Cheri-research/snmalloc
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
106 Commits 1 Branch 0 Tags
d588e8ecb1dd8f701439d299df5099493f7f2541
Commit Graph

106 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Matthew Parkinson
d588e8ecb1 Updated to match documentation. 2019-02-19 15:00:55 +00:00
Matthew Parkinson
ccccd686fb Merge pull request #16 from Microsoft/Sizeclass 
Simplified sizeclass calculations and added tests.
 2019-02-19 13:07:08 +00:00
Matthew Parkinson
aac2b9212e Merge pull request #21 from plietar/smart-next 
Place the next pointer at a different place on every object.
 2019-02-19 09:04:23 +00:00
Paul Liétar
ffe496dd18 Address review comments. 2019-02-18 21:29:32 +00:00
Paul Liétar
66400af419 Add a cache-friendly version of the tests. 
This only tests CACHE_FRIENDLY_OFFSET=64, which is probably what we'll be using in the end.
 2019-02-18 14:51:04 +00:00
Paul Liétar
4ac3421487 Place the next pointer at a different place on every object. 
This limits the collision in cache buckets, especially for larger objects.
 2019-02-18 14:22:50 +00:00
David Chisnall
c47eed1922 Tweaks to end bounds checking. 
Introduce a `OnePastEnd` option for the pointer immediately after the
end of the allocation.  This simplifies some of the logic in callers,
where they wants to say 'is base + length safe to use?'.

Also restructure some of the other logic somewhat.
 2019-02-15 20:05:00 +01:00
Theo Butler
9a6b0aef1f Merge pull request #23 from Microsoft/comment 
Fix comment to represent current PAL API.
 2019-02-15 13:42:59 -05:00
Matthew Parkinson
5e149b083f One more constexpr 2019-02-15 17:43:27 +00:00
Matthew Parkinson
8698f87018 Added some constexpr to some ifs. 2019-02-15 16:12:38 +00:00
Matthew Parkinson
c02077a06a Bug fix in umul code for 32-bit Win 2019-02-15 14:36:47 +00:00
Matthew Parkinson
e7d90966f6 Made the malloc tests run on Windows 2019-02-15 14:36:47 +00:00
Matthew Parkinson
ac8e5e4e5b Fix comment to represent current PAL API. 2019-02-15 09:24:01 +00:00
Matthew Parkinson
bf58015c25 Merge pull request #20 from Theodus/malloc-tests 
Add malloc tests
 2019-02-15 09:12:07 +00:00
Theo Butler
a3fb2b9531 cleanup some tests 2019-02-14 22:31:45 -05:00
Theo Butler
d2909eed0a Merge branch 'master' into malloc-tests 2019-02-14 22:30:48 -05:00
Theo Butler
90414f82f6 Merge pull request #22 from Microsoft/zero_bug 
Pal zero bug alignment
 2019-02-14 22:26:18 -05:00
Matthew Parkinson
adeecfb0f1 Added bug fix to alignment of using. 2019-02-14 20:08:04 +00:00
Matthew Parkinson
8b9a525500 Added zero test at threshold. 2019-02-14 19:59:36 +00:00
Theo Butler
c555bf7218 fix doc comments for notify_using 2019-02-13 17:15:06 -05:00
Matthew Parkinson
35803305f2 Merge pull request #19 from plietar/visibility 
Make internal symbols hidden.
 2019-02-13 21:50:00 +00:00
Theo Butler
057595a57e remove -1 check in calloc 2019-02-13 16:03:38 -05:00
Theo Butler
942313fec7 replace asserts with abort 2019-02-13 10:03:41 -05:00
Theo Butler
24ba068dce remove randomness from malloc tests 2019-02-13 08:42:51 -05:00
Theo Butler
0ff2301083 use malloc shim in malloc tests 2019-02-13 08:12:07 -05:00
Theo Butler
e42551bb15 only build malloc tests on POSIX platforms 2019-02-12 22:05:36 -05:00
theodus
a9615bc6aa mark variables unused in release build 2019-02-12 20:22:10 -05:00
Theo Butler
f6497e6ee3 Add malloc tests 2019-02-12 19:50:15 -05:00
Paul Liétar
8d8761f248 Make internal symbols hidden. 
Only the malloc/free/... interface is exported.

