Commit Graph

953 Commits

Author SHA1 Message Date
Jason Evans
12efefb195 Fix dss/mmap allocation precedence code.
Fix dss/mmap allocation precedence code to use recyclable mmap memory
only after primary dss allocation fails.
2012-10-16 22:06:56 -07:00
Jason Evans
3b1f3aca54 Merge branch 'dev' 2012-10-16 10:40:57 -07:00
Jason Evans
2b592b0f0b Update ChangeLog for 3.1.0. 2012-10-16 10:12:40 -07:00
Jason Evans
a5c80f893e Add ctl_mutex proection to arena_i_dss_ctl().
Add ctl_mutex proection to arena_i_dss_ctl(), since ctl_stats.narenas is
accessed.
2012-10-15 12:48:59 -07:00
Jason Evans
609ae595f0 Add arena-specific and selective dss allocation.
Add the "arenas.extend" mallctl, so that it is possible to create new
arenas that are outside the set that jemalloc automatically multiplexes
threads onto.

Add the ALLOCM_ARENA() flag for {,r,d}allocm(), so that it is possible
to explicitly allocate from a particular arena.

Add the "opt.dss" mallctl, which controls the default precedence of dss
allocation relative to mmap allocation.

Add the "arena.<i>.dss" mallctl, which makes it possible to set the
default dss precedence on a per arena or global basis.

Add the "arena.<i>.purge" mallctl, which obsoletes "arenas.purge".

Add the "stats.arenas.<i>.dss" mallctl.
2012-10-12 18:26:16 -07:00
Jan Beich
d0ffd8ed4f mark _pthread_mutex_init_calloc_cb as public explicitly
Mozilla build hides everything by default using visibility pragma and
unhides only explicitly listed headers. But this doesn't work on FreeBSD
because _pthread_mutex_init_calloc_cb is neither documented nor exposed
via any header.
2012-10-10 09:10:37 -07:00
Jason Evans
2cc11ff837 Make malloc_usable_size() implementation consistent with prototype.
Use JEMALLOC_USABLE_SIZE_CONST for the malloc_usable_size()
implementation as well as the prototype, for consistency's sake.
2012-10-09 16:29:21 -07:00
Jason Evans
247d124847 Drop const from malloc_usable_size() argument on Linux.
Drop const from malloc_usable_size() argument on Linux, in order to
match the prototype in Linux's malloc.h.
2012-10-09 16:20:10 -07:00
Jason Evans
b5225928fe Fix fork(2)-related mutex acquisition order.
Fix mutex acquisition order inversion for the chunks rtree and the base
mutex.  Chunks rtree acquisition was introduced by the previous commit,
so this bug was short-lived.
2012-10-09 16:16:00 -07:00
Jason Evans
20f1fc95ad Fix fork(2)-related deadlocks.
Add a library constructor for jemalloc that initializes the allocator.
This fixes a race that could occur if threads were created by the main
thread prior to any memory allocation, followed by fork(2), and then
memory allocation in the child process.

Fix the prefork/postfork functions to acquire/release the ctl, prof, and
rtree mutexes.  This fixes various fork() child process deadlocks, but
one possible deadlock remains (intentionally) unaddressed: prof
backtracing can acquire runtime library mutexes, so deadlock is still
possible if heap profiling is enabled during fork().  This deadlock is
known to be a real issue in at least the case of libgcc-based
backtracing.

Reported by tfengjun.
2012-10-09 15:21:46 -07:00
Jason Evans
7de92767c2 Fix mlockall()/madvise() interaction.
mlockall(2) can cause purging via madvise(2) to fail.  Fix purging code
to check whether madvise() succeeded, and base zeroed page metadata on
the result.

