nfsd41 server backchannel for 2.6.31 (try 3)
Subsystems (3)
cover nfsd41 server backchannel for 2.6.31 (try 3)
Bruce, Trond,
The following patch set addresses your comments on the server v4.1 backchannel RPC functionality previously submitted. It also addresses Benny's comments on the implementation of the async RPC v4.1 callbacks. Please consider for 2.6.31.
[RFC 01/11] nfsd41: Backchannel: cleanup nfs4.0 callback encode routines [RFC 02/11] nfsd41: Backchannel: minorversion support for the back channel
[RFC 03/11] nfsd41: sunrpc: svc_tcp_recv_record()
[RFC 04/11] nfsd41: sunrpc: Added rpc server-side backchannel handling [RFC 05/11] nfsd41: Backchannel: callback infrastructure [RFC 06/11] nfsd41: Backchannel: Add sequence arguments to callback RPC arguments
[RFC 07/11] nfsd41: Backchannel: Server backchannel RPC wait queue [RFC 08/11] nfsd41: Backchannel: Setup sequence information [RFC 09/11] nfsd41: Backchannel: cb_sequence callback
[RFC 10/11] nfsd41: Backchannel: Implement cb_recall over NFSv4.1 [RFC 11/11] nfsd41: Refactor create_client()
As requested, this patch set squashes the following patches recently submitted to the pnfs list by Alexandros, Benny, and myself.
nfsd41: sunrpc: Remove unused functions
nfsd41: sunrpc: Don't auto close the server backchannel connection
nfsd41: sunrpc: eliminate unneeded switch statement in xs_setup_tcp()
nfsd41: sunrpc: remove bc_close and bc_init_auto_disconnect dummy fun
nfsd41: sunrpc: Define xprt_server_backchannel()
nfsd41: sunrpc: create common send routine for the fore and the back
nfsd41: sunrpc: remove bc_connect_worker()
nfsd41: sunrpc: Document server backchannel locking
nfsd41: sunrpc: Use free_page() to free server backchannel pages
nfsd41: sunrpc: New svc_process_calldir()
nfsd41: sunrpc: svc_tcp_recv_record()
nfsd41: decode_cb_sequence does not need to actually decode ignored fields
Thanks,
- ricardo
A message that is not in the archive (sent off-list or not yet received): 273FE88A07F5D445824060902F7003440612BB9D-hX7t0kiaRRpT+ZUat5FNkAK/[email protected]
RFC 1/11 nfsd41: Backchannel: cleanup nfs4.0 callback encode routines
From: Andy Adamson <[email protected]>
Mimic the client and prepare to share the back channel xdr with NFSv4.1. Bump the number of operations in each encode routine, then backfill the number of operations.
--- fs/nfsd/nfs4callback.c | 24 ++++++++++++++++-------- 1 files changed, 16 insertions(+), 8 deletions(-)
fs/nfsd/nfs4callback.c +16 -8
@@ -140,8 +140,9 @@ struct nfs4_cb_compound_hdr {int status;u32 ident;u32 nops; +__be32 *nops_p;u32 taglen; -char * tag; +char *tag; }; static struct {
@@ -201,7 +202,7 @@ nfs_cb_stat_to_errno(int stat)* XDR encode */ -static int +static void encode_cb_compound_hdr (struct xdr_stream *xdr,struct nfs4_cb_compound_hdr *hdr) {__be32 * p;
@@ -210,12 +211,18 @@ encode_cb_compound_hdr(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr)WRITE32 (0 );/* tag length is always 0 */ WRITE32 (NFS4_MINOR_VERSION );WRITE32 (hdr->ident); + hdr->nops_p = p;WRITE32 (hdr->nops); -return 0 ; } -static int -encode_cb_recall (struct xdr_stream *xdr,struct nfs4_delegation *dp) +static void encode_cb_nops (struct nfs4_cb_compound_hdr *hdr) +{ + *hdr->nops_p =htonl (hdr->nops); +} + +static void +encode_cb_recall (struct xdr_stream *xdr,struct nfs4_delegation *dp, +struct nfs4_cb_compound_hdr *hdr) {__be32 *p;int len = dp->dl_fh.fh_size;
@@ -227,7 +234,7 @@ encode_cb_recall(struct xdr_stream *xdr, struct nfs4_delegation *dp)WRITE32 (0 );/* truncate optimization not implemented */ WRITE32 (len);WRITEMEM (&dp->dl_fh.fh_base, len); -return 0 ; + hdr->nops++; } static int
@@ -246,12 +253,13 @@ nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, __be32 *p, struct nfs4_delegation *struct xdr_stream xdr;struct nfs4_cb_compound_hdr hdr = { .ident = args->dl_ident, - .nops =1 , };xdr_init_encode (&xdr, &req->rq_snd_buf, p);encode_cb_compound_hdr (&xdr, &hdr); -return (encode_cb_recall (&xdr, args)); +encode_cb_recall (&xdr, args, &hdr); +encode_cb_nops (&hdr); +return 0 ; }
Signature · 1 line
1.5.4.3
RFC 2/11 nfsd41: Backchannel: minorversion support for the back channel
From: Andy Adamson <[email protected]>
Prepare to share backchannel code with NFSv4.1.
