if (tsd_boot0()) { return true; } tsd_boot1(); return false; } JEMALLOC_ALWAYS_INLINE bool tsd_booted_get(void) { return tsd_booted; } JEMALLOC_ALWAYS_INLINE bool tsd_get_allocates(void) { return true; } /* Get/set. */ JEMALLOC_ALWAYS_INLINE tsd_t * tsd_get(bool init) { tsd_wrapper_t *wrapper; assert(tsd_booted); wrapper = tsd_wrapper_get(init); if (tsd_get_allocates() && !init && wrapper == NULL) { return NULL; } return &wrapper->val; } JEMALLOC_ALWAYS_INLINE void tsd_set(tsd_t *val) { tsd_wrapper_t *wrapper; assert(tsd_booted); wrapper = tsd_wrapper_get(true); if (likely(&wrapper->val != val)) { wrapper->val = *(val); } wrapper->initialized = true; } Index: head/contrib/jemalloc/include/jemalloc/internal/tsd_malloc_thread_cleanup.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/tsd_malloc_thread_cleanup.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/tsd_malloc_thread_cleanup.h (revision 360233) @@ -1,60 +1,61 @@ #ifdef JEMALLOC_INTERNAL_TSD_MALLOC_THREAD_CLEANUP_H #error This file should be included only once, by tsd.h. #endif #define JEMALLOC_INTERNAL_TSD_MALLOC_THREAD_CLEANUP_H -extern __thread tsd_t tsd_tls; -extern __thread bool tsd_initialized; +#define JEMALLOC_TSD_TYPE_ATTR(type) __thread type JEMALLOC_TLS_MODEL + +extern JEMALLOC_TSD_TYPE_ATTR(tsd_t) tsd_tls; +extern JEMALLOC_TSD_TYPE_ATTR(bool) tsd_initialized; extern bool tsd_booted; /* Initialization/cleanup. */ JEMALLOC_ALWAYS_INLINE bool tsd_cleanup_wrapper(void) { if (tsd_initialized) { tsd_initialized = false; tsd_cleanup(&tsd_tls); } return tsd_initialized; } JEMALLOC_ALWAYS_INLINE bool tsd_boot0(void) { malloc_tsd_cleanup_register(&tsd_cleanup_wrapper); tsd_booted = true; return false; } JEMALLOC_ALWAYS_INLINE void tsd_boot1(void) { /* Do nothing. */ } JEMALLOC_ALWAYS_INLINE bool tsd_boot(void) { return tsd_boot0(); } JEMALLOC_ALWAYS_INLINE bool tsd_booted_get(void) { return tsd_booted; } JEMALLOC_ALWAYS_INLINE bool tsd_get_allocates(void) { return false; } /* Get/set. */ JEMALLOC_ALWAYS_INLINE tsd_t * tsd_get(bool init) { - assert(tsd_booted); return &tsd_tls; } JEMALLOC_ALWAYS_INLINE void tsd_set(tsd_t *val) { assert(tsd_booted); if (likely(&tsd_tls != val)) { tsd_tls = (*val); } tsd_initialized = true; } Index: head/contrib/jemalloc/include/jemalloc/internal/tsd_tls.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/tsd_tls.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/tsd_tls.h (revision 360233) @@ -1,59 +1,60 @@ #ifdef JEMALLOC_INTERNAL_TSD_TLS_H #error This file should be included only once, by tsd.h. #endif #define JEMALLOC_INTERNAL_TSD_TLS_H -extern __thread tsd_t tsd_tls; +#define JEMALLOC_TSD_TYPE_ATTR(type) __thread type JEMALLOC_TLS_MODEL + +extern JEMALLOC_TSD_TYPE_ATTR(tsd_t) tsd_tls; extern pthread_key_t tsd_tsd; extern bool tsd_booted; /* Initialization/cleanup. */ JEMALLOC_ALWAYS_INLINE bool tsd_boot0(void) { if (pthread_key_create(&tsd_tsd, &tsd_cleanup) != 0) { return true; } tsd_booted = true; return false; } JEMALLOC_ALWAYS_INLINE void tsd_boot1(void) { /* Do nothing. */ } JEMALLOC_ALWAYS_INLINE bool tsd_boot(void) { return tsd_boot0(); } JEMALLOC_ALWAYS_INLINE bool tsd_booted_get(void) { return tsd_booted; } JEMALLOC_ALWAYS_INLINE bool tsd_get_allocates(void) { return false; } /* Get/set. */ JEMALLOC_ALWAYS_INLINE tsd_t * -tsd_get(UNUSED bool init) { - assert(tsd_booted); +tsd_get(bool init) { return &tsd_tls; } JEMALLOC_ALWAYS_INLINE void tsd_set(tsd_t *val) { assert(tsd_booted); if (likely(&tsd_tls != val)) { tsd_tls = (*val); } if (pthread_setspecific(tsd_tsd, (void *)(&tsd_tls)) != 0) { malloc_write(": Error setting tsd.\n"); if (opt_abort) { abort(); } } } Index: head/contrib/jemalloc/include/jemalloc/internal/witness.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/internal/witness.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/internal/witness.h (revision 360233) @@ -1,346 +1,347 @@ #ifndef JEMALLOC_INTERNAL_WITNESS_H #define JEMALLOC_INTERNAL_WITNESS_H #include "jemalloc/internal/ql.h" /******************************************************************************/ /* LOCK RANKS */ /******************************************************************************/ /* * Witnesses with rank WITNESS_RANK_OMIT are completely ignored by the witness * machinery. */ #define WITNESS_RANK_OMIT 0U #define WITNESS_RANK_MIN 1U #define WITNESS_RANK_INIT 1U #define WITNESS_RANK_CTL 1U #define WITNESS_RANK_TCACHES 2U #define WITNESS_RANK_ARENAS 3U #define WITNESS_RANK_BACKGROUND_THREAD_GLOBAL 4U #define WITNESS_RANK_PROF_DUMP 5U #define WITNESS_RANK_PROF_BT2GCTX 6U #define WITNESS_RANK_PROF_TDATAS 7U #define WITNESS_RANK_PROF_TDATA 8U -#define WITNESS_RANK_PROF_GCTX 9U +#define WITNESS_RANK_PROF_LOG 9U +#define WITNESS_RANK_PROF_GCTX 10U +#define WITNESS_RANK_BACKGROUND_THREAD 11U -#define WITNESS_RANK_BACKGROUND_THREAD 10U - /* * Used as an argument to witness_assert_depth_to_rank() in order to validate * depth excluding non-core locks with lower ranks. Since the rank argument to * witness_assert_depth_to_rank() is inclusive rather than exclusive, this * definition can have the same value as the minimally ranked core lock. */ -#define WITNESS_RANK_CORE 11U +#define WITNESS_RANK_CORE 12U -#define WITNESS_RANK_DECAY 11U -#define WITNESS_RANK_TCACHE_QL 12U -#define WITNESS_RANK_EXTENT_GROW 13U -#define WITNESS_RANK_EXTENTS 14U -#define WITNESS_RANK_EXTENT_AVAIL 15U +#define WITNESS_RANK_DECAY 12U +#define WITNESS_RANK_TCACHE_QL 13U +#define WITNESS_RANK_EXTENT_GROW 14U +#define WITNESS_RANK_EXTENTS 15U +#define WITNESS_RANK_EXTENT_AVAIL 16U -#define WITNESS_RANK_EXTENT_POOL 16U -#define WITNESS_RANK_RTREE 17U -#define WITNESS_RANK_BASE 18U -#define WITNESS_RANK_ARENA_LARGE 19U +#define WITNESS_RANK_EXTENT_POOL 17U +#define WITNESS_RANK_RTREE 18U +#define WITNESS_RANK_BASE 19U +#define WITNESS_RANK_ARENA_LARGE 20U +#define WITNESS_RANK_HOOK 21U #define WITNESS_RANK_LEAF 0xffffffffU #define WITNESS_RANK_BIN WITNESS_RANK_LEAF #define WITNESS_RANK_ARENA_STATS WITNESS_RANK_LEAF #define WITNESS_RANK_DSS WITNESS_RANK_LEAF #define WITNESS_RANK_PROF_ACTIVE WITNESS_RANK_LEAF #define WITNESS_RANK_PROF_ACCUM WITNESS_RANK_LEAF #define WITNESS_RANK_PROF_DUMP_SEQ WITNESS_RANK_LEAF #define WITNESS_RANK_PROF_GDUMP WITNESS_RANK_LEAF #define WITNESS_RANK_PROF_NEXT_THR_UID WITNESS_RANK_LEAF #define WITNESS_RANK_PROF_THREAD_ACTIVE_INIT WITNESS_RANK_LEAF /******************************************************************************/ /* PER-WITNESS DATA */ /******************************************************************************/ #if defined(JEMALLOC_DEBUG) # define WITNESS_INITIALIZER(name, rank) {name, rank, NULL, NULL, {NULL, NULL}} #else # define WITNESS_INITIALIZER(name, rank) #endif typedef struct witness_s witness_t; typedef unsigned witness_rank_t; typedef ql_head(witness_t) witness_list_t; typedef int witness_comp_t (const witness_t *, void *, const witness_t *, void *); struct witness_s { /* Name, used for printing lock order reversal messages. */ const char *name; /* * Witness rank, where 0 is lowest and UINT_MAX is highest. Witnesses * must be acquired in order of increasing rank. */ witness_rank_t rank; /* * If two witnesses are of equal rank and they have the samp comp * function pointer, it is called as a last attempt to differentiate * between witnesses of equal rank. */ witness_comp_t *comp; /* Opaque data, passed to comp(). */ void *opaque; /* Linkage for thread's currently owned locks. */ ql_elm(witness_t) link; }; /******************************************************************************/ /* PER-THREAD DATA */ /******************************************************************************/ typedef struct witness_tsd_s witness_tsd_t; struct witness_tsd_s { witness_list_t witnesses; bool forking; }; #define WITNESS_TSD_INITIALIZER { ql_head_initializer(witnesses), false } #define WITNESS_TSDN_NULL ((witness_tsdn_t *)0) /******************************************************************************/ /* (PER-THREAD) NULLABILITY HELPERS */ /******************************************************************************/ typedef struct witness_tsdn_s witness_tsdn_t; struct witness_tsdn_s { witness_tsd_t witness_tsd; }; JEMALLOC_ALWAYS_INLINE witness_tsdn_t * witness_tsd_tsdn(witness_tsd_t *witness_tsd) { return (witness_tsdn_t *)witness_tsd; } JEMALLOC_ALWAYS_INLINE bool witness_tsdn_null(witness_tsdn_t *witness_tsdn) { return witness_tsdn == NULL; } JEMALLOC_ALWAYS_INLINE witness_tsd_t * witness_tsdn_tsd(witness_tsdn_t *witness_tsdn) { assert(!witness_tsdn_null(witness_tsdn)); return &witness_tsdn->witness_tsd; } /******************************************************************************/ /* API */ /******************************************************************************/ void witness_init(witness_t *witness, const char *name, witness_rank_t rank, witness_comp_t *comp, void *opaque); typedef void (witness_lock_error_t)(const witness_list_t *, const witness_t *); extern witness_lock_error_t *JET_MUTABLE witness_lock_error; typedef void (witness_owner_error_t)(const witness_t *); extern witness_owner_error_t *JET_MUTABLE witness_owner_error; typedef void (witness_not_owner_error_t)(const witness_t *); extern witness_not_owner_error_t *JET_MUTABLE witness_not_owner_error; typedef void (witness_depth_error_t)(const witness_list_t *, witness_rank_t rank_inclusive, unsigned depth); extern witness_depth_error_t *JET_MUTABLE witness_depth_error; void witnesses_cleanup(witness_tsd_t *witness_tsd); void witness_prefork(witness_tsd_t *witness_tsd); void witness_postfork_parent(witness_tsd_t *witness_tsd); void witness_postfork_child(witness_tsd_t *witness_tsd); /* Helper, not intended for direct use. */ static inline bool witness_owner(witness_tsd_t *witness_tsd, const witness_t *witness) { witness_list_t *witnesses; witness_t *w; cassert(config_debug); witnesses = &witness_tsd->witnesses; ql_foreach(w, witnesses, link) { if (w == witness) { return true; } } return false; } static inline void witness_assert_owner(witness_tsdn_t *witness_tsdn, const witness_t *witness) { witness_tsd_t *witness_tsd; if (!config_debug) { return; } if (witness_tsdn_null(witness_tsdn)) { return; } witness_tsd = witness_tsdn_tsd(witness_tsdn); if (witness->rank == WITNESS_RANK_OMIT) { return; } if (witness_owner(witness_tsd, witness)) { return; } witness_owner_error(witness); } static inline void witness_assert_not_owner(witness_tsdn_t *witness_tsdn, const witness_t *witness) { witness_tsd_t *witness_tsd; witness_list_t *witnesses; witness_t *w; if (!config_debug) { return; } if (witness_tsdn_null(witness_tsdn)) { return; } witness_tsd = witness_tsdn_tsd(witness_tsdn); if (witness->rank == WITNESS_RANK_OMIT) { return; } witnesses = &witness_tsd->witnesses; ql_foreach(w, witnesses, link) { if (w == witness) { witness_not_owner_error(witness); } } } static inline void witness_assert_depth_to_rank(witness_tsdn_t *witness_tsdn, witness_rank_t rank_inclusive, unsigned depth) { witness_tsd_t *witness_tsd; unsigned d; witness_list_t *witnesses; witness_t *w; if (!config_debug) { return; } if (witness_tsdn_null(witness_tsdn)) { return; } witness_tsd = witness_tsdn_tsd(witness_tsdn); d = 0; witnesses = &witness_tsd->witnesses; w = ql_last(witnesses, link); if (w != NULL) { ql_reverse_foreach(w, witnesses, link) { if (w->rank < rank_inclusive) { break; } d++; } } if (d != depth) { witness_depth_error(witnesses, rank_inclusive, depth); } } static inline void witness_assert_depth(witness_tsdn_t *witness_tsdn, unsigned depth) { witness_assert_depth_to_rank(witness_tsdn, WITNESS_RANK_MIN, depth); } static inline void witness_assert_lockless(witness_tsdn_t *witness_tsdn) { witness_assert_depth(witness_tsdn, 0); } static inline void witness_lock(witness_tsdn_t *witness_tsdn, witness_t *witness) { witness_tsd_t *witness_tsd; witness_list_t *witnesses; witness_t *w; if (!config_debug) { return; } if (witness_tsdn_null(witness_tsdn)) { return; } witness_tsd = witness_tsdn_tsd(witness_tsdn); if (witness->rank == WITNESS_RANK_OMIT) { return; } witness_assert_not_owner(witness_tsdn, witness); witnesses = &witness_tsd->witnesses; w = ql_last(witnesses, link); if (w == NULL) { /* No other locks; do nothing. */ } else if (witness_tsd->forking && w->rank <= witness->rank) { /* Forking, and relaxed ranking satisfied. */ } else if (w->rank > witness->rank) { /* Not forking, rank order reversal. */ witness_lock_error(witnesses, witness); } else if (w->rank == witness->rank && (w->comp == NULL || w->comp != witness->comp || w->comp(w, w->opaque, witness, witness->opaque) > 0)) { /* * Missing/incompatible comparison function, or comparison * function indicates rank order reversal. */ witness_lock_error(witnesses, witness); } ql_elm_new(witness, link); ql_tail_insert(witnesses, witness, link); } static inline void witness_unlock(witness_tsdn_t *witness_tsdn, witness_t *witness) { witness_tsd_t *witness_tsd; witness_list_t *witnesses; if (!config_debug) { return; } if (witness_tsdn_null(witness_tsdn)) { return; } witness_tsd = witness_tsdn_tsd(witness_tsdn); if (witness->rank == WITNESS_RANK_OMIT) { return; } /* * Check whether owner before removal, rather than relying on * witness_assert_owner() to abort, so that unit tests can test this * function's failure mode without causing undefined behavior. */ if (witness_owner(witness_tsd, witness)) { witnesses = &witness_tsd->witnesses; ql_remove(witnesses, witness, link); } else { witness_assert_owner(witness_tsdn, witness); } } #endif /* JEMALLOC_INTERNAL_WITNESS_H */ Index: head/contrib/jemalloc/include/jemalloc/jemalloc.h =================================================================== --- head/contrib/jemalloc/include/jemalloc/jemalloc.h (revision 360232) +++ head/contrib/jemalloc/include/jemalloc/jemalloc.h (revision 360233) @@ -1,420 +1,433 @@ #ifndef JEMALLOC_H_ #define JEMALLOC_H_ #ifdef __cplusplus extern "C" { #endif /* Defined if __attribute__((...)) syntax is supported. */ #define JEMALLOC_HAVE_ATTR /* Defined if alloc_size attribute is supported. */ -/* #undef JEMALLOC_HAVE_ATTR_ALLOC_SIZE */ +#define JEMALLOC_HAVE_ATTR_ALLOC_SIZE +/* Defined if format_arg(...) attribute is supported. */ +#define JEMALLOC_HAVE_ATTR_FORMAT_ARG + /* Defined if format(gnu_printf, ...) attribute is supported. */ /* #undef JEMALLOC_HAVE_ATTR_FORMAT_GNU_PRINTF */ /* 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. */ /* #undef 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 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. */ /* #undef 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 /* * Name mangling for public symbols is controlled by --with-mangling and * --with-jemalloc-prefix. With default settings the je_ prefix is stripped by * these macro definitions. */ #ifndef JEMALLOC_NO_RENAME # define je_aligned_alloc aligned_alloc # define je_calloc calloc # define je_dallocx dallocx # define je_free free # define je_mallctl mallctl # define je_mallctlbymib mallctlbymib # define je_mallctlnametomib mallctlnametomib # define je_malloc malloc # define je_malloc_conf malloc_conf # define je_malloc_message malloc_message # define je_malloc_stats_print malloc_stats_print # define je_malloc_usable_size malloc_usable_size # define je_mallocx mallocx +# define je_smallocx_ea6b3e973b477b8061e0076bb257dbd7f3faa756 smallocx_ea6b3e973b477b8061e0076bb257dbd7f3faa756 # define je_nallocx nallocx # define je_posix_memalign posix_memalign # define je_rallocx rallocx # define je_realloc realloc # define je_sallocx sallocx # define je_sdallocx sdallocx # define je_xallocx xallocx # define je_valloc valloc #endif #include "jemalloc_FreeBSD.h" #include #include #include #include #include -#define JEMALLOC_VERSION "5.1.0-0-g61efbda7098de6fe64c362d309824864308c36d4" +#define JEMALLOC_VERSION "5.2.1-0-gea6b3e973b477b8061e0076bb257dbd7f3faa756" #define JEMALLOC_VERSION_MAJOR 5 -#define JEMALLOC_VERSION_MINOR 1 -#define JEMALLOC_VERSION_BUGFIX 0 +#define JEMALLOC_VERSION_MINOR 2 +#define JEMALLOC_VERSION_BUGFIX 1 #define JEMALLOC_VERSION_NREV 0 -#define JEMALLOC_VERSION_GID "61efbda7098de6fe64c362d309824864308c36d4" +#define JEMALLOC_VERSION_GID "ea6b3e973b477b8061e0076bb257dbd7f3faa756" +#define JEMALLOC_VERSION_GID_IDENT ea6b3e973b477b8061e0076bb257dbd7f3faa756 #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_ARG(i) # 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_ARG +# define JEMALLOC_FORMAT_ARG(i) JEMALLOC_ATTR(__format_arg__(3)) +# else +# define JEMALLOC_FORMAT_ARG(i) +# 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 /* * 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 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; }; /* * By default application code must explicitly refer to mangled symbol names, * so that it is possible to use jemalloc in conjunction with another allocator * in the same application. Define JEMALLOC_MANGLE in order to cause automatic * name mangling that matches the API prefixing that happened as a result of * --with-mangling and/or --with-jemalloc-prefix configuration settings. */ #ifdef JEMALLOC_MANGLE # ifndef JEMALLOC_NO_DEMANGLE # define JEMALLOC_NO_DEMANGLE # endif # define aligned_alloc je_aligned_alloc # define calloc je_calloc # define dallocx je_dallocx # define free je_free # define mallctl je_mallctl # define mallctlbymib je_mallctlbymib # define mallctlnametomib je_mallctlnametomib # define malloc je_malloc # define malloc_conf je_malloc_conf # define malloc_message je_malloc_message # define malloc_stats_print je_malloc_stats_print # define malloc_usable_size je_malloc_usable_size # define mallocx je_mallocx +# define smallocx_ea6b3e973b477b8061e0076bb257dbd7f3faa756 je_smallocx_ea6b3e973b477b8061e0076bb257dbd7f3faa756 # define nallocx je_nallocx # define posix_memalign je_posix_memalign # define rallocx je_rallocx # define realloc je_realloc # define sallocx je_sallocx # define sdallocx je_sdallocx # define xallocx je_xallocx # define valloc je_valloc #endif /* * The je_* macros can be used as stable alternative names for the * public jemalloc API if JEMALLOC_NO_DEMANGLE is defined. This is primarily * meant for use in jemalloc itself, but it can be used by application code to * provide isolation from the name mangling specified via --with-mangling * and/or --with-jemalloc-prefix. */ #ifndef JEMALLOC_NO_DEMANGLE # undef je_aligned_alloc # undef je_calloc # undef je_dallocx # undef je_free # undef je_mallctl # undef je_mallctlbymib # undef je_mallctlnametomib # undef je_malloc # undef je_malloc_conf # undef je_malloc_message # undef je_malloc_stats_print # undef je_malloc_usable_size # undef je_mallocx +# undef je_smallocx_ea6b3e973b477b8061e0076bb257dbd7f3faa756 # undef je_nallocx # undef je_posix_memalign # undef je_rallocx # undef je_realloc # undef je_sallocx # undef je_sdallocx # undef je_xallocx # undef je_valloc #endif #ifdef __cplusplus } #endif #endif /* JEMALLOC_H_ */ Index: head/contrib/jemalloc/src/hooks.c =================================================================== --- head/contrib/jemalloc/src/hooks.c (revision 360232) +++ head/contrib/jemalloc/src/hooks.c (nonexistent) @@ -1,12 +0,0 @@ -#include "jemalloc/internal/jemalloc_preamble.h" - -/* - * The hooks are a little bit screwy -- they're not genuinely exported in the - * sense that we want them available to end-users, but we do want them visible - * from outside the generated library, so that we can use them in test code. - */ -JEMALLOC_EXPORT -void (*hooks_arena_new_hook)() = NULL; - -JEMALLOC_EXPORT -void (*hooks_libc_hook)() = NULL; Property changes on: head/contrib/jemalloc/src/hooks.c ___________________________________________________________________ Deleted: svn:eol-style ## -1 +0,0 ## -native \ No newline at end of property Deleted: svn:keywords ## -1 +0,0 ## -FreeBSD=%H \ No newline at end of property Deleted: svn:mime-type ## -1 +0,0 ## -text/plain \ No newline at end of property Index: head/contrib/jemalloc/src/arena.c =================================================================== --- head/contrib/jemalloc/src/arena.c (revision 360232) +++ head/contrib/jemalloc/src/arena.c (revision 360233) @@ -1,2043 +1,2298 @@ #define JEMALLOC_ARENA_C_ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/jemalloc_internal_includes.h" #include "jemalloc/internal/assert.h" #include "jemalloc/internal/div.h" #include "jemalloc/internal/extent_dss.h" #include "jemalloc/internal/extent_mmap.h" #include "jemalloc/internal/mutex.h" #include "jemalloc/internal/rtree.h" -#include "jemalloc/internal/size_classes.h" +#include "jemalloc/internal/safety_check.h" #include "jemalloc/internal/util.h" +JEMALLOC_DIAGNOSTIC_DISABLE_SPURIOUS + /******************************************************************************/ /* Data. */ /* * Define names for both unininitialized and initialized phases, so that * options and mallctl processing are straightforward. */ const char *percpu_arena_mode_names[] = { "percpu", "phycpu", "disabled", "percpu", "phycpu" }; percpu_arena_mode_t opt_percpu_arena = PERCPU_ARENA_DEFAULT; ssize_t opt_dirty_decay_ms = DIRTY_DECAY_MS_DEFAULT; ssize_t opt_muzzy_decay_ms = MUZZY_DECAY_MS_DEFAULT; static atomic_zd_t dirty_decay_ms_default; static atomic_zd_t muzzy_decay_ms_default; const uint64_t h_steps[SMOOTHSTEP_NSTEPS] = { #define STEP(step, h, x, y) \ h, SMOOTHSTEP #undef STEP }; -static div_info_t arena_binind_div_info[NBINS]; +static div_info_t arena_binind_div_info[SC_NBINS]; +size_t opt_oversize_threshold = OVERSIZE_THRESHOLD_DEFAULT; +size_t oversize_threshold = OVERSIZE_THRESHOLD_DEFAULT; +static unsigned huge_arena_ind; + /******************************************************************************/ /* * Function prototypes for static functions that are referenced prior to * definition. */ static void arena_decay_to_limit(tsdn_t *tsdn, arena_t *arena, arena_decay_t *decay, extents_t *extents, bool all, size_t npages_limit, size_t npages_decay_max, bool is_background_thread); static bool arena_decay_dirty(tsdn_t *tsdn, arena_t *arena, bool is_background_thread, bool all); static void arena_dalloc_bin_slab(tsdn_t *tsdn, arena_t *arena, extent_t *slab, bin_t *bin); static void arena_bin_lower_slab(tsdn_t *tsdn, arena_t *arena, extent_t *slab, bin_t *bin); /******************************************************************************/ void -arena_basic_stats_merge(UNUSED tsdn_t *tsdn, arena_t *arena, unsigned *nthreads, +arena_basic_stats_merge(tsdn_t *tsdn, arena_t *arena, unsigned *nthreads, const char **dss, ssize_t *dirty_decay_ms, ssize_t *muzzy_decay_ms, size_t *nactive, size_t *ndirty, size_t *nmuzzy) { *nthreads += arena_nthreads_get(arena, false); *dss = dss_prec_names[arena_dss_prec_get(arena)]; *dirty_decay_ms = arena_dirty_decay_ms_get(arena); *muzzy_decay_ms = arena_muzzy_decay_ms_get(arena); *nactive += atomic_load_zu(&arena->nactive, ATOMIC_RELAXED); *ndirty += extents_npages_get(&arena->extents_dirty); *nmuzzy += extents_npages_get(&arena->extents_muzzy); } void arena_stats_merge(tsdn_t *tsdn, arena_t *arena, unsigned *nthreads, const char **dss, ssize_t *dirty_decay_ms, ssize_t *muzzy_decay_ms, size_t *nactive, size_t *ndirty, size_t *nmuzzy, arena_stats_t *astats, - bin_stats_t *bstats, arena_stats_large_t *lstats) { + bin_stats_t *bstats, arena_stats_large_t *lstats, + arena_stats_extents_t *estats) { cassert(config_stats); arena_basic_stats_merge(tsdn, arena, nthreads, dss, dirty_decay_ms, muzzy_decay_ms, nactive, ndirty, nmuzzy); size_t base_allocated, base_resident, base_mapped, metadata_thp; base_stats_get(tsdn, arena->base, &base_allocated, &base_resident, &base_mapped, &metadata_thp); arena_stats_lock(tsdn, &arena->stats); arena_stats_accum_zu(&astats->mapped, base_mapped + arena_stats_read_zu(tsdn, &arena->stats, &arena->stats.mapped)); arena_stats_accum_zu(&astats->retained, extents_npages_get(&arena->extents_retained) << LG_PAGE); + atomic_store_zu(&astats->extent_avail, + atomic_load_zu(&arena->extent_avail_cnt, ATOMIC_RELAXED), + ATOMIC_RELAXED); + arena_stats_accum_u64(&astats->decay_dirty.npurge, arena_stats_read_u64(tsdn, &arena->stats, &arena->stats.decay_dirty.npurge)); arena_stats_accum_u64(&astats->decay_dirty.nmadvise, arena_stats_read_u64(tsdn, &arena->stats, &arena->stats.decay_dirty.nmadvise)); arena_stats_accum_u64(&astats->decay_dirty.purged, arena_stats_read_u64(tsdn, &arena->stats, &arena->stats.decay_dirty.purged)); arena_stats_accum_u64(&astats->decay_muzzy.npurge, arena_stats_read_u64(tsdn, &arena->stats, &arena->stats.decay_muzzy.npurge)); arena_stats_accum_u64(&astats->decay_muzzy.nmadvise, arena_stats_read_u64(tsdn, &arena->stats, &arena->stats.decay_muzzy.nmadvise)); arena_stats_accum_u64(&astats->decay_muzzy.purged, arena_stats_read_u64(tsdn, &arena->stats, &arena->stats.decay_muzzy.purged)); arena_stats_accum_zu(&astats->base, base_allocated); arena_stats_accum_zu(&astats->internal, arena_internal_get(arena)); arena_stats_accum_zu(&astats->metadata_thp, metadata_thp); arena_stats_accum_zu(&astats->resident, base_resident + (((atomic_load_zu(&arena->nactive, ATOMIC_RELAXED) + extents_npages_get(&arena->extents_dirty) + extents_npages_get(&arena->extents_muzzy)) << LG_PAGE))); + arena_stats_accum_zu(&astats->abandoned_vm, atomic_load_zu( + &arena->stats.abandoned_vm, ATOMIC_RELAXED)); - for (szind_t i = 0; i < NSIZES - NBINS; i++) { + for (szind_t i = 0; i < SC_NSIZES - SC_NBINS; i++) { uint64_t nmalloc = arena_stats_read_u64(tsdn, &arena->stats, &arena->stats.lstats[i].nmalloc); arena_stats_accum_u64(&lstats[i].nmalloc, nmalloc); arena_stats_accum_u64(&astats->nmalloc_large, nmalloc); uint64_t ndalloc = arena_stats_read_u64(tsdn, &arena->stats, &arena->stats.lstats[i].ndalloc); arena_stats_accum_u64(&lstats[i].ndalloc, ndalloc); arena_stats_accum_u64(&astats->ndalloc_large, ndalloc); uint64_t nrequests = arena_stats_read_u64(tsdn, &arena->stats, &arena->stats.lstats[i].nrequests); arena_stats_accum_u64(&lstats[i].nrequests, nmalloc + nrequests); arena_stats_accum_u64(&astats->nrequests_large, nmalloc + nrequests); + /* nfill == nmalloc for large currently. */ + arena_stats_accum_u64(&lstats[i].nfills, nmalloc); + arena_stats_accum_u64(&astats->nfills_large, nmalloc); + + uint64_t nflush = arena_stats_read_u64(tsdn, &arena->stats, + &arena->stats.lstats[i].nflushes); + arena_stats_accum_u64(&lstats[i].nflushes, nflush); + arena_stats_accum_u64(&astats->nflushes_large, nflush); + assert(nmalloc >= ndalloc); assert(nmalloc - ndalloc <= SIZE_T_MAX); size_t curlextents = (size_t)(nmalloc - ndalloc); lstats[i].curlextents += curlextents; arena_stats_accum_zu(&astats->allocated_large, - curlextents * sz_index2size(NBINS + i)); + curlextents * sz_index2size(SC_NBINS + i)); } + for (pszind_t i = 0; i < SC_NPSIZES; i++) { + size_t dirty, muzzy, retained, dirty_bytes, muzzy_bytes, + retained_bytes; + dirty = extents_nextents_get(&arena->extents_dirty, i); + muzzy = extents_nextents_get(&arena->extents_muzzy, i); + retained = extents_nextents_get(&arena->extents_retained, i); + dirty_bytes = extents_nbytes_get(&arena->extents_dirty, i); + muzzy_bytes = extents_nbytes_get(&arena->extents_muzzy, i); + retained_bytes = + extents_nbytes_get(&arena->extents_retained, i); + + atomic_store_zu(&estats[i].ndirty, dirty, ATOMIC_RELAXED); + atomic_store_zu(&estats[i].nmuzzy, muzzy, ATOMIC_RELAXED); + atomic_store_zu(&estats[i].nretained, retained, ATOMIC_RELAXED); + atomic_store_zu(&estats[i].dirty_bytes, dirty_bytes, + ATOMIC_RELAXED); + atomic_store_zu(&estats[i].muzzy_bytes, muzzy_bytes, + ATOMIC_RELAXED); + atomic_store_zu(&estats[i].retained_bytes, retained_bytes, + ATOMIC_RELAXED); + } + arena_stats_unlock(tsdn, &arena->stats); /* tcache_bytes counts currently cached bytes. */ atomic_store_zu(&astats->tcache_bytes, 0, ATOMIC_RELAXED); malloc_mutex_lock(tsdn, &arena->tcache_ql_mtx); cache_bin_array_descriptor_t *descriptor; ql_foreach(descriptor, &arena->cache_bin_array_descriptor_ql, link) { szind_t i = 0; - for (; i < NBINS; i++) { + for (; i < SC_NBINS; i++) { cache_bin_t *tbin = &descriptor->bins_small[i]; arena_stats_accum_zu(&astats->tcache_bytes, tbin->ncached * sz_index2size(i)); } for (; i < nhbins; i++) { cache_bin_t *tbin = &descriptor->bins_large[i]; arena_stats_accum_zu(&astats->tcache_bytes, tbin->ncached * sz_index2size(i)); } } malloc_mutex_prof_read(tsdn, &astats->mutex_prof_data[arena_prof_mutex_tcache_list], &arena->tcache_ql_mtx); malloc_mutex_unlock(tsdn, &arena->tcache_ql_mtx); #define READ_ARENA_MUTEX_PROF_DATA(mtx, ind) \ malloc_mutex_lock(tsdn, &arena->mtx); \ malloc_mutex_prof_read(tsdn, &astats->mutex_prof_data[ind], \ &arena->mtx); \ malloc_mutex_unlock(tsdn, &arena->mtx); /* Gather per arena mutex profiling data. */ READ_ARENA_MUTEX_PROF_DATA(large_mtx, arena_prof_mutex_large); READ_ARENA_MUTEX_PROF_DATA(extent_avail_mtx, arena_prof_mutex_extent_avail) READ_ARENA_MUTEX_PROF_DATA(extents_dirty.mtx, arena_prof_mutex_extents_dirty) READ_ARENA_MUTEX_PROF_DATA(extents_muzzy.mtx, arena_prof_mutex_extents_muzzy) READ_ARENA_MUTEX_PROF_DATA(extents_retained.mtx, arena_prof_mutex_extents_retained) READ_ARENA_MUTEX_PROF_DATA(decay_dirty.mtx, arena_prof_mutex_decay_dirty) READ_ARENA_MUTEX_PROF_DATA(decay_muzzy.mtx, arena_prof_mutex_decay_muzzy) READ_ARENA_MUTEX_PROF_DATA(base->mtx, arena_prof_mutex_base) #undef READ_ARENA_MUTEX_PROF_DATA nstime_copy(&astats->uptime, &arena->create_time); nstime_update(&astats->uptime); nstime_subtract(&astats->uptime, &arena->create_time); - for (szind_t i = 0; i < NBINS; i++) { - bin_stats_merge(tsdn, &bstats[i], &arena->bins[i]); + for (szind_t i = 0; i < SC_NBINS; i++) { + for (unsigned j = 0; j < bin_infos[i].n_shards; j++) { + bin_stats_merge(tsdn, &bstats[i], + &arena->bins[i].bin_shards[j]); + } } } void arena_extents_dirty_dalloc(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent) { witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); extents_dalloc(tsdn, arena, r_extent_hooks, &arena->extents_dirty, extent); if (arena_dirty_decay_ms_get(arena) == 0) { arena_decay_dirty(tsdn, arena, false, true); } else { arena_background_thread_inactivity_check(tsdn, arena, false); } } static void * arena_slab_reg_alloc(extent_t *slab, const bin_info_t *bin_info) { void *ret; arena_slab_data_t *slab_data = extent_slab_data_get(slab); size_t regind; assert(extent_nfree_get(slab) > 0); assert(!bitmap_full(slab_data->bitmap, &bin_info->bitmap_info)); regind = bitmap_sfu(slab_data->bitmap, &bin_info->bitmap_info); ret = (void *)((uintptr_t)extent_addr_get(slab) + (uintptr_t)(bin_info->reg_size * regind)); extent_nfree_dec(slab); return ret; } +static void +arena_slab_reg_alloc_batch(extent_t *slab, const bin_info_t *bin_info, + unsigned cnt, void** ptrs) { + arena_slab_data_t *slab_data = extent_slab_data_get(slab); + + assert(extent_nfree_get(slab) >= cnt); + assert(!bitmap_full(slab_data->bitmap, &bin_info->bitmap_info)); + +#if (! defined JEMALLOC_INTERNAL_POPCOUNTL) || (defined BITMAP_USE_TREE) + for (unsigned i = 0; i < cnt; i++) { + size_t regind = bitmap_sfu(slab_data->bitmap, + &bin_info->bitmap_info); + *(ptrs + i) = (void *)((uintptr_t)extent_addr_get(slab) + + (uintptr_t)(bin_info->reg_size * regind)); + } +#else + unsigned group = 0; + bitmap_t g = slab_data->bitmap[group]; + unsigned i = 0; + while (i < cnt) { + while (g == 0) { + g = slab_data->bitmap[++group]; + } + size_t shift = group << LG_BITMAP_GROUP_NBITS; + size_t pop = popcount_lu(g); + if (pop > (cnt - i)) { + pop = cnt - i; + } + + /* + * Load from memory locations only once, outside the + * hot loop below. + */ + uintptr_t base = (uintptr_t)extent_addr_get(slab); + uintptr_t regsize = (uintptr_t)bin_info->reg_size; + while (pop--) { + size_t bit = cfs_lu(&g); + size_t regind = shift + bit; + *(ptrs + i) = (void *)(base + regsize * regind); + + i++; + } + slab_data->bitmap[group] = g; + } +#endif + extent_nfree_sub(slab, cnt); +} + #ifndef JEMALLOC_JET static #endif size_t arena_slab_regind(extent_t *slab, szind_t binind, const void *ptr) { size_t diff, regind; /* Freeing a pointer outside the slab can cause assertion failure. */ assert((uintptr_t)ptr >= (uintptr_t)extent_addr_get(slab)); assert((uintptr_t)ptr < (uintptr_t)extent_past_get(slab)); /* Freeing an interior pointer can cause assertion failure. */ assert(((uintptr_t)ptr - (uintptr_t)extent_addr_get(slab)) % (uintptr_t)bin_infos[binind].reg_size == 0); diff = (size_t)((uintptr_t)ptr - (uintptr_t)extent_addr_get(slab)); /* Avoid doing division with a variable divisor. */ regind = div_compute(&arena_binind_div_info[binind], diff); assert(regind < bin_infos[binind].nregs); return regind; } static void arena_slab_reg_dalloc(extent_t *slab, arena_slab_data_t *slab_data, void *ptr) { szind_t binind = extent_szind_get(slab); const bin_info_t *bin_info = &bin_infos[binind]; size_t regind = arena_slab_regind(slab, binind, ptr); assert(extent_nfree_get(slab) < bin_info->nregs); /* Freeing an unallocated pointer can cause assertion failure. */ assert(bitmap_get(slab_data->bitmap, &bin_info->bitmap_info, regind)); bitmap_unset(slab_data->bitmap, &bin_info->bitmap_info, regind); extent_nfree_inc(slab); } static void arena_nactive_add(arena_t *arena, size_t add_pages) { atomic_fetch_add_zu(&arena->nactive, add_pages, ATOMIC_RELAXED); } static void arena_nactive_sub(arena_t *arena, size_t sub_pages) { assert(atomic_load_zu(&arena->nactive, ATOMIC_RELAXED) >= sub_pages); atomic_fetch_sub_zu(&arena->nactive, sub_pages, ATOMIC_RELAXED); } static void arena_large_malloc_stats_update(tsdn_t *tsdn, arena_t *arena, size_t usize) { szind_t index, hindex; cassert(config_stats); - if (usize < LARGE_MINCLASS) { - usize = LARGE_MINCLASS; + if (usize < SC_LARGE_MINCLASS) { + usize = SC_LARGE_MINCLASS; } index = sz_size2index(usize); - hindex = (index >= NBINS) ? index - NBINS : 0; + hindex = (index >= SC_NBINS) ? index - SC_NBINS : 0; arena_stats_add_u64(tsdn, &arena->stats, &arena->stats.lstats[hindex].nmalloc, 1); } static void arena_large_dalloc_stats_update(tsdn_t *tsdn, arena_t *arena, size_t usize) { szind_t index, hindex; cassert(config_stats); - if (usize < LARGE_MINCLASS) { - usize = LARGE_MINCLASS; + if (usize < SC_LARGE_MINCLASS) { + usize = SC_LARGE_MINCLASS; } index = sz_size2index(usize); - hindex = (index >= NBINS) ? index - NBINS : 0; + hindex = (index >= SC_NBINS) ? index - SC_NBINS : 0; arena_stats_add_u64(tsdn, &arena->stats, &arena->stats.lstats[hindex].ndalloc, 1); } static void arena_large_ralloc_stats_update(tsdn_t *tsdn, arena_t *arena, size_t oldusize, size_t usize) { arena_large_dalloc_stats_update(tsdn, arena, oldusize); arena_large_malloc_stats_update(tsdn, arena, usize); } +static bool +arena_may_have_muzzy(arena_t *arena) { + return (pages_can_purge_lazy && (arena_muzzy_decay_ms_get(arena) != 0)); +} + extent_t * arena_extent_alloc_large(tsdn_t *tsdn, arena_t *arena, size_t usize, size_t alignment, bool *zero) { extent_hooks_t *extent_hooks = EXTENT_HOOKS_INITIALIZER; witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); szind_t szind = sz_size2index(usize); size_t mapped_add; bool commit = true; extent_t *extent = extents_alloc(tsdn, arena, &extent_hooks, &arena->extents_dirty, NULL, usize, sz_large_pad, alignment, false, szind, zero, &commit); - if (extent == NULL) { + if (extent == NULL && arena_may_have_muzzy(arena)) { extent = extents_alloc(tsdn, arena, &extent_hooks, &arena->extents_muzzy, NULL, usize, sz_large_pad, alignment, false, szind, zero, &commit); } size_t size = usize + sz_large_pad; if (extent == NULL) { extent = extent_alloc_wrapper(tsdn, arena, &extent_hooks, NULL, usize, sz_large_pad, alignment, false, szind, zero, &commit); if (config_stats) { /* * extent may be NULL on OOM, but in that case * mapped_add isn't used below, so there's no need to * conditionlly set it to 0 here. */ mapped_add = size; } } else if (config_stats) { mapped_add = 0; } if (extent != NULL) { if (config_stats) { arena_stats_lock(tsdn, &arena->stats); arena_large_malloc_stats_update(tsdn, arena, usize); if (mapped_add != 0) { arena_stats_add_zu(tsdn, &arena->stats, &arena->stats.mapped, mapped_add); } arena_stats_unlock(tsdn, &arena->stats); } arena_nactive_add(arena, size >> LG_PAGE); } return extent; } void arena_extent_dalloc_large_prep(tsdn_t *tsdn, arena_t *arena, extent_t *extent) { if (config_stats) { arena_stats_lock(tsdn, &arena->stats); arena_large_dalloc_stats_update(tsdn, arena, extent_usize_get(extent)); arena_stats_unlock(tsdn, &arena->stats); } arena_nactive_sub(arena, extent_size_get(extent) >> LG_PAGE); } void arena_extent_ralloc_large_shrink(tsdn_t *tsdn, arena_t *arena, extent_t *extent, size_t oldusize) { size_t usize = extent_usize_get(extent); size_t udiff = oldusize - usize; if (config_stats) { arena_stats_lock(tsdn, &arena->stats); arena_large_ralloc_stats_update(tsdn, arena, oldusize, usize); arena_stats_unlock(tsdn, &arena->stats); } arena_nactive_sub(arena, udiff >> LG_PAGE); } void arena_extent_ralloc_large_expand(tsdn_t *tsdn, arena_t *arena, extent_t *extent, size_t oldusize) { size_t usize = extent_usize_get(extent); size_t udiff = usize - oldusize; if (config_stats) { arena_stats_lock(tsdn, &arena->stats); arena_large_ralloc_stats_update(tsdn, arena, oldusize, usize); arena_stats_unlock(tsdn, &arena->stats); } arena_nactive_add(arena, udiff >> LG_PAGE); } static ssize_t arena_decay_ms_read(arena_decay_t *decay) { return atomic_load_zd(&decay->time_ms, ATOMIC_RELAXED); } static void arena_decay_ms_write(arena_decay_t *decay, ssize_t decay_ms) { atomic_store_zd(&decay->time_ms, decay_ms, ATOMIC_RELAXED); } static void arena_decay_deadline_init(arena_decay_t *decay) { /* * Generate a new deadline that is uniformly random within the next * epoch after the current one. */ nstime_copy(&decay->deadline, &decay->epoch); nstime_add(&decay->deadline, &decay->interval); if (arena_decay_ms_read(decay) > 0) { nstime_t jitter; nstime_init(&jitter, prng_range_u64(&decay->jitter_state, nstime_ns(&decay->interval))); nstime_add(&decay->deadline, &jitter); } } static bool arena_decay_deadline_reached(const arena_decay_t *decay, const nstime_t *time) { return (nstime_compare(&decay->deadline, time) <= 0); } static size_t arena_decay_backlog_npages_limit(const arena_decay_t *decay) { uint64_t sum; size_t npages_limit_backlog; unsigned i; /* * For each element of decay_backlog, multiply by the corresponding * fixed-point smoothstep decay factor. Sum the products, then divide * to round down to the nearest whole number of pages. */ sum = 0; for (i = 0; i < SMOOTHSTEP_NSTEPS; i++) { sum += decay->backlog[i] * h_steps[i]; } npages_limit_backlog = (size_t)(sum >> SMOOTHSTEP_BFP); return npages_limit_backlog; } static void arena_decay_backlog_update_last(arena_decay_t *decay, size_t current_npages) { size_t npages_delta = (current_npages > decay->nunpurged) ? current_npages - decay->nunpurged : 0; decay->backlog[SMOOTHSTEP_NSTEPS-1] = npages_delta; if (config_debug) { if (current_npages > decay->ceil_npages) { decay->ceil_npages = current_npages; } size_t npages_limit = arena_decay_backlog_npages_limit(decay); assert(decay->ceil_npages >= npages_limit); if (decay->ceil_npages > npages_limit) { decay->ceil_npages = npages_limit; } } } static void arena_decay_backlog_update(arena_decay_t *decay, uint64_t nadvance_u64, size_t current_npages) { if (nadvance_u64 >= SMOOTHSTEP_NSTEPS) { memset(decay->backlog, 0, (SMOOTHSTEP_NSTEPS-1) * sizeof(size_t)); } else { size_t nadvance_z = (size_t)nadvance_u64; assert((uint64_t)nadvance_z == nadvance_u64); memmove(decay->backlog, &decay->backlog[nadvance_z], (SMOOTHSTEP_NSTEPS - nadvance_z) * sizeof(size_t)); if (nadvance_z > 1) { memset(&decay->backlog[SMOOTHSTEP_NSTEPS - nadvance_z], 0, (nadvance_z-1) * sizeof(size_t)); } } arena_decay_backlog_update_last(decay, current_npages); } static void arena_decay_try_purge(tsdn_t *tsdn, arena_t *arena, arena_decay_t *decay, extents_t *extents, size_t current_npages, size_t npages_limit, bool is_background_thread) { if (current_npages > npages_limit) { arena_decay_to_limit(tsdn, arena, decay, extents, false, npages_limit, current_npages - npages_limit, is_background_thread); } } static void arena_decay_epoch_advance_helper(arena_decay_t *decay, const nstime_t *time, size_t current_npages) { assert(arena_decay_deadline_reached(decay, time)); nstime_t delta; nstime_copy(&delta, time); nstime_subtract(&delta, &decay->epoch); uint64_t nadvance_u64 = nstime_divide(&delta, &decay->interval); assert(nadvance_u64 > 0); /* Add nadvance_u64 decay intervals to epoch. */ nstime_copy(&delta, &decay->interval); nstime_imultiply(&delta, nadvance_u64); nstime_add(&decay->epoch, &delta); /* Set a new deadline. */ arena_decay_deadline_init(decay); /* Update the backlog. */ arena_decay_backlog_update(decay, nadvance_u64, current_npages); } static void arena_decay_epoch_advance(tsdn_t *tsdn, arena_t *arena, arena_decay_t *decay, extents_t *extents, const nstime_t *time, bool is_background_thread) { size_t current_npages = extents_npages_get(extents); arena_decay_epoch_advance_helper(decay, time, current_npages); size_t npages_limit = arena_decay_backlog_npages_limit(decay); /* We may unlock decay->mtx when try_purge(). Finish logging first. */ decay->nunpurged = (npages_limit > current_npages) ? npages_limit : current_npages; if (!background_thread_enabled() || is_background_thread) { arena_decay_try_purge(tsdn, arena, decay, extents, current_npages, npages_limit, is_background_thread); } } static void arena_decay_reinit(arena_decay_t *decay, ssize_t decay_ms) { arena_decay_ms_write(decay, decay_ms); if (decay_ms > 0) { nstime_init(&decay->interval, (uint64_t)decay_ms * KQU(1000000)); nstime_idivide(&decay->interval, SMOOTHSTEP_NSTEPS); } nstime_init(&decay->epoch, 0); nstime_update(&decay->epoch); decay->jitter_state = (uint64_t)(uintptr_t)decay; arena_decay_deadline_init(decay); decay->nunpurged = 0; memset(decay->backlog, 0, SMOOTHSTEP_NSTEPS * sizeof(size_t)); } static bool arena_decay_init(arena_decay_t *decay, ssize_t decay_ms, arena_stats_decay_t *stats) { if (config_debug) { for (size_t i = 0; i < sizeof(arena_decay_t); i++) { assert(((char *)decay)[i] == 0); } decay->ceil_npages = 0; } if (malloc_mutex_init(&decay->mtx, "decay", WITNESS_RANK_DECAY, malloc_mutex_rank_exclusive)) { return true; } decay->purging = false; arena_decay_reinit(decay, decay_ms); /* Memory is zeroed, so there is no need to clear stats. */ if (config_stats) { decay->stats = stats; } return false; } static bool arena_decay_ms_valid(ssize_t decay_ms) { if (decay_ms < -1) { return false; } if (decay_ms == -1 || (uint64_t)decay_ms <= NSTIME_SEC_MAX * KQU(1000)) { return true; } return false; } static bool arena_maybe_decay(tsdn_t *tsdn, arena_t *arena, arena_decay_t *decay, extents_t *extents, bool is_background_thread) { malloc_mutex_assert_owner(tsdn, &decay->mtx); /* Purge all or nothing if the option is disabled. */ ssize_t decay_ms = arena_decay_ms_read(decay); if (decay_ms <= 0) { if (decay_ms == 0) { arena_decay_to_limit(tsdn, arena, decay, extents, false, 0, extents_npages_get(extents), is_background_thread); } return false; } nstime_t time; nstime_init(&time, 0); nstime_update(&time); if (unlikely(!nstime_monotonic() && nstime_compare(&decay->epoch, &time) > 0)) { /* * Time went backwards. Move the epoch back in time and * generate a new deadline, with the expectation that time * typically flows forward for long enough periods of time that * epochs complete. Unfortunately, this strategy is susceptible * to clock jitter triggering premature epoch advances, but * clock jitter estimation and compensation isn't feasible here * because calls into this code are event-driven. */ nstime_copy(&decay->epoch, &time); arena_decay_deadline_init(decay); } else { /* Verify that time does not go backwards. */ assert(nstime_compare(&decay->epoch, &time) <= 0); } /* * If the deadline has been reached, advance to the current epoch and * purge to the new limit if necessary. Note that dirty pages created * during the current epoch are not subject to purge until a future * epoch, so as a result purging only happens during epoch advances, or * being triggered by background threads (scheduled event). */ bool advance_epoch = arena_decay_deadline_reached(decay, &time); if (advance_epoch) { arena_decay_epoch_advance(tsdn, arena, decay, extents, &time, is_background_thread); } else if (is_background_thread) { arena_decay_try_purge(tsdn, arena, decay, extents, extents_npages_get(extents), arena_decay_backlog_npages_limit(decay), is_background_thread); } return advance_epoch; } static ssize_t arena_decay_ms_get(arena_decay_t *decay) { return arena_decay_ms_read(decay); } ssize_t arena_dirty_decay_ms_get(arena_t *arena) { return arena_decay_ms_get(&arena->decay_dirty); } ssize_t arena_muzzy_decay_ms_get(arena_t *arena) { return arena_decay_ms_get(&arena->decay_muzzy); } static bool arena_decay_ms_set(tsdn_t *tsdn, arena_t *arena, arena_decay_t *decay, extents_t *extents, ssize_t decay_ms) { if (!arena_decay_ms_valid(decay_ms)) { return true; } malloc_mutex_lock(tsdn, &decay->mtx); /* * Restart decay backlog from scratch, which may cause many dirty pages * to be immediately purged. It would conceptually be possible to map * the old backlog onto the new backlog, but there is no justification * for such complexity since decay_ms changes are intended to be * infrequent, either between the {-1, 0, >0} states, or a one-time * arbitrary change during initial arena configuration. */ arena_decay_reinit(decay, decay_ms); arena_maybe_decay(tsdn, arena, decay, extents, false); malloc_mutex_unlock(tsdn, &decay->mtx); return false; } bool arena_dirty_decay_ms_set(tsdn_t *tsdn, arena_t *arena, ssize_t decay_ms) { return arena_decay_ms_set(tsdn, arena, &arena->decay_dirty, &arena->extents_dirty, decay_ms); } bool arena_muzzy_decay_ms_set(tsdn_t *tsdn, arena_t *arena, ssize_t decay_ms) { return arena_decay_ms_set(tsdn, arena, &arena->decay_muzzy, &arena->extents_muzzy, decay_ms); } static size_t arena_stash_decayed(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extents_t *extents, size_t npages_limit, size_t npages_decay_max, extent_list_t *decay_extents) { witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); /* Stash extents according to npages_limit. */ size_t nstashed = 0; extent_t *extent; while (nstashed < npages_decay_max && (extent = extents_evict(tsdn, arena, r_extent_hooks, extents, npages_limit)) != NULL) { extent_list_append(decay_extents, extent); nstashed += extent_size_get(extent) >> LG_PAGE; } return nstashed; } static size_t arena_decay_stashed(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, arena_decay_t *decay, extents_t *extents, bool all, extent_list_t *decay_extents, bool is_background_thread) { - UNUSED size_t nmadvise, nunmapped; + size_t nmadvise, nunmapped; size_t npurged; if (config_stats) { nmadvise = 0; nunmapped = 0; } npurged = 0; ssize_t muzzy_decay_ms = arena_muzzy_decay_ms_get(arena); for (extent_t *extent = extent_list_first(decay_extents); extent != NULL; extent = extent_list_first(decay_extents)) { if (config_stats) { nmadvise++; } size_t npages = extent_size_get(extent) >> LG_PAGE; npurged += npages; extent_list_remove(decay_extents, extent); switch (extents_state_get(extents)) { case extent_state_active: not_reached(); case extent_state_dirty: if (!all && muzzy_decay_ms != 0 && !extent_purge_lazy_wrapper(tsdn, arena, r_extent_hooks, extent, 0, extent_size_get(extent))) { extents_dalloc(tsdn, arena, r_extent_hooks, &arena->extents_muzzy, extent); arena_background_thread_inactivity_check(tsdn, arena, is_background_thread); break; } /* Fall through. */ case extent_state_muzzy: extent_dalloc_wrapper(tsdn, arena, r_extent_hooks, extent); if (config_stats) { nunmapped += npages; } break; case extent_state_retained: default: not_reached(); } } if (config_stats) { arena_stats_lock(tsdn, &arena->stats); arena_stats_add_u64(tsdn, &arena->stats, &decay->stats->npurge, 1); arena_stats_add_u64(tsdn, &arena->stats, &decay->stats->nmadvise, nmadvise); arena_stats_add_u64(tsdn, &arena->stats, &decay->stats->purged, npurged); arena_stats_sub_zu(tsdn, &arena->stats, &arena->stats.mapped, nunmapped << LG_PAGE); arena_stats_unlock(tsdn, &arena->stats); } return npurged; } /* * npages_limit: Decay at most npages_decay_max pages without violating the * invariant: (extents_npages_get(extents) >= npages_limit). We need an upper * bound on number of pages in order to prevent unbounded growth (namely in * stashed), otherwise unbounded new pages could be added to extents during the * current decay run, so that the purging thread never finishes. */ static void arena_decay_to_limit(tsdn_t *tsdn, arena_t *arena, arena_decay_t *decay, extents_t *extents, bool all, size_t npages_limit, size_t npages_decay_max, bool is_background_thread) { witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 1); malloc_mutex_assert_owner(tsdn, &decay->mtx); if (decay->purging) { return; } decay->purging = true; malloc_mutex_unlock(tsdn, &decay->mtx); extent_hooks_t *extent_hooks = extent_hooks_get(arena); extent_list_t decay_extents; extent_list_init(&decay_extents); size_t npurge = arena_stash_decayed(tsdn, arena, &extent_hooks, extents, npages_limit, npages_decay_max, &decay_extents); if (npurge != 0) { - UNUSED size_t npurged = arena_decay_stashed(tsdn, arena, + size_t npurged = arena_decay_stashed(tsdn, arena, &extent_hooks, decay, extents, all, &decay_extents, is_background_thread); assert(npurged == npurge); } malloc_mutex_lock(tsdn, &decay->mtx); decay->purging = false; } static bool arena_decay_impl(tsdn_t *tsdn, arena_t *arena, arena_decay_t *decay, extents_t *extents, bool is_background_thread, bool all) { if (all) { malloc_mutex_lock(tsdn, &decay->mtx); arena_decay_to_limit(tsdn, arena, decay, extents, all, 0, extents_npages_get(extents), is_background_thread); malloc_mutex_unlock(tsdn, &decay->mtx); return false; } if (malloc_mutex_trylock(tsdn, &decay->mtx)) { /* No need to wait if another thread is in progress. */ return true; } bool epoch_advanced = arena_maybe_decay(tsdn, arena, decay, extents, is_background_thread); - UNUSED size_t npages_new; + size_t npages_new; if (epoch_advanced) { /* Backlog is updated on epoch advance. */ npages_new = decay->backlog[SMOOTHSTEP_NSTEPS-1]; } malloc_mutex_unlock(tsdn, &decay->mtx); if (have_background_thread && background_thread_enabled() && epoch_advanced && !is_background_thread) { background_thread_interval_check(tsdn, arena, decay, npages_new); } return false; } static bool arena_decay_dirty(tsdn_t *tsdn, arena_t *arena, bool is_background_thread, bool all) { return arena_decay_impl(tsdn, arena, &arena->decay_dirty, &arena->extents_dirty, is_background_thread, all); } static bool arena_decay_muzzy(tsdn_t *tsdn, arena_t *arena, bool is_background_thread, bool all) { return arena_decay_impl(tsdn, arena, &arena->decay_muzzy, &arena->extents_muzzy, is_background_thread, all); } void arena_decay(tsdn_t *tsdn, arena_t *arena, bool is_background_thread, bool all) { if (arena_decay_dirty(tsdn, arena, is_background_thread, all)) { return; } arena_decay_muzzy(tsdn, arena, is_background_thread, all); } static void arena_slab_dalloc(tsdn_t *tsdn, arena_t *arena, extent_t *slab) { arena_nactive_sub(arena, extent_size_get(slab) >> LG_PAGE); extent_hooks_t *extent_hooks = EXTENT_HOOKS_INITIALIZER; arena_extents_dirty_dalloc(tsdn, arena, &extent_hooks, slab); } static void arena_bin_slabs_nonfull_insert(bin_t *bin, extent_t *slab) { assert(extent_nfree_get(slab) > 0); extent_heap_insert(&bin->slabs_nonfull, slab); + if (config_stats) { + bin->stats.nonfull_slabs++; + } } static void arena_bin_slabs_nonfull_remove(bin_t *bin, extent_t *slab) { extent_heap_remove(&bin->slabs_nonfull, slab); + if (config_stats) { + bin->stats.nonfull_slabs--; + } } static extent_t * arena_bin_slabs_nonfull_tryget(bin_t *bin) { extent_t *slab = extent_heap_remove_first(&bin->slabs_nonfull); if (slab == NULL) { return NULL; } if (config_stats) { bin->stats.reslabs++; + bin->stats.nonfull_slabs--; } return slab; } static void arena_bin_slabs_full_insert(arena_t *arena, bin_t *bin, extent_t *slab) { assert(extent_nfree_get(slab) == 0); /* * Tracking extents is required by arena_reset, which is not allowed * for auto arenas. Bypass this step to avoid touching the extent * linkage (often results in cache misses) for auto arenas. */ if (arena_is_auto(arena)) { return; } extent_list_append(&bin->slabs_full, slab); } static void arena_bin_slabs_full_remove(arena_t *arena, bin_t *bin, extent_t *slab) { if (arena_is_auto(arena)) { return; } extent_list_remove(&bin->slabs_full, slab); } +static void +arena_bin_reset(tsd_t *tsd, arena_t *arena, bin_t *bin) { + extent_t *slab; + + malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock); + if (bin->slabcur != NULL) { + slab = bin->slabcur; + bin->slabcur = NULL; + malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock); + arena_slab_dalloc(tsd_tsdn(tsd), arena, slab); + malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock); + } + while ((slab = extent_heap_remove_first(&bin->slabs_nonfull)) != NULL) { + malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock); + arena_slab_dalloc(tsd_tsdn(tsd), arena, slab); + malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock); + } + for (slab = extent_list_first(&bin->slabs_full); slab != NULL; + slab = extent_list_first(&bin->slabs_full)) { + arena_bin_slabs_full_remove(arena, bin, slab); + malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock); + arena_slab_dalloc(tsd_tsdn(tsd), arena, slab); + malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock); + } + if (config_stats) { + bin->stats.curregs = 0; + bin->stats.curslabs = 0; + } + malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock); +} + void arena_reset(tsd_t *tsd, arena_t *arena) { /* * Locking in this function is unintuitive. The caller guarantees that * no concurrent operations are happening in this arena, but there are * still reasons that some locking is necessary: * * - Some of the functions in the transitive closure of calls assume * appropriate locks are held, and in some cases these locks are * temporarily dropped to avoid lock order reversal or deadlock due to * reentry. * - mallctl("epoch", ...) may concurrently refresh stats. While * strictly speaking this is a "concurrent operation", disallowing * stats refreshes would impose an inconvenient burden. */ /* Large allocations. */ malloc_mutex_lock(tsd_tsdn(tsd), &arena->large_mtx); for (extent_t *extent = extent_list_first(&arena->large); extent != NULL; extent = extent_list_first(&arena->large)) { void *ptr = extent_base_get(extent); size_t usize; malloc_mutex_unlock(tsd_tsdn(tsd), &arena->large_mtx); alloc_ctx_t alloc_ctx; rtree_ctx_t *rtree_ctx = tsd_rtree_ctx(tsd); rtree_szind_slab_read(tsd_tsdn(tsd), &extents_rtree, rtree_ctx, (uintptr_t)ptr, true, &alloc_ctx.szind, &alloc_ctx.slab); - assert(alloc_ctx.szind != NSIZES); + assert(alloc_ctx.szind != SC_NSIZES); if (config_stats || (config_prof && opt_prof)) { usize = sz_index2size(alloc_ctx.szind); assert(usize == isalloc(tsd_tsdn(tsd), ptr)); } /* Remove large allocation from prof sample set. */ if (config_prof && opt_prof) { prof_free(tsd, ptr, usize, &alloc_ctx); } large_dalloc(tsd_tsdn(tsd), extent); malloc_mutex_lock(tsd_tsdn(tsd), &arena->large_mtx); } malloc_mutex_unlock(tsd_tsdn(tsd), &arena->large_mtx); /* Bins. */ - for (unsigned i = 0; i < NBINS; i++) { - extent_t *slab; - bin_t *bin = &arena->bins[i]; - malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock); - if (bin->slabcur != NULL) { - slab = bin->slabcur; - bin->slabcur = NULL; - malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock); - arena_slab_dalloc(tsd_tsdn(tsd), arena, slab); - malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock); + for (unsigned i = 0; i < SC_NBINS; i++) { + for (unsigned j = 0; j < bin_infos[i].n_shards; j++) { + arena_bin_reset(tsd, arena, + &arena->bins[i].bin_shards[j]); } - while ((slab = extent_heap_remove_first(&bin->slabs_nonfull)) != - NULL) { - malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock); - arena_slab_dalloc(tsd_tsdn(tsd), arena, slab); - malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock); - } - for (slab = extent_list_first(&bin->slabs_full); slab != NULL; - slab = extent_list_first(&bin->slabs_full)) { - arena_bin_slabs_full_remove(arena, bin, slab); - malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock); - arena_slab_dalloc(tsd_tsdn(tsd), arena, slab); - malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock); - } - if (config_stats) { - bin->stats.curregs = 0; - bin->stats.curslabs = 0; - } - malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock); } atomic_store_zu(&arena->nactive, 0, ATOMIC_RELAXED); } static void arena_destroy_retained(tsdn_t *tsdn, arena_t *arena) { /* * Iterate over the retained extents and destroy them. This gives the * extent allocator underlying the extent hooks an opportunity to unmap * all retained memory without having to keep its own metadata * structures. In practice, virtual memory for dss-allocated extents is * leaked here, so best practice is to avoid dss for arenas to be * destroyed, or provide custom extent hooks that track retained * dss-based extents for later reuse. */ extent_hooks_t *extent_hooks = extent_hooks_get(arena); extent_t *extent; while ((extent = extents_evict(tsdn, arena, &extent_hooks, &arena->extents_retained, 0)) != NULL) { extent_destroy_wrapper(tsdn, arena, &extent_hooks, extent); } } void arena_destroy(tsd_t *tsd, arena_t *arena) { assert(base_ind_get(arena->base) >= narenas_auto); assert(arena_nthreads_get(arena, false) == 0); assert(arena_nthreads_get(arena, true) == 0); /* * No allocations have occurred since arena_reset() was called. * Furthermore, the caller (arena_i_destroy_ctl()) purged all cached * extents, so only retained extents may remain. */ assert(extents_npages_get(&arena->extents_dirty) == 0); assert(extents_npages_get(&arena->extents_muzzy) == 0); /* Deallocate retained memory. */ arena_destroy_retained(tsd_tsdn(tsd), arena); /* * Remove the arena pointer from the arenas array. We rely on the fact * that there is no way for the application to get a dirty read from the * arenas array unless there is an inherent race in the application * involving access of an arena being concurrently destroyed. The * application must synchronize knowledge of the arena's validity, so as * long as we use an atomic write to update the arenas array, the * application will get a clean read any time after it synchronizes * knowledge that the arena is no longer valid. */ arena_set(base_ind_get(arena->base), NULL); /* * Destroy the base allocator, which manages all metadata ever mapped by * this arena. */ base_delete(tsd_tsdn(tsd), arena->base); } static extent_t * arena_slab_alloc_hard(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, const bin_info_t *bin_info, szind_t szind) { extent_t *slab; bool zero, commit; witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); zero = false; commit = true; slab = extent_alloc_wrapper(tsdn, arena, r_extent_hooks, NULL, bin_info->slab_size, 0, PAGE, true, szind, &zero, &commit); if (config_stats && slab != NULL) { arena_stats_mapped_add(tsdn, &arena->stats, bin_info->slab_size); } return slab; } static extent_t * -arena_slab_alloc(tsdn_t *tsdn, arena_t *arena, szind_t binind, +arena_slab_alloc(tsdn_t *tsdn, arena_t *arena, szind_t binind, unsigned binshard, const bin_info_t *bin_info) { witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); extent_hooks_t *extent_hooks = EXTENT_HOOKS_INITIALIZER; szind_t szind = sz_size2index(bin_info->reg_size); bool zero = false; bool commit = true; extent_t *slab = extents_alloc(tsdn, arena, &extent_hooks, &arena->extents_dirty, NULL, bin_info->slab_size, 0, PAGE, true, binind, &zero, &commit); - if (slab == NULL) { + if (slab == NULL && arena_may_have_muzzy(arena)) { slab = extents_alloc(tsdn, arena, &extent_hooks, &arena->extents_muzzy, NULL, bin_info->slab_size, 0, PAGE, true, binind, &zero, &commit); } if (slab == NULL) { slab = arena_slab_alloc_hard(tsdn, arena, &extent_hooks, bin_info, szind); if (slab == NULL) { return NULL; } } assert(extent_slab_get(slab)); /* Initialize slab internals. */ arena_slab_data_t *slab_data = extent_slab_data_get(slab); - extent_nfree_set(slab, bin_info->nregs); + extent_nfree_binshard_set(slab, bin_info->nregs, binshard); bitmap_init(slab_data->bitmap, &bin_info->bitmap_info, false); arena_nactive_add(arena, extent_size_get(slab) >> LG_PAGE); return slab; } static extent_t * arena_bin_nonfull_slab_get(tsdn_t *tsdn, arena_t *arena, bin_t *bin, - szind_t binind) { + szind_t binind, unsigned binshard) { extent_t *slab; const bin_info_t *bin_info; /* Look for a usable slab. */ slab = arena_bin_slabs_nonfull_tryget(bin); if (slab != NULL) { return slab; } /* No existing slabs have any space available. */ bin_info = &bin_infos[binind]; /* Allocate a new slab. */ malloc_mutex_unlock(tsdn, &bin->lock); /******************************/ - slab = arena_slab_alloc(tsdn, arena, binind, bin_info); + slab = arena_slab_alloc(tsdn, arena, binind, binshard, bin_info); /********************************/ malloc_mutex_lock(tsdn, &bin->lock); if (slab != NULL) { if (config_stats) { bin->stats.nslabs++; bin->stats.curslabs++; } return slab; } /* * arena_slab_alloc() failed, but another thread may have made * sufficient memory available while this one dropped bin->lock above, * so search one more time. */ slab = arena_bin_slabs_nonfull_tryget(bin); if (slab != NULL) { return slab; } return NULL; } /* Re-fill bin->slabcur, then call arena_slab_reg_alloc(). */ static void * arena_bin_malloc_hard(tsdn_t *tsdn, arena_t *arena, bin_t *bin, - szind_t binind) { + szind_t binind, unsigned binshard) { const bin_info_t *bin_info; extent_t *slab; bin_info = &bin_infos[binind]; if (!arena_is_auto(arena) && bin->slabcur != NULL) { arena_bin_slabs_full_insert(arena, bin, bin->slabcur); bin->slabcur = NULL; } - slab = arena_bin_nonfull_slab_get(tsdn, arena, bin, binind); + slab = arena_bin_nonfull_slab_get(tsdn, arena, bin, binind, binshard); if (bin->slabcur != NULL) { /* * Another thread updated slabcur while this one ran without the * bin lock in arena_bin_nonfull_slab_get(). */ if (extent_nfree_get(bin->slabcur) > 0) { void *ret = arena_slab_reg_alloc(bin->slabcur, bin_info); if (slab != NULL) { /* * arena_slab_alloc() may have allocated slab, * or it may have been pulled from * slabs_nonfull. Therefore it is unsafe to * make any assumptions about how slab has * previously been used, and * arena_bin_lower_slab() must be called, as if * a region were just deallocated from the slab. */ if (extent_nfree_get(slab) == bin_info->nregs) { arena_dalloc_bin_slab(tsdn, arena, slab, bin); } else { arena_bin_lower_slab(tsdn, arena, slab, bin); } } return ret; } arena_bin_slabs_full_insert(arena, bin, bin->slabcur); bin->slabcur = NULL; } if (slab == NULL) { return NULL; } bin->slabcur = slab; assert(extent_nfree_get(bin->slabcur) > 0); return arena_slab_reg_alloc(slab, bin_info); } +/* Choose a bin shard and return the locked bin. */ +bin_t * +arena_bin_choose_lock(tsdn_t *tsdn, arena_t *arena, szind_t binind, + unsigned *binshard) { + bin_t *bin; + if (tsdn_null(tsdn) || tsd_arena_get(tsdn_tsd(tsdn)) == NULL) { + *binshard = 0; + } else { + *binshard = tsd_binshardsp_get(tsdn_tsd(tsdn))->binshard[binind]; + } + assert(*binshard < bin_infos[binind].n_shards); + bin = &arena->bins[binind].bin_shards[*binshard]; + malloc_mutex_lock(tsdn, &bin->lock); + + return bin; +} + void arena_tcache_fill_small(tsdn_t *tsdn, arena_t *arena, tcache_t *tcache, cache_bin_t *tbin, szind_t binind, uint64_t prof_accumbytes) { - unsigned i, nfill; - bin_t *bin; + unsigned i, nfill, cnt; assert(tbin->ncached == 0); if (config_prof && arena_prof_accum(tsdn, arena, prof_accumbytes)) { prof_idump(tsdn); } - bin = &arena->bins[binind]; - malloc_mutex_lock(tsdn, &bin->lock); + + unsigned binshard; + bin_t *bin = arena_bin_choose_lock(tsdn, arena, binind, &binshard); + for (i = 0, nfill = (tcache_bin_info[binind].ncached_max >> - tcache->lg_fill_div[binind]); i < nfill; i++) { + tcache->lg_fill_div[binind]); i < nfill; i += cnt) { extent_t *slab; - void *ptr; if ((slab = bin->slabcur) != NULL && extent_nfree_get(slab) > 0) { - ptr = arena_slab_reg_alloc(slab, &bin_infos[binind]); + unsigned tofill = nfill - i; + cnt = tofill < extent_nfree_get(slab) ? + tofill : extent_nfree_get(slab); + arena_slab_reg_alloc_batch( + slab, &bin_infos[binind], cnt, + tbin->avail - nfill + i); } else { - ptr = arena_bin_malloc_hard(tsdn, arena, bin, binind); - } - if (ptr == NULL) { + cnt = 1; + void *ptr = arena_bin_malloc_hard(tsdn, arena, bin, + binind, binshard); /* * OOM. tbin->avail isn't yet filled down to its first * element, so the successful allocations (if any) must * be moved just before tbin->avail before bailing out. */ - if (i > 0) { - memmove(tbin->avail - i, tbin->avail - nfill, - i * sizeof(void *)); + if (ptr == NULL) { + if (i > 0) { + memmove(tbin->avail - i, + tbin->avail - nfill, + i * sizeof(void *)); + } + break; } - break; + /* Insert such that low regions get used first. */ + *(tbin->avail - nfill + i) = ptr; } if (config_fill && unlikely(opt_junk_alloc)) { - arena_alloc_junk_small(ptr, &bin_infos[binind], true); + for (unsigned j = 0; j < cnt; j++) { + void* ptr = *(tbin->avail - nfill + i + j); + arena_alloc_junk_small(ptr, &bin_infos[binind], + true); + } } - /* Insert such that low regions get used first. */ - *(tbin->avail - nfill + i) = ptr; } if (config_stats) { bin->stats.nmalloc += i; bin->stats.nrequests += tbin->tstats.nrequests; bin->stats.curregs += i; bin->stats.nfills++; tbin->tstats.nrequests = 0; } malloc_mutex_unlock(tsdn, &bin->lock); tbin->ncached = i; arena_decay_tick(tsdn, arena); } void arena_alloc_junk_small(void *ptr, const bin_info_t *bin_info, bool zero) { if (!zero) { memset(ptr, JEMALLOC_ALLOC_JUNK, bin_info->reg_size); } } static void arena_dalloc_junk_small_impl(void *ptr, const bin_info_t *bin_info) { memset(ptr, JEMALLOC_FREE_JUNK, bin_info->reg_size); } arena_dalloc_junk_small_t *JET_MUTABLE arena_dalloc_junk_small = arena_dalloc_junk_small_impl; static void * arena_malloc_small(tsdn_t *tsdn, arena_t *arena, szind_t binind, bool zero) { void *ret; bin_t *bin; size_t usize; extent_t *slab; - assert(binind < NBINS); - bin = &arena->bins[binind]; + assert(binind < SC_NBINS); usize = sz_index2size(binind); + unsigned binshard; + bin = arena_bin_choose_lock(tsdn, arena, binind, &binshard); - malloc_mutex_lock(tsdn, &bin->lock); if ((slab = bin->slabcur) != NULL && extent_nfree_get(slab) > 0) { ret = arena_slab_reg_alloc(slab, &bin_infos[binind]); } else { - ret = arena_bin_malloc_hard(tsdn, arena, bin, binind); + ret = arena_bin_malloc_hard(tsdn, arena, bin, binind, binshard); } if (ret == NULL) { malloc_mutex_unlock(tsdn, &bin->lock); return NULL; } if (config_stats) { bin->stats.nmalloc++; bin->stats.nrequests++; bin->stats.curregs++; } malloc_mutex_unlock(tsdn, &bin->lock); if (config_prof && arena_prof_accum(tsdn, arena, usize)) { prof_idump(tsdn); } if (!zero) { if (config_fill) { if (unlikely(opt_junk_alloc)) { arena_alloc_junk_small(ret, &bin_infos[binind], false); } else if (unlikely(opt_zero)) { memset(ret, 0, usize); } } } else { if (config_fill && unlikely(opt_junk_alloc)) { arena_alloc_junk_small(ret, &bin_infos[binind], true); } memset(ret, 0, usize); } arena_decay_tick(tsdn, arena); return ret; } void * arena_malloc_hard(tsdn_t *tsdn, arena_t *arena, size_t size, szind_t ind, bool zero) { assert(!tsdn_null(tsdn) || arena != NULL); if (likely(!tsdn_null(tsdn))) { - arena = arena_choose(tsdn_tsd(tsdn), arena); + arena = arena_choose_maybe_huge(tsdn_tsd(tsdn), arena, size); } if (unlikely(arena == NULL)) { return NULL; } - if (likely(size <= SMALL_MAXCLASS)) { + if (likely(size <= SC_SMALL_MAXCLASS)) { return arena_malloc_small(tsdn, arena, ind, zero); } return large_malloc(tsdn, arena, sz_index2size(ind), zero); } void * arena_palloc(tsdn_t *tsdn, arena_t *arena, size_t usize, size_t alignment, bool zero, tcache_t *tcache) { void *ret; - if (usize <= SMALL_MAXCLASS && (alignment < PAGE || (alignment == PAGE - && (usize & PAGE_MASK) == 0))) { + if (usize <= SC_SMALL_MAXCLASS + && (alignment < PAGE + || (alignment == PAGE && (usize & PAGE_MASK) == 0))) { /* Small; alignment doesn't require special slab placement. */ ret = arena_malloc(tsdn, arena, usize, sz_size2index(usize), zero, tcache, true); } else { if (likely(alignment <= CACHELINE)) { ret = large_malloc(tsdn, arena, usize, zero); } else { ret = large_palloc(tsdn, arena, usize, alignment, zero); } } return ret; } void -arena_prof_promote(tsdn_t *tsdn, const void *ptr, size_t usize) { +arena_prof_promote(tsdn_t *tsdn, void *ptr, size_t usize) { cassert(config_prof); assert(ptr != NULL); - assert(isalloc(tsdn, ptr) == LARGE_MINCLASS); - assert(usize <= SMALL_MAXCLASS); + assert(isalloc(tsdn, ptr) == SC_LARGE_MINCLASS); + assert(usize <= SC_SMALL_MAXCLASS); + if (config_opt_safety_checks) { + safety_check_set_redzone(ptr, usize, SC_LARGE_MINCLASS); + } + rtree_ctx_t rtree_ctx_fallback; rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); extent_t *extent = rtree_extent_read(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr, true); arena_t *arena = extent_arena_get(extent); szind_t szind = sz_size2index(usize); extent_szind_set(extent, szind); rtree_szind_slab_update(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr, szind, false); prof_accum_cancel(tsdn, &arena->prof_accum, usize); assert(isalloc(tsdn, ptr) == usize); } static size_t arena_prof_demote(tsdn_t *tsdn, extent_t *extent, const void *ptr) { cassert(config_prof); assert(ptr != NULL); - extent_szind_set(extent, NBINS); + extent_szind_set(extent, SC_NBINS); rtree_ctx_t rtree_ctx_fallback; rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); rtree_szind_slab_update(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr, - NBINS, false); + SC_NBINS, false); - assert(isalloc(tsdn, ptr) == LARGE_MINCLASS); + assert(isalloc(tsdn, ptr) == SC_LARGE_MINCLASS); - return LARGE_MINCLASS; + return SC_LARGE_MINCLASS; } void arena_dalloc_promoted(tsdn_t *tsdn, void *ptr, tcache_t *tcache, bool slow_path) { cassert(config_prof); assert(opt_prof); extent_t *extent = iealloc(tsdn, ptr); - size_t usize = arena_prof_demote(tsdn, extent, ptr); - if (usize <= tcache_maxclass) { + size_t usize = extent_usize_get(extent); + size_t bumped_usize = arena_prof_demote(tsdn, extent, ptr); + if (config_opt_safety_checks && usize < SC_LARGE_MINCLASS) { + /* + * Currently, we only do redzoning for small sampled + * allocations. + */ + assert(bumped_usize == SC_LARGE_MINCLASS); + safety_check_verify_redzone(ptr, usize, bumped_usize); + } + if (bumped_usize <= tcache_maxclass && tcache != NULL) { tcache_dalloc_large(tsdn_tsd(tsdn), tcache, ptr, - sz_size2index(usize), slow_path); + sz_size2index(bumped_usize), slow_path); } else { large_dalloc(tsdn, extent); } } static void arena_dissociate_bin_slab(arena_t *arena, extent_t *slab, bin_t *bin) { /* Dissociate slab from bin. */ if (slab == bin->slabcur) { bin->slabcur = NULL; } else { szind_t binind = extent_szind_get(slab); const bin_info_t *bin_info = &bin_infos[binind]; /* * The following block's conditional is necessary because if the * slab only contains one region, then it never gets inserted * into the non-full slabs heap. */ if (bin_info->nregs == 1) { arena_bin_slabs_full_remove(arena, bin, slab); } else { arena_bin_slabs_nonfull_remove(bin, slab); } } } static void arena_dalloc_bin_slab(tsdn_t *tsdn, arena_t *arena, extent_t *slab, bin_t *bin) { assert(slab != bin->slabcur); malloc_mutex_unlock(tsdn, &bin->lock); /******************************/ arena_slab_dalloc(tsdn, arena, slab); /****************************/ malloc_mutex_lock(tsdn, &bin->lock); if (config_stats) { bin->stats.curslabs--; } } static void -arena_bin_lower_slab(UNUSED tsdn_t *tsdn, arena_t *arena, extent_t *slab, +arena_bin_lower_slab(tsdn_t *tsdn, arena_t *arena, extent_t *slab, bin_t *bin) { assert(extent_nfree_get(slab) > 0); /* * Make sure that if bin->slabcur is non-NULL, it refers to the * oldest/lowest non-full slab. It is okay to NULL slabcur out rather * than proactively keeping it pointing at the oldest/lowest non-full * slab. */ if (bin->slabcur != NULL && extent_snad_comp(bin->slabcur, slab) > 0) { /* Switch slabcur. */ if (extent_nfree_get(bin->slabcur) > 0) { arena_bin_slabs_nonfull_insert(bin, bin->slabcur); } else { arena_bin_slabs_full_insert(arena, bin, bin->slabcur); } bin->slabcur = slab; if (config_stats) { bin->stats.reslabs++; } } else { arena_bin_slabs_nonfull_insert(bin, slab); } } static void -arena_dalloc_bin_locked_impl(tsdn_t *tsdn, arena_t *arena, extent_t *slab, - void *ptr, bool junked) { +arena_dalloc_bin_locked_impl(tsdn_t *tsdn, arena_t *arena, bin_t *bin, + szind_t binind, extent_t *slab, void *ptr, bool junked) { arena_slab_data_t *slab_data = extent_slab_data_get(slab); - szind_t binind = extent_szind_get(slab); - bin_t *bin = &arena->bins[binind]; const bin_info_t *bin_info = &bin_infos[binind]; if (!junked && config_fill && unlikely(opt_junk_free)) { arena_dalloc_junk_small(ptr, bin_info); } arena_slab_reg_dalloc(slab, slab_data, ptr); unsigned nfree = extent_nfree_get(slab); if (nfree == bin_info->nregs) { arena_dissociate_bin_slab(arena, slab, bin); arena_dalloc_bin_slab(tsdn, arena, slab, bin); } else if (nfree == 1 && slab != bin->slabcur) { arena_bin_slabs_full_remove(arena, bin, slab); arena_bin_lower_slab(tsdn, arena, slab, bin); } if (config_stats) { bin->stats.ndalloc++; bin->stats.curregs--; } } void -arena_dalloc_bin_junked_locked(tsdn_t *tsdn, arena_t *arena, extent_t *extent, - void *ptr) { - arena_dalloc_bin_locked_impl(tsdn, arena, extent, ptr, true); +arena_dalloc_bin_junked_locked(tsdn_t *tsdn, arena_t *arena, bin_t *bin, + szind_t binind, extent_t *extent, void *ptr) { + arena_dalloc_bin_locked_impl(tsdn, arena, bin, binind, extent, ptr, + true); } static void arena_dalloc_bin(tsdn_t *tsdn, arena_t *arena, extent_t *extent, void *ptr) { szind_t binind = extent_szind_get(extent); - bin_t *bin = &arena->bins[binind]; + unsigned binshard = extent_binshard_get(extent); + bin_t *bin = &arena->bins[binind].bin_shards[binshard]; malloc_mutex_lock(tsdn, &bin->lock); - arena_dalloc_bin_locked_impl(tsdn, arena, extent, ptr, false); + arena_dalloc_bin_locked_impl(tsdn, arena, bin, binind, extent, ptr, + false); malloc_mutex_unlock(tsdn, &bin->lock); } void arena_dalloc_small(tsdn_t *tsdn, void *ptr) { extent_t *extent = iealloc(tsdn, ptr); arena_t *arena = extent_arena_get(extent); arena_dalloc_bin(tsdn, arena, extent, ptr); arena_decay_tick(tsdn, arena); } bool arena_ralloc_no_move(tsdn_t *tsdn, void *ptr, size_t oldsize, size_t size, - size_t extra, bool zero) { + size_t extra, bool zero, size_t *newsize) { + bool ret; /* Calls with non-zero extra had to clamp extra. */ - assert(extra == 0 || size + extra <= LARGE_MAXCLASS); + assert(extra == 0 || size + extra <= SC_LARGE_MAXCLASS); - if (unlikely(size > LARGE_MAXCLASS)) { - return true; + extent_t *extent = iealloc(tsdn, ptr); + if (unlikely(size > SC_LARGE_MAXCLASS)) { + ret = true; + goto done; } - extent_t *extent = iealloc(tsdn, ptr); size_t usize_min = sz_s2u(size); size_t usize_max = sz_s2u(size + extra); - if (likely(oldsize <= SMALL_MAXCLASS && usize_min <= SMALL_MAXCLASS)) { + if (likely(oldsize <= SC_SMALL_MAXCLASS && usize_min + <= SC_SMALL_MAXCLASS)) { /* * Avoid moving the allocation if the size class can be left the * same. */ assert(bin_infos[sz_size2index(oldsize)].reg_size == oldsize); - if ((usize_max > SMALL_MAXCLASS || sz_size2index(usize_max) != - sz_size2index(oldsize)) && (size > oldsize || usize_max < - oldsize)) { - return true; + if ((usize_max > SC_SMALL_MAXCLASS + || sz_size2index(usize_max) != sz_size2index(oldsize)) + && (size > oldsize || usize_max < oldsize)) { + ret = true; + goto done; } arena_decay_tick(tsdn, extent_arena_get(extent)); - return false; - } else if (oldsize >= LARGE_MINCLASS && usize_max >= LARGE_MINCLASS) { - return large_ralloc_no_move(tsdn, extent, usize_min, usize_max, + ret = false; + } else if (oldsize >= SC_LARGE_MINCLASS + && usize_max >= SC_LARGE_MINCLASS) { + ret = large_ralloc_no_move(tsdn, extent, usize_min, usize_max, zero); + } else { + ret = true; } +done: + assert(extent == iealloc(tsdn, ptr)); + *newsize = extent_usize_get(extent); - return true; + return ret; } static void * arena_ralloc_move_helper(tsdn_t *tsdn, arena_t *arena, size_t usize, size_t alignment, bool zero, tcache_t *tcache) { if (alignment == 0) { return arena_malloc(tsdn, arena, usize, sz_size2index(usize), zero, tcache, true); } usize = sz_sa2u(usize, alignment); - if (unlikely(usize == 0 || usize > LARGE_MAXCLASS)) { + if (unlikely(usize == 0 || usize > SC_LARGE_MAXCLASS)) { return NULL; } return ipalloct(tsdn, usize, alignment, zero, tcache, arena); } void * arena_ralloc(tsdn_t *tsdn, arena_t *arena, void *ptr, size_t oldsize, - size_t size, size_t alignment, bool zero, tcache_t *tcache) { + size_t size, size_t alignment, bool zero, tcache_t *tcache, + hook_ralloc_args_t *hook_args) { size_t usize = sz_s2u(size); - if (unlikely(usize == 0 || size > LARGE_MAXCLASS)) { + if (unlikely(usize == 0 || size > SC_LARGE_MAXCLASS)) { return NULL; } - if (likely(usize <= SMALL_MAXCLASS)) { + if (likely(usize <= SC_SMALL_MAXCLASS)) { /* Try to avoid moving the allocation. */ - if (!arena_ralloc_no_move(tsdn, ptr, oldsize, usize, 0, zero)) { + UNUSED size_t newsize; + if (!arena_ralloc_no_move(tsdn, ptr, oldsize, usize, 0, zero, + &newsize)) { + hook_invoke_expand(hook_args->is_realloc + ? hook_expand_realloc : hook_expand_rallocx, + ptr, oldsize, usize, (uintptr_t)ptr, + hook_args->args); return ptr; } } - if (oldsize >= LARGE_MINCLASS && usize >= LARGE_MINCLASS) { - return large_ralloc(tsdn, arena, iealloc(tsdn, ptr), usize, - alignment, zero, tcache); + if (oldsize >= SC_LARGE_MINCLASS + && usize >= SC_LARGE_MINCLASS) { + return large_ralloc(tsdn, arena, ptr, usize, + alignment, zero, tcache, hook_args); } /* * size and oldsize are different enough that we need to move the * object. In that case, fall back to allocating new space and copying. */ void *ret = arena_ralloc_move_helper(tsdn, arena, usize, alignment, zero, tcache); if (ret == NULL) { return NULL; } + hook_invoke_alloc(hook_args->is_realloc + ? hook_alloc_realloc : hook_alloc_rallocx, ret, (uintptr_t)ret, + hook_args->args); + hook_invoke_dalloc(hook_args->is_realloc + ? hook_dalloc_realloc : hook_dalloc_rallocx, ptr, hook_args->args); + /* * Junk/zero-filling were already done by * ipalloc()/arena_malloc(). */ - size_t copysize = (usize < oldsize) ? usize : oldsize; memcpy(ret, ptr, copysize); isdalloct(tsdn, ptr, oldsize, tcache, NULL, true); return ret; } dss_prec_t arena_dss_prec_get(arena_t *arena) { return (dss_prec_t)atomic_load_u(&arena->dss_prec, ATOMIC_ACQUIRE); } bool arena_dss_prec_set(arena_t *arena, dss_prec_t dss_prec) { if (!have_dss) { return (dss_prec != dss_prec_disabled); } atomic_store_u(&arena->dss_prec, (unsigned)dss_prec, ATOMIC_RELEASE); return false; } ssize_t arena_dirty_decay_ms_default_get(void) { return atomic_load_zd(&dirty_decay_ms_default, ATOMIC_RELAXED); } bool arena_dirty_decay_ms_default_set(ssize_t decay_ms) { if (!arena_decay_ms_valid(decay_ms)) { return true; } atomic_store_zd(&dirty_decay_ms_default, decay_ms, ATOMIC_RELAXED); return false; } ssize_t arena_muzzy_decay_ms_default_get(void) { return atomic_load_zd(&muzzy_decay_ms_default, ATOMIC_RELAXED); } bool arena_muzzy_decay_ms_default_set(ssize_t decay_ms) { if (!arena_decay_ms_valid(decay_ms)) { return true; } atomic_store_zd(&muzzy_decay_ms_default, decay_ms, ATOMIC_RELAXED); return false; } bool arena_retain_grow_limit_get_set(tsd_t *tsd, arena_t *arena, size_t *old_limit, size_t *new_limit) { assert(opt_retain); pszind_t new_ind JEMALLOC_CC_SILENCE_INIT(0); if (new_limit != NULL) { size_t limit = *new_limit; /* Grow no more than the new limit. */ - if ((new_ind = sz_psz2ind(limit + 1) - 1) > - EXTENT_GROW_MAX_PIND) { + if ((new_ind = sz_psz2ind(limit + 1) - 1) >= SC_NPSIZES) { return true; } } malloc_mutex_lock(tsd_tsdn(tsd), &arena->extent_grow_mtx); if (old_limit != NULL) { *old_limit = sz_pind2sz(arena->retain_grow_limit); } if (new_limit != NULL) { arena->retain_grow_limit = new_ind; } malloc_mutex_unlock(tsd_tsdn(tsd), &arena->extent_grow_mtx); return false; } unsigned arena_nthreads_get(arena_t *arena, bool internal) { return atomic_load_u(&arena->nthreads[internal], ATOMIC_RELAXED); } void arena_nthreads_inc(arena_t *arena, bool internal) { atomic_fetch_add_u(&arena->nthreads[internal], 1, ATOMIC_RELAXED); } void arena_nthreads_dec(arena_t *arena, bool internal) { atomic_fetch_sub_u(&arena->nthreads[internal], 1, ATOMIC_RELAXED); } size_t arena_extent_sn_next(arena_t *arena) { return atomic_fetch_add_zu(&arena->extent_sn_next, 1, ATOMIC_RELAXED); } arena_t * arena_new(tsdn_t *tsdn, unsigned ind, extent_hooks_t *extent_hooks) { arena_t *arena; base_t *base; unsigned i; if (ind == 0) { base = b0get(); } else { base = base_new(tsdn, ind, extent_hooks); if (base == NULL) { return NULL; } } - arena = (arena_t *)base_alloc(tsdn, base, sizeof(arena_t), CACHELINE); + unsigned nbins_total = 0; + for (i = 0; i < SC_NBINS; i++) { + nbins_total += bin_infos[i].n_shards; + } + size_t arena_size = sizeof(arena_t) + sizeof(bin_t) * nbins_total; + arena = (arena_t *)base_alloc(tsdn, base, arena_size, CACHELINE); if (arena == NULL) { goto label_error; } atomic_store_u(&arena->nthreads[0], 0, ATOMIC_RELAXED); atomic_store_u(&arena->nthreads[1], 0, ATOMIC_RELAXED); arena->last_thd = NULL; if (config_stats) { if (arena_stats_init(tsdn, &arena->stats)) { goto label_error; } ql_new(&arena->tcache_ql); ql_new(&arena->cache_bin_array_descriptor_ql); if (malloc_mutex_init(&arena->tcache_ql_mtx, "tcache_ql", WITNESS_RANK_TCACHE_QL, malloc_mutex_rank_exclusive)) { goto label_error; } } if (config_prof) { if (prof_accum_init(tsdn, &arena->prof_accum)) { goto label_error; } } if (config_cache_oblivious) { /* * A nondeterministic seed based on the address of arena reduces * the likelihood of lockstep non-uniform cache index * utilization among identical concurrent processes, but at the * cost of test repeatability. For debug builds, instead use a * deterministic seed. */ atomic_store_zu(&arena->offset_state, config_debug ? ind : (size_t)(uintptr_t)arena, ATOMIC_RELAXED); } atomic_store_zu(&arena->extent_sn_next, 0, ATOMIC_RELAXED); atomic_store_u(&arena->dss_prec, (unsigned)extent_dss_prec_get(), ATOMIC_RELAXED); atomic_store_zu(&arena->nactive, 0, ATOMIC_RELAXED); extent_list_init(&arena->large); if (malloc_mutex_init(&arena->large_mtx, "arena_large", WITNESS_RANK_ARENA_LARGE, malloc_mutex_rank_exclusive)) { goto label_error; } /* * Delay coalescing for dirty extents despite the disruptive effect on * memory layout for best-fit extent allocation, since cached extents * are likely to be reused soon after deallocation, and the cost of * merging/splitting extents is non-trivial. */ if (extents_init(tsdn, &arena->extents_dirty, extent_state_dirty, true)) { goto label_error; } /* * Coalesce muzzy extents immediately, because operations on them are in * the critical path much less often than for dirty extents. */ if (extents_init(tsdn, &arena->extents_muzzy, extent_state_muzzy, false)) { goto label_error; } /* * Coalesce retained extents immediately, in part because they will * never be evicted (and therefore there's no opportunity for delayed * coalescing), but also because operations on retained extents are not * in the critical path. */ if (extents_init(tsdn, &arena->extents_retained, extent_state_retained, false)) { goto label_error; } if (arena_decay_init(&arena->decay_dirty, arena_dirty_decay_ms_default_get(), &arena->stats.decay_dirty)) { goto label_error; } if (arena_decay_init(&arena->decay_muzzy, arena_muzzy_decay_ms_default_get(), &arena->stats.decay_muzzy)) { goto label_error; } arena->extent_grow_next = sz_psz2ind(HUGEPAGE); - arena->retain_grow_limit = EXTENT_GROW_MAX_PIND; + arena->retain_grow_limit = sz_psz2ind(SC_LARGE_MAXCLASS); if (malloc_mutex_init(&arena->extent_grow_mtx, "extent_grow", WITNESS_RANK_EXTENT_GROW, malloc_mutex_rank_exclusive)) { goto label_error; } extent_avail_new(&arena->extent_avail); if (malloc_mutex_init(&arena->extent_avail_mtx, "extent_avail", WITNESS_RANK_EXTENT_AVAIL, malloc_mutex_rank_exclusive)) { goto label_error; } /* Initialize bins. */ - for (i = 0; i < NBINS; i++) { - bool err = bin_init(&arena->bins[i]); - if (err) { - goto label_error; + uintptr_t bin_addr = (uintptr_t)arena + sizeof(arena_t); + atomic_store_u(&arena->binshard_next, 0, ATOMIC_RELEASE); + for (i = 0; i < SC_NBINS; i++) { + unsigned nshards = bin_infos[i].n_shards; + arena->bins[i].bin_shards = (bin_t *)bin_addr; + bin_addr += nshards * sizeof(bin_t); + for (unsigned j = 0; j < nshards; j++) { + bool err = bin_init(&arena->bins[i].bin_shards[j]); + if (err) { + goto label_error; + } } } + assert(bin_addr == (uintptr_t)arena + arena_size); arena->base = base; /* Set arena before creating background threads. */ arena_set(ind, arena); nstime_init(&arena->create_time, 0); nstime_update(&arena->create_time); /* We don't support reentrancy for arena 0 bootstrapping. */ if (ind != 0) { /* * If we're here, then arena 0 already exists, so bootstrapping * is done enough that we should have tsd. */ assert(!tsdn_null(tsdn)); pre_reentrancy(tsdn_tsd(tsdn), arena); - if (hooks_arena_new_hook) { - hooks_arena_new_hook(); + if (test_hooks_arena_new_hook) { + test_hooks_arena_new_hook(); } post_reentrancy(tsdn_tsd(tsdn)); } return arena; label_error: if (ind != 0) { base_delete(tsdn, base); } return NULL; } +arena_t * +arena_choose_huge(tsd_t *tsd) { + /* huge_arena_ind can be 0 during init (will use a0). */ + if (huge_arena_ind == 0) { + assert(!malloc_initialized()); + } + + arena_t *huge_arena = arena_get(tsd_tsdn(tsd), huge_arena_ind, false); + if (huge_arena == NULL) { + /* Create the huge arena on demand. */ + assert(huge_arena_ind != 0); + huge_arena = arena_get(tsd_tsdn(tsd), huge_arena_ind, true); + if (huge_arena == NULL) { + return NULL; + } + /* + * Purge eagerly for huge allocations, because: 1) number of + * huge allocations is usually small, which means ticker based + * decay is not reliable; and 2) less immediate reuse is + * expected for huge allocations. + */ + if (arena_dirty_decay_ms_default_get() > 0) { + arena_dirty_decay_ms_set(tsd_tsdn(tsd), huge_arena, 0); + } + if (arena_muzzy_decay_ms_default_get() > 0) { + arena_muzzy_decay_ms_set(tsd_tsdn(tsd), huge_arena, 0); + } + } + + return huge_arena; +} + +bool +arena_init_huge(void) { + bool huge_enabled; + + /* The threshold should be large size class. */ + if (opt_oversize_threshold > SC_LARGE_MAXCLASS || + opt_oversize_threshold < SC_LARGE_MINCLASS) { + opt_oversize_threshold = 0; + oversize_threshold = SC_LARGE_MAXCLASS + PAGE; + huge_enabled = false; + } else { + /* Reserve the index for the huge arena. */ + huge_arena_ind = narenas_total_get(); + oversize_threshold = opt_oversize_threshold; + huge_enabled = true; + } + + return huge_enabled; +} + +bool +arena_is_huge(unsigned arena_ind) { + if (huge_arena_ind == 0) { + return false; + } + return (arena_ind == huge_arena_ind); +} + void -arena_boot(void) { +arena_boot(sc_data_t *sc_data) { arena_dirty_decay_ms_default_set(opt_dirty_decay_ms); arena_muzzy_decay_ms_default_set(opt_muzzy_decay_ms); -#define REGIND_bin_yes(index, reg_size) \ - div_init(&arena_binind_div_info[(index)], (reg_size)); -#define REGIND_bin_no(index, reg_size) -#define SC(index, lg_grp, lg_delta, ndelta, psz, bin, pgs, \ - lg_delta_lookup) \ - REGIND_bin_##bin(index, (1U<sc[i]; + div_init(&arena_binind_div_info[i], + (1U << sc->lg_base) + (sc->ndelta << sc->lg_delta)); + } } void arena_prefork0(tsdn_t *tsdn, arena_t *arena) { malloc_mutex_prefork(tsdn, &arena->decay_dirty.mtx); malloc_mutex_prefork(tsdn, &arena->decay_muzzy.mtx); } void arena_prefork1(tsdn_t *tsdn, arena_t *arena) { if (config_stats) { malloc_mutex_prefork(tsdn, &arena->tcache_ql_mtx); } } void arena_prefork2(tsdn_t *tsdn, arena_t *arena) { malloc_mutex_prefork(tsdn, &arena->extent_grow_mtx); } void arena_prefork3(tsdn_t *tsdn, arena_t *arena) { extents_prefork(tsdn, &arena->extents_dirty); extents_prefork(tsdn, &arena->extents_muzzy); extents_prefork(tsdn, &arena->extents_retained); } void arena_prefork4(tsdn_t *tsdn, arena_t *arena) { malloc_mutex_prefork(tsdn, &arena->extent_avail_mtx); } void arena_prefork5(tsdn_t *tsdn, arena_t *arena) { base_prefork(tsdn, arena->base); } void arena_prefork6(tsdn_t *tsdn, arena_t *arena) { malloc_mutex_prefork(tsdn, &arena->large_mtx); } void arena_prefork7(tsdn_t *tsdn, arena_t *arena) { - for (unsigned i = 0; i < NBINS; i++) { - bin_prefork(tsdn, &arena->bins[i]); + for (unsigned i = 0; i < SC_NBINS; i++) { + for (unsigned j = 0; j < bin_infos[i].n_shards; j++) { + bin_prefork(tsdn, &arena->bins[i].bin_shards[j]); + } } } void arena_postfork_parent(tsdn_t *tsdn, arena_t *arena) { unsigned i; - for (i = 0; i < NBINS; i++) { - bin_postfork_parent(tsdn, &arena->bins[i]); + for (i = 0; i < SC_NBINS; i++) { + for (unsigned j = 0; j < bin_infos[i].n_shards; j++) { + bin_postfork_parent(tsdn, + &arena->bins[i].bin_shards[j]); + } } malloc_mutex_postfork_parent(tsdn, &arena->large_mtx); base_postfork_parent(tsdn, arena->base); malloc_mutex_postfork_parent(tsdn, &arena->extent_avail_mtx); extents_postfork_parent(tsdn, &arena->extents_dirty); extents_postfork_parent(tsdn, &arena->extents_muzzy); extents_postfork_parent(tsdn, &arena->extents_retained); malloc_mutex_postfork_parent(tsdn, &arena->extent_grow_mtx); malloc_mutex_postfork_parent(tsdn, &arena->decay_dirty.mtx); malloc_mutex_postfork_parent(tsdn, &arena->decay_muzzy.mtx); if (config_stats) { malloc_mutex_postfork_parent(tsdn, &arena->tcache_ql_mtx); } } void arena_postfork_child(tsdn_t *tsdn, arena_t *arena) { unsigned i; atomic_store_u(&arena->nthreads[0], 0, ATOMIC_RELAXED); atomic_store_u(&arena->nthreads[1], 0, ATOMIC_RELAXED); if (tsd_arena_get(tsdn_tsd(tsdn)) == arena) { arena_nthreads_inc(arena, false); } if (tsd_iarena_get(tsdn_tsd(tsdn)) == arena) { arena_nthreads_inc(arena, true); } if (config_stats) { ql_new(&arena->tcache_ql); ql_new(&arena->cache_bin_array_descriptor_ql); tcache_t *tcache = tcache_get(tsdn_tsd(tsdn)); if (tcache != NULL && tcache->arena == arena) { ql_elm_new(tcache, link); ql_tail_insert(&arena->tcache_ql, tcache, link); cache_bin_array_descriptor_init( &tcache->cache_bin_array_descriptor, tcache->bins_small, tcache->bins_large); ql_tail_insert(&arena->cache_bin_array_descriptor_ql, &tcache->cache_bin_array_descriptor, link); } } - for (i = 0; i < NBINS; i++) { - bin_postfork_child(tsdn, &arena->bins[i]); + for (i = 0; i < SC_NBINS; i++) { + for (unsigned j = 0; j < bin_infos[i].n_shards; j++) { + bin_postfork_child(tsdn, &arena->bins[i].bin_shards[j]); + } } malloc_mutex_postfork_child(tsdn, &arena->large_mtx); base_postfork_child(tsdn, arena->base); malloc_mutex_postfork_child(tsdn, &arena->extent_avail_mtx); extents_postfork_child(tsdn, &arena->extents_dirty); extents_postfork_child(tsdn, &arena->extents_muzzy); extents_postfork_child(tsdn, &arena->extents_retained); malloc_mutex_postfork_child(tsdn, &arena->extent_grow_mtx); malloc_mutex_postfork_child(tsdn, &arena->decay_dirty.mtx); malloc_mutex_postfork_child(tsdn, &arena->decay_muzzy.mtx); if (config_stats) { malloc_mutex_postfork_child(tsdn, &arena->tcache_ql_mtx); } } Index: head/contrib/jemalloc/src/background_thread.c =================================================================== --- head/contrib/jemalloc/src/background_thread.c (revision 360232) +++ head/contrib/jemalloc/src/background_thread.c (revision 360233) @@ -1,909 +1,939 @@ #define JEMALLOC_BACKGROUND_THREAD_C_ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/jemalloc_internal_includes.h" #include "jemalloc/internal/assert.h" +JEMALLOC_DIAGNOSTIC_DISABLE_SPURIOUS + /******************************************************************************/ /* Data. */ /* This option should be opt-in only. */ #define BACKGROUND_THREAD_DEFAULT false /* Read-only after initialization. */ bool opt_background_thread = BACKGROUND_THREAD_DEFAULT; -size_t opt_max_background_threads = MAX_BACKGROUND_THREAD_LIMIT; +size_t opt_max_background_threads = MAX_BACKGROUND_THREAD_LIMIT + 1; /* Used for thread creation, termination and stats. */ malloc_mutex_t background_thread_lock; /* Indicates global state. Atomic because decay reads this w/o locking. */ atomic_b_t background_thread_enabled_state; size_t n_background_threads; size_t max_background_threads; /* Thread info per-index. */ background_thread_info_t *background_thread_info; -/* False if no necessary runtime support. */ -bool can_enable_background_thread; - /******************************************************************************/ #ifdef JEMALLOC_PTHREAD_CREATE_WRAPPER -#include static int (*pthread_create_fptr)(pthread_t *__restrict, const pthread_attr_t *, void *(*)(void *), void *__restrict); static void pthread_create_wrapper_init(void) { #ifdef JEMALLOC_LAZY_LOCK if (!isthreaded) { isthreaded = true; } #endif } int pthread_create_wrapper(pthread_t *__restrict thread, const pthread_attr_t *attr, void *(*start_routine)(void *), void *__restrict arg) { pthread_create_wrapper_init(); return pthread_create_fptr(thread, attr, start_routine, arg); } #endif /* JEMALLOC_PTHREAD_CREATE_WRAPPER */ #ifndef JEMALLOC_BACKGROUND_THREAD #define NOT_REACHED { not_reached(); } bool background_thread_create(tsd_t *tsd, unsigned arena_ind) NOT_REACHED bool background_threads_enable(tsd_t *tsd) NOT_REACHED bool background_threads_disable(tsd_t *tsd) NOT_REACHED void background_thread_interval_check(tsdn_t *tsdn, arena_t *arena, arena_decay_t *decay, size_t npages_new) NOT_REACHED void background_thread_prefork0(tsdn_t *tsdn) NOT_REACHED void background_thread_prefork1(tsdn_t *tsdn) NOT_REACHED void background_thread_postfork_parent(tsdn_t *tsdn) NOT_REACHED void background_thread_postfork_child(tsdn_t *tsdn) NOT_REACHED bool background_thread_stats_read(tsdn_t *tsdn, background_thread_stats_t *stats) NOT_REACHED void background_thread_ctl_init(tsdn_t *tsdn) NOT_REACHED #undef NOT_REACHED #else static bool background_thread_enabled_at_fork; static void background_thread_info_init(tsdn_t *tsdn, background_thread_info_t *info) { background_thread_wakeup_time_set(tsdn, info, 0); info->npages_to_purge_new = 0; if (config_stats) { info->tot_n_runs = 0; nstime_init(&info->tot_sleep_time, 0); } } static inline bool -set_current_thread_affinity(UNUSED int cpu) { +set_current_thread_affinity(int cpu) { #if defined(JEMALLOC_HAVE_SCHED_SETAFFINITY) cpu_set_t cpuset; CPU_ZERO(&cpuset); CPU_SET(cpu, &cpuset); int ret = sched_setaffinity(0, sizeof(cpu_set_t), &cpuset); return (ret != 0); #else return false; #endif } /* Threshold for determining when to wake up the background thread. */ #define BACKGROUND_THREAD_NPAGES_THRESHOLD UINT64_C(1024) #define BILLION UINT64_C(1000000000) /* Minimal sleep interval 100 ms. */ #define BACKGROUND_THREAD_MIN_INTERVAL_NS (BILLION / 10) static inline size_t decay_npurge_after_interval(arena_decay_t *decay, size_t interval) { size_t i; uint64_t sum = 0; for (i = 0; i < interval; i++) { sum += decay->backlog[i] * h_steps[i]; } for (; i < SMOOTHSTEP_NSTEPS; i++) { sum += decay->backlog[i] * (h_steps[i] - h_steps[i - interval]); } return (size_t)(sum >> SMOOTHSTEP_BFP); } static uint64_t arena_decay_compute_purge_interval_impl(tsdn_t *tsdn, arena_decay_t *decay, extents_t *extents) { if (malloc_mutex_trylock(tsdn, &decay->mtx)) { /* Use minimal interval if decay is contended. */ return BACKGROUND_THREAD_MIN_INTERVAL_NS; } uint64_t interval; ssize_t decay_time = atomic_load_zd(&decay->time_ms, ATOMIC_RELAXED); if (decay_time <= 0) { /* Purging is eagerly done or disabled currently. */ interval = BACKGROUND_THREAD_INDEFINITE_SLEEP; goto label_done; } uint64_t decay_interval_ns = nstime_ns(&decay->interval); assert(decay_interval_ns > 0); size_t npages = extents_npages_get(extents); if (npages == 0) { unsigned i; for (i = 0; i < SMOOTHSTEP_NSTEPS; i++) { if (decay->backlog[i] > 0) { break; } } if (i == SMOOTHSTEP_NSTEPS) { /* No dirty pages recorded. Sleep indefinitely. */ interval = BACKGROUND_THREAD_INDEFINITE_SLEEP; goto label_done; } } if (npages <= BACKGROUND_THREAD_NPAGES_THRESHOLD) { /* Use max interval. */ interval = decay_interval_ns * SMOOTHSTEP_NSTEPS; goto label_done; } size_t lb = BACKGROUND_THREAD_MIN_INTERVAL_NS / decay_interval_ns; size_t ub = SMOOTHSTEP_NSTEPS; /* Minimal 2 intervals to ensure reaching next epoch deadline. */ lb = (lb < 2) ? 