diff options
Diffstat (limited to 'fs/afs/internal.h')
| -rw-r--r-- | fs/afs/internal.h | 1928 |
1 files changed, 1507 insertions, 421 deletions
diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 82e16556afea..009064b8d661 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -1,18 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* internal AFS stuff * * Copyright (C) 2002, 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/compiler.h> #include <linux/kernel.h> #include <linux/ktime.h> #include <linux/fs.h> +#include <linux/filelock.h> #include <linux/pagemap.h> #include <linux/rxrpc.h> #include <linux/key.h> @@ -21,6 +18,12 @@ #include <linux/fscache.h> #include <linux/backing-dev.h> #include <linux/uuid.h> +#include <linux/mm_types.h> +#include <linux/dns_resolver.h> +#include <crypto/krb5.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> +#include <net/sock.h> #include <net/af_rxrpc.h> #include "afs.h" @@ -30,38 +33,96 @@ struct pagevec; struct afs_call; +struct afs_vnode; +struct afs_server_probe; + +/* + * Partial file-locking emulation mode. (The problem being that AFS3 only + * allows whole-file locks and no upgrading/downgrading). + */ +enum afs_flock_mode { + afs_flock_mode_unset, + afs_flock_mode_local, /* Local locking only */ + afs_flock_mode_openafs, /* Don't get server lock for a partial lock */ + afs_flock_mode_strict, /* Always get a server lock for a partial lock */ + afs_flock_mode_write, /* Get an exclusive server lock for a partial lock */ +}; -typedef enum { - AFS_VL_NEW, /* new, uninitialised record */ - AFS_VL_CREATING, /* creating record */ - AFS_VL_VALID, /* record is pending */ - AFS_VL_NO_VOLUME, /* no such volume available */ - AFS_VL_UPDATING, /* update in progress */ - AFS_VL_VOLUME_DELETED, /* volume was deleted */ - AFS_VL_UNCERTAIN, /* uncertain state (update failed) */ -} __attribute__((packed)) afs_vlocation_state_t; - -struct afs_mount_params { - bool rwpath; /* T if the parent should be considered R/W */ +struct afs_fs_context { bool force; /* T to force cell type */ bool autocell; /* T if set auto mount operation */ + bool dyn_root; /* T if dynamic root */ + bool no_cell; /* T if the source is "none" (for dynroot) */ + enum afs_flock_mode flock_mode; /* Partial file-locking emulation mode */ afs_voltype_t type; /* type of volume requested */ - int volnamesz; /* size of volume name */ + unsigned int volnamesz; /* size of volume name */ const char *volname; /* name of volume to mount */ + struct afs_net *net; /* the AFS net namespace stuff */ struct afs_cell *cell; /* cell in which to find volume */ struct afs_volume *volume; /* volume record */ struct key *key; /* key to use for secure mounting */ }; enum afs_call_state { - AFS_CALL_REQUESTING, /* request is being sent for outgoing call */ - AFS_CALL_AWAIT_REPLY, /* awaiting reply to outgoing call */ - AFS_CALL_AWAIT_OP_ID, /* awaiting op ID on incoming call */ - AFS_CALL_AWAIT_REQUEST, /* awaiting request data on incoming call */ - AFS_CALL_REPLYING, /* replying to incoming call */ - AFS_CALL_AWAIT_ACK, /* awaiting final ACK of incoming call */ - AFS_CALL_COMPLETE, /* Completed or failed */ + AFS_CALL_CL_REQUESTING, /* Client: Request is being sent */ + AFS_CALL_CL_AWAIT_REPLY, /* Client: Awaiting reply */ + AFS_CALL_CL_PROC_REPLY, /* Client: rxrpc call complete; processing reply */ + AFS_CALL_SV_AWAIT_OP_ID, /* Server: Awaiting op ID */ + AFS_CALL_SV_AWAIT_REQUEST, /* Server: Awaiting request data */ + AFS_CALL_SV_REPLYING, /* Server: Replying */ + AFS_CALL_SV_AWAIT_ACK, /* Server: Awaiting final ACK */ + AFS_CALL_COMPLETE, /* Completed or failed */ }; + +/* + * Address preferences. + */ +struct afs_addr_preference { + union { + struct in_addr ipv4_addr; /* AF_INET address to compare against */ + struct in6_addr ipv6_addr; /* AF_INET6 address to compare against */ + }; + sa_family_t family; /* Which address to use */ + u16 prio; /* Priority */ + u8 subnet_mask; /* How many bits to compare */ +}; + +struct afs_addr_preference_list { + struct rcu_head rcu; + u16 version; /* Incremented when prefs list changes */ + u8 ipv6_off; /* Offset of IPv6 addresses */ + u8 nr; /* Number of addresses in total */ + u8 max_prefs; /* Number of prefs allocated */ + struct afs_addr_preference prefs[] __counted_by(max_prefs); +}; + +struct afs_address { + struct rxrpc_peer *peer; + short last_error; /* Last error from this address */ + u16 prio; /* Address priority */ +}; + +/* + * List of server addresses. + */ +struct afs_addr_list { + struct rcu_head rcu; + refcount_t usage; + u32 version; /* Version */ + unsigned int debug_id; + unsigned int addr_pref_version; /* Version of address preference list */ + unsigned char max_addrs; + unsigned char nr_addrs; + unsigned char preferred; /* Preferred address */ + unsigned char nr_ipv4; /* Number of IPv4 addresses */ + enum dns_record_source source:8; + enum dns_lookup_status status:8; + unsigned long probe_failed; /* Mask of addrs that failed locally/ICMP */ + unsigned long responded; /* Mask of addrs that responded */ + struct afs_address addrs[] __counted_by(max_addrs); +#define AFS_MAX_ADDRESSES ((unsigned int)(sizeof(unsigned long) * 8)) +}; + /* * a record of an in-progress RxRPC call */ @@ -70,110 +131,127 @@ struct afs_call { wait_queue_head_t waitq; /* processes awaiting completion */ struct work_struct async_work; /* async I/O processor */ struct work_struct work; /* actual work processor */ + struct work_struct free_work; /* Deferred free processor */ struct rxrpc_call *rxcall; /* RxRPC call handle */ + struct rxrpc_peer *peer; /* Remote endpoint */ struct key *key; /* security for this call */ - struct afs_server *server; /* server affected by incoming CM call */ + struct afs_net *net; /* The network namespace */ + struct afs_server *server; /* The fileserver record if fs op (pins ref) */ + struct afs_vlserver *vlserver; /* The vlserver record if vl op */ void *request; /* request data (first part) */ - struct address_space *mapping; /* page set */ - struct afs_writeback *wb; /* writeback being performed */ + size_t iov_len; /* Size of *iter to be used */ + struct iov_iter def_iter; /* Default buffer/data iterator */ + struct iov_iter *write_iter; /* Iterator defining write to be made */ + struct iov_iter *iter; /* Iterator currently in use */ + union { /* Convenience for ->def_iter */ + struct kvec kvec[1]; + struct bio_vec bvec[1]; + }; void *buffer; /* reply receive buffer */ - void *reply; /* reply buffer (first part) */ - void *reply2; /* reply buffer (second part) */ - void *reply3; /* reply buffer (third part) */ - void *reply4; /* reply buffer (fourth part) */ - pgoff_t first; /* first page in mapping to deal with */ - pgoff_t last; /* last page in mapping to deal with */ - size_t offset; /* offset into received data store */ - atomic_t usage; + union { + struct afs_endpoint_state *probe; + struct afs_addr_list *vl_probe; + struct afs_addr_list *ret_alist; + struct afs_vldb_entry *ret_vldb; + char *ret_str; + }; + struct afs_fid fid; /* Primary vnode ID (or all zeroes) */ + unsigned char probe_index; /* Address in ->probe_alist */ + struct afs_operation *op; + unsigned int server_index; + refcount_t ref; enum afs_call_state state; + spinlock_t state_lock; int error; /* error code */ u32 abort_code; /* Remote abort ID or 0 */ + unsigned long long remaining; /* How much is left to receive */ + unsigned int max_lifespan; /* Maximum lifespan in secs to set if not 0 */ unsigned request_size; /* size of request data */ unsigned reply_max; /* maximum size of reply */ - unsigned first_offset; /* offset into mapping[first] */ - union { - unsigned last_to; /* amount of mapping[last] */ - unsigned count2; /* count used in unmarshalling */ - }; + unsigned count2; /* count used in unmarshalling */ unsigned char unmarshall; /* unmarshalling phase */ - bool incoming; /* T if incoming call */ - bool send_pages; /* T if data from mapping should be sent */ + bool drop_ref; /* T if need to drop ref for incoming call */ bool need_attention; /* T if RxRPC poked us */ bool async; /* T if asynchronous */ - u16 service_id; /* RxRPC service ID to call */ - __be16 port; /* target UDP port */ + bool upgrade; /* T to request service upgrade */ + bool intr; /* T if interruptible */ + bool unmarshalling_error; /* T if an unmarshalling error occurred */ + bool responded; /* Got a response from the call (may be abort) */ + u8 security_ix; /* Security class */ + u16 service_id; /* Actual service ID (after upgrade) */ + unsigned int debug_id; /* Trace ID */ + u32 enctype; /* Security encoding type */ u32 operation_ID; /* operation ID for an incoming call */ u32 count; /* count for use in unmarshalling */ - __be32 tmp; /* place to extract temporary data */ - afs_dataversion_t store_version; /* updated version expected from store */ + union { /* place to extract temporary data */ + struct { + __be32 tmp_u; + __be32 tmp; + } __attribute__((packed)); + __be64 tmp64; + }; + ktime_t issue_time; /* Time of issue of operation */ }; struct afs_call_type { const char *name; + unsigned int op; /* Really enum afs_fs_operation */ /* deliver request or reply data to an call * - returning an error will cause the call to be aborted */ int (*deliver)(struct afs_call *call); - /* map an abort code to an error number */ - int (*abort_to_error)(u32 abort_code); - /* clean up a call */ void (*destructor)(struct afs_call *call); + /* Async receive processing function */ + void (*async_rx)(struct work_struct *work); + /* Work function */ void (*work)(struct work_struct *work); + + /* Call done function (gets called immediately on success or failure) */ + void (*done)(struct afs_call *call); + + /* Handle a call being immediately cancelled. */ + void (*immediate_cancel)(struct afs_call *call); }; /* - * Record of an outstanding read operation on a vnode. + * Key available for writeback on a file. */ -struct afs_read { - loff_t pos; /* Where to start reading */ - loff_t len; /* How much we're asking for */ - loff_t actual_len; /* How much we're actually getting */ - loff_t remain; /* Amount remaining */ - atomic_t usage; - unsigned int index; /* Which page we're reading into */ - unsigned int nr_pages; - void (*page_done)(struct afs_call *, struct afs_read *); - struct page *pages[]; +struct afs_wb_key { + refcount_t usage; + struct key *key; + struct list_head vnode_link; /* Link in vnode->wb_keys */ }; /* - * record of an outstanding writeback on a vnode + * AFS open file information record. Pointed to by file->private_data. */ -struct afs_writeback { - struct list_head link; /* link in vnode->writebacks */ - struct work_struct writer; /* work item to perform the writeback */ - struct afs_vnode *vnode; /* vnode to which this write applies */ - struct key *key; /* owner of this write */ - wait_queue_head_t waitq; /* completion and ready wait queue */ - pgoff_t first; /* first page in batch */ - pgoff_t point; /* last page in current store op */ - pgoff_t last; /* last page in batch (inclusive) */ - unsigned offset_first; /* offset into first page of start of write */ - unsigned to_last; /* offset into last page of end of write */ - int num_conflicts; /* count of conflicting writes in list */ - int usage; - bool conflicts; /* T if has dependent conflicts */ - enum { - AFS_WBACK_SYNCING, /* synchronisation being performed */ - AFS_WBACK_PENDING, /* write pending */ - AFS_WBACK_CONFLICTING, /* conflicting writes posted */ - AFS_WBACK_WRITING, /* writing back */ - AFS_WBACK_COMPLETE /* the writeback record has been unlinked */ - } state __attribute__((packed)); +struct afs_file { + struct key *key; /* The key this file was opened with */ + struct afs_wb_key *wb; /* Writeback key record for this file */ }; +static inline struct key *afs_file_key(struct file *file) +{ + struct afs_file *af = file->private_data; + + return af->key; +} + /* * AFS superblock private data * - there's one superblock per volume */ struct afs_super_info { + struct net *net_ns; /* Network namespace */ + struct afs_cell *cell; /* The cell in which the volume resides */ struct afs_volume *volume; /* volume record */ - char rwparent; /* T if parent is R/W AFS volume */ + enum afs_flock_mode flock_mode:8; /* File locking emulation mode */ + bool dyn_root; /* True if dynamic root */ }; static inline struct afs_super_info *AFS_FS_S(struct super_block *sb) @@ -184,285 +262,816 @@ static inline struct afs_super_info *AFS_FS_S(struct super_block *sb) extern struct file_system_type afs_fs_type; /* - * entry in the cached cell catalogue + * Set of substitutes for @sys. */ -struct afs_cache_cell { - char name[AFS_MAXCELLNAME]; /* cell name (padded with NULs) */ - struct in_addr vl_servers[15]; /* cached cell VL servers */ +struct afs_sysnames { +#define AFS_NR_SYSNAME 16 + char *subs[AFS_NR_SYSNAME]; + refcount_t usage; + unsigned short nr; + char blank[1]; }; /* - * AFS cell record + * AFS network namespace record. + */ +struct afs_net { + struct net *net; /* Backpointer to the owning net namespace */ + struct afs_uuid uuid; + bool live; /* F if this namespace is being removed */ + + /* AF_RXRPC I/O stuff */ + struct socket *socket; + struct afs_call *spare_incoming_call; + struct work_struct charge_preallocation_work; + struct work_struct rx_oob_work; + struct mutex socket_mutex; + atomic_t nr_outstanding_calls; + atomic_t nr_superblocks; + + /* Cell database */ + struct rb_root cells; + struct idr cells_dyn_ino; /* cell->dynroot_ino mapping */ + struct afs_cell __rcu *ws_cell; + atomic_t cells_outstanding; + struct rw_semaphore cells_lock; + struct mutex cells_alias_lock; + + struct mutex proc_cells_lock; + struct hlist_head proc_cells; + + /* Known servers. Theoretically each fileserver can only be in one + * cell, but in practice, people create aliases and subsets and there's + * no easy way to distinguish them. + */ + seqlock_t fs_lock; /* For fs_probe_*, fs_proc */ + struct list_head fs_probe_fast; /* List of afs_server to probe at 30s intervals */ + struct list_head fs_probe_slow; /* List of afs_server to probe at 5m intervals */ + struct hlist_head fs_proc; /* procfs servers list */ + + struct key *fs_cm_token_key; /* Key for creating CM tokens */ + struct work_struct fs_prober; + struct timer_list fs_probe_timer; + atomic_t servers_outstanding; + + /* File locking renewal management */ + struct mutex lock_manager_mutex; + + /* Misc */ + struct super_block *dynroot_sb; /* Dynamic root mount superblock */ + struct proc_dir_entry *proc_afs; /* /proc/net/afs directory */ + struct afs_sysnames *sysnames; + rwlock_t sysnames_lock; + struct afs_addr_preference_list __rcu *address_prefs; + u16 address_pref_version; + + /* Statistics counters */ + atomic_t n_lookup; /* Number of lookups done */ + atomic_t n_reval; /* Number of dentries needing revalidation */ + atomic_t n_inval; /* Number of invalidations by the server */ + atomic_t n_relpg; /* Number of invalidations by release_folio */ + atomic_t n_read_dir; /* Number of directory pages read */ + atomic_t n_dir_cr; /* Number of directory entry creation edits */ + atomic_t n_dir_rm; /* Number of directory entry removal edits */ + atomic_t n_stores; /* Number of store ops */ + atomic_long_t n_store_bytes; /* Number of bytes stored */ + atomic_long_t n_fetch_bytes; /* Number of bytes fetched */ + atomic_t n_fetches; /* Number of data fetch ops */ +}; + +extern const char afs_init_sysname[]; + +enum afs_cell_state { + AFS_CELL_SETTING_UP, + AFS_CELL_UNLOOKED, + AFS_CELL_ACTIVE, + AFS_CELL_REMOVING, + AFS_CELL_DEAD, +}; + +/* + * AFS cell record. + * + * This is a tricky concept to get right as it is possible to create aliases + * simply by pointing AFSDB/SRV records for two names at the same set of VL + * servers; it is also possible to do things like setting up two sets of VL + * servers, one of which provides a superset of the volumes provided by the + * other (for internal/external division, for example). + * + * Cells only exist in the sense that (a) a cell's name maps to a set of VL + * servers and (b) a cell's name is used by the client to select the key to use + * for authentication and encryption. The cell name is not typically used in + * the protocol. + * + * Two cells are determined to be aliases if they have an explicit alias (YFS + * only), share any VL servers in common or have at least one volume in common. + * "In common" means that the address list of the VL servers or the fileservers + * share at least one endpoint. */ struct afs_cell { - atomic_t usage; - struct list_head link; /* main cell list link */ + union { + struct rcu_head rcu; + struct rb_node net_node; /* Node in net->cells */ + }; + struct afs_net *net; + struct afs_cell *alias_of; /* The cell this is an alias of */ + struct afs_volume *root_volume; /* The root.cell volume if there is one */ struct key *anonymous_key; /* anonymous user key for this cell */ - struct list_head proc_link; /* /proc cell list link */ -#ifdef CONFIG_AFS_FSCACHE - struct fscache_cookie *cache; /* caching cookie */ -#endif + struct work_struct destroyer; /* Destroyer for cell */ + struct work_struct manager; /* Manager for init/deinit/dns */ + struct timer_list management_timer; /* General management timer */ + struct hlist_node proc_link; /* /proc cell list link */ + time64_t dns_expiry; /* Time AFSDB/SRV record expires */ + time64_t last_inactive; /* Time of last drop of usage count */ + refcount_t ref; /* Struct refcount */ + atomic_t active; /* Active usage counter */ + unsigned long flags; +#define AFS_CELL_FL_NO_GC 0 /* The cell was added manually, don't auto-gc */ +#define AFS_CELL_FL_DO_LOOKUP 1 /* DNS lookup requested */ +#define AFS_CELL_FL_CHECK_ALIAS 2 /* Need to check for aliases */ + enum afs_cell_state state; + short error; + enum dns_record_source dns_source:8; /* Latest source of data from lookup */ + enum dns_lookup_status dns_status:8; /* Latest status of data from lookup */ + unsigned int dns_lookup_count; /* Counter of DNS lookups */ + unsigned int debug_id; + unsigned int dynroot_ino; /* Inode numbers for dynroot (a pair) */ + + /* The volumes belonging to this cell */ + struct rw_semaphore vs_lock; /* Lock for server->volumes */ + struct rb_root volumes; /* Tree of volumes on this server */ + struct hlist_head proc_volumes; /* procfs volume list */ + seqlock_t volume_lock; /* For volumes */ + + /* Active fileserver interaction state. */ + struct rb_root fs_servers; /* afs_server (by server UUID) */ + struct rw_semaphore fs_lock; /* For fs_servers */ + + /* VL server list. */ + rwlock_t vl_servers_lock; /* Lock on vl_servers */ + struct afs_vlserver_list __rcu *vl_servers; + + u8 name_len; /* Length of name */ + char *name; /* Cell name, case-flattened and NUL-padded */ + char *key_desc; /* Authentication key description */ +}; - /* server record management */ - rwlock_t servers_lock; /* active server list lock */ - struct list_head servers; /* active server list */ +/* + * Volume Location server record. + */ +struct afs_vlserver { + struct rcu_head rcu; + struct afs_addr_list __rcu *addresses; /* List of addresses for this VL server */ + unsigned long flags; +#define AFS_VLSERVER_FL_PROBED 0 /* The VL server has been probed */ +#define AFS_VLSERVER_FL_PROBING 1 /* VL server is being probed */ +#define AFS_VLSERVER_FL_IS_YFS 2 /* Server is YFS not AFS */ +#define AFS_VLSERVER_FL_RESPONDING 3 /* VL server is responding */ + rwlock_t lock; /* Lock on addresses */ + refcount_t ref; + unsigned int rtt; /* Server's current RTT in uS */ + unsigned int debug_id; + + /* Probe state */ + wait_queue_head_t probe_wq; + atomic_t probe_outstanding; + spinlock_t probe_lock; + struct { + unsigned int rtt; /* Best RTT in uS (or UINT_MAX) */ + u32 abort_code; + short error; + unsigned short flags; +#define AFS_VLSERVER_PROBE_RESPONDED 0x01 /* At least once response (may be abort) */ +#define AFS_VLSERVER_PROBE_IS_YFS 0x02 /* The peer appears to be YFS */ +#define AFS_VLSERVER_PROBE_NOT_YFS 0x04 /* The peer appears not to be YFS */ +#define AFS_VLSERVER_PROBE_LOCAL_FAILURE 0x08 /* A local failure prevented a probe */ + } probe; + + u16 service_id; /* Service ID we're using */ + u16 port; + u16 name_len; /* Length of name */ + char name[]; /* Server name, case-flattened */ +}; - /* volume location record management */ - struct rw_semaphore vl_sem; /* volume management serialisation semaphore */ - struct list_head vl_list; /* cell's active VL record list */ - spinlock_t vl_lock; /* vl_list lock */ - unsigned short vl_naddrs; /* number of VL servers in addr list */ - unsigned short vl_curr_svix; /* current server index */ - struct in_addr vl_addrs[AFS_CELL_MAX_ADDRS]; /* cell VL server addresses */ +/* + * Weighted list of Volume Location servers. + */ +struct afs_vlserver_entry { + u16 priority; /* Preference (as SRV) */ + u16 weight; /* Weight (as SRV) */ + enum dns_record_source source:8; + enum dns_lookup_status status:8; + struct afs_vlserver *server; +}; - char name[0]; /* cell name - must go last */ +struct afs_vlserver_list { + struct rcu_head rcu; + refcount_t ref; + u8 nr_servers; + u8 index; /* Server currently in use */ + u8 preferred; /* Preferred server */ + enum dns_record_source source:8; + enum dns_lookup_status status:8; + rwlock_t lock; + struct afs_vlserver_entry servers[]; }; /* - * entry in the cached volume location catalogue + * Cached VLDB entry. + * + * This is pointed to by cell->vldb_entries, indexed by name. */ -struct afs_cache_vlocation { - /* volume name (lowercase, padded