xref: /titanic_44/usr/src/man/man7i/dkio.7i (revision 87308b749adb04ab3f564c765b089962af3edb4d)

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]


Copyright (c) 2009 Sun Microsystems, Inc. All Rights Reserved.
Copyright 2016 Nexenta Systems, Inc.

DKIO 7I "Oct 8, 2016"
NAME
dkio - disk control operations
SYNOPSIS

#include <sys/dkio.h>
#include <sys/vtoc.h>


DESCRIPTION

Disk drivers support a set of ioctl(2) requests for disk controller, geometry, and partition information. Basic to these ioctl() requests are the definitions in <sys/dkio.h>.

IOCTLS

The following ioctl() requests set and/or retrieve the current disk controller, partitions, or geometry information on all architectures: DKIOCINFO

The argument is a pointer to a dk_cinfo structure (described below). This structure tells the controller-type and attributes regarding bad-block processing done on the controller.

/*
 * Structures and definitions for disk I/O control commands
 */
#define DK_DEVLEN 16 /* device name max length, */
 /* including unit # and NULL */
 /* Used for controller info */
struct dk_cinfo {
 char dki_cname[DK_DEVLEN]; /* controller name */
 /* (no unit #) */
 ushort_t dki_ctype; /* controller type */
 ushort_t dki_flags; /* flags */
 ushort_t dki_cnum; /* controller number */
 uint_t dki_addr; /* controller address */
 uint_t dki_space; /* controller bus type */
 uint_t dki_prio; /* interrupt priority */
 uint_t dki_vec; /* interrupt vector */
 char dki_dname[DK_DEVLEN]; /* drive name (no unit #) */
 uint_t dki_unit; /* unit number */
 uint_t dki_slave; /* slave number */
 ushort_t dki_partition; /* partition number */
 ushort_t dki_maxtransfer; /* maximum transfer size */
 /* in DEV_BSIZE */

 };
 /*
 * Controller types
 */

 #define DKC_UNKNOWN 0
 #define DKC_CDROM 1 /* CD-ROM, SCSI or other */
 #define DKC_WDC2880 2
 #define DKC_XXX_0 3 /* unassigned */
 #define DKC_XXX_1 4 /* unassigned */
 #define DKC_DSD5215 5
 #define DKC_ACB4000 7
 #define DKC_XXX_2 9 /* unassigned */
 #define DKC_NCRFLOPPY 10
 #define DKC_SMSFLOPPY 12
 #define DKC_SCSI_CCS 13 /* SCSI CCS compatible */
 #define DKC_INTEL82072 14 /* native floppy chip */
 #define DKC_INTEL82077 19 /* 82077 floppy disk */
 /* controller */
 #define DKC_DIRECT 20 /* Intel direct attached */
 /* device (IDE) */
 #define DKC_PCMCIA_MEM 21 /* PCMCIA memory disk-like */
 /* type */
 #define DKC_PCMCIA_ATA 22 /* PCMCIA AT Attached type */

 /*
 * Sun reserves up through 1023
 */

 #define DKC_CUSTOMER_BASE 1024

 /*
 * Flags
 */

 #define DKI_BAD144 0x01 /* use DEC std 144 */
 /* bad sector fwding */
 #define DKI_MAPTRK 0x02 /* controller does */
 /* track mapping */
 #define DKI_FMTTRK 0x04 /* formats only full
 /* track at a time*/
 #define DKI_FMTVOL 0x08 /* formats only full */
 /* volume at a time*/
 #define DKI_FMTCYL 0x10 /* formats only full */
 /* cylinders at a time*/
 #define DKI_HEXUNIT 0x20 /* unit number printed as */
 /* 3 hexdigits */
 #define DKI_PCMCIA_PFD 0x40 /* PCMCIA pseudo-floppy */
 /* memory card */
DKIOCGAPART

The argument is a pointer to a dk_allmap structure (described below). This ioctl() gets the controller's notion of the current partition table for disk drive.

