Update jemalloc to version 4.0.4.

svn path=/head/; revision=289900

contrib/jemalloc/ChangeLog

@@ -4,6 +4,32 @@ brevity.  Much more detail can be found in the git revision history:
 
     https://github.com/jemalloc/jemalloc
 
+* 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.

contrib/jemalloc/FREEBSD-diffs

@@ -1,5 +1,5 @@
 diff --git a/doc/jemalloc.xml.in b/doc/jemalloc.xml.in
-index 8fc774b..fdbef95 100644
+index 26a5e14..2a801b7 100644
 --- a/doc/jemalloc.xml.in
 +++ b/doc/jemalloc.xml.in
 @@ -53,11 +53,23 @@
@@ -47,7 +47,7 @@ index 8fc774b..fdbef95 100644
 +  </refsect1>
  </refentry>
 diff --git a/include/jemalloc/internal/jemalloc_internal.h.in b/include/jemalloc/internal/jemalloc_internal.h.in
-index 8536a3e..0c2a81f 100644
+index 654cd08..ad5382d 100644
 --- a/include/jemalloc/internal/jemalloc_internal.h.in
 +++ b/include/jemalloc/internal/jemalloc_internal.h.in
 @@ -8,6 +8,9 @@

contrib/jemalloc/VERSION

@@ -1 +1 @@
-4.0.2-0-g486d249fb4715fd3de679b6c2a04f7e657883111
+4.0.4-0-g91010a9e2ebfc84b1ac1ed7fdde3bfed4f65f180

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: 09/21/2015
+.\"      Date: 10/24/2015
 .\"    Manual: User Manual
-.\"    Source: jemalloc 4.0.2-0-g486d249fb4715fd3de679b6c2a04f7e657883111
+.\"    Source: jemalloc 4.0.4-0-g91010a9e2ebfc84b1ac1ed7fdde3bfed4f65f180
 .\"  Language: English
 .\"
-.TH "JEMALLOC" "3" "09/21/2015" "jemalloc 4.0.2-0-g486d249fb471" "User Manual"
+.TH "JEMALLOC" "3" "10/24/2015" "jemalloc 4.0.4-0-g91010a9e2ebf" "User Manual"
 .\" -----------------------------------------------------------------
 .\" * Define some portability stuff
 .\" -----------------------------------------------------------------
@@ -31,7 +31,7 @@
 jemalloc \- general purpose memory allocation functions
 .SH "LIBRARY"
 .PP
-This manual describes jemalloc 4\&.0\&.2\-0\-g486d249fb4715fd3de679b6c2a04f7e657883111\&. More information can be found at the
+This manual describes jemalloc 4\&.0\&.4\-0\-g91010a9e2ebfc84b1ac1ed7fdde3bfed4f65f180\&. 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:
@@ -1041,7 +1041,7 @@ Flush calling thread\*(Aqs thread\-specific cache (tcache)\&. This interface rel
 .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 nil\-terminated and comprised only of characters in the sets recognized by
+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)\&.

contrib/jemalloc/include/jemalloc/internal/jemalloc_internal.h

@@ -314,6 +314,10 @@ typedef unsigned szind_t;
 #define	PAGE		((size_t)(1U << LG_PAGE))
 #define	PAGE_MASK	((size_t)(PAGE - 1))
 
+/* Return the page base address for the page containing address a. */
+#define	PAGE_ADDR2BASE(a)						\
+	((void *)((uintptr_t)(a) & ~PAGE_MASK))
+
 /* Return the smallest pagesize multiple that is >= s. */
 #define	PAGE_CEILING(s)							\
 	(((s) + PAGE_MASK) & ~PAGE_MASK)

contrib/jemalloc/include/jemalloc/jemalloc.h

@@ -79,12 +79,12 @@ extern "C" {
 #include <limits.h>
 #include <strings.h>
 
-#define	JEMALLOC_VERSION "4.0.2-0-g486d249fb4715fd3de679b6c2a04f7e657883111"
+#define	JEMALLOC_VERSION "4.0.4-0-g91010a9e2ebfc84b1ac1ed7fdde3bfed4f65f180"
 #define	JEMALLOC_VERSION_MAJOR 4
 #define	JEMALLOC_VERSION_MINOR 0
-#define	JEMALLOC_VERSION_BUGFIX 2
+#define	JEMALLOC_VERSION_BUGFIX 4
 #define	JEMALLOC_VERSION_NREV 0
-#define	JEMALLOC_VERSION_GID "486d249fb4715fd3de679b6c2a04f7e657883111"
+#define	JEMALLOC_VERSION_GID "91010a9e2ebfc84b1ac1ed7fdde3bfed4f65f180"
 
 #  define MALLOCX_LG_ALIGN(la)	(la)
 #  if LG_SIZEOF_PTR == 2

contrib/jemalloc/src/arena.c

@@ -2679,6 +2679,22 @@ arena_ralloc_large_grow(arena_t *arena, arena_chunk_t *chunk, void *ptr,
 		if (arena_run_split_large(arena, run, splitsize, zero))
 			goto label_fail;
 
