From a4773c08f2872626cb923433284488fbe8acb0ae Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 2 Feb 2009 17:23:10 -0500 Subject: nfsd4: use helper for copying filehandles for replay Signed-off-by: J. Bruce Fields --- include/linux/nfsd/nfsfh.h | 7 +++++++ include/linux/nfsd/state.h | 3 +-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h index fa317f6c154b..afa19016c4a8 100644 --- a/include/linux/nfsd/nfsfh.h +++ b/include/linux/nfsd/nfsfh.h @@ -269,6 +269,13 @@ fh_copy(struct svc_fh *dst, struct svc_fh *src) return dst; } +static inline void +fh_copy_shallow(struct knfsd_fh *dst, struct knfsd_fh *src) +{ + dst->fh_size = src->fh_size; + memcpy(&dst->fh_base, &src->fh_base, src->fh_size); +} + static __inline__ struct svc_fh * fh_init(struct svc_fh *fhp, int maxsize) { diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 128298c0362d..b65b2a6274b0 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -168,8 +168,7 @@ struct nfs4_replay { unsigned int rp_buflen; char *rp_buf; unsigned intrp_allocated; - int rp_openfh_len; - char rp_openfh[NFS4_FHSIZE]; + struct knfsd_fh rp_openfh; char rp_ibuf[NFSD4_REPLAY_ISIZE]; }; -- cgit v1.2.3 From 6c02eaa1d1e53b9b2cc27d0c6fff3e57da4b611f Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 2 Feb 2009 17:30:51 -0500 Subject: nfsd4: use helper for copying delegation filehandle Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4callback.c | 4 ++-- fs/nfsd/nfs4state.c | 4 +--- include/linux/nfsd/state.h | 6 ++---- 3 files changed, 5 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index c464181b5994..c6804db33c17 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -218,7 +218,7 @@ static int encode_cb_recall(struct xdr_stream *xdr, struct nfs4_cb_recall *cb_rec) { __be32 *p; - int len = cb_rec->cbr_fhlen; + int len = cb_rec->cbr_fh.fh_size; RESERVE_SPACE(12+sizeof(cb_rec->cbr_stateid) + len); WRITE32(OP_CB_RECALL); @@ -226,7 +226,7 @@ encode_cb_recall(struct xdr_stream *xdr, struct nfs4_cb_recall *cb_rec) WRITEMEM(&cb_rec->cbr_stateid.si_opaque, sizeof(stateid_opaque_t)); WRITE32(cb_rec->cbr_trunc); WRITE32(len); - WRITEMEM(cb_rec->cbr_fhval, len); + WRITEMEM(&cb_rec->cbr_fh.fh_base, len); return 0; } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 41a3590ef2cc..7f616e928a57 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -215,9 +215,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_f dp->dl_stateid.si_stateownerid = current_delegid++; dp->dl_stateid.si_fileid = 0; dp->dl_stateid.si_generation = 0; - dp->dl_fhlen = current_fh->fh_handle.fh_size; - memcpy(dp->dl_fhval, ¤t_fh->fh_handle.fh_base, - current_fh->fh_handle.fh_size); + fh_copy_shallow(&dp->dl_fh, ¤t_fh->fh_handle); dp->dl_time = 0; atomic_set(&dp->dl_count, 1); list_add(&dp->dl_perfile, &fp->fi_delegations); diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index b65b2a6274b0..1130d534bb63 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -66,8 +66,7 @@ struct nfs4_cb_recall { u32 cbr_ident; int cbr_trunc; stateid_t cbr_stateid; - u32 cbr_fhlen; - char cbr_fhval[NFS4_FHSIZE]; + struct knfsd_fh cbr_fh; struct nfs4_delegation *cbr_dp; }; @@ -86,8 +85,7 @@ struct nfs4_delegation { }; #define dl_stateid dl_recall.cbr_stateid -#define dl_fhlen dl_recall.cbr_fhlen -#define dl_fhval dl_recall.cbr_fhval +#define dl_fh dl_recall.cbr_fh /* client delegation callback info */ struct nfs4_callback { -- cgit v1.2.3 From 77f18f5e4ebdea35ec3d92343b0ed7546dc87637 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Wed, 11 Feb 2009 17:16:58 -0800 Subject: nfs: replace uses of __constant_{endian} The base versions handle constant folding now, none of these headers are exported to userspace, so the __ prefixed versions are not necessary. Signed-off-by: Harvey Harrison Reviewed-by: NeilBrown Signed-off-by: J. Bruce Fields --- include/linux/lockd/xdr.h | 12 ++--- include/linux/lockd/xdr4.h | 10 ++-- include/linux/nfsd/nfsd.h | 132 ++++++++++++++++++++++----------------------- include/linux/sunrpc/xdr.h | 42 +++++++-------- 4 files changed, 98 insertions(+), 98 deletions(-) (limited to 'include') diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index 7dc5b6cb44cd..d39ed1cc5fbf 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -25,13 +25,13 @@ struct svc_rqst; #define NLM_MAXCOOKIELEN 32 #define NLM_MAXSTRLEN 1024 -#define nlm_granted __constant_htonl(NLM_LCK_GRANTED) -#define nlm_lck_denied __constant_htonl(NLM_LCK_DENIED) -#define nlm_lck_denied_nolocks __constant_htonl(NLM_LCK_DENIED_NOLOCKS) -#define nlm_lck_blocked __constant_htonl(NLM_LCK_BLOCKED) -#define nlm_lck_denied_grace_period __constant_htonl(NLM_LCK_DENIED_GRACE_PERIOD) +#define nlm_granted cpu_to_be32(NLM_LCK_GRANTED) +#define nlm_lck_denied cpu_to_be32(NLM_LCK_DENIED) +#define nlm_lck_denied_nolocks cpu_to_be32(NLM_LCK_DENIED_NOLOCKS) +#define nlm_lck_blocked cpu_to_be32(NLM_LCK_BLOCKED) +#define nlm_lck_denied_grace_period cpu_to_be32(NLM_LCK_DENIED_GRACE_PERIOD) -#define nlm_drop_reply __constant_htonl(30000) +#define nlm_drop_reply cpu_to_be32(30000) /* Lock info passed via NLM */ struct nlm_lock { diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index 12bfe09de2b1..7353821341ed 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -15,11 +15,11 @@ #include /* error codes new to NLMv4 */ -#define nlm4_deadlock __constant_htonl(NLM_DEADLCK) -#define nlm4_rofs __constant_htonl(NLM_ROFS) -#define nlm4_stale_fh __constant_htonl(NLM_STALE_FH) -#define nlm4_fbig __constant_htonl(NLM_FBIG) -#define nlm4_failed __constant_htonl(NLM_FAILED) +#define nlm4_deadlock cpu_to_be32(NLM_DEADLCK) +#define nlm4_rofs cpu_to_be32(NLM_ROFS) +#define nlm4_stale_fh cpu_to_be32(NLM_STALE_FH) +#define nlm4_fbig cpu_to_be32(NLM_FBIG) +#define nlm4_failed cpu_to_be32(NLM_FAILED) diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index e19f45991b2e..16f7b403d9c1 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -186,78 +186,78 @@ void nfsd_lockd_shutdown(void); /* * These macros provide pre-xdr'ed values for faster operation. */ -#define nfs_ok __constant_htonl(NFS_OK) -#define nfserr_perm __constant_htonl(NFSERR_PERM) -#define nfserr_noent __constant_htonl(NFSERR_NOENT) -#define nfserr_io __constant_htonl(NFSERR_IO) -#define nfserr_nxio __constant_htonl(NFSERR_NXIO) -#define nfserr_eagain __constant_htonl(NFSERR_EAGAIN) -#define nfserr_acces __constant_htonl(NFSERR_ACCES) -#define nfserr_exist __constant_htonl(NFSERR_EXIST) -#define nfserr_xdev __constant_htonl(NFSERR_XDEV) -#define nfserr_nodev __constant_htonl(NFSERR_NODEV) -#define nfserr_notdir __constant_htonl(NFSERR_NOTDIR) -#define nfserr_isdir __constant_htonl(NFSERR_ISDIR) -#define nfserr_inval __constant_htonl(NFSERR_INVAL) -#define nfserr_fbig __constant_htonl(NFSERR_FBIG) -#define nfserr_nospc __constant_htonl(NFSERR_NOSPC) -#define nfserr_rofs __constant_htonl(NFSERR_ROFS) -#define nfserr_mlink __constant_htonl(NFSERR_MLINK) -#define nfserr_opnotsupp __constant_htonl(NFSERR_OPNOTSUPP) -#define nfserr_nametoolong __constant_htonl(NFSERR_NAMETOOLONG) -#define nfserr_notempty __constant_htonl(NFSERR_NOTEMPTY) -#define nfserr_dquot __constant_htonl(NFSERR_DQUOT) -#define nfserr_stale __constant_htonl(NFSERR_STALE) -#define nfserr_remote __constant_htonl(NFSERR_REMOTE) -#define nfserr_wflush __constant_htonl(NFSERR_WFLUSH) -#define nfserr_badhandle __constant_htonl(NFSERR_BADHANDLE) -#define nfserr_notsync __constant_htonl(NFSERR_NOT_SYNC) -#define nfserr_badcookie __constant_htonl(NFSERR_BAD_COOKIE) -#define nfserr_notsupp __constant_htonl(NFSERR_NOTSUPP) -#define nfserr_toosmall __constant_htonl(NFSERR_TOOSMALL) -#define nfserr_serverfault __constant_htonl(NFSERR_SERVERFAULT) -#define nfserr_badtype __constant_htonl(NFSERR_BADTYPE) -#define nfserr_jukebox __constant_htonl(NFSERR_JUKEBOX) -#define nfserr_denied __constant_htonl(NFSERR_DENIED) -#define nfserr_deadlock __constant_htonl(NFSERR_DEADLOCK) -#define nfserr_expired __constant_htonl(NFSERR_EXPIRED) -#define nfserr_bad_cookie __constant_htonl(NFSERR_BAD_COOKIE) -#define nfserr_same __constant_htonl(NFSERR_SAME) -#define nfserr_clid_inuse __constant_htonl(NFSERR_CLID_INUSE) -#define nfserr_stale_clientid __constant_htonl(NFSERR_STALE_CLIENTID) -#define nfserr_resource __constant_htonl(NFSERR_RESOURCE) -#define nfserr_moved __constant_htonl(NFSERR_MOVED) -#define nfserr_nofilehandle __constant_htonl(NFSERR_NOFILEHANDLE) -#define nfserr_minor_vers_mismatch __constant_htonl(NFSERR_MINOR_VERS_MISMATCH) -#define nfserr_share_denied __constant_htonl(NFSERR_SHARE_DENIED) -#define nfserr_stale_stateid __constant_htonl(NFSERR_STALE_STATEID) -#define nfserr_old_stateid __constant_htonl(NFSERR_OLD_STATEID) -#define nfserr_bad_stateid __constant_htonl(NFSERR_BAD_STATEID) -#define nfserr_bad_seqid __constant_htonl(NFSERR_BAD_SEQID) -#define nfserr_symlink __constant_htonl(NFSERR_SYMLINK) -#define nfserr_not_same __constant_htonl(NFSERR_NOT_SAME) -#define nfserr_restorefh __constant_htonl(NFSERR_RESTOREFH) -#define nfserr_attrnotsupp __constant_htonl(NFSERR_ATTRNOTSUPP) -#define nfserr_bad_xdr __constant_htonl(NFSERR_BAD_XDR) -#define nfserr_openmode __constant_htonl(NFSERR_OPENMODE) -#define nfserr_locks_held __constant_htonl(NFSERR_LOCKS_HELD) -#define nfserr_op_illegal __constant_htonl(NFSERR_OP_ILLEGAL) -#define nfserr_grace __constant_htonl(NFSERR_GRACE) -#define nfserr_no_grace __constant_htonl(NFSERR_NO_GRACE) -#define nfserr_reclaim_bad __constant_htonl(NFSERR_RECLAIM_BAD) -#define nfserr_badname __constant_htonl(NFSERR_BADNAME) -#define nfserr_cb_path_down __constant_htonl(NFSERR_CB_PATH_DOWN) -#define nfserr_locked __constant_htonl(NFSERR_LOCKED) -#define nfserr_wrongsec __constant_htonl(NFSERR_WRONGSEC) -#define nfserr_replay_me __constant_htonl(NFSERR_REPLAY_ME) +#define nfs_ok cpu_to_be32(NFS_OK) +#define nfserr_perm cpu_to_be32(NFSERR_PERM) +#define nfserr_noent cpu_to_be32(NFSERR_NOENT) +#define nfserr_io cpu_to_be32(NFSERR_IO) +#define nfserr_nxio cpu_to_be32(NFSERR_NXIO) +#define nfserr_eagain cpu_to_be32(NFSERR_EAGAIN) +#define nfserr_acces cpu_to_be32(NFSERR_ACCES) +#define nfserr_exist cpu_to_be32(NFSERR_EXIST) +#define nfserr_xdev cpu_to_be32(NFSERR_XDEV) +#define nfserr_nodev cpu_to_be32(NFSERR_NODEV) +#define nfserr_notdir cpu_to_be32(NFSERR_NOTDIR) +#define nfserr_isdir cpu_to_be32(NFSERR_ISDIR) +#define nfserr_inval cpu_to_be32(NFSERR_INVAL) +#define nfserr_fbig cpu_to_be32(NFSERR_FBIG) +#define nfserr_nospc cpu_to_be32(NFSERR_NOSPC) +#define nfserr_rofs cpu_to_be32(NFSERR_ROFS) +#define nfserr_mlink cpu_to_be32(NFSERR_MLINK) +#define nfserr_opnotsupp cpu_to_be32(NFSERR_OPNOTSUPP) +#define nfserr_nametoolong cpu_to_be32(NFSERR_NAMETOOLONG) +#define nfserr_notempty cpu_to_be32(NFSERR_NOTEMPTY) +#define nfserr_dquot cpu_to_be32(NFSERR_DQUOT) +#define nfserr_stale cpu_to_be32(NFSERR_STALE) +#define nfserr_remote cpu_to_be32(NFSERR_REMOTE) +#define nfserr_wflush cpu_to_be32(NFSERR_WFLUSH) +#define nfserr_badhandle cpu_to_be32(NFSERR_BADHANDLE) +#define nfserr_notsync cpu_to_be32(NFSERR_NOT_SYNC) +#define nfserr_badcookie cpu_to_be32(NFSERR_BAD_COOKIE) +#define nfserr_notsupp cpu_to_be32(NFSERR_NOTSUPP) +#define nfserr_toosmall cpu_to_be32(NFSERR_TOOSMALL) +#define nfserr_serverfault cpu_to_be32(NFSERR_SERVERFAULT) +#define nfserr_badtype cpu_to_be32(NFSERR_BADTYPE) +#define nfserr_jukebox cpu_to_be32(NFSERR_JUKEBOX) +#define nfserr_denied cpu_to_be32(NFSERR_DENIED) +#define nfserr_deadlock cpu_to_be32(NFSERR_DEADLOCK) +#define nfserr_expired cpu_to_be32(NFSERR_EXPIRED) +#define nfserr_bad_cookie cpu_to_be32(NFSERR_BAD_COOKIE) +#define nfserr_same cpu_to_be32(NFSERR_SAME) +#define nfserr_clid_inuse cpu_to_be32(NFSERR_CLID_INUSE) +#define nfserr_stale_clientid cpu_to_be32(NFSERR_STALE_CLIENTID) +#define nfserr_resource cpu_to_be32(NFSERR_RESOURCE) +#define nfserr_moved cpu_to_be32(NFSERR_MOVED) +#define nfserr_nofilehandle cpu_to_be32(NFSERR_NOFILEHANDLE) +#define nfserr_minor_vers_mismatch cpu_to_be32(NFSERR_MINOR_VERS_MISMATCH) +#define nfserr_share_denied cpu_to_be32(NFSERR_SHARE_DENIED) +#define nfserr_stale_stateid cpu_to_be32(NFSERR_STALE_STATEID) +#define nfserr_old_stateid cpu_to_be32(NFSERR_OLD_STATEID) +#define nfserr_bad_stateid cpu_to_be32(NFSERR_BAD_STATEID) +#define nfserr_bad_seqid cpu_to_be32(NFSERR_BAD_SEQID) +#define nfserr_symlink cpu_to_be32(NFSERR_SYMLINK) +#define nfserr_not_same cpu_to_be32(NFSERR_NOT_SAME) +#define nfserr_restorefh cpu_to_be32(NFSERR_RESTOREFH) +#define nfserr_attrnotsupp cpu_to_be32(NFSERR_ATTRNOTSUPP) +#define nfserr_bad_xdr cpu_to_be32(NFSERR_BAD_XDR) +#define nfserr_openmode cpu_to_be32(NFSERR_OPENMODE) +#define nfserr_locks_held cpu_to_be32(NFSERR_LOCKS_HELD) +#define nfserr_op_illegal cpu_to_be32(NFSERR_OP_ILLEGAL) +#define nfserr_grace cpu_to_be32(NFSERR_GRACE) +#define nfserr_no_grace cpu_to_be32(NFSERR_NO_GRACE) +#define nfserr_reclaim_bad cpu_to_be32(NFSERR_RECLAIM_BAD) +#define nfserr_badname cpu_to_be32(NFSERR_BADNAME) +#define nfserr_cb_path_down cpu_to_be32(NFSERR_CB_PATH_DOWN) +#define nfserr_locked cpu_to_be32(NFSERR_LOCKED) +#define nfserr_wrongsec cpu_to_be32(NFSERR_WRONGSEC) +#define nfserr_replay_me cpu_to_be32(NFSERR_REPLAY_ME) /* error codes for internal use */ /* if a request fails due to kmalloc failure, it gets dropped. * Client should resend eventually */ -#define nfserr_dropit __constant_htonl(30000) +#define nfserr_dropit cpu_to_be32(30000) /* end-of-file indicator in readdir */ -#define nfserr_eof __constant_htonl(30001) +#define nfserr_eof cpu_to_be32(30001) /* Check for dir entries '.' and '..' */ #define isdotent(n, l) (l < 3 && n[0] == '.' && (l == 1 || n[1] == '.')) diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 49e1eb454465..d8910b68e1bd 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -69,27 +69,27 @@ struct xdr_buf { * pre-xdr'ed macros. */ -#define xdr_zero __constant_htonl(0) -#define xdr_one __constant_htonl(1) -#define xdr_two __constant_htonl(2) - -#define rpc_success __constant_htonl(RPC_SUCCESS) -#define rpc_prog_unavail __constant_htonl(RPC_PROG_UNAVAIL) -#define rpc_prog_mismatch __constant_htonl(RPC_PROG_MISMATCH) -#define rpc_proc_unavail __constant_htonl(RPC_PROC_UNAVAIL) -#define rpc_garbage_args __constant_htonl(RPC_GARBAGE_ARGS) -#define rpc_system_err __constant_htonl(RPC_SYSTEM_ERR) -#define rpc_drop_reply __constant_htonl(RPC_DROP_REPLY) - -#define rpc_auth_ok __constant_htonl(RPC_AUTH_OK) -#define rpc_autherr_badcred __constant_htonl(RPC_AUTH_BADCRED) -#define rpc_autherr_rejectedcred __constant_htonl(RPC_AUTH_REJECTEDCRED) -#define rpc_autherr_badverf __constant_htonl(RPC_AUTH_BADVERF) -#define rpc_autherr_rejectedverf __constant_htonl(RPC_AUTH_REJECTEDVERF) -#define rpc_autherr_tooweak __constant_htonl(RPC_AUTH_TOOWEAK) -#define rpcsec_gsserr_credproblem __constant_htonl(RPCSEC_GSS_CREDPROBLEM) -#define rpcsec_gsserr_ctxproblem __constant_htonl(RPCSEC_GSS_CTXPROBLEM) -#define rpc_autherr_oldseqnum __constant_htonl(101) +#define xdr_zero cpu_to_be32(0) +#define xdr_one cpu_to_be32(1) +#define xdr_two cpu_to_be32(2) + +#define rpc_success cpu_to_be32(RPC_SUCCESS) +#define rpc_prog_unavail cpu_to_be32(RPC_PROG_UNAVAIL) +#define rpc_prog_mismatch cpu_to_be32(RPC_PROG_MISMATCH) +#define rpc_proc_unavail cpu_to_be32(RPC_PROC_UNAVAIL) +#define rpc_garbage_args cpu_to_be32(RPC_GARBAGE_ARGS) +#define rpc_system_err cpu_to_be32(RPC_SYSTEM_ERR) +#define rpc_drop_reply cpu_to_be32(RPC_DROP_REPLY) + +#define rpc_auth_ok cpu_to_be32(RPC_AUTH_OK) +#define rpc_autherr_badcred cpu_to_be32(RPC_AUTH_BADCRED) +#define rpc_autherr_rejectedcred cpu_to_be32(RPC_AUTH_REJECTEDCRED) +#define rpc_autherr_badverf cpu_to_be32(RPC_AUTH_BADVERF) +#define rpc_autherr_rejectedverf cpu_to_be32(RPC_AUTH_REJECTEDVERF) +#define rpc_autherr_tooweak cpu_to_be32(RPC_AUTH_TOOWEAK) +#define rpcsec_gsserr_credproblem cpu_to_be32(RPCSEC_GSS_CREDPROBLEM) +#define rpcsec_gsserr_ctxproblem cpu_to_be32(RPCSEC_GSS_CTXPROBLEM) +#define rpc_autherr_oldseqnum cpu_to_be32(101) /* * Miscellaneous XDR helper functions -- cgit v1.2.3 From 203a8c8e66278a5936a230edaac29017e50c88fb Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Sat, 21 Feb 2009 13:29:14 -0800 Subject: nfsd4: separate delegreturn case from preprocess_stateid_op Delegreturn is enough a special case for preprocess_stateid_op to warrant just open-coding it in delegreturn. There should be no change in behavior here; we're just reshuffling code. Thanks to Yang Hongyang for catching a critical typo. Reviewed-by: Yang Hongyang Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 40 ++++++++++++++++++++++++++++------------ include/linux/nfsd/state.h | 1 - 2 files changed, 28 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index d5555850cb64..3570a0d1133f 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -2000,10 +2000,7 @@ out: static inline __be32 check_special_stateids(svc_fh *current_fh, stateid_t *stateid, int flags) { - /* Trying to call delegreturn with a special stateid? Yuch: */ - if (!(flags & (RD_STATE | WR_STATE))) - return nfserr_bad_stateid; - else if (ONE_STATEID(stateid) && (flags & RD_STATE)) + if (ONE_STATEID(stateid) && (flags & RD_STATE)) return nfs_ok; else if (locks_in_grace()) { /* Answer in remaining cases depends on existance of @@ -2024,8 +2021,7 @@ check_special_stateids(svc_fh *current_fh, stateid_t *stateid, int flags) static inline int io_during_grace_disallowed(struct inode *inode, int flags) { - return locks_in_grace() && (flags & (RD_STATE | WR_STATE)) - && mandatory_lock(inode); + return locks_in_grace() && mandatory_lock(inode); } static int check_stateid_generation(stateid_t *in, stateid_t *ref) @@ -2089,8 +2085,6 @@ nfs4_preprocess_stateid_op(struct svc_fh *current_fh, stateid_t *stateid, int fl if (status) goto out; renew_client(dp->dl_client); - if (flags & DELEG_RET) - unhash_delegation(dp); if (filpp) *filpp = dp->dl_vfs_file; } else { /* open or lock stateid */ @@ -2408,16 +2402,38 @@ __be32 nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_delegreturn *dr) { + struct nfs4_delegation *dp; + stateid_t *stateid = &dr->dr_stateid; + struct inode *inode; __be32 status; if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) - goto out; + return status; + inode = cstate->current_fh.fh_dentry->d_inode; nfs4_lock_state(); - status = nfs4_preprocess_stateid_op(&cstate->current_fh, - &dr->dr_stateid, DELEG_RET, NULL); - nfs4_unlock_state(); + status = nfserr_bad_stateid; + if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) + goto out; + status = nfserr_stale_stateid; + if (STALE_STATEID(stateid)) + goto out; + status = nfs_ok; + if (!is_delegation_stateid(stateid)) + goto out; + status = nfserr_bad_stateid; + dp = find_delegation_stateid(inode, stateid); + if (!dp) + goto out; + status = check_stateid_generation(stateid, &dp->dl_stateid); + if (status) + goto out; + renew_client(dp->dl_client); + + unhash_delegation(dp); out: + nfs4_unlock_state(); + return status; } diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 1130d534bb63..c9311a1e2e1a 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -263,7 +263,6 @@ struct nfs4_stateid { #define RD_STATE 0x00000010 #define WR_STATE 0x00000020 #define CLOSE_STATE 0x00000040 -#define DELEG_RET 0x00000080 #define seqid_mutating_err(err) \ (((err) != nfserr_stale_clientid) && \ -- cgit v1.2.3 From 6150ef0dc7f734366d297e2eb5697ae458a1ea19 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Sat, 21 Feb 2009 13:36:16 -0800 Subject: nfsd4: remove unused CHECK_FH flag All users now pass this, so it's meaningless. Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 6 +++--- fs/nfsd/nfs4state.c | 2 +- include/linux/nfsd/state.h | 1 - 3 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index af66073ed423..77f584f69dfe 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -519,7 +519,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, /* check stateid */ if ((status = nfs4_preprocess_stateid_op(&cstate->current_fh, &read->rd_stateid, - CHECK_FH | RD_STATE, &read->rd_filp))) { + RD_STATE, &read->rd_filp))) { dprintk("NFSD: nfsd4_read: couldn't process stateid!\n"); goto out; } @@ -651,7 +651,7 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (setattr->sa_iattr.ia_valid & ATTR_SIZE) { nfs4_lock_state(); status = nfs4_preprocess_stateid_op(&cstate->current_fh, - &setattr->sa_stateid, CHECK_FH | WR_STATE, NULL); + &setattr->sa_stateid, WR_STATE, NULL); nfs4_unlock_state(); if (status) { dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n"); @@ -690,7 +690,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfs4_lock_state(); status = nfs4_preprocess_stateid_op(&cstate->current_fh, stateid, - CHECK_FH | WR_STATE, &filp); + WR_STATE, &filp); if (filp) get_file(filp); nfs4_unlock_state(); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 6ae28e606afc..5957f7766bdc 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -2091,7 +2091,7 @@ nfs4_preprocess_stateid_op(struct svc_fh *current_fh, stateid_t *stateid, int fl stp = find_stateid(stateid, flags); if (!stp) goto out; - if ((flags & CHECK_FH) && nfs4_check_fh(current_fh, stp)) + if (nfs4_check_fh(current_fh, stp)) goto out; if (!stp->st_stateowner->so_confirmed) goto out; diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index c9311a1e2e1a..503b6bb53a56 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -256,7 +256,6 @@ struct nfs4_stateid { }; /* flags for preprocess_seqid_op() */ -#define CHECK_FH 0x00000001 #define CONFIRM 0x00000002 #define OPEN_STATE 0x00000004 #define LOCK_STATE 0x00000008 -- cgit v1.2.3 From 8b671b80707e4fc76adfe4387df07b3be1007c1e Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Sun, 22 Feb 2009 14:51:34 -0800 Subject: nfsd4: remove use of mutex for file_hashtable As part of reducing the scope of the client_mutex, and in order to remove the need for mutexes from the callback code (so that callbacks can be done as asynchronous rpc calls), move manipulations of the file_hashtable under the recall_lock. Update the relevant comments while we're here. Signed-off-by: J. Bruce Fields Cc: Alexandros Batsakis Reviewed-by: Benny Halevy --- fs/nfsd/nfs4callback.c | 2 -- fs/nfsd/nfs4state.c | 47 +++++++++++++++++++++++----------------------- include/linux/nfsd/state.h | 2 +- 3 files changed, 24 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 3fd7136321ca..5dcd38e5f138 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -491,8 +491,6 @@ out_put_cred: * or deleg_return. */ put_nfs4_client(clp); - nfs4_lock_state(); nfs4_put_delegation(dp); - nfs4_unlock_state(); return; } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 89e575e7daea..54651aa45790 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -78,14 +78,18 @@ static struct nfs4_delegation * find_delegation_stateid(struct inode *ino, state static char user_recovery_dirname[PATH_MAX] = "/var/lib/nfs/v4recovery"; static void nfs4_set_recdir(char *recdir); -/* Locking: - * - * client_mutex: - * protects clientid_hashtbl[], clientstr_hashtbl[], - * unconfstr_hashtbl[], uncofid_hashtbl[]. - */ +/* Locking: */ + +/* Currently used for almost all code touching nfsv4 state: */ static DEFINE_MUTEX(client_mutex); +/* + * Currently used for the del_recall_lru and file hash table. In an + * effort to decrease the scope of the client_mutex, this spinlock may + * eventually cover more: + */ +static DEFINE_SPINLOCK(recall_lock); + static struct kmem_cache *stateowner_slab = NULL; static struct kmem_cache *file_slab = NULL; static struct kmem_cache *stateid_slab = NULL; @@ -116,33 +120,23 @@ opaque_hashval(const void *ptr, int nbytes) return x; } -/* - * Delegation state - */ - -/* recall_lock protects the del_recall_lru */ -static DEFINE_SPINLOCK(recall_lock); static struct list_head del_recall_lru; -static void -free_nfs4_file(struct kref *kref) -{ - struct nfs4_file *fp = container_of(kref, struct nfs4_file, fi_ref); - list_del(&fp->fi_hash); - iput(fp->fi_inode); - kmem_cache_free(file_slab, fp); -} - static inline void put_nfs4_file(struct nfs4_file *fi) { - kref_put(&fi->fi_ref, free_nfs4_file); + if (atomic_dec_and_lock(&fi->fi_ref, &recall_lock)) { + list_del(&fi->fi_hash); + spin_unlock(&recall_lock); + iput(fi->fi_inode); + kmem_cache_free(file_slab, fi); + } } static