linux/drivers/block/rsxx/dev.c
Kent Overstreet 4f024f3797 block: Abstract out bvec iterator
Immutable biovecs are going to require an explicit iterator. To
implement immutable bvecs, a later patch is going to add a bi_bvec_done
member to this struct; for now, this patch effectively just renames
things.

Signed-off-by: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "Ed L. Cashin" <ecashin@coraid.com>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Lars Ellenberg <drbd-dev@lists.linbit.com>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: Geoff Levand <geoff@infradead.org>
Cc: Yehuda Sadeh <yehuda@inktank.com>
Cc: Sage Weil <sage@inktank.com>
Cc: Alex Elder <elder@inktank.com>
Cc: ceph-devel@vger.kernel.org
Cc: Joshua Morris <josh.h.morris@us.ibm.com>
Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Neil Brown <neilb@suse.de>
Cc: Alasdair Kergon <agk@redhat.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: dm-devel@redhat.com
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: linux390@de.ibm.com
Cc: Boaz Harrosh <bharrosh@panasas.com>
Cc: Benny Halevy <bhalevy@tonian.com>
Cc: "James E.J. Bottomley" <JBottomley@parallels.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Chris Mason <chris.mason@fusionio.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Dave Kleikamp <shaggy@kernel.org>
Cc: Joern Engel <joern@logfs.org>
Cc: Prasad Joshi <prasadjoshi.linux@gmail.com>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Ben Myers <bpm@sgi.com>
Cc: xfs@oss.sgi.com
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com>
Cc: Ben Hutchings <ben@decadent.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Guo Chao <yan@linux.vnet.ibm.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Asai Thambi S P <asamymuthupa@micron.com>
Cc: Selvan Mani <smani@micron.com>
Cc: Sam Bradshaw <sbradshaw@micron.com>
Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Cc: "Roger Pau Monné" <roger.pau@citrix.com>
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Cc: Ian Campbell <Ian.Campbell@citrix.com>
Cc: Sebastian Ott <sebott@linux.vnet.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Jerome Marchand <jmarchand@redhat.com>
Cc: Joe Perches <joe@perches.com>
Cc: Peng Tao <tao.peng@emc.com>
Cc: Andy Adamson <andros@netapp.com>
Cc: fanchaoting <fanchaoting@cn.fujitsu.com>
Cc: Jie Liu <jeff.liu@oracle.com>
Cc: Sunil Mushran <sunil.mushran@gmail.com>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Namjae Jeon <namjae.jeon@samsung.com>
Cc: Pankaj Kumar <pankaj.km@samsung.com>
Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Mel Gorman <mgorman@suse.de>6
2013-11-23 22:33:47 -08:00

361 lines
8.5 KiB
C

/*
* Filename: dev.c
*
*
* Authors: Joshua Morris <josh.h.morris@us.ibm.com>
* Philip Kelleher <pjk1939@linux.vnet.ibm.com>
*
* (C) Copyright 2013 IBM Corporation
*
* 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 of the
* License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software Foundation,
* Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <linux/kernel.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/slab.h>
#include <linux/hdreg.h>
#include <linux/genhd.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/fs.h>
#include "rsxx_priv.h"
static unsigned int blkdev_minors = 64;
module_param(blkdev_minors, uint, 0444);
MODULE_PARM_DESC(blkdev_minors, "Number of minors(partitions)");
/*
* For now I'm making this tweakable in case any applications hit this limit.
* If you see a "bio too big" error in the log you will need to raise this
* value.
*/
static unsigned int blkdev_max_hw_sectors = 1024;
module_param(blkdev_max_hw_sectors, uint, 0444);
MODULE_PARM_DESC(blkdev_max_hw_sectors, "Max hw sectors for a single BIO");
static unsigned int enable_blkdev = 1;
module_param(enable_blkdev , uint, 0444);
MODULE_PARM_DESC(enable_blkdev, "Enable block device interfaces");
struct rsxx_bio_meta {
struct bio *bio;
atomic_t pending_dmas;
atomic_t error;
unsigned long start_time;
};
static struct kmem_cache *bio_meta_pool;
/*----------------- Block Device Operations -----------------*/
static int rsxx_blkdev_ioctl(struct block_device *bdev,
fmode_t mode,
unsigned int cmd,
unsigned long arg)
{
struct rsxx_cardinfo *card = bdev->bd_disk->private_data;
switch (cmd) {
case RSXX_GETREG:
return rsxx_reg_access(card, (void __user *)arg, 1);
case RSXX_SETREG:
return rsxx_reg_access(card, (void __user *)arg, 0);
}
return -ENOTTY;
}
static int rsxx_getgeo(struct block_device *bdev, struct hd_geometry *geo)
{
struct rsxx_cardinfo *card = bdev->bd_disk->private_data;
u64 blocks = card->size8 >> 9;
/*
* get geometry: Fake it. I haven't found any drivers that set
* geo->start, so we won't either.
