- 18 2月, 2016 16 次提交
-
-
由 Matt Caswell 提交于
Certain code paths in tls_decrypt_ticket could return early without first freeing the HMAC_CTX or the EVP_CIPHER_CTX. Reviewed-by: NRich Salz <rsalz@openssl.org>
-
由 Zhao Junwang 提交于
As handshake_func is a function pointer, it should compare to NULL Signed-off-by: NRich Salz <rsalz@openssl.org> Reviewed-by: NMatt Caswell <matt@openssl.org>
-
由 Dr. Stephen Henson 提交于
Reviewed-by: NRich Salz <rsalz@openssl.org>
-
由 Rich Salz 提交于
Thanks to Viktor for additional review. Reviewed-by: NRichard Levitte <levitte@openssl.org>
-
由 Richard Levitte 提交于
Reviewed-by: NRich Salz <rsalz@openssl.org>
-
由 Richard Levitte 提交于
Reviewed-by: NRich Salz <rsalz@openssl.org>
-
由 Richard Levitte 提交于
Reviewed-by: NRich Salz <rsalz@openssl.org>
-
由 Richard Levitte 提交于
The reason is that we use hstrerror() and other resolver functions. Reporter: Erik Forsberg <erik@efca.com> Reviewed-by: NRich Salz <rsalz@openssl.org>
-
由 David Woodhouse 提交于
Reviewed-by: NTim Hudson <tjh@openssl.org>
-
由 Richard Levitte 提交于
"or" has lower priority than "||" and works better to have Perl less confused. Reviewed-by: NRich Salz <rsalz@openssl.org>
-
由 Richard Levitte 提交于
It's near impossible to figure out what goes wrong with the execution of sub-commands otherwise. Reviewed-by: NRich Salz <rsalz@openssl.org>
-
由 David Woodhouse 提交于
Although I explicitly don't care about the tinfoil-hat reason given in the initial opening of RT#3628, that "paths usually contain private information", there *are* situations where it's useful to eliminate the filenames from the compiled binary. The two reasons we do care about in the context of firmware such as EDK2 are that it allows for a smaller footprint, and it is also a necessary component of a binary-reproducible build. To that end, introduce OPENSSL_FILE and OPENSSL_LINE macros, defining them to __FILE__ and __LINE__ respectively in the normal case, but to "" and 0 when OPENSSL_NO_FILENAMES is set. This is mostly a naïve invocation of $ sed 's/__\([FL]I[NL]E\)__/OPENSSL_\1/g' -i `git grep -l __LINE__` but with a few instances change to just print the function name instead (although those probably need to die anyway) and test cases left untouched. Signed-off-by: NRich Salz <rsalz@openssl.org> Reviewed-by: NTim Hudson <tjh@openssl.org>
-
由 Richard Levitte 提交于
For example, this works instead of giving a big error message (note the lack of '--unified'): mkdir ../_build (cd ../_build/; ../openssl-src/config; make) Reviewed-by: NAndy Polyakov <appro@openssl.org>
-
由 Richard Levitte 提交于
The previous fix wasn't right. Also, change all (^|\s) and (\s|$) constructs to (?:^|\s) and (?:\s|$). Perl seems to like that better. Reviewed-by: NAndy Polyakov <appro@openssl.org>
-
由 Rich Salz 提交于
When OPENSSL_NO_ASYNC is set, make ASYNC_{un,}block_pause() do nothing. This prevents md_rand.c from failing to build. Probably better to do it this way than to wrap every instance in an explicit #ifdef. A bunch of new socket code got added to a new file crypto/bio/b_addr.c. Make it all go away if OPENSSL_NO_SOCK is defined. Allow configuration with no-ripemd, no-ts, no-ui We use these for the UEFI build. Also remove the 'Really???' comment from no-err and no-locking. We use those too. We need to drop the crypto/engine directory from the build too, and also set OPENSSL_NO_ENGINE Signed-off-by: NRich Salz <rsalz@openssl.org> Reviewed-by: NTim Hudson <tjh@openssl.org>
-
由 Dr. Stephen Henson 提交于
Reviewed-by: NMatt Caswell <matt@openssl.org>
-
- 17 2月, 2016 11 次提交
-
-
由 David Woodhouse 提交于
Commit e634b448 ("Defines OSSL_SSIZE_MAX") introduced a definition of OSSL_SSIZE_MAX which broke the UEFI build. Fix that by making UEFI take the same definition as Ultrix (ssize_t == int). Signed-off-by: NRich Salz <rsalz@openssl.org> Reviewed-by: NMatt Caswell <matt@openssl.org>
-
由 David Woodhouse 提交于
We don't have atexit() in the EDK2 environment. Firmware never exits. Signed-off-by: NRich Salz <rsalz@openssl.org> Reviewed-by: NMatt Caswell <matt@openssl.org>
-
由 Rich Salz 提交于
Reviewed-by: NViktor Dukhovni <viktor@openssl.org>