DKIOCSAPART

The argument is a pointer to a dk_allmap structure (described below). This ioctl() sets the controller's notion of the partition table without changing the disk itself.

/*
 * Partition map (part of dk_label)
 */ struct dk_map {
 daddr_t dkl_cylno; /* starting cylinder */
 daddr_t dkl_nblk; /* number of blocks */
 };
/*
 * Used for all partitions
 */
struct dk_allmap {
 struct dk_map dka_map[NDKMAP];
};
DKIOCGGEOM

The argument is a pointer to a dk_geom structure (described below). This ioctl() gets the controller's notion of the current geometry of the disk drive.

DKIOCSGEOM

The argument is a pointer to a dk_geom structure (described below). This ioctl() sets the controller's notion of the geometry without changing the disk itself.

DKIOCGVTOC

The argument is a pointer to a vtoc structure (described below). This ioctl() returns the device's current volume table of contents (VTOC.) For disks larger than 1TB, DKIOCGEXTVTOC must be used instead.

DKIOCSVTOC

The argument is a pointer to a vtoc structure (described below). This ioctl() changes the VTOC associated with the device. For disks larger than 1TB, DKIOCSEXTVTOC must be used instead.

struct partition {
ushort_t p_tag; /* ID tag of partition */
ushort_t p_flag; /* permission flags */
daddr_t p_start; /* start sector of partition */
long p_size; /* # of blocks in partition */
};

If DKIOCSVTOC is used with a floppy diskette, the p_start field must be the first sector of a cylinder. To compute the number of sectors per cylinder, multiply the number of heads by the number of sectors per track.

struct vtoc {
unsigned long v_bootinfo[3]; /* info needed by mboot
 /* (unsupported)*/
unsigned long v_sanity; /* to verify vtoc */
 /* sanity */
unsigned long v_version; /* layout version */
char v_volume[LEN_DKL_VVOL]; /* volume name */
ushort_t v_sectorsz; /* sector size in bytes*/
ushort_t v_nparts; /* number of partitions*/
unsigned long v_reserved[10]; /* free space */
struct partition v_part[V_NUMPAR]; /* partition headers */
time_t timestamp[V_NUMPAR]; /* partition timestamp */
 /* (unsupported) */
char v_asciilabel[LEN_DKL_ASCII]; /* compatibility */
};

/*
* Partition permission flags
*/

#define V_UNMNT 0x01 /* Unmountable partition */
#define V_RONLY 0x10 /* Read only */

/*
* Partition identification tags
*/

#define V_UNASSIGNED 0x00 /* unassigned partition */
#define V_BOOT 0x01 /* Boot partition */
#define V_ROOT 0x02 /* Root filesystem */
#define V_SWAP 0x03 /* Swap filesystem */
#define V_USR 0x04 /* Usr filesystem */
#define V_BACKUP 0x05 /* full disk */
#define V_VAR 0x07 /* Var partition */
#define V_HOME 0x08 /* Home partition */
#define V_ALTSCTR 0x09 /* Alternate sector partition */
DKIOCGEXTVTOC

The argument is a pointer to an extvtoc structure (described below). This ioctl returns the device's current volume table of contents (VTOC). VTOC is extended to support a disk up to 2TB in size. For disks larger than 1TB this ioctl must be used instead of DKIOCGVTOC.