2 : lb; if ((decay_interval_ns * ub <= BACKGROUND_THREAD_MIN_INTERVAL_NS) || (lb + 2 > ub)) { interval = BACKGROUND_THREAD_MIN_INTERVAL_NS; goto label_done; } assert(lb + 2 <= ub); size_t npurge_lb, npurge_ub; npurge_lb = decay_npurge_after_interval(decay, lb); if (npurge_lb > BACKGROUND_THREAD_NPAGES_THRESHOLD) { interval = decay_interval_ns * lb; goto label_done; } npurge_ub = decay_npurge_after_interval(decay, ub); if (npurge_ub < BACKGROUND_THREAD_NPAGES_THRESHOLD) { interval = decay_interval_ns * ub; goto label_done; } unsigned n_search = 0; size_t target, npurge; while ((npurge_lb + BACKGROUND_THREAD_NPAGES_THRESHOLD < npurge_ub) && (lb + 2 < ub)) { target = (lb + ub) / 2; npurge = decay_npurge_after_interval(decay, target); if (npurge > BACKGROUND_THREAD_NPAGES_THRESHOLD) { ub = target; npurge_ub = npurge; } else { lb = target; npurge_lb = npurge; } assert(n_search++ < lg_floor(SMOOTHSTEP_NSTEPS) + 1); } interval = decay_interval_ns * (ub + lb) / 2; label_done: interval = (interval < BACKGROUND_THREAD_MIN_INTERVAL_NS) ? BACKGROUND_THREAD_MIN_INTERVAL_NS : interval; malloc_mutex_unlock(tsdn, &decay->mtx); return interval; } /* Compute purge interval for background threads. */ static uint64_t arena_decay_compute_purge_interval(tsdn_t *tsdn, arena_t *arena) { uint64_t i1, i2; i1 = arena_decay_compute_purge_interval_impl(tsdn, &arena->decay_dirty, &arena->extents_dirty); if (i1 == BACKGROUND_THREAD_MIN_INTERVAL_NS) { return i1; } i2 = arena_decay_compute_purge_interval_impl(tsdn, &arena->decay_muzzy, &arena->extents_muzzy); return i1 < i2 ? i1 : i2; } static void background_thread_sleep(tsdn_t *tsdn, background_thread_info_t *info, uint64_t interval) { if (config_stats) { info->tot_n_runs++; } info->npages_to_purge_new = 0; struct timeval tv; /* Specific clock required by timedwait. */ gettimeofday(&tv, NULL); nstime_t before_sleep; nstime_init2(&before_sleep, tv.tv_sec, tv.tv_usec * 1000); int ret; if (interval == BACKGROUND_THREAD_INDEFINITE_SLEEP) { assert(background_thread_indefinite_sleep(info)); ret = pthread_cond_wait(&info->cond, &info->mtx.lock); assert(ret == 0); } else { assert(interval >= BACKGROUND_THREAD_MIN_INTERVAL_NS && interval <= BACKGROUND_THREAD_INDEFINITE_SLEEP); /* We need malloc clock (can be different from tv). */ nstime_t next_wakeup; nstime_init(&next_wakeup, 0); nstime_update(&next_wakeup); nstime_iadd(&next_wakeup, interval); assert(nstime_ns(&next_wakeup) < BACKGROUND_THREAD_INDEFINITE_SLEEP); background_thread_wakeup_time_set(tsdn, info, nstime_ns(&next_wakeup)); nstime_t ts_wakeup; nstime_copy(&ts_wakeup, &before_sleep); nstime_iadd(&ts_wakeup, interval); struct timespec ts; ts.tv_sec = (size_t)nstime_sec(&ts_wakeup); ts.tv_nsec = (size_t)nstime_nsec(&ts_wakeup); assert(!background_thread_indefinite_sleep(info)); ret = pthread_cond_timedwait(&info->cond, &info->mtx.lock, &ts); assert(ret == ETIMEDOUT || ret == 0); background_thread_wakeup_time_set(tsdn, info, BACKGROUND_THREAD_INDEFINITE_SLEEP); } if (config_stats) { gettimeofday(&tv, NULL); nstime_t after_sleep; nstime_init2(&after_sleep, tv.tv_sec, tv.tv_usec * 1000); if (nstime_compare(&after_sleep, &before_sleep) > 0) { nstime_subtract(&after_sleep, &before_sleep); nstime_add(&info->tot_sleep_time, &after_sleep); } } } static bool background_thread_pause_check(tsdn_t *tsdn, background_thread_info_t *info) { if (unlikely(info->state == background_thread_paused)) { malloc_mutex_unlock(tsdn, &info->mtx); /* Wait on global lock to update status. */ malloc_mutex_lock(tsdn, &background_thread_lock); malloc_mutex_unlock(tsdn, &background_thread_lock); malloc_mutex_lock(tsdn, &info->mtx); return true; } return false; } static inline void background_work_sleep_once(tsdn_t *tsdn, background_thread_info_t *info, unsigned ind) { uint64_t min_interval = BACKGROUND_THREAD_INDEFINITE_SLEEP; unsigned narenas = narenas_total_get(); for (unsigned i = ind; i < narenas; i += max_background_threads) { arena_t *arena = arena_get(tsdn, i, false); if (!arena) { continue; } arena_decay(tsdn, arena, true, false); if (min_interval == BACKGROUND_THREAD_MIN_INTERVAL_NS) { /* Min interval will be used. */ continue; } uint64_t interval = arena_decay_compute_purge_interval(tsdn, arena); assert(interval >= BACKGROUND_THREAD_MIN_INTERVAL_NS); if (min_interval > interval) { min_interval = interval; } } background_thread_sleep(tsdn, info, min_interval); } static bool background_threads_disable_single(tsd_t *tsd, background_thread_info_t *info) { if (info == &background_thread_info[0]) { malloc_mutex_assert_owner(tsd_tsdn(tsd), &background_thread_lock); } else { malloc_mutex_assert_not_owner(tsd_tsdn(tsd), &background_thread_lock); } pre_reentrancy(tsd, NULL); malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx); bool has_thread; assert(info->state != background_thread_paused); if (info->state == background_thread_started) { has_thread = true; info->state = background_thread_stopped; pthread_cond_signal(&info->cond); } else { has_thread = false; } malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx); if (!has_thread) { post_reentrancy(tsd); return false; } void *ret; if (pthread_join(info->thread, &ret)) { post_reentrancy(tsd); return true; } assert(ret == NULL); n_background_threads--; post_reentrancy(tsd); return false; } static void *background_thread_entry(void *ind_arg); static int background_thread_create_signals_masked(pthread_t *thread, const pthread_attr_t *attr, void *(*start_routine)(void *), void *arg) { /* * Mask signals during thread creation so that the thread inherits * an empty signal set. */ sigset_t set; sigfillset(&set); sigset_t oldset; int mask_err = pthread_sigmask(SIG_SETMASK, &set, &oldset); if (mask_err != 0) { return mask_err; } int create_err = pthread_create_wrapper(thread, attr, start_routine, arg); /* * Restore the signal mask. Failure to restore the signal mask here * changes program behavior. */ int restore_err = pthread_sigmask(SIG_SETMASK, &oldset, NULL); if (restore_err != 0) { malloc_printf(": background thread creation " "failed (%d), and signal mask restoration failed " "(%d)\n", create_err, restore_err); if (opt_abort) { abort(); } } return create_err; } static bool check_background_thread_creation(tsd_t *tsd, unsigned *n_created, bool *created_threads) { bool ret = false; if (likely(*n_created == n_background_threads)) { return ret; } tsdn_t *tsdn = tsd_tsdn(tsd); malloc_mutex_unlock(tsdn, &background_thread_info[0].mtx); for (unsigned i = 1; i < max_background_threads; i++) { if (created_threads[i]) { continue; } background_thread_info_t *info = &background_thread_info[i]; malloc_mutex_lock(tsdn, &info->mtx); /* * In case of the background_thread_paused state because of * arena reset, delay the creation. */ bool create = (info->state == background_thread_started); malloc_mutex_unlock(tsdn, &info->mtx); if (!create) { continue; } pre_reentrancy(tsd, NULL); int err = background_thread_create_signals_masked(&info->thread, NULL, background_thread_entry, (void *)(uintptr_t)i); post_reentrancy(tsd); if (err == 0) { (*n_created)++; created_threads[i] = true; } else { malloc_printf(": background thread " "creation failed (%d)\n", err); if (opt_abort) { abort(); } } /* Return to restart the loop since we unlocked. */ ret = true; break; } malloc_mutex_lock(tsdn, &background_thread_info[0].mtx); return ret; } static void background_thread0_work(tsd_t *tsd) { /* Thread0 is also responsible for launching / terminating threads. */ VARIABLE_ARRAY(bool, created_threads, max_background_threads); unsigned i; for (i = 1; i < max_background_threads; i++) { created_threads[i] = false; } /* Start working, and create more threads when asked. */ unsigned n_created = 1; while (background_thread_info[0].state != background_thread_stopped) { if (background_thread_pause_check(tsd_tsdn(tsd), &background_thread_info[0])) { continue; } if (check_background_thread_creation(tsd, &n_created, (bool *)&created_threads)) { continue; } background_work_sleep_once(tsd_tsdn(tsd), &background_thread_info[0], 0); } /* * Shut down other threads at exit. Note that the ctl thread is holding * the global background_thread mutex (and is waiting) for us. */ assert(!background_thread_enabled()); for (i = 1; i < max_background_threads; i++) { background_thread_info_t *info = &background_thread_info[i]; assert(info->state != background_thread_paused); if (created_threads[i]) { background_threads_disable_single(tsd, info); } else { malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx); if (info->state != background_thread_stopped) { /* The thread was not created. */ assert(info->state == background_thread_started); n_background_threads--; info->state = background_thread_stopped; } malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx); } } background_thread_info[0].state = background_thread_stopped; assert(n_background_threads == 1); } static void background_work(tsd_t *tsd, unsigned ind) { background_thread_info_t *info = &background_thread_info[ind]; malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx); background_thread_wakeup_time_set(tsd_tsdn(tsd), info, BACKGROUND_THREAD_INDEFINITE_SLEEP); if (ind == 0) { background_thread0_work(tsd); } else { while (info->state != background_thread_stopped) { if (background_thread_pause_check(tsd_tsdn(tsd), info)) { continue; } background_work_sleep_once(tsd_tsdn(tsd), info, ind); } } assert(info->state == background_thread_stopped); background_thread_wakeup_time_set(tsd_tsdn(tsd), info, 0); malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx); } static void * background_thread_entry(void *ind_arg) { unsigned thread_ind = (unsigned)(uintptr_t)ind_arg; assert(thread_ind < max_background_threads); #ifdef JEMALLOC_HAVE_PTHREAD_SETNAME_NP pthread_setname_np(pthread_self(), "jemalloc_bg_thd"); +#elif defined(__FreeBSD__) + pthread_set_name_np(pthread_self(), "jemalloc_bg_thd"); #endif if (opt_percpu_arena != percpu_arena_disabled) { set_current_thread_affinity((int)thread_ind); } /* * Start periodic background work. We use internal tsd which avoids * side effects, for example triggering new arena creation (which in * turn triggers another background thread creation). */ background_work(tsd_internal_fetch(), thread_ind); assert(pthread_equal(pthread_self(), background_thread_info[thread_ind].thread)); return NULL; } static void background_thread_init(tsd_t *tsd, background_thread_info_t *info) { malloc_mutex_assert_owner(tsd_tsdn(tsd), &background_thread_lock); info->state = background_thread_started; background_thread_info_init(tsd_tsdn(tsd), info); n_background_threads++; } -/* Create a new background thread if needed. */ -bool -background_thread_create(tsd_t *tsd, unsigned arena_ind) { +static bool +background_thread_create_locked(tsd_t *tsd, unsigned arena_ind) { assert(have_background_thread); malloc_mutex_assert_owner(tsd_tsdn(tsd), &background_thread_lock); /* We create at most NCPUs threads. */ size_t thread_ind = arena_ind % max_background_threads; background_thread_info_t *info = &background_thread_info[thread_ind]; bool need_new_thread; malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx); need_new_thread = background_thread_enabled() && (info->state == background_thread_stopped); if (need_new_thread) { background_thread_init(tsd, info); } malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx); if (!need_new_thread) { return false; } if (arena_ind != 0) { /* Threads are created asynchronously by Thread 0. */ background_thread_info_t *t0 = &background_thread_info[0]; malloc_mutex_lock(tsd_tsdn(tsd), &t0->mtx); assert(t0->state == background_thread_started); pthread_cond_signal(&t0->cond); malloc_mutex_unlock(tsd_tsdn(tsd), &t0->mtx); return false; } pre_reentrancy(tsd, NULL); /* * To avoid complications (besides reentrancy), create internal * background threads with the underlying pthread_create. */ int err = background_thread_create_signals_masked(&info->thread, NULL, background_thread_entry, (void *)thread_ind); post_reentrancy(tsd); if (err != 0) { malloc_printf(": arena 0 background thread creation " "failed (%d)\n", err); malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx); info->state = background_thread_stopped; n_background_threads--; malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx); return true; } return false; } +/* Create a new background thread if needed. */ bool +background_thread_create(tsd_t *tsd, unsigned arena_ind) { + assert(have_background_thread); + + bool ret; + malloc_mutex_lock(tsd_tsdn(tsd), &background_thread_lock); + ret = background_thread_create_locked(tsd, arena_ind); + malloc_mutex_unlock(tsd_tsdn(tsd), &background_thread_lock); + + return ret; +} + +bool background_threads_enable(tsd_t *tsd) { assert(n_background_threads == 0); assert(background_thread_enabled()); malloc_mutex_assert_owner(tsd_tsdn(tsd), &background_thread_lock); VARIABLE_ARRAY(bool, marked, max_background_threads); unsigned i, nmarked; for (i = 0; i < max_background_threads; i++) { marked[i] = false; } nmarked = 0; /* Thread 0 is required and created at the end. */ marked[0] = true; /* Mark the threads we need to create for thread 0. */ unsigned n = narenas_total_get(); for (i = 1; i < n; i++) { if (marked[i % max_background_threads] || arena_get(tsd_tsdn(tsd), i, false) == NULL) { continue; } background_thread_info_t *info = &background_thread_info[ i % max_background_threads]; malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx); assert(info->state == background_thread_stopped); background_thread_init(tsd, info); malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx); marked[i % max_background_threads] = true; if (++nmarked == max_background_threads) { break; } } - return background_thread_create(tsd, 0); + return background_thread_create_locked(tsd, 0); } bool background_threads_disable(tsd_t *tsd) { assert(!background_thread_enabled()); malloc_mutex_assert_owner(tsd_tsdn(tsd), &background_thread_lock); /* Thread 0 will be responsible for terminating other threads. */ if (background_threads_disable_single(tsd, &background_thread_info[0])) { return true; } assert(n_background_threads == 0); return false; } /* Check if we need to signal the background thread early. */ void background_thread_interval_check(tsdn_t *tsdn, arena_t *arena, arena_decay_t *decay, size_t npages_new) { background_thread_info_t *info = arena_background_thread_info_get( arena); if (malloc_mutex_trylock(tsdn, &info->mtx)) { /* * Background thread may hold the mutex for a long period of * time. We'd like to avoid the variance on application * threads. So keep this non-blocking, and leave the work to a * future epoch. */ return; } if (info->state != background_thread_started) { goto label_done; } if (malloc_mutex_trylock(tsdn, &decay->mtx)) { goto label_done; } ssize_t decay_time = atomic_load_zd(&decay->time_ms, ATOMIC_RELAXED); if (decay_time <= 0) { /* Purging is eagerly done or disabled currently. */ goto label_done_unlock2; } uint64_t decay_interval_ns = nstime_ns(&decay->interval); assert(decay_interval_ns > 0); nstime_t diff; nstime_init(&diff, background_thread_wakeup_time_get(info)); if (nstime_compare(&diff, &decay->epoch) <= 0) { goto label_done_unlock2; } nstime_subtract(&diff, &decay->epoch); if (nstime_ns(&diff) < BACKGROUND_THREAD_MIN_INTERVAL_NS) { goto label_done_unlock2; } if (npages_new > 0) { size_t n_epoch = (size_t)(nstime_ns(&diff) / decay_interval_ns); /* * Compute how many new pages we would need to purge by the next * wakeup, which is used to determine if we should signal the * background thread. */ uint64_t npurge_new; if (n_epoch >= SMOOTHSTEP_NSTEPS) { npurge_new = npages_new; } else { uint64_t h_steps_max = h_steps[SMOOTHSTEP_NSTEPS - 1]; assert(h_steps_max >= h_steps[SMOOTHSTEP_NSTEPS - 1 - n_epoch]); npurge_new = npages_new * (h_steps_max - h_steps[SMOOTHSTEP_NSTEPS - 1 - n_epoch]); npurge_new >>= SMOOTHSTEP_BFP; } info->npages_to_purge_new += npurge_new; } bool should_signal; if (info->npages_to_purge_new > BACKGROUND_THREAD_NPAGES_THRESHOLD) { should_signal = true; } else if (unlikely(background_thread_indefinite_sleep(info)) && (extents_npages_get(&arena->extents_dirty) > 0 || extents_npages_get(&arena->extents_muzzy) > 0 || info->npages_to_purge_new > 0)) { should_signal = true; } else { should_signal = false; } if (should_signal) { info->npages_to_purge_new = 0; pthread_cond_signal(&info->cond); } label_done_unlock2: malloc_mutex_unlock(tsdn, &decay->mtx); label_done: malloc_mutex_unlock(tsdn, &info->mtx); } void background_thread_prefork0(tsdn_t *tsdn) { malloc_mutex_prefork(tsdn, &background_thread_lock); background_thread_enabled_at_fork = background_thread_enabled(); } void background_thread_prefork1(tsdn_t *tsdn) { for (unsigned i = 0; i < max_background_threads; i++) { malloc_mutex_prefork(tsdn, &background_thread_info[i].mtx); } } void background_thread_postfork_parent(tsdn_t *tsdn) { for (unsigned i = 0; i < max_background_threads; i++) { malloc_mutex_postfork_parent(tsdn, &background_thread_info[i].mtx); } malloc_mutex_postfork_parent(tsdn, &background_thread_lock); } void background_thread_postfork_child(tsdn_t *tsdn) { for (unsigned i = 0; i < max_background_threads; i++) { malloc_mutex_postfork_child(tsdn, &background_thread_info[i].mtx); } malloc_mutex_postfork_child(tsdn, &background_thread_lock); if (!background_thread_enabled_at_fork) { return; } /* Clear background_thread state (reset to disabled for child). */ malloc_mutex_lock(tsdn, &background_thread_lock); n_background_threads = 0; background_thread_enabled_set(tsdn, false); for (unsigned i = 0; i < max_background_threads; i++) { background_thread_info_t *info = &background_thread_info[i]; malloc_mutex_lock(tsdn, &info->mtx); info->state = background_thread_stopped; int ret = pthread_cond_init(&info->cond, NULL); assert(ret == 0); background_thread_info_init(tsdn, info); malloc_mutex_unlock(tsdn, &info->mtx); } malloc_mutex_unlock(tsdn, &background_thread_lock); } bool background_thread_stats_read(tsdn_t *tsdn, background_thread_stats_t *stats) { assert(config_stats); malloc_mutex_lock(tsdn, &background_thread_lock); if (!background_thread_enabled()) { malloc_mutex_unlock(tsdn, &background_thread_lock); return true; } stats->num_threads = n_background_threads; uint64_t num_runs = 0; nstime_init(&stats->run_interval, 0); for (unsigned i = 0; i < max_background_threads; i++) { background_thread_info_t *info = &background_thread_info[i]; - malloc_mutex_lock(tsdn, &info->mtx); + if (malloc_mutex_trylock(tsdn, &info->mtx)) { + /* + * Each background thread run may take a long time; + * avoid waiting on the stats if the thread is active. + */ + continue; + } if (info->state != background_thread_stopped) { num_runs += info->tot_n_runs; nstime_add(&stats->run_interval, &info->tot_sleep_time); } malloc_mutex_unlock(tsdn, &info->mtx); } stats->num_runs = num_runs; if (num_runs > 0) { nstime_idivide(&stats->run_interval, num_runs); } malloc_mutex_unlock(tsdn, &background_thread_lock); return false; } #undef BACKGROUND_THREAD_NPAGES_THRESHOLD #undef BILLION #undef BACKGROUND_THREAD_MIN_INTERVAL_NS +#ifdef JEMALLOC_HAVE_DLSYM +#include +#endif + static bool pthread_create_fptr_init(void) { if (pthread_create_fptr != NULL) { return false; } + /* + * Try the next symbol first, because 1) when use lazy_lock we have a + * wrapper for pthread_create; and 2) application may define its own + * wrapper as well (and can call malloc within the wrapper). + */ +#ifdef JEMALLOC_HAVE_DLSYM pthread_create_fptr = dlsym(RTLD_NEXT, "pthread_create"); +#else + pthread_create_fptr = NULL; +#endif if (pthread_create_fptr == NULL) { - can_enable_background_thread = false; - if (config_lazy_lock || opt_background_thread) { + if (config_lazy_lock) { malloc_write(": Error in dlsym(RTLD_NEXT, " "\"pthread_create\")\n"); abort(); + } else { + /* Fall back to the default symbol. */ + pthread_create_fptr = pthread_create; } - } else { - can_enable_background_thread = true; } return false; } /* * When lazy lock is enabled, we need to make sure setting isthreaded before * taking any background_thread locks. This is called early in ctl (instead of * wait for the pthread_create calls to trigger) because the mutex is required * before creating background threads. */ void background_thread_ctl_init(tsdn_t *tsdn) { malloc_mutex_assert_not_owner(tsdn, &background_thread_lock); #ifdef JEMALLOC_PTHREAD_CREATE_WRAPPER pthread_create_fptr_init(); pthread_create_wrapper_init(); #endif } #endif /* defined(JEMALLOC_BACKGROUND_THREAD) */ bool background_thread_boot0(void) { if (!have_background_thread && opt_background_thread) { malloc_printf(": option background_thread currently " "supports pthread only\n"); return true; } #ifdef JEMALLOC_PTHREAD_CREATE_WRAPPER if ((config_lazy_lock || opt_background_thread) && pthread_create_fptr_init()) { return true; } #endif return false; } bool background_thread_boot1(tsdn_t *tsdn) { #ifdef JEMALLOC_BACKGROUND_THREAD assert(have_background_thread); assert(narenas_total_get() > 0); - if (opt_max_background_threads == MAX_BACKGROUND_THREAD_LIMIT && - ncpus < MAX_BACKGROUND_THREAD_LIMIT) { - opt_max_background_threads = ncpus; + if (opt_max_background_threads > MAX_BACKGROUND_THREAD_LIMIT) { + opt_max_background_threads = DEFAULT_NUM_BACKGROUND_THREAD; } max_background_threads = opt_max_background_threads; background_thread_enabled_set(tsdn, opt_background_thread); if (malloc_mutex_init(&background_thread_lock, "background_thread_global", WITNESS_RANK_BACKGROUND_THREAD_GLOBAL, malloc_mutex_rank_exclusive)) { return true; } background_thread_info = (background_thread_info_t *)base_alloc(tsdn, b0get(), opt_max_background_threads * sizeof(background_thread_info_t), CACHELINE); if (background_thread_info == NULL) { return true; } for (unsigned i = 0; i < max_background_threads; i++) { background_thread_info_t *info = &background_thread_info[i]; /* Thread mutex is rank_inclusive because of thread0. */ if (malloc_mutex_init(&info->mtx, "background_thread", WITNESS_RANK_BACKGROUND_THREAD, malloc_mutex_address_ordered)) { return true; } if (pthread_cond_init(&info->cond, NULL)) { return true; } malloc_mutex_lock(tsdn, &info->mtx); info->state = background_thread_stopped; background_thread_info_init(tsdn, info); malloc_mutex_unlock(tsdn, &info->mtx); } #endif return false; } Index: head/contrib/jemalloc/src/base.c =================================================================== --- head/contrib/jemalloc/src/base.c (revision 360232) +++ head/contrib/jemalloc/src/base.c (revision 360233) @@ -1,514 +1,514 @@ #define JEMALLOC_BASE_C_ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/jemalloc_internal_includes.h" #include "jemalloc/internal/assert.h" #include "jemalloc/internal/extent_mmap.h" #include "jemalloc/internal/mutex.h" #include "jemalloc/internal/sz.h" /******************************************************************************/ /* Data. */ static base_t *b0; metadata_thp_mode_t opt_metadata_thp = METADATA_THP_DEFAULT; const char *metadata_thp_mode_names[] = { "disabled", "auto", "always" }; /******************************************************************************/ static inline bool metadata_thp_madvise(void) { return (metadata_thp_enabled() && (init_system_thp_mode == thp_mode_default)); } static void * base_map(tsdn_t *tsdn, extent_hooks_t *extent_hooks, unsigned ind, size_t size) { void *addr; bool zero = true; bool commit = true; /* Use huge page sizes and alignment regardless of opt_metadata_thp. */ assert(size == HUGEPAGE_CEILING(size)); size_t alignment = HUGEPAGE; if (extent_hooks == &extent_hooks_default) { addr = extent_alloc_mmap(NULL, size, alignment, &zero, &commit); } else { /* No arena context as we are creating new arenas. */ tsd_t *tsd = tsdn_null(tsdn) ? tsd_fetch() : tsdn_tsd(tsdn); pre_reentrancy(tsd, NULL); addr = extent_hooks->alloc(extent_hooks, NULL, size, alignment, &zero, &commit, ind); post_reentrancy(tsd); } return addr; } static void base_unmap(tsdn_t *tsdn, extent_hooks_t *extent_hooks, unsigned ind, void *addr, size_t size) { /* * Cascade through dalloc, decommit, purge_forced, and purge_lazy, * stopping at first success. This cascade is performed for consistency * with the cascade in extent_dalloc_wrapper() because an application's * custom hooks may not support e.g. dalloc. This function is only ever * called as a side effect of arena destruction, so although it might * seem pointless to do anything besides dalloc here, the application * may in fact want the end state of all associated virtual memory to be * in some consistent-but-allocated state. */ if (extent_hooks == &extent_hooks_default) { if (!extent_dalloc_mmap(addr, size)) { goto label_done; } if (!pages_decommit(addr, size)) { goto label_done; } if (!pages_purge_forced(addr, size)) { goto label_done; } if (!pages_purge_lazy(addr, size)) { goto label_done; } /* Nothing worked. This should never happen. */ not_reached(); } else { tsd_t *tsd = tsdn_null(tsdn) ? tsd_fetch() : tsdn_tsd(tsdn); pre_reentrancy(tsd, NULL); if (extent_hooks->dalloc != NULL && !extent_hooks->dalloc(extent_hooks, addr, size, true, ind)) { goto label_post_reentrancy; } if (extent_hooks->decommit != NULL && !extent_hooks->decommit(extent_hooks, addr, size, 0, size, ind)) { goto label_post_reentrancy; } if (extent_hooks->purge_forced != NULL && !extent_hooks->purge_forced(extent_hooks, addr, size, 0, size, ind)) { goto label_post_reentrancy; } if (extent_hooks->purge_lazy != NULL && !extent_hooks->purge_lazy(extent_hooks, addr, size, 0, size, ind)) { goto label_post_reentrancy; } /* Nothing worked. That's the application's problem. */ label_post_reentrancy: post_reentrancy(tsd); } label_done: if (metadata_thp_madvise()) { /* Set NOHUGEPAGE after unmap to avoid kernel defrag. */ assert(((uintptr_t)addr & HUGEPAGE_MASK) == 0 && (size & HUGEPAGE_MASK) == 0); pages_nohuge(addr, size); } } static void base_extent_init(size_t *extent_sn_next, extent_t *extent, void *addr, size_t size) { size_t sn; sn = *extent_sn_next; (*extent_sn_next)++; extent_binit(extent, addr, size, sn); } static size_t base_get_num_blocks(base_t *base, bool with_new_block) { base_block_t *b = base->blocks; assert(b != NULL); size_t n_blocks = with_new_block ? 2 : 1; while (b->next != NULL) { n_blocks++; b = b->next; } return n_blocks; } static void base_auto_thp_switch(tsdn_t *tsdn, base_t *base) { assert(opt_metadata_thp == metadata_thp_auto); malloc_mutex_assert_owner(tsdn, &base->mtx); if (base->auto_thp_switched) { return; } /* Called when adding a new block. */ bool should_switch; if (base_ind_get(base) != 0) { should_switch = (base_get_num_blocks(base, true) == BASE_AUTO_THP_THRESHOLD); } else { should_switch = (base_get_num_blocks(base, true) == BASE_AUTO_THP_THRESHOLD_A0); } if (!should_switch) { return; } base->auto_thp_switched = true; assert(!config_stats || base->n_thp == 0); /* Make the initial blocks THP lazily. */ base_block_t *block = base->blocks; while (block != NULL) { assert((block->size & HUGEPAGE_MASK) == 0); pages_huge(block, block->size); if (config_stats) { base->n_thp += HUGEPAGE_CEILING(block->size - extent_bsize_get(&block->extent)) >> LG_HUGEPAGE; } block = block->next; assert(block == NULL || (base_ind_get(base) == 0)); } } static void * base_extent_bump_alloc_helper(extent_t *extent, size_t *gap_size, size_t size, size_t alignment) { void *ret; assert(alignment == ALIGNMENT_CEILING(alignment, QUANTUM)); assert(size == ALIGNMENT_CEILING(size, alignment)); *gap_size = ALIGNMENT_CEILING((uintptr_t)extent_addr_get(extent), alignment) - (uintptr_t)extent_addr_get(extent); ret = (void *)((uintptr_t)extent_addr_get(extent) + *gap_size); assert(extent_bsize_get(extent) >= *gap_size + size); extent_binit(extent, (void *)((uintptr_t)extent_addr_get(extent) + *gap_size + size), extent_bsize_get(extent) - *gap_size - size, extent_sn_get(extent)); return ret; } static void base_extent_bump_alloc_post(base_t *base, extent_t *extent, size_t gap_size, void *addr, size_t size) { if (extent_bsize_get(extent) > 0) { /* * Compute the index for the largest size class that does not * exceed extent's size. */ szind_t index_floor = sz_size2index(extent_bsize_get(extent) + 1) - 1; extent_heap_insert(&base->avail[index_floor], extent); } if (config_stats) { base->allocated += size; /* * Add one PAGE to base_resident for every page boundary that is * crossed by the new allocation. Adjust n_thp similarly when * metadata_thp is enabled. */ base->resident += PAGE_CEILING((uintptr_t)addr + size) - PAGE_CEILING((uintptr_t)addr - gap_size); assert(base->allocated <= base->resident); assert(base->resident <= base->mapped); if (metadata_thp_madvise() && (opt_metadata_thp == metadata_thp_always || base->auto_thp_switched)) { base->n_thp += (HUGEPAGE_CEILING((uintptr_t)addr + size) - HUGEPAGE_CEILING((uintptr_t)addr - gap_size)) >> LG_HUGEPAGE; assert(base->mapped >= base->n_thp << LG_HUGEPAGE); } } } static void * base_extent_bump_alloc(base_t *base, extent_t *extent, size_t size, size_t alignment) { void *ret; size_t gap_size; ret = base_extent_bump_alloc_helper(extent, &gap_size, size, alignment); base_extent_bump_alloc_post(base, extent, gap_size, ret, size); return ret; } /* * Allocate a block of virtual memory that is large enough to start with a * base_block_t header, followed by an object of specified size and alignment. * On success a pointer to the initialized base_block_t header is returned. */ static base_block_t * base_block_alloc(tsdn_t *tsdn, base_t *base, extent_hooks_t *extent_hooks, unsigned ind, pszind_t *pind_last, size_t *extent_sn_next, size_t size, size_t alignment) { alignment = ALIGNMENT_CEILING(alignment, QUANTUM); size_t usize = ALIGNMENT_CEILING(size, alignment); size_t header_size = sizeof(base_block_t); size_t gap_size = ALIGNMENT_CEILING(header_size, alignment) - header_size; /* * Create increasingly larger blocks in order to limit the total number * of disjoint virtual memory ranges. Choose the next size in the page * size class series (skipping size classes that are not a multiple of * HUGEPAGE), or a size large enough to satisfy the requested size and * alignment, whichever is larger. */ size_t min_block_size = HUGEPAGE_CEILING(sz_psz2u(header_size + gap_size + usize)); - pszind_t pind_next = (*pind_last + 1 < NPSIZES) ? *pind_last + 1 : - *pind_last; + pszind_t pind_next = (*pind_last + 1 < sz_psz2ind(SC_LARGE_MAXCLASS)) ? + *pind_last + 1 : *pind_last; size_t next_block_size = HUGEPAGE_CEILING(sz_pind2sz(pind_next)); size_t block_size = (min_block_size > next_block_size) ? min_block_size : next_block_size; base_block_t *block = (base_block_t *)base_map(tsdn, extent_hooks, ind, block_size); if (block == NULL) { return NULL; } if (metadata_thp_madvise()) { void *addr = (void *)block; assert(((uintptr_t)addr & HUGEPAGE_MASK) == 0 && (block_size & HUGEPAGE_MASK) == 0); if (opt_metadata_thp == metadata_thp_always) { pages_huge(addr, block_size); } else if (opt_metadata_thp == metadata_thp_auto && base != NULL) { /* base != NULL indicates this is not a new base. */ malloc_mutex_lock(tsdn, &base->mtx); base_auto_thp_switch(tsdn, base); if (base->auto_thp_switched) { pages_huge(addr, block_size); } malloc_mutex_unlock(tsdn, &base->mtx); } } *pind_last = sz_psz2ind(block_size); block->size = block_size; block->next = NULL; assert(block_size >= header_size); base_extent_init(extent_sn_next, &block->extent, (void *)((uintptr_t)block + header_size), block_size - header_size); return block; } /* * Allocate an extent that is at least as large as specified size, with * specified alignment. */ static extent_t * base_extent_alloc(tsdn_t *tsdn, base_t *base, size_t size, size_t alignment) { malloc_mutex_assert_owner(tsdn, &base->mtx); extent_hooks_t *extent_hooks = base_extent_hooks_get(base); /* * Drop mutex during base_block_alloc(), because an extent hook will be * called. */ malloc_mutex_unlock(tsdn, &base->mtx); base_block_t *block = base_block_alloc(tsdn, base, extent_hooks, base_ind_get(base), &base->pind_last, &base->extent_sn_next, size, alignment); malloc_mutex_lock(tsdn, &base->mtx); if (block == NULL) { return NULL; } block->next = base->blocks; base->blocks = block; if (config_stats) { base->allocated += sizeof(base_block_t); base->resident += PAGE_CEILING(sizeof(base_block_t)); base->mapped += block->size; if (metadata_thp_madvise() && !(opt_metadata_thp == metadata_thp_auto && !base->auto_thp_switched)) { assert(base->n_thp > 0); base->n_thp += HUGEPAGE_CEILING(sizeof(base_block_t)) >> LG_HUGEPAGE; } assert(base->allocated <= base->resident); assert(base->resident <= base->mapped); assert(base->n_thp << LG_HUGEPAGE <= base->mapped); } return &block->extent; } base_t * b0get(void) { return b0; } base_t * base_new(tsdn_t *tsdn, unsigned ind, extent_hooks_t *extent_hooks) { pszind_t pind_last = 0; size_t extent_sn_next = 0; base_block_t *block = base_block_alloc(tsdn, NULL, extent_hooks, ind, &pind_last, &extent_sn_next, sizeof(base_t), QUANTUM); if (block == NULL) { return NULL; } size_t gap_size; size_t base_alignment = CACHELINE; size_t base_size = ALIGNMENT_CEILING(sizeof(base_t), base_alignment); base_t *base = (base_t *)base_extent_bump_alloc_helper(&block->extent, &gap_size, base_size, base_alignment); base->ind = ind; atomic_store_p(&base->extent_hooks, extent_hooks, ATOMIC_RELAXED); if (malloc_mutex_init(&base->mtx, "base", WITNESS_RANK_BASE, malloc_mutex_rank_exclusive)) { base_unmap(tsdn, extent_hooks, ind, block, block->size); return NULL; } base->pind_last = pind_last; base->extent_sn_next = extent_sn_next; base->blocks = block; base->auto_thp_switched = false; - for (szind_t i = 0; i < NSIZES; i++) { + for (szind_t i = 0; i < SC_NSIZES; i++) { extent_heap_new(&base->avail[i]); } if (config_stats) { base->allocated = sizeof(base_block_t); base->resident = PAGE_CEILING(sizeof(base_block_t)); base->mapped = block->size; base->n_thp = (opt_metadata_thp == metadata_thp_always) && metadata_thp_madvise() ? HUGEPAGE_CEILING(sizeof(base_block_t)) >> LG_HUGEPAGE : 0; assert(base->allocated <= base->resident); assert(base->resident <= base->mapped); assert(base->n_thp << LG_HUGEPAGE <= base->mapped); } base_extent_bump_alloc_post(base, &block->extent, gap_size, base, base_size); return base; } void base_delete(tsdn_t *tsdn, base_t *base) { extent_hooks_t *extent_hooks = base_extent_hooks_get(base); base_block_t *next = base->blocks; do { base_block_t *block = next; next = block->next; base_unmap(tsdn, extent_hooks, base_ind_get(base), block, block->size); } while (next != NULL); } extent_hooks_t * base_extent_hooks_get(base_t *base) { return (extent_hooks_t *)atomic_load_p(&base->extent_hooks, ATOMIC_ACQUIRE); } extent_hooks_t * base_extent_hooks_set(base_t *base, extent_hooks_t *extent_hooks) { extent_hooks_t *old_extent_hooks = base_extent_hooks_get(base); atomic_store_p(&base->extent_hooks, extent_hooks, ATOMIC_RELEASE); return old_extent_hooks; } static void * base_alloc_impl(tsdn_t *tsdn, base_t *base, size_t size, size_t alignment, size_t *esn) { alignment = QUANTUM_CEILING(alignment); size_t usize = ALIGNMENT_CEILING(size, alignment); size_t asize = usize + alignment - QUANTUM; extent_t *extent = NULL; malloc_mutex_lock(tsdn, &base->mtx); - for (szind_t i = sz_size2index(asize); i < NSIZES; i++) { + for (szind_t i = sz_size2index(asize); i < SC_NSIZES; i++) { extent = extent_heap_remove_first(&base->avail[i]); if (extent != NULL) { /* Use existing space. */ break; } } if (extent == NULL) { /* Try to allocate more space. */ extent = base_extent_alloc(tsdn, base, usize, alignment); } void *ret; if (extent == NULL) { ret = NULL; goto label_return; } ret = base_extent_bump_alloc(base, extent, usize, alignment); if (esn != NULL) { *esn = extent_sn_get(extent); } label_return: malloc_mutex_unlock(tsdn, &base->mtx); return ret; } /* * base_alloc() returns zeroed memory, which is always demand-zeroed for the * auto arenas, in order to make multi-page sparse data structures such as radix * tree nodes efficient with respect to physical memory usage. Upon success a * pointer to at least size bytes with specified alignment is returned. Note * that size is rounded up to the nearest multiple of alignment to avoid false * sharing. */ void * base_alloc(tsdn_t *tsdn, base_t *base, size_t size, size_t alignment) { return base_alloc_impl(tsdn, base, size, alignment, NULL); } extent_t * base_alloc_extent(tsdn_t *tsdn, base_t *base) { size_t esn; extent_t *extent = base_alloc_impl(tsdn, base, sizeof(extent_t), CACHELINE, &esn); if (extent == NULL) { return NULL; } extent_esn_set(extent, esn); return extent; } void base_stats_get(tsdn_t *tsdn, base_t *base, size_t *allocated, size_t *resident, size_t *mapped, size_t *n_thp) { cassert(config_stats); malloc_mutex_lock(tsdn, &base->mtx); assert(base->allocated <= base->resident); assert(base->resident <= base->mapped); *allocated = base->allocated; *resident = base->resident; *mapped = base->mapped; *n_thp = base->n_thp; malloc_mutex_unlock(tsdn, &base->mtx); } void base_prefork(tsdn_t *tsdn, base_t *base) { malloc_mutex_prefork(tsdn, &base->mtx); } void base_postfork_parent(tsdn_t *tsdn, base_t *base) { malloc_mutex_postfork_parent(tsdn, &base->mtx); } void base_postfork_child(tsdn_t *tsdn, base_t *base) { malloc_mutex_postfork_child(tsdn, &base->mtx); } bool base_boot(tsdn_t *tsdn) { b0 = base_new(tsdn, 0, (extent_hooks_t *)&extent_hooks_default); return (b0 == NULL); } Index: head/contrib/jemalloc/src/bin.c =================================================================== --- head/contrib/jemalloc/src/bin.c (revision 360232) +++ head/contrib/jemalloc/src/bin.c (revision 360233) @@ -1,50 +1,95 @@ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/jemalloc_internal_includes.h" +#include "jemalloc/internal/assert.h" #include "jemalloc/internal/bin.h" +#include "jemalloc/internal/sc.h" #include "jemalloc/internal/witness.h" -const bin_info_t bin_infos[NBINS] = { -#define BIN_INFO_bin_yes(reg_size, slab_size, nregs) \ - {reg_size, slab_size, nregs, BITMAP_INFO_INITIALIZER(nregs)}, -#define BIN_INFO_bin_no(reg_size, slab_size, nregs) -#define SC(index, lg_grp, lg_delta, ndelta, psz, bin, pgs, \ - lg_delta_lookup) \ - BIN_INFO_bin_##bin((1U<sc[i]; + bin_info->reg_size = ((size_t)1U << sc->lg_base) + + ((size_t)sc->ndelta << sc->lg_delta); + bin_info->slab_size = (sc->pgs << LG_PAGE); + bin_info->nregs = + (uint32_t)(bin_info->slab_size / bin_info->reg_size); + bin_info->n_shards = bin_shard_sizes[i]; + bitmap_info_t bitmap_info = BITMAP_INFO_INITIALIZER( + bin_info->nregs); + bin_info->bitmap_info = bitmap_info; + } +} + +bool +bin_update_shard_size(unsigned bin_shard_sizes[SC_NBINS], size_t start_size, + size_t end_size, size_t nshards) { + if (nshards > BIN_SHARDS_MAX || nshards == 0) { + return true; + } + + if (start_size > SC_SMALL_MAXCLASS) { + return false; + } + if (end_size > SC_SMALL_MAXCLASS) { + end_size = SC_SMALL_MAXCLASS; + } + + /* Compute the index since this may happen before sz init. */ + szind_t ind1 = sz_size2index_compute(start_size); + szind_t ind2 = sz_size2index_compute(end_size); + for (unsigned i = ind1; i <= ind2; i++) { + bin_shard_sizes[i] = (unsigned)nshards; + } + + return false; +} + +void +bin_shard_sizes_boot(unsigned bin_shard_sizes[SC_NBINS]) { + /* Load the default number of shards. */ + for (unsigned i = 0; i < SC_NBINS; i++) { + bin_shard_sizes[i] = N_BIN_SHARDS_DEFAULT; + } +} + +void +bin_boot(sc_data_t *sc_data, unsigned bin_shard_sizes[SC_NBINS]) { + assert(sc_data->initialized); + bin_infos_init(sc_data, bin_shard_sizes, bin_infos); +} bool bin_init(bin_t *bin) { if (malloc_mutex_init(&bin->lock, "bin", WITNESS_RANK_BIN, malloc_mutex_rank_exclusive)) { return true; } bin->slabcur = NULL; extent_heap_new(&bin->slabs_nonfull); extent_list_init(&bin->slabs_full); if (config_stats) { memset(&bin->stats, 0, sizeof(bin_stats_t)); } return false; } void bin_prefork(tsdn_t *tsdn, bin_t *bin) { malloc_mutex_prefork(tsdn, &bin->lock); } void bin_postfork_parent(tsdn_t *tsdn, bin_t *bin) { malloc_mutex_postfork_parent(tsdn, &bin->lock); } void bin_postfork_child(tsdn_t *tsdn, bin_t *bin) { malloc_mutex_postfork_child(tsdn, &bin->lock); } Index: head/contrib/jemalloc/src/ckh.c =================================================================== --- head/contrib/jemalloc/src/ckh.c (revision 360232) +++ head/contrib/jemalloc/src/ckh.c (revision 360233) @@ -1,569 +1,570 @@ /* ******************************************************************************* * Implementation of (2^1+,2) cuckoo hashing, where 2^1+ indicates that each * hash bucket contains 2^n cells, for n >= 1, and 2 indicates that two hash * functions are employed. The original cuckoo hashing algorithm was described * in: * * Pagh, R., F.F. Rodler (2004) Cuckoo Hashing. Journal of Algorithms * 51(2):122-144. * * Generalization of cuckoo hashing was discussed in: * * Erlingsson, U., M. Manasse, F. McSherry (2006) A cool and practical * alternative to traditional hash tables. In Proceedings of the 7th * Workshop on Distributed Data and Structures (WDAS'06), Santa Clara, CA, * January 2006. * * This implementation uses precisely two hash functions because that is the * fewest that can work, and supporting multiple hashes is an implementation * burden. Here is a reproduction of Figure 1 from Erlingsson et al. (2006) * that shows approximate expected maximum load factors for various * configurations: * * | #cells/bucket | * #hashes | 1 | 2 | 4 | 8 | * --------+-------+-------+-------+-------+ * 1 | 0.006 | 0.006 | 0.03 | 0.12 | * 2 | 0.49 | 0.86 |>0.93< |>0.96< | * 3 | 0.91 | 0.97 | 0.98 | 0.999 | * 4 | 0.97 | 0.99 | 0.999 | | * * The number of cells per bucket is chosen such that a bucket fits in one cache * line. So, on 32- and 64-bit systems, we use (8,2) and (4,2) cuckoo hashing, * respectively. * ******************************************************************************/ #define JEMALLOC_CKH_C_ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/ckh.h" #include "jemalloc/internal/jemalloc_internal_includes.h" #include "jemalloc/internal/assert.h" #include "jemalloc/internal/hash.h" #include "jemalloc/internal/malloc_io.h" #include "jemalloc/internal/prng.h" #include "jemalloc/internal/util.h" /******************************************************************************/ /* Function prototypes for non-inline static functions. */ static bool ckh_grow(tsd_t *tsd, ckh_t *ckh); static void ckh_shrink(tsd_t *tsd, ckh_t *ckh); /******************************************************************************/ /* * Search bucket for key and return the cell number if found; SIZE_T_MAX * otherwise. */ static size_t ckh_bucket_search(ckh_t *ckh, size_t bucket, const void *key) { ckhc_t *cell; unsigned i; for (i = 0; i < (ZU(1) << LG_CKH_BUCKET_CELLS); i++) { cell = &ckh->tab[(bucket << LG_CKH_BUCKET_CELLS) + i]; if (cell->key != NULL && ckh->keycomp(key, cell->key)) { return (bucket << LG_CKH_BUCKET_CELLS) + i; } } return SIZE_T_MAX; } /* * Search table for key and return cell number if found; SIZE_T_MAX otherwise. */ static size_t ckh_isearch(ckh_t *ckh, const void *key) { size_t hashes[2], bucket, cell; assert(ckh != NULL); ckh->hash(key, hashes); /* Search primary bucket. */ bucket = hashes[0] & ((ZU(1) << ckh->lg_curbuckets) - 1); cell = ckh_bucket_search(ckh, bucket, key); if (cell != SIZE_T_MAX) { return cell; } /* Search secondary bucket. */ bucket = hashes[1] & ((ZU(1) << ckh->lg_curbuckets) - 1); cell = ckh_bucket_search(ckh, bucket, key); return cell; } static bool ckh_try_bucket_insert(ckh_t *ckh, size_t bucket, const void *key, const void *data) { ckhc_t *cell; unsigned offset, i; /* * Cycle through the cells in the bucket, starting at a random position. * The randomness avoids worst-case search overhead as buckets fill up. */ offset = (unsigned)prng_lg_range_u64(&ckh->prng_state, LG_CKH_BUCKET_CELLS); for (i = 0; i < (ZU(1) << LG_CKH_BUCKET_CELLS); i++) { cell = &ckh->tab[(bucket << LG_CKH_BUCKET_CELLS) + ((i + offset) & ((ZU(1) << LG_CKH_BUCKET_CELLS) - 1))]; if (cell->key == NULL) { cell->key = key; cell->data = data; ckh->count++; return false; } } return true; } /* * No space is available in bucket. Randomly evict an item, then try to find an * alternate location for that item. Iteratively repeat this * eviction/relocation procedure until either success or detection of an * eviction/relocation bucket cycle. */ static bool ckh_evict_reloc_insert(ckh_t *ckh, size_t argbucket, void const **argkey, void const **argdata) { const void *key, *data, *tkey, *tdata; ckhc_t *cell; size_t hashes[2], bucket, tbucket; unsigned i; bucket = argbucket; key = *argkey; data = *argdata; while (true) { /* * Choose a random item within the bucket to evict. This is * critical to correct function, because without (eventually) * evicting all items within a bucket during iteration, it * would be possible to get stuck in an infinite loop if there * were an item for which both hashes indicated the same * bucket. */ i = (unsigned)prng_lg_range_u64(&ckh->prng_state, LG_CKH_BUCKET_CELLS); cell = &ckh->tab[(bucket << LG_CKH_BUCKET_CELLS) + i]; assert(cell->key != NULL); /* Swap cell->{key,data} and {key,data} (evict). */ tkey = cell->key; tdata = cell->data; cell->key = key; cell->data = data; key = tkey; data = tdata; #ifdef CKH_COUNT ckh->nrelocs++; #endif /* Find the alternate bucket for the evicted item. */ ckh->hash(key, hashes); tbucket = hashes[1] & ((ZU(1) << ckh->lg_curbuckets) - 1); if (tbucket == bucket) { tbucket = hashes[0] & ((ZU(1) << ckh->lg_curbuckets) - 1); /* * It may be that (tbucket == bucket) still, if the * item's hashes both indicate this bucket. However, * we are guaranteed to eventually escape this bucket * during iteration, assuming pseudo-random item * selection (true randomness would make infinite * looping a remote possibility). The reason we can * never get trapped forever is that there are two * cases: * * 1) This bucket == argbucket, so we will quickly * detect an eviction cycle and terminate. * 2) An item was evicted to this bucket from another, * which means that at least one item in this bucket * has hashes that indicate distinct buckets. */ } /* Check for a cycle. */ if (tbucket == argbucket) { *argkey = key; *argdata = data; return true; } bucket = tbucket; if (!ckh_try_bucket_insert(ckh, bucket, key, data)) { return false; } } } static bool ckh_try_insert(ckh_t *ckh, void const**argkey, void const**argdata) { size_t hashes[2], bucket; const void *key = *argkey; const void *data = *argdata; ckh->hash(key, hashes); /* Try to insert in primary bucket. */ bucket = hashes[0] & ((ZU(1) << ckh->lg_curbuckets) - 1); if (!ckh_try_bucket_insert(ckh, bucket, key, data)) { return false; } /* Try to insert in secondary bucket. */ bucket = hashes[1] & ((ZU(1) << ckh->lg_curbuckets) - 1); if (!ckh_try_bucket_insert(ckh, bucket, key, data)) { return false; } /* * Try to find a place for this item via iterative eviction/relocation. */ return ckh_evict_reloc_insert(ckh, bucket, argkey, argdata); } /* * Try to rebuild the hash table from scratch by inserting all items from the * old table into the new. */ static bool ckh_rebuild(ckh_t *ckh, ckhc_t *aTab) { size_t count, i, nins; const void *key, *data; count = ckh->count; ckh->count = 0; for (i = nins = 0; nins < count; i++) { if (aTab[i].key != NULL) { key = aTab[i].key; data = aTab[i].data; if (ckh_try_insert(ckh, &key, &data)) { ckh->count = count; return true; } nins++; } } return false; } static bool ckh_grow(tsd_t *tsd, ckh_t *ckh) { bool ret; ckhc_t *tab, *ttab; unsigned lg_prevbuckets, lg_curcells; #ifdef CKH_COUNT ckh->ngrows++; #endif /* * It is possible (though unlikely, given well behaved hashes) that the * table will have to be doubled more than once in order to create a * usable table. */ lg_prevbuckets = ckh->lg_curbuckets; lg_curcells = ckh->lg_curbuckets + LG_CKH_BUCKET_CELLS; while (true) { size_t usize; lg_curcells++; usize = sz_sa2u(sizeof(ckhc_t) << lg_curcells, CACHELINE); - if (unlikely(usize == 0 || usize > LARGE_MAXCLASS)) { + if (unlikely(usize == 0 + || usize > SC_LARGE_MAXCLASS)) { ret = true; goto label_return; } tab = (ckhc_t *)ipallocztm(tsd_tsdn(tsd), usize, CACHELINE, true, NULL, true, arena_ichoose(tsd, NULL)); if (tab == NULL) { ret = true; goto label_return; } /* Swap in new table. */ ttab = ckh->tab; ckh->tab = tab; tab = ttab; ckh->lg_curbuckets = lg_curcells - LG_CKH_BUCKET_CELLS; if (!ckh_rebuild(ckh, tab)) { idalloctm(tsd_tsdn(tsd), tab, NULL, NULL, true, true); break; } /* Rebuilding failed, so back out partially rebuilt table. */ idalloctm(tsd_tsdn(tsd), ckh->tab, NULL, NULL, true, true); ckh->tab = tab; ckh->lg_curbuckets = lg_prevbuckets; } ret = false; label_return: return ret; } static void ckh_shrink(tsd_t *tsd, ckh_t *ckh) { ckhc_t *tab, *ttab; size_t usize; unsigned lg_prevbuckets, lg_curcells; /* * It is possible (though unlikely, given well behaved hashes) that the * table rebuild will fail. */ lg_prevbuckets = ckh->lg_curbuckets; lg_curcells = ckh->lg_curbuckets + LG_CKH_BUCKET_CELLS - 1; usize = sz_sa2u(sizeof(ckhc_t) << lg_curcells, CACHELINE); - if (unlikely(usize == 0 || usize > LARGE_MAXCLASS)) { + if (unlikely(usize == 0 || usize > SC_LARGE_MAXCLASS)) { return; } tab = (ckhc_t *)ipallocztm(tsd_tsdn(tsd), usize, CACHELINE, true, NULL, true, arena_ichoose(tsd, NULL)); if (tab == NULL) { /* * An OOM error isn't worth propagating, since it doesn't * prevent this or future operations from proceeding. */ return; } /* Swap in new table. */ ttab = ckh->tab; ckh->tab = tab; tab = ttab; ckh->lg_curbuckets = lg_curcells - LG_CKH_BUCKET_CELLS; if (!ckh_rebuild(ckh, tab)) { idalloctm(tsd_tsdn(tsd), tab, NULL, NULL, true, true); #ifdef CKH_COUNT ckh->nshrinks++; #endif return; } /* Rebuilding failed, so back out partially rebuilt table. */ idalloctm(tsd_tsdn(tsd), ckh->tab, NULL, NULL, true, true); ckh->tab = tab; ckh->lg_curbuckets = lg_prevbuckets; #ifdef CKH_COUNT ckh->nshrinkfails++; #endif } bool ckh_new(tsd_t *tsd, ckh_t *ckh, size_t minitems, ckh_hash_t *hash, ckh_keycomp_t *keycomp) { bool ret; size_t mincells, usize; unsigned lg_mincells; assert(minitems > 0); assert(hash != NULL); assert(keycomp != NULL); #ifdef CKH_COUNT ckh->ngrows = 0; ckh->nshrinks = 0; ckh->nshrinkfails = 0; ckh->ninserts = 0; ckh->nrelocs = 0; #endif ckh->prng_state = 42; /* Value doesn't really matter. */ ckh->count = 0; /* * Find the minimum power of 2 that is large enough to fit minitems * entries. We are using (2+,2) cuckoo hashing, which has an expected * maximum load factor of at least ~0.86, so 0.75 is a conservative load * factor that will typically allow mincells items to fit without ever * growing the table. */ assert(LG_CKH_BUCKET_CELLS > 0); mincells = ((minitems + (3 - (minitems % 3))) / 3) << 2; for (lg_mincells = LG_CKH_BUCKET_CELLS; (ZU(1) << lg_mincells) < mincells; lg_mincells++) { /* Do nothing. */ } ckh->lg_minbuckets = lg_mincells - LG_CKH_BUCKET_CELLS; ckh->lg_curbuckets = lg_mincells - LG_CKH_BUCKET_CELLS; ckh->hash = hash; ckh->keycomp = keycomp; usize = sz_sa2u(sizeof(ckhc_t) << lg_mincells, CACHELINE); - if (unlikely(usize == 0 || usize > LARGE_MAXCLASS)) { + if (unlikely(usize == 0 || usize > SC_LARGE_MAXCLASS)) { ret = true; goto label_return; } ckh->tab = (ckhc_t *)ipallocztm(tsd_tsdn(tsd), usize, CACHELINE, true, NULL, true, arena_ichoose(tsd, NULL)); if (ckh->tab == NULL) { ret = true; goto label_return; } ret = false; label_return: return ret; } void ckh_delete(tsd_t *tsd, ckh_t *ckh) { assert(ckh != NULL); #ifdef CKH_VERBOSE malloc_printf( "%s(%p): ngrows: %"FMTu64", nshrinks: %"FMTu64"," " nshrinkfails: %"FMTu64", ninserts: %"FMTu64"," " nrelocs: %"FMTu64"\n", __func__, ckh, (unsigned long long)ckh->ngrows, (unsigned long long)ckh->nshrinks, (unsigned long long)ckh->nshrinkfails, (unsigned long long)ckh->ninserts, (unsigned long long)ckh->nrelocs); #endif idalloctm(tsd_tsdn(tsd), ckh->tab, NULL, NULL, true, true); if (config_debug) { memset(ckh, JEMALLOC_FREE_JUNK, sizeof(ckh_t)); } } size_t ckh_count(ckh_t *ckh) { assert(ckh != NULL); return ckh->count; } bool ckh_iter(ckh_t *ckh, size_t *tabind, void **key, void **data) { size_t i, ncells; for (i = *tabind, ncells = (ZU(1) << (ckh->lg_curbuckets + LG_CKH_BUCKET_CELLS)); i < ncells; i++) { if (ckh->tab[i].key != NULL) { if (key != NULL) { *key = (void *)ckh->tab[i].key; } if (data != NULL) { *data = (void *)ckh->tab[i].data; } *tabind = i + 1; return false; } } return true; } bool ckh_insert(tsd_t *tsd, ckh_t *ckh, const void *key, const void *data) { bool ret; assert(ckh != NULL); assert(ckh_search(ckh, key, NULL, NULL)); #ifdef CKH_COUNT ckh->ninserts++; #endif while (ckh_try_insert(ckh, &key, &data)) { if (ckh_grow(tsd, ckh)) { ret = true; goto label_return; } } ret = false; label_return: return ret; } bool ckh_remove(tsd_t *tsd, ckh_t *ckh, const void *searchkey, void **key, void **data) { size_t cell; assert(ckh != NULL); cell = ckh_isearch(ckh, searchkey); if (cell != SIZE_T_MAX) { if (key != NULL) { *key = (void *)ckh->tab[cell].key; } if (data != NULL) { *data = (void *)ckh->tab[cell].data; } ckh->tab[cell].key = NULL; ckh->tab[cell].data = NULL; /* Not necessary. */ ckh->count--; /* Try to halve the table if it is less than 1/4 full. */ if (ckh->count < (ZU(1) << (ckh->lg_curbuckets + LG_CKH_BUCKET_CELLS - 2)) && ckh->lg_curbuckets > ckh->lg_minbuckets) { /* Ignore error due to OOM. */ ckh_shrink(tsd, ckh); } return false; } return true; } bool ckh_search(ckh_t *ckh, const void *searchkey, void **key, void **data) { size_t cell; assert(ckh != NULL); cell = ckh_isearch(ckh, searchkey); if (cell != SIZE_T_MAX) { if (key != NULL) { *key = (void *)ckh->tab[cell].key; } if (data != NULL) { *data = (void *)ckh->tab[cell].data; } return false; } return true; } void ckh_string_hash(const void *key, size_t r_hash[2]) { hash(key, strlen((const char *)key), 0x94122f33U, r_hash); } bool ckh_string_keycomp(const void *k1, const void *k2) { assert(k1 != NULL); assert(k2 != NULL); return !strcmp((char *)k1, (char *)k2); } void ckh_pointer_hash(const void *key, size_t r_hash[2]) { union { const void *v; size_t i; } u; assert(sizeof(u.v) == sizeof(u.i)); u.v = key; hash(&u.i, sizeof(u.i), 0xd983396eU, r_hash); } bool ckh_pointer_keycomp(const void *k1, const void *k2) { return (k1 == k2); } Index: head/contrib/jemalloc/src/ctl.c =================================================================== --- head/contrib/jemalloc/src/ctl.c (revision 360232) +++ head/contrib/jemalloc/src/ctl.c (revision 360233) @@ -1,2883 +1,3435 @@ #define JEMALLOC_CTL_C_ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/jemalloc_internal_includes.h" #include "jemalloc/internal/assert.h" #include "jemalloc/internal/ctl.h" #include "jemalloc/internal/extent_dss.h" #include "jemalloc/internal/extent_mmap.h" #include "jemalloc/internal/mutex.h" #include "jemalloc/internal/nstime.h" -#include "jemalloc/internal/size_classes.h" +#include "jemalloc/internal/sc.h" #include "jemalloc/internal/util.h" /******************************************************************************/ /* Data. */ /* * ctl_mtx protects the following: * - ctl_stats->* */ static malloc_mutex_t ctl_mtx; static bool ctl_initialized; static ctl_stats_t *ctl_stats; static ctl_arenas_t *ctl_arenas; /******************************************************************************/ /* Helpers for named and indexed nodes. */ static const ctl_named_node_t * ctl_named_node(const ctl_node_t *node) { return ((node->named) ? (const ctl_named_node_t *)node : NULL); } static const ctl_named_node_t * ctl_named_children(const ctl_named_node_t *node, size_t index) { const ctl_named_node_t *children = ctl_named_node(node->children); return (children ? &children[index] : NULL); } static const ctl_indexed_node_t * ctl_indexed_node(const ctl_node_t *node) { return (!node->named ? (const ctl_indexed_node_t *)node : NULL); } /******************************************************************************/ /* Function prototypes for non-inline static functions. */ #define CTL_PROTO(n) \ static int n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, \ void *oldp, size_t *oldlenp, void *newp, size_t newlen); #define INDEX_PROTO(n) \ static const ctl_named_node_t *n##_index(tsdn_t *tsdn, \ const size_t *mib, size_t miblen, size_t i); CTL_PROTO(version) CTL_PROTO(epoch) CTL_PROTO(background_thread) CTL_PROTO(max_background_threads) CTL_PROTO(thread_tcache_enabled) CTL_PROTO(thread_tcache_flush) CTL_PROTO(thread_prof_name) CTL_PROTO(thread_prof_active) CTL_PROTO(thread_arena) CTL_PROTO(thread_allocated) CTL_PROTO(thread_allocatedp) CTL_PROTO(thread_deallocated) CTL_PROTO(thread_deallocatedp) CTL_PROTO(config_cache_oblivious) CTL_PROTO(config_debug) CTL_PROTO(config_fill) CTL_PROTO(config_lazy_lock) CTL_PROTO(config_malloc_conf) +CTL_PROTO(config_opt_safety_checks) CTL_PROTO(config_prof) CTL_PROTO(config_prof_libgcc) CTL_PROTO(config_prof_libunwind) CTL_PROTO(config_stats) CTL_PROTO(config_utrace) CTL_PROTO(config_xmalloc) CTL_PROTO(opt_abort) CTL_PROTO(opt_abort_conf) +CTL_PROTO(opt_confirm_conf) CTL_PROTO(opt_metadata_thp) CTL_PROTO(opt_retain) CTL_PROTO(opt_dss) CTL_PROTO(opt_narenas) CTL_PROTO(opt_percpu_arena) +CTL_PROTO(opt_oversize_threshold) CTL_PROTO(opt_background_thread) CTL_PROTO(opt_max_background_threads) CTL_PROTO(opt_dirty_decay_ms) CTL_PROTO(opt_muzzy_decay_ms) CTL_PROTO(opt_stats_print) CTL_PROTO(opt_stats_print_opts) CTL_PROTO(opt_junk) CTL_PROTO(opt_zero) CTL_PROTO(opt_utrace) CTL_PROTO(opt_xmalloc) CTL_PROTO(opt_tcache) CTL_PROTO(opt_thp) CTL_PROTO(opt_lg_extent_max_active_fit) CTL_PROTO(opt_lg_tcache_max) CTL_PROTO(opt_prof) CTL_PROTO(opt_prof_prefix) CTL_PROTO(opt_prof_active) CTL_PROTO(opt_prof_thread_active_init) CTL_PROTO(opt_lg_prof_sample) CTL_PROTO(opt_lg_prof_interval) CTL_PROTO(opt_prof_gdump) CTL_PROTO(opt_prof_final) CTL_PROTO(opt_prof_leak) CTL_PROTO(opt_prof_accum) CTL_PROTO(tcache_create) CTL_PROTO(tcache_flush) CTL_PROTO(tcache_destroy) CTL_PROTO(arena_i_initialized) CTL_PROTO(arena_i_decay) CTL_PROTO(arena_i_purge) CTL_PROTO(arena_i_reset) CTL_PROTO(arena_i_destroy) CTL_PROTO(arena_i_dss) CTL_PROTO(arena_i_dirty_decay_ms) CTL_PROTO(arena_i_muzzy_decay_ms) CTL_PROTO(arena_i_extent_hooks) CTL_PROTO(arena_i_retain_grow_limit) INDEX_PROTO(arena_i) CTL_PROTO(arenas_bin_i_size) CTL_PROTO(arenas_bin_i_nregs) CTL_PROTO(arenas_bin_i_slab_size) +CTL_PROTO(arenas_bin_i_nshards) INDEX_PROTO(arenas_bin_i) CTL_PROTO(arenas_lextent_i_size) INDEX_PROTO(arenas_lextent_i) CTL_PROTO(arenas_narenas) CTL_PROTO(arenas_dirty_decay_ms) CTL_PROTO(arenas_muzzy_decay_ms) CTL_PROTO(arenas_quantum) CTL_PROTO(arenas_page) CTL_PROTO(arenas_tcache_max) CTL_PROTO(arenas_nbins) CTL_PROTO(arenas_nhbins) CTL_PROTO(arenas_nlextents) CTL_PROTO(arenas_create) CTL_PROTO(arenas_lookup) CTL_PROTO(prof_thread_active_init) CTL_PROTO(prof_active) CTL_PROTO(prof_dump) CTL_PROTO(prof_gdump) CTL_PROTO(prof_reset) CTL_PROTO(prof_interval) CTL_PROTO(lg_prof_sample) +CTL_PROTO(prof_log_start) +CTL_PROTO(prof_log_stop) CTL_PROTO(stats_arenas_i_small_allocated) CTL_PROTO(stats_arenas_i_small_nmalloc) CTL_PROTO(stats_arenas_i_small_ndalloc) CTL_PROTO(stats_arenas_i_small_nrequests) +CTL_PROTO(stats_arenas_i_small_nfills) +CTL_PROTO(stats_arenas_i_small_nflushes) CTL_PROTO(stats_arenas_i_large_allocated) CTL_PROTO(stats_arenas_i_large_nmalloc) CTL_PROTO(stats_arenas_i_large_ndalloc) CTL_PROTO(stats_arenas_i_large_nrequests) +CTL_PROTO(stats_arenas_i_large_nfills) +CTL_PROTO(stats_arenas_i_large_nflushes) CTL_PROTO(stats_arenas_i_bins_j_nmalloc) CTL_PROTO(stats_arenas_i_bins_j_ndalloc) CTL_PROTO(stats_arenas_i_bins_j_nrequests) CTL_PROTO(stats_arenas_i_bins_j_curregs) CTL_PROTO(stats_arenas_i_bins_j_nfills) CTL_PROTO(stats_arenas_i_bins_j_nflushes) CTL_PROTO(stats_arenas_i_bins_j_nslabs) CTL_PROTO(stats_arenas_i_bins_j_nreslabs) CTL_PROTO(stats_arenas_i_bins_j_curslabs) +CTL_PROTO(stats_arenas_i_bins_j_nonfull_slabs) INDEX_PROTO(stats_arenas_i_bins_j) CTL_PROTO(stats_arenas_i_lextents_j_nmalloc) CTL_PROTO(stats_arenas_i_lextents_j_ndalloc) CTL_PROTO(stats_arenas_i_lextents_j_nrequests) CTL_PROTO(stats_arenas_i_lextents_j_curlextents) INDEX_PROTO(stats_arenas_i_lextents_j) +CTL_PROTO(stats_arenas_i_extents_j_ndirty) +CTL_PROTO(stats_arenas_i_extents_j_nmuzzy) +CTL_PROTO(stats_arenas_i_extents_j_nretained) +CTL_PROTO(stats_arenas_i_extents_j_dirty_bytes) +CTL_PROTO(stats_arenas_i_extents_j_muzzy_bytes) +CTL_PROTO(stats_arenas_i_extents_j_retained_bytes) +INDEX_PROTO(stats_arenas_i_extents_j) CTL_PROTO(stats_arenas_i_nthreads) CTL_PROTO(stats_arenas_i_uptime) CTL_PROTO(stats_arenas_i_dss) CTL_PROTO(stats_arenas_i_dirty_decay_ms) CTL_PROTO(stats_arenas_i_muzzy_decay_ms) CTL_PROTO(stats_arenas_i_pactive) CTL_PROTO(stats_arenas_i_pdirty) CTL_PROTO(stats_arenas_i_pmuzzy) CTL_PROTO(stats_arenas_i_mapped) CTL_PROTO(stats_arenas_i_retained) +CTL_PROTO(stats_arenas_i_extent_avail) CTL_PROTO(stats_arenas_i_dirty_npurge) CTL_PROTO(stats_arenas_i_dirty_nmadvise) CTL_PROTO(stats_arenas_i_dirty_purged) CTL_PROTO(stats_arenas_i_muzzy_npurge) CTL_PROTO(stats_arenas_i_muzzy_nmadvise) CTL_PROTO(stats_arenas_i_muzzy_purged) CTL_PROTO(stats_arenas_i_base) CTL_PROTO(stats_arenas_i_internal) CTL_PROTO(stats_arenas_i_metadata_thp) CTL_PROTO(stats_arenas_i_tcache_bytes) CTL_PROTO(stats_arenas_i_resident) +CTL_PROTO(stats_arenas_i_abandoned_vm) INDEX_PROTO(stats_arenas_i) CTL_PROTO(stats_allocated) CTL_PROTO(stats_active) CTL_PROTO(stats_background_thread_num_threads) CTL_PROTO(stats_background_thread_num_runs) CTL_PROTO(stats_background_thread_run_interval) CTL_PROTO(stats_metadata) CTL_PROTO(stats_metadata_thp) CTL_PROTO(stats_resident) CTL_PROTO(stats_mapped) CTL_PROTO(stats_retained) +CTL_PROTO(experimental_hooks_install) +CTL_PROTO(experimental_hooks_remove) +CTL_PROTO(experimental_utilization_query) +CTL_PROTO(experimental_utilization_batch_query) +CTL_PROTO(experimental_arenas_i_pactivep) +INDEX_PROTO(experimental_arenas_i) #define MUTEX_STATS_CTL_PROTO_GEN(n) \ CTL_PROTO(stats_##n##_num_ops) \ CTL_PROTO(stats_##n##_num_wait) \ CTL_PROTO(stats_##n##_num_spin_acq) \ CTL_PROTO(stats_##n##_num_owner_switch) \ CTL_PROTO(stats_##n##_total_wait_time) \ CTL_PROTO(stats_##n##_max_wait_time) \ CTL_PROTO(stats_##n##_max_num_thds) /* Global mutexes. */ #define OP(mtx) MUTEX_STATS_CTL_PROTO_GEN(mutexes_##mtx) MUTEX_PROF_GLOBAL_MUTEXES #undef OP /* Per arena mutexes. */ #define OP(mtx) MUTEX_STATS_CTL_PROTO_GEN(arenas_i_mutexes_##mtx) MUTEX_PROF_ARENA_MUTEXES #undef OP /* Arena bin mutexes. */ MUTEX_STATS_CTL_PROTO_GEN(arenas_i_bins_j_mutex) #undef MUTEX_STATS_CTL_PROTO_GEN CTL_PROTO(stats_mutexes_reset) /******************************************************************************/ /* mallctl tree. */ #define NAME(n) {true}, n #define CHILD(t, c) \ sizeof(c##_node) / sizeof(ctl_##t##_node_t), \ (ctl_node_t *)c##_node, \ NULL #define CTL(c) 0, NULL, c##_ctl /* * Only handles internal indexed nodes, since there are currently no external * ones. */ #define INDEX(i) {false}, i##_index static const ctl_named_node_t thread_tcache_node[] = { {NAME("enabled"), CTL(thread_tcache_enabled)}, {NAME("flush"), CTL(thread_tcache_flush)} }; static const ctl_named_node_t thread_prof_node[] = { {NAME("name"), CTL(thread_prof_name)}, {NAME("active"), CTL(thread_prof_active)} }; static const ctl_named_node_t thread_node[] = { {NAME("arena"), CTL(thread_arena)}, {NAME("allocated"), CTL(thread_allocated)}, {NAME("allocatedp"), CTL(thread_allocatedp)}, {NAME("deallocated"), CTL(thread_deallocated)}, {NAME("deallocatedp"), CTL(thread_deallocatedp)}, {NAME("tcache"), CHILD(named, thread_tcache)}, {NAME("prof"), CHILD(named, thread_prof)} }; static const ctl_named_node_t config_node[] = { {NAME("cache_oblivious"), CTL(config_cache_oblivious)}, {NAME("debug"), CTL(config_debug)}, {NAME("fill"), CTL(config_fill)}, {NAME("lazy_lock"), CTL(config_lazy_lock)}, {NAME("malloc_conf"), CTL(config_malloc_conf)}, + {NAME("opt_safety_checks"), CTL(config_opt_safety_checks)}, {NAME("prof"), CTL(config_prof)}, {NAME("prof_libgcc"), CTL(config_prof_libgcc)}, {NAME("prof_libunwind"), CTL(config_prof_libunwind)}, {NAME("stats"), CTL(config_stats)}, {NAME("utrace"), CTL(config_utrace)}, {NAME("xmalloc"), CTL(config_xmalloc)} }; static const ctl_named_node_t opt_node[] = { {NAME("abort"), CTL(opt_abort)}, {NAME("abort_conf"), CTL(opt_abort_conf)}, + {NAME("confirm_conf"), CTL(opt_confirm_conf)}, {NAME("metadata_thp"), CTL(opt_metadata_thp)}, {NAME("retain"), CTL(opt_retain)}, {NAME("dss"), CTL(opt_dss)}, {NAME("narenas"), CTL(opt_narenas)}, {NAME("percpu_arena"), CTL(opt_percpu_arena)}, + {NAME("oversize_threshold"), CTL(opt_oversize_threshold)}, {NAME("background_thread"), CTL(opt_background_thread)}, {NAME("max_background_threads"), CTL(opt_max_background_threads)}, {NAME("dirty_decay_ms"), CTL(opt_dirty_decay_ms)}, {NAME("muzzy_decay_ms"), CTL(opt_muzzy_decay_ms)}, {NAME("stats_print"), CTL(opt_stats_print)}, {NAME("stats_print_opts"), CTL(opt_stats_print_opts)}, {NAME("junk"), CTL(opt_junk)}, {NAME("zero"), CTL(opt_zero)}, {NAME("utrace"), CTL(opt_utrace)}, {NAME("xmalloc"), CTL(opt_xmalloc)}, {NAME("tcache"), CTL(opt_tcache)}, {NAME("thp"), CTL(opt_thp)}, {NAME("lg_extent_max_active_fit"), CTL(opt_lg_extent_max_active_fit)}, {NAME("lg_tcache_max"), CTL(opt_lg_tcache_max)}, {NAME("prof"), CTL(opt_prof)}, {NAME("prof_prefix"), CTL(opt_prof_prefix)}, {NAME("prof_active"), CTL(opt_prof_active)}, {NAME("prof_thread_active_init"), CTL(opt_prof_thread_active_init)}, {NAME("lg_prof_sample"), CTL(opt_lg_prof_sample)}, {NAME("lg_prof_interval"), CTL(opt_lg_prof_interval)}, {NAME("prof_gdump"), CTL(opt_prof_gdump)}, {NAME("prof_final"), CTL(opt_prof_final)}, {NAME("prof_leak"), CTL(opt_prof_leak)}, {NAME("prof_accum"), CTL(opt_prof_accum)} }; static const ctl_named_node_t tcache_node[] = { {NAME("create"), CTL(tcache_create)}, {NAME("flush"), CTL(tcache_flush)}, {NAME("destroy"), CTL(tcache_destroy)} }; static const ctl_named_node_t arena_i_node[] = { {NAME("initialized"), CTL(arena_i_initialized)}, {NAME("decay"), CTL(arena_i_decay)}, {NAME("purge"), CTL(arena_i_purge)}, {NAME("reset"), CTL(arena_i_reset)}, {NAME("destroy"), CTL(arena_i_destroy)}, {NAME("dss"), CTL(arena_i_dss)}, {NAME("dirty_decay_ms"), CTL(arena_i_dirty_decay_ms)}, {NAME("muzzy_decay_ms"), CTL(arena_i_muzzy_decay_ms)}, {NAME("extent_hooks"), CTL(arena_i_extent_hooks)}, {NAME("retain_grow_limit"), CTL(arena_i_retain_grow_limit)} }; static const ctl_named_node_t super_arena_i_node[] = { {NAME(""), CHILD(named, arena_i)} }; static const ctl_indexed_node_t arena_node[] = { {INDEX(arena_i)} }; static const ctl_named_node_t arenas_bin_i_node[] = { {NAME("size"), CTL(arenas_bin_i_size)}, {NAME("nregs"), CTL(arenas_bin_i_nregs)}, - {NAME("slab_size"), CTL(arenas_bin_i_slab_size)} + {NAME("slab_size"), CTL(arenas_bin_i_slab_size)}, + {NAME("nshards"), CTL(arenas_bin_i_nshards)} }; static const ctl_named_node_t super_arenas_bin_i_node[] = { {NAME(""), CHILD(named, arenas_bin_i)} }; static const ctl_indexed_node_t arenas_bin_node[] = { {INDEX(arenas_bin_i)} }; static const ctl_named_node_t arenas_lextent_i_node[] = { {NAME("size"), CTL(arenas_lextent_i_size)} }; static const ctl_named_node_t super_arenas_lextent_i_node[] = { {NAME(""), CHILD(named, arenas_lextent_i)} }; static const ctl_indexed_node_t arenas_lextent_node[] = { {INDEX(arenas_lextent_i)} }; static const ctl_named_node_t arenas_node[] = { {NAME("narenas"), CTL(arenas_narenas)}, {NAME("dirty_decay_ms"), CTL(arenas_dirty_decay_ms)}, {NAME("muzzy_decay_ms"), CTL(arenas_muzzy_decay_ms)}, {NAME("quantum"), CTL(arenas_quantum)}, {NAME("page"), CTL(arenas_page)}, {NAME("tcache_max"), CTL(arenas_tcache_max)}, {NAME("nbins"), CTL(arenas_nbins)}, {NAME("nhbins"), CTL(arenas_nhbins)}, {NAME("bin"), CHILD(indexed, arenas_bin)}, {NAME("nlextents"), CTL(arenas_nlextents)}, {NAME("lextent"), CHILD(indexed, arenas_lextent)}, {NAME("create"), CTL(arenas_create)}, {NAME("lookup"), CTL(arenas_lookup)} }; static const ctl_named_node_t prof_node[] = { {NAME("thread_active_init"), CTL(prof_thread_active_init)}, {NAME("active"), CTL(prof_active)}, {NAME("dump"), CTL(prof_dump)}, {NAME("gdump"), CTL(prof_gdump)}, {NAME("reset"), CTL(prof_reset)}, {NAME("interval"), CTL(prof_interval)}, - {NAME("lg_sample"), CTL(lg_prof_sample)} + {NAME("lg_sample"), CTL(lg_prof_sample)}, + {NAME("log_start"), CTL(prof_log_start)}, + {NAME("log_stop"), CTL(prof_log_stop)} }; - static const ctl_named_node_t stats_arenas_i_small_node[] = { {NAME("allocated"), CTL(stats_arenas_i_small_allocated)}, {NAME("nmalloc"), CTL(stats_arenas_i_small_nmalloc)}, {NAME("ndalloc"), CTL(stats_arenas_i_small_ndalloc)}, - {NAME("nrequests"), CTL(stats_arenas_i_small_nrequests)} + {NAME("nrequests"), CTL(stats_arenas_i_small_nrequests)}, + {NAME("nfills"), CTL(stats_arenas_i_small_nfills)}, + {NAME("nflushes"), CTL(stats_arenas_i_small_nflushes)} }; static const ctl_named_node_t stats_arenas_i_large_node[] = { {NAME("allocated"), CTL(stats_arenas_i_large_allocated)}, {NAME("nmalloc"), CTL(stats_arenas_i_large_nmalloc)}, {NAME("ndalloc"), CTL(stats_arenas_i_large_ndalloc)}, - {NAME("nrequests"), CTL(stats_arenas_i_large_nrequests)} + {NAME("nrequests"), CTL(stats_arenas_i_large_nrequests)}, + {NAME("nfills"), CTL(stats_arenas_i_large_nfills)}, + {NAME("nflushes"), CTL(stats_arenas_i_large_nflushes)} }; #define MUTEX_PROF_DATA_NODE(prefix) \ static const ctl_named_node_t stats_##prefix##_node[] = { \ {NAME("num_ops"), \ CTL(stats_##prefix##_num_ops)}, \ {NAME("num_wait"), \ CTL(stats_##prefix##_num_wait)}, \ {NAME("num_spin_acq"), \ CTL(stats_##prefix##_num_spin_acq)}, \ {NAME("num_owner_switch"), \ CTL(stats_##prefix##_num_owner_switch)}, \ {NAME("total_wait_time"), \ CTL(stats_##prefix##_total_wait_time)}, \ {NAME("max_wait_time"), \ CTL(stats_##prefix##_max_wait_time)}, \ {NAME("max_num_thds"), \ CTL(stats_##prefix##_max_num_thds)} \ /* Note that # of current waiting thread not provided. */ \ }; MUTEX_PROF_DATA_NODE(arenas_i_bins_j_mutex) static const ctl_named_node_t stats_arenas_i_bins_j_node[] = { {NAME("nmalloc"), CTL(stats_arenas_i_bins_j_nmalloc)}, {NAME("ndalloc"), CTL(stats_arenas_i_bins_j_ndalloc)}, {NAME("nrequests"), CTL(stats_arenas_i_bins_j_nrequests)}, {NAME("curregs"), CTL(stats_arenas_i_bins_j_curregs)}, {NAME("nfills"), CTL(stats_arenas_i_bins_j_nfills)}, {NAME("nflushes"), CTL(stats_arenas_i_bins_j_nflushes)}, {NAME("nslabs"), CTL(stats_arenas_i_bins_j_nslabs)}, {NAME("nreslabs"), CTL(stats_arenas_i_bins_j_nreslabs)}, {NAME("curslabs"), CTL(stats_arenas_i_bins_j_curslabs)}, + {NAME("nonfull_slabs"), CTL(stats_arenas_i_bins_j_nonfull_slabs)}, {NAME("mutex"), CHILD(named, stats_arenas_i_bins_j_mutex)} }; static const ctl_named_node_t super_stats_arenas_i_bins_j_node[] = { {NAME(""), CHILD(named, stats_arenas_i_bins_j)} }; static const ctl_indexed_node_t stats_arenas_i_bins_node[] = { {INDEX(stats_arenas_i_bins_j)} }; static const ctl_named_node_t stats_arenas_i_lextents_j_node[] = { {NAME("nmalloc"), CTL(stats_arenas_i_lextents_j_nmalloc)}, {NAME("ndalloc"), CTL(stats_arenas_i_lextents_j_ndalloc)}, {NAME("nrequests"), CTL(stats_arenas_i_lextents_j_nrequests)}, {NAME("curlextents"), CTL(stats_arenas_i_lextents_j_curlextents)} }; static const ctl_named_node_t super_stats_arenas_i_lextents_j_node[] = { {NAME(""), CHILD(named, stats_arenas_i_lextents_j)} }; static const ctl_indexed_node_t stats_arenas_i_lextents_node[] = { {INDEX(stats_arenas_i_lextents_j)} }; +static const ctl_named_node_t stats_arenas_i_extents_j_node[] = { + {NAME("ndirty"), CTL(stats_arenas_i_extents_j_ndirty)}, + {NAME("nmuzzy"), CTL(stats_arenas_i_extents_j_nmuzzy)}, + {NAME("nretained"), CTL(stats_arenas_i_extents_j_nretained)}, + {NAME("dirty_bytes"), CTL(stats_arenas_i_extents_j_dirty_bytes)}, + {NAME("muzzy_bytes"), CTL(stats_arenas_i_extents_j_muzzy_bytes)}, + {NAME("retained_bytes"), CTL(stats_arenas_i_extents_j_retained_bytes)} +}; + +static const ctl_named_node_t super_stats_arenas_i_extents_j_node[] = { + {NAME(""), CHILD(named, stats_arenas_i_extents_j)} +}; + +static const ctl_indexed_node_t stats_arenas_i_extents_node[] = { + {INDEX(stats_arenas_i_extents_j)} +}; + #define OP(mtx) MUTEX_PROF_DATA_NODE(arenas_i_mutexes_##mtx) MUTEX_PROF_ARENA_MUTEXES #undef OP static const ctl_named_node_t stats_arenas_i_mutexes_node[] = { #define OP(mtx) {NAME(#mtx), CHILD(named, stats_arenas_i_mutexes_##mtx)}, MUTEX_PROF_ARENA_MUTEXES #undef OP }; static const ctl_named_node_t stats_arenas_i_node[] = { {NAME("nthreads"), CTL(stats_arenas_i_nthreads)}, {NAME("uptime"), CTL(stats_arenas_i_uptime)}, {NAME("dss"), CTL(stats_arenas_i_dss)}, {NAME("dirty_decay_ms"), CTL(stats_arenas_i_dirty_decay_ms)}, {NAME("muzzy_decay_ms"), CTL(stats_arenas_i_muzzy_decay_ms)}, {NAME("pactive"), CTL(stats_arenas_i_pactive)}, {NAME("pdirty"), CTL(stats_arenas_i_pdirty)}, {NAME("pmuzzy"), CTL(stats_arenas_i_pmuzzy)}, {NAME("mapped"), CTL(stats_arenas_i_mapped)}, {NAME("retained"), CTL(stats_arenas_i_retained)}, + {NAME("extent_avail"), CTL(stats_arenas_i_extent_avail)}, {NAME("dirty_npurge"), CTL(stats_arenas_i_dirty_npurge)}, {NAME("dirty_nmadvise"), CTL(stats_arenas_i_dirty_nmadvise)}, {NAME("dirty_purged"), CTL(stats_arenas_i_dirty_purged)}, {NAME("muzzy_npurge"), CTL(stats_arenas_i_muzzy_npurge)}, {NAME("muzzy_nmadvise"), CTL(stats_arenas_i_muzzy_nmadvise)}, {NAME("muzzy_purged"), CTL(stats_arenas_i_muzzy_purged)}, {NAME("base"), CTL(stats_arenas_i_base)}, {NAME("internal"), CTL(stats_arenas_i_internal)}, {NAME("metadata_thp"), CTL(stats_arenas_i_metadata_thp)}, {NAME("tcache_bytes"), CTL(stats_arenas_i_tcache_bytes)}, {NAME("resident"), CTL(stats_arenas_i_resident)}, + {NAME("abandoned_vm"), CTL(stats_arenas_i_abandoned_vm)}, {NAME("small"), CHILD(named, stats_arenas_i_small)}, {NAME("large"), CHILD(named, stats_arenas_i_large)}, {NAME("bins"), CHILD(indexed, stats_arenas_i_bins)}, {NAME("lextents"), CHILD(indexed, stats_arenas_i_lextents)}, + {NAME("extents"), CHILD(indexed, stats_arenas_i_extents)}, {NAME("mutexes"), CHILD(named, stats_arenas_i_mutexes)} }; static const ctl_named_node_t super_stats_arenas_i_node[] = { {NAME(""), CHILD(named, stats_arenas_i)} }; static const ctl_indexed_node_t stats_arenas_node[] = { {INDEX(stats_arenas_i)} }; static const ctl_named_node_t stats_background_thread_node[] = { {NAME("num_threads"), CTL(stats_background_thread_num_threads)}, {NAME("num_runs"), CTL(stats_background_thread_num_runs)}, {NAME("run_interval"), CTL(stats_background_thread_run_interval)} }; #define OP(mtx) MUTEX_PROF_DATA_NODE(mutexes_##mtx) MUTEX_PROF_GLOBAL_MUTEXES #undef OP static const ctl_named_node_t stats_mutexes_node[] = { #define OP(mtx) {NAME(#mtx), CHILD(named, stats_mutexes_##mtx)}, MUTEX_PROF_GLOBAL_MUTEXES #undef OP {NAME("reset"), CTL(stats_mutexes_reset)} }; #undef MUTEX_PROF_DATA_NODE static const ctl_named_node_t