mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-05 22:36:40 +07:00
9bc89cd82d
The async_tx api provides methods for describing a chain of asynchronous bulk memory transfers/transforms with support for inter-transactional dependencies. It is implemented as a dmaengine client that smooths over the details of different hardware offload engine implementations. Code that is written to the api can optimize for asynchronous operation and the api will fit the chain of operations to the available offload resources. I imagine that any piece of ADMA hardware would register with the 'async_*' subsystem, and a call to async_X would be routed as appropriate, or be run in-line. - Neil Brown async_tx exploits the capabilities of struct dma_async_tx_descriptor to provide an api of the following general format: struct dma_async_tx_descriptor * async_<operation>(..., struct dma_async_tx_descriptor *depend_tx, dma_async_tx_callback cb_fn, void *cb_param) { struct dma_chan *chan = async_tx_find_channel(depend_tx, <operation>); struct dma_device *device = chan ? chan->device : NULL; int int_en = cb_fn ? 1 : 0; struct dma_async_tx_descriptor *tx = device ? device->device_prep_dma_<operation>(chan, len, int_en) : NULL; if (tx) { /* run <operation> asynchronously */ ... tx->tx_set_dest(addr, tx, index); ... tx->tx_set_src(addr, tx, index); ... async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param); } else { /* run <operation> synchronously */ ... <operation> ... async_tx_sync_epilog(flags, depend_tx, cb_fn, cb_param); } return tx; } async_tx_find_channel() returns a capable channel from its pool. The channel pool is organized as a per-cpu array of channel pointers. The async_tx_rebalance() routine is tasked with managing these arrays. In the uniprocessor case async_tx_rebalance() tries to spread responsibility evenly over channels of similar capabilities. For example if there are two copy+xor channels, one will handle copy operations and the other will handle xor. In the SMP case async_tx_rebalance() attempts to spread the operations evenly over the cpus, e.g. cpu0 gets copy channel0 and xor channel0 while cpu1 gets copy channel 1 and xor channel 1. When a dependency is specified async_tx_find_channel defaults to keeping the operation on the same channel. A xor->copy->xor chain will stay on one channel if it supports both operation types, otherwise the transaction will transition between a copy and a xor resource. Currently the raid5 implementation in the MD raid456 driver has been converted to the async_tx api. A driver for the offload engines on the Intel Xscale series of I/O processors, iop-adma, is provided in a later commit. With the iop-adma driver and async_tx, raid456 is able to offload copy, xor, and xor-zero-sum operations to hardware engines. On iop342 tiobench showed higher throughput for sequential writes (20 - 30% improvement) and sequential reads to a degraded array (40 - 55% improvement). For the other cases performance was roughly equal, +/- a few percentage points. On a x86-smp platform the performance of the async_tx implementation (in synchronous mode) was also +/- a few percentage points of the original implementation. According to 'top' on iop342 CPU utilization drops from ~50% to ~15% during a 'resync' while the speed according to /proc/mdstat doubles from ~25 MB/s to ~50 MB/s. The tiobench command line used for testing was: tiobench --size 2048 --block 4096 --block 131072 --dir /mnt/raid --numruns 5 * iop342 had 1GB of memory available Details: * if CONFIG_DMA_ENGINE=n the asynchronous path is compiled away by making async_tx_find_channel a static inline routine that always returns NULL * when a callback is specified for a given transaction an interrupt will fire at operation completion time and the callback will occur in a tasklet. if the the channel does not support interrupts then a live polling wait will be performed * the api is written as a dmaengine client that requests all available channels * In support of dependencies the api implicitly schedules channel-switch interrupts. The interrupt triggers the cleanup tasklet which causes pending operations to be scheduled on the next channel * Xor engines treat an xor destination address differently than a software xor routine. To the software routine the destination address is an implied source, whereas engines treat it as a write-only destination. This patch modifies the xor_blocks routine to take a an explicit destination address to mirror the hardware. Changelog: * fixed a leftover debug print * don't allow callbacks in async_interrupt_cond * fixed xor_block changes * fixed usage of ASYNC_TX_XOR_DROP_DEST * drop dma mapping methods, suggested by Chris Leech * printk warning fixups from Andrew Morton * don't use inline in C files, Adrian Bunk * select the API when MD is enabled * BUG_ON xor source counts <= 1 * implicitly handle hardware concerns like channel switching and interrupts, Neil Brown * remove the per operation type list, and distribute operation capabilities evenly amongst the available channels * simplify async_tx_find_channel to optimize the fast path * introduce the channel_table_initialized flag to prevent early calls to the api * reorganize the code to mimic crypto * include mm.h as not all archs include it in dma-mapping.h * make the Kconfig options non-user visible, Adrian Bunk * move async_tx under crypto since it is meant as 'core' functionality, and the two may share algorithms in the future * move large inline functions into c files * checkpatch.pl fixes * gpl v2 only correction Cc: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-By: NeilBrown <neilb@suse.de>
156 lines
3.6 KiB
C
156 lines
3.6 KiB
C
/*
|
|
* 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.
