diff options
Diffstat (limited to 'fs/nfsd/nfs4callback.c')
| -rw-r--r-- | fs/nfsd/nfs4callback.c | 1362 |
1 files changed, 1056 insertions, 306 deletions
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 7f05cd140de3..e00b2aea8da2 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -31,29 +31,26 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ +#include <linux/nfs4.h> #include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/xprt.h> #include <linux/sunrpc/svc_xprt.h> #include <linux/slab.h> #include "nfsd.h" #include "state.h" #include "netns.h" +#include "trace.h" #include "xdr4cb.h" +#include "xdr4.h" +#include "nfs4xdr_gen.h" #define NFSDDBG_FACILITY NFSDDBG_PROC -static void nfsd4_mark_cb_fault(struct nfs4_client *, int reason); - #define NFSPROC4_CB_NULL 0 #define NFSPROC4_CB_COMPOUND 1 /* Index of predefined Linux callback client operations */ -enum { - NFSPROC4_CLNT_CB_NULL = 0, - NFSPROC4_CLNT_CB_RECALL, - NFSPROC4_CLNT_CB_SEQUENCE, -}; - struct nfs4_cb_compound_hdr { /* args */ u32 ident; /* minorversion 0 only */ @@ -64,16 +61,6 @@ struct nfs4_cb_compound_hdr { int status; }; -/* - * Handle decode buffer overflows out-of-line. - */ -static void print_overflow_msg(const char *func, const struct xdr_stream *xdr) -{ - dprintk("NFS: %s prematurely hit the end of our receive buffer. " - "Remaining buffer length is %tu words.\n", - func, xdr->end - xdr->p); -} - static __be32 *xdr_encode_empty_array(__be32 *p) { *p++ = xdr_zero; @@ -89,29 +76,53 @@ static __be32 *xdr_encode_empty_array(__be32 *p) * 1 Protocol" */ -/* - * nfs_cb_opnum4 - * - * enum nfs_cb_opnum4 { - * OP_CB_GETATTR = 3, - * ... - * }; - */ -enum nfs_cb_opnum4 { - OP_CB_GETATTR = 3, - OP_CB_RECALL = 4, - OP_CB_LAYOUTRECALL = 5, - OP_CB_NOTIFY = 6, - OP_CB_PUSH_DELEG = 7, - OP_CB_RECALL_ANY = 8, - OP_CB_RECALLABLE_OBJ_AVAIL = 9, - OP_CB_RECALL_SLOT = 10, - OP_CB_SEQUENCE = 11, - OP_CB_WANTS_CANCELLED = 12, - OP_CB_NOTIFY_LOCK = 13, - OP_CB_NOTIFY_DEVICEID = 14, - OP_CB_ILLEGAL = 10044 -}; +static void encode_uint32(struct xdr_stream *xdr, u32 n) +{ + WARN_ON_ONCE(xdr_stream_encode_u32(xdr, n) < 0); +} + +static void encode_bitmap4(struct xdr_stream *xdr, const __u32 *bitmap, + size_t len) +{ + xdr_stream_encode_uint32_array(xdr, bitmap, len); +} + +static int decode_cb_fattr4(struct xdr_stream *xdr, uint32_t *bitmap, + struct nfs4_cb_fattr *fattr) +{ + fattr->ncf_cb_change = 0; + fattr->ncf_cb_fsize = 0; + fattr->ncf_cb_atime.tv_sec = 0; + fattr->ncf_cb_atime.tv_nsec = 0; + fattr->ncf_cb_mtime.tv_sec = 0; + fattr->ncf_cb_mtime.tv_nsec = 0; + + if (bitmap[0] & FATTR4_WORD0_CHANGE) + if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_change) < 0) + return -EIO; + if (bitmap[0] & FATTR4_WORD0_SIZE) + if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_fsize) < 0) + return -EIO; + if (bitmap[2] & FATTR4_WORD2_TIME_DELEG_ACCESS) { + fattr4_time_deleg_access access; + + if (!xdrgen_decode_fattr4_time_deleg_access(xdr, &access)) + return -EIO; + fattr->ncf_cb_atime.tv_sec = access.seconds; + fattr->ncf_cb_atime.tv_nsec = access.nseconds; + + } + if (bitmap[2] & FATTR4_WORD2_TIME_DELEG_MODIFY) { + fattr4_time_deleg_modify modify; + + if (!xdrgen_decode_fattr4_time_deleg_modify(xdr, &modify)) + return -EIO; + fattr->ncf_cb_mtime.tv_sec = modify.seconds; + fattr->ncf_cb_mtime.tv_nsec = modify.nseconds; + + } + return 0; +} static void encode_nfs_cb_opnum4(struct xdr_stream *xdr, enum nfs_cb_opnum4 op) { @@ -133,7 +144,7 @@ static void encode_nfs_fh4(struct xdr_stream *xdr, const struct knfsd_fh *fh) BUG_ON(length > NFS4_FHSIZE); p = xdr_reserve_space(xdr, 4 + length); - xdr_encode_opaque(p, &fh->fh_base, length); + xdr_encode_opaque(p, &fh->fh_raw, length); } /* @@ -228,8 +239,8 @@ static int nfs_cb_stat_to_errno(int status) return -status; } -static int decode_cb_op_status(struct xdr_stream *xdr, enum nfs_opnum4 expected, - enum nfsstat4 *status) +static int decode_cb_op_status(struct xdr_stream *xdr, + enum nfs_cb_opnum4 expected, int *status) { __be32 *p; u32 op; @@ -240,10 +251,9 @@ static int decode_cb_op_status(struct xdr_stream *xdr, enum nfs_opnum4 expected, op = be32_to_cpup(p++); if (unlikely(op != expected)) goto out_unexpected; - *status = be32_to_cpup(p); + *status = nfs_cb_stat_to_errno(be32_to_cpup(p)); return 0; out_overflow: - print_overflow_msg(__func__, xdr); return -EIO; out_unexpected: dprintk("NFSD: Callback server returned operation %d but " @@ -299,19 +309,19 @@ static int decode_cb_compound4res(struct xdr_stream *xdr, u32 length; __be32 *p; - p = xdr_inline_decode(xdr, 4 + 4); + p = xdr_inline_decode(xdr, XDR_UNIT); if (unlikely(p == NULL)) goto out_overflow; - hdr->status = be32_to_cpup(p++); + hdr->status = be32_to_cpup(p); /* Ignore the tag */ - length = be32_to_cpup(p++); - p = xdr_inline_decode(xdr, length + 4); - if (unlikely(p == NULL)) + if (xdr_stream_decode_u32(xdr, &length) < 0) + goto out_overflow; + if (xdr_inline_decode(xdr, length) == NULL) + goto out_overflow; + if (xdr_stream_decode_u32(xdr, &hdr->nops) < 0) goto out_overflow; - hdr->nops = be32_to_cpup(p); return 0; out_overflow: - print_overflow_msg(__func__, xdr); return -EIO; } @@ -336,12 +346,101 @@ static void encode_cb_recall4args(struct xdr_stream *xdr, p = xdr_reserve_space(xdr, 4); *p++ = xdr_zero; /* truncate */ - encode_nfs_fh4(xdr, &dp->dl_fh); + encode_nfs_fh4(xdr, &dp->dl_stid.sc_file->fi_fhandle); hdr->nops++; } /* + * CB_RECALLANY4args + * + * struct CB_RECALLANY4args { + * uint32_t craa_objects_to_keep; + * bitmap4 craa_type_mask; + * }; + */ +static void +encode_cb_recallany4args(struct xdr_stream *xdr, + struct nfs4_cb_compound_hdr *hdr, struct nfsd4_cb_recall_any *ra) +{ + encode_nfs_cb_opnum4(xdr, OP_CB_RECALL_ANY); + encode_uint32(xdr, ra->ra_keep); + encode_bitmap4(xdr, ra->ra_bmval, ARRAY_SIZE(ra->ra_bmval)); + hdr->nops++; +} + +/* + * CB_GETATTR4args + * struct CB_GETATTR4args { + * nfs_fh4 fh; + * bitmap4 attr_request; + * }; + * + * The size and change attributes are the only one + * guaranteed to be serviced by the client. + */ +static void +encode_cb_getattr4args(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr, + struct nfs4_cb_fattr *fattr) +{ + struct