1
linux/fs/afs/afs.h

207 lines
6.8 KiB
C
Raw Permalink Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/* AFS common types
*
* Copyright (C) 2002, 2007 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*/
#ifndef AFS_H
#define AFS_H
#include <linux/in.h>
#define AFS_MAXCELLNAME 256 /* Maximum length of a cell name */
#define AFS_MAXVOLNAME 64 /* Maximum length of a volume name */
#define AFS_MAXNSERVERS 8 /* Maximum servers in a basic volume record */
#define AFS_NMAXNSERVERS 13 /* Maximum servers in a N/U-class volume record */
#define AFS_MAXTYPES 3 /* Maximum number of volume types */
#define AFSNAMEMAX 256 /* Maximum length of a filename plus NUL */
#define AFSPATHMAX 1024 /* Maximum length of a pathname plus NUL */
#define AFSOPAQUEMAX 1024 /* Maximum length of an opaque field */
rxrpc: Fix timeout of a call that hasn't yet been granted a channel afs_make_call() calls rxrpc_kernel_begin_call() to begin a call (which may get stalled in the background waiting for a connection to become available); it then calls rxrpc_kernel_set_max_life() to set the timeouts - but that starts the call timer so the call timer might then expire before we get a connection assigned - leading to the following oops if the call stalled: BUG: kernel NULL pointer dereference, address: 0000000000000000 ... CPU: 1 PID: 5111 Comm: krxrpcio/0 Not tainted 6.3.0-rc7-build3+ #701 RIP: 0010:rxrpc_alloc_txbuf+0xc0/0x157 ... Call Trace: <TASK> rxrpc_send_ACK+0x50/0x13b rxrpc_input_call_event+0x16a/0x67d rxrpc_io_thread+0x1b6/0x45f ? _raw_spin_unlock_irqrestore+0x1f/0x35 ? rxrpc_input_packet+0x519/0x519 kthread+0xe7/0xef ? kthread_complete_and_exit+0x1b/0x1b ret_from_fork+0x22/0x30 Fix this by noting the timeouts in struct rxrpc_call when the call is created. The timer will be started when the first packet is transmitted. It shouldn't be possible to trigger this directly from userspace through AF_RXRPC as sendmsg() will return EBUSY if the call is in the waiting-for-conn state if it dropped out of the wait due to a signal. Fixes: 9d35d880e0e4 ("rxrpc: Move client call connection to the I/O thread") Reported-by: Marc Dionne <marc.dionne@auristor.com> Signed-off-by: David Howells <dhowells@redhat.com> cc: "David S. Miller" <davem@davemloft.net> cc: Eric Dumazet <edumazet@google.com> cc: Jakub Kicinski <kuba@kernel.org> cc: Paolo Abeni <pabeni@redhat.com> cc: linux-afs@lists.infradead.org cc: netdev@vger.kernel.org cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2023-04-28 13:27:56 -07:00
#define AFS_VL_MAX_LIFESPAN 120
#define AFS_PROBE_MAX_LIFESPAN 30
typedef u64 afs_volid_t;
typedef u64 afs_vnodeid_t;
typedef u64 afs_dataversion_t;
typedef enum {
AFSVL_RWVOL, /* read/write volume */
AFSVL_ROVOL, /* read-only volume */
AFSVL_BACKVOL, /* backup volume */
} __attribute__((packed)) afs_voltype_t;
typedef enum {
AFS_FTYPE_INVALID = 0,
AFS_FTYPE_FILE = 1,
AFS_FTYPE_DIR = 2,
AFS_FTYPE_SYMLINK = 3,
} afs_file_type_t;
typedef enum {
AFS_LOCK_READ = 0, /* read lock request */
AFS_LOCK_WRITE = 1, /* write lock request */
} afs_lock_type_t;
#define AFS_LOCKWAIT (5 * 60) /* time until a lock times out (seconds) */
/*
* AFS file identifier
*/
struct afs_fid {
afs_volid_t vid; /* volume ID */
afs_vnodeid_t vnode; /* Lower 64-bits of file index within volume */
u32 vnode_hi; /* Upper 32-bits of file index */
u32 unique; /* unique ID number (file index version) */
};
/*
* AFS callback notification
*/
typedef enum {
AFSCM_CB_UNTYPED = 0, /* no type set on CB break */
AFSCM_CB_EXCLUSIVE = 1, /* CB exclusive to CM [not implemented] */
AFSCM_CB_SHARED = 2, /* CB shared by other CM's */
AFSCM_CB_DROPPED = 3, /* CB promise cancelled by file server */
} afs_callback_type_t;
struct afs_callback {
time64_t expires_at; /* Time at which expires */
//unsigned version; /* Callback version */
//afs_callback_type_t type; /* Type of callback */
};
struct afs_callback_break {
struct afs_fid fid; /* File identifier */
//struct afs_callback cb; /* Callback details */
};
#define AFSCBMAX 50 /* maximum callbacks transferred per bulk op */
