- Add 0001-ARM-Don-t-extend-bit-LG_VADDR-to-compute-high-addres.patch:
  fixes #979.
- Add 0001-remove-CPU_SPINWAIT.patch:
  revert 701daa5298b3befe2aff05ce590533165abb9ba4 in order to fix #761.
- Update to version 5.0.1
   Bug fixes:
     * Update decay->nunpurged before purging, in order to avoid potential
       update races and subsequent incorrect purging volume.
       ([37]@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. ([38]@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. ([39]@interwq)
     * Mask signals during background thread creation. This prevents
       signals from being inadvertently delivered to background threads.
       ([40]@jasone, [41]@davidtgoldblatt, [42]@interwq)
     * Avoid inactivity checks within background threads, in order to
       prevent recursive mutex acquisition. ([43]@interwq)
     * Fix extent_grow_retained() to use the specified hooks when the
       arena.<i>.extent_hooks mallctl is used to override the default
       hooks. ([44]@interwq)
     * Add missing reentrancy support for custom extent hooks which
       allocate. ([45]@interwq)
     * Post-fork(2), re-initialize the list of tcaches associated with
       each arena to contain no tcaches except the forking thread's.
       ([46]@interwq)
     * Add missing post-fork(2) mutex reinitialization for
       extent_grow_mtx. This fixes potential deadlocks after fork(2).
       ([47]@interwq)
     * Enforce minimum autoconf version (currently 2.68), since 2.63 is
       known to generate corrupt configure scripts. ([48]@jasone)
     * Ensure that the configured page size (--with-lg-page) is no larger
       than the configured huge page size (--with-lg-hugepage).
       ([49]@jasone)
   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. ([59]@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. ([60]@jasone)
     * Increase decay time resolution from seconds to milliseconds.
       ([61]@jasone)
     * Implement opt-in per CPU background threads, and use them for
       asynchronous decay-driven unused dirty page purging. ([62]@interwq)
     * Add mutex profiling, which collects a variety of statistics useful
       for diagnosing overhead/contention issues. ([63]@interwq)
     * Add C++ new/delete operator bindings. ([64]@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. ([65]@jasone)
     * Add MALLCTL_ARENAS_ALL as a fixed index for use in accessing
       merged/destroyed arena statistics via mallctl. ([66]@jasone)
     * Add opt.abort_conf to optionally abort if invalid configuration
       options are detected during initialization. ([67]@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.
       ([68]@jasone)
     * Add --with-version=VERSION for use when embedding jemalloc into
       another project's git repository. ([69]@jasone)
     * Add --disable-thp to support cross compiling. ([70]@jasone)
     * Add --with-lg-hugepage to support cross compiling. ([71]@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.<i>.initialized
          + arena.<i>.destroy
          + arena.<i>.{dirty,muzzy}_decay_ms
          + arena.<i>.extent_hooks
          + arenas.{dirty,muzzy}_decay_ms
          + arenas.bin.<i>.slab_size
          + arenas.nlextents
          + arenas.lextent.<i>.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,n
            um_owner_switch}
          + stats.arenas.<i>.{dirty,muzzy}_decay_ms
          + stats.arenas.<i>.uptime
          + stats.arenas.<i>.{pmuzzy,base,internal,resident}
          + stats.arenas.<i>.{dirty,muzzy}_{npurge,nmadvise,purged}
          + stats.arenas.<i>.bins.<j>.{nslabs,reslabs,curslabs}
          + stats.arenas.<i>.bins.<j>.mutex.{num_ops,num_spin_acq,num_wait
            ,max_wait_time,total_wait_time,max_num_thds,num_owner_switch}
          + stats.arenas.<i>.lextents.<j>.{nmalloc,ndalloc,nrequests,curle
            xtents}
          + stats.arenas.i.mutexes.{large,extent_avail,extents_dirty,exten
            ts_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.
