Commit graph

37 commits

Author SHA1 Message Date
Matt Caswell
72a7a7021f Update copyright year
Reviewed-by: Richard Levitte <levitte@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/8347)
2019-02-26 14:05:09 +00:00
David Benjamin
2086edb799 Fix some CFI issues in x86_64 assembly
The add/double shortcut in ecp_nistz256-x86_64.pl left one instruction
point that did not unwind, and the "slow" path in AES_cbc_encrypt was
not annotated correctly. For the latter, add
.cfi_{remember,restore}_state support to perlasm.

Next, fill in a bunch of functions that are missing no-op .cfi_startproc
and .cfi_endproc blocks. libunwind cannot unwind those stack frames
otherwise.

Finally, work around a bug in libunwind by not encoding rflags. (rflags
isn't a callee-saved register, so there's not much need to annotate it
anyway.)

These were found as part of ABI testing work in BoringSSL.

Reviewed-by: Richard Levitte <levitte@openssl.org>
GH: #8109
(cherry picked from commit c0e8e5007b)
2019-02-17 23:41:11 +01:00
Matt Caswell
83cf7abf8e Update copyright year
Reviewed-by: Richard Levitte <levitte@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/6371)
2018-05-29 13:16:04 +01:00
Andy Polyakov
774ff8fed6 bn/asm/*-mont.pl: harmonize with BN_from_montgomery_word.
Montgomery multiplication post-conditions in some of code paths were
formally non-constant time. Cache access pattern was result-neutral,
but a little bit asymmetric, which might have produced a signal [if
processor reordered load and stores at run-time].

Reviewed-by: Rich Salz <rsalz@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/6141)
2018-05-02 21:55:21 +02:00
Josh Soref
46f4e1bec5 Many spelling fixes/typo's corrected.
Around 138 distinct errors found and fixed; thanks!

Reviewed-by: Kurt Roeckx <kurt@roeckx.be>
Reviewed-by: Tim Hudson <tjh@openssl.org>
Reviewed-by: Rich Salz <rsalz@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/3459)
2017-11-11 19:03:10 -05:00
Andy Polyakov
668a709a8d bn/asm/x86_64-mont5.pl: fix carry bug in bn_sqrx8x_internal.
Credit to OSS-Fuzz for finding this.

CVE-2017-3736

Reviewed-by: Rich Salz <rsalz@openssl.org>
2017-11-02 11:00:48 +00:00
David Benjamin
25b802bb85 Fix typo in x86_64-mont5.pl CFI directives
Reviewed-by: Kurt Roeckx <kurt@openssl.org>
Reviewed-by: Andy Polyakov <appro@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/2655)
2017-02-17 10:32:13 +01:00
Adam Langley
3f55ec6792 Fix copy-pasteism in CFI directives.
I don't think this actually affects anything since the cfi_restore
directives aren't strictly needed anyway. (The old values are still in
memory so either will do.)

CLA: trivial

Reviewed-by: Rich Salz <rsalz@openssl.org>
Reviewed-by: Andy Polyakov <appro@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/2582)
2017-02-10 20:28:28 +01:00
Andy Polyakov
76e624a003 bn/asm/x86_64*: add DWARF CFI directives.
Reviewed-by: Rich Salz <rsalz@openssl.org>
2017-02-09 20:05:16 +01:00
Andy Polyakov
384e6de4c7 x86_64 assembly pack: Win64 SEH face-lift.
- harmonize handlers with guidelines and themselves;
- fix some bugs in handlers;
- add missing handlers in chacha and ecp_nistz256 modules;

Reviewed-by: Rich Salz <rsalz@openssl.org>
2017-02-06 08:21:42 +01:00
Andy Polyakov
3f4bcf5bb6 bn/asm/x86_64-mont5.pl: fix carry bug in bn_sqr8x_internal.
CVE-2017-3732

Reviewed-by: Rich Salz <rsalz@openssl.org>
2017-01-26 10:54:01 +00:00
David Benjamin
609b0852e4 Remove trailing whitespace from some files.
The prevailing style seems to not have trailing whitespace, but a few
lines do. This is mostly in the perlasm files, but a few C files got
them after the reformat. This is the result of:

  find . -name '*.pl' | xargs sed -E -i '' -e 's/( |'$'\t'')*$//'
  find . -name '*.c' | xargs sed -E -i '' -e 's/( |'$'\t'')*$//'
  find . -name '*.h' | xargs sed -E -i '' -e 's/( |'$'\t'')*$//'

Then bn_prime.h was excluded since this is a generated file.

Note mkerr.pl has some changes in a heredoc for some help output, but
other lines there lack trailing whitespace too.

Reviewed-by: Kurt Roeckx <kurt@openssl.org>
Reviewed-by: Matt Caswell <matt@openssl.org>
2016-10-10 23:36:21 +01:00
Andy Polyakov
3ba1ef829c bn/asm/x86[_64]-mont*.pl: implement slightly alternative page-walking.
Original strategy for page-walking was adjust stack pointer and then
touch pages in order. This kind of asks for double-fault, because
if touch fails, then signal will be delivered to frame above adjusted
stack pointer. But touching pages prior adjusting stack pointer would
upset valgrind. As compromise let's adjust stack pointer in pages,
touching top of the stack. This still asks for double-fault, but at
least prevents corruption of neighbour stack if allocation is to
overstep the guard page.

Also omit predict-non-taken hints as they reportedly trigger illegal
instructions in some VM setups.

