powerpc/32: Fix again csum_partial_copy_generic()

Commit 7aef4136566b0 ("powerpc32: rewrite csum_partial_copy_generic()
based on copy_tofrom_user()") introduced a bug when destination address
is odd and len is lower than cacheline size.

In that case the resulting csum value doesn't have to be rotated one
byte because the cache-aligned copy part is skipped so no alignment
is performed.

Fixes: 7aef4136566b0 ("powerpc32: rewrite csum_partial_copy_generic() based on copy_tofrom_user()")
Cc: stable@vger.kernel.org # v4.6+
Reported-by: Alessio Igor Bogani <alessio.bogani@elettra.eu>
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Tested-by: Alessio Igor Bogani <alessio.bogani@elettra.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S
index 0a57fe6d49ccf43a07224c4f7da1f597e36cc10c..aa8214f30c920e05c6bf62349c6ea52e0ca68dc9 100644 (file)
--- a/arch/powerpc/lib/checksum_32.S
+++ b/arch/powerpc/lib/checksum_32.S
@@ -127,18 +127,19 @@ _GLOBAL(csum_partial_copy_generic)
        stw     r7,12(r1)
        stw     r8,8(r1)
 
-       rlwinm  r0,r4,3,0x8
-       rlwnm   r6,r6,r0,0,31   /* odd destination address: rotate one byte */
-       cmplwi  cr7,r0,0        /* is destination address even ? */
        addic   r12,r6,0
        addi    r6,r4,-4
        neg     r0,r4
        addi    r4,r3,-4
        andi.   r0,r0,CACHELINE_MASK    /* # bytes to start of cache line */
+       crset   4*cr7+eq
        beq     58f
 
        cmplw   0,r5,r0                 /* is this more than total to do? */
        blt     63f                     /* if not much to do */
+       rlwinm  r7,r6,3,0x8
+       rlwnm   r12,r12,r7,0,31 /* odd destination address: rotate one byte */
+       cmplwi  cr7,r7,0        /* is destination address even ? */
        andi.   r8,r0,3                 /* get it word-aligned first */
        mtctr   r8
        beq+    61f