X-Git-Url: http://ftp.safe.ca/?p=safe%2Fjmp%2Flinux-2.6;a=blobdiff_plain;f=fs%2Fnfsd%2Fnfs4callback.c;h=4bc22c763de7b433b4a37f2affdf75cc560d3908;hp=c1cb7e009c1ef54fc3391b933564f872f769c2b7;hb=8d75da8afd068fa58b35e69c7c8c46770d9e7a98;hpb=dd4877bfb6f09cb4a294b459b354c8fc8fa66904 diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index c1cb7e0..4bc22c7 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -1,6 +1,4 @@ /* - * linux/fs/nfsd/nfs4callback.c - * * Copyright (c) 2001 The Regents of the University of Michigan. * All rights reserved. * @@ -33,38 +31,27 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ -#include -#include -#include -#include -#include -#include -#include -#include -#include #include -#include -#include -#include -#include +#include "nfsd.h" +#include "state.h" #define NFSDDBG_FACILITY NFSDDBG_PROC #define NFSPROC4_CB_NULL 0 #define NFSPROC4_CB_COMPOUND 1 - -/* declarations */ -static const struct rpc_call_ops nfs4_cb_null_ops; +#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 @@ -73,17 +60,29 @@ 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) +struct nfs4_rpc_args { + void *args_op; + struct nfsd4_cb_sequence args_seq; +}; + /* * Generic encode routines from fs/nfs/nfs4xdr.c */ @@ -104,7 +103,7 @@ xdr_writemem(__be32 *p, const void *ptr, int nbytes) } while (0) #define RESERVE_SPACE(nbytes) do { \ p = xdr_reserve_space(xdr, nbytes); \ - if (!p) dprintk("NFSD: RESERVE_SPACE(%d) failed in function %s\n", (int) (nbytes), __FUNCTION__); \ + if (!p) dprintk("NFSD: RESERVE_SPACE(%d) failed in function %s\n", (int) (nbytes), __func__); \ BUG_ON(!p); \ } while (0) @@ -134,17 +133,21 @@ xdr_error: \ p = xdr_inline_decode(xdr, nbytes); \ if (!p) { \ dprintk("NFSD: %s: reply buffer overflowed in line %d.\n", \ - __FUNCTION__, __LINE__); \ + __func__, __LINE__); \ return -EIO; \ } \ } 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; + char *tag; }; static struct { @@ -204,32 +207,60 @@ 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; 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); - return 0; } -static int -encode_cb_recall(struct xdr_stream *xdr, struct nfs4_cb_recall *cb_rec) +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 = cb_rec->cbr_fhlen; + int len = dp->dl_fh.fh_size; - RESERVE_SPACE(12+sizeof(cb_rec->cbr_stateid) + len); + RESERVE_SPACE(12+sizeof(dp->dl_stateid) + len); WRITE32(OP_CB_RECALL); - WRITEMEM(&cb_rec->cbr_stateid, sizeof(stateid_t)); - WRITE32(cb_rec->cbr_trunc); + WRITE32(dp->dl_stateid.si_generation); + WRITEMEM(&dp->dl_stateid.si_opaque, sizeof(stateid_opaque_t)); + WRITE32(0); /* truncate optimization not implemented */ WRITE32(len); - WRITEMEM(cb_rec->cbr_fhval, len); - return 0; + WRITEMEM(&dp->dl_fh.fh_base, len); + 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 @@ -243,17 +274,22 @@ 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_cb_recall *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->cbr_ident, - .nops = 1, + .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); - return (encode_cb_recall(&xdr, args)); + encode_cb_sequence(&xdr, &rpc_args->args_seq, &hdr); + encode_cb_recall(&xdr, args, &hdr); + encode_cb_nops(&hdr); + return 0; } @@ -292,6 +328,57 @@ 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) { @@ -299,7 +386,8 @@ 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; @@ -309,6 +397,11 @@ 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; @@ -344,28 +437,120 @@ static struct rpc_version * nfs_cb_version[] = { &nfs_cb_version4, }; +static struct rpc_program cb_program; + +static struct rpc_stat cb_stats = { + .program = &cb_program +}; + +#define NFS4_CALLBACK 0x40000000 +static struct rpc_program cb_program = { + .name = "nfs4_cb", + .number = NFS4_CALLBACK, + .nrvers = ARRAY_SIZE(nfs_cb_version), + .version = nfs_cb_version, + .stats = &cb_stats, + .pipe_dir_name = "/nfsd4_cb", +}; + +static int max_cb_time(void) +{ + return max(NFSD_LEASE_TIME/10, (time_t)1) * HZ; +} + /* Reference counting, callback cleanup, etc., all look racy as heck. * And why is cb_set an atomic? */ -static int do_probe_callback(void *data) +int setup_callback_client(struct nfs4_client *clp) +{ + struct nfs4_cb_conn *cb = &clp->cl_cb_conn; + struct rpc_timeout timeparms = { + .to_initval = max_cb_time(), + .to_retries = 0, + }; + struct rpc_create_args args = { + .protocol = XPRT_TRANSPORT_TCP, + .address = (struct sockaddr *) &cb->cb_addr, + .addrsize = cb->cb_addrlen, + .timeout = &timeparms, + .program = &cb_program, + .prognumber = cb->cb_prog, + .version = nfs_cb_version[1]->number, + .authflavor = clp->cl_flavor, + .flags = (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET), + .client_name = clp->cl_principal, + }; + struct rpc_clnt *client; + + if (!clp->cl_principal && (clp->cl_flavor >= RPC_AUTH_GSS_KRB5)) + return -EINVAL; + if (cb->cb_minorversion) { + args.bc_xprt = clp->cl_cb_xprt; + args.protocol = XPRT_TRANSPORT_BC_TCP; + } + /* Create RPC client */ + client = rpc_create(&args); + if (IS_ERR(client)) { + dprintk("NFSD: couldn't create callback client: %ld\n", + PTR_ERR(client)); + return PTR_ERR(client); + } + cb->cb_client = client; + return 0; + +} + +static void warn_no_callback_path(struct nfs4_client *clp, int reason) { - struct nfs4_client *clp = data; - struct nfs4_callback *cb = &clp->cl_callback; + dprintk("NFSD: warning: no callback path to client %.*s: error %d\n", + (int)clp->cl_name.len, clp->cl_name.data, reason); +} + +static void nfsd4_cb_probe_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_client *clp = calldata; + + if (task->tk_status) + warn_no_callback_path(clp, task->tk_status); + else + atomic_set(&clp->cl_cb_conn.cb_set, 1); + put_nfs4_client(clp); +} + +static const struct rpc_call_ops nfsd4_cb_probe_ops = { + .rpc_call_done = nfsd4_cb_probe_done, +}; + +static struct rpc_cred *callback_cred; + +int set_callback_cred(void) +{ + if (callback_cred) + return 0; + callback_cred = rpc_lookup_machine_cred(); + if (!callback_cred) + return -ENOMEM; + return 0; +} + + +void do_probe_callback(struct nfs4_client *clp) +{ + struct nfs4_cb_conn *cb = &clp->cl_cb_conn; struct rpc_message msg = { .rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL], .rpc_argp = clp, + .rpc_cred = callback_cred }; int status; - status = rpc_call_sync(cb->cb_client, &msg, RPC_TASK_SOFT); - + status = rpc_call_async(cb->cb_client, &msg, + RPC_TASK_SOFT | RPC_TASK_SOFTCONN, + &nfsd4_cb_probe_ops, (void *)clp); if (status) { - rpc_shutdown_client(cb->cb_client); - cb->cb_client = NULL; - } else - atomic_set(&cb->cb_set, 1); - put_nfs4_client(clp); - return 0; + warn_no_callback_path(clp, status); + put_nfs4_client(clp); + } } /* @@ -374,118 +559,180 @@ static int do_probe_callback(void *data) void nfsd4_probe_callback(struct nfs4_client *clp) { - struct sockaddr_in addr; - struct nfs4_callback *cb = &clp->cl_callback; - struct rpc_timeout timeparms = { - .to_initval = (NFSD_LEASE_TIME/4) * HZ, - .to_retries = 5, - .to_maxval = (NFSD_LEASE_TIME/2) * HZ, - .to_exponential = 1, - }; - struct rpc_program * program = &cb->cb_program; - struct rpc_create_args args = { - .protocol = IPPROTO_TCP, - .address = (struct sockaddr *)&addr, - .addrsize = sizeof(addr), - .timeout = &timeparms, - .program = program, - .version = nfs_cb_version[1]->number, - .authflavor = RPC_AUTH_UNIX, /* XXX: need AUTH_GSS... */ - .flags = (RPC_CLNT_CREATE_NOPING), - }; - struct task_struct *t; + int status; + + BUG_ON(atomic_read(&clp->cl_cb_conn.cb_set)); - if (atomic_read(&cb->cb_set)) + status = setup_callback_client(clp); + if (status) { + warn_no_callback_path(clp, status); return; + } - /* Initialize address */ - memset(&addr, 