6e916a7eb1
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>
257 lines
5.4 KiB
C
257 lines
5.4 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Assorted bcache debug code
|
|
*
|
|
* Copyright 2010, 2011 Kent Overstreet <kent.overstreet@gmail.com>
|
|
* Copyright 2012 Google, Inc.
|
|
*/
|
|
|
|
#include "bcache.h"
|
|
#include "btree.h"
|
|
#include "debug.h"
|
|
#include "extents.h"
|
|
|
|
#include <linux/console.h>
|
|
#include <linux/debugfs.h>
|
|
#include <linux/module.h>
|
|
#include <linux/random.h>
|
|
#include <linux/seq_file.h>
|
|
|
|
struct dentry *bcache_debug;
|
|
|
|
#ifdef CONFIG_BCACHE_DEBUG
|
|
|
|
#define for_each_written_bset(b, start, i) \
|
|
for (i = (start); \
|
|
(void *) i < (void *) (start) + (KEY_SIZE(&b->key) << 9) &&\
|
|
i->seq == (start)->seq; \
|
|
i = (void *) i + set_blocks(i, block_bytes(b->c)) * \
|
|
block_bytes(b->c))
|
|
|
|
void bch_btree_verify(struct btree *b)
|
|
{
|
|
struct btree *v = b->c->verify_data;
|
|
struct bset *ondisk, *sorted, *inmemory;
|
|
struct bio *bio;
|
|
|
|
if (!b->c->verify || !b->c->verify_ondisk)
|
|
return;
|
|
|
|
down(&b->io_mutex);
|
|
mutex_lock(&b->c->verify_lock);
|
|
|
|
ondisk = b->c->verify_ondisk;
|
|
sorted = b->c->verify_data->keys.set->data;
|
|
inmemory = b->keys.set->data;
|
|
|
|
bkey_copy(&v->key, &b->key);
|
|
v->written = 0;
|
|
v->level = b->level;
|
|
v->keys.ops = b->keys.ops;
|
|
|
|
bio = bch_bbio_alloc(b->c);
|
|
bio_set_dev(bio, PTR_CACHE(b->c, &b->key, 0)->bdev);
|
|
bio->bi_iter.bi_sector = PTR_OFFSET(&b->key, 0);
|
|
bio->bi_iter.bi_size = KEY_SIZE(&v->key) << 9;
|
|
bio->bi_opf = REQ_OP_READ | REQ_META;
|
|
bch_bio_map(bio, sorted);
|
|
|
|
submit_bio_wait(bio);
|
|
bch_bbio_free(bio, b->c);
|
|
|
|
memcpy(ondisk, sorted, KEY_SIZE(&v->key) << 9);
|
|
|
|
bch_btree_node_read_done(v);
|
|
sorted = v->keys.set->data;
|
|
|
|
if (inmemory->keys != sorted->keys ||
|
|
memcmp(inmemory->start,
|
|
sorted->start,
|
|
(void *) bset_bkey_last(inmemory) - (void *) inmemory->start)) {
|
|
struct bset *i;
|
|
unsigned j;
|
|
|
|
console_lock();
|
|
|
|
printk(KERN_ERR "*** in memory:\n");
|
|
bch_dump_bset(&b->keys, inmemory, 0);
|
|
|
|
printk(KERN_ERR "*** read back in:\n");
|
|
bch_dump_bset(&v->keys, sorted, 0);
|
|
|
|
for_each_written_bset(b, ondisk, i) {
|
|
unsigned block = ((void *) i - (void *) ondisk) /
|
|
block_bytes(b->c);
|
|
|
|
printk(KERN_ERR "*** on disk block %u:\n", block);
|
|
bch_dump_bset(&b->keys, i, block);
|
|
}
|
|
|
|
printk(KERN_ERR "*** block %zu not written\n",
|
|
((void *) i - (void *) ondisk) / block_bytes(b->c));
|
|
|
|
for (j = 0; j < inmemory->keys; j++)
|
|
if (inmemory->d[j] != sorted->d[j])
|
|
break;
|
|
|
|
printk(KERN_ERR "b->written %u\n", b->written);
|
|
|
|
console_unlock();
|
|
panic("verify failed at %u\n", j);
|
|
}
|
|
|
|
mutex_unlock(&b->c->verify_lock);
|
|
up(&b->io_mutex);
|
|
}
|
|
|
|
void bch_data_verify(struct cached_dev *dc, struct bio *bio)
|
|
{
|
|
struct bio *check;
|
|
struct bio_vec bv, cbv;
|
|
struct bvec_iter iter, citer = { 0 };
|
|
|
|
check = bio_clone_kmalloc(bio, GFP_NOIO);
|
|
if (!check)
|
|
return;
|
|
check->bi_opf = REQ_OP_READ;
