summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2009-06-22 12:55:50 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2009-06-22 12:55:50 -0700
commit7e0338c0de18c50f09aea1fbef45110cf7d64a3c (patch)
tree30a935c1f6eee7125a9fbb802a33292b1f7268fa /fs
parentdf36b439c5fedefe013d4449cb6a50d15e2f4d70 (diff)
parent47fcb03fefee2501e79176932a4184fc24d6f8ec (diff)
Merge branch 'for-2.6.31' of git://fieldses.org/git/linux-nfsd
* 'for-2.6.31' of git://fieldses.org/git/linux-nfsd: (60 commits) SUNRPC: Fix the TCP server's send buffer accounting nfsd41: Backchannel: minorversion support for the back channel nfsd41: Backchannel: cleanup nfs4.0 callback encode routines nfsd41: Remove ip address collision detection case nfsd: optimise the starting of zero threads when none are running. nfsd: don't take nfsd_mutex twice when setting number of threads. nfsd41: sanity check client drc maxreqs nfsd41: move channel attributes from nfsd4_session to a nfsd4_channel_attr struct NFS: kill off complicated macro 'PROC' sunrpc: potential memory leak in function rdma_read_xdr nfsd: minor nfsd_vfs_write cleanup nfsd: Pull write-gathering code out of nfsd_vfs_write nfsd: track last inode only in use_wgather case sunrpc: align cache_clean work's timer nfsd: Use write gathering only with NFSv2 NFSv4: kill off complicated macro 'PROC' NFSv4: do exact check about attribute specified knfsd: remove unreported filehandle stats counters knfsd: fix reply cache memory corruption knfsd: reply cache cleanups ...
Diffstat (limited to 'fs')
-rw-r--r--fs/Kconfig2
-rw-r--r--fs/lockd/svclock.c2
-rw-r--r--fs/locks.c3
-rw-r--r--fs/nfs/Kconfig2
-rw-r--r--fs/nfsd/export.c13
-rw-r--r--fs/nfsd/nfs3proc.c237
-rw-r--r--fs/nfsd/nfs3xdr.c1
-rw-r--r--fs/nfsd/nfs4callback.c247
-rw-r--r--fs/nfsd/nfs4proc.c129
-rw-r--r--fs/nfsd/nfs4state.c171
-rw-r--r--fs/nfsd/nfs4xdr.c296
-rw-r--r--fs/nfsd/nfscache.c33
-rw-r--r--fs/nfsd/nfsctl.c294
-rw-r--r--fs/nfsd/nfsfh.c6
-rw-r--r--fs/nfsd/nfsproc.c198
-rw-r--r--fs/nfsd/nfssvc.c12
-rw-r--r--fs/nfsd/vfs.c93
17 files changed, 1142 insertions, 597 deletions
diff --git a/fs/Kconfig b/fs/Kconfig
index d78e950402c..a97263be6a9 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -236,10 +236,12 @@ source "fs/nfsd/Kconfig"
config LOCKD
tristate
+ depends on FILE_LOCKING
config LOCKD_V4
bool
depends on NFSD_V3 || NFS_V3
+ depends on FILE_LOCKING
default y
config EXPORTFS
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 83ee34203bd..e577a78d7ba 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -326,6 +326,8 @@ static void nlmsvc_freegrantargs(struct nlm_rqst *call)
{
if (call->a_args.lock.oh.data != call->a_owner)
kfree(call->a_args.lock.oh.data);
+
+ locks_release_private(&call->a_args.lock.fl);
}
/*
diff --git a/fs/locks.c b/fs/locks.c
index ec3deea29e3..b6440f52178 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -151,7 +151,7 @@ static struct file_lock *locks_alloc_lock(void)
return kmem_cache_alloc(filelock_cache, GFP_KERNEL);
}
-static void locks_release_private(struct file_lock *fl)
+void locks_release_private(struct file_lock *fl)
{
if (fl->fl_ops) {
if (fl->fl_ops->fl_release_private)
@@ -165,6 +165,7 @@ static void locks_release_private(struct file_lock *fl)
}
}
+EXPORT_SYMBOL_GPL(locks_release_private);
/* Free a lock which is not in use. */
static void locks_free_lock(struct file_lock *fl)
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 5d6d6f41593..2a77bc25d5a 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -1,6 +1,6 @@
config NFS_FS
tristate "NFS client support"
- depends on INET
+ depends on INET && FILE_LOCKING
select LOCKD
select SUNRPC
select NFS_ACL_SUPPORT if NFS_V3_ACL
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 8b1f8efb469..b92a27629fb 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -464,16 +464,11 @@ static int secinfo_parse(char **mesg, char *buf, struct svc_export *exp)
if (err)
return err;
/*
- * Just a quick sanity check; we could also try to check
- * whether this pseudoflavor is supported, but at worst
- * an unsupported pseudoflavor on the export would just
- * be a pseudoflavor that won't match the flavor of any
- * authenticated request. The administrator will
- * probably discover the problem when someone fails to
- * authenticate.
+ * XXX: It would be nice to also check whether this
+ * pseudoflavor is supported, so we can discover the
+ * problem at export time instead of when a client fails
+ * to authenticate.
*/
- if (f->pseudoflavor < 0)
- return -EINVAL;
err = get_int(mesg, &f->flags);
if (err)
return err;
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 7c9fe838f03..a713c418a92 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -652,8 +652,6 @@ nfsd3_proc_commit(struct svc_rqst * rqstp, struct nfsd3_commitargs *argp,
* NFSv3 Server procedures.
* Only the results of non-idempotent operations are cached.