Reported by Olivier Lecomte.
2012-10-08 18:04:49 -07:00
Jason Evans
f4c3f8545b Fix error return value in thread_tcache_enabled_ctl().
Reported by Corey Richardson.
2012-10-08 15:48:04 -07:00
Corey Richardson
1d553f72cb If sysconf() fails, the number of CPUs is reported as UINT_MAX, not 1 as it should be 2012-10-08 15:45:38 -07:00
Corey Richardson
35579afb55 Remove unused variable and branch (reported by clang-analzyer) 2012-10-08 15:45:38 -07:00
Jason Evans
dd03a2e377 Define LG_QUANTUM for hppa.
Submitted by Jory Pratt.
2012-10-08 15:41:06 -07:00
Jason Evans
5c710cee78 Remove const from __*_hook variable declarations.
Remove const from __*_hook variable declarations, so that glibc can
modify them during process forking.
2012-05-23 16:09:22 -07:00
Jason Evans
f1966e1dc7 Update a comment. 2012-05-16 00:35:08 -07:00
Jason Evans
174b70efb4 Disable tcache by default if running inside Valgrind.
Disable tcache by default if running inside Valgrind, in order to avoid
making unallocated objects appear reachable to Valgrind.
2012-05-15 23:31:53 -07:00
Jason Evans
781fe75e0a Auto-detect whether running inside Valgrind.
Auto-detect whether running inside Valgrind, thus removing the need to
manually specify MALLOC_CONF=valgrind:true.
2012-05-15 14:48:14 -07:00
Jason Evans
3860eac170 Fix heap profiling crash for realloc(p, 0) case.
Fix prof_realloc() to not call prof_ctx_set() if a sampled object is
being freed via realloc(p, 0).
2012-05-15 13:56:28 -07:00
Jason Evans
fc9b1dbf69 Merge branch 'dev'
Conflicts:
	ChangeLog
	include/jemalloc/internal/chunk.h
	src/chunk.c
	src/huge.c
	src/jemalloc.c
	test/rallocm.c
2012-05-11 17:48:33 -07:00
Jason Evans
cbb71caceb Update ChangeLog for 3.0.0. 2012-05-11 17:42:50 -07:00
Jason Evans
58ad1e4956 Return early in _malloc_{pre,post}fork() if uninitialized.
Avoid mutex operations in _malloc_{pre,post}fork() unless jemalloc has
been initialized.

Reported by David Xu.
2012-05-11 17:40:16 -07:00
Jason Evans
d8ceef6c55 Fix large calloc() zeroing bugs.
Refactor code such that arena_mapbits_{large,small}_set() always
preserves the unzeroed flag, and manually manipulate the unzeroed flag
in the one case where it actually gets reset (in arena_chunk_purge()).
This fixes unzeroed preservation bugs in arena_run_split() and
arena_ralloc_large_grow().  These bugs caused large calloc() to return
non-zeroed memory under some circumstances.
2012-05-10 21:49:43 -07:00
Jason Evans
30fe12b866 Add arena chunk map assertions. 2012-05-10 21:49:43 -07:00
Jason Evans
5b0c99649f Refactor arena_run_alloc().
Refactor duplicated arena_run_alloc() code into
arena_run_alloc_helper().
2012-05-10 21:49:43 -07:00
Jason Evans
53bd42c1fe Update a comment. 2012-05-10 00:18:46 -07:00
Jason Evans
80fe0478e6 Generalize "stats.mapped" documentation.
Generalize "stats.mapped" documentation to state that all inactive
chunks are omitted, now that it is possible for mmap'ed chunks to be
omitted in addition to DSS chunks.
2012-05-09 23:08:48 -07:00
Mike Hommey
37b6f95dcd Export je_memalign and je_valloc
da99e31 removed attributes on je_memalign and je_valloc, while they didn't
have a definition in the jemalloc.h header, thus making them non-exported.
Export them again, by defining them in the jemalloc.h header.
2012-05-09 16:17:01 -07:00
Mike Hommey
a6770a7049 Remove -fno-common compiler flag for OS X.
It doesn't allow the je_malloc_message and je_malloc_conf symbols to be
overridden when linking statically.
2012-05-09 16:16:48 -07:00
Jason Evans
2e671ffbad Add the --enable-mremap option.
Add the --enable-mremap option, and disable the use of mremap(2) by
default, for the same reason that freeing chunks via munmap(2) is
disabled by default on Linux: semi-permanent VM map fragmentation.
2012-05-09 16:12:00 -07:00
Jason Evans
374d26a43b Fix chunk_recycle() to stop leaking trailing chunks.
Fix chunk_recycle() to correctly compute trailsize and re-insert
trailing chunks.  This fixes a major virtual memory leak.

Simplify chunk_record() to avoid dropping/re-acquiring chunks_mtx.
2012-05-09 14:48:35 -07:00
Jason Evans
de6fbdb72c Fix chunk_alloc_mmap() bugs.
Simplify chunk_alloc_mmap() to no longer attempt map extension.  The
extra complexity isn't warranted, because although in the success case
it saves one system call as compared to immediately falling back to
chunk_alloc_mmap_slow(), it also makes the failure case even more
expensive.  This simplification removes two bugs:

