diff --git a/Documentation/filesystems/nfs/knfsd-stats.txt b/Documentation/filesystems/nfs/knfsd-stats.txt index 64ced5149d37..1a5d82180b84 100644 --- a/Documentation/filesystems/nfs/knfsd-stats.txt +++ b/Documentation/filesystems/nfs/knfsd-stats.txt @@ -68,16 +68,10 @@ sockets-enqueued rate of change for this counter is zero; significantly non-zero values may indicate a performance limitation. - This can happen either because there are too few nfsd threads in the - thread pool for the NFS workload (the workload is thread-limited), - or because the NFS workload needs more CPU time than is available in - the thread pool (the workload is CPU-limited). In the former case, - configuring more nfsd threads will probably improve the performance - of the NFS workload. In the latter case, the sunrpc server layer is - already choosing not to wake idle nfsd threads because there are too - many nfsd threads which want to run but cannot, so configuring more - nfsd threads will make no difference whatsoever. The overloads-avoided - statistic (see below) can be used to distinguish these cases. + This can happen because there are too few nfsd threads in the thread + pool for the NFS workload (the workload is thread-limited), in which + case configuring more nfsd threads will probably improve the + performance of the NFS workload. threads-woken Counts how many times an idle nfsd thread is woken to try to @@ -88,36 +82,6 @@ threads-woken thing. The ideal rate of change for this counter will be close to but less than the rate of change of the packets-arrived counter. -overloads-avoided - Counts how many times the sunrpc server layer chose not to wake an - nfsd thread, despite the presence of idle nfsd threads, because - too many nfsd threads had been recently woken but could not get - enough CPU time to actually run. - - This statistic counts a circumstance where the sunrpc layer - heuristically avoids overloading the CPU scheduler with too many - runnable nfsd threads. The ideal rate of change for this counter - is zero. Significant non-zero values indicate that the workload - is CPU limited. Usually this is associated with heavy CPU usage - on all the CPUs in the nfsd thread pool. - - If a sustained large overloads-avoided rate is detected on a pool, - the top(1) utility should be used to check for the following - pattern of CPU usage on all the CPUs associated with the given - nfsd thread pool. - - - %us ~= 0 (as you're *NOT* running applications on your NFS server) - - - %wa ~= 0 - - - %id ~= 0 - - - %sy + %hi + %si ~= 100 - - If this pattern is seen, configuring more nfsd threads will *not* - improve the performance of the workload. If this patten is not - seen, then something more subtle is wrong. - threads-timedout Counts how many times an nfsd thread triggered an idle timeout, i.e. was not woken to handle any incoming network packets for diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index e4b2b4322553..f6e7cbabac5a 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -805,7 +805,7 @@ encode_entry_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name, static __be32 compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp, - const char *name, int namlen) + const char *name, int namlen, u64 ino) { struct svc_export *exp; struct dentry *dparent, *dchild; @@ -830,19 +830,21 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp, goto out; if (d_really_is_negative(dchild)) goto out; + if (dchild->d_inode->i_ino != ino) + goto out; rv = fh_compose(fhp, exp, dchild, &cd->fh); out: dput(dchild); return rv; } -static __be32 *encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name, int namlen) +static __be32 *encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name, int namlen, u64 ino) { struct svc_fh *fh = &cd->scratch; __be32 err; fh_init(fh, NFS3_FHSIZE); - err = compose_entry_fh(cd, fh, name, namlen); + err = compose_entry_fh(cd, fh, name, namlen, ino); if (err) { *p++ = 0; *p++ = 0; @@ -927,7 +929,7 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen, p = encode_entry_baggage(cd, p, name, namlen, ino); if (plus) - p = encode_entryplus_baggage(cd, p, name, namlen); + p = encode_entryplus_baggage(cd, p, name, namlen, ino); num_entry_words = p - cd->buffer; } else if (*(page+1) != NULL) { /* temporarily encode entry into next page, then move back to @@ -941,7 +943,7 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen, p1 = encode_entry_baggage(cd, p1, name, namlen, ino); if (plus) - p1 = encode_entryplus_baggage(cd, p1, name, namlen); + p1 = encode_entryplus_baggage(cd, p1, name, namlen, ino); /* determine entry word length and lengths to go in pages */ num_entry_words = p1 - tmp; diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index 67242bf7c6cc..eb5accf1b37f 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -52,10 +52,6 @@ #define NFS4_ANYONE_MODE (NFS4_ACE_READ_ATTRIBUTES | NFS4_ACE_READ_ACL | NFS4_ACE_SYNCHRONIZE) #define NFS4_OWNER_MODE (NFS4_ACE_WRITE_ATTRIBUTES | NFS4_ACE_WRITE_ACL) -/* We don't support these bits; insist they be neither allowed nor denied */ -#define NFS4_MASK_UNSUPP (NFS4_ACE_DELETE | NFS4_ACE_WRITE_OWNER \ - | NFS4_ACE_READ_NAMED_ATTRS | NFS4_ACE_WRITE_NAMED_ATTRS) - /* flags used to simulate posix default ACLs */ #define NFS4_INHERITANCE_FLAGS (NFS4_ACE_FILE_INHERIT_ACE \ | NFS4_ACE_DIRECTORY_INHERIT_ACE) @@ -64,9 +60,6 @@ | NFS4_ACE_INHERIT_ONLY_ACE \ | NFS4_ACE_IDENTIFIER_GROUP) -#define MASK_EQUAL(mask1, mask2) \ - ( ((mask1) & NFS4_ACE_MASK_ALL) == ((mask2) & NFS4_ACE_MASK_ALL) ) - static u32 mask_from_posix(unsigned short perm, unsigned int flags) { @@ -126,11 +119,6 @@ low_mode_from_nfs4(u32 perm, unsigned short *mode, unsigned int flags) *mode |= ACL_EXECUTE; } -struct ace_container { - struct nfs4_ace *ace; - struct list_head ace_l; -}; - static short ace2type(struct nfs4_ace *); static void _posix_to_nfsv4_one(struct posix_acl *, struct nfs4_acl *, unsigned int); @@ -384,7 +372,6 @@ pace_gt(struct posix_acl_entry *pace1, struct posix_acl_entry *pace2) static void sort_pacl_range(struct posix_acl *pacl, int start, int end) { int sorted = 0, i; - struct posix_acl_entry tmp; /* We just do a bubble sort; easy to do in place, and we're not * expecting acl's to be long enough to justify anything more. */ @@ -394,9 +381,8 @@ sort_pacl_range(struct posix_acl *pacl, int start, int end) { if (pace_gt(&pacl->a_entries[i], &pacl->a_entries[i+1])) { sorted = 0; - tmp = pacl->a_entries[i]; - pacl->a_entries[i] = pacl->a_entries[i+1]; - pacl->a_entries[i+1] = tmp; + swap(pacl->a_entries[i], + pacl->a_entries[i + 1]); } } } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 5694cfb7a47b..a49201835a97 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -455,6 +455,7 @@ static int decode_cb_sequence4res(struct xdr_stream *xdr, if (unlikely(status || cb->cb_status)) return status; + cb->cb_update_seq_nr = true; return decode_cb_sequence4resok(xdr, cb); } @@ -875,6 +876,8 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) u32 minorversion = clp->cl_minorversion; cb->cb_minorversion = minorversion; + cb->cb_update_seq_nr = false; + cb->cb_status = 0; if (minorversion) { if (!nfsd41_cb_get_slot(clp, task)) return; @@ -891,9 +894,16 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata) clp->cl_minorversion); if (clp->cl_minorversion) { - /* No need for lock, access serialized in nfsd4_cb_prepare */ - if (!task->tk_status) + /* + * 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. + */ + if (cb->cb_update_seq_nr) ++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__, @@ -1090,6 +1100,7 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, cb->cb_ops = ops; INIT_WORK(&cb->cb_work, nfsd4_run_cb_work); cb->cb_status = 0; + cb->cb_update_seq_nr = false; cb->cb_need_restart = false; } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 864e2003e8de..90cfda75313c 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -760,8 +760,6 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, { __be32 status; - /* no need to check permission - this will be done in nfsd_read() */ - read->rd_filp = NULL; if (read->rd_offset >= OFFSET_MAX) return nfserr_inval; @@ -778,9 +776,9 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); /* check stateid */ - if ((status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), - cstate, &read->rd_stateid, - RD_STATE, &read->rd_filp))) { + status = nfs4_preprocess_stateid_op(rqstp, cstate, &read->rd_stateid, + RD_STATE, &read->rd_filp, &read->rd_tmp_file); + if (status) { dprintk("NFSD: nfsd4_read: couldn't process stateid!\n"); goto out; } @@ -924,8 +922,8 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, int err; if (setattr->sa_iattr.ia_valid & ATTR_SIZE) { - status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate, - &setattr->sa_stateid, WR_STATE, NULL); + status = nfs4_preprocess_stateid_op(rqstp, cstate, + &setattr->sa_stateid, WR_STATE, NULL, NULL); if (status) { dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n"); return status; @@ -986,13 +984,11 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, unsigned long cnt; int nvecs; - /* no need to check permission - this will be done in nfsd_write() */ - if (write->wr_offset >= OFFSET_MAX) return nfserr_inval; - status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), - cstate, stateid, WR_STATE, &filp); + status = nfs4_preprocess_stateid_op(rqstp, cstate, stateid, WR_STATE, + &filp, NULL); if (status) { dprintk("NFSD: nfsd4_write: couldn't process stateid!\n"); return status; @@ -1005,11 +1001,10 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nvecs = fill_in_write_vector(rqstp->rq_vec, write); WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec)); - status = nfsd_write(rqstp, &cstate->current_fh, filp, - write->wr_offset, rqstp->rq_vec, nvecs, - &cnt, &write->wr_how_written); - if (filp) - fput(filp); + status = nfsd_vfs_write(rqstp, &cstate->current_fh, filp, + write->wr_offset, rqstp->rq_vec, nvecs, &cnt, + &write->wr_how_written); + fput(filp); write->wr_bytes_written = cnt; @@ -1023,15 +1018,13 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status = nfserr_notsupp; struct file *file; - status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate, + status = nfs4_preprocess_stateid_op(rqstp, cstate, &fallocate->falloc_stateid, - WR_STATE, &file); + WR_STATE, &file, NULL); if (status != nfs_ok) { dprintk("NFSD: nfsd4_fallocate: couldn't process stateid!\n"); return status; } - if (!file) - return nfserr_bad_stateid; status = nfsd4_vfs_fallocate(rqstp, &cstate->current_fh, file, fallocate->falloc_offset, @@ -1064,15 +1057,13 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct file *file; - status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate, + status = nfs4_preprocess_stateid_op(rqstp, cstate, &seek->seek_stateid, - RD_STATE, &file); + RD_STATE, &file, NULL); if (status) { dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n"); return status; } - if (!file) - return nfserr_bad_stateid; switch (seek->seek_whence) { case NFS4_CONTENT_DATA: @@ -1732,10 +1723,6 @@ encode_op: be32_to_cpu(status)); nfsd4_cstate_clear_replay(cstate); - /* XXX Ugh, we need to get rid of this kind of special case: */ - if (op->opnum == OP_READ && op->u.read.rd_filp) - fput(op->u.read.rd_filp); - nfsd4_increment_op_stats(op->opnum); } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 039f9c8a95e8..61dfb33f0559 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3861,7 +3861,7 @@ static __be32 nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, struct nfsd4_open *open) { __be32 status; - unsigned char old_deny_bmap; + unsigned char old_deny_bmap = stp->st_deny_bmap; if (!test_access(open->op_share_access, stp)) return nfs4_get_vfs_file(rqstp, fp, cur_fh, stp, open); @@ -3870,7 +3870,6 @@ nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *c spin_lock(&fp->fi_lock); status = nfs4_file_check_deny(fp, open->op_share_deny); if (status == nfs_ok) { - old_deny_bmap = stp->st_deny_bmap; set_deny(open->op_share_deny, stp); fp->fi_share_deny |= (open->op_share_deny & NFS4_SHARE_DENY_BOTH); @@ -4574,85 +4573,130 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, return nfs_ok; } -/* -* Checks for stateid operations -*/ -__be32 -nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate, - stateid_t *stateid, int flags, struct file **filpp) +static struct file * +nfs4_find_file(struct nfs4_stid *s, int flags) { - struct nfs4_stid *s; - struct nfs4_ol_stateid *stp = NULL; - struct nfs4_delegation *dp = NULL; - struct svc_fh *current_fh = &cstate->current_fh; - struct inode *ino = d_inode(current_fh->fh_dentry); + if (!s) + return NULL; + + switch (s->sc_type) { + case NFS4_DELEG_STID: + if (WARN_ON_ONCE(!s->sc_file->fi_deleg_file)) + return NULL; + return get_file(s->sc_file->fi_deleg_file); + case NFS4_OPEN_STID: + case NFS4_LOCK_STID: + if (flags & RD_STATE) + return find_readable_file(s->sc_file); + else + return find_writeable_file(s->sc_file); + break; + } + + return NULL; +} + +static __be32 +nfs4_check_olstateid(struct svc_fh *fhp, struct nfs4_ol_stateid *ols, int flags) +{ + __be32 status; + + status = nfs4_check_fh(fhp, ols); + if (status) + return status; + status = nfsd4_check_openowner_confirmed(ols); + if (status) + return status; + return nfs4_check_openmode(ols, flags); +} + +static __be32 +nfs4_check_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfs4_stid *s, + struct file **filpp, bool *tmp_file, int flags) +{ + int acc = (flags & RD_STATE) ? NFSD_MAY_READ : NFSD_MAY_WRITE; + struct file *file; + __be32 status; + + file = nfs4_find_file(s, flags); + if (file) { + status = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry, + acc | NFSD_MAY_OWNER_OVERRIDE); + if (status) { + fput(file); + return status; + } + + *filpp = file; + } else { + status = nfsd_open(rqstp, fhp, S_IFREG, acc, filpp); + if (status) + return status; + + if (tmp_file) + *tmp_file = true; + } + + return 0; +} + +/* + * Checks for stateid operations + */ +__be32 +nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, stateid_t *stateid, + int flags, struct file **filpp, bool *tmp_file) +{ + struct svc_fh *fhp = &cstate->current_fh; + struct inode *ino = d_inode(fhp->fh_dentry); + struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); - struct file *file = NULL; + struct nfs4_stid *s = NULL; __be32 status; if (filpp) *filpp = NULL; + if (tmp_file) + *tmp_file = false; if (grace_disallows_io(net, ino)) return nfserr_grace; - if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) - return check_special_stateids(net, current_fh, stateid, flags); + if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) { + status = check_special_stateids(net, fhp, stateid, flags); + goto done; + } status = nfsd4_lookup_stateid(cstate, stateid, NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID, &s, nn); if (status) return status; - status = check_stateid_generation(stateid, &s->sc_stateid, nfsd4_has_session(cstate)); + status = check_stateid_generation(stateid, &s->sc_stateid, + nfsd4_has_session(cstate)); if (status) goto out; + switch (s->sc_type) { case NFS4_DELEG_STID: - dp = delegstateid(s); - status = nfs4_check_delegmode(dp, flags); - if (status) - goto out; - if (filpp) { - file = dp->dl_stid.sc_file->fi_deleg_file; - if (!file) { - WARN_ON_ONCE(1); - status = nfserr_serverfault; - goto out; - } - get_file(file); - } + status = nfs4_check_delegmode(delegstateid(s), flags); break; case NFS4_OPEN_STID: case NFS4_LOCK_STID: - stp = openlockstateid(s); - status = nfs4_check_fh(current_fh, stp); - if (status) - goto out; - status = nfsd4_check_openowner_confirmed(stp); - if (status) - goto out; - status = nfs4_check_openmode(stp, flags); - if (status) - goto out; - if (filpp) { - struct nfs4_file *fp = stp->st_stid.sc_file; - - if (flags & RD_STATE) - file = find_readable_file(fp); - else - file = find_writeable_file(fp); - } + status = nfs4_check_olstateid(fhp, openlockstateid(s), flags); break; default: status = nfserr_bad_stateid; - goto out; + break; } - status = nfs_ok; - if (file) - *filpp = file; + +done: + if (!status && filpp) + status = nfs4_check_file(rqstp, fhp, s, filpp, tmp_file, flags); out: - nfs4_put_stid(s); + if (s) + nfs4_put_stid(s); return status; } @@ -5505,7 +5549,7 @@ static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct __be32 err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file); if (!err) { err = nfserrno(vfs_test_lock(file, lock)); - nfsd_close(file); + fput(file); } return err; } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 158badf945df..54633858733a 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -33,6 +33,7 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ +#include #include #include #include @@ -2227,7 +2228,6 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, u32 rdattr_err = 0; __be32 status; int err; - int aclsupport = 0; struct nfs4_acl *acl = NULL; void *context = NULL; int contextlen; @@ -2274,19 +2274,15 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, goto out; fhp = tempfh; } - if (bmval0 & (FATTR4_WORD0_ACL | FATTR4_WORD0_ACLSUPPORT - | FATTR4_WORD0_SUPPORTED_ATTRS)) { + if (bmval0 & FATTR4_WORD0_ACL) { err = nfsd4_get_nfs4_acl(rqstp, dentry, &acl); - aclsupport = (err == 0); - if (bmval0 & FATTR4_WORD0_ACL) { - if (err == -EOPNOTSUPP) - bmval0 &= ~FATTR4_WORD0_ACL; - else if (err == -EINVAL) { - status = nfserr_attrnotsupp; - goto out; - } else if (err != 0) - goto out_nfserr; - } + if (err == -EOPNOTSUPP) + bmval0 &= ~FATTR4_WORD0_ACL; + else if (err == -EINVAL) { + status = nfserr_attrnotsupp; + goto out; + } else if (err != 0) + goto out_nfserr; } #ifdef CONFIG_NFSD_V4_SECURITY_LABEL @@ -2338,7 +2334,7 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, u32 word1 = nfsd_suppattrs1(minorversion); u32 word2 = nfsd_suppattrs2(minorversion); - if (!aclsupport) + if (!IS_POSIXACL(dentry->d_inode)) word0 &= ~FATTR4_WORD0_ACL; if (!contextsupport) word2 &= ~FATTR4_WORD2_SECURITY_LABEL; @@ -2486,7 +2482,7 @@ out_acl: p = xdr_reserve_space(xdr, 4); if (!p) goto out_resource; - *p++ = cpu_to_be32(aclsupport ? + *p++ = cpu_to_be32(IS_POSIXACL(dentry->d_inode) ? ACL4_SUPPORT_ALLOW_ACL|ACL4_SUPPORT_DENY_ACL : 0); } if (bmval0 & FATTR4_WORD0_CANSETTIME) { @@ -3422,52 +3418,51 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, unsigned long maxcount; struct xdr_stream *xdr = &resp->xdr; struct file *file = read->rd_filp; - struct svc_fh *fhp = read->rd_fhp; int starting_len = xdr->buf->len; - struct raparms *ra; + struct raparms *ra = NULL; __be32 *p; - __be32 err; if (nfserr) - return nfserr; + goto out; p = xdr_reserve_space(xdr, 8); /* eof flag and byte count */ if (!p) { WARN_ON_ONCE(test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)); - return nfserr_resource; + nfserr = nfserr_resource; + goto out; } - if (resp->xdr.buf->page_len && test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) { + if (resp->xdr.buf->page_len && + test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) { WARN_ON_ONCE(1); - return nfserr_resource; + nfserr = nfserr_resource; + goto out; } xdr_commit_encode(xdr); maxcount = svc_max_payload(resp->rqstp); - maxcount = min_t(unsigned long, maxcount, (xdr->buf->buflen - xdr->buf->len)); + maxcount = min_t(unsigned long, maxcount, + (xdr->buf->buflen - xdr->buf->len)); maxcount = min_t(unsigned long, maxcount, read->rd_length); - if (read->rd_filp) - err = nfsd_permission(resp->rqstp, fhp->fh_export, - fhp->fh_dentry, - NFSD_MAY_READ|NFSD_MAY_OWNER_OVERRIDE); + if (read->rd_tmp_file) + ra = nfsd_init_raparms(file); + + if (file->f_op->splice_read && + test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) + nfserr = nfsd4_encode_splice_read(resp, read, file, maxcount); else - err = nfsd_get_tmp_read_open(resp->rqstp, read->rd_fhp, - &file, &ra); - if (err) - goto err_truncate; + nfserr = nfsd4_encode_readv(resp, read, file, maxcount); - if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) - err = nfsd4_encode_splice_read(resp, read, file, maxcount); - else - err = nfsd4_encode_readv(resp, read, file, maxcount); + if (ra) + nfsd_put_raparams(file, ra); - if (!read->rd_filp) - nfsd_put_tmp_read_open(file, ra); - -err_truncate: - if (err) + if (nfserr) xdr_truncate_encode(xdr, starting_len); - return err; + +out: + if (file) + fput(file); + return nfserr; } static __be32 diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index aecbcd34d336..4cd78ef4c95c 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -59,13 +59,61 @@ static __be32 nfsd_proc_setattr(struct svc_rqst *rqstp, struct nfsd_sattrargs *argp, struct nfsd_attrstat *resp) { + struct iattr *iap = &argp->attrs; + struct svc_fh *fhp; __be32 nfserr; + dprintk("nfsd: SETATTR %s, valid=%x, size=%ld\n", SVCFH_fmt(&argp->fh), argp->attrs.ia_valid, (long) argp->attrs.ia_size); - fh_copy(&resp->fh, &argp->fh); - nfserr = nfsd_setattr(rqstp, &resp->fh, &argp->attrs,0, (time_t)0); + fhp = fh_copy(&resp->fh, &argp->fh); + + /* + * NFSv2 does not differentiate between "set-[ac]time-to-now" + * which only requires access, and "set-[ac]time-to-X" which + * requires ownership. + * So if it looks like it might be "set both to the same time which + * is close to now", and if inode_change_ok fails, then we + * convert to "set to now" instead of "set to explicit time" + * + * We only call inode_change_ok as the last test as technically + * it is not an interface that we should be using. + */ +#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET) +#define MAX_TOUCH_TIME_ERROR (30*60) + if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET && + iap->ia_mtime.tv_sec == iap->ia_atime.tv_sec) { + /* + * Looks probable. + * + * Now just make sure time is in the right ballpark. + * Solaris, at least, doesn't seem to care what the time + * request is. We require it be within 30 minutes of now. + */ + time_t delta = iap->ia_atime.tv_sec - get_seconds(); + struct inode *inode; + + nfserr = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP); + if (nfserr) + goto done; + inode = d_inode(fhp->fh_dentry); + + if (delta < 0) + delta = -delta; + if (delta < MAX_TOUCH_TIME_ERROR && + inode_change_ok(inode, iap) != 0) { + /* + * Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME. + * This will cause notify_change to set these times + * to "now" + */ + iap->ia_valid &= ~BOTH_TIME_SET; + } + } + + nfserr = nfsd_setattr(rqstp, fhp, iap, 0, (time_t)0); +done: return nfsd_return_attrs(nfserr, resp); } diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index dbc4f85a5008..4874ce515fc1 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -68,6 +68,7 @@ struct nfsd4_callback { struct nfsd4_callback_ops *cb_ops; struct work_struct cb_work; int cb_status; + bool cb_update_seq_nr; bool cb_need_restart; }; @@ -582,9 +583,9 @@ enum nfsd4_cb_op { struct nfsd4_compound_state; struct nfsd_net; -extern __be32 nfs4_preprocess_stateid_op(struct net *net, - struct nfsd4_compound_state *cstate, - stateid_t *stateid, int flags, struct file **filp); +extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, stateid_t *stateid, + int flags, struct file **filp, bool *tmp_file); __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid, unsigned char typemask, struct nfs4_stid **s, struct nfsd_net *nn); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 84d770be056e..b5e077a6e7d4 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -302,42 +302,6 @@ commit_metadata(struct svc_fh *fhp) static void nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap) { - /* - * NFSv2 does not differentiate between "set-[ac]time-to-now" - * which only requires access, and "set-[ac]time-to-X" which - * requires ownership. - * So if it looks like it might be "set both to the same time which - * is close to now", and if inode_change_ok fails, then we - * convert to "set to now" instead of "set to explicit time" - * - * We only call inode_change_ok as the last test as technically - * it is not an interface that we should be using. - */ -#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET) -#define MAX_TOUCH_TIME_ERROR (30*60) - if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET && - iap->ia_mtime.tv_sec == iap->ia_atime.tv_sec) { - /* - * Looks probable. - * - * Now just make sure time is in the right ballpark. - * Solaris, at least, doesn't seem to care what the time - * request is. We require it be within 30 minutes of now. - */ - time_t delta = iap->ia_atime.tv_sec - get_seconds(); - if (delta < 0) - delta = -delta; - if (delta < MAX_TOUCH_TIME_ERROR && - inode_change_ok(inode, iap) != 0) { - /* - * Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME. - * This will cause notify_change to set these times - * to "now" - */ - iap->ia_valid &= ~BOTH_TIME_SET; - } - } - /* sanitize the mode change */ if (iap->ia_valid & ATTR_MODE) { iap->ia_mode &= S_IALLUGO; @@ -538,16 +502,11 @@ __be32 nfsd4_vfs_fallocate(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t offset, loff_t len, int flags) { - __be32 err; int error; if (!S_ISREG(file_inode(file)->i_mode)) return nfserr_inval; - err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry, NFSD_MAY_WRITE); - if (err) - return err; - error = vfs_fallocate(file, flags, offset, len); if (!error) error = commit_metadata(fhp); @@ -744,7 +703,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, host_err = ima_file_check(file, may_flags, 0); if (host_err) { - nfsd_close(file); + fput(file); goto out_nfserr; } @@ -761,23 +720,12 @@ out: return err; } -/* - * Close a file. - */ -void -nfsd_close(struct file *filp) -{ - fput(filp); -} - -/* - * Obtain the readahead parameters for the file - * specified by (dev, ino). - */ - -static inline struct raparms * -nfsd_get_raparms(dev_t dev, ino_t ino) +struct raparms * +nfsd_init_raparms(struct file *file) { + struct inode *inode = file_inode(file); + dev_t dev = inode->i_sb->s_dev; + ino_t ino = inode->i_ino; struct raparms *ra, **rap, **frap = NULL; int depth = 0; unsigned int hash; @@ -814,9 +762,23 @@ found: ra->p_count++; nfsdstats.ra_depth[depth*10/nfsdstats.ra_size]++; spin_unlock(&rab->pb_lock); + + if (ra->p_set) + file->f_ra = ra->p_ra; return ra; } +void nfsd_put_raparams(struct file *file, struct raparms *ra) +{ + struct raparm_hbucket *rab = &raparm_hash[ra->p_hindex]; + + spin_lock(&rab->pb_lock); + ra->p_ra = file->f_ra; + ra->p_set = 1; + ra->p_count--; + spin_unlock(&rab->pb_lock); +} + /* * Grab and keep cached pages associated with a file in the svc_rqst * so that they can be passed to the network sendmsg/sendpage routines @@ -945,7 +907,7 @@ static int wait_for_concurrent_writes(struct file *file) return err; } -static __be32 +__be32 nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t offset, struct kvec *vec, int vlen, unsigned long *cnt, int *stablep) @@ -1009,40 +971,6 @@ out_nfserr: return err; } -__be32 nfsd_get_tmp_read_open(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct file **file, struct raparms **ra) -{ - struct inode *inode; - __be32 err; - - err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, file); - if (err) - return err; - - inode = file_inode(*file); - - /* Get readahead parameters */ - *ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino); - - if (*ra && (*ra)->p_set) - (*file)->f_ra = (*ra)->p_ra; - return nfs_ok; -} - -void