linux_dsm_epyc7002/include/linux/lockd/lockd.h

370 lines
11 KiB
C
Raw Normal View History

/*
* linux/include/linux/lockd/lockd.h
*
* General-purpose lockd include file.
*
* Copyright (C) 1996 Olaf Kirch <okir@monad.swb.de>
*/
#ifndef LINUX_LOCKD_LOCKD_H
#define LINUX_LOCKD_LOCKD_H
#ifdef __KERNEL__
#include <linux/in.h>
#include <linux/in6.h>
#include <net/ipv6.h>
#include <linux/fs.h>
#include <linux/kref.h>
#include <linux/utsname.h>
#include <linux/lockd/bind.h>
#include <linux/lockd/xdr.h>
#ifdef CONFIG_LOCKD_V4
#include <linux/lockd/xdr4.h>
#endif
#include <linux/lockd/debug.h>
#include <linux/sunrpc/svc.h>
/*
* Version string
*/
#define LOCKD_VERSION "0.5"
/*
* Default timeout for RPC calls (seconds)
*/
#define LOCKD_DFLT_TIMEO 10
/*
* Lockd host handle (used both by the client and server personality).
*/
struct nlm_host {
struct hlist_node h_hash; /* doubly linked list */
struct sockaddr_storage h_addr; /* peer address */
size_t h_addrlen;
struct sockaddr_storage h_srcaddr; /* our address (optional) */
size_t h_srcaddrlen;
struct rpc_clnt *h_rpcclnt; /* RPC client to talk to peer */
char *h_name; /* remote hostname */
u32 h_version; /* interface version */
unsigned short h_proto; /* transport proto */
unsigned short h_reclaiming : 1,
h_server : 1, /* server side, not client side */
h_noresvport : 1,
h_inuse : 1;
wait_queue_head_t h_gracewait; /* wait while reclaiming */
struct rw_semaphore h_rwsem; /* Reboot recovery lock */
u32 h_state; /* pseudo-state counter */
u32 h_nsmstate; /* true remote NSM state */
u32 h_pidcount; /* Pseudopids */
atomic_t h_count; /* reference count */
struct mutex h_mutex; /* mutex for pmap binding */
unsigned long h_nextrebind; /* next portmap call */
unsigned long h_expires; /* eligible for GC */
struct list_head h_lockowners; /* Lockowners for the client */
spinlock_t h_lock;
struct list_head h_granted; /* Locks in GRANTED state */
struct list_head h_reclaim; /* Locks in RECLAIM state */
struct nsm_handle *h_nsmhandle; /* NSM status handle */
char *h_addrbuf; /* address eyecatcher */
struct net *net; /* host net */
char nodename[UNX_MAXNODENAME + 1];
};
/*
* The largest string sm_addrbuf should hold is a full-size IPv6 address
* (no "::" anywhere) with a scope ID. The buffer size is computed to
* hold eight groups of colon-separated four-hex-digit numbers, a
* percent sign, a scope id (at most 32 bits, in decimal), and NUL.
*/
#define NSM_ADDRBUF ((8 * 4 + 7) + (1 + 10) + 1)
struct nsm_handle {
struct list_head sm_link;
atomic_t sm_count;
NSM: Support IPv6 version of mon_name The "mon_name" argument of the NSMPROC_MON and NSMPROC_UNMON upcalls is a string that contains the hostname or IP address of the remote peer to be notified when this host has rebooted. The sm-notify command uses this identifier to contact the peer when we reboot, so it must be either a well-qualified DNS hostname or a presentation format IP address string. When the "nsm_use_hostnames" sysctl is set to zero, the kernel's NSM provides a presentation format IP address in the "mon_name" argument. Otherwise, the "caller_name" argument from NLM requests is used, which is usually just the DNS hostname of the peer. To support IPv6 addresses for the mon_name argument, we use the nsm_handle's address eye-catcher, which already contains an appropriate presentation format address string. Using the eye-catcher string obviates the need to use a large buffer on the stack to form the presentation address string for the upcall. This patch also addresses a subtle bug. An NSMPROC_MON request and the subsequent NSMPROC_UNMON request for the same peer are required to use the same value for the "mon_name" argument. Otherwise, rpc.statd's NSMPROC_UNMON processing cannot locate the database entry for that peer and remove it. If the setting of nsm_use_hostnames is changed between the time the kernel sends an NSMPROC_MON request and the time it sends the NSMPROC_UNMON request for the same peer, the "mon_name" argument for these two requests may not be the same. This is because the value of "mon_name" is currently chosen at the moment the call is made based on the setting of nsm_use_hostnames To ensure both requests pass identical contents in the "mon_name" argument, we now select which string to use for the argument in the nsm_monitor() function. A pointer to this string is saved in the nsm_handle so it can be used for a subsequent NSMPROC_UNMON upcall. NB: There are other potential problems, such as how nlm_host_rebooted() might behave if nsm_use_hostnames were changed while hosts are still being monitored. This patch does not attempt to address those problems. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-12-05 02:20:46 +07:00