DKIOCSEXTVTOC

The argument is a pointer to an extvtoc structure (described below). This ioctl changes the VTOC associated with the device. VTOC is extended to support a disk up to 2TB in size. For disks larger than 1TB this ioctl must be used instead of DKIOCSVTOC.

struct extpartition {
ushort_t p_tag; /* ID tag of partition */
ushort_t p_flag; /* permission flags */
ushort_t p_pad[2]; /* reserved */
diskaddr_t p_start; /* start sector no of partition */
diskaddr_t p_size; /* # of blocks in partition */
};


struct extvtoc {
uint64_t v_bootinfo[3]; /* info needed by mboot (unsupported) */
uint64_t v_sanity; /* to verify vtoc sanity */
uint64_t v_version; /* layout version */
char v_volume[LEN_DKL_VVOL]; /* volume name */
ushort_t v_sectorsz; /* sector size in bytes */
ushort_t v_nparts; /* number of partitions */
ushort_t pad[2];
uint64_t v_reserved[10];
struct extpartition v_part[V_NUMPAR]; /* partition headers */
uint64_t timestamp[V_NUMPAR]; /* partition timestamp (unsupported)*/
char v_asciilabel[LEN_DKL_ASCII]; /* for compatibility */
};

Partition permissions flags and identification tags
are defined the same as vtoc structure.
DKIOCEJECT

If the drive supports removable media, this ioctl() requests the disk drive to eject its disk.

DKIOCREMOVABLE

The argument to this ioctl() is an integer. After successful completion, this ioctl() sets that integer to a non-zero value if the drive in question has removable media. If the media is not removable, the integer is set to 0.

DKIOCHOTPLUGGABLE

The argument to this ioctl() is an integer. After successful completion, this ioctl() sets that integer to a non-zero value if the drive in question is hotpluggable. If the media is not hotpluggable, the integer is set to 0.

DKIOCSTATE

This ioctl() blocks until the state of the drive, inserted or ejected, is changed. The argument is a pointer to a dkio_state, enum, whose possible enumerations are listed below. The initial value should be either the last reported state of the drive, or DKIO_NONE. Upon return, the enum pointed to by the argument is updated with the current state of the drive.

enum dkio_state {
DKIO_NONE, /* Return disk's current state */
DKIO_EJECTED, /* Disk state is 'ejected' */
DKIO_INSERTED /* Disk state is 'inserted' */
};
DKIOCLOCK

For devices with removable media, this ioctl() requests the disk drive to lock the door.

DKIOCUNLOCK

For devices with removable media, this ioctl() requests the disk drive to unlock the door.

DKIOCGMEDIAINFO

The argument to this ioctl() is a pointer to a dk_minfo structure. The structure indicates the type of media or the command set profile used by the drive to operate on the media. The dk_minfo structure also indicates the logical media block size the drive uses as the basic unit block size of operation and the raw formatted capacity of the media in number of logical blocks.

DKIOCGMEDIAINFOEXT

The argument to this ioctl() is a pointer to a dk_minfo_ext structure. The structure indicates the type of media or the command set profile used by the drive to operate on the media. The dk_minfo_ext structure also indicates the logical media block size the drive uses as the basic unit block size of operation, the raw formatted capacity of the media in number of logical blocks and the physical block size of the media.

/*
* Used for media info or profile info
*/
struct dk_minfo {
uint_t dki_media_type; /* Media type or profile info */
uint_t dki_lbsize; /* Logical blocksize of media */
diskaddr_t dki_capacity; /* Capacity as # of dki_lbsize blks */
};

/*
* Used for media info or profile info and physical blocksize
*/
struct dk_minfo_ext {
uint_t dki_media_type; /* Media type or profile info */
uint_t dki_lbsize; /* Logical blocksize of media */
diskaddr_t dki_capacity; /* Capacity as # of dki_lbsize blks */
uint_t dki_pbsize; /* Physical blocksize of media */
};


/*
* Media types or profiles known
*/
#define DK_UNKNOWN 0x00 /* Media inserted - type unknown */