with NULs) */ - uint8_t name[AFS_MAXVOLNAME + 1]; +struct afs_vldb_entry { + afs_volid_t vid[3]; /* Volume IDs for R/W, R/O and Bak volumes */ - uint8_t nservers; /* number of entries used in servers[] */ - uint8_t vidmask; /* voltype mask for vid[] */ - uint8_t srvtmask[8]; /* voltype masks for servers[] */ + unsigned long flags; +#define AFS_VLDB_HAS_RW 0 /* - R/W volume exists */ +#define AFS_VLDB_HAS_RO 1 /* - R/O volume exists */ +#define AFS_VLDB_HAS_BAK 2 /* - Backup volume exists */ +#define AFS_VLDB_QUERY_VALID 3 /* - Record is valid */ +#define AFS_VLDB_QUERY_ERROR 4 /* - VL server returned error */ + + uuid_t fs_server[AFS_NMAXNSERVERS]; + u32 addr_version[AFS_NMAXNSERVERS]; /* Registration change counters */ + u8 fs_mask[AFS_NMAXNSERVERS]; #define AFS_VOL_VTM_RW 0x01 /* R/W version of the volume is available (on this server) */ #define AFS_VOL_VTM_RO 0x02 /* R/O version of the volume is available (on this server) */ #define AFS_VOL_VTM_BAK 0x04 /* backup version of the volume is available (on this server) */ - - afs_volid_t vid[3]; /* volume IDs for R/W, R/O and Bak volumes */ - struct in_addr servers[8]; /* fileserver addresses */ - time_t rtime; /* last retrieval time */ + u8 vlsf_flags[AFS_NMAXNSERVERS]; + short error; + u8 nr_servers; /* Number of server records */ + u8 name_len; + u8 name[AFS_MAXVOLNAME + 1]; /* NUL-padded volume name */ }; /* - * volume -> vnode hash table entry + * Fileserver endpoint state. The records the addresses of a fileserver's + * endpoints and the state and result of a round of probing on them. This + * allows the rotation algorithm to access those results without them being + * erased by a subsequent round of probing. */ -struct afs_cache_vhash { - afs_voltype_t vtype; /* which volume variation */ - uint8_t hash_bucket; /* which hash bucket this represents */ -} __attribute__((packed)); - -/* - * AFS volume location record - */ -struct afs_vlocation { - atomic_t usage; - time64_t time_of_death; /* time at which put reduced usage to 0 */ - struct list_head link; /* link in cell volume location list */ - struct list_head grave; /* link in master graveyard list */ - struct list_head update; /* link in master update list */ - struct afs_cell *cell; /* cell to which volume belongs */ -#ifdef CONFIG_AFS_FSCACHE - struct fscache_cookie *cache; /* caching cookie */ -#endif - struct afs_cache_vlocation vldb; /* volume information DB record */ - struct afs_volume *vols[3]; /* volume access record pointer (index by type) */ - wait_queue_head_t waitq; /* status change waitqueue */ - time64_t update_at; /* time at which record should be updated */ - spinlock_t lock; /* access lock */ - afs_vlocation_state_t state; /* volume location state */ - unsigned short upd_rej_cnt; /* ENOMEDIUM count during update */ - unsigned short upd_busy_cnt; /* EBUSY count during update */ - bool valid; /* T if valid */ +struct afs_endpoint_state { + struct rcu_head rcu; + struct afs_addr_list *addresses; /* The addresses being probed */ + unsigned long responsive_set; /* Bitset of responsive endpoints */ + unsigned long failed_set; /* Bitset of endpoints we failed to probe */ + refcount_t ref; + unsigned int server_id; /* Debug ID of server */ + unsigned int probe_seq; /* Probe sequence (from server::probe_counter) */ + atomic_t nr_probing; /* Number of outstanding probes */ + unsigned int rtt; /* Best RTT in uS (or UINT_MAX) */ + s32 abort_code; + short error; + unsigned long flags; +#define AFS_ESTATE_RESPONDED 0 /* Set if the server responded */ +#define AFS_ESTATE_SUPERSEDED 1 /* Set if this record has been superseded */ +#define AFS_ESTATE_IS_YFS 2 /* Set if probe upgraded to YFS */ +#define AFS_ESTATE_NOT_YFS 3 /* Set if probe didn't upgrade to YFS */ +#define AFS_ESTATE_LOCAL_FAILURE 4 /* Set if there was a local failure (eg. ENOMEM) */ }; /* - * AFS fileserver record + * Record of fileserver with which we're actively communicating. */ struct afs_server { - atomic_t usage; - time64_t time_of_death; /* time at which put reduced usage to 0 */ - struct in_addr addr; /* server address */ - struct afs_cell *cell; /* cell in which server resides */ - struct list_head link; /* link in cell's server list */ - struct list_head grave; /* link in master graveyard list */ - struct rb_node master_rb; /* link in master by-addr tree */ - struct rw_semaphore sem; /* access lock */ + struct rcu_head rcu; + union { + uuid_t uuid; /* Server ID */ + struct afs_uuid _uuid; + }; + + struct afs_cell *cell; /* Cell to which belongs (pins ref) */ + struct rb_node uuid_rb; /* Link in cell->fs_servers */ + struct list_head probe_link; /* Link in net->fs_probe_* */ + struct hlist_node proc_link; /* Link in net->fs_proc */ + struct list_head volumes; /* RCU list of afs_server_entry objects */ + struct work_struct destroyer; /* Work item to try and destroy a server */ + struct timer_list timer; /* Management timer */ + struct mutex cm_token_lock; /* Lock governing creation of appdata */ + struct krb5_buffer cm_rxgk_appdata; /* Appdata to be included in RESPONSE packet */ + time64_t unuse_time; /* Time at which last unused */ + unsigned long flags; +#define AFS_SERVER_FL_RESPONDING 0 /* The server is responding */ +#define AFS_SERVER_FL_UPDATING 1 +#define AFS_SERVER_FL_NEEDS_UPDATE 2 /* Fileserver address list is out of date */ +#define AFS_SERVER_FL_UNCREATED 3 /* The record needs creating */ +#define AFS_SERVER_FL_CREATING 4 /* The record is being created */ +#define AFS_SERVER_FL_EXPIRED 5 /* The record has expired */ +#define AFS_SERVER_FL_NOT_FOUND 6 /* VL server says no such server */ +#define AFS_SERVER_FL_VL_FAIL 7 /* Failed to access VL server */ +#define AFS_SERVER_FL_MAY_HAVE_CB 8 /* May have callbacks on this fileserver */ +#define AFS_SERVER_FL_IS_YFS 16 /* Server is YFS not AFS */ +#define AFS_SERVER_FL_NO_IBULK 17 /* Fileserver doesn't support FS.InlineBulkStatus */ +#define AFS_SERVER_FL_NO_RM2 18 /* Fileserver doesn't support YFS.RemoveFile2 */ +#define AFS_SERVER_FL_HAS_FS64 19 /* Fileserver supports FS.{Fetch,Store}Data64 */ +#define AFS_SERVER_FL_NO_RENAME2 20 /* YFS Fileserver doesn't support enhanced rename */ + refcount_t ref; /* Object refcount */ + atomic_t active; /* Active user count */ + u32 addr_version; /* Address list version */ + u16 service_id; /* Service ID we're using. */ + short create_error; /* Creation error */ + unsigned int rtt; /* Server's current RTT in uS */ + unsigned int debug_id; /* Debugging ID for traces */ /* file service access */ - struct rb_root fs_vnodes; /* vnodes backed by this server (ordered by FID) */ - unsigned long fs_act_jif; /* time at which last activity occurred */ - unsigned long fs_dead_jif; /* time at which no longer to be considered dead */ - spinlock_t fs_lock; /* access lock */ - int fs_state; /* 0 or reason FS currently marked dead (-errno) */ + rwlock_t fs_lock; /* access lock */ + + /* Probe state */ + struct afs_endpoint_state __rcu *endpoint_state; /* Latest endpoint/probe state */ + unsigned long probed_at; /* Time last probe was dispatched (jiffies) */ + wait_queue_head_t probe_wq; + unsigned int probe_counter; /* Number of probes issued */ + spinlock_t probe_lock; +}; + +enum afs_ro_replicating { + AFS_RO_NOT_REPLICATING, /* Not doing replication */ + AFS_RO_REPLICATING_USE_OLD, /* Replicating; use old version */ + AFS_RO_REPLICATING_USE_NEW, /* Replicating; switch to new version */ +} __mode(byte); + +/* + * Replaceable volume server list. + */ +struct afs_server_entry { + struct afs_server *server; + struct afs_volume *volume; + struct list_head slink; /* Link in server->volumes */ + time64_t cb_expires_at; /* Time at which volume-level callback expires */ + unsigned long flags; +#define AFS_SE_EXCLUDED 0 /* Set if server is to be excluded in rotation */ +#define AFS_SE_VOLUME_OFFLINE 1 /* Set if volume offline notice given */ +#define AFS_SE_VOLUME_BUSY 2 /* Set if volume busy notice given */ +}; - /* callback promise management */ - struct rb_root cb_promises; /* vnode expiration list (ordered earliest first) */ - struct delayed_work cb_updater; /* callback updater */ - struct delayed_work cb_break_work; /* collected break dispatcher */ - wait_queue_head_t cb_break_waitq; /* space available in cb_break waitqueue */ - spinlock_t cb_lock; /* access lock */ - struct afs_callback cb_break[64]; /* ring of callbacks awaiting breaking */ - atomic_t cb_break_n; /* number of pending breaks */ - u8 cb_break_head; /* head of callback breaking ring */ - u8 cb_break_tail; /* tail of callback breaking ring */ +struct afs_server_list { + struct rcu_head rcu; + refcount_t usage; + bool attached; /* T if attached to servers */ + enum afs_ro_replicating ro_replicating; /* RW->RO update (probably) in progress */ + unsigned char nr_servers; + unsigned short vnovol_mask; /* Servers to be skipped due to VNOVOL */ + unsigned int seq; /* Set to ->servers_seq when installed */ + rwlock_t lock; + struct afs_server_entry servers[]; }; /* - * AFS volume access record + * Live AFS volume management. */ struct afs_volume { - atomic_t usage; - struct afs_cell *cell; /* cell to which belongs (unrefd ptr) */ - struct afs_vlocation *vlocation; /* volume location */ + struct rcu_head rcu; + afs_volid_t vid; /* The volume ID of this volume */ + afs_volid_t vids[AFS_MAXTYPES]; /* All associated volume IDs */ + refcount_t ref; + unsigned int debug_id; /* Debugging ID for traces */ + time64_t update_at; /* Time at which to next update */ + struct afs_cell *cell; /* Cell to which belongs (pins ref) */ + struct rb_node cell_node; /* Link in cell->volumes */ + struct hlist_node proc_link; /* Link in cell->proc_volumes */ + struct super_block __rcu *sb; /* Superblock on which inodes reside */ + struct work_struct destructor; /* Deferred destructor */ + unsigned long flags; +#define AFS_VOLUME_NEEDS_UPDATE 0 /* - T if an update needs performing */ +#define AFS_VOLUME_UPDATING 1 /* - T if an update is in progress */ +#define AFS_VOLUME_WAIT 2 /* - T if users must wait for update */ +#define AFS_VOLUME_DELETED 3 /* - T if volume appears deleted */ +#define AFS_VOLUME_MAYBE_NO_IBULK 4 /* - T if some servers don't have InlineBulkStatus */ +#define AFS_VOLUME_RM_TREE 5 /* - Set if volume removed from cell->volumes */ #ifdef CONFIG_AFS_FSCACHE - struct fscache_cookie *cache; /* caching cookie */ + struct fscache_volume *cache; /* Caching cookie */ #endif - afs_volid_t vid; /* volume ID */ + struct afs_server_list __rcu *servers; /* List of servers on which volume resides */ + rwlock_t servers_lock; /* Lock for ->servers */ + unsigned int servers_seq; /* Incremented each time ->servers changes */ + + /* RO release tracking */ + struct mutex volsync_lock; /* Time/state evaluation lock */ + time64_t