Revert "sh: Handle calling csum_partial with misaligned data"

This reverts commit cadc4e1.

Commit cadc4e1 ("sh: Handle calling csum_partial with misaligned
data") causes bad checksum calculations on unaligned data. Reverting
it fixes the problem.

    # Subtest: checksum
    # module: checksum_kunit
    1..5
    # test_csum_fixed_random_inputs: ASSERTION FAILED at lib/checksum_kunit.c:500
    Expected ( u64)result == ( u64)expec, but
        ( u64)result == 53378 (0xd082)
        ( u64)expec == 33488 (0x82d0)
    # test_csum_fixed_random_inputs: pass:0 fail:1 skip:0 total:1
    not ok 1 test_csum_fixed_random_inputs
    # test_csum_all_carry_inputs: ASSERTION FAILED at lib/checksum_kunit.c:525
    Expected ( u64)result == ( u64)expec, but
        ( u64)result == 65281 (0xff01)
        ( u64)expec == 65280 (0xff00)
    # test_csum_all_carry_inputs: pass:0 fail:1 skip:0 total:1
    not ok 2 test_csum_all_carry_inputs
    # test_csum_no_carry_inputs: ASSERTION FAILED at lib/checksum_kunit.c:573
    Expected ( u64)result == ( u64)expec, but
        ( u64)result == 65535 (0xffff)
        ( u64)expec == 65534 (0xfffe)
    # test_csum_no_carry_inputs: pass:0 fail:1 skip:0 total:1
    not ok 3 test_csum_no_carry_inputs
    # test_ip_fast_csum: pass:1 fail:0 skip:0 total:1
    ok 4 test_ip_fast_csum
    # test_csum_ipv6_magic: pass:1 fail:0 skip:0 total:1
    ok 5 test_csum_ipv6_magic
 # checksum: pass:2 fail:3 skip:0 total:5
 # Totals: pass:2 fail:3 skip:0 total:5
not ok 22 checksum

Fixes: cadc4e1 ("sh: Handle calling csum_partial with misaligned data")
Signed-off-by: Guenter Roeck <[email protected]>
Tested-by: Geert Uytterhoeven <[email protected]>
Reviewed-by: John Paul Adrian Glaubitz <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: John Paul Adrian Glaubitz <[email protected]>

Author: groeck

arch/sh/lib/checksum.S

@@ -33,7 +33,8 @@
  */
 
 /*	
- * asmlinkage __wsum csum_partial(const void *buf, int len, __wsum sum);
+ * unsigned int csum_partial(const unsigned char *buf, int len,
+ *                           unsigned int sum);
  */
 
 .text
@@ -45,49 +46,28 @@ ENTRY(csum_partial)
 	   * Fortunately, it is easy to convert 2-byte alignment to 4-byte
 	   * alignment for the unrolled loop.
 	   */
+	mov	r5, r1
 	mov	r4, r0
-	tst	#3, r0		! Check alignment.
-	bt/s	2f		! Jump if alignment is ok.
-	 mov	r4, r7		! Keep a copy to check for alignment
+	tst	#2, r0		! Check alignment.
+	bt	2f		! Jump if alignment is ok.
 	!
-	tst	#1, r0		! Check alignment.
-	bt	21f		! Jump if alignment is boundary of 2bytes.
-
-	! buf is odd
-	tst	r5, r5
-	add	#-1, r5
-	bt	9f
-	mov.b	@r4+, r0
-	extu.b	r0, r0
-	addc	r0, r6		! t=0 from previous tst
-	mov	r6, r0
-	shll8	r6
-	shlr16	r0
-	shlr8	r0
-	or	r0, r6
-	mov	r4, r0
-	tst	#2, r0
-	bt	2f
-21:
-	! buf is 2 byte aligned (len could be 0)
 	add	#-2, r5		! Alignment uses up two bytes.
 	cmp/pz	r5		!
 	bt/s	1f		! Jump if we had at least two bytes.
 	 clrt
 	bra	6f
 	 add	#2, r5		! r5 was < 2.  Deal with it.
 1:
+	mov	r5, r1		! Save new len for later use.
 	mov.w	@r4+, r0
 	extu.w	r0, r0
 	addc	r0, r6
 	bf	2f
 	add	#1, r6
 2:
-	! buf is 4 byte aligned (len could be 0)
-	mov	r5, r1
 	mov	#-5, r0
-	shld	r0, r1
-	tst	r1, r1
+	shld	r0, r5
+	tst	r5, r5
 	bt/s	4f		! if it's =0, go to 4f
 	 clrt
 	.align	2
@@ -109,31 +89,30 @@ ENTRY(csum_partial)
 	addc	r0, r6
 	addc	r2, r6
 	movt	r0
-	dt	r1
+	dt	r5
 	bf/s	3b
 	 cmp/eq	#1, r0
-	! here, we know r1==0
-	addc	r1, r6			! add carry to r6
+	! here, we know r5==0
+	addc	r5, r6			! add carry to r6
 4:
-	mov	r5, r0
+	mov	r1, r0
 	and	#0x1c, r0
 	tst	r0, r0
-	bt	6f
-	! 4 bytes or more remaining
-	mov	r0, r1
-	shlr2	r1
+	bt/s	6f
+	 mov	r0, r5
+	shlr2	r5
 	mov	#0, r2
 5:
 	addc	r2, r6
 	mov.l	@r4+, r2
 	movt	r0
-	dt	r1
+	dt	r5
 	bf/s	5b
 	 cmp/eq	#1, r0
 	addc	r2, r6
-	addc	r1, r6		! r1==0 here, so it means add carry-bit
+	addc	r5, r6		! r5==0 here, so it means add carry-bit
 6:
-	! 3 bytes or less remaining
+	mov	r1, r5
 	mov	#3, r0
 	and	r0, r5
 	tst	r5, r5
@@ -159,16 +138,6 @@ ENTRY(csum_partial)
 	mov	#0, r0
 	addc	r0, r6
 9:
-	! Check if the buffer was misaligned, if so realign sum
-	mov	r7, r0
-	tst	#1, r0
-	bt	10f
-	mov	r6, r0
-	shll8	r6
-	shlr16	r0
-	shlr8	r0
-	or	r0, r6
-10:
 	rts
 	 mov	r6, r0