c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2024-12-26 19:19:32 +03:00
Code Issues Packages Projects Releases Wiki Activity
6c29422e90
mirror_zfs/include/sys/vdev.h
George Wilson 460d887c43
panic loop when removing slog device 
There is a window in the slog removal code where a panic loop could
ensue if the system crashes during that operation. The original design
of slog removal did not persisted any state because the removal happened
synchronously. This was changed by a later commit which persisted the
vdev_removing flag and exposed this bug. If a slog removal is in
progress and happens to crash after persisting the vdev_removing flag to
the label but before the vdev is removed from the spa config, then the
pool will continue to panic on import. Here's a sample of the panic:

[  134.387411] VERIFY0(0 == dmu_buf_hold_array(os, object, offset, size,
FALSE, FTAG, &numbufs, &dbp)) failed (0 == 22)
[  134.393865] PANIC at dmu.c:1135:dmu_write()
[  134.396035] Kernel panic - not syncing: VERIFY0(0 ==
dmu_buf_hold_array(os, object, offset, size, FALSE, FTAG, &numbufs,
&dbp)) failed (0 == 22)
[  134.397857] CPU: 2 PID: 5914 Comm: txg_sync Kdump: loaded Tainted:
P           OE     5.4.0-1100-dx2023020205-b3751f8c2-azure #106
[  134.407938] Hardware name: Microsoft Corporation Virtual
Machine/Virtual Machine, BIOS 090008  12/07/2018
[  134.407938] Call Trace:
[  134.407938]  dump_stack+0x57/0x6d
[  134.407938]  panic+0xfb/0x2d7
[  134.407938]  spl_panic+0xcf/0x102 [spl]
[  134.407938]  ? traverse_impl+0x1ca/0x420 [zfs]
[  134.407938]  ? dmu_object_alloc_impl+0x3b4/0x3c0 [zfs]
[  134.407938]  ? dnode_hold+0x1b/0x20 [zfs]
[  134.407938]  dmu_write+0xc3/0xd0 [zfs]
[  134.407938]  ? space_map_alloc+0x55/0x80 [zfs]
[  134.407938]  metaslab_sync+0x61a/0x830 [zfs]
[  134.407938]  ? queued_spin_unlock+0x9/0x10 [zfs]
[  134.407938]  vdev_sync+0x72/0x190 [zfs]
[  134.407938]  spa_sync_iterate_to_convergence+0x160/0x250 [zfs]
[  134.407938]  spa_sync+0x2f7/0x670 [zfs]
[  134.407938]  txg_sync_thread+0x22d/0x2d0 [zfs]
[  134.407938]  ? txg_dispatch_callbacks+0xf0/0xf0 [zfs]
[  134.407938]  thread_generic_wrapper+0x83/0xa0 [spl]
[  134.407938]  kthread+0x104/0x140
[  134.407938]  ? kasan_check_write.constprop.0+0x10/0x10 [spl]
[  134.407938]  ? kthread_park+0x90/0x90
[  134.457802]  ret_from_fork+0x1f/0x40

This change no longer persists the vdev_removing flag when removing slog
devices and also cleans up some code that was added which is not used.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Mark Maybee <mark.maybee@delphix.com>
Signed-off-by: George Wilson <gwilson@delphix.com>
Closes #14652
2023-03-24 10:27:07 -07:00

232 lines
8.8 KiB
C
Raw Blame History

/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* or https://opensource.org/licenses/CDDL-1.0.
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2011, 2020 by Delphix. All rights reserved.
* Copyright (c) 2017, Intel Corporation.
* Copyright (c) 2019, Datto Inc. All rights reserved.
*/
#ifndef _SYS_VDEV_H
#define _SYS_VDEV_H
#include <sys/spa.h>
#include <sys/zio.h>
#include <sys/dmu.h>
#include <sys/space_map.h>
#include <sys/metaslab.h>
#include <sys/fs/zfs.h>
#ifdef __cplusplus
extern "C" {
#endif
typedef enum vdev_dtl_type {
DTL_MISSING, /* 0% replication: no copies of the data */
DTL_PARTIAL, /* less than 100% replication: some copies missing */
DTL_SCRUB, /* unable to fully repair during scrub/resilver */
DTL_OUTAGE, /* temporarily missing (used to attempt detach) */
DTL_TYPES
} vdev_dtl_type_t;
extern int zfs_nocacheflush;
typedef boolean_t vdev_open_children_func_t(vdev_t *vd);
extern void vdev_dbgmsg(vdev_t *vd, const char *fmt, ...)