nfs4_delegation *dp = container_of(fattr, struct nfs4_delegation, dl_cb_fattr); + struct knfsd_fh *fh = &dp->dl_stid.sc_file->fi_fhandle; + struct nfs4_cb_fattr *ncf = &dp->dl_cb_fattr; + u32 bmap_size = 1; + u32 bmap[3]; + + bmap[0] = FATTR4_WORD0_SIZE; + if (!ncf->ncf_file_modified) + bmap[0] |= FATTR4_WORD0_CHANGE; + + if (deleg_attrs_deleg(dp->dl_type)) { + bmap[1] = 0; + bmap[2] = FATTR4_WORD2_TIME_DELEG_ACCESS | FATTR4_WORD2_TIME_DELEG_MODIFY; + bmap_size = 3; + } + encode_nfs_cb_opnum4(xdr, OP_CB_GETATTR); + encode_nfs_fh4(xdr, fh); + encode_bitmap4(xdr, bmap, bmap_size); + hdr->nops++; +} + +static u32 highest_slotid(struct nfsd4_session *ses) +{ + u32 idx; + + spin_lock(&ses->se_lock); + idx = fls(~ses->se_cb_slot_avail); + if (idx > 0) + --idx; + idx = max(idx, ses->se_cb_highest_slot); + spin_unlock(&ses->se_lock); + return idx; +} + +static void +encode_referring_call4(struct xdr_stream *xdr, + const struct nfsd4_referring_call *rc) +{ + encode_uint32(xdr, rc->rc_sequenceid); + encode_uint32(xdr, rc->rc_slotid); +} + +static void +encode_referring_call_list4(struct xdr_stream *xdr, + const struct nfsd4_referring_call_list *rcl) +{ + struct nfsd4_referring_call *rc; + __be32 *p; + + p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN); + xdr_encode_opaque_fixed(p, rcl->rcl_sessionid.data, + NFS4_MAX_SESSIONID_LEN); + encode_uint32(xdr, rcl->__nr_referring_calls); + list_for_each_entry(rc, &rcl->rcl_referring_calls, __list) + encode_referring_call4(xdr, rc); +} + +/* * CB_SEQUENCE4args * * struct CB_SEQUENCE4args { @@ -358,6 +457,7 @@ static void encode_cb_sequence4args(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr) { struct nfsd4_session *session = cb->cb_clp->cl_cb_session; + struct nfsd4_referring_call_list *rcl; __be32 *p; if (hdr->minorversion == 0) @@ -366,16 +466,45 @@ static void encode_cb_sequence4args(struct xdr_stream *xdr, encode_nfs_cb_opnum4(xdr, OP_CB_SEQUENCE); encode_sessionid4(xdr, session); - p = xdr_reserve_space(xdr, 4 + 4 + 4 + 4 + 4); - *p++ = cpu_to_be32(session->se_cb_seq_nr); /* csa_sequenceid */ - *p++ = xdr_zero; /* csa_slotid */ - *p++ = xdr_zero; /* csa_highest_slotid */ + p = xdr_reserve_space(xdr, XDR_UNIT * 4); + *p++ = cpu_to_be32(session->se_cb_seq_nr[cb->cb_held_slot]); /* csa_sequenceid */ + *p++ = cpu_to_be32(cb->cb_held_slot); /* csa_slotid */ + *p++ = cpu_to_be32(highest_slotid(session)); /* csa_highest_slotid */ *p++ = xdr_zero; /* csa_cachethis */ - xdr_encode_empty_array(p); /* csa_referring_call_lists */ + + /* csa_referring_call_lists */ + encode_uint32(xdr, cb->cb_nr_referring_call_list); + list_for_each_entry(rcl, &cb->cb_referring_call_list, __list) + encode_referring_call_list4(xdr, rcl); hdr->nops++; } +static void update_cb_slot_table(struct nfsd4_session *ses, u32 target) +{ + /* No need to do anything if nothing changed */ + if (likely(target == READ_ONCE(ses->se_cb_highest_slot))) + return; + + spin_lock(&ses->se_lock); + if (target > ses->se_cb_highest_slot) { + int i; + + target = min(target, NFSD_BC_SLOT_TABLE_SIZE - 1); + + /* + * Growing the slot table. Reset any new sequences to 1. + * + * NB: There is some debate about whether the RFC requires this, + * but the Linux client expects it. + */ + for (i = ses->se_cb_highest_slot + 1; i <= target; ++i) + ses->se_cb_seq_nr[i] = 1; + } + ses->se_cb_highest_slot = target; + spin_unlock(&ses->se_lock); +} + /* * CB_SEQUENCE4resok * @@ -401,12 +530,9 @@ static int decode_cb_sequence4resok(struct xdr_stream *xdr, struct nfsd4_callback *cb) { struct nfsd4_session *session = cb->cb_clp->cl_cb_session; - struct nfs4_sessionid id; - int status; + int status = -ESERVERFAULT; __be32 *p; - u32 dummy; - - status = -ESERVERFAULT; + u32 seqid, slotid, target; /* * If the server returns different values for sessionID, slotID or @@ -415,58 +541,51 @@ static int decode_cb_sequence4resok(struct xdr_stream *xdr, p = xdr_inline_decode(xdr, NFS4_MAX_SESSIONID_LEN + 4 + 4 + 4 + 4); if (unlikely(p == NULL)) goto out_overflow; - memcpy(id.data, p, NFS4_MAX_SESSIONID_LEN); - if (memcmp(id.data, session->se_sessionid.data, - NFS4_MAX_SESSIONID_LEN) != 0) { + + if (memcmp(p, session->se_sessionid.data, NFS4_MAX_SESSIONID_LEN)) { dprintk("NFS: %s Invalid session id\n", __func__); goto out; } p += XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN); - dummy = be32_to_cpup(p++); - if (dummy != session->se_cb_seq_nr) { + seqid = be32_to_cpup(p++); + if (seqid != session->se_cb_seq_nr[cb->cb_held_slot]) { dprintk("NFS: %s Invalid sequence number\n", __func__); goto out; } - dummy = be32_to_cpup(p++); - if (dummy != 0) { + slotid = be32_to_cpup(p++); + if (slotid != cb->cb_held_slot) { dprintk("NFS: %s Invalid slotid\n", __func__); goto out; } - /* - * FIXME: process highest slotid and target highest slotid - */ + p++; // ignore current highest slot value + + target = be32_to_cpup(p++); + update_cb_slot_table(session, target); status = 0; out: - if (status) - nfsd4_mark_cb_fault(cb->cb_clp, status); + cb->cb_seq_status = status; return status; out_overflow: - print_overflow_msg(__func__, xdr); - return -EIO; + status = -EIO; + goto out; } static int decode_cb_sequence4res(struct xdr_stream *xdr, struct nfsd4_callback *cb) { - enum nfsstat4 nfserr; int status; - if (cb->cb_minorversion == 0) + if (cb->cb_clp->cl_minorversion == 0) return 0; - status = decode_cb_op_status(xdr, OP_CB_SEQUENCE, &nfserr); - if (unlikely(status)) - goto out; - if (unlikely(nfserr != NFS4_OK)) - goto out_default; - status = decode_cb_sequence4resok(xdr, cb); -out: - return status; -out_default: - return nfs_cb_stat_to_errno(nfserr); + status = decode_cb_op_status(xdr, OP_CB_SEQUENCE, &cb->cb_seq_status); + if (unlikely(status || cb->cb_seq_status)) + return status; + + return decode_cb_sequence4resok(xdr, cb); } /* @@ -482,29 +601,70 @@ out_default: * NB: Without this zero space reservation, callbacks over krb5p fail */ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, - void *__unused) + const void *__unused) { xdr_reserve_space(xdr, 0); } /* + * 20.1. Operation 3: CB_GETATTR - Get Attributes + */ +static void nfs4_xdr_enc_cb_getattr(struct rpc_rqst *req, + struct xdr_stream *xdr, const