Replace GPLV3 MD5 with OpenSSL MD5

Ric asked me to look at replacing the GPL licensed MD5 code with
something better, i.e. perhaps faster, and with a less restrictive
license, etc. So I took a couple hour holiday from working on
wrapping up the client_t and did this.

OpenSSL (nee SSLeay) is released under the OpenSSL license, a BSD/MIT
style license. OpenSSL (libcrypto.so) is used on Linux, OS X and *BSD,
Open Solaris, etc. IOW it's universally available on the platforms we
care about. It's written by Eric Young (eay), now at EMC/RSA, and I
can say from experience that the OpenSSL implementation of MD5 (at least)
is every bit as fast as RSA's proprietary implementation (primarily
because the implementations are very, very similar.) The last time I
surveyed MD5 implementations I found they're all pretty much the same
speed.

I changed the APIs (and ABIs) for the strong and weak checksums.
Strictly speaking I didn't need to do that. They're only called on
short strings of data, i.e. pathnames, so using int32_t and uint32_t
is ostensibly okay. My change is arguably a better, more general API
for this sort of thing. It's also what bit me when gerrit/jenkins
validation failed due to glusterfs segv-ing. (I didn't pay close enough
attention to the implementation of the weak checksum. But it forced me
to learn what gerrit/jenkins are doing and going forward I can do better
testing before submitting to gerrit.)

Now resubmitting with a BZ

Change-Id: I545fade1604e74fc68399894550229bd57a5e0df
BUG: 807718
Signed-off-by: Kaleb KEITHLEY <kkeithle@redhat.com>
Reviewed-on: http://review.gluster.com/3019
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Jeff Darcy <jdarcy@redhat.com>

6 files changed, 24 insertions, 43 deletions

diff --git a/libglusterfs/src/Makefile.am b/libglusterfs/src/Makefile.am
index c7f3d9ba7..2dab8735c 100644
--- a/libglusterfs/src/Makefile.am
+++ b/libglusterfs/src/Makefile.am
@@ -4,8 +4,7 @@ libglusterfs_la_CFLAGS = -fPIC  -Wall -g -shared -nostartfiles $(GF_CFLAGS) \
 libglusterfs_la_CPPFLAGS = -D_FILE_OFFSET_BITS=64 -D__USE_FILE_OFFSET64 \
 	-D_GNU_SOURCE -DXLATORDIR=\"$(libdir)/glusterfs/$(PACKAGE_VERSION)/xlator\" \
 	-D$(GF_HOST_OS) -I$(CONTRIBDIR)/rbtree \
-	-DSCHEDULERDIR=\"$(libdir)/glusterfs/$(PACKAGE_VERSION)/scheduler\" \
-	-I$(CONTRIBDIR)/md5
+	-DSCHEDULERDIR=\"$(libdir)/glusterfs/$(PACKAGE_VERSION)/scheduler\"
 
 libglusterfs_la_LIBADD = @LEXLIB@
 
@@ -17,7 +16,7 @@ libglusterfs_la_SOURCES = dict.c xlator.c logging.c \
 	hashfn.c defaults.c common-utils.c timer.c inode.c call-stub.c \
 	compat.c fd.c compat-errno.c event.c mem-pool.c gf-dirent.c syscall.c \
 	iobuf.c globals.c statedump.c stack.c checksum.c daemon.c \
-	$(CONTRIBDIR)/md5/md5.c $(CONTRIBDIR)/rbtree/rb.c rbthash.c latency.c \
+	$(CONTRIBDIR)/rbtree/rb.c rbthash.c latency.c \
 	graph.c $(CONTRIBDIR)/uuid/clear.c $(CONTRIBDIR)/uuid/copy.c \
 	$(CONTRIBDIR)/uuid/gen_uuid.c $(CONTRIBDIR)/uuid/pack.c \
 	$(CONTRIBDIR)/uuid/parse.c $(CONTRIBDIR)/uuid/unparse.c \
@@ -33,7 +32,7 @@ noinst_HEADERS = common-utils.h defaults.h dict.h glusterfs.h hashfn.h \
 	logging.h xlator.h stack.h timer.h list.h inode.h call-stub.h compat.h \
 	fd.h revision.h compat-errno.h event.h mem-pool.h byte-order.h \
 	gf-dirent.h locking.h syscall.h iobuf.h globals.h statedump.h \
-	checksum.h daemon.h $(CONTRIBDIR)/md5/md5.h $(CONTRIBDIR)/rbtree/rb.h \
+	checksum.h daemon.h $(CONTRIBDIR)/rbtree/rb.h \
 	rbthash.h iatt.h latency.h mem-types.h $(CONTRIBDIR)/uuid/uuidd.h \
 	$(CONTRIBDIR)/uuid/uuid.h $(CONTRIBDIR)/uuid/uuidP.h \
 	$(CONTRIB_BUILDDIR)/uuid/uuid_types.h syncop.h graph-utils.h trie.h run.h \
diff --git a/libglusterfs/src/call-stub.c b/libglusterfs/src/call-stub.c
index 01e919d69..308a9ad1f 100644
--- a/libglusterfs/src/call-stub.c
+++ b/libglusterfs/src/call-stub.c
@@ -22,9 +22,9 @@
 #include "config.h"
 #endif
 
+#include <openssl/md5.h>
 #include <inttypes.h>
 
-#include "md5.h"
 #include "call-stub.h"
 #include "mem-types.h"
 
