btrfs-progs: crypto: fix SSE2/SSE4.1 detection of BLAKE2

On recent x86-64 system with march=native|<cpu>|<microarchitecture
level> gcc/clang will automatically define all the available vector
extensions macros. crypto/blake2-config.h then correctly set all the
HAVE_<EXTENSION> macros.

crypto/blake2-round.h then checks the HAVE_<EXTENSION> macros for
including further headers:

    #if defined(HAVE_SSE41)
    #include "blake2b-load-sse41.h"
    #else
    #include "blake2b-load-sse2.h"
    #endif

which is wrong. On recent systems it always results in including
blake2b-load-sse41.h. crypto/blake2-round.h itself is included by
crypto/blake2b-sse2.c and now we have a SSE2/SSE4.1 code mixing
resulting in the incompatible type for argument build errors described
in #589.

The idea is to remove the lines above from crypto/blake2-round.h and put
the includes directly into crypto/blake2b-sse2.c and
crypto/blake2b-sse41.c respectively.

Note this slightly diverges from the upstream BLAKE2 sources.

Pull-request: #591
Author: Tino Mai <mai.tino@gmail.com>
Signed-off-by: David Sterba <dsterba@suse.com>

crypto/blake2b-round.h

@@ -136,12 +136,6 @@
 
 #endif
 
-#if defined(HAVE_SSE41)
-#include "blake2b-load-sse41.h"
-#else
-#include "blake2b-load-sse2.h"
-#endif
-
 #define ROUND(r) \
   LOAD_MSG_ ##r ##_1(b0, b1); \
   G1(row1l,row2l,row3l,row4l,row1h,row2h,row3h,row4h,b0,b1); \

crypto/blake2b-sse2.c

@@ -30,6 +30,7 @@
 #include <x86intrin.h>
 #endif
 
+#include "blake2b-load-sse2.h"
 #include "blake2b-round.h"
 
 static const uint64_t blake2b_IV[8] =

crypto/blake2b-sse41.c

@@ -34,6 +34,7 @@
 #include <x86intrin.h>
 #endif
 
+#include "blake2b-load-sse41.h"
 #include "blake2b-round.h"
 
 static const uint64_t blake2b_IV[8] =