stats_node[] = { {NAME("allocated"), CTL(stats_allocated)}, {NAME("active"), CTL(stats_active)}, {NAME("metadata"), CTL(stats_metadata)}, {NAME("metadata_thp"), CTL(stats_metadata_thp)}, {NAME("resident"), CTL(stats_resident)}, {NAME("mapped"), CTL(stats_mapped)}, {NAME("retained"), CTL(stats_retained)}, {NAME("background_thread"), CHILD(named, stats_background_thread)}, {NAME("mutexes"), CHILD(named, stats_mutexes)}, {NAME("arenas"), CHILD(indexed, stats_arenas)} }; +static const ctl_named_node_t experimental_hooks_node[] = { + {NAME("install"), CTL(experimental_hooks_install)}, + {NAME("remove"), CTL(experimental_hooks_remove)} +}; + +static const ctl_named_node_t experimental_utilization_node[] = { + {NAME("query"), CTL(experimental_utilization_query)}, + {NAME("batch_query"), CTL(experimental_utilization_batch_query)} +}; + +static const ctl_named_node_t experimental_arenas_i_node[] = { + {NAME("pactivep"), CTL(experimental_arenas_i_pactivep)} +}; +static const ctl_named_node_t super_experimental_arenas_i_node[] = { + {NAME(""), CHILD(named, experimental_arenas_i)} +}; + +static const ctl_indexed_node_t experimental_arenas_node[] = { + {INDEX(experimental_arenas_i)} +}; + +static const ctl_named_node_t experimental_node[] = { + {NAME("hooks"), CHILD(named, experimental_hooks)}, + {NAME("utilization"), CHILD(named, experimental_utilization)}, + {NAME("arenas"), CHILD(indexed, experimental_arenas)} +}; + static const ctl_named_node_t root_node[] = { {NAME("version"), CTL(version)}, {NAME("epoch"), CTL(epoch)}, {NAME("background_thread"), CTL(background_thread)}, {NAME("max_background_threads"), CTL(max_background_threads)}, {NAME("thread"), CHILD(named, thread)}, {NAME("config"), CHILD(named, config)}, {NAME("opt"), CHILD(named, opt)}, {NAME("tcache"), CHILD(named, tcache)}, {NAME("arena"), CHILD(indexed, arena)}, {NAME("arenas"), CHILD(named, arenas)}, {NAME("prof"), CHILD(named, prof)}, - {NAME("stats"), CHILD(named, stats)} + {NAME("stats"), CHILD(named, stats)}, + {NAME("experimental"), CHILD(named, experimental)} }; static const ctl_named_node_t super_root_node[] = { {NAME(""), CHILD(named, root)} }; #undef NAME #undef CHILD #undef CTL #undef INDEX /******************************************************************************/ /* * Sets *dst + *src non-atomically. This is safe, since everything is * synchronized by the ctl mutex. */ static void ctl_accum_arena_stats_u64(arena_stats_u64_t *dst, arena_stats_u64_t *src) { #ifdef JEMALLOC_ATOMIC_U64 uint64_t cur_dst = atomic_load_u64(dst, ATOMIC_RELAXED); uint64_t cur_src = atomic_load_u64(src, ATOMIC_RELAXED); atomic_store_u64(dst, cur_dst + cur_src, ATOMIC_RELAXED); #else *dst += *src; #endif } /* Likewise: with ctl mutex synchronization, reading is simple. */ static uint64_t ctl_arena_stats_read_u64(arena_stats_u64_t *p) { #ifdef JEMALLOC_ATOMIC_U64 return atomic_load_u64(p, ATOMIC_RELAXED); #else return *p; #endif } static void accum_atomic_zu(atomic_zu_t *dst, atomic_zu_t *src) { size_t cur_dst = atomic_load_zu(dst, ATOMIC_RELAXED); size_t cur_src = atomic_load_zu(src, ATOMIC_RELAXED); atomic_store_zu(dst, cur_dst + cur_src, ATOMIC_RELAXED); } /******************************************************************************/ static unsigned arenas_i2a_impl(size_t i, bool compat, bool validate) { unsigned a; switch (i) { case MALLCTL_ARENAS_ALL: a = 0; break; case MALLCTL_ARENAS_DESTROYED: a = 1; break; default: if (compat && i == ctl_arenas->narenas) { /* * Provide deprecated backward compatibility for * accessing the merged stats at index narenas rather * than via MALLCTL_ARENAS_ALL. This is scheduled for * removal in 6.0.0. */ a = 0; } else if (validate && i >= ctl_arenas->narenas) { a = UINT_MAX; } else { /* * This function should never be called for an index * more than one past the range of indices that have * initialized ctl data. */ assert(i < ctl_arenas->narenas || (!validate && i == ctl_arenas->narenas)); a = (unsigned)i + 2; } break; } return a; } static unsigned arenas_i2a(size_t i) { return arenas_i2a_impl(i, true, false); } static ctl_arena_t * arenas_i_impl(tsd_t *tsd, size_t i, bool compat, bool init) { ctl_arena_t *ret; assert(!compat || !init); ret = ctl_arenas->arenas[arenas_i2a_impl(i, compat, false)]; if (init && ret == NULL) { if (config_stats) { struct container_s { ctl_arena_t ctl_arena; ctl_arena_stats_t astats; }; struct container_s *cont = (struct container_s *)base_alloc(tsd_tsdn(tsd), b0get(), sizeof(struct container_s), QUANTUM); if (cont == NULL) { return NULL; } ret = &cont->ctl_arena; ret->astats = &cont->astats; } else { ret = (ctl_arena_t *)base_alloc(tsd_tsdn(tsd), b0get(), sizeof(ctl_arena_t), QUANTUM); if (ret == NULL) { return NULL; } } ret->arena_ind = (unsigned)i; ctl_arenas->arenas[arenas_i2a_impl(i, compat, false)] = ret; } assert(ret == NULL || arenas_i2a(ret->arena_ind) == arenas_i2a(i)); return ret; } static ctl_arena_t * arenas_i(size_t i) { ctl_arena_t *ret = arenas_i_impl(tsd_fetch(), i, true, false); assert(ret != NULL); return ret; } static void ctl_arena_clear(ctl_arena_t *ctl_arena) { ctl_arena->nthreads = 0; ctl_arena->dss = dss_prec_names[dss_prec_limit]; ctl_arena->dirty_decay_ms = -1; ctl_arena->muzzy_decay_ms = -1; ctl_arena->pactive = 0; ctl_arena->pdirty = 0; ctl_arena->pmuzzy = 0; if (config_stats) { memset(&ctl_arena->astats->astats, 0, sizeof(arena_stats_t)); ctl_arena->astats->allocated_small = 0; ctl_arena->astats->nmalloc_small = 0; ctl_arena->astats->ndalloc_small = 0; ctl_arena->astats->nrequests_small = 0; - memset(ctl_arena->astats->bstats, 0, NBINS * + ctl_arena->astats->nfills_small = 0; + ctl_arena->astats->nflushes_small = 0; + memset(ctl_arena->astats->bstats, 0, SC_NBINS * sizeof(bin_stats_t)); - memset(ctl_arena->astats->lstats, 0, (NSIZES - NBINS) * + memset(ctl_arena->astats->lstats, 0, (SC_NSIZES - SC_NBINS) * sizeof(arena_stats_large_t)); + memset(ctl_arena->astats->estats, 0, SC_NPSIZES * + sizeof(arena_stats_extents_t)); } } static void ctl_arena_stats_amerge(tsdn_t *tsdn, ctl_arena_t *ctl_arena, arena_t *arena) { unsigned i; if (config_stats) { arena_stats_merge(tsdn, arena, &ctl_arena->nthreads, &ctl_arena->dss, &ctl_arena->dirty_decay_ms, &ctl_arena->muzzy_decay_ms, &ctl_arena->pactive, &ctl_arena->pdirty, &ctl_arena->pmuzzy, &ctl_arena->astats->astats, ctl_arena->astats->bstats, - ctl_arena->astats->lstats); + ctl_arena->astats->lstats, ctl_arena->astats->estats); - for (i = 0; i < NBINS; i++) { + for (i = 0; i < SC_NBINS; i++) { ctl_arena->astats->allocated_small += ctl_arena->astats->bstats[i].curregs * sz_index2size(i); ctl_arena->astats->nmalloc_small += ctl_arena->astats->bstats[i].nmalloc; ctl_arena->astats->ndalloc_small += ctl_arena->astats->bstats[i].ndalloc; ctl_arena->astats->nrequests_small += ctl_arena->astats->bstats[i].nrequests; + ctl_arena->astats->nfills_small += + ctl_arena->astats->bstats[i].nfills; + ctl_arena->astats->nflushes_small += + ctl_arena->astats->bstats[i].nflushes; } } else { arena_basic_stats_merge(tsdn, arena, &ctl_arena->nthreads, &ctl_arena->dss, &ctl_arena->dirty_decay_ms, &ctl_arena->muzzy_decay_ms, &ctl_arena->pactive, &ctl_arena->pdirty, &ctl_arena->pmuzzy); } } static void ctl_arena_stats_sdmerge(ctl_arena_t *ctl_sdarena, ctl_arena_t *ctl_arena, bool destroyed) { unsigned i; if (!destroyed) { ctl_sdarena->nthreads += ctl_arena->nthreads; ctl_sdarena->pactive += ctl_arena->pactive; ctl_sdarena->pdirty += ctl_arena->pdirty; ctl_sdarena->pmuzzy += ctl_arena->pmuzzy; } else { assert(ctl_arena->nthreads == 0); assert(ctl_arena->pactive == 0); assert(ctl_arena->pdirty == 0); assert(ctl_arena->pmuzzy == 0); } if (config_stats) { ctl_arena_stats_t *sdstats = ctl_sdarena->astats; ctl_arena_stats_t *astats = ctl_arena->astats; if (!destroyed) { accum_atomic_zu(&sdstats->astats.mapped, &astats->astats.mapped); accum_atomic_zu(&sdstats->astats.retained, &astats->astats.retained); + accum_atomic_zu(&sdstats->astats.extent_avail, + &astats->astats.extent_avail); } ctl_accum_arena_stats_u64(&sdstats->astats.decay_dirty.npurge, &astats->astats.decay_dirty.npurge); ctl_accum_arena_stats_u64(&sdstats->astats.decay_dirty.nmadvise, &astats->astats.decay_dirty.nmadvise); ctl_accum_arena_stats_u64(&sdstats->astats.decay_dirty.purged, &astats->astats.decay_dirty.purged); ctl_accum_arena_stats_u64(&sdstats->astats.decay_muzzy.npurge, &astats->astats.decay_muzzy.npurge); ctl_accum_arena_stats_u64(&sdstats->astats.decay_muzzy.nmadvise, &astats->astats.decay_muzzy.nmadvise); ctl_accum_arena_stats_u64(&sdstats->astats.decay_muzzy.purged, &astats->astats.decay_muzzy.purged); #define OP(mtx) malloc_mutex_prof_merge( \ &(sdstats->astats.mutex_prof_data[ \ arena_prof_mutex_##mtx]), \ &(astats->astats.mutex_prof_data[ \ arena_prof_mutex_##mtx])); MUTEX_PROF_ARENA_MUTEXES #undef OP if (!destroyed) { accum_atomic_zu(&sdstats->astats.base, &astats->astats.base); accum_atomic_zu(&sdstats->astats.internal, &astats->astats.internal); accum_atomic_zu(&sdstats->astats.resident, &astats->astats.resident); accum_atomic_zu(&sdstats->astats.metadata_thp, &astats->astats.metadata_thp); } else { assert(atomic_load_zu( &astats->astats.internal, ATOMIC_RELAXED) == 0); } if (!destroyed) { sdstats->allocated_small += astats->allocated_small; } else { assert(astats->allocated_small == 0); } sdstats->nmalloc_small += astats->nmalloc_small; sdstats->ndalloc_small += astats->ndalloc_small; sdstats->nrequests_small += astats->nrequests_small; + sdstats->nfills_small += astats->nfills_small; + sdstats->nflushes_small += astats->nflushes_small; if (!destroyed) { accum_atomic_zu(&sdstats->astats.allocated_large, &astats->astats.allocated_large); } else { assert(atomic_load_zu(&astats->astats.allocated_large, ATOMIC_RELAXED) == 0); } ctl_accum_arena_stats_u64(&sdstats->astats.nmalloc_large, &astats->astats.nmalloc_large); ctl_accum_arena_stats_u64(&sdstats->astats.ndalloc_large, &astats->astats.ndalloc_large); ctl_accum_arena_stats_u64(&sdstats->astats.nrequests_large, &astats->astats.nrequests_large); + accum_atomic_zu(&sdstats->astats.abandoned_vm, + &astats->astats.abandoned_vm); accum_atomic_zu(&sdstats->astats.tcache_bytes, &astats->astats.tcache_bytes); if (ctl_arena->arena_ind == 0) { sdstats->astats.uptime = astats->astats.uptime; } - for (i = 0; i < NBINS; i++) { + /* Merge bin stats. */ + for (i = 0; i < SC_NBINS; i++) { sdstats->bstats[i].nmalloc += astats->bstats[i].nmalloc; sdstats->bstats[i].ndalloc += astats->bstats[i].ndalloc; sdstats->bstats[i].nrequests += astats->bstats[i].nrequests; if (!destroyed) { sdstats->bstats[i].curregs += astats->bstats[i].curregs; } else { assert(astats->bstats[i].curregs == 0); } sdstats->bstats[i].nfills += astats->bstats[i].nfills; sdstats->bstats[i].nflushes += astats->bstats[i].nflushes; sdstats->bstats[i].nslabs += astats->bstats[i].nslabs; sdstats->bstats[i].reslabs += astats->bstats[i].reslabs; if (!destroyed) { sdstats->bstats[i].curslabs += astats->bstats[i].curslabs; + sdstats->bstats[i].nonfull_slabs += + astats->bstats[i].nonfull_slabs; } else { assert(astats->bstats[i].curslabs == 0); + assert(astats->bstats[i].nonfull_slabs == 0); } malloc_mutex_prof_merge(&sdstats->bstats[i].mutex_data, &astats->bstats[i].mutex_data); } - for (i = 0; i < NSIZES - NBINS; i++) { + /* Merge stats for large allocations. */ + for (i = 0; i < SC_NSIZES - SC_NBINS; i++) { ctl_accum_arena_stats_u64(&sdstats->lstats[i].nmalloc, &astats->lstats[i].nmalloc); ctl_accum_arena_stats_u64(&sdstats->lstats[i].ndalloc, &astats->lstats[i].ndalloc); ctl_accum_arena_stats_u64(&sdstats->lstats[i].nrequests, &astats->lstats[i].nrequests); if (!destroyed) { sdstats->lstats[i].curlextents += astats->lstats[i].curlextents; } else { assert(astats->lstats[i].curlextents == 0); } } + + /* Merge extents stats. */ + for (i = 0; i < SC_NPSIZES; i++) { + accum_atomic_zu(&sdstats->estats[i].ndirty, + &astats->estats[i].ndirty); + accum_atomic_zu(&sdstats->estats[i].nmuzzy, + &astats->estats[i].nmuzzy); + accum_atomic_zu(&sdstats->estats[i].nretained, + &astats->estats[i].nretained); + accum_atomic_zu(&sdstats->estats[i].dirty_bytes, + &astats->estats[i].dirty_bytes); + accum_atomic_zu(&sdstats->estats[i].muzzy_bytes, + &astats->estats[i].muzzy_bytes); + accum_atomic_zu(&sdstats->estats[i].retained_bytes, + &astats->estats[i].retained_bytes); + } } } static void ctl_arena_refresh(tsdn_t *tsdn, arena_t *arena, ctl_arena_t *ctl_sdarena, unsigned i, bool destroyed) { ctl_arena_t *ctl_arena = arenas_i(i); ctl_arena_clear(ctl_arena); ctl_arena_stats_amerge(tsdn, ctl_arena, arena); /* Merge into sum stats as well. */ ctl_arena_stats_sdmerge(ctl_sdarena, ctl_arena, destroyed); } static unsigned ctl_arena_init(tsd_t *tsd, extent_hooks_t *extent_hooks) { unsigned arena_ind; ctl_arena_t *ctl_arena; if ((ctl_arena = ql_last(&ctl_arenas->destroyed, destroyed_link)) != NULL) { ql_remove(&ctl_arenas->destroyed, ctl_arena, destroyed_link); arena_ind = ctl_arena->arena_ind; } else { arena_ind = ctl_arenas->narenas; } /* Trigger stats allocation. */ if (arenas_i_impl(tsd, arena_ind, false, true) == NULL) { return UINT_MAX; } /* Initialize new arena. */ if (arena_init(tsd_tsdn(tsd), arena_ind, extent_hooks) == NULL) { return UINT_MAX; } if (arena_ind == ctl_arenas->narenas) { ctl_arenas->narenas++; } return arena_ind; } static void ctl_background_thread_stats_read(tsdn_t *tsdn) { background_thread_stats_t *stats = &ctl_stats->background_thread; if (!have_background_thread || background_thread_stats_read(tsdn, stats)) { memset(stats, 0, sizeof(background_thread_stats_t)); nstime_init(&stats->run_interval, 0); } } static void ctl_refresh(tsdn_t *tsdn) { unsigned i; ctl_arena_t *ctl_sarena = arenas_i(MALLCTL_ARENAS_ALL); VARIABLE_ARRAY(arena_t *, tarenas, ctl_arenas->narenas); /* * Clear sum stats, since they will be merged into by * ctl_arena_refresh(). */ ctl_arena_clear(ctl_sarena); for (i = 0; i < ctl_arenas->narenas; i++) { tarenas[i] = arena_get(tsdn, i, false); } for (i = 0; i < ctl_arenas->narenas; i++) { ctl_arena_t *ctl_arena = arenas_i(i); bool initialized = (tarenas[i] != NULL); ctl_arena->initialized = initialized; if (initialized) { ctl_arena_refresh(tsdn, tarenas[i], ctl_sarena, i, false); } } if (config_stats) { ctl_stats->allocated = ctl_sarena->astats->allocated_small + atomic_load_zu(&ctl_sarena->astats->astats.allocated_large, ATOMIC_RELAXED); ctl_stats->active = (ctl_sarena->pactive << LG_PAGE); ctl_stats->metadata = atomic_load_zu( &ctl_sarena->astats->astats.base, ATOMIC_RELAXED) + atomic_load_zu(&ctl_sarena->astats->astats.internal, ATOMIC_RELAXED); ctl_stats->metadata_thp = atomic_load_zu( &ctl_sarena->astats->astats.metadata_thp, ATOMIC_RELAXED); ctl_stats->resident = atomic_load_zu( &ctl_sarena->astats->astats.resident, ATOMIC_RELAXED); ctl_stats->mapped = atomic_load_zu( &ctl_sarena->astats->astats.mapped, ATOMIC_RELAXED); ctl_stats->retained = atomic_load_zu( &ctl_sarena->astats->astats.retained, ATOMIC_RELAXED); ctl_background_thread_stats_read(tsdn); #define READ_GLOBAL_MUTEX_PROF_DATA(i, mtx) \ malloc_mutex_lock(tsdn, &mtx); \ malloc_mutex_prof_read(tsdn, &ctl_stats->mutex_prof_data[i], &mtx); \ malloc_mutex_unlock(tsdn, &mtx); if (config_prof && opt_prof) { READ_GLOBAL_MUTEX_PROF_DATA(global_prof_mutex_prof, bt2gctx_mtx); } if (have_background_thread) { READ_GLOBAL_MUTEX_PROF_DATA( global_prof_mutex_background_thread, background_thread_lock); } else { memset(&ctl_stats->mutex_prof_data[ global_prof_mutex_background_thread], 0, sizeof(mutex_prof_data_t)); } /* We own ctl mutex already. */ malloc_mutex_prof_read(tsdn, &ctl_stats->mutex_prof_data[global_prof_mutex_ctl], &ctl_mtx); #undef READ_GLOBAL_MUTEX_PROF_DATA } ctl_arenas->epoch++; } static bool ctl_init(tsd_t *tsd) { bool ret; tsdn_t *tsdn = tsd_tsdn(tsd); malloc_mutex_lock(tsdn, &ctl_mtx); if (!ctl_initialized) { ctl_arena_t *ctl_sarena, *ctl_darena; unsigned i; /* * Allocate demand-zeroed space for pointers to the full * range of supported arena indices. */ if (ctl_arenas == NULL) { ctl_arenas = (ctl_arenas_t *)base_alloc(tsdn, b0get(), sizeof(ctl_arenas_t), QUANTUM); if (ctl_arenas == NULL) { ret = true; goto label_return; } } if (config_stats && ctl_stats == NULL) { ctl_stats = (ctl_stats_t *)base_alloc(tsdn, b0get(), sizeof(ctl_stats_t), QUANTUM); if (ctl_stats == NULL) { ret = true; goto label_return; } } /* * Allocate space for the current full range of arenas * here rather than doing it lazily elsewhere, in order * to limit when OOM-caused errors can occur. */ if ((ctl_sarena = arenas_i_impl(tsd, MALLCTL_ARENAS_ALL, false, true)) == NULL) { ret = true; goto label_return; } ctl_sarena->initialized = true; if ((ctl_darena = arenas_i_impl(tsd, MALLCTL_ARENAS_DESTROYED, false, true)) == NULL) { ret = true; goto label_return; } ctl_arena_clear(ctl_darena); /* * Don't toggle ctl_darena to initialized until an arena is * actually destroyed, so that arena..initialized can be used * to query whether the stats are relevant. */ ctl_arenas->narenas = narenas_total_get(); for (i = 0; i < ctl_arenas->narenas; i++) { if (arenas_i_impl(tsd, i, false, true) == NULL) { ret = true; goto label_return; } } ql_new(&ctl_arenas->destroyed); ctl_refresh(tsdn); ctl_initialized = true; } ret = false; label_return: malloc_mutex_unlock(tsdn, &ctl_mtx); return ret; } static int ctl_lookup(tsdn_t *tsdn, const char *name, ctl_node_t const **nodesp, size_t *mibp, size_t *depthp) { int ret; const char *elm, *tdot, *dot; size_t elen, i, j; const ctl_named_node_t *node; elm = name; /* Equivalent to strchrnul(). */ dot = ((tdot = strchr(elm, '.')) != NULL) ? tdot : strchr(elm, '\0'); elen = (size_t)((uintptr_t)dot - (uintptr_t)elm); if (elen == 0) { ret = ENOENT; goto label_return; } node = super_root_node; for (i = 0; i < *depthp; i++) { assert(node); assert(node->nchildren > 0); if (ctl_named_node(node->children) != NULL) { const ctl_named_node_t *pnode = node; /* Children are named. */ for (j = 0; j < node->nchildren; j++) { const ctl_named_node_t *child = ctl_named_children(node, j); if (strlen(child->name) == elen && strncmp(elm, child->name, elen) == 0) { node = child; if (nodesp != NULL) { nodesp[i] = (const ctl_node_t *)node; } mibp[i] = j; break; } } if (node == pnode) { ret = ENOENT; goto label_return; } } else { uintmax_t index; const ctl_indexed_node_t *inode; /* Children are indexed. */ index = malloc_strtoumax(elm, NULL, 10); if (index == UINTMAX_MAX || index > SIZE_T_MAX) { ret = ENOENT; goto label_return; } inode = ctl_indexed_node(node->children); node = inode->index(tsdn, mibp, *depthp, (size_t)index); if (node == NULL) { ret = ENOENT; goto label_return; } if (nodesp != NULL) { nodesp[i] = (const ctl_node_t *)node; } mibp[i] = (size_t)index; } if (node->ctl != NULL) { /* Terminal node. */ if (*dot != '\0') { /* * The name contains more elements than are * in this path through the tree. */ ret = ENOENT; goto label_return; } /* Complete lookup successful. */ *depthp = i + 1; break; } /* Update elm. */ if (*dot == '\0') { /* No more elements. */ ret = ENOENT; goto label_return; } elm = &dot[1]; dot = ((tdot = strchr(elm, '.')) != NULL) ? tdot : strchr(elm, '\0'); elen = (size_t)((uintptr_t)dot - (uintptr_t)elm); } ret = 0; label_return: return ret; } int ctl_byname(tsd_t *tsd, const char *name, void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; size_t depth; ctl_node_t const *nodes[CTL_MAX_DEPTH]; size_t mib[CTL_MAX_DEPTH]; const ctl_named_node_t *node; if (!ctl_initialized && ctl_init(tsd)) { ret = EAGAIN; goto label_return; } depth = CTL_MAX_DEPTH; ret = ctl_lookup(tsd_tsdn(tsd), name, nodes, mib, &depth); if (ret != 0) { goto label_return; } node = ctl_named_node(nodes[depth-1]); if (node != NULL && node->ctl) { ret = node->ctl(tsd, mib, depth, oldp, oldlenp, newp, newlen); } else { /* The name refers to a partial path through the ctl tree. */ ret = ENOENT; } label_return: return(ret); } int ctl_nametomib(tsd_t *tsd, const char *name, size_t *mibp, size_t *miblenp) { int ret; if (!ctl_initialized && ctl_init(tsd)) { ret = EAGAIN; goto label_return; } ret = ctl_lookup(tsd_tsdn(tsd), name, NULL, mibp, miblenp); label_return: return(ret); } int ctl_bymib(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; const ctl_named_node_t *node; size_t i; if (!ctl_initialized && ctl_init(tsd)) { ret = EAGAIN; goto label_return; } /* Iterate down the tree. */ node = super_root_node; for (i = 0; i < miblen; i++) { assert(node); assert(node->nchildren > 0); if (ctl_named_node(node->children) != NULL) { /* Children are named. */ if (node->nchildren <= mib[i]) { ret = ENOENT; goto label_return; } node = ctl_named_children(node, mib[i]); } else { const ctl_indexed_node_t *inode; /* Indexed element. */ inode = ctl_indexed_node(node->children); node = inode->index(tsd_tsdn(tsd), mib, miblen, mib[i]); if (node == NULL) { ret = ENOENT; goto label_return; } } } /* Call the ctl function. */ if (node && node->ctl) { ret = node->ctl(tsd, mib, miblen, oldp, oldlenp, newp, newlen); } else { /* Partial MIB. */ ret = ENOENT; } label_return: return(ret); } bool ctl_boot(void) { if (malloc_mutex_init(&ctl_mtx, "ctl", WITNESS_RANK_CTL, malloc_mutex_rank_exclusive)) { return true; } ctl_initialized = false; return false; } void ctl_prefork(tsdn_t *tsdn) { malloc_mutex_prefork(tsdn, &ctl_mtx); } void ctl_postfork_parent(tsdn_t *tsdn) { malloc_mutex_postfork_parent(tsdn, &ctl_mtx); } void ctl_postfork_child(tsdn_t *tsdn) { malloc_mutex_postfork_child(tsdn, &ctl_mtx); } /******************************************************************************/ /* *_ctl() functions. */ #define READONLY() do { \ if (newp != NULL || newlen != 0) { \ ret = EPERM; \ goto label_return; \ } \ } while (0) #define WRITEONLY() do { \ if (oldp != NULL || oldlenp != NULL) { \ ret = EPERM; \ goto label_return; \ } \ } while (0) #define READ_XOR_WRITE() do { \ if ((oldp != NULL && oldlenp != NULL) && (newp != NULL || \ newlen != 0)) { \ ret = EPERM; \ goto label_return; \ } \ } while (0) #define READ(v, t) do { \ if (oldp != NULL && oldlenp != NULL) { \ if (*oldlenp != sizeof(t)) { \ size_t copylen = (sizeof(t) <= *oldlenp) \ ? sizeof(t) : *oldlenp; \ memcpy(oldp, (void *)&(v), copylen); \ ret = EINVAL; \ goto label_return; \ } \ *(t *)oldp = (v); \ } \ } while (0) #define WRITE(v, t) do { \ if (newp != NULL) { \ if (newlen != sizeof(t)) { \ ret = EINVAL; \ goto label_return; \ } \ (v) = *(t *)newp; \ } \ } while (0) #define MIB_UNSIGNED(v, i) do { \ if (mib[i] > UINT_MAX) { \ ret = EFAULT; \ goto label_return; \ } \ v = (unsigned)mib[i]; \ } while (0) /* * There's a lot of code duplication in the following macros due to limitations * in how nested cpp macros are expanded. */ #define CTL_RO_CLGEN(c, l, n, v, t) \ static int \ n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, \ size_t *oldlenp, void *newp, size_t newlen) { \ int ret; \ t oldval; \ \ if (!(c)) { \ return ENOENT; \ } \ if (l) { \ malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx); \ } \ READONLY(); \ oldval = (v); \ READ(oldval, t); \ \ ret = 0; \ label_return: \ if (l) { \ malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx); \ } \ return ret; \ } #define CTL_RO_CGEN(c, n, v, t) \ static int \ -n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, \ - size_t *oldlenp, void *newp, size_t newlen) { \ +n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, \ + void *oldp, size_t *oldlenp, void *newp, size_t newlen) { \ int ret; \ t oldval; \ \ if (!(c)) { \ return ENOENT; \ } \ malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx); \ READONLY(); \ oldval = (v); \ READ(oldval, t); \ \ ret = 0; \ label_return: \ malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx); \ return ret; \ } #define CTL_RO_GEN(n, v, t) \ static int \ n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, \ size_t *oldlenp, void *newp, size_t newlen) { \ int ret; \ t oldval; \ \ malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx); \ READONLY(); \ oldval = (v); \ READ(oldval, t); \ \ ret = 0; \ label_return: \ malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx); \ return ret; \ } /* * ctl_mtx is not acquired, under the assumption that no pertinent data will * mutate during the call. */ #define CTL_RO_NL_CGEN(c, n, v, t) \ static int \ -n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, \ - size_t *oldlenp, void *newp, size_t newlen) { \ +n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, \ + void *oldp, size_t *oldlenp, void *newp, size_t newlen) { \ int ret; \ t oldval; \ \ if (!(c)) { \ return ENOENT; \ } \ READONLY(); \ oldval = (v); \ READ(oldval, t); \ \ ret = 0; \ label_return: \ return ret; \ } #define CTL_RO_NL_GEN(n, v, t) \ static int \ -n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, \ - size_t *oldlenp, void *newp, size_t newlen) { \ +n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, \ + void *oldp, size_t *oldlenp, void *newp, size_t newlen) { \ int ret; \ t oldval; \ \ READONLY(); \ oldval = (v); \ READ(oldval, t); \ \ ret = 0; \ label_return: \ return ret; \ } #define CTL_TSD_RO_NL_CGEN(c, n, m, t) \ static int \ n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, \ size_t *oldlenp, void *newp, size_t newlen) { \ int ret; \ t oldval; \ \ if (!(c)) { \ return ENOENT; \ } \ READONLY(); \ oldval = (m(tsd)); \ READ(oldval, t); \ \ ret = 0; \ label_return: \ return ret; \ } #define CTL_RO_CONFIG_GEN(n, t) \ static int \ -n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, \ - size_t *oldlenp, void *newp, size_t newlen) { \ +n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, \ + void *oldp, size_t *oldlenp, void *newp, size_t newlen) { \ int ret; \ t oldval; \ \ READONLY(); \ oldval = n; \ READ(oldval, t); \ \ ret = 0; \ label_return: \ return ret; \ } /******************************************************************************/ CTL_RO_NL_GEN(version, JEMALLOC_VERSION, const char *) static int -epoch_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, - size_t *oldlenp, void *newp, size_t newlen) { +epoch_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, + void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; UNUSED uint64_t newval; malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx); WRITE(newval, uint64_t); if (newp != NULL) { ctl_refresh(tsd_tsdn(tsd)); } READ(ctl_arenas->epoch, uint64_t); ret = 0; label_return: malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx); return ret; } static int -background_thread_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, - void *oldp, size_t *oldlenp, void *newp, size_t newlen) { +background_thread_ctl(tsd_t *tsd, const size_t *mib, + size_t miblen, void *oldp, size_t *oldlenp, + void *newp, size_t newlen) { int ret; bool oldval; if (!have_background_thread) { return ENOENT; } background_thread_ctl_init(tsd_tsdn(tsd)); malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx); malloc_mutex_lock(tsd_tsdn(tsd), &background_thread_lock); if (newp == NULL) { oldval = background_thread_enabled(); READ(oldval, bool); } else { if (newlen != sizeof(bool)) { ret = EINVAL; goto label_return; } oldval = background_thread_enabled(); READ(oldval, bool); bool newval = *(bool *)newp; if (newval == oldval) { ret = 0; goto label_return; } background_thread_enabled_set(tsd_tsdn(tsd), newval); if (newval) { - if (!can_enable_background_thread) { - malloc_printf(": Error in dlsym(" - "RTLD_NEXT, \"pthread_create\"). Cannot " - "enable background_thread\n"); - ret = EFAULT; - goto label_return; - } if (background_threads_enable(tsd)) { ret = EFAULT; goto label_return; } } else { if (background_threads_disable(tsd)) { ret = EFAULT; goto label_return; } } } ret = 0; label_return: malloc_mutex_unlock(tsd_tsdn(tsd), &background_thread_lock); malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx); return ret; } static int -max_background_threads_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, - void *oldp, size_t *oldlenp, void *newp, size_t newlen) { +max_background_threads_ctl(tsd_t *tsd, const size_t *mib, + size_t miblen, void *oldp, size_t *oldlenp, void *newp, + size_t newlen) { int ret; size_t oldval; if (!have_background_thread) { return ENOENT; } background_thread_ctl_init(tsd_tsdn(tsd)); malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx); malloc_mutex_lock(tsd_tsdn(tsd), &background_thread_lock); if (newp == NULL) { oldval = max_background_threads; READ(oldval, size_t); } else { if (newlen != sizeof(size_t)) { ret = EINVAL; goto label_return; } oldval = max_background_threads; READ(oldval, size_t); size_t newval = *(size_t *)newp; if (newval == oldval) { ret = 0; goto label_return; } if (newval > opt_max_background_threads) { ret = EINVAL; goto label_return; } if (background_thread_enabled()) { - if (!can_enable_background_thread) { - malloc_printf(": Error in dlsym(" - "RTLD_NEXT, \"pthread_create\"). Cannot " - "enable background_thread\n"); - ret = EFAULT; - goto label_return; - } background_thread_enabled_set(tsd_tsdn(tsd), false); if (background_threads_disable(tsd)) { ret = EFAULT; goto label_return; } max_background_threads = newval; background_thread_enabled_set(tsd_tsdn(tsd), true); if (background_threads_enable(tsd)) { ret = EFAULT; goto label_return; } } else { max_background_threads = newval; } } ret = 0; label_return: malloc_mutex_unlock(tsd_tsdn(tsd), &background_thread_lock); malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx); return ret; } /******************************************************************************/ CTL_RO_CONFIG_GEN(config_cache_oblivious, bool) CTL_RO_CONFIG_GEN(config_debug, bool) CTL_RO_CONFIG_GEN(config_fill, bool) CTL_RO_CONFIG_GEN(config_lazy_lock, bool) CTL_RO_CONFIG_GEN(config_malloc_conf, const char *) +CTL_RO_CONFIG_GEN(config_opt_safety_checks, bool) CTL_RO_CONFIG_GEN(config_prof, bool) CTL_RO_CONFIG_GEN(config_prof_libgcc, bool) CTL_RO_CONFIG_GEN(config_prof_libunwind, bool) CTL_RO_CONFIG_GEN(config_stats, bool) CTL_RO_CONFIG_GEN(config_utrace, bool) CTL_RO_CONFIG_GEN(config_xmalloc, bool) /******************************************************************************/ CTL_RO_NL_GEN(opt_abort, opt_abort, bool) CTL_RO_NL_GEN(opt_abort_conf, opt_abort_conf, bool) +CTL_RO_NL_GEN(opt_confirm_conf, opt_confirm_conf, bool) CTL_RO_NL_GEN(opt_metadata_thp, metadata_thp_mode_names[opt_metadata_thp], const char *) CTL_RO_NL_GEN(opt_retain, opt_retain, bool) CTL_RO_NL_GEN(opt_dss, opt_dss, const char *) CTL_RO_NL_GEN(opt_narenas, opt_narenas, unsigned) CTL_RO_NL_GEN(opt_percpu_arena, percpu_arena_mode_names[opt_percpu_arena], const char *) +CTL_RO_NL_GEN(opt_oversize_threshold, opt_oversize_threshold, size_t) CTL_RO_NL_GEN(opt_background_thread, opt_background_thread, bool) CTL_RO_NL_GEN(opt_max_background_threads, opt_max_background_threads, size_t) CTL_RO_NL_GEN(opt_dirty_decay_ms, opt_dirty_decay_ms, ssize_t) CTL_RO_NL_GEN(opt_muzzy_decay_ms, opt_muzzy_decay_ms, ssize_t) CTL_RO_NL_GEN(opt_stats_print, opt_stats_print, bool) CTL_RO_NL_GEN(opt_stats_print_opts, opt_stats_print_opts, const char *) CTL_RO_NL_CGEN(config_fill, opt_junk, opt_junk, const char *) CTL_RO_NL_CGEN(config_fill, opt_zero, opt_zero, bool) CTL_RO_NL_CGEN(config_utrace, opt_utrace, opt_utrace, bool) CTL_RO_NL_CGEN(config_xmalloc, opt_xmalloc, opt_xmalloc, bool) CTL_RO_NL_GEN(opt_tcache, opt_tcache, bool) CTL_RO_NL_GEN(opt_thp, thp_mode_names[opt_thp], const char *) CTL_RO_NL_GEN(opt_lg_extent_max_active_fit, opt_lg_extent_max_active_fit, size_t) CTL_RO_NL_GEN(opt_lg_tcache_max, opt_lg_tcache_max, ssize_t) CTL_RO_NL_CGEN(config_prof, opt_prof, opt_prof, bool) CTL_RO_NL_CGEN(config_prof, opt_prof_prefix, opt_prof_prefix, const char *) CTL_RO_NL_CGEN(config_prof, opt_prof_active, opt_prof_active, bool) CTL_RO_NL_CGEN(config_prof, opt_prof_thread_active_init, opt_prof_thread_active_init, bool) CTL_RO_NL_CGEN(config_prof, opt_lg_prof_sample, opt_lg_prof_sample, size_t) CTL_RO_NL_CGEN(config_prof, opt_prof_accum, opt_prof_accum, bool) CTL_RO_NL_CGEN(config_prof, opt_lg_prof_interval, opt_lg_prof_interval, ssize_t) CTL_RO_NL_CGEN(config_prof, opt_prof_gdump, opt_prof_gdump, bool) CTL_RO_NL_CGEN(config_prof, opt_prof_final, opt_prof_final, bool) CTL_RO_NL_CGEN(config_prof, opt_prof_leak, opt_prof_leak, bool) /******************************************************************************/ static int -thread_arena_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, - size_t *oldlenp, void *newp, size_t newlen) { +thread_arena_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, + void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; arena_t *oldarena; unsigned newind, oldind; oldarena = arena_choose(tsd, NULL); if (oldarena == NULL) { return EAGAIN; } newind = oldind = arena_ind_get(oldarena); WRITE(newind, unsigned); READ(oldind, unsigned); if (newind != oldind) { arena_t *newarena; if (newind >= narenas_total_get()) { /* New arena index is out of range. */ ret = EFAULT; goto label_return; } if (have_percpu_arena && PERCPU_ARENA_ENABLED(opt_percpu_arena)) { if (newind < percpu_arena_ind_limit(opt_percpu_arena)) { /* * If perCPU arena is enabled, thread_arena * control is not allowed for the auto arena * range. */ ret = EPERM; goto label_return; } } /* Initialize arena if necessary. */ newarena = arena_get(tsd_tsdn(tsd), newind, true); if (newarena == NULL) { ret = EAGAIN; goto label_return; } /* Set new arena/tcache associations. */ arena_migrate(tsd, oldind, newind); if (tcache_available(tsd)) { tcache_arena_reassociate(tsd_tsdn(tsd), tsd_tcachep_get(tsd), newarena); } } ret = 0; label_return: return ret; } CTL_TSD_RO_NL_CGEN(config_stats, thread_allocated, tsd_thread_allocated_get, uint64_t) CTL_TSD_RO_NL_CGEN(config_stats, thread_allocatedp, tsd_thread_allocatedp_get, uint64_t *) CTL_TSD_RO_NL_CGEN(config_stats, thread_deallocated, tsd_thread_deallocated_get, uint64_t) CTL_TSD_RO_NL_CGEN(config_stats, thread_deallocatedp, tsd_thread_deallocatedp_get, uint64_t *) static int -thread_tcache_enabled_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, - void *oldp, size_t *oldlenp, void *newp, size_t newlen) { +thread_tcache_enabled_ctl(tsd_t *tsd, const size_t *mib, + size_t miblen, void *oldp, size_t *oldlenp, void *newp, + size_t newlen) { int ret; bool oldval; oldval = tcache_enabled_get(tsd); if (newp != NULL) { if (newlen != sizeof(bool)) { ret = EINVAL; goto label_return; } tcache_enabled_set(tsd, *(bool *)newp); } READ(oldval, bool); ret = 0; label_return: return ret; } static int -thread_tcache_flush_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, - void *oldp, size_t *oldlenp, void *newp, size_t newlen) { +thread_tcache_flush_ctl(tsd_t *tsd, const size_t *mib, + size_t miblen, void *oldp, size_t *oldlenp, void *newp, + size_t newlen) { int ret; if (!tcache_available(tsd)) { ret = EFAULT; goto label_return; } READONLY(); WRITEONLY(); tcache_flush(tsd); ret = 0; label_return: return ret; } static int -thread_prof_name_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, - size_t *oldlenp, void *newp, size_t newlen) { +thread_prof_name_ctl(tsd_t *tsd, const size_t *mib, + size_t miblen, void *oldp, size_t *oldlenp, void *newp, + size_t newlen) { int ret; if (!config_prof) { return ENOENT; } READ_XOR_WRITE(); if (newp != NULL) { if (newlen != sizeof(const char *)) { ret = EINVAL; goto label_return; } if ((ret = prof_thread_name_set(tsd, *(const char **)newp)) != 0) { goto label_return; } } else { const char *oldname = prof_thread_name_get(tsd); READ(oldname, const char *); } ret = 0; label_return: return ret; } static int -thread_prof_active_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, - size_t *oldlenp, void *newp, size_t newlen) { +thread_prof_active_ctl(tsd_t *tsd, const size_t *mib, + size_t miblen, void *oldp, size_t *oldlenp, void *newp, + size_t newlen) { int ret; bool oldval; if (!config_prof) { return ENOENT; } oldval = prof_thread_active_get(tsd); if (newp != NULL) { if (newlen != sizeof(bool)) { ret = EINVAL; goto label_return; } if (prof_thread_active_set(tsd, *(bool *)newp)) { ret = EAGAIN; goto label_return; } } READ(oldval, bool); ret = 0; label_return: return ret; } /******************************************************************************/ static int -tcache_create_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, - size_t *oldlenp, void *newp, size_t newlen) { +tcache_create_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, + void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; unsigned tcache_ind; READONLY(); if (tcaches_create(tsd, &tcache_ind)) { ret = EFAULT; goto label_return; } READ(tcache_ind, unsigned); ret = 0; label_return: return ret; } static int -tcache_flush_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, - size_t *oldlenp, void *newp, size_t newlen) { +tcache_flush_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, + void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; unsigned tcache_ind; WRITEONLY(); tcache_ind = UINT_MAX; WRITE(tcache_ind, unsigned); if (tcache_ind == UINT_MAX) { ret = EFAULT; goto label_return; } tcaches_flush(tsd, tcache_ind); ret = 0; label_return: return ret; } static int -tcache_destroy_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, - size_t *oldlenp, void *newp, size_t newlen) { +tcache_destroy_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, + void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; unsigned tcache_ind; WRITEONLY(); tcache_ind = UINT_MAX; WRITE(tcache_ind, unsigned); if (tcache_ind == UINT_MAX) { ret = EFAULT; goto label_return; } tcaches_destroy(tsd, tcache_ind); ret = 0; label_return: return ret; } /******************************************************************************/ static int arena_i_initialized_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; tsdn_t *tsdn = tsd_tsdn(tsd); unsigned arena_ind; bool initialized; READONLY(); MIB_UNSIGNED(arena_ind, 1); malloc_mutex_lock(tsdn, &ctl_mtx); initialized = arenas_i(arena_ind)->initialized; malloc_mutex_unlock(tsdn, &ctl_mtx); READ(initialized, bool); ret = 0; label_return: return ret; } static void arena_i_decay(tsdn_t *tsdn, unsigned arena_ind, bool all) { malloc_mutex_lock(tsdn, &ctl_mtx); { unsigned narenas = ctl_arenas->narenas; /* * Access via index narenas is deprecated, and scheduled for * removal in 6.0.0. */ if (arena_ind == MALLCTL_ARENAS_ALL || arena_ind == narenas) { unsigned i; VARIABLE_ARRAY(arena_t *, tarenas, narenas); for (i = 0; i < narenas; i++) { tarenas[i] = arena_get(tsdn, i, false); } /* * No further need to hold ctl_mtx, since narenas and * tarenas contain everything needed below. */ malloc_mutex_unlock(tsdn, &ctl_mtx); for (i = 0; i < narenas; i++) { if (tarenas[i] != NULL) { arena_decay(tsdn, tarenas[i], false, all); } } } else { arena_t *tarena; assert(arena_ind < narenas); tarena = arena_get(tsdn, arena_ind, false); /* No further need to hold ctl_mtx. */ malloc_mutex_unlock(tsdn, &ctl_mtx); if (tarena != NULL) { arena_decay(tsdn, tarena, false, all); } } } } static int arena_i_decay_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; unsigned arena_ind; READONLY(); WRITEONLY(); MIB_UNSIGNED(arena_ind, 1); arena_i_decay(tsd_tsdn(tsd), arena_ind, false); ret = 0; label_return: return ret; } static int arena_i_purge_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; unsigned arena_ind; READONLY(); WRITEONLY(); MIB_UNSIGNED(arena_ind, 1); arena_i_decay(tsd_tsdn(tsd), arena_ind, true); ret = 0; label_return: return ret; } static int arena_i_reset_destroy_helper(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen, unsigned *arena_ind, arena_t **arena) { int ret; READONLY(); WRITEONLY(); MIB_UNSIGNED(*arena_ind, 1); *arena = arena_get(tsd_tsdn(tsd), *arena_ind, false); if (*arena == NULL || arena_is_auto(*arena)) { ret = EFAULT; goto label_return; } ret = 0; label_return: return ret; } static void arena_reset_prepare_background_thread(tsd_t *tsd, unsigned arena_ind) { /* Temporarily disable the background thread during arena reset. */ if (have_background_thread) { malloc_mutex_lock(tsd_tsdn(tsd), &background_thread_lock); if (background_thread_enabled()) { - unsigned ind = arena_ind % ncpus; background_thread_info_t *info = - &background_thread_info[ind]; + background_thread_info_get(arena_ind); assert(info->state == background_thread_started); malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx); info->state = background_thread_paused; malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx); } } } static void arena_reset_finish_background_thread(tsd_t *tsd, unsigned arena_ind) { if (have_background_thread) { if (background_thread_enabled()) { - unsigned ind = arena_ind % ncpus; background_thread_info_t *info = - &background_thread_info[ind]; + background_thread_info_get(arena_ind); assert(info->state == background_thread_paused); malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx); info->state = background_thread_started; malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx); } malloc_mutex_unlock(tsd_tsdn(tsd), &background_thread_lock); } } static int arena_i_reset_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; unsigned arena_ind; arena_t *arena; ret = arena_i_reset_destroy_helper(tsd, mib, miblen, oldp, oldlenp, newp, newlen, &arena_ind, &arena); if (ret != 0) { return ret; } arena_reset_prepare_background_thread(tsd, arena_ind); arena_reset(tsd, arena); arena_reset_finish_background_thread(tsd, arena_ind); return ret; } static int arena_i_destroy_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; unsigned arena_ind; arena_t *arena; ctl_arena_t *ctl_darena, *ctl_arena; ret = arena_i_reset_destroy_helper(tsd, mib, miblen, oldp, oldlenp, newp, newlen, &arena_ind, &arena); if (ret != 0) { goto label_return; } if (arena_nthreads_get(arena, false) != 0 || arena_nthreads_get(arena, true) != 0) { ret = EFAULT; goto label_return; } arena_reset_prepare_background_thread(tsd, arena_ind); /* Merge stats after resetting and purging arena. */ arena_reset(tsd, arena); arena_decay(tsd_tsdn(tsd), arena, false, true); ctl_darena = arenas_i(MALLCTL_ARENAS_DESTROYED); ctl_darena->initialized = true; ctl_arena_refresh(tsd_tsdn(tsd), arena, ctl_darena, arena_ind, true); /* Destroy arena. */ arena_destroy(tsd, arena); ctl_arena = arenas_i(arena_ind); ctl_arena->initialized = false; /* Record arena index for later recycling via arenas.create. */ ql_elm_new(ctl_arena, destroyed_link); ql_tail_insert(&ctl_arenas->destroyed, ctl_arena, destroyed_link); arena_reset_finish_background_thread(tsd, arena_ind); assert(ret == 0); label_return: return ret; } static int arena_i_dss_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; const char *dss = NULL; unsigned arena_ind; dss_prec_t dss_prec_old = dss_prec_limit; dss_prec_t dss_prec = dss_prec_limit; malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx); WRITE(dss, const char *); MIB_UNSIGNED(arena_ind, 1); if (dss != NULL) { int i; bool match = false; for (i = 0; i < dss_prec_limit; i++) { if (strcmp(dss_prec_names[i], dss) == 0) { dss_prec = i; match = true; break; } } if (!match) { ret = EINVAL; goto label_return; } } /* * Access via index narenas is deprecated, and scheduled for removal in * 6.0.0. */ if (arena_ind == MALLCTL_ARENAS_ALL || arena_ind == ctl_arenas->narenas) { if (dss_prec != dss_prec_limit && extent_dss_prec_set(dss_prec)) { ret = EFAULT; goto label_return; } dss_prec_old = extent_dss_prec_get(); } else { arena_t *arena = arena_get(tsd_tsdn(tsd), arena_ind, false); if (arena == NULL || (dss_prec != dss_prec_limit && arena_dss_prec_set(arena, dss_prec))) { ret = EFAULT; goto label_return; } dss_prec_old = arena_dss_prec_get(arena); } dss = dss_prec_names[dss_prec_old]; READ(dss, const char *); ret = 0; label_return: malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx); return ret; } static int arena_i_decay_ms_ctl_impl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen, bool dirty) { int ret; unsigned arena_ind; arena_t *arena; MIB_UNSIGNED(arena_ind, 1); arena = arena_get(tsd_tsdn(tsd), arena_ind, false); if (arena == NULL) { ret = EFAULT; goto label_return; } if (oldp != NULL && oldlenp != NULL) { size_t oldval = dirty ? arena_dirty_decay_ms_get(arena) : arena_muzzy_decay_ms_get(arena); READ(oldval, ssize_t); } if (newp != NULL) { if (newlen != sizeof(ssize_t)) { ret = EINVAL; goto label_return; } + if (arena_is_huge(arena_ind) && *(ssize_t *)newp > 0) { + /* + * By default the huge arena purges eagerly. If it is + * set to non-zero decay time afterwards, background + * thread might be needed. + */ + if (background_thread_create(tsd, arena_ind)) { + ret = EFAULT; + goto label_return; + } + } if (dirty ? arena_dirty_decay_ms_set(tsd_tsdn(tsd), arena, *(ssize_t *)newp) : arena_muzzy_decay_ms_set(tsd_tsdn(tsd), arena, *(ssize_t *)newp)) { ret = EFAULT; goto label_return; } } ret = 0; label_return: return ret; } static int arena_i_dirty_decay_ms_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen) { return arena_i_decay_ms_ctl_impl(tsd, mib, miblen, oldp, oldlenp, newp, newlen, true); } static int arena_i_muzzy_decay_ms_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen) { return arena_i_decay_ms_ctl_impl(tsd, mib, miblen, oldp, oldlenp, newp, newlen, false); } static int arena_i_extent_hooks_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; unsigned arena_ind; arena_t *arena; malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx); MIB_UNSIGNED(arena_ind, 1); if (arena_ind < narenas_total_get()) { extent_hooks_t *old_extent_hooks; arena = arena_get(tsd_tsdn(tsd), arena_ind, false); if (arena == NULL) { if (arena_ind >= narenas_auto) { ret = EFAULT; goto label_return; } old_extent_hooks = (extent_hooks_t *)&extent_hooks_default; READ(old_extent_hooks, extent_hooks_t *); if (newp != NULL) { /* Initialize a new arena as a side effect. */ extent_hooks_t *new_extent_hooks JEMALLOC_CC_SILENCE_INIT(NULL); WRITE(new_extent_hooks, extent_hooks_t *); arena = arena_init(tsd_tsdn(tsd), arena_ind, new_extent_hooks); if (arena == NULL) { ret = EFAULT; goto label_return; } } } else { if (newp != NULL) { extent_hooks_t *new_extent_hooks JEMALLOC_CC_SILENCE_INIT(NULL); WRITE(new_extent_hooks, extent_hooks_t *); old_extent_hooks = extent_hooks_set(tsd, arena, new_extent_hooks); READ(old_extent_hooks, extent_hooks_t *); } else { old_extent_hooks = extent_hooks_get(arena); READ(old_extent_hooks, extent_hooks_t *); } } } else { ret = EFAULT; goto label_return; } ret = 0; label_return: malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx); return ret; } static int -arena_i_retain_grow_limit_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, - void *oldp, size_t *oldlenp, void *newp, size_t newlen) { +arena_i_retain_grow_limit_ctl(tsd_t *tsd, const size_t *mib, + size_t miblen, void *oldp, size_t *oldlenp, void *newp, + size_t newlen) { int ret; unsigned arena_ind; arena_t *arena; if (!opt_retain) { /* Only relevant when retain is enabled. */ return ENOENT; } malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx); MIB_UNSIGNED(arena_ind, 1); if (arena_ind < narenas_total_get() && (arena = arena_get(tsd_tsdn(tsd), arena_ind, false)) != NULL) { size_t old_limit, new_limit; if (newp != NULL) { WRITE(new_limit, size_t); } bool err = arena_retain_grow_limit_get_set(tsd, arena, &old_limit, newp != NULL ? &new_limit : NULL); if (!err) { READ(old_limit, size_t); ret = 0; } else { ret = EFAULT; } } else { ret = EFAULT; } label_return: malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx); return ret; } static const ctl_named_node_t * -arena_i_index(tsdn_t *tsdn, const size_t *mib, size_t miblen, size_t i) { +arena_i_index(tsdn_t *tsdn, const size_t *mib, size_t miblen, + size_t i) { const ctl_named_node_t *ret; malloc_mutex_lock(tsdn, &ctl_mtx); switch (i) { case MALLCTL_ARENAS_ALL: case MALLCTL_ARENAS_DESTROYED: break; default: if (i > ctl_arenas->narenas) { ret = NULL; goto label_return; } break; } ret = super_arena_i_node; label_return: malloc_mutex_unlock(tsdn, &ctl_mtx); return ret; } /******************************************************************************/ static int -arenas_narenas_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, - size_t *oldlenp, void *newp, size_t newlen) { +arenas_narenas_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, + void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; unsigned narenas; malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx); READONLY(); if (*oldlenp != sizeof(unsigned)) { ret = EINVAL; goto label_return; } narenas = ctl_arenas->narenas; READ(narenas, unsigned); ret = 0; label_return: malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx); return ret; } static int -arenas_decay_ms_ctl_impl(tsd_t *tsd, const size_t *mib, size_t miblen, - void *oldp, size_t *oldlenp, void *newp, size_t newlen, bool dirty) { +arenas_decay_ms_ctl_impl(tsd_t *tsd, const size_t *mib, + size_t miblen, void *oldp, size_t *oldlenp, void *newp, + size_t newlen, bool dirty) { int ret; if (oldp != NULL && oldlenp != NULL) { size_t oldval = (dirty ? arena_dirty_decay_ms_default_get() : arena_muzzy_decay_ms_default_get()); READ(oldval, ssize_t); } if (newp != NULL) { if (newlen != sizeof(ssize_t)) { ret = EINVAL; goto label_return; } if (dirty ? arena_dirty_decay_ms_default_set(*(ssize_t *)newp) : arena_muzzy_decay_ms_default_set(*(ssize_t *)newp)) { ret = EFAULT; goto label_return; } } ret = 0; label_return: return ret; } static int arenas_dirty_decay_ms_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen) { return arenas_decay_ms_ctl_impl(tsd, mib, miblen, oldp, oldlenp, newp, newlen, true); } static int arenas_muzzy_decay_ms_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen) { return arenas_decay_ms_ctl_impl(tsd, mib, miblen, oldp, oldlenp, newp, newlen, false); } CTL_RO_NL_GEN(arenas_quantum, QUANTUM, size_t) CTL_RO_NL_GEN(arenas_page, PAGE, size_t) CTL_RO_NL_GEN(arenas_tcache_max, tcache_maxclass, size_t) -CTL_RO_NL_GEN(arenas_nbins, NBINS, unsigned) +CTL_RO_NL_GEN(arenas_nbins, SC_NBINS, unsigned) CTL_RO_NL_GEN(arenas_nhbins, nhbins, unsigned) CTL_RO_NL_GEN(arenas_bin_i_size, bin_infos[mib[2]].reg_size, size_t) CTL_RO_NL_GEN(arenas_bin_i_nregs, bin_infos[mib[2]].nregs, uint32_t) CTL_RO_NL_GEN(arenas_bin_i_slab_size, bin_infos[mib[2]].slab_size, size_t) +CTL_RO_NL_GEN(arenas_bin_i_nshards, bin_infos[mib[2]].n_shards, uint32_t) static const ctl_named_node_t * -arenas_bin_i_index(tsdn_t *tsdn, const size_t *mib, size_t miblen, size_t i) { - if (i > NBINS) { +arenas_bin_i_index(tsdn_t *tsdn, const size_t *mib, + size_t miblen, size_t i) { + if (i > SC_NBINS) { return NULL; } return super_arenas_bin_i_node; } -CTL_RO_NL_GEN(arenas_nlextents, NSIZES - NBINS, unsigned) -CTL_RO_NL_GEN(arenas_lextent_i_size, sz_index2size(NBINS+(szind_t)mib[2]), +CTL_RO_NL_GEN(arenas_nlextents, SC_NSIZES - SC_NBINS, unsigned) +CTL_RO_NL_GEN(arenas_lextent_i_size, sz_index2size(SC_NBINS+(szind_t)mib[2]), size_t) static const ctl_named_node_t * -arenas_lextent_i_index(tsdn_t *tsdn, const size_t *mib, size_t miblen, - size_t i) { - if (i > NSIZES - NBINS) { +arenas_lextent_i_index(tsdn_t *tsdn, const size_t *mib, + size_t miblen, size_t i) { + if (i > SC_NSIZES - SC_NBINS) { return NULL; } return super_arenas_lextent_i_node; } static int -arenas_create_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, - size_t *oldlenp, void *newp, size_t newlen) { +arenas_create_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, + void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; extent_hooks_t *extent_hooks; unsigned arena_ind; malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx); extent_hooks = (extent_hooks_t *)&extent_hooks_default; WRITE(extent_hooks, extent_hooks_t *); if ((arena_ind = ctl_arena_init(tsd, extent_hooks)) == UINT_MAX) { ret = EAGAIN; goto label_return; } READ(arena_ind, unsigned); ret = 0; label_return: malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx); return ret; } static int -arenas_lookup_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, - size_t *oldlenp, void *newp, size_t newlen) { +arenas_lookup_ctl(tsd_t *tsd, const size_t *mib, + size_t miblen, void *oldp, size_t *oldlenp, void *newp, + size_t newlen) { int ret; unsigned arena_ind; void *ptr; extent_t *extent; arena_t *arena; ptr = NULL; ret = EINVAL; malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx); WRITE(ptr, void *); extent = iealloc(tsd_tsdn(tsd), ptr); if (extent == NULL) goto label_return; arena = extent_arena_get(extent); if (arena == NULL) goto label_return; arena_ind = arena_ind_get(arena); READ(arena_ind, unsigned); ret = 0; label_return: malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx); return ret; } /******************************************************************************/ static int -prof_thread_active_init_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, - void *oldp, size_t *oldlenp, void *newp, size_t newlen) { +prof_thread_active_init_ctl(tsd_t *tsd, const size_t *mib, + size_t miblen, void *oldp, size_t *oldlenp, void *newp, + size_t newlen) { int ret; bool oldval; if (!config_prof) { return ENOENT; } if (newp != NULL) { if (newlen != sizeof(bool)) { ret = EINVAL; goto label_return; } oldval = prof_thread_active_init_set(tsd_tsdn(tsd), *(bool *)newp); } else { oldval = prof_thread_active_init_get(tsd_tsdn(tsd)); } READ(oldval, bool); ret = 0; label_return: return ret; } static int -prof_active_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, - size_t *oldlenp, void *newp, size_t newlen) { +prof_active_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, + void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; bool oldval; if (!config_prof) { return ENOENT; } if (newp != NULL) { if (newlen != sizeof(bool)) { ret = EINVAL; goto label_return; } oldval = prof_active_set(tsd_tsdn(tsd), *(bool *)newp); } else { oldval = prof_active_get(tsd_tsdn(tsd)); } READ(oldval, bool); ret = 0; label_return: return ret; } static int -prof_dump_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, - size_t *oldlenp, void *newp, size_t newlen) { +prof_dump_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, + void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; const char *filename = NULL; if (!config_prof) { return ENOENT; } WRITEONLY(); WRITE(filename, const char *); if (prof_mdump(tsd, filename)) { ret = EFAULT; goto label_return; } ret = 0; label_return: return ret; } static int -prof_gdump_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, - size_t *oldlenp, void *newp, size_t newlen) { +prof_gdump_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, + void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; bool oldval; if (!config_prof) { return ENOENT; } if (newp != NULL) { if (newlen != sizeof(bool)) { ret = EINVAL; goto label_return; } oldval = prof_gdump_set(tsd_tsdn(tsd), *(bool *)newp); } else { oldval = prof_gdump_get(tsd_tsdn(tsd)); } READ(oldval, bool); ret = 0; label_return: return ret; } static int -prof_reset_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, - size_t *oldlenp, void *newp, size_t newlen) { +prof_reset_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, + void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; size_t lg_sample = lg_prof_sample; if (!config_prof) { return ENOENT; } WRITEONLY(); WRITE(lg_sample, size_t); if (lg_sample >= (sizeof(uint64_t) << 3)) { lg_sample = (sizeof(uint64_t) << 3) - 1; } prof_reset(tsd, lg_sample); ret = 0; label_return: return ret; } CTL_RO_NL_CGEN(config_prof, prof_interval, prof_interval, uint64_t) CTL_RO_NL_CGEN(config_prof, lg_prof_sample, lg_prof_sample, size_t) +static int +prof_log_start_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, + size_t *oldlenp, void *newp, size_t newlen) { + int ret; + + const char *filename = NULL; + + if (!config_prof) { + return ENOENT; + } + + WRITEONLY(); + WRITE(filename, const char *); + + if (prof_log_start(tsd_tsdn(tsd), filename)) { + ret = EFAULT; + goto label_return; + } + + ret = 0; +label_return: + return ret; +} + +static int +prof_log_stop_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp, + size_t *oldlenp, void *newp, size_t newlen) { + if (!config_prof) { + return ENOENT; + } + + if (prof_log_stop(tsd_tsdn(tsd))) { + return EFAULT; + } + + return 0; +} + /******************************************************************************/ CTL_RO_CGEN(config_stats, stats_allocated, ctl_stats->allocated, size_t) CTL_RO_CGEN(config_stats, stats_active, ctl_stats->active, size_t) CTL_RO_CGEN(config_stats, stats_metadata, ctl_stats->metadata, size_t) CTL_RO_CGEN(config_stats, stats_metadata_thp, ctl_stats->metadata_thp, size_t) CTL_RO_CGEN(config_stats, stats_resident, ctl_stats->resident, size_t) CTL_RO_CGEN(config_stats, stats_mapped, ctl_stats->mapped, size_t) CTL_RO_CGEN(config_stats, stats_retained, ctl_stats->retained, size_t) CTL_RO_CGEN(config_stats, stats_background_thread_num_threads, ctl_stats->background_thread.num_threads, size_t) CTL_RO_CGEN(config_stats, stats_background_thread_num_runs, ctl_stats->background_thread.num_runs, uint64_t) CTL_RO_CGEN(config_stats, stats_background_thread_run_interval, nstime_ns(&ctl_stats->background_thread.run_interval), uint64_t) CTL_RO_GEN(stats_arenas_i_dss, arenas_i(mib[2])->dss, const char *) CTL_RO_GEN(stats_arenas_i_dirty_decay_ms, arenas_i(mib[2])->dirty_decay_ms, ssize_t) CTL_RO_GEN(stats_arenas_i_muzzy_decay_ms, arenas_i(mib[2])->muzzy_decay_ms, ssize_t) CTL_RO_GEN(stats_arenas_i_nthreads, arenas_i(mib[2])->nthreads, unsigned) CTL_RO_GEN(stats_arenas_i_uptime, nstime_ns(&arenas_i(mib[2])->astats->astats.uptime), uint64_t) CTL_RO_GEN(stats_arenas_i_pactive, arenas_i(mib[2])->pactive, size_t) CTL_RO_GEN(stats_arenas_i_pdirty, arenas_i(mib[2])->pdirty, size_t) CTL_RO_GEN(stats_arenas_i_pmuzzy, arenas_i(mib[2])->pmuzzy, size_t) CTL_RO_CGEN(config_stats, stats_arenas_i_mapped, atomic_load_zu(&arenas_i(mib[2])->astats->astats.mapped, ATOMIC_RELAXED), size_t) CTL_RO_CGEN(config_stats, stats_arenas_i_retained, atomic_load_zu(&arenas_i(mib[2])->astats->astats.retained, ATOMIC_RELAXED), size_t) +CTL_RO_CGEN(config_stats, stats_arenas_i_extent_avail, + atomic_load_zu(&arenas_i(mib[2])->astats->astats.extent_avail, + ATOMIC_RELAXED), + size_t) CTL_RO_CGEN(config_stats, stats_arenas_i_dirty_npurge, ctl_arena_stats_read_u64( &arenas_i(mib[2])->astats->astats.decay_dirty.npurge), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_dirty_nmadvise, ctl_arena_stats_read_u64( &arenas_i(mib[2])->astats->astats.decay_dirty.nmadvise), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_dirty_purged, ctl_arena_stats_read_u64( &arenas_i(mib[2])->astats->astats.decay_dirty.purged), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_muzzy_npurge, ctl_arena_stats_read_u64( &arenas_i(mib[2])->astats->astats.decay_muzzy.npurge), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_muzzy_nmadvise, ctl_arena_stats_read_u64( &arenas_i(mib[2])->astats->astats.decay_muzzy.nmadvise), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_muzzy_purged, ctl_arena_stats_read_u64( &arenas_i(mib[2])->astats->astats.decay_muzzy.purged), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_base, atomic_load_zu(&arenas_i(mib[2])->astats->astats.base, ATOMIC_RELAXED), size_t) CTL_RO_CGEN(config_stats, stats_arenas_i_internal, atomic_load_zu(&arenas_i(mib[2])->astats->astats.internal, ATOMIC_RELAXED), size_t) CTL_RO_CGEN(config_stats, stats_arenas_i_metadata_thp, atomic_load_zu(&arenas_i(mib[2])->astats->astats.metadata_thp, ATOMIC_RELAXED), size_t) CTL_RO_CGEN(config_stats, stats_arenas_i_tcache_bytes, atomic_load_zu(&arenas_i(mib[2])->astats->astats.tcache_bytes, ATOMIC_RELAXED), size_t) CTL_RO_CGEN(config_stats, stats_arenas_i_resident, atomic_load_zu(&arenas_i(mib[2])->astats->astats.resident, ATOMIC_RELAXED), size_t) +CTL_RO_CGEN(config_stats, stats_arenas_i_abandoned_vm, + atomic_load_zu(&arenas_i(mib[2])->astats->astats.abandoned_vm, + ATOMIC_RELAXED), size_t) CTL_RO_CGEN(config_stats, stats_arenas_i_small_allocated, arenas_i(mib[2])->astats->allocated_small, size_t) CTL_RO_CGEN(config_stats, stats_arenas_i_small_nmalloc, arenas_i(mib[2])->astats->nmalloc_small, uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_small_ndalloc, arenas_i(mib[2])->astats->ndalloc_small, uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_small_nrequests, arenas_i(mib[2])->astats->nrequests_small, uint64_t) +CTL_RO_CGEN(config_stats, stats_arenas_i_small_nfills, + arenas_i(mib[2])->astats->nfills_small, uint64_t) +CTL_RO_CGEN(config_stats, stats_arenas_i_small_nflushes, + arenas_i(mib[2])->astats->nflushes_small, uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_large_allocated, atomic_load_zu(&arenas_i(mib[2])->astats->astats.allocated_large, ATOMIC_RELAXED), size_t) CTL_RO_CGEN(config_stats, stats_arenas_i_large_nmalloc, ctl_arena_stats_read_u64( &arenas_i(mib[2])->astats->astats.nmalloc_large), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_large_ndalloc, ctl_arena_stats_read_u64( &arenas_i(mib[2])->astats->astats.ndalloc_large), uint64_t) +CTL_RO_CGEN(config_stats, stats_arenas_i_large_nrequests, + ctl_arena_stats_read_u64( + &arenas_i(mib[2])->astats->astats.nrequests_large), uint64_t) /* - * Note: "nmalloc" here instead of "nrequests" in the read. This is intentional. + * Note: "nmalloc_large" here instead of "nfills" in the read. This is + * intentional (large has no batch fill). */ -CTL_RO_CGEN(config_stats, stats_arenas_i_large_nrequests, +CTL_RO_CGEN(config_stats, stats_arenas_i_large_nfills, ctl_arena_stats_read_u64( - &arenas_i(mib[2])->astats->astats.nmalloc_large), uint64_t) /* Intentional. */ + &arenas_i(mib[2])->astats->astats.nmalloc_large), uint64_t) +CTL_RO_CGEN(config_stats, stats_arenas_i_large_nflushes, + ctl_arena_stats_read_u64( + &arenas_i(mib[2])->astats->astats.nflushes_large), uint64_t) /* Lock profiling related APIs below. */ #define RO_MUTEX_CTL_GEN(n, l) \ CTL_RO_CGEN(config_stats, stats_##n##_num_ops, \ l.n_lock_ops, uint64_t) \ CTL_RO_CGEN(config_stats, stats_##n##_num_wait, \ l.n_wait_times, uint64_t) \ CTL_RO_CGEN(config_stats, stats_##n##_num_spin_acq, \ l.n_spin_acquired, uint64_t) \ CTL_RO_CGEN(config_stats, stats_##n##_num_owner_switch, \ l.n_owner_switches, uint64_t) \ CTL_RO_CGEN(config_stats, stats_##n##_total_wait_time, \ nstime_ns(&l.tot_wait_time), uint64_t) \ CTL_RO_CGEN(config_stats, stats_##n##_max_wait_time, \ nstime_ns(&l.max_wait_time), uint64_t) \ CTL_RO_CGEN(config_stats, stats_##n##_max_num_thds, \ l.max_n_thds, uint32_t) /* Global mutexes. */ #define OP(mtx) \ RO_MUTEX_CTL_GEN(mutexes_##mtx, \ ctl_stats->mutex_prof_data[global_prof_mutex_##mtx]) MUTEX_PROF_GLOBAL_MUTEXES #undef OP /* Per arena mutexes */ #define OP(mtx) RO_MUTEX_CTL_GEN(arenas_i_mutexes_##mtx, \ arenas_i(mib[2])->astats->astats.mutex_prof_data[arena_prof_mutex_##mtx]) MUTEX_PROF_ARENA_MUTEXES #undef OP /* tcache bin mutex */ RO_MUTEX_CTL_GEN(arenas_i_bins_j_mutex, arenas_i(mib[2])->astats->bstats[mib[4]].mutex_data) #undef RO_MUTEX_CTL_GEN /* Resets all mutex stats, including global, arena and bin mutexes. */ static int -stats_mutexes_reset_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, - void *oldp, size_t *oldlenp, void *newp, size_t newlen) { +stats_mutexes_reset_ctl(tsd_t *tsd, const size_t *mib, + size_t miblen, void *oldp, size_t *oldlenp, + void *newp, size_t newlen) { if (!config_stats) { return ENOENT; } tsdn_t *tsdn = tsd_tsdn(tsd); #define MUTEX_PROF_RESET(mtx) \ malloc_mutex_lock(tsdn, &mtx); \ malloc_mutex_prof_data_reset(tsdn, &mtx); \ malloc_mutex_unlock(tsdn, &mtx); /* Global mutexes: ctl and prof. */ MUTEX_PROF_RESET(ctl_mtx); if (have_background_thread) { MUTEX_PROF_RESET(background_thread_lock); } if (config_prof && opt_prof) { MUTEX_PROF_RESET(bt2gctx_mtx); } /* Per arena mutexes. */ unsigned n = narenas_total_get(); for (unsigned i = 0; i < n; i++) { arena_t *arena = arena_get(tsdn, i, false); if (!arena) { continue; } MUTEX_PROF_RESET(arena->large_mtx); MUTEX_PROF_RESET(arena->extent_avail_mtx); MUTEX_PROF_RESET(arena->extents_dirty.mtx); MUTEX_PROF_RESET(arena->extents_muzzy.mtx); MUTEX_PROF_RESET(arena->extents_retained.mtx); MUTEX_PROF_RESET(arena->decay_dirty.mtx); MUTEX_PROF_RESET(arena->decay_muzzy.mtx); MUTEX_PROF_RESET(arena->tcache_ql_mtx); MUTEX_PROF_RESET(arena->base->mtx); - for (szind_t i = 0; i < NBINS; i++) { - bin_t *bin = &arena->bins[i]; - MUTEX_PROF_RESET(bin->lock); + for (szind_t i = 0; i < SC_NBINS; i++) { + for (unsigned j = 0; j < bin_infos[i].n_shards; j++) { + bin_t *bin = &arena->bins[i].bin_shards[j]; + MUTEX_PROF_RESET(bin->lock); + } } } #undef MUTEX_PROF_RESET return 0; } CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_nmalloc, arenas_i(mib[2])->astats->bstats[mib[4]].nmalloc, uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_ndalloc, arenas_i(mib[2])->astats->bstats[mib[4]].ndalloc, uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_nrequests, arenas_i(mib[2])->astats->bstats[mib[4]].nrequests, uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_curregs, arenas_i(mib[2])->astats->bstats[mib[4]].curregs, size_t) CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_nfills, arenas_i(mib[2])->astats->bstats[mib[4]].nfills, uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_nflushes, arenas_i(mib[2])->astats->bstats[mib[4]].nflushes, uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_nslabs, arenas_i(mib[2])->astats->bstats[mib[4]].nslabs, uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_nreslabs, arenas_i(mib[2])->astats->bstats[mib[4]].reslabs, uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_curslabs, arenas_i(mib[2])->astats->bstats[mib[4]].curslabs, size_t) +CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_nonfull_slabs, + arenas_i(mib[2])->astats->bstats[mib[4]].nonfull_slabs, size_t) static const ctl_named_node_t * -stats_arenas_i_bins_j_index(tsdn_t *tsdn, const size_t *mib, size_t miblen, - size_t j) { - if (j > NBINS) { +stats_arenas_i_bins_j_index(tsdn_t *tsdn, const size_t *mib, + size_t miblen, size_t j) { + if (j > SC_NBINS) { return NULL; } return super_stats_arenas_i_bins_j_node; } CTL_RO_CGEN(config_stats, stats_arenas_i_lextents_j_nmalloc, ctl_arena_stats_read_u64( &arenas_i(mib[2])->astats->lstats[mib[4]].nmalloc), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_lextents_j_ndalloc, ctl_arena_stats_read_u64( &arenas_i(mib[2])->astats->lstats[mib[4]].ndalloc), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_lextents_j_nrequests, ctl_arena_stats_read_u64( &arenas_i(mib[2])->astats->lstats[mib[4]].nrequests), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_lextents_j_curlextents, arenas_i(mib[2])->astats->lstats[mib[4]].curlextents, size_t) static const ctl_named_node_t * -stats_arenas_i_lextents_j_index(tsdn_t *tsdn, const size_t *mib, size_t miblen, - size_t j) { - if (j > NSIZES - NBINS) { +stats_arenas_i_lextents_j_index(tsdn_t *tsdn, const size_t *mib, + size_t miblen, size_t j) { + if (j > SC_NSIZES - SC_NBINS) { return NULL; } return super_stats_arenas_i_lextents_j_node; } +CTL_RO_CGEN(config_stats, stats_arenas_i_extents_j_ndirty, + atomic_load_zu( + &arenas_i(mib[2])->astats->estats[mib[4]].ndirty, + ATOMIC_RELAXED), size_t); +CTL_RO_CGEN(config_stats, stats_arenas_i_extents_j_nmuzzy, + atomic_load_zu( + &arenas_i(mib[2])->astats->estats[mib[4]].nmuzzy, + ATOMIC_RELAXED), size_t); +CTL_RO_CGEN(config_stats, stats_arenas_i_extents_j_nretained, + atomic_load_zu( + &arenas_i(mib[2])->astats->estats[mib[4]].nretained, + ATOMIC_RELAXED), size_t); +CTL_RO_CGEN(config_stats, stats_arenas_i_extents_j_dirty_bytes, + atomic_load_zu( + &arenas_i(mib[2])->astats->estats[mib[4]].dirty_bytes, + ATOMIC_RELAXED), size_t); +CTL_RO_CGEN(config_stats, stats_arenas_i_extents_j_muzzy_bytes, + atomic_load_zu( + &arenas_i(mib[2])->astats->estats[mib[4]].muzzy_bytes, + ATOMIC_RELAXED), size_t); +CTL_RO_CGEN(config_stats, stats_arenas_i_extents_j_retained_bytes, + atomic_load_zu( + &arenas_i(mib[2])->astats->estats[mib[4]].retained_bytes, + ATOMIC_RELAXED), size_t); + static const ctl_named_node_t * -stats_arenas_i_index(tsdn_t *tsdn, const size_t *mib, size_t miblen, size_t i) { +stats_arenas_i_extents_j_index(tsdn_t *tsdn, const size_t *mib, + size_t miblen, size_t j) { + if (j >= SC_NPSIZES) { + return NULL; + } + return super_stats_arenas_i_extents_j_node; +} + +static bool +ctl_arenas_i_verify(size_t i) { + size_t a = arenas_i2a_impl(i, true, true); + if (a == UINT_MAX || !ctl_arenas->arenas[a]->initialized) { + return true; + } + + return false; +} + +static const ctl_named_node_t * +stats_arenas_i_index(tsdn_t *tsdn, const size_t *mib, + size_t miblen, size_t i) { const ctl_named_node_t *ret; - size_t a; malloc_mutex_lock(tsdn, &ctl_mtx); - a = arenas_i2a_impl(i, true, true); - if (a == UINT_MAX || !ctl_arenas->arenas[a]->initialized) { + if (ctl_arenas_i_verify(i)) { ret = NULL; goto label_return; } ret = super_stats_arenas_i_node; label_return: malloc_mutex_unlock(tsdn, &ctl_mtx); + return ret; +} + +static int +experimental_hooks_install_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, + void *oldp, size_t *oldlenp, void *newp, size_t newlen) { + int ret; + if (oldp == NULL || oldlenp == NULL|| newp == NULL) { + ret = EINVAL; + goto label_return; + } + /* + * Note: this is a *private* struct. This is an experimental interface; + * forcing the user to know the jemalloc internals well enough to + * extract the ABI hopefully ensures nobody gets too comfortable with + * this API, which can change at a moment's notice. + */ + hooks_t hooks; + WRITE(hooks, hooks_t); + void *handle = hook_install(tsd_tsdn(tsd), &hooks); + if (handle == NULL) { + ret = EAGAIN; + goto label_return; + } + READ(handle, void *); + + ret = 0; +label_return: + return ret; +} + +static int +experimental_hooks_remove_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, + void *oldp, size_t *oldlenp, void *newp, size_t newlen) { + int ret; + WRITEONLY(); + void *handle = NULL; + WRITE(handle, void *); + if (handle == NULL) { + ret = EINVAL; + goto label_return; + } + hook_remove(tsd_tsdn(tsd), handle); + ret = 0; +label_return: + return ret; +} + +/* + * Output six memory utilization entries for an input pointer, the first one of + * type (void *) and the remaining five of type size_t, describing the following + * (in the same order): + * + * (a) memory address of the extent a potential reallocation would go into, + * == the five fields below describe about the extent the pointer resides in == + * (b) number of free regions in the extent, + * (c) number of regions in the extent, + * (d) size of the extent in terms of bytes, + * (e) total number of free regions in the bin the extent belongs to, and + * (f) total number of regions in the bin the extent belongs to. + * + * Note that "(e)" and "(f)" are only available when stats are enabled; + * otherwise their values are undefined. + * + * This API is mainly intended for small class allocations, where extents are + * used as slab. + * + * In case of large class allocations, "(a)" will be NULL, and "(e)" and "(f)" + * will be zero (if stats are enabled; otherwise undefined). The other three + * fields will be properly set though the values are trivial: "(b)" will be 0, + * "(c)" will be 1, and "(d)" will be the usable size. + * + * The input pointer and size are respectively passed in by newp and newlen, + * and the output fields and size are respectively oldp and *oldlenp. + * + * It can be beneficial to define the following macros to make it easier to + * access the output: + * + * #define SLABCUR_READ(out) (*(void **)out) + * #define COUNTS(out) ((size_t *)((void **)out + 1)) + * #define NFREE_READ(out) COUNTS(out)[0] + * #define NREGS_READ(out) COUNTS(out)[1] + * #define SIZE_READ(out) COUNTS(out)[2] + * #define BIN_NFREE_READ(out) COUNTS(out)[3] + * #define BIN_NREGS_READ(out) COUNTS(out)[4] + * + * and then write e.g. NFREE_READ(oldp) to fetch the output. See the unit test + * test_query in test/unit/extent_util.c for an example. + * + * For a typical defragmentation workflow making use of this API for + * understanding the fragmentation level, please refer to the comment for + * experimental_utilization_batch_query_ctl. + * + * It's up to the application how to determine the significance of + * fragmentation relying on the outputs returned. Possible choices are: + * + * (a) if extent utilization ratio is below certain threshold, + * (b) if extent memory consumption is above certain threshold, + * (c) if extent utilization ratio is significantly below bin utilization ratio, + * (d) if input pointer deviates a lot from potential reallocation address, or + * (e) some selection/combination of the above. + * + * The caller needs to make sure that the input/output arguments are valid, + * in particular, that the size of the output is correct, i.e.: + * + * *oldlenp = sizeof(void *) + sizeof(size_t) * 5 + * + * Otherwise, the function immediately returns EINVAL without touching anything. + * + * In the rare case where there's no associated extent found for the input + * pointer, the function zeros out all output fields and return. Please refer + * to the comment for experimental_utilization_batch_query_ctl to understand the + * motivation from C++. + */ +static int +experimental_utilization_query_ctl(tsd_t *tsd, const size_t *mib, + size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen) { + int ret; + + assert(sizeof(extent_util_stats_verbose_t) + == sizeof(void *) + sizeof(size_t) * 5); + + if (oldp == NULL || oldlenp == NULL + || *oldlenp != sizeof(extent_util_stats_verbose_t) + || newp == NULL) { + ret = EINVAL; + goto label_return; + } + + void *ptr = NULL; + WRITE(ptr, void *); + extent_util_stats_verbose_t *util_stats + = (extent_util_stats_verbose_t *)oldp; + extent_util_stats_verbose_get(tsd_tsdn(tsd), ptr, + &util_stats->nfree, &util_stats->nregs, &util_stats->size, + &util_stats->bin_nfree, &util_stats->bin_nregs, + &util_stats->slabcur_addr); + ret = 0; + +label_return: + return ret; +} + +/* + * Given an input array of pointers, output three memory utilization entries of + * type size_t for each input pointer about the extent it resides in: + * + * (a) number of free regions in the extent, + * (b) number of regions in the extent, and + * (c) size of the extent in terms of bytes. + * + * This API is mainly intended for small class allocations, where extents are + * used as slab. In case of large class allocations, the outputs are trivial: + * "(a)" will be 0, "(b)" will be 1, and "(c)" will be the usable size. + * + * Note that multiple input pointers may reside on a same extent so the output + * fields may contain duplicates. + * + * The format of the input/output looks like: + * + * input[0]: 1st_pointer_to_query | output[0]: 1st_extent_n_free_regions + * | output[1]: 1st_extent_n_regions + * | output[2]: 1st_extent_size + * input[1]: 2nd_pointer_to_query | output[3]: 2nd_extent_n_free_regions + * | output[4]: 2nd_extent_n_regions + * | output[5]: 2nd_extent_size + * ... | ... + * + * The input array and size are respectively passed in by newp and newlen, and + * the output array and size are respectively oldp and *oldlenp. + * + * It can be beneficial to define the following macros to make it easier to + * access the output: + * + * #define NFREE_READ(out, i) out[(i) * 3] + * #define NREGS_READ(out, i) out[(i) * 3 + 1] + * #define SIZE_READ(out, i) out[(i) * 3 + 2] + * + * and then write e.g. NFREE_READ(oldp, i) to fetch the output. See the unit + * test test_batch in test/unit/extent_util.c for a concrete example. + * + * A typical workflow would be composed of the following steps: + * + * (1) flush tcache: mallctl("thread.tcache.flush", ...) + * (2) initialize input array of pointers to query fragmentation + * (3) allocate output array to hold utilization statistics + * (4) query utilization: mallctl("experimental.utilization.batch_query", ...) + * (5) (optional) decide if it's worthwhile to defragment; otherwise stop here + * (6) disable tcache: mallctl("thread.tcache.enabled", ...) + * (7) defragment allocations with significant fragmentation, e.g.: + * for each allocation { + * if it's fragmented { + * malloc(...); + * memcpy(...); + * free(...); + * } + * } + * (8) enable tcache: mallctl("thread.tcache.enabled", ...) + * + * The application can determine the significance of fragmentation themselves + * relying on the statistics returned, both at the overall level i.e. step "(5)" + * and at individual allocation level i.e. within step "(7)". Possible choices + * are: + * + * (a) whether memory utilization ratio is below certain threshold, + * (b) whether memory consumption is above certain threshold, or + * (c) some combination of the two. + * + * The caller needs to make sure that the input/output arrays are valid and + * their sizes are proper as well as matched, meaning: + * + * (a) newlen = n_pointers * sizeof(const void *) + * (b) *oldlenp = n_pointers * sizeof(size_t) * 3 + * (c) n_pointers > 0 + * + * Otherwise, the function immediately returns EINVAL without touching anything. + * + * In the rare case where there's no associated extent found for some pointers, + * rather than immediately terminating the computation and raising an error, + * the function simply zeros out the corresponding output fields and continues + * the computation until all input pointers are handled. The motivations of + * such a design are as follows: + * + * (a) The function always either processes nothing or processes everything, and + * never leaves the output half touched and half untouched. + * + * (b) It facilitates usage needs especially common in C++. A vast variety of + * C++ objects are instantiated with multiple dynamic memory allocations. For + * example, std::string and std::vector typically use at least two allocations, + * one for the metadata and one for the actual content. Other types may use + * even more allocations. When inquiring about utilization statistics, the + * caller often wants to examine into all such allocations, especially internal + * one(s), rather than just the topmost one. The issue comes when some + * implementations do certain optimizations to reduce/aggregate some internal + * allocations, e.g. putting short strings directly into the metadata, and such + * decisions are not known to the caller. Therefore, we permit pointers to + * memory usages that may not be returned by previous malloc calls, and we + * provide the caller a convenient way to identify such cases. + */ +static int +experimental_utilization_batch_query_ctl(tsd_t *tsd, const size_t *mib, + size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen) { + int ret; + + assert(sizeof(extent_util_stats_t) == sizeof(size_t) * 3); + + const size_t len = newlen / sizeof(const void *); + if (oldp == NULL || oldlenp == NULL || newp == NULL || newlen == 0 + || newlen != len * sizeof(const void *) + || *oldlenp != len * sizeof(extent_util_stats_t)) { + ret = EINVAL; + goto label_return; + } + + void **ptrs = (void **)newp; + extent_util_stats_t *util_stats = (extent_util_stats_t *)oldp; + size_t i; + for (i = 0; i < len; ++i) { + extent_util_stats_get(tsd_tsdn(tsd), ptrs[i], + &util_stats[i].nfree, &util_stats[i].nregs, + &util_stats[i].size); + } + ret = 0; + +label_return: + return ret; +} + +static const ctl_named_node_t * +experimental_arenas_i_index(tsdn_t *tsdn, const size_t *mib, + size_t miblen, size_t i) { + const ctl_named_node_t *ret; + + malloc_mutex_lock(tsdn, &ctl_mtx); + if (ctl_arenas_i_verify(i)) { + ret = NULL; + goto label_return; + } + ret = super_experimental_arenas_i_node; +label_return: + malloc_mutex_unlock(tsdn, &ctl_mtx); + return ret; +} + +static int +experimental_arenas_i_pactivep_ctl(tsd_t *tsd, const size_t *mib, + size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen) { + if (!config_stats) { + return ENOENT; + } + if (oldp == NULL || oldlenp == NULL || *oldlenp != sizeof(size_t *)) { + return EINVAL; + } + + unsigned arena_ind; + arena_t *arena; + int ret; + size_t *pactivep; + + malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx); + READONLY(); + MIB_UNSIGNED(arena_ind, 2); + if (arena_ind < narenas_total_get() && (arena = + arena_get(tsd_tsdn(tsd), arena_ind, false)) != NULL) { +#if defined(JEMALLOC_GCC_ATOMIC_ATOMICS) || \ + defined(JEMALLOC_GCC_SYNC_ATOMICS) || defined(_MSC_VER) + /* Expose the underlying counter for fast read. */ + pactivep = (size_t *)&(arena->nactive.repr); + READ(pactivep, size_t *); + ret = 0; +#else + ret = EFAULT; +#endif + } else { + ret = EFAULT; + } +label_return: + malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx); return ret; } Index: head/contrib/jemalloc/src/extent.c =================================================================== --- head/contrib/jemalloc/src/extent.c (revision 360232) +++ head/contrib/jemalloc/src/extent.c (revision 360233) @@ -1,2178 +1,2403 @@ #define JEMALLOC_EXTENT_C_ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/jemalloc_internal_includes.h" #include "jemalloc/internal/assert.h" #include "jemalloc/internal/extent_dss.h" #include "jemalloc/internal/extent_mmap.h" #include "jemalloc/internal/ph.h" #include "jemalloc/internal/rtree.h" #include "jemalloc/internal/mutex.h" #include "jemalloc/internal/mutex_pool.h" /******************************************************************************/ /* Data. */ rtree_t extents_rtree; /* Keyed by the address of the extent_t being protected. */ mutex_pool_t extent_mutex_pool; size_t opt_lg_extent_max_active_fit = LG_EXTENT_MAX_ACTIVE_FIT_DEFAULT; static const bitmap_info_t extents_bitmap_info = - BITMAP_INFO_INITIALIZER(NPSIZES+1); + BITMAP_INFO_INITIALIZER(SC_NPSIZES+1); static void *extent_alloc_default(extent_hooks_t *extent_hooks, void *new_addr, size_t size, size_t alignment, bool *zero, bool *commit, unsigned arena_ind); static bool extent_dalloc_default(extent_hooks_t *extent_hooks, void *addr, size_t size, bool committed, unsigned arena_ind); static void extent_destroy_default(extent_hooks_t *extent_hooks, void *addr, size_t size, bool committed, unsigned arena_ind); static bool extent_commit_default(extent_hooks_t *extent_hooks, void *addr, size_t size, size_t offset, size_t length, unsigned arena_ind); static bool extent_commit_impl(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset, size_t length, bool growing_retained); static bool extent_decommit_default(extent_hooks_t *extent_hooks, void *addr, size_t size, size_t offset, size_t length, unsigned arena_ind); #ifdef PAGES_CAN_PURGE_LAZY static bool extent_purge_lazy_default(extent_hooks_t *extent_hooks, void *addr, size_t size, size_t offset, size_t length, unsigned arena_ind); #endif static bool extent_purge_lazy_impl(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset, size_t length, bool growing_retained); #ifdef PAGES_CAN_PURGE_FORCED static bool extent_purge_forced_default(extent_hooks_t *extent_hooks, void *addr, size_t size, size_t offset, size_t length, unsigned arena_ind); #endif static bool extent_purge_forced_impl(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset, size_t length, bool growing_retained); -#ifdef JEMALLOC_MAPS_COALESCE static bool extent_split_default(extent_hooks_t *extent_hooks, void *addr, size_t size, size_t size_a, size_t size_b, bool committed, unsigned arena_ind); -#endif static extent_t *extent_split_impl(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent, size_t size_a, szind_t szind_a, bool slab_a, size_t size_b, szind_t szind_b, bool slab_b, bool growing_retained); -#ifdef JEMALLOC_MAPS_COALESCE static bool extent_merge_default(extent_hooks_t *extent_hooks, void *addr_a, size_t size_a, void *addr_b, size_t size_b, bool committed, unsigned arena_ind); -#endif static bool extent_merge_impl(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *a, extent_t *b, bool growing_retained); const extent_hooks_t extent_hooks_default = { extent_alloc_default, extent_dalloc_default, extent_destroy_default, extent_commit_default, extent_decommit_default #ifdef PAGES_CAN_PURGE_LAZY , extent_purge_lazy_default #else , NULL #endif #ifdef PAGES_CAN_PURGE_FORCED , extent_purge_forced_default #else , NULL #endif -#ifdef JEMALLOC_MAPS_COALESCE , extent_split_default, extent_merge_default -#endif }; /* Used exclusively for gdump triggering. */ static atomic_zu_t curpages; static atomic_zu_t highpages; /******************************************************************************/ /* * Function prototypes for static functions that are referenced prior to * definition. */ static void extent_deregister(tsdn_t *tsdn, extent_t *extent); static extent_t *extent_recycle(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extents_t *extents, void *new_addr, size_t usize, size_t pad, size_t alignment, bool slab, szind_t szind, bool *zero, bool *commit, bool growing_retained); static extent_t *extent_try_coalesce(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, rtree_ctx_t *rtree_ctx, extents_t *extents, extent_t *extent, bool *coalesced, bool growing_retained); static void extent_record(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extents_t *extents, extent_t *extent, bool growing_retained); /******************************************************************************/ -ph_gen(UNUSED, extent_avail_, extent_tree_t, extent_t, ph_link, +#define ATTR_NONE /* does nothing */ + +ph_gen(ATTR_NONE, extent_avail_, extent_tree_t, extent_t, ph_link, extent_esnead_comp) +#undef ATTR_NONE + typedef enum { lock_result_success, lock_result_failure, lock_result_no_extent } lock_result_t; static lock_result_t extent_rtree_leaf_elm_try_lock(tsdn_t *tsdn, rtree_leaf_elm_t *elm, - extent_t **result) { + extent_t **result, bool inactive_only) { extent_t *extent1 = rtree_leaf_elm_extent_read(tsdn, &extents_rtree, elm, true); - if (extent1 == NULL) { + /* Slab implies active extents and should be skipped. */ + if (extent1 == NULL || (inactive_only && rtree_leaf_elm_slab_read(tsdn, + &extents_rtree, elm, true))) { return lock_result_no_extent; } + /* * It's possible that the extent changed out from under us, and with it * the leaf->extent mapping. We have to recheck while holding the lock. */ extent_lock(tsdn, extent1); extent_t *extent2 = rtree_leaf_elm_extent_read(tsdn, &extents_rtree, elm, true); if (extent1 == extent2) { *result = extent1; return lock_result_success; } else { extent_unlock(tsdn, extent1); return lock_result_failure; } } /* * Returns a pool-locked extent_t * if there's one associated with the given * address, and NULL otherwise. */ static extent_t * -extent_lock_from_addr(tsdn_t *tsdn, rtree_ctx_t *rtree_ctx, void *addr) { +extent_lock_from_addr(tsdn_t *tsdn, rtree_ctx_t *rtree_ctx, void *addr, + bool inactive_only) { extent_t *ret = NULL; rtree_leaf_elm_t *elm = rtree_leaf_elm_lookup(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)addr, false, false); if (elm == NULL) { return NULL; } lock_result_t lock_result; do { - lock_result = extent_rtree_leaf_elm_try_lock(tsdn, elm, &ret); + lock_result = extent_rtree_leaf_elm_try_lock(tsdn, elm, &ret, + inactive_only); } while (lock_result == lock_result_failure); return ret; } extent_t * extent_alloc(tsdn_t *tsdn, arena_t *arena) { malloc_mutex_lock(tsdn, &arena->extent_avail_mtx); extent_t *extent = extent_avail_first(&arena->extent_avail); if (extent == NULL) { malloc_mutex_unlock(tsdn, &arena->extent_avail_mtx); return base_alloc_extent(tsdn, arena->base); } extent_avail_remove(&arena->extent_avail, extent); + atomic_fetch_sub_zu(&arena->extent_avail_cnt, 1, ATOMIC_RELAXED); malloc_mutex_unlock(tsdn, &arena->extent_avail_mtx); return extent; } void extent_dalloc(tsdn_t *tsdn, arena_t *arena, extent_t *extent) { malloc_mutex_lock(tsdn, &arena->extent_avail_mtx); extent_avail_insert(&arena->extent_avail, extent); + atomic_fetch_add_zu(&arena->extent_avail_cnt, 1, ATOMIC_RELAXED); malloc_mutex_unlock(tsdn, &arena->extent_avail_mtx); } extent_hooks_t * extent_hooks_get(arena_t *arena) { return base_extent_hooks_get(arena->base); } extent_hooks_t * extent_hooks_set(tsd_t *tsd, arena_t *arena, extent_hooks_t *extent_hooks) { background_thread_info_t *info; if (have_background_thread) { info = arena_background_thread_info_get(arena); malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx); } extent_hooks_t *ret = base_extent_hooks_set(arena->base, extent_hooks); if (have_background_thread) { malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx); } return ret; } static void extent_hooks_assure_initialized(arena_t *arena, extent_hooks_t **r_extent_hooks) { if (*r_extent_hooks == EXTENT_HOOKS_INITIALIZER) { *r_extent_hooks = extent_hooks_get(arena); } } #ifndef JEMALLOC_JET static #endif size_t extent_size_quantize_floor(size_t size) { size_t ret; pszind_t pind; assert(size > 0); assert((size & PAGE_MASK) == 0); pind = sz_psz2ind(size - sz_large_pad + 1); if (pind == 0) { /* * Avoid underflow. This short-circuit would also do the right * thing for all sizes in the range for which there are * PAGE-spaced size classes, but it's simplest to just handle * the one case that would cause erroneous results. */ return size; } ret = sz_pind2sz(pind - 1) + sz_large_pad; assert(ret <= size); return ret; } #ifndef JEMALLOC_JET static #endif size_t extent_size_quantize_ceil(size_t size) { size_t ret; assert(size > 0); - assert(size - sz_large_pad <= LARGE_MAXCLASS); + assert(size - sz_large_pad <= SC_LARGE_MAXCLASS); assert((size & PAGE_MASK) == 0); ret = extent_size_quantize_floor(size); if (ret < size) { /* * Skip a quantization that may have an adequately large extent, * because under-sized extents may be mixed in. This only * happens when an unusual size is requested, i.e. for aligned * allocation, and is just one of several places where linear * search would potentially find sufficiently aligned available * memory somewhere lower. */ ret = sz_pind2sz(sz_psz2ind(ret - sz_large_pad + 1)) + sz_large_pad; } return ret; } /* Generate pairing heap functions. */ ph_gen(, extent_heap_, extent_heap_t, extent_t, ph_link, extent_snad_comp) bool extents_init(tsdn_t *tsdn, extents_t *extents, extent_state_t state, bool delay_coalesce) { if (malloc_mutex_init(&extents->mtx, "extents", WITNESS_RANK_EXTENTS, malloc_mutex_rank_exclusive)) { return true; } - for (unsigned i = 0; i < NPSIZES+1; i++) { + for (unsigned i = 0; i < SC_NPSIZES + 1; i++) { extent_heap_new(&extents->heaps[i]); } bitmap_init(extents->bitmap, &extents_bitmap_info, true); extent_list_init(&extents->lru); atomic_store_zu(&extents->npages, 0, ATOMIC_RELAXED); extents->state = state; extents->delay_coalesce = delay_coalesce; return false; } extent_state_t extents_state_get(const extents_t *extents) { return extents->state; } size_t extents_npages_get(extents_t *extents) { return atomic_load_zu(&extents->npages, ATOMIC_RELAXED); } +size_t +extents_nextents_get(extents_t *extents, pszind_t pind) { + return atomic_load_zu(&extents->nextents[pind], ATOMIC_RELAXED); +} + +size_t +extents_nbytes_get(extents_t *extents, pszind_t pind) { + return atomic_load_zu(&extents->nbytes[pind], ATOMIC_RELAXED); +} + static void +extents_stats_add(extents_t *extent, pszind_t pind, size_t sz) { + size_t cur = atomic_load_zu(&extent->nextents[pind], ATOMIC_RELAXED); + atomic_store_zu(&extent->nextents[pind], cur + 1, ATOMIC_RELAXED); + cur = atomic_load_zu(&extent->nbytes[pind], ATOMIC_RELAXED); + atomic_store_zu(&extent->nbytes[pind], cur + sz, ATOMIC_RELAXED); +} + +static void +extents_stats_sub(extents_t *extent, pszind_t pind, size_t sz) { + size_t cur = atomic_load_zu(&extent->nextents[pind], ATOMIC_RELAXED); + atomic_store_zu(&extent->nextents[pind], cur - 1, ATOMIC_RELAXED); + cur = atomic_load_zu(&extent->nbytes[pind], ATOMIC_RELAXED); + atomic_store_zu(&extent->nbytes[pind], cur - sz, ATOMIC_RELAXED); +} + +static void extents_insert_locked(tsdn_t *tsdn, extents_t *extents, extent_t *extent) { malloc_mutex_assert_owner(tsdn, &extents->mtx); assert(extent_state_get(extent) == extents->state); size_t size = extent_size_get(extent); size_t psz = extent_size_quantize_floor(size); pszind_t pind = sz_psz2ind(psz); if (extent_heap_empty(&extents->heaps[pind])) { bitmap_unset(extents->bitmap, &extents_bitmap_info, (size_t)pind); } extent_heap_insert(&extents->heaps[pind], extent); + + if (config_stats) { + extents_stats_add(extents, pind, size); + } + extent_list_append(&extents->lru, extent); size_t npages = size >> LG_PAGE; /* * All modifications to npages hold the mutex (as asserted above), so we * don't need an atomic fetch-add; we can get by with a load followed by * a store. */ size_t cur_extents_npages = atomic_load_zu(&extents->npages, ATOMIC_RELAXED); atomic_store_zu(&extents->npages, cur_extents_npages + npages, ATOMIC_RELAXED); } static void extents_remove_locked(tsdn_t *tsdn, extents_t *extents, extent_t *extent) { malloc_mutex_assert_owner(tsdn, &extents->mtx); assert(extent_state_get(extent) == extents->state); size_t size = extent_size_get(extent); size_t psz = extent_size_quantize_floor(size); pszind_t pind = sz_psz2ind(psz); extent_heap_remove(&extents->heaps[pind], extent); + + if (config_stats) { + extents_stats_sub(extents, pind, size); + } + if (extent_heap_empty(&extents->heaps[pind])) { bitmap_set(extents->bitmap, &extents_bitmap_info, (size_t)pind); } extent_list_remove(&extents->lru, extent); size_t npages = size >> LG_PAGE; /* * As in extents_insert_locked, we hold extents->mtx and so don't need * atomic operations for updating extents->npages. */ size_t cur_extents_npages = atomic_load_zu(&extents->npages, ATOMIC_RELAXED); assert(cur_extents_npages >= npages); atomic_store_zu(&extents->npages, cur_extents_npages - (size >> LG_PAGE), ATOMIC_RELAXED); } /* * Find an extent with size [min_size, max_size) to satisfy the alignment * requirement. For each size, try only the first extent in the heap. */ static extent_t * extents_fit_alignment(extents_t *extents, size_t min_size, size_t max_size, size_t alignment) { pszind_t pind = sz_psz2ind(extent_size_quantize_ceil(min_size)); pszind_t pind_max = sz_psz2ind(extent_size_quantize_ceil(max_size)); for (pszind_t i = (pszind_t)bitmap_ffu(extents->bitmap, &extents_bitmap_info, (size_t)pind); i < pind_max; i = (pszind_t)bitmap_ffu(extents->bitmap, &extents_bitmap_info, (size_t)i+1)) { - assert(i < NPSIZES); + assert(i < SC_NPSIZES); assert(!extent_heap_empty(&extents->heaps[i])); extent_t *extent = extent_heap_first(&extents->heaps[i]); uintptr_t base = (uintptr_t)extent_base_get(extent); size_t candidate_size = extent_size_get(extent); assert(candidate_size >= min_size); uintptr_t next_align = ALIGNMENT_CEILING((uintptr_t)base, PAGE_CEILING(alignment)); if (base > next_align || base + candidate_size <= next_align) { /* Overflow or not crossing the next alignment. */ continue; } size_t leadsize = next_align - base; if (candidate_size - leadsize >= min_size) { return extent; } } return NULL; } -/* Do any-best-fit extent selection, i.e. select any extent that best fits. */ -static extent_t * -extents_best_fit_locked(tsdn_t *tsdn, arena_t *arena, extents_t *extents, - size_t size) { - pszind_t pind = sz_psz2ind(extent_size_quantize_ceil(size)); - pszind_t i = (pszind_t)bitmap_ffu(extents->bitmap, &extents_bitmap_info, - (size_t)pind); - if (i < NPSIZES+1) { - /* - * In order to reduce fragmentation, avoid reusing and splitting - * large extents for much smaller sizes. - */ - if ((sz_pind2sz(i) >> opt_lg_extent_max_active_fit) > size) { - return NULL; - } - assert(!extent_heap_empty(&extents->heaps[i])); - extent_t *extent = extent_heap_first(&extents->heaps[i]); - assert(extent_size_get(extent) >= size); - return extent; - } - - return NULL; -} - /* * Do first-fit extent selection, i.e. select the oldest/lowest extent that is * large enough. */ static extent_t * extents_first_fit_locked(tsdn_t *tsdn, arena_t *arena, extents_t *extents, size_t size) { extent_t *ret = NULL; pszind_t pind = sz_psz2ind(extent_size_quantize_ceil(size)); + + if (!maps_coalesce && !opt_retain) { + /* + * No split / merge allowed (Windows w/o retain). Try exact fit + * only. + */ + return extent_heap_empty(&extents->heaps[pind]) ? NULL : + extent_heap_first(&extents->heaps[pind]); + } + for (pszind_t i = (pszind_t)bitmap_ffu(extents->bitmap, - &extents_bitmap_info, (size_t)pind); i < NPSIZES+1; i = - (pszind_t)bitmap_ffu(extents->bitmap, &extents_bitmap_info, + &extents_bitmap_info, (size_t)pind); + i < SC_NPSIZES + 1; + i = (pszind_t)bitmap_ffu(extents->bitmap, &extents_bitmap_info, (size_t)i+1)) { assert(!extent_heap_empty(&extents->heaps[i])); extent_t *extent = extent_heap_first(&extents->heaps[i]); assert(extent_size_get(extent) >= size); + /* + * In order to reduce fragmentation, avoid reusing and splitting + * large extents for much smaller sizes. + * + * Only do check for dirty extents (delay_coalesce). + */ + if (extents->delay_coalesce && + (sz_pind2sz(i) >> opt_lg_extent_max_active_fit) > size) { + break; + } if (ret == NULL || extent_snad_comp(extent, ret) < 0) { ret = extent; } - if (i == NPSIZES) { + if (i == SC_NPSIZES) { break; } - assert(i < NPSIZES); + assert(i < SC_NPSIZES); } return ret; } /* - * Do {best,first}-fit extent selection, where the selection policy choice is - * based on extents->delay_coalesce. Best-fit selection requires less - * searching, but its layout policy is less stable and may cause higher virtual - * memory fragmentation as a side effect. + * Do first-fit extent selection, where the selection policy choice is + * based on extents->delay_coalesce. */ static extent_t * extents_fit_locked(tsdn_t *tsdn, arena_t *arena, extents_t *extents, size_t esize, size_t alignment) { malloc_mutex_assert_owner(tsdn, &extents->mtx); size_t max_size = esize + PAGE_CEILING(alignment) - PAGE; /* Beware size_t wrap-around. */ if (max_size < esize) { return NULL; } - extent_t *extent = extents->delay_coalesce ? - extents_best_fit_locked(tsdn, arena, extents, max_size) : + extent_t *extent = extents_first_fit_locked(tsdn, arena, extents, max_size); if (alignment > PAGE && extent == NULL) { /* * max_size guarantees the alignment requirement but is rather * pessimistic. Next we try to satisfy the aligned allocation * with sizes in [esize, max_size). */ extent = extents_fit_alignment(extents, esize, max_size, alignment); } return extent; } static bool extent_try_delayed_coalesce(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, rtree_ctx_t *rtree_ctx, extents_t *extents, extent_t *extent) { extent_state_set(extent, extent_state_active); bool coalesced; extent = extent_try_coalesce(tsdn, arena, r_extent_hooks, rtree_ctx, extents, extent, &coalesced, false); extent_state_set(extent, extents_state_get(extents)); if (!coalesced) { return true; } extents_insert_locked(tsdn, extents, extent); return false; } extent_t * extents_alloc(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extents_t *extents, void *new_addr, size_t size, size_t pad, size_t alignment, bool slab, szind_t szind, bool *zero, bool *commit) { assert(size + pad != 0); assert(alignment != 0); witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); extent_t *extent = extent_recycle(tsdn, arena, r_extent_hooks, extents, new_addr, size, pad, alignment, slab, szind, zero, commit, false); assert(extent == NULL || extent_dumpable_get(extent)); return extent; } void extents_dalloc(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extents_t *extents, extent_t *extent) { assert(extent_base_get(extent) != NULL); assert(extent_size_get(extent) != 0); assert(extent_dumpable_get(extent)); witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); extent_addr_set(extent, extent_base_get(extent)); extent_zeroed_set(extent, false); extent_record(tsdn, arena, r_extent_hooks, extents, extent, false); } extent_t * extents_evict(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extents_t *extents, size_t npages_min) { rtree_ctx_t rtree_ctx_fallback; rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); malloc_mutex_lock(tsdn, &extents->mtx); /* * Get the LRU coalesced extent, if any. If coalescing was delayed, * the loop will iterate until the LRU extent is fully coalesced. */ extent_t *extent; while (true) { /* Get the LRU extent, if any. */ extent = extent_list_first(&extents->lru); if (extent == NULL) { goto label_return; } /* Check the eviction limit. */ size_t extents_npages = atomic_load_zu(&extents->npages, ATOMIC_RELAXED); if (extents_npages <= npages_min) { extent = NULL; goto label_return; } extents_remove_locked(tsdn, extents, extent); if (!extents->delay_coalesce) { break; } /* Try to coalesce. */ if (extent_try_delayed_coalesce(tsdn, arena, r_extent_hooks, rtree_ctx, extents, extent)) { break; } /* * The LRU extent was just coalesced and the result placed in * the LRU at its neighbor's position. Start over. */ } /* * Either mark the extent active or deregister it to protect against * concurrent operations. */ switch (extents_state_get(extents)) { case extent_state_active: not_reached(); case extent_state_dirty: case extent_state_muzzy: extent_state_set(extent, extent_state_active); break; case extent_state_retained: extent_deregister(tsdn, extent); break; default: not_reached(); } label_return: malloc_mutex_unlock(tsdn, &extents->mtx); return extent; } +/* + * This can only happen when we fail to allocate a new extent struct (which + * indicates OOM), e.g. when trying to split an existing extent. + */ static void -extents_leak(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, +extents_abandon_vm(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extents_t *extents, extent_t *extent, bool growing_retained) { + size_t sz = extent_size_get(extent); + if (config_stats) { + arena_stats_accum_zu(&arena->stats.abandoned_vm, sz); + } /* * Leak extent after making sure its pages have already been purged, so * that this is only a virtual memory leak. */ if (extents_state_get(extents) == extent_state_dirty) { if (extent_purge_lazy_impl(tsdn, arena, r_extent_hooks, - extent, 0, extent_size_get(extent), growing_retained)) { + extent, 0, sz, growing_retained)) { extent_purge_forced_impl(tsdn, arena, r_extent_hooks, extent, 0, extent_size_get(extent), growing_retained); } } extent_dalloc(tsdn, arena, extent); } void extents_prefork(tsdn_t *tsdn, extents_t *extents) { malloc_mutex_prefork(tsdn, &extents->mtx); } void extents_postfork_parent(tsdn_t *tsdn, extents_t *extents) { malloc_mutex_postfork_parent(tsdn, &extents->mtx); } void extents_postfork_child(tsdn_t *tsdn, extents_t *extents) { malloc_mutex_postfork_child(tsdn, &extents->mtx); } static void extent_deactivate_locked(tsdn_t *tsdn, arena_t *arena, extents_t *extents, extent_t *extent) { assert(extent_arena_get(extent) == arena); assert(extent_state_get(extent) == extent_state_active); extent_state_set(extent, extents_state_get(extents)); extents_insert_locked(tsdn, extents, extent); } static void extent_deactivate(tsdn_t *tsdn, arena_t *arena, extents_t *extents, extent_t *extent) { malloc_mutex_lock(tsdn, &extents->mtx); extent_deactivate_locked(tsdn, arena, extents, extent); malloc_mutex_unlock(tsdn, &extents->mtx); } static void extent_activate_locked(tsdn_t *tsdn, arena_t *arena, extents_t *extents, extent_t *extent) { assert(extent_arena_get(extent) == arena); assert(extent_state_get(extent) == extents_state_get(extents)); extents_remove_locked(tsdn, extents, extent); extent_state_set(extent, extent_state_active); } static bool extent_rtree_leaf_elms_lookup(tsdn_t *tsdn, rtree_ctx_t *rtree_ctx, const extent_t *extent, bool dependent, bool init_missing, rtree_leaf_elm_t **r_elm_a, rtree_leaf_elm_t **r_elm_b) { *r_elm_a = rtree_leaf_elm_lookup(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)extent_base_get(extent), dependent, init_missing); if (!dependent && *r_elm_a == NULL) { return true; } assert(*r_elm_a != NULL); *r_elm_b = rtree_leaf_elm_lookup(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)extent_last_get(extent), dependent, init_missing); if (!dependent && *r_elm_b == NULL) { return true; } assert(*r_elm_b != NULL); return false; } static void extent_rtree_write_acquired(tsdn_t *tsdn, rtree_leaf_elm_t *elm_a, rtree_leaf_elm_t *elm_b, extent_t *extent, szind_t szind, bool slab) { rtree_leaf_elm_write(tsdn, &extents_rtree, elm_a, extent, szind, slab); if (elm_b != NULL) { rtree_leaf_elm_write(tsdn, &extents_rtree, elm_b, extent, szind, slab); } } static void extent_interior_register(tsdn_t *tsdn, rtree_ctx_t *rtree_ctx, extent_t *extent, szind_t szind) { assert(extent_slab_get(extent)); /* Register interior. */ for (size_t i = 1; i < (extent_size_get(extent) >> LG_PAGE) - 1; i++) { rtree_write(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)extent_base_get(extent) + (uintptr_t)(i << LG_PAGE), extent, szind, true); } } static void extent_gdump_add(tsdn_t *tsdn, const extent_t *extent) { cassert(config_prof); /* prof_gdump() requirement. */ witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); if (opt_prof && extent_state_get(extent) == extent_state_active) { size_t nadd = extent_size_get(extent) >> LG_PAGE; size_t cur = atomic_fetch_add_zu(&curpages, nadd, ATOMIC_RELAXED) + nadd; size_t high = atomic_load_zu(&highpages, ATOMIC_RELAXED); while (cur > high && !atomic_compare_exchange_weak_zu( &highpages, &high, cur, ATOMIC_RELAXED, ATOMIC_RELAXED)) { /* * Don't refresh cur, because it may have decreased * since this thread lost the highpages update race. * Note that high is updated in case of CAS failure. */ } if (cur > high && prof_gdump_get_unlocked()) { prof_gdump(tsdn); } } } static void extent_gdump_sub(tsdn_t *tsdn, const extent_t *extent) { cassert(config_prof); if (opt_prof && extent_state_get(extent) == extent_state_active) { size_t nsub = extent_size_get(extent) >> LG_PAGE; assert(atomic_load_zu(&curpages, ATOMIC_RELAXED) >= nsub); atomic_fetch_sub_zu(&curpages, nsub, ATOMIC_RELAXED); } } static bool extent_register_impl(tsdn_t *tsdn, extent_t *extent, bool gdump_add) { rtree_ctx_t rtree_ctx_fallback; rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); rtree_leaf_elm_t *elm_a, *elm_b; /* * We need to hold the lock to protect against a concurrent coalesce * operation that sees us in a partial state. */ extent_lock(tsdn, extent); if (extent_rtree_leaf_elms_lookup(tsdn, rtree_ctx, extent, false, true, &elm_a, &elm_b)) { + extent_unlock(tsdn, extent); return true; } szind_t szind = extent_szind_get_maybe_invalid(extent); bool slab = extent_slab_get(extent); extent_rtree_write_acquired(tsdn, elm_a, elm_b, extent, szind, slab); if (slab) { extent_interior_register(tsdn, rtree_ctx, extent, szind); } extent_unlock(tsdn, extent); if (config_prof && gdump_add) { extent_gdump_add(tsdn, extent); } return false; } static bool extent_register(tsdn_t *tsdn, extent_t *extent) { return extent_register_impl(tsdn, extent, true); } static bool extent_register_no_gdump_add(tsdn_t *tsdn, extent_t *extent) { return extent_register_impl(tsdn, extent, false); } static void extent_reregister(tsdn_t *tsdn, extent_t *extent) { bool err = extent_register(tsdn, extent); assert(!err); } /* * Removes all pointers to the given extent from the global rtree indices for * its interior. This is relevant for slab extents, for which we need to do * metadata lookups at places other than the head of the extent. We deregister * on the interior, then, when an extent moves from being an active slab to an * inactive state. */ static void extent_interior_deregister(tsdn_t *tsdn, rtree_ctx_t *rtree_ctx, extent_t *extent) { size_t i; assert(extent_slab_get(extent)); for (i = 1; i < (extent_size_get(extent) >> LG_PAGE) - 1; i++) { rtree_clear(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)extent_base_get(extent) + (uintptr_t)(i << LG_PAGE)); } } /* * Removes all pointers to the given extent from the global rtree. */ static void extent_deregister_impl(tsdn_t *tsdn, extent_t *extent, bool gdump) { rtree_ctx_t rtree_ctx_fallback; rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); rtree_leaf_elm_t *elm_a, *elm_b; extent_rtree_leaf_elms_lookup(tsdn, rtree_ctx, extent, true, false, &elm_a, &elm_b); extent_lock(tsdn, extent); - extent_rtree_write_acquired(tsdn, elm_a, elm_b, NULL, NSIZES, false); + extent_rtree_write_acquired(tsdn, elm_a, elm_b, NULL, SC_NSIZES, false); if (extent_slab_get(extent)) { extent_interior_deregister(tsdn, rtree_ctx, extent); extent_slab_set(extent, false); } extent_unlock(tsdn, extent); if (config_prof && gdump) { extent_gdump_sub(tsdn, extent); } } static void extent_deregister(tsdn_t *tsdn, extent_t *extent) { extent_deregister_impl(tsdn, extent, true); } static void extent_deregister_no_gdump_sub(tsdn_t *tsdn, extent_t *extent) { extent_deregister_impl(tsdn, extent, false); } /* * Tries to find and remove an extent from extents that can be used for the * given allocation request. */ static extent_t * extent_recycle_extract(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, rtree_ctx_t *rtree_ctx, extents_t *extents, void *new_addr, size_t size, size_t pad, size_t alignment, bool slab, bool growing_retained) { witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, growing_retained ? 1 : 0); assert(alignment > 0); if (config_debug && new_addr != NULL) { /* * Non-NULL new_addr has two use cases: * * 1) Recycle a known-extant extent, e.g. during purging. * 2) Perform in-place expanding reallocation. * * Regardless of use case, new_addr must either refer to a * non-existing extent, or to the base of an extant extent, * since only active slabs support interior lookups (which of * course cannot be recycled). */ assert(PAGE_ADDR2BASE(new_addr) == new_addr); assert(pad == 0); assert(alignment <= PAGE); } size_t esize = size + pad; malloc_mutex_lock(tsdn, &extents->mtx); extent_hooks_assure_initialized(arena, r_extent_hooks); extent_t *extent; if (new_addr != NULL) { - extent = extent_lock_from_addr(tsdn, rtree_ctx, new_addr); + extent = extent_lock_from_addr(tsdn, rtree_ctx, new_addr, + false); if (extent != NULL) { /* * We might null-out extent to report an error, but we * still need to unlock the associated mutex after. */ extent_t *unlock_extent = extent; assert(extent_base_get(extent) == new_addr); if (extent_arena_get(extent) != arena || extent_size_get(extent) < esize || extent_state_get(extent) != extents_state_get(extents)) { extent = NULL; } extent_unlock(tsdn, unlock_extent); } } else { extent = extents_fit_locked(tsdn, arena, extents, esize, alignment); } if (extent == NULL) { malloc_mutex_unlock(tsdn, &extents->mtx); return NULL; } extent_activate_locked(tsdn, arena, extents, extent); malloc_mutex_unlock(tsdn, &extents->mtx); return extent; } /* * Given an allocation request and an extent guaranteed to be able to satisfy * it, this splits off lead and trail extents, leaving extent pointing to an * extent satisfying the allocation. * This function doesn't put lead or trail into any extents_t; it's the caller's * job to ensure that they can be reused. */ typedef enum { /* * Split successfully. lead, extent, and trail, are modified to extents * describing the ranges before, in, and after the given allocation. */ extent_split_interior_ok, /* * The extent can't satisfy the given allocation request. None of the * input extent_t *s are touched. */ extent_split_interior_cant_alloc, /* * In a potentially invalid state. Must leak (if *to_leak is non-NULL), * and salvage what's still salvageable (if *to_salvage is non-NULL). * None of lead, extent, or trail are valid. */ extent_split_interior_error } extent_split_interior_result_t; static extent_split_interior_result_t extent_split_interior(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, rtree_ctx_t *rtree_ctx, /* The result of splitting, in case of success. */ extent_t **extent, extent_t **lead, extent_t **trail, /* The mess to clean up, in case of error. */ extent_t **to_leak, extent_t **to_salvage, void *new_addr, size_t size, size_t pad, size_t alignment, bool slab, szind_t szind, bool growing_retained) { size_t esize = size + pad; size_t leadsize = ALIGNMENT_CEILING((uintptr_t)extent_base_get(*extent), PAGE_CEILING(alignment)) - (uintptr_t)extent_base_get(*extent); assert(new_addr == NULL || leadsize == 0); if (extent_size_get(*extent) < leadsize + esize) { return extent_split_interior_cant_alloc; } size_t trailsize = extent_size_get(*extent) - leadsize - esize; *lead = NULL; *trail = NULL; *to_leak = NULL; *to_salvage = NULL; /* Split the lead. */ if (leadsize != 0) { *lead = *extent; *extent = extent_split_impl(tsdn, arena, r_extent_hooks, - *lead, leadsize, NSIZES, false, esize + trailsize, szind, + *lead, leadsize, SC_NSIZES, false, esize + trailsize, szind, slab, growing_retained); if (*extent == NULL) { *to_leak = *lead; *lead = NULL; return extent_split_interior_error; } } /* Split the trail. */ if (trailsize != 0) { *trail = extent_split_impl(tsdn, arena, r_extent_hooks, *extent, - esize, szind, slab, trailsize, NSIZES, false, + esize, szind, slab, trailsize, SC_NSIZES, false, growing_retained); if (*trail == NULL) { *to_leak = *extent; *to_salvage = *lead; *lead = NULL; *extent = NULL; return extent_split_interior_error; } } if (leadsize == 0 && trailsize == 0) { /* * Splitting causes szind to be set as a side effect, but no * splitting occurred. */ extent_szind_set(*extent, szind); - if (szind != NSIZES) { + if (szind != SC_NSIZES) { rtree_szind_slab_update(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)extent_addr_get(*extent), szind, slab); if (slab && extent_size_get(*extent) > PAGE) { rtree_szind_slab_update(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)extent_past_get(*extent) - (uintptr_t)PAGE, szind, slab); } } } return extent_split_interior_ok; } /* * This fulfills the indicated allocation request out of the given extent (which * the caller should have ensured was big enough). If there's any unused space * before or after the resulting allocation, that space is given its own extent * and put back into extents. */ static extent_t * extent_recycle_split(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, rtree_ctx_t *rtree_ctx, extents_t *extents, void *new_addr, size_t size, size_t pad, size_t alignment, bool slab, szind_t szind, extent_t *extent, bool growing_retained) { extent_t *lead; extent_t *trail; extent_t *to_leak; extent_t *to_salvage; extent_split_interior_result_t result = extent_split_interior( tsdn, arena, r_extent_hooks, rtree_ctx, &extent, &lead, &trail, &to_leak, &to_salvage, new_addr, size, pad, alignment, slab, szind, growing_retained); + if (!maps_coalesce && result != extent_split_interior_ok + && !opt_retain) { + /* + * Split isn't supported (implies Windows w/o retain). Avoid + * leaking the extents. + */ + assert(to_leak != NULL && lead == NULL && trail == NULL); + extent_deactivate(tsdn, arena, extents, to_leak); + return NULL; + } + if (result == extent_split_interior_ok) { if (lead != NULL) { extent_deactivate(tsdn, arena, extents, lead); } if (trail != NULL) { extent_deactivate(tsdn, arena, extents, trail); } return extent; } else { /* * We should have picked an extent that was large enough to * fulfill our allocation request. */ assert(result == extent_split_interior_error); if (to_salvage != NULL) { extent_deregister(tsdn, to_salvage); } if (to_leak != NULL) { void *leak = extent_base_get(to_leak); extent_deregister_no_gdump_sub(tsdn, to_leak); - extents_leak(tsdn, arena, r_extent_hooks, extents, + extents_abandon_vm(tsdn, arena, r_extent_hooks, extents, to_leak, growing_retained); - assert(extent_lock_from_addr(tsdn, rtree_ctx, leak) - == NULL); + assert(extent_lock_from_addr(tsdn, rtree_ctx, leak, + false) == NULL); } return NULL; } unreachable(); } +static bool +extent_need_manual_zero(arena_t *arena) { + /* + * Need to manually zero the extent on repopulating if either; 1) non + * default extent hooks installed (in which case the purge semantics may + * change); or 2) transparent huge pages enabled. + */ + return (!arena_has_default_hooks(arena) || + (opt_thp == thp_mode_always)); +} + /* * Tries to satisfy the given allocation request by reusing one of the extents * in the given extents_t. */ static extent_t * extent_recycle(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extents_t *extents, void *new_addr, size_t size, size_t pad, size_t alignment, bool slab, szind_t szind, bool *zero, bool *commit, bool growing_retained) { witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, growing_retained ? 1 : 0); assert(new_addr == NULL || !slab); assert(pad == 0 || !slab); assert(!*zero || !slab); rtree_ctx_t rtree_ctx_fallback; rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); extent_t *extent = extent_recycle_extract(tsdn, arena, r_extent_hooks, rtree_ctx, extents, new_addr, size, pad, alignment, slab, growing_retained); if (extent == NULL) { return NULL; } extent = extent_recycle_split(tsdn, arena, r_extent_hooks, rtree_ctx, extents, new_addr, size, pad, alignment, slab, szind, extent, growing_retained); if (extent == NULL) { return NULL; } if (*commit && !extent_committed_get(extent)) { if (extent_commit_impl(tsdn, arena, r_extent_hooks, extent, 0, extent_size_get(extent), growing_retained)) { extent_record(tsdn, arena, r_extent_hooks, extents, extent, growing_retained); return NULL; } - extent_zeroed_set(extent, true); + if (!extent_need_manual_zero(arena)) { + extent_zeroed_set(extent, true); + } } if (extent_committed_get(extent)) { *commit = true; } if (extent_zeroed_get(extent)) { *zero = true; } if (pad != 0) { extent_addr_randomize(tsdn, extent, alignment); } assert(extent_state_get(extent) == extent_state_active); if (slab) { extent_slab_set(extent, slab); extent_interior_register(tsdn, rtree_ctx, extent, szind); } if (*zero) { void *addr = extent_base_get(extent); if (!extent_zeroed_get(extent)) { size_t size = extent_size_get(extent); - if (pages_purge_forced(addr, size)) { + if (extent_need_manual_zero(arena) || + pages_purge_forced(addr, size)) { memset(addr, 0, size); } } else if (config_debug) { size_t *p = (size_t *)(uintptr_t)addr; /* Check the first page only. */ for (size_t i = 0; i < PAGE / sizeof(size_t); i++) { assert(p[i] == 0); } } } return extent; } /* * If the caller specifies (!*zero), it is still possible to receive zeroed * memory, in which case *zero is toggled to true. arena_extent_alloc() takes * advantage of this to avoid demanding zeroed extents, but taking advantage of * them if they are returned. */ static void * extent_alloc_core(tsdn_t *tsdn, arena_t *arena, void *new_addr, size_t size, size_t alignment, bool *zero, bool *commit, dss_prec_t dss_prec) { void *ret; assert(size != 0); assert(alignment != 0); /* "primary" dss. */ if (have_dss && dss_prec == dss_prec_primary && (ret = extent_alloc_dss(tsdn, arena, new_addr, size, alignment, zero, commit)) != NULL) { return ret; } /* mmap. */ if ((ret = extent_alloc_mmap(new_addr, size, alignment, zero, commit)) != NULL) { return ret; } /* "secondary" dss. */ if (have_dss && dss_prec == dss_prec_secondary && (ret = extent_alloc_dss(tsdn, arena, new_addr, size, alignment, zero, commit)) != NULL) { return ret; } /* All strategies for allocation failed. */ return NULL; } static void * extent_alloc_default_impl(tsdn_t *tsdn, arena_t *arena, void *new_addr, size_t size, size_t alignment, bool *zero, bool *commit) { void *ret = extent_alloc_core(tsdn, arena, new_addr, size, alignment, zero, commit, (dss_prec_t)atomic_load_u(&arena->dss_prec, ATOMIC_RELAXED)); if (have_madvise_huge && ret) { pages_set_thp_state(ret, size); } return ret; } static void * extent_alloc_default(extent_hooks_t *extent_hooks, void *new_addr, size_t size, size_t alignment, bool *zero, bool *commit, unsigned arena_ind) { tsdn_t *tsdn; arena_t *arena; tsdn = tsdn_fetch(); arena = arena_get(tsdn, arena_ind, false); /* * The arena we're allocating on behalf of must have been initialized * already. */ assert(arena != NULL); return extent_alloc_default_impl(tsdn, arena, new_addr, size, - alignment, zero, commit); + ALIGNMENT_CEILING(alignment, PAGE), zero, commit); } static void extent_hook_pre_reentrancy(tsdn_t *tsdn, arena_t *arena) { tsd_t *tsd = tsdn_null(tsdn) ? tsd_fetch() : tsdn_tsd(tsdn); if (arena == arena_get(tsd_tsdn(tsd), 0, false)) { /* * The only legitimate case of customized extent hooks for a0 is * hooks with no allocation activities. One such example is to * place metadata on pre-allocated resources such as huge pages. * In that case, rely on reentrancy_level checks to catch * infinite recursions. */ pre_reentrancy(tsd, NULL); } else { pre_reentrancy(tsd, arena); } } static void extent_hook_post_reentrancy(tsdn_t *tsdn) { tsd_t *tsd = tsdn_null(tsdn) ? tsd_fetch() : tsdn_tsd(tsdn); post_reentrancy(tsd); } /* * If virtual memory is retained, create increasingly larger extents from which * to split requested extents in order to limit the total number of disjoint * virtual memory ranges retained by each arena. */ static extent_t * extent_grow_retained(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, size_t size, size_t pad, size_t alignment, bool slab, szind_t szind, bool *zero, bool *commit) { malloc_mutex_assert_owner(tsdn, &arena->extent_grow_mtx); assert(pad == 0 || !slab); assert(!*zero || !slab); size_t esize = size + pad; size_t alloc_size_min = esize + PAGE_CEILING(alignment) - PAGE; /* Beware size_t wrap-around. */ if (alloc_size_min < esize) { goto label_err; } /* * Find the next extent size in the series that would be large enough to * satisfy this request. */ pszind_t egn_skip = 0; size_t alloc_size = sz_pind2sz(arena->extent_grow_next + egn_skip); while (alloc_size < alloc_size_min) { egn_skip++; - if (arena->extent_grow_next + egn_skip == NPSIZES) { + if (arena->extent_grow_next + egn_skip >= + sz_psz2ind(SC_LARGE_MAXCLASS)) { /* Outside legal range. */ goto label_err; } - assert(arena->extent_grow_next + egn_skip < NPSIZES); alloc_size = sz_pind2sz(arena->extent_grow_next + egn_skip); } extent_t *extent = extent_alloc(tsdn, arena); if (extent == NULL) { goto label_err; } bool zeroed = false; bool committed = false; void *ptr; if (*r_extent_hooks == &extent_hooks_default) { ptr = extent_alloc_default_impl(tsdn, arena, NULL, alloc_size, PAGE, &zeroed, &committed); } else { extent_hook_pre_reentrancy(tsdn, arena); ptr = (*r_extent_hooks)->alloc(*r_extent_hooks, NULL, alloc_size, PAGE, &zeroed, &committed, arena_ind_get(arena)); extent_hook_post_reentrancy(tsdn); } - extent_init(extent, arena, ptr, alloc_size, false, NSIZES, + extent_init(extent, arena, ptr, alloc_size, false, SC_NSIZES, arena_extent_sn_next(arena), extent_state_active, zeroed, - committed, true); + committed, true, EXTENT_IS_HEAD); if (ptr == NULL) { extent_dalloc(tsdn, arena, extent); goto label_err; } if (extent_register_no_gdump_add(tsdn, extent)) { - extents_leak(tsdn, arena, r_extent_hooks, - &arena->extents_retained, extent, true); + extent_dalloc(tsdn, arena, extent); goto label_err; } if (extent_zeroed_get(extent) && extent_committed_get(extent)) { *zero = true; } if (extent_committed_get(extent)) { *commit = true; } rtree_ctx_t rtree_ctx_fallback; rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); extent_t *lead; extent_t *trail; extent_t *to_leak; extent_t *to_salvage; extent_split_interior_result_t result = extent_split_interior( tsdn, arena, r_extent_hooks, rtree_ctx, &extent, &lead, &trail, &to_leak, &to_salvage, NULL, size, pad, alignment, slab, szind, true); if (result == extent_split_interior_ok) { if (lead != NULL) { extent_record(tsdn, arena, r_extent_hooks, &arena->extents_retained, lead, true); } if (trail != NULL) { extent_record(tsdn, arena, r_extent_hooks, &arena->extents_retained, trail, true); } } else { /* * We should have allocated a sufficiently large extent; the * cant_alloc case should not occur. */ assert(result == extent_split_interior_error); if (to_salvage != NULL) { if (config_prof) { extent_gdump_add(tsdn, to_salvage); } extent_record(tsdn, arena, r_extent_hooks, &arena->extents_retained, to_salvage, true); } if (to_leak != NULL) { extent_deregister_no_gdump_sub(tsdn, to_leak); - extents_leak(tsdn, arena, r_extent_hooks, + extents_abandon_vm(tsdn, arena, r_extent_hooks, &arena->extents_retained, to_leak, true); } goto label_err; } if (*commit && !extent_committed_get(extent)) { if (extent_commit_impl(tsdn, arena, r_extent_hooks, extent, 0, extent_size_get(extent), true)) { extent_record(tsdn, arena, r_extent_hooks, &arena->extents_retained, extent, true); goto label_err; } - extent_zeroed_set(extent, true); + if (!extent_need_manual_zero(arena)) { + extent_zeroed_set(extent, true); + } } /* * Increment extent_grow_next if doing so wouldn't exceed the allowed * range. */ if (arena->extent_grow_next + egn_skip + 1 <= arena->retain_grow_limit) { arena->extent_grow_next += egn_skip + 1; } else { arena->extent_grow_next = arena->retain_grow_limit; } /* All opportunities for failure are past. */ malloc_mutex_unlock(tsdn, &arena->extent_grow_mtx); if (config_prof) { /* Adjust gdump stats now that extent is final size. */ extent_gdump_add(tsdn, extent); } if (pad != 0) { extent_addr_randomize(tsdn, extent, alignment); } if (slab) { rtree_ctx_t rtree_ctx_fallback; rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); extent_slab_set(extent, true); extent_interior_register(tsdn, rtree_ctx, extent, szind); } if (*zero && !extent_zeroed_get(extent)) { void *addr = extent_base_get(extent); size_t size = extent_size_get(extent); - if (pages_purge_forced(addr, size)) { + if (extent_need_manual_zero(arena) || + pages_purge_forced(addr, size)) { memset(addr, 0, size); } } return extent; label_err: malloc_mutex_unlock(tsdn, &arena->extent_grow_mtx); return NULL; } static extent_t * extent_alloc_retained(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, void *new_addr, size_t size, size_t pad, size_t alignment, bool slab, szind_t szind, bool *zero, bool *commit) { assert(size != 0); assert(alignment != 0); malloc_mutex_lock(tsdn, &arena->extent_grow_mtx); extent_t *extent = extent_recycle(tsdn, arena, r_extent_hooks, &arena->extents_retained, new_addr, size, pad, alignment, slab, szind, zero, commit, true); if (extent != NULL) { malloc_mutex_unlock(tsdn, &arena->extent_grow_mtx); if (config_prof) { extent_gdump_add(tsdn, extent); } } else if (opt_retain && new_addr == NULL) { extent = extent_grow_retained(tsdn, arena, r_extent_hooks, size, pad, alignment, slab, szind, zero, commit); /* extent_grow_retained() always releases extent_grow_mtx. */ } else { malloc_mutex_unlock(tsdn, &arena->extent_grow_mtx); } malloc_mutex_assert_not_owner(tsdn, &arena->extent_grow_mtx); return extent; } static extent_t * extent_alloc_wrapper_hard(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, void *new_addr, size_t size, size_t pad, size_t alignment, bool slab, szind_t szind, bool *zero, bool *commit) { size_t esize = size + pad; extent_t *extent = extent_alloc(tsdn, arena); if (extent == NULL) { return NULL; } void *addr; + size_t palignment = ALIGNMENT_CEILING(alignment, PAGE); if (*r_extent_hooks == &extent_hooks_default) { /* Call directly to propagate tsdn. */ addr = extent_alloc_default_impl(tsdn, arena, new_addr, esize, - alignment, zero, commit); + palignment, zero, commit); } else { extent_hook_pre_reentrancy(tsdn, arena); addr = (*r_extent_hooks)->alloc(*r_extent_hooks, new_addr, - esize, alignment, zero, commit, arena_ind_get(arena)); + esize, palignment, zero, commit, arena_ind_get(arena)); extent_hook_post_reentrancy(tsdn); } if (addr == NULL) { extent_dalloc(tsdn, arena, extent); return NULL; } extent_init(extent, arena, addr, esize, slab, szind, arena_extent_sn_next(arena), extent_state_active, *zero, *commit, - true); + true, EXTENT_NOT_HEAD); if (pad != 0) { extent_addr_randomize(tsdn, extent, alignment); } if (extent_register(tsdn, extent)) { - extents_leak(tsdn, arena, r_extent_hooks, - &arena->extents_retained, extent, false); + extent_dalloc(tsdn, arena, extent); return NULL; } return extent; } extent_t * extent_alloc_wrapper(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, void *new_addr, size_t size, size_t pad, size_t alignment, bool slab, szind_t szind, bool *zero, bool *commit) { witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); extent_hooks_assure_initialized(arena, r_extent_hooks); extent_t *extent = extent_alloc_retained(tsdn, arena, r_extent_hooks, new_addr, size, pad, alignment, slab, szind, zero, commit); if (extent == NULL) { if (opt_retain && new_addr != NULL) { /* * When retain is enabled and new_addr is set, we do not * attempt extent_alloc_wrapper_hard which does mmap * that is very unlikely to succeed (unless it happens * to be at the end). */ return NULL; } extent = extent_alloc_wrapper_hard(tsdn, arena, r_extent_hooks, new_addr, size, pad, alignment, slab, szind, zero, commit); } assert(extent == NULL || extent_dumpable_get(extent)); return extent; } static bool extent_can_coalesce(arena_t *arena, extents_t *extents, const extent_t *inner, const extent_t *outer) { assert(extent_arena_get(inner) == arena); if (extent_arena_get(outer) != arena) { return false; } assert(extent_state_get(inner) == extent_state_active); if (extent_state_get(outer) != extents->state) { return false; } if (extent_committed_get(inner) != extent_committed_get(outer)) { return false; } return true; } static bool extent_coalesce(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extents_t *extents, extent_t *inner, extent_t *outer, bool forward, bool growing_retained) { assert(extent_can_coalesce(arena, extents, inner, outer)); extent_activate_locked(tsdn, arena, extents, outer); malloc_mutex_unlock(tsdn, &extents->mtx); bool err = extent_merge_impl(tsdn, arena, r_extent_hooks, forward ? inner : outer, forward ? outer : inner, growing_retained); malloc_mutex_lock(tsdn, &extents->mtx); if (err) { extent_deactivate_locked(tsdn, arena, extents, outer); } return err; } static extent_t * -extent_try_coalesce(tsdn_t *tsdn, arena_t *arena, +extent_try_coalesce_impl(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, rtree_ctx_t *rtree_ctx, extents_t *extents, - extent_t *extent, bool *coalesced, bool growing_retained) { + extent_t *extent, bool *coalesced, bool growing_retained, + bool inactive_only) { /* + * We avoid checking / locking inactive neighbors for large size + * classes, since they are eagerly coalesced on deallocation which can + * cause lock contention. + */ + /* * Continue attempting to coalesce until failure, to protect against * races with other threads that are thwarted by this one. */ bool again; do { again = false; /* Try to coalesce forward. */ extent_t *next = extent_lock_from_addr(tsdn, rtree_ctx, - extent_past_get(extent)); + extent_past_get(extent), inactive_only); if (next != NULL) { /* * extents->mtx only protects against races for * like-state extents, so call extent_can_coalesce() * before releasing next's pool lock. */ bool can_coalesce = extent_can_coalesce(arena, extents, extent, next); extent_unlock(tsdn, next); if (can_coalesce && !extent_coalesce(tsdn, arena, r_extent_hooks, extents, extent, next, true, growing_retained)) { if (extents->delay_coalesce) { /* Do minimal coalescing. */ *coalesced = true; return extent; } again = true; } } /* Try to coalesce backward. */ extent_t *prev = extent_lock_from_addr(tsdn, rtree_ctx, - extent_before_get(extent)); + extent_before_get(extent), inactive_only); if (prev != NULL) { bool can_coalesce = extent_can_coalesce(arena, extents, extent, prev); extent_unlock(tsdn, prev); if (can_coalesce && !extent_coalesce(tsdn, arena, r_extent_hooks, extents, extent, prev, false, growing_retained)) { extent = prev; if (extents->delay_coalesce) { /* Do minimal coalescing. */ *coalesced = true; return extent; } again = true; } } } while (again); if (extents->delay_coalesce) { *coalesced = false; } return extent; } +static extent_t * +extent_try_coalesce(tsdn_t *tsdn, arena_t *arena, + extent_hooks_t **r_extent_hooks, rtree_ctx_t *rtree_ctx, extents_t *extents, + extent_t *extent, bool *coalesced, bool growing_retained) { + return extent_try_coalesce_impl(tsdn, arena, r_extent_hooks, rtree_ctx, + extents, extent, coalesced, growing_retained, false); +} + +static extent_t * +extent_try_coalesce_large(tsdn_t *tsdn, arena_t *arena, + extent_hooks_t **r_extent_hooks, rtree_ctx_t *rtree_ctx, extents_t *extents, + extent_t *extent, bool *coalesced, bool growing_retained) { + return extent_try_coalesce_impl(tsdn, arena, r_extent_hooks, rtree_ctx, + extents, extent, coalesced, growing_retained, true); +} + /* * Does the metadata management portions of putting an unused extent into the * given extents_t (coalesces, deregisters slab interiors, the heap operations). */ static void extent_record(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extents_t *extents, extent_t *extent, bool growing_retained) { rtree_ctx_t rtree_ctx_fallback; rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); assert((extents_state_get(extents) != extent_state_dirty && extents_state_get(extents) != extent_state_muzzy) || !extent_zeroed_get(extent)); malloc_mutex_lock(tsdn, &extents->mtx); extent_hooks_assure_initialized(arena, r_extent_hooks); - extent_szind_set(extent, NSIZES); + extent_szind_set(extent, SC_NSIZES); if (extent_slab_get(extent)) { extent_interior_deregister(tsdn, rtree_ctx, extent); extent_slab_set(extent, false); } assert(rtree_extent_read(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)extent_base_get(extent), true) == extent); if (!extents->delay_coalesce) { extent = extent_try_coalesce(tsdn, arena, r_extent_hooks, rtree_ctx, extents, extent, NULL, growing_retained); - } else if (extent_size_get(extent) >= LARGE_MINCLASS) { + } else if (extent_size_get(extent) >= SC_LARGE_MINCLASS) { + assert(extents == &arena->extents_dirty); /* Always coalesce large extents eagerly. */ bool coalesced; - size_t prev_size; do { - prev_size = extent_size_get(extent); assert(extent_state_get(extent) == extent_state_active); - extent = extent_try_coalesce(tsdn, arena, + extent = extent_try_coalesce_large(tsdn, arena, r_extent_hooks, rtree_ctx, extents, extent, &coalesced, growing_retained); - } while (coalesced && - extent_size_get(extent) >= prev_size + LARGE_MINCLASS); + } while (coalesced); + if (extent_size_get(extent) >= oversize_threshold) { + /* Shortcut to purge the oversize extent eagerly. */ + malloc_mutex_unlock(tsdn, &extents->mtx); + arena_decay_extent(tsdn, arena, r_extent_hooks, extent); + return; + } } extent_deactivate_locked(tsdn, arena, extents, extent); malloc_mutex_unlock(tsdn, &extents->mtx); } void extent_dalloc_gap(tsdn_t *tsdn, arena_t *arena, extent_t *extent) { extent_hooks_t *extent_hooks = EXTENT_HOOKS_INITIALIZER; witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); if (extent_register(tsdn, extent)) { - extents_leak(tsdn, arena, &extent_hooks, - &arena->extents_retained, extent, false); + extent_dalloc(tsdn, arena, extent); return; } extent_dalloc_wrapper(tsdn, arena, &extent_hooks, extent); } static bool +extent_may_dalloc(void) { + /* With retain enabled, the default dalloc always fails. */ + return !opt_retain; +} + +static bool extent_dalloc_default_impl(void *addr, size_t size) { if (!have_dss || !extent_in_dss(addr)) { return extent_dalloc_mmap(addr, size); } return true; } static bool extent_dalloc_default(extent_hooks_t *extent_hooks, void *addr, size_t size, bool committed, unsigned arena_ind) { return extent_dalloc_default_impl(addr, size); } static bool extent_dalloc_wrapper_try(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent) { bool err; assert(extent_base_get(extent) != NULL); assert(extent_size_get(extent) != 0); witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); extent_addr_set(extent, extent_base_get(extent)); extent_hooks_assure_initialized(arena, r_extent_hooks); /* Try to deallocate. */ if (*r_extent_hooks == &extent_hooks_default) { /* Call directly to propagate tsdn. */ err = extent_dalloc_default_impl(extent_base_get(extent), extent_size_get(extent)); } else { extent_hook_pre_reentrancy(tsdn, arena); err = ((*r_extent_hooks)->dalloc == NULL || (*r_extent_hooks)->dalloc(*r_extent_hooks, extent_base_get(extent), extent_size_get(extent), extent_committed_get(extent), arena_ind_get(arena))); extent_hook_post_reentrancy(tsdn); } if (!err) { extent_dalloc(tsdn, arena, extent); } return err; } void extent_dalloc_wrapper(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent) { assert(extent_dumpable_get(extent)); witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); - /* - * Deregister first to avoid a race with other allocating threads, and - * reregister if deallocation fails. - */ - extent_deregister(tsdn, extent); - if (!extent_dalloc_wrapper_try(tsdn, arena, r_extent_hooks, extent)) { - return; + /* Avoid calling the default extent_dalloc unless have to. */ + if (*r_extent_hooks != &extent_hooks_default || extent_may_dalloc()) { + /* + * Deregister first to avoid a race with other allocating + * threads, and reregister if deallocation fails. + */ + extent_deregister(tsdn, extent); + if (!extent_dalloc_wrapper_try(tsdn, arena, r_extent_hooks, + extent)) { + return; + } + extent_reregister(tsdn, extent); } - extent_reregister(tsdn, extent); if (*r_extent_hooks != &extent_hooks_default) { extent_hook_pre_reentrancy(tsdn, arena); } /* Try to decommit; purge if that fails. */ bool zeroed; if (!extent_committed_get(extent)) { zeroed = true; } else if (!extent_decommit_wrapper(tsdn, arena, r_extent_hooks, extent, 0, extent_size_get(extent))) { zeroed = true; } else if ((*r_extent_hooks)->purge_forced != NULL && !(*r_extent_hooks)->purge_forced(*r_extent_hooks, extent_base_get(extent), extent_size_get(extent), 0, extent_size_get(extent), arena_ind_get(arena))) { zeroed = true; } else if (extent_state_get(extent) == extent_state_muzzy || ((*r_extent_hooks)->purge_lazy != NULL && !(*r_extent_hooks)->purge_lazy(*r_extent_hooks, extent_base_get(extent), extent_size_get(extent), 0, extent_size_get(extent), arena_ind_get(arena)))) { zeroed = false; } else { zeroed = false; } if (*r_extent_hooks != &extent_hooks_default) { extent_hook_post_reentrancy(tsdn); } extent_zeroed_set(extent, zeroed); if (config_prof) { extent_gdump_sub(tsdn, extent); } extent_record(tsdn, arena, r_extent_hooks, &arena->extents_retained, extent, false); } static void extent_destroy_default_impl(void *addr, size_t size) { if (!have_dss || !extent_in_dss(addr)) { pages_unmap(addr, size); } } static void extent_destroy_default(extent_hooks_t *extent_hooks, void *addr, size_t size, bool committed, unsigned arena_ind) { extent_destroy_default_impl(addr, size); } void extent_destroy_wrapper(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent) { assert(extent_base_get(extent) != NULL); assert(extent_size_get(extent) != 0); witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); /* Deregister first to avoid a race with other allocating threads. */ extent_deregister(tsdn, extent); extent_addr_set(extent, extent_base_get(extent)); extent_hooks_assure_initialized(arena, r_extent_hooks); /* Try to destroy; silently fail otherwise. */ if (*r_extent_hooks == &extent_hooks_default) { /* Call directly to propagate tsdn. */ extent_destroy_default_impl(extent_base_get(extent), extent_size_get(extent)); } else if ((*r_extent_hooks)->destroy != NULL) { extent_hook_pre_reentrancy(tsdn, arena); (*r_extent_hooks)->destroy(*r_extent_hooks, extent_base_get(extent), extent_size_get(extent), extent_committed_get(extent), arena_ind_get(arena)); extent_hook_post_reentrancy(tsdn); } extent_dalloc(tsdn, arena, extent); } static bool extent_commit_default(extent_hooks_t *extent_hooks, void *addr, size_t size, size_t offset, size_t length, unsigned arena_ind) { return pages_commit((void *)((uintptr_t)addr + (uintptr_t)offset), length); } static bool extent_commit_impl(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset, size_t length, bool growing_retained) { witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, growing_retained ? 1 : 0); extent_hooks_assure_initialized(arena, r_extent_hooks); if (*r_extent_hooks != &extent_hooks_default) { extent_hook_pre_reentrancy(tsdn, arena); } bool err = ((*r_extent_hooks)->commit == NULL || (*r_extent_hooks)->commit(*r_extent_hooks, extent_base_get(extent), extent_size_get(extent), offset, length, arena_ind_get(arena))); if (*r_extent_hooks != &extent_hooks_default) { extent_hook_post_reentrancy(tsdn); } extent_committed_set(extent, extent_committed_get(extent) || !err); return err; } bool extent_commit_wrapper(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset, size_t length) { return extent_commit_impl(tsdn, arena, r_extent_hooks, extent, offset, length, false); } static bool extent_decommit_default(extent_hooks_t *extent_hooks, void *addr, size_t size, size_t offset, size_t length, unsigned arena_ind) { return pages_decommit((void *)((uintptr_t)addr + (uintptr_t)offset), length); } bool extent_decommit_wrapper(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset, size_t length) { witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, 0); extent_hooks_assure_initialized(arena, r_extent_hooks); if (*r_extent_hooks != &extent_hooks_default) { extent_hook_pre_reentrancy(tsdn, arena); } bool err = ((*r_extent_hooks)->decommit == NULL || (*r_extent_hooks)->decommit(*r_extent_hooks, extent_base_get(extent), extent_size_get(extent), offset, length, arena_ind_get(arena))); if (*r_extent_hooks != &extent_hooks_default) { extent_hook_post_reentrancy(tsdn); } extent_committed_set(extent, extent_committed_get(extent) && err); return err; } #ifdef PAGES_CAN_PURGE_LAZY static bool extent_purge_lazy_default(extent_hooks_t *extent_hooks, void *addr, size_t size, size_t offset, size_t length, unsigned arena_ind) { assert(addr != NULL); assert((offset & PAGE_MASK) == 0); assert(length != 0); assert((length & PAGE_MASK) == 0); return pages_purge_lazy((void *)((uintptr_t)addr + (uintptr_t)offset), length); } #endif static bool extent_purge_lazy_impl(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset, size_t length, bool growing_retained) { witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, growing_retained ? 1 : 0); extent_hooks_assure_initialized(arena, r_extent_hooks); if ((*r_extent_hooks)->purge_lazy == NULL) { return true; } if (*r_extent_hooks != &extent_hooks_default) { extent_hook_pre_reentrancy(tsdn, arena); } bool err = (*r_extent_hooks)->purge_lazy(*r_extent_hooks, extent_base_get(extent), extent_size_get(extent), offset, length, arena_ind_get(arena)); if (*r_extent_hooks != &extent_hooks_default) { extent_hook_post_reentrancy(tsdn); } return err; } bool extent_purge_lazy_wrapper(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset, size_t length) { return extent_purge_lazy_impl(tsdn, arena, r_extent_hooks, extent, offset, length, false); } #ifdef PAGES_CAN_PURGE_FORCED static bool extent_purge_forced_default(extent_hooks_t *extent_hooks, void *addr, size_t size, size_t offset, size_t length, unsigned arena_ind) { assert(addr != NULL); assert((offset & PAGE_MASK) == 0); assert(length != 0); assert((length & PAGE_MASK) == 0); return pages_purge_forced((void *)((uintptr_t)addr + (uintptr_t)offset), length); } #endif static bool extent_purge_forced_impl(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset, size_t length, bool growing_retained) { witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, growing_retained ? 1 : 0); extent_hooks_assure_initialized(arena, r_extent_hooks); if ((*r_extent_hooks)->purge_forced == NULL) { return true; } if (*r_extent_hooks != &extent_hooks_default) { extent_hook_pre_reentrancy(tsdn, arena); } bool err = (*r_extent_hooks)->purge_forced(*r_extent_hooks, extent_base_get(extent), extent_size_get(extent), offset, length, arena_ind_get(arena)); if (*r_extent_hooks != &extent_hooks_default) { extent_hook_post_reentrancy(tsdn); } return err; } bool extent_purge_forced_wrapper(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset, size_t length) { return extent_purge_forced_impl(tsdn, arena, r_extent_hooks, extent, offset, length, false); } -#ifdef JEMALLOC_MAPS_COALESCE static bool extent_split_default(extent_hooks_t *extent_hooks, void *addr, size_t size, size_t size_a, size_t size_b, bool committed, unsigned arena_ind) { - return !maps_coalesce; + if (!maps_coalesce) { + /* + * Without retain, only whole regions can be purged (required by + * MEM_RELEASE on Windows) -- therefore disallow splitting. See + * comments in extent_head_no_merge(). + */ + return !opt_retain; + } + + return false; } -#endif /* * Accepts the extent to split, and the characteristics of each side of the * split. The 'a' parameters go with the 'lead' of the resulting pair of * extents (the lower addressed portion of the split), and the 'b' parameters go * with the trail (the higher addressed portion). This makes 'extent' the lead, * and returns the trail (except in case of error). */ static extent_t * extent_split_impl(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent, size_t size_a, szind_t szind_a, bool slab_a, size_t size_b, szind_t szind_b, bool slab_b, bool growing_retained) { assert(extent_size_get(extent) == size_a + size_b); witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, growing_retained ? 1 : 0); extent_hooks_assure_initialized(arena, r_extent_hooks); if ((*r_extent_hooks)->split == NULL) { return NULL; } extent_t *trail = extent_alloc(tsdn, arena); if (trail == NULL) { goto label_error_a; } extent_init(trail, arena, (void *)((uintptr_t)extent_base_get(extent) + size_a), size_b, slab_b, szind_b, extent_sn_get(extent), extent_state_get(extent), extent_zeroed_get(extent), - extent_committed_get(extent), extent_dumpable_get(extent)); + extent_committed_get(extent), extent_dumpable_get(extent), + EXTENT_NOT_HEAD); rtree_ctx_t rtree_ctx_fallback; rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); rtree_leaf_elm_t *lead_elm_a, *lead_elm_b; { extent_t lead; extent_init(&lead, arena, extent_addr_get(extent), size_a, slab_a, szind_a, extent_sn_get(extent), extent_state_get(extent), extent_zeroed_get(extent), - extent_committed_get(extent), extent_dumpable_get(extent)); + extent_committed_get(extent), extent_dumpable_get(extent), + EXTENT_NOT_HEAD); extent_rtree_leaf_elms_lookup(tsdn, rtree_ctx, &lead, false, true, &lead_elm_a, &lead_elm_b); } rtree_leaf_elm_t *trail_elm_a, *trail_elm_b; extent_rtree_leaf_elms_lookup(tsdn, rtree_ctx, trail, false, true, &trail_elm_a, &trail_elm_b); if (lead_elm_a == NULL || lead_elm_b == NULL || trail_elm_a == NULL || trail_elm_b == NULL) { goto label_error_b; } extent_lock2(tsdn, extent, trail); if (*r_extent_hooks != &extent_hooks_default) { extent_hook_pre_reentrancy(tsdn, arena); } bool err = (*r_extent_hooks)->split(*r_extent_hooks, extent_base_get(extent), size_a + size_b, size_a, size_b, extent_committed_get(extent), arena_ind_get(arena)); if (*r_extent_hooks != &extent_hooks_default) { extent_hook_post_reentrancy(tsdn); } if (err) { goto label_error_c; } extent_size_set(extent, size_a); extent_szind_set(extent, szind_a); extent_rtree_write_acquired(tsdn, lead_elm_a, lead_elm_b, extent, szind_a, slab_a); extent_rtree_write_acquired(tsdn, trail_elm_a, trail_elm_b, trail, szind_b, slab_b); extent_unlock2(tsdn, extent, trail); return trail; label_error_c: extent_unlock2(tsdn, extent, trail); label_error_b: extent_dalloc(tsdn, arena, trail); label_error_a: return NULL; } extent_t * extent_split_wrapper(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent, size_t size_a, szind_t szind_a, bool slab_a, size_t size_b, szind_t szind_b, bool slab_b) { return extent_split_impl(tsdn, arena, r_extent_hooks, extent, size_a, szind_a, slab_a, size_b, szind_b, slab_b, false); } static bool extent_merge_default_impl(void *addr_a, void *addr_b) { - if (!maps_coalesce) { + if (!maps_coalesce && !opt_retain) { return true; } if (have_dss && !extent_dss_mergeable(addr_a, addr_b)) { return true; } return false; } -#ifdef JEMALLOC_MAPS_COALESCE +/* + * Returns true if the given extents can't be merged because of their head bit + * settings. Assumes the second extent has the higher address. + */ static bool +extent_head_no_merge(extent_t *a, extent_t *b) { + assert(extent_base_get(a) < extent_base_get(b)); + /* + * When coalesce is not always allowed (Windows), only merge extents + * from the same VirtualAlloc region under opt.retain (in which case + * MEM_DECOMMIT is utilized for purging). + */ + if (maps_coalesce) { + return false; + } + if (!opt_retain) { + return true; + } + /* If b is a head extent, disallow the cross-region merge. */ + if (extent_is_head_get(b)) { + /* + * Additionally, sn should not overflow with retain; sanity + * check that different regions have unique sn. + */ + assert(extent_sn_comp(a, b) != 0); + return true; + } + assert(extent_sn_comp(a, b) == 0); + + return false; +} + +static bool extent_merge_default(extent_hooks_t *extent_hooks, void *addr_a, size_t size_a, void *addr_b, size_t size_b, bool committed, unsigned arena_ind) { + if (!maps_coalesce) { + tsdn_t *tsdn = tsdn_fetch(); + extent_t *a = iealloc(tsdn, addr_a); + extent_t *b = iealloc(tsdn, addr_b); + if (extent_head_no_merge(a, b)) { + return true; + } + } return extent_merge_default_impl(addr_a, addr_b); } -#endif static bool extent_merge_impl(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *a, extent_t *b, bool growing_retained) { witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn), WITNESS_RANK_CORE, growing_retained ? 1 : 0); + assert(extent_base_get(a) < extent_base_get(b)); extent_hooks_assure_initialized(arena, r_extent_hooks); - if ((*r_extent_hooks)->merge == NULL) { + if ((*r_extent_hooks)->merge == NULL || extent_head_no_merge(a, b)) { return true; } bool err; if (*r_extent_hooks == &extent_hooks_default) { /* Call directly to propagate tsdn. */ err = extent_merge_default_impl(extent_base_get(a), extent_base_get(b)); } else { extent_hook_pre_reentrancy(tsdn, arena); err = (*r_extent_hooks)->merge(*r_extent_hooks, extent_base_get(a), extent_size_get(a), extent_base_get(b), extent_size_get(b), extent_committed_get(a), arena_ind_get(arena)); extent_hook_post_reentrancy(tsdn); } if (err) { return true; } /* * The rtree writes must happen while all the relevant elements are * owned, so the following code uses decomposed helper functions rather * than extent_{,de}register() to do things in the right order. */ rtree_ctx_t rtree_ctx_fallback; rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); rtree_leaf_elm_t *a_elm_a, *a_elm_b, *b_elm_a, *b_elm_b; extent_rtree_leaf_elms_lookup(tsdn, rtree_ctx, a, true, false, &a_elm_a, &a_elm_b); extent_rtree_leaf_elms_lookup(tsdn, rtree_ctx, b, true, false, &b_elm_a, &b_elm_b); extent_lock2(tsdn, a, b); if (a_elm_b != NULL) { rtree_leaf_elm_write(tsdn, &extents_rtree, a_elm_b, NULL, - NSIZES, false); + SC_NSIZES, false); } if (b_elm_b != NULL) { rtree_leaf_elm_write(tsdn, &extents_rtree, b_elm_a, NULL, - NSIZES, false); + SC_NSIZES, false); } else { b_elm_b = b_elm_a; } extent_size_set(a, extent_size_get(a) + extent_size_get(b)); - extent_szind_set(a, NSIZES); + extent_szind_set(a, SC_NSIZES); extent_sn_set(a, (extent_sn_get(a) < extent_sn_get(b)) ? extent_sn_get(a) : extent_sn_get(b)); extent_zeroed_set(a, extent_zeroed_get(a) && extent_zeroed_get(b)); - extent_rtree_write_acquired(tsdn, a_elm_a, b_elm_b, a, NSIZES, false); + extent_rtree_write_acquired(tsdn, a_elm_a, b_elm_b, a, SC_NSIZES, + false); extent_unlock2(tsdn, a, b); extent_dalloc(tsdn, extent_arena_get(b), b); return false; } bool extent_merge_wrapper(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *a, extent_t *b) { return extent_merge_impl(tsdn, arena, r_extent_hooks, a, b, false); } bool extent_boot(void) { if (rtree_new(&extents_rtree, true)) { return true; } if (mutex_pool_init(&extent_mutex_pool, "extent_mutex_pool", WITNESS_RANK_EXTENT_POOL)) { return true; } if (have_dss) { extent_dss_boot(); } return false; +} + +void +extent_util_stats_get(tsdn_t *tsdn, const void *ptr, + size_t *nfree, size_t *nregs, size_t *size) { + assert(ptr != NULL && nfree != NULL && nregs != NULL && size != NULL); + + const extent_t *extent = iealloc(tsdn, ptr); + if (unlikely(extent == NULL)) { + *nfree = *nregs = *size = 0; + return; + } + + *size = extent_size_get(extent); + if (!extent_slab_get(extent)) { + *nfree = 0; + *nregs = 1; + } else { + *nfree = extent_nfree_get(extent); + *nregs = bin_infos[extent_szind_get(extent)].nregs; + assert(*nfree <= *nregs); + assert(*nfree * extent_usize_get(extent) <= *size); + } +} + +void +extent_util_stats_verbose_get(tsdn_t *tsdn, const void *ptr, + size_t *nfree, size_t *nregs, size_t *size, + size_t *bin_nfree, size_t *bin_nregs, void **slabcur_addr) { + assert(ptr != NULL && nfree != NULL && nregs != NULL && size != NULL + && bin_nfree != NULL && bin_nregs != NULL && slabcur_addr != NULL); + + const extent_t *extent = iealloc(tsdn, ptr); + if (unlikely(extent == NULL)) { + *nfree = *nregs = *size = *bin_nfree = *bin_nregs = 0; + *slabcur_addr = NULL; + return; + } + + *size = extent_size_get(extent); + if (!extent_slab_get(extent)) { + *nfree = *bin_nfree = *bin_nregs = 0; + *nregs = 1; + *slabcur_addr = NULL; + return; + } + + *nfree = extent_nfree_get(extent); + const szind_t szind = extent_szind_get(extent); + *nregs = bin_infos[szind].nregs; + assert(*nfree <= *nregs); + assert(*nfree * extent_usize_get(extent) <= *size); + + const arena_t *arena = extent_arena_get(extent); + assert(arena != NULL); + const unsigned binshard = extent_binshard_get(extent); + bin_t *bin = &arena->bins[szind].bin_shards[binshard]; + + malloc_mutex_lock(tsdn, &bin->lock); + if (config_stats) { + *bin_nregs = *nregs * bin->stats.curslabs; + assert(*bin_nregs >= bin->stats.curregs); + *bin_nfree = *bin_nregs - bin->stats.curregs; + } else { + *bin_nfree = *bin_nregs = 0; + } + *slabcur_addr = extent_addr_get(bin->slabcur); + assert(*slabcur_addr != NULL); + malloc_mutex_unlock(tsdn, &bin->lock); } Index: head/contrib/jemalloc/src/extent_dss.c =================================================================== --- head/contrib/jemalloc/src/extent_dss.c (revision 360232) +++ head/contrib/jemalloc/src/extent_dss.c (revision 360233) @@ -1,270 +1,271 @@ #define JEMALLOC_EXTENT_DSS_C_ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/jemalloc_internal_includes.h" #include "jemalloc/internal/assert.h" #include "jemalloc/internal/extent_dss.h" #include "jemalloc/internal/spin.h" /******************************************************************************/ /* Data. */ const char *opt_dss = DSS_DEFAULT; const char *dss_prec_names[] = { "disabled", "primary", "secondary", "N/A" }; /* * Current dss precedence default, used when creating new arenas. NB: This is * stored as unsigned rather than dss_prec_t because in principle there's no * guarantee that sizeof(dss_prec_t) is the same as sizeof(unsigned), and we use * atomic operations to synchronize the setting. */ static atomic_u_t dss_prec_default = ATOMIC_INIT( (unsigned)DSS_PREC_DEFAULT); /* Base address of the DSS. */ static void *dss_base; /* Atomic boolean indicating whether a thread is currently extending DSS. */ static atomic_b_t dss_extending; /* Atomic boolean indicating whether the DSS is exhausted. */ static atomic_b_t dss_exhausted; /* Atomic current upper limit on DSS addresses. */ static atomic_p_t dss_max; /******************************************************************************/ static void * extent_dss_sbrk(intptr_t increment) { #ifdef JEMALLOC_DSS return sbrk(increment); #else not_implemented(); return NULL; #endif } dss_prec_t extent_dss_prec_get(void) { dss_prec_t ret; if (!have_dss) { return dss_prec_disabled; } ret = (dss_prec_t)atomic_load_u(&dss_prec_default, ATOMIC_ACQUIRE); return ret; } bool extent_dss_prec_set(dss_prec_t dss_prec) { if (!have_dss) { return (dss_prec != dss_prec_disabled); } atomic_store_u(&dss_prec_default, (unsigned)dss_prec, ATOMIC_RELEASE); return false; } static void extent_dss_extending_start(void) { spin_t spinner = SPIN_INITIALIZER; while (true) { bool expected = false; if (atomic_compare_exchange_weak_b(&dss_extending, &expected, true, ATOMIC_ACQ_REL, ATOMIC_RELAXED)) { break; } spin_adaptive(&spinner); } } static void extent_dss_extending_finish(void) { assert(atomic_load_b(&dss_extending, ATOMIC_RELAXED)); atomic_store_b(&dss_extending, false, ATOMIC_RELEASE); } static void * extent_dss_max_update(void *new_addr) { /* * Get the current end of the DSS as max_cur and assure that dss_max is * up to date. */ void *max_cur = extent_dss_sbrk(0); if (max_cur == (void *)-1) { return NULL; } atomic_store_p(&dss_max, max_cur, ATOMIC_RELEASE); /* Fixed new_addr can only be supported if it is at the edge of DSS. */ if (new_addr != NULL && max_cur != new_addr) { return NULL; } return max_cur; } void * extent_alloc_dss(tsdn_t *tsdn, arena_t *arena, void *new_addr, size_t size, size_t alignment, bool *zero, bool *commit) { extent_t *gap; cassert(have_dss); assert(size > 0); - assert(alignment > 0); + assert(alignment == ALIGNMENT_CEILING(alignment, PAGE)); /* * sbrk() uses a signed increment argument, so take care not to * interpret a large allocation request as a negative increment. */ if ((intptr_t)size < 0) { return NULL; } gap = extent_alloc(tsdn, arena); if (gap == NULL) { return NULL; } extent_dss_extending_start(); if (!atomic_load_b(&dss_exhausted, ATOMIC_ACQUIRE)) { /* * The loop is necessary to recover from races with other * threads that are using the DSS for something other than * malloc. */ while (true) { void *max_cur = extent_dss_max_update(new_addr); if (max_cur == NULL) { goto label_oom; } /* * Compute how much page-aligned gap space (if any) is * necessary to satisfy alignment. This space can be * recycled for later use. */ void *gap_addr_page = (void *)(PAGE_CEILING( (uintptr_t)max_cur)); void *ret = (void *)ALIGNMENT_CEILING( (uintptr_t)gap_addr_page, alignment); size_t gap_size_page = (uintptr_t)ret - (uintptr_t)gap_addr_page; if (gap_size_page != 0) { extent_init(gap, arena, gap_addr_page, - gap_size_page, false, NSIZES, + gap_size_page, false, SC_NSIZES, arena_extent_sn_next(arena), - extent_state_active, false, true, true); + extent_state_active, false, true, true, + EXTENT_NOT_HEAD); } /* * Compute the address just past the end of the desired * allocation space. */ void *dss_next = (void *)((uintptr_t)ret + size); if ((uintptr_t)ret < (uintptr_t)max_cur || (uintptr_t)dss_next < (uintptr_t)max_cur) { goto label_oom; /* Wrap-around. */ } /* Compute the increment, including subpage bytes. */ void *gap_addr_subpage = max_cur; size_t gap_size_subpage = (uintptr_t)ret - (uintptr_t)gap_addr_subpage; intptr_t incr = gap_size_subpage + size; assert((uintptr_t)max_cur + incr == (uintptr_t)ret + size); /* Try to allocate. */ void *dss_prev = extent_dss_sbrk(incr); if (dss_prev == max_cur) { /* Success. */ atomic_store_p(&dss_max, dss_next, ATOMIC_RELEASE); extent_dss_extending_finish(); if (gap_size_page != 0) { extent_dalloc_gap(tsdn, arena, gap); } else { extent_dalloc(tsdn, arena, gap); } if (!*commit) { *commit = pages_decommit(ret, size); } if (*zero && *commit) { extent_hooks_t *extent_hooks = EXTENT_HOOKS_INITIALIZER; extent_t extent; extent_init(&extent, arena, ret, size, - size, false, NSIZES, + size, false, SC_NSIZES, extent_state_active, false, true, - true); + true, EXTENT_NOT_HEAD); if (extent_purge_forced_wrapper(tsdn, arena, &extent_hooks, &extent, 0, size)) { memset(ret, 0, size); } } return ret; } /* * Failure, whether due to OOM or a race with a raw * sbrk() call from outside the allocator. */ if (dss_prev == (void *)-1) { /* OOM. */ atomic_store_b(&dss_exhausted, true, ATOMIC_RELEASE); goto label_oom; } } } label_oom: extent_dss_extending_finish(); extent_dalloc(tsdn, arena, gap); return NULL; } static bool extent_in_dss_helper(void *addr, void *max) { return ((uintptr_t)addr >= (uintptr_t)dss_base && (uintptr_t)addr < (uintptr_t)max); } bool extent_in_dss(void *addr) { cassert(have_dss); return extent_in_dss_helper(addr, atomic_load_p(&dss_max, ATOMIC_ACQUIRE)); } bool extent_dss_mergeable(void *addr_a, void *addr_b) { void *max; cassert(have_dss); if ((uintptr_t)addr_a < (uintptr_t)dss_base && (uintptr_t)addr_b < (uintptr_t)dss_base) { return true; } max = atomic_load_p(&dss_max, ATOMIC_ACQUIRE); return (extent_in_dss_helper(addr_a, max) == extent_in_dss_helper(addr_b, max)); } void extent_dss_boot(void) { cassert(have_dss); dss_base = extent_dss_sbrk(0); atomic_store_b(&dss_extending, false, ATOMIC_RELAXED); atomic_store_b(&dss_exhausted, dss_base == (void *)-1, ATOMIC_RELAXED); atomic_store_p(&dss_max, dss_base, ATOMIC_RELAXED); } /******************************************************************************/ Index: head/contrib/jemalloc/src/extent_mmap.c =================================================================== --- head/contrib/jemalloc/src/extent_mmap.c (revision 360232) +++ head/contrib/jemalloc/src/extent_mmap.c (revision 360233) @@ -1,42 +1,42 @@ #define JEMALLOC_EXTENT_MMAP_C_ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/jemalloc_internal_includes.h" #include "jemalloc/internal/assert.h" #include "jemalloc/internal/extent_mmap.h" /******************************************************************************/ /* Data. */ bool opt_retain = #ifdef JEMALLOC_RETAIN true #else false #endif ; /******************************************************************************/ void * extent_alloc_mmap(void *new_addr, size_t size, size_t alignment, bool *zero, bool *commit) { - void *ret = pages_map(new_addr, size, ALIGNMENT_CEILING(alignment, - PAGE), commit); + assert(alignment == ALIGNMENT_CEILING(alignment, PAGE)); + void *ret = pages_map(new_addr, size, alignment, commit); if (ret == NULL) { return NULL; } assert(ret != NULL); if (*commit) { *zero = true; } return ret; } bool extent_dalloc_mmap(void *addr, size_t size) { if (!opt_retain) { pages_unmap(addr, size); } return opt_retain; } Index: head/contrib/jemalloc/src/hook.c =================================================================== --- head/contrib/jemalloc/src/hook.c (nonexistent) +++ head/contrib/jemalloc/src/hook.c (revision 360233) @@ -0,0 +1,195 @@ +#include "jemalloc/internal/jemalloc_preamble.h" + +#include "jemalloc/internal/hook.h" + +#include "jemalloc/internal/atomic.h" +#include "jemalloc/internal/mutex.h" +#include "jemalloc/internal/seq.h" + +typedef struct hooks_internal_s hooks_internal_t; +struct hooks_internal_s { + hooks_t hooks; + bool in_use; +}; + +seq_define(hooks_internal_t, hooks) + +static atomic_u_t nhooks = ATOMIC_INIT(0); +static seq_hooks_t hooks[HOOK_MAX]; +static malloc_mutex_t hooks_mu; + +bool +hook_boot() { + return malloc_mutex_init(&hooks_mu, "hooks", WITNESS_RANK_HOOK, + malloc_mutex_rank_exclusive); +} + +static void * +hook_install_locked(hooks_t *to_install) { + hooks_internal_t hooks_internal; + for (int i = 0; i < HOOK_MAX; i++) { + bool success = seq_try_load_hooks(&hooks_internal, &hooks[i]); + /* We hold mu; no concurrent access. */ + assert(success); + if (!hooks_internal.in_use) { + hooks_internal.hooks = *to_install; + hooks_internal.in_use = true; + seq_store_hooks(&hooks[i], &hooks_internal); + atomic_store_u(&nhooks, + atomic_load_u(&nhooks, ATOMIC_RELAXED) + 1, + ATOMIC_RELAXED); + return &hooks[i]; + } + } + return NULL; +} + +void * +hook_install(tsdn_t *tsdn, hooks_t *to_install) { + malloc_mutex_lock(tsdn, &hooks_mu); + void *ret = hook_install_locked(to_install); + if (ret != NULL) { + tsd_global_slow_inc(tsdn); + } + malloc_mutex_unlock(tsdn, &hooks_mu); + return ret; +} + +static void +hook_remove_locked(seq_hooks_t *to_remove) { + hooks_internal_t hooks_internal; + bool success = seq_try_load_hooks(&hooks_internal, to_remove); + /* We hold mu; no concurrent access. */ + assert(success); + /* Should only remove hooks that were added. */ + assert(hooks_internal.in_use); + hooks_internal.in_use = false; + seq_store_hooks(to_remove, &hooks_internal); + atomic_store_u(&nhooks, atomic_load_u(&nhooks, ATOMIC_RELAXED) - 1, + ATOMIC_RELAXED); +} + +void +hook_remove(tsdn_t *tsdn, void *opaque) { + if (config_debug) { + char *hooks_begin = (char *)&hooks[0]; + char *hooks_end = (char *)&hooks[HOOK_MAX]; + char *hook = (char *)opaque; + assert(hooks_begin <= hook && hook < hooks_end + && (hook - hooks_begin) % sizeof(seq_hooks_t) == 0); + } + malloc_mutex_lock(tsdn, &hooks_mu); + hook_remove_locked((seq_hooks_t *)opaque); + tsd_global_slow_dec(tsdn); + malloc_mutex_unlock(tsdn, &hooks_mu); +} + +#define FOR_EACH_HOOK_BEGIN(hooks_internal_ptr) \ +for (int for_each_hook_counter = 0; \ + for_each_hook_counter < HOOK_MAX; \ + for_each_hook_counter++) { \ + bool for_each_hook_success = seq_try_load_hooks( \ + (hooks_internal_ptr), &hooks[for_each_hook_counter]); \ + if (!for_each_hook_success) { \ + continue; \ + } \ + if (!(hooks_internal_ptr)->in_use) { \ + continue; \ + } +#define FOR_EACH_HOOK_END \ +} + +static bool * +hook_reentrantp() { + /* + * We prevent user reentrancy within hooks. This is basically just a + * thread-local bool that triggers an early-exit. + * + * We don't fold in_hook into reentrancy. There are two reasons for + * this: + * - Right now, we turn on reentrancy during things like extent hook + * execution. Allocating during extent hooks is not officially + * supported, but we don't want to break it for the time being. These + * sorts of allocations should probably still be hooked, though. + * - If a hook allocates, we may want it to be relatively fast (after + * all, it executes on every allocator operation). Turning on + * reentrancy is a fairly heavyweight mode (disabling tcache, + * redirecting to arena 0, etc.). It's possible we may one day want + * to turn on reentrant mode here, if it proves too difficult to keep + * this working. But that's fairly easy for us to see; OTOH, people + * not using hooks because they're too slow is easy for us to miss. + * + * The tricky part is + * that this code might get invoked even if we don't have access to tsd. + * This function mimics getting a pointer to thread-local data, except + * that it might secretly return a pointer to some global data if we + * know that the caller will take the early-exit path. + * If we return a bool that indicates that we are reentrant, then the + * caller will go down the early exit path, leaving the global + * untouched. + */ + static bool in_hook_global = true; + tsdn_t *tsdn = tsdn_fetch(); + tcache_t *tcache = tsdn_tcachep_get(tsdn); + if (tcache != NULL) { + return &tcache->in_hook; + } + return &in_hook_global; +} + +#define HOOK_PROLOGUE \ + if (likely(atomic_load_u(&nhooks, ATOMIC_RELAXED) == 0)) { \ + return; \ + } \ + bool *in_hook = hook_reentrantp(); \ + if (*in_hook) { \ + return; \ + } \ + *in_hook = true; + +#define HOOK_EPILOGUE \ + *in_hook = false; + +void +hook_invoke_alloc(hook_alloc_t type, void *result, uintptr_t result_raw, + uintptr_t args_raw[3]) { + HOOK_PROLOGUE + + hooks_internal_t hook; + FOR_EACH_HOOK_BEGIN(&hook) + hook_alloc h = hook.hooks.alloc_hook; + if (h != NULL) { + h(hook.hooks.extra, type, result, result_raw, args_raw); + } + FOR_EACH_HOOK_END + + HOOK_EPILOGUE +} + +void +hook_invoke_dalloc(hook_dalloc_t type, void *address, uintptr_t args_raw[3]) { + HOOK_PROLOGUE + hooks_internal_t hook; + FOR_EACH_HOOK_BEGIN(&hook) + hook_dalloc h = hook.hooks.dalloc_hook; + if (h != NULL) { + h(hook.hooks.extra, type, address, args_raw); + } + FOR_EACH_HOOK_END + HOOK_EPILOGUE +} + +void +hook_invoke_expand(hook_expand_t type, void *address, size_t old_usize, + size_t new_usize, uintptr_t result_raw, uintptr_t args_raw[4]) { + HOOK_PROLOGUE + hooks_internal_t hook; + FOR_EACH_HOOK_BEGIN(&hook) + hook_expand h = hook.hooks.expand_hook; + if (h != NULL) { + h(hook.hooks.extra, type, address, old_usize, new_usize, + result_raw, args_raw); + } + FOR_EACH_HOOK_END + HOOK_EPILOGUE +} Property changes on: head/contrib/jemalloc/src/hook.c ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/jemalloc/src/jemalloc.c =================================================================== --- head/contrib/jemalloc/src/jemalloc.c (revision 360232) +++ head/contrib/jemalloc/src/jemalloc.c (revision 360233) @@ -1,3419 +1,4011 @@ #define JEMALLOC_C_ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/jemalloc_internal_includes.h" #include "jemalloc/internal/assert.h" #include "jemalloc/internal/atomic.h" #include "jemalloc/internal/ctl.h" #include "jemalloc/internal/extent_dss.h" #include "jemalloc/internal/extent_mmap.h" +#include "jemalloc/internal/hook.h" #include "jemalloc/internal/jemalloc_internal_types.h" #include "jemalloc/internal/log.h" #include "jemalloc/internal/malloc_io.h" #include "jemalloc/internal/mutex.h" #include "jemalloc/internal/rtree.h" -#include "jemalloc/internal/size_classes.h" +#include "jemalloc/internal/safety_check.h" +#include "jemalloc/internal/sc.h" #include "jemalloc/internal/spin.h" #include "jemalloc/internal/sz.h" #include "jemalloc/internal/ticker.h" #include "jemalloc/internal/util.h" /******************************************************************************/ /* Data. */ /* Work around : */ const char *__malloc_options_1_0 = NULL; __sym_compat(_malloc_options, __malloc_options_1_0, FBSD_1.0); /* Runtime configuration options. */ const char *je_malloc_conf #ifndef _WIN32 JEMALLOC_ATTR(weak) #endif ; bool opt_abort = #ifdef JEMALLOC_DEBUG true #else false #endif ; bool opt_abort_conf = #ifdef JEMALLOC_DEBUG true #else false #endif ; +/* Intentionally default off, even with debug builds. */ +bool opt_confirm_conf = false; const char *opt_junk = #if (defined(JEMALLOC_DEBUG) && defined(JEMALLOC_FILL)) "true" #else "false" #endif ; bool opt_junk_alloc = #if (defined(JEMALLOC_DEBUG) && defined(JEMALLOC_FILL)) true #else false #endif ; bool opt_junk_free = #if (defined(JEMALLOC_DEBUG) && defined(JEMALLOC_FILL)) true #else false #endif ; bool opt_utrace = false; bool opt_xmalloc = false; bool opt_zero = false; unsigned opt_narenas = 0; unsigned ncpus; /* Protects arenas initialization. */ malloc_mutex_t arenas_lock; /* * Arenas that are used to service external requests. Not all elements of the * arenas array are necessarily used; arenas are created lazily as needed. * * arenas[0..narenas_auto) are used for automatic multiplexing of threads and * arenas. arenas[narenas_auto..narenas_total) are only used if the application * takes some action to create them and allocate from them. * * Points to an arena_t. */ JEMALLOC_ALIGNED(CACHELINE) atomic_p_t arenas[MALLOCX_ARENA_LIMIT]; static atomic_u_t narenas_total; /* Use narenas_total_*(). */ -static arena_t *a0; /* arenas[0]; read-only after initialization. */ -unsigned narenas_auto; /* Read-only after initialization. */ +/* Below three are read-only after initialization. */ +static arena_t *a0; /* arenas[0]. */ +unsigned narenas_auto; +unsigned manual_arena_base; typedef enum { malloc_init_uninitialized = 3, malloc_init_a0_initialized = 2, malloc_init_recursible = 1, malloc_init_initialized = 0 /* Common case --> jnz. */ } malloc_init_t; static malloc_init_t malloc_init_state = malloc_init_uninitialized; /* False should be the common case. Set to true to trigger initialization. */ bool malloc_slow = true; /* When malloc_slow is true, set the corresponding bits for sanity check. */ enum { flag_opt_junk_alloc = (1U), flag_opt_junk_free = (1U << 1), flag_opt_zero = (1U << 2), flag_opt_utrace = (1U << 3), flag_opt_xmalloc = (1U << 4) }; static uint8_t malloc_slow_flags; #ifdef JEMALLOC_THREADED_INIT /* Used to let the initializing thread recursively allocate. */ # define NO_INITIALIZER ((unsigned long)0) # define INITIALIZER pthread_self() # define IS_INITIALIZER (malloc_initializer == pthread_self()) static pthread_t malloc_initializer = NO_INITIALIZER; #else # define NO_INITIALIZER false # define INITIALIZER true # define IS_INITIALIZER malloc_initializer static bool malloc_initializer = NO_INITIALIZER; #endif /* Used to avoid initialization races. */ #ifdef _WIN32 #if _WIN32_WINNT >= 0x0600 static malloc_mutex_t init_lock = SRWLOCK_INIT; #else static malloc_mutex_t init_lock; static bool init_lock_initialized = false; JEMALLOC_ATTR(constructor) static void WINAPI _init_init_lock(void) { /* * If another constructor in the same binary is using mallctl to e.g. * set up extent hooks, it may end up running before this one, and * malloc_init_hard will crash trying to lock the uninitialized lock. So * we force an initialization of the lock in malloc_init_hard as well. * We don't try to care about atomicity of the accessed to the * init_lock_initialized boolean, since it really only matters early in * the process creation, before any separate thread normally starts * doing anything. */ if (!init_lock_initialized) { malloc_mutex_init(&init_lock, "init", WITNESS_RANK_INIT, malloc_mutex_rank_exclusive); } init_lock_initialized = true; } #ifdef _MSC_VER # pragma section(".CRT$XCU", read) JEMALLOC_SECTION(".CRT$XCU") JEMALLOC_ATTR(used) static const void (WINAPI *init_init_lock)(void) = _init_init_lock; #endif #endif #else static malloc_mutex_t init_lock = MALLOC_MUTEX_INITIALIZER; #endif typedef struct { void *p; /* Input pointer (as in realloc(p, s)). */ size_t s; /* Request size. */ void *r; /* Result pointer. */ } malloc_utrace_t; #ifdef JEMALLOC_UTRACE # define UTRACE(a, b, c) do { \ if (unlikely(opt_utrace)) { \ int utrace_serrno = errno; \ malloc_utrace_t ut; \ ut.p = (a); \ ut.s = (b); \ ut.r = (c); \ utrace(&ut, sizeof(ut)); \ errno = utrace_serrno; \ } \ } while (0) #else # define UTRACE(a, b, c) #endif /* Whether encountered any invalid config options. */ static bool had_conf_error = false; /******************************************************************************/ /* * Function prototypes for static functions that are referenced prior to * definition. */ static bool malloc_init_hard_a0(void); static bool malloc_init_hard(void); /******************************************************************************/ /* * Begin miscellaneous support functions. */ bool malloc_initialized(void) { return (malloc_init_state == malloc_init_initialized); } JEMALLOC_ALWAYS_INLINE bool malloc_init_a0(void) { if (unlikely(malloc_init_state == malloc_init_uninitialized)) { return malloc_init_hard_a0(); } return false; } JEMALLOC_ALWAYS_INLINE bool malloc_init(void) { if (unlikely(!malloc_initialized()) && malloc_init_hard()) { return true; } return false; } /* * The a0*() functions are used instead of i{d,}alloc() in situations that * cannot tolerate TLS variable access. */ static void * a0ialloc(size_t size, bool zero, bool is_internal) { if (unlikely(malloc_init_a0())) { return NULL; } return iallocztm(TSDN_NULL, size, sz_size2index(size), zero, NULL, is_internal, arena_get(TSDN_NULL, 0, true), true); } static void a0idalloc(void *ptr, bool is_internal) { idalloctm(TSDN_NULL, ptr, NULL, NULL, is_internal, true); } void * a0malloc(size_t size) { return a0ialloc(size, false, true); } void a0dalloc(void *ptr) { a0idalloc(ptr, true); } /* * FreeBSD's libc uses the bootstrap_*() functions in bootstrap-senstive * situations that cannot tolerate TLS variable access (TLS allocation and very * early internal data structure initialization). */ void * bootstrap_malloc(size_t size) { if (unlikely(size == 0)) { size = 1; } return a0ialloc(size, false, false); } void * bootstrap_calloc(size_t num, size_t size) { size_t num_size; num_size = num * size; if (unlikely(num_size == 0)) { assert(num == 0 || size == 0); num_size = 1; } return a0ialloc(num_size, true, false); } void bootstrap_free(void *ptr) { if (unlikely(ptr == NULL)) { return; } a0idalloc(ptr, false); } void arena_set(unsigned ind, arena_t *arena) { atomic_store_p(&arenas[ind], arena, ATOMIC_RELEASE); } static void narenas_total_set(unsigned narenas) { atomic_store_u(&narenas_total, narenas, ATOMIC_RELEASE); } static void narenas_total_inc(void) { atomic_fetch_add_u(&narenas_total, 1, ATOMIC_RELEASE); } unsigned narenas_total_get(void) { return atomic_load_u(&narenas_total, ATOMIC_ACQUIRE); } /* Create a new arena and insert it into the arenas array at index ind. */ static arena_t * arena_init_locked(tsdn_t *tsdn, unsigned ind, extent_hooks_t *extent_hooks) { arena_t *arena; assert(ind <= narenas_total_get()); if (ind >= MALLOCX_ARENA_LIMIT) { return NULL; } if (ind == narenas_total_get()) { narenas_total_inc(); } /* * Another thread may have already initialized arenas[ind] if it's an * auto arena. */ arena = arena_get(tsdn, ind, false); if (arena != NULL) { - assert(ind < narenas_auto); + assert(arena_is_auto(arena)); return arena; } /* Actually initialize the arena. */ arena = arena_new(tsdn, ind, extent_hooks); return arena; } static void arena_new_create_background_thread(tsdn_t *tsdn, unsigned ind) { if (ind == 0) { return; } - if (have_background_thread) { - bool err; - malloc_mutex_lock(tsdn, &background_thread_lock); - err = background_thread_create(tsdn_tsd(tsdn), ind); - malloc_mutex_unlock(tsdn, &background_thread_lock); - if (err) { + /* + * Avoid creating a new background thread just for the huge arena, which + * purges eagerly by default. + */ + if (have_background_thread && !arena_is_huge(ind)) { + if (background_thread_create(tsdn_tsd(tsdn), ind)) { malloc_printf(": error in background thread " "creation for arena %u. Abort.