This addresses only those cases that are easy to fix by adding or
moving a const qualifier or removing an unnecessary cast.  There are
many more complicated cases remaining.

A password containing a character with the high bit set was misprocessed
on machines where char is signed (which is most).  This could cause the
preceding one to three characters to fail to affect the hashed result,
thus weakening the password.  The result was also unportable, and failed
to match some other blowfish implementations such as OpenBSD's.

Since the fix changes the output for such passwords, upstream chose
to provide a compatibility hack: password salts beginning with $2x$
(instead of the usual $2a$ for blowfish) are intentionally processed
"wrong" to give the same hash as before.  Stored password hashes can
thus be modified if necessary to still match, though it'd be better
to change any affected passwords.

In passing, sync a couple other upstream changes that marginally improve
performance and/or tighten error checking.

Back-patch to all supported branches.  Since this issue is already
public, no reason not to commit the fix ASAP.

provided by Andrew.

right, there seems precious little reason to have a pile of hand-maintained
endianness definitions in src/include/port/*.h.  Get rid of those, and make
the couple of places that used them depend on WORDS_BIGENDIAN instead.

them, the executation behavior could be unexpected.

  It was a bad style to begin with, and now several loops can be clearer.
* pgcrypto.c: Fix function comments
* crypt-gensalt.c, crypt-blowfish.c: stop messing with errno
* openssl.c: use px_free instead pfree
* px.h: make redefining px_alloc/px_realloc/px_free easier

Marko Kreen

  produces garbage.

I learned the hard way that

        #if UNDEFINED_1 == UNDEFINED_2
        #error "gcc is idiot"
        #endif

prints "gcc is idiot" ...

Affected are MD5/SHA1 in internal library, and also HMAC-MD5/HMAC-SHA1/
crypt-md5 which use them.  Blowfish is ok, also Rijndael on at
least x86.

Big thanks to Daniel Holtzman who send me a build log which
contained warning:

        md5.c:246: warning: `X' defined but not used

Yes, gcc is that helpful...

Please apply this.

--
marko

initdb/regression tests pass.

tests pass.

these macros fail in if/else cases:

#define X \
{ \
	... \
}


{

	if (...)
		X;
	else
		...
}

with proper setup:

#define X \
do { \
	... \
} while (0)

it works fine.

salt generation code.  He also urged using better random source
and making possible to choose using bcrypt and xdes rounds more
easily.  So, here's patch:

* For all salt generation, use Solar Designer's own code.  This
  is mostly due fact that his code is more fit for get_random_bytes()
  style interface.
* New function: gen_salt(type, rounds).  This lets specify iteration
  count for algorithm.
* random.c: px_get_random_bytes() function.
  Supported randomness soure: /dev/urandom, OpenSSL PRNG, libc random()
  Default: /dev/urandom.
* Draft description of C API for pgcrypto functions.

New files: API, crypt-gensalt.c, random.c

Marko Kreen