afs: Lay the groundwork for supporting network namespaces Lay the groundwork for supporting network namespaces (netns) to the AFS filesystem by moving various global features to a network-namespace struct (afs_net) and providing an instance of this as a temporary global variable that everything uses via accessor functions for the moment. The following changes have been made: (1) Store the netns in the superblock info. This will be obtained from the mounter's nsproxy on a manual mount and inherited from the parent superblock on an automount. (2) The cell list is made per-netns. It can be viewed through /proc/net/afs/cells and also be modified by writing commands to that file. (3) The local workstation cell is set per-ns in /proc/net/afs/rootcell. This is unset by default. (4) The 'rootcell' module parameter, which sets a cell and VL server list modifies the init net namespace, thereby allowing an AFS root fs to be theoretically used. (5) The volume location lists and the file lock manager are made per-netns. (6) The AF_RXRPC socket and associated I/O bits are made per-ns. The various workqueues remain global for the moment. Changes still to be made: (1) /proc/fs/afs/ should be moved to /proc/net/afs/ and a symlink emplaced from the old name. (2) A per-netns subsys needs to be registered for AFS into which it can store its per-netns data. (3) Rather than the AF_RXRPC socket being opened on module init, it needs to be opened on the creation of a superblock in that netns. (4) The socket needs to be closed when the last superblock using it is destroyed and all outstanding client calls on it have been completed. This prevents a reference loop on the namespace. (5) It is possible that several namespaces will want to use AFS, in which case each one will need its own UDP port. These can either be set through /proc/net/afs/cm_port or the kernel can pick one at random. The init_ns gets 7001 by default. Other issues that need resolving: (1) The DNS keyring needs net-namespacing. (2) Where do upcalls go (eg. DNS request-key upcall)? (3) Need something like open_socket_in_file_ns() syscall so that AFS command line tools attempting to operate on an AFS file/volume have their RPC calls go to the right place. Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 08:27:45 -07:00
struct afs_uuid {
__be32 time_low; /* low part of timestamp */
__be16 time_mid; /* mid part of timestamp */
__be16 time_hi_and_version; /* high part of timestamp and version */
__s8 clock_seq_hi_and_reserved; /* clock seq hi and variant */
__s8 clock_seq_low; /* clock seq low */
__s8 node[6]; /* spatially unique node ID (MAC addr) */
afs: Lay the groundwork for supporting network namespaces Lay the groundwork for supporting network namespaces (netns) to the AFS filesystem by moving various global features to a network-namespace struct (afs_net) and providing an instance of this as a temporary global variable that everything uses via accessor functions for the moment. The following changes have been made: (1) Store the netns in the superblock info. This will be obtained from the mounter's nsproxy on a manual mount and inherited from the parent superblock on an automount. (2) The cell list is made per-netns. It can be viewed through /proc/net/afs/cells and also be modified by writing commands to that file. (3) The local workstation cell is set per-ns in /proc/net/afs/rootcell. This is unset by default. (4) The 'rootcell' module parameter, which sets a cell and VL server list modifies the init net namespace, thereby allowing an AFS root fs to be theoretically used. (5) The volume location lists and the file lock manager are made per-netns. (6) The AF_RXRPC socket and associated I/O bits are made per-ns. The various workqueues remain global for the moment. Changes still to be made: (1) /proc/fs/afs/ should be moved to /proc/net/afs/ and a symlink emplaced from the old name. (2) A per-netns subsys needs to be registered for AFS into which it can store its per-netns data. (3) Rather