mirror_zfs/include/sys/zfs_ioctl.h

353 lines
9.0 KiB
C
Raw Normal View History

2008-11-20 23:01:55 +03:00
/*
* 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 http://www.opensolaris.org/os/licensing.
* 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.
2008-11-20 23:01:55 +03:00
*/
#ifndef _SYS_ZFS_IOCTL_H
#define _SYS_ZFS_IOCTL_H
#include <sys/cred.h>
#include <sys/dmu.h>
#include <sys/zio.h>
#include <sys/dsl_deleg.h>
#include <sys/spa.h>
#include <sys/zfs_stat.h>
2008-11-20 23:01:55 +03:00
#ifdef _KERNEL
#include <sys/nvpair.h>
#endif /* _KERNEL */
#ifdef __cplusplus
extern "C" {
#endif
/*
* Property values for snapdir
*/
#define ZFS_SNAPDIR_HIDDEN 0
#define ZFS_SNAPDIR_VISIBLE 1
Add snapdev=[hidden|visible] dataset property The new snapdev dataset property may be set to control the visibility of zvol snapshot devices. By default this value is set to 'hidden' which will prevent zvol snapshots from appearing under /dev/zvol/ and /dev/<dataset>/. When set to 'visible' all zvol snapshots for the dataset will be visible. This functionality was largely added because when automatic snapshoting is enabled large numbers of read-only zvol snapshots will be created. When creating these devices the kernel will attempt to read their partition tables, and blkid will attempt to identify any filesystems on those partitions. This leads to a variety of issues: 1) The zvol partition tables will be read in the context of the `modprobe zfs` for automatically imported pools. This is undesirable and should be done asynchronously, but for now reducing the number of visible devices helps. 2) Udev expects to be able to complete its work for a new block devices fairly quickly. When many zvol devices are added at the same time this is no longer be true. It can lead to udev timeouts and missing /dev/zvol links. 3) Simply having lots of devices in /dev/ can be aukward from a management standpoint. Hidding the devices your unlikely to ever use helps with this. Any snapshot device which is needed can be made visible by changing the snapdev property. NOTE: This patch changes the default behavior for zvols which was effectively 'snapdev=visible'. Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #1235 Closes #945 Issue #956 Issue #756
2013-02-14 03:11:59 +04:00
/*
* Property values for snapdev
*/
#define ZFS_SNAPDEV_HIDDEN 0
#define ZFS_SNAPDEV_VISIBLE 1
/*
* Field manipulation macros for the drr_versioninfo field of the
* send stream header.
*/
/*
* Header types for zfs send streams.
*/
typedef enum drr_headertype {
DMU_SUBSTREAM = 0x1,
DMU_COMPOUNDSTREAM = 0x2
} drr_headertype_t;
#define DMU_GET_STREAM_HDRTYPE(vi) BF64_GET((vi), 0, 2)
#define DMU_SET_STREAM_HDRTYPE(vi, x) BF64_SET((vi), 0, 2, x)
#define DMU_GET_FEATUREFLAGS(vi) BF64_GET((vi), 2, 30)
#define DMU_SET_FEATUREFLAGS(vi, x) BF64_SET((vi), 2, 30, x)
/*
* Feature flags for zfs send streams (flags in drr_versioninfo)
*/
#define DMU_BACKUP_FEATURE_DEDUP (0x1)
#define DMU_BACKUP_FEATURE_DEDUPPROPS (0x2)
#define DMU_BACKUP_FEATURE_SA_SPILL (0x4)
/*
* Mask of all supported backup features
*/
#define DMU_BACKUP_FEATURE_MASK (DMU_BACKUP_FEATURE_DEDUP | \
DMU_BACKUP_FEATURE_DEDUPPROPS | DMU_BACKUP_FEATURE_SA_SPILL)
/* Are all features in the given flag word currently supported? */
#define DMU_STREAM_SUPPORTED(x) (!((x) & ~DMU_BACKUP_FEATURE_MASK))
/*
* The drr_versioninfo field of the dmu_replay_record has the
* following layout:
*
* 64 56 48 40 32 24 16 8 0
* +-------+-------+-------+-------+-------+-------+-------+-------+
* | reserved | feature-flags |C|S|
* +-------+-------+-------+-------+-------+-------+-------+-------+
*
* The low order two bits indicate the header type: SUBSTREAM (0x1)
* or COMPOUNDSTREAM (0x2). Using two bits for this is historical:
* this field used to be a version number, where the two version types
* were 1 and 2. Using two bits for this allows earlier versions of
* the code to be able to recognize send streams that don't use any
* of the features indicated by feature flags.
