linux_dsm_epyc7002/include/linux/sunrpc/xprt.h

390 lines
11 KiB
C
Raw Normal View History

/*
* linux/include/linux/sunrpc/xprt.h
*
* Declarations for the RPC transport interface.
*
* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
*/
#ifndef _LINUX_SUNRPC_XPRT_H
#define _LINUX_SUNRPC_XPRT_H
#include <linux/uio.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kref.h>
#include <linux/ktime.h>
#include <linux/sunrpc/sched.h>
#include <linux/sunrpc/xdr.h>
#include <linux/sunrpc/msg_prot.h>
#ifdef __KERNEL__
#define RPC_MIN_SLOT_TABLE (2U)
#define RPC_DEF_SLOT_TABLE (16U)
#define RPC_MAX_SLOT_TABLE (128U)
/*
* This describes a timeout strategy
*/
struct rpc_timeout {
unsigned long to_initval, /* initial timeout */
to_maxval, /* max timeout */
to_increment; /* if !exponential */
unsigned int to_retries; /* max # of retries */
unsigned char to_exponential;
};
enum rpc_display_format_t {
RPC_DISPLAY_ADDR = 0,
RPC_DISPLAY_PORT,
RPC_DISPLAY_PROTO,
RPC_DISPLAY_HEX_ADDR,
RPC_DISPLAY_HEX_PORT,
RPC_DISPLAY_NETID,
RPC_DISPLAY_MAX,
};
struct rpc_task;
struct rpc_xprt;
struct seq_file;
/*
* This describes a complete RPC request
*/
struct rpc_rqst {
/*
* This is the user-visible part
*/
struct rpc_xprt * rq_xprt; /* RPC client */
struct xdr_buf rq_snd_buf; /* send buffer */
struct xdr_buf rq_rcv_buf; /* recv buffer */
/*
* This is the private part
*/
struct rpc_task * rq_task; /* RPC task data */
__be32 rq_xid; /* request XID */
int rq_cong; /* has incremented xprt->cong */
int rq_reply_bytes_recvd; /* number of reply */
/* bytes received */
u32 rq_seqno; /* gss seq no. used on req. */
int rq_enc_pages_num;
struct page **rq_enc_pages; /* scratch pages for use by
gss privacy code */
void (*rq_release_snd_buf)(struct rpc_rqst *); /* release rq_enc_pages */
struct list_head rq_list;
__u32 * rq_buffer; /* XDR encode buffer */
size_t rq_callsize,
rq_rcvsize;
struct xdr_buf rq_private_buf; /* The receive buffer
* used in the softirq.
*/
unsigned long rq_majortimeo; /* major timeout alarm */
unsigned long rq_timeout; /* Current timeout value */
unsigned int rq_retries; /* # of retries */
unsigned int rq_connect_cookie;
/* A cookie used to track the
state of the transport
connection */
/*
* Partial send handling
*/
u32 rq_bytes_sent; /* Bytes we have sent */
ktime_t rq_xtime; /* transmit time stamp */
int rq_ntrans;
#if defined(CONFIG_NFS_V4_1)
struct list_head rq_bc_list; /* Callback service list */
unsigned long rq_bc_pa_state; /* Backchannel prealloc state */
struct list_head rq_bc_pa_list; /* Backchannel prealloc list */
#endif /* CONFIG_NFS_V4_1 */
};
#define rq_svec rq_snd_buf.head
#define rq_slen rq_snd_buf.len
struct rpc_xprt_ops {
void (*set_buffer_size)(struct rpc_xprt *xprt, size_t sndsize, size_t rcvsize);
int (*reserve_xprt)(struct rpc_task *task);
void (*release_xprt)(struct rpc_xprt *xprt, struct rpc_task *task);
void (*rpcbind)(struct rpc_task *task);
void (*set_port)(struct rpc_xprt *xprt, unsigned short port);
void (*connect)(struct rpc_task *task);
void * (*buf_alloc)(struct rpc_task *task, size_t size);
void (*buf_free)(void *buffer);
int (*send_request)(struct rpc_task *task);
void (*set_retrans_timeout)(struct rpc_task *task);
void (*timer)(struct rpc_task *task);
void (*release_request)(struct rpc_task *task);
void (*close)(struct rpc_xprt *xprt);
void (*destroy)(struct rpc_xprt *xprt);
void (*print_stats)(struct rpc_xprt *xprt, struct seq_file *seq);
};
/*
* RPC transport identifiers
*
* To preserve compatibility with the historical use of raw IP protocol
* id's for transport selection, UDP and TCP identifiers are specified
* with the previous values. No such restriction exists for new transports,
* except that they may not collide with these values (17 and 6,
* respectively).