--- fs/nfsd/nfs4callback.c | 3 ++- fs/nfsd/nfs4state.c | 1 + include/linux/nfsd/state.h | 3 ++- 3 files changed, 5 insertions(+), 2 deletions(-)
fs/nfsd/nfs4callback.c +2 -1
@@ -141,6 +141,7 @@ struct nfs4_cb_compound_hdr {u32 ident;u32 nops;__be32 *nops_p; +u32 minorversion;u32 taglen;char *tag; };
@@ -209,7 +210,7 @@ encode_cb_compound_hdr(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr)RESERVE_SPACE (16 );WRITE32 (0 );/* tag length is always 0 */ -WRITE32 (NFS4_MINOR_VERSION ); +WRITE32 (hdr->minorversion);WRITE32 (hdr->ident); hdr->nops_p = p;WRITE32 (hdr->nops);
fs/nfsd/nfs4state.c +1 -0
@@ -978,6 +978,7 @@ gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se)if ( !(parse_ipv4 (se->se_callback_addr_len, se->se_callback_addr_val, &cb->cb_addr, &cb->cb_port))) goto out_err; + cb->cb_minorversion =0 ; cb->cb_prog = se->se_callback_prog; cb->cb_ident = se->se_callback_ident;return ;
include/linux/nfsd/state.h +2 -1
@@ -85,7 +85,8 @@ struct nfs4_cb_conn {u32 cb_addr;unsigned short cb_port;u32 cb_prog; -u32 cb_ident; +u32 cb_minorversion; +u32 cb_ident;/* minorversion 0 only */ /* RPC client info */ atomic_t cb_set;/* successful CB_NULL call */ struct rpc_clnt * cb_client;
Signature · 1 line
1.5.4.3
RFC 3/11 nfsd41: sunrpc: svc_tcp_recv_record()
From: Alexandros Batsakis <[email protected]>
Factor functionality out of svc_tcp_recvfrom() to simplify routine
--- net/sunrpc/svcsock.c | 79 ++++++++++++++++++++++++++++++++----------------- 1 files changed, 51 insertions(+), 28 deletions(-)
net/sunrpc/svcsock.c +51 -28
@@ -815,28 +815,18 @@ failed: }/* -* Receive data from a TCP socket. +* Receive data. +* If we haven't gotten the record length yet, get the next four bytes. +* Otherwise try to gobble up as much as possible up to the complete +* record length. */ -static int svc_tcp_recvfrom (struct svc_rqst *rqstp) +static int svc_tcp_recv_record (struct svc_sock *svsk,struct svc_rqst *rqstp) { -struct svc_sock *svsk = - container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);struct svc_serv *serv = svsk->sk_xprt.xpt_server; -int len; -struct kvec *vec; -int pnum, vlen; - -dprintk ("svc: tcp_recv %p data %d conn %d close %d\n" , - svsk,test_bit (XPT_DATA , &svsk->sk_xprt.xpt_flags), -test_bit (XPT_CONN , &svsk->sk_xprt.xpt_flags), -test_bit (XPT_CLOSE , &svsk->sk_xprt.xpt_flags)); +int len;clear_bit (XPT_DATA , &svsk->sk_xprt.xpt_flags); -/* Receive data. If we haven't got the record length yet, get -* the next four bytes. Otherwise try to gobble up as much as -* possible up to the complete record length. -*/ if (svsk->sk_tcplen <sizeof (rpc_fraghdr)) {int want =sizeof (rpc_fraghdr) - svsk->sk_tcplen;struct kvec iov;
@@ -851,7 +841,7 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)dprintk ("svc: short recvfrom while reading record " "length (%d of %d)\n" , len, want);svc_xprt_received (&svsk->sk_xprt); -return -EAGAIN ;/* record header not complete */ + goto err_again;/* record header not complete */ } svsk->sk_reclen =ntohl (svsk->sk_reclen);
@@ -866,6 +856,7 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) "per record not supported\n"); goto err_delete; } + svsk->sk_reclen &=RPC_FRAGMENT_SIZE_MASK ;dprintk ("svc: TCP record, %d bytes\n" , svsk->sk_reclen);if (svsk->sk_reclen > serv->sv_max_mesg) {
@@ -886,11 +877,45 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)dprintk ("svc: incomplete TCP record (%d of %d)\n" , len, svsk->sk_reclen);svc_xprt_received (&svsk->sk_xprt); -return -EAGAIN ;/* record not complete */ + goto err_again;/* record not complete */ } len = svsk->sk_reclen;set_bit (XPT_DATA , &svsk->sk_xprt.xpt_flags); +return len; + error: +if (len == -EAGAIN ) { +dprintk ("RPC: TCP recv_record got EAGAIN\n" ); +svc_xprt_received (&svsk->sk_xprt); + } +return len; + err_delete: +set_bit (XPT_CLOSE , &svsk->sk_xprt.xpt_flags); + err_again: +return -EAGAIN ; +} + +/* +* Receive data from a TCP socket. +*/ +static int svc_tcp_recvfrom (struct svc_rqst *rqstp) +{ +struct svc_sock *svsk = + container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt); +struct svc_serv *serv = svsk->sk_xprt.xpt_server; +int len; +struct kvec *vec; +int pnum, vlen; + +dprintk ("svc: tcp_recv %p data %d conn %d close %d\n" , + svsk,test_bit (XPT_DATA , &svsk->sk_xprt.xpt_flags), +test_bit (XPT_CONN , &svsk->sk_xprt.xpt_flags), +test_bit (XPT_CLOSE , &svsk->sk_xprt.xpt_flags)); + + len =svc_tcp_recv_record (svsk, rqstp); +if (len <0 ) + goto error; + vec = rqstp->rq_vec; vec[0 ] = rqstp->rq_arg.head[0 ]; vlen =PAGE_SIZE ;
@@ -906,7 +931,7 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)/* Now receive data */ len =svc_recvfrom (rqstp, vec, pnum, len);if (len <0 ) - goto error; + goto err_again;dprintk ("svc: TCP complete record (%d bytes)\n" , len); rqstp->rq_arg.len = len;
@@ -932,21 +957,19 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)return len; - err_delete: -set_bit (XPT_CLOSE , &svsk->sk_xprt.xpt_flags); -return -EAGAIN ; - - error: +err_again:if (len == -EAGAIN ) {dprintk ("RPC: TCP recvfrom got EAGAIN\n" );svc_xprt_received (&svsk->sk_xprt); - }else { +return len; + } +error: +if (len != -EAGAIN ) {printk (KERN_NOTICE "%s: recvfrom returned errno %d\n" , svsk->sk_xprt.xpt_server->sv_name, -len); - goto err_delete; +set_bit (XPT_CLOSE , &svsk->sk_xprt.xpt_flags); } - -return len; +return -EAGAIN ; }/*
Signature · 1 line
1.5.4.3
RFC 4/11 nfsd41: sunrpc: Added rpc server-side backchannel handling
From: Rahul Iyer <[email protected]>
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.