*/
2008-11-20 23:01:55 +03:00
#define DMU_BACKUP_MAGIC 0x2F5bacbacULL
#define DRR_FLAG_CLONE (1<<0)
#define DRR_FLAG_CI_DATA (1<<1)
/*
* flags in the drr_checksumflags field in the DRR_WRITE and
* DRR_WRITE_BYREF blocks
*/
#define DRR_CHECKSUM_DEDUP (1<<0)
#define DRR_IS_DEDUP_CAPABLE(flags) ((flags) & DRR_CHECKSUM_DEDUP)
2008-11-20 23:01:55 +03:00
/*
* zfs ioctl command structure
*/
typedef struct dmu_replay_record {
enum {
DRR_BEGIN, DRR_OBJECT, DRR_FREEOBJECTS,
DRR_WRITE, DRR_FREE, DRR_END, DRR_WRITE_BYREF,
DRR_SPILL, DRR_NUMTYPES
2008-11-20 23:01:55 +03:00
} drr_type;
uint32_t drr_payloadlen;
union {
struct drr_begin {
uint64_t drr_magic;
uint64_t drr_versioninfo; /* was drr_version */
2008-11-20 23:01:55 +03:00
uint64_t drr_creation_time;
dmu_objset_type_t drr_type;
uint32_t drr_flags;
uint64_t drr_toguid;
uint64_t drr_fromguid;
char drr_toname[MAXNAMELEN];
} drr_begin;
struct drr_end {
zio_cksum_t drr_checksum;
uint64_t drr_toguid;
2008-11-20 23:01:55 +03:00
} drr_end;
struct drr_object {
uint64_t drr_object;
dmu_object_type_t drr_type;
dmu_object_type_t drr_bonustype;
uint32_t drr_blksz;
uint32_t drr_bonuslen;
uint8_t drr_checksumtype;
2008-11-20 23:01:55 +03:00
uint8_t drr_compress;
uint8_t drr_pad[6];
uint64_t drr_toguid;
2008-11-20 23:01:55 +03:00
/* bonus content follows */
} drr_object;
struct drr_freeobjects {
uint64_t drr_firstobj;
uint64_t drr_numobjs;
uint64_t drr_toguid;
2008-11-20 23:01:55 +03:00
} drr_freeobjects;
struct drr_write {
uint64_t drr_object;
dmu_object_type_t drr_type;
uint32_t drr_pad;
uint64_t drr_offset;
uint64_t drr_length;
uint64_t drr_toguid;
uint8_t drr_checksumtype;
uint8_t drr_checksumflags;
uint8_t drr_pad2[6];
ddt_key_t drr_key; /* deduplication key */
2008-11-20 23:01:55 +03:00
/* content follows */
} drr_write;
struct drr_free {
uint64_t drr_object;
uint64_t drr_offset;
uint64_t drr_length;
uint64_t drr_toguid;
2008-11-20 23:01:55 +03:00
} drr_free;
struct drr_write_byref {
/* where to put the data */
uint64_t drr_object;
uint64_t drr_offset;
uint64_t drr_length;
uint64_t drr_toguid;
/* where to find the prior copy of the data */
uint64_t drr_refguid;
uint64_t drr_refobject;
uint64_t drr_refoffset;
/* properties of the data */
uint8_t drr_checksumtype;
uint8_t drr_checksumflags;
uint8_t drr_pad2[6];
ddt_key_t drr_key; /* deduplication key */
} drr_write_byref;
struct drr_spill {
uint64_t drr_object;
uint64_t drr_length;
uint64_t drr_toguid;
uint64_t drr_pad[4]; /* needed for crypto */
/* spill data follows */
} drr_spill;
2008-11-20 23:01:55 +03:00
} drr_u;
} dmu_replay_record_t;
/* diff record range types */
typedef enum diff_type {
DDR_NONE = 0x1,
DDR_INUSE = 0x2,
DDR_FREE = 0x4
} diff_type_t;
/*
* The diff reports back ranges of free or in-use objects.