       ([72]@davidtgoldblatt, [73]@interwq)
     * Support static linking of jemalloc with glibc. ([74]@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). ([75]@jasone)
     * Fold large and huge size classes together; only small and large
       size classes remain. ([76]@jasone)
     * Unify the allocation paths, and merge most fast-path branching
       decisions. ([77]@davidtgoldblatt, [78]@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. ([79]@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. ([80]@davidtgoldblatt)
     * Extensively optimize rtree via various methods:
          + Add multiple layers of rtree lookup caching, since rtree
            lookups are now part of fast-path deallocation. ([81]@interwq)
          + Determine rtree layout at compile time. ([82]@jasone)
          + Make the tree shallower for common configurations.
            ([83]@jasone)
          + Embed the root node in the top-level rtree data structure,
            thus avoiding one level of indirection. ([84]@jasone)
          + Further specialize leaf elements as compared to internal node
            elements, and directly embed extent metadata needed for
            fast-path deallocation. ([85]@jasone)
          + Ignore leading always-zero address bits
            (architecture-specific). ([86]@jasone)
     * Reorganize headers (ongoing work) to make them hermetic, and
       disentangle various module dependencies. ([87]@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. ([88]@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. ([89]@jasone)
     * Lock individual extents when possible for localized extent
       operations, rather than relying on a top-level arena lock.
       ([90]@davidtgoldblatt, [91]@jasone)
     * Use first fit layout policy instead of best fit, in order to
       improve packing. ([92]@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. ([93]@jasone)
     * Implement per arena base allocators, so that arenas never share any
       virtual memory pages. ([94]@jasone)
     * Automatically generate private symbol name mangling macros.
       ([95]@jasone)
   Incompatible changes:
     * Replace chunk hooks with an expanded/normalized set of extent
       hooks. ([96]@jasone)
     * Remove ratio-based purging. ([97]@jasone)
     * Remove --disable-tcache. ([98]@jasone)
     * Remove --disable-tls. ([99]@jasone)
     * Remove --enable-ivsalloc. ([100]@jasone)
     * Remove --with-lg-size-class-group. ([101]@jasone)
     * Remove --with-lg-tiny-min. ([102]@jasone)
     * Remove --disable-cc-silence. ([103]@jasone)
     * Remove --enable-code-coverage. ([104]@jasone)
     * Remove --disable-munmap (replaced by opt.retain). ([105]@jasone)
     * Remove Valgrind support. ([106]@jasone)
     * Remove quarantine support. ([107]@jasone)
     * Remove redzone support. ([108]@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.<i>.lg_dirty_mult
          + arena.<i>.decay_time
          + arena.<i>.chunk_hooks
          + arenas.initialized
          + arenas.lg_dirty_mult
          + arenas.decay_time
          + arenas.bin.<i>.run_size
          + arenas.nlruns
          + arenas.lrun.<i>.size
          + arenas.nhchunks
          + arenas.hchunk.<i>.size
          + arenas.extend
          + stats.cactive
          + stats.arenas.<i>.lg_dirty_mult
          + stats.arenas.<i>.decay_time
          + stats.arenas.<i>.metadata.{mapped,allocated}
          + stats.arenas.<i>.{npurge,nmadvise,purged}
          + stats.arenas.<i>.huge.{allocated,nmalloc,ndalloc,nrequests}
          + stats.arenas.<i>.bins.<j>.{nruns,reruns,curruns}
          + stats.arenas.<i>.lruns.<j>.{nmalloc,ndalloc,nrequests,curruns}
          + stats.arenas.<i>.hchunks.<j>.{nmalloc,ndalloc,nrequests,curhch
            unks}
   Bug fixes:
     * Improve interval-based profile dump triggering to dump only one
       profile when a single allocation's size exceeds the interval.
       ([109]@jasone)
     * Use prefixed function names (as controlled by
       --with-jemalloc-prefix) when pruning backtrace frames in jeprof.
       ([110]@jasone)

• Files Changed
• Browse Source