*/
#define XPRT_TRANSPORT_BC (1 << 31)
enum xprt_transports {
XPRT_TRANSPORT_UDP = IPPROTO_UDP,
XPRT_TRANSPORT_TCP = IPPROTO_TCP,
XPRT_TRANSPORT_BC_TCP = IPPROTO_TCP | XPRT_TRANSPORT_BC,
XPRT_TRANSPORT_RDMA = 256
};
struct rpc_xprt {
struct kref kref; /* Reference count */
struct rpc_xprt_ops * ops; /* transport methods */
const struct rpc_timeout *timeout; /* timeout parms */
struct sockaddr_storage addr; /* server address */
size_t addrlen; /* size of server address */
int prot; /* IP protocol */
unsigned long cong; /* current congestion */
unsigned long cwnd; /* congestion window */
size_t max_payload; /* largest RPC payload size,
in bytes */
unsigned int tsh_size; /* size of transport specific
header */
struct rpc_wait_queue binding; /* requests waiting on rpcbind */
struct rpc_wait_queue sending; /* requests waiting to send */
struct rpc_wait_queue resend; /* requests waiting to resend */
struct rpc_wait_queue pending; /* requests in flight */
struct rpc_wait_queue backlog; /* waiting for slot */
struct list_head free; /* free slots */
struct rpc_rqst * slot; /* slot table storage */
unsigned int max_reqs; /* total slots */
unsigned long state; /* transport state */
unsigned char shutdown : 1, /* being shut down */
resvport : 1; /* use a reserved port */
unsigned int bind_index; /* bind function index */
/*
* Connection of transports
*/
unsigned long bind_timeout,
reestablish_timeout;
unsigned int connect_cookie; /* A cookie that gets bumped
every time the transport
is reconnected */
/*
* Disconnection of idle transports
*/
struct work_struct task_cleanup;
struct timer_list timer;
unsigned long last_used,
idle_timeout;
/*
* Send stuff
*/
spinlock_t transport_lock; /* lock transport info */
spinlock_t reserve_lock; /* lock slot table */
u32 xid; /* Next XID value to use */
struct rpc_task * snd_task; /* Task blocked in send */
nfsd41: sunrpc: Added rpc server-side backchannel handling When the call direction is a reply, copy the xid and call direction into the req->rq_private_buf.head[0].iov_base otherwise rpc_verify_header returns rpc_garbage. Signed-off-by: Rahul Iyer <iyer@netapp.com> Signed-off-by: Mike Sager <sager@netapp.com> Signed-off-by: Marc Eshel <eshel@almaden.ibm.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [get rid of CONFIG_NFSD_V4_1] [sunrpc: refactoring of svc_tcp_recvfrom] [nfsd41: sunrpc: create common send routine for the fore and the back channels] [nfsd41: sunrpc: Use free_page() to free server backchannel pages] [nfsd41: sunrpc: Document server backchannel locking] [nfsd41: sunrpc: remove bc_connect_worker()] [nfsd41: sunrpc: Define xprt_server_backchannel()[ [nfsd41: sunrpc: remove bc_close and bc_init_auto_disconnect dummy functions] [nfsd41: sunrpc: eliminate unneeded switch statement in xs_setup_tcp()] [nfsd41: sunrpc: Don't auto close the server backchannel connection] [nfsd41: sunrpc: Remove unused functions] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfsd41: change bc_sock to bc_xprt] [nfsd41: sunrpc: move struct rpc_buffer def into a common header file] [nfsd41: sunrpc: use rpc_sleep in bc_send_request so not to block on mutex] [removed cosmetic changes] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [sunrpc: add new xprt class for nfsv4.1 backchannel] [sunrpc: v2.1 change handling of auto_close and init_auto_disconnect operations for the nfsv4.1 backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> [reverted more cosmetic leftovers] [got rid of xprt_server_backchannel] [separated "nfsd41: sunrpc: add new xprt class for nfsv4.1 backchannel"] Signed-off-by: Benny Halevy <bhalevy@panasas.com> Cc: Trond Myklebust <trond.myklebust@netapp.com> [sunrpc: change idle timeout value for the backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Acked-by: Trond Myklebust <trond.myklebust@netapp.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-09-10 21:32:28 +07:00
struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */
#if defined(CONFIG_NFS_V4_1)
struct svc_serv *bc_serv; /* The RPC service which will */
/* process the callback */