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation; either version 2, or (at your option)
|
|
* any later version.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* (for example /usr/src/linux/COPYING); if not, write to the Free
|
|
* Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
|
*/
|
|
|
|
#define BH_TRACE 0
|
|
#include <linux/module.h>
|
|
#include <linux/raid/md.h>
|
|
#include <linux/raid/xor.h>
|
|
#include <asm/xor.h>
|
|
|
|
/* 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 *template_list;
|
|
|
|
#define BENCH_SIZE (PAGE_SIZE)
|
|
|
|
static void
|
|
do_xor_speed(struct xor_block_template *tmpl, void *b1, void *b2)
|
|
{
|
|
int speed;
|
|
unsigned long now;
|
|
int i, count, max;
|
|
|
|
tmpl->next = template_list;
|
|
template_list = tmpl;
|
|
|
|
/*
|
|
* Count the number of XORs done during a whole jiffy, and use
|
|
* this to calculate the speed of checksumming. We use a 2-page
|
|
* allocation to have guaranteed color L1-cache layout.
|
|
*/
|
|
max = 0;
|
|
for (i = 0; i < 5; i++) {
|
|
now = jiffies;
|
|
count = 0;
|
|
while (jiffies == now) {
|
|
mb(); /* prevent loop optimzation */
|
|
tmpl->do_2(BENCH_SIZE, b1, b2);
|
|
mb();
|
|
count++;
|
|
mb();
|
|
}
|
|
if (count > max)
|
|
max = count;
|
|
}
|
|
|
|
speed = max * (HZ * BENCH_SIZE / 1024);
|
|
tmpl->speed = speed;
|
|
|
|
printk(KERN_INFO " %-10s: %5d.%03d MB/sec\n", tmpl->name,
|
|
speed / 1000, speed % 1000);
|
|
}
|
|
|
|
static int __init
|
|
calibrate_xor_blocks(void)
|
|
{
|
|
void *b1, *b2;
|
|
struct xor_block_template *f, *fastest;
|
|
|
|
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
|
|
*/
|
|
|
|
fastest = NULL;
|
|
|
|
#ifdef XOR_SELECT_TEMPLATE
|
|
fastest = XOR_SELECT_TEMPLATE(fastest);
|
|
#endif
|
|
|
|
#define xor_speed(templ) do_xor_speed((templ), b1, b2)
|
|
|
|
if (fastest) {
|
|
printk(KERN_INFO "xor: automatically using best "
|
|
"checksumming function: %s\n",
|
|
fastest->name);
|
|
xor_speed(fastest);
|
|
} else {
|
|
printk(KERN_INFO "xor: measuring software checksum speed\n");
|
|
XOR_TRY_TEMPLATES;
|
|
fastest = template_list;
|
|
for (f = fastest; f; f = f->next)
|
|
if (f->speed > fastest->speed)
|
|
fastest = f;
|
|
}
|
|
|
|
printk(KERN_INFO "xor: using function: %s (%d.%03d MB/sec)\n",
|
|
fastest->name, fastest->speed / 1000, fastest->speed % 1000);
|
|
|
|
#undef xor_speed
|
|
|
|
free_pages((unsigned long)b1, 2);
|
|
|
|
active_template = fastest;
|
|
return 0;
|
|
}
|
|
|
|
static __exit void xor_exit(void) { }
|
|
|
|
MODULE_LICENSE("GPL");
|
|
|
|
/* when built-in xor.o must initialize before drivers/md/md.o */
|
|
core_initcall(calibrate_xor_blocks);
|
|
module_exit(xor_exit);
|