[nfsd41: sunrpc: Define xprt_server_backchannel()[
--- include/linux/sunrpc/clnt.h | 1 + include/linux/sunrpc/svcsock.h | 1 + include/linux/sunrpc/xprt.h | 7 ++ net/sunrpc/clnt.c | 1 + net/sunrpc/sunrpc.h | 35 +++++++ net/sunrpc/svcsock.c | 172 +++++++++++++++++++++++++++------- net/sunrpc/xprt.c | 16 +++- net/sunrpc/xprtsock.c | 201 ++++++++++++++++++++++++++++++++++++++-- 8 files changed, 390 insertions(+), 44 deletions(-) create mode 100644 net/sunrpc/sunrpc.h
include/linux/sunrpc/clnt.h +1 -0
@@ -110,6 +110,7 @@ struct rpc_create_args {rpc_authflavor_t authflavor;unsigned long flags;char *client_name; +struct svc_sock *bc_sock;/* NFSv4.1 backchannel */ };/* Values for "flags" field */
include/linux/sunrpc/svcsock.h +1 -0
@@ -28,6 +28,7 @@ struct svc_sock {/* private TCP part */ u32 sk_reclen;/* length of record */ u32 sk_tcplen;/* current read length */ +struct rpc_xprt *sk_bc_xprt;/* NFSv4.1 backchannel xprt */ };/*
include/linux/sunrpc/xprt.h +7 -0
@@ -174,6 +174,7 @@ struct rpc_xprt {spinlock_t reserve_lock;/* lock slot table */ u32 xid;/* Next XID value to use */ struct rpc_task * snd_task;/* Task blocked in send */ +struct svc_sock *bc_sock;/* NFSv4.1 backchannel */ struct list_head recv;struct {
@@ -197,6 +198,7 @@ struct xprt_create {struct sockaddr * srcaddr;/* optional local address */ struct sockaddr * dstaddr;/* remote peer address */ size_t addrlen; +struct svc_sock *bc_sock;/* NFSv4.1 backchannel */ };struct xprt_class {
@@ -331,6 +333,11 @@ static inline int xprt_test_and_set_binding(struct rpc_xprt *xprt)return test_and_set_bit (XPRT_BINDING , &xprt->state); } +static inline int xprt_server_backchannel (struct rpc_xprt *xprt) +{ +return xprt->bc_sock !=NULL ; +} +#endif /* __KERNEL__*/ #endif /* _LINUX_SUNRPC_XPRT_H */
net/sunrpc/clnt.c +1 -0
@@ -266,6 +266,7 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) .srcaddr = args->saddress, .dstaddr = args->address, .addrlen = args->addrsize, + .bc_sock = args->bc_sock, };char servername[48 ];
net/sunrpc/sunrpc.h new file +35 -0
@@ -0,0 +1,35 @@ +/****************************************************************************** + +(c) 2008 NetApp. All Rights Reserved. + +NetApp provides this source code under the GPL v2 License. +The GPL v2 license is available at +http://opensource.org/licenses/gpl-license.php. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR +CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, +EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, +PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR +PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF +LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING +NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS +SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +******************************************************************************/ + +/* +* Functions and macros used internally by RPC +*/ + +#ifndef _NET_SUNRPC_SUNRPC_H +#define _NET_SUNRPC_SUNRPC_H + +int svc_send_common (struct socket *sock,struct xdr_buf *xdr, +struct page *headpage,unsigned long headoffset, +struct page *tailpage,unsigned long tailoffset); + +#endif /* _NET_SUNRPC_SUNRPC_H */ +
net/sunrpc/svcsock.c +137 -35
241 lines not on this page · raw message
net/sunrpc/xprt.c +15 -1
@@ -596,6 +596,9 @@ static void xprt_autoclose(struct work_struct *work)struct rpc_xprt *xprt = container_of(work, struct rpc_xprt, task_cleanup); +if (xprt_server_backchannel (xprt)) +return ; + xprt->ops->close (xprt);clear_bit (XPRT_CLOSE_WAIT , &xprt->state);xprt_release_write (xprt,NULL );
@@ -666,6 +669,9 @@ xprt_init_autodisconnect(unsigned long data) {struct rpc_xprt *xprt = (struct rpc_xprt *)data; +if (xprt_server_backchannel (xprt)) +return ; +spin_lock (&xprt->transport_lock);if (!list_empty (&xprt->recv) || xprt->shutdown) goto out_abort;
@@ -1053,7 +1059,8 @@ found:INIT_LIST_HEAD (&xprt->recv);INIT_WORK (&xprt->task_cleanup, xprt_autoclose);setup_timer (&xprt->timer, xprt_init_autodisconnect, - (unsigned long )xprt); + (unsigned long )xprt); + xprt->last_used = jiffies; xprt->cwnd =RPC_INITCWND ; xprt->bind_index =0 ;
@@ -1073,6 +1080,13 @@ found:dprintk ("RPC: created transport %p with %u slots\n" , xprt, xprt->max_reqs); +/* +* Since we don't want connections for the backchannel, we set +* the xprt status to connected +*/ +if (args->bc_sock) +xprt_set_connected (xprt); +return xprt; }
net/sunrpc/xprtsock.c +193 -8
251 lines not on this page · raw message
Signature · 1 line
1.5.4.3
RFC 5/11 nfsd41: Backchannel: callback infrastructure
From: Andy Adamson <[email protected]>
Keep the xprt used for create_session in cl_cb_xprt. Mark cl_callback.cb_minorversion = 1 and remember the client provided cl_callback.cb_prog rpc program number. Use it to probe the callback path.