nfsd_put_tmp_read_open(struct file *file, struct raparms *ra) -{ - /* Write back readahead params */ - if (ra) { - struct raparm_hbucket *rab = &raparm_hash[ra->p_hindex]; - spin_lock(&rab->pb_lock); - ra->p_ra = file->f_ra; - ra->p_set = 1; - ra->p_count--; - spin_unlock(&rab->pb_lock); - } - nfsd_close(file); -} - /* * Read data from a file. count must contain the requested read count * on entry. On return, *count contains the number of bytes actually read. @@ -1055,13 +983,15 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct raparms *ra; __be32 err; - err = nfsd_get_tmp_read_open(rqstp, fhp, &file, &ra); + err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file); if (err) return err; + ra = nfsd_init_raparms(file); err = nfsd_vfs_read(rqstp, file, offset, vec, vlen, count); - - nfsd_put_tmp_read_open(file, ra); + if (ra) + nfsd_put_raparams(file, ra); + fput(file); return err; } @@ -1093,7 +1023,7 @@ nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, if (cnt) err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen, cnt, stablep); - nfsd_close(file); + fput(file); } out: return err; @@ -1138,7 +1068,7 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, err = nfserr_notsupp; } - nfsd_close(file); + fput(file); out: return err; } @@ -1977,7 +1907,7 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, if (err == nfserr_eof || err == nfserr_toosmall) err = nfs_ok; /* can still be found in ->err */ out_close: - nfsd_close(file); + fput(file); out: return err; } diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index 2050cb016998..5be875e3e638 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -71,11 +71,7 @@ __be32 nfsd_commit(struct svc_rqst *, struct svc_fh *, #endif /* CONFIG_NFSD_V3 */ __be32 nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t, int, struct file **); -void nfsd_close(struct file *); struct raparms; -__be32 nfsd_get_tmp_read_open(struct svc_rqst *, struct svc_fh *, - struct file **, struct raparms **); -void nfsd_put_tmp_read_open(struct file *, struct raparms *); __be32 nfsd_splice_read(struct svc_rqst *, struct file *, loff_t, unsigned long *); __be32 nfsd_readv(struct file *, loff_t, struct kvec *, int, @@ -84,6 +80,10 @@ __be32 nfsd_read(struct svc_rqst *, struct svc_fh *, loff_t, struct kvec *, int, unsigned long *); __be32 nfsd_write(struct svc_rqst *, struct svc_fh *,struct file *, loff_t, struct kvec *,int, unsigned long *, int *); +__be32 nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct file *file, loff_t offset, + struct kvec *vec, int vlen, unsigned long *cnt, + int *stablep); __be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *, char *, int *); __be32 nfsd_symlink(struct svc_rqst *, struct svc_fh *, @@ -104,6 +104,9 @@ __be32 nfsd_statfs(struct svc_rqst *, struct svc_fh *, __be32 nfsd_permission(struct svc_rqst *, struct svc_export *, struct dentry *, int); +struct raparms *nfsd_init_raparms(struct file *file); +void nfsd_put_raparams(struct file *file, struct raparms *ra); + static inline int fh_want_write(struct svc_fh *fh) { int ret = mnt_want_write(fh->fh_export->ex_path.mnt); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 2f8c092be2b3..9f991007a578 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -273,6 +273,7 @@ struct nfsd4_read { u32 rd_length; /* request */ int rd_vlen; struct file *rd_filp; + bool rd_tmp_file; struct svc_rqst *rd_rqstp; /* response */ struct svc_fh * rd_fhp; /* response */ diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index df8edf8ec914..cb94ee4181d4 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -172,6 +172,13 @@ struct svcxprt_rdma { #define RDMAXPRT_SQ_PENDING 2 #define RDMAXPRT_CONN_PENDING 3 +#define RPCRDMA_MAX_SVC_SEGS (64) /* server max scatter/gather */ +#if RPCSVC_MAXPAYLOAD < (RPCRDMA_MAX_SVC_SEGS << PAGE_SHIFT) +#define RPCRDMA_MAXPAYLOAD RPCSVC_MAXPAYLOAD +#else +#define RPCRDMA_MAXPAYLOAD (RPCRDMA_MAX_SVC_SEGS << PAGE_SHIFT) +#endif + #define RPCRDMA_LISTEN_BACKLOG 10 /* The default ORD value is based on two outstanding full-size writes with a * page size of 4k, or 32k * 2 ops / 4k = 16 outstanding RDMA_READ. */ @@ -182,10 +189,9 @@ struct svcxprt_rdma { /* svc_rdma_marshal.c */ extern int svc_rdma_xdr_decode_req(struct rpcrdma_msg **, struct svc_rqst *); -extern int svc_rdma_xdr_decode_deferred_req(struct svc_rqst *); extern int svc_rdma_xdr_encode_error(struct svcxprt_rdma *, struct rpcrdma_msg *, - enum rpcrdma_errcode, u32 *); + enum rpcrdma_errcode, __be32 *); extern void svc_rdma_xdr_encode_write_list(struct rpcrdma_msg *, int); extern void svc_rdma_xdr_encode_reply_array(struct rpcrdma_write_array *, int); extern void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *, int, @@ -212,7 +218,6 @@ extern int svc_rdma_sendto(struct svc_rqst *); extern int svc_rdma_send(struct svcxprt_rdma *, struct ib_send_wr *); extern void svc_rdma_send_error(struct svcxprt_rdma *, struct rpcrdma_msg *, enum rpcrdma_errcode); -struct page *svc_rdma_get_page(void); extern int svc_rdma_post_recv(struct svcxprt_rdma *); extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *); extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *); diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h index adc0aff83fbb..2119c7c274d7 100644 --- a/include/uapi/linux/nfs4.h +++ b/include/uapi/linux/nfs4.h @@ -86,6 +86,10 @@ #define ACL4_SUPPORT_AUDIT_ACL 0x04 #define ACL4_SUPPORT_ALARM_ACL 0x08 +#define NFS4_ACL_AUTO_INHERIT 0x00000001 +#define NFS4_ACL_PROTECTED 0x00000002 +#define NFS4_ACL_DEFAULTED 0x00000004 + #define NFS4_ACE_FILE_INHERIT_ACE 0x00000001 #define NFS4_ACE_DIRECTORY_INHERIT_ACE 0x00000002 #define NFS4_ACE_NO_PROPAGATE_INHERIT_ACE 0x00000004 @@ -93,6 +97,7 @@ #define NFS4_ACE_SUCCESSFUL_ACCESS_ACE_FLAG 0x00000010 #define NFS4_ACE_FAILED_ACCESS_ACE_FLAG 0x00000020 #define NFS4_ACE_IDENTIFIER_GROUP 0x00000040 +#define NFS4_ACE_INHERITED_ACE 0x00000080 #define NFS4_ACE_READ_DATA 0x00000001 #define NFS4_ACE_LIST_DIRECTORY 0x00000001 @@ -106,6 +111,8 @@ #define NFS4_ACE_DELETE_CHILD 0x00000040 #define NFS4_ACE_READ_ATTRIBUTES 0x00000080 #define NFS4_ACE_WRITE_ATTRIBUTES 0x00000100 +#define NFS4_ACE_WRITE_RETENTION 0x00000200 +#define NFS4_ACE_WRITE_RETENTION_HOLD 0x00000400 #define NFS4_ACE_DELETE 0x00010000 #define NFS4_ACE_READ_ACL 0x00020000 #define NFS4_ACE_WRITE_ACL 0x00040000 diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index 9068e72aa73c..04ce2c0b660e 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -48,28 +48,16 @@ config SUNRPC_DEBUG If unsure, say Y. -config SUNRPC_XPRT_RDMA_CLIENT - tristate "RPC over RDMA Client Support" +config SUNRPC_XPRT_RDMA + tristate "RPC-over-RDMA transport" depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS default SUNRPC && INFINIBAND help - This option allows the NFS client to support an RDMA-enabled - transport. + This