void *data) +{ + const struct nfsd4_callback *cb = data; + struct nfs4_cb_fattr *ncf = + container_of(cb, struct nfs4_cb_fattr, ncf_getattr); + struct nfs4_cb_compound_hdr hdr = { + .ident = cb->cb_clp->cl_cb_ident, + .minorversion = cb->cb_clp->cl_minorversion, + }; + + encode_cb_compound4args(xdr, &hdr); + encode_cb_sequence4args(xdr, cb, &hdr); + encode_cb_getattr4args(xdr, &hdr, ncf); + encode_cb_nops(&hdr); +} + +/* * 20.2. Operation 4: CB_RECALL - Recall a Delegation */ static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfsd4_callback *cb) + const void *data) { - const struct nfs4_delegation *args = cb->cb_op; + const struct nfsd4_callback *cb = data; + const struct nfs4_delegation *dp = cb_to_delegation(cb); struct nfs4_cb_compound_hdr hdr = { .ident = cb->cb_clp->cl_cb_ident, - .minorversion = cb->cb_minorversion, + .minorversion = cb->cb_clp->cl_minorversion, }; encode_cb_compound4args(xdr, &hdr); encode_cb_sequence4args(xdr, cb, &hdr); - encode_cb_recall4args(xdr, args, &hdr); + encode_cb_recall4args(xdr, dp, &hdr); encode_cb_nops(&hdr); } +/* + * 20.6. Operation 8: CB_RECALL_ANY - Keep Any N Recallable Objects + */ +static void +nfs4_xdr_enc_cb_recall_any(struct rpc_rqst *req, + struct xdr_stream *xdr, const void *data) +{ + const struct nfsd4_callback *cb = data; + struct nfsd4_cb_recall_any *ra; + struct nfs4_cb_compound_hdr hdr = { + .ident = cb->cb_clp->cl_cb_ident, + .minorversion = cb->cb_clp->cl_minorversion, + }; + + ra = container_of(cb, struct nfsd4_cb_recall_any, ra_cb); + encode_cb_compound4args(xdr, &hdr); + encode_cb_sequence4args(xdr, cb, &hdr); + encode_cb_recallany4args(xdr, &hdr, ra); + encode_cb_nops(&hdr); +} /* * NFSv4.0 and NFSv4.1 XDR decode functions @@ -522,55 +682,358 @@ static int nfs4_xdr_dec_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, } /* + * 20.1. Operation 3: CB_GETATTR - Get Attributes + */ +static int nfs4_xdr_dec_cb_getattr(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *data) +{ + struct nfsd4_callback *cb = data; + struct nfs4_cb_compound_hdr hdr; + int status; + u32 bitmap[3] = {0}; + u32 attrlen, maxlen; + struct nfs4_cb_fattr *ncf = + container_of(cb, struct nfs4_cb_fattr, ncf_getattr); + + status = decode_cb_compound4res(xdr, &hdr); + if (unlikely(status)) + return status; + + status = decode_cb_sequence4res(xdr, cb); + if (unlikely(status || cb->cb_seq_status)) + return status; + + status = decode_cb_op_status(xdr, OP_CB_GETATTR, &cb->cb_status); + if (unlikely(status || cb->cb_status)) + return status; + if (xdr_stream_decode_uint32_array(xdr, bitmap, 3) < 0) + return -EIO; + if (xdr_stream_decode_u32(xdr, &attrlen) < 0) + return -EIO; + maxlen = sizeof(ncf->ncf_cb_change) + sizeof(ncf->ncf_cb_fsize); + if (bitmap[2] != 0) + maxlen += (sizeof(ncf->ncf_cb_mtime.tv_sec) + + sizeof(ncf->ncf_cb_mtime.tv_nsec)) * 2; + if (attrlen > maxlen) + return -EIO; + status = decode_cb_fattr4(xdr, bitmap, ncf); + return status; +} + +/* * 20.2. Operation 4: CB_RECALL - Recall a Delegation */ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfsd4_callback *cb) + void *data) { + struct nfsd4_callback *cb = data; struct nfs4_cb_compound_hdr hdr; - enum nfsstat4 nfserr; int status; status = decode_cb_compound4res(xdr, &hdr); if (unlikely(status)) - goto out; + return status; - if (cb != NULL) { - status = decode_cb_sequence4res(xdr, cb); - if (unlikely(status)) - goto out; - } + status = decode_cb_sequence4res(xdr, cb); + if (unlikely(status || cb->cb_seq_status)) + return status; - status = decode_cb_op_status(xdr, OP_CB_RECALL, &nfserr); + return decode_cb_op_status(xdr, OP_CB_RECALL, &cb->cb_status); +} + +/* + * 20.6. Operation 8: CB_RECALL_ANY - Keep Any N Recallable Objects + */ +static int +nfs4_xdr_dec_cb_recall_any(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *data) +{ + struct nfsd4_callback *cb = data; + struct nfs4_cb_compound_hdr hdr; + int status; + + status = decode_cb_compound4res(xdr, &hdr); if (unlikely(status)) - goto out; - if (unlikely(nfserr != NFS4_OK)) - status = nfs_cb_stat_to_errno(nfserr); -out: + return status; + status = decode_cb_sequence4res(xdr, cb); + if (unlikely(status || cb->cb_seq_status)) + return status; + status = decode_cb_op_status(xdr, OP_CB_RECALL_ANY, &cb->cb_status); return status; } +#ifdef CONFIG_NFSD_PNFS +/* + * CB_LAYOUTRECALL4args + * + * struct layoutrecall_file4 { + * nfs_fh4 lor_fh; + * offset4 lor_offset; + * length4 lor_length; + * stateid4 lor_stateid; + * }; + * + * union layoutrecall4 switch(layoutrecall_type4 lor_recalltype) { + * case LAYOUTRECALL4_FILE: + * layoutrecall_file4 lor_layout; + * case LAYOUTRECALL4_FSID: + * fsid4 lor_fsid; + * case LAYOUTRECALL4_ALL: + * void; + * }; + * + * struct CB_LAYOUTRECALL4args { + * layouttype4 clora_type; + * layoutiomode4 clora_iomode; + * bool clora_changed; + * layoutrecall4 clora_recall; + * }; + */ +static void encode_cb_layout4args(struct xdr_stream *xdr, + const struct nfs4_layout_stateid *ls, + struct nfs4_cb_compound_hdr *hdr) +{ + __be32 *p; + + BUG_ON(hdr->minorversion == 0); + + p = xdr_reserve_space(xdr, 5 * 4); + *p++ = cpu_to_be32(OP_CB_LAYOUTRECALL); + *p++ = cpu_to_be32(ls->ls_layout_type); + *p++ = cpu_to_be32(IOMODE_ANY); + *p++ = cpu_to_be32(1); + *p = cpu_to_be32(RETURN_FILE); + + encode_nfs_fh4(xdr, &ls->ls_stid.sc_file->fi_fhandle); + + p = xdr_reserve_space(xdr, 2 * 8); + p = xdr_encode_hyper(p, 0); + xdr_encode_hyper(p, NFS4_MAX_UINT64); + + encode_stateid4(xdr, &ls->ls_recall_sid); + + hdr->nops++; +} + +static void nfs4_xdr_enc_cb_layout(struct rpc_rqst *req, + struct xdr_stream *xdr, + const void *data) +{ + const struct nfsd4_callback *cb = data; + const struct nfs4_layout_stateid *ls = + container_of(cb, struct nfs4_layout_stateid, ls_recall); + struct nfs4_cb_compound_hdr hdr = { + .ident = 0, + .minorversion = cb->cb_clp->cl_minorversion, + }; + + encode_cb_compound4args(xdr, &hdr); + encode_cb_sequence4args(xdr, cb, &hdr); + encode_cb_layout4args(xdr, ls, &hdr); + encode_cb_nops(&hdr); +} + +static int nfs4_xdr_dec_cb_layout(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *data) +{ + struct nfsd4_callback *cb = data; + struct nfs4_cb_compound_hdr hdr; + int