inline void get_nfs4_file(struct nfs4_file *fi) { - kref_get(&fi->fi_ref); + atomic_inc(&fi->fi_ref); } static int num_delegations; @@ -1000,11 +994,13 @@ alloc_init_file(struct inode *ino) fp = kmem_cache_alloc(file_slab, GFP_KERNEL); if (fp) { - kref_init(&fp->fi_ref); + atomic_set(&fp->fi_ref, 1); INIT_LIST_HEAD(&fp->fi_hash); INIT_LIST_HEAD(&fp->fi_stateids); INIT_LIST_HEAD(&fp->fi_delegations); + spin_lock(&recall_lock); list_add(&fp->fi_hash, &file_hashtbl[hashval]); + spin_unlock(&recall_lock); fp->fi_inode = igrab(ino); fp->fi_id = current_fileid++; fp->fi_had_conflict = false; @@ -1177,12 +1173,15 @@ find_file(struct inode *ino) unsigned int hashval = file_hashval(ino); struct nfs4_file *fp; + spin_lock(&recall_lock); list_for_each_entry(fp, &file_hashtbl[hashval], fi_hash) { if (fp->fi_inode == ino) { get_nfs4_file(fp); + spin_unlock(&recall_lock); return fp; } } + spin_unlock(&recall_lock); return NULL; } diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 503b6bb53a56..a6e4a00fa392 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -214,7 +214,7 @@ struct nfs4_stateowner { * share_acces, share_deny on the file. */ struct nfs4_file { - struct kref fi_ref; + atomic_t fi_ref; struct list_head fi_hash; /* hash by "struct inode *" */ struct list_head fi_stateids; struct list_head fi_delegations; -- cgit v1.2.3 From 31dec2538e45e9fff2007ea1f4c6bae9f78db724 Mon Sep 17 00:00:00 2001 From: David Shaw Date: Thu, 5 Mar 2009 20:16:14 -0500 Subject: Short write in nfsd becomes a full write to the client If a filesystem being written to via NFS returns a short write count (as opposed to an error) to nfsd, nfsd treats that as a success for the entire write, rather than the short count that actually succeeded. For example, given a 8192 byte write, if the underlying filesystem only writes 4096 bytes, nfsd will ack back to the nfs client that all 8192 bytes were written. The nfs client does have retry logic for short writes, but this is never called as the client is told the complete write succeeded. There are probably other ways it could happen, but in my case it happened with a fuse (filesystem in userspace) filesystem which can rather easily have a partial write. Here is a patch to properly return the short write count to the client. Signed-off-by: David Shaw Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs3proc.c | 5 +++-- fs/nfsd/nfs4proc.c | 7 +++++-- fs/nfsd/nfsproc.c | 3 ++- fs/nfsd/vfs.c | 13 +++++++------ include/linux/nfsd/nfsd.h | 2 +- 5 files changed, 18 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 579ce8c69daa..7c9fe838f038 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -203,6 +203,7 @@ nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp, struct nfsd3_writeres *resp) { __be32 nfserr; + unsigned long cnt = argp->len; dprintk("nfsd: WRITE(3) %s %d bytes at %ld%s\n", SVCFH_fmt(&argp->fh), @@ -215,9 +216,9 @@ nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp, nfserr = nfsd_write(rqstp, &resp->fh, NULL, argp->offset, rqstp->rq_vec, argp->vlen, - argp->len, + &cnt, &resp->committed); - resp->count = argp->count; + resp->count = cnt; RETURN_STATUS(nfserr); } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 77f584f69dfe..283d77a47120 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -682,6 +682,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct file *filp = NULL; u32 *p; __be32 status = nfs_ok; + unsigned long cnt; /* no need to check permission - this will be done in nfsd_write() */ @@ -700,7 +701,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return status; } - write->wr_bytes_written = write->wr_buflen; + cnt = write->wr_buflen; write->wr_how_written = write->wr_stable_how; p = (u32 *)write->wr_verifier.data; *p++ = nfssvc_boot.tv_sec; @@ -708,10 +709,12 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfsd_write(rqstp, &cstate->current_fh, filp, write->wr_offset, rqstp->rq_vec, write->wr_vlen, - write->wr_buflen, &write->wr_how_written); + &cnt, &write->wr_how_written); if (filp) fput(filp); + write->wr_bytes_written = cnt; + if (status == nfserr_symlink) status = nfserr_inval; return status; diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 6f7f26351227..e298e260b5f1 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -180,6 +180,7 @@ nfsd_proc_write(struct svc_rqst *rqstp, struct nfsd_writeargs *argp, { __be32 nfserr; int stable = 1; + unsigned long cnt = argp->len; dprintk("nfsd: WRITE %s %d bytes at %d\n", SVCFH_fmt(&argp->fh), @@ -188,7 +189,7 @@ nfsd_proc_write(struct svc_rqst *rqstp, struct nfsd_writeargs *argp, nfserr = nfsd_write(rqstp, fh_copy(&resp->fh, &argp->fh), NULL, argp->offset, rqstp->rq_vec, argp->vlen, - argp->len, + &cnt, &stable); return nfsd_return_attrs(nfserr, resp); } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 0c076293155d..54404d730809 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -960,7 +960,7 @@ static void kill_suid(struct dentry *dentry) static __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) + unsigned long *cnt, int *stablep) { struct svc_export *exp; struct dentry *dentry; @@ -974,7 +974,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, err = nfserr_perm; if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) && - (!lock_may_write(file->f_path.dentry->d_inode, offset, cnt))) + (!lock_may_write(file->f_path.dentry->d_inode, offset, *cnt))) goto out; #endif @@ -1006,7 +1006,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &offset); set_fs(oldfs); if (host_err >= 0) { - nfsdstats.io_write += cnt; + nfsdstats.io_write += host_err; fsnotify_modify(file->f_path.dentry); } @@ -1051,9 +1051,10 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, } dprintk("nfsd: write complete host_err=%d\n", host_err); - if (host_err >= 0) + if (host_err >= 0) { err = 0; - else + *cnt = host_err; + } else err = nfserrno(host_err); out: return err; @@ -1095,7 +1096,7 @@ out: */ __be32 nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, - loff_t offset, struct kvec *vec, int vlen, unsigned long cnt, + loff_t offset, struct kvec *vec, int vlen, unsigned long *cnt, int *stablep) { __be32 err = 0; diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 16f7b403d9c1..54beda12d26b 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -105,7 +105,7 @@ void nfsd_close(struct file *); __be32 nfsd_read(struct svc_rqst *, struct svc_fh *, struct file *, 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 *); + loff_t, struct kvec *,int, unsigned long *, int *); __be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *, char *, int *); __be32 nfsd_symlink(struct svc_rqst *, struct svc_fh *, -- cgit v1.2.3 From 59a252ff8c0f2fa32c896f69d56ae33e641ce7ad Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Tue, 13 Jan 2009 21:26:35 +1100 Subject: knfsd: avoid overloading the CPU scheduler with enormous load averages Avoid overloading the CPU scheduler with enormous load averages when handling high call-rate NFS loads. When the knfsd bottom half is made aware of an incoming call by the socket layer, it tries to choose an nfsd thread and wake it up. As long as there are idle threads, one will be woken up. If there are lot of nfsd threads (a sensible configuration when the server is disk-bound or is running an HSM), there will be many more nfsd threads than CPUs to run them. Under a high call-rate low service-time workload, the result is that almost every nfsd is runnable, but only a handful are actually able to run. This situation causes two significant problems: 1. The CPU scheduler takes over 10% of each CPU, which is robbing the nfsd threads of valuable CPU time. 2. At a high enough load, the nfsd threads starve userspace threads of CPU time, to the point where daemons like portmap and rpc.mountd do not schedule for tens of seconds at a time. Clients attempting to mount an NFS filesystem timeout at the very first step (opening a TCP connection to portmap) because portmap cannot wake up from select() and call accept() in time. Disclaimer: these effects were observed on a SLES9 kernel, modern kernels' schedulers may behave more gracefully. The solution is simple: keep in each svc_pool a counter of the number of threads which have been woken but have not yet run, and do not wake any more if that count reaches an arbitrary small threshold. Testing was on a 4 CPU 4 NIC Altix using 4 IRIX clients, each with 16 synthetic client threads simulating an rsync (i.e. recursive directory listing) workload reading from an i386 RH9 install image (161480 regular files in 10841 directories) on the server. That tree is small enough to fill in the server's RAM so no disk traffic was involved. This setup gives a sustained call rate in excess of 60000 calls/sec before being CPU-bound on the server. The server was running 128 nfsds. Profiling showed schedule() taking 6.7% of every CPU, and __wake_up() taking 5.2%. This patch drops those contributions to 3.0% and 2.2%. Load average was over 120 before the patch, and 20.9 after. This patch is a forward-ported version of knfsd-avoid-nfsd-overload which has been shipping in the SGI "Enhanced NFS" product since 2006. It has been posted before: http://article.gmane.org/gmane.linux.nfs/10374 Signed-off-by: Greg Banks Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 2 ++ net/sunrpc/svc_xprt.c | 25 ++++++++++++++++++------- 2 files changed, 20 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 3435d24bfe55..39ec186a492d 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -41,6 +41,7 @@ struct svc_pool { struct list_head sp_sockets; /* pending sockets */ unsigned int sp_nrthreads; /* # of threads in pool */ struct list_head sp_all_threads; /* all server threads */ + int sp_nwaking; /* number of threads woken but not yet active */ } ____cacheline_aligned_in_smp; /* @@ -264,6 +265,7 @@ struct svc_rqst { * cache pages */ wait_queue_head_t rq_wait; /* synchronization */ struct task_struct *rq_task; /* service thread */ + int rq_waking; /* 1 if thread is being woken */ }; /* diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index e588df5d6b34..0551b6b6cf8c 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -14,6 +14,8 @@ #define RPCDBG_FACILITY RPCDBG_SVCXPRT +#define SVC_MAX_WAKING 5 + static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt); static int svc_deferred_recv(struct svc_rqst *rqstp); static struct cache_deferred_req *svc_defer(struct cache_req *req); @@ -298,6 +300,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) struct svc_pool *pool; struct svc_rqst *rqstp; int cpu; + int thread_avail; if (!(xprt->xpt_flags & ((1<sp_lock); - if (!list_empty(&pool->sp_threads) && - !list_empty(&pool->sp_sockets)) - printk(KERN_ERR - "svc_xprt_enqueue: " - "threads and transports both waiting??\n"); - if (test_bit(XPT_DEAD, &xprt->xpt_flags)) { /* Don't enqueue dead transports */ dprintk("svc: transport %p is dead, not enqueued\n", xprt); @@ -353,7 +350,14 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) } process: - if (!list_empty(&pool->sp_threads)) { + /* Work out whether threads are available */ + thread_avail = !list_empty(&pool->sp_threads); /* threads are asleep */ + if (pool->sp_nwaking >= SVC_MAX_WAKING) { + /* too many threads are runnable and trying to wake up */ + thread_avail = 0; + } + + if (thread_avail) { rqstp = list_entry(pool->sp_threads.next, struct svc_rqst, rq_list); @@ -368,6 +372,8 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) svc_xprt_get(xprt); rqstp->rq_reserved = serv->sv_max_mesg; atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved); + rqstp->rq_waking = 1; + pool->sp_nwaking++; BUG_ON(xprt->xpt_pool != pool); wake_up(&rqstp->rq_wait); } else { @@ -633,6 +639,11 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) return -EINTR; spin_lock_bh(&pool->sp_lock); + if (rqstp->rq_waking) { + rqstp->rq_waking = 0; + pool->sp_nwaking--; + BUG_ON(pool->sp_nwaking < 0); + } xprt = svc_xprt_dequeue(pool); if (xprt) { rqstp->rq_xprt = xprt; -- cgit v1.2.3 From 03cf6c9f49a8fea953d38648d016e3f46e814991 Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Tue, 13 Jan 2009 21:26:36 +1100 Subject: knfsd: add file to export stats about nfsd pools Add /proc/fs/nfsd/pool_stats to export to userspace various statistics about the operation of rpc server thread pools. This patch is based on a forward-ported version of knfsd-add-pool-thread-stats which has been shipping in the SGI "Enhanced NFS" product since 2006 and which was previously posted: http://article.gmane.org/gmane.linux.nfs/10375 It has also been updated thus: * moved EXPORT_SYMBOL() to near the function it exports * made the new struct struct seq_operations const * used SEQ_START_TOKEN instead of ((void *)1) * merged fix from SGI PV 990526 "sunrpc: use dprintk instead of printk in svc_pool_stats_*()" by Harshula Jayasuriya. * merged fix from SGI PV 964001 "Crash reading pool_stats before nfsds are started". Signed-off-by: Greg Banks Signed-off-by: Harshula Jayasuriya Signed-off-by: J. Bruce Fields --- fs/nfsd/nfsctl.c | 12 ++++++ fs/nfsd/nfssvc.c | 7 ++++ include/linux/sunrpc/svc.h | 11 +++++ net/sunrpc/svc_xprt.c | 100 ++++++++++++++++++++++++++++++++++++++++++++- 4 files changed, 129 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 3d93b2064ce5..4adebb6312c4 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -60,6 +60,7 @@ enum { NFSD_FO_UnlockFS, NFSD_Threads, NFSD_Pool_Threads, + NFSD_Pool_Stats, NFSD_Versions, NFSD_Ports, NFSD_MaxBlkSize, @@ -172,6 +173,16 @@ static const struct file_operations exports_operations = { .owner = THIS_MODULE, }; +extern int nfsd_pool_stats_open(struct inode *inode, struct file *file); + +static struct file_operations pool_stats_operations = { + .open = nfsd_pool_stats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, + .owner = THIS_MODULE, +}; + /*----------------------------------------------------------------------------*/ /* * payload - write methods @@ -1246,6 +1257,7 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent) [NFSD_Fh] = {"filehandle", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Threads] = {"threads", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Pool_Threads] = {"pool_threads", &transaction_ops, S_IWUSR|S_IRUSR}, + [NFSD_Pool_Stats] = {"pool_stats", &pool_stats_operations, S_IRUGO}, [NFSD_Versions] = {"versions", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Ports] = {"portlist", &transaction_ops, S_IWUSR|S_IRUGO}, [NFSD_MaxBlkSize] = {"max_block_size", &transaction_ops, S_IWUSR|S_IRUGO}, diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index c3eb0759fd57..ef0a3686639d 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -546,3 +546,10 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) nfsd_cache_update(rqstp, proc->pc_cachetype, statp + 1); return 1; } + +int nfsd_pool_stats_open(struct inode *inode, struct file *file) +{ + if (nfsd_serv == NULL) + return -ENODEV; + return svc_pool_stats_open(nfsd_serv, file); +} diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 39ec186a492d..9f9f699dd469 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -24,6 +24,15 @@ */ typedef int (*svc_thread_fn)(void *); +/* statistics for svc_pool structures */ +struct svc_pool_stats { + unsigned long packets; + unsigned long sockets_queued; + unsigned long threads_woken; + unsigned long overloads_avoided; + unsigned long threads_timedout; +}; + /* * * RPC service thread pool. @@ -42,6 +51,7 @@ struct svc_pool { unsigned int sp_nrthreads; /* # of threads in pool */ struct list_head sp_all_threads; /* all server threads */ int sp_nwaking; /* number of threads woken but not yet active */ + struct svc_pool_stats sp_stats; /* statistics on pool operation */ } ____cacheline_aligned_in_smp; /* @@ -396,6 +406,7 @@ struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, sa_family_t, void (*shutdown)(struct svc_serv *), svc_thread_fn, struct module *); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); +int svc_pool_stats_open(struct svc_serv *serv, struct file *file); void svc_destroy(struct svc_serv *); int svc_process(struct svc_rqst *); int svc_register(const struct svc_serv *, const unsigned short, diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 0551b6b6cf8c..1e66f2491460 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -318,6 +318,8 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) goto out_unlock; } + pool->sp_stats.packets++; + /* Mark transport as busy. It will remain in this state until * the provider calls svc_xprt_received. We update XPT_BUSY * atomically because it also guards against trying to enqueue @@ -355,6 +357,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) if (pool->sp_nwaking >= SVC_MAX_WAKING) { /* too many threads are runnable and trying to wake up */ thread_avail = 0; + pool->sp_stats.overloads_avoided++; } if (thread_avail) { @@ -374,11 +377,13 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved); rqstp->rq_waking = 1; pool->sp_nwaking++; + pool->sp_stats.threads_woken++; BUG_ON(xprt->xpt_pool != pool); wake_up(&rqstp->rq_wait); } else { dprintk("svc: transport %p put into queue\n", xprt); list_add_tail(&xprt->xpt_ready, &pool->sp_sockets); + pool->sp_stats.sockets_queued++; BUG_ON(xprt->xpt_pool != pool); } @@ -591,6 +596,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) int pages; struct xdr_buf *arg; DECLARE_WAITQUEUE(wait, current); + long time_left; dprintk("svc: server %p waiting for data (to = %ld)\n", rqstp, timeout); @@ -676,12 +682,14 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) add_wait_queue(&rqstp->rq_wait, &wait); spin_unlock_bh(&pool->sp_lock); - schedule_timeout(timeout); + time_left = schedule_timeout(timeout); try_to_freeze(); spin_lock_bh(&pool->sp_lock); remove_wait_queue(&rqstp->rq_wait, &wait); + if (!time_left) + pool->sp_stats.threads_timedout++; xprt = rqstp->rq_xprt; if (!xprt) { @@ -1114,3 +1122,93 @@ int svc_xprt_names(struct svc_serv *serv, char *buf, int buflen) return totlen; } EXPORT_SYMBOL_GPL(svc_xprt_names); + + +/*----------------------------------------------------------------------------*/ + +static void *svc_pool_stats_start(struct seq_file *m, loff_t *pos) +{ + unsigned int pidx = (unsigned int)*pos; + struct svc_serv *serv = m->private; + + dprintk("svc_pool_stats_start, *pidx=%u\n", pidx); + + lock_kernel(); + /* bump up the pseudo refcount while traversing */ + svc_get(serv); + unlock_kernel(); + + if (!pidx) + return SEQ_START_TOKEN; + return (pidx > serv->sv_nrpools ? NULL : &serv->sv_pools[pidx-1]); +} + +static void *svc_pool_stats_next(struct seq_file *m, void *p, loff_t *pos) +{ + struct svc_pool *pool = p; + struct svc_serv *serv = m->private; + + dprintk("svc_pool_stats_next, *pos=%llu\n", *pos); + + if (p == SEQ_START_TOKEN) { + pool = &serv->sv_pools[0]; + } else { + unsigned int pidx = (pool - &serv->sv_pools[0]); + if (pidx < serv->sv_nrpools-1) + pool = &serv->sv_pools[pidx+1]; + else + pool = NULL; + } + ++*pos; + return pool; +} + +static void svc_pool_stats_stop(struct seq_file *m, void *p) +{ + struct svc_serv *serv = m->private; + + lock_kernel(); + /* this function really, really should have been called svc_put() */ + svc_destroy(serv); + unlock_kernel(); +} + +static int svc_pool_stats_show(struct seq_file *m, void *p) +{ + struct svc_pool *pool = p; + + if (p == SEQ_START_TOKEN) { + seq_puts(m, "# pool packets-arrived sockets-enqueued threads-woken overloads-avoided threads-timedout\n"); + return 0; + } + + seq_printf(m, "%u %lu %lu %lu %lu %lu\n", + pool->sp_id, + pool->sp_stats.packets, + pool->sp_stats.sockets_queued, + pool->sp_stats.threads_woken, + pool->sp_stats.overloads_avoided, + pool->sp_stats.threads_timedout); + + return 0; +} + +static const struct seq_operations svc_pool_stats_seq_ops = { + .start = svc_pool_stats_start, + .next = svc_pool_stats_next, + .stop = svc_pool_stats_stop, + .show = svc_pool_stats_show, +}; + +int svc_pool_stats_open(struct svc_serv *serv, struct file *file) +{ + int err; + + err = seq_open(file, &svc_pool_stats_seq_ops); + if (!err) + ((struct seq_file *) file->private_data)->private = serv; + return err; +} +EXPORT_SYMBOL(svc_pool_stats_open); + +/*----------------------------------------------------------------------------*/ -- cgit v1.2.3 From 2795e53b4ed5d1f49d2283f416c922f55ec7d461 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 12 Mar 2009 12:07:14 -0400 Subject: SUNRPC: Clean up static inline functions in svc_xprt.h Clean up: Enable the use of const arguments in higher level svc_ APIs by adding const to the arguments of the helper functions in svc_xprt.h Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_xprt.h | 46 +++++++++++++++++++++++------------------ 1 file changed, 26 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 0127daca4354..959b931b6053 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -88,29 +88,32 @@ static inline void svc_xprt_get(struct svc_xprt *xprt) kref_get(&xprt->xpt_ref); } static inline void svc_xprt_set_local(struct svc_xprt *xprt, - struct sockaddr *sa, int salen) + const struct sockaddr *sa, + const size_t salen) { memcpy(&xprt->xpt_local, sa, salen); xprt->xpt_locallen = salen; } static inline void svc_xprt_set_remote(struct svc_xprt *xprt, - struct sockaddr *sa, int salen) + const struct sockaddr *sa, + const size_t salen) { memcpy(&xprt->xpt_remote, sa, salen); xprt->xpt_remotelen = salen; } -static inline unsigned short svc_addr_port(struct sockaddr *sa) +static inline unsigned short svc_addr_port(const struct sockaddr *sa) { - unsigned short ret = 0; + const struct sockaddr_in *sin = (const struct sockaddr_in *)sa; + const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)sa; + switch (sa->sa_family) { case AF_INET: - ret = ntohs(((struct sockaddr_in *)sa)->sin_port); - break; + return ntohs(sin->sin_port); case AF_INET6: - ret = ntohs(((struct sockaddr_in6 *)sa)->sin6_port); - break; + return ntohs(sin6->sin6_port); } - return ret; + + return 0; } static inline size_t svc_addr_len(struct sockaddr *sa) @@ -124,36 +127,39 @@ static inline size_t svc_addr_len(struct sockaddr *sa) return -EAFNOSUPPORT; } -static inline unsigned short svc_xprt_local_port(struct svc_xprt *xprt) +static inline unsigned short svc_xprt_local_port(const struct svc_xprt *xprt) { - return svc_addr_port((struct sockaddr *)&xprt->xpt_local); + return svc_addr_port((const struct sockaddr *)&xprt->xpt_local); } -static inline unsigned short svc_xprt_remote_port(struct svc_xprt *xprt) +static inline unsigned short svc_xprt_remote_port(const struct svc_xprt *xprt) { - return svc_addr_port((struct sockaddr *)&xprt->xpt_remote); + return svc_addr_port((const struct sockaddr *)&xprt->xpt_remote); } -static inline char *__svc_print_addr(struct sockaddr *addr, - char *buf, size_t len) +static inline char *__svc_print_addr(const struct sockaddr *addr, + char *buf, const size_t len) { + const struct sockaddr_in *sin = (const struct sockaddr_in *)addr; + const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)addr; + switch (addr->sa_family) { case AF_INET: - snprintf(buf, len, "%pI4, port=%u", - &((struct sockaddr_in *)addr)->sin_addr, - ntohs(((struct sockaddr_in *) addr)->sin_port)); + snprintf(buf, len, "%pI4, port=%u", &sin->sin_addr, + ntohs(sin->sin_port)); break; case AF_INET6: snprintf(buf, len, "%pI6, port=%u", - &((struct sockaddr_in6 *)addr)->sin6_addr, - ntohs(((struct sockaddr_in6 *) addr)->sin6_port)); + &sin6->sin6_addr, + ntohs(sin6->sin6_port)); break; default: snprintf(buf, len, "unknown address type: %d", addr->sa_family); break; } + return buf; } #endif /* SUNRPC_SVC_XPRT_H */ -- cgit v1.2.3 From 42d671c78f6486c932b68a50f88768c7b4e57ebf Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Fri, 27 Mar 2009 02:32:47 +1100 Subject: Fix a build warning about leaking CONFIG_NFSD to userspace. Fix a build warning about leaking CONFIG_NFSD to userspace. The nfsd_stats data structure does not need to be available to userspace; no kernel interface uses it. So move it inside #ifdef __KERNEL__ and the warning goes away. Signed-off-by: Greg Banks Signed-off-by: J. Bruce Fields --- include/linux/nfsd/stats.