*/
-#define nfs3svc_decode_voidargs NULL
-#define nfs3svc_release_void NULL
#define nfs3svc_decode_fhandleargs nfs3svc_decode_fhandle
#define nfs3svc_encode_attrstatres nfs3svc_encode_attrstat
#define nfs3svc_encode_wccstatres nfs3svc_encode_wccstat
@@ -686,28 +684,219 @@ struct nfsd3_voidargs { int dummy; };
#define WC (7+pAT) /* WCC attributes */
static struct svc_procedure nfsd_procedures3[22] = {
- PROC(null, void, void, void, RC_NOCACHE, ST),
- PROC(getattr, fhandle, attrstat, fhandle, RC_NOCACHE, ST+AT),
- PROC(setattr, sattr, wccstat, fhandle, RC_REPLBUFF, ST+WC),
- PROC(lookup, dirop, dirop, fhandle2, RC_NOCACHE, ST+FH+pAT+pAT),
- PROC(access, access, access, fhandle, RC_NOCACHE, ST+pAT+1),
- PROC(readlink, readlink, readlink, fhandle, RC_NOCACHE, ST+pAT+1+NFS3_MAXPATHLEN/4),
- PROC(read, read, read, fhandle, RC_NOCACHE, ST+pAT+4+NFSSVC_MAXBLKSIZE/4),
- PROC(write, write, write, fhandle, RC_REPLBUFF, ST+WC+4),
- PROC(create, create, create, fhandle2, RC_REPLBUFF, ST+(1+FH+pAT)+WC),
- PROC(mkdir, mkdir, create, fhandle2, RC_REPLBUFF, ST+(1+FH+pAT)+WC),
- PROC(symlink, symlink, create, fhandle2, RC_REPLBUFF, ST+(1+FH+pAT)+WC),
- PROC(mknod, mknod, create, fhandle2, RC_REPLBUFF, ST+(1+FH+pAT)+WC),
- PROC(remove, dirop, wccstat, fhandle, RC_REPLBUFF, ST+WC),
- PROC(rmdir, dirop, wccstat, fhandle, RC_REPLBUFF, ST+WC),
- PROC(rename, rename, rename, fhandle2, RC_REPLBUFF, ST+WC+WC),
- PROC(link, link, link, fhandle2, RC_REPLBUFF, ST+pAT+WC),
- PROC(readdir, readdir, readdir, fhandle, RC_NOCACHE, 0),
- PROC(readdirplus,readdirplus, readdir, fhandle, RC_NOCACHE, 0),
- PROC(fsstat, fhandle, fsstat, void, RC_NOCACHE, ST+pAT+2*6+1),
- PROC(fsinfo, fhandle, fsinfo, void, RC_NOCACHE, ST+pAT+12),
- PROC(pathconf, fhandle, pathconf, void, RC_NOCACHE, ST+pAT+6),
- PROC(commit, commit, commit, fhandle, RC_NOCACHE, ST+WC+2),
+ [NFS3PROC_NULL] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_null,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_voidres,
+ .pc_argsize = sizeof(struct nfsd3_voidargs),
+ .pc_ressize = sizeof(struct nfsd3_voidres),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = ST,
+ },
+ [NFS3PROC_GETATTR] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_getattr,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres,
+ .pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+ .pc_argsize = sizeof(struct nfsd3_fhandleargs),
+ .pc_ressize = sizeof(struct nfsd3_attrstatres),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = ST+AT,
+ },
+ [NFS3PROC_SETATTR] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_setattr,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_sattrargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
+ .pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+ .pc_argsize = sizeof(struct nfsd3_sattrargs),
+ .pc_ressize = sizeof(struct nfsd3_wccstatres),
+ .pc_cachetype = RC_REPLBUFF,
+ .pc_xdrressize = ST+WC,
+ },
+ [NFS3PROC_LOOKUP] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_lookup,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_diropres,
+ .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+ .pc_argsize = sizeof(struct nfsd3_diropargs),
+ .pc_ressize = sizeof(struct nfsd3_diropres),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = ST+FH+pAT+pAT,
+ },
+ [NFS3PROC_ACCESS] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_access,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_accessargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_accessres,
+ .pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+ .pc_argsize = sizeof(struct nfsd3_accessargs),
+ .pc_ressize = sizeof(struct nfsd3_accessres),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = ST+pAT+1,
+ },
+ [NFS3PROC_READLINK] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_readlink,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_readlinkargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres,
+ .pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+ .pc_argsize = sizeof(struct nfsd3_readlinkargs),
+ .pc_ressize = sizeof(struct nfsd3_readlinkres),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = ST+pAT+1+NFS3_MAXPATHLEN/4,
+ },
+ [NFS3PROC_READ] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_read,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_readargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_readres,
+ .pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+ .pc_argsize = sizeof(struct nfsd3_readargs),
+ .pc_ressize = sizeof(struct nfsd3_readres),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = ST+pAT+4+NFSSVC_MAXBLKSIZE/4,
+ },
+ [NFS3PROC_WRITE] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_write,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_writeargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_writeres,
+ .pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+ .pc_argsize = sizeof(struct nfsd3_writeargs),
+ .pc_ressize = sizeof(struct nfsd3_writeres),
+ .pc_cachetype = RC_REPLBUFF,
+ .pc_xdrressize = ST+WC+4,
+ },
+ [NFS3PROC_CREATE] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_create,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_createargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+ .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+ .pc_argsize = sizeof(struct nfsd3_createargs),
+ .pc_ressize = sizeof(struct nfsd3_createres),
+ .pc_cachetype = RC_REPLBUFF,
+ .pc_xdrressize = ST+(1+FH+pAT)+WC,
+ },
+ [NFS3PROC_MKDIR] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_mkdir,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_mkdirargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+ .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+ .pc_argsize = sizeof(struct nfsd3_mkdirargs),
+ .pc_ressize = sizeof(struct nfsd3_createres),
+ .pc_cachetype = RC_REPLBUFF,
+ .pc_xdrressize = ST+(1+FH+pAT)+WC,
+ },
+ [NFS3PROC_SYMLINK] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_symlink,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_symlinkargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+ .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+ .pc_argsize = sizeof(struct nfsd3_symlinkargs),
+ .pc_ressize = sizeof(struct nfsd3_createres),
+ .pc_cachetype = RC_REPLBUFF,
+ .pc_xdrressize = ST+(1+FH+pAT)+WC,
+ },
+ [NFS3PROC_MKNOD] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_mknod,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_mknodargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+ .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+ .pc_argsize = sizeof(struct nfsd3_mknodargs),
+ .pc_ressize = sizeof(struct nfsd3_createres),
+ .pc_cachetype = RC_REPLBUFF,
