linux_kernel/drivers/md/dm-snap-transient.c
Mikulas Patocka 385277bfb5 dm snapshot: fix hung bios when copy error occurs
When there is an error copying a chunk dm-snapshot can incorrectly hold
associated bios indefinitely, resulting in hung IO.

The function copy_callback sets pe->error if there was error copying the
chunk, and then calls complete_exception.  complete_exception calls
pending_complete on error, otherwise it calls commit_exception with
commit_callback (and commit_callback calls complete_exception).

The persistent exception store (dm-snap-persistent.c) assumes that calls
to prepare_exception and commit_exception are paired.
persistent_prepare_exception increases ps->pending_count and
persistent_commit_exception decreases it.

If there is a copy error, persistent_prepare_exception is called but
persistent_commit_exception is not.  This results in the variable
ps->pending_count never returning to zero and that causes some pending
exceptions (and their associated bios) to be held forever.

Fix this by unconditionally calling commit_exception regardless of
whether the copy was successful.  A new "valid" parameter is added to
commit_exception -- when the copy fails this parameter is set to zero so
that the chunk that failed to copy (and all following chunks) is not
recorded in the snapshot store.  Also, remove commit_callback now that
it is merely a wrapper around pending_complete.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
2016-01-08 20:03:05 -05:00

153 lines
3.7 KiB
C

/*
* Copyright (C) 2001-2002 Sistina Software (UK) Limited.
* Copyright (C) 2006-2008 Red Hat GmbH
*
* This file is released under the GPL.
*/
#include "dm-exception-store.h"
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/vmalloc.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/dm-io.h>
#define DM_MSG_PREFIX "transient snapshot"
/*-----------------------------------------------------------------
* Implementation of the store for non-persistent snapshots.
*---------------------------------------------------------------*/
struct transient_c {
sector_t next_free;
};
static void transient_dtr(struct dm_exception_store *store)
{
kfree(store->context);
}
static int transient_read_metadata(struct dm_exception_store *store,
int (*callback)(void *callback_context,
chunk_t old, chunk_t new),
void *callback_context)
{
return 0;
}
static int transient_prepare_exception(struct dm_exception_store *store,
struct dm_exception *e)
{
struct transient_c *tc = store->context;
sector_t size = get_dev_size(dm_snap_cow(store->snap)->bdev);
if (size < (tc->next_free + store->chunk_size))
return -1;
e->new_chunk = sector_to_chunk(store, tc->next_free);
tc->next_free += store->chunk_size;
return 0;
}
static void transient_commit_exception(struct dm_exception_store *store,
struct dm_exception *e, int valid,
void (*callback) (void *, int success),
void *callback_context)
{
/* Just succeed */
callback(callback_context, valid);
}
static void transient_usage(struct dm_exception_store *store,
sector_t *total_sectors,
sector_t *sectors_allocated,
sector_t *metadata_sectors)
{
*sectors_allocated = ((struct transient_c *) store->context)->next_free;
*total_sectors = get_dev_size(dm_snap_cow(store->snap)->bdev);
*metadata_sectors = 0;
}
static int transient_ctr(struct dm_exception_store *store, char *options)
{
struct transient_c *tc;
tc = kmalloc(sizeof(struct transient_c), GFP_KERNEL);
if (!tc)
return -ENOMEM;
tc->next_free = 0;
store->context = tc;
return 0;
}
static unsigned transient_status(struct dm_exception_store *store,
status_type_t status, char *result,
unsigned maxlen)
{
unsigned sz = 0;
switch (status) {
case STATUSTYPE_INFO:
break;
case STATUSTYPE_TABLE:
DMEMIT(" N %llu", (unsigned long long)store->chunk_size);
}
return sz;
}
static struct dm_exception_store_type _transient_type = {
.name = "transient",
.module = THIS_MODULE,
.ctr = transient_ctr,
.dtr = transient_dtr,
.read_metadata = transient_read_metadata,
.prepare_exception = transient_prepare_exception,
.commit_exception = transient_commit_exception,
.usage = transient_usage,
.status = transient_status,
};
static struct dm_exception_store_type _transient_compat_type = {
.name = "N",
.module = THIS_MODULE,
.ctr = transient_ctr,
.dtr = transient_dtr,
.read_metadata = transient_read_metadata,
.prepare_exception = transient_prepare_exception,
.commit_exception = transient_commit_exception,
.usage = transient_usage,
.status = transient_status,
};
int dm_transient_snapshot_init(void)
{
int r;
r = dm_exception_store_type_register(&_transient_type);
if (r) {
DMWARN("Unable to register transient exception store type");
return r;
}
r = dm_exception_store_type_register(&_transient_compat_type);
if (r) {
DMWARN("Unable to register old-style transient "
"exception store type");
dm_exception_store_type_unregister(&_transient_type);
return r;
}
return r;
}
void dm_transient_snapshot_exit(void)
{
dm_exception_store_type_unregister(&_transient_type);
dm_exception_store_type_unregister(&_transient_compat_type);
}