status; + + status = decode_cb_compound4res(xdr, &hdr); + if (unlikely(status)) + return status; + + status = decode_cb_sequence4res(xdr, cb); + if (unlikely(status || cb->cb_seq_status)) + return status; + + return decode_cb_op_status(xdr, OP_CB_LAYOUTRECALL, &cb->cb_status); +} +#endif /* CONFIG_NFSD_PNFS */ + +static void encode_stateowner(struct xdr_stream *xdr, struct nfs4_stateowner *so) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, 8 + 4 + so->so_owner.len); + p = xdr_encode_opaque_fixed(p, &so->so_client->cl_clientid, 8); + xdr_encode_opaque(p, so->so_owner.data, so->so_owner.len); +} + +static void nfs4_xdr_enc_cb_notify_lock(struct rpc_rqst *req, + struct xdr_stream *xdr, + const void *data) +{ + const struct nfsd4_callback *cb = data; + const struct nfsd4_blocked_lock *nbl = + container_of(cb, struct nfsd4_blocked_lock, nbl_cb); + struct nfs4_lockowner *lo = (struct nfs4_lockowner *)nbl->nbl_lock.c.flc_owner; + struct nfs4_cb_compound_hdr hdr = { + .ident = 0, + .minorversion = cb->cb_clp->cl_minorversion, + }; + + __be32 *p; + + BUG_ON(hdr.minorversion == 0); + + encode_cb_compound4args(xdr, &hdr); + encode_cb_sequence4args(xdr, cb, &hdr); + + p = xdr_reserve_space(xdr, 4); + *p = cpu_to_be32(OP_CB_NOTIFY_LOCK); + encode_nfs_fh4(xdr, &nbl->nbl_fh); + encode_stateowner(xdr, &lo->lo_owner); + hdr.nops++; + + encode_cb_nops(&hdr); +} + +static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *data) +{ + struct nfsd4_callback *cb = data; + struct nfs4_cb_compound_hdr hdr; + int status; + + status = decode_cb_compound4res(xdr, &hdr); + if (unlikely(status)) + return status; + + status = decode_cb_sequence4res(xdr, cb); + if (unlikely(status || cb->cb_seq_status)) + return status; + + return decode_cb_op_status(xdr, OP_CB_NOTIFY_LOCK, &cb->cb_status); +} + +/* + * struct write_response4 { + * stateid4 wr_callback_id<1>; + * length4 wr_count; + * stable_how4 wr_committed; + * verifier4 wr_writeverf; + * }; + * union offload_info4 switch (nfsstat4 coa_status) { + * case NFS4_OK: + * write_response4 coa_resok4; + * default: + * length4 coa_bytes_copied; + * }; + * struct CB_OFFLOAD4args { + * nfs_fh4 coa_fh; + * stateid4 coa_stateid; + * offload_info4 coa_offload_info; + * }; + */ +static void encode_offload_info4(struct xdr_stream *xdr, + const struct nfsd4_cb_offload *cbo) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, 4); + *p = cbo->co_nfserr; + switch (cbo->co_nfserr) { + case nfs_ok: + p = xdr_reserve_space(xdr, 4 + 8 + 4 + NFS4_VERIFIER_SIZE); + p = xdr_encode_empty_array(p); + p = xdr_encode_hyper(p, cbo->co_res.wr_bytes_written); + *p++ = cpu_to_be32(cbo->co_res.wr_stable_how); + p = xdr_encode_opaque_fixed(p, cbo->co_res.wr_verifier.data, + NFS4_VERIFIER_SIZE); + break; + default: + p = xdr_reserve_space(xdr, 8); + /* We always return success if bytes were written */ + p = xdr_encode_hyper(p, 0); + } +} + +static void encode_cb_offload4args(struct xdr_stream *xdr, + const struct nfsd4_cb_offload *cbo, + struct nfs4_cb_compound_hdr *hdr) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, 4); + *p = cpu_to_be32(OP_CB_OFFLOAD); + encode_nfs_fh4(xdr, &cbo->co_fh); + encode_stateid4(xdr, &cbo->co_res.cb_stateid); + encode_offload_info4(xdr, cbo); + + hdr->nops++; +} + +static void nfs4_xdr_enc_cb_offload(struct rpc_rqst *req, + struct xdr_stream *xdr, + const void *data) +{ + const struct nfsd4_callback *cb = data; + const struct nfsd4_cb_offload *cbo = + container_of(cb, struct nfsd4_cb_offload, co_cb); + struct nfs4_cb_compound_hdr hdr = { + .ident = 0, + .minorversion = cb->cb_clp->cl_minorversion, + }; + + encode_cb_compound4args(xdr, &hdr); + encode_cb_sequence4args(xdr, cb, &hdr); + encode_cb_offload4args(xdr, cbo, &hdr); + encode_cb_nops(&hdr); +} + +static int nfs4_xdr_dec_cb_offload(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *data) +{ + struct nfsd4_callback *cb = data; + struct nfs4_cb_compound_hdr hdr; + int status; + + status = decode_cb_compound4res(xdr, &hdr); + if (unlikely(status)) + return status; + + status = decode_cb_sequence4res(xdr, cb); + if (unlikely(status || cb->cb_seq_status)) + return status; + + return decode_cb_op_status(xdr, OP_CB_OFFLOAD, &cb->cb_status); +} /* * RPC procedure tables */ #define PROC(proc, call, argtype, restype) \ [NFSPROC4_CLNT_##proc] = { \ .p_proc = NFSPROC4_CB_##call, \ - .p_encode = (kxdreproc_t)nfs4_xdr_enc_##argtype, \ - .p_decode = (kxdrdproc_t)nfs4_xdr_dec_##restype, \ + .p_encode = nfs4_xdr_enc_##argtype, \ + .p_decode = nfs4_xdr_dec_##restype, \ .p_arglen = NFS4_enc_##argtype##_sz, \ .p_replen = NFS4_dec_##restype##_sz, \ .p_statidx = NFSPROC4_CB_##call, \ .p_name = #proc, \ } -static struct rpc_procinfo nfs4_cb_procedures[] = { +static const struct rpc_procinfo nfs4_cb_procedures[] = { PROC(CB_NULL, NULL, cb_null, cb_null), PROC(CB_RECALL, COMPOUND, cb_recall, cb_recall), +#ifdef CONFIG_NFSD_PNFS + PROC(CB_LAYOUT, COMPOUND, cb_layout, cb_layout), +#endif + PROC(CB_NOTIFY_LOCK, COMPOUND, cb_notify_lock, cb_notify_lock), + PROC(CB_OFFLOAD, COMPOUND, cb_offload, cb_offload), + PROC(CB_RECALL_ANY, COMPOUND, cb_recall_any, cb_recall_any), + PROC(CB_GETATTR, COMPOUND, cb_getattr, cb_getattr), }; -static struct rpc_version nfs_cb_version4 = { +static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)]; +static const struct rpc_version nfs_cb_version4 = { /* * Note on the callback rpc program version number: despite language in rfc * 5661 section 18.36.3 requiring servers to use 4 in this field, the @@ -580,11 +1043,12 @@ static struct rpc_version nfs_cb_version4 = { */ .number = 1, .nrprocs = ARRAY_SIZE(nfs4_cb_procedures), - .procs = nfs4_cb_procedures + .procs = nfs4_cb_procedures, + .counts = nfs4_cb_counts, }; -static const struct rpc_version *nfs_cb_version[] = { - &nfs_cb_version4, +static const struct rpc_version *nfs_cb_version[2] = { + [1] = &nfs_cb_version4, }; static const struct rpc_program cb_program; @@ -606,40 +1070,81 @@ static const struct rpc_program cb_program = { static int max_cb_time(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - return max(nn->nfsd4_lease/10, (time_t)1) * HZ; + + /* + * nfsd4_lease is set to at most one hour in __nfsd4_write_time, + * so we can use 32-bit math on it. Warn if that assumption + * ever stops being true. + */ + if (WARN_ON_ONCE(nn->nfsd4_lease > 3600)) + return 360 * HZ; + + return max(((u32)nn->nfsd4_lease)/10, 1u) * HZ; +} + +static bool nfsd4_queue_cb(struct nfsd4_callback *cb) +{ + struct nfs4_client *clp = cb->cb_clp; + + trace_nfsd_cb_queue(clp, cb); + return queue_work(clp->cl_callback_wq, &cb->cb_work); } -static struct rpc_cred *callback_cred; +static void nfsd4_requeue_cb(struct rpc_task *task, struct nfsd4_callback *cb) +{ + struct nfs4_client *clp = cb->cb_clp; -int set_callback_cred(void) + if (!test_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags)) { + trace_nfsd_cb_restart(clp, cb); + task->tk_status = 0; + set_bit(NFSD4_CALLBACK_REQUEUE, &cb->cb_flags); + } +} + +static void nfsd41_cb_inflight_begin(struct nfs4_client *clp) { - if (callback_cred) - return 0; - callback_cred = rpc_lookup_machine_cred("nfs"); - if (!callback_cred) - return -ENOMEM; - return 0; + atomic_inc(&clp->cl_cb_inflight); +} + +static void nfsd41_cb_inflight_end(struct nfs4_client *clp) +{ + + atomic_dec_and_wake_up(&clp->cl_cb_inflight); } -static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc_clnt *client, struct nfsd4_session *ses) +static void nfsd41_cb_inflight_wait_complete(struct nfs4_client *clp) +{ + wait_var_event(&clp->cl_cb_inflight, + !atomic_read(&clp->cl_cb_inflight)); +} + +static const struct cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc_clnt *client, struct nfsd4_session *ses) { if (clp->cl_minorversion == 0) { - return get_rpccred(callback_cred); + client->cl_principal = clp->cl_cred.cr_targ_princ ? + clp->cl_cred.cr_targ_princ : "nfs"; + + return get_cred(rpc_machine_cred()); } else { - struct rpc_auth *auth = client->cl_auth; - struct auth_cred acred = {}; + struct cred *kcred; - acred.uid = ses->se_cb_sec.uid; - acred.gid = ses->se_cb_sec.gid; - return auth->au_ops->lookup_cred(client->cl_auth, &acred, 0); + kcred = prepare_kernel_cred(&init_task); + if (!kcred) + return NULL; + + kcred->fsuid = ses->se_cb_sec.uid; + kcred->fsgid = ses->se_cb_sec.gid; + return kcred; } } static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses) { + int maxtime = max_cb_time(clp->net); struct rpc_timeout timeparms = { - .to_initval = max_cb_time(clp->net), + .to_initval = maxtime, .to_retries = 0, + .to_maxval = maxtime, }; struct rpc_create_args args = { .net = clp->net, @@ -648,64 +1153,78 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c .saddress = (struct sockaddr *) &conn->cb_saddr, .timeout = &timeparms, .program = &cb_program, - .version = 0, + .version = 1, .flags = (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET), + .cred = current_cred(), }; struct rpc_clnt *client; - struct rpc_cred *cred; + const struct cred *cred; if (clp->cl_minorversion == 0) { if (!clp->cl_cred.cr_principal && - (clp->cl_cred.cr_flavor >= RPC_AUTH_GSS_KRB5)) + (clp->cl_cred.cr_flavor >= RPC_AUTH_GSS_KRB5)) { + trace_nfsd_cb_setup_err(clp, -EINVAL); return -EINVAL; + } args.client_name = clp->cl_cred.cr_principal; - args.prognumber = conn->cb_prog, + args.prognumber = conn->cb_prog; args.protocol = XPRT_TRANSPORT_TCP; args.authflavor = clp->cl_cred.cr_flavor; clp->cl_cb_ident = conn->cb_ident; } else { - if (!conn->cb_xprt) + if (!conn->cb_xprt || !ses) return -EINVAL; - clp->cl_cb_conn.cb_xprt = conn->cb_xprt; clp->cl_cb_session = ses; args.bc_xprt = conn->cb_xprt; args.prognumber = clp->cl_cb_session->se_cb_prog; - args.protocol = XPRT_TRANSPORT_BC_TCP; + args.protocol = conn->cb_xprt->xpt_class->xcl_ident | + XPRT_TRANSPORT_BC; args.authflavor = ses->se_cb_sec.flavor; } /* Create RPC client */ client = rpc_create(&args); if (IS_ERR(client)) { - dprintk("NFSD: couldn't create callback client: %ld\n", - PTR_ERR(client)); + trace_nfsd_cb_setup_err(clp, PTR_ERR(client)); return PTR_ERR(client); } cred = get_backchannel_cred(clp, client, ses); - if (IS_ERR(cred)) { + if (!cred) { + trace_nfsd_cb_setup_err(clp, -ENOMEM); rpc_shutdown_client(client); - return PTR_ERR(cred); + return -ENOMEM; } + + if (clp->cl_minorversion != 0) + clp->cl_cb_conn.cb_xprt = conn->cb_xprt; clp->cl_cb_client = client; clp->cl_cb_cred = cred; + rcu_read_lock(); + trace_nfsd_cb_setup(clp, rpc_peeraddr2str(client, RPC_DISPLAY_NETID), + args.authflavor); + rcu_read_unlock(); return 0; } -static void warn_no_callback_path(struct nfs4_client *clp, int reason) +static void nfsd4_mark_cb_state(struct nfs4_client *clp, int newstate) { - dprintk("NFSD: warning: no callback path to client %.*s: error %d\n", - (int)clp->cl_name.len, clp->cl_name.data, reason); + if (clp->cl_cb_state != newstate) { + clp->cl_cb_state = newstate; + trace_nfsd_cb_new_state(clp); + } } -static void nfsd4_mark_cb_down(struct nfs4_client *clp, int reason) +static void nfsd4_mark_cb_down(struct nfs4_client *clp) { - clp->cl_cb_state = NFSD4_CB_DOWN; - warn_no_callback_path(clp, reason); + if (test_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags)) + return; + nfsd4_mark_cb_state(clp, NFSD4_CB_DOWN); } -static void nfsd4_mark_cb_fault(struct nfs4_client *clp, int reason) +static void nfsd4_mark_cb_fault(struct nfs4_client *clp) { - clp->cl_cb_state = NFSD4_CB_FAULT; - warn_no_callback_path(clp, reason); + if (test_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags)) + return; + nfsd4_mark_cb_state(clp, NFSD4_CB_FAULT); } static void nfsd4_cb_probe_done(struct rpc_task *task, void *calldata) @@ -713,226 +1232,409 @@ static void nfsd4_cb_probe_done(struct rpc_task *task, void *calldata) struct nfs4_client *clp = container_of(calldata, struct nfs4_client, cl_cb_null); if (task->tk_status) - nfsd4_mark_cb_down(clp, task->tk_status); + nfsd4_mark_cb_down(clp); else - clp->cl_cb_state = NFSD4_CB_UP; + nfsd4_mark_cb_state(clp, NFSD4_CB_UP); +} + +static void nfsd4_cb_probe_release(void *calldata) +{ + struct nfs4_client *clp = container_of(calldata, struct nfs4_client, cl_cb_null); + + nfsd41_cb_inflight_end(clp); + } static const struct rpc_call_ops nfsd4_cb_probe_ops = { /* XXX: release method to ensure we set the cb channel down if * necessary on early failure? */ .rpc_call_done = nfsd4_cb_probe_done, + .rpc_release = nfsd4_cb_probe_release, }; -static struct workqueue_struct *callback_wq; - -static void run_nfsd4_cb(struct nfsd4_callback *cb) -{ - queue_work(callback_wq, &cb->cb_work); -} - -static void do_probe_callback(struct nfs4_client *clp) -{ - struct nfsd4_callback *cb = &clp->cl_cb_null; - - cb->cb_op = NULL; - cb->cb_clp = clp; - - cb->cb_msg.