+ .pc_xdrressize = ST+(1+FH+pAT)+WC,
+ },
+ [NFS3PROC_REMOVE] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_remove,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
+ .pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+ .pc_argsize = sizeof(struct nfsd3_diropargs),
+ .pc_ressize = sizeof(struct nfsd3_wccstatres),
+ .pc_cachetype = RC_REPLBUFF,
+ .pc_xdrressize = ST+WC,
+ },
+ [NFS3PROC_RMDIR] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_rmdir,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
+ .pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+ .pc_argsize = sizeof(struct nfsd3_diropargs),
+ .pc_ressize = sizeof(struct nfsd3_wccstatres),
+ .pc_cachetype = RC_REPLBUFF,
+ .pc_xdrressize = ST+WC,
+ },
+ [NFS3PROC_RENAME] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_rename,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_renameargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_renameres,
+ .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+ .pc_argsize = sizeof(struct nfsd3_renameargs),
+ .pc_ressize = sizeof(struct nfsd3_renameres),
+ .pc_cachetype = RC_REPLBUFF,
+ .pc_xdrressize = ST+WC+WC,
+ },
+ [NFS3PROC_LINK] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_link,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_linkargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_linkres,
+ .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+ .pc_argsize = sizeof(struct nfsd3_linkargs),
+ .pc_ressize = sizeof(struct nfsd3_linkres),
+ .pc_cachetype = RC_REPLBUFF,
+ .pc_xdrressize = ST+pAT+WC,
+ },
+ [NFS3PROC_READDIR] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_readdir,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_readdirargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
+ .pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+ .pc_argsize = sizeof(struct nfsd3_readdirargs),
+ .pc_ressize = sizeof(struct nfsd3_readdirres),
+ .pc_cachetype = RC_NOCACHE,
+ },
+ [NFS3PROC_READDIRPLUS] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_readdirplus,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_readdirplusargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
+ .pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+ .pc_argsize = sizeof(struct nfsd3_readdirplusargs),
+ .pc_ressize = sizeof(struct nfsd3_readdirres),
+ .pc_cachetype = RC_NOCACHE,
+ },
+ [NFS3PROC_FSSTAT] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_fsstat,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_fsstatres,
+ .pc_argsize = sizeof(struct nfsd3_fhandleargs),
+ .pc_ressize = sizeof(struct nfsd3_fsstatres),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = ST+pAT+2*6+1,
+ },
+ [NFS3PROC_FSINFO] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_fsinfo,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_fsinfores,
+ .pc_argsize = sizeof(struct nfsd3_fhandleargs),
+ .pc_ressize = sizeof(struct nfsd3_fsinfores),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = ST+pAT+12,
+ },
+ [NFS3PROC_PATHCONF] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_pathconf,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_pathconfres,
+ .pc_argsize = sizeof(struct nfsd3_fhandleargs),
+ .pc_ressize = sizeof(struct nfsd3_pathconfres),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = ST+pAT+6,
+ },
+ [NFS3PROC_COMMIT] = {
+ .pc_func = (svc_procfunc) nfsd3_proc_commit,
+ .pc_decode = (kxdrproc_t) nfs3svc_decode_commitargs,
+ .pc_encode = (kxdrproc_t) nfs3svc_encode_commitres,
+ .pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+ .pc_argsize = sizeof(struct nfsd3_commitargs),
+ .pc_ressize = sizeof(struct nfsd3_commitres),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = ST+WC+2,
+ },
};
struct svc_version nfsd_version3 = {
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 17d0dd99720..01d4ec1c88e 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -272,6 +272,7 @@ void fill_post_wcc(struct svc_fh *fhp)
err = vfs_getattr(fhp->fh_export->ex_path.mnt, fhp->fh_dentry,
&fhp->fh_post_attr);
+ fhp->fh_post_change = fhp->fh_dentry->d_inode->i_version;
if (err)
fhp->fh_post_saved = 0;
else
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 290289bd44f..3fd23f7acec 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -140,8 +140,10 @@ struct nfs4_cb_compound_hdr {
int status;
u32 ident;
u32 nops;
+ __be32 *nops_p;
+ u32 minorversion;
u32 taglen;
- char * tag;
+ char *tag;
};
static struct {
@@ -201,33 +203,39 @@ nfs_cb_stat_to_errno(int stat)
* XDR encode
*/
-static int
+static void
encode_cb_compound_hdr(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr)
{
__be32 * p;
RESERVE_SPACE(16);
WRITE32(0); /* tag length is always 0 */
- WRITE32(NFS4_MINOR_VERSION);
+ WRITE32(hdr->minorversion);
WRITE32(hdr->ident);
+ hdr->nops_p = p;
WRITE32(hdr->nops);
- return 0;
}
-static int
-encode_cb_recall(struct xdr_stream *xdr, struct nfs4_cb_recall *cb_rec)
+static void encode_cb_nops(struct nfs4_cb_compound_hdr *hdr)
+{
+ *hdr->nops_p = htonl(hdr->nops);
+}
+
+static void
+encode_cb_recall(struct xdr_stream *xdr, struct nfs4_delegation *dp,
+ struct nfs4_cb_compound_hdr *hdr)
{
__be32 *p;
- int len = cb_rec->cbr_fh.fh_size;
+ int len = dp->dl_fh.fh_size;
- RESERVE_SPACE(12+sizeof(cb_rec->cbr_stateid) + len);
+ RESERVE_SPACE(12+sizeof(dp->dl_stateid) + len);
WRITE32(OP_CB_RECALL);
- WRITE32(cb_rec->cbr_stateid.si_generation);
- WRITEMEM(&cb_rec->cbr_stateid.si_opaque, sizeof(stateid_opaque_t));
- WRITE32(cb_rec->cbr_trunc);
+ WRITE32(dp->dl_stateid.si_generation);
+ WRITEMEM(&dp->dl_stateid.si_opaque, sizeof(stateid_opaque_t));
+ WRITE32(0); /* truncate optimization not implemented */
WRITE32(len);
- WRITEMEM(&cb_rec->cbr_fh.fh_base, len);
- return 0;
+ WRITEMEM(&dp->dl_fh.fh_base, len);
+ hdr->nops++;
}
static int
@@ -241,17 +249,18 @@ nfs4_xdr_enc_cb_null(struct rpc_rqst *req, __be32 *p)
}
static int
-nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, __be32 *p, struct nfs4_cb_recall *args)
+nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, __be32 *p, struct nfs4_delegation *args)
{
struct xdr_stream xdr;
struct nfs4_cb_compound_hdr hdr = {
- .ident = args->cbr_ident,
- .nops = 1,
+ .ident = args->dl_ident,
};
xdr_init_encode(&xdr, &req->rq_snd_buf, p);
encode_cb_compound_hdr(&xdr, &hdr);
- return (encode_cb_recall(&xdr, args));
+ encode_cb_recall(&xdr, args, &hdr);
+ encode_cb_nops(&hdr);
+ return 0;
}
@@ -358,18 +367,21 @@ static struct rpc_program cb_program = {
.pipe_dir_name = "/nfsd4_cb",
};
+static int max_cb_time(void)
+{
+ return max(NFSD_LEASE_TIME/10, (time_t)1) * HZ;
+}
+
/* Reference counting, callback cleanup, etc., all look racy as heck.
