mirrors/mimalloc
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,433 Commits 21 Branches 59 Tags 7.4 MiB
1ca48210fb
Commit Graph

425 Commits

Author SHA1 Message Date
Daan
766f1f9345
Merge pull request #388 from nico-abram/patch-2 
Fix typo in comment
 2021-04-22 10:34:13 -07:00
Daan
f941015928
Merge pull request #384 from kdrag0n/fix-android-thread-id 
Fix thread ID getter on Android ARM/AArch64
 2021-04-22 10:33:53 -07:00
Jim Huang
3402c6cc3f Revise the use of macOS predefined macro 
Quoted from "Porting UNIX/Linux Applications to OS X,"[1]
* macro __MACH__ is defined if Mach system calls are supported;
* macro __APPLE__ is defined in any Apple computer.

__MACH__ is not specific to macOS since GNU/Hurd runs on a Mach-based
microkernel (gnumach) [2]. __MACH__ is defined by the compiler,
leading to potential confusions. The solution is just changing the
checked identifier (i.e. __APPLE__), so it is really used only on
macOS.

[1] https://developer.apple.com/library/archive/documentation/Porting/Conceptual/PortingUnix/compiling/compiling.html
[2] https://www.gnu.org/software/hurd/microkernel/mach/gnumach.html
 2021-04-21 15:24:02 +08:00
unknown
8311cef0d1 Fix typo in comment 
it -> if in mimalloc-types.h
 2021-04-17 15:08:25 -03:00
Danny Lin
ad2fa2bf6f
Fix thread ID getter on Android ARM/AArch64 
Android's Bionic libc stores the thread ID in TLS slot 1 instead of 0
on 32-bit ARM and AArch64. Slot 0 contains a pointer to the ELF DTV
(Dynamic Thread Vector) instead, which is constant for each loaded DSO.

Because mimalloc uses the thread ID to determine whether operations are
thread-local or cross-thread (atomic), all threads having the same ID
causes internal data structures to get corrupted quickly when multiple
threads are using the allocator:

mimalloc: assertion failed: at "external/mimalloc/src/page.c":563, mi_page_extend_free
  assertion: "page->local_free == NULL"
mimalloc: assertion failed: at "external/mimalloc/src/page.c":74, mi_page_is_valid_init
  assertion: "page->used <= page->capacity"
mimalloc: assertion failed: at "external/mimalloc/src/page.c":100, mi_page_is_valid_init
  assertion: "page->used + free_count == page->capacity"
mimalloc: assertion failed: at "external/mimalloc/src/page.c":74, mi_page_is_valid_init
  assertion: "page->used <= page->capacity"

Add support for Android's alternate TLS layout to fix the crashes in
multi-threaded use cases.