/*
* SFF 8090 Specification Version 3, media types 0x01 - 0xfffe are
* retained to maintain compatibility with SFF8090. The following
* define the optical media type.
*/
#define DK_MO_ERASABLE 0x03 /* MO Erasable */
#define DK_MO_WRITEONCE 0x04 /* MO Write once */
#define DK_AS_MO 0x05 /* AS MO */
#define DK_CDROM 0x08 /* CDROM */
#define DK_CDR 0x09 /* CD-R */
#define DK_CDRW 0x0A /* CD-RW */
#define DK_DVDROM 0x10 /* DVD-ROM */
#define DK_DVDR 0x11 /* DVD-R */
#define DK_DVDRAM 0x12 /* DVD_RAM or DVD-RW */

/*
* Media types for other rewritable magnetic media
*/
#define DK_FIXED_DISK 0x10001 /* Fixed disk SCSI or otherwise */
#define DK_FLOPPY 0x10002 /* Floppy media */
#define DK_ZIP 0x10003 /* IOMEGA ZIP media */
#define DK_JAZ 0x10004 /* IOMEGA JAZ media */

If the media exists and the host can obtain a current profile list, the command succeeds and returns the dk_minfo structure with data representing that media.

If there is no media in the drive, the command fails and the host returns an ENXIO error, indicating that it cannot gather the information requested.

If the profile list is not available, the host attempts to identify the media-type based on the available information.

If identification is not possible, the host returns media type DK_UNKNOWN. See NOTES for blocksize usage and capacity information. DKIOCSMBOOT

The argument is a pointer to struct mboot. Copies the mboot information supplied in the argument to the absolute sector 0 of the device. Prior to copying the information, this ioctl() performs the following checks on the mboot data:

Ensures that the signature field is set to 0xAA55.

Ensures that partitions do not overlap.

On SPARC platforms, determines if the device is a removable media.

If the above verification fails, errno is set to EINVAL and the ioctl() command fails. x86 Platforms \(em Upon successful write of mboot, the partition map structure maintained in the driver is updated. If the new Solaris partition is different from the previous one, the internal VTOC table maintained in the driver is set as follows: If _SUNOS_VTOC_8 is defined: Partition: 0. Start: 0. Capacity = Capacity of device. Partition: 2. Start: 0. Capacity = Capacity of device. If _SUNOS_VTOC_16 is defined: Partition: 2. Start: 0. Size = Size specified in mboot - 2 cylinders. Partition: 8. Start: 0. Size = Sectors/cylinder. Partition: 9. Start: Sectors/cylinder. Size = 2 * sectors/cylinder To determine if the Solaris partition has changed: If either offset or the size of the Solaris partition is different from the previous one then it shall be deemed to have changed. In all other cases, the internal VTOC info remains as before. SPARC Platforms \(em The VTOC label and mboot both occupy the same location, namely sector 0. As a result, following the successful write of mboot info, the internal VTOC table maintained in the driver is set as follows: Partition: 0. Start: 0. Size = Capacity of device. Partition: 2. Start: 0. Size = Capacity of device. See the NOTES section for usage of DKIOCSMBOOT when modifying Solaris partitions.
DKIOCGETVOLCAP

This ioctl provides information and status of available capabilities. vc_info is a bitmap and the valid flag values are:

DKV_ABR_CAP - Capable of application-based recovery
DKV_DMR_CAP - Ability to read specific copy of data when
 multiple copies exist. For example, in a two
 way mirror, this ioctl is used to read each
 side of the mirror.
vc_set is a bitmap and the valid flag values are:
DKV_ABR_CAP - This flag is set if ABR has been set on a device
 that supports ABR functionality.
DKV_DMR_CAP - Directed read has been enabled.
These capabilities are not required to be persistent across a system reboot and their persistence depends upon the implementation. For example, if the ABR capability for a DRL mirror simply clears the dirty-region list and subsequently stops updating this list, there is no reason for persistence because the VM recovery is a no-op. Conversely, if the ABR capability is applied to a non-DRL mirror to indicate that the VM should not perform a full recovery of the mirror following a system crash, the capability must be persistent so that the VM know whether or not to perform recovery. Return Errors: EINVAL

Invalid device for this operation.