@@ -2124,7 +2124,7 @@ fop_rchecksum_cbk_stub (call_frame_t *frame,
                         weak_checksum;
 
                 stub->args.rchecksum_cbk.strong_checksum =
-                        memdup (strong_checksum, MD5_DIGEST_LEN);
+                        memdup (strong_checksum, MD5_DIGEST_LENGTH);
         }
         if (xdata)
                 stub->xdata = dict_ref (xdata);
diff --git a/libglusterfs/src/checksum.c b/libglusterfs/src/checksum.c
index cea782293..7575b2f15 100644
--- a/libglusterfs/src/checksum.c
+++ b/libglusterfs/src/checksum.c
@@ -17,12 +17,10 @@
   <http://www.gnu.org/licenses/>.
 */
 
-#include <inttypes.h>
+#include <openssl/md5.h>
+#include <stdint.h>
 
 #include "glusterfs.h"
-#include "md5.h"
-#include "checksum.h"
-
 
 /*
  * The "weak" checksum required for the rsync algorithm,
@@ -31,22 +29,26 @@
  *
  * "a simple 32 bit checksum that can be upadted from either end
  *  (inspired by Mark Adler's Adler-32 checksum)"
+ *
+ * Note: these functions are only called to compute checksums on
+ * pathnames; they don't need to handle arbitrarily long strings of
+ * data. Thus int32_t and uint32_t are sufficient
  */
 
 uint32_t
-gf_rsync_weak_checksum (char *buf1, int32_t len)
+gf_rsync_weak_checksum (unsigned char *buf, size_t len)
 {
-        int32_t i;
+        int32_t i = 0;
         uint32_t s1, s2;
 
-        signed char *buf = (signed char *) buf1;
         uint32_t csum;
 
         s1 = s2 = 0;
-        for (i = 0; i < (len-4); i+=4) {
-                s2 += 4*(s1 + buf[i]) + 3*buf[i+1] + 2*buf[i+2] + buf[i+3];
-
-                s1 += buf[i+0] + buf[i+1] + buf[i+2] + buf[i+3];
+        if (len >= 4) {
+                for (; i < (len-4); i+=4) {
+                        s2 += 4*(s1 + buf[i]) + 3*buf[i+1] + 2*buf[i+2] + buf[i+3];
+                        s1 += buf[i+0] + buf[i+1] + buf[i+2] + buf[i+3];
+                }
         }
 
         for (; i < len; i++) {
@@ -66,13 +68,7 @@ gf_rsync_weak_checksum (char *buf1, int32_t len)
  */
 
 void
-gf_rsync_strong_checksum (char *buf, int32_t len, uint8_t *sum)
+gf_rsync_strong_checksum (unsigned char *data, size_t len, unsigned char *md5)
 {
-        md_context m;
-
-        md5_begin (&m);
-        md5_update (&m, (unsigned char *) buf, len);
-        md5_result (&m, (unsigned char *) sum);
-
-        return;
+        MD5(data, len, md5);
 }
diff --git a/libglusterfs/src/checksum.h b/libglusterfs/src/checksum.h
index 3542036bf..19221b922 100644
--- a/libglusterfs/src/checksum.h
+++ b/libglusterfs/src/checksum.h
@@ -20,8 +20,10 @@
 #ifndef __CHECKSUM_H__
 #define __CHECKSUM_H__
 
-uint32_t gf_rsync_weak_checksum (char *buf, int32_t len);
+uint32_t
+gf_rsync_weak_checksum (unsigned char *buf, size_t len);
 
-void gf_rsync_strong_checksum (char *buf, int32_t len, uint8_t *sum);
+void
+gf_rsync_strong_checksum (unsigned char *buf, size_t len, unsigned char *sum);
 
 #endif /* __CHECKSUM_H__ */
diff --git a/libglusterfs/src/common-utils.c b/libglusterfs/src/common-utils.c
index f26d2bdc3..c5080246a 100644
--- a/libglusterfs/src/common-utils.c
+++ b/libglusterfs/src/common-utils.c
@@ -52,7 +52,6 @@
 #include "glusterfs.h"
 #include "stack.h"
 #include "globals.h"
-#include "md5.h"
 #include "lkowner.h"
 
 #ifndef AI_ADDRCONFIG
@@ -1786,19 +1785,6 @@ lkowner_utoa_r (gf_lkowner_t *lkowner, char *dst, int len)
         return dst;
 }
 
-void _get_md5_str (char *out_str, size_t outlen,
-                   const uint8_t *input, int n)
-{
-        uint8_t out[MD5_DIGEST_LEN] = {0};
-        int     j = 0;
-
-        GF_ASSERT (outlen >= (2*MD5_DIGEST_LEN + 1));
-        get_md5 (out, input, n);
-        for (j = 0; j < MD5_DIGEST_LEN; j++)
-                snprintf(out_str + j * 2, outlen-j*2, "%02x", out[j]);
-
-}
-
 void* gf_array_elem (void *a, int index, size_t elem_size)
 {
         uint8_t* ptr = a;
diff --git a/libglusterfs/src/common-utils.h b/libglusterfs/src/common-utils.h
index 3aa0143d2..9d98975e1 100644
--- a/libglusterfs/src/common-utils.h
+++ b/libglusterfs/src/common-utils.h
@@ -482,8 +482,6 @@ char *uuid_utoa_r (uuid_t uuid, char *dst);
 char *lkowner_utoa (gf_lkowner_t *lkowner);
 char *lkowner_utoa_r (gf_lkowner_t *lkowner, char *dst, int len);
 
-void _get_md5_str (char *out_str, size_t outlen,
-                   const uint8_t *input, int n);
 void gf_array_insertionsort (void *a, int l, int r, size_t elem_size,
                              gf_cmp cmp);
 int gf_is_str_int (const char *value);