-
由 David Woodhouse 提交于
Commit 05c7b163 ("Implement the use of heap manipulator implementions") added 'file' and 'line' arguments to CRYPTO_free() and friends, but neglected to fix up the !IMPLEMENTED case within CRYPTO_secure_free(). Add the missing arguments there too. Signed-off-by: NRich Salz <rsalz@openssl.org> Reviewed-by: NMatt Caswell <matt@openssl.org>
-
由 Richard Levitte 提交于
Switching it to use OPENSSL_free() et al when appropriate. Reviewed-by: NMatt Caswell <matt@openssl.org>
-
由 Dmitry-Me 提交于
Reviewed-by: NMatt Caswell <matt@openssl.org> Reviewed-by: NRichard Levitte <levitte@openssl.org>
-
由 Richard Levitte 提交于
Reviewed-by: NRich Salz <rsalz@openssl.org>
-
由 Richard Levitte 提交于
- Make use of the functions given through CRYPTO_set_mem_functions(). - CRYPTO_free(), CRYPTO_clear_free() and CRYPTO_secure_free() now receive __FILE__ and __LINE__. - The API for CRYPTO_set_mem_functions() and CRYPTO_get_mem_functions() is slightly changed, the implementation for free() now takes a couple of extra arguments, taking __FILE__ and __LINE__. - The CRYPTO_ memory functions will *always* receive __FILE__ and __LINE__ from the corresponding OPENSSL_ macros, regardless of if crypto-mdebug has been enabled or not. The reason is that if someone swaps out the malloc(), realloc() and free() implementations, we can't know if they will use them or not. Reviewed-by: NRich Salz <rsalz@openssl.org>
-
由 Viktor Szakats 提交于
Signed-off-by: NRich Salz <rsalz@openssl.org> Reviewed-by: NMatt Caswell <matt@openssl.org>
-
由 Viktor Szakats 提交于
Reviewed-by: NMatt Caswell <matt@openssl.org> Reviewed-by: NRichard Levitte <levitte@openssl.org>
-
由 Richard Levitte 提交于
For orthogonality, we change sin -> s_in and sin6 -> s_in6 as well. Reviewed-by: NMatt Caswell <matt@openssl.org>
-
- 16 2月, 2016 10 次提交
-
-
由 Richard Levitte 提交于
Macro definitions "should" be found in $config{defines}, but some configs haven't transfered macro definitions from their 'cflags' settings (which isn't mandatory anyway), so check both places. Reviewed-by: NAndy Polyakov <appro@openssl.org>
-
由 Richard Levitte 提交于
This check is meaningless on VMS and only produce an error because the underlying shell (DCL) doesn't understand sh syntax such as '2>&1'. Reviewed-by: NAndy Polyakov <appro@openssl.org>
-
由 Richard Levitte 提交于
Depending on user preferences, Configure might get something like --PREFIX=blah just as well as --prefix=blah, or "SHARED" just as well as "shared". On VMS, let's therefore lowercase at least the portion of the argument before a possible equal sign. For good measure, we lowercase the arguments to be checked in config.com as well. The original argument is sent on to Configure, however. Reviewed-by: NAndy Polyakov <appro@openssl.org>
-
由 Richard Levitte 提交于
A long time ago, Solaris cc didn't seem to handle -Wl, linker options, while gcc on Solaris required it. Since then, Solaris cc has developed to understand -Wl, options, and our little dance to figure out how to pass linker options to the C compiler that's used isn't needed any more. Reviewed-by: NAndy Polyakov <appro@openssl.org>
-
由 Dr. Stephen Henson 提交于
Reviewed-by: NMatt Caswell <matt@openssl.org>
-
由 Dr. Stephen Henson 提交于
Reviewed-by: NMatt Caswell <matt@openssl.org>
-
由 Dr. Stephen Henson 提交于
Reviewed-by: NMatt Caswell <matt@openssl.org>
-
由 Richard Levitte 提交于
These two functions take a separator to concatenat the strings with as first argument. Reviewed-by: NViktor Dukhovni <viktor@openssl.org>
-
由 Richard Levitte 提交于
Reviewed-by: NStephen Henson <steve@openssl.org>
-
由 Richard Levitte 提交于
Reviewed-by: NStephen Henson <steve@openssl.org>
-
- 15 2月, 2016 3 次提交
-
-
由 Richard Levitte 提交于
Reported in GH#684 Reviewed-by: NMatt Caswell <matt@openssl.org>
-
由 Rich Salz 提交于
Combination of heartbeats and unit-tests. Reviewed-by: NRichard Levitte <levitte@openssl.org>
-
由 Richard Levitte 提交于
That variable isn't for us, it's for any user, distributor or package builder that wants one after the section number. "ssl" seems to be popular... Reviewed-by: NMatt Caswell <matt@openssl.org>
-