\n", ind); abort(); } } } arena_t * arena_init(tsdn_t *tsdn, unsigned ind, extent_hooks_t *extent_hooks) { arena_t *arena; malloc_mutex_lock(tsdn, &arenas_lock); arena = arena_init_locked(tsdn, ind, extent_hooks); malloc_mutex_unlock(tsdn, &arenas_lock); arena_new_create_background_thread(tsdn, ind); return arena; } static void arena_bind(tsd_t *tsd, unsigned ind, bool internal) { arena_t *arena = arena_get(tsd_tsdn(tsd), ind, false); arena_nthreads_inc(arena, internal); if (internal) { tsd_iarena_set(tsd, arena); } else { tsd_arena_set(tsd, arena); + unsigned shard = atomic_fetch_add_u(&arena->binshard_next, 1, + ATOMIC_RELAXED); + tsd_binshards_t *bins = tsd_binshardsp_get(tsd); + for (unsigned i = 0; i < SC_NBINS; i++) { + assert(bin_infos[i].n_shards > 0 && + bin_infos[i].n_shards <= BIN_SHARDS_MAX); + bins->binshard[i] = shard % bin_infos[i].n_shards; + } } } void arena_migrate(tsd_t *tsd, unsigned oldind, unsigned newind) { arena_t *oldarena, *newarena; oldarena = arena_get(tsd_tsdn(tsd), oldind, false); newarena = arena_get(tsd_tsdn(tsd), newind, false); arena_nthreads_dec(oldarena, false); arena_nthreads_inc(newarena, false); tsd_arena_set(tsd, newarena); } static void arena_unbind(tsd_t *tsd, unsigned ind, bool internal) { arena_t *arena; arena = arena_get(tsd_tsdn(tsd), ind, false); arena_nthreads_dec(arena, internal); if (internal) { tsd_iarena_set(tsd, NULL); } else { tsd_arena_set(tsd, NULL); } } arena_tdata_t * arena_tdata_get_hard(tsd_t *tsd, unsigned ind) { arena_tdata_t *tdata, *arenas_tdata_old; arena_tdata_t *arenas_tdata = tsd_arenas_tdata_get(tsd); unsigned narenas_tdata_old, i; unsigned narenas_tdata = tsd_narenas_tdata_get(tsd); unsigned narenas_actual = narenas_total_get(); /* * Dissociate old tdata array (and set up for deallocation upon return) * if it's too small. */ if (arenas_tdata != NULL && narenas_tdata < narenas_actual) { arenas_tdata_old = arenas_tdata; narenas_tdata_old = narenas_tdata; arenas_tdata = NULL; narenas_tdata = 0; tsd_arenas_tdata_set(tsd, arenas_tdata); tsd_narenas_tdata_set(tsd, narenas_tdata); } else { arenas_tdata_old = NULL; narenas_tdata_old = 0; } /* Allocate tdata array if it's missing. */ if (arenas_tdata == NULL) { bool *arenas_tdata_bypassp = tsd_arenas_tdata_bypassp_get(tsd); narenas_tdata = (ind < narenas_actual) ? narenas_actual : ind+1; if (tsd_nominal(tsd) && !*arenas_tdata_bypassp) { *arenas_tdata_bypassp = true; arenas_tdata = (arena_tdata_t *)a0malloc( sizeof(arena_tdata_t) * narenas_tdata); *arenas_tdata_bypassp = false; } if (arenas_tdata == NULL) { tdata = NULL; goto label_return; } assert(tsd_nominal(tsd) && !*arenas_tdata_bypassp); tsd_arenas_tdata_set(tsd, arenas_tdata); tsd_narenas_tdata_set(tsd, narenas_tdata); } /* * Copy to tdata array. It's possible that the actual number of arenas * has increased since narenas_total_get() was called above, but that * causes no correctness issues unless two threads concurrently execute * the arenas.create mallctl, which we trust mallctl synchronization to * prevent. */ /* Copy/initialize tickers. */ for (i = 0; i < narenas_actual; i++) { if (i < narenas_tdata_old) { ticker_copy(&arenas_tdata[i].decay_ticker, &arenas_tdata_old[i].decay_ticker); } else { ticker_init(&arenas_tdata[i].decay_ticker, DECAY_NTICKS_PER_UPDATE); } } if (narenas_tdata > narenas_actual) { memset(&arenas_tdata[narenas_actual], 0, sizeof(arena_tdata_t) * (narenas_tdata - narenas_actual)); } /* Read the refreshed tdata array. */ tdata = &arenas_tdata[ind]; label_return: if (arenas_tdata_old != NULL) { a0dalloc(arenas_tdata_old); } return tdata; } /* Slow path, called only by arena_choose(). */ arena_t * arena_choose_hard(tsd_t *tsd, bool internal) { arena_t *ret JEMALLOC_CC_SILENCE_INIT(NULL); if (have_percpu_arena && PERCPU_ARENA_ENABLED(opt_percpu_arena)) { unsigned choose = percpu_arena_choose(); ret = arena_get(tsd_tsdn(tsd), choose, true); assert(ret != NULL); arena_bind(tsd, arena_ind_get(ret), false); arena_bind(tsd, arena_ind_get(ret), true); return ret; } if (narenas_auto > 1) { unsigned i, j, choose[2], first_null; bool is_new_arena[2]; /* * Determine binding for both non-internal and internal * allocation. * * choose[0]: For application allocation. * choose[1]: For internal metadata allocation. */ for (j = 0; j < 2; j++) { choose[j] = 0; is_new_arena[j] = false; } first_null = narenas_auto; malloc_mutex_lock(tsd_tsdn(tsd), &arenas_lock); assert(arena_get(tsd_tsdn(tsd), 0, false) != NULL); for (i = 1; i < narenas_auto; i++) { if (arena_get(tsd_tsdn(tsd), i, false) != NULL) { /* * Choose the first arena that has the lowest * number of threads assigned to it. */ for (j = 0; j < 2; j++) { if (arena_nthreads_get(arena_get( tsd_tsdn(tsd), i, false), !!j) < arena_nthreads_get(arena_get( tsd_tsdn(tsd), choose[j], false), !!j)) { choose[j] = i; } } } else if (first_null == narenas_auto) { /* * Record the index of the first uninitialized * arena, in case all extant arenas are in use. * * NB: It is possible for there to be * discontinuities in terms of initialized * versus uninitialized arenas, due to the * "thread.arena" mallctl. */ first_null = i; } } for (j = 0; j < 2; j++) { if (arena_nthreads_get(arena_get(tsd_tsdn(tsd), choose[j], false), !!j) == 0 || first_null == narenas_auto) { /* * Use an unloaded arena, or the least loaded * arena if all arenas are already initialized. */ if (!!j == internal) { ret = arena_get(tsd_tsdn(tsd), choose[j], false); } } else { arena_t *arena; /* Initialize a new arena. */ choose[j] = first_null; arena = arena_init_locked(tsd_tsdn(tsd), choose[j], (extent_hooks_t *)&extent_hooks_default); if (arena == NULL) { malloc_mutex_unlock(tsd_tsdn(tsd), &arenas_lock); return NULL; } is_new_arena[j] = true; if (!!j == internal) { ret = arena; } } arena_bind(tsd, choose[j], !!j); } malloc_mutex_unlock(tsd_tsdn(tsd), &arenas_lock); for (j = 0; j < 2; j++) { if (is_new_arena[j]) { assert(choose[j] > 0); arena_new_create_background_thread( tsd_tsdn(tsd), choose[j]); } } } else { ret = arena_get(tsd_tsdn(tsd), 0, false); arena_bind(tsd, 0, false); arena_bind(tsd, 0, true); } return ret; } void iarena_cleanup(tsd_t *tsd) { arena_t *iarena; iarena = tsd_iarena_get(tsd); if (iarena != NULL) { arena_unbind(tsd, arena_ind_get(iarena), true); } } void arena_cleanup(tsd_t *tsd) { arena_t *arena; arena = tsd_arena_get(tsd); if (arena != NULL) { arena_unbind(tsd, arena_ind_get(arena), false); } } void arenas_tdata_cleanup(tsd_t *tsd) { arena_tdata_t *arenas_tdata; /* Prevent tsd->arenas_tdata from being (re)created. */ *tsd_arenas_tdata_bypassp_get(tsd) = true; arenas_tdata = tsd_arenas_tdata_get(tsd); if (arenas_tdata != NULL) { tsd_arenas_tdata_set(tsd, NULL); a0dalloc(arenas_tdata); } } static void stats_print_atexit(void) { if (config_stats) { tsdn_t *tsdn; unsigned narenas, i; tsdn = tsdn_fetch(); /* * Merge stats from extant threads. This is racy, since * individual threads do not lock when recording tcache stats * events. As a consequence, the final stats may be slightly * out of date by the time they are reported, if other threads * continue to allocate. */ for (i = 0, narenas = narenas_total_get(); i < narenas; i++) { arena_t *arena = arena_get(tsdn, i, false); if (arena != NULL) { tcache_t *tcache; malloc_mutex_lock(tsdn, &arena->tcache_ql_mtx); ql_foreach(tcache, &arena->tcache_ql, link) { tcache_stats_merge(tsdn, tcache, arena); } malloc_mutex_unlock(tsdn, &arena->tcache_ql_mtx); } } } je_malloc_stats_print(NULL, NULL, opt_stats_print_opts); } /* * Ensure that we don't hold any locks upon entry to or exit from allocator * code (in a "broad" sense that doesn't count a reentrant allocation as an * entrance or exit). */ JEMALLOC_ALWAYS_INLINE void check_entry_exit_locking(tsdn_t *tsdn) { if (!config_debug) { return; } if (tsdn_null(tsdn)) { return; } tsd_t *tsd = tsdn_tsd(tsdn); /* * It's possible we hold locks at entry/exit if we're in a nested * allocation. */ int8_t reentrancy_level = tsd_reentrancy_level_get(tsd); if (reentrancy_level != 0) { return; } witness_assert_lockless(tsdn_witness_tsdp_get(tsdn)); } /* * End miscellaneous support functions. */ /******************************************************************************/ /* * Begin initialization functions. */ static char * jemalloc_secure_getenv(const char *name) { #ifdef JEMALLOC_HAVE_SECURE_GETENV return secure_getenv(name); #else # ifdef JEMALLOC_HAVE_ISSETUGID if (issetugid() != 0) { return NULL; } # endif return getenv(name); #endif } static unsigned malloc_ncpus(void) { long result; #ifdef _WIN32 SYSTEM_INFO si; GetSystemInfo(&si); result = si.dwNumberOfProcessors; #elif defined(JEMALLOC_GLIBC_MALLOC_HOOK) && defined(CPU_COUNT) /* * glibc >= 2.6 has the CPU_COUNT macro. * * glibc's sysconf() uses isspace(). glibc allocates for the first time * *before* setting up the isspace tables. Therefore we need a * different method to get the number of CPUs. */ { cpu_set_t set; pthread_getaffinity_np(pthread_self(), sizeof(set), &set); result = CPU_COUNT(&set); } #else result = sysconf(_SC_NPROCESSORS_ONLN); #endif return ((result == -1) ? 1 : (unsigned)result); } static void init_opt_stats_print_opts(const char *v, size_t vlen) { size_t opts_len = strlen(opt_stats_print_opts); assert(opts_len <= stats_print_tot_num_options); for (size_t i = 0; i < vlen; i++) { switch (v[i]) { #define OPTION(o, v, d, s) case o: break; STATS_PRINT_OPTIONS #undef OPTION default: continue; } if (strchr(opt_stats_print_opts, v[i]) != NULL) { /* Ignore repeated. */ continue; } opt_stats_print_opts[opts_len++] = v[i]; opt_stats_print_opts[opts_len] = '\0'; assert(opts_len <= stats_print_tot_num_options); } assert(opts_len == strlen(opt_stats_print_opts)); } +/* Reads the next size pair in a multi-sized option. */ static bool +malloc_conf_multi_sizes_next(const char **slab_size_segment_cur, + size_t *vlen_left, size_t *slab_start, size_t *slab_end, size_t *new_size) { + const char *cur = *slab_size_segment_cur; + char *end; + uintmax_t um; + + set_errno(0); + + /* First number, then '-' */ + um = malloc_strtoumax(cur, &end, 0); + if (get_errno() != 0 || *end != '-') { + return true; + } + *slab_start = (size_t)um; + cur = end + 1; + + /* Second number, then ':' */ + um = malloc_strtoumax(cur, &end, 0); + if (get_errno() != 0 || *end != ':') { + return true; + } + *slab_end = (size_t)um; + cur = end + 1; + + /* Last number */ + um = malloc_strtoumax(cur, &end, 0); + if (get_errno() != 0) { + return true; + } + *new_size = (size_t)um; + + /* Consume the separator if there is one. */ + if (*end == '|') { + end++; + } + + *vlen_left -= end - *slab_size_segment_cur; + *slab_size_segment_cur = end; + + return false; +} + +static bool malloc_conf_next(char const **opts_p, char const **k_p, size_t *klen_p, char const **v_p, size_t *vlen_p) { bool accept; const char *opts = *opts_p; *k_p = opts; for (accept = false; !accept;) { switch (*opts) { case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': case 'G': case 'H': case 'I': case 'J': case 'K': case 'L': case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R': case 'S': case 'T': case 'U': case 'V': case 'W': case 'X': case 'Y': case 'Z': case 'a': case 'b': case 'c': case 'd': case 'e': case 'f': case 'g': case 'h': case 'i': case 'j': case 'k': case 'l': case 'm': case 'n': case 'o': case 'p': case 'q': case 'r': case 's': case 't': case 'u': case 'v': case 'w': case 'x': case 'y': case 'z': case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9': case '_': opts++; break; case ':': opts++; *klen_p = (uintptr_t)opts - 1 - (uintptr_t)*k_p; *v_p = opts; accept = true; break; case '\0': if (opts != *opts_p) { malloc_write(": Conf string ends " "with key\n"); } return true; default: malloc_write(": Malformed conf string\n"); return true; } } for (accept = false; !accept;) { switch (*opts) { case ',': opts++; /* * Look ahead one character here, because the next time * this function is called, it will assume that end of * input has been cleanly reached if no input remains, * but we have optimistically already consumed the * comma if one exists. */ if (*opts == '\0') { malloc_write(": Conf string ends " "with comma\n"); } *vlen_p = (uintptr_t)opts - 1 - (uintptr_t)*v_p; accept = true; break; case '\0': *vlen_p = (uintptr_t)opts - (uintptr_t)*v_p; accept = true; break; default: opts++; break; } } *opts_p = opts; return false; } static void malloc_abort_invalid_conf(void) { assert(opt_abort_conf); malloc_printf(": Abort (abort_conf:true) on invalid conf " "value (see above).\n"); abort(); } static void malloc_conf_error(const char *msg, const char *k, size_t klen, const char *v, size_t vlen) { malloc_printf(": %s: %.*s:%.*s\n", msg, (int)klen, k, (int)vlen, v); /* If abort_conf is set, error out after processing all options. */ + const char *experimental = "experimental_"; + if (strncmp(k, experimental, strlen(experimental)) == 0) { + /* However, tolerate experimental features. */ + return; + } had_conf_error = true; } static void malloc_slow_flag_init(void) { /* * Combine the runtime options into malloc_slow for fast path. Called * after processing all the options. */ malloc_slow_flags |= (opt_junk_alloc ? flag_opt_junk_alloc : 0) | (opt_junk_free ? flag_opt_junk_free : 0) | (opt_zero ? flag_opt_zero : 0) | (opt_utrace ? flag_opt_utrace : 0) | (opt_xmalloc ? flag_opt_xmalloc : 0); malloc_slow = (malloc_slow_flags != 0); } -static void -malloc_conf_init(void) { - unsigned i; - char buf[PATH_MAX + 1]; - const char *opts, *k, *v; - size_t klen, vlen; +/* Number of sources for initializing malloc_conf */ +#define MALLOC_CONF_NSOURCES 4 - for (i = 0; i < 4; i++) { - /* Get runtime configuration. */ - switch (i) { - case 0: - opts = config_malloc_conf; - break; - case 1: - if (je_malloc_conf != NULL) { - /* - * Use options that were compiled into the - * program. - */ - opts = je_malloc_conf; - } else { - /* No configuration specified. */ - buf[0] = '\0'; - opts = buf; - } - break; - case 2: { - ssize_t linklen = 0; +static const char * +obtain_malloc_conf(unsigned which_source, char buf[PATH_MAX + 1]) { + if (config_debug) { + static unsigned read_source = 0; + /* + * Each source should only be read once, to minimize # of + * syscalls on init. + */ + assert(read_source++ == which_source); + } + assert(which_source < MALLOC_CONF_NSOURCES); + + const char *ret; + switch (which_source) { + case 0: + ret = config_malloc_conf; + break; + case 1: + if (je_malloc_conf != NULL) { + /* Use options that were compiled into the program. */ + ret = je_malloc_conf; + } else { + /* No configuration specified. */ + ret = NULL; + } + break; + case 2: { + ssize_t linklen = 0; #ifndef _WIN32 - int saved_errno = errno; - const char *linkname = + int saved_errno = errno; + const char *linkname = # ifdef JEMALLOC_PREFIX - "/etc/"JEMALLOC_PREFIX"malloc.conf" + "/etc/"JEMALLOC_PREFIX"malloc.conf" # else - "/etc/malloc.conf" + "/etc/malloc.conf" # endif - ; + ; - /* - * Try to use the contents of the "/etc/malloc.conf" - * symbolic link's name. - */ - linklen = readlink(linkname, buf, sizeof(buf) - 1); - if (linklen == -1) { - /* No configuration specified. */ - linklen = 0; - /* Restore errno. */ - set_errno(saved_errno); - } + /* + * Try to use the contents of the "/etc/malloc.conf" symbolic + * link's name. + */ +#ifndef JEMALLOC_READLINKAT + linklen = readlink(linkname, buf, PATH_MAX); +#else + linklen = readlinkat(AT_FDCWD, linkname, buf, PATH_MAX); #endif - buf[linklen] = '\0'; - opts = buf; - break; - } case 3: { - const char *envname = + if (linklen == -1) { + /* No configuration specified. */ + linklen = 0; + /* Restore errno. */ + set_errno(saved_errno); + } +#endif + buf[linklen] = '\0'; + ret = buf; + break; + } case 3: { + const char *envname = #ifdef JEMALLOC_PREFIX - JEMALLOC_CPREFIX"MALLOC_CONF" + JEMALLOC_CPREFIX"MALLOC_CONF" #else - "MALLOC_CONF" + "MALLOC_CONF" #endif - ; + ; - if ((opts = jemalloc_secure_getenv(envname)) != NULL) { - /* - * Do nothing; opts is already initialized to - * the value of the MALLOC_CONF environment - * variable. - */ - } else { - /* No configuration specified. */ - buf[0] = '\0'; - opts = buf; - } - break; - } default: - not_reached(); - buf[0] = '\0'; - opts = buf; + if ((ret = jemalloc_secure_getenv(envname)) != NULL) { + /* + * Do nothing; opts is already initialized to the value + * of the MALLOC_CONF environment variable. + */ + } else { + /* No configuration specified. */ + ret = NULL; } + break; + } default: + not_reached(); + ret = NULL; + } + return ret; +} +static void +malloc_conf_init_helper(sc_data_t *sc_data, unsigned bin_shard_sizes[SC_NBINS], + bool initial_call, const char *opts_cache[MALLOC_CONF_NSOURCES], + char buf[PATH_MAX + 1]) { + static const char *opts_explain[MALLOC_CONF_NSOURCES] = { + "string specified via --with-malloc-conf", + "string pointed to by the global variable malloc_conf", + "\"name\" of the file referenced by the symbolic link named " + "/etc/malloc.conf", + "value of the environment variable MALLOC_CONF" + }; + unsigned i; + const char *opts, *k, *v; + size_t klen, vlen; + + for (i = 0; i < MALLOC_CONF_NSOURCES; i++) { + /* Get runtime configuration. */ + if (initial_call) { + opts_cache[i] = obtain_malloc_conf(i, buf); + } + opts = opts_cache[i]; + if (!initial_call && opt_confirm_conf) { + malloc_printf( + ": malloc_conf #%u (%s): \"%s\"\n", + i + 1, opts_explain[i], opts != NULL ? opts : ""); + } + if (opts == NULL) { + continue; + } + while (*opts != '\0' && !malloc_conf_next(&opts, &k, &klen, &v, &vlen)) { + +#define CONF_ERROR(msg, k, klen, v, vlen) \ + if (!initial_call) { \ + malloc_conf_error( \ + msg, k, klen, v, vlen); \ + cur_opt_valid = false; \ + } +#define CONF_CONTINUE { \ + if (!initial_call && opt_confirm_conf \ + && cur_opt_valid) { \ + malloc_printf(": -- " \ + "Set conf value: %.*s:%.*s" \ + "\n", (int)klen, k, \ + (int)vlen, v); \ + } \ + continue; \ + } #define CONF_MATCH(n) \ (sizeof(n)-1 == klen && strncmp(n, k, klen) == 0) #define CONF_MATCH_VALUE(n) \ (sizeof(n)-1 == vlen && strncmp(n, v, vlen) == 0) #define CONF_HANDLE_BOOL(o, n) \ if (CONF_MATCH(n)) { \ if (CONF_MATCH_VALUE("true")) { \ o = true; \ } else if (CONF_MATCH_VALUE("false")) { \ o = false; \ } else { \ - malloc_conf_error( \ - "Invalid conf value", \ + CONF_ERROR("Invalid conf value",\ k, klen, v, vlen); \ } \ - continue; \ + CONF_CONTINUE; \ } -#define CONF_MIN_no(um, min) false -#define CONF_MIN_yes(um, min) ((um) < (min)) -#define CONF_MAX_no(um, max) false -#define CONF_MAX_yes(um, max) ((um) > (max)) + /* + * One of the CONF_MIN macros below expands, in one of the use points, + * to "unsigned integer < 0", which is always false, triggering the + * GCC -Wtype-limits warning, which we disable here and re-enable below. + */ + JEMALLOC_DIAGNOSTIC_PUSH + JEMALLOC_DIAGNOSTIC_IGNORE_TYPE_LIMITS + +#define CONF_DONT_CHECK_MIN(um, min) false +#define CONF_CHECK_MIN(um, min) ((um) < (min)) +#define CONF_DONT_CHECK_MAX(um, max) false +#define CONF_CHECK_MAX(um, max) ((um) > (max)) #define CONF_HANDLE_T_U(t, o, n, min, max, check_min, check_max, clip) \ if (CONF_MATCH(n)) { \ uintmax_t um; \ char *end; \ \ set_errno(0); \ um = malloc_strtoumax(v, &end, 0); \ if (get_errno() != 0 || (uintptr_t)end -\ (uintptr_t)v != vlen) { \ - malloc_conf_error( \ - "Invalid conf value", \ + CONF_ERROR("Invalid conf value",\ k, klen, v, vlen); \ } else if (clip) { \ - if (CONF_MIN_##check_min(um, \ - (t)(min))) { \ + if (check_min(um, (t)(min))) { \ o = (t)(min); \ } else if ( \ - CONF_MAX_##check_max(um, \ - (t)(max))) { \ + check_max(um, (t)(max))) { \ o = (t)(max); \ } else { \ o = (t)um; \ } \ } else { \ - if (CONF_MIN_##check_min(um, \ - (t)(min)) || \ - CONF_MAX_##check_max(um, \ - (t)(max))) { \ - malloc_conf_error( \ + if (check_min(um, (t)(min)) || \ + check_max(um, (t)(max))) { \ + CONF_ERROR( \ "Out-of-range " \ "conf value", \ k, klen, v, vlen); \ } else { \ o = (t)um; \ } \ } \ - continue; \ + CONF_CONTINUE; \ } #define CONF_HANDLE_UNSIGNED(o, n, min, max, check_min, check_max, \ clip) \ CONF_HANDLE_T_U(unsigned, o, n, min, max, \ check_min, check_max, clip) #define CONF_HANDLE_SIZE_T(o, n, min, max, check_min, check_max, clip) \ CONF_HANDLE_T_U(size_t, o, n, min, max, \ check_min, check_max, clip) #define CONF_HANDLE_SSIZE_T(o, n, min, max) \ if (CONF_MATCH(n)) { \ long l; \ char *end; \ \ set_errno(0); \ l = strtol(v, &end, 0); \ if (get_errno() != 0 || (uintptr_t)end -\ (uintptr_t)v != vlen) { \ - malloc_conf_error( \ - "Invalid conf value", \ + CONF_ERROR("Invalid conf value",\ k, klen, v, vlen); \ } else if (l < (ssize_t)(min) || l > \ (ssize_t)(max)) { \ - malloc_conf_error( \ + CONF_ERROR( \ "Out-of-range conf value", \ k, klen, v, vlen); \ } else { \ o = l; \ } \ - continue; \ + CONF_CONTINUE; \ } #define CONF_HANDLE_CHAR_P(o, n, d) \ if (CONF_MATCH(n)) { \ size_t cpylen = (vlen <= \ sizeof(o)-1) ? vlen : \ sizeof(o)-1; \ strncpy(o, v, cpylen); \ o[cpylen] = '\0'; \ - continue; \ + CONF_CONTINUE; \ } + bool cur_opt_valid = true; + + CONF_HANDLE_BOOL(opt_confirm_conf, "confirm_conf") + if (initial_call) { + continue; + } + CONF_HANDLE_BOOL(opt_abort, "abort") CONF_HANDLE_BOOL(opt_abort_conf, "abort_conf") if (strncmp("metadata_thp", k, klen) == 0) { int i; bool match = false; for (i = 0; i < metadata_thp_mode_limit; i++) { if (strncmp(metadata_thp_mode_names[i], v, vlen) == 0) { opt_metadata_thp = i; match = true; break; } } if (!match) { - malloc_conf_error("Invalid conf value", + CONF_ERROR("Invalid conf value", k, klen, v, vlen); } - continue; + CONF_CONTINUE; } CONF_HANDLE_BOOL(opt_retain, "retain") if (strncmp("dss", k, klen) == 0) { int i; bool match = false; for (i = 0; i < dss_prec_limit; i++) { if (strncmp(dss_prec_names[i], v, vlen) == 0) { if (extent_dss_prec_set(i)) { - malloc_conf_error( + CONF_ERROR( "Error setting dss", k, klen, v, vlen); } else { opt_dss = dss_prec_names[i]; match = true; break; } } } if (!match) { - malloc_conf_error("Invalid conf value", + CONF_ERROR("Invalid conf value", k, klen, v, vlen); } - continue; + CONF_CONTINUE; } CONF_HANDLE_UNSIGNED(opt_narenas, "narenas", 1, - UINT_MAX, yes, no, false) + UINT_MAX, CONF_CHECK_MIN, CONF_DONT_CHECK_MAX, + false) + if (CONF_MATCH("bin_shards")) { + const char *bin_shards_segment_cur = v; + size_t vlen_left = vlen; + do { + size_t size_start; + size_t size_end; + size_t nshards; + bool err = malloc_conf_multi_sizes_next( + &bin_shards_segment_cur, &vlen_left, + &size_start, &size_end, &nshards); + if (err || bin_update_shard_size( + bin_shard_sizes, size_start, + size_end, nshards)) { + CONF_ERROR( + "Invalid settings for " + "bin_shards", k, klen, v, + vlen); + break; + } + } while (vlen_left > 0); + CONF_CONTINUE; + } CONF_HANDLE_SSIZE_T(opt_dirty_decay_ms, "dirty_decay_ms", -1, NSTIME_SEC_MAX * KQU(1000) < QU(SSIZE_MAX) ? NSTIME_SEC_MAX * KQU(1000) : SSIZE_MAX); CONF_HANDLE_SSIZE_T(opt_muzzy_decay_ms, "muzzy_decay_ms", -1, NSTIME_SEC_MAX * KQU(1000) < QU(SSIZE_MAX) ? NSTIME_SEC_MAX * KQU(1000) : SSIZE_MAX); CONF_HANDLE_BOOL(opt_stats_print, "stats_print") if (CONF_MATCH("stats_print_opts")) { init_opt_stats_print_opts(v, vlen); - continue; + CONF_CONTINUE; } if (config_fill) { if (CONF_MATCH("junk")) { if (CONF_MATCH_VALUE("true")) { opt_junk = "true"; opt_junk_alloc = opt_junk_free = true; } else if (CONF_MATCH_VALUE("false")) { opt_junk = "false"; opt_junk_alloc = opt_junk_free = false; } else if (CONF_MATCH_VALUE("alloc")) { opt_junk = "alloc"; opt_junk_alloc = true; opt_junk_free = false; } else if (CONF_MATCH_VALUE("free")) { opt_junk = "free"; opt_junk_alloc = false; opt_junk_free = true; } else { - malloc_conf_error( - "Invalid conf value", k, - klen, v, vlen); + CONF_ERROR( + "Invalid conf value", + k, klen, v, vlen); } - continue; + CONF_CONTINUE; } CONF_HANDLE_BOOL(opt_zero, "zero") } if (config_utrace) { CONF_HANDLE_BOOL(opt_utrace, "utrace") } if (config_xmalloc) { CONF_HANDLE_BOOL(opt_xmalloc, "xmalloc") } CONF_HANDLE_BOOL(opt_tcache, "tcache") - CONF_HANDLE_SIZE_T(opt_lg_extent_max_active_fit, - "lg_extent_max_active_fit", 0, - (sizeof(size_t) << 3), yes, yes, false) CONF_HANDLE_SSIZE_T(opt_lg_tcache_max, "lg_tcache_max", -1, (sizeof(size_t) << 3) - 1) + + /* + * The runtime option of oversize_threshold remains + * undocumented. It may be tweaked in the next major + * release (6.0). The default value 8M is rather + * conservative / safe. Tuning it further down may + * improve fragmentation a bit more, but may also cause + * contention on the huge arena. + */ + CONF_HANDLE_SIZE_T(opt_oversize_threshold, + "oversize_threshold", 0, SC_LARGE_MAXCLASS, + CONF_DONT_CHECK_MIN, CONF_CHECK_MAX, false) + CONF_HANDLE_SIZE_T(opt_lg_extent_max_active_fit, + "lg_extent_max_active_fit", 0, + (sizeof(size_t) << 3), CONF_DONT_CHECK_MIN, + CONF_CHECK_MAX, false) + if (strncmp("percpu_arena", k, klen) == 0) { bool match = false; for (int i = percpu_arena_mode_names_base; i < percpu_arena_mode_names_limit; i++) { if (strncmp(percpu_arena_mode_names[i], v, vlen) == 0) { if (!have_percpu_arena) { - malloc_conf_error( + CONF_ERROR( "No getcpu support", k, klen, v, vlen); } opt_percpu_arena = i; match = true; break; } } if (!match) { - malloc_conf_error("Invalid conf value", + CONF_ERROR("Invalid conf value", k, klen, v, vlen); } - continue; + CONF_CONTINUE; } CONF_HANDLE_BOOL(opt_background_thread, "background_thread"); CONF_HANDLE_SIZE_T(opt_max_background_threads, "max_background_threads", 1, - opt_max_background_threads, yes, yes, + opt_max_background_threads, + CONF_CHECK_MIN, CONF_CHECK_MAX, true); + if (CONF_MATCH("slab_sizes")) { + bool err; + const char *slab_size_segment_cur = v; + size_t vlen_left = vlen; + do { + size_t slab_start; + size_t slab_end; + size_t pgs; + err = malloc_conf_multi_sizes_next( + &slab_size_segment_cur, + &vlen_left, &slab_start, &slab_end, + &pgs); + if (!err) { + sc_data_update_slab_size( + sc_data, slab_start, + slab_end, (int)pgs); + } else { + CONF_ERROR("Invalid settings " + "for slab_sizes", + k, klen, v, vlen); + } + } while (!err && vlen_left > 0); + CONF_CONTINUE; + } if (config_prof) { CONF_HANDLE_BOOL(opt_prof, "prof") CONF_HANDLE_CHAR_P(opt_prof_prefix, "prof_prefix", "jeprof") CONF_HANDLE_BOOL(opt_prof_active, "prof_active") CONF_HANDLE_BOOL(opt_prof_thread_active_init, "prof_thread_active_init") CONF_HANDLE_SIZE_T(opt_lg_prof_sample, "lg_prof_sample", 0, (sizeof(uint64_t) << 3) - - 1, no, yes, true) + - 1, CONF_DONT_CHECK_MIN, CONF_CHECK_MAX, + true) CONF_HANDLE_BOOL(opt_prof_accum, "prof_accum") CONF_HANDLE_SSIZE_T(opt_lg_prof_interval, "lg_prof_interval", -1, (sizeof(uint64_t) << 3) - 1) CONF_HANDLE_BOOL(opt_prof_gdump, "prof_gdump") CONF_HANDLE_BOOL(opt_prof_final, "prof_final") CONF_HANDLE_BOOL(opt_prof_leak, "prof_leak") + CONF_HANDLE_BOOL(opt_prof_log, "prof_log") } if (config_log) { if (CONF_MATCH("log")) { size_t cpylen = ( vlen <= sizeof(log_var_names) ? vlen : sizeof(log_var_names) - 1); strncpy(log_var_names, v, cpylen); log_var_names[cpylen] = '\0'; - continue; + CONF_CONTINUE; } } if (CONF_MATCH("thp")) { bool match = false; for (int i = 0; i < thp_mode_names_limit; i++) { if (strncmp(thp_mode_names[i],v, vlen) == 0) { if (!have_madvise_huge) { - malloc_conf_error( + CONF_ERROR( "No THP support", k, klen, v, vlen); } opt_thp = i; match = true; break; } } if (!match) { - malloc_conf_error("Invalid conf value", + CONF_ERROR("Invalid conf value", k, klen, v, vlen); } - continue; + CONF_CONTINUE; } - malloc_conf_error("Invalid conf pair", k, klen, v, - vlen); + CONF_ERROR("Invalid conf pair", k, klen, v, vlen); +#undef CONF_ERROR +#undef CONF_CONTINUE #undef CONF_MATCH #undef CONF_MATCH_VALUE #undef CONF_HANDLE_BOOL -#undef CONF_MIN_no -#undef CONF_MIN_yes -#undef CONF_MAX_no -#undef CONF_MAX_yes +#undef CONF_DONT_CHECK_MIN +#undef CONF_CHECK_MIN +#undef CONF_DONT_CHECK_MAX +#undef CONF_CHECK_MAX #undef CONF_HANDLE_T_U #undef CONF_HANDLE_UNSIGNED #undef CONF_HANDLE_SIZE_T #undef CONF_HANDLE_SSIZE_T #undef CONF_HANDLE_CHAR_P + /* Re-enable diagnostic "-Wtype-limits" */ + JEMALLOC_DIAGNOSTIC_POP } if (opt_abort_conf && had_conf_error) { malloc_abort_invalid_conf(); } } atomic_store_b(&log_init_done, true, ATOMIC_RELEASE); } +static void +malloc_conf_init(sc_data_t *sc_data, unsigned bin_shard_sizes[SC_NBINS]) { + const char *opts_cache[MALLOC_CONF_NSOURCES] = {NULL, NULL, NULL, NULL}; + char buf[PATH_MAX + 1]; + + /* The first call only set the confirm_conf option and opts_cache */ + malloc_conf_init_helper(NULL, NULL, true, opts_cache, buf); + malloc_conf_init_helper(sc_data, bin_shard_sizes, false, opts_cache, + NULL); +} + +#undef MALLOC_CONF_NSOURCES + static bool malloc_init_hard_needed(void) { if (malloc_initialized() || (IS_INITIALIZER && malloc_init_state == malloc_init_recursible)) { /* * Another thread initialized the allocator before this one * acquired init_lock, or this thread is the initializing * thread, and it is recursively allocating. */ return false; } #ifdef JEMALLOC_THREADED_INIT if (malloc_initializer != NO_INITIALIZER && !IS_INITIALIZER) { /* Busy-wait until the initializing thread completes. */ spin_t spinner = SPIN_INITIALIZER; do { malloc_mutex_unlock(TSDN_NULL, &init_lock); spin_adaptive(&spinner); malloc_mutex_lock(TSDN_NULL, &init_lock); } while (!malloc_initialized()); return false; } #endif return true; } static bool malloc_init_hard_a0_locked() { malloc_initializer = INITIALIZER; + JEMALLOC_DIAGNOSTIC_PUSH + JEMALLOC_DIAGNOSTIC_IGNORE_MISSING_STRUCT_FIELD_INITIALIZERS + sc_data_t sc_data = {0}; + JEMALLOC_DIAGNOSTIC_POP + + /* + * Ordering here is somewhat tricky; we need sc_boot() first, since that + * determines what the size classes will be, and then + * malloc_conf_init(), since any slab size tweaking will need to be done + * before sz_boot and bin_boot, which assume that the values they read + * out of sc_data_global are final. + */ + sc_boot(&sc_data); + unsigned bin_shard_sizes[SC_NBINS]; + bin_shard_sizes_boot(bin_shard_sizes); + /* + * prof_boot0 only initializes opt_prof_prefix. We need to do it before + * we parse malloc_conf options, in case malloc_conf parsing overwrites + * it. + */ if (config_prof) { prof_boot0(); } - malloc_conf_init(); + malloc_conf_init(&sc_data, bin_shard_sizes); + sz_boot(&sc_data); + bin_boot(&sc_data, bin_shard_sizes); + if (opt_stats_print) { /* Print statistics at exit. */ if (atexit(stats_print_atexit) != 0) { malloc_write(": Error in atexit()\n"); if (opt_abort) { abort(); } } } if (pages_boot()) { return true; } if (base_boot(TSDN_NULL)) { return true; } if (extent_boot()) { return true; } if (ctl_boot()) { return true; } if (config_prof) { prof_boot1(); } - arena_boot(); + arena_boot(&sc_data); if (tcache_boot(TSDN_NULL)) { return true; } if (malloc_mutex_init(&arenas_lock, "arenas", WITNESS_RANK_ARENAS, malloc_mutex_rank_exclusive)) { return true; } + hook_boot(); /* * Create enough scaffolding to allow recursive allocation in * malloc_ncpus(). */ narenas_auto = 1; + manual_arena_base = narenas_auto + 1; memset(arenas, 0, sizeof(arena_t *) * narenas_auto); /* * Initialize one arena here. The rest are lazily created in * arena_choose_hard(). */ if (arena_init(TSDN_NULL, 0, (extent_hooks_t *)&extent_hooks_default) == NULL) { return true; } a0 = arena_get(TSDN_NULL, 0, false); malloc_init_state = malloc_init_a0_initialized; return false; } static bool malloc_init_hard_a0(void) { bool ret; malloc_mutex_lock(TSDN_NULL, &init_lock); ret = malloc_init_hard_a0_locked(); malloc_mutex_unlock(TSDN_NULL, &init_lock); return ret; } /* Initialize data structures which may trigger recursive allocation. */ static bool malloc_init_hard_recursible(void) { malloc_init_state = malloc_init_recursible; ncpus = malloc_ncpus(); #if (defined(JEMALLOC_HAVE_PTHREAD_ATFORK) && !defined(JEMALLOC_MUTEX_INIT_CB) \ && !defined(JEMALLOC_ZONE) && !defined(_WIN32) && \ !defined(__native_client__)) /* LinuxThreads' pthread_atfork() allocates. */ if (pthread_atfork(jemalloc_prefork, jemalloc_postfork_parent, jemalloc_postfork_child) != 0) { malloc_write(": Error in pthread_atfork()\n"); if (opt_abort) { abort(); } return true; } #endif if (background_thread_boot0()) { return true; } return false; } static unsigned malloc_narenas_default(void) { assert(ncpus > 0); /* * For SMP systems, create more than one arena per CPU by * default. */ if (ncpus > 1) { return ncpus << 2; } else { return 1; } } static percpu_arena_mode_t percpu_arena_as_initialized(percpu_arena_mode_t mode) { assert(!malloc_initialized()); assert(mode <= percpu_arena_disabled); if (mode != percpu_arena_disabled) { mode += percpu_arena_mode_enabled_base; } return mode; } static bool malloc_init_narenas(void) { assert(ncpus > 0); if (opt_percpu_arena != percpu_arena_disabled) { if (!have_percpu_arena || malloc_getcpu() < 0) { opt_percpu_arena = percpu_arena_disabled; malloc_printf(": perCPU arena getcpu() not " "available. Setting narenas to %u.\n", opt_narenas ? opt_narenas : malloc_narenas_default()); if (opt_abort) { abort(); } } else { if (ncpus >= MALLOCX_ARENA_LIMIT) { malloc_printf(": narenas w/ percpu" "arena beyond limit (%d)\n", ncpus); if (opt_abort) { abort(); } return true; } /* NB: opt_percpu_arena isn't fully initialized yet. */ if (percpu_arena_as_initialized(opt_percpu_arena) == per_phycpu_arena && ncpus % 2 != 0) { malloc_printf(": invalid " "configuration -- per physical CPU arena " "with odd number (%u) of CPUs (no hyper " "threading?).\n", ncpus); if (opt_abort) abort(); } unsigned n = percpu_arena_ind_limit( percpu_arena_as_initialized(opt_percpu_arena)); if (opt_narenas < n) { /* * If narenas is specified with percpu_arena * enabled, actual narenas is set as the greater * of the two. percpu_arena_choose will be free * to use any of the arenas based on CPU * id. This is conservative (at a small cost) * but ensures correctness. * * If for some reason the ncpus determined at * boot is not the actual number (e.g. because * of affinity setting from numactl), reserving * narenas this way provides a workaround for * percpu_arena. */ opt_narenas = n; } } } if (opt_narenas == 0) { opt_narenas = malloc_narenas_default(); } assert(opt_narenas > 0); narenas_auto = opt_narenas; /* * Limit the number of arenas to the indexing range of MALLOCX_ARENA(). */ if (narenas_auto >= MALLOCX_ARENA_LIMIT) { narenas_auto = MALLOCX_ARENA_LIMIT - 1; malloc_printf(": Reducing narenas to limit (%d)\n", narenas_auto); } narenas_total_set(narenas_auto); + if (arena_init_huge()) { + narenas_total_inc(); + } + manual_arena_base = narenas_total_get(); return false; } static void malloc_init_percpu(void) { opt_percpu_arena = percpu_arena_as_initialized(opt_percpu_arena); } static bool malloc_init_hard_finish(void) { if (malloc_mutex_boot()) { return true; } malloc_init_state = malloc_init_initialized; malloc_slow_flag_init(); return false; } static void malloc_init_hard_cleanup(tsdn_t *tsdn, bool reentrancy_set) { malloc_mutex_assert_owner(tsdn, &init_lock); malloc_mutex_unlock(tsdn, &init_lock); if (reentrancy_set) { assert(!tsdn_null(tsdn)); tsd_t *tsd = tsdn_tsd(tsdn); assert(tsd_reentrancy_level_get(tsd) > 0); post_reentrancy(tsd); } } static bool malloc_init_hard(void) { tsd_t *tsd; #if defined(_WIN32) && _WIN32_WINNT < 0x0600 _init_init_lock(); #endif malloc_mutex_lock(TSDN_NULL, &init_lock); #define UNLOCK_RETURN(tsdn, ret, reentrancy) \ malloc_init_hard_cleanup(tsdn, reentrancy); \ return ret; if (!malloc_init_hard_needed()) { UNLOCK_RETURN(TSDN_NULL, false, false) } if (malloc_init_state != malloc_init_a0_initialized && malloc_init_hard_a0_locked()) { UNLOCK_RETURN(TSDN_NULL, true, false) } malloc_mutex_unlock(TSDN_NULL, &init_lock); /* Recursive allocation relies on functional tsd. */ tsd = malloc_tsd_boot0(); if (tsd == NULL) { return true; } if (malloc_init_hard_recursible()) { return true; } malloc_mutex_lock(tsd_tsdn(tsd), &init_lock); /* Set reentrancy level to 1 during init. */ pre_reentrancy(tsd, NULL); /* Initialize narenas before prof_boot2 (for allocation). */ if (malloc_init_narenas() || background_thread_boot1(tsd_tsdn(tsd))) { UNLOCK_RETURN(tsd_tsdn(tsd), true, true) } if (config_prof && prof_boot2(tsd)) { UNLOCK_RETURN(tsd_tsdn(tsd), true, true) } malloc_init_percpu(); if (malloc_init_hard_finish()) { UNLOCK_RETURN(tsd_tsdn(tsd), true, true) } post_reentrancy(tsd); malloc_mutex_unlock(tsd_tsdn(tsd), &init_lock); witness_assert_lockless(witness_tsd_tsdn( tsd_witness_tsdp_get_unsafe(tsd))); malloc_tsd_boot1(); /* Update TSD after tsd_boot1. */ tsd = tsd_fetch(); if (opt_background_thread) { assert(have_background_thread); /* * Need to finish init & unlock first before creating background * threads (pthread_create depends on malloc). ctl_init (which * sets isthreaded) needs to be called without holding any lock. */ background_thread_ctl_init(tsd_tsdn(tsd)); - - malloc_mutex_lock(tsd_tsdn(tsd), &background_thread_lock); - bool err = background_thread_create(tsd, 0); - malloc_mutex_unlock(tsd_tsdn(tsd), &background_thread_lock); - if (err) { + if (background_thread_create(tsd, 0)) { return true; } } #undef UNLOCK_RETURN return false; } /* * End initialization functions. */ /******************************************************************************/ /* * Begin allocation-path internal functions and data structures. */ /* * Settings determined by the documented behavior of the allocation functions. */ typedef struct static_opts_s static_opts_t; struct static_opts_s { /* Whether or not allocation size may overflow. */ bool may_overflow; - /* Whether or not allocations of size 0 should be treated as size 1. */ - bool bump_empty_alloc; + /* + * Whether or not allocations (with alignment) of size 0 should be + * treated as size 1. + */ + bool bump_empty_aligned_alloc; + /* * Whether to assert that allocations are not of size 0 (after any * bumping). */ bool assert_nonempty_alloc; /* * Whether or not to modify the 'result' argument to malloc in case of * error. */ bool null_out_result_on_error; /* Whether to set errno when we encounter an error condition. */ bool set_errno_on_error; /* * The minimum valid alignment for functions requesting aligned storage. */ size_t min_alignment; /* The error string to use if we oom. */ const char *oom_string; /* The error string to use if the passed-in alignment is invalid. */ const char *invalid_alignment_string; /* * False if we're configured to skip some time-consuming operations. * * This isn't really a malloc "behavior", but it acts as a useful * summary of several other static (or at least, static after program * initialization) options. */ bool slow; + /* + * Return size. + */ + bool usize; }; JEMALLOC_ALWAYS_INLINE void static_opts_init(static_opts_t *static_opts) { static_opts->may_overflow = false; - static_opts->bump_empty_alloc = false; + static_opts->bump_empty_aligned_alloc = false; static_opts->assert_nonempty_alloc = false; static_opts->null_out_result_on_error = false; static_opts->set_errno_on_error = false; static_opts->min_alignment = 0; static_opts->oom_string = ""; static_opts->invalid_alignment_string = ""; static_opts->slow = false; + static_opts->usize = false; } /* * These correspond to the macros in jemalloc/jemalloc_macros.h. Broadly, we * should have one constant here per magic value there. Note however that the * representations need not be related. */ #define TCACHE_IND_NONE ((unsigned)-1) #define TCACHE_IND_AUTOMATIC ((unsigned)-2) #define ARENA_IND_AUTOMATIC ((unsigned)-1) typedef struct dynamic_opts_s dynamic_opts_t; struct dynamic_opts_s { void **result; + size_t usize; size_t num_items; size_t item_size; size_t alignment; bool zero; unsigned tcache_ind; unsigned arena_ind; }; JEMALLOC_ALWAYS_INLINE void dynamic_opts_init(dynamic_opts_t *dynamic_opts) { dynamic_opts->result = NULL; + dynamic_opts->usize = 0; dynamic_opts->num_items = 0; dynamic_opts->item_size = 0; dynamic_opts->alignment = 0; dynamic_opts->zero = false; dynamic_opts->tcache_ind = TCACHE_IND_AUTOMATIC; dynamic_opts->arena_ind = ARENA_IND_AUTOMATIC; } /* ind is ignored if dopts->alignment > 0. */ JEMALLOC_ALWAYS_INLINE void * imalloc_no_sample(static_opts_t *sopts, dynamic_opts_t *dopts, tsd_t *tsd, size_t size, size_t usize, szind_t ind) { tcache_t *tcache; arena_t *arena; /* Fill in the tcache. */ if (dopts->tcache_ind == TCACHE_IND_AUTOMATIC) { if (likely(!sopts->slow)) { /* Getting tcache ptr unconditionally. */ tcache = tsd_tcachep_get(tsd); assert(tcache == tcache_get(tsd)); } else { tcache = tcache_get(tsd); } } else if (dopts->tcache_ind == TCACHE_IND_NONE) { tcache = NULL; } else { tcache = tcaches_get(tsd, dopts->tcache_ind); } /* Fill in the arena. */ if (dopts->arena_ind == ARENA_IND_AUTOMATIC) { /* * In case of automatic arena management, we defer arena * computation until as late as we can, hoping to fill the * allocation out of the tcache. */ arena = NULL; } else { arena = arena_get(tsd_tsdn(tsd), dopts->arena_ind, true); } if (unlikely(dopts->alignment != 0)) { return ipalloct(tsd_tsdn(tsd), usize, dopts->alignment, dopts->zero, tcache, arena); } return iallocztm(tsd_tsdn(tsd), size, ind, dopts->zero, tcache, false, arena, sopts->slow); } JEMALLOC_ALWAYS_INLINE void * imalloc_sample(static_opts_t *sopts, dynamic_opts_t *dopts, tsd_t *tsd, size_t usize, szind_t ind) { void *ret; /* * For small allocations, sampling bumps the usize. If so, we allocate * from the ind_large bucket. */ szind_t ind_large; size_t bumped_usize = usize; - if (usize <= SMALL_MAXCLASS) { - assert(((dopts->alignment == 0) ? sz_s2u(LARGE_MINCLASS) : - sz_sa2u(LARGE_MINCLASS, dopts->alignment)) - == LARGE_MINCLASS); - ind_large = sz_size2index(LARGE_MINCLASS); - bumped_usize = sz_s2u(LARGE_MINCLASS); + if (usize <= SC_SMALL_MAXCLASS) { + assert(((dopts->alignment == 0) ? + sz_s2u(SC_LARGE_MINCLASS) : + sz_sa2u(SC_LARGE_MINCLASS, dopts->alignment)) + == SC_LARGE_MINCLASS); + ind_large = sz_size2index(SC_LARGE_MINCLASS); + bumped_usize = sz_s2u(SC_LARGE_MINCLASS); ret = imalloc_no_sample(sopts, dopts, tsd, bumped_usize, bumped_usize, ind_large); if (unlikely(ret == NULL)) { return NULL; } arena_prof_promote(tsd_tsdn(tsd), ret, usize); } else { ret = imalloc_no_sample(sopts, dopts, tsd, usize, usize, ind); } return ret; } /* * Returns true if the allocation will overflow, and false otherwise. Sets * *size to the product either way. */ JEMALLOC_ALWAYS_INLINE bool compute_size_with_overflow(bool may_overflow, dynamic_opts_t *dopts, size_t *size) { /* * This function is just num_items * item_size, except that we may have * to check for overflow. */ if (!may_overflow) { assert(dopts->num_items == 1); *size = dopts->item_size; return false; } /* A size_t with its high-half bits all set to 1. */ static const size_t high_bits = SIZE_T_MAX << (sizeof(size_t) * 8 / 2); *size = dopts->item_size * dopts->num_items; if (unlikely(*size == 0)) { return (dopts->num_items != 0 && dopts->item_size != 0); } /* * We got a non-zero size, but we don't know if we overflowed to get * there. To avoid having to do a divide, we'll be clever and note that * if both A and B can be represented in N/2 bits, then their product * can be represented in N bits (without the possibility of overflow). */ if (likely((high_bits & (dopts->num_items | dopts->item_size)) == 0)) { return false; } if (likely(*size / dopts->item_size == dopts->num_items)) { return false; } return true; } JEMALLOC_ALWAYS_INLINE int imalloc_body(static_opts_t *sopts, dynamic_opts_t *dopts, tsd_t *tsd) { /* Where the actual allocated memory will live. */ void *allocation = NULL; /* Filled in by compute_size_with_overflow below. */ size_t size = 0; /* * For unaligned allocations, we need only ind. For aligned * allocations, or in case of stats or profiling we need usize. * * These are actually dead stores, in that their values are reset before * any branch on their value is taken. Sometimes though, it's * convenient to pass them as arguments before this point. To avoid * undefined behavior then, we initialize them with dummy stores. */ szind_t ind = 0; size_t usize = 0; /* Reentrancy is only checked on slow path. */ int8_t reentrancy_level; /* Compute the amount of memory the user wants. */ if (unlikely(compute_size_with_overflow(sopts->may_overflow, dopts, &size))) { goto label_oom; } - /* Validate the user input. */ - if (sopts->bump_empty_alloc) { - if (unlikely(size == 0)) { - size = 1; - } - } - - if (sopts->assert_nonempty_alloc) { - assert (size != 0); - } - if (unlikely(dopts->alignment < sopts->min_alignment || (dopts->alignment & (dopts->alignment - 1)) != 0)) { goto label_invalid_alignment; } /* This is the beginning of the "core" algorithm. */ if (dopts->alignment == 0) { ind = sz_size2index(size); - if (unlikely(ind >= NSIZES)) { + if (unlikely(ind >= SC_NSIZES)) { goto label_oom; } - if (config_stats || (config_prof && opt_prof)) { + if (config_stats || (config_prof && opt_prof) || sopts->usize) { usize = sz_index2size(ind); - assert(usize > 0 && usize <= LARGE_MAXCLASS); + dopts->usize = usize; + assert(usize > 0 && usize + <= SC_LARGE_MAXCLASS); } } else { + if (sopts->bump_empty_aligned_alloc) { + if (unlikely(size == 0)) { + size = 1; + } + } usize = sz_sa2u(size, dopts->alignment); - if (unlikely(usize == 0 || usize > LARGE_MAXCLASS)) { + dopts->usize = usize; + if (unlikely(usize == 0 + || usize > SC_LARGE_MAXCLASS)) { goto label_oom; } } + /* Validate the user input. */ + if (sopts->assert_nonempty_alloc) { + assert (size != 0); + } check_entry_exit_locking(tsd_tsdn(tsd)); /* * If we need to handle reentrancy, we can do it out of a * known-initialized arena (i.e. arena 0). */ reentrancy_level = tsd_reentrancy_level_get(tsd); if (sopts->slow && unlikely(reentrancy_level > 0)) { /* * We should never specify particular arenas or tcaches from * within our internal allocations. */ assert(dopts->tcache_ind == TCACHE_IND_AUTOMATIC || dopts->tcache_ind == TCACHE_IND_NONE); assert(dopts->arena_ind == ARENA_IND_AUTOMATIC); dopts->tcache_ind = TCACHE_IND_NONE; /* We know that arena 0 has already been initialized. */ dopts->arena_ind = 0; } /* If profiling is on, get our profiling context. */ if (config_prof && opt_prof) { /* * Note that if we're going down this path, usize must have been * initialized in the previous if statement. */ prof_tctx_t *tctx = prof_alloc_prep( tsd, usize, prof_active_get_unlocked(), true); alloc_ctx_t alloc_ctx; if (likely((uintptr_t)tctx == (uintptr_t)1U)) { - alloc_ctx.slab = (usize <= SMALL_MAXCLASS); + alloc_ctx.slab = (usize + <= SC_SMALL_MAXCLASS); allocation = imalloc_no_sample( sopts, dopts, tsd, usize, usize, ind); } else if ((uintptr_t)tctx > (uintptr_t)1U) { /* * Note that ind might still be 0 here. This is fine; * imalloc_sample ignores ind if dopts->alignment > 0. */ allocation = imalloc_sample( sopts, dopts, tsd, usize, ind); alloc_ctx.slab = false; } else { allocation = NULL; } if (unlikely(allocation == NULL)) { prof_alloc_rollback(tsd, tctx, true); goto label_oom; } prof_malloc(tsd_tsdn(tsd), allocation, usize, &alloc_ctx, tctx); } else { /* * If dopts->alignment > 0, then ind is still 0, but usize was * computed in the previous if statement. Down the positive * alignment path, imalloc_no_sample ignores ind and size * (relying only on usize). */ allocation = imalloc_no_sample(sopts, dopts, tsd, size, usize, ind); if (unlikely(allocation == NULL)) { goto label_oom; } } /* * Allocation has been done at this point. We still have some * post-allocation work to do though. */ assert(dopts->alignment == 0 || ((uintptr_t)allocation & (dopts->alignment - 1)) == ZU(0)); if (config_stats) { assert(usize == isalloc(tsd_tsdn(tsd), allocation)); *tsd_thread_allocatedp_get(tsd) += usize; } if (sopts->slow) { UTRACE(0, size, allocation); } /* Success! */ check_entry_exit_locking(tsd_tsdn(tsd)); *dopts->result = allocation; return 0; label_oom: if (unlikely(sopts->slow) && config_xmalloc && unlikely(opt_xmalloc)) { malloc_write(sopts->oom_string); abort(); } if (sopts->slow) { UTRACE(NULL, size, NULL); } check_entry_exit_locking(tsd_tsdn(tsd)); if (sopts->set_errno_on_error) { set_errno(ENOMEM); } if (sopts->null_out_result_on_error) { *dopts->result = NULL; } return ENOMEM; /* * This label is only jumped to by one goto; we move it out of line * anyways to avoid obscuring the non-error paths, and for symmetry with * the oom case. */ label_invalid_alignment: if (config_xmalloc && unlikely(opt_xmalloc)) { malloc_write(sopts->invalid_alignment_string); abort(); } if (sopts->set_errno_on_error) { set_errno(EINVAL); } if (sopts->slow) { UTRACE(NULL, size, NULL); } check_entry_exit_locking(tsd_tsdn(tsd)); if (sopts->null_out_result_on_error) { *dopts->result = NULL; } return EINVAL; } -/* Returns the errno-style error code of the allocation. */ -JEMALLOC_ALWAYS_INLINE int -imalloc(static_opts_t *sopts, dynamic_opts_t *dopts) { +JEMALLOC_ALWAYS_INLINE bool +imalloc_init_check(static_opts_t *sopts, dynamic_opts_t *dopts) { if (unlikely(!malloc_initialized()) && unlikely(malloc_init())) { if (config_xmalloc && unlikely(opt_xmalloc)) { malloc_write(sopts->oom_string); abort(); } UTRACE(NULL, dopts->num_items * dopts->item_size, NULL); set_errno(ENOMEM); *dopts->result = NULL; + return false; + } + + return true; +} + +/* Returns the errno-style error code of the allocation. */ +JEMALLOC_ALWAYS_INLINE int +imalloc(static_opts_t *sopts, dynamic_opts_t *dopts) { + if (tsd_get_allocates() && !imalloc_init_check(sopts, dopts)) { return ENOMEM; } /* We always need the tsd. Let's grab it right away. */ tsd_t *tsd = tsd_fetch(); assert(tsd); if (likely(tsd_fast(tsd))) { /* Fast and common path. */ tsd_assert_fast(tsd); sopts->slow = false; return imalloc_body(sopts, dopts, tsd); } else { + if (!tsd_get_allocates() && !imalloc_init_check(sopts, dopts)) { + return ENOMEM; + } + sopts->slow = true; return imalloc_body(sopts, dopts, tsd); } } -/******************************************************************************/ -/* - * Begin malloc(3)-compatible functions. - */ -JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN -void JEMALLOC_NOTHROW * -JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE(1) -je_malloc(size_t size) { +JEMALLOC_NOINLINE +void * +malloc_default(size_t size) { void *ret; static_opts_t sopts; dynamic_opts_t dopts; LOG("core.malloc.entry", "size: %zu", size); static_opts_init(&sopts); dynamic_opts_init(&dopts); - sopts.bump_empty_alloc = true; sopts.null_out_result_on_error = true; sopts.set_errno_on_error = true; sopts.oom_string = ": Error in malloc(): out of memory\n"; dopts.result = &ret; dopts.num_items = 1; dopts.item_size = size; imalloc(&sopts, &dopts); + /* + * Note that this branch gets optimized away -- it immediately follows + * the check on tsd_fast that sets sopts.slow. + */ + if (sopts.slow) { + uintptr_t args[3] = {size}; + hook_invoke_alloc(hook_alloc_malloc, ret, (uintptr_t)ret, args); + } LOG("core.malloc.exit", "result: %p", ret); return ret; } +/******************************************************************************/ +/* + * Begin malloc(3)-compatible functions. + */ + +/* + * malloc() fastpath. + * + * Fastpath assumes size <= SC_LOOKUP_MAXCLASS, and that we hit + * tcache. If either of these is false, we tail-call to the slowpath, + * malloc_default(). Tail-calling is used to avoid any caller-saved + * registers. + * + * fastpath supports ticker and profiling, both of which will also + * tail-call to the slowpath if they fire. + */ +JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN +void JEMALLOC_NOTHROW * +JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE(1) +je_malloc(size_t size) { + LOG("core.malloc.entry", "size: %zu", size); + + if (tsd_get_allocates() && unlikely(!malloc_initialized())) { + return malloc_default(size); + } + + tsd_t *tsd = tsd_get(false); + if (unlikely(!tsd || !tsd_fast(tsd) || (size > SC_LOOKUP_MAXCLASS))) { + return malloc_default(size); + } + + tcache_t *tcache = tsd_tcachep_get(tsd); + + if (unlikely(ticker_trytick(&tcache->gc_ticker))) { + return malloc_default(size); + } + + szind_t ind = sz_size2index_lookup(size); + size_t usize; + if (config_stats || config_prof) { + usize = sz_index2size(ind); + } + /* Fast path relies on size being a bin. I.e. SC_LOOKUP_MAXCLASS < SC_SMALL_MAXCLASS */ + assert(ind < SC_NBINS); + assert(size <= SC_SMALL_MAXCLASS); + + if (config_prof) { + int64_t bytes_until_sample = tsd_bytes_until_sample_get(tsd); + bytes_until_sample -= usize; + tsd_bytes_until_sample_set(tsd, bytes_until_sample); + + if (unlikely(bytes_until_sample < 0)) { + /* + * Avoid a prof_active check on the fastpath. + * If prof_active is false, set bytes_until_sample to + * a large value. If prof_active is set to true, + * bytes_until_sample will be reset. + */ + if (!prof_active) { + tsd_bytes_until_sample_set(tsd, SSIZE_MAX); + } + return malloc_default(size); + } + } + + cache_bin_t *bin = tcache_small_bin_get(tcache, ind); + bool tcache_success; + void* ret = cache_bin_alloc_easy(bin, &tcache_success); + + if (tcache_success) { + if (config_stats) { + *tsd_thread_allocatedp_get(tsd) += usize; + bin->tstats.nrequests++; + } + if (config_prof) { + tcache->prof_accumbytes += usize; + } + + LOG("core.malloc.exit", "result: %p", ret); + + /* Fastpath success */ + return ret; + } + + return malloc_default(size); +} + JEMALLOC_EXPORT int JEMALLOC_NOTHROW JEMALLOC_ATTR(nonnull(1)) je_posix_memalign(void **memptr, size_t alignment, size_t size) { int ret; static_opts_t sopts; dynamic_opts_t dopts; LOG("core.posix_memalign.entry", "mem ptr: %p, alignment: %zu, " "size: %zu", memptr, alignment, size); static_opts_init(&sopts); dynamic_opts_init(&dopts); - sopts.bump_empty_alloc = true; + sopts.bump_empty_aligned_alloc = true; sopts.min_alignment = sizeof(void *); sopts.oom_string = ": Error allocating aligned memory: out of memory\n"; sopts.invalid_alignment_string = ": Error allocating aligned memory: invalid alignment\n"; dopts.result = memptr; dopts.num_items = 1; dopts.item_size = size; dopts.alignment = alignment; ret = imalloc(&sopts, &dopts); + if (sopts.slow) { + uintptr_t args[3] = {(uintptr_t)memptr, (uintptr_t)alignment, + (uintptr_t)size}; + hook_invoke_alloc(hook_alloc_posix_memalign, *memptr, + (uintptr_t)ret, args); + } LOG("core.posix_memalign.exit", "result: %d, alloc ptr: %p", ret, *memptr); return ret; } JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN void JEMALLOC_NOTHROW * JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE(2) je_aligned_alloc(size_t alignment, size_t size) { void *ret; static_opts_t sopts; dynamic_opts_t dopts; LOG("core.aligned_alloc.entry", "alignment: %zu, size: %zu\n", alignment, size); static_opts_init(&sopts); dynamic_opts_init(&dopts); - sopts.bump_empty_alloc = true; + sopts.bump_empty_aligned_alloc = true; sopts.null_out_result_on_error = true; sopts.set_errno_on_error = true; sopts.min_alignment = 1; sopts.oom_string = ": Error allocating aligned memory: out of memory\n"; sopts.invalid_alignment_string = ": Error allocating aligned memory: invalid alignment\n"; dopts.result = &ret; dopts.num_items = 1; dopts.item_size = size; dopts.alignment = alignment; imalloc(&sopts, &dopts); + if (sopts.slow) { + uintptr_t args[3] = {(uintptr_t)alignment, (uintptr_t)size}; + hook_invoke_alloc(hook_alloc_aligned_alloc, ret, + (uintptr_t)ret, args); + } LOG("core.aligned_alloc.exit", "result: %p", ret); return ret; } JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN void JEMALLOC_NOTHROW * JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE2(1, 2) je_calloc(size_t num, size_t size) { void *ret; static_opts_t sopts; dynamic_opts_t dopts; LOG("core.calloc.entry", "num: %zu, size: %zu\n", num, size); static_opts_init(&sopts); dynamic_opts_init(&dopts); sopts.may_overflow = true; - sopts.bump_empty_alloc = true; sopts.null_out_result_on_error = true; sopts.set_errno_on_error = true; sopts.oom_string = ": Error in calloc(): out of memory\n"; dopts.result = &ret; dopts.num_items = num; dopts.item_size = size; dopts.zero = true; imalloc(&sopts, &dopts); + if (sopts.slow) { + uintptr_t args[3] = {(uintptr_t)num, (uintptr_t)size}; + hook_invoke_alloc(hook_alloc_calloc, ret, (uintptr_t)ret, args); + } LOG("core.calloc.exit", "result: %p", ret); return ret; } static void * irealloc_prof_sample(tsd_t *tsd, void *old_ptr, size_t old_usize, size_t usize, - prof_tctx_t *tctx) { + prof_tctx_t *tctx, hook_ralloc_args_t *hook_args) { void *p; if (tctx == NULL) { return NULL; } - if (usize <= SMALL_MAXCLASS) { - p = iralloc(tsd, old_ptr, old_usize, LARGE_MINCLASS, 0, false); + if (usize <= SC_SMALL_MAXCLASS) { + p = iralloc(tsd, old_ptr, old_usize, + SC_LARGE_MINCLASS, 0, false, hook_args); if (p == NULL) { return NULL; } arena_prof_promote(tsd_tsdn(tsd), p, usize); } else { - p = iralloc(tsd, old_ptr, old_usize, usize, 0, false); + p = iralloc(tsd, old_ptr, old_usize, usize, 0, false, + hook_args); } return p; } JEMALLOC_ALWAYS_INLINE void * irealloc_prof(tsd_t *tsd, void *old_ptr, size_t old_usize, size_t usize, - alloc_ctx_t *alloc_ctx) { + alloc_ctx_t *alloc_ctx, hook_ralloc_args_t *hook_args) { void *p; bool prof_active; prof_tctx_t *old_tctx, *tctx; prof_active = prof_active_get_unlocked(); old_tctx = prof_tctx_get(tsd_tsdn(tsd), old_ptr, alloc_ctx); tctx = prof_alloc_prep(tsd, usize, prof_active, true); if (unlikely((uintptr_t)tctx != (uintptr_t)1U)) { - p = irealloc_prof_sample(tsd, old_ptr, old_usize, usize, tctx); + p = irealloc_prof_sample(tsd, old_ptr, old_usize, usize, tctx, + hook_args); } else { - p = iralloc(tsd, old_ptr, old_usize, usize, 0, false); + p = iralloc(tsd, old_ptr, old_usize, usize, 0, false, + hook_args); } if (unlikely(p == NULL)) { prof_alloc_rollback(tsd, tctx, true); return NULL; } prof_realloc(tsd, p, usize, tctx, prof_active, true, old_ptr, old_usize, old_tctx); return p; } JEMALLOC_ALWAYS_INLINE void ifree(tsd_t *tsd, void *ptr, tcache_t *tcache, bool slow_path) { if (!slow_path) { tsd_assert_fast(tsd); } check_entry_exit_locking(tsd_tsdn(tsd)); if (tsd_reentrancy_level_get(tsd) != 0) { assert(slow_path); } assert(ptr != NULL); assert(malloc_initialized() || IS_INITIALIZER); alloc_ctx_t alloc_ctx; rtree_ctx_t *rtree_ctx = tsd_rtree_ctx(tsd); rtree_szind_slab_read(tsd_tsdn(tsd), &extents_rtree, rtree_ctx, (uintptr_t)ptr, true, &alloc_ctx.szind, &alloc_ctx.slab); - assert(alloc_ctx.szind != NSIZES); + assert(alloc_ctx.szind != SC_NSIZES); size_t usize; if (config_prof && opt_prof) { usize = sz_index2size(alloc_ctx.szind); prof_free(tsd, ptr, usize, &alloc_ctx); } else if (config_stats) { usize = sz_index2size(alloc_ctx.szind); } if (config_stats) { *tsd_thread_deallocatedp_get(tsd) += usize; } if (likely(!slow_path)) { idalloctm(tsd_tsdn(tsd), ptr, tcache, &alloc_ctx, false, false); } else { idalloctm(tsd_tsdn(tsd), ptr, tcache, &alloc_ctx, false, true); } } JEMALLOC_ALWAYS_INLINE void isfree(tsd_t *tsd, void *ptr, size_t usize, tcache_t *tcache, bool slow_path) { if (!slow_path) { tsd_assert_fast(tsd); } check_entry_exit_locking(tsd_tsdn(tsd)); if (tsd_reentrancy_level_get(tsd) != 0) { assert(slow_path); } assert(ptr != NULL); assert(malloc_initialized() || IS_INITIALIZER); alloc_ctx_t alloc_ctx, *ctx; if (!config_cache_oblivious && ((uintptr_t)ptr & PAGE_MASK) != 0) { /* * When cache_oblivious is disabled and ptr is not page aligned, * the allocation was not sampled -- usize can be used to * determine szind directly. */ alloc_ctx.szind = sz_size2index(usize); alloc_ctx.slab = true; ctx = &alloc_ctx; if (config_debug) { alloc_ctx_t dbg_ctx; rtree_ctx_t *rtree_ctx = tsd_rtree_ctx(tsd); rtree_szind_slab_read(tsd_tsdn(tsd), &extents_rtree, rtree_ctx, (uintptr_t)ptr, true, &dbg_ctx.szind, &dbg_ctx.slab); assert(dbg_ctx.szind == alloc_ctx.szind); assert(dbg_ctx.slab == alloc_ctx.slab); } } else if (config_prof && opt_prof) { rtree_ctx_t *rtree_ctx = tsd_rtree_ctx(tsd); rtree_szind_slab_read(tsd_tsdn(tsd), &extents_rtree, rtree_ctx, (uintptr_t)ptr, true, &alloc_ctx.szind, &alloc_ctx.slab); assert(alloc_ctx.szind == sz_size2index(usize)); ctx = &alloc_ctx; } else { ctx = NULL; } if (config_prof && opt_prof) { prof_free(tsd, ptr, usize, ctx); } if (config_stats) { *tsd_thread_deallocatedp_get(tsd) += usize; } if (likely(!slow_path)) { isdalloct(tsd_tsdn(tsd), ptr, usize, tcache, ctx, false); } else { isdalloct(tsd_tsdn(tsd), ptr, usize, tcache, ctx, true); } } JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN void JEMALLOC_NOTHROW * JEMALLOC_ALLOC_SIZE(2) -je_realloc(void *ptr, size_t size) { +je_realloc(void *ptr, size_t arg_size) { void *ret; tsdn_t *tsdn JEMALLOC_CC_SILENCE_INIT(NULL); size_t usize JEMALLOC_CC_SILENCE_INIT(0); size_t old_usize = 0; + size_t size = arg_size; LOG("core.realloc.entry", "ptr: %p, size: %zu\n", ptr, size); if (unlikely(size == 0)) { size = 1; } if (likely(ptr != NULL)) { assert(malloc_initialized() || IS_INITIALIZER); tsd_t *tsd = tsd_fetch(); check_entry_exit_locking(tsd_tsdn(tsd)); + + hook_ralloc_args_t hook_args = {true, {(uintptr_t)ptr, + (uintptr_t)arg_size, 0, 0}}; + alloc_ctx_t alloc_ctx; rtree_ctx_t *rtree_ctx = tsd_rtree_ctx(tsd); rtree_szind_slab_read(tsd_tsdn(tsd), &extents_rtree, rtree_ctx, (uintptr_t)ptr, true, &alloc_ctx.szind, &alloc_ctx.slab); - assert(alloc_ctx.szind != NSIZES); + assert(alloc_ctx.szind != SC_NSIZES); old_usize = sz_index2size(alloc_ctx.szind); assert(old_usize == isalloc(tsd_tsdn(tsd), ptr)); if (config_prof && opt_prof) { usize = sz_s2u(size); - ret = unlikely(usize == 0 || usize > LARGE_MAXCLASS) ? - NULL : irealloc_prof(tsd, ptr, old_usize, usize, - &alloc_ctx); + if (unlikely(usize == 0 + || usize > SC_LARGE_MAXCLASS)) { + ret = NULL; + } else { + ret = irealloc_prof(tsd, ptr, old_usize, usize, + &alloc_ctx, &hook_args); + } } else { if (config_stats) { usize = sz_s2u(size); } - ret = iralloc(tsd, ptr, old_usize, size, 0, false); + ret = iralloc(tsd, ptr, old_usize, size, 0, false, + &hook_args); } tsdn = tsd_tsdn(tsd); } else { /* realloc(NULL, size) is equivalent to malloc(size). */ - void *ret = je_malloc(size); - LOG("core.realloc.exit", "result: %p", ret); + static_opts_t sopts; + dynamic_opts_t dopts; + + static_opts_init(&sopts); + dynamic_opts_init(&dopts); + + sopts.null_out_result_on_error = true; + sopts.set_errno_on_error = true; + sopts.oom_string = + ": Error in realloc(): out of memory\n"; + + dopts.result = &ret; + dopts.num_items = 1; + dopts.item_size = size; + + imalloc(&sopts, &dopts); + if (sopts.slow) { + uintptr_t args[3] = {(uintptr_t)ptr, arg_size}; + hook_invoke_alloc(hook_alloc_realloc, ret, + (uintptr_t)ret, args); + } + return ret; } if (unlikely(ret == NULL)) { if (config_xmalloc && unlikely(opt_xmalloc)) { malloc_write(": Error in realloc(): " "out of memory\n"); abort(); } set_errno(ENOMEM); } if (config_stats && likely(ret != NULL)) { tsd_t *tsd; assert(usize == isalloc(tsdn, ret)); tsd = tsdn_tsd(tsdn); *tsd_thread_allocatedp_get(tsd) += usize; *tsd_thread_deallocatedp_get(tsd) += old_usize; } UTRACE(ptr, size, ret); check_entry_exit_locking(tsdn); LOG("core.realloc.exit", "result: %p", ret); return ret; } -JEMALLOC_EXPORT void JEMALLOC_NOTHROW -je_free(void *ptr) { - LOG("core.free.entry", "ptr: %p", ptr); - +JEMALLOC_NOINLINE +void +free_default(void *ptr) { UTRACE(ptr, 0, 0); if (likely(ptr != NULL)) { /* * We avoid setting up tsd fully (e.g. tcache, arena binding) * based on only free() calls -- other activities trigger the * minimal to full transition. This is because free() may * happen during thread shutdown after tls deallocation: if a * thread never had any malloc activities until then, a * fully-setup tsd won't be destructed properly. */ tsd_t *tsd = tsd_fetch_min(); check_entry_exit_locking(tsd_tsdn(tsd)); tcache_t *tcache; if (likely(tsd_fast(tsd))) { tsd_assert_fast(tsd); /* Unconditionally get tcache ptr on fast path. */ tcache = tsd_tcachep_get(tsd); ifree(tsd, ptr, tcache, false); } else { if (likely(tsd_reentrancy_level_get(tsd) == 0)) { tcache = tcache_get(tsd); } else { tcache = NULL; } + uintptr_t args_raw[3] = {(uintptr_t)ptr}; + hook_invoke_dalloc(hook_dalloc_free, ptr, args_raw); ifree(tsd, ptr, tcache, true); } check_entry_exit_locking(tsd_tsdn(tsd)); } +} + +JEMALLOC_ALWAYS_INLINE +bool free_fastpath(void *ptr, size_t size, bool size_hint) { + tsd_t *tsd = tsd_get(false); + if (unlikely(!tsd || !tsd_fast(tsd))) { + return false; + } + + tcache_t *tcache = tsd_tcachep_get(tsd); + + alloc_ctx_t alloc_ctx; + /* + * If !config_cache_oblivious, we can check PAGE alignment to + * detect sampled objects. Otherwise addresses are + * randomized, and we have to look it up in the rtree anyway. + * See also isfree(). + */ + if (!size_hint || config_cache_oblivious) { + rtree_ctx_t *rtree_ctx = tsd_rtree_ctx(tsd); + bool res = rtree_szind_slab_read_fast(tsd_tsdn(tsd), &extents_rtree, + rtree_ctx, (uintptr_t)ptr, + &alloc_ctx.szind, &alloc_ctx.slab); + + /* Note: profiled objects will have alloc_ctx.slab set */ + if (!res || !alloc_ctx.slab) { + return false; + } + assert(alloc_ctx.szind != SC_NSIZES); + } else { + /* + * Check for both sizes that are too large, and for sampled objects. + * Sampled objects are always page-aligned. The sampled object check + * will also check for null ptr. + */ + if (size > SC_LOOKUP_MAXCLASS || (((uintptr_t)ptr & PAGE_MASK) == 0)) { + return false; + } + alloc_ctx.szind = sz_size2index_lookup(size); + } + + if (unlikely(ticker_trytick(&tcache->gc_ticker))) { + return false; + } + + cache_bin_t *bin = tcache_small_bin_get(tcache, alloc_ctx.szind); + cache_bin_info_t *bin_info = &tcache_bin_info[alloc_ctx.szind]; + if (!cache_bin_dalloc_easy(bin, bin_info, ptr)) { + return false; + } + + if (config_stats) { + size_t usize = sz_index2size(alloc_ctx.szind); + *tsd_thread_deallocatedp_get(tsd) += usize; + } + + return true; +} + +JEMALLOC_EXPORT void JEMALLOC_NOTHROW +je_free(void *ptr) { + LOG("core.free.entry", "ptr: %p", ptr); + + if (!free_fastpath(ptr, 0, false)) { + free_default(ptr); + } + LOG("core.free.exit", ""); } /* * End malloc(3)-compatible functions. */ /******************************************************************************/ /* * Begin non-standard override functions. */ #ifdef JEMALLOC_OVERRIDE_MEMALIGN JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN void JEMALLOC_NOTHROW * JEMALLOC_ATTR(malloc) je_memalign(size_t alignment, size_t size) { void *ret; static_opts_t sopts; dynamic_opts_t dopts; LOG("core.memalign.entry", "alignment: %zu, size: %zu\n", alignment, size); static_opts_init(&sopts); dynamic_opts_init(&dopts); - sopts.bump_empty_alloc = true; sopts.min_alignment = 1; sopts.oom_string = ": Error allocating aligned memory: out of memory\n"; sopts.invalid_alignment_string = ": Error allocating aligned memory: invalid alignment\n"; sopts.null_out_result_on_error = true; dopts.result = &ret; dopts.num_items = 1; dopts.item_size = size; dopts.alignment = alignment; imalloc(&sopts, &dopts); + if (sopts.slow) { + uintptr_t args[3] = {alignment, size}; + hook_invoke_alloc(hook_alloc_memalign, ret, (uintptr_t)ret, + args); + } LOG("core.memalign.exit", "result: %p", ret); return ret; } #endif #ifdef JEMALLOC_OVERRIDE_VALLOC JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN void JEMALLOC_NOTHROW * JEMALLOC_ATTR(malloc) je_valloc(size_t size) { void *ret; static_opts_t sopts; dynamic_opts_t dopts; LOG("core.valloc.entry", "size: %zu\n", size); static_opts_init(&sopts); dynamic_opts_init(&dopts); - sopts.bump_empty_alloc = true; sopts.null_out_result_on_error = true; sopts.min_alignment = PAGE; sopts.oom_string = ": Error allocating aligned memory: out of memory\n"; sopts.invalid_alignment_string = ": Error allocating aligned memory: invalid alignment\n"; dopts.result = &ret; dopts.num_items = 1; dopts.item_size = size; dopts.alignment = PAGE; imalloc(&sopts, &dopts); + if (sopts.slow) { + uintptr_t args[3] = {size}; + hook_invoke_alloc(hook_alloc_valloc, ret, (uintptr_t)ret, args); + } LOG("core.valloc.exit", "result: %p\n", ret); return ret; } #endif #if defined(JEMALLOC_IS_MALLOC) && defined(JEMALLOC_GLIBC_MALLOC_HOOK) /* * glibc provides the RTLD_DEEPBIND flag for dlopen which can make it possible * to inconsistently reference libc's malloc(3)-compatible functions * (https://bugzilla.mozilla.org/show_bug.cgi?id=493541). * * These definitions interpose hooks in glibc. The functions are actually * passed an extra argument for the caller return address, which will be * ignored. */ JEMALLOC_EXPORT void (*__free_hook)(void *ptr) = je_free; JEMALLOC_EXPORT void *(*__malloc_hook)(size_t size) = je_malloc; JEMALLOC_EXPORT void *(*__realloc_hook)(void *ptr, size_t size) = je_realloc; # ifdef JEMALLOC_GLIBC_MEMALIGN_HOOK JEMALLOC_EXPORT void *(*__memalign_hook)(size_t alignment, size_t size) = je_memalign; # endif # ifdef CPU_COUNT /* * To enable static linking with glibc, the libc specific malloc interface must * be implemented also, so none of glibc's malloc.o functions are added to the * link. */ # define ALIAS(je_fn) __attribute__((alias (#je_fn), used)) /* To force macro expansion of je_ prefix before stringification. */ # define PREALIAS(je_fn) ALIAS(je_fn) # ifdef JEMALLOC_OVERRIDE___LIBC_CALLOC void *__libc_calloc(size_t n, size_t size) PREALIAS(je_calloc); # endif # ifdef JEMALLOC_OVERRIDE___LIBC_FREE void __libc_free(void* ptr) PREALIAS(je_free); # endif # ifdef JEMALLOC_OVERRIDE___LIBC_MALLOC void *__libc_malloc(size_t size) PREALIAS(je_malloc); # endif # ifdef JEMALLOC_OVERRIDE___LIBC_MEMALIGN void *__libc_memalign(size_t align, size_t s) PREALIAS(je_memalign); # endif # ifdef JEMALLOC_OVERRIDE___LIBC_REALLOC void *__libc_realloc(void* ptr, size_t size) PREALIAS(je_realloc); # endif # ifdef JEMALLOC_OVERRIDE___LIBC_VALLOC void *__libc_valloc(size_t size) PREALIAS(je_valloc); # endif # ifdef JEMALLOC_OVERRIDE___POSIX_MEMALIGN int __posix_memalign(void** r, size_t a, size_t s) PREALIAS(je_posix_memalign); # endif # undef PREALIAS # undef ALIAS # endif #endif /* * End non-standard override functions. */ /******************************************************************************/ /* * Begin non-standard functions. */ +#ifdef JEMALLOC_EXPERIMENTAL_SMALLOCX_API + +#define JEMALLOC_SMALLOCX_CONCAT_HELPER(x, y) x ## y +#define JEMALLOC_SMALLOCX_CONCAT_HELPER2(x, y) \ + JEMALLOC_SMALLOCX_CONCAT_HELPER(x, y) + +typedef struct { + void *ptr; + size_t size; +} smallocx_return_t; + JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN +smallocx_return_t JEMALLOC_NOTHROW +/* + * The attribute JEMALLOC_ATTR(malloc) cannot be used due to: + * - https://gcc.gnu.org/bugzilla/show_bug.cgi?id=86488 + */ +JEMALLOC_SMALLOCX_CONCAT_HELPER2(je_smallocx_, JEMALLOC_VERSION_GID_IDENT) + (size_t size, int flags) { + /* + * Note: the attribute JEMALLOC_ALLOC_SIZE(1) cannot be + * used here because it makes writing beyond the `size` + * of the `ptr` undefined behavior, but the objective + * of this function is to allow writing beyond `size` + * up to `smallocx_return_t::size`. + */ + smallocx_return_t ret; + static_opts_t sopts; + dynamic_opts_t dopts; + + LOG("core.smallocx.entry", "size: %zu, flags: %d", size, flags); + + static_opts_init(&sopts); + dynamic_opts_init(&dopts); + + sopts.assert_nonempty_alloc = true; + sopts.null_out_result_on_error = true; + sopts.oom_string = ": Error in mallocx(): out of memory\n"; + sopts.usize = true; + + dopts.result = &ret.ptr; + dopts.num_items = 1; + dopts.item_size = size; + if (unlikely(flags != 0)) { + if ((flags & MALLOCX_LG_ALIGN_MASK) != 0) { + dopts.alignment = MALLOCX_ALIGN_GET_SPECIFIED(flags); + } + + dopts.zero = MALLOCX_ZERO_GET(flags); + + if ((flags & MALLOCX_TCACHE_MASK) != 0) { + if ((flags & MALLOCX_TCACHE_MASK) + == MALLOCX_TCACHE_NONE) { + dopts.tcache_ind = TCACHE_IND_NONE; + } else { + dopts.tcache_ind = MALLOCX_TCACHE_GET(flags); + } + } else { + dopts.tcache_ind = TCACHE_IND_AUTOMATIC; + } + + if ((flags & MALLOCX_ARENA_MASK) != 0) + dopts.arena_ind = MALLOCX_ARENA_GET(flags); + } + + imalloc(&sopts, &dopts); + assert(dopts.usize == je_nallocx(size, flags)); + ret.size = dopts.usize; + + LOG("core.smallocx.exit", "result: %p, size: %zu", ret.ptr, ret.size); + return ret; +} +#undef JEMALLOC_SMALLOCX_CONCAT_HELPER +#undef JEMALLOC_SMALLOCX_CONCAT_HELPER2 +#endif + +JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN void JEMALLOC_NOTHROW * JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE(1) je_mallocx(size_t size, int flags) { void *ret; static_opts_t sopts; dynamic_opts_t dopts; LOG("core.mallocx.entry", "size: %zu, flags: %d", size, flags); static_opts_init(&sopts); dynamic_opts_init(&dopts); sopts.assert_nonempty_alloc = true; sopts.null_out_result_on_error = true; sopts.oom_string = ": Error in mallocx(): out of memory\n"; dopts.result = &ret; dopts.num_items = 1; dopts.item_size = size; if (unlikely(flags != 0)) { if ((flags & MALLOCX_LG_ALIGN_MASK) != 0) { dopts.alignment = MALLOCX_ALIGN_GET_SPECIFIED(flags); } dopts.zero = MALLOCX_ZERO_GET(flags); if ((flags & MALLOCX_TCACHE_MASK) != 0) { if ((flags & MALLOCX_TCACHE_MASK) == MALLOCX_TCACHE_NONE) { dopts.tcache_ind = TCACHE_IND_NONE; } else { dopts.tcache_ind = MALLOCX_TCACHE_GET(flags); } } else { dopts.tcache_ind = TCACHE_IND_AUTOMATIC; } if ((flags & MALLOCX_ARENA_MASK) != 0) dopts.arena_ind = MALLOCX_ARENA_GET(flags); } imalloc(&sopts, &dopts); + if (sopts.slow) { + uintptr_t args[3] = {size, flags}; + hook_invoke_alloc(hook_alloc_mallocx, ret, (uintptr_t)ret, + args); + } LOG("core.mallocx.exit", "result: %p", ret); return ret; } static void * irallocx_prof_sample(tsdn_t *tsdn, void *old_ptr, size_t old_usize, size_t usize, size_t alignment, bool zero, tcache_t *tcache, arena_t *arena, - prof_tctx_t *tctx) { + prof_tctx_t *tctx, hook_ralloc_args_t *hook_args) { void *p; if (tctx == NULL) { return NULL; } - if (usize <= SMALL_MAXCLASS) { - p = iralloct(tsdn, old_ptr, old_usize, LARGE_MINCLASS, - alignment, zero, tcache, arena); + if (usize <= SC_SMALL_MAXCLASS) { + p = iralloct(tsdn, old_ptr, old_usize, + SC_LARGE_MINCLASS, alignment, zero, tcache, + arena, hook_args); if (p == NULL) { return NULL; } arena_prof_promote(tsdn, p, usize); } else { p = iralloct(tsdn, old_ptr, old_usize, usize, alignment, zero, - tcache, arena); + tcache, arena, hook_args); } return p; } JEMALLOC_ALWAYS_INLINE void * irallocx_prof(tsd_t *tsd, void *old_ptr, size_t old_usize, size_t size, size_t alignment, size_t *usize, bool zero, tcache_t *tcache, - arena_t *arena, alloc_ctx_t *alloc_ctx) { + arena_t *arena, alloc_ctx_t *alloc_ctx, hook_ralloc_args_t *hook_args) { void *p; bool prof_active; prof_tctx_t *old_tctx, *tctx; prof_active = prof_active_get_unlocked(); old_tctx = prof_tctx_get(tsd_tsdn(tsd), old_ptr, alloc_ctx); tctx = prof_alloc_prep(tsd, *usize, prof_active, false); if (unlikely((uintptr_t)tctx != (uintptr_t)1U)) { p = irallocx_prof_sample(tsd_tsdn(tsd), old_ptr, old_usize, - *usize, alignment, zero, tcache, arena, tctx); + *usize, alignment, zero, tcache, arena, tctx, hook_args); } else { p = iralloct(tsd_tsdn(tsd), old_ptr, old_usize, size, alignment, - zero, tcache, arena); + zero, tcache, arena, hook_args); } if (unlikely(p == NULL)) { prof_alloc_rollback(tsd, tctx, false); return NULL; } if (p == old_ptr && alignment != 0) { /* * The allocation did not move, so it is possible that the size * class is smaller than would guarantee the requested * alignment, and that the alignment constraint was * serendipitously satisfied. Additionally, old_usize may not * be the same as the current usize because of in-place large * reallocation. Therefore, query the actual value of usize. */ *usize = isalloc(tsd_tsdn(tsd), p); } prof_realloc(tsd, p, *usize, tctx, prof_active, false, old_ptr, old_usize, old_tctx); return p; } JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN void JEMALLOC_NOTHROW * JEMALLOC_ALLOC_SIZE(2) je_rallocx(void *ptr, size_t size, int flags) { void *p; tsd_t *tsd; size_t usize; size_t old_usize; size_t alignment = MALLOCX_ALIGN_GET(flags); bool zero = flags & MALLOCX_ZERO; arena_t *arena; tcache_t *tcache; LOG("core.rallocx.entry", "ptr: %p, size: %zu, flags: %d", ptr, size, flags); assert(ptr != NULL); assert(size != 0); assert(malloc_initialized() || IS_INITIALIZER); tsd = tsd_fetch(); check_entry_exit_locking(tsd_tsdn(tsd)); if (unlikely((flags & MALLOCX_ARENA_MASK) != 0)) { unsigned arena_ind = MALLOCX_ARENA_GET(flags); arena = arena_get(tsd_tsdn(tsd), arena_ind, true); if (unlikely(arena == NULL)) { goto label_oom; } } else { arena = NULL; } if (unlikely((flags & MALLOCX_TCACHE_MASK) != 0)) { if ((flags & MALLOCX_TCACHE_MASK) == MALLOCX_TCACHE_NONE) { tcache = NULL; } else { tcache = tcaches_get(tsd, MALLOCX_TCACHE_GET(flags)); } } else { tcache = tcache_get(tsd); } alloc_ctx_t alloc_ctx; rtree_ctx_t *rtree_ctx = tsd_rtree_ctx(tsd); rtree_szind_slab_read(tsd_tsdn(tsd), &extents_rtree, rtree_ctx, (uintptr_t)ptr, true, &alloc_ctx.szind, &alloc_ctx.slab); - assert(alloc_ctx.szind != NSIZES); + assert(alloc_ctx.szind != SC_NSIZES); old_usize = sz_index2size(alloc_ctx.szind); assert(old_usize == isalloc(tsd_tsdn(tsd), ptr)); + + hook_ralloc_args_t hook_args = {false, {(uintptr_t)ptr, size, flags, + 0}}; if (config_prof && opt_prof) { usize = (alignment == 0) ? sz_s2u(size) : sz_sa2u(size, alignment); - if (unlikely(usize == 0 || usize > LARGE_MAXCLASS)) { + if (unlikely(usize == 0 + || usize > SC_LARGE_MAXCLASS)) { goto label_oom; } p = irallocx_prof(tsd, ptr, old_usize, size, alignment, &usize, - zero, tcache, arena, &alloc_ctx); + zero, tcache, arena, &alloc_ctx, &hook_args); if (unlikely(p == NULL)) { goto label_oom; } } else { p = iralloct(tsd_tsdn(tsd), ptr, old_usize, size, alignment, - zero, tcache, arena); + zero, tcache, arena, &hook_args); if (unlikely(p == NULL)) { goto label_oom; } if (config_stats) { usize = isalloc(tsd_tsdn(tsd), p); } } assert(alignment == 0 || ((uintptr_t)p & (alignment - 1)) == ZU(0)); if (config_stats) { *tsd_thread_allocatedp_get(tsd) += usize; *tsd_thread_deallocatedp_get(tsd) += old_usize; } UTRACE(ptr, size, p); check_entry_exit_locking(tsd_tsdn(tsd)); LOG("core.rallocx.exit", "result: %p", p); return p; label_oom: if (config_xmalloc && unlikely(opt_xmalloc)) { malloc_write(": Error in rallocx(): out of memory\n"); abort(); } UTRACE(ptr, size, 0); check_entry_exit_locking(tsd_tsdn(tsd)); LOG("core.rallocx.exit", "result: %p", NULL); return NULL; } JEMALLOC_ALWAYS_INLINE size_t ixallocx_helper(tsdn_t *tsdn, void *ptr, size_t old_usize, size_t size, size_t extra, size_t alignment, bool zero) { - size_t usize; + size_t newsize; - if (ixalloc(tsdn, ptr, old_usize, size, extra, alignment, zero)) { + if (ixalloc(tsdn, ptr, old_usize, size, extra, alignment, zero, + &newsize)) { return old_usize; } - usize = isalloc(tsdn, ptr); - return usize; + return newsize; } static size_t ixallocx_prof_sample(tsdn_t *tsdn, void *ptr, size_t old_usize, size_t size, size_t extra, size_t alignment, bool zero, prof_tctx_t *tctx) { size_t usize; if (tctx == NULL) { return old_usize; } usize = ixallocx_helper(tsdn, ptr, old_usize, size, extra, alignment, zero); return usize; } JEMALLOC_ALWAYS_INLINE size_t ixallocx_prof(tsd_t *tsd, void *ptr, size_t old_usize, size_t size, size_t extra, size_t alignment, bool zero, alloc_ctx_t *alloc_ctx) { size_t usize_max, usize; bool prof_active; prof_tctx_t *old_tctx, *tctx; prof_active = prof_active_get_unlocked(); old_tctx = prof_tctx_get(tsd_tsdn(tsd), ptr, alloc_ctx); /* * usize isn't knowable before ixalloc() returns when extra is non-zero. * Therefore, compute its maximum possible value and use that in * prof_alloc_prep() to decide whether to capture a backtrace. * prof_realloc() will use the actual usize to decide whether to sample. */ if (alignment == 0) { usize_max = sz_s2u(size+extra); - assert(usize_max > 0 && usize_max <= LARGE_MAXCLASS); + assert(usize_max > 0 + && usize_max <= SC_LARGE_MAXCLASS); } else { usize_max = sz_sa2u(size+extra, alignment); - if (unlikely(usize_max == 0 || usize_max > LARGE_MAXCLASS)) { + if (unlikely(usize_max == 0 + || usize_max > SC_LARGE_MAXCLASS)) { /* * usize_max is out of range, and chances are that * allocation will fail, but use the maximum possible * value and carry on with prof_alloc_prep(), just in * case allocation succeeds. */ - usize_max = LARGE_MAXCLASS; + usize_max = SC_LARGE_MAXCLASS; } } tctx = prof_alloc_prep(tsd, usize_max, prof_active, false); if (unlikely((uintptr_t)tctx != (uintptr_t)1U)) { usize = ixallocx_prof_sample(tsd_tsdn(tsd), ptr, old_usize, size, extra, alignment, zero, tctx); } else { usize = ixallocx_helper(tsd_tsdn(tsd), ptr, old_usize, size, extra, alignment, zero); } if (usize == old_usize) { prof_alloc_rollback(tsd, tctx, false); return usize; } prof_realloc(tsd, ptr, usize, tctx, prof_active, false, ptr, old_usize, old_tctx); return usize; } JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW je_xallocx(void *ptr, size_t size, size_t extra, int flags) { tsd_t *tsd; size_t usize, old_usize; size_t alignment = MALLOCX_ALIGN_GET(flags); bool zero = flags & MALLOCX_ZERO; LOG("core.xallocx.entry", "ptr: %p, size: %zu, extra: %zu, " "flags: %d", ptr, size, extra, flags); assert(ptr != NULL); assert(size != 0); assert(SIZE_T_MAX - size >= extra); assert(malloc_initialized() || IS_INITIALIZER); tsd = tsd_fetch(); check_entry_exit_locking(tsd_tsdn(tsd)); alloc_ctx_t alloc_ctx; rtree_ctx_t *rtree_ctx = tsd_rtree_ctx(tsd); rtree_szind_slab_read(tsd_tsdn(tsd), &extents_rtree, rtree_ctx, (uintptr_t)ptr, true, &alloc_ctx.szind, &alloc_ctx.slab); - assert(alloc_ctx.szind != NSIZES); + assert(alloc_ctx.szind != SC_NSIZES); old_usize = sz_index2size(alloc_ctx.szind); assert(old_usize == isalloc(tsd_tsdn(tsd), ptr)); /* * The API explicitly absolves itself of protecting against (size + * extra) numerical overflow, but we may need to clamp extra to avoid - * exceeding LARGE_MAXCLASS. + * exceeding SC_LARGE_MAXCLASS. * * Ordinarily, size limit checking is handled deeper down, but here we * have to check as part of (size + extra) clamping, since we need the * clamped value in the above helper functions. */ - if (unlikely(size > LARGE_MAXCLASS)) { + if (unlikely(size > SC_LARGE_MAXCLASS)) { usize = old_usize; goto label_not_resized; } - if (unlikely(LARGE_MAXCLASS - size < extra)) { - extra = LARGE_MAXCLASS - size; + if (unlikely(SC_LARGE_MAXCLASS - size < extra)) { + extra = SC_LARGE_MAXCLASS - size; } if (config_prof && opt_prof) { usize = ixallocx_prof(tsd, ptr, old_usize, size, extra, alignment, zero, &alloc_ctx); } else { usize = ixallocx_helper(tsd_tsdn(tsd), ptr, old_usize, size, extra, alignment, zero); } if (unlikely(usize == old_usize)) { goto label_not_resized; } if (config_stats) { *tsd_thread_allocatedp_get(tsd) += usize; *tsd_thread_deallocatedp_get(tsd) += old_usize; } label_not_resized: + if (unlikely(!tsd_fast(tsd))) { + uintptr_t args[4] = {(uintptr_t)ptr, size, extra, flags}; + hook_invoke_expand(hook_expand_xallocx, ptr, old_usize, + usize, (uintptr_t)usize, args); + } + UTRACE(ptr, size, ptr); check_entry_exit_locking(tsd_tsdn(tsd)); LOG("core.xallocx.exit", "result: %zu", usize); return usize; } JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW JEMALLOC_ATTR(pure) -je_sallocx(const void *ptr, UNUSED int flags) { +je_sallocx(const void *ptr, int flags) { size_t usize; tsdn_t *tsdn; LOG("core.sallocx.entry", "ptr: %p, flags: %d", ptr, flags); assert(malloc_initialized() || IS_INITIALIZER); assert(ptr != NULL); tsdn = tsdn_fetch(); check_entry_exit_locking(tsdn); if (config_debug || force_ivsalloc) { usize = ivsalloc(tsdn, ptr); assert(force_ivsalloc || usize != 0); } else { usize = isalloc(tsdn, ptr); } check_entry_exit_locking(tsdn); LOG("core.sallocx.exit", "result: %zu", usize); return usize; } JEMALLOC_EXPORT void JEMALLOC_NOTHROW je_dallocx(void *ptr, int flags) { LOG("core.dallocx.entry", "ptr: %p, flags: %d", ptr, flags); assert(ptr != NULL); assert(malloc_initialized() || IS_INITIALIZER); tsd_t *tsd = tsd_fetch(); bool fast = tsd_fast(tsd); check_entry_exit_locking(tsd_tsdn(tsd)); tcache_t *tcache; if (unlikely((flags & MALLOCX_TCACHE_MASK) != 0)) { /* Not allowed to be reentrant and specify a custom tcache. */ assert(tsd_reentrancy_level_get(tsd) == 0); if ((flags & MALLOCX_TCACHE_MASK) == MALLOCX_TCACHE_NONE) { tcache = NULL; } else { tcache = tcaches_get(tsd, MALLOCX_TCACHE_GET(flags)); } } else { if (likely(fast)) { tcache = tsd_tcachep_get(tsd); assert(tcache == tcache_get(tsd)); } else { if (likely(tsd_reentrancy_level_get(tsd) == 0)) { tcache = tcache_get(tsd); } else { tcache = NULL; } } } UTRACE(ptr, 0, 0); if (likely(fast)) { tsd_assert_fast(tsd); ifree(tsd, ptr, tcache, false); } else { + uintptr_t args_raw[3] = {(uintptr_t)ptr, flags}; + hook_invoke_dalloc(hook_dalloc_dallocx, ptr, args_raw); ifree(tsd, ptr, tcache, true); } check_entry_exit_locking(tsd_tsdn(tsd)); LOG("core.dallocx.exit", ""); } JEMALLOC_ALWAYS_INLINE size_t inallocx(tsdn_t *tsdn, size_t size, int flags) { check_entry_exit_locking(tsdn); size_t usize; if (likely((flags & MALLOCX_LG_ALIGN_MASK) == 0)) { usize = sz_s2u(size); } else { usize = sz_sa2u(size, MALLOCX_ALIGN_GET_SPECIFIED(flags)); } check_entry_exit_locking(tsdn); return usize; } -JEMALLOC_EXPORT void JEMALLOC_NOTHROW -je_sdallocx(void *ptr, size_t size, int flags) { +JEMALLOC_NOINLINE void +sdallocx_default(void *ptr, size_t size, int flags) { assert(ptr != NULL); assert(malloc_initialized() || IS_INITIALIZER); - LOG("core.sdallocx.entry", "ptr: %p, size: %zu, flags: %d", ptr, - size, flags); - tsd_t *tsd = tsd_fetch(); bool fast = tsd_fast(tsd); size_t usize = inallocx(tsd_tsdn(tsd), size, flags); assert(usize == isalloc(tsd_tsdn(tsd), ptr)); check_entry_exit_locking(tsd_tsdn(tsd)); tcache_t *tcache; if (unlikely((flags & MALLOCX_TCACHE_MASK) != 0)) { /* Not allowed to be reentrant and specify a custom tcache. */ assert(tsd_reentrancy_level_get(tsd) == 0); if ((flags & MALLOCX_TCACHE_MASK) == MALLOCX_TCACHE_NONE) { tcache = NULL; } else { tcache = tcaches_get(tsd, MALLOCX_TCACHE_GET(flags)); } } else { if (likely(fast)) { tcache = tsd_tcachep_get(tsd); assert(tcache == tcache_get(tsd)); } else { if (likely(tsd_reentrancy_level_get(tsd) == 0)) { tcache = tcache_get(tsd); } else { tcache = NULL; } } } UTRACE(ptr, 0, 0); if (likely(fast)) { tsd_assert_fast(tsd); isfree(tsd, ptr, usize, tcache, false); } else { + uintptr_t args_raw[3] = {(uintptr_t)ptr, size, flags}; + hook_invoke_dalloc(hook_dalloc_sdallocx, ptr, args_raw); isfree(tsd, ptr, usize, tcache, true); } check_entry_exit_locking(tsd_tsdn(tsd)); +} + +JEMALLOC_EXPORT void JEMALLOC_NOTHROW +je_sdallocx(void *ptr, size_t size, int flags) { + LOG("core.sdallocx.entry", "ptr: %p, size: %zu, flags: %d", ptr, + size, flags); + + if (flags !