creation_time; /* Volume creation time (or TIME64_MIN) */ + time64_t update_time; /* Volume update time (or TIME64_MIN) */ + + /* Callback management */ + struct mutex cb_check_lock; /* Lock to control race to check after v_break */ + time64_t cb_expires_at; /* Earliest volume callback expiry time */ + atomic_t cb_ro_snapshot; /* RO volume update-from-snapshot counter */ + atomic_t cb_v_break; /* Volume-break event counter. */ + atomic_t cb_v_check; /* Volume-break has-been-checked counter. */ + atomic_t cb_scrub; /* Scrub-all-data event counter. */ + rwlock_t cb_v_break_lock; + struct rw_semaphore open_mmaps_lock; + struct list_head open_mmaps; /* List of vnodes that are mmapped */ + afs_voltype_t type; /* type of volume */ char type_force; /* force volume type (suppress R/O -> R/W) */ - unsigned short nservers; /* number of server slots filled */ - unsigned short rjservers; /* number of servers discarded due to -ENOMEDIUM */ - struct afs_server *servers[8]; /* servers on which volume resides (ordered) */ - struct rw_semaphore server_sem; /* lock for accessing current server */ + u8 name_len; + u8 name[AFS_MAXVOLNAME + 1]; /* NUL-padded volume name */ }; -/* - * vnode catalogue entry - */ -struct afs_cache_vnode { - afs_vnodeid_t vnode_id; /* vnode ID */ - unsigned vnode_unique; /* vnode ID uniquifier */ - afs_dataversion_t data_version; /* data version */ +enum afs_lock_state { + AFS_VNODE_LOCK_NONE, /* The vnode has no lock on the server */ + AFS_VNODE_LOCK_WAITING_FOR_CB, /* We're waiting for the server to break the callback */ + AFS_VNODE_LOCK_SETTING, /* We're asking the server for a lock */ + AFS_VNODE_LOCK_GRANTED, /* We have a lock on the server */ + AFS_VNODE_LOCK_EXTENDING, /* We're extending a lock on the server */ + AFS_VNODE_LOCK_NEED_UNLOCK, /* We need to unlock on the server */ + AFS_VNODE_LOCK_UNLOCKING, /* We're telling the server to unlock */ + AFS_VNODE_LOCK_DELETED, /* The vnode has been deleted whilst we have a lock */ }; /* - * AFS inode private data + * AFS inode private data. + * + * Note that afs_alloc_inode() *must* reset anything that could incorrectly + * leak from one inode to another. */ struct afs_vnode { - struct inode vfs_inode; /* the VFS's inode record */ - + struct netfs_inode netfs; /* Netfslib context and vfs inode */ struct afs_volume *volume; /* volume on which vnode resides */ - struct afs_server *server; /* server currently supplying this file */ struct afs_fid fid; /* the file identifier for this inode */ struct afs_file_status status; /* AFS status info for this file */ -#ifdef CONFIG_AFS_FSCACHE - struct fscache_cookie *cache; /* caching cookie */ -#endif - struct afs_permits *permits; /* cache of permits so far obtained */ - struct mutex permits_lock; /* lock for altering permits list */ - struct mutex validate_lock; /* lock for validating this vnode */ - wait_queue_head_t update_waitq; /* status fetch waitqueue */ - int update_cnt; /* number of outstanding ops that will update the - * status */ - spinlock_t writeback_lock; /* lock for writebacks */ + afs_dataversion_t invalid_before; /* Child dentries are invalid before this */ + struct afs_permits __rcu *permit_cache; /* cache of permits so far obtained */ + struct list_head io_lock_waiters; /* Threads waiting for the I/O lock */ + struct rw_semaphore validate_lock; /* lock for validating this vnode */ + struct rw_semaphore rmdir_lock; /* Lock for rmdir vs sillyrename */ + struct key *silly_key; /* Silly rename key */ + spinlock_t wb_lock; /* lock for wb_keys */ spinlock_t lock; /* waitqueue/flags lock */ unsigned long flags; -#define AFS_VNODE_CB_BROKEN 0 /* set if vnode's callback was broken */ +#define AFS_VNODE_IO_LOCK 0 /* Set if the I/O serialisation lock is held */ #define AFS_VNODE_UNSET 1 /* set if vnode attributes not yet set */ -#define AFS_VNODE_MODIFIED 2 /* set if vnode's data modified */ +#define AFS_VNODE_DIR_VALID 2 /* Set if dir contents are valid */ #define AFS_VNODE_ZAP_DATA 3 /* set if vnode's data should be invalidated */ #define AFS_VNODE_DELETED 4 /* set if vnode deleted on server */ #define AFS_VNODE_MOUNTPOINT 5 /* set if vnode is a mountpoint symlink */ -#define AFS_VNODE_LOCKING 6 /* set if waiting for lock on vnode */ -#define AFS_VNODE_READLOCKED 7 /* set if vnode is read-locked on the server */ -#define AFS_VNODE_WRITELOCKED 8 /* set if vnode is write-locked on the server */ -#define AFS_VNODE_UNLOCKING 9 /* set if vnode is being unlocked on the server */ -#define AFS_VNODE_AUTOCELL 10 /* set if Vnode is an auto mount point */ -#define AFS_VNODE_PSEUDODIR 11 /* set if Vnode is a pseudo directory */ - - long acl_order; /* ACL check count (callback break count) */ - - struct list_head writebacks; /* alterations in pagecache that need writing */ +#define AFS_VNODE_PSEUDODIR 7 /* set if Vnode is a pseudo directory */ +#define AFS_VNODE_NEW_CONTENT 8 /* Set if file has new content (create/trunc-0) */ +#define AFS_VNODE_SILLY_DELETED 9 /* Set if file has been silly-deleted */ +#define AFS_VNODE_MODIFYING 10 /* Set if we're performing a modification op */ +#define AFS_VNODE_DIR_READ 11 /* Set if we've read a dir's contents */ + + struct folio_queue *directory; /* Directory contents */ + struct list_head wb_keys; /* List of keys available for writeback */ struct list_head pending_locks; /* locks waiting to be granted */ struct list_head granted_locks; /* locks granted on this file */ struct delayed_work lock_work; /* work to be done in locking */ - struct key *unlock_key; /* key to be used in unlocking */ + struct key *lock_key; /* Key to be used in lock ops */ + ktime_t locked_at; /* Time at which lock obtained */ + enum afs_lock_state lock_state : 8; + afs_lock_type_t lock_type : 8; + unsigned int directory_size; /* Amount of space in ->directory */ /* outstanding callback notification on this file */ - struct rb_node server_rb; /* link in server->fs_vnodes */ - struct rb_node cb_promise; /* link in server->cb_promises */ - struct work_struct cb_broken_work; /* work to be done on callback break */ - time64_t cb_expires; /* time at which callback expires */ - time64_t cb_expires_at; /* time used to order cb_promise */ - unsigned cb_version; /* callback version */ - unsigned cb_expiry; /* callback expiry time */ - afs_callback_type_t cb_type; /* type of callback */ - bool cb_promised; /* true if promise still holds */ + struct work_struct cb_work; /* Work for mmap'd files */ + struct list_head cb_mmap_link; /* Link in cell->fs_open_mmaps */ + void *cb_server; /* Server with callback/filelock */ + atomic_t cb_nr_mmap; /* Number of mmaps */ + unsigned int cb_ro_snapshot; /* RO volume release counter on ->volume */ + unsigned int cb_scrub; /* Scrub counter on ->volume */ + unsigned int cb_break; /* Break counter on vnode */ + unsigned int cb_v_check; /* Break check counter on ->volume */ + seqlock_t cb_lock; /* Lock for ->cb_server, ->status, ->cb_*break */ + + atomic64_t cb_expires_at; /* time at which callback expires */ +#define AFS_NO_CB_PROMISE TIME64_MIN }; +static inline struct fscache_cookie *afs_vnode_cache(struct afs_vnode *vnode) +{ +#ifdef CONFIG_AFS_FSCACHE + return netfs_i_cookie(&vnode->netfs); +#else + return NULL; +#endif +} + +static inline void afs_vnode_set_cache(struct afs_vnode *vnode, + struct fscache_cookie *cookie) +{ +#ifdef CONFIG_AFS_FSCACHE + vnode->netfs.cache = cookie; + if (cookie) + mapping_set_release_always(vnode->netfs.inode.i_mapping); +#endif +} + /* * cached security record for one user's attempt to access a vnode */ struct afs_permit { struct key *key; /* RxRPC ticket holding a security context */ - afs_access_t access_mask; /* access mask for this key */ + afs_access_t access; /* CallerAccess value for this key */ }; /* - * cache of security records from attempts to access a vnode + * Immutable cache of CallerAccess records from attempts to access vnodes. + * These may be shared between multiple vnodes. */ struct afs_permits { - struct rcu_head rcu; /* disposal procedure */ - int count; /* number of records */ - struct afs_permit permits[0]; /* the permits so far examined */ + struct rcu_head rcu; + struct hlist_node hash_node; /* Link in hash */ + unsigned long h; /* Hash value for this permit list */ + refcount_t usage; + unsigned short nr_permits; /* Number of records */ + bool invalidated; /* Invalidated due to key change */ + struct afs_permit permits[] __counted_by(nr_permits); /* List of permits sorted by key pointer */ +}; + +/* + * Error prioritisation and accumulation. + */ +struct afs_error { + s32 abort_code; /* Cumulative abort code */ + short error; /* Cumulative error */ + bool responded; /* T if server responded */ + bool aborted; /* T if ->error is from an abort */ +}; + +/* + * Cursor for iterating over a set of volume location servers. + */ +struct afs_vl_cursor { + struct afs_cell *cell; /* The cell we're querying */ + struct afs_vlserver_list *server_list; /* Current server list (pins ref) */ + struct afs_vlserver *server; /* Server on which this resides */ + struct afs_addr_list *alist; /* Current address list (pins ref) */ + struct key *key; /* Key for the server */ + unsigned long untried_servers; /* Bitmask of untried servers */ + unsigned long addr_tried; /* Tried addresses */ + struct afs_error cumul_error; /* Cumulative error */ + unsigned int debug_id; + s32 call_abort_code; + short call_error; /* Error from single call */ + short server_index; /* Current server */ + signed char addr_index; /* Current address */ + unsigned short flags; +#define AFS_VL_CURSOR_STOP 0x0001 /* Set to cease iteration */ +#define AFS_VL_CURSOR_RETRY 0x0002 /* Set to do a retry */ +#define AFS_VL_CURSOR_RETRIED 0x0004 /* Set if started a retry */ + short nr_iterations; /* Number of server iterations */ + bool call_responded; /* T if the current address responded */ +}; + +/* + * Fileserver state tracking for an operation. An array of these is kept, + * indexed by server index. + */ +struct afs_server_state { + /* Tracking of fileserver probe state. Other operations may interfere + * by probing a fileserver when accessing other volumes. + */ + unsigned int probe_seq; + unsigned long untried_addrs; /* Addresses we haven't tried yet */ + struct wait_queue_entry probe_waiter; + struct afs_endpoint_state *endpoint_state; /* Endpoint state being monitored */ }; /* - * record of one of a system's set of network interfaces + * Fileserver operation methods. */ -struct afs_interface { - struct in_addr address; /* IPv4 address bound to interface */ - struct in_addr netmask; /* netmask applied to address */ - unsigned mtu; /* MTU of interface */ +struct afs_operation_ops { + void (*issue_afs_rpc)(struct afs_operation *op); + void (*issue_yfs_rpc)(struct afs_operation *op); + void (*success)(struct afs_operation *op); + void (*aborted)(struct afs_operation *op); + void (*failed)(struct afs_operation *op); + void (*edit_dir)(struct afs_operation *op); + void (*put)(struct afs_operation *op); +}; + +struct afs_vnode_param { + struct afs_vnode *vnode; + struct afs_fid fid; /* Fid to access */ + struct afs_status_cb scb; /* Returned status and callback promise */ + afs_dataversion_t dv_before; /* Data version before the call */ + unsigned int cb_break_before; /* cb_break before the call */ + u8 dv_delta; /* Expected change in data version */ + bool put_vnode:1; /* T if we have a ref on the vnode */ + bool need_io_lock:1; /* T if we need the I/O lock on this */ + bool update_ctime:1; /* Need to update the ctime */ + bool set_size:1; /* Must update i_size */ + bool op_unlinked:1; /* True if file was unlinked by op */ + bool speculative:1; /* T if speculative status fetch (no vnode lock) */ + bool modification:1; /* Set if the content gets modified */ +}; + +/* + * Fileserver operation wrapper, handling server and address rotation + * asynchronously. May make simultaneous calls to multiple servers. + */ +struct afs_operation { + struct afs_net *net; /* Network namespace */ + struct key *key; /* Key for the cell */ + const struct afs_call_type *type; /* Type of call done */ + const struct afs_operation_ops *ops; + + /* Parameters/results for the operation */ + struct afs_volume *volume; /* Volume being accessed */ + struct afs_vnode_param file[2]; + struct afs_vnode_param *more_files; + struct afs_volsync pre_volsync; /* Volsync before op */ + struct afs_volsync volsync; /* Volsync returned by op */ + struct dentry *dentry; /* Dentry to be altered */ + struct dentry *dentry_2; /* Second dentry to be altered */ + struct timespec64 mtime; /* Modification time to record */ + struct timespec64 ctime; /* Change time to set */ + struct afs_error cumul_error; /* Cumulative error */ + short nr_files; /* Number of entries in file[], more_files */ + unsigned int debug_id; + + unsigned int cb_v_break; /* Volume break counter before op */ + + union { + struct { + int which; /* Which ->file[] to fetch for */ + } fetch_status; + struct { + int reason; /* enum afs_edit_dir_reason */ + mode_t mode; + const char *symlink; + } create; + struct { + bool need_rehash; + } unlink; + struct { + struct dentry *rehash; + struct dentry *tmp; + unsigned int rename_flags; + bool new_negative; + } rename; + struct { + struct netfs_io_subrequest *subreq; + } fetch; + struct { + afs_lock_type_t type; + } lock; + struct { + struct iov_iter *write_iter; + loff_t pos; + loff_t size; + loff_t i_size; + } store; + struct { + struct iattr *attr; + loff_t old_i_size; + } setattr; + struct afs_acl *acl; + struct yfs_acl *yacl; + struct { + struct afs_volume_status vs; + struct kstatfs *buf; + } volstatus; + }; + + /* Fileserver iteration state */ + struct afs_server_list *server_list; /* Current server list (pins ref) */ + struct afs_server *server; /* Server we're using (ref pinned by server_list) */ + struct afs_endpoint_state *estate; /* Current endpoint state (doesn't pin ref) */ + struct afs_server_state *server_states; /* States of the servers involved */ + struct afs_call *call; + unsigned long untried_servers; /* Bitmask of untried servers */ + unsigned long addr_tried; /* Tried addresses */ + s32 call_abort_code; /* Abort code from single call */ + short call_error; /* Error from single call */ + short server_index; /* Current server */ + short nr_iterations; /* Number of server iterations */ + signed char addr_index; /* Current address */ + bool call_responded; /* T if the current address responded */ + + unsigned int flags; +#define AFS_OPERATION_STOP 0x0001 /* Set to cease iteration */ +#define AFS_OPERATION_VBUSY 0x0002 /* Set if seen VBUSY */ +#define AFS_OPERATION_VMOVED 0x0004 /* Set if seen VMOVED */ +#define AFS_OPERATION_VNOVOL 0x0008 /* Set if seen VNOVOL */ +#define AFS_OPERATION_CUR_ONLY 0x0010 /* Set if current server only (file lock held) */ +#define AFS_OPERATION_NO_VSLEEP 0x0020 /* Set to prevent sleep on VBUSY, VOFFLINE, ... */ +#define AFS_OPERATION_UNINTR 0x0040 /* Set if op is uninterruptible */ +#define AFS_OPERATION_DOWNGRADE 0x0080 /* Set to retry with downgraded opcode */ +#define AFS_OPERATION_LOCK_0 0x0100 /* Set if have io_lock on file[0] */ +#define AFS_OPERATION_LOCK_1 0x0200 /* Set if have io_lock on file[1] */ +#define AFS_OPERATION_TRIED_ALL 0x0400 /* Set if we've tried all the fileservers */ +#define AFS_OPERATION_RETRY_SERVER 0x0800 /* Set if we should retry the current server */ +#define AFS_OPERATION_DIR_CONFLICT 0x1000 /* Set if we detected a 3rd-party dir change */ +#define AFS_OPERATION_ASYNC 0x2000 /* Set if should run asynchronously */ }; -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 */ - __u8 clock_seq_hi_and_reserved; /* clock seq hi and variant */ - __u8 clock_seq_low; /* clock seq low */ - __u8 node[6]; /* spatially unique node ID (MAC addr) */ +/* + * Cache auxiliary data. + */ +struct afs_vnode_cache_aux { + __be64 data_version; +} __packed; + +static inline void afs_set_cache_aux(struct afs_vnode *vnode, + struct afs_vnode_cache_aux *aux) +{ + aux->data_version = cpu_to_be64(vnode->status.data_version); +} + +static inline void afs_invalidate_cache(struct afs_vnode *vnode, unsigned int flags) +{ + struct afs_vnode_cache_aux aux; + + afs_set_cache_aux(vnode, &aux); + fscache_invalidate(afs_vnode_cache(vnode), &aux, + i_size_read(&vnode->netfs.inode), flags); +} + +/* + * Directory iteration management. + */ +struct afs_dir_iter { + struct afs_vnode *dvnode; + union afs_xdr_dir_block *block; + struct folio_queue *fq; + unsigned int fpos; + int fq_slot; + unsigned int loop_check; + u8 nr_slots; + u8 bucket; + unsigned int prev_entry; }; +#include <trace/events/afs.h> + /*****************************************************************************/ /* - * cache.c + * addr_list.c */ -#ifdef CONFIG_AFS_FSCACHE -extern struct fscache_netfs afs_cache_netfs; -extern struct fscache_cookie_def afs_cell_cache_index_def; -extern struct fscache_cookie_def afs_vlocation_cache_index_def; -extern struct fscache_cookie_def afs_volume_cache_index_def; -extern struct fscache_cookie_def afs_vnode_cache_index_def; -#else -#define afs_cell_cache_index_def (*(struct fscache_cookie_def *) NULL) -#define afs_vlocation_cache_index_def (*(struct fscache_cookie_def *) NULL) -#define afs_volume_cache_index_def (*(struct fscache_cookie_def *) NULL) -#define afs_vnode_cache_index_def (*(struct fscache_cookie_def *) NULL) -#endif +struct afs_addr_list *afs_get_addrlist(struct afs_addr_list *alist, enum afs_alist_trace reason); +extern struct afs_addr_list *afs_alloc_addrlist(unsigned int nr); +extern void afs_put_addrlist(struct afs_addr_list *alist, enum afs_alist_trace reason); +extern struct afs_vlserver_list *afs_parse_text_addrs(struct afs_net *, + const char *, size_t, char, + unsigned short, unsigned short); +bool afs_addr_list_same(const struct afs_addr_list *a, + const struct afs_addr_list *b); +extern struct afs_vlserver_list *afs_dns_query(struct afs_cell *, time64_t *); + +extern int afs_merge_fs_addr4(struct afs_net *net, struct afs_addr_list *addr, + __be32 xdr, u16 port); +extern int afs_merge_fs_addr6(struct afs_net *net, struct afs_addr_list *addr, + __be32 *xdr, u16 port); +void afs_set_peer_appdata(struct afs_server *server, + struct afs_addr_list *old_alist, + struct afs_addr_list *new_alist); + +/* + * addr_prefs.c + */ +int afs_proc_addr_prefs_write(struct file *file, char *buf, size_t size); +void afs_get_address_preferences_rcu(struct afs_net *net, struct afs_addr_list *alist); +void afs_get_address_preferences(struct afs_net *net, struct afs_addr_list *alist); /* * callback.c */ +extern void afs_invalidate_mmap_work(struct work_struct *); extern void afs_init_callback_state(struct afs_server *); -extern void afs_broken_callback_work(struct work_struct *); -extern void afs_break_callbacks(struct afs_server *, size_t, - struct afs_callback[]); -extern void afs_discard_callback_on_delete(struct afs_vnode *); -extern void afs_give_up_callback(struct afs_vnode *); -extern void afs_dispatch_give_up_callbacks(struct work_struct *); -extern void afs_flush_callback_breaks(struct afs_server *); -extern int __init afs_callback_update_init(void); -extern void afs_callback_update_kill(void); +extern void __afs_break_callback(struct afs_vnode *, enum afs_cb_break_reason); +extern void afs_break_callback(struct afs_vnode *, enum afs_cb_break_reason); +extern void afs_break_callbacks(struct afs_server *, size_t, struct afs_callback_break *); + +static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode) +{ + return vnode->cb_break + vnode->cb_ro_snapshot + vnode->cb_scrub; +} + +static inline bool afs_cb_is_broken(unsigned int cb_break, + const struct afs_vnode *vnode) +{ + return cb_break != (vnode->cb_break + + atomic_read(&vnode->volume->cb_ro_snapshot) + + atomic_read(&vnode->volume->cb_scrub)); +} /* * cell.c */ -extern struct rw_semaphore afs_proc_cells_sem; -extern struct list_head afs_proc_cells; - -#define afs_get_cell(C) do { atomic_inc(&(C)->usage); } while(0) -extern int afs_cell_init(char *); -extern struct afs_cell *afs_cell_create(const char *, unsigned, char *, bool); -extern struct afs_cell *afs_cell_lookup(const char *, unsigned, bool); -extern struct afs_cell *afs_grab_cell(struct afs_cell *); -extern void afs_put_cell(struct afs_cell *); -extern void afs_cell_purge(void); +extern int afs_cell_init(struct afs_net *, const char *); +extern struct afs_cell *afs_find_cell(struct afs_net *, const char *, unsigned, + enum afs_cell_trace); +enum afs_lookup_cell_for { + AFS_LOOKUP_CELL_DYNROOT, + AFS_LOOKUP_CELL_MOUNTPOINT, + AFS_LOOKUP_CELL_DIRECT_MOUNT, + AFS_LOOKUP_CELL_PRELOAD, + AFS_LOOKUP_CELL_ROOTCELL, + AFS_LOOKUP_CELL_ALIAS_CHECK, +}; +struct afs_cell *afs_lookup_cell(struct afs_net *net, + const char *name, unsigned int namesz, + const char *vllist, + enum afs_lookup_cell_for reason, + enum afs_cell_trace trace); +extern struct afs_cell *afs_use_cell(struct afs_cell *, enum afs_cell_trace); +void afs_unuse_cell(struct afs_cell *cell, enum afs_cell_trace reason); +extern struct afs_cell *afs_get_cell(struct afs_cell *, enum afs_cell_trace); +extern void afs_see_cell(struct afs_cell *, enum afs_cell_trace); +extern void afs_put_cell(struct afs_cell *, enum afs_cell_trace); +extern void afs_queue_cell(struct afs_cell *, enum afs_cell_trace); +void afs_set_cell_timer(struct afs_cell *cell, unsigned int delay_secs); +extern void __net_exit afs_cell_purge(struct afs_net *); /* * cmservice.c @@ -470,28 +1079,92 @@ extern void afs_cell_purge(void); extern bool afs_cm_incoming_call(struct