2019-05-27 14:55:01 +08:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0-or-later */
|
2007-04-27 06:55:03 +08:00
|
|
|
/* AFS Volume Location Service client interface
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
2007-04-27 06:55:03 +08:00
|
|
|
* Copyright (C) 2002, 2007 Red Hat, Inc. All Rights Reserved.
|
2005-04-17 06:20:36 +08:00
|
|
|
* Written by David Howells (dhowells@redhat.com)
|
|
|
|
*/
|
|
|
|
|
2007-04-27 06:55:03 +08:00
|
|
|
#ifndef AFS_VL_H
|
|
|
|
#define AFS_VL_H
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-04-27 06:55:03 +08:00
|
|
|
#include "afs.h"
|
|
|
|
|
|
|
|
#define AFS_VL_PORT 7003 /* volume location service port */
|
|
|
|
#define VL_SERVICE 52 /* RxRPC service ID for the Volume Location service */
|
2017-11-02 23:27:51 +08:00
|
|
|
#define YFS_VL_SERVICE 2503 /* Service ID for AuriStor upgraded VL service */
|
2007-04-27 06:55:03 +08:00
|
|
|
|
|
|
|
enum AFSVL_Operations {
|
2017-11-02 23:27:46 +08:00
|
|
|
VLGETENTRYBYID = 503, /* AFS Get VLDB entry by ID */
|
|
|
|
VLGETENTRYBYNAME = 504, /* AFS Get VLDB entry by name */
|
|
|
|
VLPROBE = 514, /* AFS probe VL service */
|
|
|
|
VLGETENTRYBYIDU = 526, /* AFS Get VLDB entry by ID (UUID-variant) */
|
|
|
|
VLGETENTRYBYNAMEU = 527, /* AFS Get VLDB entry by name (UUID-variant) */
|
|
|
|
VLGETADDRSU = 533, /* AFS Get addrs for fileserver */
|
2017-11-02 23:27:51 +08:00
|
|
|
YVLGETENDPOINTS = 64002, /* YFS Get endpoints for file/volume server */
|
|
|
|
VLGETCAPABILITIES = 65537, /* AFS Get server capabilities */
|
2007-04-27 06:55:03 +08:00
|
|
|
};
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
enum AFSVL_Errors {
|
|
|
|
AFSVL_IDEXIST = 363520, /* Volume Id entry exists in vl database */
|
|
|
|
AFSVL_IO = 363521, /* I/O related error */
|
|
|
|
AFSVL_NAMEEXIST = 363522, /* Volume name entry exists in vl database */
|
|
|
|
AFSVL_CREATEFAIL = 363523, /* Internal creation failure */
|
|
|
|
AFSVL_NOENT = 363524, /* No such entry */
|
|
|
|
AFSVL_EMPTY = 363525, /* Vl database is empty */
|
|
|
|
AFSVL_ENTDELETED = 363526, /* Entry is deleted (soft delete) */
|
|
|
|
AFSVL_BADNAME = 363527, /* Volume name is illegal */
|
|
|
|
AFSVL_BADINDEX = 363528, /* Index is out of range */
|
|
|
|
AFSVL_BADVOLTYPE = 363529, /* Bad volume type */
|
|
|
|
AFSVL_BADSERVER = 363530, /* Illegal server number (out of range) */
|
|
|
|
AFSVL_BADPARTITION = 363531, /* Bad partition number */
|
|
|
|
AFSVL_REPSFULL = 363532, /* Run out of space for Replication sites */
|
|
|
|
AFSVL_NOREPSERVER = 363533, /* No such Replication server site exists */
|
|
|
|
AFSVL_DUPREPSERVER = 363534, /* Replication site already exists */
|
|
|
|
AFSVL_RWNOTFOUND = 363535, /* Parent R/W entry not found */
|
|
|
|
AFSVL_BADREFCOUNT = 363536, /* Illegal Reference Count number */
|
|
|
|
AFSVL_SIZEEXCEEDED = 363537, /* Vl size for attributes exceeded */
|
|
|
|
AFSVL_BADENTRY = 363538, /* Bad incoming vl entry */
|
|
|
|
AFSVL_BADVOLIDBUMP = 363539, /* Illegal max volid increment */
|
|
|
|
AFSVL_IDALREADYHASHED = 363540, /* RO/BACK id already hashed */
|
|
|
|
AFSVL_ENTRYLOCKED = 363541, /* Vl entry is already locked */
|
|
|
|
AFSVL_BADVOLOPER = 363542, /* Bad volume operation code */
|
|
|
|
AFSVL_BADRELLOCKTYPE = 363543, /* Bad release lock type */
|
|
|
|
AFSVL_RERELEASE = 363544, /* Status report: last release was aborted */
|
2011-07-18 20:50:00 +08:00
|
|
|
AFSVL_BADSERVERFLAG = 363545, /* Invalid replication site server flag */
|
2005-04-17 06:20:36 +08:00
|
|
|
AFSVL_PERM = 363546, /* No permission access */
|
|
|
|
AFSVL_NOMEM = 363547, /* malloc/realloc failed to alloc enough memory */
|
|
|
|
};
|
|
|
|
|
2017-11-02 23:27:51 +08:00
|
|
|
enum {
|
|
|
|
YFS_SERVER_INDEX = 0,
|
|
|
|
YFS_SERVER_UUID = 1,
|
|
|
|
YFS_SERVER_ENDPOINT = 2,
|
|
|
|
};
|
|
|
|
|
|
|
|