* And why is cb_set an atomic? */
-static struct rpc_clnt *setup_callback_client(struct nfs4_client *clp)
+int setup_callback_client(struct nfs4_client *clp)
{
struct sockaddr_in addr;
- struct nfs4_callback *cb = &clp->cl_callback;
+ struct nfs4_cb_conn *cb = &clp->cl_cb_conn;
struct rpc_timeout timeparms = {
- .to_initval = (NFSD_LEASE_TIME/4) * HZ,
- .to_retries = 5,
- .to_maxval = (NFSD_LEASE_TIME/2) * HZ,
- .to_exponential = 1,
+ .to_initval = max_cb_time(),
+ .to_retries = 0,
};
struct rpc_create_args args = {
.protocol = IPPROTO_TCP,
@@ -386,7 +398,7 @@ static struct rpc_clnt *setup_callback_client(struct nfs4_client *clp)
struct rpc_clnt *client;
if (!clp->cl_principal && (clp->cl_flavor >= RPC_AUTH_GSS_KRB5))
- return ERR_PTR(-EINVAL);
+ return -EINVAL;
/* Initialize address */
memset(&addr, 0, sizeof(addr));
@@ -396,48 +408,77 @@ static struct rpc_clnt *setup_callback_client(struct nfs4_client *clp)
/* Create RPC client */
client = rpc_create(&args);
- if (IS_ERR(client))
+ if (IS_ERR(client)) {
dprintk("NFSD: couldn't create callback client: %ld\n",
PTR_ERR(client));
- return client;
+ return PTR_ERR(client);
+ }
+ cb->cb_client = client;
+ return 0;
+
+}
+
+static void warn_no_callback_path(struct nfs4_client *clp, int reason)
+{
+ dprintk("NFSD: warning: no callback path to client %.*s: error %d\n",
+ (int)clp->cl_name.len, clp->cl_name.data, reason);
+}
+
+static void nfsd4_cb_probe_done(struct rpc_task *task, void *calldata)
+{
+ struct nfs4_client *clp = calldata;
+
+ if (task->tk_status)
+ warn_no_callback_path(clp, task->tk_status);
+ else
+ atomic_set(&clp->cl_cb_conn.cb_set, 1);
+ put_nfs4_client(clp);
+}
+
+static const struct rpc_call_ops nfsd4_cb_probe_ops = {
+ .rpc_call_done = nfsd4_cb_probe_done,
+};
+static struct rpc_cred *lookup_cb_cred(struct nfs4_cb_conn *cb)
+{
+ struct auth_cred acred = {
+ .machine_cred = 1
+ };
+
+ /*
+ * Note in the gss case this doesn't actually have to wait for a
+ * gss upcall (or any calls to the client); this just creates a
+ * non-uptodate cred which the rpc state machine will fill in with
+ * a refresh_upcall later.
+ */
+ return rpcauth_lookup_credcache(cb->cb_client->cl_auth, &acred,
+ RPCAUTH_LOOKUP_NEW);
}
-static int do_probe_callback(void *data)
+void do_probe_callback(struct nfs4_client *clp)
{
- struct nfs4_client *clp = data;
- struct nfs4_callback *cb = &clp->cl_callback;
+ struct nfs4_cb_conn *cb = &clp->cl_cb_conn;
struct rpc_message msg = {
.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL],
.rpc_argp = clp,
};
- struct rpc_clnt *client;
+ struct rpc_cred *cred;
int status;
- client = setup_callback_client(clp);
- if (IS_ERR(client)) {
- status = PTR_ERR(client);
- dprintk("NFSD: couldn't create callback client: %d\n",
- status);
- goto out_err;
+ cred = lookup_cb_cred(cb);
+ if (IS_ERR(cred)) {
+ status = PTR_ERR(cred);
+ goto out;
+ }
+ cb->cb_cred = cred;
+ msg.rpc_cred = cb->cb_cred;
+ status = rpc_call_async(cb->cb_client, &msg, RPC_TASK_SOFT,
+ &nfsd4_cb_probe_ops, (void *)clp);
+out:
+ if (status) {
+ warn_no_callback_path(clp, status);
+ put_nfs4_client(clp);
}
-
- status = rpc_call_sync(client, &msg, RPC_TASK_SOFT);
-
- if (status)
- goto out_release_client;
-
- cb->cb_client = client;
- atomic_set(&cb->cb_set, 1);
- put_nfs4_client(clp);
- return 0;
-out_release_client:
- rpc_shutdown_client(client);
-out_err:
- dprintk("NFSD: warning: no callback path to client %.*s: error %d\n",
- (int)clp->cl_name.len, clp->cl_name.data, status);
- put_nfs4_client(clp);
- return 0;
}
/*
@@ -446,21 +487,65 @@ out_err:
void
nfsd4_probe_callback(struct nfs4_client *clp)
{
- struct task_struct *t;
+ int status;
- BUG_ON(atomic_read(&clp->cl_callback.cb_set));
+ BUG_ON(atomic_read(&clp->cl_cb_conn.cb_set));
+
+ status = setup_callback_client(clp);
+ if (status) {
+ warn_no_callback_path(clp, status);
+ return;
+ }
/* the task holds a reference to the nfs4_client struct */
atomic_inc(&clp->cl_count);
- t = kthread_run(do_probe_callback, clp, "nfs4_cb_probe");
+ do_probe_callback(clp);
+}
- if (IS_ERR(t))
- atomic_dec(&clp->cl_count);
+static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata)
+{
+ struct nfs4_delegation *dp = calldata;
+ struct nfs4_client *clp = dp->dl_client;
- return;
+ switch (task->tk_status) {
+ case -EIO:
+ /* Network partition? */
+ atomic_set(&clp->cl_cb_conn.cb_set, 0);
+ warn_no_callback_path(clp, task->tk_status);
+ case -EBADHANDLE:
+ case -NFS4ERR_BAD_STATEID:
+ /* Race: client probably got cb_recall
+ * before open reply granting delegation */
+ break;
+ default:
+ /* success, or error we can't handle */
+ return;
+ }
+ if (dp->dl_retries--) {
+ rpc_delay(task, 2*HZ);
+ task->tk_status = 0;
+ rpc_restart_call(task);
+ } else {
+ atomic_set(&clp->cl_cb_conn.cb_set, 0);
+ warn_no_callback_path(clp, task->tk_status);
+ }
+}
+
+static void nfsd4_cb_recall_release(void *calldata)
+{
+ struct nfs4_delegation *dp = calldata;
+ struct nfs4_client *clp = dp->dl_client;
+
+ nfs4_put_delegation(dp);
+ put_nfs4_client(clp);
}
+static const struct rpc_call_ops nfsd4_cb_recall_ops = {
+ .rpc_call_done = nfsd4_cb_recall_done,
+ .rpc_release = nfsd4_cb_recall_release,
+};
+
/*
* called with dp->dl_count inc'ed.
*/
@@ -468,41 +553,19 @@ void
nfsd4_cb_recall(struct nfs4_delegation *dp)
{
struct nfs4_client *clp = dp->dl_client;
- struct rpc_clnt *clnt = clp->cl_callback.cb_client;
- struct nfs4_cb_recall *cbr = &dp->dl_recall;
+ struct rpc_clnt *clnt = clp->cl_cb_conn.cb_client;
struct rpc_message msg = {
.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_RECALL],
- .rpc_argp = cbr,
+ .rpc_argp = dp,
+ .rpc_cred = clp->cl_cb_conn.cb_cred
};
- int retries = 1;
- int status = 0;
-
- cbr->cbr_trunc = 0; /* XXX need to implement truncate optimization */
- cbr->cbr_dp = dp;
-
- status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFT);
- while (retries--) {
- switch (status) {
- case -EIO:
- /* Network partition? */
- atomic_set(&clp->cl_callback.cb_set, 0);
- case -EBADHANDLE:
- case -NFS4ERR_BAD_STATEID:
- /* Race: client probably got cb_recall
- * before open reply granting delegation */
- break;
- default:
- goto out_put_cred;
- }
- ssleep(2);
- status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFT);
+ int status;
+
+ dp->dl_retries = 1;
+ status = rpc_call_async(clnt, &msg, RPC_TASK_SOFT,
+ &nfsd4_cb_recall_ops, dp);
+ if (status) {
+ put_nfs4_client(clp);
+ nfs4_put_delegation(dp);
}
-out_put_cred:
- /*
- * Success or failure, now we're either waiting for lease expiration
- * or deleg_return.
