[SPARC32]: Fix bug in sparc optimized memset.

Sparc optimized memset (arch/sparc/lib/memset.S) does not fill last
byte of the memory area, if area size is less than 8 bytes and start
address is not word (4-bytes) aligned.

Here is code chunk where bug located:
/* %o0 - memory address, %o1 - size, %g3 - value */
8:
     add    %o0, 1, %o0
    subcc    %o1, 1, %o1
    bne,a    8b
     stb %g3, [%o0 - 1]

This code should write byte every loop iteration, but last time delay
instruction stb is not executed because branch instruction sets
"annul" bit.

Patch replaces bne,a by bne instruction.

Error can be reproduced by simple kernel module:

--------------------
#include <linux/module.h>
#include <linux/config.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <string.h>

static void do_memset(void **p, int size)
{
        memset(p, 0x00, size);
}

static int __init memset_test_init(void)
{
    char fooc[8];
    int *fooi;
    memset(fooc, 0xba, sizeof(fooc));

    do_memset((void**)(fooc + 3), 1);

    fooi = (int*) fooc;
    printk("%08X %08X\n", fooi[0], fooi[1]);

    return -1;
}

static void __exit memset_test_cleanup(void)
{
    return;
}

module_init(memset_test_init);
module_exit(memset_test_cleanup);

MODULE_LICENSE("GPL");
EXPORT_NO_SYMBOLS;
--------------------

Signed-off-by: Alexander Shmelev <ashmelev@task.sun.mcst.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S
index a65eba4..1c37ea8 100644 (file)
--- a/arch/sparc/lib/memset.S
+++ b/arch/sparc/lib/memset.S
@@ -162,7 +162,7 @@ __bzero:
 8:
         add    %o0, 1, %o0
        subcc   %o1, 1, %o1
-       bne,a   8b
+       bne     8b
         EX(stb %g3, [%o0 - 1], add %o1, 1)
 0:
        retl