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL]; - cb->cb_msg.rpc_argp = NULL; - cb->cb_msg.rpc_resp = NULL; - - cb->cb_ops = &nfsd4_cb_probe_ops; - - run_nfsd4_cb(cb); -} - /* * Poke the callback thread to process any updates to the callback * parameters, and send a null probe. */ void nfsd4_probe_callback(struct nfs4_client *clp) { - clp->cl_cb_state = NFSD4_CB_UNKNOWN; + trace_nfsd_cb_probe(clp); + nfsd4_mark_cb_state(clp, NFSD4_CB_UNKNOWN); set_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags); - do_probe_callback(clp); + nfsd4_run_cb(&clp->cl_cb_null); } void nfsd4_probe_callback_sync(struct nfs4_client *clp) { nfsd4_probe_callback(clp); - flush_workqueue(callback_wq); + flush_workqueue(clp->cl_callback_wq); } void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn) { - clp->cl_cb_state = NFSD4_CB_UNKNOWN; + nfsd4_mark_cb_state(clp, NFSD4_CB_UNKNOWN); spin_lock(&clp->cl_lock); memcpy(&clp->cl_cb_conn, conn, sizeof(struct nfs4_cb_conn)); spin_unlock(&clp->cl_lock); } +static int grab_slot(struct nfsd4_session *ses) +{ + int idx; + + spin_lock(&ses->se_lock); + idx = ffs(ses->se_cb_slot_avail) - 1; + if (idx < 0 || idx > ses->se_cb_highest_slot) { + spin_unlock(&ses->se_lock); + return -1; + } + /* clear the bit for the slot */ + ses->se_cb_slot_avail &= ~BIT(idx); + spin_unlock(&ses->se_lock); + return idx; +} + /* * 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 bool nfsd41_cb_get_slot(struct nfs4_client *clp, struct rpc_task *task) +static bool nfsd41_cb_get_slot(struct nfsd4_callback *cb, struct rpc_task *task) { - if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) { + struct nfs4_client *clp = cb->cb_clp; + struct nfsd4_session *ses = clp->cl_cb_session; + + if (cb->cb_held_slot >= 0) + return true; + cb->cb_held_slot = grab_slot(ses); + if (cb->cb_held_slot < 0) { rpc_sleep_on(&clp->cl_cb_waitq, task, NULL); - dprintk("%s slot is busy\n", __func__); - return false; + /* Race breaker */ + cb->cb_held_slot = grab_slot(ses); + if (cb->cb_held_slot < 0) + return false; + rpc_wake_up_queued_task(&clp->cl_cb_waitq, task); } return true; } -/* - * 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) +static void nfsd41_cb_release_slot(struct nfsd4_callback *cb) { - struct nfsd4_callback *cb = calldata; struct nfs4_client *clp = cb->cb_clp; - u32 minorversion = clp->cl_minorversion; + struct nfsd4_session *ses = clp->cl_cb_session; - cb->cb_minorversion = minorversion; - if (minorversion) { - if (!nfsd41_cb_get_slot(clp, task)) - return; - } - spin_lock(&clp->cl_lock); - if (list_empty(&cb->cb_per_client)) { - /* This is the first call, not a restart */ - cb->cb_done = false; - list_add(&cb->cb_per_client, &clp->cl_callbacks); + if (cb->cb_held_slot >= 0) { + spin_lock(&ses->se_lock); + ses->se_cb_slot_avail |= BIT(cb->cb_held_slot); + spin_unlock(&ses->se_lock); + cb->cb_held_slot = -1; + rpc_wake_up_next(&clp->cl_cb_waitq); } - spin_unlock(&clp->cl_lock); - rpc_call_start(task); } -static void nfsd4_cb_done(struct rpc_task *task, void *calldata) +static void nfsd41_destroy_cb(struct nfsd4_callback *cb) { - struct nfsd4_callback *cb = calldata; struct nfs4_client *clp = cb->cb_clp; - dprintk("%s: minorversion=%d\n", __func__, - clp->cl_minorversion); + trace_nfsd_cb_destroy(clp, cb); + nfsd41_cb_release_slot(cb); + if (test_bit(NFSD4_CALLBACK_WAKE, &cb->cb_flags)) + clear_and_wake_up_bit(NFSD4_CALLBACK_RUNNING, &cb->cb_flags); + else + clear_bit(NFSD4_CALLBACK_RUNNING, &cb->cb_flags); - if (clp->cl_minorversion) { - /* No need for lock, access serialized in nfsd4_cb_prepare */ - ++clp->cl_cb_session->se_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_session->se_cb_seq_nr); + if (cb->cb_ops && cb->cb_ops->release) + cb->cb_ops->release(cb); + nfsd41_cb_inflight_end(clp); +} + +/** + * nfsd41_cb_referring_call - add a referring call to a callback operation + * @cb: context of callback to add the rc to + * @sessionid: referring call's session ID + * @slotid: referring call's session slot index + * @seqno: referring call's slot sequence number + * + * Caller serializes access to @cb. + * + * NB: If memory allocation fails, the referring call is not added. + */ +void nfsd41_cb_referring_call(struct nfsd4_callback *cb, + struct nfs4_sessionid *sessionid, + u32 slotid, u32 seqno) +{ + struct nfsd4_referring_call_list *rcl; + struct nfsd4_referring_call *rc; + bool found; + + might_sleep(); + + found = false; + list_for_each_entry(rcl, &cb->cb_referring_call_list, __list) { + if (!memcmp(rcl->rcl_sessionid.data, sessionid->data, + NFS4_MAX_SESSIONID_LEN)) { + found = true; + break; + } + } + if (!found) { + rcl = kmalloc(sizeof(*rcl), GFP_KERNEL); + if (!rcl) + return; + memcpy(rcl->rcl_sessionid.data, sessionid->data, + NFS4_MAX_SESSIONID_LEN); + rcl->__nr_referring_calls = 0; + INIT_LIST_HEAD(&rcl->rcl_referring_calls); + list_add(&rcl->__list, &cb->cb_referring_call_list); + cb->cb_nr_referring_call_list++; + } - /* We're done looking into the sequence information */ - task->tk_msg.rpc_resp = NULL; + found = false; + list_for_each_entry(rc, &rcl->rcl_referring_calls, __list) { + if (rc->rc_sequenceid == seqno && rc->rc_slotid == slotid) { + found = true; + break; + } + } + if (!found) { + rc = kmalloc(sizeof(*rc), GFP_KERNEL); + if (!rc) + goto out; + rc->rc_sequenceid = seqno; + rc->rc_slotid = slotid; + rcl->__nr_referring_calls++; + list_add(&rc->__list, &rcl->rcl_referring_calls); + } + +out: + if (!rcl->__nr_referring_calls) { + cb->cb_nr_referring_call_list--; + list_del(&rcl->__list); + kfree(rcl); } } +/** + * nfsd41_cb_destroy_referring_call_list - release referring call info + * @cb: context of a callback that has completed + * + * Callers who allocate referring calls using nfsd41_cb_referring_call() must + * release those resources by calling