|
|
|
|
if (bch_bio_alloc_pages(check, GFP_NOIO))
|
|
goto out_put;
|
|
|
|
submit_bio_wait(check);
|
|
|
|
citer.bi_size = UINT_MAX;
|
|
bio_for_each_segment(bv, bio, iter) {
|
|
void *p1 = kmap_atomic(bv.bv_page);
|
|
void *p2;
|
|
|
|
cbv = bio_iter_iovec(check, citer);
|
|
p2 = page_address(cbv.bv_page);
|
|
|
|
cache_set_err_on(memcmp(p1 + bv.bv_offset,
|
|
p2 + bv.bv_offset,
|
|
bv.bv_len),
|
|
dc->disk.c,
|
|
"verify failed at dev %s sector %llu",
|
|
dc->backing_dev_name,
|
|
(uint64_t) bio->bi_iter.bi_sector);
|
|
|
|
kunmap_atomic(p1);
|
|
bio_advance_iter(check, &citer, bv.bv_len);
|
|
}
|
|
|
|
bio_free_pages(check);
|
|
out_put:
|
|
bio_put(check);
|
|
}
|
|
|
|
#endif
|
|
|
|
#ifdef CONFIG_DEBUG_FS
|
|
|
|
/* XXX: cache set refcounting */
|
|
|
|
struct dump_iterator {
|
|
char buf[PAGE_SIZE];
|
|
size_t bytes;
|
|
struct cache_set *c;
|
|
struct keybuf keys;
|
|
};
|
|
|
|
static bool dump_pred(struct keybuf *buf, struct bkey *k)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static ssize_t bch_dump_read(struct file *file, char __user *buf,
|
|
size_t size, loff_t *ppos)
|
|
{
|
|
struct dump_iterator *i = file->private_data;
|
|
ssize_t ret = 0;
|
|
char kbuf[80];
|
|
|
|
while (size) {
|
|
struct keybuf_key *w;
|
|
unsigned bytes = min(i->bytes, size);
|
|
|
|
int err = copy_to_user(buf, i->buf, bytes);
|
|
if (err)
|
|
return err;
|
|
|
|
ret += bytes;
|
|
buf += bytes;
|
|
size -= bytes;
|
|
i->bytes -= bytes;
|
|
memmove(i->buf, i->buf + bytes, i->bytes);
|
|
|
|
if (i->bytes)
|
|
break;
|
|
|
|
w = bch_keybuf_next_rescan(i->c, &i->keys, &MAX_KEY, dump_pred);
|
|
if (!w)
|
|
break;
|
|
|
|
bch_extent_to_text(kbuf, sizeof(kbuf), &w->key);
|
|
i->bytes = snprintf(i->buf, PAGE_SIZE, "%s\n", kbuf);
|
|
bch_keybuf_del(&i->keys, w);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int bch_dump_open(struct inode *inode, struct file *file)
|
|
{
|
|
struct cache_set *c = inode->i_private;
|
|
struct dump_iterator *i;
|
|
|
|
i = kzalloc(sizeof(struct dump_iterator), GFP_KERNEL);
|
|
if (!i)
|
|
return -ENOMEM;
|
|
|
|
file->private_data = i;
|
|
i->c = c;
|
|
bch_keybuf_init(&i->keys);
|
|
i->keys.last_scanned = KEY(0, 0, 0);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int bch_dump_release(struct inode *inode, struct file *file)
|
|
{
|
|
kfree(file->private_data);
|
|
return 0;
|
|
}
|
|
|
|
static const struct file_operations cache_set_debug_ops = {
|
|
.owner = THIS_MODULE,
|
|
.open = bch_dump_open,
|
|
.read = bch_dump_read,
|
|
.release = bch_dump_release
|
|
};
|
|
|
|
void bch_debug_init_cache_set(struct cache_set *c)
|
|
{
|
|
if (!IS_ERR_OR_NULL(bcache_debug)) {
|
|
char name[50];
|
|
snprintf(name, 50, "bcache-%pU", c->sb.set_uuid);
|
|
|
|
c->debug = debugfs_create_file(name, 0400, bcache_debug, c,
|
|
&cache_set_debug_ops);
|
|
}
|
|
}
|
|
|
|
#endif
|
|
|
|
void bch_debug_exit(void)
|
|
{
|
|
if (!IS_ERR_OR_NULL(bcache_debug))
|
|
debugfs_remove_recursive(bcache_debug);
|
|
}
|
|
|
|
int __init bch_debug_init(struct kobject *kobj)
|
|
{
|
|
bcache_debug = debugfs_create_dir("bcache", NULL);
|
|
|
|
return IS_ERR_OR_NULL(bcache_debug);
|
|
}
|