linux/crypto/xor.c
Kirill Tkhai 3c02e04fd4 crypto: xor - Fix divide error in do_xor_speed()
crypto: Fix divide error in do_xor_speed()

From: Kirill Tkhai <ktkhai@virtuozzo.com>

Latest (but not only latest) linux-next panics with divide
error on my QEMU setup.

The patch at the bottom of this message fixes the problem.

xor: measuring software checksum speed
divide error: 0000 [#1] PREEMPT SMP KASAN
PREEMPT SMP KASAN
CPU: 3 PID: 1 Comm: swapper/0 Not tainted 5.10.0-next-20201223+ #2177
RIP: 0010:do_xor_speed+0xbb/0xf3
Code: 41 ff cc 75 b5 bf 01 00 00 00 e8 3d 23 8b fe 65 8b 05 f6 49 83 7d 85 c0 75 05 e8
 84 70 81 fe b8 00 00 50 c3 31 d2 48 8d 7b 10 <f7> f5 41 89 c4 e8 58 07 a2 fe 44 89 63 10 48 8d 7b 08
 e8 cb 07 a2
RSP: 0000:ffff888100137dc8 EFLAGS: 00010246
RAX: 00000000c3500000 RBX: ffffffff823f0160 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 0000000000000808 RDI: ffffffff823f0170
RBP: 0000000000000000 R08: ffffffff8109c50f R09: ffffffff824bb6f7
R10: fffffbfff04976de R11: 0000000000000001 R12: 0000000000000000
R13: ffff888101997000 R14: ffff888101994000 R15: ffffffff823f0178
FS:  0000000000000000(0000) GS:ffff8881f7780000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000000 CR3: 000000000220e000 CR4: 00000000000006a0
Call Trace:
 calibrate_xor_blocks+0x13c/0x1c4
 ? do_xor_speed+0xf3/0xf3
 do_one_initcall+0xc1/0x1b7
 ? start_kernel+0x373/0x373
 ? unpoison_range+0x3a/0x60
 kernel_init_freeable+0x1dd/0x238
 ? rest_init+0xc6/0xc6
 kernel_init+0x8/0x10a
 ret_from_fork+0x1f/0x30
---[ end trace 5bd3c1d0b77772da ]---

Fixes: c055e3eae0 ("crypto: xor - use ktime for template benchmarking")
Cc: <stable@vger.kernel.org>
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2021-01-08 15:37:55 +11:00

177 lines
3.8 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* xor.c : Multiple Devices driver for Linux
*
* Copyright (C) 1996, 1997, 1998, 1999, 2000,
* Ingo Molnar, Matti Aarnio, Jakub Jelinek, Richard Henderson.
*
* Dispatch optimized RAID-5 checksumming functions.
*/
#define BH_TRACE 0
#include <linux/module.h>
#include <linux/gfp.h>
#include <linux/raid/xor.h>
#include <linux/jiffies.h>
#include <linux/preempt.h>
#include <asm/xor.h>
#ifndef XOR_SELECT_TEMPLATE
#define XOR_SELECT_TEMPLATE(x) (x)
#endif
/* The xor routines to use. */
static struct xor_block_template *active_template;
void
xor_blocks(unsigned int src_count, unsigned int bytes, void *dest, void **srcs)
{
unsigned long *p1, *p2, *p3, *p4;
p1 = (unsigned long *) srcs[0];
if (src_count == 1) {
active_template->do_2(bytes, dest, p1);
return;
}
p2 = (unsigned long *) srcs[1];
if (src_count == 2) {
active_template->do_3(bytes, dest, p1, p2);
return;
}
p3 = (unsigned long *) srcs[2];
if (src_count == 3) {
active_template->do_4(bytes, dest, p1, p2, p3);
return;
}
p4 = (unsigned long *) srcs[3];
active_template->do_5(bytes, dest, p1, p2, p3, p4);
}
EXPORT_SYMBOL(xor_blocks);
/* Set of all registered templates. */
static struct xor_block_template *__initdata template_list;
#ifndef MODULE
static void __init do_xor_register(struct xor_block_template *tmpl)
{
tmpl->next = template_list;
template_list = tmpl;
}
static int __init register_xor_blocks(void)
{
active_template = XOR_SELECT_TEMPLATE(NULL);
if (!active_template) {
#define xor_speed do_xor_register
// register all the templates and pick the first as the default
XOR_TRY_TEMPLATES;
#undef xor_speed
active_template = template_list;
}
return 0;
}
#endif
#define BENCH_SIZE 4096
#define REPS 800U
static void __init
do_xor_speed(struct xor_block_template *tmpl, void *b1, void *b2)
{
int speed;
int i, j;
ktime_t min, start, diff;
tmpl->next = template_list;
template_list = tmpl;
preempt_disable();
min = (ktime_t)S64_MAX;
for (i = 0; i < 3; i++) {
start = ktime_get();
for (j = 0; j < REPS; j++) {
mb(); /* prevent loop optimzation */
tmpl->do_2(BENCH_SIZE, b1, b2);
mb();
}
diff = ktime_sub(ktime_get(), start);
if (diff < min)
min = diff;
}
preempt_enable();
// bytes/ns == GB/s, multiply by 1000 to get MB/s [not MiB/s]
if (!min)
min = 1;
speed = (1000 * REPS * BENCH_SIZE) / (unsigned int)ktime_to_ns(min);
tmpl->speed = speed;
pr_info(" %-16s: %5d MB/sec\n", tmpl->name, speed);
}
static int __init
calibrate_xor_blocks(void)
{
void *b1, *b2;
struct xor_block_template *f, *fastest;
fastest = XOR_SELECT_TEMPLATE(NULL);
if (fastest) {
printk(KERN_INFO "xor: automatically using best "
"checksumming function %-10s\n",
fastest->name);
goto out;
}
b1 = (void *) __get_free_pages(GFP_KERNEL, 2);
if (!b1) {
printk(KERN_WARNING "xor: Yikes! No memory available.\n");
return -ENOMEM;
}
b2 = b1 + 2*PAGE_SIZE + BENCH_SIZE;
/*
* If this arch/cpu has a short-circuited selection, don't loop through
* all the possible functions, just test the best one
*/
#define xor_speed(templ) do_xor_speed((templ), b1, b2)
printk(KERN_INFO "xor: measuring software checksum speed\n");
template_list = NULL;
XOR_TRY_TEMPLATES;
fastest = template_list;
for (f = fastest; f; f = f->next)
if (f->speed > fastest->speed)
fastest = f;
pr_info("xor: using function: %s (%d MB/sec)\n",
fastest->name, fastest->speed);
#undef xor_speed
free_pages((unsigned long)b1, 2);
out:
active_template = fastest;
return 0;
}
static __exit void xor_exit(void) { }
MODULE_LICENSE("GPL");
#ifndef MODULE
/* when built-in xor.o must initialize before drivers/md/md.o */
core_initcall(register_xor_blocks);
#endif
module_init(calibrate_xor_blocks);
module_exit(xor_exit);