Update jemalloc to 4.2.0.

contrib/jemalloc/ChangeLog

@@ -4,6 +4,50 @@ brevity.  Much more detail can be found in the git revision history:
 
     https://github.com/jemalloc/jemalloc
 
+* 4.2.0 (May 12, 2016)
+
+  New features:
+  - Add the arena.<i>.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.<i>.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
@@ -59,14 +103,14 @@ brevity.  Much more detail can be found in the git revision history:
   Bug fixes:
   - Fix stats.cactive accounting regression.  (@rustyx, @jasone)
   - Handle unaligned keys in hash().  This caused problems for some ARM systems.
-    (@jasone, Christopher Ferris)
+    (@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.  (Christopher Ferris, @jasone)
+  - 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)

contrib/jemalloc/FREEBSD-diffs

@@ -1,5 +1,5 @@
 diff --git a/doc/jemalloc.xml.in b/doc/jemalloc.xml.in
-index bc5dbd1..ba182da 100644
+index c4a44e3..4626e9b 100644
 --- a/doc/jemalloc.xml.in
 +++ b/doc/jemalloc.xml.in
 @@ -53,11 +53,23 @@
@@ -27,7 +27,7 @@ index bc5dbd1..ba182da 100644
        <refsect2>
          <title>Standard API</title>
          <funcprototype>
-@@ -2905,4 +2917,18 @@ malloc_conf = "lg_chunk:24";]]></programlisting></para>
+@@ -2961,4 +2973,18 @@ malloc_conf = "lg_chunk:24";]]></programlisting></para>
      <para>The <function>posix_memalign<parameter/></function> function conforms
      to IEEE Std 1003.1-2001 (&ldquo;POSIX.1&rdquo;).</para>
    </refsect1>
@@ -47,7 +47,7 @@ index bc5dbd1..ba182da 100644
 +  </refsect1>
  </refentry>
 diff --git a/include/jemalloc/internal/jemalloc_internal.h.in b/include/jemalloc/internal/jemalloc_internal.h.in
-index 3f54391..d240256 100644
+index 51bf897..7de22ea 100644
 --- a/include/jemalloc/internal/jemalloc_internal.h.in
 +++ b/include/jemalloc/internal/jemalloc_internal.h.in
 @@ -8,6 +8,9 @@
@@ -90,10 +90,10 @@ index 2b8ca5d..42d97f2 100644
  #ifdef _WIN32
  #  include <windows.h>
 diff --git a/include/jemalloc/internal/mutex.h b/include/jemalloc/internal/mutex.h
-index f051f29..561378f 100644
+index 5221799..60ab041 100644
 --- a/include/jemalloc/internal/mutex.h
 +++ b/include/jemalloc/internal/mutex.h
-@@ -47,15 +47,13 @@ struct malloc_mutex_s {
+@@ -52,9 +52,6 @@ struct malloc_mutex_s {
 
  #ifdef JEMALLOC_LAZY_LOCK
  extern bool isthreaded;
@@ -102,19 +102,20 @@ index f051f29..561378f 100644
 -#  define isthreaded true
  #endif
 
- bool	malloc_mutex_init(malloc_mutex_t *mutex);
- void	malloc_mutex_prefork(malloc_mutex_t *mutex);
- void	malloc_mutex_postfork_parent(malloc_mutex_t *mutex);
- void	malloc_mutex_postfork_child(malloc_mutex_t *mutex);
+ bool	malloc_mutex_init(malloc_mutex_t *mutex, const char *name,
+@@ -62,6 +59,7 @@ 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	mutex_boot(void);
+ bool	malloc_mutex_boot(void);
 