char *sm_mon_name;
char *sm_name;
struct sockaddr_storage sm_addr;
size_t sm_addrlen;
unsigned int sm_monitored : 1,
sm_sticky : 1; /* don't unmonitor */
struct nsm_private sm_priv;
char sm_addrbuf[NSM_ADDRBUF];
};
/*
* Rigorous type checking on sockaddr type conversions
*/
static inline struct sockaddr_in *nlm_addr_in(const struct nlm_host *host)
{
return (struct sockaddr_in *)&host->h_addr;
}
static inline struct sockaddr *nlm_addr(const struct nlm_host *host)
{
return (struct sockaddr *)&host->h_addr;
}
static inline struct sockaddr_in *nlm_srcaddr_in(const struct nlm_host *host)
{
return (struct sockaddr_in *)&host->h_srcaddr;
}
static inline struct sockaddr *nlm_srcaddr(const struct nlm_host *host)
{
return (struct sockaddr *)&host->h_srcaddr;
}
/*
* Map an fl_owner_t into a unique 32-bit "pid"
*/
struct nlm_lockowner {
struct list_head list;
atomic_t count;
struct nlm_host *host;
fl_owner_t owner;
uint32_t pid;
};
struct nlm_wait;
/*
* Memory chunk for NLM client RPC request.
*/
#define NLMCLNT_OHSIZE ((__NEW_UTS_LEN) + 10u)
struct nlm_rqst {
atomic_t a_count;
unsigned int a_flags; /* initial RPC task flags */
struct nlm_host * a_host; /* host handle */
struct nlm_args a_args; /* arguments */
struct nlm_res a_res; /* result */
struct nlm_block * a_block;
unsigned int a_retries; /* Retry count */
u8 a_owner[NLMCLNT_OHSIZE];
};
/*
* This struct describes a file held open by lockd on behalf of
* an NFS client.
*/
struct nlm_file {
struct hlist_node f_list; /* linked list */
struct nfs_fh f_handle; /* NFS file handle */
struct file * f_file; /* VFS file pointer */
struct nlm_share * f_shares; /* DOS shares */
struct list_head f_blocks; /* blocked locks */
unsigned int f_locks; /* guesstimate # of locks */
unsigned int f_count; /* reference count */
struct mutex f_mutex; /* avoid concurrent access */
};
/*
* This is a server block (i.e. a lock requested by some client which
* couldn't be granted because of a conflicting lock).
*/
#define NLM_NEVER (~(unsigned long) 0)
/* timeout on non-blocking call: */
#define NLM_TIMEOUT (7 * HZ)
struct nlm_block {
struct kref b_count; /* Reference count */
struct list_head b_list; /* linked list of all blocks */
struct list_head b_flist; /* linked list (per file) */
struct nlm_rqst * b_call; /* RPC args & callback info */
struct svc_serv * b_daemon; /* NLM service */
struct nlm_host * b_host; /* host handle for RPC clnt */
unsigned long b_when; /* next re-xmit */
unsigned int b_id; /* block id */
unsigned char b_granted; /* VFS granted lock */
struct nlm_file * b_file; /* file in question */
struct cache_req * b_cache_req; /* deferred request handling */
struct cache_deferred_req * b_deferred_req;
unsigned int b_flags; /* block flags */
#define B_QUEUED 1 /* lock queued */
#define B_GOT_CALLBACK 2 /* got lock or conflicting lock */
#define B_TIMED_OUT 4 /* filesystem too slow to respond */
};
/*
* Global variables
*/
extern const struct rpc_program nlm_program;
extern struct svc_procedure nlmsvc_procedures[];
#ifdef CONFIG_LOCKD_V4
extern struct svc_procedure nlmsvc_procedures4[];
#endif
extern int nlmsvc_grace_period;
extern unsigned long nlmsvc_timeout;
extern bool nsm_use_hostnames;
lockd: Update NSM state from SM_MON replies When rpc.statd starts up in user space at boot time, it attempts to write the latest NSM local state number into /proc/sys/fs/nfs/nsm_local_state. If lockd.ko isn't loaded yet (as is the case in most configurations), that file doesn't exist, thus the kernel's NSM state remains set to its initial value of zero during lockd operation. This is a problem because rpc.statd and lockd use the NSM state number to prevent repeated lock recovery on rebooted hosts. If lockd sends a zero NSM state, but then a delayed SM_NOTIFY with a real NSM state number is received, there is no way for lockd or