ENOTSUP

Functionality that is attempted to be set is not supported.

DKIOCSETVOLCAP

This ioctl sets the available capabilities for the device. If a capability flag is not set in vc_set, that capability is cleared. vc_info flags are ignored vc_set valid flags are:

DKV_ABR_CAP - Flag to set application-based recovery. A device can
 successfully support ABR only if it is capable.
DKV_DMR_CAP - Flag to set directed read.


int
ioctl(int , DKIODMR, vol_directed_rd *);
DKIODMR

This ioctl allows highly available applications to perform round-robin reads from the underlying devices of a replicated device.

vdr_offset - offset at which the read should occur.
vdr_nbytes - number of bytes to be read
vdr_bytesread - number of bytes successfully read by the kernel.
vdr_data - pointer to a user allocated buffer to return the
 data read
vdr_side - side to be read. Initialized to DKV_SIDE_INIT
vdr_side_name - The volume name that has been read.

Valid vdr_flags are:
 DKV_DMR_NEXT_SIDE (set by user)
 DKV_DMR_DONE (return value)
 DKV_DMR_ERROR (return value)
 DKV_DMR_SUCCESS(return value)
 DKV_DMR_SHORT(return value)
The calling sequence is as follows: The caller sets the vdr_flags to DK_DMR_NEXT_SIDE and vdr_side to DKV_SIDE_INIT at the start. Subsequent calls should be made without any changes to these values. If they are changed the results of the ioctl are indeterminate. When DKV_SIDE_INIT is set, the call results in the kernel reading from the first side. The kernel updates vdr_side to indicate the side that was read, and vdr_side_name to contain the name of that side. vdr_data contains the data that was read. Therefore to perform a round-robin read all of the valid sides, there is no need for the caller to change the contents of vdr_side. Subsequent ioctl calls result in reads from the next valid side until all valid sides have been read. On success, the kernel sets DKV_DMR_SUCCESS. The following table shows the values of vdr_flags that are returned when an error occurs:
vdr_flags | vdr_side | Notes
-------------|-------------------|----------------------------
DKV_DMR_ERROR| DKV_SIDE_INIT | No valid side to read
DKV_DMR_DONE | Not Init side | All valid sides read
DKV_DMR_SHORT| Any value | Bytes requested cannot
 be read. vdr_bytesread
 set to bytes actually
 read.
Typical code fragment:

enable->vc_set |= DKV_ABR_SET;
retval = ioctl(filedes, DKIOSETVOLCAP, enable);
if (retval != EINVAL || retval != ENOTSUP) {
 if (info->vc_set & DKV_DMR_SET) {
 dr->vdr_flags |= DKV_DMR_NEXT_SIDE;
 dr->vdr_side = DKV_SIDE_INIT;
 dr->vdr_nbytes = 1024;
 dr->vdr_offset = 0xff00;
 do {
 rval =ioctl(fildes, DKIODMR, dr);
 if (rval != EINVAL) {
 /* Process data */
 }
 } while (rval != EINVAL || dr->vdr_flags &
 (DKV_DMR_DONE | DKV_DMR_ERROR | DKV_DMR_SHORT)
 }
}
"RETURN VALUES"

Upon successful completion, the value returned is 0. Otherwise, -1 is returned and errno is set to indicate the error.

"x86 Only"

The following ioctl() requests set and/or retrieve the current disk controller, partitions, or geometry information on the x86 architecture. DKIOCG_PHYGEOM

The argument is a pointer to a dk_geom structure (described below). This ioctl() gets the driver's notion of the physical geometry of the disk drive. It is functionally identical to the DKIOCGGEOM ioctl().

DKIOCG_VIRTGEOM

The argument is a pointer to a dk_geom structure (described below). This ioctl() gets the controller's (and hence the driver's) notion of the virtual geometry of the disk drive. Virtual geometry is a view of the disk geometry maintained by the firmware in a host bus adapter or disk controller. If the disk is larger than 8 Gbytes, this ioctl fails because a CHS-based geometry is not relevant or useful for this drive.