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/nfsd/stats.h b/include/linux/nfsd/stats.h index 7678cfbe9960..2693ef647df6 100644 --- a/include/linux/nfsd/stats.h +++ b/include/linux/nfsd/stats.h @@ -11,6 +11,11 @@ #include +/* thread usage wraps very million seconds (approx one fortnight) */ +#define NFSD_USAGE_WRAP (HZ*1000000) + +#ifdef __KERNEL__ + struct nfsd_stats { unsigned int rchits; /* repcache hits */ unsigned int rcmisses; /* repcache hits */ @@ -35,10 +40,6 @@ struct nfsd_stats { }; -/* thread usage wraps very million seconds (approx one fortnight) */ -#define NFSD_USAGE_WRAP (HZ*1000000) - -#ifdef __KERNEL__ extern struct nfsd_stats nfsdstats; extern struct svc_stat nfsd_svcstats; -- cgit v1.2.3 From e354d571bb481f1d71f2c3004b9ff570b32e83bd Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Sat, 28 Mar 2009 11:30:52 +0300 Subject: nfsd: embed nfsd4_current_state in nfsd4_compoundres Remove the allocation of struct nfsd4_compound_state. Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 40 +++++++++------------------------------- include/linux/nfsd/xdr4.h | 9 +++++---- 2 files changed, 14 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index f156b85b4129..7bb8cb321dfe 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -809,29 +809,6 @@ static inline void nfsd4_increment_op_stats(u32 opnum) nfsdstats.nfs4_opcount[opnum]++; } -static void cstate_free(struct nfsd4_compound_state *cstate) -{ - if (cstate == NULL) - return; - fh_put(&cstate->current_fh); - fh_put(&cstate->save_fh); - BUG_ON(cstate->replay_owner); - kfree(cstate); -} - -static struct nfsd4_compound_state *cstate_alloc(void) -{ - struct nfsd4_compound_state *cstate; - - cstate = kmalloc(sizeof(struct nfsd4_compound_state), GFP_KERNEL); - if (cstate == NULL) - return NULL; - fh_init(&cstate->current_fh, NFS4_FHSIZE); - fh_init(&cstate->save_fh, NFS4_FHSIZE); - cstate->replay_owner = NULL; - return cstate; -} - typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *, void *); @@ -859,12 +836,13 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, { struct nfsd4_op *op; struct nfsd4_operation *opdesc; - struct nfsd4_compound_state *cstate = NULL; + struct nfsd4_compound_state *cstate = &resp->cstate; int slack_bytes; __be32 status; resp->xbuf = &rqstp->rq_res; - resp->p = rqstp->rq_res.head[0].iov_base + rqstp->rq_res.head[0].iov_len; + resp->p = rqstp->rq_res.head[0].iov_base + + rqstp->rq_res.head[0].iov_len; resp->tagp = resp->p; /* reserve space for: taglen, tag, and opcnt */ resp->p += 2 + XDR_QUADLEN(args->taglen); @@ -873,6 +851,9 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, resp->tag = args->tag; resp->opcnt = 0; resp->rqstp = rqstp; + resp->cstate.replay_owner = NULL; + fh_init(&resp->cstate.current_fh, NFS4_FHSIZE); + fh_init(&resp->cstate.save_fh, NFS4_FHSIZE); /* * According to RFC3010, this takes precedence over all other errors. @@ -881,11 +862,6 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, if (args->minorversion > NFSD_SUPPORTED_MINOR_VERSION) goto out; - status = nfserr_resource; - cstate = cstate_alloc(); - if (cstate == NULL) - goto out; - status = nfs_ok; while (!status && resp->opcnt < args->opcnt) { op = &args->ops[resp->opcnt++]; @@ -958,7 +934,9 @@ encode_op: nfsd4_increment_op_stats(op->opnum); } - cstate_free(cstate); + fh_put(&resp->cstate.current_fh); + fh_put(&resp->cstate.save_fh); + BUG_ON(resp->cstate.replay_owner); out: nfsd4_release_compoundargs(args); dprintk("nfsv4 compound returned %d\n", ntohl(status)); diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 27bd3e38ec5a..fd15ddc3359d 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -45,9 +45,9 @@ #define XDR_LEN(n) (((n) + 3) & ~3) struct nfsd4_compound_state { - struct svc_fh current_fh; - struct svc_fh save_fh; - struct nfs4_stateowner *replay_owner; + struct svc_fh current_fh; + struct svc_fh save_fh; + struct nfs4_stateowner *replay_owner; }; struct nfsd4_change_info { @@ -416,7 +416,8 @@ struct nfsd4_compoundres { u32 taglen; char * tag; u32 opcnt; - __be32 * tagp; /* where to encode tag and opcount */ + __be32 * tagp; /* tag, opcount encode location */ + struct nfsd4_compound_state cstate; }; #define NFS4_SVC_XDRSIZE sizeof(struct nfsd4_compoundargs) -- cgit v1.2.3 From 2f425878b6a71571341dcd3f9e9d1a6f6355da9c Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:27:32 +0300 Subject: nfsd: don't use the deferral service, return NFS4ERR_DELAY On an NFSv4.1 server cache miss that causes an upcall, NFS4ERR_DELAY will be returned. It is up to the NFSv4.1 client to resend only the operations that have not been processed. Initialize rq_usedeferral to 1 in svc_process(). It sill be turned off in nfsd4_proc_compound() only when NFSv4.1 Sessions are used. Note: this isn't an adequate solution on its own. It's acceptable as a way to get some minimal 4.1 up and working, but we're going to have to find a way to avoid returning DELAY in all common cases before 4.1 can really be considered ready. Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [nfsd41: reverse rq_nodeferral negative logic] Signed-off-by: Benny Halevy [sunrpc: initialize rq_usedeferral] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 8 ++++++++ include/linux/sunrpc/svc.h | 1 + net/sunrpc/svc.c | 2 ++ net/sunrpc/svc_xprt.c | 2 +- 4 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 249dad987a16..ded469ff08b3 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -854,6 +854,8 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, resp->cstate.replay_owner = NULL; fh_init(&resp->cstate.current_fh, NFS4_FHSIZE); fh_init(&resp->cstate.save_fh, NFS4_FHSIZE); + /* Use the deferral mechanism only for NFSv4.0 compounds */ + rqstp->rq_usedeferral = (args->minorversion == 0); /* * According to RFC3010, this takes precedence over all other errors. @@ -933,12 +935,18 @@ encode_op: nfsd4_increment_op_stats(op->opnum); } + if (!rqstp->rq_usedeferral && status == nfserr_dropit) { + dprintk("%s Dropit - send NFS4ERR_DELAY\n", __func__); + status = nfserr_jukebox; + } fh_put(&resp->cstate.current_fh); fh_put(&resp->cstate.save_fh); BUG_ON(resp->cstate.replay_owner); out: nfsd4_release_compoundargs(args); + /* Reset deferral mechanism for RPC deferrals */ + rqstp->rq_usedeferral = 1; dprintk("nfsv4 compound returned %d\n", ntohl(status)); return status; } diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 9f9f699dd469..815dd589d4db 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -230,6 +230,7 @@ struct svc_rqst { struct svc_cred rq_cred; /* auth info */ void * rq_xprt_ctxt; /* transport specific context ptr */ struct svc_deferred_req*rq_deferred; /* deferred request we are replaying */ + int rq_usedeferral; /* use deferral */ size_t rq_xprt_hlen; /* xprt header len */ struct xdr_buf rq_arg; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index fff09a2d8960..45984cbe1bfa 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1023,6 +1023,8 @@ svc_process(struct svc_rqst *rqstp) rqstp->rq_res.tail[0].iov_len = 0; /* Will be turned off only in gss privacy case: */ rqstp->rq_splice_ok = 1; + /* Will be turned off only when NFSv4 Sessions are used */ + rqstp->rq_usedeferral = 1; /* Setup reply header */ rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 1e66f2491460..600d0918e3ae 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -974,7 +974,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) struct svc_rqst *rqstp = container_of(req, struct svc_rqst, rq_chandle); struct svc_deferred_req *dr; - if (rqstp->rq_arg.page_len) + if (rqstp->rq_arg.page_len || !rqstp->rq_usedeferral) return NULL; /* if more than a page, give up FIXME */ if (rqstp->rq_deferred) { dr = rqstp->rq_deferred; -- cgit v1.2.3 From 18df1884a872a2cc405a578cfd0d3adc8d227277 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 3 Apr 2009 08:27:36 +0300 Subject: nfs41: common protocol definitions Define all NFSv4.1 common operation and error code constants. Note that some of the definitions are used by both the nfs41 client and the server code. This patch is duplicated in the nfs41 and nfsd41 sessions patchset. Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [nfs41: add exchange id flags] Signed-off-by: Mike Sager Signed-off-by: Benny Halevy [removed server-only hunk changing NFSERR_REPLAY_ME] Signed-off-by: Benny Halevy [nfs41: add SEQ4_XX to nfs41-common-protocol] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [nfs41: generic error code update] [nfs41: reverse EXCHGID4_INVAL_FLAG_MASK_{A,R}] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfs4.h | 128 ++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 127 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index b912311a56b1..29ed600e193b 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -21,6 +21,7 @@ #define NFS4_FHSIZE 128 #define NFS4_MAXPATHLEN PATH_MAX #define NFS4_MAXNAMLEN NAME_MAX +#define NFS4_MAX_SESSIONID_LEN 16 #define NFS4_ACCESS_READ 0x0001 #define NFS4_ACCESS_LOOKUP 0x0002 @@ -38,6 +39,7 @@ #define NFS4_OPEN_RESULT_CONFIRM 0x0002 #define NFS4_OPEN_RESULT_LOCKTYPE_POSIX 0x0004 +#define NFS4_SHARE_ACCESS_MASK 0x000F #define NFS4_SHARE_ACCESS_READ 0x0001 #define NFS4_SHARE_ACCESS_WRITE 0x0002 #define NFS4_SHARE_ACCESS_BOTH 0x0003 @@ -45,6 +47,19 @@ #define NFS4_SHARE_DENY_WRITE 0x0002 #define NFS4_SHARE_DENY_BOTH 0x0003 +/* nfs41 */ +#define NFS4_SHARE_WANT_MASK 0xFF00 +#define NFS4_SHARE_WANT_NO_PREFERENCE 0x0000 +#define NFS4_SHARE_WANT_READ_DELEG 0x0100 +#define NFS4_SHARE_WANT_WRITE_DELEG 0x0200 +#define NFS4_SHARE_WANT_ANY_DELEG 0x0300 +#define NFS4_SHARE_WANT_NO_DELEG 0x0400 +#define NFS4_SHARE_WANT_CANCEL 0x0500 + +#define NFS4_SHARE_WHEN_MASK 0xF0000 +#define NFS4_SHARE_SIGNAL_DELEG_WHEN_RESRC_AVAIL 0x10000 +#define NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED 0x20000 + #define NFS4_SET_TO_SERVER_TIME 0 #define NFS4_SET_TO_CLIENT_TIME 1 @@ -88,6 +103,31 @@ #define NFS4_ACE_GENERIC_EXECUTE 0x001200A0 #define NFS4_ACE_MASK_ALL 0x001F01FF +#define EXCHGID4_FLAG_SUPP_MOVED_REFER 0x00000001 +#define EXCHGID4_FLAG_SUPP_MOVED_MIGR 0x00000002 +#define EXCHGID4_FLAG_USE_NON_PNFS 0x00010000 +#define EXCHGID4_FLAG_USE_PNFS_MDS 0x00020000 +#define EXCHGID4_FLAG_USE_PNFS_DS 0x00040000 +#define EXCHGID4_FLAG_UPD_CONFIRMED_REC_A 0x40000000 +#define EXCHGID4_FLAG_CONFIRMED_R 0x80000000 +/* + * Since the validity of these bits depends on whether + * they're set in the argument or response, have separate + * invalid flag masks for arg (_A) and resp (_R). + */ +#define EXCHGID4_FLAG_MASK_A 0x40070003 +#define EXCHGID4_FLAG_MASK_R 0x80070003 + +#define SEQ4_STATUS_CB_PATH_DOWN 0x00000001 +#define SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING 0x00000002 +#define SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRED 0x00000004 +#define SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED 0x00000008 +#define SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED 0x00000010 +#define SEQ4_STATUS_ADMIN_STATE_REVOKED 0x00000020 +#define SEQ4_STATUS_RECALLABLE_STATE_REVOKED 0x00000040 +#define SEQ4_STATUS_LEASE_MOVED 0x00000080 +#define SEQ4_STATUS_RESTART_RECLAIM_NEEDED 0x00000100 + #define NFS4_MAX_UINT64 (~(u64)0) enum nfs4_acl_whotype { @@ -154,6 +194,28 @@ enum nfs_opnum4 { OP_VERIFY = 37, OP_WRITE = 38, OP_RELEASE_LOCKOWNER = 39, + + /* nfs41 */ + OP_BACKCHANNEL_CTL = 40, + OP_BIND_CONN_TO_SESSION = 41, + OP_EXCHANGE_ID = 42, + OP_CREATE_SESSION = 43, + OP_DESTROY_SESSION = 44, + OP_FREE_STATEID = 45, + OP_GET_DIR_DELEGATION = 46, + OP_GETDEVICEINFO = 47, + OP_GETDEVICELIST = 48, + OP_LAYOUTCOMMIT = 49, + OP_LAYOUTGET = 50, + OP_LAYOUTRETURN = 51, + OP_SECINFO_NO_NAME = 52, + OP_SEQUENCE = 53, + OP_SET_SSV = 54, + OP_TEST_STATEID = 55, + OP_WANT_DELEGATION = 56, + OP_DESTROY_CLIENTID = 57, + OP_RECLAIM_COMPLETE = 58, + OP_ILLEGAL = 10044, }; @@ -230,7 +292,48 @@ enum nfsstat4 { NFS4ERR_DEADLOCK = 10045, NFS4ERR_FILE_OPEN = 10046, NFS4ERR_ADMIN_REVOKED = 10047, - NFS4ERR_CB_PATH_DOWN = 10048 + NFS4ERR_CB_PATH_DOWN = 10048, + + /* nfs41 */ + NFS4ERR_BADIOMODE = 10049, + NFS4ERR_BADLAYOUT = 10050, + NFS4ERR_BAD_SESSION_DIGEST = 10051, + NFS4ERR_BADSESSION = 10052, + NFS4ERR_BADSLOT = 10053, + NFS4ERR_COMPLETE_ALREADY = 10054, + NFS4ERR_CONN_NOT_BOUND_TO_SESSION = 10055, + NFS4ERR_DELEG_ALREADY_WANTED = 10056, + NFS4ERR_BACK_CHAN_BUSY = 10057, /* backchan reqs outstanding */ + NFS4ERR_LAYOUTTRYLATER = 10058, + NFS4ERR_LAYOUTUNAVAILABLE = 10059, + NFS4ERR_NOMATCHING_LAYOUT = 10060, + NFS4ERR_RECALLCONFLICT = 10061, + NFS4ERR_UNKNOWN_LAYOUTTYPE = 10062, + NFS4ERR_SEQ_MISORDERED = 10063, /* unexpected seq.id in req */ + NFS4ERR_SEQUENCE_POS = 10064, /* [CB_]SEQ. op not 1st op */ + NFS4ERR_REQ_TOO_BIG = 10065, /* request too big */ + NFS4ERR_REP_TOO_BIG = 10066, /* reply too big */ + NFS4ERR_REP_TOO_BIG_TO_CACHE = 10067, /* rep. not all cached */ + NFS4ERR_RETRY_UNCACHED_REP = 10068, /* retry & rep. uncached */ + NFS4ERR_UNSAFE_COMPOUND = 10069, /* retry/recovery too hard */ + NFS4ERR_TOO_MANY_OPS = 10070, /* too many ops in [CB_]COMP */ + NFS4ERR_OP_NOT_IN_SESSION = 10071, /* op needs [CB_]SEQ. op */ + NFS4ERR_HASH_ALG_UNSUPP = 10072, /* hash alg. not supp. */ + /* Error 10073 is unused. */ + NFS4ERR_CLIENTID_BUSY = 10074, /* clientid has state */ + NFS4ERR_PNFS_IO_HOLE = 10075, /* IO to _SPARSE file hole */ + NFS4ERR_SEQ_FALSE_RETRY = 10076, /* retry not origional */ + NFS4ERR_BAD_HIGH_SLOT = 10077, /* sequence arg bad */ + NFS4ERR_DEADSESSION = 10078, /* persistent session dead */ + NFS4ERR_ENCR_ALG_UNSUPP = 10079, /* SSV alg mismatch */ + NFS4ERR_PNFS_NO_LAYOUT = 10080, /* direct I/O with no layout */ + NFS4ERR_NOT_ONLY_OP = 10081, /* bad compound */ + NFS4ERR_WRONG_CRED = 10082, /* permissions:state change */ + NFS4ERR_WRONG_TYPE = 10083, /* current operation mismatch */ + NFS4ERR_DIRDELEG_UNAVAIL = 10084, /* no directory delegation */ + NFS4ERR_REJECT_DELEG = 10085, /* on callback */ + NFS4ERR_RETURNCONFLICT = 10086, /* outstanding layoutreturn */ + NFS4ERR_DELEG_REVOKED = 10087, /* deleg./layout revoked */ }; /* @@ -391,6 +494,29 @@ enum { NFSPROC4_CLNT_GETACL, NFSPROC4_CLNT_SETACL, NFSPROC4_CLNT_FS_LOCATIONS, + + /* nfs41 */ + NFSPROC4_CLNT_EXCHANGE_ID, + NFSPROC4_CLNT_CREATE_SESSION, + NFSPROC4_CLNT_DESTROY_SESSION, + NFSPROC4_CLNT_SEQUENCE, + NFSPROC4_CLNT_GET_LEASE_TIME, +}; + +/* nfs41 types */ +struct nfs4_sessionid { + unsigned char data[NFS4_MAX_SESSIONID_LEN]; +}; + +/* Create Session Flags */ +#define SESSION4_PERSIST 0x001 +#define SESSION4_BACK_CHAN 0x002 +#define SESSION4_RDMA 0x004 + +enum state_protect_how4 { + SP4_NONE = 0, + SP4_MACH_CRED = 1, + SP4_SSV = 2 }; #endif -- cgit v1.2.3 From 10add806c38c022d18af48f3ec28c91b4eaf7bb3 Mon Sep 17 00:00:00 2001 From: Marc Eshel Date: Fri, 3 Apr 2009 08:27:40 +0300 Subject: nfsd41: define nfs41 error codes Define all error code present in http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-29. Signed-off-by: Benny Halevy [nfsd41: clean up error code definitions] [nfsd41: change NFSERR_REPLAY_ME] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfs.h | 1 - include/linux/nfsd/nfsd.h | 43 ++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 42 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nfs.h b/include/linux/nfs.h index 54af92c1c70b..214d499718f7 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -109,7 +109,6 @@ NFSERR_FILE_OPEN = 10046, /* v4 */ NFSERR_ADMIN_REVOKED = 10047, /* v4 */ NFSERR_CB_PATH_DOWN = 10048, /* v4 */ - NFSERR_REPLAY_ME = 10049 /* v4 */ }; /* NFSv2 file types - beware, these are not the same in NFSv3 */ diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 54beda12d26b..ab9616d09204 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -249,7 +249,44 @@ void nfsd_lockd_shutdown(void); #define nfserr_cb_path_down cpu_to_be32(NFSERR_CB_PATH_DOWN) #define nfserr_locked cpu_to_be32(NFSERR_LOCKED) #define nfserr_wrongsec cpu_to_be32(NFSERR_WRONGSEC) -#define nfserr_replay_me cpu_to_be32(NFSERR_REPLAY_ME) +#define nfserr_badiomode cpu_to_be32(NFS4ERR_BADIOMODE) +#define nfserr_badlayout cpu_to_be32(NFS4ERR_BADLAYOUT) +#define nfserr_bad_session_digest cpu_to_be32(NFS4ERR_BAD_SESSION_DIGEST) +#define nfserr_badsession cpu_to_be32(NFS4ERR_BADSESSION) +#define nfserr_badslot cpu_to_be32(NFS4ERR_BADSLOT) +#define nfserr_complete_already cpu_to_be32(NFS4ERR_COMPLETE_ALREADY) +#define nfserr_conn_not_bound_to_session cpu_to_be32(NFS4ERR_CONN_NOT_BOUND_TO_SESSION) +#define nfserr_deleg_already_wanted cpu_to_be32(NFS4ERR_DELEG_ALREADY_WANTED) +#define nfserr_back_chan_busy cpu_to_be32(NFS4ERR_BACK_CHAN_BUSY) +#define nfserr_layouttrylater cpu_to_be32(NFS4ERR_LAYOUTTRYLATER) +#define nfserr_layoutunavailable cpu_to_be32(NFS4ERR_LAYOUTUNAVAILABLE) +#define nfserr_nomatching_layout cpu_to_be32(NFS4ERR_NOMATCHING_LAYOUT) +#define nfserr_recallconflict cpu_to_be32(NFS4ERR_RECALLCONFLICT) +#define nfserr_unknown_layouttype cpu_to_be32(NFS4ERR_UNKNOWN_LAYOUTTYPE) +#define nfserr_seq_misordered cpu_to_be32(NFS4ERR_SEQ_MISORDERED) +#define nfserr_sequence_pos cpu_to_be32(NFS4ERR_SEQUENCE_POS) +#define nfserr_req_too_big cpu_to_be32(NFS4ERR_REQ_TOO_BIG) +#define nfserr_rep_too_big cpu_to_be32(NFS4ERR_REP_TOO_BIG) +#define nfserr_rep_too_big_to_cache cpu_to_be32(NFS4ERR_REP_TOO_BIG_TO_CACHE) +#define nfserr_retry_uncached_rep cpu_to_be32(NFS4ERR_RETRY_UNCACHED_REP) +#define nfserr_unsafe_compound cpu_to_be32(NFS4ERR_UNSAFE_COMPOUND) +#define nfserr_too_many_ops cpu_to_be32(NFS4ERR_TOO_MANY_OPS) +#define nfserr_op_not_in_session cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION) +#define nfserr_hash_alg_unsupp cpu_to_be32(NFS4ERR_HASH_ALG_UNSUPP) +#define nfserr_clientid_busy cpu_to_be32(NFS4ERR_CLIENTID_BUSY) +#define nfserr_pnfs_io_hole cpu_to_be32(NFS4ERR_PNFS_IO_HOLE) +#define nfserr_seq_false_retry cpu_to_be32(NFS4ERR_SEQ_FALSE_RETRY) +#define nfserr_bad_high_slot cpu_to_be32(NFS4ERR_BAD_HIGH_SLOT) +#define nfserr_deadsession cpu_to_be32(NFS4ERR_DEADSESSION) +#define nfserr_encr_alg_unsupp cpu_to_be32(NFS4ERR_ENCR_ALG_UNSUPP) +#define nfserr_pnfs_no_layout cpu_to_be32(NFS4ERR_PNFS_NO_LAYOUT) +#define nfserr_not_only_op cpu_to_be32(NFS4ERR_NOT_ONLY_OP) +#define nfserr_wrong_cred cpu_to_be32(NFS4ERR_WRONG_CRED) +#define nfserr_wrong_type cpu_to_be32(NFS4ERR_WRONG_TYPE) +#define nfserr_dirdeleg_unavail cpu_to_be32(NFS4ERR_DIRDELEG_UNAVAIL) +#define nfserr_reject_deleg cpu_to_be32(NFS4ERR_REJECT_DELEG) +#define nfserr_returnconflict cpu_to_be32(NFS4ERR_RETURNCONFLICT) +#define nfserr_deleg_revoked cpu_to_be32(NFS4ERR_DELEG_REVOKED) /* error codes for internal use */ /* if a request fails due to kmalloc failure, it gets dropped. @@ -258,6 +295,10 @@ void nfsd_lockd_shutdown(void); #define nfserr_dropit cpu_to_be32(30000) /* end-of-file indicator in readdir */ #define nfserr_eof cpu_to_be32(30001) +/* replay detected */ +#define nfserr_replay_me cpu_to_be32(11001) +/* nfs41 replay detected */ +#define nfserr_replay_cache cpu_to_be32(11002) /* Check for dir entries '.' and '..' */ #define isdotent(n, l) (l < 3 && n[0] == '.' && (l == 1 || n[1] == '.')) -- cgit v1.2.3 From 7116ed6b9973021ff43edeb10f4cb834db94000f Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:27:43 +0300 Subject: nfsd41: sessions basic data types This patch provides basic data structures representing the nfs41 sessions and slots, plus helpers for keeping a reference count on the session and freeing it. Note that our server only support a headerpadsz of 0 and it ignores backchannel attributes at the moment. Signed-off-by: Benny Halevy [nfsd41: remove headerpadsz from channel attributes] [nfsd41: embed nfsd4_channel in nfsd4_session] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [nfsd41: use bool inuse for slot state] Signed-off-by: Benny Halevy [nfsd41 remove sl_session from nfsd4_slot] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 18 ++++++++++++++++++ include/linux/nfsd/state.h | 33 +++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+) (limited to 'include') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 070e9e5c0452..8c70f12159b6 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -382,6 +382,24 @@ static void release_openowner(struct nfs4_stateowner *sop) nfs4_put_stateowner(sop); } +static void +release_session(struct nfsd4_session *ses) +{ + list_del(&ses->se_hash); + list_del(&ses->se_perclnt); + nfsd4_put_session(ses); +} + +void +free_session(struct kref *kref) +{ + struct nfsd4_session *ses; + + ses = container_of(kref, struct nfsd4_session, se_ref); + kfree(ses->se_slots); + kfree(ses); +} + static inline void renew_client(struct nfs4_client *clp) { diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index a6e4a00fa392..baea7f1fdb4a 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -99,6 +99,39 @@ struct nfs4_callback { struct rpc_clnt * cb_client; }; +struct nfsd4_slot { + bool sl_inuse; + u32 sl_seqid; +}; + +struct nfsd4_session { + struct kref se_ref; + struct list_head se_hash; /* hash by sessionid */ + struct list_head se_perclnt; + u32 se_flags; + struct nfs4_client *se_client; /* for expire_client */ + struct nfs4_sessionid se_sessionid; + u32 se_fmaxreq_sz; + u32 se_fmaxresp_sz; + u32 se_fmaxresp_cached; + u32 se_fmaxops; + u32 se_fnumslots; + struct nfsd4_slot *se_slots; /* forward channel slots */ +}; + +static inline void +nfsd4_put_session(struct nfsd4_session *ses) +{ + extern void free_session(struct kref *kref); + kref_put(&ses->se_ref, free_session); +} + +static inline void +nfsd4_get_session(struct nfsd4_session *ses) +{ + kref_get(&ses->se_ref); +} + #define HEXDIR_LEN 33 /* hex version of 16 byte md5 of cl_name plus '\0' */ /* -- cgit v1.2.3 From 9fb870702d02c05f9410423bfff3f63e46e26180 Mon Sep 17 00:00:00 2001 From: Marc Eshel Date: Fri, 3 Apr 2009 08:27:46 +0300 Subject: nfsd41: introduce nfs4_client cl_sessions list [get rid of CONFIG_NFSD_V4_1] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 1 + include/linux/nfsd/state.