Fixes #376.
 2021-04-07 01:59:47 -07:00
Daan Leijen
985f313b35 bump version to 1.7.1 2021-04-06 10:56:26 -07:00
Daan Leijen
71ac98ab08 rename <Windows.h> include to <windows.h> for mingw compatibility (see pr #367) 2021-02-22 13:04:11 -08:00
Daan Leijen
331491e1e8 build fix for Apple M1 (issue #354 and pr #356) 2021-02-02 10:46:30 -08:00
Daan Leijen
a7c33a3b0e fix getting the unique thread id on the Apple M1, see issue #354. 2021-02-01 15:47:22 -08:00
Daan Leijen
92ead2d880 bump version to 1.7.0 2021-01-31 13:51:19 -08:00
Daan Leijen
35c1fc2be9 limit memcpy as rep stosb to windows where the cpu supporst FSRM; add mi_memcpy_aligned for machine-word aligned copy. see issue #201 and pr #253 2021-01-30 14:33:46 -08:00
Daan Leijen
92ec493a5d possible fix for aligment warning (issue #341) 2021-01-29 16:21:50 -08:00
Daan Leijen
0a06884732 ensure memcpy with rep stosb is only used on windows 2021-01-29 16:09:09 -08:00
Daan
9b966c3492
Merge pull request #253 from haneefmubarak/memcpy-rep-movsb-windows-201 
resolve #201 with a platform-selective REP MOVSB implementation
 2021-01-29 16:00:00 -08:00
Daan
b759bcf5c7
Merge pull request #329 from asl/mi_stat_agg 
Unify statistics collection
 2021-01-29 12:52:29 -08:00
Daan Leijen
78ce716e2d add comment on use of tpidrro_el0 on macOS 2021-01-28 17:36:56 -08:00
Daan Leijen
8d4444ef00 remove spurious parenthesis (#350) 2021-01-28 17:36:35 -08:00
Daan
d9ae916a74
Merge pull request #350 from mr-c/patch-1 
add/improve atomic yields for SSE2, ARM*, PowerPC
 2021-01-28 17:29:54 -08:00
Uwe L. Korn
a753084f74 Use APPLE instead of MACH 2021-01-28 11:38:38 +01:00
Michael R. Crusoe
fb66ebea1d
add/improve atomic yields for SSE2, ARM*, PowerPC 2021-01-23 16:45:47 +01:00
Uwe L. Korn
88330cfc9f Use __APPLE__ instead of __MACH__ 2021-01-22 17:06:43 +01:00
Uwe L. Korn
ab3dac04c2 Use tpidrro_el0 for thread local storage in macOS-arm64 
Fixes #343
 2020-12-30 21:49:41 +01:00
Daan
03503ea4e5
Merge pull request #339 from devnexen/spin_impl_upd 
Restricts cpu yield instructions a little.
 2020-12-17 14:06:23 -08:00
Daan
33614cc054
Merge pull request #342 from wsmoses/fix2 
Fix strndup override
 2020-12-17 14:06:01 -08:00
Daan Leijen
bb386025b5 update override on macOS with interpose of malloc_default_zone (issues #313) 2020-12-15 16:03:54 -08:00
William S. Moses
30fc86cca9 Fix strndup override 2020-12-13 01:50:31 -05:00
David Carlier
33a10b4860 Restricts cpu yield instructions a little. 
adding clobber for ARM and preventing older 32 bits chips not supporting this instruction.
 2020-12-12 12:19:04 +00:00
Daan
9d0555c65b
Merge pull request #326 from asl/mi_stat_counter 
Honour MI_STAT in couple more places
 2020-12-10 11:53:30 -08:00
Daan
56a1c852ea
Merge pull request #325 from asl/max-error-counter 
Do not use the same counter for warnings and errors
 2020-12-10 10:23:08 -08:00
Daan
5bbe1c0216
Merge pull request #323 from devnexen/dfbsd_build_fix 
DragonFly support fix (for 5.8.x and forward).
 2020-12-10 10:19:05 -08:00
Daan
8b8011b4f0
Merge pull request #322 from Kokokokoka/x32_patch 
fix for x32 builds
 2020-12-10 10:14:04 -08:00
Anton Korobeynikov
765fc9c0ca Unify statistic collection: 
- For MI_STAT == 0 no allocation stats are collected
  - For MI_STAT == 1 only aggregated values (across normal, large and huge heaps) are collected
  - For MI_STAT == 1 separate per-bin collection for normal heap is done as well
 2020-11-11 11:41:39 +03:00
Anton Korobeynikov
00fb89f771 Rename the field 2020-11-11 11:41:33 +03:00
Anton Korobeynikov
39bcf8a6b0 Honour MI_STAT in couple more places. 2020-11-02 00:14:02 +03:00
Anton Korobeynikov
9c45221243 Do not use the same counter for warnings and errors. 
Warnings happen normally and could be safely ignored in the most cases,
however errors, if enabled, should not be ignored. Currently since warnings
and errors share the same counter we effectively stop showing errors after
16 warnings (which happen all the time).