__attribute__((format(printf, 2, 3)));
extern void vdev_dbgmsg_print_tree(vdev_t *, int);
extern int vdev_open(vdev_t *);
extern void vdev_open_children(vdev_t *);
extern void vdev_open_children_subset(vdev_t *, vdev_open_children_func_t *);
extern int vdev_validate(vdev_t *);
extern int vdev_copy_path_strict(vdev_t *, vdev_t *);
extern void vdev_copy_path_relaxed(vdev_t *, vdev_t *);
extern void vdev_close(vdev_t *);
extern int vdev_create(vdev_t *, uint64_t txg, boolean_t isreplace);
extern void vdev_reopen(vdev_t *);
extern int vdev_validate_aux(vdev_t *vd);
extern zio_t *vdev_probe(vdev_t *vd, zio_t *pio);
extern boolean_t vdev_is_concrete(vdev_t *vd);
extern boolean_t vdev_is_bootable(vdev_t *vd);
extern vdev_t *vdev_lookup_top(spa_t *spa, uint64_t vdev);
extern vdev_t *vdev_lookup_by_guid(vdev_t *vd, uint64_t guid);
extern int vdev_count_leaves(spa_t *spa);
extern void vdev_dtl_dirty(vdev_t *vd, vdev_dtl_type_t d,
uint64_t txg, uint64_t size);
extern boolean_t vdev_dtl_contains(vdev_t *vd, vdev_dtl_type_t d,
uint64_t txg, uint64_t size);
extern boolean_t vdev_dtl_empty(vdev_t *vd, vdev_dtl_type_t d);
extern boolean_t vdev_default_need_resilver(vdev_t *vd, const dva_t *dva,
size_t psize, uint64_t phys_birth);
extern boolean_t vdev_dtl_need_resilver(vdev_t *vd, const dva_t *dva,
size_t psize, uint64_t phys_birth);
extern void vdev_dtl_reassess(vdev_t *vd, uint64_t txg, uint64_t scrub_txg,
boolean_t scrub_done, boolean_t rebuild_done);
extern boolean_t vdev_dtl_required(vdev_t *vd);
extern boolean_t vdev_resilver_needed(vdev_t *vd,
uint64_t *minp, uint64_t *maxp);
extern void vdev_destroy_unlink_zap(vdev_t *vd, uint64_t zapobj,
dmu_tx_t *tx);
extern uint64_t vdev_create_link_zap(vdev_t *vd, dmu_tx_t *tx);
extern void vdev_construct_zaps(vdev_t *vd, dmu_tx_t *tx);
extern void vdev_destroy_spacemaps(vdev_t *vd, dmu_tx_t *tx);
extern void vdev_indirect_mark_obsolete(vdev_t *vd, uint64_t offset,
uint64_t size);
extern void spa_vdev_indirect_mark_obsolete(spa_t *spa, uint64_t vdev,
uint64_t offset, uint64_t size, dmu_tx_t *tx);
extern boolean_t vdev_replace_in_progress(vdev_t *vdev);
extern void vdev_hold(vdev_t *);
extern void vdev_rele(vdev_t *);
extern int vdev_metaslab_init(vdev_t *vd, uint64_t txg);
extern void vdev_metaslab_fini(vdev_t *vd);
extern void vdev_metaslab_set_size(vdev_t *);
extern void vdev_expand(vdev_t *vd, uint64_t txg);
extern void vdev_split(vdev_t *vd);
extern void vdev_deadman(vdev_t *vd, const char *tag);
typedef void vdev_xlate_func_t(void *arg, range_seg64_t *physical_rs);
extern boolean_t vdev_xlate_is_empty(range_seg64_t *rs);
extern void vdev_xlate(vdev_t *vd, const range_seg64_t *logical_rs,
range_seg64_t *physical_rs, range_seg64_t *remain_rs);
extern void vdev_xlate_walk(vdev_t *vd, const range_seg64_t *logical_rs,
vdev_xlate_func_t *func, void *arg);
extern void vdev_get_stats_ex(vdev_t *vd, vdev_stat_t *vs, vdev_stat_ex_t *vsx);
extern metaslab_group_t *vdev_get_mg(vdev_t *vd, metaslab_class_t *mc);
extern void vdev_get_stats(vdev_t *vd, vdev_stat_t *vs);
extern void vdev_clear_stats(vdev_t *vd);
extern void vdev_stat_update(zio_t *zio, uint64_t psize);
extern void vdev_scan_stat_init(vdev_t *vd);
extern void vdev_propagate_state(vdev_t *vd);
extern void vdev_set_state(vdev_t *vd, boolean_t isopen, vdev_state_t state,
vdev_aux_t aux);
extern boolean_t vdev_children_are_offline(vdev_t *vd);
extern void vdev_space_update(vdev_t *vd,
int64_t alloc_delta, int64_t defer_delta, int64_t space_delta);
extern int64_t vdev_deflated_space(vdev_t *vd, int64_t space);
extern uint64_t vdev_psize_to_asize(vdev_t *vd, uint64_t psize);
/*
* Return the amount of space allocated for a gang block header.