Define xdr sizes and code nfs4_cb_compound header to be able to send a null callback rpc.
--- fs/nfsd/nfs4callback.c | 27 ++++++++++++++++++++++++--- fs/nfsd/nfs4state.c | 11 +++++++++++ 2 files changed, 35 insertions(+), 3 deletions(-)
fs/nfsd/nfs4callback.c +24 -3
@@ -43,6 +43,7 @@#include <linux/sunrpc/xdr.h> #include <linux/sunrpc/svc.h> #include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/svcsock.h> #include <linux/nfsd/nfsd.h> #include <linux/nfsd/state.h> #include <linux/sunrpc/sched.h>
@@ -52,16 +53,19 @@#define NFSPROC4_CB_NULL 0#define NFSPROC4_CB_COMPOUND 1 +#define NFS4_STATEID_SIZE 16/* Index of predefined Linux callback client operations */ enum { -NFSPROC4_CLNT_CB_NULL =0 , +NFSPROC4_CLNT_CB_NULL =0 ,NFSPROC4_CLNT_CB_RECALL , +NFSPROC4_CLNT_CB_SEQUENCE , };enum nfs_cb_opnum4 {OP_CB_RECALL =4 , +OP_CB_SEQUENCE =11 , };#define NFS4_MAXTAGLEN 20
@@ -70,15 +74,22 @@ enum nfs_cb_opnum4 {#define NFS4_dec_cb_null_sz 0#define cb_compound_enc_hdr_sz 4#define cb_compound_dec_hdr_sz (3 + (NFS4_MAXTAGLEN >> 2)) +#define sessionid_sz (NFS4_MAX_SESSIONID_LEN >> 2) +#define cb_sequence_enc_sz (sessionid_sz + 4 + \ + 1 /* no referring calls list yet */) +#define cb_sequence_dec_sz (op_dec_sz + sessionid_sz + 4) +#define op_enc_sz 1#define op_dec_sz 2#define enc_nfs4_fh_sz (1 + (NFS4_FHSIZE >> 2))#define enc_stateid_sz (NFS4_STATEID_SIZE >> 2)#define NFS4_enc_cb_recall_sz (cb_compound_enc_hdr_sz + \ + cb_sequence_enc_sz + \ 1 + enc_stateid_sz + \ enc_nfs4_fh_sz)#define NFS4_dec_cb_recall_sz (cb_compound_dec_hdr_sz + \ + cb_sequence_dec_sz + \ op_dec_sz)/*
@@ -137,11 +148,13 @@ xdr_error: \ }while (0 ) struct nfs4_cb_compound_hdr { -int status; -u32 ident; +/* args */ +u32 ident;/* minorversion 0 only */ u32 nops;__be32 *nops_p;u32 minorversion; +/* res */ +int status;u32 taglen;char *tag; };
@@ -405,6 +418,14 @@ int setup_callback_client(struct nfs4_client *clp) addr.sin_family =AF_INET ; addr.sin_port =htons (cb->cb_port); addr.sin_addr.s_addr =htonl (cb->cb_addr); +if (cb->cb_minorversion) { + args.bc_sock = container_of(clp->cl_cb_xprt, struct svc_sock, + sk_xprt); + } + +dprintk ("%s: program %s 0x%x nrvers %u version %u minorversion %u\n" , + __func__, args.program->name, args.prognumber, + args.program->nrvers, args.version, cb->cb_minorversion);/* Create RPC client */ client =rpc_create (&args);
fs/nfsd/nfs4state.c +11 -0
@@ -653,6 +653,8 @@ free_client(struct nfs4_client *clp)shutdown_callback_client (clp);nfsd4_release_respages (clp->cl_slot.sl_cache_entry.ce_respages, clp->cl_slot.sl_cache_entry.ce_resused); +if (clp->cl_cb_xprt) +svc_xprt_put (clp->cl_cb_xprt);if (clp->cl_cred.cr_group_info)put_group_info (clp->cl_cred.cr_group_info);kfree (clp->cl_principal);
@@ -1396,6 +1398,15 @@ nfsd4_create_session(struct svc_rqst *rqstp, cr_ses->flags &= ~SESSION4_PERSIST ; cr_ses->flags &= ~SESSION4_RDMA ; +if (cr_ses->flags &SESSION4_BACK_CHAN ) { + unconf->cl_cb_xprt = rqstp->rq_xprt; +svc_xprt_get (unconf->cl_cb_xprt); + unconf->cl_cb_conn.cb_minorversion = + cstate->minorversion; + unconf->cl_cb_conn.cb_prog = cr_ses->callback_prog; + unconf->cl_cb_seq_nr =1 ; +nfsd4_probe_callback (unconf); + } conf = unconf; }else { status = nfserr_stale_clientid;
Signature · 1 line
1.5.4.3
RFC 6/11 nfsd41: Backchannel: Add sequence arguments to callback RPC arguments
Follow the model we use in the client. Make the sequence arguments part of the regular RPC arguments. None of the callbacks that are soon to be implemented expect results that need to be passed back to the caller, so we don't define a separate RPC results structure. For session validation, the cb_sequence decoding will use a pointer to the sequence arguments that are part of the RPC argument.
