mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2026-01-14 17:22:05 +03:00
96f9d271ea
When destroying a zvol, it is not "unpublished" from the system (that is, /dev/zd* node removed) until zvol_os_free(). Under Linux, at the time del_gendisk() and put_disk() are called, the device node may still be have an active hold, from a userspace program or something inside the kernel (a partition probe). As it is currently, this can lead to calls to zvol_open() or zvol_release() while the zvol_state_t is partially or fully freed. zvol_open() has some protection against this by checking that private_data is NULL, but zvol_release does not. This implements a better ordering for all of this by adding a new OS-side method, zvol_os_remove_minor(), which is responsible for fully decoupling the "private" (OS-side) objects from the zvol_state_t. For Linux, that means calling put_disk(), nulling private_data, and freeing zv_zso. This takes the place of zvol_os_clear_private(), which was a nod in that direction but did not do enough, and did not do it early enough. Equivalent changes are made on the FreeBSD side to follow the API change. Sponsored-by: Klara, Inc. Sponsored-by: Railway Corporation Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Fedor Uporov <fuporov.vstack@gmail.com> Signed-off-by: Rob Norris <rob.norris@klarasystems.com> Closes #17625
143 lines
4.8 KiB
C
143 lines
4.8 KiB
C
// SPDX-License-Identifier: CDDL-1.0
|
|
/*
|
|
* 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) 2024, 2025, Klara, Inc.
|
|
*/
|
|
|
|
#ifndef _SYS_ZVOL_IMPL_H
|
|
#define _SYS_ZVOL_IMPL_H
|
|
|
|
#include <sys/zfs_context.h>
|
|
|
|
#define ZVOL_RDONLY (1<<0) /* zvol is readonly (writes rejected) */
|
|
#define ZVOL_WRITTEN_TO (1<<1) /* zvol has been written to (needs flush) */
|
|
#define ZVOL_EXCL (1<<2) /* zvol has O_EXCL client right now */
|
|
#define ZVOL_REMOVING (1<<3) /* zvol waiting to remove minor */
|
|
|
|
/*
|
|
* The in-core state of each volume.
|
|
*/
|
|
typedef struct zvol_state {
|
|
char zv_name[MAXNAMELEN]; /* name */
|
|
uint64_t zv_volsize; /* advertised space */
|
|
uint64_t zv_volblocksize; /* volume block size */
|
|
objset_t *zv_objset; /* objset handle */
|
|
uint32_t zv_flags; /* ZVOL_* flags */
|
|
uint32_t zv_open_count; /* open counts */
|
|
uint32_t zv_changed; /* disk changed */
|
|
uint32_t zv_volmode; /* volmode */
|
|
zilog_t *zv_zilog; /* ZIL handle */
|
|
zfs_rangelock_t zv_rangelock; /* for range locking */
|
|
dnode_t *zv_dn; /* dnode hold */
|
|
dataset_kstats_t zv_kstat; /* zvol kstats */
|
|
list_node_t zv_next; /* next zvol_state_t linkage */
|
|
uint64_t zv_hash; /* name hash */
|
|
struct hlist_node zv_hlink; /* hash link */
|
|
kmutex_t zv_state_lock; /* protects zvol_state_t */
|
|
atomic_t zv_suspend_ref; /* refcount for suspend */
|
|
krwlock_t zv_suspend_lock; /* suspend lock */
|
|
kcondvar_t zv_removing_cv; /* ready to remove minor */
|
|
struct zvol_state_os *zv_zso; /* private platform state */
|
|
boolean_t zv_threading; /* volthreading property */
|
|
} zvol_state_t;
|
|
|
|
/*
|
|
* zvol taskqs
|
|
*/
|
|
typedef struct zv_taskq {
|
|
uint_t tqs_cnt;
|
|
taskq_t **tqs_taskq;
|
|
} zv_taskq_t;
|
|
|
|
typedef struct zv_request_stack {
|
|
zvol_state_t *zv;
|
|
struct bio *bio;
|
|
#ifdef __linux__
|
|
struct request *rq;
|
|
#endif
|
|
} zv_request_t;
|
|
|
|
typedef struct zv_request_task {
|
|
zv_request_t zvr;
|
|
taskq_ent_t ent;
|
|
} zv_request_task_t;
|
|
|
|
/*
|
|
* Switch taskq at multiple of 512 MB offset. This can be set to a lower value
|
|
* to utilize more threads for small files but may affect prefetch hits.