*/
if (card->size8) {
geo->heads = 64;
geo->sectors = 16;
do_div(blocks, (geo->heads * geo->sectors));
geo->cylinders = blocks;
} else {
geo->heads = 0;
geo->sectors = 0;
geo->cylinders = 0;
}
return 0;
}
static const struct block_device_operations rsxx_fops = {
.owner = THIS_MODULE,
.getgeo = rsxx_getgeo,
.ioctl = rsxx_blkdev_ioctl,
};
static void disk_stats_start(struct rsxx_cardinfo *card, struct bio *bio)
{
struct hd_struct *part0 = &card->gendisk->part0;
int rw = bio_data_dir(bio);
int cpu;
cpu = part_stat_lock();
part_round_stats(cpu, part0);
part_inc_in_flight(part0, rw);
part_stat_unlock();
}
static void disk_stats_complete(struct rsxx_cardinfo *card,
struct bio *bio,
unsigned long start_time)
{
struct hd_struct *part0 = &card->gendisk->part0;
unsigned long duration = jiffies - start_time;
int rw = bio_data_dir(bio);
int cpu;
cpu = part_stat_lock();
part_stat_add(cpu, part0, sectors[rw], bio_sectors(bio));
part_stat_inc(cpu, part0, ios[rw]);
part_stat_add(cpu, part0, ticks[rw], duration);
part_round_stats(cpu, part0);
part_dec_in_flight(part0, rw);
part_stat_unlock();
}
static void bio_dma_done_cb(struct rsxx_cardinfo *card,
void *cb_data,
unsigned int error)
{
struct rsxx_bio_meta *meta = cb_data;
if (error)
atomic_set(&meta->error, 1);
if (atomic_dec_and_test(&meta->pending_dmas)) {
if (!card->eeh_state && card->gendisk)
disk_stats_complete(card, meta->bio, meta->start_time);
bio_endio(meta->bio, atomic_read(&meta->error) ? -EIO : 0);
kmem_cache_free(bio_meta_pool, meta);
}
}
static void rsxx_make_request(struct request_queue *q, struct bio *bio)
{
struct rsxx_cardinfo *card = q->queuedata;
struct rsxx_bio_meta *bio_meta;
int st = -EINVAL;
might_sleep();
if (!card)
goto req_err;
if (bio_end_sector(bio) > get_capacity(card->gendisk))
goto req_err;
if (unlikely(card->halt)) {
st = -EFAULT;
goto req_err;
}
if (unlikely(card->dma_fault)) {
st = (-EFAULT);
goto req_err;
}
if (bio->bi_iter.bi_size == 0) {
dev_err(CARD_TO_DEV(card), "size zero BIO!\n");
goto req_err;
}
bio_meta = kmem_cache_alloc(bio_meta_pool, GFP_KERNEL);
if (!bio_meta) {
st = -ENOMEM;
goto req_err;
}
bio_meta->bio = bio;
atomic_set(&bio_meta->error, 0);
atomic_set(&bio_meta->pending_dmas, 0);
bio_meta->start_time = jiffies;
if (!unlikely(card->halt))
disk_stats_start(card, bio);
dev_dbg(CARD_TO_DEV(card), "BIO[%c]: meta: %p addr8: x%llx size: %d\n",
bio_data_dir(bio) ? 'W' : 'R', bio_meta,
(u64)bio->bi_iter.bi_sector << 9, bio->bi_iter.bi_size);
st = rsxx_dma_queue_bio(card, bio, &bio_meta->pending_dmas,
bio_dma_done_cb, bio_meta);
if (st)
goto queue_err;
return;
queue_err:
kmem_cache_free(bio_meta_pool, bio_meta);
req_err:
bio_endio(bio, st);
}
/*----------------- Device Setup -------------------*/
static bool rsxx_discard_supported(struct rsxx_cardinfo *card)
{
unsigned char pci_rev;
pci_read_config_byte(card->dev, PCI_REVISION_ID, &pci_rev);