Use different counters for errors and warnings.
 2020-11-01 23:57:42 +03:00
David Carlier
e6c2fd44fc DragonFly support fix (for 5.8.x and forward). 
The pthread slot approach is somewhat buggy (pretty visible
 with the stress unit test which segfault more or less randomly,
 but the stats never show up).
Using the default approach instead, the test passes eventough
 it s relatively slow (e.g 1.5 sec on FreeBSD vs 4.5 on DragonFly with same
 machine).
 2020-10-22 11:15:37 +01:00
Vasya B
cb45e3c6b1 fix for x32 builds 2020-10-19 21:00:16 +00:00
daan
13a4030619 bump version to 1.6.7 2020-09-24 16:30:40 -07:00
daan
9d5098c705 bump version to 1.6.7 for further development 2020-09-24 10:16:40 -07:00
daan
6adb919085 bump version to 1.6.6 2020-09-24 10:14:10 -07:00
daan
f88b4b4c27 extend mi_process_info to include elapsed time 2020-09-24 10:13:25 -07:00
daan
d0d3634143 bump version for further development 2020-09-24 09:29:37 -07:00
daan
c05302f097 Merge branch 'dev' into dev-exp 2020-09-24 09:11:49 -07:00
daan
64a3d24dcd bump version to 1.6.5 2020-09-23 20:00:23 -07:00
daan
8607ff617c add environment option mi_reserve_os_memory 2020-09-08 17:16:31 -07:00
daan
364674185e add option to limit OS allocation and only allow allocation from arenas 2020-09-08 16:56:51 -07:00
daan
14b8d27386 track pinned memory separately from large os pages 2020-09-08 16:46:03 -07:00
daan
c86459afef split bitmap code into separate header and source file 2020-09-08 10:14:13 -07:00
daan
30b993ecf3 consolidate bit scan operations 2020-09-08 09:27:57 -07:00
daan
c7272afa9a add mi_reserve_os_memory/mi_manage_os_memory; allow arena allocations to cross multiple bitmap fields 2020-09-07 21:34:34 -07:00
daan
46ee8952eb update mi_process_info to not use doubles 2020-09-06 13:53:02 -07:00
daan
ee286919d9 add mi_process_info api call 2020-09-06 13:21:19 -07:00
daan
4355ab7d20 add i64 atomics 2020-09-06 13:21:02 -07:00
daan
83bd352f37 roll back previous commit (use standard C++ atomics on msvc 2020-09-05 11:29:38 -07:00
daan
102a85937e experiment with using non-c++ atomics on msvc 2020-09-05 11:27:06 -07:00
daan
2e311f341b fix msvc compilation in C mode 2020-09-05 09:37:09 -07:00
daan
50de0d2358 fix C++ compilation with new atomics 2020-09-05 09:17:42 -07:00
daan
f107acb3c8 fix __cplusplus test (pr #287) 2020-09-04 10:40:05 -07:00
daan
900c97664a merge from dev-atomic 2020-09-03 09:47:01 -07:00
daan
76a68cd7af bump version to 1.6.6 with new atomics 2020-09-03 09:45:53 -07:00
daan
b4825372ab small compilation warning fixes (extra semicolon etc) 2020-08-29 19:30:38 -07:00
daan
8033b62979 allow overriding MI_MAX_ALIGN_SIZE 2020-08-29 09:59:15 -07:00
daan
5805c39916 enable --std=c99 compilation; fix mingw compilation 2020-08-09 17:55:17 -07:00
daan
ac0c121c68 update documentation for 1.6.4 release 2020-07-27 08:55:26 -07:00
daan
ef8e5d18a6 replace atomics with C11/C++ atomics with explicit memory order; passes tsan. Issue #130 2020-07-26 18:01:33 -07:00
daan
a468430772 strengthen memory order of bit operations; insert memory fences 2020-07-26 14:19:30 -07:00
daan
a9f46dc86f reduce memory order constraints for better efficiency on ARM etc 2020-07-26 11:58:02 -07:00
daan
ebf951e851 extra checks for atomic ptr exchange; extend mi_atomic_yield for win32 2020-07-26 00:15:57 -07:00
daan