than the AF_RXRPC socket being opened on module init, it needs to be opened on the creation of a superblock in that netns. (4) The socket needs to be closed when the last superblock using it is destroyed and all outstanding client calls on it have been completed. This prevents a reference loop on the namespace. (5) It is possible that several namespaces will want to use AFS, in which case each one will need its own UDP port. These can either be set through /proc/net/afs/cm_port or the kernel can pick one at random. The init_ns gets 7001 by default. Other issues that need resolving: (1) The DNS keyring needs net-namespacing. (2) Where do upcalls go (eg. DNS request-key upcall)? (3) Need something like open_socket_in_file_ns() syscall so that AFS command line tools attempting to operate on an AFS file/volume have their RPC calls go to the right place. Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 08:27:45 -07:00
};
/*
* AFS volume information
*/
struct afs_volume_info {
afs_volid_t vid; /* volume ID */
afs_voltype_t type; /* type of this volume */
afs_volid_t type_vids[5]; /* volume ID's for possible types for this vol */
/* list of fileservers serving this volume */
size_t nservers; /* number of entries used in servers[] */
struct {
struct in_addr addr; /* fileserver address */
} servers[8];
};
/*
* AFS security ACE access mask
*/
typedef u32 afs_access_t;
#define AFS_ACE_READ 0x00000001U /* - permission to read a file/dir */
#define AFS_ACE_WRITE 0x00000002U /* - permission to write/chmod a file */
#define AFS_ACE_INSERT 0x00000004U /* - permission to create dirent in a dir */
#define AFS_ACE_LOOKUP 0x00000008U /* - permission to lookup a file/dir in a dir */
#define AFS_ACE_DELETE 0x00000010U /* - permission to delete a dirent from a dir */
#define AFS_ACE_LOCK 0x00000020U /* - permission to lock a file */
#define AFS_ACE_ADMINISTER 0x00000040U /* - permission to change ACL */
#define AFS_ACE_USER_A 0x01000000U /* - 'A' user-defined permission */
#define AFS_ACE_USER_B 0x02000000U /* - 'B' user-defined permission */
#define AFS_ACE_USER_C 0x04000000U /* - 'C' user-defined permission */
#define AFS_ACE_USER_D 0x08000000U /* - 'D' user-defined permission */
#define AFS_ACE_USER_E 0x10000000U /* - 'E' user-defined permission */
#define AFS_ACE_USER_F 0x20000000U /* - 'F' user-defined permission */
#define AFS_ACE_USER_G 0x40000000U /* - 'G' user-defined permission */
#define AFS_ACE_USER_H 0x80000000U /* - 'H' user-defined permission */
/*
* AFS file status information
*/
struct afs_file_status {
u64 size; /* file size */
afs_dataversion_t data_version; /* current data version */
struct timespec64 mtime_client; /* Last time client changed data */
struct timespec64 mtime_server; /* Last time server changed data */
s64 author; /* author ID */
s64 owner; /* owner ID */
s64 group; /* group ID */
afs_access_t caller_access; /* access rights for authenticated caller */
afs_access_t anon_access; /* access rights for unauthenticated caller */
umode_t mode; /* UNIX mode */
afs_file_type_t type; /* file type */
u32 nlink; /* link count */
s32 lock_count; /* file lock count (0=UNLK -1=WRLCK +ve=#RDLCK */
u32 abort_code; /* Abort if bulk-fetching this failed */
};
struct afs_status_cb {
struct afs_file_status status;
struct afs_callback callback;
bool have_status; /* True if status record was retrieved */
bool have_cb; /* True if cb record was retrieved */
bool have_error; /* True if status.abort_code indicates an error */
};
/*
* AFS file status change request
*/
#define AFS_SET_MTIME 0x01 /* set the mtime */
#define AFS_SET_OWNER 0x02 /* set the owner ID */
#define AFS_SET_GROUP 0x04 /* set the group ID (unsupported?) */
#define AFS_SET_MODE 0x08 /* set the UNIX mode */
#define AFS_SET_SEG_SIZE 0x10 /* set the segment size (unsupported) */
/*
* AFS volume synchronisation information
*/
struct afs_volsync {