afs_call *); /* + * cm_security.c + */ +void afs_process_oob_queue(struct work_struct *work); +#ifdef CONFIG_RXGK +int afs_create_token_key(struct afs_net *net, struct socket *socket); +#else +static inline int afs_create_token_key(struct afs_net *net, struct socket *socket) +{ + return 0; +} +#endif + +/* * dir.c */ +extern const struct file_operations afs_dir_file_operations; extern const struct inode_operations afs_dir_inode_operations; +extern const struct address_space_operations afs_dir_aops; extern const struct dentry_operations afs_fs_dentry_operations; -extern const struct file_operations afs_dir_file_operations; + +ssize_t afs_read_single(struct afs_vnode *dvnode, struct file *file); +ssize_t afs_read_dir(struct afs_vnode *dvnode, struct file *file) + __acquires(&dvnode->validate_lock); +extern void afs_d_release(struct dentry *); +extern void afs_check_for_remote_deletion(struct afs_operation *); +int afs_single_writepages(struct address_space *mapping, + struct writeback_control *wbc); + +/* + * dir_edit.c + */ +extern void afs_edit_dir_add(struct afs_vnode *, const struct qstr *, struct afs_fid *, + enum afs_edit_dir_reason); +extern void afs_edit_dir_remove(struct afs_vnode *, const struct qstr *, enum afs_edit_dir_reason); +void afs_edit_dir_update(struct afs_vnode *vnode, const struct qstr *name, + struct afs_vnode *new_dvnode, enum afs_edit_dir_reason why); +void afs_mkdir_init_dir(struct afs_vnode *dvnode, struct afs_vnode *parent_vnode); + +/* + * dir_search.c + */ +unsigned int afs_dir_hash_name(const struct qstr *name); +bool afs_dir_init_iter(struct afs_dir_iter *iter, const struct qstr *name); +union afs_xdr_dir_block *afs_dir_find_block(struct afs_dir_iter *iter, size_t block); +int afs_dir_search_bucket(struct afs_dir_iter *iter, const struct qstr *name, + struct afs_fid *_fid); +int afs_dir_search(struct afs_vnode *dvnode, const struct qstr *name, + struct afs_fid *_fid, afs_dataversion_t *_dir_version); + +/* + * dir_silly.c + */ +extern int afs_sillyrename(struct afs_vnode *, struct afs_vnode *, + struct dentry *, struct key *); +extern int afs_silly_iput(struct dentry *, struct inode *); + +/* + * dynroot.c + */ +extern const struct inode_operations afs_dynroot_inode_operations; +extern const struct dentry_operations afs_dynroot_dentry_operations; + +struct inode *afs_dynroot_iget_root(struct super_block *sb); /* * file.c */ -extern const struct address_space_operations afs_fs_aops; +extern const struct address_space_operations afs_file_aops; extern const struct inode_operations afs_file_inode_operations; extern const struct file_operations afs_file_operations; +extern const struct afs_operation_ops afs_fetch_data_operation; +extern const struct netfs_request_ops afs_req_ops; +extern int afs_cache_wb_key(struct afs_vnode *, struct afs_file *); +extern void afs_put_wb_key(struct afs_wb_key *); extern int afs_open(struct inode *, struct file *); extern int afs_release(struct inode *, struct file *); -extern int afs_page_filler(void *, struct page *); -extern void afs_put_read(struct afs_read *); +void afs_fetch_data_async_rx(struct work_struct *work); +void afs_fetch_data_immediate_cancel(struct afs_call *call); /* * flock.c */ -extern void __exit afs_kill_lock_manager(void); +extern struct workqueue_struct *afs_lock_manager; + +extern void afs_lock_op_done(struct afs_call *); extern void afs_lock_work(struct work_struct *); extern void afs_lock_may_be_available(struct afs_vnode *); extern int afs_lock(struct file *, int, struct file_lock *); @@ -500,52 +1173,92 @@ extern int afs_flock(struct file *, int, struct file_lock *); /* * fsclient.c */ -extern int afs_fs_fetch_file_status(struct afs_server *, struct key *, - struct afs_vnode *, struct afs_volsync *, - bool); -extern int afs_fs_give_up_callbacks(struct afs_server *, bool); -extern int afs_fs_fetch_data(struct afs_server *, struct key *, - struct afs_vnode *, struct afs_read *, bool); -extern int afs_fs_create(struct afs_server *, struct key *, - struct afs_vnode *, const char *, umode_t, - struct afs_fid *, struct afs_file_status *, - struct afs_callback *, bool); -extern int afs_fs_remove(struct afs_server *, struct key *, - struct afs_vnode *, const char *, bool, bool); -extern int afs_fs_link(struct afs_server *, struct key *, struct afs_vnode *, - struct afs_vnode *, const char *, bool); -extern int afs_fs_symlink(struct afs_server *, struct key *, - struct afs_vnode *, const char *, const char *, - struct afs_fid *, struct afs_file_status *, bool); -extern int afs_fs_rename(struct afs_server *, struct key *, - struct afs_vnode *, const char *, - struct afs_vnode *, const char *, bool); -extern int afs_fs_store_data(struct afs_server *, struct afs_writeback *, - pgoff_t, pgoff_t, unsigned, unsigned, bool); -extern int afs_fs_setattr(struct afs_server *, struct key *, - struct afs_vnode *, struct iattr *, bool); -extern int afs_fs_get_volume_status(struct afs_server *, struct key *, - struct afs_vnode *, - struct afs_volume_status *, bool); -extern int afs_fs_set_lock(struct afs_server *, struct key *, - struct afs_vnode *, afs_lock_type_t, bool); -extern int afs_fs_extend_lock(struct afs_server *, struct key *, - struct afs_vnode *, bool); -extern int afs_fs_release_lock(struct afs_server *, struct key *, - struct afs_vnode *, bool); +extern void afs_fs_fetch_status(struct afs_operation *); +extern void afs_fs_fetch_data(struct afs_operation *); +extern void afs_fs_create_file(struct afs_operation *); +extern void afs_fs_make_dir(struct afs_operation *); +extern void afs_fs_remove_file(struct afs_operation *); +extern void afs_fs_remove_dir(struct afs_operation *); +extern void afs_fs_link(struct afs_operation *); +extern void afs_fs_symlink(struct afs_operation *); +extern void afs_fs_rename(struct afs_operation *); +extern void afs_fs_store_data(struct afs_operation *); +extern void afs_fs_setattr(struct afs_operation *); +extern void afs_fs_get_volume_status(struct afs_operation *); +extern void afs_fs_set_lock(struct afs_operation *); +extern void afs_fs_extend_lock(struct afs_operation *); +extern void afs_fs_release_lock(struct afs_operation *); +int afs_fs_give_up_all_callbacks(struct afs_net *net, struct afs_server *server, + struct afs_address *addr, struct key *key); +bool afs_fs_get_capabilities(struct afs_net *net, struct afs_server *server, + struct afs_endpoint_state *estate, unsigned int addr_index, + struct key *key); +extern void afs_fs_inline_bulk_status(struct afs_operation *); + +struct afs_acl { + u32 size; + u8 data[] __counted_by(size); +}; + +extern void afs_fs_fetch_acl(struct afs_operation *); +extern void afs_fs_store_acl(struct afs_operation *); + +/* + * fs_operation.c + */ +extern struct afs_operation *afs_alloc_operation(struct key *, struct afs_volume *); +extern int afs_put_operation(struct afs_operation *); +extern bool afs_begin_vnode_operation(struct afs_operation *); +extern void afs_end_vnode_operation(struct afs_operation *op); +extern void afs_wait_for_operation(struct afs_operation *); +extern int afs_do_sync_operation(struct afs_operation *); + +static inline void afs_op_set_vnode(struct afs_operation *op, unsigned int n, + struct afs_vnode *vnode) +{ + op->file[n].vnode = vnode; + op->file[n].need_io_lock = true; +} + +static inline void afs_op_set_fid(struct afs_operation *op, unsigned int n, + const struct afs_fid *fid) +{ + op->file[n].fid = *fid; +} + +/* + * fs_probe.c + */ +struct afs_endpoint_state *afs_get_endpoint_state(struct afs_endpoint_state *estate, + enum afs_estate_trace where); +void afs_put_endpoint_state(struct afs_endpoint_state *estate, enum afs_estate_trace where); +extern void afs_fileserver_probe_result(struct afs_call *); +int afs_fs_probe_fileserver(struct afs_net *net, struct afs_server *server, + struct afs_addr_list *new_alist, struct key *key); +int afs_wait_for_fs_probes(struct afs_operation *op, struct afs_server_state *states, bool intr); +extern void afs_probe_fileserver(struct afs_net *, struct afs_server *); +extern void afs_fs_probe_dispatcher(struct work_struct *); +int afs_wait_for_one_fs_probe(struct afs_server *server, struct afs_endpoint_state *estate, + unsigned long exclude, bool is_intr); +extern void afs_fs_probe_cleanup(struct afs_net *); /* * inode.c */ -extern struct inode *afs_iget_autocell(struct inode *, const char *, int, - struct key *); -extern struct inode *afs_iget(struct super_block *, struct key *, - struct afs_fid *, struct afs_file_status *, - struct afs_callback *); -extern void afs_zap_data(struct afs_vnode *); -extern int afs_validate(struct afs_vnode *, struct key *); -extern int afs_getattr(const struct path *, struct kstat *, u32, unsigned int); -extern int afs_setattr(struct dentry *, struct iattr *); +extern const struct afs_operation_ops afs_fetch_status_operation; + +void afs_init_new_symlink(struct afs_vnode *vnode, struct afs_operation *op); +const char *afs_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback); +int afs_readlink(struct dentry *dentry, char __user *buffer, int buflen); +extern void afs_vnode_commit_status(struct afs_operation *, struct afs_vnode_param *); +extern int afs_fetch_status(struct afs_vnode *, struct key *, bool, afs_access_t *); +extern int afs_ilookup5_test_by_fid(struct inode *, void *); +extern struct inode *afs_iget(struct afs_operation *, struct afs_vnode_param *); +extern struct inode *afs_root_iget(struct super_block *, struct key *); +extern int afs_getattr(struct mnt_idmap *idmap, const struct path *, + struct kstat *, u32, unsigned int); +extern int afs_setattr(struct mnt_idmap *idmap, struct dentry *, struct iattr *); extern void afs_evict_inode(struct inode *); extern int afs_drop_inode(struct inode *); @@ -553,12 +1266,75 @@ extern int afs_drop_inode(struct inode *); * main.c */ extern struct workqueue_struct *afs_wq; -extern struct afs_uuid afs_uuid; +extern int afs_net_id; + +static inline struct afs_net *afs_net(struct net *net) +{ + return net_generic(net, afs_net_id); +} + +static inline struct afs_net *afs_sb2net(struct super_block *sb) +{ + return afs_net(AFS_FS_S(sb)->net_ns); +} + +static inline struct afs_net *afs_d2net(struct dentry *dentry) +{ + return afs_sb2net(dentry->d_sb); +} + +static inline struct afs_net *afs_i2net(struct inode *inode) +{ + return afs_sb2net(inode->i_sb); +} + +static inline struct afs_net *afs_v2net(struct afs_vnode *vnode) +{ + return afs_i2net(&vnode->netfs.inode); +} + +static inline struct afs_net *afs_sock2net(struct sock *sk) +{ + return net_generic(sock_net(sk), afs_net_id); +} + +static inline void __afs_stat(atomic_t *s) +{ + atomic_inc(s); +} + +#define afs_stat_v(vnode, n) __afs_stat(&afs_v2net(vnode)->n) /* * misc.c */ extern int