- */
- put_nfs4_client(clp);
- nfs4_put_delegation(dp);
- return;
}
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index b2883e9c638..7c8801769a3 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -51,6 +51,78 @@
#define NFSDDBG_FACILITY NFSDDBG_PROC
+static u32 nfsd_attrmask[] = {
+ NFSD_WRITEABLE_ATTRS_WORD0,
+ NFSD_WRITEABLE_ATTRS_WORD1,
+ NFSD_WRITEABLE_ATTRS_WORD2
+};
+
+static u32 nfsd41_ex_attrmask[] = {
+ NFSD_SUPPATTR_EXCLCREAT_WORD0,
+ NFSD_SUPPATTR_EXCLCREAT_WORD1,
+ NFSD_SUPPATTR_EXCLCREAT_WORD2
+};
+
+static __be32
+check_attr_support(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+ u32 *bmval, u32 *writable)
+{
+ struct dentry *dentry = cstate->current_fh.fh_dentry;
+ struct svc_export *exp = cstate->current_fh.fh_export;
+
+ /*
+ * Check about attributes are supported by the NFSv4 server or not.
+ * According to spec, unsupported attributes return ERR_ATTRNOTSUPP.
+ */
+ if ((bmval[0] & ~nfsd_suppattrs0(cstate->minorversion)) ||
+ (bmval[1] & ~nfsd_suppattrs1(cstate->minorversion)) ||
+ (bmval[2] & ~nfsd_suppattrs2(cstate->minorversion)))
+ return nfserr_attrnotsupp;
+
+ /*
+ * Check FATTR4_WORD0_ACL & FATTR4_WORD0_FS_LOCATIONS can be supported
+ * in current environment or not.
+ */
+ if (bmval[0] & FATTR4_WORD0_ACL) {
+ if (!IS_POSIXACL(dentry->d_inode))
+ return nfserr_attrnotsupp;
+ }
+ if (bmval[0] & FATTR4_WORD0_FS_LOCATIONS) {
+ if (exp->ex_fslocs.locations == NULL)
+ return nfserr_attrnotsupp;
+ }
+
+ /*
+ * According to spec, read-only attributes return ERR_INVAL.
+ */
+ if (writable) {
+ if ((bmval[0] & ~writable[0]) || (bmval[1] & ~writable[1]) ||
+ (bmval[2] & ~writable[2]))
+ return nfserr_inval;
+ }
+
+ return nfs_ok;
+}
+
+static __be32
+nfsd4_check_open_attributes(struct svc_rqst *rqstp,
+ struct nfsd4_compound_state *cstate, struct nfsd4_open *open)
+{
+ __be32 status = nfs_ok;
+
+ if (open->op_create == NFS4_OPEN_CREATE) {
+ if (open->op_createmode == NFS4_CREATE_UNCHECKED
+ || open->op_createmode == NFS4_CREATE_GUARDED)
+ status = check_attr_support(rqstp, cstate,
+ open->op_bmval, nfsd_attrmask);
+ else if (open->op_createmode == NFS4_CREATE_EXCLUSIVE4_1)
+ status = check_attr_support(rqstp, cstate,
+ open->op_bmval, nfsd41_ex_attrmask);
+ }
+
+ return status;
+}
+
static inline void
fh_dup2(struct svc_fh *dst, struct svc_fh *src)
{
@@ -225,6 +297,10 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (status)
goto out;
+ status = nfsd4_check_open_attributes(rqstp, cstate, open);
+ if (status)
+ goto out;
+
/* Openowner is now set, so sequence id will get bumped. Now we need
* these checks before we do any creates: */
status = nfserr_grace;
@@ -395,6 +471,11 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (status)
return status;
+ status = check_attr_support(rqstp, cstate, create->cr_bmval,
+ nfsd_attrmask);
+ if (status)
+ return status;
+
switch (create->cr_type) {
case NF4LNK:
/* ugh! we have to null-terminate the linktext, or
@@ -689,6 +770,12 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (status)
return status;
status = nfs_ok;
+
+ status = check_attr_support(rqstp, cstate, setattr->sa_bmval,
+ nfsd_attrmask);
+ if (status)
+ goto out;
+
if (setattr->sa_acl != NULL)
status = nfsd4_set_nfs4_acl(rqstp, &cstate->current_fh,
setattr->sa_acl);
@@ -763,10 +850,10 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (status)
return status;
- 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;
+ status = check_attr_support(rqstp, cstate, verify->ve_bmval, NULL);
+ if (status)
+ return status;
+
if ((verify->ve_bmval[0] & FATTR4_WORD0_RDATTR_ERROR)
|| (verify->ve_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1))
return nfserr_inval;
@@ -1226,24 +1313,9 @@ static const char *nfsd4_op_name(unsigned opnum)
return "unknown_operation";
}
-#define nfs4svc_decode_voidargs NULL
-#define nfs4svc_release_void NULL
#define nfsd4_voidres nfsd4_voidargs
-#define nfs4svc_release_compound NULL
struct nfsd4_voidargs { int dummy; };
-#define PROC(name, argt, rest, relt, cache, respsize) \
- { (svc_procfunc) nfsd4_proc_##name, \
- (kxdrproc_t) nfs4svc_decode_##argt##args, \
- (kxdrproc_t) nfs4svc_encode_##rest##res, \
- (kxdrproc_t) nfs4svc_release_##relt, \
- sizeof(struct nfsd4_##argt##args), \
- sizeof(struct nfsd4_##rest##res), \
- 0, \
- cache, \
- respsize, \
- }
-
/*
* TODO: At the present time, the NFSv4 server does not do XID caching
* of requests. Implementing XID caching would not be a serious problem,
@@ -1255,8 +1327,23 @@ struct nfsd4_voidargs { int dummy; };
* better XID's.
