linux-next/fs/nfsd/netns.h
Weston Andros Adamson fa4983862e nfsd: add LOCALIO support
Add server support for bypassing NFS for localhost reads, writes, and
commits. This is only useful when both the client and server are
running on the same host.

If nfsd_open_local_fh() fails then the NFS client will both retry and
fallback to normal network-based read, write and commit operations if
localio is no longer supported.

Care is taken to ensure the same NFS security mechanisms are used
(authentication, etc) regardless of whether localio or regular NFS
access is used.  The auth_domain established as part of the traditional
NFS client access to the NFS server is also used for localio.  Store
auth_domain for localio in nfsd_uuid_t and transfer it to the client
if it is local to the server.

Relative to containers, localio gives the client access to the network
namespace the server has.  This is required to allow the client to
access the server's per-namespace nfsd_net struct.

This commit also introduces the use of NFSD's percpu_ref to interlock
nfsd_destroy_serv and nfsd_open_local_fh, to ensure nn->nfsd_serv is
not destroyed while in use by nfsd_open_local_fh and other LOCALIO
client code.

CONFIG_NFS_LOCALIO enables NFS server support for LOCALIO.

Signed-off-by: Weston Andros Adamson <dros@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Co-developed-by: Mike Snitzer <snitzer@kernel.org>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Co-developed-by: NeilBrown <neilb@suse.de>
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Acked-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
2024-09-23 15:03:30 -04:00