- For Windows platforms, pages_unmap() wasn't being called for unaligned
  mappings prior to falling back to chunk_alloc_mmap_slow().  This
  caused permanent virtual memory leaks.
- For non-Windows platforms, alignment greater than chunksize caused
  pages_map() to be called with size 0 when attempting map extension.
  This always resulted in an mmap() error, and subsequent fallback to
  chunk_alloc_mmap_slow().
2012-05-09 13:05:04 -07:00
Jason Evans
34a8cf6c40 Fix a base allocator deadlock.
Fix a base allocator deadlock due to chunk_recycle() calling back into
the base allocator.
2012-05-02 20:41:42 -07:00
Mike Hommey
c584fc75bb Don't use sizeof() on a VARIABLE_ARRAY
In the alloca() case, this fails to be the right size.
2012-05-02 16:33:19 -07:00
Mike Hommey
1d01206bbc Use "standard" printf prefixes instead of MSVC ones in inttypes.h
We don't use MSVC's printf, but ours, and it doesn't support the I32 and I64
prefixes.
2012-05-02 16:32:37 -07:00
Mike Hommey
79c4bca7d1 Use "hardcoded" dependencies when compiler doesn't support -MM 2012-05-02 16:31:17 -07:00
Mike Hommey
3597e91482 Allow je_malloc_message to be overridden when linking statically
If an application wants to override je_malloc_message, it is better to define
the symbol locally than to change its value in main(), which might be too late
for various reasons.

Due to je_malloc_message being initialized in util.c, statically linking
jemalloc with an application defining je_malloc_message fails due to
"multiple definition of" the symbol.

Defining it without a value (like je_malloc_conf) makes it more easily
overridable.
2012-05-02 16:25:41 -07:00
Jason Evans
80737c3323 Further optimize and harden arena_salloc().
Further optimize arena_salloc() to only look at the binind chunk map
bits in the common case.

Add more sanity checks to arena_salloc() that detect chunk map
inconsistencies for large allocations (whether due to allocator bugs or
application bugs).
2012-05-02 16:11:03 -07:00
Mike Hommey
7bfecf412d Check for VALGRIND_RESIZEINPLACE_BLOCK support
VALGRIND_RESIZEINPLACE_BLOCK was added in valgrind 3.7. Unfortunately, the
__VALGRIND_MINOR__ macro still says 6 in 3.7 :(
2012-05-02 03:24:21 -07:00
Jason Evans
1b523da21c Fix partial rename of s/EXPORT/JEMALLOC_EXPORT/g. 2012-05-02 03:02:53 -07:00
Jason Evans
9a7944f8ab Update private namespace mangling. 2012-05-02 02:16:51 -07:00
Jason Evans
889ec59bd3 Make malloc_write() non-inline.
Make malloc_write() non-inline, in order to resolve its dependency on
je_malloc_write().
2012-05-02 02:08:03 -07:00
Jason Evans
8d5865eb57 Make CACHELINE a raw constant.
Make CACHELINE a raw constant in order to work around a
__declspec(align()) limitation.

Submitted by Mike Hommey.
2012-05-02 01:22:16 -07:00
Jason Evans
203484e2ea Optimize malloc() and free() fast paths.
Embed the bin index for small page runs into the chunk page map, in
order to omit [...] in the following dependent load sequence:
  ptr-->mapelm-->[run-->bin-->]bin_info

Move various non-critcal code out of the inlined function chain into
helper functions (tcache_event_hard(), arena_dalloc_small(), and
locking).
2012-05-02 00:30:36 -07:00
Mike Hommey
fd97b1dfc7 Add support for MSVC
Tested with MSVC 8 32 and 64 bits.
2012-05-01 11:32:11 -07:00
Mike Hommey
b45c57ecaf Import msinttypes
http://code.google.com/p/msinttypes/
2012-05-01 11:16:10 -07:00
Mike Hommey
da99e31105 Replace JEMALLOC_ATTR with various different macros when it makes sense
Theses newly added macros will be used to implement the equivalent under
MSVC. Also, move the definitions to headers, where they make more sense,
and for some, are even more useful there (e.g. malloc).
2012-04-30 17:57:31 -07:00
Mike Hommey
7cdea3973c Few configure.ac adjustments
- Use the extensions autoconf finds for object and executable files.
- Remove the sorev variable, and replace SOREV definition with sorev's.
- Default to je_ prefix on win32.
2012-04-30 17:13:45 -07:00
Mike Hommey
a14bce85e8 Use Get/SetLastError on Win32
Using errno on win32 doesn't quite work, because the value set in a shared
library can't be read from e.g. an executable calling the function setting
errno.

At the same time, since buferror always uses errno/GetLastError, don't pass
it.
2012-04-30 16:50:55 -07:00