afs_abort_to_error(u32); +extern void afs_prioritise_error(struct afs_error *, int, u32); + +static inline void afs_op_nomem(struct afs_operation *op) +{ + op->cumul_error.error = -ENOMEM; +} + +static inline int afs_op_error(const struct afs_operation *op) +{ + return op->cumul_error.error; +} + +static inline s32 afs_op_abort_code(const struct afs_operation *op) +{ + return op->cumul_error.abort_code; +} + +static inline int afs_op_set_error(struct afs_operation *op, int error) +{ + return op->cumul_error.error = error; +} + +static inline void afs_op_accumulate_error(struct afs_operation *op, int error, s32 abort_code) +{ + afs_prioritise_error(&op->cumul_error, error, abort_code); +} /* * mntpt.c @@ -571,178 +1347,488 @@ extern struct vfsmount *afs_d_automount(struct path *); extern void afs_mntpt_kill_timer(void); /* - * netdevices.c - */ -extern int afs_get_ipv4_interfaces(struct afs_interface *, size_t, bool); - -/* * proc.c */ -extern int afs_proc_init(void); -extern void afs_proc_cleanup(void); +#ifdef CONFIG_PROC_FS +extern int __net_init afs_proc_init(struct afs_net *); +extern void __net_exit afs_proc_cleanup(struct afs_net *); extern int afs_proc_cell_setup(struct afs_cell *); extern void afs_proc_cell_remove(struct afs_cell *); +extern void afs_put_sysnames(struct afs_sysnames *); +#else +static inline int afs_proc_init(struct afs_net *net) { return 0; } +static inline void afs_proc_cleanup(struct afs_net *net) {} +static inline int afs_proc_cell_setup(struct afs_cell *cell) { return 0; } +static inline void afs_proc_cell_remove(struct afs_cell *cell) {} +static inline void afs_put_sysnames(struct afs_sysnames *sysnames) {} +#endif + +/* + * rotate.c + */ +void afs_clear_server_states(struct afs_operation *op); +extern bool afs_select_fileserver(struct afs_operation *); +extern void afs_dump_edestaddrreq(const struct afs_operation *); /* * rxrpc.c */ -extern struct socket *afs_socket; -extern atomic_t afs_outstanding_calls; +extern struct workqueue_struct *afs_async_calls; -extern int afs_open_socket(void); -extern void afs_close_socket(void); +extern int __net_init afs_open_socket(struct afs_net *); +extern void __net_exit afs_close_socket(struct afs_net *); +extern void afs_charge_preallocation(struct work_struct *); extern void afs_put_call(struct afs_call *); -extern int afs_queue_call_work(struct afs_call *); -extern int afs_make_call(struct in_addr *, struct afs_call *, gfp_t, bool); -extern struct afs_call *afs_alloc_flat_call(const struct afs_call_type *, +void afs_deferred_put_call(struct afs_call *call); +void afs_make_call(struct afs_call *call, gfp_t gfp); +void afs_deliver_to_call(struct afs_call *call); +void afs_wait_for_call_to_complete(struct afs_call *call); +extern struct afs_call *afs_alloc_flat_call(struct afs_net *, + const struct afs_call_type *, size_t, size_t); extern void afs_flat_call_destructor(struct afs_call *); extern void afs_send_empty_reply(struct afs_call *); extern void afs_send_simple_reply(struct afs_call *, const void *, size_t); -extern int afs_extract_data(struct afs_call *, void *, size_t, bool); +extern int afs_extract_data(struct afs_call *, bool); +extern int afs_protocol_error(struct afs_call *, enum afs_eproto_cause); + +static inline struct afs_call *afs_get_call(struct afs_call *call, + enum afs_call_trace why) +{ + int r; + + __refcount_inc(&call->ref, &r); + + trace_afs_call(call->debug_id, why, r + 1, + atomic_read(&call->net->nr_outstanding_calls), + __builtin_return_address(0)); + return call; +} + +static inline void afs_see_call(struct afs_call *call, enum afs_call_trace why) +{ + int r = refcount_read(&call->ref); + + trace_afs_call(call->debug_id, why, r, + atomic_read(&call->net->nr_outstanding_calls), + __builtin_return_address(0)); +} + +static inline void afs_make_op_call(struct afs_operation *op, struct afs_call *call, + gfp_t gfp) +{ + struct afs_addr_list *alist = op->estate->addresses; + + op->call = call; + op->type = call->type; + call->op = op; + call->key = op->key; + call->intr = !(op->flags & AFS_OPERATION_UNINTR); + call->peer = rxrpc_kernel_get_peer(alist->addrs[op->addr_index].peer); + call->service_id = op->server->service_id; + afs_make_call(call, gfp); +} + +static inline void afs_extract_begin(struct afs_call *call, void *buf, size_t size) +{ + call->iov_len = size; + call->kvec[0].iov_base = buf; + call->kvec[0].iov_len = size; + iov_iter_kvec(&call->def_iter, ITER_DEST, call->kvec, 1, size); +} + +static inline void afs_extract_to_tmp(struct afs_call *call) +{ + call->iov_len = sizeof(call->tmp); + afs_extract_begin(call, &call->tmp, sizeof(call->tmp)); +} + +static inline void afs_extract_to_tmp64(struct afs_call *call) +{ + call->iov_len = sizeof(call->tmp64); + afs_extract_begin(call, &call->tmp64, sizeof(call->tmp64)); +} + +static inline void afs_extract_discard(struct afs_call *call, size_t size) +{ + call->iov_len = size; + iov_iter_discard(&call->def_iter, ITER_DEST, size); +} + +static inline void afs_extract_to_buf(struct afs_call *call, size_t size) +{ + call->iov_len = size; + afs_extract_begin(call, call->buffer, size); +} static inline int afs_transfer_reply(struct afs_call *call) { - return afs_extract_data(call, call->buffer, call->reply_max, false); + return afs_extract_data(call, false); +} + +static inline bool afs_check_call_state(struct afs_call *call, + enum afs_call_state state) +{ + return READ_ONCE(call->state) == state; +} + +static inline bool afs_set_call_state(struct afs_call *call, + enum afs_call_state from, + enum afs_call_state to) +{ + bool ok = false; + + spin_lock_bh(&call->state_lock); + if (call->state == from) { + call->state = to; + trace_afs_call_state(call, from, to, 0, 0); + ok = true; + } + spin_unlock_bh(&call->state_lock); + return ok; +} + +static inline void afs_set_call_complete(struct afs_call *call, + int error, u32 remote_abort) +{ + enum afs_call_state state; + bool ok = false; + + spin_lock_bh(&call->state_lock); + state = call->state; + if (state != AFS_CALL_COMPLETE) { + call->abort_code = remote_abort; + call->error = error; + call->state = AFS_CALL_COMPLETE; + trace_afs_call_state(call, state, AFS_CALL_COMPLETE, + error, remote_abort); + ok = true; + } + spin_unlock_bh(&call->state_lock); + if (ok) { + trace_afs_call_done(call); + + /* Asynchronous calls have two refs to release - one from the alloc and + * one queued with the work item - and we can't just deallocate the + * call because the work item may be queued again. + */ + if (call->drop_ref) + afs_put_call(call); + } } /* * security.c */ +extern void afs_put_permits(struct afs_permits *); extern void afs_clear_permits(struct afs_vnode *); -extern void afs_cache_permit(struct afs_vnode *, struct key *, long); -extern void afs_zap_permits(struct rcu_head *); +extern void afs_cache_permit(struct afs_vnode *, struct key *, unsigned int, + struct afs_status_cb *); extern struct key *afs_request_key(struct afs_cell *); -extern int afs_permission(struct inode *, int); +extern struct key *afs_request_key_rcu(struct afs_cell *); +extern int afs_check_permit(struct afs_vnode *, struct key *, afs_access_t *); +extern int afs_permission(struct mnt_idmap *, struct inode *, int); +extern void __exit afs_clean_up_permit_cache(void); /* * server.c */ extern spinlock_t afs_server_peer_lock; -#define afs_get_server(S) \ -do { \ - _debug("GET SERVER %d", atomic_read(&(S)->usage)); \ - atomic_inc(&(S)->usage); \ -} while(0) +struct afs_server *afs_find_server(const struct rxrpc_peer *peer); +extern struct afs_server *afs_lookup_server(struct afs_cell *, struct key *, const uuid_t *, u32); +extern struct afs_server *afs_get_server(struct afs_server *, enum afs_server_trace); +struct afs_server *afs_use_server(struct afs_server *server, bool activate, + enum afs_server_trace reason); +void afs_unuse_server(struct afs_net *net, struct afs_server *server, + enum afs_server_trace reason); +void afs_unuse_server_notime(struct afs_net *net, struct afs_server *server, + enum afs_server_trace reason); +extern void afs_put_server(struct afs_net *, struct afs_server *, enum afs_server_trace); +void afs_purge_servers(struct afs_cell *cell); +extern void afs_fs_probe_timer(struct timer_list *); +void __net_exit afs_wait_for_servers(struct afs_net *net); +bool afs_check_server_record(struct afs_operation *op, struct afs_server *server, struct key *key); + +static inline void afs_see_server(struct afs_server *server, enum afs_server_trace trace) +{ + int r = refcount_read(&server->ref); + int a = atomic_read(&server->active); + + trace_afs_server(server->debug_id, r, a, trace); + +} + +static inline void afs_inc_servers_outstanding(struct afs_net *net) +{ + atomic_inc(&net->servers_outstanding); +} + +static inline void afs_dec_servers_outstanding(struct afs_net *net) +{ + if (atomic_dec_and_test(&net->servers_outstanding)) + wake_up_var(&net->servers_outstanding); +} + +static inline bool afs_is_probing_server(struct afs_server *server) +{ + return list_empty(&server->probe_link); +} + +/* + * server_list.c + */ +static inline struct afs_server_list *afs_get_serverlist(struct afs_server_list *slist) +{ + refcount_inc(&slist->usage); + return slist; +} -extern struct afs_server *afs_lookup_server(struct afs_cell *, - const struct in_addr *); -extern struct afs_server *afs_find_server(const struct sockaddr_rxrpc *); -extern void afs_put_server(struct afs_server *); -extern void __exit afs_purge_servers(void); +extern void afs_put_serverlist(struct afs_net *, struct afs_server_list *); +struct afs_server_list *afs_alloc_server_list(struct afs_volume *volume, + struct key *key, + struct afs_vldb_entry *vldb); +extern bool afs_annotate_server_list(struct afs_server_list *, struct afs_server_list *); +void afs_attach_volume_to_servers(struct afs_volume *volume, struct afs_server_list *slist); +void afs_reattach_volume_to_servers(struct afs_volume *volume, struct afs_server_list *slist, + struct afs_server_list *old); +void afs_detach_volume_from_servers(struct afs_volume *volume, struct afs_server_list *slist); /* * super.c */ -extern int afs_fs_init(void); +extern int __init afs_fs_init(void); extern void afs_fs_exit(void); /* + * validation.c + */ +bool afs_check_validity(const struct afs_vnode *vnode); +int afs_update_volume_state(struct afs_operation *op); +int afs_validate(struct afs_vnode *vnode, struct key *key); + +/* * vlclient.c */ -extern int afs_vl_get_entry_by_name(struct in_addr *, struct key *, - const char *, struct afs_cache_vlocation *, - bool); -extern int afs_vl_get_entry_by_id(struct in_addr *, struct key *, - afs_volid_t, afs_voltype_t, - struct afs_cache_vlocation *, bool); +extern struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_vl_cursor *, + const char *, int); +extern struct afs_addr_list *afs_vl_get_addrs_u(struct afs_vl_cursor *, const uuid_t *); +struct afs_call *afs_vl_get_capabilities(struct afs_net *net, + struct afs_addr_list *alist, + unsigned int addr_index, + struct key *key, + struct afs_vlserver *server, + unsigned int server_index); +extern struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *, const uuid_t *); +extern char *afs_yfsvl_get_cell_name(struct afs_vl_cursor *); /* - * vlocation.c + * vl_alias.c */ -#define afs_get_vlocation(V) do { atomic_inc(&(V)->usage); } while(0) +extern int afs_cell_detect_alias(struct afs_cell *, struct key *); -extern int __init afs_vlocation_update_init(void); -extern struct afs_vlocation *afs_vlocation_lookup(struct afs_cell *, - struct key *, - const char *, size_t); -extern void afs_put_vlocation(struct afs_vlocation *); -extern void afs_vlocation_purge(void); +/* + * vl_probe.c + */ +extern void afs_vlserver_probe_result(struct afs_call *); +extern int afs_send_vl_probes(struct afs_net *, struct key *, struct afs_vlserver_list *); +extern int afs_wait_for_vl_probes(struct afs_vlserver_list *, unsigned long); /* - * vnode.c + * vl_rotate.c */ -static inline struct afs_vnode *AFS_FS_I(struct inode *inode) +extern bool afs_begin_vlserver_operation(struct afs_vl_cursor *, + struct afs_cell *, struct key *); +extern bool afs_select_vlserver(struct afs_vl_cursor *); +extern bool afs_select_current_vlserver(struct afs_vl_cursor *); +extern int afs_end_vlserver_operation(struct afs_vl_cursor *); + +/* + * vlserver_list.c + */ +static inline struct afs_vlserver *afs_get_vlserver(struct afs_vlserver *vlserver) { - return container_of(inode, struct afs_vnode, vfs_inode); + refcount_inc(&vlserver->ref); + return vlserver; } -static inline struct inode *AFS_VNODE_TO_I(struct afs_vnode *vnode) +static inline struct afs_vlserver_list *afs_get_vlserverlist(struct afs_vlserver_list *vllist) { - return &vnode->vfs_inode; -} - -extern void afs_vnode_finalise_status_update(struct afs_vnode *, - struct afs_server *); -extern int afs_vnode_fetch_status(struct afs_vnode *, struct afs_vnode *, - struct key *); -extern int afs_vnode_fetch_data(struct afs_vnode *, struct key *, - struct afs_read *); -extern int afs_vnode_create(struct afs_vnode *, struct key *, const char *, - umode_t, struct afs_fid *, struct afs_file_status *, - struct afs_callback *, struct afs_server **); -extern int afs_vnode_remove(struct afs_vnode *, struct key *, const char *, - bool); -extern int afs_vnode_link(struct afs_vnode *, struct afs_vnode *, struct key *, - const char *); -extern int afs_vnode_symlink(struct afs_vnode *, struct key *, const char *, - const char *, struct afs_fid *, - struct afs_file_status *, struct afs_server **); -extern int afs_vnode_rename(struct afs_vnode *, struct afs_vnode *, - struct key *, const char *, const char *); -extern int afs_vnode_store_data(struct afs_writeback *, pgoff_t, pgoff_t, - unsigned, unsigned); -extern int afs_vnode_setattr(struct afs_vnode *, struct key *, struct iattr *); -extern int afs_vnode_get_volume_status(struct afs_vnode *, struct key *, - struct afs_volume_status *); -extern int afs_vnode_set_lock(struct afs_vnode *, struct key *, - afs_lock_type_t); -extern int afs_vnode_extend_lock(struct afs_vnode *, struct key *); -extern int afs_vnode_release_lock(struct afs_vnode *, struct key *); + if (vllist) + refcount_inc(&vllist->ref); + return vllist; +} + +extern struct afs_vlserver *afs_alloc_vlserver(const char *, size_t, unsigned short); +extern void afs_put_vlserver(struct afs_net *, struct afs_vlserver *); +extern struct afs_vlserver_list *afs_alloc_vlserver_list(unsigned int); +extern void afs_put_vlserverlist(struct afs_net *, struct afs_vlserver_list *); +extern struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *, + const void *, size_t); /* * volume.c */ -#define afs_get_volume(V) do { atomic_inc(&(V)->usage); } while(0) - -extern void afs_put_volume(struct afs_volume *); -extern struct afs_volume *afs_volume_lookup(struct afs_mount_params *); -extern struct afs_server *afs_volume_pick_fileserver(struct afs_vnode *); -extern int afs_volume_release_fileserver(struct afs_vnode *, - struct afs_server *, int); +extern struct afs_volume *afs_create_volume(struct afs_fs_context *); +extern int afs_activate_volume(struct afs_volume *); +extern void afs_deactivate_volume(struct afs_volume *); +bool afs_try_get_volume(struct afs_volume *volume, enum afs_volume_trace reason); +extern struct afs_volume *afs_get_volume(struct afs_volume *, enum afs_volume_trace); +void afs_put_volume(struct afs_volume *volume, enum afs_volume_trace reason); +extern int afs_check_volume_status(struct afs_volume *, struct afs_operation *); /* * write.c */ -extern int afs_set_page_dirty(struct page *); -extern void afs_put_writeback(struct afs_writeback *); -extern int afs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata); -extern int afs_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata); -extern int afs_writepage(struct page *, struct writeback_control *); +void afs_prepare_write(struct netfs_io_subrequest *subreq); +void afs_issue_write(struct netfs_io_subrequest *subreq); +void afs_begin_writeback(struct netfs_io_request *wreq); +void afs_retry_request(struct netfs_io_request *wreq, struct netfs_io_stream *stream); extern int afs_writepages(struct address_space *, struct writeback_control *); -extern void afs_pages_written_back(struct afs_vnode *, struct afs_call *); -extern ssize_t afs_file_write(struct kiocb *, struct iov_iter *); -extern int afs_writeback_all(struct afs_vnode *); -extern int afs_flush(struct file *, fl_owner_t); extern int afs_fsync(struct file *, loff_t, loff_t, int); +extern vm_fault_t afs_page_mkwrite(struct vm_fault *vmf); +extern void afs_prune_wb_keys(struct afs_vnode *); /* * xattr.c */ -extern const struct xattr_handler *afs_xattr_handlers[]; -extern ssize_t afs_listxattr(struct dentry *, char *, size_t); +extern const struct xattr_handler * const afs_xattr_handlers[]; + +/* + * yfsclient.c + */ +extern void yfs_fs_fetch_data(struct afs_operation *); +extern void yfs_fs_create_file(struct afs_operation *); +extern void yfs_fs_make_dir(struct afs_operation *); +extern void yfs_fs_remove_file2(struct afs_operation *); +extern void yfs_fs_remove_file(struct afs_operation *); +extern void yfs_fs_remove_dir(struct afs_operation *); +extern void yfs_fs_link(struct afs_operation *); +extern void yfs_fs_symlink(struct afs_operation *); +extern void yfs_fs_rename(struct afs_operation *); +void yfs_fs_rename_replace(struct afs_operation *op); +void yfs_fs_rename_noreplace(struct afs_operation *op); +void yfs_fs_rename_exchange(struct afs_operation *op); +extern void yfs_fs_store_data(struct afs_operation *); +extern void yfs_fs_setattr(struct afs_operation *); +extern void yfs_fs_get_volume_status(struct afs_operation *); +extern void yfs_fs_set_lock(struct afs_operation *); +extern void yfs_fs_extend_lock(struct afs_operation *); +extern void yfs_fs_release_lock(struct afs_operation *); +extern void yfs_fs_fetch_status(struct afs_operation *); +extern void yfs_fs_inline_bulk_status(struct afs_operation *); + +struct yfs_acl { + struct afs_acl *acl; /* Dir/file/symlink ACL */ + struct afs_acl *vol_acl; /* Whole volume ACL */ + u32 inherit_flag; /* True if ACL is inherited from parent dir */ + u32 num_cleaned; /* Number of ACEs removed due to subject removal */ + unsigned int flags; +#define YFS_ACL_WANT_ACL 0x01 /* Set if caller wants ->acl */ +#define YFS_ACL_WANT_VOL_ACL 0x02 /* Set if caller wants ->vol_acl */ +}; + +extern void yfs_free_opaque_acl(struct yfs_acl *); +extern void yfs_fs_fetch_opaque_acl(struct afs_operation *); +extern void yfs_fs_store_opaque_acl2(struct afs_operation *); + +/* + * Miscellaneous inline functions. + */ +static inline struct afs_vnode *AFS_FS_I(struct inode *inode) +{ + return container_of(inode, struct afs_vnode, netfs.inode); +} + +static inline struct inode *AFS_VNODE_TO_I(struct afs_vnode *vnode) +{ + return &vnode->netfs.inode; +} + +/* + * Note that a dentry got changed. We need to set d_fsdata to the data version + * number derived from the result of the operation. It doesn't matter if + * d_fsdata goes backwards as we'll just revalidate. + */ +static inline void afs_update_dentry_version(struct afs_operation *op, + struct afs_vnode_param *dir_vp, + struct dentry *dentry) +{ + if (!op->cumul_error.error) + dentry->d_fsdata = + (void *)(unsigned long)dir_vp->scb.status.data_version; +} + +/* + * Set the file size and block count. Estimate the number of 512 bytes blocks + * used, rounded up to nearest 1K for consistency with other AFS clients. + */ +static inline void afs_set_i_size(struct afs_vnode *vnode, u64 size) +{ + i_size_write(&vnode->netfs.inode, size); + vnode->netfs.inode.i_blocks = ((size + 1023) >> 10) << 1; +} + +/* + * Check for a conflicting operation on a directory that we just unlinked from. + * If someone managed to sneak a link or an unlink in on the file we just + * unlinked, we won't be able to trust nlink on an AFS file (but not YFS). + */ +static inline void afs_check_dir_conflict(struct afs_operation *op, + struct afs_vnode_param *dvp) +{ + if (dvp->dv_before + dvp->dv_delta != dvp->scb.status.data_version) + op->flags |= AFS_OPERATION_DIR_CONFLICT; +} + +static inline int afs_io_error(struct afs_call *call, enum afs_io_error where) +{ + trace_afs_io_error(call->debug_id, -EIO, where); + return -EIO; +} + +static inline int afs_bad(struct afs_vnode *vnode, enum afs_file_error where) +{ + trace_afs_file_error(vnode, -EIO, where); + return -EIO; +} + +/* + * Set the callback promise on a vnode. + */ +static inline void afs_set_cb_promise(struct afs_vnode *vnode, time64_t expires_at, + enum afs_cb_promise_trace trace) +{ + atomic64_set(&vnode->cb_expires_at, expires_at); + trace_afs_cb_promise(vnode, trace); +} + +/* + * Clear the callback promise on a vnode, returning true if it was promised. + */ +static inline bool afs_clear_cb_promise(struct afs_vnode *vnode, + enum afs_cb_promise_trace trace) +{ + trace_afs_cb_promise(vnode, trace); + return atomic64_xchg(&vnode->cb_expires_at, AFS_NO_CB_PROMISE) != AFS_NO_CB_PROMISE; +} + +/* + * Mark a directory as being invalid. + */ +static inline void afs_invalidate_dir(struct afs_vnode *dvnode, + enum afs_dir_invalid_trace trace) +{ + if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) { + trace_afs_dir_invalid(dvnode, trace); + afs_stat_v(dvnode, n_inval); + } +} /*****************************************************************************/ /* * debug tracing */ -#include <trace/events/afs.h> - extern unsigned afs_debug; #define dbgprintk(FMT,...) \ |