nfs41: New backchannel helper routines This patch introduces support to setup the callback xprt on the client side. It allocates/ destroys the preallocated memory structures used to process backchannel requests. At setup time, xprt_setup_backchannel() is invoked to allocate one or more rpc_rqst structures and substructures. This ensures that they are available when an RPC callback arrives. The rpc_rqst structures are maintained in a linked list attached to the rpc_xprt structure. We keep track of the number of allocations so that they can be correctly removed when the channel is destroyed. When an RPC callback arrives, xprt_alloc_bc_request() is invoked to obtain a preallocated rpc_rqst structure. An rpc_xprt structure is returned, and its RPC_BC_PREALLOC_IN_USE bit is set in rpc_xprt->bc_flags. The structure is removed from the the list since it is now in use, and it will be later added back when its user is done with it. After the RPC callback replies, the rpc_rqst structure is returned by invoking xprt_free_bc_request(). This clears the RPC_BC_PREALLOC_IN_USE bit and adds it back to the list, allowing it to be reused by a subsequent RPC callback request. To be consistent with the reception of RPC messages, the backchannel requests should be placed into the 'struct rpc_rqst' rq_rcv_buf, which is then in turn copied to the 'struct rpc_rqst' rq_private_buf. [nfs41: Preallocate rpc_rqst receive buffer for handling callbacks] Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [Update copyright notice and explain page allocation] Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com>
2009-04-01 20:23:00 +07:00
unsigned int bc_alloc_count; /* Total number of preallocs */
spinlock_t bc_pa_lock; /* Protects the preallocated
* items */
struct list_head bc_pa_list; /* List of preallocated
* backchannel rpc_rqst's */
#endif /* CONFIG_NFS_V4_1 */
struct list_head recv;
struct {
unsigned long bind_count, /* total number of binds */
connect_count, /* total number of connects */
connect_start, /* connect start timestamp */
connect_time, /* jiffies waiting for connect */
sends, /* how many complete requests */
recvs, /* how many complete requests */
bad_xids; /* lookup_rqst didn't find XID */
unsigned long long req_u, /* average requests on the wire */
bklog_u; /* backlog queue utilization */
} stat;
const char *address_strings[RPC_DISPLAY_MAX];
};
#if defined(CONFIG_NFS_V4_1)
/*
* Backchannel flags
*/
#define RPC_BC_PA_IN_USE 0x0001 /* Preallocated backchannel */
/* buffer in use */
#endif /* CONFIG_NFS_V4_1 */
nfs41: Add backchannel processing support to RPC state machine Adds rpc_run_bc_task() which is called by the NFS callback service to process backchannel requests. It performs similar work to rpc_run_task() though "schedules" the backchannel task to be executed starting at the call_trasmit state in the RPC state machine. It also introduces some miscellaneous updates to the argument validation, call_transmit, and transport cleanup functions to take into account that there are now forechannel and backchannel tasks. Backchannel requests do not carry an RPC message structure, since the payload has already been XDR encoded using the existing NFSv4 callback mechanism. Introduce a new transmit state for the client to reply on to backchannel requests. This new state simply reserves the transport and issues the reply. In case of a connection related error, disconnects the transport and drops the reply. It requires the forechannel to re-establish the connection and the server to retransmit the request, as stated in NFSv4.1 section 2.9.2 "Client and Server Transport Behavior". Note: There is no need to loop attempting to reserve the transport. If EAGAIN is returned by xprt_prepare_transmit(), return with tk_status == 0, setting tk_action to call_bc_transmit. rpc_execute() will invoke it again after the task is taken off the sleep queue. [nfs41: rpc_run_bc_task() need not be exported outside RPC module] [nfs41: New call_bc_transmit RPC state] Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfs41: Backchannel: No need to loop in call_bc_transmit()] Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [rpc_count_iostats incorrectly exits early] Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [Convert rpc_reply_expected() to inline function] [Remove unnecessary BUG_ON()] [Rename variable] Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com>
2009-04-01 20:23:03 +07:00
#if defined(CONFIG_NFS_V4_1)
static inline int bc_prealloc(struct rpc_rqst *req)