option allows the NFS client and server to use RDMA + transports (InfiniBand, iWARP, or RoCE). - To compile RPC client RDMA transport support as a module, - choose M here: the module will be called xprtrdma. + To compile this support as a module, choose M. The module + will be called rpcrdma.ko. - If unsure, say N. - -config SUNRPC_XPRT_RDMA_SERVER - tristate "RPC over RDMA Server Support" - depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS - default SUNRPC && INFINIBAND - help - This option allows the NFS server to support an RDMA-enabled - transport. - - To compile RPC server RDMA transport support as a module, - choose M here: the module will be called svcrdma. - - If unsure, say N. + If unsure, or you know there is no RDMA capability on your + hardware platform, say N. diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile index 15e6f6c23c5d..936ad0a15371 100644 --- a/net/sunrpc/Makefile +++ b/net/sunrpc/Makefile @@ -5,8 +5,7 @@ obj-$(CONFIG_SUNRPC) += sunrpc.o obj-$(CONFIG_SUNRPC_GSS) += auth_gss/ - -obj-y += xprtrdma/ +obj-$(CONFIG_SUNRPC_XPRT_RDMA) += xprtrdma/ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \ auth.o auth_null.o auth_unix.o auth_generic.o \ diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index b5408e8a37f2..fee3c15a4b52 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -881,9 +881,7 @@ krb5_rc4_setup_seq_key(struct krb5_ctx *kctx, struct crypto_blkcipher *cipher, if (err) goto out_err; - sg_init_table(sg, 1); - sg_set_buf(sg, &zeroconstant, 4); - + sg_init_one(sg, &zeroconstant, 4); err = crypto_hash_digest(&desc, sg, 4, Kseq); if (err) goto out_err; @@ -951,9 +949,7 @@ krb5_rc4_setup_enc_key(struct krb5_ctx *kctx, struct crypto_blkcipher *cipher, if (err) goto out_err; - sg_init_table(sg, 1); - sg_set_buf(sg, zeroconstant, 4); - + sg_init_one(sg, zeroconstant, 4); err = crypto_hash_digest(&desc, sg, 4, Kcrypt); if (err) goto out_err; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 78974e4d9ad2..852ae606b02a 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1290,7 +1290,6 @@ err_bad: svc_putnl(resv, ntohl(rpc_stat)); goto sendit; } -EXPORT_SYMBOL_GPL(svc_process); /* * Process the RPC request. @@ -1338,6 +1337,7 @@ out_drop: svc_drop(rqstp); return 0; } +EXPORT_SYMBOL_GPL(svc_process); #if defined(CONFIG_SUNRPC_BACKCHANNEL) /* diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile index 579f72bbcf4b..48913de240bd 100644 --- a/net/sunrpc/xprtrdma/Makefile +++ b/net/sunrpc/xprtrdma/Makefile @@ -1,9 +1,7 @@ -obj-$(CONFIG_SUNRPC_XPRT_RDMA_CLIENT) += xprtrdma.o +obj-$(CONFIG_SUNRPC_XPRT_RDMA) += rpcrdma.o -xprtrdma-y := transport.o rpc_rdma.o verbs.o \ - fmr_ops.o frwr_ops.o physical_ops.o - -obj-$(CONFIG_SUNRPC_XPRT_RDMA_SERVER) += svcrdma.o - -svcrdma-y := svc_rdma.o svc_rdma_transport.o \ - svc_rdma_marshal.o svc_rdma_sendto.o svc_rdma_recvfrom.o +rpcrdma-y := transport.o rpc_rdma.o verbs.o \ + fmr_ops.o frwr_ops.o physical_ops.o \ + svc_rdma.o svc_rdma_transport.o \ + svc_rdma_marshal.o svc_rdma_sendto.o svc_rdma_recvfrom.o \ + module.o diff --git a/net/sunrpc/xprtrdma/module.c b/net/sunrpc/xprtrdma/module.c new file mode 100644 index 000000000000..560712bd9fa2 --- /dev/null +++ b/net/sunrpc/xprtrdma/module.c @@ -0,0 +1,46 @@ +/* + * Copyright (c) 2015 Oracle. All rights reserved. + */ + +/* rpcrdma.ko module initialization + */ + +#include +#include +#include +#include "xprt_rdma.h" + +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) +# define RPCDBG_FACILITY RPCDBG_TRANS +#endif + +MODULE_AUTHOR("Open Grid Computing and Network Appliance, Inc."); +MODULE_DESCRIPTION("RPC/RDMA Transport"); +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_ALIAS("svcrdma"); +MODULE_ALIAS("xprtrdma"); + +static void __exit rpc_rdma_cleanup(void) +{ + xprt_rdma_cleanup(); + svc_rdma_cleanup(); +} + +static int __init rpc_rdma_init(void) +{ + int rc; + + rc = svc_rdma_init(); + if (rc) + goto out; + + rc = xprt_rdma_init(); + if (rc) + svc_rdma_cleanup(); + +out: + return rc; +} + +module_init(rpc_rdma_init); +module_exit(rpc_rdma_cleanup); diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index c1b6270262c2..2cd252f023a5 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -38,8 +38,7 @@ * * Author: Tom Tucker */ -#include -#include + #include #include #include @@ -295,8 +294,3 @@ int svc_rdma_init(void) destroy_workqueue(svc_rdma_wq); return -ENOMEM; } -MODULE_AUTHOR("Tom Tucker "); -MODULE_DESCRIPTION("SVC RDMA Transport"); -MODULE_LICENSE("Dual BSD/GPL"); -module_init(svc_rdma_init); -module_exit(svc_rdma_cleanup); diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c index b681855cf970..e2fca7617242 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c +++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c @@ -50,12 +50,12 @@ /* * Decodes a read chunk list. The expected format is as follows: * descrim : xdr_one - * position : u32 offset into XDR stream - * handle : u32 RKEY + * position : __be32 offset into XDR stream + * handle : __be32 RKEY * . . . * end-of-list: xdr_zero */ -static u32 *decode_read_list(u32 *va, u32 *vaend) +static __be32 *decode_read_list(__be32 *va, __be32 *vaend) { struct rpcrdma_read_chunk *ch = (struct rpcrdma_read_chunk *)va; @@ -67,20 +67,20 @@ static u32 *decode_read_list(u32 *va, u32 *vaend) } ch++; } - return (u32 *)&ch->rc_position; + return &ch->rc_position; } /* * Decodes a write chunk list. The expected format is as follows: * descrim : xdr_one * nchunks : - * handle : u32 RKEY ---+ - * length : u32 | + * handle : __be32 RKEY ---+ + * length : __be32 | * offset : remove va + * . . . | * ---+ */ -static u32 *decode_write_list(u32 *va, u32 *vaend) +static __be32 *decode_write_list(__be32 *va, __be32 *vaend) { unsigned long start, end; int nchunks; @@ -90,14 +90,14 @@ static u32 *decode_write_list(u32 *va, u32 *vaend) /* Check for not write-array */ if (ary->wc_discrim == xdr_zero) - return (u32 *)&ary->wc_nchunks; + return &ary->wc_nchunks; if ((unsigned long)ary + sizeof(struct rpcrdma_write_array) > (unsigned long)vaend) { dprintk("svcrdma: ary=%p, vaend=%p\n", ary, vaend); return NULL; } - nchunks = ntohl(ary->wc_nchunks); + nchunks = be32_to_cpu(ary->wc_nchunks); start = (unsigned long)&ary->wc_array[0]; end = (unsigned long)vaend; @@ -112,10 +112,10 @@ static u32 *decode_write_list(u32 *va, u32 *vaend) * rs_length is the 2nd 4B field in wc_target and taking its * address skips the list terminator */ - return (u32 *)&ary->wc_array[nchunks].wc_target.rs_length; + return &ary->wc_array[nchunks].wc_target.rs_length; } -static u32 *decode_reply_array(u32 *va, u32 *vaend) +static __be32 *decode_reply_array(__be32 *va, __be32 *vaend) { unsigned long start, end; int nchunks; @@ -124,14 +124,14 @@ static u32 *decode_reply_array(u32 *va, u32 *vaend) /* Check for no reply-array */ if (ary->wc_discrim == xdr_zero) - return (u32 *)&ary->wc_nchunks; + return &ary->wc_nchunks; if ((unsigned long)ary + sizeof(struct rpcrdma_write_array) > (unsigned long)vaend) { dprintk("svcrdma: ary=%p, vaend=%p\n", ary, vaend); return NULL; } - nchunks = ntohl(ary->wc_nchunks); + nchunks = be32_to_cpu(ary->wc_nchunks); start = (unsigned long)&ary->wc_array[0]; end = (unsigned long)vaend; @@ -142,15 +142,14 @@ static u32 *decode_reply_array(u32 *va, u32 *vaend) ary, nchunks, vaend); return NULL; } - return (u32 *)&ary->wc_array[nchunks]; + return (__be32 *)&ary->wc_array[nchunks]; } int svc_rdma_xdr_decode_req(struct rpcrdma_msg **rdma_req, struct svc_rqst *rqstp) { struct rpcrdma_msg *rmsgp = NULL; - u32 *va; - u32 *vaend; + __be32 *va, *vaend; u32 hdr_len; rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base; @@ -162,22 +161,17 @@ int svc_rdma_xdr_decode_req(struct rpcrdma_msg **rdma_req, return -EINVAL; } - /* Decode the header */ - rmsgp->rm_xid = ntohl(rmsgp->rm_xid); - rmsgp->rm_vers = ntohl(rmsgp->rm_vers); - rmsgp->rm_credit = ntohl(rmsgp->rm_credit); - rmsgp->rm_type = ntohl(rmsgp->rm_type); - - if (rmsgp->rm_vers != RPCRDMA_VERSION) + if (rmsgp->rm_vers != rpcrdma_version) return -ENOSYS; /* Pull in the extra for the padded case and bump our pointer */ - if (rmsgp->rm_type == RDMA_MSGP) { + if (rmsgp->rm_type == rdma_msgp) { int hdrlen; + rmsgp->rm_body.rm_padded.rm_align = - ntohl(rmsgp->rm_body.rm_padded.rm_align); + be32_to_cpu(rmsgp->rm_body.rm_padded.rm_align); rmsgp->rm_body.rm_padded.rm_thresh = - ntohl(rmsgp->rm_body.rm_padded.rm_thresh); + be32_to_cpu(rmsgp->rm_body.rm_padded.rm_thresh); va = &rmsgp->rm_body.rm_padded.rm_pempty[4]; rqstp->rq_arg.head[0].iov_base = va; @@ -192,7 +186,7 @@ int svc_rdma_xdr_decode_req(struct rpcrdma_msg **rdma_req, * chunk list and a reply chunk list. */ va = &rmsgp->rm_body.rm_chunks[0]; - vaend = (u32 *)((unsigned long)rmsgp + rqstp->rq_arg.len); + vaend = (__be32 *)((unsigned long)rmsgp + rqstp->rq_arg.len); va = decode_read_list(va, vaend); if (!va) return -EINVAL; @@ -211,76 +205,20 @@ int svc_rdma_xdr_decode_req(struct rpcrdma_msg **rdma_req, return hdr_len; } -int svc_rdma_xdr_decode_deferred_req(struct svc_rqst *rqstp) -{ - struct rpcrdma_msg *rmsgp = NULL; - struct rpcrdma_read_chunk *ch; - struct rpcrdma_write_array *ary; - u32 *va; - u32 hdrlen; - - dprintk("svcrdma: processing deferred RDMA header on rqstp=%p\n", - rqstp); - rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base; - - /* Pull in the extra for the padded case and bump our pointer */ - if (rmsgp->rm_type == RDMA_MSGP) { - va = &rmsgp->rm_body.rm_padded.rm_pempty[4]; - rqstp->rq_arg.head[0].iov_base = va; - hdrlen = (u32)((unsigned long)va - (unsigned long)rmsgp); - rqstp->rq_arg.head[0].iov_len -= hdrlen; - return hdrlen; - } - - /* - * Skip all chunks to find RPC msg. These were previously processed - */ - va = &rmsgp->rm_body.rm_chunks[0]; - - /* Skip read-list */ - for (ch = (struct rpcrdma_read_chunk *)va; - ch->rc_discrim != xdr_zero; ch++); - va = (u32 *)&ch->rc_position; - - /* Skip write-list */ - ary = (struct rpcrdma_write_array *)va; - if (ary->wc_discrim == xdr_zero) - va = (u32 *)&ary->wc_nchunks; - else - /* - * rs_length is the 2nd 4B field in wc_target and taking its - * address skips the list terminator - */ - va = (u32 *)&ary->wc_array[ary->wc_nchunks].wc_target.rs_length; - - /* Skip reply-array */ - ary = (struct rpcrdma_write_array *)va; - if (ary->wc_discrim == xdr_zero) - va = (u32 *)&ary->wc_nchunks; - else - va = (u32 *)&ary->wc_array[ary->wc_nchunks]; - - rqstp->rq_arg.head[0].iov_base = va; - hdrlen = (unsigned long)va - (unsigned long)rmsgp; - rqstp->rq_arg.head[0].iov_len -= hdrlen; - - return hdrlen; -} - int svc_rdma_xdr_encode_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, - enum rpcrdma_errcode err, u32 *va) + enum rpcrdma_errcode err, __be32 *va) { - u32 *startp = va; + __be32 *startp = va; - *va++ = htonl(rmsgp->rm_xid); - *va++ = htonl(rmsgp->rm_vers); - *va++ = htonl(xprt->sc_max_requests); - *va++ = htonl(RDMA_ERROR); - *va++ = htonl(err); + *va++ = rmsgp->rm_xid; + *va++ = rmsgp->rm_vers; + *va++ = cpu_to_be32(xprt->sc_max_requests); + *va++ = rdma_error; + *va++ = cpu_to_be32(err); if (err == ERR_VERS) { - *va++ = htonl(RPCRDMA_VERSION); - *va++ = htonl(RPCRDMA_VERSION); + *va++ = rpcrdma_version; + *va++ = rpcrdma_version; } return (int)((unsigned long)va - (unsigned long)startp); @@ -297,7 +235,7 @@ int svc_rdma_xdr_get_reply_hdr_len(struct rpcrdma_msg *rmsgp) &rmsgp->rm_body.rm_chunks[1]; if (wr_ary->wc_discrim) wr_ary = (struct rpcrdma_write_array *) - &wr_ary->wc_array[ntohl(wr_ary->wc_nchunks)]. + &wr_ary->wc_array[be32_to_cpu(wr_ary->wc_nchunks)]. wc_target.rs_length; else wr_ary = (struct rpcrdma_write_array *) @@ -306,7 +244,7 @@ int svc_rdma_xdr_get_reply_hdr_len(struct rpcrdma_msg *rmsgp) /* skip reply array */ if (wr_ary->wc_discrim) wr_ary = (struct rpcrdma_write_array *) - &wr_ary->wc_array[ntohl(wr_ary->wc_nchunks)]; + &wr_ary->wc_array[be32_to_cpu(wr_ary->wc_nchunks)]; else wr_ary = (struct rpcrdma_write_array *) &wr_ary->wc_nchunks; @@ -325,7 +263,7 @@ void svc_rdma_xdr_encode_write_list(struct rpcrdma_msg *rmsgp, int chunks) ary = (struct rpcrdma_write_array *) &rmsgp->rm_body.rm_chunks[1]; ary->wc_discrim = xdr_one; - ary->wc_nchunks = htonl(chunks); + ary->wc_nchunks = cpu_to_be32(chunks); /* write-list terminator */ ary->wc_array[chunks].wc_target.rs_handle = xdr_zero; @@ -338,7 +276,7 @@ void svc_rdma_xdr_encode_reply_array(struct rpcrdma_write_array *ary, int chunks) { ary->wc_discrim = xdr_one; - ary->wc_nchunks = htonl(chunks); + ary->wc_nchunks = cpu_to_be32(chunks); } void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *ary, @@ -350,7 +288,7 @@ void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *ary, struct rpcrdma_segment *seg = &ary->wc_array[chunk_no].wc_target; seg->rs_handle = rs_handle; seg->rs_offset = rs_offset; - seg->rs_length = htonl(write_len); + seg->rs_length = cpu_to_be32(write_len); } void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *xprt, @@ -358,10 +296,10 @@ void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rdma_resp, enum rpcrdma_proc rdma_type) { - rdma_resp->rm_xid = htonl(rdma_argp->rm_xid); - rdma_resp->rm_vers = htonl(rdma_argp->rm_vers); - rdma_resp->rm_credit = htonl(xprt->sc_max_requests); - rdma_resp->rm_type = htonl(rdma_type); + rdma_resp->rm_xid = rdma_argp->rm_xid; + rdma_resp->rm_vers = rdma_argp->rm_vers; + rdma_resp->rm_credit = cpu_to_be32(xprt->sc_max_requests); + rdma_resp->rm_type = cpu_to_be32(rdma_type); /* Encode chunks lists */ rdma_resp->rm_body.rm_chunks[0] = xdr_zero; diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 86b44164172b..2e1348bde325 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -85,7 +85,7 