*/
typedef struct dmu_diff_record {
uint64_t ddr_type;
uint64_t ddr_first;
uint64_t ddr_last;
} dmu_diff_record_t;
2008-11-20 23:01:55 +03:00
typedef struct zinject_record {
uint64_t zi_objset;
uint64_t zi_object;
uint64_t zi_start;
uint64_t zi_end;
uint64_t zi_guid;
uint32_t zi_level;
uint32_t zi_error;
uint64_t zi_type;
uint32_t zi_freq;
2009-07-03 02:44:48 +04:00
uint32_t zi_failfast;
char zi_func[MAXNAMELEN];
uint32_t zi_iotype;
int32_t zi_duration;
uint64_t zi_timer;
2008-11-20 23:01:55 +03:00
} zinject_record_t;
#define ZINJECT_NULL 0x1
#define ZINJECT_FLUSH_ARC 0x2
#define ZINJECT_UNLOAD_SPA 0x4
Add linux events This topic branch leverages the Solaris style FMA call points in ZFS to create a user space visible event notification system under Linux. This new system is called zevent and it unifies all previous Solaris style ereports and sysevent notifications. Under this Linux specific scheme when a sysevent or ereport event occurs an nvlist describing the event is created which looks almost exactly like a Solaris ereport. These events are queued up in the kernel when they occur and conditionally logged to the console. It is then up to a user space application to consume the events and do whatever it likes with them. To make this possible the existing /dev/zfs ABI has been extended with two new ioctls which behave as follows. * ZFS_IOC_EVENTS_NEXT Get the next pending event. The kernel will keep track of the last event consumed by the file descriptor and provide the next one if available. If no new events are available the ioctl() will block waiting for the next event. This ioctl may also be called in a non-blocking mode by setting zc.zc_guid = ZEVENT_NONBLOCK. In the non-blocking case if no events are available ENOENT will be returned. It is possible that ESHUTDOWN will be returned if the ioctl() is called while module unloading is in progress. And finally ENOMEM may occur if the provided nvlist buffer is not large enough to contain the entire event. * ZFS_IOC_EVENTS_CLEAR Clear are events queued by the kernel. The kernel will keep a fairly large number of recent events queued, use this ioctl to clear the in kernel list. This will effect all user space processes consuming events. The zpool command has been extended to use this events ABI with the 'events' subcommand. You may run 'zpool events -v' to output a verbose log of all recent events. This is very similar to the Solaris 'fmdump -ev' command with the key difference being it also includes what would be considered sysevents under Solaris. You may also run in follow mode with the '-f' option. To clear the in kernel event queue use the '-c' option. $ sudo cmd/zpool/zpool events -fv TIME CLASS May 13 2010 16:31:15.777711000 ereport.fs.zfs.config.sync class = "ereport.fs.zfs.config.sync" ena = 0x40982b7897700001 detector = (embedded nvlist) version = 0x0 scheme = "zfs" pool = 0xed976600de75dfa6 (end detector) time = 0x4bec8bc3 0x2e5aed98 pool = "zpios" pool_guid = 0xed976600de75dfa6 pool_context = 0x0 While the 'zpool events' command is handy for interactive debugging it is not expected to be the primary consumer of zevents. This ABI was primarily added to facilitate the addition of a user space monitoring daemon. This daemon would consume all events posted by the kernel and based on the type of event perform an action. For most events simply forwarding them on to syslog is likely enough. But this interface also cleanly allows for more sophisticated actions to be taken such as generating an email for a failed drive. Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
2010-08-26 22:42:43 +04:00
#define ZEVENT_NONBLOCK 0x1
#define ZEVENT_SIZE 1024
2008-11-20 23:01:55 +03:00
typedef struct zfs_share {
uint64_t z_exportdata;
uint64_t z_sharedata;
uint64_t z_sharetype; /* 0 = share, 1 = unshare */
uint64_t z_sharemax; /* max length of share string */
} zfs_share_t;
/*
* ZFS file systems may behave the usual, POSIX-compliant way, where
* name lookups are case-sensitive. They may also be set up so that
* all the name lookups are case-insensitive, or so that only some
* lookups, the ones that set an FIGNORECASE flag, are case-insensitive.