afs: Parse the VolSync record in the reply of a number of RPC ops A number of fileserver RPC operations return a VolSync record as part of their reply that gives some information about the state of the volume being accessed, including: (1) A volume Creation timestamp. For an RW volume, this is the time at which the volume was created; if it changes, the RW volume was presumably restored from a backup and all cached data should be scrubbed as Data Version numbers could regress on the files in the volume. For an RO volume, this is the time it was last snapshotted from the RW volume. It is expected to advance each time this happens; if it regresses, cached data should be scrubbed. (2) A volume Update timestamp (Auristor only). For an RW volume, this is updated any time any change is made to a volume or its contents. If it regresses, all cached data must be scrubbed. For an RO volume, this is a copy of the RW volume's Update timestamp at the point of snapshotting. It can be used as a version number when checking to see if a callback on a RO volume was due to a snapshot. If it regresses, all cached data must be scrubbed. but this is currently not made use of by the in-kernel afs filesystem. Make the afs filesystem use this by: (1) Add an update time field to the afs_volsync struct and use a value of TIME64_MIN in both that and the creation time to indicate that they are unset. (2) Add creation and update time fields to the afs_volume struct and use this to track the two timestamps. (3) Add a volsync_lock mutex to the afs_volume struct to control modification access for when we detect a change in these values. (3) Add a 'pre-op volsync' struct to the afs_operation struct to record the state of the volume tracking before the op. (4) Add a new counter, cb_scrub, to the afs_volume struct to count events that require all data to be scrubbed. A copy is placed in the afs_vnode struct (inode) and if they no longer match, a scrub takes place. (5) When the result of an operation is being parsed, parse the VolSync data too, if it is provided. Note that the two timestamps are handled separately, since they don't work in quite the same way. - If the afs_volume tracking is unset, just set it and do nothing else. - If the result timestamps are the same as the ones in afs_volume, do nothing. - If the timestamps regress, increment cb_scrub if not already done so. - If the creation timestamp on a RW volume changes, increment cb_scrub if not already done so. - If the creation timestamp on a RO volume advances, update the server list and see if the current server has been excluded, if so reissue the op. Once over half of the replication sites have been updated, increment cb_ro_snapshot to indicate updates may be required and switch over to excluding unupdated replication sites. - If the creation timestamp on a Backup volume advances, just increment cb_ro_snapshot to trigger updates. Signed-off-by: David Howells <dhowells@redhat.com> cc: Marc Dionne <marc.dionne@auristor.com> cc: linux-afs@lists.infradead.org
2023-11-05 09:11:07 -07:00
time64_t creation; /* Volume creation time (or TIME64_MIN) */
time64_t update; /* Volume update time (or TIME64_MIN) */
};
/*
* AFS volume status record
*/
struct afs_volume_status {
afs_volid_t vid; /* volume ID */
afs_volid_t parent_id; /* parent volume ID */
u8 online; /* true if volume currently online and available */
u8 in_service; /* true if volume currently in service */
u8 blessed; /* same as in_service */
u8 needs_salvage; /* true if consistency checking required */
u32 type; /* volume type (afs_voltype_t) */
u64 min_quota; /* minimum space set aside (blocks) */
u64 max_quota; /* maximum space this volume may occupy (blocks) */
u64 blocks_in_use; /* space this volume currently occupies (blocks) */
u64 part_blocks_avail; /* space available in volume's partition */
u64 part_max_blocks; /* size of volume's partition */
s64 vol_copy_date;
s64 vol_backup_date;
};
#define AFS_BLOCK_SIZE 1024
/*
* XDR encoding of UUID in AFS.
*/
struct afs_uuid__xdr {
__be32 time_low;
__be32 time_mid;
__be32 time_hi_and_version;
__be32 clock_seq_hi_and_reserved;
__be32 clock_seq_low;
__be32 node[6];
};
#endif /* AFS_H */