enum {
|
|
|
|
YFS_ENDPOINT_IPV4 = 0,
|
|
|
|
YFS_ENDPOINT_IPV6 = 1,
|
|
|
|
};
|
|
|
|
|
|
|
|
#define YFS_MAXENDPOINTS 16
|
|
|
|
|
2007-04-27 06:55:03 +08:00
|
|
|
/*
|
|
|
|
* maps to "struct vldbentry" in vvl-spec.pdf
|
|
|
|
*/
|
2005-04-17 06:20:36 +08:00
|
|
|
struct afs_vldbentry {
|
2007-04-27 06:55:03 +08:00
|
|
|
char name[65]; /* name of volume (with NUL char) */
|
2005-04-17 06:20:36 +08:00
|
|
|
afs_voltype_t type; /* volume type */
|
|
|
|
unsigned num_servers; /* num servers that hold instances of this vol */
|
|
|
|
unsigned clone_id; /* cloning ID */
|
|
|
|
|
|
|
|
unsigned flags;
|
|
|
|
#define AFS_VLF_RWEXISTS 0x1000 /* R/W volume exists */
|
|
|
|
#define AFS_VLF_ROEXISTS 0x2000 /* R/O volume exists */
|
|
|
|
#define AFS_VLF_BACKEXISTS 0x4000 /* backup volume exists */
|
|
|
|
|
|
|
|
afs_volid_t volume_ids[3]; /* volume IDs */
|
|
|
|
|
|
|
|
struct {
|
|
|
|
struct in_addr addr; /* server address */
|
|
|
|
unsigned partition; /* partition ID on this server */
|
|
|
|
unsigned flags; /* server specific flags */
|
2017-11-02 23:27:46 +08:00
|
|
|
#define AFS_VLSF_NEWREPSITE 0x0001 /* Ignore all 'non-new' servers */
|
2005-04-17 06:20:36 +08:00
|
|
|
#define AFS_VLSF_ROVOL 0x0002 /* this server holds a R/O instance of the volume */
|
|
|
|
#define AFS_VLSF_RWVOL 0x0004 /* this server holds a R/W instance of the volume */
|
|
|
|
#define AFS_VLSF_BACKVOL 0x0008 /* this server holds a backup instance of the volume */
|
2017-11-02 23:27:46 +08:00
|
|
|
#define AFS_VLSF_UUID 0x0010 /* This server is referred to by its UUID */
|
|
|
|
#define AFS_VLSF_DONTUSE 0x0020 /* This server ref should be ignored */
|
2005-04-17 06:20:36 +08:00
|
|
|
} servers[8];
|
|
|
|
};
|
|
|
|
|
2017-11-02 23:27:46 +08:00
|
|
|
#define AFS_VLDB_MAXNAMELEN 65
|
|
|
|
|
afs: Overhaul volume and server record caching and fileserver rotation
The current code assumes that volumes and servers are per-cell and are
never shared, but this is not enforced, and, indeed, public cells do exist
that are aliases of each other. Further, an organisation can, say, set up
a public cell and a private cell with overlapping, but not identical, sets
of servers. The difference is purely in the database attached to the VL
servers.
The current code will malfunction if it sees a server in two cells as it
assumes global address -> server record mappings and that each server is in
just one cell.
Further, each server may have multiple addresses - and may have addresses
of different families (IPv4 and IPv6, say).
To this end, the following structural changes are made:
(1) Server record management is overhauled:
(a) Server records are made independent of cell. The namespace keeps
track of them, volume records have lists of them and each vnode
has a server on which its callback interest currently resides.
(b) The cell record no longer keeps a list of servers known to be in
that cell.
(c) The server records are now kept in a flat list because there's no
single address to sort on.
(d) Server records are now keyed by their UUID within the namespace.
(e) The addresses for a server are obtained with the VL.GetAddrsU
rather than with VL.GetEntryByName, using the server's UUID as a
parameter.
(f) Cached server records are garbage collected after a period of
non-use and are counted out of existence before purging is allowed
to complete. This protects the work functions against rmmod.
(g) The servers list is now in /proc/fs/afs/servers.
(2) Volume record management is overhauled:
(a) An RCU-replaceable server list is introduced. This tracks both
servers and their coresponding callback interests.
(b) The superblock is now keyed on cell record and numeric volume ID.
(c) The volume record is now tied to the superblock which mounts it,
and is activated when mounted and deactivated when unmounted.