{
return test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state);
}
#else
static inline int bc_prealloc(struct rpc_rqst *req)
{
return 0;
}
#endif /* CONFIG_NFS_V4_1 */
struct xprt_create {
int ident; /* XPRT_TRANSPORT identifier */
struct sockaddr * srcaddr; /* optional local address */
struct sockaddr * dstaddr; /* remote peer address */
size_t addrlen;
struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */
};
struct xprt_class {
struct list_head list;
int ident; /* XPRT_TRANSPORT identifier */
struct rpc_xprt * (*setup)(struct xprt_create *);
struct module *owner;
char name[32];
};
/*
* Generic internal transport functions
*/
struct rpc_xprt *xprt_create_transport(struct xprt_create *args);
void xprt_connect(struct rpc_task *task);
void xprt_reserve(struct rpc_task *task);
int xprt_reserve_xprt(struct rpc_task *task);
int xprt_reserve_xprt_cong(struct rpc_task *task);
int xprt_prepare_transmit(struct rpc_task *task);
void xprt_transmit(struct rpc_task *task);
void xprt_end_transmit(struct rpc_task *task);
int xprt_adjust_timeout(struct rpc_rqst *req);
void xprt_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task);
void xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task);
void xprt_release(struct rpc_task *task);
struct rpc_xprt * xprt_get(struct rpc_xprt *xprt);
void xprt_put(struct rpc_xprt *xprt);
static inline __be32 *xprt_skip_transport_header(struct rpc_xprt *xprt, __be32 *p)
{
return p + xprt->tsh_size;
}
/*
* Transport switch helper functions
*/
int xprt_register_transport(struct xprt_class *type);
int xprt_unregister_transport(struct xprt_class *type);
int xprt_load_transport(const char *);
void xprt_set_retrans_timeout_def(struct rpc_task *task);
void xprt_set_retrans_timeout_rtt(struct rpc_task *task);
void xprt_wake_pending_tasks(struct rpc_xprt *xprt, int status);
void xprt_wait_for_buffer_space(struct rpc_task *task, rpc_action action);
void xprt_write_space(struct rpc_xprt *xprt);
void xprt_adjust_cwnd(struct rpc_task *task, int result);
struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid);
void xprt_complete_rqst(struct rpc_task *task, int copied);
void xprt_release_rqst_cong(struct rpc_task *task);
void xprt_disconnect_done(struct rpc_xprt *xprt);
void xprt_force_disconnect(struct rpc_xprt *xprt);
void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie);
/*
* Reserved bit positions in xprt->state
*/
#define XPRT_LOCKED (0)
#define XPRT_CONNECTED (1)
#define XPRT_CONNECTING (2)
#define XPRT_CLOSE_WAIT (3)
#define XPRT_BOUND (4)
#define XPRT_BINDING (5)
#define XPRT_CLOSING (6)
#define XPRT_CONNECTION_ABORT (7)
#define XPRT_CONNECTION_CLOSE (8)
static inline void xprt_set_connected(struct rpc_xprt *xprt)
{
set_bit(XPRT_CONNECTED, &xprt->state);
}
static inline void xprt_clear_connected(struct rpc_xprt *xprt)
{
clear_bit(XPRT_CONNECTED, &xprt->state);
}
static inline int xprt_connected(struct rpc_xprt *xprt)
{
return test_bit(XPRT_CONNECTED, &xprt->state);
}
static inline int xprt_test_and_set_connected(struct rpc_xprt *xprt)
{
return test_and_set_bit(XPRT_CONNECTED, &xprt->state);
}
static inline int xprt_test_and_clear_connected(struct rpc_xprt *xprt)
{
return test_and_clear_bit(XPRT_CONNECTED, &xprt->state);
}
static inline void xprt_clear_connecting(struct rpc_xprt *xprt)
{
smp_mb__before_clear_bit();
clear_bit(XPRT_CONNECTING, &xprt->state);
smp_mb__after_clear_bit();
}
static inline int xprt_connecting(struct rpc_xprt *xprt)
{
return test_bit(XPRT_CONNECTING, &xprt->state);
}
static inline int xprt_test_and_set_connecting(struct rpc_xprt *xprt)
{
return test_and_set_bit(XPRT_CONNECTING, &xprt->state);
}
static inline void xprt_set_bound(struct rpc_xprt *xprt)
{
test_and_set_bit(XPRT_BOUND, &xprt->state);
}
static inline int xprt_bound(struct rpc_xprt *xprt)
{
return test_bit(XPRT_BOUND, &xprt->state);
}
static inline void xprt_clear_bound(struct rpc_xprt *xprt)
{
clear_bit(XPRT_BOUND, &xprt->state);
}
static inline void xprt_clear_binding(struct rpc_xprt *xprt)
{
smp_mb__before_clear_bit();
clear_bit(XPRT_BINDING, &xprt->state);
smp_mb__after_clear_bit();
}
static inline int xprt_test_and_set_binding(struct rpc_xprt *xprt)
{
return test_and_set_bit(XPRT_BINDING, &xprt->state);
}
#endif /* __KERNEL__*/
#endif /* _LINUX_SUNRPC_XPRT_H */