--- fs/nfsd/nfs4callback.c | 5 +++++ include/linux/nfsd/state.h | 9 +++++++++ 2 files changed, 14 insertions(+), 0 deletions(-)
fs/nfsd/nfs4callback.c +5 -0
@@ -92,6 +92,11 @@ enum nfs_cb_opnum4 { cb_sequence_dec_sz + \ op_dec_sz) +struct nfs4_rpc_args { +void *args_op; +struct nfsd4_cb_sequence args_seq; +}; +/* * Generic encode routines from fs/nfs/nfs4xdr.c */
include/linux/nfsd/state.h +9 -0
@@ -61,6 +61,12 @@ typedef struct {#define si_stateownerid si_opaque.so_stateownerid#define si_fileid si_opaque.so_fileid +struct nfsd4_cb_sequence { +/* args/res */ +u32 cbs_minorversion; +struct nfs4_client *cbs_clp; +}; +struct nfs4_delegation {struct list_head dl_perfile;struct list_head dl_perclnt;
@@ -188,6 +194,9 @@ struct nfs4_client {struct nfsd4_slot cl_slot;/* create_session slot */ u32 cl_exchange_flags;struct nfs4_sessionid cl_sessionid; + +/* for nfs41 callbacks */ +struct svc_xprt *cl_cb_xprt;/* 4.1 callback transport */ };/* struct nfs4_client_reset
Signature · 1 line
1.5.4.3
RFC 7/11 nfsd41: Backchannel: Server backchannel RPC wait queue
RPC callback requests will wait on this wait queue if the backchannel is out of slots.
--- fs/nfsd/nfs4state.c | 2 ++ include/linux/nfsd/state.h | 4 ++++ 2 files changed, 6 insertions(+), 0 deletions(-)
fs/nfsd/nfs4state.c +2 -0
@@ -726,6 +726,8 @@ static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir)INIT_LIST_HEAD (&clp->cl_delegations);INIT_LIST_HEAD (&clp->cl_sessions);INIT_LIST_HEAD (&clp->cl_lru); +clear_bit (0 , &clp->cl_cb_slot_busy); +rpc_init_wait_queue (&clp->cl_cb_waitq,"Backchannel slot table" );return clp; }
include/linux/nfsd/state.h +4 -0
@@ -196,7 +196,11 @@ struct nfs4_client {struct nfs4_sessionid cl_sessionid;/* for nfs41 callbacks */ +/* We currently support a single back channel with a single slot */ +unsigned long cl_cb_slot_busy;struct svc_xprt *cl_cb_xprt;/* 4.1 callback transport */ +struct rpc_wait_queue cl_cb_waitq;/* backchannel callers may */ +/* wait here for slots */ };/* struct nfs4_client_reset
Signature · 1 line
1.5.4.3
RFC 8/11 nfsd41: Backchannel: Setup sequence information
Follows the model used by the NFS client. Setup the RPC prepare and done function pointers so that we can populate the sequence information if minorversion == 1. rpc_run_task() is then invoked directly just like existing NFS client operations do.
nfsd4_cb_prepare() determines if the sequence information needs to be setup. If the slot is in use, it adds itself to the wait queue.
nfsd4_cb_done() wakes anyone sleeping on the callback channel wait queue after our RPC reply has been received. It also sets the task message result pointer to NULL to clearly indicate we're done using it.
--- fs/nfsd/nfs4callback.c | 83 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/nfsd/state.h | 1 + 2 files changed, 84 insertions(+), 0 deletions(-)
fs/nfsd/nfs4callback.c +83 -0
@@ -529,6 +529,88 @@ nfsd4_probe_callback(struct nfs4_client *clp)do_probe_callback (clp); } +/* +* There's currently a single callback channel slot. +* If the slot is available, then mark it busy. Otherwise, set the +* thread for sleeping on the callback RPC wait queue. +*/ +static int nfsd41_cb_setup_sequence (struct nfs4_client *clp, +struct rpc_task *task) +{ +struct nfs4_rpc_args *args = task->tk_msg.rpc_argp; +u32 *ptr = (u32 *)clp->cl_sessionid.data; +int status =0 ; + +dprintk ("%s: %u:%u:%u:%u\n" , __func__, + ptr[0 ], ptr[1 ], ptr[2 ], ptr[3 ]); + +if (test_and_set_bit (0 , &clp->cl_cb_slot_busy) !=0 ) { +rpc_sleep_on (&clp->cl_cb_waitq, task,NULL ); +dprintk ("%s slot is busy\n" , __func__); + status = -EAGAIN ; + goto out; + } + +/* +* We'll need the clp during XDR encoding and decoding, +* and the sequence during decoding to verify the reply +*/ + args->args_seq.cbs_clp = clp; + task->tk_msg.rpc_resp = &args->args_seq; + +out: +dprintk ("%s status=%d\n" , __func__, status); +return status; +} + +/* +* TODO: cb_sequence should support referring call lists, cachethis, multiple +* slots, and mark callback channel down on communication errors. +*/ +static void nfsd4_cb_prepare (struct rpc_task *task,void *calldata) +{ +struct nfs4_delegation *dp = calldata; +struct nfs4_client *clp = dp->dl_client; +struct nfs4_rpc_args *args = task->tk_msg.rpc_argp; +u32 minorversion = clp->cl_cb_conn.cb_minorversion; +int status =0 ; + + args->args_seq.cbs_minorversion = minorversion; +if (minorversion) { + status =nfsd41_cb_setup_sequence (clp, task); +if (status) { +if (status != -EAGAIN ) { +/* terminate rpc task */ + task->tk_status = status; + task->tk_action =NULL ; + } +return ; + } + } +rpc_call_start (task); +} + +static void nfsd4_cb_done (struct rpc_task *task,void *calldata) +{ +struct nfs4_delegation *dp = calldata; +struct nfs4_client *clp = dp->dl_client; + +dprintk ("%s: minorversion=%d\n" , __func__, + clp->cl_cb_conn.cb_minorversion); + +if (clp->cl_cb_conn.cb_minorversion) { +/* No need for lock, access serialized in nfsd4_cb_prepare */ + ++clp->cl_cb_seq_nr; +clear_bit (0 , &clp->cl_cb_slot_busy); +rpc_wake_up_next (&clp->cl_cb_waitq); +dprintk ("%s: freed slot, new seqid=%d\n" , __func__, + clp->cl_cb_seq_nr); + +/* We're done looking into the sequence information */ + task->tk_msg.rpc_resp =NULL ; + } +} +static void nfsd4_cb_recall_done (struct rpc_task *task,void *calldata) {struct nfs4_delegation *dp = calldata;
@@ -568,6 +650,7 @@ static void nfsd4_cb_recall_release(void *calldata) }static const struct rpc_call_ops nfsd4_cb_recall_ops = { + .rpc_call_prepare = nfsd4_cb_prepare, .rpc_call_done = nfsd4_cb_recall_done, .rpc_release = nfsd4_cb_recall_release, };
include/linux/nfsd/state.h +1 -0
@@ -198,6 +198,7 @@ struct nfs4_client {/* for nfs41 callbacks */ /* We currently support a single back channel with a single slot */ unsigned long cl_cb_slot_busy; +u32 cl_cb_seq_nr;struct svc_xprt *cl_cb_xprt;/* 4.1 callback transport */ struct rpc_wait_queue cl_cb_waitq;/* backchannel callers may */ /* wait here for slots */
Signature · 1 line
1.5.4.3
RFC 9/11 nfsd41: Backchannel: cb_sequence callback
From: Benny Halevy <[email protected]>
Implement the cb_sequence callback conforming to draft-ietf-nfsv4-minorversion1
Note: highest slot id and target highest slot id do not have to be 0 as was previously implemented. They can be greater than what the nfs server sent if the client supports a larger slot table on the backchannel. At this point we just ignore that.
[nfsd41: fix verification of CB_SEQUENCE highest slot id[
--- fs/nfsd/nfs4callback.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 files changed, 72 insertions(+), 0 deletions(-)
fs/nfsd/nfs4callback.c +72 -0
@@ -256,6 +256,27 @@ encode_cb_recall(struct xdr_stream *xdr, struct nfs4_delegation *dp, hdr->nops++; } +static void +encode_cb_sequence (struct xdr_stream *xdr,struct nfsd4_cb_sequence *args, +struct nfs4_cb_compound_hdr *hdr) +{ +__be32 *p; + +if (hdr->minorversion ==0 ) +return ; + +RESERVE_SPACE (1 +NFS4_MAX_SESSIONID_LEN +20 ); + +WRITE32 (OP_CB_SEQUENCE ); +WRITEMEM (args->cbs_clp->cl_sessionid.data,NFS4_MAX_SESSIONID_LEN ); +WRITE32 (args->cbs_clp->cl_cb_seq_nr); +WRITE32 (0 );/* slotid, always 0 */ +WRITE32 (0 );/* highest slotid always 0 */ +WRITE32 (0 );/* cachethis always 0 */ +WRITE32 (0 );/* FIXME: support referring_call_lists */ + hdr->nops++; +} +static int nfs4_xdr_enc_cb_null (struct rpc_rqst *req,__be32 *p) {
@@ -317,6 +338,57 @@ decode_cb_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)return 0 ; } +/* +* Our current back channel implmentation supports a single backchannel +* with a single slot. +*/ +static int +decode_cb_sequence (struct xdr_stream *xdr,struct nfsd4_cb_sequence *res, +struct rpc_rqst *rqstp) +{ +struct nfs4_sessionid id; +int status; +u32 dummy; +__be32 *p; + +if (res->cbs_minorversion ==0 ) +return 0 ; + + status =decode_cb_op_hdr (xdr,OP_CB_SEQUENCE ); +if (status) +return status; + +/* +* If the server returns different values for sessionID, slotID or +* sequence number, the server is looney tunes. +*/ + status = -ESERVERFAULT ; + +READ_BUF (NFS4_MAX_SESSIONID_LEN +16 ); +memcpy (id.data, p,NFS4_MAX_SESSIONID_LEN ); + p +=XDR_QUADLEN (NFS4_MAX_SESSIONID_LEN ); +if (memcmp (id.data, res->cbs_clp->cl_sessionid.data, +NFS4_MAX_SESSIONID_LEN )) { +dprintk ("%s Invalid session id\n" , __func__); + goto out; + } +READ32 (dummy); +if (dummy != res->cbs_clp->cl_cb_seq_nr) { +dprintk ("%s Invalid sequence number\n" , __func__); + goto out; + } +READ32 (dummy);/* slotid must be 0 */ +if (dummy !=0 ) { +dprintk ("%s Invalid slotid\n" , __func__); + goto out; + } +/* FIXME: process highest slotid and target highest slotid */ + status =0 ; +out: +return status; +} + +static int nfs4_xdr_dec_cb_null (struct rpc_rqst *req,__be32 *p) {
Signature · 1 line
1.5.4.3
RFC 10/11 nfsd41: Backchannel: Implement cb_recall over NFSv4.1
--- fs/nfsd/nfs4callback.c | 31 +++++++++++++++++++++++++++---- 1 files changed, 27 insertions(+), 4 deletions(-)
fs/nfsd/nfs4callback.c +27 -4