=0 || !free_fastpath(ptr, size, true)) { + sdallocx_default(ptr, size, flags); + } + LOG("core.sdallocx.exit", ""); } +void JEMALLOC_NOTHROW +je_sdallocx_noflags(void *ptr, size_t size) { + LOG("core.sdallocx.entry", "ptr: %p, size: %zu, flags: 0", ptr, + size); + + if (!free_fastpath(ptr, size, true)) { + sdallocx_default(ptr, size, 0); + } + + LOG("core.sdallocx.exit", ""); +} + JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW JEMALLOC_ATTR(pure) je_nallocx(size_t size, int flags) { size_t usize; tsdn_t *tsdn; assert(size != 0); if (unlikely(malloc_init())) { LOG("core.nallocx.exit", "result: %zu", ZU(0)); return 0; } tsdn = tsdn_fetch(); check_entry_exit_locking(tsdn); usize = inallocx(tsdn, size, flags); - if (unlikely(usize > LARGE_MAXCLASS)) { + if (unlikely(usize > SC_LARGE_MAXCLASS)) { LOG("core.nallocx.exit", "result: %zu", ZU(0)); return 0; } check_entry_exit_locking(tsdn); LOG("core.nallocx.exit", "result: %zu", usize); return usize; } JEMALLOC_EXPORT int JEMALLOC_NOTHROW je_mallctl(const char *name, void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; tsd_t *tsd; LOG("core.mallctl.entry", "name: %s", name); if (unlikely(malloc_init())) { LOG("core.mallctl.exit", "result: %d", EAGAIN); return EAGAIN; } tsd = tsd_fetch(); check_entry_exit_locking(tsd_tsdn(tsd)); ret = ctl_byname(tsd, name, oldp, oldlenp, newp, newlen); check_entry_exit_locking(tsd_tsdn(tsd)); LOG("core.mallctl.exit", "result: %d", ret); return ret; } JEMALLOC_EXPORT int JEMALLOC_NOTHROW je_mallctlnametomib(const char *name, size_t *mibp, size_t *miblenp) { int ret; LOG("core.mallctlnametomib.entry", "name: %s", name); if (unlikely(malloc_init())) { LOG("core.mallctlnametomib.exit", "result: %d", EAGAIN); return EAGAIN; } tsd_t *tsd = tsd_fetch(); check_entry_exit_locking(tsd_tsdn(tsd)); ret = ctl_nametomib(tsd, name, mibp, miblenp); check_entry_exit_locking(tsd_tsdn(tsd)); LOG("core.mallctlnametomib.exit", "result: %d", ret); return ret; } JEMALLOC_EXPORT int JEMALLOC_NOTHROW je_mallctlbymib(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen) { int ret; tsd_t *tsd; LOG("core.mallctlbymib.entry", ""); if (unlikely(malloc_init())) { LOG("core.mallctlbymib.exit", "result: %d", EAGAIN); return EAGAIN; } tsd = tsd_fetch(); check_entry_exit_locking(tsd_tsdn(tsd)); ret = ctl_bymib(tsd, mib, miblen, oldp, oldlenp, newp, newlen); check_entry_exit_locking(tsd_tsdn(tsd)); LOG("core.mallctlbymib.exit", "result: %d", ret); return ret; } JEMALLOC_EXPORT void JEMALLOC_NOTHROW je_malloc_stats_print(void (*write_cb)(void *, const char *), void *cbopaque, const char *opts) { tsdn_t *tsdn; LOG("core.malloc_stats_print.entry", ""); tsdn = tsdn_fetch(); check_entry_exit_locking(tsdn); stats_print(write_cb, cbopaque, opts); check_entry_exit_locking(tsdn); LOG("core.malloc_stats_print.exit", ""); } JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW je_malloc_usable_size(JEMALLOC_USABLE_SIZE_CONST void *ptr) { size_t ret; tsdn_t *tsdn; LOG("core.malloc_usable_size.entry", "ptr: %p", ptr); assert(malloc_initialized() || IS_INITIALIZER); tsdn = tsdn_fetch(); check_entry_exit_locking(tsdn); if (unlikely(ptr == NULL)) { ret = 0; } else { if (config_debug || force_ivsalloc) { ret = ivsalloc(tsdn, ptr); assert(force_ivsalloc || ret != 0); } else { ret = isalloc(tsdn, ptr); } } check_entry_exit_locking(tsdn); LOG("core.malloc_usable_size.exit", "result: %zu", ret); return ret; } /* * End non-standard functions. */ /******************************************************************************/ /* * Begin compatibility functions. */ #define ALLOCM_LG_ALIGN(la) (la) #define ALLOCM_ALIGN(a) (ffsl(a)-1) #define ALLOCM_ZERO ((int)0x40) #define ALLOCM_NO_MOVE ((int)0x80) #define ALLOCM_SUCCESS 0 #define ALLOCM_ERR_OOM 1 #define ALLOCM_ERR_NOT_MOVED 2 int je_allocm(void **ptr, size_t *rsize, size_t size, int flags) { assert(ptr != NULL); void *p = je_mallocx(size, flags); if (p == NULL) { return (ALLOCM_ERR_OOM); } if (rsize != NULL) { *rsize = isalloc(tsdn_fetch(), p); } *ptr = p; return ALLOCM_SUCCESS; } int je_rallocm(void **ptr, size_t *rsize, size_t size, size_t extra, int flags) { assert(ptr != NULL); assert(*ptr != NULL); assert(size != 0); assert(SIZE_T_MAX - size >= extra); int ret; bool no_move = flags & ALLOCM_NO_MOVE; if (no_move) { size_t usize = je_xallocx(*ptr, size, extra, flags); ret = (usize >= size) ? ALLOCM_SUCCESS : ALLOCM_ERR_NOT_MOVED; if (rsize != NULL) { *rsize = usize; } } else { void *p = je_rallocx(*ptr, size+extra, flags); if (p != NULL) { *ptr = p; ret = ALLOCM_SUCCESS; } else { ret = ALLOCM_ERR_OOM; } if (rsize != NULL) { *rsize = isalloc(tsdn_fetch(), *ptr); } } return ret; } int je_sallocm(const void *ptr, size_t *rsize, int flags) { assert(rsize != NULL); *rsize = je_sallocx(ptr, flags); return ALLOCM_SUCCESS; } int je_dallocm(void *ptr, int flags) { je_dallocx(ptr, flags); return ALLOCM_SUCCESS; } int je_nallocm(size_t *rsize, size_t size, int flags) { size_t usize = je_nallocx(size, flags); if (usize == 0) { return ALLOCM_ERR_OOM; } if (rsize != NULL) { *rsize = usize; } return ALLOCM_SUCCESS; } #undef ALLOCM_LG_ALIGN #undef ALLOCM_ALIGN #undef ALLOCM_ZERO #undef ALLOCM_NO_MOVE #undef ALLOCM_SUCCESS #undef ALLOCM_ERR_OOM #undef ALLOCM_ERR_NOT_MOVED /* * End compatibility functions. */ /******************************************************************************/ /* * The following functions are used by threading libraries for protection of * malloc during fork(). */ /* * If an application creates a thread before doing any allocation in the main * thread, then calls fork(2) in the main thread followed by memory allocation * in the child process, a race can occur that results in deadlock within the * child: the main thread may have forked while the created thread had * partially initialized the allocator. Ordinarily jemalloc prevents * fork/malloc races via the following functions it registers during * initialization using pthread_atfork(), but of course that does no good if * the allocator isn't fully initialized at fork time. The following library * constructor is a partial solution to this problem. It may still be possible * to trigger the deadlock described above, but doing so would involve forking * via a library constructor that runs before jemalloc's runs. */ #ifndef JEMALLOC_JET JEMALLOC_ATTR(constructor) static void jemalloc_constructor(void) { malloc_init(); } #endif #ifndef JEMALLOC_MUTEX_INIT_CB void jemalloc_prefork(void) #else JEMALLOC_EXPORT void _malloc_prefork(void) #endif { tsd_t *tsd; unsigned i, j, narenas; arena_t *arena; #ifdef JEMALLOC_MUTEX_INIT_CB if (!malloc_initialized()) { return; } #endif assert(malloc_initialized()); tsd = tsd_fetch(); narenas = narenas_total_get(); witness_prefork(tsd_witness_tsdp_get(tsd)); /* Acquire all mutexes in a safe order. */ ctl_prefork(tsd_tsdn(tsd)); tcache_prefork(tsd_tsdn(tsd)); malloc_mutex_prefork(tsd_tsdn(tsd), &arenas_lock); if (have_background_thread) { background_thread_prefork0(tsd_tsdn(tsd)); } prof_prefork0(tsd_tsdn(tsd)); if (have_background_thread) { background_thread_prefork1(tsd_tsdn(tsd)); } /* Break arena prefork into stages to preserve lock order. */ for (i = 0; i < 8; i++) { for (j = 0; j < narenas; j++) { if ((arena = arena_get(tsd_tsdn(tsd), j, false)) != NULL) { switch (i) { case 0: arena_prefork0(tsd_tsdn(tsd), arena); break; case 1: arena_prefork1(tsd_tsdn(tsd), arena); break; case 2: arena_prefork2(tsd_tsdn(tsd), arena); break; case 3: arena_prefork3(tsd_tsdn(tsd), arena); break; case 4: arena_prefork4(tsd_tsdn(tsd), arena); break; case 5: arena_prefork5(tsd_tsdn(tsd), arena); break; case 6: arena_prefork6(tsd_tsdn(tsd), arena); break; case 7: arena_prefork7(tsd_tsdn(tsd), arena); break; default: not_reached(); } } } } prof_prefork1(tsd_tsdn(tsd)); + tsd_prefork(tsd); } #ifndef JEMALLOC_MUTEX_INIT_CB void jemalloc_postfork_parent(void) #else JEMALLOC_EXPORT void _malloc_postfork(void) #endif { tsd_t *tsd; unsigned i, narenas; #ifdef JEMALLOC_MUTEX_INIT_CB if (!malloc_initialized()) { return; } #endif assert(malloc_initialized()); tsd = tsd_fetch(); + tsd_postfork_parent(tsd); + witness_postfork_parent(tsd_witness_tsdp_get(tsd)); /* Release all mutexes, now that fork() has completed. */ for (i = 0, narenas = narenas_total_get(); i < narenas; i++) { arena_t *arena; if ((arena = arena_get(tsd_tsdn(tsd), i, false)) != NULL) { arena_postfork_parent(tsd_tsdn(tsd), arena); } } prof_postfork_parent(tsd_tsdn(tsd)); if (have_background_thread) { background_thread_postfork_parent(tsd_tsdn(tsd)); } malloc_mutex_postfork_parent(tsd_tsdn(tsd), &arenas_lock); tcache_postfork_parent(tsd_tsdn(tsd)); ctl_postfork_parent(tsd_tsdn(tsd)); } void jemalloc_postfork_child(void) { tsd_t *tsd; unsigned i, narenas; assert(malloc_initialized()); tsd = tsd_fetch(); + + tsd_postfork_child(tsd); witness_postfork_child(tsd_witness_tsdp_get(tsd)); /* Release all mutexes, now that fork() has completed. */ for (i = 0, narenas = narenas_total_get(); i < narenas; i++) { arena_t *arena; if ((arena = arena_get(tsd_tsdn(tsd), i, false)) != NULL) { arena_postfork_child(tsd_tsdn(tsd), arena); } } prof_postfork_child(tsd_tsdn(tsd)); if (have_background_thread) { background_thread_postfork_child(tsd_tsdn(tsd)); } malloc_mutex_postfork_child(tsd_tsdn(tsd), &arenas_lock); tcache_postfork_child(tsd_tsdn(tsd)); ctl_postfork_child(tsd_tsdn(tsd)); } void _malloc_first_thread(void) { (void)malloc_mutex_first_thread(); } /******************************************************************************/ Index: head/contrib/jemalloc/src/large.c =================================================================== --- head/contrib/jemalloc/src/large.c (revision 360232) +++ head/contrib/jemalloc/src/large.c (revision 360233) @@ -1,371 +1,395 @@ #define JEMALLOC_LARGE_C_ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/jemalloc_internal_includes.h" #include "jemalloc/internal/assert.h" #include "jemalloc/internal/extent_mmap.h" #include "jemalloc/internal/mutex.h" #include "jemalloc/internal/rtree.h" #include "jemalloc/internal/util.h" /******************************************************************************/ void * large_malloc(tsdn_t *tsdn, arena_t *arena, size_t usize, bool zero) { assert(usize == sz_s2u(usize)); return large_palloc(tsdn, arena, usize, CACHELINE, zero); } void * large_palloc(tsdn_t *tsdn, arena_t *arena, size_t usize, size_t alignment, bool zero) { size_t ausize; extent_t *extent; bool is_zeroed; UNUSED bool idump JEMALLOC_CC_SILENCE_INIT(false); assert(!tsdn_null(tsdn) || arena != NULL); ausize = sz_sa2u(usize, alignment); - if (unlikely(ausize == 0 || ausize > LARGE_MAXCLASS)) { + if (unlikely(ausize == 0 || ausize > SC_LARGE_MAXCLASS)) { return NULL; } if (config_fill && unlikely(opt_zero)) { zero = true; } /* * Copy zero into is_zeroed and pass the copy when allocating the * extent, so that it is possible to make correct junk/zero fill * decisions below, even if is_zeroed ends up true when zero is false. */ is_zeroed = zero; if (likely(!tsdn_null(tsdn))) { - arena = arena_choose(tsdn_tsd(tsdn), arena); + arena = arena_choose_maybe_huge(tsdn_tsd(tsdn), arena, usize); } if (unlikely(arena == NULL) || (extent = arena_extent_alloc_large(tsdn, arena, usize, alignment, &is_zeroed)) == NULL) { return NULL; } /* See comments in arena_bin_slabs_full_insert(). */ if (!arena_is_auto(arena)) { /* Insert extent into large. */ malloc_mutex_lock(tsdn, &arena->large_mtx); extent_list_append(&arena->large, extent); malloc_mutex_unlock(tsdn, &arena->large_mtx); } if (config_prof && arena_prof_accum(tsdn, arena, usize)) { prof_idump(tsdn); } if (zero) { assert(is_zeroed); } else if (config_fill && unlikely(opt_junk_alloc)) { memset(extent_addr_get(extent), JEMALLOC_ALLOC_JUNK, extent_usize_get(extent)); } arena_decay_tick(tsdn, arena); return extent_addr_get(extent); } static void large_dalloc_junk_impl(void *ptr, size_t size) { memset(ptr, JEMALLOC_FREE_JUNK, size); } large_dalloc_junk_t *JET_MUTABLE large_dalloc_junk = large_dalloc_junk_impl; static void large_dalloc_maybe_junk_impl(void *ptr, size_t size) { if (config_fill && have_dss && unlikely(opt_junk_free)) { /* * Only bother junk filling if the extent isn't about to be * unmapped. */ if (opt_retain || (have_dss && extent_in_dss(ptr))) { large_dalloc_junk(ptr, size); } } } large_dalloc_maybe_junk_t *JET_MUTABLE large_dalloc_maybe_junk = large_dalloc_maybe_junk_impl; static bool large_ralloc_no_move_shrink(tsdn_t *tsdn, extent_t *extent, size_t usize) { arena_t *arena = extent_arena_get(extent); size_t oldusize = extent_usize_get(extent); extent_hooks_t *extent_hooks = extent_hooks_get(arena); size_t diff = extent_size_get(extent) - (usize + sz_large_pad); assert(oldusize > usize); if (extent_hooks->split == NULL) { return true; } /* Split excess pages. */ if (diff != 0) { extent_t *trail = extent_split_wrapper(tsdn, arena, &extent_hooks, extent, usize + sz_large_pad, - sz_size2index(usize), false, diff, NSIZES, false); + sz_size2index(usize), false, diff, SC_NSIZES, false); if (trail == NULL) { return true; } if (config_fill && unlikely(opt_junk_free)) { large_dalloc_maybe_junk(extent_addr_get(trail), extent_size_get(trail)); } arena_extents_dirty_dalloc(tsdn, arena, &extent_hooks, trail); } arena_extent_ralloc_large_shrink(tsdn, arena, extent, oldusize); return false; } static bool large_ralloc_no_move_expand(tsdn_t *tsdn, extent_t *extent, size_t usize, bool zero) { arena_t *arena = extent_arena_get(extent); size_t oldusize = extent_usize_get(extent); extent_hooks_t *extent_hooks = extent_hooks_get(arena); size_t trailsize = usize - oldusize; if (extent_hooks->merge == NULL) { return true; } if (config_fill && unlikely(opt_zero)) { zero = true; } /* * Copy zero into is_zeroed_trail and pass the copy when allocating the * extent, so that it is possible to make correct junk/zero fill * decisions below, even if is_zeroed_trail ends up true when zero is * false. */ bool is_zeroed_trail = zero; bool commit = true; extent_t *trail; bool new_mapping; if ((trail = extents_alloc(tsdn, arena, &extent_hooks, &arena->extents_dirty, extent_past_get(extent), trailsize, 0, - CACHELINE, false, NSIZES, &is_zeroed_trail, &commit)) != NULL + CACHELINE, false, SC_NSIZES, &is_zeroed_trail, &commit)) != NULL || (trail = extents_alloc(tsdn, arena, &extent_hooks, &arena->extents_muzzy, extent_past_get(extent), trailsize, 0, - CACHELINE, false, NSIZES, &is_zeroed_trail, &commit)) != NULL) { + CACHELINE, false, SC_NSIZES, &is_zeroed_trail, &commit)) != NULL) { if (config_stats) { new_mapping = false; } } else { if ((trail = extent_alloc_wrapper(tsdn, arena, &extent_hooks, extent_past_get(extent), trailsize, 0, CACHELINE, false, - NSIZES, &is_zeroed_trail, &commit)) == NULL) { + SC_NSIZES, &is_zeroed_trail, &commit)) == NULL) { return true; } if (config_stats) { new_mapping = true; } } if (extent_merge_wrapper(tsdn, arena, &extent_hooks, extent, trail)) { extent_dalloc_wrapper(tsdn, arena, &extent_hooks, trail); return true; } rtree_ctx_t rtree_ctx_fallback; rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); szind_t szind = sz_size2index(usize); extent_szind_set(extent, szind); rtree_szind_slab_update(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)extent_addr_get(extent), szind, false); if (config_stats && new_mapping) { arena_stats_mapped_add(tsdn, &arena->stats, trailsize); } if (zero) { if (config_cache_oblivious) { /* * Zero the trailing bytes of the original allocation's * last page, since they are in an indeterminate state. * There will always be trailing bytes, because ptr's * offset from the beginning of the extent is a multiple * of CACHELINE in [0 .. PAGE). */ void *zbase = (void *) ((uintptr_t)extent_addr_get(extent) + oldusize); void *zpast = PAGE_ADDR2BASE((void *)((uintptr_t)zbase + PAGE)); size_t nzero = (uintptr_t)zpast - (uintptr_t)zbase; assert(nzero > 0); memset(zbase, 0, nzero); } assert(is_zeroed_trail); } else if (config_fill && unlikely(opt_junk_alloc)) { memset((void *)((uintptr_t)extent_addr_get(extent) + oldusize), JEMALLOC_ALLOC_JUNK, usize - oldusize); } arena_extent_ralloc_large_expand(tsdn, arena, extent, oldusize); return false; } bool large_ralloc_no_move(tsdn_t *tsdn, extent_t *extent, size_t usize_min, size_t usize_max, bool zero) { size_t oldusize = extent_usize_get(extent); /* The following should have been caught by callers. */ - assert(usize_min > 0 && usize_max <= LARGE_MAXCLASS); + assert(usize_min > 0 && usize_max <= SC_LARGE_MAXCLASS); /* Both allocation sizes must be large to avoid a move. */ - assert(oldusize >= LARGE_MINCLASS && usize_max >= LARGE_MINCLASS); + assert(oldusize >= SC_LARGE_MINCLASS + && usize_max >= SC_LARGE_MINCLASS); if (usize_max > oldusize) { /* Attempt to expand the allocation in-place. */ if (!large_ralloc_no_move_expand(tsdn, extent, usize_max, zero)) { arena_decay_tick(tsdn, extent_arena_get(extent)); return false; } /* Try again, this time with usize_min. */ if (usize_min < usize_max && usize_min > oldusize && large_ralloc_no_move_expand(tsdn, extent, usize_min, zero)) { arena_decay_tick(tsdn, extent_arena_get(extent)); return false; } } /* * Avoid moving the allocation if the existing extent size accommodates * the new size. */ if (oldusize >= usize_min && oldusize <= usize_max) { arena_decay_tick(tsdn, extent_arena_get(extent)); return false; } /* Attempt to shrink the allocation in-place. */ if (oldusize > usize_max) { if (!large_ralloc_no_move_shrink(tsdn, extent, usize_max)) { arena_decay_tick(tsdn, extent_arena_get(extent)); return false; } } return true; } static void * large_ralloc_move_helper(tsdn_t *tsdn, arena_t *arena, size_t usize, size_t alignment, bool zero) { if (alignment <= CACHELINE) { return large_malloc(tsdn, arena, usize, zero); } return large_palloc(tsdn, arena, usize, alignment, zero); } void * -large_ralloc(tsdn_t *tsdn, arena_t *arena, extent_t *extent, size_t usize, - size_t alignment, bool zero, tcache_t *tcache) { - size_t oldusize = extent_usize_get(extent); +large_ralloc(tsdn_t *tsdn, arena_t *arena, void *ptr, size_t usize, + size_t alignment, bool zero, tcache_t *tcache, + hook_ralloc_args_t *hook_args) { + extent_t *extent = iealloc(tsdn, ptr); + size_t oldusize = extent_usize_get(extent); /* The following should have been caught by callers. */ - assert(usize > 0 && usize <= LARGE_MAXCLASS); + assert(usize > 0 && usize <= SC_LARGE_MAXCLASS); /* Both allocation sizes must be large to avoid a move. */ - assert(oldusize >= LARGE_MINCLASS && usize >= LARGE_MINCLASS); + assert(oldusize >= SC_LARGE_MINCLASS + && usize >= SC_LARGE_MINCLASS); /* Try to avoid moving the allocation. */ if (!large_ralloc_no_move(tsdn, extent, usize, usize, zero)) { + hook_invoke_expand(hook_args->is_realloc + ? hook_expand_realloc : hook_expand_rallocx, ptr, oldusize, + usize, (uintptr_t)ptr, hook_args->args); return extent_addr_get(extent); } /* * usize and old size are different enough that we need to use a * different size class. In that case, fall back to allocating new * space and copying. */ void *ret = large_ralloc_move_helper(tsdn, arena, usize, alignment, zero); if (ret == NULL) { return NULL; } + hook_invoke_alloc(hook_args->is_realloc + ? hook_alloc_realloc : hook_alloc_rallocx, ret, (uintptr_t)ret, + hook_args->args); + hook_invoke_dalloc(hook_args->is_realloc + ? hook_dalloc_realloc : hook_dalloc_rallocx, ptr, hook_args->args); + size_t copysize = (usize < oldusize) ? usize : oldusize; memcpy(ret, extent_addr_get(extent), copysize); isdalloct(tsdn, extent_addr_get(extent), oldusize, tcache, NULL, true); return ret; } /* * junked_locked indicates whether the extent's data have been junk-filled, and * whether the arena's large_mtx is currently held. */ static void large_dalloc_prep_impl(tsdn_t *tsdn, arena_t *arena, extent_t *extent, bool junked_locked) { if (!junked_locked) { /* See comments in arena_bin_slabs_full_insert(). */ if (!arena_is_auto(arena)) { malloc_mutex_lock(tsdn, &arena->large_mtx); extent_list_remove(&arena->large, extent); malloc_mutex_unlock(tsdn, &arena->large_mtx); } large_dalloc_maybe_junk(extent_addr_get(extent), extent_usize_get(extent)); } else { - malloc_mutex_assert_owner(tsdn, &arena->large_mtx); + /* Only hold the large_mtx if necessary. */ if (!arena_is_auto(arena)) { + malloc_mutex_assert_owner(tsdn, &arena->large_mtx); extent_list_remove(&arena->large, extent); } } arena_extent_dalloc_large_prep(tsdn, arena, extent); } static void large_dalloc_finish_impl(tsdn_t *tsdn, arena_t *arena, extent_t *extent) { extent_hooks_t *extent_hooks = EXTENT_HOOKS_INITIALIZER; arena_extents_dirty_dalloc(tsdn, arena, &extent_hooks, extent); } void large_dalloc_prep_junked_locked(tsdn_t *tsdn, extent_t *extent) { large_dalloc_prep_impl(tsdn, extent_arena_get(extent), extent, true); } void large_dalloc_finish(tsdn_t *tsdn, extent_t *extent) { large_dalloc_finish_impl(tsdn, extent_arena_get(extent), extent); } void large_dalloc(tsdn_t *tsdn, extent_t *extent) { arena_t *arena = extent_arena_get(extent); large_dalloc_prep_impl(tsdn, arena, extent, false); large_dalloc_finish_impl(tsdn, arena, extent); arena_decay_tick(tsdn, arena); } size_t large_salloc(tsdn_t *tsdn, const extent_t *extent) { return extent_usize_get(extent); } prof_tctx_t * large_prof_tctx_get(tsdn_t *tsdn, const extent_t *extent) { return extent_prof_tctx_get(extent); } void large_prof_tctx_set(tsdn_t *tsdn, extent_t *extent, prof_tctx_t *tctx) { extent_prof_tctx_set(extent, tctx); } void large_prof_tctx_reset(tsdn_t *tsdn, extent_t *extent) { large_prof_tctx_set(tsdn, extent, (prof_tctx_t *)(uintptr_t)1U); +} + +nstime_t +large_prof_alloc_time_get(const extent_t *extent) { + return extent_prof_alloc_time_get(extent); +} + +void +large_prof_alloc_time_set(extent_t *extent, nstime_t t) { + extent_prof_alloc_time_set(extent, t); } Index: head/contrib/jemalloc/src/malloc_io.c =================================================================== --- head/contrib/jemalloc/src/malloc_io.c (revision 360232) +++ head/contrib/jemalloc/src/malloc_io.c (revision 360233) @@ -1,690 +1,689 @@ #define JEMALLOC_MALLOC_IO_C_ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/jemalloc_internal_includes.h" #include "jemalloc/internal/malloc_io.h" #include "jemalloc/internal/util.h" #ifdef assert # undef assert #endif #ifdef not_reached # undef not_reached #endif #ifdef not_implemented # undef not_implemented #endif #ifdef assert_not_implemented # undef assert_not_implemented #endif /* * Define simple versions of assertion macros that won't recurse in case * of assertion failures in malloc_*printf(). */ #define assert(e) do { \ if (config_debug && !(e)) { \ malloc_write(": Failed assertion\n"); \ abort(); \ } \ } while (0) #define not_reached() do { \ if (config_debug) { \ malloc_write(": Unreachable code reached\n"); \ abort(); \ } \ unreachable(); \ } while (0) #define not_implemented() do { \ if (config_debug) { \ malloc_write(": Not implemented\n"); \ abort(); \ } \ } while (0) #define assert_not_implemented(e) do { \ if (unlikely(config_debug && !(e))) { \ not_implemented(); \ } \ } while (0) /******************************************************************************/ /* Function prototypes for non-inline static functions. */ static void wrtmessage(void *cbopaque, const char *s); #define U2S_BUFSIZE ((1U << (LG_SIZEOF_INTMAX_T + 3)) + 1) static char *u2s(uintmax_t x, unsigned base, bool uppercase, char *s, size_t *slen_p); #define D2S_BUFSIZE (1 + U2S_BUFSIZE) static char *d2s(intmax_t x, char sign, char *s, size_t *slen_p); #define O2S_BUFSIZE (1 + U2S_BUFSIZE) static char *o2s(uintmax_t x, bool alt_form, char *s, size_t *slen_p); #define X2S_BUFSIZE (2 + U2S_BUFSIZE) static char *x2s(uintmax_t x, bool alt_form, bool uppercase, char *s, size_t *slen_p); /******************************************************************************/ /* malloc_message() setup. */ static void wrtmessage(void *cbopaque, const char *s) { malloc_write_fd(STDERR_FILENO, s, strlen(s)); } JEMALLOC_EXPORT void (*je_malloc_message)(void *, const char *s); JEMALLOC_ATTR(visibility("hidden")) void wrtmessage_1_0(const char *s1, const char *s2, const char *s3, const char *s4) { wrtmessage(NULL, s1); wrtmessage(NULL, s2); wrtmessage(NULL, s3); wrtmessage(NULL, s4); } void (*__malloc_message_1_0)(const char *s1, const char *s2, const char *s3, const char *s4) = wrtmessage_1_0; __sym_compat(_malloc_message, __malloc_message_1_0, FBSD_1.0); /* * Wrapper around malloc_message() that avoids the need for * je_malloc_message(...) throughout the code. */ void malloc_write(const char *s) { if (je_malloc_message != NULL) { je_malloc_message(NULL, s); } else { wrtmessage(NULL, s); } } /* * glibc provides a non-standard strerror_r() when _GNU_SOURCE is defined, so * provide a wrapper. */ int buferror(int err, char *buf, size_t buflen) { #ifdef _WIN32 FormatMessageA(FORMAT_MESSAGE_FROM_SYSTEM, NULL, err, 0, (LPSTR)buf, (DWORD)buflen, NULL); return 0; #elif defined(JEMALLOC_STRERROR_R_RETURNS_CHAR_WITH_GNU_SOURCE) && defined(_GNU_SOURCE) char *b = strerror_r(err, buf, buflen); if (b != buf) { strncpy(buf, b, buflen); buf[buflen-1] = '\0'; } return 0; #else return strerror_r(err, buf, buflen); #endif } uintmax_t malloc_strtoumax(const char *restrict nptr, char **restrict endptr, int base) { uintmax_t ret, digit; unsigned b; bool neg; const char *p, *ns; p = nptr; if (base < 0 || base == 1 || base > 36) { ns = p; set_errno(EINVAL); ret = UINTMAX_MAX; goto label_return; } b = base; /* Swallow leading whitespace and get sign, if any. */ neg = false; while (true) { switch (*p) { case '\t': case '\n': case '\v': case '\f': case '\r': case ' ': p++; break; case '-': neg = true; /* Fall through. */ case '+': p++; /* Fall through. */ default: goto label_prefix; } } /* Get prefix, if any. */ label_prefix: /* * Note where the first non-whitespace/sign character is so that it is * possible to tell whether any digits are consumed (e.g., " 0" vs. * " -x"). */ ns = p; if (*p == '0') { switch (p[1]) { case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': if (b == 0) { b = 8; } if (b == 8) { p++; } break; case 'X': case 'x': switch (p[2]) { case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9': case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': case 'a': case 'b': case 'c': case 'd': case 'e': case 'f': if (b == 0) { b = 16; } if (b == 16) { p += 2; } break; default: break; } break; default: p++; ret = 0; goto label_return; } } if (b == 0) { b = 10; } /* Convert. */ ret = 0; while ((*p >= '0' && *p <= '9' && (digit = *p - '0') < b) || (*p >= 'A' && *p <= 'Z' && (digit = 10 + *p - 'A') < b) || (*p >= 'a' && *p <= 'z' && (digit = 10 + *p - 'a') < b)) { uintmax_t pret = ret; ret *= b; ret += digit; if (ret < pret) { /* Overflow. */ set_errno(ERANGE); ret = UINTMAX_MAX; goto label_return; } p++; } if (neg) { ret = (uintmax_t)(-((intmax_t)ret)); } if (p == ns) { /* No conversion performed. */ set_errno(EINVAL); ret = UINTMAX_MAX; goto label_return; } label_return: if (endptr != NULL) { if (p == ns) { /* No characters were converted. */ *endptr = (char *)nptr; } else { *endptr = (char *)p; } } return ret; } static char * u2s(uintmax_t x, unsigned base, bool uppercase, char *s, size_t *slen_p) { unsigned i; i = U2S_BUFSIZE - 1; s[i] = '\0'; switch (base) { case 10: do { i--; s[i] = "0123456789"[x % (uint64_t)10]; x /= (uint64_t)10; } while (x > 0); break; case 16: { const char *digits = (uppercase) ? "0123456789ABCDEF" : "0123456789abcdef"; do { i--; s[i] = digits[x & 0xf]; x >>= 4; } while (x > 0); break; } default: { const char *digits = (uppercase) ? "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ" : "0123456789abcdefghijklmnopqrstuvwxyz"; assert(base >= 2 && base <= 36); do { i--; s[i] = digits[x % (uint64_t)base]; x /= (uint64_t)base; } while (x > 0); }} *slen_p = U2S_BUFSIZE - 1 - i; return &s[i]; } static char * d2s(intmax_t x, char sign, char *s, size_t *slen_p) { bool neg; if ((neg = (x < 0))) { x = -x; } s = u2s(x, 10, false, s, slen_p); if (neg) { sign = '-'; } switch (sign) { case '-': if (!neg) { break; } /* Fall through. */ case ' ': case '+': s--; (*slen_p)++; *s = sign; break; default: not_reached(); } return s; } static char * o2s(uintmax_t x, bool alt_form, char *s, size_t *slen_p) { s = u2s(x, 8, false, s, slen_p); if (alt_form && *s != '0') { s--; (*slen_p)++; *s = '0'; } return s; } static char * x2s(uintmax_t x, bool alt_form, bool uppercase, char *s, size_t *slen_p) { s = u2s(x, 16, uppercase, s, slen_p); if (alt_form) { s -= 2; (*slen_p) += 2; memcpy(s, uppercase ? "0X" : "0x", 2); } return s; } size_t malloc_vsnprintf(char *str, size_t size, const char *format, va_list ap) { size_t i; const char *f; #define APPEND_C(c) do { \ if (i < size) { \ str[i] = (c); \ } \ i++; \ } while (0) #define APPEND_S(s, slen) do { \ if (i < size) { \ size_t cpylen = (slen <= size - i) ? slen : size - i; \ memcpy(&str[i], s, cpylen); \ } \ i += slen; \ } while (0) #define APPEND_PADDED_S(s, slen, width, left_justify) do { \ /* Left padding. */ \ size_t pad_len = (width == -1) ? 0 : ((slen < (size_t)width) ? \ (size_t)width - slen : 0); \ if (!left_justify && pad_len != 0) { \ size_t j; \ for (j = 0; j < pad_len; j++) { \ APPEND_C(' '); \ } \ } \ /* Value. */ \ APPEND_S(s, slen); \ /* Right padding. */ \ if (left_justify && pad_len != 0) { \ size_t j; \ for (j = 0; j < pad_len; j++) { \ APPEND_C(' '); \ } \ } \ } while (0) #define GET_ARG_NUMERIC(val, len) do { \ switch ((unsigned char)len) { \ case '?': \ val = va_arg(ap, int); \ break; \ case '?' | 0x80: \ val = va_arg(ap, unsigned int); \ break; \ case 'l': \ val = va_arg(ap, long); \ break; \ case 'l' | 0x80: \ val = va_arg(ap, unsigned long); \ break; \ case 'q': \ val = va_arg(ap, long long); \ break; \ case 'q' | 0x80: \ val = va_arg(ap, unsigned long long); \ break; \ case 'j': \ val = va_arg(ap, intmax_t); \ break; \ case 'j' | 0x80: \ val = va_arg(ap, uintmax_t); \ break; \ case 't': \ val = va_arg(ap, ptrdiff_t); \ break; \ case 'z': \ val = va_arg(ap, ssize_t); \ break; \ case 'z' | 0x80: \ val = va_arg(ap, size_t); \ break; \ case 'p': /* Synthetic; used for %p. */ \ val = va_arg(ap, uintptr_t); \ break; \ default: \ not_reached(); \ val = 0; \ } \ } while (0) i = 0; f = format; while (true) { switch (*f) { case '\0': goto label_out; case '%': { bool alt_form = false; bool left_justify = false; bool plus_space = false; bool plus_plus = false; int prec = -1; int width = -1; unsigned char len = '?'; char *s; size_t slen; f++; /* Flags. */ while (true) { switch (*f) { case '#': assert(!alt_form); alt_form = true; break; case '-': assert(!left_justify); left_justify = true; break; case ' ': assert(!plus_space); plus_space = true; break; case '+': assert(!plus_plus); plus_plus = true; break; default: goto label_width; } f++; } /* Width. */ label_width: switch (*f) { case '*': width = va_arg(ap, int); f++; if (width < 0) { left_justify = true; width = -width; } break; case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9': { uintmax_t uwidth; set_errno(0); uwidth = malloc_strtoumax(f, (char **)&f, 10); assert(uwidth != UINTMAX_MAX || get_errno() != ERANGE); width = (int)uwidth; break; } default: break; } /* Width/precision separator. */ if (*f == '.') { f++; } else { goto label_length; } /* Precision. */ switch (*f) { case '*': prec = va_arg(ap, int); f++; break; case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9': { uintmax_t uprec; set_errno(0); uprec = malloc_strtoumax(f, (char **)&f, 10); assert(uprec != UINTMAX_MAX || get_errno() != ERANGE); prec = (int)uprec; break; } default: break; } /* Length. */ label_length: switch (*f) { case 'l': f++; if (*f == 'l') { len = 'q'; f++; } else { len = 'l'; } break; case 'q': case 'j': case 't': case 'z': len = *f; f++; break; default: break; } /* Conversion specifier. */ switch (*f) { case '%': /* %% */ APPEND_C(*f); f++; break; case 'd': case 'i': { intmax_t val JEMALLOC_CC_SILENCE_INIT(0); char buf[D2S_BUFSIZE]; GET_ARG_NUMERIC(val, len); s = d2s(val, (plus_plus ? '+' : (plus_space ? ' ' : '-')), buf, &slen); APPEND_PADDED_S(s, slen, width, left_justify); f++; break; } case 'o': { uintmax_t val JEMALLOC_CC_SILENCE_INIT(0); char buf[O2S_BUFSIZE]; GET_ARG_NUMERIC(val, len | 0x80); s = o2s(val, alt_form, buf, &slen); APPEND_PADDED_S(s, slen, width, left_justify); f++; break; } case 'u': { uintmax_t val JEMALLOC_CC_SILENCE_INIT(0); char buf[U2S_BUFSIZE]; GET_ARG_NUMERIC(val, len | 0x80); s = u2s(val, 10, false, buf, &slen); APPEND_PADDED_S(s, slen, width, left_justify); f++; break; } case 'x': case 'X': { uintmax_t val JEMALLOC_CC_SILENCE_INIT(0); char buf[X2S_BUFSIZE]; GET_ARG_NUMERIC(val, len | 0x80); s = x2s(val, alt_form, *f == 'X', buf, &slen); APPEND_PADDED_S(s, slen, width, left_justify); f++; break; } case 'c': { unsigned char val; char buf[2]; assert(len == '?' || len == 'l'); assert_not_implemented(len != 'l'); val = va_arg(ap, int); buf[0] = val; buf[1] = '\0'; APPEND_PADDED_S(buf, 1, width, left_justify); f++; break; } case 's': assert(len == '?' || len == 'l'); assert_not_implemented(len != 'l'); s = va_arg(ap, char *); slen = (prec < 0) ? strlen(s) : (size_t)prec; APPEND_PADDED_S(s, slen, width, left_justify); f++; break; case 'p': { uintmax_t val; char buf[X2S_BUFSIZE]; GET_ARG_NUMERIC(val, 'p'); s = x2s(val, true, false, buf, &slen); APPEND_PADDED_S(s, slen, width, left_justify); f++; break; } default: not_reached(); } break; } default: { APPEND_C(*f); f++; break; }} } label_out: if (i < size) { str[i] = '\0'; } else { str[size - 1] = '\0'; } #undef APPEND_C #undef APPEND_S #undef APPEND_PADDED_S #undef GET_ARG_NUMERIC return i; } JEMALLOC_FORMAT_PRINTF(3, 4) size_t malloc_snprintf(char *str, size_t size, const char *format, ...) { size_t ret; va_list ap; va_start(ap, format); ret = malloc_vsnprintf(str, size, format, ap); va_end(ap); return ret; } void malloc_vcprintf(void (*write_cb)(void *, const char *), void *cbopaque, const char *format, va_list ap) { char buf[MALLOC_PRINTF_BUFSIZE]; if (write_cb == NULL) { /* * The caller did not provide an alternate write_cb callback * function, so use the default one. malloc_write() is an * inline function, so use malloc_message() directly here. */ write_cb = (je_malloc_message != NULL) ? je_malloc_message : wrtmessage; - cbopaque = NULL; } malloc_vsnprintf(buf, sizeof(buf), format, ap); write_cb(cbopaque, buf); } /* * Print to a callback function in such a way as to (hopefully) avoid memory * allocation. */ JEMALLOC_FORMAT_PRINTF(3, 4) void malloc_cprintf(void (*write_cb)(void *, const char *), void *cbopaque, const char *format, ...) { va_list ap; va_start(ap, format); malloc_vcprintf(write_cb, cbopaque, format, ap); va_end(ap); } /* Print to stderr in such a way as to avoid memory allocation. */ JEMALLOC_FORMAT_PRINTF(1, 2) void malloc_printf(const char *format, ...) { va_list ap; va_start(ap, format); malloc_vcprintf(NULL, NULL, format, ap); va_end(ap); } /* * Restore normal assertion macros, in order to make it possible to compile all * C files as a single concatenation. */ #undef assert #undef not_reached #undef not_implemented #undef assert_not_implemented #include "jemalloc/internal/assert.h" Index: head/contrib/jemalloc/src/mutex.c =================================================================== --- head/contrib/jemalloc/src/mutex.c (revision 360232) +++ head/contrib/jemalloc/src/mutex.c (revision 360233) @@ -1,245 +1,244 @@ #define JEMALLOC_MUTEX_C_ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/jemalloc_internal_includes.h" #include "jemalloc/internal/assert.h" #include "jemalloc/internal/malloc_io.h" #include "jemalloc/internal/spin.h" #ifndef _CRT_SPINCOUNT #define _CRT_SPINCOUNT 4000 #endif /******************************************************************************/ /* Data. */ #ifdef JEMALLOC_LAZY_LOCK bool isthreaded = false; #endif #ifdef JEMALLOC_MUTEX_INIT_CB static bool postpone_init = true; static malloc_mutex_t *postponed_mutexes = NULL; #endif /******************************************************************************/ /* * We intercept pthread_create() calls in order to toggle isthreaded if the * process goes multi-threaded. */ #if defined(JEMALLOC_LAZY_LOCK) && !defined(_WIN32) JEMALLOC_EXPORT int pthread_create(pthread_t *__restrict thread, const pthread_attr_t *__restrict attr, void *(*start_routine)(void *), void *__restrict arg) { return pthread_create_wrapper(thread, attr, start_routine, arg); } #endif /******************************************************************************/ #ifdef JEMALLOC_MUTEX_INIT_CB JEMALLOC_EXPORT int _pthread_mutex_init_calloc_cb(pthread_mutex_t *mutex, void *(calloc_cb)(size_t, size_t)); #pragma weak _pthread_mutex_init_calloc_cb int _pthread_mutex_init_calloc_cb(pthread_mutex_t *mutex, void *(calloc_cb)(size_t, size_t)) { return (((int (*)(pthread_mutex_t *, void *(*)(size_t, size_t))) __libc_interposing[INTERPOS__pthread_mutex_init_calloc_cb])(mutex, calloc_cb)); } #endif void malloc_mutex_lock_slow(malloc_mutex_t *mutex) { mutex_prof_data_t *data = &mutex->prof_data; - UNUSED nstime_t before = NSTIME_ZERO_INITIALIZER; + nstime_t before = NSTIME_ZERO_INITIALIZER; if (ncpus == 1) { goto label_spin_done; } int cnt = 0, max_cnt = MALLOC_MUTEX_MAX_SPIN; do { spin_cpu_spinwait(); - if (!malloc_mutex_trylock_final(mutex)) { + if (!atomic_load_b(&mutex->locked, ATOMIC_RELAXED) + && !malloc_mutex_trylock_final(mutex)) { data->n_spin_acquired++; return; } } while (cnt++ < max_cnt); if (!config_stats) { /* Only spin is useful when stats is off. */ malloc_mutex_lock_final(mutex); return; } label_spin_done: nstime_update(&before); /* Copy before to after to avoid clock skews. */ nstime_t after; nstime_copy(&after, &before); uint32_t n_thds = atomic_fetch_add_u32(&data->n_waiting_thds, 1, ATOMIC_RELAXED) + 1; /* One last try as above two calls may take quite some cycles. */ if (!malloc_mutex_trylock_final(mutex)) { atomic_fetch_sub_u32(&data->n_waiting_thds, 1, ATOMIC_RELAXED); data->n_spin_acquired++; return; } /* True slow path. */ malloc_mutex_lock_final(mutex); /* Update more slow-path only counters. */ atomic_fetch_sub_u32(&data->n_waiting_thds, 1, ATOMIC_RELAXED); nstime_update(&after); nstime_t delta; nstime_copy(&delta, &after); nstime_subtract(&delta, &before); data->n_wait_times++; nstime_add(&data->tot_wait_time, &delta); if (nstime_compare(&data->max_wait_time, &delta) < 0) { nstime_copy(&data->max_wait_time, &delta); } if (n_thds > data->max_n_thds) { data->max_n_thds = n_thds; } } static void mutex_prof_data_init(mutex_prof_data_t *data) { memset(data, 0, sizeof(mutex_prof_data_t)); nstime_init(&data->max_wait_time, 0); nstime_init(&data->tot_wait_time, 0); data->prev_owner = NULL; } void malloc_mutex_prof_data_reset(tsdn_t *tsdn, malloc_mutex_t *mutex) { malloc_mutex_assert_owner(tsdn, mutex); mutex_prof_data_init(&mutex->prof_data); } static int mutex_addr_comp(const witness_t *witness1, void *mutex1, const witness_t *witness2, void *mutex2) { assert(mutex1 != NULL); assert(mutex2 != NULL); uintptr_t mu1int = (uintptr_t)mutex1; uintptr_t mu2int = (uintptr_t)mutex2; if (mu1int < mu2int) { return -1; } else if (mu1int == mu2int) { return 0; } else { return 1; } } bool malloc_mutex_first_thread(void) { #ifndef JEMALLOC_MUTEX_INIT_CB return (malloc_mutex_first_thread()); #else return (false); #endif } bool malloc_mutex_init(malloc_mutex_t *mutex, const char *name, witness_rank_t rank, malloc_mutex_lock_order_t lock_order) { mutex_prof_data_init(&mutex->prof_data); #ifdef _WIN32 # if _WIN32_WINNT >= 0x0600 InitializeSRWLock(&mutex->lock); # else if (!InitializeCriticalSectionAndSpinCount(&mutex->lock, _CRT_SPINCOUNT)) { return true; } # endif #elif (defined(JEMALLOC_OS_UNFAIR_LOCK)) - mutex->lock = OS_UNFAIR_LOCK_INIT; -#elif (defined(JEMALLOC_OSSPIN)) - mutex->lock = 0; + mutex->lock = OS_UNFAIR_LOCK_INIT; #elif (defined(JEMALLOC_MUTEX_INIT_CB)) if (postpone_init) { mutex->postponed_next = postponed_mutexes; postponed_mutexes = mutex; } else { if (_pthread_mutex_init_calloc_cb(&mutex->lock, bootstrap_calloc) != 0) { return true; } } #else pthread_mutexattr_t attr; if (pthread_mutexattr_init(&attr) != 0) { return true; } pthread_mutexattr_settype(&attr, MALLOC_MUTEX_TYPE); if (pthread_mutex_init(&mutex->lock, &attr) != 0) { pthread_mutexattr_destroy(&attr); return true; } pthread_mutexattr_destroy(&attr); #endif if (config_debug) { mutex->lock_order = lock_order; if (lock_order == malloc_mutex_address_ordered) { witness_init(&mutex->witness, name, rank, mutex_addr_comp, mutex); } else { witness_init(&mutex->witness, name, rank, NULL, NULL); } } return false; } void malloc_mutex_prefork(tsdn_t *tsdn, malloc_mutex_t *mutex) { malloc_mutex_lock(tsdn, mutex); } void malloc_mutex_postfork_parent(tsdn_t *tsdn, malloc_mutex_t *mutex) { malloc_mutex_unlock(tsdn, mutex); } void malloc_mutex_postfork_child(tsdn_t *tsdn, malloc_mutex_t *mutex) { #ifdef JEMALLOC_MUTEX_INIT_CB malloc_mutex_unlock(tsdn, mutex); #else if (malloc_mutex_init(mutex, mutex->witness.name, mutex->witness.rank, mutex->lock_order)) { malloc_printf(": Error re-initializing mutex in " "child\n"); if (opt_abort) { abort(); } } #endif } bool malloc_mutex_boot(void) { #ifdef JEMALLOC_MUTEX_INIT_CB postpone_init = false; while (postponed_mutexes != NULL) { if (_pthread_mutex_init_calloc_cb(&postponed_mutexes->lock, bootstrap_calloc) != 0) { return true; } postponed_mutexes = postponed_mutexes->postponed_next; } #endif return false; } Index: head/contrib/jemalloc/src/pages.c =================================================================== --- head/contrib/jemalloc/src/pages.c (revision 360232) +++ head/contrib/jemalloc/src/pages.c (revision 360233) @@ -1,641 +1,649 @@ #define JEMALLOC_PAGES_C_ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/pages.h" #include "jemalloc/internal/jemalloc_internal_includes.h" #include "jemalloc/internal/assert.h" #include "jemalloc/internal/malloc_io.h" #ifdef JEMALLOC_SYSCTL_VM_OVERCOMMIT #include #ifdef __FreeBSD__ #include #endif #endif /******************************************************************************/ /* Data. */ /* Actual operating system page size, detected during bootstrap, <= PAGE. */ static size_t os_page; #ifndef _WIN32 # define PAGES_PROT_COMMIT (PROT_READ | PROT_WRITE) # define PAGES_PROT_DECOMMIT (PROT_NONE) static int mmap_flags; #endif static bool os_overcommits; const char *thp_mode_names[] = { "default", "always", "never", "not supported" }; thp_mode_t opt_thp = THP_MODE_DEFAULT; thp_mode_t init_system_thp_mode; /* Runtime support for lazy purge. Irrelevant when !pages_can_purge_lazy. */ static bool pages_can_purge_lazy_runtime = true; /******************************************************************************/ /* * Function prototypes for static functions that are referenced prior to * definition. */ static void os_pages_unmap(void *addr, size_t size); /******************************************************************************/ static void * os_pages_map(void *addr, size_t size, size_t alignment, bool *commit) { assert(ALIGNMENT_ADDR2BASE(addr, os_page) == addr); assert(ALIGNMENT_CEILING(size, os_page) == size); assert(size != 0); if (os_overcommits) { *commit = true; } void *ret; #ifdef _WIN32 /* * If VirtualAlloc can't allocate at the given address when one is * given, it fails and returns NULL. */ ret = VirtualAlloc(addr, size, MEM_RESERVE | (*commit ? MEM_COMMIT : 0), PAGE_READWRITE); #else /* * We don't use MAP_FIXED here, because it can cause the *replacement* * of existing mappings, and we only want to create new mappings. */ { int prot = *commit ? PAGES_PROT_COMMIT : PAGES_PROT_DECOMMIT; ret = mmap(addr, size, prot, mmap_flags, -1, 0); } assert(ret != NULL); if (ret == MAP_FAILED) { ret = NULL; } else if (addr != NULL && ret != addr) { /* * We succeeded in mapping memory, but not in the right place. */ os_pages_unmap(ret, size); ret = NULL; } #endif assert(ret == NULL || (addr == NULL && ret != addr) || (addr != NULL && ret == addr)); return ret; } static void * os_pages_trim(void *addr, size_t alloc_size, size_t leadsize, size_t size, bool *commit) { void *ret = (void *)((uintptr_t)addr + leadsize); assert(alloc_size >= leadsize + size); #ifdef _WIN32 os_pages_unmap(addr, alloc_size); void *new_addr = os_pages_map(ret, size, PAGE, commit); if (new_addr == ret) { return ret; } if (new_addr != NULL) { os_pages_unmap(new_addr, size); } return NULL; #else size_t trailsize = alloc_size - leadsize - size; if (leadsize != 0) { os_pages_unmap(addr, leadsize); } if (trailsize != 0) { os_pages_unmap((void *)((uintptr_t)ret + size), trailsize); } return ret; #endif } static void os_pages_unmap(void *addr, size_t size) { assert(ALIGNMENT_ADDR2BASE(addr, os_page) == addr); assert(ALIGNMENT_CEILING(size, os_page) == size); #ifdef _WIN32 if (VirtualFree(addr, 0, MEM_RELEASE) == 0) #else if (munmap(addr, size) == -1) #endif { char buf[BUFERROR_BUF]; buferror(get_errno(), buf, sizeof(buf)); malloc_printf(": Error in " #ifdef _WIN32 "VirtualFree" #else "munmap" #endif "(): %s\n", buf); if (opt_abort) { abort(); } } } static void * pages_map_slow(size_t size, size_t alignment, bool *commit) { size_t alloc_size = size + alignment - os_page; /* Beware size_t wrap-around. */ if (alloc_size < size) { return NULL; } void *ret; do { void *pages = os_pages_map(NULL, alloc_size, alignment, commit); if (pages == NULL) { return NULL; } size_t leadsize = ALIGNMENT_CEILING((uintptr_t)pages, alignment) - (uintptr_t)pages; ret = os_pages_trim(pages, alloc_size, leadsize, size, commit); } while (ret == NULL); assert(ret != NULL); assert(PAGE_ADDR2BASE(ret) == ret); return ret; } void * pages_map(void *addr, size_t size, size_t alignment, bool *commit) { assert(alignment >= PAGE); assert(ALIGNMENT_ADDR2BASE(addr, alignment) == addr); #if defined(__FreeBSD__) && defined(MAP_EXCL) /* * FreeBSD has mechanisms both to mmap at specific address without * touching existing mappings, and to mmap with specific alignment. */ { if (os_overcommits) { *commit = true; } int prot = *commit ? PAGES_PROT_COMMIT : PAGES_PROT_DECOMMIT; int flags = mmap_flags; if (addr != NULL) { flags |= MAP_FIXED | MAP_EXCL; } else { unsigned alignment_bits = ffs_zu(alignment); assert(alignment_bits > 1); flags |= MAP_ALIGNED(alignment_bits - 1); } void *ret = mmap(addr, size, prot, flags, -1, 0); if (ret == MAP_FAILED) { ret = NULL; } return ret; } #endif /* * Ideally, there would be a way to specify alignment to mmap() (like * NetBSD has), but in the absence of such a feature, we have to work * hard to efficiently create aligned mappings. The reliable, but * slow method is to create a mapping that is over-sized, then trim the * excess. However, that always results in one or two calls to * os_pages_unmap(), and it can leave holes in the process's virtual * memory map if memory grows downward. * * Optimistically try mapping precisely the right amount before falling * back to the slow method, with the expectation that the optimistic * approach works most of the time. */ void *ret = os_pages_map(addr, size, os_page, commit); if (ret == NULL || ret == addr) { return ret; } assert(addr == NULL); if (ALIGNMENT_ADDR2OFFSET(ret, alignment) != 0) { os_pages_unmap(ret, size); return pages_map_slow(size, alignment, commit); } assert(PAGE_ADDR2BASE(ret) == ret); return ret; } void pages_unmap(void *addr, size_t size) { assert(PAGE_ADDR2BASE(addr) == addr); assert(PAGE_CEILING(size) == size); os_pages_unmap(addr, size); } static bool pages_commit_impl(void *addr, size_t size, bool commit) { assert(PAGE_ADDR2BASE(addr) == addr); assert(PAGE_CEILING(size) == size); if (os_overcommits) { return true; } #ifdef _WIN32 return (commit ? (addr != VirtualAlloc(addr, size, MEM_COMMIT, PAGE_READWRITE)) : (!VirtualFree(addr, size, MEM_DECOMMIT))); #else { int prot = commit ? PAGES_PROT_COMMIT : PAGES_PROT_DECOMMIT; void *result = mmap(addr, size, prot, mmap_flags | MAP_FIXED, -1, 0); if (result == MAP_FAILED) { return true; } if (result != addr) { /* * We succeeded in mapping memory, but not in the right * place. */ os_pages_unmap(result, size); return true; } return false; } #endif } bool pages_commit(void *addr, size_t size) { return pages_commit_impl(addr, size, true); } bool pages_decommit(void *addr, size_t size) { return pages_commit_impl(addr, size, false); } bool pages_purge_lazy(void *addr, size_t size) { - assert(PAGE_ADDR2BASE(addr) == addr); + assert(ALIGNMENT_ADDR2BASE(addr, os_page) == addr); assert(PAGE_CEILING(size) == size); if (!pages_can_purge_lazy) { return true; } if (!pages_can_purge_lazy_runtime) { /* * Built with lazy purge enabled, but detected it was not * supported on the current system. */ return true; } #ifdef _WIN32 VirtualAlloc(addr, size, MEM_RESET, PAGE_READWRITE); return false; #elif defined(JEMALLOC_PURGE_MADVISE_FREE) return (madvise(addr, size, # ifdef MADV_FREE MADV_FREE # else JEMALLOC_MADV_FREE # endif ) != 0); #elif defined(JEMALLOC_PURGE_MADVISE_DONTNEED) && \ !defined(JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS) return (madvise(addr, size, MADV_DONTNEED) != 0); #else not_reached(); #endif } bool pages_purge_forced(void *addr, size_t size) { assert(PAGE_ADDR2BASE(addr) == addr); assert(PAGE_CEILING(size) == size); if (!pages_can_purge_forced) { return true; } #if defined(JEMALLOC_PURGE_MADVISE_DONTNEED) && \ defined(JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS) return (madvise(addr, size, MADV_DONTNEED) != 0); #elif defined(JEMALLOC_MAPS_COALESCE) /* Try to overlay a new demand-zeroed mapping. */ return pages_commit(addr, size); #else not_reached(); #endif } static bool pages_huge_impl(void *addr, size_t size, bool aligned) { if (aligned) { assert(HUGEPAGE_ADDR2BASE(addr) == addr); assert(HUGEPAGE_CEILING(size) == size); } #ifdef JEMALLOC_HAVE_MADVISE_HUGE return (madvise(addr, size, MADV_HUGEPAGE) != 0); #else return true; #endif } bool pages_huge(void *addr, size_t size) { return pages_huge_impl(addr, size, true); } static bool pages_huge_unaligned(void *addr, size_t size) { return pages_huge_impl(addr, size, false); } static bool pages_nohuge_impl(void *addr, size_t size, bool aligned) { if (aligned) { assert(HUGEPAGE_ADDR2BASE(addr) == addr); assert(HUGEPAGE_CEILING(size) == size); } #ifdef JEMALLOC_HAVE_MADVISE_HUGE return (madvise(addr, size, MADV_NOHUGEPAGE) != 0); #else return false; #endif } bool pages_nohuge(void *addr, size_t size) { return pages_nohuge_impl(addr, size, true); } static bool pages_nohuge_unaligned(void *addr, size_t size) { return pages_nohuge_impl(addr, size, false); } bool pages_dontdump(void *addr, size_t size) { assert(PAGE_ADDR2BASE(addr) == addr); assert(PAGE_CEILING(size) == size); #ifdef JEMALLOC_MADVISE_DONTDUMP return madvise(addr, size, MADV_DONTDUMP) != 0; #else return false; #endif } bool pages_dodump(void *addr, size_t size) { assert(PAGE_ADDR2BASE(addr) == addr); assert(PAGE_CEILING(size) == size); #ifdef JEMALLOC_MADVISE_DONTDUMP return madvise(addr, size, MADV_DODUMP) != 0; #else return false; #endif } static size_t os_page_detect(void) { #ifdef _WIN32 SYSTEM_INFO si; GetSystemInfo(&si); return si.dwPageSize; #elif defined(__FreeBSD__) + /* + * This returns the value obtained from + * the auxv vector, avoiding a syscall. + */ return getpagesize(); #else long result = sysconf(_SC_PAGESIZE); if (result == -1) { return LG_PAGE; } return (size_t)result; #endif } #ifdef JEMALLOC_SYSCTL_VM_OVERCOMMIT static bool os_overcommits_sysctl(void) { int vm_overcommit; size_t sz; sz = sizeof(vm_overcommit); #if defined(__FreeBSD__) && defined(VM_OVERCOMMIT) int mib[2]; mib[0] = CTL_VM; mib[1] = VM_OVERCOMMIT; if (sysctl(mib, 2, &vm_overcommit, &sz, NULL, 0) != 0) { return false; /* Error. */ } #else if (sysctlbyname("vm.overcommit", &vm_overcommit, &sz, NULL, 0) != 0) { return false; /* Error. */ } #endif return ((vm_overcommit & 0x3) == 0); } #endif #ifdef JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY /* * Use syscall(2) rather than {open,read,close}(2) when possible to avoid * reentry during bootstrapping if another library has interposed system call * wrappers. */ static bool os_overcommits_proc(void) { int fd; char buf[1]; #if defined(JEMALLOC_USE_SYSCALL) && defined(SYS_open) #if defined(O_CLOEXEC) fd = (int)syscall(SYS_open, "/proc/sys/vm/overcommit_memory", O_RDONLY | O_CLOEXEC); #else fd = (int)syscall(SYS_open, "/proc/sys/vm/overcommit_memory", O_RDONLY); if (fd != -1) { fcntl(fd, F_SETFD, fcntl(fd, F_GETFD) | FD_CLOEXEC); } #endif #elif defined(JEMALLOC_USE_SYSCALL) && defined(SYS_openat) #if defined(O_CLOEXEC) fd = (int)syscall(SYS_openat, AT_FDCWD, "/proc/sys/vm/overcommit_memory", O_RDONLY | O_CLOEXEC); #else fd = (int)syscall(SYS_openat, AT_FDCWD, "/proc/sys/vm/overcommit_memory", O_RDONLY); if (fd != -1) { fcntl(fd, F_SETFD, fcntl(fd, F_GETFD) | FD_CLOEXEC); } #endif #else #if defined(O_CLOEXEC) fd = open("/proc/sys/vm/overcommit_memory", O_RDONLY | O_CLOEXEC); #else fd = open("/proc/sys/vm/overcommit_memory", O_RDONLY); if (fd != -1) { fcntl(fd, F_SETFD, fcntl(fd, F_GETFD) | FD_CLOEXEC); } #endif #endif if (fd == -1) { return false; /* Error. */ } ssize_t nread = malloc_read_fd(fd, &buf, sizeof(buf)); #if defined(JEMALLOC_USE_SYSCALL) && defined(SYS_close) syscall(SYS_close, fd); #else close(fd); #endif if (nread < 1) { return false; /* Error. */ } /* * /proc/sys/vm/overcommit_memory meanings: * 0: Heuristic overcommit. * 1: Always overcommit. * 2: Never overcommit. */ return (buf[0] == '0' || buf[0] == '1'); } #endif void pages_set_thp_state (void *ptr, size_t size) { if (opt_thp == thp_mode_default || opt_thp == init_system_thp_mode) { return; } assert(opt_thp != thp_mode_not_supported && init_system_thp_mode != thp_mode_not_supported); if (opt_thp == thp_mode_always && init_system_thp_mode != thp_mode_never) { assert(init_system_thp_mode == thp_mode_default); pages_huge_unaligned(ptr, size); } else if (opt_thp == thp_mode_never) { assert(init_system_thp_mode == thp_mode_default || init_system_thp_mode == thp_mode_always); pages_nohuge_unaligned(ptr, size); } } static void init_thp_state(void) { if (!have_madvise_huge) { if (metadata_thp_enabled() && opt_abort) { malloc_write(": no MADV_HUGEPAGE support\n"); abort(); } goto label_error; } static const char sys_state_madvise[] = "always [madvise] never\n"; static const char sys_state_always[] = "[always] madvise never\n"; static const char sys_state_never[] = "always madvise [never]\n"; char buf[sizeof(sys_state_madvise)]; #if defined(JEMALLOC_USE_SYSCALL) && defined(SYS_open) int fd = (int)syscall(SYS_open, "/sys/kernel/mm/transparent_hugepage/enabled", O_RDONLY); #else int fd = open("/sys/kernel/mm/transparent_hugepage/enabled", O_RDONLY); #endif if (fd == -1) { goto label_error; } ssize_t nread = malloc_read_fd(fd, &buf, sizeof(buf)); #if defined(JEMALLOC_USE_SYSCALL) && defined(SYS_close) syscall(SYS_close, fd); #else close(fd); #endif + + if (nread < 0) { + goto label_error; + } if (strncmp(buf, sys_state_madvise, (size_t)nread) == 0) { init_system_thp_mode = thp_mode_default; } else if (strncmp(buf, sys_state_always, (size_t)nread) == 0) { init_system_thp_mode = thp_mode_always; } else if (strncmp(buf, sys_state_never, (size_t)nread) == 0) { init_system_thp_mode = thp_mode_never; } else { goto label_error; } return; label_error: opt_thp = init_system_thp_mode = thp_mode_not_supported; } bool pages_boot(void) { os_page = os_page_detect(); if (os_page > PAGE) { malloc_write(": Unsupported system page size\n"); if (opt_abort) { abort(); } return true; } #ifndef _WIN32 mmap_flags = MAP_PRIVATE | MAP_ANON; #endif #ifdef JEMALLOC_SYSCTL_VM_OVERCOMMIT os_overcommits = os_overcommits_sysctl(); #elif defined(JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY) os_overcommits = os_overcommits_proc(); # ifdef MAP_NORESERVE if (os_overcommits) { mmap_flags |= MAP_NORESERVE; } # endif #else os_overcommits = false; #endif init_thp_state(); #ifdef __FreeBSD__ /* * FreeBSD doesn't need the check; madvise(2) is known to work. */ #else /* Detect lazy purge runtime support. */ if (pages_can_purge_lazy) { bool committed = false; void *madv_free_page = os_pages_map(NULL, PAGE, PAGE, &committed); if (madv_free_page == NULL) { return true; } assert(pages_can_purge_lazy_runtime); if (pages_purge_lazy(madv_free_page, PAGE)) { pages_can_purge_lazy_runtime = false; } os_pages_unmap(madv_free_page, PAGE); } #endif return false; } Index: head/contrib/jemalloc/src/prof.c =================================================================== --- head/contrib/jemalloc/src/prof.c (revision 360232) +++ head/contrib/jemalloc/src/prof.c (revision 360233) @@ -1,2473 +1,3160 @@ #define JEMALLOC_PROF_C_ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/jemalloc_internal_includes.h" #include "jemalloc/internal/assert.h" #include "jemalloc/internal/ckh.h" #include "jemalloc/internal/hash.h" #include "jemalloc/internal/malloc_io.h" #include "jemalloc/internal/mutex.h" +#include "jemalloc/internal/emitter.h" /******************************************************************************/ #ifdef JEMALLOC_PROF_LIBUNWIND #define UNW_LOCAL_ONLY #include #endif #ifdef JEMALLOC_PROF_LIBGCC /* * We have a circular dependency -- jemalloc_internal.h tells us if we should * use libgcc's unwinding functionality, but after we've included that, we've * already hooked _Unwind_Backtrace. We'll temporarily disable hooking. */ #undef _Unwind_Backtrace #include -#define _Unwind_Backtrace JEMALLOC_HOOK(_Unwind_Backtrace, hooks_libc_hook) +#define _Unwind_Backtrace JEMALLOC_HOOK(_Unwind_Backtrace, test_hooks_libc_hook) #endif /******************************************************************************/ /* Data. */ bool opt_prof = false; bool opt_prof_active = true; bool opt_prof_thread_active_init = true; size_t opt_lg_prof_sample = LG_PROF_SAMPLE_DEFAULT; ssize_t opt_lg_prof_interval = LG_PROF_INTERVAL_DEFAULT; bool opt_prof_gdump = false; bool opt_prof_final = false; bool opt_prof_leak = false; bool opt_prof_accum = false; +bool opt_prof_log = false; char opt_prof_prefix[ /* Minimize memory bloat for non-prof builds. */ #ifdef JEMALLOC_PROF PATH_MAX + #endif 1]; /* * Initialized as opt_prof_active, and accessed via * prof_active_[gs]et{_unlocked,}(). */ bool prof_active; static malloc_mutex_t prof_active_mtx; /* * Initialized as opt_prof_thread_active_init, and accessed via * prof_thread_active_init_[gs]et(). */ static bool prof_thread_active_init; static malloc_mutex_t prof_thread_active_init_mtx; /* * Initialized as opt_prof_gdump, and accessed via * prof_gdump_[gs]et{_unlocked,}(). */ bool prof_gdump_val; static malloc_mutex_t prof_gdump_mtx; uint64_t prof_interval = 0; size_t lg_prof_sample; +typedef enum prof_logging_state_e prof_logging_state_t; +enum prof_logging_state_e { + prof_logging_state_stopped, + prof_logging_state_started, + prof_logging_state_dumping +}; + /* + * - stopped: log_start never called, or previous log_stop has completed. + * - started: log_start called, log_stop not called yet. Allocations are logged. + * - dumping: log_stop called but not finished; samples are not logged anymore. + */ +prof_logging_state_t prof_logging_state = prof_logging_state_stopped; + +#ifdef JEMALLOC_JET +static bool prof_log_dummy = false; +#endif + +/* Incremented for every log file that is output. */ +static uint64_t log_seq = 0; +static char log_filename[ + /* Minimize memory bloat for non-prof builds. */ +#ifdef JEMALLOC_PROF + PATH_MAX + +#endif + 1]; + +/* Timestamp for most recent call to log_start(). */ +static nstime_t log_start_timestamp = NSTIME_ZERO_INITIALIZER; + +/* Increment these when adding to the log_bt and log_thr linked lists. */ +static size_t log_bt_index = 0; +static size_t log_thr_index = 0; + +/* Linked list node definitions. These are only used in prof.c. */ +typedef struct prof_bt_node_s prof_bt_node_t; + +struct prof_bt_node_s { + prof_bt_node_t *next; + size_t index; + prof_bt_t bt; + /* Variable size backtrace vector pointed to by bt. */ + void *vec[1]; +}; + +typedef struct prof_thr_node_s prof_thr_node_t; + +struct prof_thr_node_s { + prof_thr_node_t *next; + size_t index; + uint64_t thr_uid; + /* Variable size based on thr_name_sz. */ + char name[1]; +}; + +typedef struct prof_alloc_node_s prof_alloc_node_t; + +/* This is output when logging sampled allocations. */ +struct prof_alloc_node_s { + prof_alloc_node_t *next; + /* Indices into an array of thread data. */ + size_t alloc_thr_ind; + size_t free_thr_ind; + + /* Indices into an array of backtraces. */ + size_t alloc_bt_ind; + size_t free_bt_ind; + + uint64_t alloc_time_ns; + uint64_t free_time_ns; + + size_t usize; +}; + +/* + * Created on the first call to prof_log_start and deleted on prof_log_stop. + * These are the backtraces and threads that have already been logged by an + * allocation. + */ +static bool log_tables_initialized = false; +static ckh_t log_bt_node_set; +static ckh_t log_thr_node_set; + +/* Store linked lists for logged data. */ +static prof_bt_node_t *log_bt_first = NULL; +static prof_bt_node_t *log_bt_last = NULL; +static prof_thr_node_t *log_thr_first = NULL; +static prof_thr_node_t *log_thr_last = NULL; +static prof_alloc_node_t *log_alloc_first = NULL; +static prof_alloc_node_t *log_alloc_last = NULL; + +/* Protects the prof_logging_state and any log_{...} variable. */ +static malloc_mutex_t log_mtx; + +/* * Table of mutexes that are shared among gctx's. These are leaf locks, so * there is no problem with using them for more than one gctx at the same time. * The primary motivation for this sharing though is that gctx's are ephemeral, * and destroying mutexes causes complications for systems that allocate when * creating/destroying mutexes. */ static malloc_mutex_t *gctx_locks; static atomic_u_t cum_gctxs; /* Atomic counter. */ /* * Table of mutexes that are shared among tdata's. No operations require * holding multiple tdata locks, so there is no problem with using them for more * than one tdata at the same time, even though a gctx lock may be acquired * while holding a tdata lock. */ static malloc_mutex_t *tdata_locks; /* * Global hash of (prof_bt_t *)-->(prof_gctx_t *). This is the master data * structure that knows about all backtraces currently captured. */ static ckh_t bt2gctx; /* Non static to enable profiling. */ malloc_mutex_t bt2gctx_mtx; /* * Tree of all extant prof_tdata_t structures, regardless of state, * {attached,detached,expired}. */ static prof_tdata_tree_t tdatas; static malloc_mutex_t tdatas_mtx; static uint64_t next_thr_uid; static malloc_mutex_t next_thr_uid_mtx; static malloc_mutex_t prof_dump_seq_mtx; static uint64_t prof_dump_seq; static uint64_t prof_dump_iseq; static uint64_t prof_dump_mseq; static uint64_t prof_dump_useq; /* * This buffer is rather large for stack allocation, so use a single buffer for * all profile dumps. */ static malloc_mutex_t prof_dump_mtx; static char prof_dump_buf[ /* Minimize memory bloat for non-prof builds. */ #ifdef JEMALLOC_PROF PROF_DUMP_BUFSIZE #else 1 #endif ]; static size_t prof_dump_buf_end; static int prof_dump_fd; /* Do not dump any profiles until bootstrapping is complete. */ static bool prof_booted = false; /******************************************************************************/ /* * Function prototypes for static functions that are referenced prior to * definition. */ static bool prof_tctx_should_destroy(tsdn_t *tsdn, prof_tctx_t *tctx); static void prof_tctx_destroy(tsd_t *tsd, prof_tctx_t *tctx); static bool prof_tdata_should_destroy(tsdn_t *tsdn, prof_tdata_t *tdata, bool even_if_attached); static void prof_tdata_destroy(tsd_t *tsd, prof_tdata_t *tdata, bool even_if_attached); static char *prof_thread_name_alloc(tsdn_t *tsdn, const char *thread_name); +/* Hashtable functions for log_bt_node_set and log_thr_node_set. */ +static void prof_thr_node_hash(const void *key, size_t r_hash[2]); +static bool prof_thr_node_keycomp(const void *k1, const void *k2); +static void prof_bt_node_hash(const void *key, size_t r_hash[2]); +static bool prof_bt_node_keycomp(const void *k1, const void *k2); + /******************************************************************************/ /* Red-black trees. */ static int prof_tctx_comp(const prof_tctx_t *a, const prof_tctx_t *b) { uint64_t a_thr_uid = a->thr_uid; uint64_t b_thr_uid = b->thr_uid; int ret = (a_thr_uid > b_thr_uid) - (a_thr_uid < b_thr_uid); if (ret == 0) { uint64_t a_thr_discrim = a->thr_discrim; uint64_t b_thr_discrim = b->thr_discrim; ret = (a_thr_discrim > b_thr_discrim) - (a_thr_discrim < b_thr_discrim); if (ret == 0) { uint64_t a_tctx_uid = a->tctx_uid; uint64_t b_tctx_uid = b->tctx_uid; ret = (a_tctx_uid > b_tctx_uid) - (a_tctx_uid < b_tctx_uid); } } return ret; } rb_gen(static UNUSED, tctx_tree_, prof_tctx_tree_t, prof_tctx_t, tctx_link, prof_tctx_comp) static int prof_gctx_comp(const prof_gctx_t *a, const prof_gctx_t *b) { unsigned a_len = a->bt.len; unsigned b_len = b->bt.len; unsigned comp_len = (a_len < b_len) ? a_len : b_len; int ret = memcmp(a->bt.vec, b->bt.vec, comp_len * sizeof(void *)); if (ret == 0) { ret = (a_len > b_len) - (a_len < b_len); } return ret; } rb_gen(static UNUSED, gctx_tree_, prof_gctx_tree_t, prof_gctx_t, dump_link, prof_gctx_comp) static int prof_tdata_comp(const prof_tdata_t *a, const prof_tdata_t *b) { int ret; uint64_t a_uid = a->thr_uid; uint64_t b_uid = b->thr_uid; ret = ((a_uid > b_uid) - (a_uid < b_uid)); if (ret == 0) { uint64_t a_discrim = a->thr_discrim; uint64_t b_discrim = b->thr_discrim; ret = ((a_discrim > b_discrim) - (a_discrim < b_discrim)); } return ret; } rb_gen(static UNUSED, tdata_tree_, prof_tdata_tree_t, prof_tdata_t, tdata_link, prof_tdata_comp) /******************************************************************************/ void prof_alloc_rollback(tsd_t *tsd, prof_tctx_t *tctx, bool updated) { prof_tdata_t *tdata; cassert(config_prof); if (updated) { /* * Compute a new sample threshold. This isn't very important in * practice, because this function is rarely executed, so the * potential for sample bias is minimal except in contrived * programs. */ tdata = prof_tdata_get(tsd, true); if (tdata != NULL) { prof_sample_threshold_update(tdata); } } if ((uintptr_t)tctx > (uintptr_t)1U) { malloc_mutex_lock(tsd_tsdn(tsd), tctx->tdata->lock); tctx->prepared = false; if (prof_tctx_should_destroy(tsd_tsdn(tsd), tctx)) { prof_tctx_destroy(tsd, tctx); } else { malloc_mutex_unlock(tsd_tsdn(tsd), tctx->tdata->lock); } } } void prof_malloc_sample_object(tsdn_t *tsdn, const void *ptr, size_t usize, prof_tctx_t *tctx) { prof_tctx_set(tsdn, ptr, usize, NULL, tctx); + /* Get the current time and set this in the extent_t. We'll read this + * when free() is called. */ + nstime_t t = NSTIME_ZERO_INITIALIZER; + nstime_update(&t); + prof_alloc_time_set(tsdn, ptr, NULL, t); + malloc_mutex_lock(tsdn, tctx->tdata->lock); tctx->cnts.curobjs++; tctx->cnts.curbytes += usize; if (opt_prof_accum) { tctx->cnts.accumobjs++; tctx->cnts.accumbytes += usize; } tctx->prepared = false; malloc_mutex_unlock(tsdn, tctx->tdata->lock); } +static size_t +prof_log_bt_index(tsd_t *tsd, prof_bt_t *bt) { + assert(prof_logging_state == prof_logging_state_started); + malloc_mutex_assert_owner(tsd_tsdn(tsd), &log_mtx); + + prof_bt_node_t dummy_node; + dummy_node.bt = *bt; + prof_bt_node_t *node; + + /* See if this backtrace is already cached in the table. */ + if (ckh_search(&log_bt_node_set, (void *)(&dummy_node), + (void **)(&node), NULL)) { + size_t sz = offsetof(prof_bt_node_t, vec) + + (bt->len * sizeof(void *)); + prof_bt_node_t *new_node = (prof_bt_node_t *) + iallocztm(tsd_tsdn(tsd), sz, sz_size2index(sz), false, NULL, + true, arena_get(TSDN_NULL, 0, true), true); + if (log_bt_first == NULL) { + log_bt_first = new_node; + log_bt_last = new_node; + } else { + log_bt_last->next = new_node; + log_bt_last = new_node; + } + + new_node->next = NULL; + new_node->index = log_bt_index; + /* + * Copy the backtrace: bt is inside a tdata or gctx, which + * might die before prof_log_stop is called. + */ + new_node->bt.len = bt->len; + memcpy(new_node->vec, bt->vec, bt->len * sizeof(void *)); + new_node->bt.vec = new_node->vec; + + log_bt_index++; + ckh_insert(tsd, &log_bt_node_set, (void *)new_node, NULL); + return new_node->index; + } else { + return node->index; + } +} +static size_t +prof_log_thr_index(tsd_t *tsd, uint64_t thr_uid, const char *name) { + assert(prof_logging_state == prof_logging_state_started); + malloc_mutex_assert_owner(tsd_tsdn(tsd), &log_mtx); + + prof_thr_node_t dummy_node; + dummy_node.thr_uid = thr_uid; + prof_thr_node_t *node; + + /* See if this thread is already cached in the table. */ + if (ckh_search(&log_thr_node_set, (void *)(&dummy_node), + (void **)(&node), NULL)) { + size_t sz = offsetof(prof_thr_node_t, name) + strlen(name) + 1; + prof_thr_node_t *new_node = (prof_thr_node_t *) + iallocztm(tsd_tsdn(tsd), sz, sz_size2index(sz), false, NULL, + true, arena_get(TSDN_NULL, 0, true), true); + if (log_thr_first == NULL) { + log_thr_first = new_node; + log_thr_last = new_node; + } else { + log_thr_last->next = new_node; + log_thr_last = new_node; + } + + new_node->next = NULL; + new_node->index = log_thr_index; + new_node->thr_uid = thr_uid; + strcpy(new_node->name, name); + + log_thr_index++; + ckh_insert(tsd, &log_thr_node_set, (void *)new_node, NULL); + return new_node->index; + } else { + return node->index; + } +} + +static void +prof_try_log(tsd_t *tsd, const void *ptr, size_t usize, prof_tctx_t *tctx) { + malloc_mutex_assert_owner(tsd_tsdn(tsd), tctx->tdata->lock); + + prof_tdata_t *cons_tdata = prof_tdata_get(tsd, false); + if (cons_tdata == NULL) { + /* + * We decide not to log these allocations. cons_tdata will be + * NULL only when the current thread is in a weird state (e.g. + * it's being destroyed). + */ + return; + } + + malloc_mutex_lock(tsd_tsdn(tsd), &log_mtx); + + if (prof_logging_state != prof_logging_state_started) { + goto label_done; + } + + if (!log_tables_initialized) { + bool err1 = ckh_new(tsd, &log_bt_node_set, PROF_CKH_MINITEMS, + prof_bt_node_hash, prof_bt_node_keycomp); + bool err2 = ckh_new(tsd, &log_thr_node_set, PROF_CKH_MINITEMS, + prof_thr_node_hash, prof_thr_node_keycomp); + if (err1 || err2) { + goto label_done; + } + log_tables_initialized = true; + } + + nstime_t alloc_time = prof_alloc_time_get(tsd_tsdn(tsd), ptr, + (alloc_ctx_t *)NULL); + nstime_t free_time = NSTIME_ZERO_INITIALIZER; + nstime_update(&free_time); + + size_t sz = sizeof(prof_alloc_node_t); + prof_alloc_node_t *new_node = (prof_alloc_node_t *) + iallocztm(tsd_tsdn(tsd), sz, sz_size2index(sz), false, NULL, true, + arena_get(TSDN_NULL, 0, true), true); + + const char *prod_thr_name = (tctx->tdata->thread_name == NULL)? + "" : tctx->tdata->thread_name; + const char *cons_thr_name = prof_thread_name_get(tsd); + + prof_bt_t bt; + /* Initialize the backtrace, using the buffer in tdata to store it. */ + bt_init(&bt, cons_tdata->vec); + prof_backtrace(&bt); + prof_bt_t *cons_bt = &bt; + + /* We haven't destroyed tctx yet, so gctx should be good to read. */ + prof_bt_t *prod_bt = &tctx->gctx->bt; + + new_node->next = NULL; + new_node->alloc_thr_ind = prof_log_thr_index(tsd, tctx->tdata->thr_uid, + prod_thr_name); + new_node->free_thr_ind = prof_log_thr_index(tsd, cons_tdata->thr_uid, + cons_thr_name); + new_node->alloc_bt_ind = prof_log_bt_index(tsd, prod_bt); + new_node->free_bt_ind = prof_log_bt_index(tsd, cons_bt); + new_node->alloc_time_ns = nstime_ns(&alloc_time); + new_node->free_time_ns = nstime_ns(&free_time); + new_node->usize = usize; + + if (log_alloc_first == NULL) { + log_alloc_first = new_node; + log_alloc_last = new_node; + } else { + log_alloc_last->next = new_node; + log_alloc_last = new_node; + } + +label_done: + malloc_mutex_unlock(tsd_tsdn(tsd), &log_mtx); +} + void -prof_free_sampled_object(tsd_t *tsd, size_t usize, prof_tctx_t *tctx) { +prof_free_sampled_object(tsd_t *tsd, const void *ptr, size_t usize, + prof_tctx_t *tctx) { malloc_mutex_lock(tsd_tsdn(tsd), tctx->tdata->lock); + assert(tctx->cnts.curobjs > 0); assert(tctx->cnts.curbytes >= usize); tctx->cnts.curobjs--; tctx->cnts.curbytes -= usize; + prof_try_log(tsd, ptr, usize, tctx); + if (prof_tctx_should_destroy(tsd_tsdn(tsd), tctx)) { prof_tctx_destroy(tsd, tctx); } else { malloc_mutex_unlock(tsd_tsdn(tsd), tctx->tdata->lock); } } void bt_init(prof_bt_t *bt, void **vec) { cassert(config_prof); bt->vec = vec; bt->len = 0; } static void prof_enter(tsd_t *tsd, prof_tdata_t *tdata) { cassert(config_prof); assert(tdata == prof_tdata_get(tsd, false)); if (tdata != NULL) { assert(!tdata->enq); tdata->enq = true; } malloc_mutex_lock(tsd_tsdn(tsd), &bt2gctx_mtx); } static void prof_leave(tsd_t *tsd, prof_tdata_t *tdata) { cassert(config_prof); assert(tdata == prof_tdata_get(tsd, false)); malloc_mutex_unlock(tsd_tsdn(tsd), &bt2gctx_mtx); if (tdata != NULL) { bool idump, gdump; assert(tdata->enq); tdata->enq = false; idump = tdata->enq_idump; tdata->enq_idump = false; gdump = tdata->enq_gdump; tdata->enq_gdump = false; if (idump) { prof_idump(tsd_tsdn(tsd)); } if (gdump) { prof_gdump(tsd_tsdn(tsd)); } } } #ifdef JEMALLOC_PROF_LIBUNWIND void prof_backtrace(prof_bt_t *bt) { int nframes; cassert(config_prof); assert(bt->len == 0); assert(bt->vec != NULL); nframes = unw_backtrace(bt->vec, PROF_BT_MAX); if (nframes <= 0) { return; } bt->len = nframes; } #elif (defined(JEMALLOC_PROF_LIBGCC)) static _Unwind_Reason_Code prof_unwind_init_callback(struct _Unwind_Context *context, void *arg) { cassert(config_prof); return _URC_NO_REASON; } static _Unwind_Reason_Code prof_unwind_callback(struct _Unwind_Context *context, void *arg) { prof_unwind_data_t *data = (prof_unwind_data_t *)arg; void *ip; cassert(config_prof); ip = (void *)_Unwind_GetIP(context); if (ip == NULL) { return _URC_END_OF_STACK; } data->bt->vec[data->bt->len] = ip; data->bt->len++; if (data->bt->len == data->max) { return _URC_END_OF_STACK; } return _URC_NO_REASON; } void prof_backtrace(prof_bt_t *bt) { prof_unwind_data_t data = {bt, PROF_BT_MAX}; cassert(config_prof); _Unwind_Backtrace(prof_unwind_callback, &data); } #elif (defined(JEMALLOC_PROF_GCC)) void prof_backtrace(prof_bt_t *bt) { #define BT_FRAME(i) \ if ((i) < PROF_BT_MAX) { \ void *p; \ if (__builtin_frame_address(i) == 0) { \ return; \ } \ p = __builtin_return_address(i); \ if (p == NULL) { \ return; \ } \ bt->vec[(i)] = p; \ bt->len = (i) + 1; \ } else { \ return; \ } cassert(config_prof); BT_FRAME(0) BT_FRAME(1) BT_FRAME(2) BT_FRAME(3) BT_FRAME(4) BT_FRAME(5) BT_FRAME(6) BT_FRAME(7) BT_FRAME(8) BT_FRAME(9) BT_FRAME(10) BT_FRAME(11) BT_FRAME(12) BT_FRAME(13) BT_FRAME(14) BT_FRAME(15) BT_FRAME(16) BT_FRAME(17) BT_FRAME(18) BT_FRAME(19) BT_FRAME(20) BT_FRAME(21) BT_FRAME(22) BT_FRAME(23) BT_FRAME(24) BT_FRAME(25) BT_FRAME(26) BT_FRAME(27) BT_FRAME(28) BT_FRAME(29) BT_FRAME(30) BT_FRAME(31) BT_FRAME(32) BT_FRAME(33) BT_FRAME(34) BT_FRAME(35) BT_FRAME(36) BT_FRAME(37) BT_FRAME(38) BT_FRAME(39) BT_FRAME(40) BT_FRAME(41) BT_FRAME(42) BT_FRAME(43) BT_FRAME(44) BT_FRAME(45) BT_FRAME(46) BT_FRAME(47) BT_FRAME(48) BT_FRAME(49) BT_FRAME(50) BT_FRAME(51) BT_FRAME(52) BT_FRAME(53) BT_FRAME(54) BT_FRAME(55) BT_FRAME(56) BT_FRAME(57) BT_FRAME(58) BT_FRAME(59) BT_FRAME(60) BT_FRAME(61) BT_FRAME(62) BT_FRAME(63) BT_FRAME(64) BT_FRAME(65) BT_FRAME(66) BT_FRAME(67) BT_FRAME(68) BT_FRAME(69) BT_FRAME(70) BT_FRAME(71) BT_FRAME(72) BT_FRAME(73) BT_FRAME(74) BT_FRAME(75) BT_FRAME(76) BT_FRAME(77) BT_FRAME(78) BT_FRAME(79) BT_FRAME(80) BT_FRAME(81) BT_FRAME(82) BT_FRAME(83) BT_FRAME(84) BT_FRAME(85) BT_FRAME(86) BT_FRAME(87) BT_FRAME(88) BT_FRAME(89) BT_FRAME(90) BT_FRAME(91) BT_FRAME(92) BT_FRAME(93) BT_FRAME(94) BT_FRAME(95) BT_FRAME(96) BT_FRAME(97) BT_FRAME(98) BT_FRAME(99) BT_FRAME(100) BT_FRAME(101) BT_FRAME(102) BT_FRAME(103) BT_FRAME(104) BT_FRAME(105) BT_FRAME(106) BT_FRAME(107) BT_FRAME(108) BT_FRAME(109) BT_FRAME(110) BT_FRAME(111) BT_FRAME(112) BT_FRAME(113) BT_FRAME(114) BT_FRAME(115) BT_FRAME(116) BT_FRAME(117) BT_FRAME(118) BT_FRAME(119) BT_FRAME(120) BT_FRAME(121) BT_FRAME(122) BT_FRAME(123) BT_FRAME(124) BT_FRAME(125) BT_FRAME(126) BT_FRAME(127) #undef BT_FRAME } #else void prof_backtrace(prof_bt_t *bt) { cassert(config_prof); not_reached(); } #endif static malloc_mutex_t * prof_gctx_mutex_choose(void) { unsigned ngctxs = atomic_fetch_add_u(&cum_gctxs, 1, ATOMIC_RELAXED); return &gctx_locks[(ngctxs - 1) % PROF_NCTX_LOCKS]; } static malloc_mutex_t * prof_tdata_mutex_choose(uint64_t thr_uid) { return &tdata_locks[thr_uid % PROF_NTDATA_LOCKS]; } static prof_gctx_t * prof_gctx_create(tsdn_t *tsdn, prof_bt_t *bt) { /* * Create a single allocation that has space for vec of length bt->len. */ size_t size = offsetof(prof_gctx_t, vec) + (bt->len * sizeof(void *)); prof_gctx_t *gctx = (prof_gctx_t *)iallocztm(tsdn, size, sz_size2index(size), false, NULL, true, arena_get(TSDN_NULL, 0, true), true); if (gctx == NULL) { return NULL; } gctx->lock = prof_gctx_mutex_choose(); /* * Set nlimbo to 1, in order to avoid a race condition with * prof_tctx_destroy()/prof_gctx_try_destroy(). */ gctx->nlimbo = 1; tctx_tree_new(&gctx->tctxs); /* Duplicate bt. */ memcpy(gctx->vec, bt->vec, bt->len * sizeof(void *)); gctx->bt.vec = gctx->vec; gctx->bt.len = bt->len; return gctx; } static void prof_gctx_try_destroy(tsd_t *tsd, prof_tdata_t *tdata_self, prof_gctx_t *gctx, prof_tdata_t *tdata) { cassert(config_prof); /* * Check that gctx is still unused by any thread cache before destroying * it. prof_lookup() increments gctx->nlimbo in order to avoid a race * condition with this function, as does prof_tctx_destroy() in order to * avoid a race between the main body of prof_tctx_destroy() and entry * into this function. */ prof_enter(tsd, tdata_self); malloc_mutex_lock(tsd_tsdn(tsd), gctx->lock); assert(gctx->nlimbo != 0); if (tctx_tree_empty(&gctx->tctxs) && gctx->nlimbo == 1) { /* Remove gctx from bt2gctx. */ if (ckh_remove(tsd, &bt2gctx, &gctx->bt, NULL, NULL)) { not_reached(); } prof_leave(tsd, tdata_self); /* Destroy gctx. */ malloc_mutex_unlock(tsd_tsdn(tsd), gctx->lock); idalloctm(tsd_tsdn(tsd), gctx, NULL, NULL, true, true); } else { /* * Compensate for increment in prof_tctx_destroy() or * prof_lookup(). */ gctx->nlimbo--; malloc_mutex_unlock(tsd_tsdn(tsd), gctx->lock); prof_leave(tsd, tdata_self); } } static bool prof_tctx_should_destroy(tsdn_t *tsdn, prof_tctx_t *tctx) { malloc_mutex_assert_owner(tsdn, tctx->tdata->lock); if (opt_prof_accum) { return false; } if (tctx->cnts.curobjs != 0) { return false; } if (tctx->prepared) { return false; } return true; } static bool prof_gctx_should_destroy(prof_gctx_t *gctx) { if (opt_prof_accum) { return false; } if (!tctx_tree_empty(&gctx->tctxs)) { return false; } if (gctx->nlimbo != 0) { return false; } return true; } static void prof_tctx_destroy(tsd_t *tsd, prof_tctx_t *tctx) { prof_tdata_t *tdata = tctx->tdata; prof_gctx_t *gctx = tctx->gctx; bool destroy_tdata, destroy_tctx, destroy_gctx; malloc_mutex_assert_owner(tsd_tsdn(tsd), tctx->tdata->lock); assert(tctx->cnts.curobjs == 0); assert(tctx->cnts.curbytes == 0); assert(!opt_prof_accum); assert(tctx->cnts.accumobjs == 0); assert(tctx->cnts.accumbytes == 0); ckh_remove(tsd, &tdata->bt2tctx, &gctx->bt, NULL, NULL); destroy_tdata = prof_tdata_should_destroy(tsd_tsdn(tsd), tdata, false); malloc_mutex_unlock(tsd_tsdn(tsd), tdata->lock); malloc_mutex_lock(tsd_tsdn(tsd), gctx->lock); switch (tctx->state) { case prof_tctx_state_nominal: tctx_tree_remove(&gctx->tctxs, tctx); destroy_tctx = true; if (prof_gctx_should_destroy(gctx)) { /* * Increment gctx->nlimbo in order to keep another * thread from winning the race to destroy gctx while * this one has gctx->lock dropped. Without this, it * would be possible for another thread to: * * 1) Sample an allocation associated with gctx. * 2) Deallocate the sampled object. * 3) Successfully prof_gctx_try_destroy(gctx). * * The result would be that gctx no longer exists by the * time this thread accesses it in * prof_gctx_try_destroy(). */ gctx->nlimbo++; destroy_gctx = true; } else { destroy_gctx = false; } break; case prof_tctx_state_dumping: /* * A dumping thread needs tctx to remain valid until dumping * has finished. Change state such that the dumping thread will * complete destruction during a late dump iteration phase. */ tctx->state = prof_tctx_state_purgatory; destroy_tctx = false; destroy_gctx = false; break; default: not_reached(); destroy_tctx = false; destroy_gctx = false; } malloc_mutex_unlock(tsd_tsdn(tsd), gctx->lock); if (destroy_gctx) { prof_gctx_try_destroy(tsd, prof_tdata_get(tsd, false), gctx, tdata); } malloc_mutex_assert_not_owner(tsd_tsdn(tsd), tctx->tdata->lock); if (destroy_tdata) { prof_tdata_destroy(tsd, tdata, false); } if (destroy_tctx) { idalloctm(tsd_tsdn(tsd), tctx, NULL, NULL, true, true); } } static bool prof_lookup_global(tsd_t *tsd, prof_bt_t *bt, prof_tdata_t *tdata, void **p_btkey, prof_gctx_t **p_gctx, bool *p_new_gctx) { union { prof_gctx_t *p; void *v; } gctx, tgctx; union { prof_bt_t *p; void *v; } btkey; bool new_gctx; prof_enter(tsd, tdata); if (ckh_search(&bt2gctx, bt, &btkey.v, &gctx.v)) { /* bt has never been seen before. Insert it. */ prof_leave(tsd, tdata); tgctx.p = prof_gctx_create(tsd_tsdn(tsd), bt); if (tgctx.v == NULL) { return true; } prof_enter(tsd, tdata); if (ckh_search(&bt2gctx, bt, &btkey.v, &gctx.v)) { gctx.p = tgctx.p; btkey.p = &gctx.p->bt; if (ckh_insert(tsd, &bt2gctx, btkey.v, gctx.v)) { /* OOM. */ prof_leave(tsd, tdata); idalloctm(tsd_tsdn(tsd), gctx.v, NULL, NULL, true, true); return true; } new_gctx = true; } else { new_gctx = false; } } else { tgctx.v = NULL; new_gctx = false; } if (!new_gctx) { /* * Increment nlimbo, in order to avoid a race condition with * prof_tctx_destroy()/prof_gctx_try_destroy(). */ malloc_mutex_lock(tsd_tsdn(tsd), gctx.p->lock); gctx.p->nlimbo++; malloc_mutex_unlock(tsd_tsdn(tsd), gctx.p->lock); new_gctx = false; if (tgctx.v != NULL) { /* Lost race to insert. */ idalloctm(tsd_tsdn(tsd), tgctx.v, NULL, NULL, true, true); } } prof_leave(tsd, tdata); *p_btkey = btkey.v; *p_gctx = gctx.p; *p_new_gctx = new_gctx; return false; } prof_tctx_t * prof_lookup(tsd_t *tsd, prof_bt_t *bt) { union { prof_tctx_t *p; void *v; } ret; prof_tdata_t *tdata; bool not_found; cassert(config_prof); tdata = prof_tdata_get(tsd, false); if (tdata == NULL) { return NULL; } malloc_mutex_lock(tsd_tsdn(tsd), tdata->lock); not_found = ckh_search(&tdata->bt2tctx, bt, NULL, &ret.v); if (!not_found) { /* Note double negative! */ ret.p->prepared = true; } malloc_mutex_unlock(tsd_tsdn(tsd), tdata->lock); if (not_found) { void *btkey; prof_gctx_t *gctx; bool new_gctx, error; /* * This thread's cache lacks bt. Look for it in the global * cache. */ if (prof_lookup_global(tsd, bt, tdata, &btkey, &gctx, &new_gctx)) { return NULL; } /* Link a prof_tctx_t into gctx for this thread. */ ret.v = iallocztm(tsd_tsdn(tsd), sizeof(prof_tctx_t), sz_size2index(sizeof(prof_tctx_t)), false, NULL, true, arena_ichoose(tsd, NULL), true); if (ret.p == NULL) { if (new_gctx) { prof_gctx_try_destroy(tsd, tdata, gctx, tdata); } return NULL; } ret.p->tdata = tdata; ret.p->thr_uid = tdata->thr_uid; ret.p->thr_discrim = tdata->thr_discrim; memset(&ret.p->cnts, 0, sizeof(prof_cnt_t)); ret.p->gctx = gctx; ret.p->tctx_uid = tdata->tctx_uid_next++; ret.p->prepared = true; ret.p->state = prof_tctx_state_initializing; malloc_mutex_lock(tsd_tsdn(tsd), tdata->lock); error = ckh_insert(tsd, &tdata->bt2tctx, btkey, ret.v); malloc_mutex_unlock(tsd_tsdn(tsd), tdata->lock); if (error) { if (new_gctx) { prof_gctx_try_destroy(tsd, tdata, gctx, tdata); } idalloctm(tsd_tsdn(tsd), ret.v, NULL, NULL, true, true); return NULL; } malloc_mutex_lock(tsd_tsdn(tsd), gctx->lock); ret.p->state = prof_tctx_state_nominal; tctx_tree_insert(&gctx->tctxs, ret.p); gctx->nlimbo--; malloc_mutex_unlock(tsd_tsdn(tsd), gctx->lock); } return ret.p; } /* * The bodies of this function and prof_leakcheck() are compiled out unless heap * profiling is enabled, so that it is possible to compile jemalloc with * floating point support completely disabled. Avoiding floating point code is * important on memory-constrained systems, but it also enables a workaround for * versions of glibc that don't properly save/restore floating point registers * during dynamic lazy symbol loading (which internally calls into whatever * malloc implementation happens to be integrated into the application). Note * that some compilers (e.g. gcc 4.8) may use floating point registers for fast * memory moves, so jemalloc must be compiled with such optimizations disabled * (e.g. * -mno-sse) in order for the workaround to be complete. */ void prof_sample_threshold_update(prof_tdata_t *tdata) { #ifdef JEMALLOC_PROF - uint64_t r; - double u; - if (!config_prof) { return; } if (lg_prof_sample == 0) { - tdata->bytes_until_sample = 0; + tsd_bytes_until_sample_set(tsd_fetch(), 0); return; } /* * Compute sample interval as a geometrically distributed random * variable with mean (2^lg_prof_sample). * * __ __ * | log(u) | 1 * tdata->bytes_until_sample = | -------- |, where p = --------------- * | log(1-p) | lg_prof_sample * 2 * * For more information on the math, see: * * Non-Uniform Random Variate Generation * Luc Devroye * Springer-Verlag, New York, 1986 * pp 500 * (http://luc.devroye.org/rnbookindex.html) */ - r = prng_lg_range_u64(&tdata->prng_state, 53); - u = (double)r * (1.0/9007199254740992.0L); - tdata->bytes_until_sample = (uint64_t)(log(u) / + uint64_t r = prng_lg_range_u64(&tdata->prng_state, 53); + double u = (double)r * (1.0/9007199254740992.0L); + uint64_t bytes_until_sample = (uint64_t)(log(u) / log(1.0 - (1.0 / (double)((uint64_t)1U << lg_prof_sample)))) + (uint64_t)1U; + if (bytes_until_sample > SSIZE_MAX) { + bytes_until_sample = SSIZE_MAX; + } + tsd_bytes_until_sample_set(tsd_fetch(), bytes_until_sample); + #endif } #ifdef JEMALLOC_JET static prof_tdata_t * prof_tdata_count_iter(prof_tdata_tree_t *tdatas, prof_tdata_t *tdata, void *arg) { size_t *tdata_count = (size_t *)arg; (*tdata_count)++; return NULL; } size_t prof_tdata_count(void) { size_t tdata_count = 0; tsdn_t *tsdn; tsdn = tsdn_fetch(); malloc_mutex_lock(tsdn, &tdatas_mtx); tdata_tree_iter(&tdatas, NULL, prof_tdata_count_iter, (void *)&tdata_count); malloc_mutex_unlock(tsdn, &tdatas_mtx); return tdata_count; } size_t prof_bt_count(void) { size_t bt_count; tsd_t *tsd; prof_tdata_t *tdata; tsd = tsd_fetch(); tdata = prof_tdata_get(tsd, false); if (tdata == NULL) { return 0; } malloc_mutex_lock(tsd_tsdn(tsd), &bt2gctx_mtx); bt_count = ckh_count(&bt2gctx); malloc_mutex_unlock(tsd_tsdn(tsd), &bt2gctx_mtx); return bt_count; } #endif static int prof_dump_open_impl(bool propagate_err, const char *filename) { int fd; fd = creat(filename, 0644); if (fd == -1 && !propagate_err) { malloc_printf(": creat(\"%s\"), 0644) failed\n", filename); if (opt_abort) { abort(); } } return fd; } prof_dump_open_t *JET_MUTABLE prof_dump_open = prof_dump_open_impl; static bool prof_dump_flush(bool propagate_err) { bool ret = false; ssize_t err; cassert(config_prof); err = malloc_write_fd(prof_dump_fd, prof_dump_buf, prof_dump_buf_end); if (err == -1) { if (!propagate_err) { malloc_write(": write() failed during heap " "profile flush\n"); if (opt_abort) { abort(); } } ret = true; } prof_dump_buf_end = 0; return ret; } static bool prof_dump_close(bool propagate_err) { bool ret; assert(prof_dump_fd != -1); ret = prof_dump_flush(propagate_err); close(prof_dump_fd); prof_dump_fd = -1; return ret; } static bool prof_dump_write(bool propagate_err, const char *s) { size_t i, slen, n; cassert(config_prof); i = 0; slen = strlen(s); while (i < slen) { /* Flush the buffer if it is full. */ if (prof_dump_buf_end == PROF_DUMP_BUFSIZE) { if (prof_dump_flush(propagate_err) && propagate_err) { return true; } } - if (prof_dump_buf_end + slen <= PROF_DUMP_BUFSIZE) { + if (prof_dump_buf_end + slen - i <= PROF_DUMP_BUFSIZE) { /* Finish writing. */ n = slen - i; } else { /* Write as much of s as will fit. */ n = PROF_DUMP_BUFSIZE - prof_dump_buf_end; } memcpy(&prof_dump_buf[prof_dump_buf_end], &s[i], n); prof_dump_buf_end += n; i += n; } + assert(i == slen); return false; } JEMALLOC_FORMAT_PRINTF(2, 3) static bool prof_dump_printf(bool propagate_err, const char *format, ...) { bool ret; va_list ap; char buf[PROF_PRINTF_BUFSIZE]; va_start(ap, format); malloc_vsnprintf(buf, sizeof(buf), format, ap); va_end(ap); ret = prof_dump_write(propagate_err, buf); return ret; } static void prof_tctx_merge_tdata(tsdn_t *tsdn, prof_tctx_t *tctx, prof_tdata_t *tdata) { malloc_mutex_assert_owner(tsdn, tctx->tdata->lock); malloc_mutex_lock(tsdn, tctx->gctx->lock); switch (tctx->state) { case prof_tctx_state_initializing: malloc_mutex_unlock(tsdn, tctx->gctx->lock); return; case prof_tctx_state_nominal: tctx->state = prof_tctx_state_dumping; malloc_mutex_unlock(tsdn, tctx->gctx->lock); memcpy(&tctx->dump_cnts, &tctx->cnts, sizeof(prof_cnt_t)); tdata->cnt_summed.curobjs += tctx->dump_cnts.curobjs; tdata->cnt_summed.curbytes += tctx->dump_cnts.curbytes; if (opt_prof_accum) { tdata->cnt_summed.accumobjs += tctx->dump_cnts.accumobjs; tdata->cnt_summed.accumbytes += tctx->dump_cnts.accumbytes; } break; case prof_tctx_state_dumping: case prof_tctx_state_purgatory: not_reached(); } } static void prof_tctx_merge_gctx(tsdn_t *tsdn, prof_tctx_t *tctx, prof_gctx_t *gctx) { malloc_mutex_assert_owner(tsdn, gctx->lock); gctx->cnt_summed.curobjs += tctx->dump_cnts.curobjs; gctx->cnt_summed.curbytes += tctx->dump_cnts.curbytes; if (opt_prof_accum) { gctx->cnt_summed.accumobjs += tctx->dump_cnts.accumobjs; gctx->cnt_summed.accumbytes += tctx->dump_cnts.accumbytes; } } static prof_tctx_t * prof_tctx_merge_iter(prof_tctx_tree_t *tctxs, prof_tctx_t *tctx, void *arg) { tsdn_t *tsdn = (tsdn_t *)arg; malloc_mutex_assert_owner(tsdn, tctx->gctx->lock); switch (tctx->state) { case prof_tctx_state_nominal: /* New since dumping started; ignore. */ break; case prof_tctx_state_dumping: case prof_tctx_state_purgatory: prof_tctx_merge_gctx(tsdn, tctx, tctx->gctx); break; default: not_reached(); } return NULL; } struct prof_tctx_dump_iter_arg_s { tsdn_t *tsdn; bool propagate_err; }; static prof_tctx_t * prof_tctx_dump_iter(prof_tctx_tree_t *tctxs, prof_tctx_t *tctx, void *opaque) { struct prof_tctx_dump_iter_arg_s *arg = (struct prof_tctx_dump_iter_arg_s *)opaque; malloc_mutex_assert_owner(arg->tsdn, tctx->gctx->lock); switch (tctx->state) { case prof_tctx_state_initializing: case prof_tctx_state_nominal: /* Not captured by this dump. */ break; case prof_tctx_state_dumping: case prof_tctx_state_purgatory: if (prof_dump_printf(arg->propagate_err, " t%"FMTu64": %"FMTu64": %"FMTu64" [%"FMTu64": " "%"FMTu64"]\n", tctx->thr_uid, tctx->dump_cnts.curobjs, tctx->dump_cnts.curbytes, tctx->dump_cnts.accumobjs, tctx->dump_cnts.accumbytes)) { return tctx; } break; default: not_reached(); } return NULL; } static prof_tctx_t * prof_tctx_finish_iter(prof_tctx_tree_t *tctxs, prof_tctx_t *tctx, void *arg) { tsdn_t *tsdn = (tsdn_t *)arg; prof_tctx_t *ret; malloc_mutex_assert_owner(tsdn, tctx->gctx->lock); switch (tctx->state) { case prof_tctx_state_nominal: /* New since dumping started; ignore. */ break; case prof_tctx_state_dumping: tctx->state = prof_tctx_state_nominal; break; case prof_tctx_state_purgatory: ret = tctx; goto label_return; default: not_reached(); } ret = NULL; label_return: return ret; } static void prof_dump_gctx_prep(tsdn_t *tsdn, prof_gctx_t *gctx, prof_gctx_tree_t *gctxs) { cassert(config_prof); malloc_mutex_lock(tsdn, gctx->lock); /* * Increment nlimbo so that gctx won't go away before dump. * Additionally, link gctx into the dump list so that it is included in * prof_dump()'s second pass. */ gctx->nlimbo++; gctx_tree_insert(gctxs, gctx); memset(&gctx->cnt_summed, 0, sizeof(prof_cnt_t)); malloc_mutex_unlock(tsdn, gctx->lock); } struct prof_gctx_merge_iter_arg_s { tsdn_t *tsdn; size_t leak_ngctx; }; static prof_gctx_t * prof_gctx_merge_iter(prof_gctx_tree_t *gctxs, prof_gctx_t *gctx, void *opaque) { struct prof_gctx_merge_iter_arg_s *arg = (struct prof_gctx_merge_iter_arg_s *)opaque; malloc_mutex_lock(arg->tsdn, gctx->lock); tctx_tree_iter(&gctx->tctxs, NULL, prof_tctx_merge_iter, (void *)arg->tsdn); if (gctx->cnt_summed.curobjs != 0) { arg->leak_ngctx++; } malloc_mutex_unlock(arg->tsdn, gctx->lock); return NULL; } static void prof_gctx_finish(tsd_t *tsd, prof_gctx_tree_t *gctxs) { prof_tdata_t *tdata = prof_tdata_get(tsd, false); prof_gctx_t *gctx; /* * Standard tree iteration won't work here, because as soon as we * decrement gctx->nlimbo and unlock gctx, another thread can * concurrently destroy it, which will corrupt the tree. Therefore, * tear down the tree one node at a time during iteration. */ while ((gctx = gctx_tree_first(gctxs)) != NULL) { gctx_tree_remove(gctxs, gctx); malloc_mutex_lock(tsd_tsdn(tsd), gctx->lock); { prof_tctx_t *next; next = NULL; do { prof_tctx_t *to_destroy = tctx_tree_iter(&gctx->tctxs, next, prof_tctx_finish_iter, (void *)tsd_tsdn(tsd)); if (to_destroy != NULL) { next = tctx_tree_next(&gctx->tctxs, to_destroy); tctx_tree_remove(&gctx->tctxs, to_destroy); idalloctm(tsd_tsdn(tsd), to_destroy, NULL, NULL, true, true); } else { next = NULL; } } while (next != NULL); } gctx->nlimbo--; if (prof_gctx_should_destroy(gctx)) { gctx->nlimbo++; malloc_mutex_unlock(tsd_tsdn(tsd), gctx->lock); prof_gctx_try_destroy(tsd, tdata, gctx, tdata); } else { malloc_mutex_unlock(tsd_tsdn(tsd), gctx->lock); } } } struct prof_tdata_merge_iter_arg_s { tsdn_t *tsdn; prof_cnt_t cnt_all; }; static prof_tdata_t * prof_tdata_merge_iter(prof_tdata_tree_t *tdatas, prof_tdata_t *tdata, void *opaque) { struct prof_tdata_merge_iter_arg_s *arg = (struct prof_tdata_merge_iter_arg_s *)opaque; malloc_mutex_lock(arg->tsdn, tdata->lock); if (!tdata->expired) { size_t tabind; union { prof_tctx_t *p; void *v; } tctx; tdata->dumping = true; memset(&tdata->cnt_summed, 0, sizeof(prof_cnt_t)); for (tabind = 0; !ckh_iter(&tdata->bt2tctx, &tabind, NULL, &tctx.v);) { prof_tctx_merge_tdata(arg->tsdn, tctx.p, tdata); } arg->cnt_all.curobjs += tdata->cnt_summed.curobjs; arg->cnt_all.curbytes += tdata->cnt_summed.curbytes; if (opt_prof_accum) { arg->cnt_all.accumobjs += tdata->cnt_summed.accumobjs; arg->cnt_all.accumbytes += tdata->cnt_summed.accumbytes; } } else { tdata->dumping = false; } malloc_mutex_unlock(arg->tsdn, tdata->lock); return NULL; } static prof_tdata_t * prof_tdata_dump_iter(prof_tdata_tree_t *tdatas, prof_tdata_t *tdata, void *arg) { bool propagate_err = *(bool *)arg; if (!tdata->dumping) { return NULL; } if (prof_dump_printf(propagate_err, " t%"FMTu64": %"FMTu64": %"FMTu64" [%"FMTu64": %"FMTu64"]%s%s\n", tdata->thr_uid, tdata->cnt_summed.curobjs, tdata->cnt_summed.curbytes, tdata->cnt_summed.accumobjs, tdata->cnt_summed.accumbytes, (tdata->thread_name != NULL) ? " " : "", (tdata->thread_name != NULL) ? tdata->thread_name : "")) { return tdata; } return NULL; } static bool prof_dump_header_impl(tsdn_t *tsdn, bool propagate_err, const prof_cnt_t *cnt_all) { bool ret; if (prof_dump_printf(propagate_err, "heap_v2/%"FMTu64"\n" " t*: %"FMTu64": %"FMTu64" [%"FMTu64": %"FMTu64"]\n", ((uint64_t)1U << lg_prof_sample), cnt_all->curobjs, cnt_all->curbytes, cnt_all->accumobjs, cnt_all->accumbytes)) { return true; } malloc_mutex_lock(tsdn, &tdatas_mtx); ret = (tdata_tree_iter(&tdatas, NULL, prof_tdata_dump_iter, (void *)&propagate_err) != NULL); malloc_mutex_unlock(tsdn, &tdatas_mtx); return ret; } prof_dump_header_t *JET_MUTABLE prof_dump_header = prof_dump_header_impl; static bool prof_dump_gctx(tsdn_t *tsdn, bool propagate_err, prof_gctx_t *gctx, const prof_bt_t *bt, prof_gctx_tree_t *gctxs) { bool ret; unsigned i; struct prof_tctx_dump_iter_arg_s prof_tctx_dump_iter_arg; cassert(config_prof); malloc_mutex_assert_owner(tsdn, gctx->lock); /* Avoid dumping such gctx's that have no useful data. */ if ((!opt_prof_accum && gctx->cnt_summed.curobjs == 0) || (opt_prof_accum && gctx->cnt_summed.accumobjs == 0)) { assert(gctx->cnt_summed.curobjs == 0); assert(gctx->cnt_summed.curbytes == 0); assert(gctx->cnt_summed.accumobjs == 0); assert(gctx->cnt_summed.accumbytes == 0); ret = false; goto label_return; } if (prof_dump_printf(propagate_err, "@")) { ret = true; goto label_return; } for (i = 0; i < bt->len; i++) { if (prof_dump_printf(propagate_err, " %#"FMTxPTR, (uintptr_t)bt->vec[i])) { ret = true; goto label_return; } } if (prof_dump_printf(propagate_err, "\n" " t*: %"FMTu64": %"FMTu64" [%"FMTu64": %"FMTu64"]\n", gctx->cnt_summed.curobjs, gctx->cnt_summed.curbytes, gctx->cnt_summed.accumobjs, gctx->cnt_summed.accumbytes)) { ret = true; goto label_return; } prof_tctx_dump_iter_arg.tsdn = tsdn; prof_tctx_dump_iter_arg.propagate_err = propagate_err; if (tctx_tree_iter(&gctx->tctxs, NULL, prof_tctx_dump_iter, (void *)&prof_tctx_dump_iter_arg) != NULL) { ret = true; goto label_return; } ret = false; label_return: return ret; } #ifndef _WIN32 JEMALLOC_FORMAT_PRINTF(1, 2) static int prof_open_maps(const char *format, ...) { int mfd; va_list ap; char filename[PATH_MAX + 1]; va_start(ap, format); malloc_vsnprintf(filename, sizeof(filename), format, ap); va_end(ap); #if defined(O_CLOEXEC) mfd = open(filename, O_RDONLY | O_CLOEXEC); #else mfd = open(filename, O_RDONLY); if (mfd != -1) { fcntl(mfd, F_SETFD, fcntl(mfd, F_GETFD) | FD_CLOEXEC); } #endif return mfd; } #endif static int prof_getpid(void) { #ifdef _WIN32 return GetCurrentProcessId(); #else return getpid(); #endif } static bool prof_dump_maps(bool propagate_err) { bool ret; int mfd; cassert(config_prof); #ifdef __FreeBSD__ mfd = prof_open_maps("/proc/curproc/map"); #elif defined(_WIN32) mfd = -1; // Not implemented #else { int pid = prof_getpid(); mfd = prof_open_maps("/proc/%d/task/%d/maps", pid, pid); if (mfd == -1) { mfd = prof_open_maps("/proc/%d/maps", pid); } } #endif if (mfd != -1) { ssize_t nread; if (prof_dump_write(propagate_err, "\nMAPPED_LIBRARIES:\n") && propagate_err) { ret = true; goto label_return; } nread = 0; do { prof_dump_buf_end += nread; if (prof_dump_buf_end == PROF_DUMP_BUFSIZE) { /* Make space in prof_dump_buf before read(). */ if (prof_dump_flush(propagate_err) && propagate_err) { ret = true; goto label_return; } } nread = malloc_read_fd(mfd, &prof_dump_buf[prof_dump_buf_end], PROF_DUMP_BUFSIZE - prof_dump_buf_end); } while (nread > 0); } else { ret = true; goto label_return; } ret = false; label_return: if (mfd != -1) { close(mfd); } return ret; } /* * See prof_sample_threshold_update() comment for why the body of this function * is conditionally compiled. */ static void prof_leakcheck(const prof_cnt_t *cnt_all, size_t leak_ngctx, const char *filename) { #ifdef JEMALLOC_PROF /* * Scaling is equivalent AdjustSamples() in jeprof, but the result may * differ slightly from what jeprof reports, because here we scale the * summary values, whereas jeprof scales each context individually and * reports the sums of the scaled values. */ if (cnt_all->curbytes != 0) { double sample_period = (double)((uint64_t)1 << lg_prof_sample); double ratio = (((double)cnt_all->curbytes) / (double)cnt_all->curobjs) / sample_period; double scale_factor = 1.0 / (1.0 - exp(-ratio)); uint64_t curbytes = (uint64_t)round(((double)cnt_all->curbytes) * scale_factor); uint64_t curobjs = (uint64_t)round(((double)cnt_all->curobjs) * scale_factor); malloc_printf(": Leak approximation summary: ~%"FMTu64 " byte%s, ~%"FMTu64" object%s, >= %zu context%s\n", curbytes, (curbytes != 1) ? "s" : "", curobjs, (curobjs != 1) ? "s" : "", leak_ngctx, (leak_ngctx != 1) ? "s" : ""); malloc_printf( ": Run jeprof on \"%s\" for leak detail\n", filename); } #endif } struct prof_gctx_dump_iter_arg_s { tsdn_t *tsdn; bool propagate_err; }; static prof_gctx_t * prof_gctx_dump_iter(prof_gctx_tree_t *gctxs, prof_gctx_t *gctx, void *opaque) { prof_gctx_t *ret; struct prof_gctx_dump_iter_arg_s *arg = (struct prof_gctx_dump_iter_arg_s *)opaque; malloc_mutex_lock(arg->tsdn, gctx->lock); if (prof_dump_gctx(arg->tsdn, arg->propagate_err, gctx, &gctx->bt, gctxs)) { ret = gctx; goto label_return; } ret = NULL; label_return: malloc_mutex_unlock(arg->tsdn, gctx->lock); return ret; } static void prof_dump_prep(tsd_t *tsd, prof_tdata_t *tdata, struct prof_tdata_merge_iter_arg_s *prof_tdata_merge_iter_arg, struct prof_gctx_merge_iter_arg_s *prof_gctx_merge_iter_arg, prof_gctx_tree_t *gctxs) { size_t tabind; union { prof_gctx_t *p; void *v; } gctx; prof_enter(tsd, tdata); /* * Put gctx's in limbo and clear their counters in preparation for * summing. */ gctx_tree_new(gctxs); for (tabind = 0; !ckh_iter(&bt2gctx, &tabind, NULL, &gctx.v);) { prof_dump_gctx_prep(tsd_tsdn(tsd), gctx.p, gctxs); } /* * Iterate over tdatas, and for the non-expired ones snapshot their tctx * stats and merge them into the associated gctx's. */ prof_tdata_merge_iter_arg->tsdn = tsd_tsdn(tsd); memset(&prof_tdata_merge_iter_arg->cnt_all, 0, sizeof(prof_cnt_t)); malloc_mutex_lock(tsd_tsdn(tsd), &tdatas_mtx); tdata_tree_iter(&tdatas, NULL, prof_tdata_merge_iter, (void *)prof_tdata_merge_iter_arg); malloc_mutex_unlock(tsd_tsdn(tsd), &tdatas_mtx); /* Merge tctx stats into gctx's. */ prof_gctx_merge_iter_arg->tsdn = tsd_tsdn(tsd); prof_gctx_merge_iter_arg->leak_ngctx = 0; gctx_tree_iter(gctxs, NULL, prof_gctx_merge_iter, (void *)prof_gctx_merge_iter_arg); prof_leave(tsd, tdata); } static bool prof_dump_file(tsd_t *tsd, bool propagate_err, const char *filename, bool leakcheck, prof_tdata_t *tdata, struct prof_tdata_merge_iter_arg_s *prof_tdata_merge_iter_arg, struct prof_gctx_merge_iter_arg_s *prof_gctx_merge_iter_arg, struct prof_gctx_dump_iter_arg_s *prof_gctx_dump_iter_arg, prof_gctx_tree_t *gctxs) { /* Create dump file. */ if ((prof_dump_fd = prof_dump_open(propagate_err, filename)) == -1) { return true; } /* Dump profile header. */ if (prof_dump_header(tsd_tsdn(tsd), propagate_err, &prof_tdata_merge_iter_arg->cnt_all)) { goto label_write_error; } /* Dump per gctx profile stats. */ prof_gctx_dump_iter_arg->tsdn = tsd_tsdn(tsd); prof_gctx_dump_iter_arg->propagate_err = propagate_err; if (gctx_tree_iter(gctxs, NULL, prof_gctx_dump_iter, (void *)prof_gctx_dump_iter_arg) != NULL) { goto label_write_error; } /* Dump /proc//maps if possible. */ if (prof_dump_maps(propagate_err)) { goto label_write_error; } if (prof_dump_close(propagate_err)) { return true; } return false; label_write_error: prof_dump_close(propagate_err); return true; } static bool prof_dump(tsd_t *tsd, bool propagate_err, const char *filename, bool leakcheck) { cassert(config_prof); assert(tsd_reentrancy_level_get(tsd) == 0); prof_tdata_t * tdata = prof_tdata_get(tsd, true); if (tdata == NULL) { return true; } pre_reentrancy(tsd, NULL); malloc_mutex_lock(tsd_tsdn(tsd), &prof_dump_mtx); prof_gctx_tree_t gctxs; struct prof_tdata_merge_iter_arg_s prof_tdata_merge_iter_arg; struct prof_gctx_merge_iter_arg_s prof_gctx_merge_iter_arg; struct prof_gctx_dump_iter_arg_s prof_gctx_dump_iter_arg; prof_dump_prep(tsd, tdata, &prof_tdata_merge_iter_arg, &prof_gctx_merge_iter_arg, &gctxs); bool err = prof_dump_file(tsd, propagate_err, filename, leakcheck, tdata, &prof_tdata_merge_iter_arg, &prof_gctx_merge_iter_arg, &prof_gctx_dump_iter_arg, &gctxs); prof_gctx_finish(tsd, &gctxs); malloc_mutex_unlock(tsd_tsdn(tsd), &prof_dump_mtx); post_reentrancy(tsd); if (err) { return true; } if (leakcheck) { prof_leakcheck(&prof_tdata_merge_iter_arg.cnt_all, prof_gctx_merge_iter_arg.leak_ngctx, filename); } return false; } #ifdef JEMALLOC_JET void prof_cnt_all(uint64_t *curobjs, uint64_t *curbytes, uint64_t *accumobjs, uint64_t *accumbytes) { tsd_t *tsd; prof_tdata_t *tdata; struct prof_tdata_merge_iter_arg_s prof_tdata_merge_iter_arg; struct prof_gctx_merge_iter_arg_s prof_gctx_merge_iter_arg; prof_gctx_tree_t gctxs; tsd = tsd_fetch(); tdata = prof_tdata_get(tsd, false); if (tdata == NULL) { if (curobjs != NULL) { *curobjs = 0; } if (curbytes != NULL) { *curbytes = 0; } if (accumobjs != NULL) { *accumobjs = 0; } if (accumbytes != NULL) { *accumbytes = 0; } return; } prof_dump_prep(tsd, tdata, &prof_tdata_merge_iter_arg, &prof_gctx_merge_iter_arg, &gctxs); prof_gctx_finish(tsd, &gctxs); if (curobjs != NULL) { *curobjs = prof_tdata_merge_iter_arg.cnt_all.curobjs; } if (curbytes != NULL) { *curbytes = prof_tdata_merge_iter_arg.cnt_all.curbytes; } if (accumobjs != NULL) { *accumobjs = prof_tdata_merge_iter_arg.cnt_all.accumobjs; } if (accumbytes != NULL) { *accumbytes = prof_tdata_merge_iter_arg.cnt_all.accumbytes; } } #endif #define DUMP_FILENAME_BUFSIZE (PATH_MAX + 1) #define VSEQ_INVALID UINT64_C(0xffffffffffffffff) static void prof_dump_filename(char *filename, char v, uint64_t vseq) { cassert(config_prof); if (vseq != VSEQ_INVALID) { /* "...v.heap" */ malloc_snprintf(filename, DUMP_FILENAME_BUFSIZE, "%s.%d.%"FMTu64".%c%"FMTu64".heap", opt_prof_prefix, prof_getpid(), prof_dump_seq, v, vseq); } else { /* "....heap" */ malloc_snprintf(filename, DUMP_FILENAME_BUFSIZE, "%s.%d.%"FMTu64".%c.heap", opt_prof_prefix, prof_getpid(), prof_dump_seq, v); } prof_dump_seq++; } static void prof_fdump(void) { tsd_t *tsd; char filename[DUMP_FILENAME_BUFSIZE]; cassert(config_prof); assert(opt_prof_final); assert(opt_prof_prefix[0] != '\0'); if (!prof_booted) { return; } tsd = tsd_fetch(); assert(tsd_reentrancy_level_get(tsd) == 0); malloc_mutex_lock(tsd_tsdn(tsd), &prof_dump_seq_mtx); prof_dump_filename(filename, 'f', VSEQ_INVALID); malloc_mutex_unlock(tsd_tsdn(tsd), &prof_dump_seq_mtx); prof_dump(tsd, false, filename, opt_prof_leak); } bool prof_accum_init(tsdn_t *tsdn, prof_accum_t *prof_accum) { cassert(config_prof); #ifndef JEMALLOC_ATOMIC_U64 if (malloc_mutex_init(&prof_accum->mtx, "prof_accum", WITNESS_RANK_PROF_ACCUM, malloc_mutex_rank_exclusive)) { return true; } prof_accum->accumbytes = 0; #else atomic_store_u64(&prof_accum->accumbytes, 0, ATOMIC_RELAXED); #endif return false; } void prof_idump(tsdn_t *tsdn) { tsd_t *tsd; prof_tdata_t *tdata; cassert(config_prof); if (!prof_booted || tsdn_null(tsdn) || !prof_active_get_unlocked()) { return; } tsd = tsdn_tsd(tsdn); if (tsd_reentrancy_level_get(tsd) > 0) { return; } tdata = prof_tdata_get(tsd, false); if (tdata == NULL) { return; } if (tdata->enq) { tdata->enq_idump = true; return; } if (opt_prof_prefix[0] != '\0') { char filename[PATH_MAX + 1]; malloc_mutex_lock(tsd_tsdn(tsd), &prof_dump_seq_mtx); prof_dump_filename(filename, 'i', prof_dump_iseq); prof_dump_iseq++; malloc_mutex_unlock(tsd_tsdn(tsd), &prof_dump_seq_mtx); prof_dump(tsd, false, filename, false); } } bool prof_mdump(tsd_t *tsd, const char *filename) { cassert(config_prof); assert(tsd_reentrancy_level_get(tsd) == 0); if (!opt_prof || !prof_booted) { return true; } char filename_buf[DUMP_FILENAME_BUFSIZE]; if (filename == NULL) { /* No filename specified, so automatically generate one. */ if (opt_prof_prefix[0] == '\0') { return true; } malloc_mutex_lock(tsd_tsdn(tsd), &prof_dump_seq_mtx); prof_dump_filename(filename_buf, 'm', prof_dump_mseq); prof_dump_mseq++; malloc_mutex_unlock(tsd_tsdn(tsd), &prof_dump_seq_mtx); filename = filename_buf; } return prof_dump(tsd, true, filename, false); } void prof_gdump(tsdn_t *tsdn) { tsd_t *tsd; prof_tdata_t *tdata; cassert(config_prof); if (!prof_booted || tsdn_null(tsdn) || !prof_active_get_unlocked()) { return; } tsd = tsdn_tsd(tsdn); if (tsd_reentrancy_level_get(tsd) > 0) { return; } tdata = prof_tdata_get(tsd, false); if (tdata == NULL) { return; } if (tdata->enq) { tdata->enq_gdump = true; return; } if (opt_prof_prefix[0] != '\0') { char filename[DUMP_FILENAME_BUFSIZE]; malloc_mutex_lock(tsdn, &prof_dump_seq_mtx); prof_dump_filename(filename, 'u', prof_dump_useq); prof_dump_useq++; malloc_mutex_unlock(tsdn, &prof_dump_seq_mtx); prof_dump(tsd, false, filename, false); } } static void prof_bt_hash(const void *key, size_t r_hash[2]) { prof_bt_t *bt = (prof_bt_t *)key; cassert(config_prof); hash(bt->vec, bt->len * sizeof(void *), 0x94122f33U, r_hash); } static bool prof_bt_keycomp(const void *k1, const void *k2) { const prof_bt_t *bt1 = (prof_bt_t *)k1; const prof_bt_t *bt2 = (prof_bt_t *)k2; cassert(config_prof); if (bt1->len != bt2->len) { return false; } return (memcmp(bt1->vec, bt2->vec, bt1->len * sizeof(void *)) == 0); } +static void +prof_bt_node_hash(const void *key, size_t r_hash[2]) { + const prof_bt_node_t *bt_node = (prof_bt_node_t *)key; + prof_bt_hash((void *)(&bt_node->bt), r_hash); +} + +static bool +prof_bt_node_keycomp(const void *k1, const void *k2) { + const prof_bt_node_t *bt_node1 = (prof_bt_node_t *)k1; + const prof_bt_node_t *bt_node2 = (prof_bt_node_t *)k2; + return prof_bt_keycomp((void *)(&bt_node1->bt), + (void *)(&bt_node2->bt)); +} + +static void +prof_thr_node_hash(const void *key, size_t r_hash[2]) { + const prof_thr_node_t *thr_node = (prof_thr_node_t *)key; + hash(&thr_node->thr_uid, sizeof(uint64_t), 0x94122f35U, r_hash); +} + +static bool +prof_thr_node_keycomp(const void *k1, const void *k2) { + const prof_thr_node_t *thr_node1 = (prof_thr_node_t *)k1; + const prof_thr_node_t *thr_node2 = (prof_thr_node_t *)k2; + return thr_node1->thr_uid == thr_node2->thr_uid; +} + static uint64_t prof_thr_uid_alloc(tsdn_t *tsdn) { uint64_t thr_uid; malloc_mutex_lock(tsdn, &next_thr_uid_mtx); thr_uid = next_thr_uid; next_thr_uid++; malloc_mutex_unlock(tsdn, &next_thr_uid_mtx); return thr_uid; } static prof_tdata_t * prof_tdata_init_impl(tsd_t *tsd, uint64_t thr_uid, uint64_t thr_discrim, char *thread_name, bool active) { prof_tdata_t *tdata; cassert(config_prof); /* Initialize an empty cache for this thread. */ tdata = (prof_tdata_t *)iallocztm(tsd_tsdn(tsd), sizeof(prof_tdata_t), sz_size2index(sizeof(prof_tdata_t)), false, NULL, true, arena_get(TSDN_NULL, 0, true), true); if (tdata == NULL) { return NULL; } tdata->lock = prof_tdata_mutex_choose(thr_uid); tdata->thr_uid = thr_uid; tdata->thr_discrim = thr_discrim; tdata->thread_name = thread_name; tdata->attached = true; tdata->expired = false; tdata->tctx_uid_next = 0; if (ckh_new(tsd, &tdata->bt2tctx, PROF_CKH_MINITEMS, prof_bt_hash, prof_bt_keycomp)) { idalloctm(tsd_tsdn(tsd), tdata, NULL, NULL, true, true); return NULL; } tdata->prng_state = (uint64_t)(uintptr_t)tdata; prof_sample_threshold_update(tdata); tdata->enq = false; tdata->enq_idump = false; tdata->enq_gdump = false; tdata->dumping = false; tdata->active = active; malloc_mutex_lock(tsd_tsdn(tsd), &tdatas_mtx); tdata_tree_insert(&tdatas, tdata); malloc_mutex_unlock(tsd_tsdn(tsd), &tdatas_mtx); return tdata; } prof_tdata_t * prof_tdata_init(tsd_t *tsd) { return prof_tdata_init_impl(tsd, prof_thr_uid_alloc(tsd_tsdn(tsd)), 0, NULL, prof_thread_active_init_get(tsd_tsdn(tsd))); } static bool prof_tdata_should_destroy_unlocked(prof_tdata_t *tdata, bool even_if_attached) { if (tdata->attached && !even_if_attached) { return false; } if (ckh_count(&tdata->bt2tctx) != 0) { return false; } return true; } static bool prof_tdata_should_destroy(tsdn_t *tsdn, prof_tdata_t *tdata, bool even_if_attached) { malloc_mutex_assert_owner(tsdn, tdata->lock); return prof_tdata_should_destroy_unlocked(tdata, even_if_attached); } static void prof_tdata_destroy_locked(tsd_t *tsd, prof_tdata_t *tdata, bool even_if_attached) { malloc_mutex_assert_owner(tsd_tsdn(tsd), &tdatas_mtx); tdata_tree_remove(&tdatas, tdata); assert(prof_tdata_should_destroy_unlocked(tdata, even_if_attached)); if (tdata->thread_name != NULL) { idalloctm(tsd_tsdn(tsd), tdata->thread_name, NULL, NULL, true, true); } ckh_delete(tsd, &tdata->bt2tctx); idalloctm(tsd_tsdn(tsd), tdata, NULL, NULL, true, true); } static void prof_tdata_destroy(tsd_t *tsd, prof_tdata_t *tdata, bool even_if_attached) { malloc_mutex_lock(tsd_tsdn(tsd), &tdatas_mtx); prof_tdata_destroy_locked(tsd, tdata, even_if_attached); malloc_mutex_unlock(tsd_tsdn(tsd), &tdatas_mtx); } static void prof_tdata_detach(tsd_t *tsd, prof_tdata_t *tdata) { bool destroy_tdata; malloc_mutex_lock(tsd_tsdn(tsd), tdata->lock); if (tdata->attached) { destroy_tdata = prof_tdata_should_destroy(tsd_tsdn(tsd), tdata, true); /* * Only detach if !destroy_tdata, because detaching would allow * another thread to win the race to destroy tdata. */ if (!destroy_tdata) { tdata->attached = false; } tsd_prof_tdata_set(tsd, NULL); } else { destroy_tdata = false; } malloc_mutex_unlock(tsd_tsdn(tsd), tdata->lock); if (destroy_tdata) { prof_tdata_destroy(tsd, tdata, true); } } prof_tdata_t * prof_tdata_reinit(tsd_t *tsd, prof_tdata_t *tdata) { uint64_t thr_uid = tdata->thr_uid; uint64_t thr_discrim = tdata->thr_discrim + 1; char *thread_name = (tdata->thread_name != NULL) ? prof_thread_name_alloc(tsd_tsdn(tsd), tdata->thread_name) : NULL; bool active = tdata->active; prof_tdata_detach(tsd, tdata); return prof_tdata_init_impl(tsd, thr_uid, thr_discrim, thread_name, active); } static bool prof_tdata_expire(tsdn_t *tsdn, prof_tdata_t *tdata) { bool destroy_tdata; malloc_mutex_lock(tsdn, tdata->lock); if (!tdata->expired) { tdata->expired = true; destroy_tdata = tdata->attached ? false : prof_tdata_should_destroy(tsdn, tdata, false); } else { destroy_tdata = false; } malloc_mutex_unlock(tsdn, tdata->lock); return destroy_tdata; } static prof_tdata_t * prof_tdata_reset_iter(prof_tdata_tree_t *tdatas, prof_tdata_t *tdata, void *arg) { tsdn_t *tsdn = (tsdn_t *)arg; return (prof_tdata_expire(tsdn, tdata) ? tdata : NULL); } void prof_reset(tsd_t *tsd, size_t lg_sample) { prof_tdata_t *next; assert(lg_sample < (sizeof(uint64_t) << 3)); malloc_mutex_lock(tsd_tsdn(tsd), &prof_dump_mtx); malloc_mutex_lock(tsd_tsdn(tsd), &tdatas_mtx); lg_prof_sample = lg_sample; next = NULL; do { prof_tdata_t *to_destroy = tdata_tree_iter(&tdatas, next, prof_tdata_reset_iter, (void *)tsd); if (to_destroy != NULL) { next = tdata_tree_next(&tdatas, to_destroy); prof_tdata_destroy_locked(tsd, to_destroy, false); } else { next = NULL; } } while (next != NULL); malloc_mutex_unlock(tsd_tsdn(tsd), &tdatas_mtx); malloc_mutex_unlock(tsd_tsdn(tsd), &prof_dump_mtx); } void prof_tdata_cleanup(tsd_t *tsd) { prof_tdata_t *tdata; if (!config_prof) { return; } tdata = tsd_prof_tdata_get(tsd); if (tdata != NULL) { prof_tdata_detach(tsd, tdata); } } bool prof_active_get(tsdn_t *tsdn) { bool prof_active_current; malloc_mutex_lock(tsdn, &prof_active_mtx); prof_active_current = prof_active; malloc_mutex_unlock(tsdn, &prof_active_mtx); return prof_active_current; } bool prof_active_set(tsdn_t *tsdn, bool active) { bool prof_active_old; malloc_mutex_lock(tsdn, &prof_active_mtx); prof_active_old = prof_active; prof_active = active; malloc_mutex_unlock(tsdn, &prof_active_mtx); return prof_active_old; } +#ifdef JEMALLOC_JET +size_t +prof_log_bt_count(void) { + size_t cnt = 0; + prof_bt_node_t *node = log_bt_first; + while (node != NULL) { + cnt++; + node = node->next; + } + return cnt; +} + +size_t +prof_log_alloc_count(void) { + size_t cnt = 0; + prof_alloc_node_t *node = log_alloc_first; + while (node != NULL) { + cnt++; + node = node->next; + } + return cnt; +} + +size_t +prof_log_thr_count(void) { + size_t cnt = 0; + prof_thr_node_t *node = log_thr_first; + while (node != NULL) { + cnt++; + node = node->next; + } + return cnt; +} + +bool +prof_log_is_logging(void) { + return prof_logging_state == prof_logging_state_started; +} + +bool +prof_log_rep_check(void) { + if (prof_logging_state == prof_logging_state_stopped + && log_tables_initialized) { + return true; + } + + if (log_bt_last != NULL && log_bt_last->next != NULL) { + return true; + } + if (log_thr_last != NULL && log_thr_last->next != NULL) { + return true; + } + if (log_alloc_last != NULL && log_alloc_last->next != NULL) { + return true; + } + + size_t bt_count = prof_log_bt_count(); + size_t thr_count = prof_log_thr_count(); + size_t alloc_count = prof_log_alloc_count(); + + + if (prof_logging_state == prof_logging_state_stopped) { + if (bt_count != 0 || thr_count != 0 || alloc_count || 0) { + return true; + } + } + + prof_alloc_node_t *node = log_alloc_first; + while (node != NULL) { + if (node->alloc_bt_ind >= bt_count) { + return true; + } + if (node->free_bt_ind >= bt_count) { + return true; + } + if (node->alloc_thr_ind >= thr_count) { + return true; + } + if (node->free_thr_ind >= thr_count) { + return true; + } + if (node->alloc_time_ns > node->free_time_ns) { + return true; + } + node = node->next; + } + + return false; +} + +void +prof_log_dummy_set(bool new_value) { + prof_log_dummy = new_value; +} +#endif + +bool +prof_log_start(tsdn_t *tsdn, const char *filename) { + if (!opt_prof || !prof_booted) { + return true; + } + + bool ret = false; + size_t buf_size = PATH_MAX + 1; + + malloc_mutex_lock(tsdn, &log_mtx); + + if (prof_logging_state != prof_logging_state_stopped) { + ret = true; + } else if (filename == NULL) { + /* Make default name. */ + malloc_snprintf(log_filename, buf_size, "%s.%d.%"FMTu64".json", + opt_prof_prefix, prof_getpid(), log_seq); + log_seq++; + prof_logging_state = prof_logging_state_started; + } else if (strlen(filename) >= buf_size) { + ret = true; + } else { + strcpy(log_filename, filename); + prof_logging_state = prof_logging_state_started; + } + + if (!ret) { + nstime_update(&log_start_timestamp); + } + + malloc_mutex_unlock(tsdn, &log_mtx); + + return ret; +} + +/* Used as an atexit function to stop logging on exit. */ +static void +prof_log_stop_final(void) { + tsd_t *tsd = tsd_fetch(); + prof_log_stop(tsd_tsdn(tsd)); +} + +struct prof_emitter_cb_arg_s { + int fd; + ssize_t ret; +}; + +static void +prof_emitter_write_cb(void *opaque, const char *to_write) { + struct prof_emitter_cb_arg_s *arg = + (struct prof_emitter_cb_arg_s *)opaque; + size_t bytes = strlen(to_write); +#ifdef JEMALLOC_JET + if (prof_log_dummy) { + return; + } +#endif + arg->ret = write(arg->fd, (void *)to_write, bytes); +} + +/* + * prof_log_emit_{...} goes through the appropriate linked list, emitting each + * node to the json and deallocating it. + */ +static void +prof_log_emit_threads(tsd_t *tsd, emitter_t *emitter) { + emitter_json_array_kv_begin(emitter, "threads"); + prof_thr_node_t *thr_node = log_thr_first; + prof_thr_node_t *thr_old_node; + while (thr_node != NULL) { + emitter_json_object_begin(emitter); + + emitter_json_kv(emitter, "thr_uid", emitter_type_uint64, + &thr_node->thr_uid); + + char *thr_name = thr_node->name; + + emitter_json_kv(emitter, "thr_name", emitter_type_string, + &thr_name); + + emitter_json_object_end(emitter); + thr_old_node = thr_node; + thr_node = thr_node->next; + idalloc(tsd, thr_old_node); + } + emitter_json_array_end(emitter); +} + +static void +prof_log_emit_traces(tsd_t *tsd, emitter_t *emitter) { + emitter_json_array_kv_begin(emitter, "stack_traces"); + prof_bt_node_t *bt_node = log_bt_first; + prof_bt_node_t *bt_old_node; + /* + * Calculate how many hex digits we need: twice number of bytes, two for + * "0x", and then one more for terminating '\0'. + */ + char buf[2 * sizeof(intptr_t) + 3]; + size_t buf_sz = sizeof(buf); + while (bt_node != NULL) { + emitter_json_array_begin(emitter); + size_t i; + for (i = 0; i < bt_node->bt.len; i++) { + malloc_snprintf(buf, buf_sz, "%p", bt_node->bt.vec[i]); + char *trace_str = buf; + emitter_json_value(emitter, emitter_type_string, + &trace_str); + } + emitter_json_array_end(emitter); + + bt_old_node = bt_node; + bt_node = bt_node->next; + idalloc(tsd, bt_old_node); + } + emitter_json_array_end(emitter); +} + +static void +prof_log_emit_allocs(tsd_t *tsd, emitter_t *emitter) { + emitter_json_array_kv_begin(emitter, "allocations"); + prof_alloc_node_t *alloc_node = log_alloc_first; + prof_alloc_node_t *alloc_old_node; + while (alloc_node != NULL) { + emitter_json_object_begin(emitter); + + emitter_json_kv(emitter, "alloc_thread", emitter_type_size, + &alloc_node->alloc_thr_ind); + + emitter_json_kv(emitter, "free_thread", emitter_type_size, + &alloc_node->free_thr_ind); + + emitter_json_kv(emitter, "alloc_trace", emitter_type_size, + &alloc_node->alloc_bt_ind); + + emitter_json_kv(emitter, "free_trace", emitter_type_size, + &alloc_node->free_bt_ind); + + emitter_json_kv(emitter, "alloc_timestamp", + emitter_type_uint64, &alloc_node->alloc_time_ns); + + emitter_json_kv(emitter, "free_timestamp", emitter_type_uint64, + &alloc_node->free_time_ns); + + emitter_json_kv(emitter, "usize", emitter_type_uint64, + &alloc_node->usize); + + emitter_json_object_end(emitter); + + alloc_old_node = alloc_node; + alloc_node = alloc_node->next; + idalloc(tsd, alloc_old_node); + } + emitter_json_array_end(emitter); +} + +static void +prof_log_emit_metadata(emitter_t *emitter) { + emitter_json_object_kv_begin(emitter, "info"); + + nstime_t now = NSTIME_ZERO_INITIALIZER; + + nstime_update(&now); + uint64_t ns = nstime_ns(&now) - nstime_ns(&log_start_timestamp); + emitter_json_kv(emitter, "duration", emitter_type_uint64, &ns); + + char *vers = JEMALLOC_VERSION; + emitter_json_kv(emitter, "version", + emitter_type_string, &vers); + + emitter_json_kv(emitter, "lg_sample_rate", + emitter_type_int, &lg_prof_sample); + + int pid = prof_getpid(); + emitter_json_kv(emitter, "pid", emitter_type_int, &pid); + + emitter_json_object_end(emitter); +} + + +bool +prof_log_stop(tsdn_t *tsdn) { + if (!opt_prof || !prof_booted) { + return true; + } + + tsd_t *tsd = tsdn_tsd(tsdn); + malloc_mutex_lock(tsdn, &log_mtx); + + if (prof_logging_state != prof_logging_state_started) { + malloc_mutex_unlock(tsdn, &log_mtx); + return true; + } + + /* + * Set the state to dumping. We'll set it to stopped when we're done. + * Since other threads won't be able to start/stop/log when the state is + * dumping, we don't have to hold the lock during the whole method. + */ + prof_logging_state = prof_logging_state_dumping; + malloc_mutex_unlock(tsdn, &log_mtx); + + + emitter_t emitter; + + /* Create a file. */ + + int fd; +#ifdef JEMALLOC_JET + if (prof_log_dummy) { + fd = 0; + } else { + fd = creat(log_filename, 0644); + } +#else + fd = creat(log_filename, 0644); +#endif + + if (fd == -1) { + malloc_printf(": creat() for log file \"%s\" " + " failed with %d\n", log_filename, errno); + if (opt_abort) { + abort(); + } + return true; + } + + /* Emit to json. */ + struct prof_emitter_cb_arg_s arg; + arg.fd = fd; + emitter_init(&emitter, emitter_output_json, &prof_emitter_write_cb, + (void *)(&arg)); + + emitter_begin(&emitter); + prof_log_emit_metadata(&emitter); + prof_log_emit_threads(tsd, &emitter); + prof_log_emit_traces(tsd, &emitter); + prof_log_emit_allocs(tsd, &emitter); + emitter_end(&emitter); + + /* Reset global state. */ + if (log_tables_initialized) { + ckh_delete(tsd, &log_bt_node_set); + ckh_delete(tsd, &log_thr_node_set); + } + log_tables_initialized = false; + log_bt_index = 0; + log_thr_index = 0; + log_bt_first = NULL; + log_bt_last = NULL; + log_thr_first = NULL; + log_thr_last = NULL; + log_alloc_first = NULL; + log_alloc_last = NULL; + + malloc_mutex_lock(tsdn, &log_mtx); + prof_logging_state = prof_logging_state_stopped; + malloc_mutex_unlock(tsdn, &log_mtx); + +#ifdef JEMALLOC_JET + if (prof_log_dummy) { + return false; + } +#endif + return close(fd); +} + const char * prof_thread_name_get(tsd_t *tsd) { prof_tdata_t *tdata; tdata = prof_tdata_get(tsd, true); if (tdata == NULL) { return ""; } return (tdata->thread_name != NULL ? tdata->thread_name : ""); } static char * prof_thread_name_alloc(tsdn_t *tsdn, const char *thread_name) { char *ret; size_t size; if (thread_name == NULL) { return NULL; } size = strlen(thread_name) + 1; if (size == 1) { return ""; } ret = iallocztm(tsdn, size, sz_size2index(size), false, NULL, true, arena_get(TSDN_NULL, 0, true), true); if (ret == NULL) { return NULL; } memcpy(ret, thread_name, size); return ret; } int prof_thread_name_set(tsd_t *tsd, const char *thread_name) { prof_tdata_t *tdata; unsigned i; char *s; tdata = prof_tdata_get(tsd, true); if (tdata == NULL) { return EAGAIN; } /* Validate input. */ if (thread_name == NULL) { return EFAULT; } for (i = 0; thread_name[i] != '\0'; i++) { char c = thread_name[i]; if (!isgraph(c) && !isblank(c)) { return EFAULT; } } s = prof_thread_name_alloc(tsd_tsdn(tsd), thread_name); if (s == NULL) { return EAGAIN; } if (tdata->thread_name != NULL) { idalloctm(tsd_tsdn(tsd), tdata->thread_name, NULL, NULL, true, true); tdata->thread_name = NULL; } if (strlen(s) > 0) { tdata->thread_name = s; } return 0; } bool prof_thread_active_get(tsd_t *tsd) { prof_tdata_t *tdata; tdata = prof_tdata_get(tsd, true); if (tdata == NULL) { return false; } return tdata->active; } bool prof_thread_active_set(tsd_t *tsd, bool active) { prof_tdata_t *tdata; tdata = prof_tdata_get(tsd, true); if (tdata == NULL) { return true; } tdata->active = active; return false; } bool prof_thread_active_init_get(tsdn_t *tsdn) { bool active_init; malloc_mutex_lock(tsdn, &prof_thread_active_init_mtx); active_init = prof_thread_active_init; malloc_mutex_unlock(tsdn, &prof_thread_active_init_mtx); return active_init; } bool prof_thread_active_init_set(tsdn_t *tsdn, bool active_init) { bool active_init_old; malloc_mutex_lock(tsdn, &prof_thread_active_init_mtx); active_init_old = prof_thread_active_init; prof_thread_active_init = active_init; malloc_mutex_unlock(tsdn, &prof_thread_active_init_mtx); return active_init_old; } bool prof_gdump_get(tsdn_t *tsdn) { bool prof_gdump_current; malloc_mutex_lock(tsdn, &prof_gdump_mtx); prof_gdump_current = prof_gdump_val; malloc_mutex_unlock(tsdn, &prof_gdump_mtx); return prof_gdump_current; } bool prof_gdump_set(tsdn_t *tsdn, bool gdump) { bool prof_gdump_old; malloc_mutex_lock(tsdn, &prof_gdump_mtx); prof_gdump_old = prof_gdump_val; prof_gdump_val = gdump; malloc_mutex_unlock(tsdn, &prof_gdump_mtx); return prof_gdump_old; } void prof_boot0(void) { cassert(config_prof); memcpy(opt_prof_prefix, PROF_PREFIX_DEFAULT, sizeof(PROF_PREFIX_DEFAULT)); } void prof_boot1(void) { cassert(config_prof); /* * opt_prof must be in its final state before any arenas are * initialized, so this function must be executed early. */ if (opt_prof_leak && !opt_prof) { /* * Enable opt_prof, but in such a way that profiles are never * automatically dumped. */ opt_prof = true; opt_prof_gdump = false; } else if (opt_prof) { if (opt_lg_prof_interval >= 0) { prof_interval = (((uint64_t)1U) << opt_lg_prof_interval); } } } bool prof_boot2(tsd_t *tsd) { cassert(config_prof); if (opt_prof) { unsigned i; lg_prof_sample = opt_lg_prof_sample; prof_active = opt_prof_active; if (malloc_mutex_init(&prof_active_mtx, "prof_active", WITNESS_RANK_PROF_ACTIVE, malloc_mutex_rank_exclusive)) { return true; } prof_gdump_val = opt_prof_gdump; if (malloc_mutex_init(&prof_gdump_mtx, "prof_gdump", WITNESS_RANK_PROF_GDUMP, malloc_mutex_rank_exclusive)) { return true; } prof_thread_active_init = opt_prof_thread_active_init; if (malloc_mutex_init(&prof_thread_active_init_mtx, "prof_thread_active_init", WITNESS_RANK_PROF_THREAD_ACTIVE_INIT, malloc_mutex_rank_exclusive)) { return true; } if (ckh_new(tsd, &bt2gctx, PROF_CKH_MINITEMS, prof_bt_hash, prof_bt_keycomp)) { return true; } if (malloc_mutex_init(&bt2gctx_mtx, "prof_bt2gctx", WITNESS_RANK_PROF_BT2GCTX, malloc_mutex_rank_exclusive)) { return true; } tdata_tree_new(&tdatas); if (malloc_mutex_init(&tdatas_mtx, "prof_tdatas", WITNESS_RANK_PROF_TDATAS, malloc_mutex_rank_exclusive)) { return true; } next_thr_uid = 0; if (malloc_mutex_init(&next_thr_uid_mtx, "prof_next_thr_uid", WITNESS_RANK_PROF_NEXT_THR_UID, malloc_mutex_rank_exclusive)) { return true; } if (malloc_mutex_init(&prof_dump_seq_mtx, "prof_dump_seq", WITNESS_RANK_PROF_DUMP_SEQ, malloc_mutex_rank_exclusive)) { return true; } if (malloc_mutex_init(&prof_dump_mtx, "prof_dump", WITNESS_RANK_PROF_DUMP, malloc_mutex_rank_exclusive)) { return true; } if (opt_prof_final && opt_prof_prefix[0] != '\0' && atexit(prof_fdump) != 0) { malloc_write(": Error in atexit()\n"); if (opt_abort) { abort(); } } + if (opt_prof_log) { + prof_log_start(tsd_tsdn(tsd), NULL); + } + + if (atexit(prof_log_stop_final) != 0) { + malloc_write(": Error in atexit() " + "for logging\n"); + if (opt_abort) { + abort(); + } + } + + if (malloc_mutex_init(&log_mtx, "prof_log", + WITNESS_RANK_PROF_LOG, malloc_mutex_rank_exclusive)) { + return true; + } + + if (ckh_new(tsd, &log_bt_node_set, PROF_CKH_MINITEMS, + prof_bt_node_hash, prof_bt_node_keycomp)) { + return true; + } + + if (ckh_new(tsd, &log_thr_node_set, PROF_CKH_MINITEMS, + prof_thr_node_hash, prof_thr_node_keycomp)) { + return true; + } + + log_tables_initialized = true; + gctx_locks = (malloc_mutex_t *)base_alloc(tsd_tsdn(tsd), b0get(), PROF_NCTX_LOCKS * sizeof(malloc_mutex_t), CACHELINE); if (gctx_locks == NULL) { return true; } for (i = 0; i < PROF_NCTX_LOCKS; i++) { if (malloc_mutex_init(&gctx_locks[i], "prof_gctx", WITNESS_RANK_PROF_GCTX, malloc_mutex_rank_exclusive)) { return true; } } tdata_locks = (malloc_mutex_t *)base_alloc(tsd_tsdn(tsd), b0get(), PROF_NTDATA_LOCKS * sizeof(malloc_mutex_t), CACHELINE); if (tdata_locks == NULL) { return true; } for (i = 0; i < PROF_NTDATA_LOCKS; i++) { if (malloc_mutex_init(&tdata_locks[i], "prof_tdata", WITNESS_RANK_PROF_TDATA, malloc_mutex_rank_exclusive)) { return true; } } - } - #ifdef JEMALLOC_PROF_LIBGCC - /* - * Cause the backtracing machinery to allocate its internal state - * before enabling profiling. - */ - _Unwind_Backtrace(prof_unwind_init_callback, NULL); + /* + * Cause the backtracing machinery to allocate its internal + * state before enabling profiling. + */ + _Unwind_Backtrace(prof_unwind_init_callback, NULL); #endif - + } prof_booted = true; return false; } void prof_prefork0(tsdn_t *tsdn) { if (config_prof && opt_prof) { unsigned i; malloc_mutex_prefork(tsdn, &prof_dump_mtx); malloc_mutex_prefork(tsdn, &bt2gctx_mtx); malloc_mutex_prefork(tsdn, &tdatas_mtx); for (i = 0; i < PROF_NTDATA_LOCKS; i++) { malloc_mutex_prefork(tsdn, &tdata_locks[i]); } for (i = 0; i < PROF_NCTX_LOCKS; i++) { malloc_mutex_prefork(tsdn, &gctx_locks[i]); } } } void prof_prefork1(tsdn_t *tsdn) { if (config_prof && opt_prof) { malloc_mutex_prefork(tsdn, &prof_active_mtx); malloc_mutex_prefork(tsdn, &prof_dump_seq_mtx); malloc_mutex_prefork(tsdn, &prof_gdump_mtx); malloc_mutex_prefork(tsdn, &next_thr_uid_mtx); malloc_mutex_prefork(tsdn, &prof_thread_active_init_mtx); } } void prof_postfork_parent(tsdn_t *tsdn) { if (config_prof && opt_prof) { unsigned i; malloc_mutex_postfork_parent(tsdn, &prof_thread_active_init_mtx); malloc_mutex_postfork_parent(tsdn, &next_thr_uid_mtx); malloc_mutex_postfork_parent(tsdn, &prof_gdump_mtx); malloc_mutex_postfork_parent(tsdn, &prof_dump_seq_mtx); malloc_mutex_postfork_parent(tsdn, &prof_active_mtx); for (i = 0; i < PROF_NCTX_LOCKS; i++) { malloc_mutex_postfork_parent(tsdn, &gctx_locks[i]); } for (i = 0; i < PROF_NTDATA_LOCKS; i++) { malloc_mutex_postfork_parent(tsdn, &tdata_locks[i]); } malloc_mutex_postfork_parent(tsdn, &tdatas_mtx); malloc_mutex_postfork_parent(tsdn, &bt2gctx_mtx); malloc_mutex_postfork_parent(tsdn, &prof_dump_mtx); } } void prof_postfork_child(tsdn_t *tsdn) { if (config_prof && opt_prof) { unsigned i; malloc_mutex_postfork_child(tsdn, &prof_thread_active_init_mtx); malloc_mutex_postfork_child(tsdn, &next_thr_uid_mtx); malloc_mutex_postfork_child(tsdn, &prof_gdump_mtx); malloc_mutex_postfork_child(tsdn, &prof_dump_seq_mtx); malloc_mutex_postfork_child(tsdn, &prof_active_mtx); for (i = 0; i < PROF_NCTX_LOCKS; i++) { malloc_mutex_postfork_child(tsdn, &gctx_locks[i]); } for (i = 0; i < PROF_NTDATA_LOCKS; i++) { malloc_mutex_postfork_child(tsdn, &tdata_locks[i]); } malloc_mutex_postfork_child(tsdn, &tdatas_mtx); malloc_mutex_postfork_child(tsdn, &bt2gctx_mtx); malloc_mutex_postfork_child(tsdn, &prof_dump_mtx); } } /******************************************************************************/ Index: head/contrib/jemalloc/src/rtree.c =================================================================== --- head/contrib/jemalloc/src/rtree.c (revision 360232) +++ head/contrib/jemalloc/src/rtree.c (revision 360233) @@ -1,320 +1,320 @@ #define JEMALLOC_RTREE_C_ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/jemalloc_internal_includes.h" #include "jemalloc/internal/assert.h" #include "jemalloc/internal/mutex.h" /* * Only the most significant bits of keys passed to rtree_{read,write}() are * used. */ bool rtree_new(rtree_t *rtree, bool zeroed) { #ifdef JEMALLOC_JET if (!zeroed) { memset(rtree, 0, sizeof(rtree_t)); /* Clear root. */ } #else assert(zeroed); #endif if (malloc_mutex_init(&rtree->init_lock, "rtree", WITNESS_RANK_RTREE, malloc_mutex_rank_exclusive)) { return true; } return false; } static rtree_node_elm_t * rtree_node_alloc_impl(tsdn_t *tsdn, rtree_t *rtree, size_t nelms) { return (rtree_node_elm_t *)base_alloc(tsdn, b0get(), nelms * sizeof(rtree_node_elm_t), CACHELINE); } rtree_node_alloc_t *JET_MUTABLE rtree_node_alloc = rtree_node_alloc_impl; static void rtree_node_dalloc_impl(tsdn_t *tsdn, rtree_t *rtree, rtree_node_elm_t *node) { /* Nodes are never deleted during normal operation. */ not_reached(); } -UNUSED rtree_node_dalloc_t *JET_MUTABLE rtree_node_dalloc = +rtree_node_dalloc_t *JET_MUTABLE rtree_node_dalloc = rtree_node_dalloc_impl; static rtree_leaf_elm_t * rtree_leaf_alloc_impl(tsdn_t *tsdn, rtree_t *rtree, size_t nelms) { return (rtree_leaf_elm_t *)base_alloc(tsdn, b0get(), nelms * sizeof(rtree_leaf_elm_t), CACHELINE); } rtree_leaf_alloc_t *JET_MUTABLE rtree_leaf_alloc = rtree_leaf_alloc_impl; static void rtree_leaf_dalloc_impl(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *leaf) { /* Leaves are never deleted during normal operation. */ not_reached(); } -UNUSED rtree_leaf_dalloc_t *JET_MUTABLE rtree_leaf_dalloc = +rtree_leaf_dalloc_t *JET_MUTABLE rtree_leaf_dalloc = rtree_leaf_dalloc_impl; #ifdef JEMALLOC_JET # if RTREE_HEIGHT > 1 static void rtree_delete_subtree(tsdn_t *tsdn, rtree_t *rtree, rtree_node_elm_t *subtree, unsigned level) { size_t nchildren = ZU(1) << rtree_levels[level].bits; if (level + 2 < RTREE_HEIGHT) { for (size_t i = 0; i < nchildren; i++) { rtree_node_elm_t *node = (rtree_node_elm_t *)atomic_load_p(&subtree[i].child, ATOMIC_RELAXED); if (node != NULL) { rtree_delete_subtree(tsdn, rtree, node, level + 1); } } } else { for (size_t i = 0; i < nchildren; i++) { rtree_leaf_elm_t *leaf = (rtree_leaf_elm_t *)atomic_load_p(&subtree[i].child, ATOMIC_RELAXED); if (leaf != NULL) { rtree_leaf_dalloc(tsdn, rtree, leaf); } } } if (subtree != rtree->root) { rtree_node_dalloc(tsdn, rtree, subtree); } } # endif void rtree_delete(tsdn_t *tsdn, rtree_t *rtree) { # if RTREE_HEIGHT > 1 rtree_delete_subtree(tsdn, rtree, rtree->root, 0); # endif } #endif static rtree_node_elm_t * rtree_node_init(tsdn_t *tsdn, rtree_t *rtree, unsigned level, atomic_p_t *elmp) { malloc_mutex_lock(tsdn, &rtree->init_lock); /* * If *elmp is non-null, then it was initialized with the init lock * held, so we can get by with 'relaxed' here. */ rtree_node_elm_t *node = atomic_load_p(elmp, ATOMIC_RELAXED); if (node == NULL) { node = rtree_node_alloc(tsdn, rtree, ZU(1) << rtree_levels[level].bits); if (node == NULL) { malloc_mutex_unlock(tsdn, &rtree->init_lock); return NULL; } /* * Even though we hold the lock, a later reader might not; we * need release semantics. */ atomic_store_p(elmp, node, ATOMIC_RELEASE); } malloc_mutex_unlock(tsdn, &rtree->init_lock); return node; } static rtree_leaf_elm_t * rtree_leaf_init(tsdn_t *tsdn, rtree_t *rtree, atomic_p_t *elmp) { malloc_mutex_lock(tsdn, &rtree->init_lock); /* * If *elmp is non-null, then it was initialized with the init lock * held, so we can get by with 'relaxed' here. */ rtree_leaf_elm_t *leaf = atomic_load_p(elmp, ATOMIC_RELAXED); if (leaf == NULL) { leaf = rtree_leaf_alloc(tsdn, rtree, ZU(1) << rtree_levels[RTREE_HEIGHT-1].bits); if (leaf == NULL) { malloc_mutex_unlock(tsdn, &rtree->init_lock); return NULL; } /* * Even though we hold the lock, a later reader might not; we * need release semantics. */ atomic_store_p(elmp, leaf, ATOMIC_RELEASE); } malloc_mutex_unlock(tsdn, &rtree->init_lock); return leaf; } static bool rtree_node_valid(rtree_node_elm_t *node) { return ((uintptr_t)node != (uintptr_t)0); } static bool rtree_leaf_valid(rtree_leaf_elm_t *leaf) { return ((uintptr_t)leaf != (uintptr_t)0); } static rtree_node_elm_t * rtree_child_node_tryread(rtree_node_elm_t *elm, bool dependent) { rtree_node_elm_t *node; if (dependent) { node = (rtree_node_elm_t *)atomic_load_p(&elm->child, ATOMIC_RELAXED); } else { node = (rtree_node_elm_t *)atomic_load_p(&elm->child, ATOMIC_ACQUIRE); } assert(!dependent || node != NULL); return node; } static rtree_node_elm_t * rtree_child_node_read(tsdn_t *tsdn, rtree_t *rtree, rtree_node_elm_t *elm, unsigned level, bool dependent) { rtree_node_elm_t *node; node = rtree_child_node_tryread(elm, dependent); if (!dependent && unlikely(!rtree_node_valid(node))) { node = rtree_node_init(tsdn, rtree, level + 1, &elm->child); } assert(!dependent || node != NULL); return node; } static rtree_leaf_elm_t * rtree_child_leaf_tryread(rtree_node_elm_t *elm, bool dependent) { rtree_leaf_elm_t *leaf; if (dependent) { leaf = (rtree_leaf_elm_t *)atomic_load_p(&elm->child, ATOMIC_RELAXED); } else { leaf = (rtree_leaf_elm_t *)atomic_load_p(&elm->child, ATOMIC_ACQUIRE); } assert(!dependent || leaf != NULL); return leaf; } static rtree_leaf_elm_t * rtree_child_leaf_read(tsdn_t *tsdn, rtree_t *rtree, rtree_node_elm_t *elm, unsigned level, bool dependent) { rtree_leaf_elm_t *leaf; leaf = rtree_child_leaf_tryread(elm, dependent); if (!dependent && unlikely(!rtree_leaf_valid(leaf))) { leaf = rtree_leaf_init(tsdn, rtree, &elm->child); } assert(!dependent || leaf != NULL); return leaf; } rtree_leaf_elm_t * rtree_leaf_elm_lookup_hard(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx, uintptr_t key, bool dependent, bool init_missing) { rtree_node_elm_t *node; rtree_leaf_elm_t *leaf; #if RTREE_HEIGHT > 1 node = rtree->root; #else leaf = rtree->root; #endif if (config_debug) { uintptr_t leafkey = rtree_leafkey(key); for (unsigned i = 0; i < RTREE_CTX_NCACHE; i++) { assert(rtree_ctx->cache[i].leafkey != leafkey); } for (unsigned i = 0; i < RTREE_CTX_NCACHE_L2; i++) { assert(rtree_ctx->l2_cache[i].leafkey != leafkey); } } #define RTREE_GET_CHILD(level) { \ assert(level < RTREE_HEIGHT-1); \ if (level != 0 && !dependent && \ unlikely(!rtree_node_valid(node))) { \ return NULL; \ } \ uintptr_t subkey = rtree_subkey(key, level); \ if (level + 2 < RTREE_HEIGHT) { \ node = init_missing ? \ rtree_child_node_read(tsdn, rtree, \ &node[subkey], level, dependent) : \ rtree_child_node_tryread(&node[subkey], \ dependent); \ } else { \ leaf = init_missing ? \ rtree_child_leaf_read(tsdn, rtree, \ &node[subkey], level, dependent) : \ rtree_child_leaf_tryread(&node[subkey], \ dependent); \ } \ } /* * Cache replacement upon hard lookup (i.e. L1 & L2 rtree cache miss): * (1) evict last entry in L2 cache; (2) move the collision slot from L1 * cache down to L2; and 3) fill L1. */ #define RTREE_GET_LEAF(level) { \ assert(level == RTREE_HEIGHT-1); \ if (!dependent && unlikely(!rtree_leaf_valid(leaf))) { \ return NULL; \ } \ if (RTREE_CTX_NCACHE_L2 > 1) { \ memmove(&rtree_ctx->l2_cache[1], \ &rtree_ctx->l2_cache[0], \ sizeof(rtree_ctx_cache_elm_t) * \ (RTREE_CTX_NCACHE_L2 - 1)); \ } \ size_t slot = rtree_cache_direct_map(key); \ rtree_ctx->l2_cache[0].leafkey = \ rtree_ctx->cache[slot].leafkey; \ rtree_ctx->l2_cache[0].leaf = \ rtree_ctx->cache[slot].leaf; \ uintptr_t leafkey = rtree_leafkey(key); \ rtree_ctx->cache[slot].leafkey = leafkey; \ rtree_ctx->cache[slot].leaf = leaf; \ uintptr_t subkey = rtree_subkey(key, level); \ return &leaf[subkey]; \ } if (RTREE_HEIGHT > 1) { RTREE_GET_CHILD(0) } if (RTREE_HEIGHT > 2) { RTREE_GET_CHILD(1) } if (RTREE_HEIGHT > 3) { for (unsigned i = 2; i < RTREE_HEIGHT-1; i++) { RTREE_GET_CHILD(i) } } RTREE_GET_LEAF(RTREE_HEIGHT-1) #undef RTREE_GET_CHILD #undef RTREE_GET_LEAF not_reached(); } void rtree_ctx_data_init(rtree_ctx_t *ctx) { for (unsigned i = 0; i < RTREE_CTX_NCACHE; i++) { rtree_ctx_cache_elm_t *cache = &ctx->cache[i]; cache->leafkey = RTREE_LEAFKEY_INVALID; cache->leaf = NULL; } for (unsigned i = 0; i < RTREE_CTX_NCACHE_L2; i++) { rtree_ctx_cache_elm_t *cache = &ctx->l2_cache[i]; cache->leafkey = RTREE_LEAFKEY_INVALID; cache->leaf = NULL; } } Index: head/contrib/jemalloc/src/safety_check.c =================================================================== --- head/contrib/jemalloc/src/safety_check.c (nonexistent) +++ head/contrib/jemalloc/src/safety_check.c (revision 360233) @@ -0,0 +1,24 @@ +#include "jemalloc/internal/jemalloc_preamble.h" +#include "jemalloc/internal/jemalloc_internal_includes.h" + +static void (*safety_check_abort)(const char *message); + +void safety_check_set_abort(void (*abort_fn)(const char *)) { + safety_check_abort = abort_fn; +} + +void safety_check_fail(const char *format, ...) { + char buf[MALLOC_PRINTF_BUFSIZE]; + + va_list ap; + va_start(ap, format); + malloc_vsnprintf(buf, MALLOC_PRINTF_BUFSIZE, format, ap); + va_end(ap); + + if (safety_check_abort == NULL) { + malloc_write(buf); + abort(); + } else { + safety_check_abort(buf); + } +} Property changes on: head/contrib/jemalloc/src/safety_check.c ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/jemalloc/src/sc.c =================================================================== --- head/contrib/jemalloc/src/sc.c (nonexistent) +++ head/contrib/jemalloc/src/sc.c (revision 360233) @@ -0,0 +1,313 @@ +#include "jemalloc/internal/jemalloc_preamble.h" + +#include "jemalloc/internal/assert.h" +#include "jemalloc/internal/bit_util.h" +#include "jemalloc/internal/bitmap.h" +#include "jemalloc/internal/pages.h" +#include "jemalloc/internal/sc.h" + +/* + * This module computes the size classes used to satisfy allocations. The logic + * here was ported more or less line-by-line from a shell script, and because of + * that is not the most idiomatic C. Eventually we should fix this, but for now + * at least the damage is compartmentalized to this file. + */ + +sc_data_t sc_data_global; + +static size_t +reg_size_compute(int lg_base, int lg_delta, int ndelta) { + return (ZU(1) << lg_base) + (ZU(ndelta) << lg_delta); +} + +/* Returns the number of pages in the slab. */ +static int +slab_size(int lg_page, int lg_base, int lg_delta, int ndelta) { + size_t page = (ZU(1) << lg_page); + size_t reg_size = reg_size_compute(lg_base, lg_delta, ndelta); + + size_t try_slab_size = page; + size_t try_nregs = try_slab_size / reg_size; + size_t perfect_slab_size = 0; + bool perfect = false; + /* + * This loop continues until we find the least common multiple of the + * page size and size class size. Size classes are all of the form + * base + ndelta * delta == (ndelta + base/ndelta) * delta, which is + * (ndelta + ngroup) * delta. The way we choose slabbing strategies + * means that delta is at most the page size and ndelta < ngroup. So + * the loop executes for at most 2 * ngroup - 1 iterations, which is + * also the bound on the number of pages in a slab chosen by default. + * With the current default settings, this is at most 7. + */ + while (!perfect) { + perfect_slab_size = try_slab_size; + size_t perfect_nregs = try_nregs; + try_slab_size += page; + try_nregs = try_slab_size / reg_size; + if (perfect_slab_size == perfect_nregs * reg_size) { + perfect = true; + } + } + return (int)(perfect_slab_size / page); +} + +static void +size_class( + /* Output. */ + sc_t *sc, + /* Configuration decisions. */ + int lg_max_lookup, int lg_page, int lg_ngroup, + /* Inputs specific to the size class. */ + int index, int lg_base, int lg_delta, int ndelta) { + sc->index = index; + sc->lg_base = lg_base; + sc->lg_delta = lg_delta; + sc->ndelta = ndelta; + sc->psz = (reg_size_compute(lg_base, lg_delta, ndelta) + % (ZU(1) << lg_page) == 0); + size_t size = (ZU(1) << lg_base) + (ZU(ndelta) << lg_delta); + if (index == 0) { + assert(!sc->psz); + } + if (size < (ZU(1) << (lg_page + lg_ngroup))) { + sc->bin = true; + sc->pgs = slab_size(lg_page, lg_base, lg_delta, ndelta); + } else { + sc->bin = false; + sc->pgs = 0; + } + if (size <= (ZU(1) << lg_max_lookup)) { + sc->lg_delta_lookup = lg_delta; + } else { + sc->lg_delta_lookup = 0; + } +} + +static void +size_classes( + /* Output. */ + sc_data_t *sc_data, + /* Determined by the system. */ + size_t lg_ptr_size, int lg_quantum, + /* Configuration decisions. */ + int lg_tiny_min, int lg_max_lookup, int lg_page, int lg_ngroup) { + int ptr_bits = (1 << lg_ptr_size) * 8; + int ngroup = (1 << lg_ngroup); + int ntiny = 0; + int nlbins = 0; + int lg_tiny_maxclass = (unsigned)-1; + int nbins = 0; + int npsizes = 0; + + int index = 0; + + int ndelta = 0; + int lg_base = lg_tiny_min; + int lg_delta = lg_base; + + /* Outputs that we update as we go. */ + size_t lookup_maxclass = 0; + size_t small_maxclass = 0; + int lg_large_minclass = 0; + size_t large_maxclass = 0; + + /* Tiny size classes. */ + while (lg_base < lg_quantum) { + sc_t *sc = &sc_data->sc[index]; + size_class(sc, lg_max_lookup, lg_page, lg_ngroup, index, + lg_base, lg_delta, ndelta); + if (sc->lg_delta_lookup != 0) { + nlbins = index + 1; + } + if (sc->psz) { + npsizes++; + } + if (sc->bin) { + nbins++; + } + ntiny++; + /* Final written value is correct. */ + lg_tiny_maxclass = lg_base; + index++; + lg_delta = lg_base; + lg_base++; + } + + /* First non-tiny (pseudo) group. */ + if (ntiny != 0) { + sc_t *sc = &sc_data->sc[index]; + /* + * See the note in sc.h; the first non-tiny size class has an + * unusual encoding. + */ + lg_base--; + ndelta = 1; + size_class(sc, lg_max_lookup, lg_page, lg_ngroup, index, + lg_base, lg_delta, ndelta); + index++; + lg_base++; + lg_delta++; + if (sc->psz) { + npsizes++; + } + if (sc->bin) { + nbins++; + } + } + while (ndelta < ngroup) { + sc_t *sc = &sc_data->sc[index]; + size_class(sc, lg_max_lookup, lg_page, lg_ngroup, index, + lg_base, lg_delta, ndelta); + index++; + ndelta++; + if (sc->psz) { + npsizes++; + } + if (sc->bin) { + nbins++; + } + } + + /* All remaining groups. */ + lg_base = lg_base + lg_ngroup; + while (lg_base < ptr_bits - 1) { + ndelta = 1; + int ndelta_limit; + if (lg_base == ptr_bits - 2) { + ndelta_limit = ngroup - 1; + } else { + ndelta_limit = ngroup; + } + while (ndelta <= ndelta_limit) { + sc_t *sc = &sc_data->sc[index]; + size_class(sc, lg_max_lookup, lg_page, lg_ngroup, index, + lg_base, lg_delta, ndelta); + if (sc->lg_delta_lookup != 0) { + nlbins = index + 1; + /* Final written value is correct. */ + lookup_maxclass = (ZU(1) << lg_base) + + (ZU(ndelta) << lg_delta); + } + if (sc->psz) { + npsizes++; + } + if (sc->bin) { + nbins++; + /* Final written value is correct. */ + small_maxclass = (ZU(1) << lg_base) + + (ZU(ndelta) << lg_delta); + if (lg_ngroup > 0) { + lg_large_minclass = lg_base + 1; + } else { + lg_large_minclass = lg_base + 2; + } + } + large_maxclass = (ZU(1) << lg_base) + + (ZU(ndelta) << lg_delta); + index++; + ndelta++; + } + lg_base++; + lg_delta++; + } + /* Additional outputs. */ + int nsizes = index; + unsigned lg_ceil_nsizes = lg_ceil(nsizes); + + /* Fill in the output data. */ + sc_data->ntiny = ntiny; + sc_data->nlbins = nlbins; + sc_data->nbins = nbins; + sc_data->nsizes = nsizes; + sc_data->lg_ceil_nsizes = lg_ceil_nsizes; + sc_data->npsizes = npsizes; + sc_data->lg_tiny_maxclass = lg_tiny_maxclass; + sc_data->lookup_maxclass = lookup_maxclass; + sc_data->small_maxclass = small_maxclass; + sc_data->lg_large_minclass = lg_large_minclass; + sc_data->large_minclass = (ZU(1) << lg_large_minclass); + sc_data->large_maxclass = large_maxclass; + + /* + * We compute these values in two ways: + * - Incrementally, as above. + * - In macros, in sc.h. + * The computation is easier when done incrementally, but putting it in + * a constant makes it available to the fast paths without having to + * touch the extra global cacheline. We assert, however, that the two + * computations are equivalent. + */ + assert(sc_data->npsizes == SC_NPSIZES); + assert(sc_data->lg_tiny_maxclass == SC_LG_TINY_MAXCLASS); + assert(sc_data->small_maxclass == SC_SMALL_MAXCLASS); + assert(sc_data->large_minclass == SC_LARGE_MINCLASS); + assert(sc_data->lg_large_minclass == SC_LG_LARGE_MINCLASS); + assert(sc_data->large_maxclass == SC_LARGE_MAXCLASS); + + /* + * In the allocation fastpath, we want to assume that we can + * unconditionally subtract the requested allocation size from + * a ssize_t, and detect passing through 0 correctly. This + * results in optimal generated code. For this to work, the + * maximum allocation size must be less than SSIZE_MAX. + */ + assert(SC_LARGE_MAXCLASS < SSIZE_MAX); +} + +void +sc_data_init(sc_data_t *sc_data) { + assert(!sc_data->initialized); + + int lg_max_lookup = 12; + + size_classes(sc_data, LG_SIZEOF_PTR, LG_QUANTUM, SC_LG_TINY_MIN, + lg_max_lookup, LG_PAGE, 2); + + sc_data->initialized = true; +} + +static void +sc_data_update_sc_slab_size(sc_t *sc, size_t reg_size, size_t pgs_guess) { + size_t min_pgs = reg_size / PAGE; + if (reg_size % PAGE != 0) { + min_pgs++; + } + /* + * BITMAP_MAXBITS is actually determined by putting the smallest + * possible size-class on one page, so this can never be 0. + */ + size_t max_pgs = BITMAP_MAXBITS * reg_size / PAGE; + + assert(min_pgs <= max_pgs); + assert(min_pgs > 0); + assert(max_pgs >= 1); + if (pgs_guess < min_pgs) { + sc->pgs = (int)min_pgs; + } else if (pgs_guess > max_pgs) { + sc->pgs = (int)max_pgs; + } else { + sc->pgs = (int)pgs_guess; + } +} + +void +sc_data_update_slab_size(sc_data_t *data, size_t begin, size_t end, int pgs) { + assert(data->initialized); + for (int i = 0; i < data->nsizes; i++) { + sc_t *sc = &data->sc[i]; + if (!sc->bin) { + break; + } + size_t reg_size = reg_size_compute(sc->lg_base, sc->lg_delta, + sc->ndelta); + if (begin <= reg_size && reg_size <= end) { + sc_data_update_sc_slab_size(sc, reg_size, pgs); + } + } +} + +void +sc_boot(sc_data_t *data) { + sc_data_init(data); +} Property changes on: head/contrib/jemalloc/src/sc.c ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/jemalloc/src/stats.c =================================================================== --- head/contrib/jemalloc/src/stats.c (revision 360232) +++ head/contrib/jemalloc/src/stats.c (revision 360233) @@ -1,1286 +1,1457 @@ #define JEMALLOC_STATS_C_ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/jemalloc_internal_includes.h" #include "jemalloc/internal/assert.h" #include "jemalloc/internal/ctl.h" #include "jemalloc/internal/emitter.h" #include "jemalloc/internal/mutex.h" #include "jemalloc/internal/mutex_prof.h" const char *global_mutex_names[mutex_prof_num_global_mutexes] = { #define OP(mtx) #mtx, MUTEX_PROF_GLOBAL_MUTEXES #undef OP }; const char *arena_mutex_names[mutex_prof_num_arena_mutexes] = { #define OP(mtx) #mtx, MUTEX_PROF_ARENA_MUTEXES #undef OP }; #define CTL_GET(n, v, t) do { \ size_t sz = sizeof(t); \ xmallctl(n, (void *)v, &sz, NULL, 0); \ } while (0) #define CTL_M2_GET(n, i, v, t) do { \ size_t mib[CTL_MAX_DEPTH]; \ size_t miblen = sizeof(mib) / sizeof(size_t); \ size_t sz = sizeof(t); \ xmallctlnametomib(n, mib, &miblen); \ mib[2] = (i); \ xmallctlbymib(mib, miblen, (void *)v, &sz, NULL, 0); \ } while (0) #define CTL_M2_M4_GET(n, i, j, v, t) do { \ size_t mib[CTL_MAX_DEPTH]; \ size_t miblen = sizeof(mib) / sizeof(size_t); \ size_t sz = sizeof(t); \ xmallctlnametomib(n, mib, &miblen); \ mib[2] = (i); \ mib[4] = (j); \ xmallctlbymib(mib, miblen, (void *)v, &sz, NULL, 0); \ } while (0) /******************************************************************************/ /* Data. */ bool opt_stats_print = false; char opt_stats_print_opts[stats_print_tot_num_options+1] = ""; /******************************************************************************/ +static uint64_t +rate_per_second(uint64_t value, uint64_t uptime_ns) { + uint64_t billion = 1000000000; + if (uptime_ns == 0 || value == 0) { + return 0; + } + if (uptime_ns < billion) { + return value; + } else { + uint64_t uptime_s = uptime_ns / billion; + return value / uptime_s; + } +} + /* Calculate x.yyy and output a string (takes a fixed sized char array). */ static bool get_rate_str(uint64_t dividend, uint64_t divisor, char str[6]) { if (divisor == 0 || dividend > divisor) { /* The rate is not supposed to be greater than 1. */ return true; } if (dividend > 0) { assert(UINT64_MAX / dividend >= 1000); } unsigned n = (unsigned)((dividend * 1000) / divisor); if (n < 10) { malloc_snprintf(str, 6, "0.00%u", n); } else if (n < 100) { malloc_snprintf(str, 6, "0.0%u", n); } else if (n < 1000) { malloc_snprintf(str, 6, "0.%u", n); } else { malloc_snprintf(str, 6, "1"); } return false; } #define MUTEX_CTL_STR_MAX_LENGTH 128 static void gen_mutex_ctl_str(char *str, size_t buf_len, const char *prefix, const char *mutex, const char *counter) { malloc_snprintf(str, buf_len, "stats.%s.%s.%s", prefix, mutex, counter); } static void mutex_stats_init_cols(emitter_row_t *row, const char *table_name, emitter_col_t *name, emitter_col_t col_uint64_t[mutex_prof_num_uint64_t_counters], emitter_col_t col_uint32_t[mutex_prof_num_uint32_t_counters]) { mutex_prof_uint64_t_counter_ind_t k_uint64_t = 0; mutex_prof_uint32_t_counter_ind_t k_uint32_t = 0; emitter_col_t *col; if (name != NULL) { emitter_col_init(name, row); name->justify = emitter_justify_left; name->width = 21; name->type = emitter_type_title; name->str_val = table_name; } #define WIDTH_uint32_t 12 #define WIDTH_uint64_t 16 -#define OP(counter, counter_type, human) \ +#define OP(counter, counter_type, human, derived, base_counter) \ col = &col_##counter_type[k_##counter_type]; \ ++k_##counter_type; \ emitter_col_init(col, row); \ col->justify = emitter_justify_right; \ - col->width = WIDTH_##counter_type; \ + col->width = derived ? 