*/
static struct svc_procedure nfsd_procedures4[2] = {
- PROC(null, void, void, void, RC_NOCACHE, 1),
- PROC(compound, compound, compound, compound, RC_NOCACHE, NFSD_BUFSIZE/4)
+ [NFSPROC4_NULL] = {
+ .pc_func = (svc_procfunc) nfsd4_proc_null,
+ .pc_encode = (kxdrproc_t) nfs4svc_encode_voidres,
+ .pc_argsize = sizeof(struct nfsd4_voidargs),
+ .pc_ressize = sizeof(struct nfsd4_voidres),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = 1,
+ },
+ [NFSPROC4_COMPOUND] = {
+ .pc_func = (svc_procfunc) nfsd4_proc_compound,
+ .pc_decode = (kxdrproc_t) nfs4svc_decode_compoundargs,
+ .pc_encode = (kxdrproc_t) nfs4svc_encode_compoundres,
+ .pc_argsize = sizeof(struct nfsd4_compoundargs),
+ .pc_ressize = sizeof(struct nfsd4_compoundres),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = NFSD_BUFSIZE/4,
+ },
};
struct svc_version nfsd_version4 = {
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 3b711f5147a..980a216a48c 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -182,7 +182,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_f
{
struct nfs4_delegation *dp;
struct nfs4_file *fp = stp->st_file;
- struct nfs4_callback *cb = &stp->st_stateowner->so_client->cl_callback;
+ struct nfs4_cb_conn *cb = &stp->st_stateowner->so_client->cl_cb_conn;
dprintk("NFSD alloc_init_deleg\n");
if (fp->fi_had_conflict)
@@ -203,10 +203,8 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_f
get_file(stp->st_vfs_file);
dp->dl_vfs_file = stp->st_vfs_file;
dp->dl_type = type;
- dp->dl_recall.cbr_dp = NULL;
- dp->dl_recall.cbr_ident = cb->cb_ident;
- dp->dl_recall.cbr_trunc = 0;
- dp->dl_stateid.si_boot = boot_time;
+ dp->dl_ident = cb->cb_ident;
+ dp->dl_stateid.si_boot = get_seconds();
dp->dl_stateid.si_stateownerid = current_delegid++;
dp->dl_stateid.si_fileid = 0;
dp->dl_stateid.si_generation = 0;
@@ -427,6 +425,11 @@ static int set_forechannel_maxreqs(struct nfsd4_channel_attrs *fchan)
{
int status = 0, np = fchan->maxreqs * NFSD_PAGES_PER_SLOT;
+ if (fchan->maxreqs < 1)
+ return nfserr_inval;
+ else if (fchan->maxreqs > NFSD_MAX_SLOTS_PER_SESSION)
+ fchan->maxreqs = NFSD_MAX_SLOTS_PER_SESSION;
+
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;
@@ -446,8 +449,8 @@ static int set_forechannel_maxreqs(struct nfsd4_channel_attrs *fchan)
* 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)
+ struct nfsd4_channel_attrs *session_fchan,
+ struct nfsd4_channel_attrs *fchan)
{
int status = 0;
__u32 maxcount = svc_max_payload(rqstp);
@@ -457,21 +460,21 @@ static int init_forechannel_attrs(struct svc_rqst *rqstp,
/* 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;
+ session_fchan->maxreq_sz = fchan->maxreq_sz;
if (fchan->maxresp_sz > maxcount)
fchan->maxresp_sz = maxcount;
- session->se_fmaxresp_sz = fchan->maxresp_sz;
+ session_fchan->maxresp_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;
+ session_fchan->maxresp_cached = NFSD_PAGES_PER_SLOT * PAGE_SIZE;
+ fchan->maxresp_cached = session_fchan->maxresp_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;
+ session_fchan->maxops = fchan->maxops;
/* try to use the client requested number of slots */
if (fchan->maxreqs > NFSD_MAX_SLOTS_PER_SESSION)
@@ -483,7 +486,7 @@ static int init_forechannel_attrs(struct svc_rqst *rqstp,
*/
status = set_forechannel_maxreqs(fchan);
- session->se_fnumslots = fchan->maxreqs;
+ session_fchan->maxreqs = fchan->maxreqs;
return status;
}
@@ -497,12 +500,14 @@ alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp,
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);
+ tmp.se_bchannel = cses->back_channel;
+ status = init_forechannel_attrs(rqstp, &tmp.se_fchannel,
+ &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);
+ slotsize = tmp.se_fchannel.maxreqs * sizeof(struct nfsd4_slot);
new = kzalloc(sizeof(*new) + slotsize, GFP_KERNEL);
if (!new)
goto out;
@@ -576,7 +581,7 @@ free_session(struct kref *kref)
int i;
ses = container_of(kref, struct nfsd4_session, se_ref);
- for (i = 0; i < ses->se_fnumslots; i++) {
+ for (i = 0; i < ses->se_fchannel.maxreqs; i++) {
struct nfsd4_cache_entry *e = &ses->se_slots[i].sl_cache_entry;
nfsd4_release_respages(e->ce_respages, e->ce_resused);
}
@@ -632,16 +637,20 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
static void
shutdown_callback_client(struct nfs4_client *clp)
{
- struct rpc_clnt *clnt = clp->cl_callback.cb_client;
+ struct rpc_clnt *clnt = clp->cl_cb_conn.cb_client;
if (clnt) {
/*
* Callback threads take a reference on the client, so there
* should be no outstanding callbacks at this point.
*/
- clp->cl_callback.cb_client = NULL;
+ clp->cl_cb_conn.cb_client = NULL;
rpc_shutdown_client(clnt);
}
+ if (clp->cl_cb_conn.cb_cred) {
+ put_rpccred(clp->cl_cb_conn.cb_cred);
+ clp->cl_cb_conn.cb_cred = NULL;
+ }
}
static inline void
@@ -714,7 +723,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir)
return NULL;
memcpy(clp->cl_recdir, recdir, HEXDIR_LEN);
atomic_set(&clp->cl_count, 1);
- atomic_set(&clp->cl_callback.cb_set, 0);
+ atomic_set(&clp->cl_cb_conn.cb_set, 0);
INIT_LIST_HEAD(&clp->cl_idhash);
INIT_LIST_HEAD(&clp->cl_strhash);
INIT_LIST_HEAD(&clp->cl_openowners);
@@ -966,7 +975,7 @@ parse_ipv4(unsigned int addr_len, char *addr_val, unsigned int *cbaddrp, unsigne
static void
gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se)
{
- struct nfs4_callback *cb = &clp->cl_callback;
+ struct nfs4_cb_conn *cb = &clp->cl_cb_conn;
/* Currently, we only support tcp for the callback channel */
if ((se->se_callback_netid_len != 3) || memcmp((char *)se->se_callback_netid_val, "tcp", 3))
@@ -975,6 +984,7 @@ gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se)
if ( !(parse_ipv4(se->se_callback_addr_len, se->se_callback_addr_val,
&cb->cb_addr, &cb->cb_port)))
goto out_err;
+ cb->cb_minorversion = 0;
cb->cb_prog = se->se_callback_prog;
cb->cb_ident = se->se_callback_ident;
return;
@@ -1128,7 +1138,7 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
* is sent (lease renewal).
*/
if (seq && nfsd4_not_cached(resp)) {
- seq->maxslots = resp->cstate.session->se_fnumslots;
+ seq->maxslots = resp->cstate.session->se_fchannel.maxreqs;
return nfs_ok;
}
@@ -1238,12 +1248,6 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
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).