  #endif /* JEMALLOC_H_EXTERNS */
 diff --git a/include/jemalloc/internal/private_symbols.txt b/include/jemalloc/internal/private_symbols.txt
-index 5880996..6e94e03 100644
+index f2b6a55..69369c9 100644
 --- a/include/jemalloc/internal/private_symbols.txt
 +++ b/include/jemalloc/internal/private_symbols.txt
-@@ -296,7 +296,6 @@ iralloct_realign
+@@ -311,7 +311,6 @@ iralloct_realign
  isalloc
  isdalloct
  isqalloc
@@ -124,10 +125,10 @@ index 5880996..6e94e03 100644
  jemalloc_postfork_child
 diff --git a/include/jemalloc/jemalloc_FreeBSD.h b/include/jemalloc/jemalloc_FreeBSD.h
 new file mode 100644
-index 0000000..433dab5
+index 0000000..c58a8f3
 --- /dev/null
 +++ b/include/jemalloc/jemalloc_FreeBSD.h
-@@ -0,0 +1,160 @@
+@@ -0,0 +1,162 @@
 +/*
 + * Override settings that were generated in jemalloc_defs.h as necessary.
 + */
@@ -138,6 +139,8 @@ index 0000000..433dab5
 +#define	JEMALLOC_DEBUG
 +#endif
 +
++#undef JEMALLOC_DSS
++
 +/*
 + * The following are architecture-dependent, so conditionally define them for
 + * each supported architecture.
@@ -300,7 +303,7 @@ index f943891..47d032c 100755
 +#include "jemalloc_FreeBSD.h"
  EOF
 diff --git a/src/jemalloc.c b/src/jemalloc.c
-index 0735376..a34b85c 100644
+index 40eb2ea..666c49d 100644
 --- a/src/jemalloc.c
 +++ b/src/jemalloc.c
 @@ -4,6 +4,10 @@
@@ -314,7 +317,7 @@ index 0735376..a34b85c 100644
  /* Runtime configuration options. */
  const char	*je_malloc_conf JEMALLOC_ATTR(weak);
  bool	opt_abort =
-@@ -2611,6 +2615,107 @@ je_malloc_usable_size(JEMALLOC_USABLE_SIZE_CONST void *ptr)
+@@ -2673,6 +2677,107 @@ je_malloc_usable_size(JEMALLOC_USABLE_SIZE_CONST void *ptr)
   */
  /******************************************************************************/
  /*
@@ -341,7 +344,7 @@ index 0735376..a34b85c 100644
 +	if (p == NULL)
 +		return (ALLOCM_ERR_OOM);
 +	if (rsize != NULL)
-+		*rsize = isalloc(p, config_prof);
++		*rsize = isalloc(tsdn_fetch(), p, config_prof);
 +	*ptr = p;
 +	return (ALLOCM_SUCCESS);
 +}
@@ -370,7 +373,7 @@ index 0735376..a34b85c 100644
 +		} else
 +			ret = ALLOCM_ERR_OOM;
 +		if (rsize != NULL)
-+			*rsize = isalloc(*ptr, config_prof);
++			*rsize = isalloc(tsdn_fetch(), *ptr, config_prof);
 +	}
 +	return (ret);
 +}
@@ -422,8 +425,8 @@ index 0735376..a34b85c 100644
   * The following functions are used by threading libraries for protection of
   * malloc during fork().
   */
-@@ -2717,4 +2822,11 @@ jemalloc_postfork_child(void)
- 	ctl_postfork_child();
+@@ -2814,4 +2919,11 @@ jemalloc_postfork_child(void)
+ 	ctl_postfork_child(tsd_tsdn(tsd));
  }
 
 +void
@@ -435,7 +438,7 @@ index 0735376..a34b85c 100644
 +
  /******************************************************************************/
 diff --git a/src/mutex.c b/src/mutex.c
-index 2d47af9..934d5aa 100644
+index a1fac34..a24e420 100644
 --- a/src/mutex.c
 +++ b/src/mutex.c
 @@ -66,6 +66,17 @@ pthread_create(pthread_t *__restrict thread,
@@ -456,22 +459,22 @@ index 2d47af9..934d5aa 100644
  #endif
 
  bool
-@@ -137,7 +148,7 @@ malloc_mutex_postfork_child(malloc_mutex_t *mutex)
+@@ -140,7 +151,7 @@ malloc_mutex_postfork_child(tsdn_t *tsdn, malloc_mutex_t *mutex)
  }
 
  bool
--mutex_boot(void)
+-malloc_mutex_boot(void)
 +malloc_mutex_first_thread(void)
  {
 
  #ifdef JEMALLOC_MUTEX_INIT_CB
-@@ -151,3 +162,14 @@ mutex_boot(void)
+@@ -154,3 +165,14 @@ malloc_mutex_boot(void)
  #endif
  	return (false);
  }
 +
 +bool
-+mutex_boot(void)
++malloc_mutex_boot(void)
 +{
 +
 +#ifndef JEMALLOC_MUTEX_INIT_CB
@@ -481,10 +484,10 @@ index 2d47af9..934d5aa 100644
 +#endif
 +}
 diff --git a/src/util.c b/src/util.c
-index 02673c7..116e981 100644
+index a1c4a2a..04f9153 100644
 --- a/src/util.c
 +++ b/src/util.c
-@@ -66,6 +66,22 @@ wrtmessage(void *cbopaque, const char *s)
+@@ -67,6 +67,22 @@ wrtmessage(void *cbopaque, const char *s)
 
  JEMALLOC_EXPORT void	(*je_malloc_message)(void *, const char *s);
 

contrib/jemalloc/VERSION

@@ -1 +1 @@
-4.1.0-1-g994da4232621dd1210fcf39bdf0d6454cefda473
+4.2.0-1-gdc7ff6306d7a15b53479e2fb8e5546404b82e6fc

