linux/drivers/md/bcache/io.c
Coly Li 6e916a7eb1 bcache: store disk name in struct cache and struct cached_dev
Current code uses bdevname() or bio_devname() to reference gendisk
disk name when bcache needs to display the disk names in kernel message.
It was safe before bcache device failure handling patch set merged in,
because when devices are failed, there was deadlock to prevent bcache
printing error messages with gendisk disk name. But after the failure
handling patch set merged, the deadlock is fixed, so it is possible
that the gendisk structure bdev->hd_disk is released when bdevname() is
called to reference bdev->bd_disk->disk_name[]. This is why I receive
bug report of NULL pointers deference panic.

This patch stores gendisk disk name in a buffer inside struct cache and
struct cached_dev, then print out the offline device name won't reference
bdev->hd_disk anymore. And this patch also avoids extra function calls
of bdevname() and bio_devnmae().

Changelog:
v3, add Reviewed-by from Hannes.
v2, call bdevname() earlier in register_bdev()
v1, first version with segguestion from Junhui Tang.

Fixes: c7b7bd0740 ("bcache: add io_disable to struct cached_dev")
Fixes: 5138ac6748 ("bcache: fix misleading error message in bch_count_io_errors()")
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-05-03 08:35:08 -06:00

161 lines
3.8 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Some low level IO code, and hacks for various block layer limitations
*
* Copyright 2010, 2011 Kent Overstreet <kent.overstreet@gmail.com>
* Copyright 2012 Google, Inc.
*/
#include "bcache.h"
#include "bset.h"
#include "debug.h"
#include <linux/blkdev.h>
/* Bios with headers */
void bch_bbio_free(struct bio *bio, struct cache_set *c)
{
struct bbio *b = container_of(bio, struct bbio, bio);
mempool_free(b, c->bio_meta);
}
struct bio *bch_bbio_alloc(struct cache_set *c)
{
struct bbio *b = mempool_alloc(c->bio_meta, GFP_NOIO);
struct bio *bio = &b->bio;
bio_init(bio, bio->bi_inline_vecs, bucket_pages(c));
return bio;
}
void __bch_submit_bbio(struct bio *bio, struct cache_set *c)
{
struct bbio *b = container_of(bio, struct bbio, bio);
bio->bi_iter.bi_sector = PTR_OFFSET(&b->key, 0);
bio_set_dev(bio, PTR_CACHE(c, &b->key, 0)->bdev);
b->submit_time_us = local_clock_us();
closure_bio_submit(c, bio, bio->bi_private);
}
void bch_submit_bbio(struct bio *bio, struct cache_set *c,
struct bkey *k, unsigned ptr)
{
struct bbio *b = container_of(bio, struct bbio, bio);
bch_bkey_copy_single_ptr(&b->key, k, ptr);
__bch_submit_bbio(bio, c);
}
/* IO errors */
void bch_count_backing_io_errors(struct cached_dev *dc, struct bio *bio)
{
unsigned errors;
WARN_ONCE(!dc, "NULL pointer of struct cached_dev");
errors = atomic_add_return(1, &dc->io_errors);
if (errors < dc->error_limit)
pr_err("%s: IO error on backing device, unrecoverable",
dc->backing_dev_name);
else
bch_cached_dev_error(dc);
}
void bch_count_io_errors(struct cache *ca,
blk_status_t error,
int is_read,
const char *m)
{
/*
* The halflife of an error is:
* log2(1/2)/log2(127/128) * refresh ~= 88 * refresh
*/
if (ca->set->error_decay) {
unsigned count = atomic_inc_return(&ca->io_count);
while (count > ca->set->error_decay) {
unsigned errors;
unsigned old = count;
unsigned new = count - ca->set->error_decay;
/*
* First we subtract refresh from count; each time we
* succesfully do so, we rescale the errors once:
*/
count = atomic_cmpxchg(&ca->io_count, old, new);
if (count == old) {
count = new;
errors = atomic_read(&ca->io_errors);
do {
old = errors;
new = ((uint64_t) errors * 127) / 128;
errors = atomic_cmpxchg(&ca->io_errors,
old, new);
} while (old != errors);
}
}
}
if (error) {
unsigned errors = atomic_add_return(1 << IO_ERROR_SHIFT,
&ca->io_errors);
errors >>= IO_ERROR_SHIFT;
if (errors < ca->set->error_limit)
pr_err("%s: IO error on %s%s",
ca->cache_dev_name, m,
is_read ? ", recovering." : ".");
else
bch_cache_set_error(ca->set,
"%s: too many IO errors %s",
ca->cache_dev_name, m);
}
}
void bch_bbio_count_io_errors(struct cache_set *c, struct bio *bio,
blk_status_t error, const char *m)
{
struct bbio *b = container_of(bio, struct bbio, bio);
struct cache *ca = PTR_CACHE(c, &b->key, 0);
int is_read = (bio_data_dir(bio) == READ ? 1 : 0);
unsigned threshold = op_is_write(bio_op(bio))
? c->congested_write_threshold_us
: c->congested_read_threshold_us;
if (threshold) {
unsigned t = local_clock_us();
int us = t - b->submit_time_us;
int congested = atomic_read(&c->congested);
if (us > (int) threshold) {
int ms = us / 1024;
c->congested_last_us = t;
ms = min(ms, CONGESTED_MAX + congested);
atomic_sub(ms, &c->congested);
} else if (congested < 0)
atomic_inc(&c->congested);
}
bch_count_io_errors(ca, error, is_read, m);
}
void bch_bbio_endio(struct cache_set *c, struct bio *bio,
blk_status_t error, const char *m)
{
struct closure *cl = bio->bi_private;
bch_bbio_count_io_errors(c, bio, error, m);
bio_put(bio);
closure_put(cl);
}