@@ -1257,12 +1261,12 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
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;
- }
+ }
+
+ /* 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, true);
@@ -1471,7 +1475,7 @@ nfsd4_sequence(struct svc_rqst *rqstp,
goto out;
status = nfserr_badslot;
- if (seq->slotid >= session->se_fnumslots)
+ if (seq->slotid >= session->se_fchannel.maxreqs)
goto out;
slot = &session->se_slots[seq->slotid];
@@ -1686,9 +1690,7 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
else {
/* XXX: We just turn off callbacks until we can handle
* change request correctly. */
- atomic_set(&conf->cl_callback.cb_set, 0);
- gen_confirm(conf);
- nfsd4_remove_clid_dir(unconf);
+ atomic_set(&conf->cl_cb_conn.cb_set, 0);
expire_client(unconf);
status = nfs_ok;
@@ -1882,7 +1884,7 @@ init_stateid(struct nfs4_stateid *stp, struct nfs4_file *fp, struct nfsd4_open *
stp->st_stateowner = sop;
get_nfs4_file(fp);
stp->st_file = fp;
- stp->st_stateid.si_boot = boot_time;
+ stp->st_stateid.si_boot = get_seconds();
stp->st_stateid.si_stateownerid = sop->so_id;
stp->st_stateid.si_fileid = fp->fi_id;
stp->st_stateid.si_generation = 0;
@@ -2059,19 +2061,6 @@ nfs4_file_downgrade(struct file *filp, unsigned int share_access)
}
/*
- * Recall a delegation
- */
-static int
-do_recall(void *__dp)
-{
- struct nfs4_delegation *dp = __dp;
-
- dp->dl_file->fi_had_conflict = true;
- nfsd4_cb_recall(dp);
- return 0;
-}
-
-/*
* Spawn a thread to perform a recall on the delegation represented
* by the lease (file_lock)
*
@@ -2082,8 +2071,7 @@ do_recall(void *__dp)
static
void nfsd_break_deleg_cb(struct file_lock *fl)
{
- struct nfs4_delegation *dp= (struct nfs4_delegation *)fl->fl_owner;
- struct task_struct *t;
+ struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner;
dprintk("NFSD nfsd_break_deleg_cb: dp %p fl %p\n",dp,fl);
if (!dp)
@@ -2111,16 +2099,8 @@ void nfsd_break_deleg_cb(struct file_lock *fl)
*/
fl->fl_break_time = 0;
- t = kthread_run(do_recall, dp, "%s", "nfs4_cb_recall");
- if (IS_ERR(t)) {
- struct nfs4_client *clp = dp->dl_client;
-
- printk(KERN_INFO "NFSD: Callback thread failed for "
- "for client (clientid %08x/%08x)\n",
- clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id);
- put_nfs4_client(dp->dl_client);
- nfs4_put_delegation(dp);
- }
+ dp->dl_file->fi_had_conflict = true;
+ nfsd4_cb_recall(dp);
}
/*
@@ -2422,7 +2402,7 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta
{
struct nfs4_delegation *dp;
struct nfs4_stateowner *sop = stp->st_stateowner;
- struct nfs4_callback *cb = &sop->so_client->cl_callback;
+ struct nfs4_cb_conn *cb = &sop->so_client->cl_cb_conn;
struct file_lock fl, *flp = &fl;
int status, flag = 0;
@@ -2614,7 +2594,7 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
renew_client(clp);
status = nfserr_cb_path_down;
if (!list_empty(&clp->cl_delegations)
- && !atomic_read(&clp->cl_callback.cb_set))
+ && !atomic_read(&clp->cl_cb_conn.cb_set))
goto out;
status = nfs_ok;
out:
@@ -2738,12 +2718,42 @@ nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stateid *stp)
static int
STALE_STATEID(stateid_t *stateid)
{
- if (stateid->si_boot == boot_time)
- return 0;
- dprintk("NFSD: stale stateid (%08x/%08x/%08x/%08x)!\n",
- stateid->si_boot, stateid->si_stateownerid, stateid->si_fileid,
- stateid->si_generation);
- return 1;
+ if (time_after((unsigned long)boot_time,
+ (unsigned long)stateid->si_boot)) {
+ dprintk("NFSD: stale stateid (%08x/%08x/%08x/%08x)!\n",
+ stateid->si_boot, stateid->si_stateownerid,
+ stateid->si_fileid, stateid->si_generation);
+ return 1;
+ }
+ return 0;
+}
+
+static int
+EXPIRED_STATEID(stateid_t *stateid)
+{
+ if (time_before((unsigned long)boot_time,
+ ((unsigned long)stateid->si_boot)) &&
+ time_before((unsigned long)(stateid->si_boot + lease_time), get_seconds())) {
+ dprintk("NFSD: expired stateid (%08x/%08x/%08x/%08x)!\n",
+ stateid->si_boot, stateid->si_stateownerid,
+ stateid->si_fileid, stateid->si_generation);
+ return 1;
+ }
+ return 0;
+}
+
+static __be32
+stateid_error_map(stateid_t *stateid)
+{
+ if (STALE_STATEID(stateid))
+ return nfserr_stale_stateid;
+ if (EXPIRED_STATEID(stateid))
+ return nfserr_expired;
+
+ dprintk("NFSD: bad stateid (%08x/%08x/%08x/%08x)!\n",
+ stateid->si_boot, stateid->si_stateownerid,
+ stateid->si_fileid, stateid->si_generation);
+ return nfserr_bad_stateid;
}
static inline int
@@ -2867,8 +2877,10 @@ nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate,
status = nfserr_bad_stateid;
if (is_delegation_stateid(stateid)) {
dp = find_delegation_stateid(ino, stateid);
- if (!dp)
+ if (!dp) {
+ status = stateid_error_map(stateid);
goto out;
+ }
status = check_stateid_generation(stateid, &dp->dl_stateid,
flags);
if (status)
@@ -2881,8 +2893,10 @@ nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate,
*filpp = dp->dl_vfs_file;
} else { /* open or lock stateid */
stp = find_stateid(stateid, flags);
- if (!stp)
+ if (!stp) {
+ status = stateid_error_map(stateid);
goto out;
+ }
if (nfs4_check_fh(current_fh, stp))
goto out;
if (!stp->st_stateowner->so_confirmed)
@@ -2956,7 +2970,7 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
*/
sop = search_close_lru(stateid->si_stateownerid, flags);
if (sop == NULL)
- return nfserr_bad_stateid;
+ return stateid_error_map(stateid);
*sopp = sop;
goto check_replay;
}
@@ -3227,8 +3241,10 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (!is_delegation_stateid(stateid))
goto out;
dp = find_delegation_stateid(inode, stateid);
- if (!dp)
+ if (!dp) {
+ status = stateid_error_map(stateid);
goto out;
+ }
status = check_stateid_generation(stateid, &dp->dl_stateid, flags);
if (status)
goto out;
@@ -3455,7 +3471,7 @@ alloc_init_lock_stateid(struct nfs4_stateowner *sop, struct nfs4_file *fp, struc
stp->st_stateowner = sop;
get_nfs4_file(fp);
stp->st_file = fp;
- stp->st_stateid.si_boot = boot_time;
+ stp->st_stateid.si_boot = get_seconds();
stp->st_stateid.si_stateownerid = sop->so_id;
stp->st_stateid.si_fileid = fp->fi_id;
stp->st_stateid.si_generation = 0;
@@ -3987,6 +4003,7 @@ nfs4_state_init(void)
INIT_LIST_HEAD(&conf_str_hashtbl[i]);
INIT_LIST_HEAD(&unconf_str_hashtbl[i]);
INIT_LIST_HEAD(&unconf_id_hashtbl[i]);
+ INIT_LIST_HEAD(&reclaim_str_hashtbl[i]);
}
for (i = 0; i < SESSION_HASH_SIZE; i++)
INIT_LIST_HEAD(&sessionid_hashtbl[i]);
@@ -4009,8 +4026,6 @@ nfs4_state_init(void)
INIT_LIST_HEAD(&close_lru);
INIT_LIST_HEAD(&client_lru);
INIT_LIST_HEAD(&del_recall_lru);
- for (i = 0; i < CLIENT_HASH_SIZE; i++)
- INIT_LIST_HEAD(&reclaim_str_hashtbl[i]);
reclaim_str_hashtbl_size = 0;
return 0;
}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index b73549d293b..2dcc7feaa6f 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -83,16 +83,6 @@ check_filename(char *str, int len, __be32 err)
return 0;
}
-/*
- * START OF "GENERIC" DECODE ROUTINES.
