linux-stable/crypto/xor.c
Linus Torvalds 31caf8b2a8 Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6
Pull crypto update from Herbert Xu:
 "API:
   - Restrict crypto_cipher to internal API users only.

  Algorithms:
   - Add x86 aesni acceleration for cts.
   - Improve x86 aesni acceleration for xts.
   - Remove x86 acceleration of some uncommon algorithms.
   - Remove RIPE-MD, Tiger and Salsa20.
   - Remove tnepres.
   - Add ARM acceleration for BLAKE2s and BLAKE2b.

  Drivers:
   - Add Keem Bay OCS HCU driver.
   - Add Marvell OcteonTX2 CPT PF driver.
   - Remove PicoXcell driver.
   - Remove mediatek driver"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (154 commits)
  hwrng: timeriomem - Use device-managed registration API
  crypto: hisilicon/qm - fix printing format issue
  crypto: hisilicon/qm - do not reset hardware when CE happens
  crypto: hisilicon/qm - update irqflag
  crypto: hisilicon/qm - fix the value of 'QM_SQC_VFT_BASE_MASK_V2'
  crypto: hisilicon/qm - fix request missing error
  crypto: hisilicon/qm - removing driver after reset
  crypto: octeontx2 - fix -Wpointer-bool-conversion warning
  crypto: hisilicon/hpre - enable Elliptic curve cryptography
  crypto: hisilicon - PASID fixed on Kunpeng 930
  crypto: hisilicon/qm - fix use of 'dma_map_single'
  crypto: hisilicon/hpre - tiny fix
  crypto: hisilicon/hpre - adapt the number of clusters
  crypto: cpt - remove casting dma_alloc_coherent
  crypto: keembay-ocs-aes - Fix 'q' assignment during CCM B0 generation
  crypto: xor - Fix typo of optimization
  hwrng: optee - Use device-managed registration API
  crypto: arm64/crc-t10dif - move NEON yield to C code
  crypto: arm64/aes-ce-mac - simplify NEON yield
  crypto: arm64/aes-neonbs - remove NEON yield calls
  ...
2021-02-21 17:23:56 -08:00

176 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 optimization */
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);