|
|
*/
|
|
#define ZVOL_TASKQ_OFFSET_SHIFT 29
|
|
|
|
extern krwlock_t zvol_state_lock;
|
|
#define ZVOL_HT_SIZE 1024
|
|
extern struct hlist_head *zvol_htable;
|
|
#define ZVOL_HT_HEAD(hash) (&zvol_htable[(hash) & (ZVOL_HT_SIZE-1)])
|
|
extern zil_replay_func_t *const zvol_replay_vector[TX_MAX_TYPE];
|
|
|
|
extern unsigned int zvol_inhibit_dev;
|
|
extern unsigned int zvol_prefetch_bytes;
|
|
extern unsigned int zvol_volmode;
|
|
extern unsigned int zvol_threads;
|
|
extern unsigned int zvol_num_taskqs;
|
|
extern unsigned int zvol_request_sync;
|
|
extern zv_taskq_t zvol_taskqs;
|
|
|
|
/*
|
|
* platform independent functions exported to platform code
|
|
*/
|
|
zvol_state_t *zvol_find_by_name_hash(const char *name,
|
|
uint64_t hash, int mode);
|
|
int zvol_first_open(zvol_state_t *zv, boolean_t readonly);
|
|
uint64_t zvol_name_hash(const char *name);
|
|
void zvol_last_close(zvol_state_t *zv);
|
|
void zvol_insert(zvol_state_t *zv);
|
|
void zvol_log_truncate(zvol_state_t *zv, dmu_tx_t *tx, uint64_t off,
|
|
uint64_t len);
|
|
void zvol_log_write(zvol_state_t *zv, dmu_tx_t *tx, uint64_t offset,
|
|
uint64_t size, boolean_t commit);
|
|
int zvol_get_data(void *arg, uint64_t arg2, lr_write_t *lr, char *buf,
|
|
struct lwb *lwb, zio_t *zio);
|
|
int zvol_init_impl(void);
|
|
void zvol_fini_impl(void);
|
|
void zvol_wait_close(zvol_state_t *zv);
|
|
int zvol_clone_range(zvol_state_handle_t *, uint64_t,
|
|
zvol_state_handle_t *, uint64_t, uint64_t);
|
|
void zvol_log_clone_range(zilog_t *zilog, dmu_tx_t *tx, int txtype,
|
|
uint64_t off, uint64_t len, uint64_t blksz, const blkptr_t *bps,
|
|
size_t nbps);
|
|
zv_request_task_t *zv_request_task_create(zv_request_t zvr);
|
|
void zv_request_task_free(zv_request_task_t *task);
|
|
|
|
/*
|
|
* platform dependent functions exported to platform independent code
|
|
*/
|
|
void zvol_os_free(zvol_state_t *zv);
|
|
int zvol_os_rename_minor(zvol_state_t *zv, const char *newname);
|
|
int zvol_os_create_minor(const char *name);
|
|
int zvol_os_update_volsize(zvol_state_t *zv, uint64_t volsize);
|
|
boolean_t zvol_os_is_zvol(const char *path);
|
|
void zvol_os_remove_minor(zvol_state_t *zv);
|
|
void zvol_os_set_disk_ro(zvol_state_t *zv, int flags);
|
|
void zvol_os_set_capacity(zvol_state_t *zv, uint64_t capacity);
|
|
|
|
#endif
|