a8950e49bd
Depending on the size of the area to be memset'ed, the nios2 memset implementation either uses a naive loop (for buffers smaller or equal than 8 bytes) or a more optimized implementation (for buffers larger than 8 bytes). This implementation does 4-byte stores rather than 1-byte stores to speed up memset. However, we discovered that on our nios2 platform, memset() was not properly setting the buffer to the expected value. A memset of 0xff would not set the entire buffer to 0xff, but to: 0xff 0x00 0xff 0x00 0xff 0x00 0xff 0x00 ... Which is obviously incorrect. Our investigation has revealed that the problem lies in the incorrect constraints used in the inline assembly. The following piece of assembly, from the nios2 memset implementation, is supposed to create a 4-byte value that repeats 4 times the 1-byte pattern passed as memset argument: /* fill8 %3, %5 (c & 0xff) */ " slli %4, %5, 8\n" " or %4, %4, %5\n" " slli %3, %4, 16\n" " or %3, %3, %4\n" However, depending on the compiler and optimization level, this code might be compiled as: 34: 280a923a slli r5,r5,8 38: 294ab03a or r5,r5,r5 3c: 2808943a slli r4,r5,16 40: 2148b03a or r4,r4,r5 This is wrong because r5 gets used both for %5 and %4, which leads to the final pattern stored in r4 to be 0xff00ff00 rather than the expected 0xffffffff. %4 is defined with the "=r" constraint, i.e as an output operand. However, as explained in http://www.ethernut.de/en/documents/arm-inline-asm.html, this does not prevent gcc from using the same register for an output operand (%4) and input operand (%5). By using the constraint modifier '&', we indicate that the register should be used for output only. With this change, we get the following assembly output: 34: 2810923a slli r8,r5,8 38: 4150b03a or r8,r8,r5 3c: 400e943a slli r7,r8,16 40: 3a0eb03a or r7,r7,r8 Which correctly produces the 0xffffffff pattern when 0xff is passed as the memset() pattern. It is worth mentioning the observed consequence of this bug: we were hitting the kernel BUG() in mm/bootmem.c:__free() that verifies when marking a page as free that it was previously marked as occupied (i.e that the bit was set to 1). The entire bootmem bitmap is set to 0xff bit via a memset() during the bootmem initialization. The bootmem_free() call right after the initialization was finding some bits to be set to 0, which didn't make sense since the bitmap has just been memset'ed to 0xff. Except that due to the bug explained above, the bitmap was in fact initialized to 0xff00ff00. Thanks to Marek Vasut for his help and feedback. Signed-off-by: Romain Perier <romain.perier@free-electrons.com> Acked-by: Marek Vasut <marex@denx.de> Acked-by: Ley Foon Tan <lftan@altera.com>
80 lines
1.8 KiB
C
80 lines
1.8 KiB
C
/*
|
|
* Copyright (C) 2011 Tobias Klauser <tklauser@distanz.ch>
|
|
* Copyright (C) 2004 Microtronix Datacom Ltd
|
|
*
|
|
* This file is subject to the terms and conditions of the GNU General Public
|
|
* License. See the file "COPYING" in the main directory of this archive
|
|
* for more details.
|
|
*/
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/string.h>
|
|
|
|
void *memset(void *s, int c, size_t count)
|
|
{
|
|
int destptr, charcnt, dwordcnt, fill8reg, wrkrega;
|
|
|
|
if (!count)
|
|
return s;
|
|
|
|
c &= 0xFF;
|
|
|
|
if (count <= 8) {
|
|
char *xs = (char *) s;
|
|
|
|
while (count--)
|
|
*xs++ = c;
|
|
return s;
|
|
}
|
|
|
|
__asm__ __volatile__ (
|
|
/* fill8 %3, %5 (c & 0xff) */
|
|
" slli %4, %5, 8\n"
|
|
" or %4, %4, %5\n"
|
|
" slli %3, %4, 16\n"
|
|
" or %3, %3, %4\n"
|
|
/* Word-align %0 (s) if necessary */
|
|
" andi %4, %0, 0x01\n"
|
|
" beq %4, zero, 1f\n"
|
|
" addi %1, %1, -1\n"
|
|
" stb %3, 0(%0)\n"
|
|
" addi %0, %0, 1\n"
|
|
"1: mov %2, %1\n"
|
|
/* Dword-align %0 (s) if necessary */
|
|
" andi %4, %0, 0x02\n"
|
|
" beq %4, zero, 2f\n"
|
|
" addi %1, %1, -2\n"
|
|
" sth %3, 0(%0)\n"
|
|
" addi %0, %0, 2\n"
|
|
" mov %2, %1\n"
|
|
/* %1 and %2 are how many more bytes to set */
|
|
"2: srli %2, %2, 2\n"
|
|
/* %2 is how many dwords to set */
|
|
"3: stw %3, 0(%0)\n"
|
|
" addi %0, %0, 4\n"
|
|
" addi %2, %2, -1\n"
|
|
" bne %2, zero, 3b\n"
|
|
/* store residual word and/or byte if necessary */
|
|
" andi %4, %1, 0x02\n"
|
|
" beq %4, zero, 4f\n"
|
|
" sth %3, 0(%0)\n"
|
|
" addi %0, %0, 2\n"
|
|
/* store residual byte if necessary */
|
|
"4: andi %4, %1, 0x01\n"
|
|
" beq %4, zero, 5f\n"
|
|
" stb %3, 0(%0)\n"
|
|
"5:\n"
|
|
: "=r" (destptr), /* %0 Output */
|
|
"=r" (charcnt), /* %1 Output */
|
|
"=r" (dwordcnt), /* %2 Output */
|
|
"=r" (fill8reg), /* %3 Output */
|
|
"=&r" (wrkrega) /* %4 Output only */
|
|
: "r" (c), /* %5 Input */
|
|
"0" (s), /* %0 Input/Output */
|
|
"1" (count) /* %1 Input/Output */
|
|
: "memory" /* clobbered */
|
|
);
|
|
|
|
return s;
|
|
}
|