238 lines
6.6 KiB
C

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* per net namespace data structures for nfsd
*
* Copyright (C) 2012, Jeff Layton <jlayton@redhat.com>
*/
#ifndef __NFSD_NETNS_H__
#define __NFSD_NETNS_H__
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <linux/filelock.h>
#include <linux/nfs4.h>
#include <linux/percpu_counter.h>
#include <linux/percpu-refcount.h>
#include <linux/siphash.h>
#include <linux/sunrpc/stats.h>
/* Hash tables for nfs4_clientid state */
#define CLIENT_HASH_BITS 4
#define CLIENT_HASH_SIZE (1 << CLIENT_HASH_BITS)
#define CLIENT_HASH_MASK (CLIENT_HASH_SIZE - 1)
#define SESSION_HASH_SIZE 512
struct cld_net;
struct nfsd4_client_tracking_ops;
enum {
/* cache misses due only to checksum comparison failures */
NFSD_STATS_PAYLOAD_MISSES,
/* amount of memory (in bytes) currently consumed by the DRC */
NFSD_STATS_DRC_MEM_USAGE,
NFSD_STATS_RC_HITS, /* repcache hits */
NFSD_STATS_RC_MISSES, /* repcache misses */
NFSD_STATS_RC_NOCACHE, /* uncached reqs */
NFSD_STATS_FH_STALE, /* FH stale error */
NFSD_STATS_IO_READ, /* bytes returned to read requests */
NFSD_STATS_IO_WRITE, /* bytes passed in write requests */
#ifdef CONFIG_NFSD_V4
NFSD_STATS_FIRST_NFS4_OP, /* count of individual nfsv4 operations */
NFSD_STATS_LAST_NFS4_OP = NFSD_STATS_FIRST_NFS4_OP + LAST_NFS4_OP,
#define NFSD_STATS_NFS4_OP(op) (NFSD_STATS_FIRST_NFS4_OP + (op))
NFSD_STATS_WDELEG_GETATTR, /* count of getattr conflict with wdeleg */
#endif
NFSD_STATS_COUNTERS_NUM
};
/*
* Represents a nfsd "container". With respect to nfsv4 state tracking, the
* fields of interest are the *_id_hashtbls and the *_name_tree. These track
* the nfs4_client objects by either short or long form clientid.
*
* Each nfsd_net runs a nfs4_laundromat workqueue job when necessary to clean
* up expired clients and delegations within the container.
*/
struct nfsd_net {
struct cld_net *cld_net;
struct cache_detail *svc_expkey_cache;
struct cache_detail *svc_export_cache;
struct cache_detail *idtoname_cache;
struct cache_detail *nametoid_cache;
struct lock_manager nfsd4_manager;
bool grace_ended;
time64_t boot_time;
struct dentry *nfsd_client_dir;
/*
* reclaim_str_hashtbl[] holds known client info from previous reset/reboot
* used in reboot/reset lease grace period processing
*
* conf_id_hashtbl[], and conf_name_tree hold confirmed
* setclientid_confirmed info.
*
* unconf_str_hastbl[] and unconf_name_tree hold unconfirmed
* setclientid info.
*/
struct list_head *reclaim_str_hashtbl;
int reclaim_str_hashtbl_size;
struct list_head *conf_id_hashtbl;
struct rb_root conf_name_tree;
struct list_head *unconf_id_hashtbl;
struct rb_root unconf_name_tree;
struct list_head *sessionid_hashtbl;
/*
* client_lru holds client queue ordered by nfs4_client.cl_time
* for lease renewal.
*
* close_lru holds (open) stateowner queue ordered by nfs4_stateowner.so_time
* for last close replay.
*
* All of the above fields are protected by the client_mutex.
*/
struct list_head client_lru;
struct list_head close_lru;
struct list_head del_recall_lru;
/* protected by blocked_locks_lock */
struct list_head blocked_locks_lru;
struct delayed_work laundromat_work;
/* client_lock protects the client lru list and session hash table */
spinlock_t client_lock;
/* protects blocked_locks_lru */
spinlock_t blocked_locks_lock;
struct file *rec_file;
bool in_grace;
const struct nfsd4_client_tracking_ops *client_tracking_ops;
time64_t nfsd4_lease;
time64_t nfsd4_grace;
bool somebody_reclaimed;
bool track_reclaim_completes;
atomic_t nr_reclaim_complete;
bool nfsd_net_up;
bool lockd_up;
seqlock_t writeverf_lock;
unsigned char writeverf[8];
/*
* Max number of connections this nfsd container will allow. Defaults
* to '0' which is means that it bases this on the number of threads.
*/
unsigned int max_connections;
u32 clientid_base;
u32 clientid_counter;
u32 clverifier_counter;
struct svc_info nfsd_info;
#define nfsd_serv nfsd_info.serv
struct percpu_ref nfsd_serv_ref;
struct completion nfsd_serv_confirm_done;
struct completion nfsd_serv_free_done;
/*
* clientid and stateid data for construction of net unique COPY
* stateids.
*/
u32 s2s_cp_cl_id;
struct idr s2s_cp_stateids;
spinlock_t s2s_cp_lock;
atomic_t pending_async_copies;
/*
* Version information
*/
bool nfsd_versions[NFSD_MAXVERS + 1];
bool nfsd4_minorversions[NFSD_SUPPORTED_MINOR_VERSION + 1];
/*
* Duplicate reply cache
*/
struct nfsd_drc_bucket *drc_hashtbl;
/* max number of entries allowed in the cache */
unsigned int max_drc_entries;
/* number of significant bits in the hash value */
unsigned int maskbits;
unsigned int drc_hashsize;
/*
* Stats and other tracking of on the duplicate reply cache.
* The longest_chain* fields are modified with only the per-bucket
* cache lock, which isn't really safe and should be fixed if we want
* these statistics to be completely accurate.
*/
/* total number of entries */
atomic_t num_drc_entries;
/* Per-netns stats counters */
struct percpu_counter counter[NFSD_STATS_COUNTERS_NUM];
/* sunrpc svc stats */
struct svc_stat nfsd_svcstats;
/* longest hash chain seen */
unsigned int longest_chain;
/* size of cache when we saw the longest hash chain */
unsigned int longest_chain_cachesize;
struct shrinker *nfsd_reply_cache_shrinker;
/* tracking server-to-server copy mounts */
spinlock_t nfsd_ssc_lock;
struct list_head nfsd_ssc_mount_list;
wait_queue_head_t nfsd_ssc_waitq;
/* utsname taken from the process that starts the server */
char nfsd_name[UNX_MAXNODENAME+1];
struct nfsd_fcache_disposal *fcache_disposal;
siphash_key_t siphash_key;
atomic_t nfs4_client_count;
int nfs4_max_clients;
atomic_t nfsd_courtesy_clients;
struct shrinker *nfsd_client_shrinker;
struct work_struct nfsd_shrinker_work;
/* last time an admin-revoke happened for NFSv4.0 */
time64_t nfs40_last_revoke;
#if IS_ENABLED(CONFIG_NFS_LOCALIO)
/* Local clients to be invalidated when net is shut down */
struct list_head local_clients;
#endif
};
/* Simple check to find out if a given net was properly initialized */
#define nfsd_netns_ready(nn) ((nn)->sessionid_hashtbl)
extern bool nfsd_support_version(int vers);
extern unsigned int nfsd_net_id;
bool nfsd_serv_try_get(struct net *net);
void nfsd_serv_put(struct net *net);
void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn);
void nfsd_reset_write_verifier(struct nfsd_net *nn);
#endif /* __NFSD_NETNS_H__ */