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, /* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */ rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base; - if (be32_to_cpu(rmsgp->rm_type) == RDMA_NOMSG) + if (rmsgp->rm_type == rdma_nomsg) rqstp->rq_arg.pages = &rqstp->rq_pages[0]; else rqstp->rq_arg.pages = &rqstp->rq_pages[1]; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 7de33d1af9b6..d25cd430f9ff 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -240,6 +240,7 @@ static int send_write_chunks(struct svcxprt_rdma *xprt, u32 xdr_off; int chunk_off; int chunk_no; + int nchunks; struct rpcrdma_write_array *arg_ary; struct rpcrdma_write_array *res_ary; int ret; @@ -251,14 +252,15 @@ static int send_write_chunks(struct svcxprt_rdma *xprt, &rdma_resp->rm_body.rm_chunks[1]; /* Write chunks start at the pagelist */ + nchunks = be32_to_cpu(arg_ary->wc_nchunks); for (xdr_off = rqstp->rq_res.head[0].iov_len, chunk_no = 0; - xfer_len && chunk_no < arg_ary->wc_nchunks; + xfer_len && chunk_no < nchunks; chunk_no++) { struct rpcrdma_segment *arg_ch; u64 rs_offset; arg_ch = &arg_ary->wc_array[chunk_no].wc_target; - write_len = min(xfer_len, ntohl(arg_ch->rs_length)); + write_len = min(xfer_len, be32_to_cpu(arg_ch->rs_length)); /* Prepare the response chunk given the length actually * written */ @@ -270,7 +272,7 @@ static int send_write_chunks(struct svcxprt_rdma *xprt, chunk_off = 0; while (write_len) { ret = send_write(xprt, rqstp, - ntohl(arg_ch->rs_handle), + be32_to_cpu(arg_ch->rs_handle), rs_offset + chunk_off, xdr_off, write_len, @@ -318,13 +320,13 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt, &rdma_resp->rm_body.rm_chunks[2]; /* xdr offset starts at RPC message */ - nchunks = ntohl(arg_ary->wc_nchunks); + nchunks = be32_to_cpu(arg_ary->wc_nchunks); for (xdr_off = 0, chunk_no = 0; xfer_len && chunk_no < nchunks; chunk_no++) { u64 rs_offset; ch = &arg_ary->wc_array[chunk_no].wc_target; - write_len = min(xfer_len, htonl(ch->rs_length)); + write_len = min(xfer_len, be32_to_cpu(ch->rs_length)); /* Prepare the reply chunk given the length actually * written */ @@ -335,7 +337,7 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt, chunk_off = 0; while (write_len) { ret = send_write(xprt, rqstp, - ntohl(ch->rs_handle), + be32_to_cpu(ch->rs_handle), rs_offset + chunk_off, xdr_off, write_len, @@ -515,7 +517,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) inline_bytes = rqstp->rq_res.len; /* Create the RDMA response header */ - res_page = svc_rdma_get_page(); + res_page = alloc_page(GFP_KERNEL | __GFP_NOFAIL); rdma_resp = page_address(res_page); reply_ary = svc_rdma_get_reply_array(rdma_argp); if (reply_ary) diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index f4cfa764d76f..6b36279e4288 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -91,7 +91,7 @@ struct svc_xprt_class svc_rdma_class = { .xcl_name = "rdma", .xcl_owner = THIS_MODULE, .xcl_ops = &svc_rdma_ops, - .xcl_max_payload = RPCSVC_MAXPAYLOAD_RDMA, + .xcl_max_payload = RPCRDMA_MAXPAYLOAD, .xcl_ident = XPRT_TRANSPORT_RDMA, }; @@ -99,12 +99,8 @@ struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt) { struct svc_rdma_op_ctxt *ctxt; - while (1) { - ctxt = kmem_cache_alloc(svc_rdma_ctxt_cachep, GFP_KERNEL); - if (ctxt) - break; - schedule_timeout_uninterruptible(msecs_to_jiffies(500)); - } + ctxt = kmem_cache_alloc(svc_rdma_ctxt_cachep, + GFP_KERNEL | __GFP_NOFAIL); ctxt->xprt = xprt; INIT_LIST_HEAD(&ctxt->dto_q); ctxt->count = 0; @@ -156,12 +152,8 @@ void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages) struct svc_rdma_req_map *svc_rdma_get_req_map(void) { struct svc_rdma_req_map *map; - while (1) { - map = kmem_cache_alloc(svc_rdma_map_cachep, GFP_KERNEL); - if (map) - break; - schedule_timeout_uninterruptible(msecs_to_jiffies(500)); - } + map = kmem_cache_alloc(svc_rdma_map_cachep, + GFP_KERNEL | __GFP_NOFAIL); map->count = 0; return map; } @@ -493,18 +485,6 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, return cma_xprt; } -struct page *svc_rdma_get_page(void) -{ - struct page *page; - - while ((page = alloc_page(GFP_KERNEL)) == NULL) { - /* If we can't get memory, wait a bit and try again */ - printk(KERN_INFO "svcrdma: out of memory...retrying in 1s\n"); - schedule_timeout_uninterruptible(msecs_to_jiffies(1000)); - } - return page; -} - int svc_rdma_post_recv(struct svcxprt_rdma *xprt) { struct ib_recv_wr recv_wr, *bad_recv_wr; @@ -523,7 +503,7 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt) pr_err("svcrdma: Too many sges (%d)\n", sge_no); goto err_put_ctxt; } - page = svc_rdma_get_page(); + page = alloc_page(GFP_KERNEL | __GFP_NOFAIL); ctxt->pages[sge_no] = page; pa = ib_dma_map_page(xprt->sc_cm_id->device, page, 0, PAGE_SIZE, @@ -1318,11 +1298,11 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, struct ib_send_wr err_wr; struct page *p; struct svc_rdma_op_ctxt *ctxt; - u32 *va; + __be32 *va; int length; int ret; - p = svc_rdma_get_page(); + p = alloc_page(GFP_KERNEL | __GFP_NOFAIL); va = page_address(p); /* XDR encode error */ diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 54f23b1be986..436da2caec95 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -48,7 +48,6 @@ */ #include -#include #include #include #include @@ -59,11 +58,6 @@ # define RPCDBG_FACILITY RPCDBG_TRANS #endif -MODULE_LICENSE("Dual BSD/GPL"); - -MODULE_DESCRIPTION("RPC/RDMA Transport for Linux kernel NFS"); -MODULE_AUTHOR("Network Appliance, Inc."); - /* * tunables */ @@ -711,7 +705,7 @@ static struct xprt_class xprt_rdma = { .setup = xprt_setup_rdma, }; -static void __exit xprt_rdma_cleanup(void) +void xprt_rdma_cleanup(void) { int rc; @@ -728,7 +722,7 @@ static void __exit xprt_rdma_cleanup(void) __func__, rc); } -static int __init xprt_rdma_init(void) +int xprt_rdma_init(void) { int rc; @@ -753,6 +747,3 @@ static int __init xprt_rdma_init(void) #endif return 0; } - -module_init(xprt_rdma_init); -module_exit(xprt_rdma_cleanup); diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 78e0b8beaa36..58163b88738c 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -480,6 +480,11 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *); */ int rpcrdma_marshal_req(struct rpc_rqst *); +/* RPC/RDMA module init - xprtrdma/transport.c + */ +int xprt_rdma_init(void); +void xprt_rdma_cleanup(void); + /* Temporary NFS request map cache. Created in svc_rdma.c */ extern struct kmem_cache *svc_rdma_map_cachep; /* WR context cache. Created in svc_rdma.c */ @@ -487,10 +492,4 @@ extern struct kmem_cache *svc_rdma_ctxt_cachep; /* Workqueue created in svc_rdma.c */ extern struct workqueue_struct *svc_rdma_wq; -#if RPCSVC_MAXPAYLOAD < (RPCRDMA_MAX_DATA_SEGS << PAGE_SHIFT) -#define RPCSVC_MAXPAYLOAD_RDMA RPCSVC_MAXPAYLOAD -#else -#define RPCSVC_MAXPAYLOAD_RDMA (RPCRDMA_MAX_DATA_SEGS << PAGE_SHIFT) -#endif - #endif /* _LINUX_SUNRPC_XPRT_RDMA_H */