crypto: padlock-aes - Fix Nano workaround data corruption

BugLink: https://bugs.launchpad.net/bugs/1791953

commit 46d8c4b2 upstream.

This was detected by the self-test thanks to Ard's chunking patch.

I finally got around to testing this out on my ancient Via box.  It
turns out that the workaround got the assembly wrong and we end up
doing count + initial cycles of the loop instead of just count.

This obviously causes corruption, either by overwriting the source
that is yet to be processed, or writing over the end of the buffer.

On CPUs that don't require the workaround only ECB is affected.
On Nano CPUs both ECB and CBC are affected.

This patch fixes it by doing the subtraction prior to the assembly.

Fixes: a76c1c23 ("crypto: padlock-aes - work around Nano CPU...")
Cc: <stable@vger.kernel.org>
Reported-by: Jamie Heilman <jamie@audible.transient.net>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Stefan Bader <stefan.bader@canonical.com>
Signed-off-by: Kleber Sacilotto de Souza <kleber.souza@canonical.com>

drivers/crypto/padlock-aes.c

@@ -266,6 +266,8 @@ static inline void padlock_xcrypt_ecb(const u8 *input, u8 *output, void *key,
 		return;
 	}
 
+	count -= initial;
+
 	if (initial)
 		asm volatile (".byte 0xf3,0x0f,0xa7,0xc8"	/* rep xcryptecb */
 			      : "+S"(input), "+D"(output)
@@ -273,7 +275,7 @@ static inline void padlock_xcrypt_ecb(const u8 *input, u8 *output, void *key,
 
 	asm volatile (".byte 0xf3,0x0f,0xa7,0xc8"	/* rep xcryptecb */
 		      : "+S"(input), "+D"(output)
-		      : "d"(control_word), "b"(key), "c"(count - initial));
+		      : "d"(control_word), "b"(key), "c"(count));
 }
 
 static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key,
@@ -284,6 +286,8 @@ static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key,
 	if (count < cbc_fetch_blocks)
 		return cbc_crypt(input, output, key, iv, control_word, count);
 
+	count -= initial;
+
 	if (initial)
 		asm volatile (".byte 0xf3,0x0f,0xa7,0xd0"	/* rep xcryptcbc */
 			      : "+S" (input), "+D" (output), "+a" (iv)
@@ -291,7 +295,7 @@ static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key,
 
 	asm volatile (".byte 0xf3,0x0f,0xa7,0xd0"	/* rep xcryptcbc */
 		      : "+S" (input), "+D" (output), "+a" (iv)
-		      : "d" (control_word), "b" (key), "c" (count-initial));
+		      : "d" (control_word), "b" (key), "c" (count));
 	return iv;
 }