rpc.statd to distinguish that stale SM_NOTIFY from an actual reboot. Thus lock recovery could be performed after the rebooted host has already started reclaiming locks, and those locks will be lost. We could change /etc/init.d/nfslock so it always modprobes lockd.ko before starting rpc.statd. However, if lockd.ko is ever unloaded and reloaded, we are back at square one, since the NSM state is not preserved across an unload/reload cycle. This may happen frequently on clients that use automounter. A period of NFS inactivity causes lockd.ko to be unloaded, and the kernel loses its NSM state setting. Instead, let's use the fact that rpc.statd plants the local system's NSM state in every SM_MON (and SM_UNMON) reply. lockd performs a synchronous SM_MON upcall to the local rpc.statd _before_ sending its first NLM request to a new remote. This would permit rpc.statd to provide the current NSM state to lockd, even after lockd.ko had been unloaded and reloaded. Note that NLMPROC_LOCK arguments are constructed before the nsm_monitor() call, so we have to rearrange argument construction very slightly to make this all work out. And, the kernel appears to treat NSM state as a u32 (see struct nlm_args and nsm_res). Make nsm_local_state a u32 as well, to ensure we don't get bogus comparison results. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-06-18 08:02:10 +07:00
extern u32 nsm_local_state;
/*
* Lockd client functions
*/
struct nlm_rqst * nlm_alloc_call(struct nlm_host *host);
int nlm_async_call(struct nlm_rqst *, u32, const struct rpc_call_ops *);
int nlm_async_reply(struct nlm_rqst *, u32, const struct rpc_call_ops *);
void nlmclnt_release_call(struct nlm_rqst *);
struct nlm_wait * nlmclnt_prepare_block(struct nlm_host *host, struct file_lock *fl);
void nlmclnt_finish_block(struct nlm_wait *block);
int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout);
__be32 nlmclnt_grant(const struct sockaddr *addr,
const struct nlm_lock *lock);
void nlmclnt_recovery(struct nlm_host *);
int nlmclnt_reclaim(struct nlm_host *, struct file_lock *,
struct nlm_rqst *);
void nlmclnt_next_cookie(struct nlm_cookie *);
/*
* Host cache
*/
struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap,
const size_t salen,
const unsigned short protocol,
const u32 version,
const char *hostname,
int noresvport,
struct net *net);
lockd: Create client-side nlm_host cache NFS clients don't need the garbage collection processing that is performed on nlm_host structures. The client picks up an nlm_host at mount time and holds a reference to it until the file system is unmounted. Servers, on the other hand, don't have a precise way to tell when an nlm_host is no longer being used, so zero refcount nlm_host entries are left to expire in the cache after a time. Basically there's nothing holding a reference to an nlm_host between individual server-side NLM requests, but we can't afford the expense of recreating them for every new NLM request from a client. The nlm_host cache adds some lifetime hysteresis to entries in the cache so the next time a particular nlm_host is needed, it's likely to be discovered by a lookup rather than created from whole cloth. With the new implementation, client nlm_host cache items are no longer garbage collected, and are destroyed directly by a new release function specialized for client entries, nlmclnt_release_host(). They are cached in their own data structure, and have their own lookup logic, simplified and specialized for client nlm_host entries. However, the client nlm_host cache still shares reboot recovery logic with the server nlm_host cache. The NSM "peer rebooted" downcall for clients and servers still come through the same RPC call. This is a legacy formal API that would be difficult to alter, and besides, the user space NSM implementation can't tell the difference between peers that are clients or servers. For this reason, the client cache continues to share the nlm_host_mutex (and reboot recovery logic) with the server cache. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-12-14 22:05:52 +07:00
void nlmclnt_release_host(struct nlm_host *);
struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp,
const char *hostname,
const size_t hostname_len);
void nlmsvc_release_host(struct nlm_host *);