*/
typedef enum zfs_case {
ZFS_CASE_SENSITIVE,
ZFS_CASE_INSENSITIVE,
ZFS_CASE_MIXED
} zfs_case_t;
typedef struct zfs_cmd {
char zc_name[MAXPATHLEN];
char zc_value[MAXPATHLEN * 2];
char zc_string[MAXNAMELEN];
char zc_top_ds[MAXPATHLEN];
2008-11-20 23:01:55 +03:00
uint64_t zc_guid;
uint64_t zc_nvlist_conf; /* really (char *) */
uint64_t zc_nvlist_conf_size;
uint64_t zc_nvlist_src; /* really (char *) */
uint64_t zc_nvlist_src_size;
uint64_t zc_nvlist_dst; /* really (char *) */
uint64_t zc_nvlist_dst_size;
uint64_t zc_cookie;
uint64_t zc_objset_type;
uint64_t zc_perm_action;
uint64_t zc_history; /* really (char *) */
uint64_t zc_history_len;
uint64_t zc_history_offset;
uint64_t zc_obj;
2009-07-03 02:44:48 +04:00
uint64_t zc_iflags; /* internal to zfs(7fs) */
2008-11-20 23:01:55 +03:00
zfs_share_t zc_share;
dmu_objset_stats_t zc_objset_stats;
struct drr_begin zc_begin_record;
zinject_record_t zc_inject_record;
2009-08-18 22:43:27 +04:00
boolean_t zc_defer_destroy;
boolean_t zc_temphold;
uint64_t zc_action_handle;
int zc_cleanup_fd;
uint8_t zc_simple;
uint8_t zc_pad[3]; /* alignment */
uint64_t zc_sendobj;
uint64_t zc_fromobj;
uint64_t zc_createtxg;
zfs_stat_t zc_stat;
2008-11-20 23:01:55 +03:00
} zfs_cmd_t;
2009-07-03 02:44:48 +04:00
typedef struct zfs_useracct {
char zu_domain[256];
uid_t zu_rid;
uint32_t zu_pad;
uint64_t zu_space;
} zfs_useracct_t;
#define ZFSDEV_MAX_MINOR (1 << 16)
#define ZFS_MIN_MINOR (ZFSDEV_MAX_MINOR + 1)
2008-11-20 23:01:55 +03:00
#define ZPOOL_EXPORT_AFTER_SPLIT 0x1
2008-11-20 23:01:55 +03:00
#ifdef _KERNEL
typedef struct zfs_creat {
nvlist_t *zct_zplprops;
nvlist_t *zct_props;
} zfs_creat_t;
extern int zfs_secpolicy_snapshot_perms(const char *name, cred_t *cr);
extern int zfs_secpolicy_rename_perms(const char *from,
const char *to, cred_t *cr);
extern int zfs_secpolicy_destroy_perms(const char *name, cred_t *cr);
extern int zfs_unmount_snap(const char *, void *);
2008-11-20 23:01:55 +03:00
enum zfsdev_state_type {
ZST_ONEXIT,
ZST_ZEVENT,
ZST_ALL,
};
typedef struct zfsdev_state {
list_node_t zs_next; /* next zfsdev_state_t link */
struct file *zs_file; /* associated file struct */
minor_t zs_minor; /* made up minor number */
void *zs_onexit; /* onexit data */
void *zs_zevent; /* zevent data */
} zfsdev_state_t;
extern void *zfsdev_get_state(minor_t minor, enum zfsdev_state_type which);
extern minor_t zfsdev_getminor(struct file *filp);
extern minor_t zfsdev_minor_alloc(void);
2008-11-20 23:01:55 +03:00
#endif /* _KERNEL */
#ifdef __cplusplus
}
#endif
#endif /* _SYS_ZFS_IOCTL_H */