This makes it easier to handle the cache cookie without causing a
double-use in fscache.
(d) The volume record is loaded from the VLDB using VL.GetEntryByNameU
to get the server UUID list.
(e) The volume name is updated if it is seen to have changed when the
volume is updated (the update is keyed on the volume ID).
(3) The vlocation record is got rid of and VLDB records are no longer
cached. Sufficient information is stored in the volume record, though
an update to a volume record is now no longer shared between related
volumes (volumes come in bundles of three: R/W, R/O and backup).
and the following procedural changes are made:
(1) The fileserver cursor introduced previously is now fleshed out and
used to iterate over fileservers and their addresses.
(2) Volume status is checked during iteration, and the server list is
replaced if a change is detected.
(3) Server status is checked during iteration, and the address list is
replaced if a change is detected.
(4) The abort code is saved into the address list cursor and -ECONNABORTED
returned in afs_make_call() if a remote abort happened rather than
translating the abort into an error message. This allows actions to
be taken depending on the abort code more easily.
(a) If a VMOVED abort is seen then this is handled by rechecking the
volume and restarting the iteration.
(b) If a VBUSY, VRESTARTING or VSALVAGING abort is seen then this is
handled by sleeping for a short period and retrying and/or trying
other servers that might serve that volume. A message is also
displayed once until the condition has cleared.
(c) If a VOFFLINE abort is seen, then this is handled as VBUSY for the
moment.
(d) If a VNOVOL abort is seen, the volume is rechecked in the VLDB to
see if it has been deleted; if not, the fileserver is probably
indicating that the volume couldn't be attached and needs
salvaging.
(e) If statfs() sees one of these aborts, it does not sleep, but
rather returns an error, so as not to block the umount program.
(5) The fileserver iteration functions in vnode.c are now merged into
their callers and more heavily macroised around the cursor. vnode.c
is removed.
(6) Operations on a particular vnode are serialised on that vnode because
the server will lock that vnode whilst it operates on it, so a second
op sent will just have to wait.
(7) Fileservers are probed with FS.GetCapabilities before being used.
This is where service upgrade will be done.
(8) A callback interest on a fileserver is set up before an FS operation
is performed and passed through to afs_make_call() so that it can be
set on the vnode if the operation returns a callback. The callback
interest is passed through to afs_iget() also so that it can be set
there too.
In general, record updating is done on an as-needed basis when we try to
access servers, volumes or vnodes rather than offloading it to work items
and special threads.
Notes:
(1) Pre AFS-3.4 servers are no longer supported, though this can be added
back if necessary (AFS-3.4 was released in 1998).
(2) VBUSY is retried forever for the moment at intervals of 1s.
(3) /proc/fs/afs/<cell>/servers no longer exists.
Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 23:27:50 +08:00
|
|
|
|
|
|
|
struct afs_ListAddrByAttributes__xdr {
|
|
|
|
__be32 Mask;
|
|
|
|
#define AFS_VLADDR_IPADDR 0x1 /* Match by ->ipaddr */
|
|
|
|
#define AFS_VLADDR_INDEX 0x2 /* Match by ->index */
|
|
|
|
#define AFS_VLADDR_UUID 0x4 /* Match by ->uuid */
|
|
|
|
__be32 ipaddr;
|
|
|
|
__be32 index;
|
|
|
|
__be32 spare;
|
|
|
|
struct afs_uuid__xdr uuid;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct afs_uvldbentry__xdr {
|
|
|
|
__be32 name[AFS_VLDB_MAXNAMELEN];
|
|
|
|
__be32 nServers;
|
|
|
|
struct afs_uuid__xdr serverNumber[AFS_NMAXNSERVERS];
|
|
|
|
__be32 serverUnique[AFS_NMAXNSERVERS];
|
|
|
|
__be32 serverPartition[AFS_NMAXNSERVERS];
|
|
|
|
__be32 serverFlags[AFS_NMAXNSERVERS];
|
|
|
|
__be32 volumeId[AFS_MAXTYPES];
|
|
|
|
__be32 cloneId;
|
|
|
|
__be32 flags;
|
|
|
|
__be32 spares1;
|
|
|
|
__be32 spares2;
|
|
|
|
__be32 spares3;
|
|
|
|
__be32 spares4;
|
|
|
|
__be32 spares5;
|
|
|
|
__be32 spares6;
|
|
|
|
__be32 spares7;
|
|
|
|
__be32 spares8;
|
|
|
|
__be32 spares9;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct afs_address_list {
|
|
|
|
refcount_t usage;
|
|
|
|
unsigned int version;
|
|
|
|
unsigned int nr_addrs;
|
|
|
|
struct sockaddr_rxrpc addrs[];
|
|
|
|
};
|
|
|
|
|
|
|
|
extern void afs_put_address_list(struct afs_address_list *alist);
|
|
|
|
|
2007-04-27 06:55:03 +08:00
|
|
|
#endif /* AFS_VL_H */
|