struct rpc_clnt * nlm_bind_host(struct nlm_host *);
void nlm_rebind_host(struct nlm_host *);
struct nlm_host * nlm_get_host(struct nlm_host *);
void nlm_shutdown_hosts(void);
void nlm_shutdown_hosts_net(struct net *net);
void nlm_host_rebooted(const struct net *net,
const struct nlm_reboot *);
/*
* Host monitoring
*/
int nsm_monitor(const struct nlm_host *host);
void nsm_unmonitor(const struct nlm_host *host);
struct nsm_handle *nsm_get_handle(const struct net *net,
const struct sockaddr *sap,
const size_t salen,
const char *hostname,
const size_t hostname_len);
struct nsm_handle *nsm_reboot_lookup(const struct net *net,
const struct nlm_reboot *info);
void nsm_release(struct nsm_handle *nsm);
/*
* This is used in garbage collection and resource reclaim
* A return value != 0 means destroy the lock/block/share
*/
lockd: unlock lockd locks associated with a given server ip For high-availability NFS service, we generally need to be able to drop file locks held on the exported filesystem before moving clients to a new server. Currently the only way to do that is by shutting down lockd entirely, which is often undesireable (for example, if you want to continue exporting other filesystems). This patch allows the administrator to release all locks held by clients accessing the client through a given server ip address, by echoing that address to a new file, /proc/fs/nfsd/unlock_ip, as in: shell> echo 10.1.1.2 > /proc/fs/nfsd/unlock_ip The expected sequence of events can be: 1. Tear down the IP address 2. Unexport the path 3. Write IP to /proc/fs/nfsd/unlock_ip to unlock files 4. Signal peer to begin take-over. For now we only support IPv4 addresses and NFSv2/v3 (NFSv4 locks are not affected). Also, if unmounting the filesystem is required, we assume at step 3 that clients using the given server ip are the only clients holding locks on the given filesystem; otherwise, an additional patch is required to allow revoking all locks held by lockd on a given filesystem. Signed-off-by: S. Wendy Cheng <wcheng@redhat.com> Cc: Lon Hohberger <lhh@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu> fs/lockd/svcsubs.c | 66 +++++++++++++++++++++++++++++++++++++++----- fs/nfsd/nfsctl.c | 65 +++++++++++++++++++++++++++++++++++++++++++ include/linux/lockd/lockd.h | 7 ++++ 3 files changed, 131 insertions(+), 7 deletions(-)
2008-01-17 23:10:12 +07:00
typedef int (*nlm_host_match_fn_t)(void *cur, struct nlm_host *ref);
/*
* Server-side lock handling
*/
__be32 nlmsvc_lock(struct svc_rqst *, struct nlm_file *,
struct nlm_host *, struct nlm_lock *, int,
struct nlm_cookie *, int);
__be32 nlmsvc_unlock(struct net *net, struct nlm_file *, struct nlm_lock *);
__be32 nlmsvc_testlock(struct svc_rqst *, struct nlm_file *,
struct nlm_host *, struct nlm_lock *,
struct nlm_lock *, struct nlm_cookie *);
__be32 nlmsvc_cancel_blocked(struct net *net, struct nlm_file *, struct nlm_lock *);
unsigned long nlmsvc_retry_blocked(void);
void nlmsvc_traverse_blocks(struct nlm_host *, struct nlm_file *,
nlm_host_match_fn_t match);
void nlmsvc_grant_reply(struct nlm_cookie *, __be32);
void nlmsvc_release_call(struct nlm_rqst *);
/*
* File handling for the server personality
*/
__be32 nlm_lookup_file(struct svc_rqst *, struct nlm_file **,
struct nfs_fh *);
void nlm_release_file(struct nlm_file *);
void nlmsvc_mark_resources(struct net *);
void nlmsvc_free_host_resources(struct nlm_host *);
void nlmsvc_invalidate_all(void);
lockd: unlock lockd locks associated with a given server ip For high-availability NFS service, we generally need to be able to drop file locks held on the exported filesystem before moving clients to a new server. Currently the only way to do that is by shutting down lockd entirely, which is often undesireable (for example, if you want to continue exporting other filesystems). This patch allows the administrator to release all locks held by clients accessing the client through a given server ip address, by echoing that address to a new file, /proc/fs/nfsd/unlock_ip, as in: shell> echo 10.1.1.2 > /proc/fs/nfsd/unlock_ip The expected sequence of events can be: 1. Tear down the IP address 2. Unexport the path 3. Write IP to /proc/fs/nfsd/unlock_ip to unlock files 4. Signal peer to begin take-over. For now we