nfsd41_cb_destroy_referring_call_list. + * + * Caller serializes access to @cb. + */ +void nfsd41_cb_destroy_referring_call_list(struct nfsd4_callback *cb) +{ + struct nfsd4_referring_call_list *rcl; + struct nfsd4_referring_call *rc; + + while (!list_empty(&cb->cb_referring_call_list)) { + rcl = list_first_entry(&cb->cb_referring_call_list, + struct nfsd4_referring_call_list, + __list); + + while (!list_empty(&rcl->rcl_referring_calls)) { + rc = list_first_entry(&rcl->rcl_referring_calls, + struct nfsd4_referring_call, + __list); + list_del(&rc->__list); + kfree(rc); + } + list_del(&rcl->__list); + kfree(rcl); + } +} -static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata) +static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) { struct nfsd4_callback *cb = calldata; - struct nfs4_delegation *dp = container_of(cb, struct nfs4_delegation, dl_recall); struct nfs4_client *clp = cb->cb_clp; - struct rpc_clnt *current_rpc_client = clp->cl_cb_client; - - nfsd4_cb_done(task, calldata); + u32 minorversion = clp->cl_minorversion; - if (current_rpc_client != task->tk_client) { - /* We're shutting down or changing cl_cb_client; leave - * it to nfsd4_process_cb_update to restart the call if - * necessary. */ + /* + * cb_seq_status is only set in decode_cb_sequence4res, + * and so will remain 1 if an rpc level failure occurs. + */ + trace_nfsd_cb_rpc_prepare(clp); + cb->cb_seq_status = 1; + cb->cb_status = 0; + if (minorversion && !nfsd41_cb_get_slot(cb, task)) return; - } + rpc_call_start(task); +} - if (cb->cb_done) - return; - switch (task->tk_status) { +/* Returns true if CB_COMPOUND processing should continue */ +static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback *cb) +{ + struct nfsd4_session *session = cb->cb_clp->cl_cb_session; + bool ret = false; + + if (cb->cb_held_slot < 0) + goto requeue; + + /* This is the operation status code for CB_SEQUENCE */ + trace_nfsd_cb_seq_status(task, cb); + switch (cb->cb_seq_status) { case 0: - cb->cb_done = true; - return; - case -EBADHANDLE: - case -NFS4ERR_BAD_STATEID: - /* Race: client probably got cb_recall - * before open reply granting delegation */ + /* + * No need for lock, access serialized in nfsd4_cb_prepare + * + * RFC5661 20.9.3 + * If CB_SEQUENCE returns an error, then the state of the slot + * (sequence ID, cached reply) MUST NOT change. + */ + ++session->se_cb_seq_nr[cb->cb_held_slot]; + ret = true; + break; + case -ESERVERFAULT: + /* + * Call succeeded, but the session, slot index, or slot + * sequence number in the response do not match the same + * in the server's call. The sequence information is thus + * untrustworthy. + */ + nfsd4_mark_cb_fault(cb->cb_clp); break; + case 1: + /* + * cb_seq_status remains 1 if an RPC Reply was never + * received. NFSD can't know if the client processed + * the CB_SEQUENCE operation. Ask the client to send a + * DESTROY_SESSION to recover. + */ + fallthrough; + case -NFS4ERR_BADSESSION: + nfsd4_mark_cb_fault(cb->cb_clp); + goto requeue; + case -NFS4ERR_DELAY: + cb->cb_seq_status = 1; + if (RPC_SIGNALLED(task) || !rpc_restart_call(task)) + goto requeue; + rpc_delay(task, 2 * HZ); + return false; + case -NFS4ERR_SEQ_MISORDERED: + case -NFS4ERR_BADSLOT: + /* + * A SEQ_MISORDERED or BADSLOT error means that the client and + * server are out of sync as to the backchannel parameters. Mark + * the backchannel faulty and restart the RPC, but leak the slot + * so that it's no longer used. + */ + nfsd4_mark_cb_fault(cb->cb_clp); + cb->cb_held_slot = -1; + goto retry_nowait; default: - /* Network partition? */ - nfsd4_mark_cb_down(clp, task->tk_status); + nfsd4_mark_cb_fault(cb->cb_clp); } - if (dp->dl_retries--) { - rpc_delay(task, 2*HZ); - task->tk_status = 0; - rpc_restart_call_prepare(task); - return; + trace_nfsd_cb_free_slot(task, cb); + nfsd41_cb_release_slot(cb); + return ret; +retry_nowait: + /* + * RPC_SIGNALLED() means that the rpc_client is being torn down and + * (possibly) recreated. Requeue the call in that case. + */ + if (!RPC_SIGNALLED(task)) { + if (rpc_restart_call_prepare(task)) + return false; } - nfsd4_mark_cb_down(clp, task->tk_status); - cb->cb_done = true; +requeue: + nfsd41_cb_release_slot(cb); + nfsd4_requeue_cb(task, cb); + return false; } -static void nfsd4_cb_recall_release(void *calldata) +static void nfsd4_cb_done(struct rpc_task *task, void *calldata) { struct nfsd4_callback *cb = calldata; struct nfs4_client *clp = cb->cb_clp; - struct nfs4_delegation *dp = container_of(cb, struct nfs4_delegation, dl_recall); - if (cb->cb_done) { - spin_lock(&clp->cl_lock); - list_del(&cb->cb_per_client); - spin_unlock(&clp->cl_lock); - nfs4_put_delegation(dp); + trace_nfsd_cb_rpc_done(clp); + + if (!clp->cl_minorversion) { + /* + * If the backchannel connection was shut down while this + * task was queued, we need to resubmit it after setting up + * a new backchannel connection. + * + * Note that if we lost our callback connection permanently + * the submission code will error out, so we don't need to + * handle that case here. + */ + if (RPC_SIGNALLED(task)) + nfsd4_requeue_cb(task, cb); + } else if (!nfsd4_cb_sequence_done(task, cb)) { + return; } -} -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, -}; + if (cb->cb_status) { + WARN_ONCE(task->tk_status, + "cb_status=%d tk_status=%d cb_opcode=%d", + cb->cb_status, task->tk_status, cb->cb_ops->opcode); + task->tk_status = cb->cb_status; + } -int nfsd4_create_callback_queue(void) -{ - callback_wq = create_singlethread_workqueue("nfsd4_callbacks"); - if (!callback_wq) - return -ENOMEM; - return 0; + switch (cb->cb_ops->done(cb, task)) { + case 0: + task->tk_status = 0; + rpc_restart_call_prepare(task); + return; + case 1: + switch (task->tk_status) { + case -EIO: + case -ETIMEDOUT: + case -EACCES: + nfsd4_mark_cb_down(clp); + } + break; + default: + BUG(); + } } -void nfsd4_destroy_callback_queue(void) +static void nfsd4_cb_release(void *calldata) { - destroy_workqueue(callback_wq); + struct nfsd4_callback *cb = calldata; + + trace_nfsd_cb_rpc_release(cb->cb_clp); + + if (test_bit(NFSD4_CALLBACK_REQUEUE, &cb->cb_flags)) + nfsd4_queue_cb(cb); + else + nfsd41_destroy_cb(cb); + } +static const struct rpc_call_ops