/*
* Definition of a disk's geometry
*/
*/struct dk_geom {
unsigned shor dkg_ncyl; /* # of data cylinders */
unsigned shor dkg_acyl; /* # of alternate cylinders */
unsigned short dkg_bcyl; /* cyl offset (for fixed head */
 /* area) */
unsigned short dkg_nhead; /* # of heads */
unsigned short dkg_obs1; /* obsolete */
unsigned short dkg_nsect; /* # of sectors per track*/
unsigned short dkg_intrlv; /* interleave factor */
unsigned short dkg_obs2; /* obsolete */
unsigned short dkg_obs3; /* obsolete */
unsigned short dkg_apc; /* alternates per cylinder */
 /* (SCSI only) */
unsigned short dkg_rpm; /* revolutions per min*/
unsigned short dkg_pcyl; /* # of physical cylinders */
unsigned short dkg_write_reinstruct; /* # sectors to skip, writes*/
unsigned short dkg_read_reinstruct; /* # sectors to skip, reads*/
unsigned short dkg_extra[7]; /* for compatible expansion*/
};
DKIOCADDBAD

This ioctl() forces the driver to re-examine the alternates slice and rebuild the internal bad block map accordingly. It should be used whenever the alternates slice is changed by any method other than the addbadsec(1M) or format(1M) utilities. DKIOCADDBAD can only be used for software remapping on IDE drives; SCSI drives use hardware remapping of alternate sectors.

DKIOCPARTINFO

The argument is a pointer to a part_info structure (described below). This ioctl() gets the driver's notion of the size and extent of the partition or slice indicated by the file descriptor argument.

/*
 * Used by applications to get partition or slice information
 */
struct part_info {
daddr_t p_start;
int p_length;
 };
DKIOCEXTPARTINFO

The argument is a pointer to an extpart_info structure (described below). This ioctl gets the driver's notion of the size and extent of the partition or slice indicated by the file descriptor argument. On disks larger than 1TB, this ioctl must be used instead of DKIOCPARTINFO.

/*
* Used by applications to get partition or slice information
*/
struct extpart_info {
diskkaddr_t p_start;
diskaddr_t p_length;
};
DKIOCSETEXTPART

This ioctl is used to update the in-memory copy of the logical drive information maintained by the driver. The ioctl takes no arguments. It causes a re-read of the partition information and recreation of minor nodes if required. Prior to updating the data structures, the ioctl ensures that the partitions do not overlap. Device nodes are created only for valid partition entries. If there is any change in the partition offset, size or ID from the previous read, the partition is deemed to have been changed and hence the device nodes are recreated. Any modification to any of the logical partitions results in the recreation of all logical device nodes.

SEE ALSO

addbadsec(1M), fdisk(1M), format(1M), ioctl(2), cdio(7I), cmdk(7D), fdio(7I), hdio(7I), sd(7D)

NOTES

Blocksize information provided in DKIOCGMEDIAINFO is the size (in bytes) of the device's basic unit of operation and can differ from the blocksize that the Solaris operating environment exports to the user. Capacity information provided in the DKIOCGMEDIAINFO are for reference only and you are advised to use the values returned by DKIOCGGEOM or other appropriate ioctl for accessing data using the standard interfaces.

For x86 only: If the DKIOCSMBOOT command is used to modify the Solaris partitions, the VTOC information should also be set appropriately to reflect the changes to partition. Failure to do so leads to unexpected results when the device is closed and reopened fresh at a later time. This is because a default VTOC is assumed by driver when a Solaris partition is changed. The default VTOC persists until the ioctl DKIOCSVTOC is called to modify VTOC or the device is closed and reopened. At that point, the old valid VTOC is read from the disk if it is still available.