*/
static inline uint64_t
vdev_gang_header_asize(vdev_t *vd)
{
return (vdev_psize_to_asize(vd, SPA_GANGBLOCKSIZE));
}
extern int vdev_fault(spa_t *spa, uint64_t guid, vdev_aux_t aux);
extern int vdev_degrade(spa_t *spa, uint64_t guid, vdev_aux_t aux);
extern int vdev_online(spa_t *spa, uint64_t guid, uint64_t flags,
vdev_state_t *);
extern int vdev_offline(spa_t *spa, uint64_t guid, uint64_t flags);
extern int vdev_remove_wanted(spa_t *spa, uint64_t guid);
extern void vdev_clear(spa_t *spa, vdev_t *vd);
extern boolean_t vdev_is_dead(vdev_t *vd);
extern boolean_t vdev_readable(vdev_t *vd);
extern boolean_t vdev_writeable(vdev_t *vd);
extern boolean_t vdev_allocatable(vdev_t *vd);
extern boolean_t vdev_accessible(vdev_t *vd, zio_t *zio);
extern boolean_t vdev_is_spacemap_addressable(vdev_t *vd);
extern void vdev_cache_init(vdev_t *vd);
extern void vdev_cache_fini(vdev_t *vd);
extern boolean_t vdev_cache_read(zio_t *zio);
extern void vdev_cache_write(zio_t *zio);
extern void vdev_cache_purge(vdev_t *vd);
extern void vdev_queue_init(vdev_t *vd);
extern void vdev_queue_fini(vdev_t *vd);
extern zio_t *vdev_queue_io(zio_t *zio);
extern void vdev_queue_io_done(zio_t *zio);
extern void vdev_queue_change_io_priority(zio_t *zio, zio_priority_t priority);
extern int vdev_queue_length(vdev_t *vd);
extern uint64_t vdev_queue_last_offset(vdev_t *vd);
extern void vdev_config_dirty(vdev_t *vd);
extern void vdev_config_clean(vdev_t *vd);
extern int vdev_config_sync(vdev_t **svd, int svdcount, uint64_t txg);
extern void vdev_state_dirty(vdev_t *vd);
extern void vdev_state_clean(vdev_t *vd);
extern void vdev_defer_resilver(vdev_t *vd);
extern boolean_t vdev_clear_resilver_deferred(vdev_t *vd, dmu_tx_t *tx);
typedef enum vdev_config_flag {
VDEV_CONFIG_SPARE = 1 << 0,
VDEV_CONFIG_L2CACHE = 1 << 1,
VDEV_CONFIG_MOS = 1 << 2,
VDEV_CONFIG_MISSING = 1 << 3
} vdev_config_flag_t;
extern void vdev_post_kobj_evt(vdev_t *vd);
extern void vdev_clear_kobj_evt(vdev_t *vd);
extern void vdev_top_config_generate(spa_t *spa, nvlist_t *config);
extern nvlist_t *vdev_config_generate(spa_t *spa, vdev_t *vd,
boolean_t getstats, vdev_config_flag_t flags);
/*
* Label routines
*/
struct uberblock;
extern uint64_t vdev_label_offset(uint64_t psize, int l, uint64_t offset);
extern int vdev_label_number(uint64_t psise, uint64_t offset);
extern nvlist_t *vdev_label_read_config(vdev_t *vd, uint64_t txg);
extern void vdev_uberblock_load(vdev_t *, struct uberblock *, nvlist_t **);
extern void vdev_config_generate_stats(vdev_t *vd, nvlist_t *nv);
extern void vdev_label_write(zio_t *zio, vdev_t *vd, int l, abd_t *buf, uint64_t
offset, uint64_t size, zio_done_func_t *done, void *priv, int flags);
extern int vdev_label_read_bootenv(vdev_t *, nvlist_t *);
extern int vdev_label_write_bootenv(vdev_t *, nvlist_t *);
typedef enum {
VDEV_LABEL_CREATE, /* create/add a new device */
VDEV_LABEL_REPLACE, /* replace an existing device */
VDEV_LABEL_SPARE, /* add a new hot spare */
VDEV_LABEL_REMOVE, /* remove an existing device */
VDEV_LABEL_L2CACHE, /* add an L2ARC cache device */
VDEV_LABEL_SPLIT /* generating new label for split-off dev */
} vdev_labeltype_t;
extern int vdev_label_init(vdev_t *vd, uint64_t txg, vdev_labeltype_t reason);
extern int vdev_prop_set(vdev_t *vd, nvlist_t *innvl, nvlist_t *outnvl);
extern int vdev_prop_get(vdev_t *vd, nvlist_t *nvprops, nvlist_t *outnvl);
#ifdef __cplusplus
}
#endif
#endif /* _SYS_VDEV_H */
Reference in New Issue View Git Blame Copy Permalink