95afd0509f make segment abandoned_next atomic; tsan passes without warnings now (issue #130) 2020-07-25 23:50:22 -07:00
daan
09ade02429 bring inline with C11 atomics; no volatile and cas order of expected/desired 2020-07-25 22:52:27 -07:00
daan
e27422adca switch to using C++ atomics in MSVC as well 2020-07-25 20:55:45 -07:00
daan
afe29cb8f5 fix ub on shift, issue #279 2020-07-25 19:33:02 -07:00
daan
a9a21f39d8 fix memory order for CAS failure, issue #130 2020-07-23 15:52:02 -07:00
daan
b74caddcc1 fix memory order to acq_rel for atomic and/or, issue #130, thanks @mpoeter! 2020-07-23 15:00:49 -07:00
daan
8aa18d3661 fix TSAN warning for statistics maximum, issue #130 2020-07-22 14:16:18 -07:00
daan
444afa934f fix memory order for weak CAS, issue #130, thanks @mary3000! 2020-07-22 13:58:00 -07:00
daan
2e1b4f512d make max update in the stats atomic 2020-07-22 13:45:04 -07:00
daan
c5406f327e move include 'limits.h' outside of definition 2020-07-21 18:51:25 -07:00
David Carlier
0c550d1626 illumos support/build fix and large page support 2020-07-10 03:26:14 +01:00
Haneef Mubarak
4c45793ec1
fix __movsb typecast error MSVC 2020-05-26 16:16:19 -07:00
Haneef Mubarak
6c92690914
fix REP MOVSB doc comment typo 2020-05-26 16:08:33 -07:00
Haneef Mubarak
429025634e
resolve #201 with a platform-selective REP MOVSB implementation 2020-05-26 16:04:28 -07:00
daan
a7d2bc8ad6 edit warning messages to be more consistent 2020-05-19 10:16:28 -07:00
daan
cefc930f72 bump version to 1.6.4 for further development 2020-05-05 10:47:46 -07:00
daan
5cfdc39ff1 remove on-demand page commit option 2020-04-30 18:23:33 -07:00
Anton Korobeynikov
079b886feb Add cmake option to specify whether warnings / errors are enabled by default. 
Currently warnings / errors are enabled by default in debug build.
Otherwise they could be enabled only via environmental variable or
API option call. Add possibility to specify the default during the
build time. This simplifies e.g. integration of the library into
bigger projects as no source changes would be required.
 2020-04-28 16:44:44 +03:00
daan
3484cda169 bump version to 1.6.3 for further development 2020-04-20 18:01:39 -07:00
daan
d102882bdf bump version to 1.6.2 2020-04-20 17:59:13 -07:00
daan
69a0846478 add MI_PADDING flag to cmake to supress use of padding in debug mode 2020-04-07 10:01:18 -07:00
daan
0a3e5bb699 further fixes to compile on mingw without warnings (issue #217) 2020-04-06 10:56:53 -07:00
daan
50bfacdb71 fix mingw compilation by using export definitions (issue #217) 2020-04-06 09:53:29 -07:00
daan
cfeee53389 remove accidental include file 2020-03-16 16:44:29 -07:00
daan
7745dde8d2 allow retirement for all object sizes (issue #212) 2020-03-16 15:31:37 -07:00
daan
82684042be bump version to 1.6.1 2020-02-17 10:10:22 -08:00
daan
f2ac272baa strengthen alignment check for memalign and aligned_alloc 2020-02-17 09:59:11 -08:00
daan
67de2549cf fix build with clang-cl due to _Check_return_ (issue #200) 2020-02-14 09:40:56 -08:00
daan
8a2a52843d delete all thread owned heaps when a thread is terminated (issue #202) 2020-02-13 12:15:23 -08:00
daan
f42b8526d0 fix wrong __declspec(restrict) and __attribute__((malloc)) attributes on reallocation functions 2020-02-13 10:36:39 -08:00
daan
04f1c3b1e2 bump version to v1.6.0 2020-02-09 18:53:39 -08:00
daan
a96e94f940 change TLS slot on OpenBSD 2020-02-02 22:46:38 -08:00