0, sizeof(addr)); - addr.sin_family = AF_INET; - addr.sin_port = htons(cb->cb_port); - addr.sin_addr.s_addr = htonl(cb->cb_addr); + /* the task holds a reference to the nfs4_client struct */ + atomic_inc(&clp->cl_count); - /* Initialize rpc_program */ - program->name = "nfs4_cb"; - program->number = cb->cb_prog; - program->nrvers = ARRAY_SIZE(nfs_cb_version); - program->version = nfs_cb_version; - program->stats = &cb->cb_stat; + do_probe_callback(clp); +} - /* Initialize rpc_stat */ - memset(program->stats, 0, sizeof(cb->cb_stat)); - program->stats->program = program; +/* + * 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; - /* Create RPC client */ - cb->cb_client = rpc_create(&args); - if (IS_ERR(cb->cb_client)) { - dprintk("NFSD: couldn't create callback client\n"); - goto out_err; + 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; } - /* the task holds a reference to the nfs4_client struct */ - atomic_inc(&clp->cl_count); + /* + * 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; - t = kthread_run(do_probe_callback, clp, "nfs4_cb_probe"); +out: + dprintk("%s status=%d\n", __func__, status); + return status; +} - if (IS_ERR(t)) - goto out_release_clp; +/* + * 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; - return; + dprintk("%s: minorversion=%d\n", __func__, + clp->cl_cb_conn.cb_minorversion); -out_release_clp: - atomic_dec(&clp->cl_count); - rpc_shutdown_client(cb->cb_client); -out_err: - cb->cb_client = NULL; - dprintk("NFSD: warning: no callback path to client %.*s\n", - (int)clp->cl_name.len, clp->cl_name.data); + 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; + struct nfs4_client *clp = dp->dl_client; + + nfsd4_cb_done(task, calldata); + + switch (task->tk_status) { + case -EIO: + /* Network partition? */ + atomic_set(&clp->cl_cb_conn.cb_set, 0); + warn_no_callback_path(clp, task->tk_status); + case -EBADHANDLE: + case -NFS4ERR_BAD_STATEID: + /* Race: client probably got cb_recall + * before open reply granting delegation */ + break; + default: + /* success, or error we can't handle */ + 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) +{ + struct nfs4_delegation *dp = calldata; + struct nfs4_client *clp = dp->dl_client; + + nfs4_put_delegation(dp); + put_nfs4_client(clp); +} + +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, +}; + /* * called with dp->dl_count inc'ed. - * nfs4_lock_state() may or may not have been called. */ void nfsd4_cb_recall(struct nfs4_delegation *dp) { struct nfs4_client *clp = dp->dl_client; - struct rpc_clnt *clnt = clp->cl_callback.cb_client; - struct nfs4_cb_recall *cbr = &dp->dl_recall; + 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 = cbr, + .rpc_cred = callback_cred }; - int retries = 1; - int status = 0; + int status = -ENOMEM; - if ((!atomic_read(&clp->cl_callback.cb_set)) || !clnt) - return; - - cbr->cbr_trunc = 0; /* XXX need to implement truncate optimization */ - cbr->cbr_dp = dp; - - status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFT); - while (retries--) { - switch (status) { - case -EIO: - /* Network partition? */ - case -EBADHANDLE: - case -NFS4ERR_BAD_STATEID: - /* Race: client probably got cb_recall - * before open reply granting delegation */ - break; - default: - goto out_put_cred; - } - ssleep(2); - status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFT); + args = kzalloc(sizeof(*args), GFP_KERNEL); + if (!args) + 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) { + kfree(args); + put_nfs4_client(clp); + nfs4_put_delegation(dp); } -out_put_cred: - if (status == -EIO) - atomic_set(&clp->cl_callback.cb_set, 0); - /* Success or failure, now we're either waiting for lease expiration - * or deleg_return. */ - dprintk("NFSD: nfs4_cb_recall: dp %p dl_flock %p dl_count %d\n",dp, dp->dl_flock, atomic_read(&dp->dl_count)); - nfs4_put_delegation(dp); - return; }