contrib/jemalloc/doc/jemalloc.3

@@ -2,12 +2,12 @@
 .\"     Title: JEMALLOC
 .\"    Author: Jason Evans
 .\" Generator: DocBook XSL Stylesheets v1.76.1 <http://docbook.sf.net/>
-.\"      Date: 02/28/2016
+.\"      Date: 05/12/2016
 .\"    Manual: User Manual
-.\"    Source: jemalloc 4.1.0-1-g994da4232621dd1210fcf39bdf0d6454cefda473
+.\"    Source: jemalloc 4.2.0-1-gdc7ff6306d7a15b53479e2fb8e5546404b82e6fc
 .\"  Language: English
 .\"
-.TH "JEMALLOC" "3" "02/28/2016" "jemalloc 4.1.0-1-g994da4232621" "User Manual"
+.TH "JEMALLOC" "3" "05/12/2016" "jemalloc 4.2.0-1-gdc7ff6306d7a" "User Manual"
 .\" -----------------------------------------------------------------
 .\" * Define some portability stuff
 .\" -----------------------------------------------------------------
@@ -31,7 +31,7 @@
 jemalloc \- general purpose memory allocation functions
 .SH "LIBRARY"
 .PP
-This manual describes jemalloc 4\&.1\&.0\-1\-g994da4232621dd1210fcf39bdf0d6454cefda473\&. More information can be found at the
+This manual describes jemalloc 4\&.2\&.0\-1\-gdc7ff6306d7a15b53479e2fb8e5546404b82e6fc\&. 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:
@@ -461,7 +461,8 @@ Memory is conceptually broken into equal\-sized chunks, where the chunk size is
 Small objects are managed in groups by page runs\&. Each run 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, large size classes are smaller than the chunk size (see the
 "opt\&.lg_chunk"
-option), and huge size classes extend from the chunk size up to one size class less than the full address space size\&.
+option), and huge size classes extend from the chunk 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
@@ -518,6 +519,8 @@ l r l
 ^ r l
 ^ r l
 ^ r l
+^ r l
+^ r l
 ^ r l.
 T{
 Small
@@ -645,6 +648,16 @@ 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"
@@ -841,7 +854,7 @@ function\&. If
 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,
 \fBatexit\fR\fB\fR
 may allocate memory during application initialization and then deadlock internally when jemalloc in turn calls
-\fBatexit\fR\fB\fR, so this option is not univerally usable (though the application can register its own
+\fBatexit\fR\fB\fR, so this option is not universally usable (though the application can register its own
 \fBatexit\fR\fB\fR
 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
@@ -1007,7 +1020,7 @@ is controlled by the
 option\&. Note that
 \fBatexit\fR\fB\fR
 may allocate memory during application initialization and then deadlock internally when jemalloc in turn calls
-\fBatexit\fR\fB\fR, so this option is not univerally usable (though the application can register its own
+\fBatexit\fR\fB\fR, so this option is not universally usable (though the application can register its own
 \fBatexit\fR\fB\fR
 function with equivalent functionality)\&. This option is disabled by default\&.
 .RE
@@ -1113,6 +1126,14 @@ Trigger decay\-based purging of unused dirty pages for arena <i>, or for all are
 for details\&.
 .RE
 .PP
+"arena\&.<i>\&.reset" (\fBvoid\fR) \-\-
+.RS 4
+Discard all of the arena\*(Aqs extant allocations\&. This interface can only be used with arenas created via
+"arenas\&.extend"\&. 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\&. This interface cannot be used if running inside Valgrind, nor if the
+quarantine
+size is non\-zero\&.
+.RE
+.PP
 "arena\&.<i>\&.dss" (\fBconst char *\fR) rw
 .RS 4
 Set the precedence of dss allocation as related to mmap allocation for arena <i>, or for all arenas if <i> equals
@@ -1503,7 +1524,7 @@ Get the current sample rate (see
 .PP
 "prof\&.interval" (\fBuint64_t\fR) r\- [\fB\-\-enable\-prof\fR]
 .RS 4
-Average number of bytes allocated between inverval\-based profile dumps\&. See the
+Average number of bytes allocated between interval\-based profile dumps\&. See the
 "opt\&.lg_prof_interval"
 option for additional information\&.
 .RE
@@ -1547,6 +1568,15 @@ Total number of bytes in active chunks mapped by the allocator\&. This is a mult
 "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)\&. Retained virtual memory is typically untouched, decommitted, or purged, so it has no strongly associated physical memory (see
+chunk hooks
+for details)\&. Retained memory is excluded from mapped memory statistics, e\&.g\&.
+"stats\&.mapped"\&.
+.RE
+.PP
 "stats\&.arenas\&.<i>\&.dss" (\fBconst char *\fR) r\-
 .RS 4
 dss (\fBsbrk\fR(2)) allocation precedence as related to
@@ -1592,6 +1622,13 @@ or similar has not been called\&.
 Number of mapped bytes\&.
 .RE
 .PP
+"stats\&.arenas\&.<i>\&.retained" (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR]
+.RS 4
+Number of retained bytes\&. See
+"stats\&.retained"
+for details\&.
+.RE
+.PP
 "stats\&.arenas\&.<i>\&.metadata\&.mapped" (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR]
 .RS 4
 Number of mapped bytes in arena chunk headers, which track the states of the non\-metadata pages\&.