@@ -288,15 +288,19 @@ nfs4_xdr_enc_cb_null(struct rpc_rqst *req, __be32 *p) }static int -nfs4_xdr_enc_cb_recall (struct rpc_rqst *req,__be32 *p,struct nfs4_delegation *args) +nfs4_xdr_enc_cb_recall (struct rpc_rqst *req,__be32 *p, +struct nfs4_rpc_args *rpc_args) {struct xdr_stream xdr; +struct nfs4_delegation *args = rpc_args->args_op;struct nfs4_cb_compound_hdr hdr = { .ident = args->dl_ident, + .minorversion = rpc_args->args_seq.cbs_minorversion, };xdr_init_encode (&xdr, &req->rq_snd_buf, p);encode_cb_compound_hdr (&xdr, &hdr); +encode_cb_sequence (&xdr, &rpc_args->args_seq, &hdr);encode_cb_recall (&xdr, args, &hdr);encode_cb_nops (&hdr);return 0 ;
@@ -396,7 +400,8 @@ nfs4_xdr_dec_cb_null(struct rpc_rqst *req, __be32 *p) }static int -nfs4_xdr_dec_cb_recall (struct rpc_rqst *rqstp,__be32 *p) +nfs4_xdr_dec_cb_recall (struct rpc_rqst *rqstp,__be32 *p, +struct nfsd4_cb_sequence *seq) {struct xdr_stream xdr;struct nfs4_cb_compound_hdr hdr;
@@ -406,6 +411,11 @@ nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, __be32 *p) status =decode_cb_compound_hdr (&xdr, &hdr);if (status) goto out; +if (seq) { + status =decode_cb_sequence (&xdr, seq, rqstp); +if (status) + goto out; + } status =decode_cb_op_hdr (&xdr,OP_CB_RECALL ); out:return status;
@@ -688,6 +698,8 @@ static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata)struct nfs4_delegation *dp = calldata;struct nfs4_client *clp = dp->dl_client; +nfsd4_cb_done (task, calldata); +switch (task->tk_status) {case -EIO :/* Network partition? */
@@ -700,16 +712,19 @@ static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata)break ;default :/* success, or error we can't handle */ -return ; + goto done; }if (dp->dl_retries--) {rpc_delay (task,2 *HZ ); task->tk_status =0 ;rpc_restart_call (task); +return ; }else {atomic_set (&clp->cl_cb_conn.cb_set,0 );warn_no_callback_path (clp, task->tk_status); } +done: +kfree (task->tk_msg.rpc_argp); }static void nfsd4_cb_recall_release (void *calldata)
@@ -735,16 +750,24 @@ nfsd4_cb_recall(struct nfs4_delegation *dp) {struct nfs4_client *clp = dp->dl_client;struct rpc_clnt *clnt = clp->cl_cb_conn.cb_client; +struct nfs4_rpc_args *args;struct rpc_message msg = { .rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_RECALL ], - .rpc_argp = dp, .rpc_cred = clp->cl_cb_conn.cb_cred };int status; + args =kzalloc (sizeof (*args),GFP_KERNEL ); +if (!args) { + status = -ENOMEM ; + goto out; + } + args->args_op = dp; + msg.rpc_argp = args; dp->dl_retries =1 ; status =rpc_call_async (clnt, &msg,RPC_TASK_SOFT , &nfsd4_cb_recall_ops, dp); +out:if (status) {put_nfs4_client (clp);nfs4_put_delegation (dp);
Signature · 1 line
1.5.4.3
RFC 11/11 nfsd41: Refactor create_client()
Move common initialization of 'struct nfs4_client' inside create_client().
--- fs/nfsd/nfs4state.c | 90 +++++++++++++++++++++++++------------------------- 1 files changed, 45 insertions(+), 45 deletions(-)
fs/nfsd/nfs4state.c +45 -45
@@ -710,27 +710,6 @@ expire_client(struct nfs4_client *clp)put_nfs4_client (clp); } -static struct nfs4_client *create_client (struct xdr_netobj name,char *recdir) -{ -struct nfs4_client *clp; - - clp =alloc_client (name); -if (clp ==NULL ) -return NULL ; -memcpy (clp->cl_recdir, recdir,HEXDIR_LEN ); -atomic_set (&clp->cl_count,1 ); -atomic_set (&clp->cl_cb_conn.cb_set,0 ); -INIT_LIST_HEAD (&clp->cl_idhash); -INIT_LIST_HEAD (&clp->cl_strhash); -INIT_LIST_HEAD (&clp->cl_openowners); -INIT_LIST_HEAD (&clp->cl_delegations); -INIT_LIST_HEAD (&clp->cl_sessions); -INIT_LIST_HEAD (&clp->cl_lru); -clear_bit (0 , &clp->cl_cb_slot_busy); -rpc_init_wait_queue (&clp->cl_cb_waitq,"Backchannel slot table" ); -return clp; -} -static void copy_verf (struct nfs4_client *target,nfs4_verifier *source) { memcpy(target->cl_verifier.data, source->data,
@@ -793,6 +772,46 @@ static void gen_confirm(struct nfs4_client *clp) *p++ = i++; } +static struct nfs4_client *create_client (struct xdr_netobj name,char *recdir, +struct svc_rqst *rqstp,nfs4_verifier *verf) +{ +struct nfs4_client *clp; +u32 ip_addr =svc_addr_in (rqstp)->sin_addr.s_addr; +char *princ; + + clp =alloc_client (name); +if (clp ==NULL ) +return NULL ; + + princ =svc_gss_principal (rqstp); +if (princ) { + clp->cl_principal =kstrdup (princ,GFP_KERNEL ); +if (clp->cl_principal ==NULL ) { +free_client (clp); +return NULL ; + } + } + +memcpy (clp->cl_recdir, recdir,HEXDIR_LEN ); +atomic_set (&clp->cl_count,1 ); +atomic_set (&clp->cl_cb_conn.cb_set,0 ); +INIT_LIST_HEAD (&clp->cl_idhash); +INIT_LIST_HEAD (&clp->cl_strhash); +INIT_LIST_HEAD (&clp->cl_openowners); +INIT_LIST_HEAD (&clp->cl_delegations); +INIT_LIST_HEAD (&clp->cl_sessions); +INIT_LIST_HEAD (&clp->cl_lru); +clear_bit (0 , &clp->cl_cb_slot_busy); +rpc_init_wait_queue (&clp->cl_cb_waitq,"Backchannel slot table" ); +copy_verf (clp, verf); + clp->cl_addr = ip_addr; + clp->cl_flavor = rqstp->rq_flavor; +copy_cred (&clp->cl_cred, &rqstp->rq_cred); +gen_confirm (clp); + +return clp; +} +static int check_name (struct xdr_netobj name) {if (name.len ==0 )