Reviewed-by: Richard Levitte <levitte@openssl.org>
2016-08-22 14:58:32 +02:00
Andy Polyakov
cfe1d9929e x86_64 assembly pack: tolerate spaces in source directory name.
[as it is now quoting $output is not required, but done just in case]

Reviewed-by: Richard Levitte <levitte@openssl.org>
2016-05-29 14:12:51 +02:00
Rich Salz
6aa36e8e5a Add OpenSSL copyright to .pl files
Reviewed-by: Richard Levitte <levitte@openssl.org>
2016-05-21 08:23:39 -04:00
Emilia Kasper
0a86f66821 On Windows, page walking is known as __chkstk.
Reviewed-by: Andy Polyakov <appro@openssl.org>
2016-03-15 23:56:23 +01:00
Emilia Kasper
1bf80d9302 Explain *cough*-dows
Reviewed-by: Andy Polyakov <appro@openssl.org>
2016-03-15 23:56:17 +01:00
Andy Polyakov
adc4f1fc25 bn/asm/x86[_64]-mont*.pl: complement alloca with page-walking.
Some OSes, *cough*-dows, insist on stack being "wired" to
physical memory in strictly sequential manner, i.e. if stack
allocation spans two pages, then reference to farmost one can
be punishable by SEGV. But page walking can do good even on
other OSes, because it guarantees that villain thread hits
the guard page before it can make damage to innocent one...

Reviewed-by: Rich Salz <rsalz@openssl.org>
2016-03-07 14:58:14 +01:00
Andy Polyakov
317be63875 bn/asm/x86_64-mont5.pl: unify gather procedure in hardly used path
and reorganize/harmonize post-conditions.

Additional hardening following on from CVE-2016-0702

Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: Rich Salz <rsalz@openssl.org>
2016-03-01 13:34:22 +00:00
Andy Polyakov
8fc8f486f7 crypto/bn/x86_64-mont5.pl: constant-time gather procedure.
At the same time remove miniscule bias in final subtraction.
Performance penalty varies from platform to platform, and even with
key length. For rsa2048 sign it was observed to be 4% for Sandy
Bridge and 7% on Broadwell.

CVE-2016-0702

Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: Rich Salz <rsalz@openssl.org>
2016-03-01 13:34:22 +00:00
Andy Polyakov
b974943234 x86_64 assembly pack: tune clang version detection even further.
RT#4171

Reviewed-by: Kurt Roeckx <kurt@openssl.org>
2015-12-13 22:18:18 +01:00
Andy Polyakov
29851264f1 bn/asm/x86_64-mont5.pl: fix carry propagating bug (CVE-2015-3193).
Reviewed-by: Richard Levitte <levitte@openssl.org>
2015-12-03 13:12:01 +00:00
Andy Polyakov
76eba0d94b x86_64 assembly pack: tune clang version detection.
RT#4142

Reviewed-by: Richard Levitte <levitte@openssl.org>
2015-11-23 16:00:06 +01:00
Andy Polyakov
69567687b0 bn/asm/x86_64-mont5.pl: fix valgrind error.
bn_get_bits5 was overstepping array boundary by 1 byte. It was exclusively
read overstep and data could not have been used. The only potential problem
would be if array happens to end on the very edge of last accesible page.

Reviewed-by: Richard Levitte <levitte@openssl.org>
2015-05-24 21:30:39 +02:00
Andy Polyakov
569e2d1257 crypto/bn/asm/x86_64-mont*.pl: add missing clang detection.
Reviewed-by: Rich Salz <rsalz@openssl.org>
2014-09-12 00:44:51 +02:00
Andy Polyakov
1b0fe79f3e x86_64 assembly pack: improve masm support. 2014-07-09 20:08:01 +02:00
Andy Polyakov
eedab5241e bn/asm/x86_64-mont5.pl: fix compilation error on Solaris. 2014-01-09 13:44:59 +01:00
Andy Polyakov
ec9cc70f72 bn/asm/x86_64-mont5.pl: add MULX/AD*X code path.
This also eliminates code duplication between x86_64-mont and x86_64-mont
and optimizes even original non-MULX code.
2013-12-09 21:02:24 +01:00
Andy Polyakov
c5d5f5bd0f bn/asm/x86_64-mont5.pl: comply with Win64 ABI.
PR: 3189
Submitted by: Oscar Ciurana
2013-12-03 23:59:55 +01:00
Andy Polyakov
30b9c2348d bn/asm/*x86_64*.pl: correct assembler requirement for ad*x. 2013-10-14 22:41:00 +02:00
Andy Polyakov
a5bb5bca52 bn/asm/x86_64-mont*.pl: add MULX/ADCX/ADOX code path. 2013-10-03 00:45:04 +02:00
Andy Polyakov
4568182a8b x86_64 assembly pack: keep making Windows build more robust.
PR: 2963 and a number of others
2013-02-02 19:54:59 +01:00
Andy Polyakov
6251989eb6 x86_64 assembly pack: make it possible to compile with Perl located on
path with spaces.

PR: 2835
2012-06-27 10:08:23 +00:00
Andy Polyakov
8329e2e776 bn_exp.c: further optimizations using more ideas from
http://eprint.iacr.org/2011/239.
2011-10-17 17:41:49 +00:00
Bodo Möller
cdfe0fdde6 Fix OPENSSL_BN_ASM_MONT5 for corner cases; add a test.
Submitted by: Emilia Kasper
2011-10-13 12:35:10 +00:00
Andy Polyakov
e7d1363d12 x86_64-mont5.pl: add missing Win64 support. 2011-08-14 09:06:06 +00:00
Andy Polyakov
361512da0d This commit completes recent modular exponentiation optimizations on
x86_64 platform. It targets specifically RSA1024 sign (using ideas
from http://eprint.iacr.org/2011/239) and adds more than 10% on most
platforms. Overall performance improvement relative to 1.0.0 is ~40%
in average, with best result of 54% on Westmere. Incidentally ~40%
is average improvement even for longer key lengths.
2011-08-12 16:44:32 +00:00