+		if (config_cache_oblivious && zero) {
+			/*
+			 * 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 run is a multiple of
+			 * CACHELINE in [0 .. PAGE).
+			 */
+			void *zbase = (void *)((uintptr_t)ptr + oldsize);
+			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);
+		}
+
 		size = oldsize + splitsize;
 		npages = (size + large_pad) >> LG_PAGE;
 

contrib/jemalloc/src/huge.c

@@ -133,7 +133,7 @@ huge_ralloc_no_move_similar(void *ptr, size_t oldsize, size_t usize_min,
 	extent_node_t *node;
 	arena_t *arena;
 	chunk_hooks_t chunk_hooks = CHUNK_HOOKS_INITIALIZER;
-	bool zeroed;
+	bool pre_zeroed, post_zeroed;
 
 	/* Increase usize to incorporate extra. */
 	for (usize = usize_min; usize < usize_max && (usize_next = s2u(usize+1))
@@ -145,26 +145,27 @@ huge_ralloc_no_move_similar(void *ptr, size_t oldsize, size_t usize_min,
 
 	node = huge_node_get(ptr);
 	arena = extent_node_arena_get(node);
+	pre_zeroed = extent_node_zeroed_get(node);
 
 	/* Fill if necessary (shrinking). */
 	if (oldsize > usize) {
 		size_t sdiff = oldsize - usize;
 		if (config_fill && unlikely(opt_junk_free)) {
 			memset((void *)((uintptr_t)ptr + usize), 0x5a, sdiff);
-			zeroed = false;
+			post_zeroed = false;
 		} else {
-			zeroed = !chunk_purge_wrapper(arena, &chunk_hooks, ptr,
-			    CHUNK_CEILING(oldsize), usize, sdiff);
+			post_zeroed = !chunk_purge_wrapper(arena, &chunk_hooks,
+			    ptr, CHUNK_CEILING(oldsize), usize, sdiff);
 		}
 	} else
-		zeroed = true;
+		post_zeroed = pre_zeroed;
 
 	malloc_mutex_lock(&arena->huge_mtx);
 	/* Update the size of the huge allocation. */
 	assert(extent_node_size_get(node) != usize);
 	extent_node_size_set(node, usize);
-	/* Clear node's zeroed field if zeroing failed above. */
-	extent_node_zeroed_set(node, extent_node_zeroed_get(node) && zeroed);
+	/* Update zeroed. */
+	extent_node_zeroed_set(node, post_zeroed);
 	malloc_mutex_unlock(&arena->huge_mtx);
 
 	arena_chunk_ralloc_huge_similar(arena, ptr, oldsize, usize);
@@ -172,7 +173,7 @@ huge_ralloc_no_move_similar(void *ptr, size_t oldsize, size_t usize_min,
 	/* Fill if necessary (growing). */
 	if (oldsize < usize) {
 		if (zero || (config_fill && unlikely(opt_zero))) {
-			if (!zeroed) {
+			if (!pre_zeroed) {
 				memset((void *)((uintptr_t)ptr + oldsize), 0,
 				    usize - oldsize);
 			}
@@ -190,10 +191,11 @@ huge_ralloc_no_move_shrink(void *ptr, size_t oldsize, size_t usize)
 	arena_t *arena;
 	chunk_hooks_t chunk_hooks;
 	size_t cdiff;
-	bool zeroed;
+	bool pre_zeroed, post_zeroed;
 
 	node = huge_node_get(ptr);
 	arena = extent_node_arena_get(node);
+	pre_zeroed = extent_node_zeroed_get(node);
 	chunk_hooks = chunk_hooks_get(arena);
 
 	assert(oldsize > usize);
@@ -209,21 +211,21 @@ huge_ralloc_no_move_shrink(void *ptr, size_t oldsize, size_t usize)
 		if (config_fill && unlikely(opt_junk_free)) {
 			huge_dalloc_junk((void *)((uintptr_t)ptr + usize),
 			    sdiff);
-			zeroed = false;
+			post_zeroed = false;
 		} else {
-			zeroed = !chunk_purge_wrapper(arena, &chunk_hooks,
+			post_zeroed = !chunk_purge_wrapper(arena, &chunk_hooks,
 			    CHUNK_ADDR2BASE((uintptr_t)ptr + usize),
 			    CHUNK_CEILING(oldsize),
 			    CHUNK_ADDR2OFFSET((uintptr_t)ptr + usize), sdiff);
 		}
 	} else
-		zeroed = true;
+		post_zeroed = pre_zeroed;
 
 	malloc_mutex_lock(&arena->huge_mtx);
 	/* Update the size of the huge allocation. */
 	extent_node_size_set(node, usize);
-	/* Clear node's zeroed field if zeroing failed above. */
-	extent_node_zeroed_set(node, extent_node_zeroed_get(node) && zeroed);
+	/* Update zeroed. */
+	extent_node_zeroed_set(node, post_zeroed);
 	malloc_mutex_unlock(&arena->huge_mtx);
 
 	/* Zap the excess chunks. */

contrib/jemalloc/src/prof.c

@@ -1102,11 +1102,23 @@ prof_tctx_dump_iter(prof_tctx_tree_t *tctxs, prof_tctx_t *tctx, void *arg)
 {
 	bool propagate_err = *(bool *)arg;
 
-	if (prof_dump_printf(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);
+	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(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);
 }
 

contrib/jemalloc/src/tsd.c

@@ -73,6 +73,9 @@ tsd_cleanup(void *arg)
 	tsd_t *tsd = (tsd_t *)arg;
 
 	switch (tsd->state) {
+	case tsd_state_uninitialized:
+		/* Do nothing. */
+		break;
 	case tsd_state_nominal:
 #define O(n, t)								\
 		n##_cleanup(tsd);