return (pci_rev >= RSXX_DISCARD_SUPPORT);
}
int rsxx_attach_dev(struct rsxx_cardinfo *card)
{
mutex_lock(&card->dev_lock);
/* The block device requires the stripe size from the config. */
if (enable_blkdev) {
if (card->config_valid)
set_capacity(card->gendisk, card->size8 >> 9);
else
set_capacity(card->gendisk, 0);
add_disk(card->gendisk);
card->bdev_attached = 1;
}
mutex_unlock(&card->dev_lock);
return 0;
}
void rsxx_detach_dev(struct rsxx_cardinfo *card)
{
mutex_lock(&card->dev_lock);
if (card->bdev_attached) {
del_gendisk(card->gendisk);
card->bdev_attached = 0;
}
mutex_unlock(&card->dev_lock);
}
int rsxx_setup_dev(struct rsxx_cardinfo *card)
{
unsigned short blk_size;
mutex_init(&card->dev_lock);
if (!enable_blkdev)
return 0;
card->major = register_blkdev(0, DRIVER_NAME);
if (card->major < 0) {
dev_err(CARD_TO_DEV(card), "Failed to get major number\n");
return -ENOMEM;
}
card->queue = blk_alloc_queue(GFP_KERNEL);
if (!card->queue) {
dev_err(CARD_TO_DEV(card), "Failed queue alloc\n");
unregister_blkdev(card->major, DRIVER_NAME);
return -ENOMEM;
}
card->gendisk = alloc_disk(blkdev_minors);
if (!card->gendisk) {
dev_err(CARD_TO_DEV(card), "Failed disk alloc\n");
blk_cleanup_queue(card->queue);
unregister_blkdev(card->major, DRIVER_NAME);
return -ENOMEM;
}
if (card->config_valid) {
blk_size = card->config.data.block_size;
blk_queue_dma_alignment(card->queue, blk_size - 1);
blk_queue_logical_block_size(card->queue, blk_size);
}
blk_queue_make_request(card->queue, rsxx_make_request);
blk_queue_bounce_limit(card->queue, BLK_BOUNCE_ANY);
blk_queue_max_hw_sectors(card->queue, blkdev_max_hw_sectors);
blk_queue_physical_block_size(card->queue, RSXX_HW_BLK_SIZE);
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, card->queue);
if (rsxx_discard_supported(card)) {
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, card->queue);
blk_queue_max_discard_sectors(card->queue,
RSXX_HW_BLK_SIZE >> 9);
card->queue->limits.discard_granularity = RSXX_HW_BLK_SIZE;
card->queue->limits.discard_alignment = RSXX_HW_BLK_SIZE;
card->queue->limits.discard_zeroes_data = 1;
}
card->queue->queuedata = card;
snprintf(card->gendisk->disk_name, sizeof(card->gendisk->disk_name),
"rsxx%d", card->disk_id);
card->gendisk->driverfs_dev = &card->dev->dev;
card->gendisk->major = card->major;
card->gendisk->first_minor = 0;
card->gendisk->fops = &rsxx_fops;
card->gendisk->private_data = card;
card->gendisk->queue = card->queue;
return 0;
}
void rsxx_destroy_dev(struct rsxx_cardinfo *card)
{
if (!enable_blkdev)
return;
put_disk(card->gendisk);
card->gendisk = NULL;
blk_cleanup_queue(card->queue);
card->queue->queuedata = NULL;
unregister_blkdev(card->major, DRIVER_NAME);
}
int rsxx_dev_init(void)
{
bio_meta_pool = KMEM_CACHE(rsxx_bio_meta, SLAB_HWCACHE_ALIGN);
if (!bio_meta_pool)
return -ENOMEM;
return 0;
}
void rsxx_dev_cleanup(void)
{
kmem_cache_destroy(bio_meta_pool);
}