8 : WIDTH_##counter_type; \ col->type = emitter_type_title; \ col->str_val = human; MUTEX_PROF_COUNTERS #undef OP #undef WIDTH_uint32_t #undef WIDTH_uint64_t + col_uint64_t[mutex_counter_total_wait_time_ps].width = 10; } static void mutex_stats_read_global(const char *name, emitter_col_t *col_name, emitter_col_t col_uint64_t[mutex_prof_num_uint64_t_counters], - emitter_col_t col_uint32_t[mutex_prof_num_uint32_t_counters]) { + emitter_col_t col_uint32_t[mutex_prof_num_uint32_t_counters], + uint64_t uptime) { char cmd[MUTEX_CTL_STR_MAX_LENGTH]; col_name->str_val = name; emitter_col_t *dst; #define EMITTER_TYPE_uint32_t emitter_type_uint32 #define EMITTER_TYPE_uint64_t emitter_type_uint64 -#define OP(counter, counter_type, human) \ +#define OP(counter, counter_type, human, derived, base_counter) \ dst = &col_##counter_type[mutex_counter_##counter]; \ dst->type = EMITTER_TYPE_##counter_type; \ - gen_mutex_ctl_str(cmd, MUTEX_CTL_STR_MAX_LENGTH, \ - "mutexes", name, #counter); \ - CTL_GET(cmd, (counter_type *)&dst->bool_val, counter_type); + if (!derived) { \ + gen_mutex_ctl_str(cmd, MUTEX_CTL_STR_MAX_LENGTH, \ + "mutexes", name, #counter); \ + CTL_GET(cmd, (counter_type *)&dst->bool_val, counter_type); \ + } else { \ + emitter_col_t *base = &col_##counter_type[mutex_counter_##base_counter]; \ + dst->counter_type##_val = rate_per_second(base->counter_type##_val, uptime); \ + } MUTEX_PROF_COUNTERS #undef OP #undef EMITTER_TYPE_uint32_t #undef EMITTER_TYPE_uint64_t } static void mutex_stats_read_arena(unsigned arena_ind, mutex_prof_arena_ind_t mutex_ind, const char *name, emitter_col_t *col_name, emitter_col_t col_uint64_t[mutex_prof_num_uint64_t_counters], - emitter_col_t col_uint32_t[mutex_prof_num_uint32_t_counters]) { + emitter_col_t col_uint32_t[mutex_prof_num_uint32_t_counters], + uint64_t uptime) { char cmd[MUTEX_CTL_STR_MAX_LENGTH]; col_name->str_val = name; emitter_col_t *dst; #define EMITTER_TYPE_uint32_t emitter_type_uint32 #define EMITTER_TYPE_uint64_t emitter_type_uint64 -#define OP(counter, counter_type, human) \ +#define OP(counter, counter_type, human, derived, base_counter) \ dst = &col_##counter_type[mutex_counter_##counter]; \ dst->type = EMITTER_TYPE_##counter_type; \ - gen_mutex_ctl_str(cmd, MUTEX_CTL_STR_MAX_LENGTH, \ - "arenas.0.mutexes", arena_mutex_names[mutex_ind], #counter);\ - CTL_M2_GET(cmd, arena_ind, \ - (counter_type *)&dst->bool_val, counter_type); + if (!derived) { \ + gen_mutex_ctl_str(cmd, MUTEX_CTL_STR_MAX_LENGTH, \ + "arenas.0.mutexes", arena_mutex_names[mutex_ind], #counter);\ + CTL_M2_GET(cmd, arena_ind, (counter_type *)&dst->bool_val, counter_type); \ + } else { \ + emitter_col_t *base = &col_##counter_type[mutex_counter_##base_counter]; \ + dst->counter_type##_val = rate_per_second(base->counter_type##_val, uptime); \ + } MUTEX_PROF_COUNTERS #undef OP #undef EMITTER_TYPE_uint32_t #undef EMITTER_TYPE_uint64_t } static void mutex_stats_read_arena_bin(unsigned arena_ind, unsigned bin_ind, emitter_col_t col_uint64_t[mutex_prof_num_uint64_t_counters], - emitter_col_t col_uint32_t[mutex_prof_num_uint32_t_counters]) { + emitter_col_t col_uint32_t[mutex_prof_num_uint32_t_counters], + uint64_t uptime) { char cmd[MUTEX_CTL_STR_MAX_LENGTH]; emitter_col_t *dst; #define EMITTER_TYPE_uint32_t emitter_type_uint32 #define EMITTER_TYPE_uint64_t emitter_type_uint64 -#define OP(counter, counter_type, human) \ +#define OP(counter, counter_type, human, derived, base_counter) \ dst = &col_##counter_type[mutex_counter_##counter]; \ dst->type = EMITTER_TYPE_##counter_type; \ - gen_mutex_ctl_str(cmd, MUTEX_CTL_STR_MAX_LENGTH, \ - "arenas.0.bins.0","mutex", #counter); \ - CTL_M2_M4_GET(cmd, arena_ind, bin_ind, \ - (counter_type *)&dst->bool_val, counter_type); + if (!derived) { \ + gen_mutex_ctl_str(cmd, MUTEX_CTL_STR_MAX_LENGTH, \ + "arenas.0.bins.0","mutex", #counter); \ + CTL_M2_M4_GET(cmd, arena_ind, bin_ind, \ + (counter_type *)&dst->bool_val, counter_type); \ + } else { \ + emitter_col_t *base = &col_##counter_type[mutex_counter_##base_counter]; \ + dst->counter_type##_val = rate_per_second(base->counter_type##_val, uptime); \ + } MUTEX_PROF_COUNTERS #undef OP #undef EMITTER_TYPE_uint32_t #undef EMITTER_TYPE_uint64_t } /* "row" can be NULL to avoid emitting in table mode. */ static void mutex_stats_emit(emitter_t *emitter, emitter_row_t *row, emitter_col_t col_uint64_t[mutex_prof_num_uint64_t_counters], emitter_col_t col_uint32_t[mutex_prof_num_uint32_t_counters]) { if (row != NULL) { emitter_table_row(emitter, row); } mutex_prof_uint64_t_counter_ind_t k_uint64_t = 0; mutex_prof_uint32_t_counter_ind_t k_uint32_t = 0; emitter_col_t *col; #define EMITTER_TYPE_uint32_t emitter_type_uint32 #define EMITTER_TYPE_uint64_t emitter_type_uint64 -#define OP(counter, type, human) \ - col = &col_##type[k_##type]; \ - ++k_##type; \ - emitter_json_kv(emitter, #counter, EMITTER_TYPE_##type, \ - (const void *)&col->bool_val); +#define OP(counter, type, human, derived, base_counter) \ + if (!derived) { \ + col = &col_##type[k_##type]; \ + ++k_##type; \ + emitter_json_kv(emitter, #counter, EMITTER_TYPE_##type, \ + (const void *)&col->bool_val); \ + } MUTEX_PROF_COUNTERS; #undef OP #undef EMITTER_TYPE_uint32_t #undef EMITTER_TYPE_uint64_t } +#define COL(row_name, column_name, left_or_right, col_width, etype) \ + emitter_col_t col_##column_name; \ + emitter_col_init(&col_##column_name, &row_name); \ + col_##column_name.justify = emitter_justify_##left_or_right; \ + col_##column_name.width = col_width; \ + col_##column_name.type = emitter_type_##etype; + +#define COL_HDR(row_name, column_name, human, left_or_right, col_width, etype) \ + COL(row_name, column_name, left_or_right, col_width, etype) \ + emitter_col_t header_##column_name; \ + emitter_col_init(&header_##column_name, &header_##row_name); \ + header_##column_name.justify = emitter_justify_##left_or_right; \ + header_##column_name.width = col_width; \ + header_##column_name.type = emitter_type_title; \ + header_##column_name.str_val = human ? human : #column_name; + + static void -stats_arena_bins_print(emitter_t *emitter, bool mutex, unsigned i) { +stats_arena_bins_print(emitter_t *emitter, bool mutex, unsigned i, uint64_t uptime) { size_t page; bool in_gap, in_gap_prev; unsigned nbins, j; CTL_GET("arenas.page", &page, size_t); CTL_GET("arenas.nbins", &nbins, unsigned); emitter_row_t header_row; emitter_row_init(&header_row); emitter_row_t row; emitter_row_init(&row); -#define COL(name, left_or_right, col_width, etype) \ - emitter_col_t col_##name; \ - emitter_col_init(&col_##name, &row); \ - col_##name.justify = emitter_justify_##left_or_right; \ - col_##name.width = col_width; \ - col_##name.type = emitter_type_##etype; \ - emitter_col_t header_col_##name; \ - emitter_col_init(&header_col_##name, &header_row); \ - header_col_##name.justify = emitter_justify_##left_or_right; \ - header_col_##name.width = col_width; \ - header_col_##name.type = emitter_type_title; \ - header_col_##name.str_val = #name; - COL(size, right, 20, size) - COL(ind, right, 4, unsigned) - COL(allocated, right, 13, uint64) - COL(nmalloc, right, 13, uint64) - COL(ndalloc, right, 13, uint64) - COL(nrequests, right, 13, uint64) - COL(curregs, right, 13, size) - COL(curslabs, right, 13, size) - COL(regs, right, 5, unsigned) - COL(pgs, right, 4, size) + COL_HDR(row, size, NULL, right, 20, size) + COL_HDR(row, ind, NULL, right, 4, unsigned) + COL_HDR(row, allocated, NULL, right, 13, uint64) + COL_HDR(row, nmalloc, NULL, right, 13, uint64) + COL_HDR(row, nmalloc_ps, "(#/sec)", right, 8, uint64) + COL_HDR(row, ndalloc, NULL, right, 13, uint64) + COL_HDR(row, ndalloc_ps, "(#/sec)", right, 8, uint64) + COL_HDR(row, nrequests, NULL, right, 13, uint64) + COL_HDR(row, nrequests_ps, "(#/sec)", right, 10, uint64) + COL_HDR(row, nshards, NULL, right, 9, unsigned) + COL_HDR(row, curregs, NULL, right, 13, size) + COL_HDR(row, curslabs, NULL, right, 13, size) + COL_HDR(row, nonfull_slabs, NULL, right, 15, size) + COL_HDR(row, regs, NULL, right, 5, unsigned) + COL_HDR(row, pgs, NULL, right, 4, size) /* To buffer a right- and left-justified column. */ - COL(justify_spacer, right, 1, title) - COL(util, right, 6, title) - COL(nfills, right, 13, uint64) - COL(nflushes, right, 13, uint64) - COL(nslabs, right, 13, uint64) - COL(nreslabs, right, 13, uint64) -#undef COL + COL_HDR(row, justify_spacer, NULL, right, 1, title) + COL_HDR(row, util, NULL, right, 6, title) + COL_HDR(row, nfills, NULL, right, 13, uint64) + COL_HDR(row, nfills_ps, "(#/sec)", right, 8, uint64) + COL_HDR(row, nflushes, NULL, right, 13, uint64) + COL_HDR(row, nflushes_ps, "(#/sec)", right, 8, uint64) + COL_HDR(row, nslabs, NULL, right, 13, uint64) + COL_HDR(row, nreslabs, NULL, right, 13, uint64) + COL_HDR(row, nreslabs_ps, "(#/sec)", right, 8, uint64) /* Don't want to actually print the name. */ - header_col_justify_spacer.str_val = " "; + header_justify_spacer.str_val = " "; col_justify_spacer.str_val = " "; - emitter_col_t col_mutex64[mutex_prof_num_uint64_t_counters]; emitter_col_t col_mutex32[mutex_prof_num_uint32_t_counters]; emitter_col_t header_mutex64[mutex_prof_num_uint64_t_counters]; emitter_col_t header_mutex32[mutex_prof_num_uint32_t_counters]; if (mutex) { mutex_stats_init_cols(&row, NULL, NULL, col_mutex64, col_mutex32); mutex_stats_init_cols(&header_row, NULL, NULL, header_mutex64, header_mutex32); } /* * We print a "bins:" header as part of the table row; we need to adjust * the header size column to compensate. */ - header_col_size.width -=5; + header_size.width -=5; emitter_table_printf(emitter, "bins:"); emitter_table_row(emitter, &header_row); - emitter_json_arr_begin(emitter, "bins"); + emitter_json_array_kv_begin(emitter, "bins"); for (j = 0, in_gap = false; j < nbins; j++) { uint64_t nslabs; size_t reg_size, slab_size, curregs; size_t curslabs; - uint32_t nregs; + size_t nonfull_slabs; + uint32_t nregs, nshards; uint64_t nmalloc, ndalloc, nrequests, nfills, nflushes; uint64_t nreslabs; CTL_M2_M4_GET("stats.arenas.0.bins.0.nslabs", i, j, &nslabs, uint64_t); in_gap_prev = in_gap; in_gap = (nslabs == 0); if (in_gap_prev && !in_gap) { emitter_table_printf(emitter, " ---\n"); } CTL_M2_GET("arenas.bin.0.size", j, ®_size, size_t); CTL_M2_GET("arenas.bin.0.nregs", j, &nregs, uint32_t); CTL_M2_GET("arenas.bin.0.slab_size", j, &slab_size, size_t); + CTL_M2_GET("arenas.bin.0.nshards", j, &nshards, uint32_t); CTL_M2_M4_GET("stats.arenas.0.bins.0.nmalloc", i, j, &nmalloc, uint64_t); CTL_M2_M4_GET("stats.arenas.0.bins.0.ndalloc", i, j, &ndalloc, uint64_t); CTL_M2_M4_GET("stats.arenas.0.bins.0.curregs", i, j, &curregs, size_t); CTL_M2_M4_GET("stats.arenas.0.bins.0.nrequests", i, j, &nrequests, uint64_t); CTL_M2_M4_GET("stats.arenas.0.bins.0.nfills", i, j, &nfills, uint64_t); CTL_M2_M4_GET("stats.arenas.0.bins.0.nflushes", i, j, &nflushes, uint64_t); CTL_M2_M4_GET("stats.arenas.0.bins.0.nreslabs", i, j, &nreslabs, uint64_t); CTL_M2_M4_GET("stats.arenas.0.bins.0.curslabs", i, j, &curslabs, size_t); + CTL_M2_M4_GET("stats.arenas.0.bins.0.nonfull_slabs", i, j, &nonfull_slabs, + size_t); if (mutex) { mutex_stats_read_arena_bin(i, j, col_mutex64, - col_mutex32); + col_mutex32, uptime); } - emitter_json_arr_obj_begin(emitter); + emitter_json_object_begin(emitter); emitter_json_kv(emitter, "nmalloc", emitter_type_uint64, &nmalloc); emitter_json_kv(emitter, "ndalloc", emitter_type_uint64, &ndalloc); emitter_json_kv(emitter, "curregs", emitter_type_size, &curregs); emitter_json_kv(emitter, "nrequests", emitter_type_uint64, &nrequests); emitter_json_kv(emitter, "nfills", emitter_type_uint64, &nfills); emitter_json_kv(emitter, "nflushes", emitter_type_uint64, &nflushes); emitter_json_kv(emitter, "nreslabs", emitter_type_uint64, &nreslabs); emitter_json_kv(emitter, "curslabs", emitter_type_size, &curslabs); + emitter_json_kv(emitter, "nonfull_slabs", emitter_type_size, + &nonfull_slabs); if (mutex) { - emitter_json_dict_begin(emitter, "mutex"); + emitter_json_object_kv_begin(emitter, "mutex"); mutex_stats_emit(emitter, NULL, col_mutex64, col_mutex32); - emitter_json_dict_end(emitter); + emitter_json_object_end(emitter); } - emitter_json_arr_obj_end(emitter); + emitter_json_object_end(emitter); size_t availregs = nregs * curslabs; char util[6]; if (get_rate_str((uint64_t)curregs, (uint64_t)availregs, util)) { if (availregs == 0) { malloc_snprintf(util, sizeof(util), "1"); } else if (curregs > availregs) { /* * Race detected: the counters were read in * separate mallctl calls and concurrent * operations happened in between. In this case * no meaningful utilization can be computed. */ malloc_snprintf(util, sizeof(util), " race"); } else { not_reached(); } } col_size.size_val = reg_size; col_ind.unsigned_val = j; col_allocated.size_val = curregs * reg_size; col_nmalloc.uint64_val = nmalloc; + col_nmalloc_ps.uint64_val = rate_per_second(nmalloc, uptime); col_ndalloc.uint64_val = ndalloc; + col_ndalloc_ps.uint64_val = rate_per_second(ndalloc, uptime); col_nrequests.uint64_val = nrequests; + col_nrequests_ps.uint64_val = rate_per_second(nrequests, uptime); + col_nshards.unsigned_val = nshards; col_curregs.size_val = curregs; col_curslabs.size_val = curslabs; + col_nonfull_slabs.size_val = nonfull_slabs; col_regs.unsigned_val = nregs; col_pgs.size_val = slab_size / page; col_util.str_val = util; col_nfills.uint64_val = nfills; + col_nfills_ps.uint64_val = rate_per_second(nfills, uptime); col_nflushes.uint64_val = nflushes; + col_nflushes_ps.uint64_val = rate_per_second(nflushes, uptime); col_nslabs.uint64_val = nslabs; col_nreslabs.uint64_val = nreslabs; + col_nreslabs_ps.uint64_val = rate_per_second(nreslabs, uptime); /* * Note that mutex columns were initialized above, if mutex == * true. */ emitter_table_row(emitter, &row); } - emitter_json_arr_end(emitter); /* Close "bins". */ + emitter_json_array_end(emitter); /* Close "bins". */ if (in_gap) { emitter_table_printf(emitter, " ---\n"); } } static void -stats_arena_lextents_print(emitter_t *emitter, unsigned i) { +stats_arena_lextents_print(emitter_t *emitter, unsigned i, uint64_t uptime) { unsigned nbins, nlextents, j; bool in_gap, in_gap_prev; CTL_GET("arenas.nbins", &nbins, unsigned); CTL_GET("arenas.nlextents", &nlextents, unsigned); emitter_row_t header_row; emitter_row_init(&header_row); emitter_row_t row; emitter_row_init(&row); -#define COL(name, left_or_right, col_width, etype) \ - emitter_col_t header_##name; \ - emitter_col_init(&header_##name, &header_row); \ - header_##name.justify = emitter_justify_##left_or_right; \ - header_##name.width = col_width; \ - header_##name.type = emitter_type_title; \ - header_##name.str_val = #name; \ - \ - emitter_col_t col_##name; \ - emitter_col_init(&col_##name, &row); \ - col_##name.justify = emitter_justify_##left_or_right; \ - col_##name.width = col_width; \ - col_##name.type = emitter_type_##etype; + COL_HDR(row, size, NULL, right, 20, size) + COL_HDR(row, ind, NULL, right, 4, unsigned) + COL_HDR(row, allocated, NULL, right, 13, size) + COL_HDR(row, nmalloc, NULL, right, 13, uint64) + COL_HDR(row, nmalloc_ps, "(#/sec)", right, 8, uint64) + COL_HDR(row, ndalloc, NULL, right, 13, uint64) + COL_HDR(row, ndalloc_ps, "(#/sec)", right, 8, uint64) + COL_HDR(row, nrequests, NULL, right, 13, uint64) + COL_HDR(row, nrequests_ps, "(#/sec)", right, 8, uint64) + COL_HDR(row, curlextents, NULL, right, 13, size) - COL(size, right, 20, size) - COL(ind, right, 4, unsigned) - COL(allocated, right, 13, size) - COL(nmalloc, right, 13, uint64) - COL(ndalloc, right, 13, uint64) - COL(nrequests, right, 13, uint64) - COL(curlextents, right, 13, size) -#undef COL - /* As with bins, we label the large extents table. */ header_size.width -= 6; emitter_table_printf(emitter, "large:"); emitter_table_row(emitter, &header_row); - emitter_json_arr_begin(emitter, "lextents"); + emitter_json_array_kv_begin(emitter, "lextents"); for (j = 0, in_gap = false; j < nlextents; j++) { uint64_t nmalloc, ndalloc, nrequests; size_t lextent_size, curlextents; CTL_M2_M4_GET("stats.arenas.0.lextents.0.nmalloc", i, j, &nmalloc, uint64_t); CTL_M2_M4_GET("stats.arenas.0.lextents.0.ndalloc", i, j, &ndalloc, uint64_t); CTL_M2_M4_GET("stats.arenas.0.lextents.0.nrequests", i, j, &nrequests, uint64_t); in_gap_prev = in_gap; in_gap = (nrequests == 0); if (in_gap_prev && !in_gap) { emitter_table_printf(emitter, " ---\n"); } CTL_M2_GET("arenas.lextent.0.size", j, &lextent_size, size_t); CTL_M2_M4_GET("stats.arenas.0.lextents.0.curlextents", i, j, &curlextents, size_t); - emitter_json_arr_obj_begin(emitter); + emitter_json_object_begin(emitter); emitter_json_kv(emitter, "curlextents", emitter_type_size, &curlextents); - emitter_json_arr_obj_end(emitter); + emitter_json_object_end(emitter); col_size.size_val = lextent_size; col_ind.unsigned_val = nbins + j; col_allocated.size_val = curlextents * lextent_size; col_nmalloc.uint64_val = nmalloc; + col_nmalloc_ps.uint64_val = rate_per_second(nmalloc, uptime); col_ndalloc.uint64_val = ndalloc; + col_ndalloc_ps.uint64_val = rate_per_second(ndalloc, uptime); col_nrequests.uint64_val = nrequests; + col_nrequests_ps.uint64_val = rate_per_second(nrequests, uptime); col_curlextents.size_val = curlextents; if (!in_gap) { emitter_table_row(emitter, &row); } } - emitter_json_arr_end(emitter); /* Close "lextents". */ + emitter_json_array_end(emitter); /* Close "lextents". */ if (in_gap) { emitter_table_printf(emitter, " ---\n"); } } static void -stats_arena_mutexes_print(emitter_t *emitter, unsigned arena_ind) { +stats_arena_extents_print(emitter_t *emitter, unsigned i) { + unsigned j; + bool in_gap, in_gap_prev; + emitter_row_t header_row; + emitter_row_init(&header_row); emitter_row_t row; + emitter_row_init(&row); + + COL_HDR(row, size, NULL, right, 20, size) + COL_HDR(row, ind, NULL, right, 4, unsigned) + COL_HDR(row, ndirty, NULL, right, 13, size) + COL_HDR(row, dirty, NULL, right, 13, size) + COL_HDR(row, nmuzzy, NULL, right, 13, size) + COL_HDR(row, muzzy, NULL, right, 13, size) + COL_HDR(row, nretained, NULL, right, 13, size) + COL_HDR(row, retained, NULL, right, 13, size) + COL_HDR(row, ntotal, NULL, right, 13, size) + COL_HDR(row, total, NULL, right, 13, size) + + /* Label this section. */ + header_size.width -= 8; + emitter_table_printf(emitter, "extents:"); + emitter_table_row(emitter, &header_row); + emitter_json_array_kv_begin(emitter, "extents"); + + in_gap = false; + for (j = 0; j < SC_NPSIZES; j++) { + size_t ndirty, nmuzzy, nretained, total, dirty_bytes, + muzzy_bytes, retained_bytes, total_bytes; + CTL_M2_M4_GET("stats.arenas.0.extents.0.ndirty", i, j, + &ndirty, size_t); + CTL_M2_M4_GET("stats.arenas.0.extents.0.nmuzzy", i, j, + &nmuzzy, size_t); + CTL_M2_M4_GET("stats.arenas.0.extents.0.nretained", i, j, + &nretained, size_t); + CTL_M2_M4_GET("stats.arenas.0.extents.0.dirty_bytes", i, j, + &dirty_bytes, size_t); + CTL_M2_M4_GET("stats.arenas.0.extents.0.muzzy_bytes", i, j, + &muzzy_bytes, size_t); + CTL_M2_M4_GET("stats.arenas.0.extents.0.retained_bytes", i, j, + &retained_bytes, size_t); + total = ndirty + nmuzzy + nretained; + total_bytes = dirty_bytes + muzzy_bytes + retained_bytes; + + in_gap_prev = in_gap; + in_gap = (total == 0); + + if (in_gap_prev && !in_gap) { + emitter_table_printf(emitter, + " ---\n"); + } + + emitter_json_object_begin(emitter); + emitter_json_kv(emitter, "ndirty", emitter_type_size, &ndirty); + emitter_json_kv(emitter, "nmuzzy", emitter_type_size, &nmuzzy); + emitter_json_kv(emitter, "nretained", emitter_type_size, + &nretained); + + emitter_json_kv(emitter, "dirty_bytes", emitter_type_size, + &dirty_bytes); + emitter_json_kv(emitter, "muzzy_bytes", emitter_type_size, + &muzzy_bytes); + emitter_json_kv(emitter, "retained_bytes", emitter_type_size, + &retained_bytes); + emitter_json_object_end(emitter); + + col_size.size_val = sz_pind2sz(j); + col_ind.size_val = j; + col_ndirty.size_val = ndirty; + col_dirty.size_val = dirty_bytes; + col_nmuzzy.size_val = nmuzzy; + col_muzzy.size_val = muzzy_bytes; + col_nretained.size_val = nretained; + col_retained.size_val = retained_bytes; + col_ntotal.size_val = total; + col_total.size_val = total_bytes; + + if (!in_gap) { + emitter_table_row(emitter, &row); + } + } + emitter_json_array_end(emitter); /* Close "extents". */ + if (in_gap) { + emitter_table_printf(emitter, " ---\n"); + } +} + +static void +stats_arena_mutexes_print(emitter_t *emitter, unsigned arena_ind, uint64_t uptime) { + emitter_row_t row; emitter_col_t col_name; emitter_col_t col64[mutex_prof_num_uint64_t_counters]; emitter_col_t col32[mutex_prof_num_uint32_t_counters]; emitter_row_init(&row); mutex_stats_init_cols(&row, "", &col_name, col64, col32); - emitter_json_dict_begin(emitter, "mutexes"); + emitter_json_object_kv_begin(emitter, "mutexes"); emitter_table_row(emitter, &row); for (mutex_prof_arena_ind_t i = 0; i < mutex_prof_num_arena_mutexes; i++) { const char *name = arena_mutex_names[i]; - emitter_json_dict_begin(emitter, name); + emitter_json_object_kv_begin(emitter, name); mutex_stats_read_arena(arena_ind, i, name, &col_name, col64, - col32); + col32, uptime); mutex_stats_emit(emitter, &row, col64, col32); - emitter_json_dict_end(emitter); /* Close the mutex dict. */ + emitter_json_object_end(emitter); /* Close the mutex dict. */ } - emitter_json_dict_end(emitter); /* End "mutexes". */ + emitter_json_object_end(emitter); /* End "mutexes". */ } static void stats_arena_print(emitter_t *emitter, unsigned i, bool bins, bool large, - bool mutex) { + bool mutex, bool extents) { unsigned nthreads; const char *dss; ssize_t dirty_decay_ms, muzzy_decay_ms; size_t page, pactive, pdirty, pmuzzy, mapped, retained; - size_t base, internal, resident, metadata_thp; + size_t base, internal, resident, metadata_thp, extent_avail; uint64_t dirty_npurge, dirty_nmadvise, dirty_purged; uint64_t muzzy_npurge, muzzy_nmadvise, muzzy_purged; size_t small_allocated; - uint64_t small_nmalloc, small_ndalloc, small_nrequests; + uint64_t small_nmalloc, small_ndalloc, small_nrequests, small_nfills, + small_nflushes; size_t large_allocated; - uint64_t large_nmalloc, large_ndalloc, large_nrequests; - size_t tcache_bytes; + uint64_t large_nmalloc, large_ndalloc, large_nrequests, large_nfills, + large_nflushes; + size_t tcache_bytes, abandoned_vm; uint64_t uptime; CTL_GET("arenas.page", &page, size_t); CTL_M2_GET("stats.arenas.0.nthreads", i, &nthreads, unsigned); emitter_kv(emitter, "nthreads", "assigned threads", emitter_type_unsigned, &nthreads); CTL_M2_GET("stats.arenas.0.uptime", i, &uptime, uint64_t); emitter_kv(emitter, "uptime_ns", "uptime", emitter_type_uint64, &uptime); CTL_M2_GET("stats.arenas.0.dss", i, &dss, const char *); emitter_kv(emitter, "dss", "dss allocation precedence", emitter_type_string, &dss); CTL_M2_GET("stats.arenas.0.dirty_decay_ms", i, &dirty_decay_ms, ssize_t); CTL_M2_GET("stats.arenas.0.muzzy_decay_ms", i, &muzzy_decay_ms, ssize_t); CTL_M2_GET("stats.arenas.0.pactive", i, &pactive, size_t); CTL_M2_GET("stats.arenas.0.pdirty", i, &pdirty, size_t); CTL_M2_GET("stats.arenas.0.pmuzzy", i, &pmuzzy, size_t); CTL_M2_GET("stats.arenas.0.dirty_npurge", i, &dirty_npurge, uint64_t); CTL_M2_GET("stats.arenas.0.dirty_nmadvise", i, &dirty_nmadvise, uint64_t); CTL_M2_GET("stats.arenas.0.dirty_purged", i, &dirty_purged, uint64_t); CTL_M2_GET("stats.arenas.0.muzzy_npurge", i, &muzzy_npurge, uint64_t); CTL_M2_GET("stats.arenas.0.muzzy_nmadvise", i, &muzzy_nmadvise, uint64_t); CTL_M2_GET("stats.arenas.0.muzzy_purged", i, &muzzy_purged, uint64_t); emitter_row_t decay_row; emitter_row_init(&decay_row); /* JSON-style emission. */ emitter_json_kv(emitter, "dirty_decay_ms", emitter_type_ssize, &dirty_decay_ms); emitter_json_kv(emitter, "muzzy_decay_ms", emitter_type_ssize, &muzzy_decay_ms); emitter_json_kv(emitter, "pactive", emitter_type_size, &pactive); emitter_json_kv(emitter, "pdirty", emitter_type_size, &pdirty); emitter_json_kv(emitter, "pmuzzy", emitter_type_size, &pmuzzy); emitter_json_kv(emitter, "dirty_npurge", emitter_type_uint64, &dirty_npurge); emitter_json_kv(emitter, "dirty_nmadvise", emitter_type_uint64, &dirty_nmadvise); emitter_json_kv(emitter, "dirty_purged", emitter_type_uint64, &dirty_purged); emitter_json_kv(emitter, "muzzy_npurge", emitter_type_uint64, &muzzy_npurge); emitter_json_kv(emitter, "muzzy_nmadvise", emitter_type_uint64, &muzzy_nmadvise); emitter_json_kv(emitter, "muzzy_purged", emitter_type_uint64, &muzzy_purged); /* Table-style emission. */ - emitter_col_t decay_type; - emitter_col_init(&decay_type, &decay_row); - decay_type.justify = emitter_justify_right; - decay_type.width = 9; - decay_type.type = emitter_type_title; - decay_type.str_val = "decaying:"; + COL(decay_row, decay_type, right, 9, title); + col_decay_type.str_val = "decaying:"; - emitter_col_t decay_time; - emitter_col_init(&decay_time, &decay_row); - decay_time.justify = emitter_justify_right; - decay_time.width = 6; - decay_time.type = emitter_type_title; - decay_time.str_val = "time"; + COL(decay_row, decay_time, right, 6, title); + col_decay_time.str_val = "time"; - emitter_col_t decay_npages; - emitter_col_init(&decay_npages, &decay_row); - decay_npages.justify = emitter_justify_right; - decay_npages.width = 13; - decay_npages.type = emitter_type_title; - decay_npages.str_val = "npages"; + COL(decay_row, decay_npages, right, 13, title); + col_decay_npages.str_val = "npages"; - emitter_col_t decay_sweeps; - emitter_col_init(&decay_sweeps, &decay_row); - decay_sweeps.justify = emitter_justify_right; - decay_sweeps.width = 13; - decay_sweeps.type = emitter_type_title; - decay_sweeps.str_val = "sweeps"; + COL(decay_row, decay_sweeps, right, 13, title); + col_decay_sweeps.str_val = "sweeps"; - emitter_col_t decay_madvises; - emitter_col_init(&decay_madvises, &decay_row); - decay_madvises.justify = emitter_justify_right; - decay_madvises.width = 13; - decay_madvises.type = emitter_type_title; - decay_madvises.str_val = "madvises"; + COL(decay_row, decay_madvises, right, 13, title); + col_decay_madvises.str_val = "madvises"; - emitter_col_t decay_purged; - emitter_col_init(&decay_purged, &decay_row); - decay_purged.justify = emitter_justify_right; - decay_purged.width = 13; - decay_purged.type = emitter_type_title; - decay_purged.str_val = "purged"; + COL(decay_row, decay_purged, right, 13, title); + col_decay_purged.str_val = "purged"; /* Title row. */ emitter_table_row(emitter, &decay_row); /* Dirty row. */ - decay_type.str_val = "dirty:"; + col_decay_type.str_val = "dirty:"; if (dirty_decay_ms >= 0) { - decay_time.type = emitter_type_ssize; - decay_time.ssize_val = dirty_decay_ms; + col_decay_time.type = emitter_type_ssize; + col_decay_time.ssize_val = dirty_decay_ms; } else { - decay_time.type = emitter_type_title; - decay_time.str_val = "N/A"; + col_decay_time.type = emitter_type_title; + col_decay_time.str_val = "N/A"; } - decay_npages.type = emitter_type_size; - decay_npages.size_val = pdirty; + col_decay_npages.type = emitter_type_size; + col_decay_npages.size_val = pdirty; - decay_sweeps.type = emitter_type_uint64; - decay_sweeps.uint64_val = dirty_npurge; + col_decay_sweeps.type = emitter_type_uint64; + col_decay_sweeps.uint64_val = dirty_npurge; - decay_madvises.type = emitter_type_uint64; - decay_madvises.uint64_val = dirty_nmadvise; + col_decay_madvises.type = emitter_type_uint64; + col_decay_madvises.uint64_val = dirty_nmadvise; - decay_purged.type = emitter_type_uint64; - decay_purged.uint64_val = dirty_purged; + col_decay_purged.type = emitter_type_uint64; + col_decay_purged.uint64_val = dirty_purged; emitter_table_row(emitter, &decay_row); /* Muzzy row. */ - decay_type.str_val = "muzzy:"; + col_decay_type.str_val = "muzzy:"; if (muzzy_decay_ms >= 0) { - decay_time.type = emitter_type_ssize; - decay_time.ssize_val = muzzy_decay_ms; + col_decay_time.type = emitter_type_ssize; + col_decay_time.ssize_val = muzzy_decay_ms; } else { - decay_time.type = emitter_type_title; - decay_time.str_val = "N/A"; + col_decay_time.type = emitter_type_title; + col_decay_time.str_val = "N/A"; } - decay_npages.type = emitter_type_size; - decay_npages.size_val = pmuzzy; + col_decay_npages.type = emitter_type_size; + col_decay_npages.size_val = pmuzzy; - decay_sweeps.type = emitter_type_uint64; - decay_sweeps.uint64_val = muzzy_npurge; + col_decay_sweeps.type = emitter_type_uint64; + col_decay_sweeps.uint64_val = muzzy_npurge; - decay_madvises.type = emitter_type_uint64; - decay_madvises.uint64_val = muzzy_nmadvise; + col_decay_madvises.type = emitter_type_uint64; + col_decay_madvises.uint64_val = muzzy_nmadvise; - decay_purged.type = emitter_type_uint64; - decay_purged.uint64_val = muzzy_purged; + col_decay_purged.type = emitter_type_uint64; + col_decay_purged.uint64_val = muzzy_purged; emitter_table_row(emitter, &decay_row); /* Small / large / total allocation counts. */ emitter_row_t alloc_count_row; emitter_row_init(&alloc_count_row); - emitter_col_t alloc_count_title; - emitter_col_init(&alloc_count_title, &alloc_count_row); - alloc_count_title.justify = emitter_justify_left; - alloc_count_title.width = 25; - alloc_count_title.type = emitter_type_title; - alloc_count_title.str_val = ""; + COL(alloc_count_row, count_title, left, 21, title); + col_count_title.str_val = ""; - emitter_col_t alloc_count_allocated; - emitter_col_init(&alloc_count_allocated, &alloc_count_row); - alloc_count_allocated.justify = emitter_justify_right; - alloc_count_allocated.width = 12; - alloc_count_allocated.type = emitter_type_title; - alloc_count_allocated.str_val = "allocated"; + COL(alloc_count_row, count_allocated, right, 16, title); + col_count_allocated.str_val = "allocated"; - emitter_col_t alloc_count_nmalloc; - emitter_col_init(&alloc_count_nmalloc, &alloc_count_row); - alloc_count_nmalloc.justify = emitter_justify_right; - alloc_count_nmalloc.width = 12; - alloc_count_nmalloc.type = emitter_type_title; - alloc_count_nmalloc.str_val = "nmalloc"; + COL(alloc_count_row, count_nmalloc, right, 16, title); + col_count_nmalloc.str_val = "nmalloc"; + COL(alloc_count_row, count_nmalloc_ps, right, 8, title); + col_count_nmalloc_ps.str_val = "(#/sec)"; - emitter_col_t alloc_count_ndalloc; - emitter_col_init(&alloc_count_ndalloc, &alloc_count_row); - alloc_count_ndalloc.justify = emitter_justify_right; - alloc_count_ndalloc.width = 12; - alloc_count_ndalloc.type = emitter_type_title; - alloc_count_ndalloc.str_val = "ndalloc"; + COL(alloc_count_row, count_ndalloc, right, 16, title); + col_count_ndalloc.str_val = "ndalloc"; + COL(alloc_count_row, count_ndalloc_ps, right, 8, title); + col_count_ndalloc_ps.str_val = "(#/sec)"; - emitter_col_t alloc_count_nrequests; - emitter_col_init(&alloc_count_nrequests, &alloc_count_row); - alloc_count_nrequests.justify = emitter_justify_right; - alloc_count_nrequests.width = 12; - alloc_count_nrequests.type = emitter_type_title; - alloc_count_nrequests.str_val = "nrequests"; + COL(alloc_count_row, count_nrequests, right, 16, title); + col_count_nrequests.str_val = "nrequests"; + COL(alloc_count_row, count_nrequests_ps, right, 10, title); + col_count_nrequests_ps.str_val = "(#/sec)"; + COL(alloc_count_row, count_nfills, right, 16, title); + col_count_nfills.str_val = "nfill"; + COL(alloc_count_row, count_nfills_ps, right, 10, title); + col_count_nfills_ps.str_val = "(#/sec)"; + + COL(alloc_count_row, count_nflushes, right, 16, title); + col_count_nflushes.str_val = "nflush"; + COL(alloc_count_row, count_nflushes_ps, right, 10, title); + col_count_nflushes_ps.str_val = "(#/sec)"; + emitter_table_row(emitter, &alloc_count_row); + col_count_nmalloc_ps.type = emitter_type_uint64; + col_count_ndalloc_ps.type = emitter_type_uint64; + col_count_nrequests_ps.type = emitter_type_uint64; + col_count_nfills_ps.type = emitter_type_uint64; + col_count_nflushes_ps.type = emitter_type_uint64; + #define GET_AND_EMIT_ALLOC_STAT(small_or_large, name, valtype) \ CTL_M2_GET("stats.arenas.0." #small_or_large "." #name, i, \ &small_or_large##_##name, valtype##_t); \ emitter_json_kv(emitter, #name, emitter_type_##valtype, \ &small_or_large##_##name); \ - alloc_count_##name.type = emitter_type_##valtype; \ - alloc_count_##name.valtype##_val = small_or_large##_##name; + col_count_##name.type = emitter_type_##valtype; \ + col_count_##name.valtype##_val = small_or_large##_##name; - emitter_json_dict_begin(emitter, "small"); - alloc_count_title.str_val = "small:"; + emitter_json_object_kv_begin(emitter, "small"); + col_count_title.str_val = "small:"; GET_AND_EMIT_ALLOC_STAT(small, allocated, size) GET_AND_EMIT_ALLOC_STAT(small, nmalloc, uint64) + col_count_nmalloc_ps.uint64_val = + rate_per_second(col_count_nmalloc.uint64_val, uptime); GET_AND_EMIT_ALLOC_STAT(small, ndalloc, uint64) + col_count_ndalloc_ps.uint64_val = + rate_per_second(col_count_ndalloc.uint64_val, uptime); GET_AND_EMIT_ALLOC_STAT(small, nrequests, uint64) + col_count_nrequests_ps.uint64_val = + rate_per_second(col_count_nrequests.uint64_val, uptime); + GET_AND_EMIT_ALLOC_STAT(small, nfills, uint64) + col_count_nfills_ps.uint64_val = + rate_per_second(col_count_nfills.uint64_val, uptime); + GET_AND_EMIT_ALLOC_STAT(small, nflushes, uint64) + col_count_nflushes_ps.uint64_val = + rate_per_second(col_count_nflushes.uint64_val, uptime); emitter_table_row(emitter, &alloc_count_row); - emitter_json_dict_end(emitter); /* Close "small". */ + emitter_json_object_end(emitter); /* Close "small". */ - emitter_json_dict_begin(emitter, "large"); - alloc_count_title.str_val = "large:"; + emitter_json_object_kv_begin(emitter, "large"); + col_count_title.str_val = "large:"; GET_AND_EMIT_ALLOC_STAT(large, allocated, size) GET_AND_EMIT_ALLOC_STAT(large, nmalloc, uint64) + col_count_nmalloc_ps.uint64_val = + rate_per_second(col_count_nmalloc.uint64_val, uptime); GET_AND_EMIT_ALLOC_STAT(large, ndalloc, uint64) + col_count_ndalloc_ps.uint64_val = + rate_per_second(col_count_ndalloc.uint64_val, uptime); GET_AND_EMIT_ALLOC_STAT(large, nrequests, uint64) + col_count_nrequests_ps.uint64_val = + rate_per_second(col_count_nrequests.uint64_val, uptime); + GET_AND_EMIT_ALLOC_STAT(large, nfills, uint64) + col_count_nfills_ps.uint64_val = + rate_per_second(col_count_nfills.uint64_val, uptime); + GET_AND_EMIT_ALLOC_STAT(large, nflushes, uint64) + col_count_nflushes_ps.uint64_val = + rate_per_second(col_count_nflushes.uint64_val, uptime); emitter_table_row(emitter, &alloc_count_row); - emitter_json_dict_end(emitter); /* Close "large". */ + emitter_json_object_end(emitter); /* Close "large". */ #undef GET_AND_EMIT_ALLOC_STAT /* Aggregated small + large stats are emitter only in table mode. */ - alloc_count_title.str_val = "total:"; - alloc_count_allocated.size_val = small_allocated + large_allocated; - alloc_count_nmalloc.uint64_val = small_nmalloc + large_nmalloc; - alloc_count_ndalloc.uint64_val = small_ndalloc + large_ndalloc; - alloc_count_nrequests.uint64_val = small_nrequests + large_nrequests; + col_count_title.str_val = "total:"; + col_count_allocated.size_val = small_allocated + large_allocated; + col_count_nmalloc.uint64_val = small_nmalloc + large_nmalloc; + col_count_ndalloc.uint64_val = small_ndalloc + large_ndalloc; + col_count_nrequests.uint64_val = small_nrequests + large_nrequests; + col_count_nfills.uint64_val = small_nfills + large_nfills; + col_count_nflushes.uint64_val = small_nflushes + large_nflushes; + col_count_nmalloc_ps.uint64_val = + rate_per_second(col_count_nmalloc.uint64_val, uptime); + col_count_ndalloc_ps.uint64_val = + rate_per_second(col_count_ndalloc.uint64_val, uptime); + col_count_nrequests_ps.uint64_val = + rate_per_second(col_count_nrequests.uint64_val, uptime); + col_count_nfills_ps.uint64_val = + rate_per_second(col_count_nfills.uint64_val, uptime); + col_count_nflushes_ps.uint64_val = + rate_per_second(col_count_nflushes.uint64_val, uptime); emitter_table_row(emitter, &alloc_count_row); emitter_row_t mem_count_row; emitter_row_init(&mem_count_row); emitter_col_t mem_count_title; emitter_col_init(&mem_count_title, &mem_count_row); mem_count_title.justify = emitter_justify_left; - mem_count_title.width = 25; + mem_count_title.width = 21; mem_count_title.type = emitter_type_title; mem_count_title.str_val = ""; emitter_col_t mem_count_val; emitter_col_init(&mem_count_val, &mem_count_row); mem_count_val.justify = emitter_justify_right; - mem_count_val.width = 12; + mem_count_val.width = 16; mem_count_val.type = emitter_type_title; mem_count_val.str_val = ""; emitter_table_row(emitter, &mem_count_row); mem_count_val.type = emitter_type_size; /* Active count in bytes is emitted only in table mode. */ mem_count_title.str_val = "active:"; mem_count_val.size_val = pactive * page; emitter_table_row(emitter, &mem_count_row); #define GET_AND_EMIT_MEM_STAT(stat) \ CTL_M2_GET("stats.arenas.0."#stat, i, &stat, size_t); \ emitter_json_kv(emitter, #stat, emitter_type_size, &stat); \ mem_count_title.str_val = #stat":"; \ mem_count_val.size_val = stat; \ emitter_table_row(emitter, &mem_count_row); GET_AND_EMIT_MEM_STAT(mapped) GET_AND_EMIT_MEM_STAT(retained) GET_AND_EMIT_MEM_STAT(base) GET_AND_EMIT_MEM_STAT(internal) GET_AND_EMIT_MEM_STAT(metadata_thp) GET_AND_EMIT_MEM_STAT(tcache_bytes) GET_AND_EMIT_MEM_STAT(resident) + GET_AND_EMIT_MEM_STAT(abandoned_vm) + GET_AND_EMIT_MEM_STAT(extent_avail) #undef GET_AND_EMIT_MEM_STAT if (mutex) { - stats_arena_mutexes_print(emitter, i); + stats_arena_mutexes_print(emitter, i, uptime); } if (bins) { - stats_arena_bins_print(emitter, mutex, i); + stats_arena_bins_print(emitter, mutex, i, uptime); } if (large) { - stats_arena_lextents_print(emitter, i); + stats_arena_lextents_print(emitter, i, uptime); } + if (extents) { + stats_arena_extents_print(emitter, i); + } } static void stats_general_print(emitter_t *emitter) { const char *cpv; bool bv, bv2; unsigned uv; uint32_t u32v; uint64_t u64v; ssize_t ssv, ssv2; size_t sv, bsz, usz, ssz, sssz, cpsz; bsz = sizeof(bool); usz = sizeof(unsigned); ssz = sizeof(size_t); sssz = sizeof(ssize_t); cpsz = sizeof(const char *); CTL_GET("version", &cpv, const char *); emitter_kv(emitter, "version", "Version", emitter_type_string, &cpv); /* config. */ emitter_dict_begin(emitter, "config", "Build-time option settings"); #define CONFIG_WRITE_BOOL(name) \ do { \ CTL_GET("config."#name, &bv, bool); \ emitter_kv(emitter, #name, "config."#name, \ emitter_type_bool, &bv); \ } while (0) CONFIG_WRITE_BOOL(cache_oblivious); CONFIG_WRITE_BOOL(debug); CONFIG_WRITE_BOOL(fill); CONFIG_WRITE_BOOL(lazy_lock); emitter_kv(emitter, "malloc_conf", "config.malloc_conf", emitter_type_string, &config_malloc_conf); + CONFIG_WRITE_BOOL(opt_safety_checks); CONFIG_WRITE_BOOL(prof); CONFIG_WRITE_BOOL(prof_libgcc); CONFIG_WRITE_BOOL(prof_libunwind); CONFIG_WRITE_BOOL(stats); CONFIG_WRITE_BOOL(utrace); CONFIG_WRITE_BOOL(xmalloc); #undef CONFIG_WRITE_BOOL emitter_dict_end(emitter); /* Close "config" dict. */ /* opt. */ #define OPT_WRITE(name, var, size, emitter_type) \ if (je_mallctl("opt."name, (void *)&var, &size, NULL, 0) == \ 0) { \ emitter_kv(emitter, name, "opt."name, emitter_type, \ &var); \ } #define OPT_WRITE_MUTABLE(name, var1, var2, size, emitter_type, \ altname) \ if (je_mallctl("opt."name, (void *)&var1, &size, NULL, 0) == \ 0 && je_mallctl(altname, (void *)&var2, &size, NULL, 0) \ == 0) { \ emitter_kv_note(emitter, name, "opt."name, \ emitter_type, &var1, altname, emitter_type, \ &var2); \ } #define OPT_WRITE_BOOL(name) OPT_WRITE(name, bv, bsz, emitter_type_bool) #define OPT_WRITE_BOOL_MUTABLE(name, altname) \ OPT_WRITE_MUTABLE(name, bv, bv2, bsz, emitter_type_bool, altname) #define OPT_WRITE_UNSIGNED(name) \ OPT_WRITE(name, uv, usz, emitter_type_unsigned) +#define OPT_WRITE_SIZE_T(name) \ + OPT_WRITE(name, sv, ssz, emitter_type_size) #define OPT_WRITE_SSIZE_T(name) \ OPT_WRITE(name, ssv, sssz, emitter_type_ssize) #define OPT_WRITE_SSIZE_T_MUTABLE(name, altname) \ OPT_WRITE_MUTABLE(name, ssv, ssv2, sssz, emitter_type_ssize, \ altname) #define OPT_WRITE_CHAR_P(name) \ OPT_WRITE(name, cpv, cpsz, emitter_type_string) emitter_dict_begin(emitter, "opt", "Run-time option settings"); OPT_WRITE_BOOL("abort") OPT_WRITE_BOOL("abort_conf") + OPT_WRITE_BOOL("confirm_conf") OPT_WRITE_BOOL("retain") OPT_WRITE_CHAR_P("dss") OPT_WRITE_UNSIGNED("narenas") OPT_WRITE_CHAR_P("percpu_arena") + OPT_WRITE_SIZE_T("oversize_threshold") OPT_WRITE_CHAR_P("metadata_thp") OPT_WRITE_BOOL_MUTABLE("background_thread", "background_thread") OPT_WRITE_SSIZE_T_MUTABLE("dirty_decay_ms", "arenas.dirty_decay_ms") OPT_WRITE_SSIZE_T_MUTABLE("muzzy_decay_ms", "arenas.muzzy_decay_ms") - OPT_WRITE_UNSIGNED("lg_extent_max_active_fit") + OPT_WRITE_SIZE_T("lg_extent_max_active_fit") OPT_WRITE_CHAR_P("junk") OPT_WRITE_BOOL("zero") OPT_WRITE_BOOL("utrace") OPT_WRITE_BOOL("xmalloc") OPT_WRITE_BOOL("tcache") OPT_WRITE_SSIZE_T("lg_tcache_max") OPT_WRITE_CHAR_P("thp") OPT_WRITE_BOOL("prof") OPT_WRITE_CHAR_P("prof_prefix") OPT_WRITE_BOOL_MUTABLE("prof_active", "prof.active") OPT_WRITE_BOOL_MUTABLE("prof_thread_active_init", "prof.thread_active_init") OPT_WRITE_SSIZE_T_MUTABLE("lg_prof_sample", "prof.lg_sample") OPT_WRITE_BOOL("prof_accum") OPT_WRITE_SSIZE_T("lg_prof_interval") OPT_WRITE_BOOL("prof_gdump") OPT_WRITE_BOOL("prof_final") OPT_WRITE_BOOL("prof_leak") OPT_WRITE_BOOL("stats_print") OPT_WRITE_CHAR_P("stats_print_opts") emitter_dict_end(emitter); #undef OPT_WRITE #undef OPT_WRITE_MUTABLE #undef OPT_WRITE_BOOL #undef OPT_WRITE_BOOL_MUTABLE #undef OPT_WRITE_UNSIGNED #undef OPT_WRITE_SSIZE_T #undef OPT_WRITE_SSIZE_T_MUTABLE #undef OPT_WRITE_CHAR_P /* prof. */ if (config_prof) { emitter_dict_begin(emitter, "prof", "Profiling settings"); CTL_GET("prof.thread_active_init", &bv, bool); emitter_kv(emitter, "thread_active_init", "prof.thread_active_init", emitter_type_bool, &bv); CTL_GET("prof.active", &bv, bool); emitter_kv(emitter, "active", "prof.active", emitter_type_bool, &bv); CTL_GET("prof.gdump", &bv, bool); emitter_kv(emitter, "gdump", "prof.gdump", emitter_type_bool, &bv); CTL_GET("prof.interval", &u64v, uint64_t); emitter_kv(emitter, "interval", "prof.interval", emitter_type_uint64, &u64v); CTL_GET("prof.lg_sample", &ssv, ssize_t); emitter_kv(emitter, "lg_sample", "prof.lg_sample", emitter_type_ssize, &ssv); emitter_dict_end(emitter); /* Close "prof". */ } /* arenas. */ /* * The json output sticks arena info into an "arenas" dict; the table * output puts them at the top-level. */ - emitter_json_dict_begin(emitter, "arenas"); + emitter_json_object_kv_begin(emitter, "arenas"); CTL_GET("arenas.narenas", &uv, unsigned); emitter_kv(emitter, "narenas", "Arenas", emitter_type_unsigned, &uv); /* * Decay settings are emitted only in json mode; in table mode, they're * emitted as notes with the opt output, above. */ CTL_GET("arenas.dirty_decay_ms", &ssv, ssize_t); emitter_json_kv(emitter, "dirty_decay_ms", emitter_type_ssize, &ssv); CTL_GET("arenas.muzzy_decay_ms", &ssv, ssize_t); emitter_json_kv(emitter, "muzzy_decay_ms", emitter_type_ssize, &ssv); CTL_GET("arenas.quantum", &sv, size_t); emitter_kv(emitter, "quantum", "Quantum size", emitter_type_size, &sv); CTL_GET("arenas.page", &sv, size_t); emitter_kv(emitter, "page", "Page size", emitter_type_size, &sv); if (je_mallctl("arenas.tcache_max", (void *)&sv, &ssz, NULL, 0) == 0) { emitter_kv(emitter, "tcache_max", "Maximum thread-cached size class", emitter_type_size, &sv); } unsigned nbins; CTL_GET("arenas.nbins", &nbins, unsigned); emitter_kv(emitter, "nbins", "Number of bin size classes", emitter_type_unsigned, &nbins); unsigned nhbins; CTL_GET("arenas.nhbins", &nhbins, unsigned); emitter_kv(emitter, "nhbins", "Number of thread-cache bin size classes", emitter_type_unsigned, &nhbins); /* * We do enough mallctls in a loop that we actually want to omit them * (not just omit the printing). */ if (emitter->output == emitter_output_json) { - emitter_json_arr_begin(emitter, "bin"); + emitter_json_array_kv_begin(emitter, "bin"); for (unsigned i = 0; i < nbins; i++) { - emitter_json_arr_obj_begin(emitter); + emitter_json_object_begin(emitter); CTL_M2_GET("arenas.bin.0.size", i, &sv, size_t); emitter_json_kv(emitter, "size", emitter_type_size, &sv); CTL_M2_GET("arenas.bin.0.nregs", i, &u32v, uint32_t); emitter_json_kv(emitter, "nregs", emitter_type_uint32, &u32v); CTL_M2_GET("arenas.bin.0.slab_size", i, &sv, size_t); emitter_json_kv(emitter, "slab_size", emitter_type_size, &sv); - emitter_json_arr_obj_end(emitter); + CTL_M2_GET("arenas.bin.0.nshards", i, &u32v, uint32_t); + emitter_json_kv(emitter, "nshards", emitter_type_uint32, + &u32v); + + emitter_json_object_end(emitter); } - emitter_json_arr_end(emitter); /* Close "bin". */ + emitter_json_array_end(emitter); /* Close "bin". */ } unsigned nlextents; CTL_GET("arenas.nlextents", &nlextents, unsigned); emitter_kv(emitter, "nlextents", "Number of large size classes", emitter_type_unsigned, &nlextents); if (emitter->output == emitter_output_json) { - emitter_json_arr_begin(emitter, "lextent"); + emitter_json_array_kv_begin(emitter, "lextent"); for (unsigned i = 0; i < nlextents; i++) { - emitter_json_arr_obj_begin(emitter); + emitter_json_object_begin(emitter); CTL_M2_GET("arenas.lextent.0.size", i, &sv, size_t); emitter_json_kv(emitter, "size", emitter_type_size, &sv); - emitter_json_arr_obj_end(emitter); + emitter_json_object_end(emitter); } - emitter_json_arr_end(emitter); /* Close "lextent". */ + emitter_json_array_end(emitter); /* Close "lextent". */ } - emitter_json_dict_end(emitter); /* Close "arenas" */ + emitter_json_object_end(emitter); /* Close "arenas" */ } static void stats_print_helper(emitter_t *emitter, bool merged, bool destroyed, - bool unmerged, bool bins, bool large, bool mutex) { + bool unmerged, bool bins, bool large, bool mutex, bool extents) { /* * These should be deleted. We keep them around for a while, to aid in * the transition to the emitter code. */ size_t allocated, active, metadata, metadata_thp, resident, mapped, retained; size_t num_background_threads; uint64_t background_thread_num_runs, background_thread_run_interval; CTL_GET("stats.allocated", &allocated, size_t); CTL_GET("stats.active", &active, size_t); CTL_GET("stats.metadata", &metadata, size_t); CTL_GET("stats.metadata_thp", &metadata_thp, size_t); CTL_GET("stats.resident", &resident, size_t); CTL_GET("stats.mapped", &mapped, size_t); CTL_GET("stats.retained", &retained, size_t); if (have_background_thread) { CTL_GET("stats.background_thread.num_threads", &num_background_threads, size_t); CTL_GET("stats.background_thread.num_runs", &background_thread_num_runs, uint64_t); CTL_GET("stats.background_thread.run_interval", &background_thread_run_interval, uint64_t); } else { num_background_threads = 0; background_thread_num_runs = 0; background_thread_run_interval = 0; } /* Generic global stats. */ - emitter_json_dict_begin(emitter, "stats"); + emitter_json_object_kv_begin(emitter, "stats"); emitter_json_kv(emitter, "allocated", emitter_type_size, &allocated); emitter_json_kv(emitter, "active", emitter_type_size, &active); emitter_json_kv(emitter, "metadata", emitter_type_size, &metadata); emitter_json_kv(emitter, "metadata_thp", emitter_type_size, &metadata_thp); emitter_json_kv(emitter, "resident", emitter_type_size, &resident); emitter_json_kv(emitter, "mapped", emitter_type_size, &mapped); emitter_json_kv(emitter, "retained", emitter_type_size, &retained); emitter_table_printf(emitter, "Allocated: %zu, active: %zu, " "metadata: %zu (n_thp %zu), resident: %zu, mapped: %zu, " "retained: %zu\n", allocated, active, metadata, metadata_thp, resident, mapped, retained); /* Background thread stats. */ - emitter_json_dict_begin(emitter, "background_thread"); + emitter_json_object_kv_begin(emitter, "background_thread"); emitter_json_kv(emitter, "num_threads", emitter_type_size, &num_background_threads); emitter_json_kv(emitter, "num_runs", emitter_type_uint64, &background_thread_num_runs); emitter_json_kv(emitter, "run_interval", emitter_type_uint64, &background_thread_run_interval); - emitter_json_dict_end(emitter); /* Close "background_thread". */ + emitter_json_object_end(emitter); /* Close "background_thread". */ emitter_table_printf(emitter, "Background threads: %zu, " "num_runs: %"FMTu64", run_interval: %"FMTu64" ns\n", num_background_threads, background_thread_num_runs, background_thread_run_interval); if (mutex) { emitter_row_t row; emitter_col_t name; emitter_col_t col64[mutex_prof_num_uint64_t_counters]; emitter_col_t col32[mutex_prof_num_uint32_t_counters]; + uint64_t uptime; emitter_row_init(&row); mutex_stats_init_cols(&row, "", &name, col64, col32); emitter_table_row(emitter, &row); - emitter_json_dict_begin(emitter, "mutexes"); + emitter_json_object_kv_begin(emitter, "mutexes"); + CTL_M2_GET("stats.arenas.0.uptime", 0, &uptime, uint64_t); + for (int i = 0; i < mutex_prof_num_global_mutexes; i++) { mutex_stats_read_global(global_mutex_names[i], &name, - col64, col32); - emitter_json_dict_begin(emitter, global_mutex_names[i]); + col64, col32, uptime); + emitter_json_object_kv_begin(emitter, global_mutex_names[i]); mutex_stats_emit(emitter, &row, col64, col32); - emitter_json_dict_end(emitter); + emitter_json_object_end(emitter); } - emitter_json_dict_end(emitter); /* Close "mutexes". */ + emitter_json_object_end(emitter); /* Close "mutexes". */ } - emitter_json_dict_end(emitter); /* Close "stats". */ + emitter_json_object_end(emitter); /* Close "stats". */ if (merged || destroyed || unmerged) { unsigned narenas; - emitter_json_dict_begin(emitter, "stats.arenas"); + emitter_json_object_kv_begin(emitter, "stats.arenas"); CTL_GET("arenas.narenas", &narenas, unsigned); size_t mib[3]; size_t miblen = sizeof(mib) / sizeof(size_t); size_t sz; VARIABLE_ARRAY(bool, initialized, narenas); bool destroyed_initialized; unsigned i, j, ninitialized; xmallctlnametomib("arena.0.initialized", mib, &miblen); for (i = ninitialized = 0; i < narenas; i++) { mib[1] = i; sz = sizeof(bool); xmallctlbymib(mib, miblen, &initialized[i], &sz, NULL, 0); if (initialized[i]) { ninitialized++; } } mib[1] = MALLCTL_ARENAS_DESTROYED; sz = sizeof(bool); xmallctlbymib(mib, miblen, &destroyed_initialized, &sz, NULL, 0); /* Merged stats. */ if (merged && (ninitialized > 1 || !unmerged)) { /* Print merged arena stats. */ emitter_table_printf(emitter, "Merged arenas stats:\n"); - emitter_json_dict_begin(emitter, "merged"); + emitter_json_object_kv_begin(emitter, "merged"); stats_arena_print(emitter, MALLCTL_ARENAS_ALL, bins, - large, mutex); - emitter_json_dict_end(emitter); /* Close "merged". */ + large, mutex, extents); + emitter_json_object_end(emitter); /* Close "merged". */ } /* Destroyed stats. */ if (destroyed_initialized && destroyed) { /* Print destroyed arena stats. */ emitter_table_printf(emitter, "Destroyed arenas stats:\n"); - emitter_json_dict_begin(emitter, "destroyed"); + emitter_json_object_kv_begin(emitter, "destroyed"); stats_arena_print(emitter, MALLCTL_ARENAS_DESTROYED, - bins, large, mutex); - emitter_json_dict_end(emitter); /* Close "destroyed". */ + bins, large, mutex, extents); + emitter_json_object_end(emitter); /* Close "destroyed". */ } /* Unmerged stats. */ if (unmerged) { for (i = j = 0; i < narenas; i++) { if (initialized[i]) { char arena_ind_str[20]; malloc_snprintf(arena_ind_str, sizeof(arena_ind_str), "%u", i); - emitter_json_dict_begin(emitter, + emitter_json_object_kv_begin(emitter, arena_ind_str); emitter_table_printf(emitter, "arenas[%s]:\n", arena_ind_str); stats_arena_print(emitter, i, bins, - large, mutex); + large, mutex, extents); /* Close "". */ - emitter_json_dict_end(emitter); + emitter_json_object_end(emitter); } } } - emitter_json_dict_end(emitter); /* Close "stats.arenas". */ + emitter_json_object_end(emitter); /* Close "stats.arenas". */ } } void stats_print(void (*write_cb)(void *, const char *), void *cbopaque, const char *opts) { int err; uint64_t epoch; size_t u64sz; #define OPTION(o, v, d, s) bool v = d; STATS_PRINT_OPTIONS #undef OPTION /* * Refresh stats, in case mallctl() was called by the application. * * Check for OOM here, since refreshing the ctl cache can trigger * allocation. In practice, none of the subsequent mallctl()-related * calls in this function will cause OOM if this one succeeds. * */ epoch = 1; u64sz = sizeof(uint64_t); err = je_mallctl("epoch", (void *)&epoch, &u64sz, (void *)&epoch, sizeof(uint64_t)); if (err != 0) { if (err == EAGAIN) { malloc_write(": Memory allocation failure in " "mallctl(\"epoch\", ...)\n"); return; } malloc_write(": Failure in mallctl(\"epoch\", " "...)\n"); abort(); } if (opts != NULL) { for (unsigned i = 0; opts[i] != '\0'; i++) { switch (opts[i]) { #define OPTION(o, v, d, s) case o: v = s; break; STATS_PRINT_OPTIONS #undef OPTION default:; } } } emitter_t emitter; emitter_init(&emitter, json ? emitter_output_json : emitter_output_table, write_cb, cbopaque); emitter_begin(&emitter); emitter_table_printf(&emitter, "___ Begin jemalloc statistics ___\n"); - emitter_json_dict_begin(&emitter, "jemalloc"); + emitter_json_object_kv_begin(&emitter, "jemalloc"); if (general) { stats_general_print(&emitter); } if (config_stats) { stats_print_helper(&emitter, merged, destroyed, unmerged, - bins, large, mutex); + bins, large, mutex, extents); } - emitter_json_dict_end(&emitter); /* Closes the "jemalloc" dict. */ + emitter_json_object_end(&emitter); /* Closes the "jemalloc" dict. */ emitter_table_printf(&emitter, "--- End jemalloc statistics ---\n"); emitter_end(&emitter); } Index: head/contrib/jemalloc/src/sz.c =================================================================== --- head/contrib/jemalloc/src/sz.c (revision 360232) +++ head/contrib/jemalloc/src/sz.c (revision 360233) @@ -1,107 +1,64 @@ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/sz.h" JEMALLOC_ALIGNED(CACHELINE) -const size_t sz_pind2sz_tab[NPSIZES+1] = { -#define PSZ_yes(lg_grp, ndelta, lg_delta) \ - (((ZU(1)<sc[i]; + if (sc->psz) { + sz_pind2sz_tab[pind] = (ZU(1) << sc->lg_base) + + (ZU(sc->ndelta) << sc->lg_delta); + pind++; + } + } + for (int i = pind; i <= (int)SC_NPSIZES; i++) { + sz_pind2sz_tab[pind] = sc_data->large_maxclass + PAGE; + } +} + JEMALLOC_ALIGNED(CACHELINE) -const size_t sz_index2size_tab[NSIZES] = { -#define SC(index, lg_grp, lg_delta, ndelta, psz, bin, pgs, lg_delta_lookup) \ - ((ZU(1)<sc[i]; + sz_index2size_tab[i] = (ZU(1) << sc->lg_base) + + (ZU(sc->ndelta) << (sc->lg_delta)); + } +} + +/* + * To keep this table small, we divide sizes by the tiny min size, which gives + * the smallest interval for which the result can change. + */ JEMALLOC_ALIGNED(CACHELINE) -const uint8_t sz_size2index_tab[] = { -#if LG_TINY_MIN == 0 -/* The div module doesn't support division by 1. */ -#error "Unsupported LG_TINY_MIN" -#define S2B_0(i) i, -#elif LG_TINY_MIN == 1 -#warning "Dangerous LG_TINY_MIN" -#define S2B_1(i) i, -#elif LG_TINY_MIN == 2 -#warning "Dangerous LG_TINY_MIN" -#define S2B_2(i) i, -#elif LG_TINY_MIN == 3 -#define S2B_3(i) i, -#elif LG_TINY_MIN == 4 -#define S2B_4(i) i, -#elif LG_TINY_MIN == 5 -#define S2B_5(i) i, -#elif LG_TINY_MIN == 6 -#define S2B_6(i) i, -#elif LG_TINY_MIN == 7 -#define S2B_7(i) i, -#elif LG_TINY_MIN == 8 -#define S2B_8(i) i, -#elif LG_TINY_MIN == 9 -#define S2B_9(i) i, -#elif LG_TINY_MIN == 10 -#define S2B_10(i) i, -#elif LG_TINY_MIN == 11 -#define S2B_11(i) i, -#else -#error "Unsupported LG_TINY_MIN" -#endif -#if LG_TINY_MIN < 1 -#define S2B_1(i) S2B_0(i) S2B_0(i) -#endif -#if LG_TINY_MIN < 2 -#define S2B_2(i) S2B_1(i) S2B_1(i) -#endif -#if LG_TINY_MIN < 3 -#define S2B_3(i) S2B_2(i) S2B_2(i) -#endif -#if LG_TINY_MIN < 4 -#define S2B_4(i) S2B_3(i) S2B_3(i) -#endif -#if LG_TINY_MIN < 5 -#define S2B_5(i) S2B_4(i) S2B_4(i) -#endif -#if LG_TINY_MIN < 6 -#define S2B_6(i) S2B_5(i) S2B_5(i) -#endif -#if LG_TINY_MIN < 7 -#define S2B_7(i) S2B_6(i) S2B_6(i) -#endif -#if LG_TINY_MIN < 8 -#define S2B_8(i) S2B_7(i) S2B_7(i) -#endif -#if LG_TINY_MIN < 9 -#define S2B_9(i) S2B_8(i) S2B_8(i) -#endif -#if LG_TINY_MIN < 10 -#define S2B_10(i) S2B_9(i) S2B_9(i) -#endif -#if LG_TINY_MIN < 11 -#define S2B_11(i) S2B_10(i) S2B_10(i) -#endif -#define S2B_no(i) -#define SC(index, lg_grp, lg_delta, ndelta, psz, bin, pgs, lg_delta_lookup) \ - S2B_##lg_delta_lookup(index) - SIZE_CLASSES -#undef S2B_3 -#undef S2B_4 -#undef S2B_5 -#undef S2B_6 -#undef S2B_7 -#undef S2B_8 -#undef S2B_9 -#undef S2B_10 -#undef S2B_11 -#undef S2B_no -#undef SC -}; +uint8_t sz_size2index_tab[(SC_LOOKUP_MAXCLASS >> SC_LG_TINY_MIN) + 1]; + +static void +sz_boot_size2index_tab(const sc_data_t *sc_data) { + size_t dst_max = (SC_LOOKUP_MAXCLASS >> SC_LG_TINY_MIN) + 1; + size_t dst_ind = 0; + for (unsigned sc_ind = 0; sc_ind < SC_NSIZES && dst_ind < dst_max; + sc_ind++) { + const sc_t *sc = &sc_data->sc[sc_ind]; + size_t sz = (ZU(1) << sc->lg_base) + + (ZU(sc->ndelta) << sc->lg_delta); + size_t max_ind = ((sz + (ZU(1) << SC_LG_TINY_MIN) - 1) + >> SC_LG_TINY_MIN); + for (; dst_ind <= max_ind && dst_ind < dst_max; dst_ind++) { + sz_size2index_tab[dst_ind] = sc_ind; + } + } +} + +void +sz_boot(const sc_data_t *sc_data) { + sz_boot_pind2sz_tab(sc_data); + sz_boot_index2size_tab(sc_data); + sz_boot_size2index_tab(sc_data); +} Index: head/contrib/jemalloc/src/tcache.c =================================================================== --- head/contrib/jemalloc/src/tcache.c (revision 360232) +++ head/contrib/jemalloc/src/tcache.c (revision 360233) @@ -1,717 +1,798 @@ #define JEMALLOC_TCACHE_C_ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/jemalloc_internal_includes.h" #include "jemalloc/internal/assert.h" #include "jemalloc/internal/mutex.h" -#include "jemalloc/internal/size_classes.h" +#include "jemalloc/internal/safety_check.h" +#include "jemalloc/internal/sc.h" /******************************************************************************/ /* Data. */ bool opt_tcache = true; ssize_t opt_lg_tcache_max = LG_TCACHE_MAXCLASS_DEFAULT; cache_bin_info_t *tcache_bin_info; static unsigned stack_nelms; /* Total stack elms per tcache. */ unsigned nhbins; size_t tcache_maxclass; tcaches_t *tcaches; /* Index of first element within tcaches that has never been used. */ static unsigned tcaches_past; /* Head of singly linked list tracking available tcaches elements. */ static tcaches_t *tcaches_avail; /* Protects tcaches{,_past,_avail}. */ static malloc_mutex_t tcaches_mtx; /******************************************************************************/ size_t tcache_salloc(tsdn_t *tsdn, const void *ptr) { return arena_salloc(tsdn, ptr); } void tcache_event_hard(tsd_t *tsd, tcache_t *tcache) { szind_t binind = tcache->next_gc_bin; cache_bin_t *tbin; - if (binind < NBINS) { + if (binind < SC_NBINS) { tbin = tcache_small_bin_get(tcache, binind); } else { tbin = tcache_large_bin_get(tcache, binind); } if (tbin->low_water > 0) { /* * Flush (ceiling) 3/4 of the objects below the low water mark. */ - if (binind < NBINS) { + if (binind < SC_NBINS) { tcache_bin_flush_small(tsd, tcache, tbin, binind, tbin->ncached - tbin->low_water + (tbin->low_water >> 2)); /* * Reduce fill count by 2X. Limit lg_fill_div such that * the fill count is always at least 1. */ cache_bin_info_t *tbin_info = &tcache_bin_info[binind]; if ((tbin_info->ncached_max >> (tcache->lg_fill_div[binind] + 1)) >= 1) { tcache->lg_fill_div[binind]++; } } else { tcache_bin_flush_large(tsd, tbin, binind, tbin->ncached - tbin->low_water + (tbin->low_water >> 2), tcache); } } else if (tbin->low_water < 0) { /* * Increase fill count by 2X for small bins. Make sure * lg_fill_div stays greater than 0. */ - if (binind < NBINS && tcache->lg_fill_div[binind] > 1) { + if (binind < SC_NBINS && tcache->lg_fill_div[binind] > 1) { tcache->lg_fill_div[binind]--; } } tbin->low_water = tbin->ncached; tcache->next_gc_bin++; if (tcache->next_gc_bin == nhbins) { tcache->next_gc_bin = 0; } } void * tcache_alloc_small_hard(tsdn_t *tsdn, arena_t *arena, tcache_t *tcache, cache_bin_t *tbin, szind_t binind, bool *tcache_success) { void *ret; assert(tcache->arena != NULL); arena_tcache_fill_small(tsdn, arena, tcache, tbin, binind, config_prof ? tcache->prof_accumbytes : 0); if (config_prof) { tcache->prof_accumbytes = 0; } ret = cache_bin_alloc_easy(tbin, tcache_success); return ret; } +/* Enabled with --enable-extra-size-check. */ +static void +tbin_extents_lookup_size_check(tsdn_t *tsdn, cache_bin_t *tbin, szind_t binind, + size_t nflush, extent_t **extents){ + rtree_ctx_t rtree_ctx_fallback; + rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback); + + /* + * Verify that the items in the tcache all have the correct size; this + * is useful for catching sized deallocation bugs, also to fail early + * instead of corrupting metadata. Since this can be turned on for opt + * builds, avoid the branch in the loop. + */ + szind_t szind; + size_t sz_sum = binind * nflush; + for (unsigned i = 0 ; i < nflush; i++) { + rtree_extent_szind_read(tsdn, &extents_rtree, + rtree_ctx, (uintptr_t)*(tbin->avail - 1 - i), true, + &extents[i], &szind); + sz_sum -= szind; + } + if (sz_sum != 0) { + safety_check_fail(": size mismatch in thread cache " + "detected, likely caused by sized deallocation bugs by " + "application. Abort.\n"); + abort(); + } +} + void tcache_bin_flush_small(tsd_t *tsd, tcache_t *tcache, cache_bin_t *tbin, szind_t binind, unsigned rem) { bool merged_stats = false; - assert(binind < NBINS); + assert(binind < SC_NBINS); assert((cache_bin_sz_t)rem <= tbin->ncached); arena_t *arena = tcache->arena; assert(arena != NULL); unsigned nflush = tbin->ncached - rem; VARIABLE_ARRAY(extent_t *, item_extent, nflush); + /* Look up extent once per item. */ - for (unsigned i = 0 ; i < nflush; i++) { - item_extent[i] = iealloc(tsd_tsdn(tsd), *(tbin->avail - 1 - i)); + if (config_opt_safety_checks) { + tbin_extents_lookup_size_check(tsd_tsdn(tsd), tbin, binind, + nflush, item_extent); + } else { + for (unsigned i = 0 ; i < nflush; i++) { + item_extent[i] = iealloc(tsd_tsdn(tsd), + *(tbin->avail - 1 - i)); + } } - while (nflush > 0) { /* Lock the arena bin associated with the first object. */ extent_t *extent = item_extent[0]; - arena_t *bin_arena = extent_arena_get(extent); - bin_t *bin = &bin_arena->bins[binind]; + unsigned bin_arena_ind = extent_arena_ind_get(extent); + arena_t *bin_arena = arena_get(tsd_tsdn(tsd), bin_arena_ind, + false); + unsigned binshard = extent_binshard_get(extent); + assert(binshard < bin_infos[binind].n_shards); + bin_t *bin = &bin_arena->bins[binind].bin_shards[binshard]; if (config_prof && bin_arena == arena) { if (arena_prof_accum(tsd_tsdn(tsd), arena, tcache->prof_accumbytes)) { prof_idump(tsd_tsdn(tsd)); } tcache->prof_accumbytes = 0; } malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock); - if (config_stats && bin_arena == arena) { - assert(!merged_stats); + if (config_stats && bin_arena == arena && !merged_stats) { merged_stats = true; bin->stats.nflushes++; bin->stats.nrequests += tbin->tstats.nrequests; tbin->tstats.nrequests = 0; } unsigned ndeferred = 0; for (unsigned i = 0; i < nflush; i++) { void *ptr = *(tbin->avail - 1 - i); extent = item_extent[i]; assert(ptr != NULL && extent != NULL); - if (extent_arena_get(extent) == bin_arena) { + if (extent_arena_ind_get(extent) == bin_arena_ind + && extent_binshard_get(extent) == binshard) { arena_dalloc_bin_junked_locked(tsd_tsdn(tsd), - bin_arena, extent, ptr); + bin_arena, bin, binind, extent, ptr); } else { /* * This object was allocated via a different * arena bin than the one that is currently * locked. Stash the object, so that it can be * handled in a future pass. */ *(tbin->avail - 1 - ndeferred) = ptr; item_extent[ndeferred] = extent; ndeferred++; } } malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock); arena_decay_ticks(tsd_tsdn(tsd), bin_arena, nflush - ndeferred); nflush = ndeferred; } if (config_stats && !merged_stats) { /* * The flush loop didn't happen to flush to this thread's * arena, so the stats didn't get merged. Manually do so now. */ - bin_t *bin = &arena->bins[binind]; - malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock); + unsigned binshard; + bin_t *bin = arena_bin_choose_lock(tsd_tsdn(tsd), arena, binind, + &binshard); bin->stats.nflushes++; bin->stats.nrequests += tbin->tstats.nrequests; tbin->tstats.nrequests = 0; malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock); } memmove(tbin->avail - rem, tbin->avail - tbin->ncached, rem * sizeof(void *)); tbin->ncached = rem; if (tbin->ncached < tbin->low_water) { tbin->low_water = tbin->ncached; } } void tcache_bin_flush_large(tsd_t *tsd, cache_bin_t *tbin, szind_t binind, unsigned rem, tcache_t *tcache) { bool merged_stats = false; assert(binind < nhbins); assert((cache_bin_sz_t)rem <= tbin->ncached); - arena_t *arena = tcache->arena; - assert(arena != NULL); + arena_t *tcache_arena = tcache->arena; + assert(tcache_arena != NULL); unsigned nflush = tbin->ncached - rem; VARIABLE_ARRAY(extent_t *, item_extent, nflush); + +#ifndef JEMALLOC_EXTRA_SIZE_CHECK /* Look up extent once per item. */ for (unsigned i = 0 ; i < nflush; i++) { item_extent[i] = iealloc(tsd_tsdn(tsd), *(tbin->avail - 1 - i)); } - +#else + tbin_extents_lookup_size_check(tsd_tsdn(tsd), tbin, binind, nflush, + item_extent); +#endif while (nflush > 0) { /* Lock the arena associated with the first object. */ extent_t *extent = item_extent[0]; - arena_t *locked_arena = extent_arena_get(extent); - UNUSED bool idump; + unsigned locked_arena_ind = extent_arena_ind_get(extent); + arena_t *locked_arena = arena_get(tsd_tsdn(tsd), + locked_arena_ind, false); + bool idump; if (config_prof) { idump = false; } - malloc_mutex_lock(tsd_tsdn(tsd), &locked_arena->large_mtx); + bool lock_large = !arena_is_auto(locked_arena); + if (lock_large) { + malloc_mutex_lock(tsd_tsdn(tsd), &locked_arena->large_mtx); + } for (unsigned i = 0; i < nflush; i++) { void *ptr = *(tbin->avail - 1 - i); assert(ptr != NULL); extent = item_extent[i]; - if (extent_arena_get(extent) == locked_arena) { + if (extent_arena_ind_get(extent) == locked_arena_ind) { large_dalloc_prep_junked_locked(tsd_tsdn(tsd), extent); } } - if ((config_prof || config_stats) && locked_arena == arena) { + if ((config_prof || config_stats) && + (locked_arena == tcache_arena)) { if (config_prof) { - idump = arena_prof_accum(tsd_tsdn(tsd), arena, - tcache->prof_accumbytes); + idump = arena_prof_accum(tsd_tsdn(tsd), + tcache_arena, tcache->prof_accumbytes); tcache->prof_accumbytes = 0; } if (config_stats) { merged_stats = true; - arena_stats_large_nrequests_add(tsd_tsdn(tsd), - &arena->stats, binind, + arena_stats_large_flush_nrequests_add( + tsd_tsdn(tsd), &tcache_arena->stats, binind, tbin->tstats.nrequests); tbin->tstats.nrequests = 0; } } - malloc_mutex_unlock(tsd_tsdn(tsd), &locked_arena->large_mtx); + if (lock_large) { + malloc_mutex_unlock(tsd_tsdn(tsd), &locked_arena->large_mtx); + } unsigned ndeferred = 0; for (unsigned i = 0; i < nflush; i++) { void *ptr = *(tbin->avail - 1 - i); extent = item_extent[i]; assert(ptr != NULL && extent != NULL); - if (extent_arena_get(extent) == locked_arena) { + if (extent_arena_ind_get(extent) == locked_arena_ind) { large_dalloc_finish(tsd_tsdn(tsd), extent); } else { /* * This object was allocated via a different * arena than the one that is currently locked. * Stash the object, so that it can be handled * in a future pass. */ *(tbin->avail - 1 - ndeferred) = ptr; item_extent[ndeferred] = extent; ndeferred++; } } if (config_prof && idump) { prof_idump(tsd_tsdn(tsd)); } arena_decay_ticks(tsd_tsdn(tsd), locked_arena, nflush - ndeferred); nflush = ndeferred; } if (config_stats && !merged_stats) { /* * The flush loop didn't happen to flush to this thread's * arena, so the stats didn't get merged. Manually do so now. */ - arena_stats_large_nrequests_add(tsd_tsdn(tsd), &arena->stats, - binind, tbin->tstats.nrequests); + arena_stats_large_flush_nrequests_add(tsd_tsdn(tsd), + &tcache_arena->stats, binind, tbin->tstats.nrequests); tbin->tstats.nrequests = 0; } memmove(tbin->avail - rem, tbin->avail - tbin->ncached, rem * sizeof(void *)); tbin->ncached = rem; if (tbin->ncached < tbin->low_water) { tbin->low_water = tbin->ncached; } } void tcache_arena_associate(tsdn_t *tsdn, tcache_t *tcache, arena_t *arena) { assert(tcache->arena == NULL); tcache->arena = arena; if (config_stats) { /* Link into list of extant tcaches. */ malloc_mutex_lock(tsdn, &arena->tcache_ql_mtx); ql_elm_new(tcache, link); ql_tail_insert(&arena->tcache_ql, tcache, link); cache_bin_array_descriptor_init( &tcache->cache_bin_array_descriptor, tcache->bins_small, tcache->bins_large); ql_tail_insert(&arena->cache_bin_array_descriptor_ql, &tcache->cache_bin_array_descriptor, link); malloc_mutex_unlock(tsdn, &arena->tcache_ql_mtx); } } static void tcache_arena_dissociate(tsdn_t *tsdn, tcache_t *tcache) { arena_t *arena = tcache->arena; assert(arena != NULL); if (config_stats) { /* Unlink from list of extant tcaches. */ malloc_mutex_lock(tsdn, &arena->tcache_ql_mtx); if (config_debug) { bool in_ql = false; tcache_t *iter; ql_foreach(iter, &arena->tcache_ql, link) { if (iter == tcache) { in_ql = true; break; } } assert(in_ql); } ql_remove(&arena->tcache_ql, tcache, link); ql_remove(&arena->cache_bin_array_descriptor_ql, &tcache->cache_bin_array_descriptor, link); tcache_stats_merge(tsdn, tcache, arena); malloc_mutex_unlock(tsdn, &arena->tcache_ql_mtx); } tcache->arena = NULL; } void tcache_arena_reassociate(tsdn_t *tsdn, tcache_t *tcache, arena_t *arena) { tcache_arena_dissociate(tsdn, tcache); tcache_arena_associate(tsdn, tcache, arena); } bool tsd_tcache_enabled_data_init(tsd_t *tsd) { /* Called upon tsd initialization. */ tsd_tcache_enabled_set(tsd, opt_tcache); tsd_slow_update(tsd); if (opt_tcache) { /* Trigger tcache init. */ tsd_tcache_data_init(tsd); } return false; } /* Initialize auto tcache (embedded in TSD). */ static void tcache_init(tsd_t *tsd, tcache_t *tcache, void *avail_stack) { memset(&tcache->link, 0, sizeof(ql_elm(tcache_t))); tcache->prof_accumbytes = 0; tcache->next_gc_bin = 0; tcache->arena = NULL; ticker_init(&tcache->gc_ticker, TCACHE_GC_INCR); size_t stack_offset = 0; assert((TCACHE_NSLOTS_SMALL_MAX & 1U) == 0); - memset(tcache->bins_small, 0, sizeof(cache_bin_t) * NBINS); - memset(tcache->bins_large, 0, sizeof(cache_bin_t) * (nhbins - NBINS)); + memset(tcache->bins_small, 0, sizeof(cache_bin_t) * SC_NBINS); + memset(tcache->bins_large, 0, sizeof(cache_bin_t) * (nhbins - SC_NBINS)); unsigned i = 0; - for (; i < NBINS; i++) { + for (; i < SC_NBINS; i++) { tcache->lg_fill_div[i] = 1; stack_offset += tcache_bin_info[i].ncached_max * sizeof(void *); /* * avail points past the available space. Allocations will * access the slots toward higher addresses (for the benefit of * prefetch). */ tcache_small_bin_get(tcache, i)->avail = (void **)((uintptr_t)avail_stack + (uintptr_t)stack_offset); } for (; i < nhbins; i++) { stack_offset += tcache_bin_info[i].ncached_max * sizeof(void *); tcache_large_bin_get(tcache, i)->avail = (void **)((uintptr_t)avail_stack + (uintptr_t)stack_offset); } assert(stack_offset == stack_nelms * sizeof(void *)); } /* Initialize auto tcache (embedded in TSD). */ bool tsd_tcache_data_init(tsd_t *tsd) { tcache_t *tcache = tsd_tcachep_get_unsafe(tsd); assert(tcache_small_bin_get(tcache, 0)->avail == NULL); size_t size = stack_nelms * sizeof(void *); /* Avoid false cacheline sharing. */ size = sz_sa2u(size, CACHELINE); void *avail_array = ipallocztm(tsd_tsdn(tsd), size, CACHELINE, true, NULL, true, arena_get(TSDN_NULL, 0, true)); if (avail_array == NULL) { return true; } tcache_init(tsd, tcache, avail_array); /* * Initialization is a bit tricky here. After malloc init is done, all * threads can rely on arena_choose and associate tcache accordingly. * However, the thread that does actual malloc bootstrapping relies on * functional tsd, and it can only rely on a0. In that case, we * associate its tcache to a0 temporarily, and later on * arena_choose_hard() will re-associate properly. */ tcache->arena = NULL; arena_t *arena; if (!malloc_initialized()) { /* If in initialization, assign to a0. */ arena = arena_get(tsd_tsdn(tsd), 0, false); tcache_arena_associate(tsd_tsdn(tsd), tcache, arena); } else { arena = arena_choose(tsd, NULL); /* This may happen if thread.tcache.enabled is used. */ if (tcache->arena == NULL) { tcache_arena_associate(tsd_tsdn(tsd), tcache, arena); } } assert(arena == tcache->arena); return false; } /* Created manual tcache for tcache.create mallctl. */ tcache_t * tcache_create_explicit(tsd_t *tsd) { tcache_t *tcache; size_t size, stack_offset; size = sizeof(tcache_t); /* Naturally align the pointer stacks. */ size = PTR_CEILING(size); stack_offset = size; size += stack_nelms * sizeof(void *); /* Avoid false cacheline sharing. */ size = sz_sa2u(size, CACHELINE); tcache = ipallocztm(tsd_tsdn(tsd), size, CACHELINE, true, NULL, true, arena_get(TSDN_NULL, 0, true)); if (tcache == NULL) { return NULL; } tcache_init(tsd, tcache, (void *)((uintptr_t)tcache + (uintptr_t)stack_offset)); tcache_arena_associate(tsd_tsdn(tsd), tcache, arena_ichoose(tsd, NULL)); return tcache; } static void tcache_flush_cache(tsd_t *tsd, tcache_t *tcache) { assert(tcache->arena != NULL); - for (unsigned i = 0; i < NBINS; i++) { + for (unsigned i = 0; i < SC_NBINS; i++) { cache_bin_t *tbin = tcache_small_bin_get(tcache, i); tcache_bin_flush_small(tsd, tcache, tbin, i, 0); if (config_stats) { assert(tbin->tstats.nrequests == 0); } } - for (unsigned i = NBINS; i < nhbins; i++) { + for (unsigned i = SC_NBINS; i < nhbins; i++) { cache_bin_t *tbin = tcache_large_bin_get(tcache, i); tcache_bin_flush_large(tsd, tbin, i, 0, tcache); if (config_stats) { assert(tbin->tstats.nrequests == 0); } } if (config_prof && tcache->prof_accumbytes > 0 && arena_prof_accum(tsd_tsdn(tsd), tcache->arena, tcache->prof_accumbytes)) { prof_idump(tsd_tsdn(tsd)); } } void tcache_flush(tsd_t *tsd) { assert(tcache_available(tsd)); tcache_flush_cache(tsd, tsd_tcachep_get(tsd)); } static void tcache_destroy(tsd_t *tsd, tcache_t *tcache, bool tsd_tcache) { tcache_flush_cache(tsd, tcache); + arena_t *arena = tcache->arena; tcache_arena_dissociate(tsd_tsdn(tsd), tcache); if (tsd_tcache) { /* Release the avail array for the TSD embedded auto tcache. */ void *avail_array = (void *)((uintptr_t)tcache_small_bin_get(tcache, 0)->avail - (uintptr_t)tcache_bin_info[0].ncached_max * sizeof(void *)); idalloctm(tsd_tsdn(tsd), avail_array, NULL, NULL, true, true); } else { /* Release both the tcache struct and avail array. */ idalloctm(tsd_tsdn(tsd), tcache, NULL, NULL, true, true); } + + /* + * The deallocation and tcache flush above may not trigger decay since + * we are on the tcache shutdown path (potentially with non-nominal + * tsd). Manually trigger decay to avoid pathological cases. Also + * include arena 0 because the tcache array is allocated from it. + */ + arena_decay(tsd_tsdn(tsd), arena_get(tsd_tsdn(tsd), 0, false), + false, false); + + if (arena_nthreads_get(arena, false) == 0 && + !background_thread_enabled()) { + /* Force purging when no threads assigned to the arena anymore. */ + arena_decay(tsd_tsdn(tsd), arena, false, true); + } else { + arena_decay(tsd_tsdn(tsd), arena, false, false); + } } /* For auto tcache (embedded in TSD) only. */ void tcache_cleanup(tsd_t *tsd) { tcache_t *tcache = tsd_tcachep_get(tsd); if (!tcache_available(tsd)) { assert(tsd_tcache_enabled_get(tsd) == false); if (config_debug) { assert(tcache_small_bin_get(tcache, 0)->avail == NULL); } return; } assert(tsd_tcache_enabled_get(tsd)); assert(tcache_small_bin_get(tcache, 0)->avail != NULL); tcache_destroy(tsd, tcache, true); if (config_debug) { tcache_small_bin_get(tcache, 0)->avail = NULL; } } void tcache_stats_merge(tsdn_t *tsdn, tcache_t *tcache, arena_t *arena) { unsigned i; cassert(config_stats); /* Merge and reset tcache stats. */ - for (i = 0; i < NBINS; i++) { - bin_t *bin = &arena->bins[i]; + for (i = 0; i < SC_NBINS; i++) { cache_bin_t *tbin = tcache_small_bin_get(tcache, i); - malloc_mutex_lock(tsdn, &bin->lock); + unsigned binshard; + bin_t *bin = arena_bin_choose_lock(tsdn, arena, i, &binshard); bin->stats.nrequests += tbin->tstats.nrequests; malloc_mutex_unlock(tsdn, &bin->lock); tbin->tstats.nrequests = 0; } for (; i < nhbins; i++) { cache_bin_t *tbin = tcache_large_bin_get(tcache, i); - arena_stats_large_nrequests_add(tsdn, &arena->stats, i, + arena_stats_large_flush_nrequests_add(tsdn, &arena->stats, i, tbin->tstats.nrequests); tbin->tstats.nrequests = 0; } } static bool tcaches_create_prep(tsd_t *tsd) { bool err; malloc_mutex_lock(tsd_tsdn(tsd), &tcaches_mtx); if (tcaches == NULL) { tcaches = base_alloc(tsd_tsdn(tsd), b0get(), sizeof(tcache_t *) * (MALLOCX_TCACHE_MAX+1), CACHELINE); if (tcaches == NULL) { err = true; goto label_return; } } if (tcaches_avail == NULL && tcaches_past > MALLOCX_TCACHE_MAX) { err = true; goto label_return; } err = false; label_return: malloc_mutex_unlock(tsd_tsdn(tsd), &tcaches_mtx); return err; } bool tcaches_create(tsd_t *tsd, unsigned *r_ind) { witness_assert_depth(tsdn_witness_tsdp_get(tsd_tsdn(tsd)), 0); bool err; if (tcaches_create_prep(tsd)) { err = true; goto label_return; } tcache_t *tcache = tcache_create_explicit(tsd); if (tcache == NULL) { err = true; goto label_return; } tcaches_t *elm; malloc_mutex_lock(tsd_tsdn(tsd), &tcaches_mtx); if (tcaches_avail != NULL) { elm = tcaches_avail; tcaches_avail = tcaches_avail->next; elm->tcache = tcache; *r_ind = (unsigned)(elm - tcaches); } else { elm = &tcaches[tcaches_past]; elm->tcache = tcache; *r_ind = tcaches_past; tcaches_past++; } malloc_mutex_unlock(tsd_tsdn(tsd), &tcaches_mtx); err = false; label_return: witness_assert_depth(tsdn_witness_tsdp_get(tsd_tsdn(tsd)), 0); return err; } static tcache_t * -tcaches_elm_remove(tsd_t *tsd, tcaches_t *elm) { +tcaches_elm_remove(tsd_t *tsd, tcaches_t *elm, bool allow_reinit) { malloc_mutex_assert_owner(tsd_tsdn(tsd), &tcaches_mtx); if (elm->tcache == NULL) { return NULL; } tcache_t *tcache = elm->tcache; - elm->tcache = NULL; + if (allow_reinit) { + elm->tcache = TCACHES_ELM_NEED_REINIT; + } else { + elm->tcache = NULL; + } + + if (tcache == TCACHES_ELM_NEED_REINIT) { + return NULL; + } return tcache; } void tcaches_flush(tsd_t *tsd, unsigned ind) { malloc_mutex_lock(tsd_tsdn(tsd), &tcaches_mtx); - tcache_t *tcache = tcaches_elm_remove(tsd, &tcaches[ind]); + tcache_t *tcache = tcaches_elm_remove(tsd, &tcaches[ind], true); malloc_mutex_unlock(tsd_tsdn(tsd), &tcaches_mtx); if (tcache != NULL) { + /* Destroy the tcache; recreate in tcaches_get() if needed. */ tcache_destroy(tsd, tcache, false); } } void tcaches_destroy(tsd_t *tsd, unsigned ind) { malloc_mutex_lock(tsd_tsdn(tsd), &tcaches_mtx); tcaches_t *elm = &tcaches[ind]; - tcache_t *tcache = tcaches_elm_remove(tsd, elm); + tcache_t *tcache = tcaches_elm_remove(tsd, elm, false); elm->next = tcaches_avail; tcaches_avail = elm; malloc_mutex_unlock(tsd_tsdn(tsd), &tcaches_mtx); if (tcache != NULL) { tcache_destroy(tsd, tcache, false); } } bool tcache_boot(tsdn_t *tsdn) { /* If necessary, clamp opt_lg_tcache_max. */ if (opt_lg_tcache_max < 0 || (ZU(1) << opt_lg_tcache_max) < - SMALL_MAXCLASS) { - tcache_maxclass = SMALL_MAXCLASS; + SC_SMALL_MAXCLASS) { + tcache_maxclass = SC_SMALL_MAXCLASS; } else { tcache_maxclass = (ZU(1) << opt_lg_tcache_max); } if (malloc_mutex_init(&tcaches_mtx, "tcaches", WITNESS_RANK_TCACHES, malloc_mutex_rank_exclusive)) { return true; } nhbins = sz_size2index(tcache_maxclass) + 1; /* Initialize tcache_bin_info. */ tcache_bin_info = (cache_bin_info_t *)base_alloc(tsdn, b0get(), nhbins * sizeof(cache_bin_info_t), CACHELINE); if (tcache_bin_info == NULL) { return true; } stack_nelms = 0; unsigned i; - for (i = 0; i < NBINS; i++) { + for (i = 0; i < SC_NBINS; i++) { if ((bin_infos[i].nregs << 1) <= TCACHE_NSLOTS_SMALL_MIN) { tcache_bin_info[i].ncached_max = TCACHE_NSLOTS_SMALL_MIN; } else if ((bin_infos[i].nregs << 1) <= TCACHE_NSLOTS_SMALL_MAX) { tcache_bin_info[i].ncached_max = (bin_infos[i].nregs << 1); } else { tcache_bin_info[i].ncached_max = TCACHE_NSLOTS_SMALL_MAX; } stack_nelms += tcache_bin_info[i].ncached_max; } for (; i < nhbins; i++) { tcache_bin_info[i].ncached_max = TCACHE_NSLOTS_LARGE; stack_nelms += tcache_bin_info[i].ncached_max; } return false; } void tcache_prefork(tsdn_t *tsdn) { if (!config_prof && opt_tcache) { malloc_mutex_prefork(tsdn, &tcaches_mtx); } } void tcache_postfork_parent(tsdn_t *tsdn) { if (!config_prof && opt_tcache) { malloc_mutex_postfork_parent(tsdn, &tcaches_mtx); } } void tcache_postfork_child(tsdn_t *tsdn) { if (!config_prof && opt_tcache) { malloc_mutex_postfork_child(tsdn, &tcaches_mtx); } } Index: head/contrib/jemalloc/src/test_hooks.c =================================================================== --- head/contrib/jemalloc/src/test_hooks.c (nonexistent) +++ head/contrib/jemalloc/src/test_hooks.c (revision 360233) @@ -0,0 +1,12 @@ +#include "jemalloc/internal/jemalloc_preamble.h" + +/* + * The hooks are a little bit screwy -- they're not genuinely exported in the + * sense that we want them available to end-users, but we do want them visible + * from outside the generated library, so that we can use them in test code. + */ +JEMALLOC_EXPORT +void (*test_hooks_arena_new_hook)() = NULL; + +JEMALLOC_EXPORT +void (*test_hooks_libc_hook)() = NULL; Property changes on: head/contrib/jemalloc/src/test_hooks.c ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/jemalloc/src/tsd.c =================================================================== --- head/contrib/jemalloc/src/tsd.c (revision 360232) +++ head/contrib/jemalloc/src/tsd.c (revision 360233) @@ -1,351 +1,534 @@ #define JEMALLOC_TSD_C_ #include "jemalloc/internal/jemalloc_preamble.h" #include "jemalloc/internal/jemalloc_internal_includes.h" #include "jemalloc/internal/assert.h" #include "jemalloc/internal/mutex.h" #include "jemalloc/internal/rtree.h" /******************************************************************************/ /* Data. */ static unsigned ncleanups; static malloc_tsd_cleanup_t cleanups[MALLOC_TSD_CLEANUPS_MAX]; +/* TSD_INITIALIZER triggers "-Wmissing-field-initializer" */ +JEMALLOC_DIAGNOSTIC_PUSH +JEMALLOC_DIAGNOSTIC_IGNORE_MISSING_STRUCT_FIELD_INITIALIZERS + #ifdef JEMALLOC_MALLOC_THREAD_CLEANUP -__thread tsd_t JEMALLOC_TLS_MODEL tsd_tls = TSD_INITIALIZER; -__thread bool JEMALLOC_TLS_MODEL tsd_initialized = false; +JEMALLOC_TSD_TYPE_ATTR(tsd_t) tsd_tls = TSD_INITIALIZER; +JEMALLOC_TSD_TYPE_ATTR(bool) JEMALLOC_TLS_MODEL tsd_initialized = false; bool tsd_booted = false; #elif (defined(JEMALLOC_TLS)) -__thread tsd_t JEMALLOC_TLS_MODEL tsd_tls = TSD_INITIALIZER; +JEMALLOC_TSD_TYPE_ATTR(tsd_t) tsd_tls = TSD_INITIALIZER; pthread_key_t tsd_tsd; bool tsd_booted = false; #elif (defined(_WIN32)) DWORD tsd_tsd; tsd_wrapper_t tsd_boot_wrapper = {false, TSD_INITIALIZER}; bool tsd_booted = false; #else /* * This contains a mutex, but it's pretty convenient to allow the mutex code to * have a dependency on tsd. So we define the struct here, and only refer to it * by pointer in the header. */ struct tsd_init_head_s { ql_head(tsd_init_block_t) blocks; malloc_mutex_t lock; }; pthread_key_t tsd_tsd; tsd_init_head_t tsd_init_head = { ql_head_initializer(blocks), MALLOC_MUTEX_INITIALIZER }; + tsd_wrapper_t tsd_boot_wrapper = { false, TSD_INITIALIZER }; bool tsd_booted = false; #endif +JEMALLOC_DIAGNOSTIC_POP /******************************************************************************/ +/* A list of all the tsds in the nominal state. */ +typedef ql_head(tsd_t) tsd_list_t; +static tsd_list_t tsd_nominal_tsds = ql_head_initializer(tsd_nominal_tsds); +static malloc_mutex_t tsd_nominal_tsds_lock; + +/* How many slow-path-enabling features are turned on. */ +static atomic_u32_t tsd_global_slow_count = ATOMIC_INIT(0); + +static bool +tsd_in_nominal_list(tsd_t *tsd) { + tsd_t *tsd_list; + bool found = false; + /* + * We don't know that tsd is nominal; it might not be safe to get data + * out of it here. + */ + malloc_mutex_lock(TSDN_NULL, &tsd_nominal_tsds_lock); + ql_foreach(tsd_list, &tsd_nominal_tsds, TSD_MANGLE(tcache).tsd_link) { + if (tsd == tsd_list) { + found = true; + break; + } + } + malloc_mutex_unlock(TSDN_NULL, &tsd_nominal_tsds_lock); + return found; +} + +static void +tsd_add_nominal(tsd_t *tsd) { + assert(!tsd_in_nominal_list(tsd)); + assert(tsd_state_get(tsd) <= tsd_state_nominal_max); + ql_elm_new(tsd, TSD_MANGLE(tcache).tsd_link); + malloc_mutex_lock(tsd_tsdn(tsd), &tsd_nominal_tsds_lock); + ql_tail_insert(&tsd_nominal_tsds, tsd, TSD_MANGLE(tcache).tsd_link); + malloc_mutex_unlock(tsd_tsdn(tsd), &tsd_nominal_tsds_lock); +} + +static void +tsd_remove_nominal(tsd_t *tsd) { + assert(tsd_in_nominal_list(tsd)); + assert(tsd_state_get(tsd) <= tsd_state_nominal_max); + malloc_mutex_lock(tsd_tsdn(tsd), &tsd_nominal_tsds_lock); + ql_remove(&tsd_nominal_tsds, tsd, TSD_MANGLE(tcache).tsd_link); + malloc_mutex_unlock(tsd_tsdn(tsd), &tsd_nominal_tsds_lock); +} + +static void +tsd_force_recompute(tsdn_t *tsdn) { + /* + * The stores to tsd->state here need to synchronize with the exchange + * in tsd_slow_update. + */ + atomic_fence(ATOMIC_RELEASE); + malloc_mutex_lock(tsdn, &tsd_nominal_tsds_lock); + tsd_t *remote_tsd; + ql_foreach(remote_tsd, &tsd_nominal_tsds, TSD_MANGLE(tcache).tsd_link) { + assert(tsd_atomic_load(&remote_tsd->state, ATOMIC_RELAXED) + <= tsd_state_nominal_max); + tsd_atomic_store(&remote_tsd->state, tsd_state_nominal_recompute, + ATOMIC_RELAXED); + } + malloc_mutex_unlock(tsdn, &tsd_nominal_tsds_lock); +} + void +tsd_global_slow_inc(tsdn_t *tsdn) { + atomic_fetch_add_u32(&tsd_global_slow_count, 1, ATOMIC_RELAXED); + /* + * We unconditionally force a recompute, even if the global slow count + * was already positive. If we didn't, then it would be possible for us + * to return to the user, have the user synchronize externally with some + * other thread, and then have that other thread not have picked up the + * update yet (since the original incrementing thread might still be + * making its way through the tsd list). + */ + tsd_force_recompute(tsdn); +} + +void tsd_global_slow_dec(tsdn_t *tsdn) { + atomic_fetch_sub_u32(&tsd_global_slow_count, 1, ATOMIC_RELAXED); + /* See the note in ..._inc(). */ + tsd_force_recompute(tsdn); +} + +static bool +tsd_local_slow(tsd_t *tsd) { + return !tsd_tcache_enabled_get(tsd) + || tsd_reentrancy_level_get(tsd) > 0; +} + +bool +tsd_global_slow() { + return atomic_load_u32(&tsd_global_slow_count, ATOMIC_RELAXED) > 0; +} + +/******************************************************************************/ + +static uint8_t +tsd_state_compute(tsd_t *tsd) { + if (!tsd_nominal(tsd)) { + return tsd_state_get(tsd); + } + /* We're in *a* nominal state; but which one? */ + if (malloc_slow || tsd_local_slow(tsd) || tsd_global_slow()) { + return tsd_state_nominal_slow; + } else { + return tsd_state_nominal; + } +} + +void tsd_slow_update(tsd_t *tsd) { - if (tsd_nominal(tsd)) { - if (malloc_slow || !tsd_tcache_enabled_get(tsd) || - tsd_reentrancy_level_get(tsd) > 0) { - tsd->state = tsd_state_nominal_slow; + uint8_t old_state; + do { + uint8_t new_state = tsd_state_compute(tsd); + old_state = tsd_atomic_exchange(&tsd->state, new_state, + ATOMIC_ACQUIRE); + } while (old_state == tsd_state_nominal_recompute); +} + +void +tsd_state_set(tsd_t *tsd, uint8_t new_state) { + /* Only the tsd module can change the state *to* recompute. */ + assert(new_state != tsd_state_nominal_recompute); + uint8_t old_state = tsd_atomic_load(&tsd->state, ATOMIC_RELAXED); + if (old_state > tsd_state_nominal_max) { + /* + * Not currently in the nominal list, but it might need to be + * inserted there. + */ + assert(!tsd_in_nominal_list(tsd)); + tsd_atomic_store(&tsd->state, new_state, ATOMIC_RELAXED); + if (new_state <= tsd_state_nominal_max) { + tsd_add_nominal(tsd); + } + } else { + /* + * We're currently nominal. If the new state is non-nominal, + * great; we take ourselves off the list and just enter the new + * state. + */ + assert(tsd_in_nominal_list(tsd)); + if (new_state > tsd_state_nominal_max) { + tsd_remove_nominal(tsd); + tsd_atomic_store(&tsd->state, new_state, + ATOMIC_RELAXED); } else { - tsd->state = tsd_state_nominal; + /* + * This is the tricky case. We're transitioning from + * one nominal state to another. The caller can't know + * about any races that are occuring at the same time, + * so we always have to recompute no matter what. + */ + tsd_slow_update(tsd); } } } static bool tsd_data_init(tsd_t *tsd) { /* * We initialize the rtree context first (before the tcache), since the * tcache initialization depends on it. */ rtree_ctx_data_init(tsd_rtree_ctxp_get_unsafe(tsd)); /* * A nondeterministic seed based on the address of tsd reduces * the likelihood of lockstep non-uniform cache index * utilization among identical concurrent processes, but at the * cost of test repeatability. For debug builds, instead use a * deterministic seed. */ *tsd_offset_statep_get(tsd) = config_debug ? 0 : (uint64_t)(uintptr_t)tsd; return tsd_tcache_enabled_data_init(tsd); } static void assert_tsd_data_cleanup_done(tsd_t *tsd) { assert(!tsd_nominal(tsd)); + assert(!tsd_in_nominal_list(tsd)); assert(*tsd_arenap_get_unsafe(tsd) == NULL); assert(*tsd_iarenap_get_unsafe(tsd) == NULL); assert(*tsd_arenas_tdata_bypassp_get_unsafe(tsd) == true); assert(*tsd_arenas_tdatap_get_unsafe(tsd) == NULL); assert(*tsd_tcache_enabledp_get_unsafe(tsd) == false); assert(*tsd_prof_tdatap_get_unsafe(tsd) == NULL); } static bool tsd_data_init_nocleanup(tsd_t *tsd) { - assert(tsd->state == tsd_state_reincarnated || - tsd->state == tsd_state_minimal_initialized); + assert(tsd_state_get(tsd) == tsd_state_reincarnated || + tsd_state_get(tsd) == tsd_state_minimal_initialized); /* * During reincarnation, there is no guarantee that the cleanup function * will be called (deallocation may happen after all tsd destructors). * We set up tsd in a way that no cleanup is needed. */ rtree_ctx_data_init(tsd_rtree_ctxp_get_unsafe(tsd)); *tsd_arenas_tdata_bypassp_get(tsd) = true; *tsd_tcache_enabledp_get_unsafe(tsd) = false; *tsd_reentrancy_levelp_get(tsd) = 1; assert_tsd_data_cleanup_done(tsd); return false; } tsd_t * tsd_fetch_slow(tsd_t *tsd, bool minimal) { assert(!tsd_fast(tsd)); - if (tsd->state == tsd_state_nominal_slow) { - /* On slow path but no work needed. */ - assert(malloc_slow || !tsd_tcache_enabled_get(tsd) || - tsd_reentrancy_level_get(tsd) > 0 || - *tsd_arenas_tdata_bypassp_get(tsd)); - } else if (tsd->state == tsd_state_uninitialized) { + if (tsd_state_get(tsd) == tsd_state_nominal_slow) { + /* + * On slow path but no work needed. Note that we can't + * necessarily *assert* that we're slow, because we might be + * slow because of an asynchronous modification to global state, + * which might be asynchronously modified *back*. + */ + } else if (tsd_state_get(tsd) == tsd_state_nominal_recompute) { + tsd_slow_update(tsd); + } else if (tsd_state_get(tsd) == tsd_state_uninitialized) { if (!minimal) { - tsd->state = tsd_state_nominal; - tsd_slow_update(tsd); - /* Trigger cleanup handler registration. */ - tsd_set(tsd); - tsd_data_init(tsd); + if (tsd_booted) { + tsd_state_set(tsd, tsd_state_nominal); + tsd_slow_update(tsd); + /* Trigger cleanup handler registration. */ + tsd_set(tsd); + tsd_data_init(tsd); + } } else { - tsd->state = tsd_state_minimal_initialized; + tsd_state_set(tsd, tsd_state_minimal_initialized); tsd_set(tsd); tsd_data_init_nocleanup(tsd); } - } else if (tsd->state == tsd_state_minimal_initialized) { + } else if (tsd_state_get(tsd) == tsd_state_minimal_initialized) { if (!minimal) { /* Switch to fully initialized. */ - tsd->state = tsd_state_nominal; + tsd_state_set(tsd, tsd_state_nominal); assert(*tsd_reentrancy_levelp_get(tsd) >= 1); (*tsd_reentrancy_levelp_get(tsd))--; tsd_slow_update(tsd); tsd_data_init(tsd); } else { assert_tsd_data_cleanup_done(tsd); } - } else if (tsd->state == tsd_state_purgatory) { - tsd->state = tsd_state_reincarnated; + } else if (tsd_state_get(tsd) == tsd_state_purgatory) { + tsd_state_set(tsd, tsd_state_reincarnated); tsd_set(tsd); tsd_data_init_nocleanup(tsd); } else { - assert(tsd->state == tsd_state_reincarnated); + assert(tsd_state_get(tsd) == tsd_state_reincarnated); } return tsd; } void * malloc_tsd_malloc(size_t size) { return a0malloc(CACHELINE_CEILING(size)); } void malloc_tsd_dalloc(void *wrapper) { a0dalloc(wrapper); } #if defined(JEMALLOC_MALLOC_THREAD_CLEANUP) || defined(_WIN32) #ifndef _WIN32 JEMALLOC_EXPORT #endif void _malloc_thread_cleanup(void) { bool pending[MALLOC_TSD_CLEANUPS_MAX], again; unsigned i; for (i = 0; i < ncleanups; i++) { pending[i] = true; } do { again = false; for (i = 0; i < ncleanups; i++) { if (pending[i]) { pending[i] = cleanups[i](); if (pending[i]) { again = true; } } } } while (again); } #endif void malloc_tsd_cleanup_register(bool (*f)(void)) { assert(ncleanups < MALLOC_TSD_CLEANUPS_MAX); cleanups[ncleanups] = f; ncleanups++; } static void tsd_do_data_cleanup(tsd_t *tsd) { prof_tdata_cleanup(tsd); iarena_cleanup(tsd); arena_cleanup(tsd); arenas_tdata_cleanup(tsd); tcache_cleanup(tsd); witnesses_cleanup(tsd_witness_tsdp_get_unsafe(tsd)); } void tsd_cleanup(void *arg) { tsd_t *tsd = (tsd_t *)arg; - switch (tsd->state) { + switch (tsd_state_get(tsd)) { case tsd_state_uninitialized: /* Do nothing. */ break; case tsd_state_minimal_initialized: /* This implies the thread only did free() in its life time. */ /* Fall through. */ case tsd_state_reincarnated: /* * Reincarnated means another destructor deallocated memory * after the destructor was called. Cleanup isn't required but * is still called for testing and completeness. */ assert_tsd_data_cleanup_done(tsd); /* Fall through. */ case tsd_state_nominal: case tsd_state_nominal_slow: tsd_do_data_cleanup(tsd); - tsd->state = tsd_state_purgatory; + tsd_state_set(tsd, tsd_state_purgatory); tsd_set(tsd); break; case tsd_state_purgatory: /* * The previous time this destructor was called, we set the * state to tsd_state_purgatory so that other destructors * wouldn't cause re-creation of the tsd. This time, do * nothing, and do not request another callback. */ break; default: not_reached(); } #ifdef JEMALLOC_JET test_callback_t test_callback = *tsd_test_callbackp_get_unsafe(tsd); int *data = tsd_test_datap_get_unsafe(tsd); if (test_callback != NULL) { test_callback(data); } #endif } tsd_t * malloc_tsd_boot0(void) { tsd_t *tsd; ncleanups = 0; + if (malloc_mutex_init(&tsd_nominal_tsds_lock, "tsd_nominal_tsds_lock", + WITNESS_RANK_OMIT, malloc_mutex_rank_exclusive)) { + return NULL; + } if (tsd_boot0()) { return NULL; } tsd = tsd_fetch(); *tsd_arenas_tdata_bypassp_get(tsd) = true; return tsd; } void malloc_tsd_boot1(void) { tsd_boot1(); tsd_t *tsd = tsd_fetch(); /* malloc_slow has been set properly. Update tsd_slow. */ tsd_slow_update(tsd); *tsd_arenas_tdata_bypassp_get(tsd) = false; } #ifdef _WIN32 static BOOL WINAPI _tls_callback(HINSTANCE hinstDLL, DWORD fdwReason, LPVOID lpvReserved) { switch (fdwReason) { #ifdef JEMALLOC_LAZY_LOCK case DLL_THREAD_ATTACH: isthreaded = true; break; #endif case DLL_THREAD_DETACH: _malloc_thread_cleanup(); break; default: break; } return true; } /* * We need to be able to say "read" here (in the "pragma section"), but have * hooked "read". We won't read for the rest of the file, so we can get away * with unhooking. */ #ifdef read # undef read #endif #ifdef _MSC_VER # ifdef _M_IX86 # pragma comment(linker, "/INCLUDE:__tls_used") # pragma comment(linker, "/INCLUDE:_tls_callback") # else # pragma comment(linker, "/INCLUDE:_tls_used") -# pragma comment(linker, "/INCLUDE:tls_callback") +# pragma comment(linker, "/INCLUDE:" STRINGIFY(tls_callback) ) # endif # pragma section(".CRT$XLY",long,read) #endif JEMALLOC_SECTION(".CRT$XLY") JEMALLOC_ATTR(used) BOOL (WINAPI *const tls_callback)(HINSTANCE hinstDLL, DWORD fdwReason, LPVOID lpvReserved) = _tls_callback; #endif #if (!defined(JEMALLOC_MALLOC_THREAD_CLEANUP) && !defined(JEMALLOC_TLS) && \ !defined(_WIN32)) void * tsd_init_check_recursion(tsd_init_head_t *head, tsd_init_block_t *block) { pthread_t self = pthread_self(); tsd_init_block_t *iter; /* Check whether this thread has already inserted into the list. */ malloc_mutex_lock(TSDN_NULL, &head->lock); ql_foreach(iter, &head->blocks, link) { if (iter->thread == self) { malloc_mutex_unlock(TSDN_NULL, &head->lock); return iter->data; } } /* Insert block into list. */ ql_elm_new(block, link); block->thread = self; ql_tail_insert(&head->blocks, block, link); malloc_mutex_unlock(TSDN_NULL, &head->lock); return NULL; } void tsd_init_finish(tsd_init_head_t *head, tsd_init_block_t *block) { malloc_mutex_lock(TSDN_NULL, &head->lock); ql_remove(&head->blocks, block, link); malloc_mutex_unlock(TSDN_NULL, &head->lock); } #endif + +void +tsd_prefork(tsd_t *tsd) { + malloc_mutex_prefork(tsd_tsdn(tsd), &tsd_nominal_tsds_lock); +} + +void +tsd_postfork_parent(tsd_t *tsd) { + malloc_mutex_postfork_parent(tsd_tsdn(tsd), &tsd_nominal_tsds_lock); +} + +void +tsd_postfork_child(tsd_t *tsd) { + malloc_mutex_postfork_child(tsd_tsdn(tsd), &tsd_nominal_tsds_lock); + ql_new(&tsd_nominal_tsds); + + if (tsd_state_get(tsd) <= tsd_state_nominal_max) { + tsd_add_nominal(tsd); + } +} Index: head/lib/libc/stdlib/jemalloc/Makefile.inc =================================================================== --- head/lib/libc/stdlib/jemalloc/Makefile.inc (revision 360232) +++ head/lib/libc/stdlib/jemalloc/Makefile.inc (revision 360233) @@ -1,49 +1,50 @@ # $FreeBSD$ .PATH: ${LIBC_SRCTOP}/stdlib/jemalloc JEMALLOCSRCS:= jemalloc.c arena.c background_thread.c base.c bin.c bitmap.c \ - ckh.c ctl.c div.c extent.c extent_dss.c extent_mmap.c hash.c hooks.c \ + ckh.c ctl.c div.c extent.c extent_dss.c extent_mmap.c hash.c hook.c \ large.c log.c malloc_io.c mutex.c mutex_pool.c nstime.c pages.c \ - prng.c prof.c rtree.c stats.c sz.c tcache.c ticker.c tsd.c witness.c + prng.c prof.c rtree.c safety_check.c sc.c stats.c sz.c tcache.c \ + test_hooks.c ticker.c tsd.c witness.c SYM_MAPS+=${LIBC_SRCTOP}/stdlib/jemalloc/Symbol.map CFLAGS+=-I${SRCTOP}/contrib/jemalloc/include .for src in ${JEMALLOCSRCS} MISRCS+=jemalloc_${src} CLEANFILES+=jemalloc_${src} jemalloc_${src}: ${SRCTOP}/contrib/jemalloc/src/${src} .NOMETA ln -sf ${.ALLSRC} ${.TARGET} .endfor MAN+=jemalloc.3 CLEANFILES+=jemalloc.3 jemalloc.3: ${SRCTOP}/contrib/jemalloc/doc/jemalloc.3 .NOMETA ln -sf ${.ALLSRC} ${.TARGET} MLINKS+= \ jemalloc.3 malloc.3 \ jemalloc.3 calloc.3 \ jemalloc.3 posix_memalign.3 \ jemalloc.3 aligned_alloc.3 \ jemalloc.3 realloc.3 \ jemalloc.3 free.3 \ jemalloc.3 malloc_usable_size.3 \ jemalloc.3 malloc_stats_print.3 \ jemalloc.3 mallctl.3 \ jemalloc.3 mallctlnametomib.3 \ jemalloc.3 mallctlbymib.3 \ jemalloc.3 mallocx.3 \ jemalloc.3 rallocx.3 \ jemalloc.3 xallocx.3 \ jemalloc.3 sallocx.3 \ jemalloc.3 dallocx.3 \ jemalloc.3 sdallocx.3 \ jemalloc.3 nallocx.3 \ jemalloc.3 malloc.conf.5 .if defined(MALLOC_PRODUCTION) CFLAGS+= -DMALLOC_PRODUCTION .endif