@@ -1285,17 +1304,13 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, out_new:/* Normal case */ - new =create_client (exid->clname, dname); + new =create_client (exid->clname, dname, rqstp, &verf);if (new ==NULL ) { status = nfserr_resource; goto out; } -copy_verf (new, &verf); -copy_cred (&new->cl_cred, &rqstp->rq_cred); - new->cl_addr = ip_addr;gen_clid (new); -gen_confirm (new);add_to_unconfirmed (new, strhashval); out_copy: exid->clientid.cl_boot = new->cl_clientid.cl_boot;
@@ -1535,7 +1550,6 @@ __be32 nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_setclientid *setclid) { - struct sockaddr_in *sin = svc_addr_in(rqstp); struct xdr_netobj clname = { .len = setclid->se_namelen, .data = setclid->se_name,
@@ -1544,7 +1558,6 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,unsigned int strhashval;struct nfs4_client *conf, *unconf, *new;__be32 status; -char *princ;char dname[HEXDIR_LEN ];if (!check_name (clname))
@@ -1586,7 +1599,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,*/ if (unconf)expire_client (unconf); - new =create_client (clname, dname); + new =create_client (clname, dname, rqstp, &clverifier);if (new ==NULL ) goto out;gen_clid (new);
@@ -1603,7 +1616,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,*/ expire_client (unconf); } - new =create_client (clname, dname); + new =create_client (clname, dname, rqstp, &clverifier);if (new ==NULL ) goto out;copy_clid (new, conf);
@@ -1613,7 +1626,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,* probable client reboot; state will be removed if * confirmed. */ - new =create_client (clname, dname); + new =create_client (clname, dname, rqstp, &clverifier);if (new ==NULL ) goto out;gen_clid (new);
@@ -1624,24 +1637,11 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,* confirmed. */ expire_client (unconf); - new =create_client (clname, dname); + new =create_client (clname, dname, rqstp, &clverifier);if (new ==NULL ) goto out;gen_clid (new); } -copy_verf (new, &clverifier); - new->cl_addr = sin->sin_addr.s_addr; - new->cl_flavor = rqstp->rq_flavor; - princ =svc_gss_principal (rqstp); -if (princ) { - new->cl_principal =kstrdup (princ,GFP_KERNEL ); -if (new->cl_principal ==NULL ) { -free_client (new); - goto out; - } - } -copy_cred (&new->cl_cred, &rqstp->rq_cred); -gen_confirm (new);gen_callback (new, setclid);add_to_unconfirmed (new, strhashval); setclid->se_clientid.cl_boot = new->cl_clientid.cl_boot;
Signature · 1 line
1.5.4.3
Merged onto the nfsd41-for-2.6.31 branch.
Thanks!
Benny
Quoted 46 lines · Ricardo
Bruce, Trond,
The following patch set addresses your comments on the server v4.1 backchannel RPC functionality previously submitted. It also addresses Benny's comments on the implementation of the async RPC v4.1 callbacks. Please consider for 2.6.31.
[RFC 01/11] nfsd41: Backchannel: cleanup nfs4.0 callback encode routines [RFC 02/11] nfsd41: Backchannel: minorversion support for the back channel
[RFC 03/11] nfsd41: sunrpc:svc_tcp_recv_record()
[RFC 04/11] nfsd41: sunrpc: Added rpc server-side backchannel handling [RFC 05/11] nfsd41: Backchannel: callback infrastructure [RFC 06/11] nfsd41: Backchannel: Add sequence arguments to callback RPC arguments
[RFC 07/11] nfsd41: Backchannel: Server backchannel RPC wait queue [RFC 08/11] nfsd41: Backchannel: Setup sequence information [RFC 09/11] nfsd41: Backchannel:cb_sequencecallback
[RFC 10/11] nfsd41: Backchannel: Implementcb_recallover NFSv4.1 [RFC 11/11] nfsd41: Refactorcreate_client()As requested, this patch set squashes the following patches recently submitted to the pnfs list by Alexandros, Benny, and myself.
nfsd41: sunrpc: Remove unused functions
nfsd41: sunrpc: Don't auto close the server backchannel connection
nfsd41: sunrpc: eliminate unneeded switch statement inxs_setup_tcp()
nfsd41: sunrpc: removebc_closeandbc_init_auto_disconnectdummy fun
nfsd41: sunrpc: Definexprt_server_backchannel()
nfsd41: sunrpc: create common send routine for the fore and the back
nfsd41: sunrpc: removebc_connect_worker()
nfsd41: sunrpc: Document server backchannel locking
nfsd41: sunrpc: Usefree_page()to free server backchannel pages
nfsd41: sunrpc: Newsvc_process_calldir()
nfsd41: sunrpc:svc_tcp_recv_record()
nfsd41:decode_cb_sequencedoes not need to actually decode ignored fieldsThanks,
- ricardo
_______________________________________________
pNFS mailing list
[email protected]
http://linux-nfs.org/cgi-bin/mailman/listinfo/pnfs