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 8c70f12159b6..b2611999600a 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -528,6 +528,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir) INIT_LIST_HEAD(&clp->cl_strhash); INIT_LIST_HEAD(&clp->cl_openowners); INIT_LIST_HEAD(&clp->cl_delegations); + INIT_LIST_HEAD(&clp->cl_sessions); INIT_LIST_HEAD(&clp->cl_lru); return clp; } diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index baea7f1fdb4a..7faefc7c9d9a 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -163,6 +163,9 @@ struct nfs4_client { struct nfs4_callback cl_callback; /* callback info */ atomic_t cl_count; /* ref count */ u32 cl_firststate; /* recovery dir creation */ + + /* for nfs41 */ + struct list_head cl_sessions; }; /* struct nfs4_client_reset -- cgit v1.2.3 From 5282fd724b667b7d65f2e41e405a825e58a78813 Mon Sep 17 00:00:00 2001 From: Marc Eshel Date: Fri, 3 Apr 2009 08:27:52 +0300 Subject: nfsd41: sessionid hashing Simple sessionid hashing using its monotonically increasing sequence number. Locking considerations: sessionid_hashtbl access is controlled by the sessionid_lock spin lock. It must be taken for insert, delete, and lookup. nfsd4_sequence looks up the session id and if the session is found, it calls nfsd4_get_session (still under the sessionid_lock). nfsd4_destroy_session calls nfsd4_put_session after unhashing it, so when the session's kref reaches zero it's going to get freed. Signed-off-by: Benny Halevy [we don't use a prime for sessionid hash table size] [use sessionid_lock spin lock] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 55 +++++++++++++++++++++++++++++++++++++++++++++- include/linux/nfsd/state.h | 7 ++++++ 2 files changed, 61 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index f23385b13065..fc20e1f38d75 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -382,11 +382,62 @@ static void release_openowner(struct nfs4_stateowner *sop) nfs4_put_stateowner(sop); } +static DEFINE_SPINLOCK(sessionid_lock); +#define SESSION_HASH_SIZE 512 +static struct list_head sessionid_hashtbl[SESSION_HASH_SIZE]; + +static inline int +hash_sessionid(struct nfs4_sessionid *sessionid) +{ + struct nfsd4_sessionid *sid = (struct nfsd4_sessionid *)sessionid; + + return sid->sequence % SESSION_HASH_SIZE; +} + +static inline void +dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid) +{ + u32 *ptr = (u32 *)(&sessionid->data[0]); + dprintk("%s: %u:%u:%u:%u\n", fn, ptr[0], ptr[1], ptr[2], ptr[3]); +} + +/* caller must hold sessionid_lock */ +static struct nfsd4_session * +find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid) +{ + struct nfsd4_session *elem; + int idx; + + dump_sessionid(__func__, sessionid); + idx = hash_sessionid(sessionid); + dprintk("%s: idx is %d\n", __func__, idx); + /* Search in the appropriate list */ + list_for_each_entry(elem, &sessionid_hashtbl[idx], se_hash) { + dump_sessionid("list traversal", &elem->se_sessionid); + if (!memcmp(elem->se_sessionid.data, sessionid->data, + NFS4_MAX_SESSIONID_LEN)) { + return elem; + } + } + + dprintk("%s: session not found\n", __func__); + return NULL; +} + +/* caller must hold sessionid_lock */ static void -release_session(struct nfsd4_session *ses) +unhash_session(struct nfsd4_session *ses) { list_del(&ses->se_hash); list_del(&ses->se_perclnt); +} + +static void +release_session(struct nfsd4_session *ses) +{ + spin_lock(&sessionid_lock); + unhash_session(ses); + spin_unlock(&sessionid_lock); nfsd4_put_session(ses); } @@ -3205,6 +3256,8 @@ nfs4_state_init(void) INIT_LIST_HEAD(&unconf_str_hashtbl[i]); INIT_LIST_HEAD(&unconf_id_hashtbl[i]); } + for (i = 0; i < SESSION_HASH_SIZE; i++) + INIT_LIST_HEAD(&sessionid_hashtbl[i]); for (i = 0; i < FILE_HASH_SIZE; i++) { INIT_LIST_HEAD(&file_hashtbl[i]); } diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 7faefc7c9d9a..5b3a6660f3af 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -132,6 +132,13 @@ nfsd4_get_session(struct nfsd4_session *ses) kref_get(&ses->se_ref); } +/* formatted contents of nfs4_sessionid */ +struct nfsd4_sessionid { + clientid_t clientid; + u32 sequence; + u32 reserved; +}; + #define HEXDIR_LEN 33 /* hex version of 16 byte md5 of cl_name plus '\0' */ /* -- cgit v1.2.3 From 2db134eb3b39faefc7fbfb200156d175edba2f68 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:27:55 +0300 Subject: nfsd41: xdr infrastructure Define nfsd41_dec_ops vector and add it to nfsd4_minorversion for minorversion 1. Note: nfsd4_enc_ops vector is shared for v4.0 and v4.1 since we don't need to filter out obsolete ops as this is done in the decoding phase. exchange_id, create_session, destroy_session, and sequence ops are implemented as stubs returning nfserr_opnotsupp at this stage. [was nfsd41: xdr stubs] [get rid of CONFIG_NFSD_V4_1] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4xdr.c | 148 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/nfsd/xdr4.h | 22 +++++++ 2 files changed, 170 insertions(+) (limited to 'include') diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 76a0b2a8d69b..6973d61bedea 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -996,6 +996,34 @@ nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_rel DECODE_TAIL; } +static __be32 +nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp, + struct nfsd4_exchange_id *clid) +{ + return nfserr_opnotsupp; /* stub */ +} + +static __be32 +nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, + struct nfsd4_create_session *sess) +{ + return nfserr_opnotsupp; /* stub */ +} + +static __be32 +nfsd4_decode_destroy_session(struct nfsd4_compoundargs *argp, + struct nfsd4_destroy_session *destroy_session) +{ + return nfserr_opnotsupp; /* stub */ +} + +static __be32 +nfsd4_decode_sequence(struct nfsd4_compoundargs *argp, + struct nfsd4_sequence *seq) +{ + return nfserr_opnotsupp; /* stub */ +} + static __be32 nfsd4_decode_noop(struct nfsd4_compoundargs *argp, void *p) { @@ -1050,6 +1078,67 @@ static nfsd4_dec nfsd4_dec_ops[] = { [OP_RELEASE_LOCKOWNER] = (nfsd4_dec)nfsd4_decode_release_lockowner, }; +static nfsd4_dec nfsd41_dec_ops[] = { + [OP_ACCESS] (nfsd4_dec)nfsd4_decode_access, + [OP_CLOSE] (nfsd4_dec)nfsd4_decode_close, + [OP_COMMIT] (nfsd4_dec)nfsd4_decode_commit, + [OP_CREATE] (nfsd4_dec)nfsd4_decode_create, + [OP_DELEGPURGE] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_DELEGRETURN] (nfsd4_dec)nfsd4_decode_delegreturn, + [OP_GETATTR] (nfsd4_dec)nfsd4_decode_getattr, + [OP_GETFH] (nfsd4_dec)nfsd4_decode_noop, + [OP_LINK] (nfsd4_dec)nfsd4_decode_link, + [OP_LOCK] (nfsd4_dec)nfsd4_decode_lock, + [OP_LOCKT] (nfsd4_dec)nfsd4_decode_lockt, + [OP_LOCKU] (nfsd4_dec)nfsd4_decode_locku, + [OP_LOOKUP] (nfsd4_dec)nfsd4_decode_lookup, + [OP_LOOKUPP] (nfsd4_dec)nfsd4_decode_noop, + [OP_NVERIFY] (nfsd4_dec)nfsd4_decode_verify, + [OP_OPEN] (nfsd4_dec)nfsd4_decode_open, + [OP_OPENATTR] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_OPEN_CONFIRM] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_OPEN_DOWNGRADE] (nfsd4_dec)nfsd4_decode_open_downgrade, + [OP_PUTFH] (nfsd4_dec)nfsd4_decode_putfh, + [OP_PUTPUBFH] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_PUTROOTFH] (nfsd4_dec)nfsd4_decode_noop, + [OP_READ] (nfsd4_dec)nfsd4_decode_read, + [OP_READDIR] (nfsd4_dec)nfsd4_decode_readdir, + [OP_READLINK] (nfsd4_dec)nfsd4_decode_noop, + [OP_REMOVE] (nfsd4_dec)nfsd4_decode_remove, + [OP_RENAME] (nfsd4_dec)nfsd4_decode_rename, + [OP_RENEW] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_RESTOREFH] (nfsd4_dec)nfsd4_decode_noop, + [OP_SAVEFH] (nfsd4_dec)nfsd4_decode_noop, + [OP_SECINFO] (nfsd4_dec)nfsd4_decode_secinfo, + [OP_SETATTR] (nfsd4_dec)nfsd4_decode_setattr, + [OP_SETCLIENTID] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_SETCLIENTID_CONFIRM](nfsd4_dec)nfsd4_decode_notsupp, + [OP_VERIFY] (nfsd4_dec)nfsd4_decode_verify, + [OP_WRITE] (nfsd4_dec)nfsd4_decode_write, + [OP_RELEASE_LOCKOWNER] (nfsd4_dec)nfsd4_decode_notsupp, + + /* new operations for NFSv4.1 */ + [OP_BACKCHANNEL_CTL] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_BIND_CONN_TO_SESSION](nfsd4_dec)nfsd4_decode_notsupp, + [OP_EXCHANGE_ID] (nfsd4_dec)nfsd4_decode_exchange_id, + [OP_CREATE_SESSION] (nfsd4_dec)nfsd4_decode_create_session, + [OP_DESTROY_SESSION] (nfsd4_dec)nfsd4_decode_destroy_session, + [OP_FREE_STATEID] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_GET_DIR_DELEGATION] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_GETDEVICEINFO] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_GETDEVICELIST] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_LAYOUTCOMMIT] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_LAYOUTGET] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_LAYOUTRETURN] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_SECINFO_NO_NAME] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_SEQUENCE] (nfsd4_dec)nfsd4_decode_sequence, + [OP_SET_SSV] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_TEST_STATEID] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_WANT_DELEGATION] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_DESTROY_CLIENTID] (nfsd4_dec)nfsd4_decode_notsupp, + [OP_RECLAIM_COMPLETE] (nfsd4_dec)nfsd4_decode_notsupp, +}; + struct nfsd4_minorversion_ops { nfsd4_dec *decoders; int nops; @@ -1057,6 +1146,7 @@ struct nfsd4_minorversion_ops { static struct nfsd4_minorversion_ops nfsd4_minorversion[] = { [0] = { nfsd4_dec_ops, ARRAY_SIZE(nfsd4_dec_ops) }, + [1] = { nfsd41_dec_ops, ARRAY_SIZE(nfsd41_dec_ops) }, }; static __be32 @@ -2571,6 +2661,38 @@ nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_w return nfserr; } +static __be32 +nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, int nfserr, + struct nfsd4_exchange_id *exid) +{ + /* stub */ + return nfserr; +} + +static __be32 +nfsd4_encode_create_session(struct nfsd4_compoundres *resp, int nfserr, + struct nfsd4_create_session *sess) +{ + /* stub */ + return nfserr; +} + +static __be32 +nfsd4_encode_destroy_session(struct nfsd4_compoundres *resp, int nfserr, + struct nfsd4_destroy_session *destroy_session) +{ + /* stub */ + return nfserr; +} + +static __be32 +nfsd4_encode_sequence(struct nfsd4_compoundres *resp, int nfserr, + struct nfsd4_sequence *seq) +{ + /* stub */ + return nfserr; +} + static __be32 nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, void *p) { @@ -2579,6 +2701,11 @@ nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, void *p) typedef __be32(* nfsd4_enc)(struct nfsd4_compoundres *, __be32, void *); +/* + * Note: nfsd4_enc_ops vector is shared for v4.0 and v4.1 + * since we don't need to filter out obsolete ops as this is + * done in the decoding phase. + */ static nfsd4_enc nfsd4_enc_ops[] = { [OP_ACCESS] = (nfsd4_enc)nfsd4_encode_access, [OP_CLOSE] = (nfsd4_enc)nfsd4_encode_close, @@ -2617,6 +2744,27 @@ static nfsd4_enc nfsd4_enc_ops[] = { [OP_VERIFY] = (nfsd4_enc)nfsd4_encode_noop, [OP_WRITE] = (nfsd4_enc)nfsd4_encode_write, [OP_RELEASE_LOCKOWNER] = (nfsd4_enc)nfsd4_encode_noop, + + /* NFSv4.1 operations */ + [OP_BACKCHANNEL_CTL] = (nfsd4_enc)nfsd4_encode_noop, + [OP_BIND_CONN_TO_SESSION] = (nfsd4_enc)nfsd4_encode_noop, + [OP_EXCHANGE_ID] = (nfsd4_enc)nfsd4_encode_exchange_id, + [OP_CREATE_SESSION] = (nfsd4_enc)nfsd4_encode_create_session, + [OP_DESTROY_SESSION] = (nfsd4_enc)nfsd4_encode_destroy_session, + [OP_FREE_STATEID] = (nfsd4_enc)nfsd4_encode_noop, + [OP_GET_DIR_DELEGATION] = (nfsd4_enc)nfsd4_encode_noop, + [OP_GETDEVICEINFO] = (nfsd4_enc)nfsd4_encode_noop, + [OP_GETDEVICELIST] = (nfsd4_enc)nfsd4_encode_noop, + [OP_LAYOUTCOMMIT] = (nfsd4_enc)nfsd4_encode_noop, + [OP_LAYOUTGET] = (nfsd4_enc)nfsd4_encode_noop, + [OP_LAYOUTRETURN] = (nfsd4_enc)nfsd4_encode_noop, + [OP_SECINFO_NO_NAME] = (nfsd4_enc)nfsd4_encode_noop, + [OP_SEQUENCE] = (nfsd4_enc)nfsd4_encode_sequence, + [OP_SET_SSV] = (nfsd4_enc)nfsd4_encode_noop, + [OP_TEST_STATEID] = (nfsd4_enc)nfsd4_encode_noop, + [OP_WANT_DELEGATION] = (nfsd4_enc)nfsd4_encode_noop, + [OP_DESTROY_CLIENTID] = (nfsd4_enc)nfsd4_encode_noop, + [OP_RECLAIM_COMPLETE] = (nfsd4_enc)nfsd4_encode_noop, }; void diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index fd15ddc3359d..28af925c2a3d 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -344,6 +344,22 @@ struct nfsd4_write { nfs4_verifier wr_verifier; /* response */ }; +struct nfsd4_exchange_id { + int foo; /* stub */ +}; + +struct nfsd4_create_session { + int foo; /* stub */ +}; + +struct nfsd4_sequence { + int foo; /* stub */ +}; + +struct nfsd4_destroy_session { + int foo; /* stub */ +}; + struct nfsd4_op { int opnum; __be32 status; @@ -378,6 +394,12 @@ struct nfsd4_op { struct nfsd4_verify verify; struct nfsd4_write write; struct nfsd4_release_lockowner release_lockowner; + + /* NFSv4.1 */ + struct nfsd4_exchange_id exchange_id; + struct nfsd4_create_session create_session; + struct nfsd4_destroy_session destroy_session; + struct nfsd4_sequence sequence; } u; struct nfs4_replay * replay; }; -- cgit v1.2.3 From 069b6ad4bb20abf175ea7875e82e8002154773af Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:27:58 +0300 Subject: nfsd41: proc stubs Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 22 ++++++++++++++++++++++ fs/nfsd/nfs4state.c | 32 ++++++++++++++++++++++++++++++++ include/linux/nfsd/xdr4.h | 12 ++++++++++++ 3 files changed, 66 insertions(+) (limited to 'include') diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index ded469ff08b3..f7be7fabe62c 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1101,6 +1101,28 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS, .op_name = "OP_RELEASE_LOCKOWNER", }, + + /* NFSv4.1 operations */ + [OP_EXCHANGE_ID] = { + .op_func = (nfsd4op_func)nfsd4_exchange_id, + .op_flags = ALLOWED_WITHOUT_FH, + .op_name = "OP_EXCHANGE_ID", + }, + [OP_CREATE_SESSION] = { + .op_func = (nfsd4op_func)nfsd4_create_session, + .op_flags = ALLOWED_WITHOUT_FH, + .op_name = "OP_CREATE_SESSION", + }, + [OP_DESTROY_SESSION] = { + .op_func = (nfsd4op_func)nfsd4_destroy_session, + .op_flags = ALLOWED_WITHOUT_FH, + .op_name = "OP_DESTROY_SESSION", + }, + [OP_SEQUENCE] = { + .op_func = (nfsd4op_func)nfsd4_sequence, + .op_flags = ALLOWED_WITHOUT_FH, + .op_name = "OP_SEQUENCE", + }, }; static const char *nfsd4_op_name(unsigned opnum) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index fc20e1f38d75..cfc01f415d15 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -832,6 +832,38 @@ out_err: return; } +__be32 +nfsd4_exchange_id(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_exchange_id *exid) +{ + return -1; /* stub */ +} + +__be32 +nfsd4_create_session(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_create_session *cr_ses) +{ + return -1; /* stub */ +} + +__be32 +nfsd4_destroy_session(struct svc_rqst *r, + struct nfsd4_compound_state *cstate, + struct nfsd4_destroy_session *sessionid) +{ + return -1; /* stub */ +} + +__be32 +nfsd4_sequence(struct svc_rqst *r, + struct nfsd4_compound_state *cstate, + struct nfsd4_sequence *seq) +{ + return -1; /* stub */ +} + __be32 nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_setclientid *setclid) diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 28af925c2a3d..294940c58094 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -471,6 +471,18 @@ extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp, extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *, struct nfsd4_setclientid_confirm *setclientid_confirm); +extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp, + struct nfsd4_compound_state *, +struct nfsd4_exchange_id *); + extern __be32 nfsd4_create_session(struct svc_rqst *, + struct nfsd4_compound_state *, + struct nfsd4_create_session *); +extern __be32 nfsd4_sequence(struct svc_rqst *, + struct nfsd4_compound_state *, + struct nfsd4_sequence *); +extern __be32 nfsd4_destroy_session(struct svc_rqst *, + struct nfsd4_compound_state *, + struct nfsd4_destroy_session *); extern __be32 nfsd4_process_open1(struct nfsd4_open *open); extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open); -- cgit v1.2.3 From 0733d21338747483985a5964e852af160d88e429 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:01 +0300 Subject: nfsd41: exchange_id operation Implement the exchange_id operation confoming to http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-28 Based on the client provided name, hash a client id. If a confirmed one is found, compare the op's creds and verifier. If the creds match and the verifier is different then expire the old client (client re-incarnated), otherwise, if both match, assume it's a replay and ignore it. If an unconfirmed client is found, then copy the new creds and verifer if need update, otherwise assume replay. The client is moved to a confirmed state on create_session. In the nfs41 branch set the exchange_id flags to EXCHGID4_FLAG_USE_NON_PNFS | EXCHGID4_FLAG_SUPP_MOVED_REFER (pNFS is not supported, Referrals are supported, Migration is not.). Address various scenarios from section 18.35 of the spec: 1. Check for EXCHGID4_FLAG_UPD_CONFIRMED_REC_A and set EXCHGID4_FLAG_CONFIRMED_R as appropriate. 2. Return error codes per 18.35.4 scenarios. 3. Update client records or generate new client ids depending on scenario. Note: 18.35.4 case 3 probably still needs revisiting. The handling seems not quite right. Signed-off-by: Benny Halevy Signed-off-by: Andy Adamosn Signed-off-by: Benny Halevy [nfsd41: use utsname for major_id (and copy to server_scope)] [nfsd41: fix handling of various exchange id scenarios] Signed-off-by: Mike Sager Signed-off-by: Benny Halevy [nfsd41: reverse use of EXCHGID4_INVAL_FLAG_MASK_A] [simplify nfsd4_encode_exchange_id error handling] [nfsd41: embed an xdr_netobj in nfsd4_exchange_id] [nfsd41: return nfserr_serverfault for spa_how == SP4_MACH_CRED] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 142 ++++++++++++++++++++++++++++++++++++++++++- fs/nfsd/nfs4xdr.c | 147 +++++++++++++++++++++++++++++++++++++++++++-- include/linux/nfsd/state.h | 2 + include/linux/nfsd/xdr4.h | 7 ++- 4 files changed, 292 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index cfc01f415d15..4f963e902972 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -832,12 +832,152 @@ out_err: return; } +/* + * Set the exchange_id flags returned by the server. + */ +static void +nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid) +{ + /* pNFS is not supported */ + new->cl_exchange_flags |= EXCHGID4_FLAG_USE_NON_PNFS; + + /* Referrals are supported, Migration is not. */ + new->cl_exchange_flags |= EXCHGID4_FLAG_SUPP_MOVED_REFER; + + /* set the wire flags to return to client. */ + clid->flags = new->cl_exchange_flags; +} + __be32 nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_exchange_id *exid) { - return -1; /* stub */ + struct nfs4_client *unconf, *conf, *new; + int status; + unsigned int strhashval; + char dname[HEXDIR_LEN]; + nfs4_verifier verf = exid->verifier; + u32 ip_addr = svc_addr_in(rqstp)->sin_addr.s_addr; + + dprintk("%s rqstp=%p exid=%p clname.len=%u clname.data=%p " + " ip_addr=%u flags %x, spa_how %d\n", + __func__, rqstp, exid, exid->clname.len, exid->clname.data, + ip_addr, exid->flags, exid->spa_how); + + if (!check_name(exid->clname) || (exid->flags & ~EXCHGID4_FLAG_MASK_A)) + return nfserr_inval; + + /* Currently only support SP4_NONE */ + switch (exid->spa_how) { + case SP4_NONE: + break; + case SP4_SSV: + return nfserr_encr_alg_unsupp; + default: + BUG(); /* checked by xdr code */ + case SP4_MACH_CRED: + return nfserr_serverfault; /* no excuse :-/ */ + } + + status = nfs4_make_rec_clidname(dname, &exid->clname); + + if (status) + goto error; + + strhashval = clientstr_hashval(dname); + + nfs4_lock_state(); + status = nfs_ok; + + conf = find_confirmed_client_by_str(dname, strhashval); + if (conf) { + if (!same_verf(&verf, &conf->cl_verifier)) { + /* 18.35.4 case 8 */ + if (exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A) { + status = nfserr_not_same; + goto out; + } + /* Client reboot: destroy old state */ + expire_client(conf); + goto out_new; + } + if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) { + /* 18.35.4 case 9 */ + if (exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A) { + status = nfserr_perm; + goto out; + } + expire_client(conf); + goto out_new; + } + if (ip_addr != conf->cl_addr && + !(exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A)) { + /* Client collision. 18.35.4 case 3 */ + status = nfserr_clid_inuse; + goto out; + } + /* + * Set bit when the owner id and verifier map to an already + * confirmed client id (18.35.3). + */ + exid->flags |= EXCHGID4_FLAG_CONFIRMED_R; + + /* + * Falling into 18.35.4 case 2, possible router replay. + * Leave confirmed record intact and return same result. + */ + copy_verf(conf, &verf); + new = conf; + goto out_copy; + } else { + /* 18.35.4 case 7 */ + if (exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A) { + status = nfserr_noent; + goto out; + } + } + + unconf = find_unconfirmed_client_by_str(dname, strhashval); + if (unconf) { + /* + * Possible retry or client restart. Per 18.35.4 case 4, + * a new unconfirmed record should be generated regardless + * of whether any properties have changed. + */ + expire_client(unconf); + } + +out_new: + /* Normal case */ + new = create_client(exid->clname, dname); + if (new == NULL) { + status = nfserr_resource; + goto out; + } + + copy_verf(new, &verf); + copy_cred(&new->cl_cred, &rqstp->rq_cred); + new->cl_addr = ip_addr; + gen_clid(new); + gen_confirm(new); + add_to_unconfirmed(new, strhashval); +out_copy: + exid->clientid.cl_boot = new->cl_clientid.cl_boot; + exid->clientid.cl_id = new->cl_clientid.cl_id; + + new->cl_seqid = exid->seqid = 1; + nfsd4_set_ex_flags(new, exid); + + dprintk("nfsd4_exchange_id seqid %d flags %x\n", + new->cl_seqid, new->cl_exchange_flags); + status = nfs_ok; + +out: + nfs4_unlock_state(); +error: + dprintk("nfsd4_exchange_id returns %d\n", ntohl(status)); + return status; } __be32 diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 6973d61bedea..bebf6d249069 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include #include @@ -998,9 +999,100 @@ nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_rel static __be32 nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp, - struct nfsd4_exchange_id *clid) + struct nfsd4_exchange_id *exid) { - return nfserr_opnotsupp; /* stub */ + int dummy; + DECODE_HEAD; + + READ_BUF(NFS4_VERIFIER_SIZE); + COPYMEM(exid->verifier.data, NFS4_VERIFIER_SIZE); + + READ_BUF(4); + READ32(exid->clname.len); + + READ_BUF(exid->clname.len); + SAVEMEM(exid->clname.data, exid->clname.len); + + READ_BUF(4); + READ32(exid->flags); + + /* Ignore state_protect4_a */ + READ_BUF(4); + READ32(exid->spa_how); + switch (exid->spa_how) { + case SP4_NONE: + break; + case SP4_MACH_CRED: + /* spo_must_enforce */ + READ_BUF(4); + READ32(dummy); + READ_BUF(dummy * 4); + p += dummy; + + /* spo_must_allow */ + READ_BUF(4); + READ32(dummy); + READ_BUF(dummy * 4); + p += dummy; + break; + case SP4_SSV: + /* ssp_ops */ + READ_BUF(4); + READ32(dummy); + READ_BUF(dummy * 4); + p += dummy; + + READ_BUF(4); + READ32(dummy); + READ_BUF(dummy * 4); + p += dummy; + + /* ssp_hash_algs<> */ + READ_BUF(4); + READ32(dummy); + READ_BUF(dummy); + p += XDR_QUADLEN(dummy); + + /* ssp_encr_algs<> */ + READ_BUF(4); + READ32(dummy); + READ_BUF(dummy); + p += XDR_QUADLEN(dummy); + + /* ssp_window and ssp_num_gss_handles */ + READ_BUF(8); + READ32(dummy); + READ32(dummy); + break; + default: + goto xdr_error; + } + + /* Ignore Implementation ID */ + READ_BUF(4); /* nfs_impl_id4 array length */ + READ32(dummy); + + if (dummy > 1) + goto xdr_error; + + if (dummy == 1) { + /* nii_domain */ + READ_BUF(4); + READ32(dummy); + READ_BUF(dummy); + p += XDR_QUADLEN(dummy); + + /* nii_name */ + READ_BUF(4); + READ32(dummy); + READ_BUF(dummy); + p += XDR_QUADLEN(dummy); + + /* nii_date */ + READ_BUF(12); + p += 3; + } + DECODE_TAIL; } static __be32 @@ -2665,8 +2757,55 @@ static __be32 nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, int nfserr, struct nfsd4_exchange_id *exid) { - /* stub */ - return nfserr; + ENCODE_HEAD; + char *major_id; + char *server_scope; + int major_id_sz; + int server_scope_sz; + uint64_t minor_id = 0; + + if (nfserr) + return nfserr; + + major_id = utsname()->nodename; + major_id_sz = strlen(major_id); + server_scope = utsname()->nodename; + server_scope_sz = strlen(server_scope); + + RESERVE_SPACE( + 8 /* eir_clientid */ + + 4 /* eir_sequenceid */ + + 4 /* eir_flags */ + + 4 /* spr_how (SP4_NONE) */ + + 8 /* so_minor_id */ + + 4 /* so_major_id.len */ + + (XDR_QUADLEN(major_id_sz) * 4) + + 4 /* eir_server_scope.len */ + + (XDR_QUADLEN(server_scope_sz) * 4) + + 4 /* eir_server_impl_id.count (0) */); + + WRITEMEM(&exid->clientid, 8); + WRITE32(exid->seqid); + WRITE32(exid->flags); + + /* state_protect4_r. Currently only support SP4_NONE */ + BUG_ON(exid->spa_how != SP4_NONE); + WRITE32(exid->spa_how); + + /* The server_owner struct */ + WRITE64(minor_id); /* Minor id */ + /* major id */ + WRITE32(major_id_sz); + WRITEMEM(major_id, major_id_sz); + + /* Server scope */ + WRITE32(server_scope_sz); + WRITEMEM(server_scope, server_scope_sz); + + /* Implementation id */ + WRITE32(0); /* zero length nfs_impl_id4 array */ + ADJUST_ARGS(); + return 0; } static __be32 diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 5b3a6660f3af..8d0b10167937 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -173,6 +173,8 @@ struct nfs4_client { /* for nfs41 */ struct list_head cl_sessions; + u32 cl_seqid; /* seqid for create_session */ + u32 cl_exchange_flags; }; /* struct nfs4_client_reset diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 294940c58094..33ee71e988b4 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -345,7 +345,12 @@ struct nfsd4_write { }; struct nfsd4_exchange_id { - int foo; /* stub */ + nfs4_verifier verifier; + struct xdr_netobj clname; + u32 flags; + clientid_t clientid; + u32 seqid; + int spa_how; }; struct nfsd4_create_session { -- cgit v1.2.3 From a1bcecd29cdf1670df6908a620add4211c0abb7a Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:05 +0300 Subject: nfsd41: match clientid establishment method We need to distinguish between client names provided by NFSv4.0 clients SETCLIENTID and those provided by NFSv4.1 via EXCHANGE_ID when looking up the clientid by string. Signed-off-by: Benny Halevy Signed-off-by: Andy Adamson [nfsd41: use boolean values for use_exchange_id argument] Signed-off-by: Benny Halevy [nfsd41: simplify