only support IPv4 addresses and NFSv2/v3 (NFSv4 locks are not affected). Also, if unmounting the filesystem is required, we assume at step 3 that clients using the given server ip are the only clients holding locks on the given filesystem; otherwise, an additional patch is required to allow revoking all locks held by lockd on a given filesystem. Signed-off-by: S. Wendy Cheng <wcheng@redhat.com> Cc: Lon Hohberger <lhh@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu> fs/lockd/svcsubs.c | 66 +++++++++++++++++++++++++++++++++++++++----- fs/nfsd/nfsctl.c | 65 +++++++++++++++++++++++++++++++++++++++++++ include/linux/lockd/lockd.h | 7 ++++ 3 files changed, 131 insertions(+), 7 deletions(-)
2008-01-17 23:10:12 +07:00
/*
* Cluster failover support
*/
int nlmsvc_unlock_all_by_sb(struct super_block *sb);
int nlmsvc_unlock_all_by_ip(struct sockaddr *server_addr);
lockd: unlock lockd locks associated with a given server ip For high-availability NFS service, we generally need to be able to drop file locks held on the exported filesystem before moving clients to a new server. Currently the only way to do that is by shutting down lockd entirely, which is often undesireable (for example, if you want to continue exporting other filesystems). This patch allows the administrator to release all locks held by clients accessing the client through a given server ip address, by echoing that address to a new file, /proc/fs/nfsd/unlock_ip, as in: shell> echo 10.1.1.2 > /proc/fs/nfsd/unlock_ip The expected sequence of events can be: 1. Tear down the IP address 2. Unexport the path 3. Write IP to /proc/fs/nfsd/unlock_ip to unlock files 4. Signal peer to begin take-over. For now we only support IPv4 addresses and NFSv2/v3 (NFSv4 locks are not affected). Also, if unmounting the filesystem is required, we assume at step 3 that clients using the given server ip are the only clients holding locks on the given filesystem; otherwise, an additional patch is required to allow revoking all locks held by lockd on a given filesystem. Signed-off-by: S. Wendy Cheng <wcheng@redhat.com> Cc: Lon Hohberger <lhh@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu> fs/lockd/svcsubs.c | 66 +++++++++++++++++++++++++++++++++++++++----- fs/nfsd/nfsctl.c | 65 +++++++++++++++++++++++++++++++++++++++++++ include/linux/lockd/lockd.h | 7 ++++ 3 files changed, 131 insertions(+), 7 deletions(-)
2008-01-17 23:10:12 +07:00
static inline struct inode *nlmsvc_file_inode(struct nlm_file *file)
{
return file_inode(file->f_file);
}
static inline int __nlm_privileged_request4(const struct sockaddr *sap)
{
const struct sockaddr_in *sin = (struct sockaddr_in *)sap;
if (ntohs(sin->sin_port) > 1023)
return 0;
return ipv4_is_loopback(sin->sin_addr.s_addr);
}
#if IS_ENABLED(CONFIG_IPV6)
static inline int __nlm_privileged_request6(const struct sockaddr *sap)
{
const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
if (ntohs(sin6->sin6_port) > 1023)
return 0;
if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_MAPPED)
return ipv4_is_loopback(sin6->sin6_addr.s6_addr32[3]);
return ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LOOPBACK;
}
#else /* IS_ENABLED(CONFIG_IPV6) */
static inline int __nlm_privileged_request6(const struct sockaddr *sap)
{
return 0;
}
#endif /* IS_ENABLED(CONFIG_IPV6) */
/*
* Ensure incoming requests are from local privileged callers.
*
* Return TRUE if sender is local and is connecting via a privileged port;
* otherwise return FALSE.
*/
static inline int nlm_privileged_requester(const struct svc_rqst *rqstp)
{
const struct sockaddr *sap = svc_addr(rqstp);
switch (sap->sa_family) {
case AF_INET:
return __nlm_privileged_request4(sap);
case AF_INET6:
return __nlm_privileged_request6(sap);
default:
return 0;
}
}
/*
* Compare two NLM locks.
* When the second lock is of type F_UNLCK, this acts like a wildcard.
*/
static inline int nlm_compare_locks(const struct file_lock *fl1,
const struct file_lock *fl2)
{
return fl1->fl_pid == fl2->fl_pid
&& fl1->fl_owner == fl2->fl_owner
&& fl1->fl_start == fl2->fl_start
&& fl1->fl_end == fl2->fl_end
&&(fl1->fl_type == fl2->fl_type || fl2->fl_type == F_UNLCK);
}
extern const struct lock_manager_operations nlmsvc_lock_operations;
#endif /* __KERNEL__ */
#endif /* LINUX_LOCKD_LOCKD_H */