nfsd4_cb_ops = { + .rpc_call_prepare = nfsd4_cb_prepare, + .rpc_call_done = nfsd4_cb_done, + .rpc_release = nfsd4_cb_release, +}; + /* must be called under the state lock */ void nfsd4_shutdown_callback(struct nfs4_client *clp) { + if (clp->cl_cb_state != NFSD4_CB_UNKNOWN) + trace_nfsd_cb_shutdown(clp); + set_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags); /* * Note this won't actually result in a null callback; - * instead, nfsd4_do_callback_rpc() will detect the killed + * instead, nfsd4_run_cb_null() will detect the killed * client, destroy the rpc client, and stop: */ - do_probe_callback(clp); - flush_workqueue(callback_wq); -} - -static void nfsd4_release_cb(struct nfsd4_callback *cb) -{ - if (cb->cb_ops->rpc_release) - cb->cb_ops->rpc_release(cb); + nfsd4_run_cb(&clp->cl_cb_null); + flush_workqueue(clp->cl_callback_wq); + nfsd41_cb_inflight_wait_complete(clp); } -/* requires cl_lock: */ static struct nfsd4_conn * __nfsd4_find_backchannel(struct nfs4_client *clp) { struct nfsd4_session *s; struct nfsd4_conn *c; + lockdep_assert_held(&clp->cl_lock); + list_for_each_entry(s, &clp->cl_sessions, se_perclnt) { list_for_each_entry(c, &s->se_conns, cn_persession) { if (c->cn_flags & NFS4_CDFC4_BACK) @@ -942,6 +1644,12 @@ static struct nfsd4_conn * __nfsd4_find_backchannel(struct nfs4_client *clp) return NULL; } +/* + * Note there isn't a lot of locking in this code; instead we depend on + * the fact that it is run from clp->cl_callback_wq, which won't run two + * work items at once. So, for example, clp->cl_callback_wq handles all + * access of cl_cb_client and all calls to rpc_create or rpc_shutdown_client. + */ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) { struct nfs4_cb_conn conn; @@ -950,14 +1658,17 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) struct nfsd4_conn *c; int err; + trace_nfsd_cb_bc_update(clp, cb); + /* * This is either an update, or the client dying; in either case, * kill the old client: */ if (clp->cl_cb_client) { + trace_nfsd_cb_bc_shutdown(clp, cb); rpc_shutdown_client(clp->cl_cb_client); clp->cl_cb_client = NULL; - put_rpccred(clp->cl_cb_cred); + put_cred(clp->cl_cb_cred); clp->cl_cb_cred = NULL; } if (clp->cl_cb_conn.cb_xprt) { @@ -966,13 +1677,15 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) } if (test_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags)) return; + spin_lock(&clp->cl_lock); /* * Only serialized callback code is allowed to clear these * flags; main nfsd code can only set them: */ - BUG_ON(!(clp->cl_flags & NFSD4_CLIENT_CB_FLAG_MASK)); + WARN_ON(!(clp->cl_flags & NFSD4_CLIENT_CB_FLAG_MASK)); clear_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags); + memcpy(&conn, &cb->cb_clp->cl_cb_conn, sizeof(struct nfs4_cb_conn)); c = __nfsd4_find_backchannel(clp); if (c) { @@ -984,55 +1697,92 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) err = setup_callback_client(clp, &conn, ses); if (err) { - nfsd4_mark_cb_down(clp, err); + nfsd4_mark_cb_down(clp); + if (c) + svc_xprt_put(c->cn_xprt); return; } - /* Yay, the callback channel's back! Restart any callbacks: */ - list_for_each_entry(cb, &clp->cl_callbacks, cb_per_client) - run_nfsd4_cb(cb); } -static void nfsd4_do_callback_rpc(struct work_struct *w) +static void +nfsd4_run_cb_work(struct work_struct *work) { - struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback, cb_work); + struct nfsd4_callback *cb = + container_of(work, struct nfsd4_callback, cb_work); struct nfs4_client *clp = cb->cb_clp; struct rpc_clnt *clnt; + int flags, ret; + + trace_nfsd_cb_start(clp); if (clp->cl_flags & NFSD4_CLIENT_CB_FLAG_MASK) nfsd4_process_cb_update(cb); clnt = clp->cl_cb_client; - if (!clnt) { - /* Callback channel broken, or client killed; give up: */ - nfsd4_release_cb(cb); + if (!clnt || clp->cl_state == NFSD4_COURTESY) { + /* + * Callback channel broken, client killed or + * nfs4_client in courtesy state; give up. + */ + nfsd41_destroy_cb(cb); return; } - cb->cb_msg.rpc_cred = clp->cl_cb_cred; - rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | RPC_TASK_SOFTCONN, - cb->cb_ops, cb); -} -void nfsd4_init_callback(struct nfsd4_callback *cb) -{ - INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc); + /* + * Don't send probe messages for 4.1 or later. + */ + if (!cb->cb_ops && clp->cl_minorversion) { + nfsd4_mark_cb_state(clp, NFSD4_CB_UP); + nfsd41_destroy_cb(cb); + return; + } + + if (!test_and_clear_bit(NFSD4_CALLBACK_REQUEUE, &cb->cb_flags)) { + if (cb->cb_ops && cb->cb_ops->prepare) + cb->cb_ops->prepare(cb); + } + + cb->cb_msg.rpc_cred = clp->cl_cb_cred; + flags = clp->cl_minorversion ? RPC_TASK_NOCONNECT : RPC_TASK_SOFTCONN; + ret = rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | flags, + cb->cb_ops ? &nfsd4_cb_ops : &nfsd4_cb_probe_ops, cb); + if (ret != 0) { + set_bit(NFSD4_CALLBACK_REQUEUE, &cb->cb_flags); + nfsd4_queue_cb(cb); + } } -void nfsd4_cb_recall(struct nfs4_delegation *dp) +void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, + const struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op) { - struct nfsd4_callback *cb = &dp->dl_recall; - struct nfs4_client *clp = dp->dl_stid.sc_client; - - dp->dl_retries = 1; - cb->cb_op = dp; cb->cb_clp = clp; - cb->cb_msg.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_RECALL]; + cb->cb_msg.rpc_proc = &nfs4_cb_procedures[op]; cb->cb_msg.rpc_argp = cb; cb->cb_msg.rpc_resp = cb; + cb->cb_flags = 0; + cb->cb_ops = ops; + INIT_WORK(&cb->cb_work, nfsd4_run_cb_work); + cb->cb_status = 0; + cb->cb_held_slot = -1; + cb->cb_nr_referring_call_list = 0; + INIT_LIST_HEAD(&cb->cb_referring_call_list); +} - cb->cb_ops = &nfsd4_cb_recall_ops; - - INIT_LIST_HEAD(&cb->cb_per_client); - cb->cb_done = true; +/** + * nfsd4_run_cb - queue up a callback job to run + * @cb: callback to queue + * + * Kick off a callback to do its thing. Returns false if it was already + * on a queue, true otherwise. + */ +bool nfsd4_run_cb(struct nfsd4_callback *cb) +{ + struct nfs4_client *clp = cb->cb_clp; + bool queued; - run_nfsd4_cb(&dp->dl_recall); + nfsd41_cb_inflight_begin(clp); + queued = nfsd4_queue_cb(cb); + if (!queued) + nfsd41_cb_inflight_end(clp); + return queued; } |