match_clientid_establishment logic] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4recover.c | 3 ++- fs/nfsd/nfs4state.c | 42 +++++++++++++++++++++++++++++++----------- include/linux/nfsd/state.h | 2 +- 3 files changed, 34 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index b11cf8d34280..3444c0052a87 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -344,7 +344,8 @@ purge_old(struct dentry *parent, struct dentry *child) { int status; - if (nfs4_has_reclaimed_state(child->d_name.name)) + /* note: we currently use this path only for minorversion 0 */ + if (nfs4_has_reclaimed_state(child->d_name.name, false)) return 0; status = nfsd4_clear_clid_dir(parent, child); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 4f963e902972..dfc6d946cdfe 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -715,25 +715,45 @@ find_unconfirmed_client(clientid_t *clid) return NULL; } +/* + * Return 1 iff clp's clientid establishment method matches the use_exchange_id + * parameter. Matching is based on the fact the at least one of the + * EXCHGID4_FLAG_USE_{NON_PNFS,PNFS_MDS,PNFS_DS} flags must be set for v4.1 + * + * FIXME: we need to unify the clientid namespaces for nfsv4.x + * and correctly deal with client upgrade/downgrade in EXCHANGE_ID + * and SET_CLIENTID{,_CONFIRM} + */ +static inline int +match_clientid_establishment(struct nfs4_client *clp, bool use_exchange_id) +{ + bool has_exchange_flags = (clp->cl_exchange_flags != 0); + return use_exchange_id == has_exchange_flags; +} + static struct nfs4_client * -find_confirmed_client_by_str(const char *dname, unsigned int hashval) +find_confirmed_client_by_str(const char *dname, unsigned int hashval, + bool use_exchange_id) { struct nfs4_client *clp; list_for_each_entry(clp, &conf_str_hashtbl[hashval], cl_strhash) { - if (same_name(clp->cl_recdir, dname)) + if (same_name(clp->cl_recdir, dname) && + match_clientid_establishment(clp, use_exchange_id)) return clp; } return NULL; } static struct nfs4_client * -find_unconfirmed_client_by_str(const char *dname, unsigned int hashval) +find_unconfirmed_client_by_str(const char *dname, unsigned int hashval, + bool use_exchange_id) { struct nfs4_client *clp; list_for_each_entry(clp, &unconf_str_hashtbl[hashval], cl_strhash) { - if (same_name(clp->cl_recdir, dname)) + if (same_name(clp->cl_recdir, dname) && + match_clientid_establishment(clp, use_exchange_id)) return clp; } return NULL; @@ -890,7 +910,7 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, nfs4_lock_state(); status = nfs_ok; - conf = find_confirmed_client_by_str(dname, strhashval); + conf = find_confirmed_client_by_str(dname, strhashval, true); if (conf) { if (!same_verf(&verf, &conf->cl_verifier)) { /* 18.35.4 case 8 */ @@ -938,7 +958,7 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, } } - unconf = find_unconfirmed_client_by_str(dname, strhashval); + unconf = find_unconfirmed_client_by_str(dname, strhashval, true); if (unconf) { /* * Possible retry or client restart. Per 18.35.4 case 4, @@ -1035,7 +1055,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, strhashval = clientstr_hashval(dname); nfs4_lock_state(); - conf = find_confirmed_client_by_str(dname, strhashval); + conf = find_confirmed_client_by_str(dname, strhashval, false); if (conf) { /* RFC 3530 14.2.33 CASE 0: */ status = nfserr_clid_inuse; @@ -1050,7 +1070,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, * has a description of SETCLIENTID request processing consisting * of 5 bullet points, labeled as CASE0 - CASE4 below. */ - unconf = find_unconfirmed_client_by_str(dname, strhashval); + unconf = find_unconfirmed_client_by_str(dname, strhashval, false); status = nfserr_resource; if (!conf) { /* @@ -1205,7 +1225,7 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, unsigned int hash = clientstr_hashval(unconf->cl_recdir); conf = find_confirmed_client_by_str(unconf->cl_recdir, - hash); + hash, false); if (conf) { nfsd4_remove_clid_dir(conf); expire_client(conf); @@ -3326,12 +3346,12 @@ alloc_reclaim(void) } int -nfs4_has_reclaimed_state(const char *name) +nfs4_has_reclaimed_state(const char *name, bool use_exchange_id) { unsigned int strhashval = clientstr_hashval(name); struct nfs4_client *clp; - clp = find_confirmed_client_by_str(name, strhashval); + clp = find_confirmed_client_by_str(name, strhashval, use_exchange_id); return clp ? 1 : 0; } diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 8d0b10167937..90829db76861 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -330,7 +330,7 @@ extern void nfsd4_init_recdir(char *recdir_name); extern int nfsd4_recdir_load(void); extern void nfsd4_shutdown_recdir(void); extern int nfs4_client_to_reclaim(const char *name); -extern int nfs4_has_reclaimed_state(const char *name); +extern int nfs4_has_reclaimed_state(const char *name, bool use_exchange_id); extern void nfsd4_recdir_purge_old(void); extern int nfsd4_create_clid_dir(struct nfs4_client *clp); extern void nfsd4_remove_clid_dir(struct nfs4_client *clp); -- cgit v1.2.3 From b85d4c01b76f6969a085d07a767fa45225cb14be Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 3 Apr 2009 08:28:08 +0300 Subject: nfsd41: sequence operation Implement the sequence operation conforming to http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-26 Check for stale clientid (as derived from the sessionid). Enforce slotid range and exactly-once semantics using the slotid and seqid. If everything went well renew the client lease and mark the slot INPROGRESS. Add a struct nfsd4_slot pointer to struct nfsd4_compound_state. To be used for sessions DRC replay. [nfsd41: rename sequence catchthis to cachethis] Signed-off-by: Andy Adamson [pulled some code to set cstate->slot from "nfsd DRC logic"] [use sessionid_lock spin lock] [nfsd41: use bool inuse for slot state] Signed-off-by: Benny Halevy [nfsd: add a struct nfsd4_slot pointer to struct nfsd4_compound_state] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [nfsd41: add nfsd4_session pointer to nfsd4_compound_state] [nfsd41: set cstate session] [nfsd41: use cstate session in nfsd4_sequence] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [simplify nfsd4_encode_sequence error handling] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 73 +++++++++++++++++++++++++++++++++++++++++++++-- fs/nfsd/nfs4xdr.c | 33 +++++++++++++++++++-- include/linux/nfsd/xdr4.h | 13 ++++++++- 3 files changed, 113 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index dfc6d946cdfe..24b6e0593184 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1000,6 +1000,32 @@ error: return status; } +static int +check_slot_seqid(u32 seqid, struct nfsd4_slot *slot) +{ + dprintk("%s enter. seqid %d slot->sl_seqid %d\n", __func__, seqid, + slot->sl_seqid); + + /* The slot is in use, and no response has been sent. */ + if (slot->sl_inuse) { + if (seqid == slot->sl_seqid) + return nfserr_jukebox; + else + return nfserr_seq_misordered; + } + /* Normal */ + if (likely(seqid == slot->sl_seqid + 1)) + return nfs_ok; + /* Replay */ + if (seqid == slot->sl_seqid) + return nfserr_replay_cache; + /* Wraparound */ + if (seqid == 1 && (slot->sl_seqid + 1) == 0) + return nfs_ok; + /* Misordered replay or misordered new request */ + return nfserr_seq_misordered; +} + __be32 nfsd4_create_session(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, @@ -1017,11 +1043,54 @@ nfsd4_destroy_session(struct svc_rqst *r, } __be32 -nfsd4_sequence(struct svc_rqst *r, +nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_sequence *seq) { - return -1; /* stub */ + struct nfsd4_session *session; + struct nfsd4_slot *slot; + int status; + + spin_lock(&sessionid_lock); + status = nfserr_badsession; + session = find_in_sessionid_hashtbl(&seq->sessionid); + if (!session) + goto out; + + status = nfserr_badslot; + if (seq->slotid >= session->se_fnumslots) + goto out; + + slot = &session->se_slots[seq->slotid]; + dprintk("%s: slotid %d\n", __func__, seq->slotid); + + status = check_slot_seqid(seq->seqid, slot); + if (status == nfserr_replay_cache) { + cstate->slot = slot; + cstate->session = session; + goto replay_cache; + } + if (status) + goto out; + + /* Success! bump slot seqid */ + slot->sl_inuse = true; + slot->sl_seqid = seq->seqid; + + cstate->slot = slot; + cstate->session = session; + +replay_cache: + /* Renew the clientid on success and on replay. + * Hold a session reference until done processing the compound: + * nfsd4_put_session called only if the cstate slot is set. + */ + renew_client(session->se_client); + nfsd4_get_session(session); +out: + spin_unlock(&sessionid_lock); + dprintk("%s: return %d\n", __func__, ntohl(status)); + return status; } __be32 diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index bebf6d249069..8556575480ce 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1113,7 +1113,16 @@ static __be32 nfsd4_decode_sequence(struct nfsd4_compoundargs *argp, struct nfsd4_sequence *seq) { - return nfserr_opnotsupp; /* stub */ + DECODE_HEAD; + + READ_BUF(NFS4_MAX_SESSIONID_LEN + 16); + COPYMEM(seq->sessionid.data, NFS4_MAX_SESSIONID_LEN); + READ32(seq->seqid); + READ32(seq->slotid); + READ32(seq->maxslots); + READ32(seq->cachethis); + + DECODE_TAIL; } static __be32 @@ -2828,8 +2837,26 @@ static __be32 nfsd4_encode_sequence(struct nfsd4_compoundres *resp, int nfserr, struct nfsd4_sequence *seq) { - /* stub */ - return nfserr; + ENCODE_HEAD; + + if (nfserr) + return nfserr; + + RESERVE_SPACE(NFS4_MAX_SESSIONID_LEN + 20); + WRITEMEM(seq->sessionid.data, NFS4_MAX_SESSIONID_LEN); + WRITE32(seq->seqid); + WRITE32(seq->slotid); + WRITE32(seq->maxslots); + /* + * FIXME: for now: + * target_maxslots = maxslots + * status_flags = 0 + */ + WRITE32(seq->maxslots); + WRITE32(0); + + ADJUST_ARGS(); + return 0; } static __be32 diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 33ee71e988b4..6e28a041008d 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -48,6 +48,9 @@ struct nfsd4_compound_state { struct svc_fh current_fh; struct svc_fh save_fh; struct nfs4_stateowner *replay_owner; + /* For sessions DRC */ + struct nfsd4_session *session; + struct nfsd4_slot *slot; }; struct nfsd4_change_info { @@ -358,7 +361,15 @@ struct nfsd4_create_session { }; struct nfsd4_sequence { - int foo; /* stub */ + struct nfs4_sessionid sessionid; /* request/response */ + u32 seqid; /* request/response */ + u32 slotid; /* request/response */ + u32 maxslots; /* request/response */ + u32 cachethis; /* request */ +#if 0 + u32 target_maxslots; /* response */ + u32 status_flags; /* response */ +#endif /* not yet */ }; struct nfsd4_destroy_session { -- cgit v1.2.3 From 074fe897536f095309c5aaffcf912952882ab2cb Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:15 +0300 Subject: nfsd41: DRC save, restore, and clear functions Cache all the result pages, including the rpc header in rq_respages[0], for a request in the slot table cache entry. Cache the statp pointer from nfsd_dispatch which points into rq_respages[0] just past the rpc header. When setting a cache entry, calculate and save the length of the nfs data minus the rpc header for rq_respages[0]. When replaying a cache entry, replace the cached rpc header with the replayed request rpc result header, unless there is not enough room in the cached results first page. In that case, use the cached rpc header. The sessions fore channel maxresponse size cached is set to NFSD_PAGES_PER_SLOT * PAGE_SIZE. For compounds we are cacheing with operations such as READDIR that use the xdr_buf->pages to hold data, we choose to cache the extra page of data rather than copying data from xdr_buf->pages into the xdr_buf->head page. [nfsd41: limit cache to maxresponsesize_cached] [nfsd41: mv nfsd4_set_statp under CONFIG_NFSD_V4_1] [nfsd41: rename nfsd4_move_pages] [nfsd41: rename page_no variable] [nfsd41: rename nfsd4_set_cache_entry] [nfsd41: fix nfsd41_copy_replay_data comment] [nfsd41: add to nfsd4_set_cache_entry] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 142 +++++++++++++++++++++++++++++++++++++++++++++ fs/nfsd/nfssvc.c | 4 ++ include/linux/nfsd/cache.h | 1 + include/linux/nfsd/state.h | 13 +++++ include/linux/nfsd/xdr4.h | 4 ++ 5 files changed, 164 insertions(+) (limited to 'include') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 9243dca3576c..a37b91dab1bf 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -852,6 +852,148 @@ out_err: return; } +void +nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp) +{ + struct nfsd4_compoundres *resp = rqstp->rq_resp; + + resp->cstate.statp = statp; +} + +/* + * Dereference the result pages. + */ +static void +nfsd4_release_respages(struct page **respages, short resused) +{ + int i; + + dprintk("--> %s\n", __func__); + for (i = 0; i < resused; i++) { + if (!respages[i]) + continue; + put_page(respages[i]); + respages[i] = NULL; + } +} + +static void +nfsd4_copy_pages(struct page **topages, struct page **frompages, short count) +{ + int i; + + for (i = 0; i < count; i++) { + topages[i] = frompages[i]; + if (!topages[i]) + continue; + get_page(topages[i]); + } +} + +/* + * Cache the reply pages up to NFSD_PAGES_PER_SLOT + 1, clearing the previous + * pages. We add a page to NFSD_PAGES_PER_SLOT for the case where the total + * length of the XDR response is less than se_fmaxresp_cached + * (NFSD_PAGES_PER_SLOT * PAGE_SIZE) but the xdr_buf pages is used for a + * of the reply (e.g. readdir). + * + * Store the base and length of the rq_req.head[0] page + * of the NFSv4.1 data, just past the rpc header. + */ +void +nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) +{ + struct nfsd4_cache_entry *entry = &resp->cstate.slot->sl_cache_entry; + struct svc_rqst *rqstp = resp->rqstp; + struct nfsd4_compoundargs *args = rqstp->rq_argp; + struct nfsd4_op *op = &args->ops[resp->opcnt]; + struct kvec *resv = &rqstp->rq_res.head[0]; + + dprintk("--> %s entry %p\n", __func__, entry); + + /* Don't cache a failed OP_SEQUENCE. */ + if (resp->opcnt == 1 && op->opnum == OP_SEQUENCE && resp->cstate.status) + return; + nfsd4_release_respages(entry->ce_respages, entry->ce_resused); + entry->ce_resused = rqstp->rq_resused; + if (entry->ce_resused > NFSD_PAGES_PER_SLOT + 1) + entry->ce_resused = NFSD_PAGES_PER_SLOT + 1; + nfsd4_copy_pages(entry->ce_respages, rqstp->rq_respages, + entry->ce_resused); + entry->ce_status = resp->cstate.status; + entry->ce_datav.iov_base = resp->cstate.statp; + entry->ce_datav.iov_len = resv->iov_len - ((char *)resp->cstate.statp - + (char *)page_address(rqstp->rq_respages[0])); + entry->ce_opcnt = resp->opcnt; + /* Current request rpc header length*/ + entry->ce_rpchdrlen = (char *)resp->cstate.statp - + (char *)page_address(rqstp->rq_respages[0]); +} + +/* + * We keep the rpc header, but take the nfs reply from the replycache. + */ +static int +nfsd41_copy_replay_data(struct nfsd4_compoundres *resp, + struct nfsd4_cache_entry *entry) +{ + struct svc_rqst *rqstp = resp->rqstp; + struct kvec *resv = &resp->rqstp->rq_res.head[0]; + int len; + + /* Current request rpc header length*/ + len = (char *)resp->cstate.statp - + (char *)page_address(rqstp->rq_respages[0]); + if (entry->ce_datav.iov_len + len > PAGE_SIZE) { + dprintk("%s v41 cached reply too large (%Zd).\n", __func__, + entry->ce_datav.iov_len); + return 0; + } + /* copy the cached reply nfsd data past the current rpc header */ + memcpy((char *)resv->iov_base + len, entry->ce_datav.iov_base, + entry->ce_datav.iov_len); + resv->iov_len = len + entry->ce_datav.iov_len; + return 1; +} + +/* + * Keep the first page of the replay. Copy the NFSv4.1 data from the first + * cached page. Replace any futher replay pages from the cache. + */ +__be32 +nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp) +{ + struct nfsd4_cache_entry *entry = &resp->cstate.slot->sl_cache_entry; + __be32 status; + + dprintk("--> %s entry %p\n", __func__, entry); + + + if (!nfsd41_copy_replay_data(resp, entry)) { + /* + * Not enough room to use the replay rpc header, send the + * cached header. Release all the allocated result pages. + */ + svc_free_res_pages(resp->rqstp); + nfsd4_copy_pages(resp->rqstp->rq_respages, entry->ce_respages, + entry->ce_resused); + } else { + /* Release all but the first allocated result page */ + + resp->rqstp->rq_resused--; + svc_free_res_pages(resp->rqstp); + + nfsd4_copy_pages(&resp->rqstp->rq_respages[1], + &entry->ce_respages[1], + entry->ce_resused - 1); + } + + resp->rqstp->rq_resused = entry->ce_resused; + status = entry->ce_status; + + return status; +} + /* * Set the exchange_id flags returned by the server. */ diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index ef0a3686639d..b5168d1898ec 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -515,6 +515,10 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) + rqstp->rq_res.head[0].iov_len; rqstp->rq_res.head[0].iov_len += sizeof(__be32); + /* NFSv4.1 DRC requires statp */ + if (rqstp->rq_vers == 4) + nfsd4_set_statp(rqstp, statp); + /* Now call the procedure handler, and encode NFS status. */ nfserr = proc->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp); nfserr = map_new_errors(rqstp->rq_vers, nfserr); diff --git a/include/linux/nfsd/cache.h b/include/linux/nfsd/cache.h index 04b355c801d8..a59a2df6d079 100644 --- a/include/linux/nfsd/cache.h +++ b/include/linux/nfsd/cache.h @@ -75,5 +75,6 @@ int nfsd_reply_cache_init(void); void nfsd_reply_cache_shutdown(void); int nfsd_cache_lookup(struct svc_rqst *, int); void nfsd_cache_update(struct svc_rqst *, int, __be32 *); +void nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp); #endif /* NFSCACHE_H */ diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 90829db76861..f1edb1d98523 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -99,9 +99,22 @@ struct nfs4_callback { struct rpc_clnt * cb_client; }; +/* Maximum number of pages per slot cache entry */ +#define NFSD_PAGES_PER_SLOT 1 + +struct nfsd4_cache_entry { + __be32 ce_status; + struct kvec ce_datav; /* encoded NFSv4.1 data in rq_res.head[0] */ + struct page *ce_respages[NFSD_PAGES_PER_SLOT + 1]; + short ce_resused; + int ce_opcnt; + int ce_rpchdrlen; +}; + struct nfsd4_slot { bool sl_inuse; u32 sl_seqid; + struct nfsd4_cache_entry sl_cache_entry; }; struct nfsd4_session { diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 6e28a041008d..d091684325af 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -51,6 +51,8 @@ struct nfsd4_compound_state { /* For sessions DRC */ struct nfsd4_session *session; struct nfsd4_slot *slot; + __be32 *statp; + u32 status; }; struct nfsd4_change_info { @@ -487,6 +489,8 @@ extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp, extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *, struct nfsd4_setclientid_confirm *setclientid_confirm); +extern void nfsd4_store_cache_entry(struct nfsd4_compoundres *resp); +extern __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp); extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *, struct nfsd4_exchange_id *); -- cgit v1.2.3 From c3d06f9ce8544fecfe13e377d1e2c2e47fe18dbc Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:18 +0300 Subject: nfsd41: hard page limit for DRC Use no more than 1/128th of the number of free pages at nfsd startup for the v4.1 DRC. This is an arbitrary default which should probably end up under the control of an administrator. Signed-off-by: Andy Adamson [moved added fields in struct svc_serv under CONFIG_NFSD_V4_1] Signed-off-by: Benny Halevy [fix set_max_drc calculation of sv_drc_max_pages] [moved NFSD_DRC_SIZE_SHIFT's declaration up in header file] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfssvc.c | 23 +++++++++++++++++++++++ include/linux/nfsd/nfsd.h | 3 +++ include/linux/sunrpc/svc.h | 2 ++ 3 files changed, 28 insertions(+) (limited to 'include') diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index b5168d1898ec..b53a098e97a4 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include @@ -197,6 +198,26 @@ void nfsd_reset_versions(void) } } +/* + * Each session guarantees a negotiated per slot memory cache for replies + * which in turn consumes memory beyond the v2/v3/v4.0 server. A dedicated + * NFSv4.1 server might want to use more memory for a DRC than a machine + * with mutiple services. + * + * Impose a hard limit on the number of pages for the DRC which varies + * according to the machines free pages. This is of course only a default. + * + * For now this is a #defined shift which could be under admin control + * in the future. + */ +static void set_max_drc(void) +{ + nfsd_serv->sv_drc_max_pages = nr_free_buffer_pages() + >> NFSD_DRC_SIZE_SHIFT; + nfsd_serv->sv_drc_pages_used = 0; + dprintk("%s svc_drc_max_pages %u\n", __func__, + nfsd_serv->sv_drc_max_pages); +} int nfsd_create_serv(void) { @@ -229,6 +250,8 @@ int nfsd_create_serv(void) nfsd_last_thread, nfsd, THIS_MODULE); if (nfsd_serv == NULL) err = -ENOMEM; + else + set_max_drc(); do_gettimeofday(&nfssvc_boot); /* record boot time */ return err; diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index ab9616d09204..1f063d495159 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -331,6 +331,9 @@ extern struct timeval nfssvc_boot; #define NFSD_LEASE_TIME (nfs4_lease_time()) #define NFSD_LAUNDROMAT_MINTIMEOUT 10 /* seconds */ +/* The percent of nr_free_buffer_pages used by the V4.1 server DRC */ +#define NFSD_DRC_SIZE_SHIFT 7 + /* * The following attributes are currently not supported by the NFSv4 server: * ARCHIVE (deprecated anyway) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 815dd589d4db..d209c630a4a1 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -95,6 +95,8 @@ struct svc_serv { struct module * sv_module; /* optional module to count when * adding threads */ svc_thread_fn sv_function; /* main function for threads */ + unsigned int sv_drc_max_pages; /* Total pages for DRC */ + unsigned int sv_drc_pages_used;/* DRC pages used */ }; /* -- cgit v1.2.3 From da3846a2866ddf239311766ff434a82e7b4ac701 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:22 +0300 Subject: nfsd41: nfsd DRC logic Replay a request in nfsd4_sequence. Add a minorversion to struct nfsd4_compound_state. Pass the current slot to nfs4svc_encode_compound res via struct nfsd4_compoundres to set an NFSv4.1 DRC entry. Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [nfsd41: use bool inuse for slot state] Signed-off-by: Benny Halevy [nfsd41: use cstate session in nfs4svc_encode_compoundres] [nfsd41 replace nfsd4_set_cache_entry] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 7 +++++++ fs/nfsd/nfs4state.c | 6 ++++++ fs/nfsd/nfs4xdr.c | 11 +++++++++++ include/linux/nfsd/xdr4.h | 1 + 4 files changed, 25 insertions(+) (limited to 'include') diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index ec51936d2ce2..9e2ee75e0f7c 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -936,6 +936,12 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, BUG_ON(op->status == nfs_ok); encode_op: + /* Only from SEQUENCE or CREATE_SESSION */ + if (resp->cstate.status == nfserr_replay_cache) { + dprintk("%s NFS4.1 replay from cache\n", __func__); + status = op->status; + goto out; + } if (op->status == nfserr_replay_me) { op->replay = &cstate->replay_owner->so_replay; nfsd4_encode_replay(resp, op); @@ -964,6 +970,7 @@ encode_op: status = nfserr_jukebox; } + resp->cstate.status = status; fh_put(&resp->cstate.current_fh); fh_put(&resp->cstate.save_fh); BUG_ON(resp->cstate.replay_owner); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index a37b91dab1bf..e20d4345040f 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -989,6 +989,8 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp) } resp->rqstp->rq_resused = entry->ce_resused; + resp->opcnt = entry->ce_opcnt; + resp->cstate.iovlen = entry->ce_datav.iov_len + entry->ce_rpchdrlen; status = entry->ce_status; return status; @@ -1214,6 +1216,10 @@ nfsd4_sequence(struct svc_rqst *rqstp, if (status == nfserr_replay_cache) { cstate->slot = slot; cstate->session = session; + /* Return the cached reply status and set cstate->status + * for nfsd4_svc_encode_compoundres processing*/ + status = nfsd4_replay_cache_entry(resp); + cstate->status = nfserr_replay_cache; goto replay_cache; } if (status) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 8556575480ce..09415bcf078e 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3049,6 +3049,17 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo iov = &rqstp->rq_res.head[0]; iov->iov_len = ((char*)resp->p) - (char*)iov->iov_base; BUG_ON(iov->iov_len > PAGE_SIZE); + if (resp->cstate.slot != NULL) { + if (resp->cstate.status == nfserr_replay_cache) { + iov->iov_len = resp->cstate.iovlen; + } else { + nfsd4_store_cache_entry(resp); + dprintk("%s: SET SLOT STATE TO AVAILABLE\n", __func__); + resp->cstate.slot->sl_inuse = 0; + } + if (resp->cstate.session) + nfsd4_put_session(resp->cstate.session); + } return 1; } diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index d091684325af..69cb467cb720 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -52,6 +52,7 @@ struct nfsd4_compound_state { struct nfsd4_session *session; struct nfsd4_slot *slot; __be32 *statp; + size_t iovlen; u32 status; }; -- cgit v1.2.3 From ec6b5d7b5064fde27aee798b81107ea3a830de85 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:28 +0300 Subject: nfsd41: create_session operation Implement the create_session operation confoming to http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-26 Look up the client id (generated by the server on exchange_id, given by the client on create_session). If neither a confirmed or unconfirmed client is found then the client id is stale If a confirmed cilent is found (i.e. we already received create_session for it) then compare the sequence id to determine if it's a replay or possibly a mis-ordered rpc. If the seqid is in order, update the confirmed client seqid and procedd with updating the session parameters. If an unconfirmed client_id is found then verify the creds and seqid. If both match move the client id to confirmed state and proceed with processing the create_session. Currently, we do not support persistent sessions, and RDMA. alloc_init_session generates a new sessionid and creates a session structure. NFSD_PAGES_PER_SLOT is used for the max response cached calculation, and for the counting of DRC pages using the hard limits set in struct srv_serv. A note on NFSD_PAGES_PER_SLOT: Other patches in this series allow for NFSD_PAGES_PER_SLOT + 1 pages to be cached in a DRC slot when the response size is less than NFSD_PAGES_PER_SLOT * PAGE_SIZE but xdr_buf pages are used. e.g. a READDIR operation will encode a small amount of data in the xdr_buf head, and then the READDIR in the xdr_buf pages. So, the hard limit calculation use of pages by a session is underestimated by the number of cached operations using the xdr_buf pages. Yet another patch caches no pages for the solo sequence operation, or any compound where cache_this is False. So the hard limit calculation use of pages by a session is overestimated by the number of these operations in the cache. TODO: improve resource pre-allocation and negotiate session parameters accordingly. Respect and possibly adjust backchannel attributes. Signed-off-by: Marc Eshel Signed-off-by: Dean Hildebrand [nfsd41: remove headerpadsz from channel attributes] Our client and server only support a headerpadsz of 0. [nfsd41: use DRC limits in fore channel init] [nfsd41: do not change CREATE_SESSION back channel attrs] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [use sessionid_lock spin lock] [nfsd41: use bool inuse for slot state] Signed-off-by: Benny Halevy [nfsd41 remove sl_session from alloc_init_session] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [simplify nfsd4_encode_create_session error handling] [nfsd41: fix comment style in init_forechannel_attrs] [nfsd41: allocate struct nfsd4_session and slot table in one piece] [nfsd41: no need to INIT_LIST_HEAD in alloc_init_session just prior to list_add] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 188 ++++++++++++++++++++++++++++++++++++++++++++- fs/nfsd/nfs4xdr.c | 148 ++++++++++++++++++++++++++++++++++- include/linux/nfsd/state.h | 7 +- include/linux/nfsd/xdr4.h | 21 ++++- 4 files changed, 358 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index f25a7d2a9fac..463ae39df148 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -68,6 +68,7 @@ static u32 current_delegid = 1; static u32 nfs4_init; static stateid_t zerostateid; /* bits all 0 */ static stateid_t onestateid; /* bits all 1 */ +static u64 current_sessionid = 1; #define ZERO_STATEID(stateid) (!memcmp((stateid), &zerostateid, sizeof(stateid_t))) #define ONE_STATEID(stateid) (!memcmp((stateid), &onestateid, sizeof(stateid_t))) @@ -401,6 +402,131 @@ dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid) dprintk("%s: %u:%u:%u:%u\n", fn, ptr[0], ptr[1], ptr[2], ptr[3]); } +static void +gen_sessionid(struct nfsd4_session *ses) +{ + struct nfs4_client *clp = ses->se_client; + struct nfsd4_sessionid *sid; + + sid = (struct nfsd4_sessionid *)ses->se_sessionid.data; + sid->clientid = clp->cl_clientid; + sid->sequence = current_sessionid++; + sid->reserved = 0; +} + +/* + * Give the client the number of slots it requests bound by + * NFSD_MAX_SLOTS_PER_SESSION and by sv_drc_max_pages. + * + * If we run out of pages (sv_drc_pages_used == sv_drc_max_pages) we + * should (up to a point) re-negotiate active sessions and reduce their + * slot usage to make rooom for new connections. For now we just fail the + * create session. + */ +static int set_forechannel_maxreqs(struct nfsd4_channel_attrs *fchan) +{ + int status = 0, np = fchan->maxreqs * NFSD_PAGES_PER_SLOT; + + spin_lock(&nfsd_serv->sv_lock); + if (np + nfsd_serv->sv_drc_pages_used > nfsd_serv->sv_drc_max_pages) + np = nfsd_serv->sv_drc_max_pages - nfsd_serv->sv_drc_pages_used; + nfsd_serv->sv_drc_pages_used += np; + spin_unlock(&nfsd_serv->sv_lock); + + if (np <= 0) { + status = nfserr_resource; + fchan->maxreqs = 0; + } else + fchan->maxreqs = np / NFSD_PAGES_PER_SLOT; + + return status; +} + +/* + * fchan holds the client values on input, and the server values on output + */ +static int init_forechannel_attrs(struct svc_rqst *rqstp, + struct nfsd4_session *session, + struct nfsd4_channel_attrs *fchan) +{ + int status = 0; + __u32 maxcount = svc_max_payload(rqstp); + + /* headerpadsz set to zero in encode routine */ + + /* Use the client's max request and max response size if possible */ + if (fchan->maxreq_sz > maxcount) + fchan->maxreq_sz = maxcount; + session->se_fmaxreq_sz = fchan->maxreq_sz; + + if (fchan->maxresp_sz > maxcount) + fchan->maxresp_sz = maxcount; + session->se_fmaxresp_sz = fchan->maxresp_sz; + + /* Set the max response cached size our default which is + * a multiple of PAGE_SIZE and small */ + session->se_fmaxresp_cached = NFSD_PAGES_PER_SLOT * PAGE_SIZE; + fchan->maxresp_cached = session->se_fmaxresp_cached; + + /* Use the client's maxops if possible */ + if (fchan->maxops > NFSD_MAX_OPS_PER_COMPOUND) + fchan->maxops = NFSD_MAX_OPS_PER_COMPOUND; + session->se_fmaxops = fchan->maxops; + + /* try to use the client requested number of slots */ + if (fchan->maxreqs > NFSD_MAX_SLOTS_PER_SESSION) + fchan->maxreqs = NFSD_MAX_SLOTS_PER_SESSION; + + /* FIXME: Error means no more DRC pages so the server should + * recover pages from existing sessions. For now fail session + * creation. + */ + status = set_forechannel_maxreqs(fchan); + + session->se_fnumslots = fchan->maxreqs; + return status; +} + +static int +alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp, + struct nfsd4_create_session *cses) +{ + struct nfsd4_session *new, tmp; + int idx, status = nfserr_resource, slotsize; + + memset(&tmp, 0, sizeof(tmp)); + + /* FIXME: For now, we just accept the client back channel attributes. */ + status = init_forechannel_attrs(rqstp, &tmp, &cses->fore_channel); + if (status) + goto out; + + /* allocate struct nfsd4_session and slot table in one piece */ + slotsize = tmp.se_fnumslots * sizeof(struct nfsd4_slot); + new = kzalloc(sizeof(*new) + slotsize, GFP_KERNEL); + if (!new) + goto out; + + memcpy(new, &tmp, sizeof(*new)); + + new->se_client = clp; + gen_sessionid(new); + idx = hash_sessionid(&new->se_sessionid); + memcpy(clp->cl_sessionid.data, new->se_sessionid.data, + NFS4_MAX_SESSIONID_LEN); + + new->se_flags = cses->flags; + kref_init(&new->se_ref); + spin_lock(&sessionid_lock); + list_add(&new->se_hash, &sessionid_hashtbl[idx]); + list_add(&new->se_perclnt, &clp->cl_sessions); + spin_unlock(&sessionid_lock); + + status = nfs_ok; +out: + return status; +} + /* caller must hold sessionid_lock */ static struct nfsd4_session * find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid) @@ -1182,7 +1308,67 @@ nfsd4_create_session(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_create_session *cr_ses) { - return -1; /* stub */ + u32 ip_addr = svc_addr_in(rqstp)->sin_addr.s_addr; + struct nfs4_client *conf, *unconf; + int status = 0; + + nfs4_lock_state(); + unconf = find_unconfirmed_client(&cr_ses->clientid); + conf = find_confirmed_client(&cr_ses->clientid); + + if (conf) { + status = nfs_ok; + if (conf->cl_seqid == cr_ses->seqid) { + dprintk("Got a create_session replay! seqid= %d\n", + conf->cl_seqid); + goto out_replay; + } else if (cr_ses->seqid != conf->cl_seqid + 1) { + status = nfserr_seq_misordered; + dprintk("Sequence misordered!\n"); + dprintk("Expected seqid= %d but got seqid= %d\n", + conf->cl_seqid, cr_ses->seqid); + goto out; + } + conf->cl_seqid++; + } else if (unconf) { + if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) || + (ip_addr != unconf->cl_addr)) { + status = nfserr_clid_inuse; + goto out; + } + + if (unconf->cl_seqid != cr_ses->seqid) { + status = nfserr_seq_misordered; + goto out; + } + + move_to_confirmed(unconf); + + /* + * We do not support RDMA or persistent sessions + */ + cr_ses->flags &= ~SESSION4_PERSIST; + cr_ses->flags &= ~SESSION4_RDMA; + + conf = unconf; + } else { + status = nfserr_stale_clientid; + goto out; + } + + status = alloc_init_session(rqstp, conf, cr_ses); + if (status) + goto out; + +out_replay: + memcpy(cr_ses->sessionid.data, conf->cl_sessionid.data, + NFS4_MAX_SESSIONID_LEN); + cr_ses->seqid = conf->cl_seqid; + +out: + nfs4_unlock_state(); + dprintk("%s returns %d\n", __func__, ntohl(status)); + return status; } __be32 diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 09415bcf078e..671f9b96429b 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1099,7 +1099,108 @@ static __be32 nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, struct nfsd4_create_session *sess) { - return nfserr_opnotsupp; /* stub */ + DECODE_HEAD; + + u32 dummy; + char *machine_name; + int i; + int nr_secflavs; + + READ_BUF(16); + COPYMEM(&sess->clientid, 8); + READ32(sess->seqid); + READ32(sess->flags); + + /* Fore channel attrs */ + READ_BUF(28); + READ32(dummy); /* headerpadsz is always 0 */ + READ32(sess->fore_channel.maxreq_sz); + READ32(sess->fore_channel.maxresp_sz); + READ32(sess->fore_channel.maxresp_cached); + READ32(sess->fore_channel.maxops); + READ32(sess->fore_channel.maxreqs); + READ32(sess->fore_channel.nr_rdma_attrs); + if (sess->fore_channel.nr_rdma_attrs == 1) { + READ_BUF(4); + READ32(sess->fore_channel.rdma_attrs); + } else if (sess->fore_channel.nr_rdma_attrs > 1) { + dprintk("Too many fore channel attr bitmaps!\n"); + goto xdr_error; + } + + /* Back channel attrs */ + READ_BUF(28); + READ32(dummy); /* headerpadsz is always 0 */ + READ32(sess->back_channel.maxreq_sz); + READ32(sess->back_channel.maxresp_sz); + READ32(sess->back_channel.maxresp_cached); + READ32(sess->back_channel.maxops); + READ32(sess->back_channel.maxreqs); + READ32(sess->back_channel.nr_rdma_attrs); + if (sess->back_channel.nr_rdma_attrs == 1) { + READ_BUF(4); + READ32(sess->back_channel.rdma_attrs); + } else if (sess->back_channel.nr_rdma_attrs > 1) { + dprintk("Too many back channel attr bitmaps!\n"); + goto xdr_error; + } + + READ_BUF(8); + READ32(sess->callback_prog); + + /* callback_sec_params4 */ + READ32(nr_secflavs); + for (i = 0; i < nr_secflavs; ++i) { + READ_BUF(4); + READ32(dummy); + switch (dummy) { + case RPC_AUTH_NULL: + /* Nothing to read */ + break; + case RPC_AUTH_UNIX: + READ_BUF(8); + /* stamp */ + READ32(dummy); + + /* machine name */ + READ32(dummy); + READ_BUF(dummy); + SAVEMEM(machine_name, dummy); + + /* uid, gid */ + READ_BUF(8); + READ32(sess->uid); + READ32(sess->gid); + + /* more gids */ + READ_BUF(4); + READ32(dummy); + READ_BUF(dummy * 4); + for (i = 0; i < dummy; ++i) + READ32(dummy); + break; + case RPC_AUTH_GSS: + dprintk("RPC_AUTH_GSS callback secflavor " + "not supported!\n"); + READ_BUF(8); + /* gcbp_service */ + READ32(dummy); + /* gcbp_handle_from_server */ + READ32(dummy); + READ_BUF(dummy); + p += XDR_QUADLEN(dummy); + /* gcbp_handle_from_client */ + READ_BUF(4); + READ32(dummy); + READ_BUF(dummy); + p += XDR_QUADLEN(dummy); + break; + default: + dprintk("Illegal callback secflavor\n"); + return nfserr_inval; + } + } + DECODE_TAIL; } static __be32 @@ -2821,8 +2922,49 @@ static __be32 nfsd4_encode_create_session(struct nfsd4_compoundres *resp, int nfserr, struct nfsd4_create_session *sess) { - /* stub */ - return nfserr; + ENCODE_HEAD; + + if (nfserr) + return nfserr; + + RESERVE_SPACE(24); + WRITEMEM(sess->sessionid.data, NFS4_MAX_SESSIONID_LEN); + WRITE32(sess->seqid); + WRITE32(sess->flags); + ADJUST_ARGS(); + + RESERVE_SPACE(28); + WRITE32(0); /* headerpadsz */ + WRITE32(sess->fore_channel.maxreq_sz); + WRITE32(sess->fore_channel.maxresp_sz); + WRITE32(sess->fore_channel.maxresp_cached); + WRITE32(sess->fore_channel.maxops); + WRITE32(sess->fore_channel.maxreqs); + WRITE32(sess->fore_channel.nr_rdma_attrs); + ADJUST_ARGS(); + + if (sess->fore_channel.nr_rdma_attrs) { + RESERVE_SPACE(4); + WRITE32(sess->fore_channel.rdma_attrs); + ADJUST_ARGS(); + } + + RESERVE_SPACE(28); + WRITE32(0); /* headerpadsz */ + WRITE32(sess->back_channel.maxreq_sz); + WRITE32(sess->back_channel.maxresp_sz); + WRITE32(sess->back_channel.maxresp_cached); + WRITE32(sess->back_channel.maxops); + WRITE32(sess->back_channel.maxreqs); + WRITE32(sess->back_channel.nr_rdma_attrs); + ADJUST_ARGS(); + + if (sess->back_channel.nr_rdma_attrs) { + RESERVE_SPACE(4); + WRITE32(sess->back_channel.rdma_attrs); + ADJUST_ARGS(); + } + return 0; } static __be32 diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index f1edb1d98523..692edf4c2e7c 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -99,8 +99,12 @@ struct nfs4_callback { struct rpc_clnt * cb_client; }; +/* Maximum number of slots per session. 128 is useful for long haul TCP */ +#define NFSD_MAX_SLOTS_PER_SESSION 128 /* Maximum number of pages per slot cache entry */ #define NFSD_PAGES_PER_SLOT 1 +/* Maximum number of operations per session compound */ +#define NFSD_MAX_OPS_PER_COMPOUND 16 struct nfsd4_cache_entry { __be32 ce_status; @@ -129,7 +133,7 @@ struct nfsd4_session { u32 se_fmaxresp_cached; u32 se_fmaxops; u32 se_fnumslots; - struct nfsd4_slot *se_slots; /* forward channel slots */ + struct nfsd4_slot se_slots[]; /* forward channel slots */ }; static inline void @@ -188,6 +192,7 @@ struct nfs4_client { struct list_head cl_sessions; u32 cl_seqid; /* seqid for create_session */ u32 cl_exchange_flags; + struct nfs4_sessionid cl_sessionid; }; /* struct nfs4_client_reset diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 69cb467cb720..9468829adb70 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -359,8 +359,27 @@ struct nfsd4_exchange_id { int spa_how; }; +struct nfsd4_channel_attrs { + u32 headerpadsz; + u32 maxreq_sz; + u32 maxresp_sz; + u32 maxresp_cached; + u32 maxops; + u32 maxreqs; + u32 nr_rdma_attrs; + u32 rdma_attrs; +}; + struct nfsd4_create_session { - int foo; /* stub */ + clientid_t clientid; + struct nfs4_sessionid sessionid; + u32 seqid; + u32 flags; + struct nfsd4_channel_attrs fore_channel; + struct nfsd4_channel_attrs back_channel; + u32 callback_prog; + u32 uid; + u32 gid; }; struct nfsd4_sequence { -- cgit v1.2.3 From 38eb76a54d803e6792816623651b1a9cb85f8d01 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:32 +0300 Subject: nfsd41: Add a create session replay cache Replace the nfs4_client cl_seqid field with a single struct nfs41_slot used for the create session replay cache. The CREATE_SESSION slot sets the sl_session pointer to NULL. Otherwise, the slot and it's replay cache are used just like the session slots. Fix unconfirmed create_session replay response by initializing the create_session slot sequence id to 0. A future patch will set the CREATE_SESSION cache when a SEQUENCE operation preceeds the CREATE_SESSION operation. This compound is currently only cached in the session slot table. Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [nfsd41: use bool inuse for slot state] Signed-off-by: Benny Halevy [nfsd41: revert portion of nfsd4_set_cache_entry] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 39 +++++++++++++++++++++++++++------------ include/linux/nfsd/state.h | 2 +- 2 files changed, 28 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 463ae39df148..58f9797eb09e 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -649,6 +649,8 @@ static inline void free_client(struct nfs4_client *clp) { shutdown_callback_client(clp); + nfsd4_release_respages(clp->cl_slot.sl_cache_entry.ce_respages, + clp->cl_slot.sl_cache_entry.ce_resused); if (clp->cl_cred.cr_group_info) put_group_info(clp->cl_cred.cr_group_info); kfree(clp->cl_principal); @@ -1263,11 +1265,12 @@ out_copy: exid->clientid.cl_boot = new->cl_clientid.cl_boot; exid->clientid.cl_id = new->cl_clientid.cl_id; - new->cl_seqid = exid->seqid = 1; + new->cl_slot.sl_seqid = 0; + exid->seqid = 1; nfsd4_set_ex_flags(new, exid); dprintk("nfsd4_exchange_id seqid %d flags %x\n", - new->cl_seqid, new->cl_exchange_flags); + new->cl_slot.sl_seqid, new->cl_exchange_flags); status = nfs_ok; out: @@ -1309,7 +1312,9 @@ nfsd4_create_session(struct svc_rqst *rqstp, struct nfsd4_create_session *cr_ses) { u32 ip_addr = svc_addr_in(rqstp)->sin_addr.s_addr; + struct nfsd4_compoundres *resp = rqstp->rq_resp; struct nfs4_client *conf, *unconf; + struct nfsd4_slot *slot = NULL; int status = 0; nfs4_lock_state(); @@ -1317,19 +1322,24 @@ nfsd4_create_session(struct svc_rqst *rqstp, conf = find_confirmed_client(&cr_ses->clientid); if (conf) { - status = nfs_ok; - if (conf->cl_seqid == cr_ses->seqid) { + slot = &conf->cl_slot; + status = check_slot_seqid(cr_ses->seqid, slot); + if (status == nfserr_replay_cache) { dprintk("Got a create_session replay! seqid= %d\n", - conf->cl_seqid); - goto out_replay; - } else if (cr_ses->seqid != conf->cl_seqid + 1) { + slot->sl_seqid); + cstate->slot = slot; + cstate->status = status; + /* Return the cached reply status */ + status = nfsd4_replay_cache_entry(resp); + goto out; + } else if (cr_ses->seqid != conf->cl_slot.sl_seqid + 1) { status = nfserr_seq_misordered; dprintk("Sequence misordered!\n"); dprintk("Expected seqid= %d but got seqid= %d\n", - conf->cl_seqid, cr_ses->seqid); + slot->sl_seqid, cr_ses->seqid); goto out; } - conf->cl_seqid++; + conf->cl_slot.sl_seqid++; } else if (unconf) { if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) || (ip_addr != unconf->cl_addr)) { @@ -1337,11 +1347,15 @@ nfsd4_create_session(struct svc_rqst *rqstp, goto out; } - if (unconf->cl_seqid != cr_ses->seqid) { + slot = &unconf->cl_slot; + status = check_slot_seqid(cr_ses->seqid, slot); + if (status) { + /* an unconfirmed replay returns misordered */ status = nfserr_seq_misordered; goto out; } + slot->sl_seqid++; /* from 0 to 1 */ move_to_confirmed(unconf); /* @@ -1360,11 +1374,12 @@ nfsd4_create_session(struct svc_rqst *rqstp, if (status) goto out; -out_replay: memcpy(cr_ses->sessionid.data, conf->cl_sessionid.data, NFS4_MAX_SESSIONID_LEN); - cr_ses->seqid = conf->cl_seqid; + cr_ses->seqid = slot->sl_seqid; + slot->sl_inuse = true; + cstate->slot = slot; out: nfs4_unlock_state(); dprintk("%s returns %d\n", __func__, ntohl(status)); diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 692edf4c2e7c..f063df7ad134 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -190,7 +190,7 @@ struct nfs4_client { /* for nfs41 */ struct list_head cl_sessions; - u32 cl_seqid; /* seqid for create_session */ + struct nfsd4_slot cl_slot; /* create_session slot */ u32 cl_exchange_flags; struct nfs4_sessionid cl_sessionid; }; -- cgit v1.2.3 From bf864a31d50e3e94d6e76537b97d664913906ff8 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:35 +0300 Subject: nfsd41: non-page DRC for solo sequence responses A session inactivity time compound (lease renewal) or a compound where the sequence operation has sa_cachethis set to FALSE do not require any pages to be held in the v4.1 DRC. This is because struct nfsd4_slot is already caching the session information. Add logic to the nfs41 server to not cache response pages for solo sequence responses. Return nfserr_replay_uncached_rep on the operation following the sequence operation when sa_cachethis is FALSE. Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [nfsd41: use cstate session in nfsd4_replay_cache_entry] [nfsd41: rename nfsd4_no_page_in_cache] [nfsd41 rename nfsd4_enc_no_page_replay] [nfsd41 nfsd4_is_solo_sequence] [nfsd41 change nfsd4_not_cached return] Signed-off-by: Andy Adamson [changed return type to bool] Signed-off-by: Benny Halevy [nfsd41 drop parens in nfsd4_is_solo_sequence call] Signed-off-by: Andy Adamson [changed "== 0" to "!"] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 34 +++++++++++++++++++++++++++++++-- fs/nfsd/nfs4state.c | 47 ++++++++++++++++++++++++++++++++++++++++------ fs/nfsd/nfs4xdr.c | 5 +++-- include/linux/nfsd/state.h | 1 + include/linux/nfsd/xdr4.h | 15 ++++++++++++++- 5 files changed, 91 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 9e2ee75e0f7c..ae21a4efe36c 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -827,6 +827,34 @@ static struct nfsd4_operation nfsd4_ops[]; static const char *nfsd4_op_name(unsigned opnum); +/* + * This is a replay of a compound for which no cache entry pages + * were used. Encode the sequence operation, and if cachethis is FALSE + * encode the uncache rep error on the next operation. + */ +static __be32 +nfsd4_enc_uncached_replay(struct nfsd4_compoundargs *args, + struct nfsd4_compoundres *resp) +{ + struct nfsd4_op *op; + + dprintk("--> %s resp->opcnt %d ce_cachethis %u \n", __func__, + resp->opcnt, resp->cstate.slot->sl_cache_entry.ce_cachethis); + + /* Encode the replayed sequence operation */ + BUG_ON(resp->opcnt != 1); + op = &args->ops[resp->opcnt - 1]; + nfsd4_encode_operation(resp, op); + + /*return nfserr_retry_uncached_rep in next operation. */ + if (resp->cstate.slot->sl_cache_entry.ce_cachethis == 0) { + op = &args->ops[resp->opcnt++]; + op->status = nfserr_retry_uncached_rep; + nfsd4_encode_operation(resp, op); + } + return op->status; +} + /* * Enforce NFSv4.1 COMPOUND ordering rules. * @@ -895,7 +923,6 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, dprintk("nfsv4 compound op #%d/%d: %d (%s)\n", resp->opcnt, args->opcnt, op->opnum, nfsd4_op_name(op->opnum)); - /* * The XDR decode routines may have pre-set op->status; * for example, if there is a miscellaneous XDR error @@ -939,7 +966,10 @@ encode_op: /* Only from SEQUENCE or CREATE_SESSION */ if (resp->cstate.status == nfserr_replay_cache) { dprintk("%s NFS4.1 replay from cache\n", __func__); - status = op->status; + if (nfsd4_not_cached(resp)) + status = nfsd4_enc_uncached_replay(args, resp); + else + status = op->status; goto out; } if (op->status == nfserr_replay_me) { diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 58f9797eb09e..04a395fb5dce 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1049,17 +1049,31 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) /* Don't cache a failed OP_SEQUENCE. */ if (resp->opcnt == 1 && op->opnum == OP_SEQUENCE && resp->cstate.status) return; + nfsd4_release_respages(entry->ce_respages, entry->ce_resused); + entry->ce_opcnt = resp->opcnt; + entry->ce_status = resp->cstate.status; + + /* + * Don't need a page to cache just the sequence operation - the slot + * does this for us! + */ + + if (nfsd4_not_cached(resp)) { + entry->ce_resused = 0; + entry->ce_rpchdrlen = 0; + dprintk("%s Just cache SEQUENCE. ce_cachethis %d\n", __func__, + resp->cstate.slot->sl_cache_entry.ce_cachethis); + return; + } entry->ce_resused = rqstp->rq_resused; if (entry->ce_resused > NFSD_PAGES_PER_SLOT + 1) entry->ce_resused = NFSD_PAGES_PER_SLOT + 1; nfsd4_copy_pages(entry->ce_respages, rqstp->rq_respages, entry->ce_resused); - entry->ce_status = resp->cstate.status; entry->ce_datav.iov_base = resp->cstate.statp; entry->ce_datav.iov_len = resv->iov_len - ((char *)resp->cstate.statp - (char *)page_address(rqstp->rq_respages[0])); - entry->ce_opcnt = resp->opcnt; /* Current request rpc header length*/ entry->ce_rpchdrlen = (char *)resp->cstate.statp - (char *)page_address(rqstp->rq_respages[0]); @@ -1096,13 +1110,28 @@ nfsd41_copy_replay_data(struct nfsd4_compoundres *resp, * cached page. Replace any futher replay pages from the cache. */ __be32 -nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp) +nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, + struct nfsd4_sequence *seq) { struct nfsd4_cache_entry *entry = &resp->cstate.slot->sl_cache_entry; __be32 status; dprintk("--> %s entry %p\n", __func__, entry); + /* + * If this is just the sequence operation, we did not keep + * a page in the cache entry because we can just use the + * slot info stored in struct nfsd4_sequence that was checked + * against the slot in nfsd4_sequence(). + * + * This occurs when seq->cachethis is FALSE, or when the client + * session inactivity timer fires and a solo sequence operation + * is sent (lease renewal). + */ + if (seq && nfsd4_not_cached(resp)) { + seq->maxslots = resp->cstate.session->se_fnumslots; + return nfs_ok; + } if (!nfsd41_copy_replay_data(resp, entry)) { /* @@ -1330,7 +1359,7 @@ nfsd4_create_session(struct svc_rqst *rqstp, cstate->slot = slot; cstate->status = status; /* Return the cached reply status */ - status = nfsd4_replay_cache_entry(resp); + status = nfsd4_replay_cache_entry(resp, NULL); goto out; } else if (cr_ses->seqid != conf->cl_slot.sl_seqid + 1) { status = nfserr_seq_misordered; @@ -1380,6 +1409,8 @@ nfsd4_create_session(struct svc_rqst *rqstp, slot->sl_inuse = true; cstate->slot = slot; + /* Ensure a page is used for the cache */ + slot->sl_cache_entry.ce_cachethis = 1; out: nfs4_unlock_state(); dprintk("%s returns %d\n", __func__, ntohl(status)); @@ -1425,8 +1456,8 @@ nfsd4_sequence(struct svc_rqst *rqstp, cstate->slot = slot; cstate->session = session; /* Return the cached reply status and set cstate->status - * for nfsd4_svc_encode_compoundres processing*/ - status = nfsd4_replay_cache_entry(resp); + * for nfsd4_svc_encode_compoundres processing */ + status = nfsd4_replay_cache_entry(resp, seq); cstate->status = nfserr_replay_cache; goto replay_cache; } @@ -1436,6 +1467,10 @@ nfsd4_sequence(struct svc_rqst *rqstp, /* Success! bump slot seqid */ slot->sl_inuse = true; slot->sl_seqid = seq->seqid; + slot->sl_cache_entry.ce_cachethis = seq->cachethis; + /* Always set the cache entry cachethis for solo sequence */ + if (nfsd4_is_solo_sequence(resp)) + slot->sl_cache_entry.ce_cachethis = 1; cstate->slot = slot; cstate->session = session; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 671f9b96429b..64bc2150a6fa 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2975,7 +2975,7 @@ nfsd4_encode_destroy_session(struct nfsd4_compoundres *resp, int nfserr, return nfserr; } -static __be32 +__be32 nfsd4_encode_sequence(struct nfsd4_compoundres *resp, int nfserr, struct nfsd4_sequence *seq) { @@ -3192,7 +3192,8 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo iov->iov_len = ((char*)resp->p) - (char*)iov->iov_base; BUG_ON(iov->iov_len > PAGE_SIZE); if (resp->cstate.slot != NULL) { - if (resp->cstate.status == nfserr_replay_cache) { + if (resp->cstate.status == nfserr_replay_cache && + !nfsd4_not_cached(resp)) { iov->iov_len = resp->cstate.iovlen; } else { nfsd4_store_cache_entry(resp); diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index f063df7ad134..18dcffa57f77 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -110,6 +110,7 @@ struct nfsd4_cache_entry { __be32 ce_status; struct kvec ce_datav; /* encoded NFSv4.1 data in rq_res.head[0] */ struct page *ce_respages[NFSD_PAGES_PER_SLOT + 1]; + int ce_cachethis; short ce_resused; int ce_opcnt; int ce_rpchdrlen; diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 9468829adb70..486188810a60 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -480,6 +480,18 @@ struct nfsd4_compoundres { struct nfsd4_compound_state cstate; }; +static inline bool nfsd4_is_solo_sequence(struct nfsd4_compoundres *resp) +{ + struct nfsd4_compoundargs *args = resp->rqstp->rq_argp; + return args->opcnt == 1; +} + +static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp) +{ + return !resp->cstate.slot->sl_cache_entry.ce_cachethis || + nfsd4_is_solo_sequence(resp); +} + #define NFS4_SVC_XDRSIZE sizeof(struct nfsd4_compoundargs) static inline void @@ -510,7 +522,8 @@ extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *, struct nfsd4_setclientid_confirm *setclientid_confirm); extern void nfsd4_store_cache_entry(struct nfsd4_compoundres *resp); -extern __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp); +extern __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, + struct nfsd4_sequence *seq); extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *, struct nfsd4_exchange_id *); -- cgit v1.2.3 From e10e0cfc2f27364c73b28adbd3c8688d97049e73 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 3 Apr 2009 08:28:38 +0300 Subject: nfsd41: destroy_session operation Implement the destory_session operation confoming to http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-26 [use sessionid_lock spin lock] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 29 ++++++++++++++++++++++++++++- fs/nfsd/nfs4xdr.c | 7 +++++-- include/linux/nfsd/xdr4.h | 2 +- 3 files changed, 34 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 04a395fb5dce..9192e5b35f42 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1422,7 +1422,34 @@ nfsd4_destroy_session(struct svc_rqst *r, struct nfsd4_compound_state *cstate, struct nfsd4_destroy_session *sessionid) { - return -1; /* stub */ + struct nfsd4_session *ses; + u32 status = nfserr_badsession; + + /* Notes: + * - The confirmed nfs4_client->cl_sessionid holds destroyed sessinid + * - Should we return nfserr_back_chan_busy if waiting for + * callbacks on to-be-destroyed session? + * - Do we need to clear any callback info from previous session? + */ + + dump_sessionid(__func__, &sessionid->sessionid); + spin_lock(&sessionid_lock); + ses = find_in_sessionid_hashtbl(&sessionid->sessionid); + if (!ses) { + spin_unlock(&sessionid_lock); + goto out; + } + + unhash_session(ses); + spin_unlock(&sessionid_lock); + + /* wait for callbacks */ + shutdown_callback_client(ses->se_client); + nfsd4_put_session(ses); + status = nfs_ok; +out: + dprintk("%s returns %d\n", __func__, ntohl(status)); + return status; } __be32 diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 64bc2150a6fa..c6a726d04efd 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1207,7 +1207,11 @@ static __be32 nfsd4_decode_destroy_session(struct nfsd4_compoundargs *argp, struct nfsd4_destroy_session *destroy_session) { - return nfserr_opnotsupp; /* stub */ + DECODE_HEAD; + READ_BUF(NFS4_MAX_SESSIONID_LEN); + COPYMEM(destroy_session->sessionid.data, NFS4_MAX_SESSIONID_LEN); + + DECODE_TAIL; } static __be32 @@ -2971,7 +2975,6 @@ static __be32 nfsd4_encode_destroy_session(struct nfsd4_compoundres *resp, int nfserr, struct nfsd4_destroy_session *destroy_session) { - /* stub */ return nfserr; } diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 486188810a60..a0a2e8317a3b 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -395,7 +395,7 @@ struct nfsd4_sequence { }; struct nfsd4_destroy_session { - int foo; /* stub */ + struct nfs4_sessionid sessionid; }; struct nfsd4_op { -- cgit v1.2.3 From dd453dfd70538cadc02cb47ff8d8cfd0cb8cf435 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 3 Apr 2009 08:28:41 +0300 Subject: nfsd: pass nfsd4_compound_state* to nfs4_preprocess_{state,seq}id_op Currently we only use cstate->current_fh, will also be used by nfsd41 code. Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 10 ++++------ fs/nfsd/nfs4state.c | 22 ++++++++++++++-------- include/linux/nfsd/state.h | 4 +++- 3 files changed, 21 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index ae21a4efe36c..e6a0f314fdbe 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -513,9 +513,8 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfs4_lock_state(); /* check stateid */ - if ((status = nfs4_preprocess_stateid_op(&cstate->current_fh, - &read->rd_stateid, - RD_STATE, &read->rd_filp))) { + if ((status = nfs4_preprocess_stateid_op(cstate, &read->rd_stateid, + RD_STATE, &read->rd_filp))) { dprintk("NFSD: nfsd4_read: couldn't process stateid!\n"); goto out; } @@ -646,7 +645,7 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (setattr->sa_iattr.ia_valid & ATTR_SIZE) { nfs4_lock_state(); - status = nfs4_preprocess_stateid_op(&cstate->current_fh, + status = nfs4_preprocess_stateid_op(cstate, &setattr->sa_stateid, WR_STATE, NULL); nfs4_unlock_state(); if (status) { @@ -686,8 +685,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfserr_inval; nfs4_lock_state(); - status = nfs4_preprocess_stateid_op(&cstate->current_fh, stateid, - WR_STATE, &filp); + status = nfs4_preprocess_stateid_op(cstate, stateid, WR_STATE, &filp); if (filp) get_file(filp); nfs4_unlock_state(); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 9192e5b35f42..f49f305096ec 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -2810,10 +2810,12 @@ static int is_delegation_stateid(stateid_t *stateid) * Checks for stateid operations */ __be32 -nfs4_preprocess_stateid_op(struct svc_fh *current_fh, stateid_t *stateid, int flags, struct file **filpp) +nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate, + stateid_t *stateid, int flags, struct file **filpp) { struct nfs4_stateid *stp = NULL; struct nfs4_delegation *dp = NULL; + struct svc_fh *current_fh = &cstate->current_fh; struct inode *ino = current_fh->fh_dentry->d_inode; __be32 status; @@ -2878,10 +2880,14 @@ setlkflg (int type) * Checks for sequence id mutating operations. */ static __be32 -nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *stateid, int flags, struct nfs4_stateowner **sopp, struct nfs4_stateid **stpp, struct nfsd4_lock *lock) +nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, + stateid_t *stateid, int flags, + struct nfs4_stateowner **sopp, + struct nfs4_stateid **stpp, struct nfsd4_lock *lock) { struct nfs4_stateid *stp; struct nfs4_stateowner *sop; + struct svc_fh *current_fh = &cstate->current_fh; __be32 status; dprintk("NFSD: preprocess_seqid_op: seqid=%d " @@ -3004,7 +3010,7 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfs4_lock_state(); - if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh, + if ((status = nfs4_preprocess_seqid_op(cstate, oc->oc_seqid, &oc->oc_req_stateid, CONFIRM | OPEN_STATE, &oc->oc_stateowner, &stp, NULL))) @@ -3074,7 +3080,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp, return nfserr_inval; nfs4_lock_state(); - if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh, + if ((status = nfs4_preprocess_seqid_op(cstate, od->od_seqid, &od->od_stateid, OPEN_STATE, @@ -3127,7 +3133,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfs4_lock_state(); /* check close_lru for replay */ - if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh, + if ((status = nfs4_preprocess_seqid_op(cstate, close->cl_seqid, &close->cl_stateid, OPEN_STATE | CLOSE_STATE, @@ -3474,7 +3480,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; /* validate and update open stateid and open seqid */ - status = nfs4_preprocess_seqid_op(&cstate->current_fh, + status = nfs4_preprocess_seqid_op(cstate, lock->lk_new_open_seqid, &lock->lk_new_open_stateid, OPEN_STATE, @@ -3501,7 +3507,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } else { /* lock (lock owner + lock stateid) already exists */ - status = nfs4_preprocess_seqid_op(&cstate->current_fh, + status = nfs4_preprocess_seqid_op(cstate, lock->lk_old_lock_seqid, &lock->lk_old_lock_stateid, LOCK_STATE, @@ -3697,7 +3703,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfs4_lock_state(); - if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh, + if ((status = nfs4_preprocess_seqid_op(cstate, locku->lu_seqid, &locku->lu_stateid, LOCK_STATE, diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 18dcffa57f77..836c0d6bbed8 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -333,7 +333,9 @@ struct nfs4_stateid { ((err) != nfserr_stale_stateid) && \ ((err) != nfserr_bad_stateid)) -extern __be32 nfs4_preprocess_stateid_op(struct svc_fh *current_fh, +struct nfsd4_compound_state; + +extern __be32 nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate, stateid_t *stateid, int flags, struct file **filp); extern void nfs4_lock_state(void); extern void nfs4_unlock_state(void); -- cgit v1.2.3 From 6668958fac1d05f55420de702f3678d46c1e93a5 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:45 +0300 Subject: nfsd41: stateid handling When sessions are used, stateful operation sequenceid and stateid handling are not used. When sessions are used, on the first open set the seqid to 1, mark state confirmed and skip seqid processing. When sessionas are used the stateid generation number is ignored when it is zero whereas without sessions bad_stateid or stale stateid is returned. Add flags to propagate session use to all stateful ops and down to check_stateid_generation. Signed-off-by: Benny Halevy Signed-off-by: Andy Adamson [nfsd4_has_session should return a boolean, not u32] Signed-off-by: Benny Halevy [nfsd41: pass nfsd4_compoundres * to nfsd4_process_open1] [nfsd41: calculate HAS_SESSION in nfs4_preprocess_stateid_op] [nfsd41: calculate HAS_SESSION in nfs4_preprocess_seqid_op] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 5 ++++- fs/nfsd/nfs4state.c | 47 ++++++++++++++++++++++++++++++++++++++-------- fs/nfsd/nfs4xdr.c | 2 +- include/linux/nfsd/state.h | 1 + include/linux/nfsd/xdr4.h | 8 +++++++- 5 files changed, 52 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index e6a0f314fdbe..aeb4888bdfad 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -168,6 +168,8 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_open *open) { __be32 status; + struct nfsd4_compoundres *resp; + dprintk("NFSD: nfsd4_open filename %.*s op_stateowner %p\n", (int)open->op_fname.len, open->op_fname.data, open->op_stateowner); @@ -179,7 +181,8 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfs4_lock_state(); /* check seqid for replay. set nfs4_owner */ - status = nfsd4_process_open1(open); + resp = rqstp->rq_resp; + status = nfsd4_process_open1(&resp->cstate, open); if (status == nfserr_replay_me) { struct nfs4_replay *rp = &open->op_stateowner->so_replay; fh_put(&cstate->current_fh); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index f49f305096ec..bbaf3c9bfe5a 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -2183,7 +2183,8 @@ static struct lock_manager_operations nfsd_lease_mng_ops = { __be32 -nfsd4_process_open1(struct nfsd4_open *open) +nfsd4_process_open1(struct nfsd4_compound_state *cstate, + struct nfsd4_open *open) { clientid_t *clientid = &open->op_clientid; struct nfs4_client *clp = NULL; @@ -2206,6 +2207,9 @@ nfsd4_process_open1(struct nfsd4_open *open) return nfserr_expired; goto renew; } + /* When sessions are used, skip open sequenceid processing */ + if (nfsd4_has_session(cstate)) + goto renew; if (!sop->so_confirmed) { /* Replace unconfirmed owners without checking for replay. */ clp = sop->so_client; @@ -2483,6 +2487,7 @@ out: __be32 nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open) { + struct nfsd4_compoundres *resp = rqstp->rq_resp; struct nfs4_file *fp = NULL; struct inode *ino = current_fh->fh_dentry->d_inode; struct nfs4_stateid *stp = NULL; @@ -2541,9 +2546,14 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf release_open_stateid(stp); goto out; } + if (nfsd4_has_session(&resp->cstate)) + update_stateid(&stp->st_stateid); } memcpy(&open->op_stateid, &stp->st_stateid, sizeof(stateid_t)); + if (nfsd4_has_session(&resp->cstate)) + open->op_stateowner->so_confirmed = 1; + /* * Attempt to hand out a delegation. No error return, because the * OPEN succeeds even if we fail. @@ -2564,7 +2574,8 @@ out: * To finish the open response, we just need to set the rflags. */ open->op_rflags = NFS4_OPEN_RESULT_LOCKTYPE_POSIX; - if (!open->op_stateowner->so_confirmed) + if (!open->op_stateowner->so_confirmed && + !nfsd4_has_session(&resp->cstate)) open->op_rflags |= NFS4_OPEN_RESULT_CONFIRM; return status; @@ -2781,8 +2792,15 @@ grace_disallows_io(struct inode *inode) return locks_in_grace() && mandatory_lock(inode); } -static int check_stateid_generation(stateid_t *in, stateid_t *ref) +static int check_stateid_generation(stateid_t *in, stateid_t *ref, int flags) { + /* + * When sessions are used the stateid generation number is ignored + * when it is zero. + */ + if ((flags & HAS_SESSION) && in->si_generation == 0) + goto out; + /* If the client sends us a stateid from the future, it's buggy: */ if (in->si_generation > ref->si_generation) return nfserr_bad_stateid; @@ -2798,6 +2816,7 @@ static int check_stateid_generation(stateid_t *in, stateid_t *ref) */ if (in->si_generation < ref->si_generation) return nfserr_old_stateid; +out: return nfs_ok; } @@ -2825,6 +2844,9 @@ nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate, if (grace_disallows_io(ino)) return nfserr_grace; + if (nfsd4_has_session(cstate)) + flags |= HAS_SESSION; + if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) return check_special_stateids(current_fh, stateid, flags); @@ -2837,7 +2859,8 @@ nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate, dp = find_delegation_stateid(ino, stateid); if (!dp) goto out; - status = check_stateid_generation(stateid, &dp->dl_stateid); + status = check_stateid_generation(stateid, &dp->dl_stateid, + flags); if (status) goto out; status = nfs4_check_delegmode(dp, flags); @@ -2854,7 +2877,8 @@ nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate, goto out; if (!stp->st_stateowner->so_confirmed) goto out; - status = check_stateid_generation(stateid, &stp->st_stateid); + status = check_stateid_generation(stateid, &stp->st_stateid, + flags); if (status) goto out; status = nfs4_check_openmode(stp, flags); @@ -2905,6 +2929,10 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, if (STALE_STATEID(stateid)) return nfserr_stale_stateid; + + if (nfsd4_has_session(cstate)) + flags |= HAS_SESSION; + /* * We return BAD_STATEID if filehandle doesn't match stateid, * the confirmed flag is incorrecly set, or the generation @@ -2961,7 +2989,7 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, * For the moment, we ignore the possibility of * generation number wraparound. */ - if (seqid != sop->so_seqid) + if (!(flags & HAS_SESSION) && seqid != sop->so_seqid) goto check_replay; if (sop->so_confirmed && flags & CONFIRM) { @@ -2974,7 +3002,7 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, " confirmed yet!\n"); return nfserr_bad_stateid; } - status = check_stateid_generation(stateid, &stp->st_stateid); + status = check_stateid_generation(stateid, &stp->st_stateid, flags); if (status) return status; renew_client(sop->so_client); @@ -3169,11 +3197,14 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stateid_t *stateid = &dr->dr_stateid; struct inode *inode; __be32 status; + int flags = 0; if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) return status; inode = cstate->current_fh.fh_dentry->d_inode; + if (nfsd4_has_session(cstate)) + flags |= HAS_SESSION; nfs4_lock_state(); status = nfserr_bad_stateid; if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) @@ -3187,7 +3218,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, dp = find_delegation_stateid(inode, stateid); if (!dp) goto out; - status = check_stateid_generation(stateid, &dp->dl_stateid); + status = check_stateid_generation(stateid, &dp->dl_stateid, flags); if (status) goto out; renew_client(dp->dl_client); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index c6a726d04efd..dd81ac1a1c6c 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3194,7 +3194,7 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo iov = &rqstp->rq_res.head[0]; iov->iov_len = ((char*)resp->p) - (char*)iov->iov_base; BUG_ON(iov->iov_len > PAGE_SIZE); - if (resp->cstate.slot != NULL) { + if (nfsd4_has_session(&resp->cstate)) { if (resp->cstate.status == nfserr_replay_cache && !nfsd4_not_cached(resp)) { iov->iov_len = resp->cstate.iovlen; diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 836c0d6bbed8..4d61c873feed 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -320,6 +320,7 @@ struct nfs4_stateid { }; /* flags for preprocess_seqid_op() */ +#define HAS_SESSION 0x00000001 #define CONFIRM 0x00000002 #define OPEN_STATE 0x00000004 #define LOCK_STATE 0x00000008 diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index a0a2e8317a3b..b8b3dcba28cc 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -56,6 +56,11 @@ struct nfsd4_compound_state { u32 status; }; +static inline bool nfsd4_has_session(struct nfsd4_compound_state *cs) +{ + return cs->slot != NULL; +} + struct nfsd4_change_info { u32 atomic; u32 before_ctime_sec; @@ -536,7 +541,8 @@ extern __be32 nfsd4_sequence(struct svc_rqst *, extern __be32 nfsd4_destroy_session(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_destroy_session *); -extern __be32 nfsd4_process_open1(struct nfsd4_open *open); +extern __be32 nfsd4_process_open1(struct nfsd4_compound_state *, + struct nfsd4_open *open); extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open); extern __be32 nfsd4_open_confirm(struct svc_rqst *rqstp, -- cgit v1.2.3 From d87a8ade95288f28c729e076cd74929f3f199b6c Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:53 +0300 Subject: nfsd41: access_valid For nfs41, the open share flags are used also for delegation "wants" and "signals". Check that they are valid. Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 1 + fs/nfsd/nfs4state.c | 20 +++++++++++++++----- include/linux/nfsd/xdr4.h | 1 + 3 files changed, 17 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 3fdcca53212a..db208dd8fdca 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -910,6 +910,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, resp->tag = args->tag; resp->opcnt = 0; resp->rqstp = rqstp; + resp->cstate.minorversion = args->minorversion; resp->cstate.replay_owner = NULL; fh_init(&resp->cstate.current_fh, NFS4_FHSIZE); fh_init(&resp->cstate.save_fh, NFS4_FHSIZE); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index d227f85b5ed2..374aaf3808e8 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1943,11 +1943,21 @@ find_file(struct inode *ino) return NULL; } -static inline int access_valid(u32 x) +static inline int access_valid(u32 x, u32 minorversion) { - if (x < NFS4_SHARE_ACCESS_READ) + if ((x & NFS4_SHARE_ACCESS_MASK) < NFS4_SHARE_ACCESS_READ) return 0; - if (x > NFS4_SHARE_ACCESS_BOTH) + if ((x & NFS4_SHARE_ACCESS_MASK) > NFS4_SHARE_ACCESS_BOTH) + return 0; + x &= ~NFS4_SHARE_ACCESS_MASK; + if (minorversion && x) { + if ((x & NFS4_SHARE_WANT_MASK) > NFS4_SHARE_WANT_CANCEL) + return 0; + if ((x & NFS4_SHARE_WHEN_MASK) > NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED) + return 0; + x &= ~(NFS4_SHARE_WANT_MASK | NFS4_SHARE_WHEN_MASK); + } + if (x) return 0; return 1; } @@ -2495,7 +2505,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf __be32 status; status = nfserr_inval; - if (!access_valid(open->op_share_access) + if (!access_valid(open->op_share_access, resp->cstate.minorversion) || !deny_valid(open->op_share_deny)) goto out; /* @@ -3104,7 +3114,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp, (int)cstate->current_fh.fh_dentry->d_name.len, cstate->current_fh.fh_dentry->d_name.name); - if (!access_valid(od->od_share_access) + if (!access_valid(od->od_share_access, cstate->minorversion) || !deny_valid(od->od_share_deny)) return nfserr_inval; diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index b8b3dcba28cc..5e16935a1eaf 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -53,6 +53,7 @@ struct nfsd4_compound_state { struct nfsd4_slot *slot; __be32 *statp; size_t iovlen; + u32 minorversion; u32 status; }; -- cgit v1.2.3 From 8daf220a6a83c47b9648c28bb819c14c60bad7f9 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 3 Apr 2009 08:28:59 +0300 Subject: nfsd41: control nfsv4.1 svc via /proc/fs/nfsd/versions Support enabling and disabling nfsv4.1 via /proc/fs/nfsd/versions by writing the strings "+4.1" or "-4.1" correspondingly. Use user mode nfs-utils (rpc.nfsd option) to enable. This will allow us to get rid of CONFIG_NFSD_V4_1 [nfsd41: disable support for minorversion by default] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 2 +- fs/nfsd/nfsctl.c | 26 +++++++++++++++++++++++--- fs/nfsd/nfssvc.c | 24 ++++++++++++++++++++++++ include/linux/nfsd/nfsd.h | 2 ++ 4 files changed, 50 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index db208dd8fdca..52bb14debb30 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -921,7 +921,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, * According to RFC3010, this takes precedence over all other errors. */ status = nfserr_minor_vers_mismatch; - if (args->minorversion > NFSD_SUPPORTED_MINOR_VERSION) + if (args->minorversion > nfsd_supported_minorversion) goto out; if (!nfs41_op_ordering_ok(args)) { diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 4adebb6312c4..a9b8c75bf0bf 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -792,8 +792,9 @@ out_free: static ssize_t __write_versions(struct file *file, char *buf, size_t size) { char *mesg = buf; - char *vers, sign; + char *vers, *minorp, sign; int len, num; + unsigned minor; ssize_t tlen = 0; char *sep; @@ -814,9 +815,20 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) do { sign = *vers; if (sign == '+' || sign == '-') - num = simple_strtol((vers+1), NULL, 0); + num = simple_strtol((vers+1), &minorp, 0); else - num = simple_strtol(vers, NULL, 0); + num = simple_strtol(vers, &minorp, 0); + if (*minorp == '.') { + if (num < 4) + return -EINVAL; + minor = simple_strtoul(minorp+1, NULL, 0); + if (minor == 0) + return -EINVAL; + if (nfsd_minorversion(minor, sign == '-' ? + NFSD_CLEAR : NFSD_SET) < 0) + return -EINVAL; + goto next; + } switch(num) { case 2: case 3: @@ -826,6 +838,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) default: return -EINVAL; } + next: vers += len + 1; tlen += len; } while ((len = qword_get(&mesg, vers, size)) > 0); @@ -844,6 +857,13 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) num); sep = " "; } + if (nfsd_vers(4, NFSD_AVAIL)) + for (minor = 1; minor <= NFSD_SUPPORTED_MINOR_VERSION; minor++) + len += sprintf(buf+len, " %c4.%u", + (nfsd_vers(4, NFSD_TEST) && + nfsd_minorversion(minor, NFSD_TEST)) ? + '+' : '-', + minor); len += sprintf(buf+len, "\n"); return len; } diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index b53a098e97a4..e9d57734a348 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -121,6 +121,8 @@ struct svc_program nfsd_program = { }; +u32 nfsd_supported_minorversion; + int nfsd_vers(int vers, enum vers_op change) { if (vers < NFSD_MINVERS || vers >= NFSD_NRVERS) @@ -147,6 +149,28 @@ int nfsd_vers(int vers, enum vers_op change) } return 0; } + +int nfsd_minorversion(u32 minorversion, enum vers_op change) +{ + if (minorversion > NFSD_SUPPORTED_MINOR_VERSION) + return -1; + switch(change) { + case NFSD_SET: + nfsd_supported_minorversion = minorversion; + break; + case NFSD_CLEAR: + if (minorversion == 0) + return -1; + nfsd_supported_minorversion = minorversion - 1; + break; + case NFSD_TEST: + return minorversion <= nfsd_supported_minorversion; + case NFSD_AVAIL: + return minorversion <= NFSD_SUPPORTED_MINOR_VERSION; + } + return 0; +} + /* * Maximum number of nfsd processes */ diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 1f063d495159..70339b7b83c0 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -53,6 +53,7 @@ typedef int (*nfsd_dirop_t)(struct inode *, struct dentry *, int, int); extern struct svc_program nfsd_program; extern struct svc_version nfsd_version2, nfsd_version3, nfsd_version4; +extern u32 nfsd_supported_minorversion; extern struct mutex nfsd_mutex; extern struct svc_serv *nfsd_serv; @@ -149,6 +150,7 @@ int nfsd_set_posix_acl(struct svc_fh *, int, struct posix_acl *); enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL }; int nfsd_vers(int vers, enum vers_op change); +int nfsd_minorversion(u32 minorversion, enum vers_op change); void nfsd_reset_versions(void); int nfsd_create_serv(void); -- cgit v1.2.3 From f3ec22b5b0b4b220ee600bf1a8b6dc045b4e72bd Mon Sep 17 00:00:00 2001 From: Marc Eshel Date: Fri, 3 Apr 2009 08:29:02 +0300 Subject: nfsd41: provide support for minor version 1 at rpc level Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/nfsd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 70339b7b83c0..5bed5096874d 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -23,7 +23,7 @@ /* * nfsd version */ -#define NFSD_SUPPORTED_MINOR_VERSION 0 +#define NFSD_SUPPORTED_MINOR_VERSION 1 /* * Flags for nfsd_permission -- cgit v1.2.3 From 7e70570647827345352cf6c17461c9fa166f570a Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:29:11 +0300 Subject: nfsd41: support for 3-word long attribute bitmask Also, use client minorversion to generate supported attrs Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 15 +++++++----- fs/nfsd/nfs4xdr.c | 59 +++++++++++++++++++++++++++++++++++++---------- include/linux/nfsd/nfsd.h | 34 +++++++++++++++++++++++++-- include/linux/nfsd/xdr4.h | 12 +++++----- 4 files changed, 94 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 937853f62834..e206053433e3 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -463,8 +463,9 @@ nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (getattr->ga_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1) return nfserr_inval; - getattr->ga_bmval[0] &= NFSD_SUPPORTED_ATTRS_WORD0; - getattr->ga_bmval[1] &= NFSD_SUPPORTED_ATTRS_WORD1; + getattr->ga_bmval[0] &= nfsd_suppattrs0(cstate->minorversion); + getattr->ga_bmval[1] &= nfsd_suppattrs1(cstate->minorversion); + getattr->ga_bmval[2] &= nfsd_suppattrs2(cstate->minorversion); getattr->ga_fhp = &cstate->current_fh; return nfs_ok; @@ -555,8 +556,9 @@ nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (readdir->rd_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1) return nfserr_inval; - readdir->rd_bmval[0] &= NFSD_SUPPORTED_ATTRS_WORD0; - readdir->rd_bmval[1] &= NFSD_SUPPORTED_ATTRS_WORD1; + readdir->rd_bmval[0] &= nfsd_suppattrs0(cstate->minorversion); + readdir->rd_bmval[1] &= nfsd_suppattrs1(cstate->minorversion); + readdir->rd_bmval[2] &= nfsd_suppattrs2(cstate->minorversion); if ((cookie > ~(u32)0) || (cookie == 1) || (cookie == 2) || (cookie == 0 && memcmp(readdir->rd_verf.data, zeroverf.data, NFS4_VERIFIER_SIZE))) @@ -746,8 +748,9 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) return status; - if ((verify->ve_bmval[0] & ~NFSD_SUPPORTED_ATTRS_WORD0) - || (verify->ve_bmval[1] & ~NFSD_SUPPORTED_ATTRS_WORD1)) + if ((verify->ve_bmval[0] & ~nfsd_suppattrs0(cstate->minorversion)) + || (verify->ve_bmval[1] & ~nfsd_suppattrs1(cstate->minorversion)) + || (verify->ve_bmval[2] & ~nfsd_suppattrs2(cstate->minorversion))) return nfserr_attrnotsupp; if ((verify->ve_bmval[0] & FATTR4_WORD0_RDATTR_ERROR) || (verify->ve_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1)) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 42f9fb661006..70296fedee41 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -236,6 +236,7 @@ nfsd4_decode_bitmap(struct nfsd4_compoundargs *argp, u32 *bmval) bmval[0] = 0; bmval[1] = 0; + bmval[2] = 0; READ_BUF(4); READ32(bmlen); @@ -247,13 +248,16 @@ nfsd4_decode_bitmap(struct nfsd4_compoundargs *argp, u32 *bmval) READ32(bmval[0]); if (bmlen > 1) READ32(bmval[1]); + if (bmlen > 2) + READ32(bmval[2]); DECODE_TAIL; } static u32 nfsd_attrmask[] = { NFSD_WRITEABLE_ATTRS_WORD0, - NFSD_WRITEABLE_ATTRS_WORD1 + NFSD_WRITEABLE_ATTRS_WORD1, + NFSD_WRITEABLE_ATTRS_WORD2 }; static __be32 @@ -274,9 +278,12 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, u32 *writable, * According to spec, unsupported attributes return ERR_ATTRNOTSUPP; * read-only attributes return ERR_INVAL. */ - if ((bmval[0] & ~NFSD_SUPPORTED_ATTRS_WORD0) || (bmval[1] & ~NFSD_SUPPORTED_ATTRS_WORD1)) + if ((bmval[0] & ~nfsd_suppattrs0(argp->minorversion)) || + (bmval[1] & ~nfsd_suppattrs1(argp->minorversion)) || + (bmval[2] & ~nfsd_suppattrs2(argp->minorversion))) return nfserr_attrnotsupp; - if ((bmval[0] & ~writable[0]) || (bmval[1] & ~writable[1])) + if ((bmval[0] & ~writable[0]) || (bmval[1] & ~writable[1]) || + (bmval[2] & ~writable[2])) return nfserr_inval; READ_BUF(4); @@ -411,6 +418,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, u32 *writable, goto xdr_error; } } + BUG_ON(bmval[2]); /* no such writeable attr supported yet */ if (len != expected_len) goto xdr_error; @@ -1726,6 +1734,7 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, { u32 bmval0 = bmval[0]; u32 bmval1 = bmval[1]; + u32 bmval2 = bmval[2]; struct kstat stat; struct svc_fh tempfh; struct kstatfs statfs; @@ -1739,12 +1748,16 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, int err; int aclsupport = 0; struct nfs4_acl *acl = NULL; + struct nfsd4_compoundres *resp = rqstp->rq_resp; + u32 minorversion = resp->cstate.minorversion; BUG_ON(bmval1 & NFSD_WRITEONLY_ATTRS_WORD1); - BUG_ON(bmval0 & ~NFSD_SUPPORTED_ATTRS_WORD0); - BUG_ON(bmval1 & ~NFSD_SUPPORTED_ATTRS_WORD1); + BUG_ON(bmval0 & ~nfsd_suppattrs0(minorversion)); + BUG_ON(bmval1 & ~nfsd_suppattrs1(minorversion)); + BUG_ON(bmval2 & ~nfsd_suppattrs2(minorversion)); if (exp->ex_fslocs.migrated) { + BUG_ON(bmval[2]); status = fattr_handle_absent_fs(&bmval0, &bmval1, &rdattr_err); if (status) goto out; @@ -1790,22 +1803,42 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, if ((buflen -= 16) < 0) goto out_resource; - WRITE32(2); - WRITE32(bmval0); - WRITE32(bmval1); + if (unlikely(bmval2)) { + WRITE32(3); + WRITE32(bmval0); + WRITE32(bmval1); + WRITE32(bmval2); + } else if (likely(bmval1)) { + WRITE32(2); + WRITE32(bmval0); + WRITE32(bmval1); + } else { + WRITE32(1); + WRITE32(bmval0); + } attrlenp = p++; /* to be backfilled later */ if (bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) { - u32 word0 = NFSD_SUPPORTED_ATTRS_WORD0; + u32 word0 = nfsd_suppattrs0(minorversion); + u32 word1 = nfsd_suppattrs1(minorversion); + u32 word2 = nfsd_suppattrs2(minorversion); + if ((buflen -= 12) < 0) goto out_resource; if (!aclsupport) word0 &= ~FATTR4_WORD0_ACL; if (!exp->ex_fslocs.locations) word0 &= ~FATTR4_WORD0_FS_LOCATIONS; - WRITE32(2); - WRITE32(word0); - WRITE32(NFSD_SUPPORTED_ATTRS_WORD1); + if (!word2) { + WRITE32(2); + WRITE32(word0); + WRITE32(word1); + } else { + WRITE32(3); + WRITE32(word0); + WRITE32(word1); + WRITE32(word2); + } } if (bmval0 & FATTR4_WORD0_TYPE) { if ((buflen -= 4) < 0) @@ -2115,6 +2148,8 @@ out_acl: } WRITE64(stat.ino); } + BUG_ON(bmval2); /* FIXME: not implemented yet */ + *attrlenp = htonl((char *)p - (char *)attrlenp - 4); *countp = p - buffer; status = nfs_ok; diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 5bed5096874d..69ca788f8fc5 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -346,7 +346,7 @@ extern struct timeval nfssvc_boot; * TIME_BACKUP (unlikely to be supported any time soon) * TIME_CREATE (unlikely to be supported any time soon) */ -#define NFSD_SUPPORTED_ATTRS_WORD0 \ +#define NFSD4_SUPPORTED_ATTRS_WORD0 \ (FATTR4_WORD0_SUPPORTED_ATTRS | FATTR4_WORD0_TYPE | FATTR4_WORD0_FH_EXPIRE_TYPE \ | FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE | FATTR4_WORD0_LINK_SUPPORT \ | FATTR4_WORD0_SYMLINK_SUPPORT | FATTR4_WORD0_NAMED_ATTR | FATTR4_WORD0_FSID \ @@ -358,7 +358,7 @@ extern struct timeval nfssvc_boot; | FATTR4_WORD0_MAXFILESIZE | FATTR4_WORD0_MAXLINK | FATTR4_WORD0_MAXNAME \ | FATTR4_WORD0_MAXREAD | FATTR4_WORD0_MAXWRITE | FATTR4_WORD0_ACL) -#define NFSD_SUPPORTED_ATTRS_WORD1 \ +#define NFSD4_SUPPORTED_ATTRS_WORD1 \ (FATTR4_WORD1_MODE | FATTR4_WORD1_NO_TRUNC | FATTR4_WORD1_NUMLINKS \ | FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP | FATTR4_WORD1_RAWDEV \ | FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | FATTR4_WORD1_SPACE_TOTAL \ @@ -366,6 +366,35 @@ extern struct timeval nfssvc_boot; | FATTR4_WORD1_TIME_DELTA | FATTR4_WORD1_TIME_METADATA \ | FATTR4_WORD1_TIME_MODIFY | FATTR4_WORD1_TIME_MODIFY_SET | FATTR4_WORD1_MOUNTED_ON_FILEID) +#define NFSD4_SUPPORTED_ATTRS_WORD2 0 + +#define NFSD4_1_SUPPORTED_ATTRS_WORD0 \ + NFSD4_SUPPORTED_ATTRS_WORD0 + +#define NFSD4_1_SUPPORTED_ATTRS_WORD1 \ + NFSD4_SUPPORTED_ATTRS_WORD1 + +#define NFSD4_1_SUPPORTED_ATTRS_WORD2 \ + NFSD4_SUPPORTED_ATTRS_WORD2 + +static inline u32 nfsd_suppattrs0(u32 minorversion) +{ + return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD0 + : NFSD4_SUPPORTED_ATTRS_WORD0; +} + +static inline u32 nfsd_suppattrs1(u32 minorversion) +{ + return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD1 + : NFSD4_SUPPORTED_ATTRS_WORD1; +} + +static inline u32 nfsd_suppattrs2(u32 minorversion) +{ + return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD2 + : NFSD4_SUPPORTED_ATTRS_WORD2; +} + /* These will return ERR_INVAL if specified in GETATTR or READDIR. */ #define NFSD_WRITEONLY_ATTRS_WORD1 \ (FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET) @@ -376,6 +405,7 @@ extern struct timeval nfssvc_boot; #define NFSD_WRITEABLE_ATTRS_WORD1 \ (FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP \ | FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET) +#define NFSD_WRITEABLE_ATTRS_WORD2 0 #endif /* CONFIG_NFSD_V4 */ diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 5e16935a1eaf..c07d8fe7bb07 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -102,7 +102,7 @@ struct nfsd4_create { u32 specdata2; } dev; /* NF4BLK, NF4CHR */ } u; - u32 cr_bmval[2]; /* request */ + u32 cr_bmval[3]; /* request */ struct iattr cr_iattr; /* request */ struct nfsd4_change_info cr_cinfo; /* response */ struct nfs4_acl *cr_acl; @@ -117,7 +117,7 @@ struct nfsd4_delegreturn { }; struct nfsd4_getattr { - u32 ga_bmval[2]; /* request */ + u32 ga_bmval[3]; /* request */ struct svc_fh *ga_fhp; /* response */ }; @@ -218,7 +218,7 @@ struct nfsd4_open { stateid_t op_delegate_stateid; /* request - response */ u32 op_create; /* request */ u32 op_createmode; /* request */ - u32 op_bmval[2]; /* request */ + u32 op_bmval[3]; /* request */ union { /* request */ struct iattr iattr; /* UNCHECKED4,GUARDED4 */ nfs4_verifier verf; /* EXCLUSIVE4 */ @@ -271,7 +271,7 @@ struct nfsd4_readdir { nfs4_verifier rd_verf; /* request */ u32 rd_dircount; /* request */ u32 rd_maxcount; /* request */ - u32 rd_bmval[2]; /* request */ + u32 rd_bmval[3]; /* request */ struct svc_rqst *rd_rqstp; /* response */ struct svc_fh * rd_fhp; /* response */ @@ -313,7 +313,7 @@ struct nfsd4_secinfo { struct nfsd4_setattr { stateid_t sa_stateid; /* request */ - u32 sa_bmval[2]; /* request */ + u32 sa_bmval[3]; /* request */ struct iattr sa_iattr; /* request */ struct nfs4_acl *sa_acl; }; @@ -339,7 +339,7 @@ struct nfsd4_setclientid_confirm { /* also used for NVERIFY */ struct nfsd4_verify { - u32 ve_bmval[2]; /* request */ + u32 ve_bmval[3]; /* request */ u32 ve_attrlen; /* request */ char * ve_attrval; /* request */ }; -- cgit v1.2.3 From 8c18f2052e756e7d5dea712fc6e7ed70c00e8a39 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 3 Apr 2009 08:29:14 +0300 Subject: nfsd41: SUPPATTR_EXCLCREAT attribute Return bitmask for supported EXCLUSIVE4_1 create attributes. Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4xdr.c | 7 ++++++- include/linux/nfs4.h | 2 ++ include/linux/nfsd/nfsd.h | 14 +++++++++++++- 3 files changed, 21 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 70296fedee41..533d14fec99e 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2148,7 +2148,12 @@ out_acl: } WRITE64(stat.ino); } - BUG_ON(bmval2); /* FIXME: not implemented yet */ + if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) { + WRITE32(3); + WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD0); + WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD1); + WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD2); + } *attrlenp = htonl((char *)p - (char *)attrlenp - 4); *countp = p - buffer; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 29ed600e193b..ec3cd49b04f5 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -404,6 +404,8 @@ enum lock_type4 { #define FATTR4_WORD0_UNIQUE_HANDLES (1UL << 9) #define FATTR4_WORD0_LEASE_TIME (1UL << 10) #define FATTR4_WORD0_RDATTR_ERROR (1UL << 11) +/* Mandatory in NFSv4.1 */ +#define FATTR4_WORD2_SUPPATTR_EXCLCREAT (1UL << 11) /* Recommended Attributes */ #define FATTR4_WORD0_ACL (1UL << 12) diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 69ca788f8fc5..0ec4d142c503 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -375,7 +375,7 @@ extern struct timeval nfssvc_boot; NFSD4_SUPPORTED_ATTRS_WORD1 #define NFSD4_1_SUPPORTED_ATTRS_WORD2 \ - NFSD4_SUPPORTED_ATTRS_WORD2 + (NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT) static inline u32 nfsd_suppattrs0(u32 minorversion) { @@ -407,6 +407,18 @@ static inline u32 nfsd_suppattrs2(u32 minorversion) | FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET) #define NFSD_WRITEABLE_ATTRS_WORD2 0 +#define NFSD_SUPPATTR_EXCLCREAT_WORD0 \ + NFSD_WRITEABLE_ATTRS_WORD0 +/* + * we currently store the exclusive create verifier in the v_{a,m}time + * attributes so the client can't set these at create time using EXCLUSIVE4_1 + */ +#define NFSD_SUPPATTR_EXCLCREAT_WORD1 \ + (NFSD_WRITEABLE_ATTRS_WORD1 & \ + ~(FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET)) +#define NFSD_SUPPATTR_EXCLCREAT_WORD2 \ + NFSD_WRITEABLE_ATTRS_WORD2 + #endif /* CONFIG_NFSD_V4 */ #endif /* LINUX_NFSD_NFSD_H */ -- cgit v1.2.3 From 79fb54abd285b442e1f30f851902f3ddf58e7704 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 3 Apr 2009 08:29:17 +0300 Subject: nfsd41: CREATE_EXCLUSIVE4_1 Implement the CREATE_EXCLUSIVE4_1 open mode conforming to http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-26 This mode allows the client to atomically create a file if it doesn't exist while setting some of its attributes. It must be implemented if the server supports persistent reply cache and/or pnfs. Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 15 +++++++++++++++ fs/nfsd/nfs4xdr.c | 17 +++++++++++++++++ include/linux/nfs4.h | 8 +++++++- include/linux/nfsd/xdr4.h | 10 ++++------ 4 files changed, 43 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index e206053433e3..b2883e9c6381 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -93,6 +93,21 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o open->op_truncate = 0; if (open->op_create) { + /* FIXME: check session persistence and pnfs flags. + * The nfsv4.1 spec requires the following semantics: + * + * Persistent | pNFS | Server REQUIRED | Client Allowed + * Reply Cache | server | | + * -------------+--------+-----------------+-------------------- + * no | no | EXCLUSIVE4_1 | EXCLUSIVE4_1 + * | | | (SHOULD) + * | | and EXCLUSIVE4 | or EXCLUSIVE4 + * | | | (SHOULD NOT) + * no | yes | EXCLUSIVE4_1 | EXCLUSIVE4_1 + * yes | no | GUARDED4 | GUARDED4 + * yes | yes | GUARDED4 | GUARDED4 + */ + /* * Note: create modes (UNCHECKED,GUARDED...) are the same * in NFSv4 as in v3. diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 533d14fec99e..b820c311931c 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -260,6 +260,12 @@ static u32 nfsd_attrmask[] = { NFSD_WRITEABLE_ATTRS_WORD2 }; +static u32 nfsd41_ex_attrmask[] = { + NFSD_SUPPATTR_EXCLCREAT_WORD0, + NFSD_SUPPATTR_EXCLCREAT_WORD1, + NFSD_SUPPATTR_EXCLCREAT_WORD2 +}; + static __be32 nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, u32 *writable, struct iattr *iattr, struct nfs4_acl **acl) @@ -684,6 +690,17 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) READ_BUF(8); COPYMEM(open->op_verf.data, 8); break; + case NFS4_CREATE_EXCLUSIVE4_1: + if (argp->minorversion < 1) + goto xdr_error; + READ_BUF(8); + COPYMEM(open->op_verf.data, 8); + status = nfsd4_decode_fattr(argp, open->op_bmval, + nfsd41_ex_attrmask, &open->op_iattr, + &open->op_acl); + if (status) + goto out; + break; default: goto xdr_error; } diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index ec3cd49b04f5..e3f0cbcbd0db 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -368,7 +368,13 @@ enum opentype4 { enum createmode4 { NFS4_CREATE_UNCHECKED = 0, NFS4_CREATE_GUARDED = 1, - NFS4_CREATE_EXCLUSIVE = 2 + NFS4_CREATE_EXCLUSIVE = 2, + /* + * New to NFSv4.1. If session is persistent, + * GUARDED4 MUST be used. Otherwise, use + * EXCLUSIVE4_1 instead of EXCLUSIVE4. + */ + NFS4_CREATE_EXCLUSIVE4_1 = 3 }; enum limit_by4 { diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index c07d8fe7bb07..f80d6013fdc3 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -219,10 +219,8 @@ struct nfsd4_open { u32 op_create; /* request */ u32 op_createmode; /* request */ u32 op_bmval[3]; /* request */ - union { /* request */ - struct iattr iattr; /* UNCHECKED4,GUARDED4 */ - nfs4_verifier verf; /* EXCLUSIVE4 */ - } u; + struct iattr iattr; /* UNCHECKED4, GUARDED4, EXCLUSIVE4_1 */ + nfs4_verifier verf; /* EXCLUSIVE4 */ clientid_t op_clientid; /* request */ struct xdr_netobj op_owner; /* request */ u32 op_seqid; /* request */ @@ -236,8 +234,8 @@ struct nfsd4_open { struct nfs4_stateowner *op_stateowner; /* used during processing */ struct nfs4_acl *op_acl; }; -#define op_iattr u.iattr -#define op_verf u.verf +#define op_iattr iattr +#define op_verf verf struct nfsd4_open_confirm { stateid_t oc_req_stateid /* request */; -- cgit v1.2.3 From f0ad670d7061efad138df19aefe569263c4ea37b Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Mon, 6 Apr 2009 12:00:36 +0300 Subject: nfsd41: define NFSD_DRC_SIZE_SHIFT in set_max_drc Fixes the following compiler error: fs/nfsd/nfssvc.c: In function 'set_max_drc': fs/nfsd/nfssvc.c:240: error: 'NFSD_DRC_SIZE_SHIFT' undeclared CONFIG_NFSD_V4 is not set Reported-by: Alexander Beregalov Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfssvc.c | 2 ++ include/linux/nfsd/nfsd.h | 3 --- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index e9d57734a348..469c931cca95 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -236,6 +236,8 @@ void nfsd_reset_versions(void) */ static void set_max_drc(void) { + /* The percent of nr_free_buffer_pages used by the V4.1 server DRC */ + #define NFSD_DRC_SIZE_SHIFT 7 nfsd_serv->sv_drc_max_pages = nr_free_buffer_pages() >> NFSD_DRC_SIZE_SHIFT; nfsd_serv->sv_drc_pages_used = 0; diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 0ec4d142c503..2b49d676d0c9 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -333,9 +333,6 @@ extern struct timeval nfssvc_boot; #define NFSD_LEASE_TIME (nfs4_lease_time()) #define NFSD_LAUNDROMAT_MINTIMEOUT 10 /* seconds */ -/* The percent of nr_free_buffer_pages used by the V4.1 server DRC */ -#define NFSD_DRC_SIZE_SHIFT 7 - /* * The following attributes are currently not supported by the NFSv4 server: * ARCHIVE (deprecated anyway) -- cgit v1.2.3 From 04826f43d4f0a4d56423eb8abb9f2ec9987df5b5 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Mon, 6 Apr 2009 12:00:49 +0300 Subject: nfsd41: define nfsd4_set_statp as noop for !CONFIG_NFSD_V4 Fixes following modpost error: ERROR: "nfsd4_set_statp" [fs/nfsd/nfsd.ko] undefined! Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/cache.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/nfsd/cache.h b/include/linux/nfsd/cache.h index a59a2df6d079..5bccaab81056 100644 --- a/include/linux/nfsd/cache.h +++ b/include/linux/nfsd/cache.h @@ -75,6 +75,13 @@ int nfsd_reply_cache_init(void); void nfsd_reply_cache_shutdown(void); int nfsd_cache_lookup(struct svc_rqst *, int); void nfsd_cache_update(struct svc_rqst *, int, __be32 *); + +#ifdef CONFIG_NFSD_V4 void nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp); +#else /* CONFIG_NFSD_V4 */ +static inline void nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp) +{ +} +#endif /* CONFIG_NFSD_V4 */ #endif /* NFSCACHE_H */ -- cgit v1.2.3