This allows all of C++'s weak ODR symbols to be resolved at
compile-time, rather than staying weak and resolved at load-time.

Since internal calls don't need to go through the PLT anymore, we get a
nice speedup, at least on small objects.
 2019-02-12 23:27:42 +00:00
Matthew Parkinson
a7f0695776 Merge pull request #17 from plietar/fix-align 
Fix the condition on when to allocate a new block.
 2019-02-12 13:10:53 +00:00
Paul Liétar
79b432ddab Fix the condition on when to allocate a new block. 
Previously we would pretty much always allocate a new block for each
allocator, making them 16MiB aligned.
 2019-02-12 12:47:22 +00:00
Matthew Parkinson
e004641cec Added to comment. 2019-02-11 14:47:12 +00:00
Matthew Parkinson
9981bad9b5 clang format 2019-02-11 14:47:12 +00:00
Matthew Parkinson
1272078487 Simplified size class calculation 
The rounding code can be integrated directly into the sizeclass code,
which means, the code paths can be simplified slightly.

The special case for zero mantissa bits is not required, as the compiler
generates the same code from the more complex path due to
eliminating dead code after folding the constant zero through.
 2019-02-11 14:47:12 +00:00
Matthew Parkinson
fdcad7feb4 Add test for sizeclass calculations 2019-02-11 14:47:12 +00:00
David Chisnall
ccd8ec9b4f Disable rtti / exceptions on the non-Windows builds. 
RTTI makes the binaries bigger, exceptions make life harder for
optimisers.  Neither are actually used.

This doesn't preclude anything #including snmalloc.h with RTTI enabled,
it just disables it in the shim libraries and tests.

The FreeBSD libc builds were already doing this with no ill effect.
 2019-02-06 17:46:58 +00:00
Matthew Parkinson
2cd84c80b2 Build shim with 1MiB superslabs. 2019-02-06 17:08:47 +00:00
Matthew Parkinson
731757b29c Merge pull request #13 from Microsoft/matt-refactor 
Simplification around remote allocation
 2019-02-06 11:25:07 +00:00
Matthew Parkinson
f3897dd3e0 Code review feedback. 2019-02-05 16:57:09 +00:00
Matthew Parkinson
83c55fe5da Simplify remote allocator. 
Don't store the sizeclass, as we can find it easily, and already are
going to touch though cache lines in the common case.
 2019-02-05 13:27:19 +00:00
Matthew Parkinson
122a5de811 Refactor code to correctly handle low bits of allocator ID. 2019-02-05 13:11:55 +00:00
David Chisnall
fc24b8be3d Merge pull request #12 from Theodus/override 
Avoid unnecessary allocation from realloc
 2019-02-03 13:30:21 +00:00
theodus
ae3f9f6aec Get alloc size without wrapper 2019-02-03 08:19:11 -05:00
theodus
2b8b4c884f Do not realloc if size is in the same sizeclass 2019-02-02 17:28:02 -05:00
theodus
85cf5dd097 Avoid unnecessary allocation from realloc 2019-02-02 14:47:06 -05:00
Matthew Parkinson
c0ceb6e08f Merge pull request #11 from Theodus/master 
Fix assertion failure in memalign
 2019-01-30 17:36:13 +00:00
theodus
61b310d9d6 Fix assertion failure in memalign 2019-01-30 12:14:16 -05:00
Matthew Parkinson
a838372989 Merge pull request #10 from Microsoft/hardening 
Hardening allocator
 2019-01-25 23:16:30 +00:00
Matthew Parkinson
ec59820970 Use placement new instead of init for metaslab. 2019-01-25 19:46:24 +00:00
Matthew Parkinson
06ff1ffe0a Renamed zero to init for metaslab. 2019-01-25 16:38:10 +00:00