- * These may look a little ugly since they are imported from a "generic"
- * set of XDR encode/decode routines which are intended to be shared by
- * all of our NFSv4 implementations (OpenBSD, MacOS X...).
- *
- * If the pain of reading these is too great, it should be a straightforward
- * task to translate them into Linux-specific versions which are more
- * consistent with the style used in NFSv2/v3...
- */
#define DECODE_HEAD \
__be32 *p; \
__be32 status
@@ -254,20 +244,8 @@ nfsd4_decode_bitmap(struct nfsd4_compoundargs *argp, u32 *bmval)
DECODE_TAIL;
}
-static u32 nfsd_attrmask[] = {
- NFSD_WRITEABLE_ATTRS_WORD0,
- NFSD_WRITEABLE_ATTRS_WORD1,
- 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,
+nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
struct iattr *iattr, struct nfs4_acl **acl)
{
int expected_len, len = 0;
@@ -280,18 +258,6 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, u32 *writable,
if ((status = nfsd4_decode_bitmap(argp, bmval)))
return status;
- /*
- * According to spec, unsupported attributes return ERR_ATTRNOTSUPP;
- * read-only attributes return ERR_INVAL.
- */
- 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]) ||
- (bmval[2] & ~writable[2]))
- return nfserr_inval;
-
READ_BUF(4);
READ32(expected_len);
@@ -424,8 +390,11 @@ 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)
+ if (bmval[0] & ~NFSD_WRITEABLE_ATTRS_WORD0
+ || bmval[1] & ~NFSD_WRITEABLE_ATTRS_WORD1
+ || bmval[2] & ~NFSD_WRITEABLE_ATTRS_WORD2)
+ READ_BUF(expected_len - len);
+ else if (len != expected_len)
goto xdr_error;
DECODE_TAIL;
@@ -518,8 +487,8 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create
if ((status = check_filename(create->cr_name, create->cr_namelen, nfserr_inval)))
return status;
- status = nfsd4_decode_fattr(argp, create->cr_bmval, nfsd_attrmask,
- &create->cr_iattr, &create->cr_acl);
+ status = nfsd4_decode_fattr(argp, create->cr_bmval, &create->cr_iattr,
+ &create->cr_acl);
if (status)
goto out;
@@ -682,7 +651,7 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
case NFS4_CREATE_UNCHECKED:
case NFS4_CREATE_GUARDED:
status = nfsd4_decode_fattr(argp, open->op_bmval,
- nfsd_attrmask, &open->op_iattr, &open->op_acl);
+ &open->op_iattr, &open->op_acl);
if (status)
goto out;
break;
@@ -696,8 +665,7 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
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);
+ &open->op_iattr, &open->op_acl);
if (status)
goto out;
break;
@@ -893,8 +861,8 @@ nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *seta
status = nfsd4_decode_stateid(argp, &setattr->sa_stateid);
if (status)
return status;
- return nfsd4_decode_fattr(argp, setattr->sa_bmval, nfsd_attrmask,
- &setattr->sa_iattr, &setattr->sa_acl);
+ return nfsd4_decode_fattr(argp, setattr->sa_bmval, &setattr->sa_iattr,
+ &setattr->sa_acl);
}
static __be32
@@ -1328,64 +1296,64 @@ static nfsd4_dec nfsd4_dec_ops[] = {
};
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,
+ [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,
+ [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 {
@@ -1489,21 +1457,6 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
DECODE_TAIL;
}
-/*
- * END OF "GENERIC" DECODE ROUTINES.
- */
-
-/*
- * START OF "GENERIC" ENCODE ROUTINES.
- * These may look a little ugly since they are imported from a "generic"
- * set of XDR encode/decode routines which are intended to be shared by
- * all of our NFSv4 implementations (OpenBSD, MacOS X...).
- *
- * If the pain of reading these is too great, it should be a straightforward
- * task to translate them into Linux-specific versions which are more
- * consistent with the style used in NFSv2/v3...
- */
-#define ENCODE_HEAD __be32 *p
#define WRITE32(n) *p++ = htonl(n)
#define WRITE64(n) do { \
@@ -1515,13 +1468,41 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
memcpy(p, ptr, nbytes); \
p += XDR_QUADLEN(nbytes); \
}} while (0)
-#define WRITECINFO(c) do { \
- *p++ = htonl(c.atomic); \
- *p++ = htonl(c.before_ctime_sec); \
- *p++ = htonl(c.before_ctime_nsec); \
- *p++ = htonl(c.after_ctime_sec); \
- *p++ = htonl(c.after_ctime_nsec); \
-} while (0)
+
+static void write32(__be32 **p, u32 n)
+{
+ *(*p)++ = n;
+}
+
+static void write64(__be32 **p, u64 n)
+{
+ write32(p, (u32)(n >> 32));
+ write32(p, (u32)n);
+}
+
+static void write_change(__be32 **p, struct kstat *stat, struct inode *inode)
+{
+ if (IS_I_VERSION(inode)) {
+ write64(p, inode->i_version);
+ } else {
+ write32(p, stat->ctime.tv_sec);
+ write32(p, stat->ctime.tv_nsec);
+ }
+}
+
+static void write_cinfo(__be32 **p, struct nfsd4_change_info *c)
+{
+ write32(p, c->atomic);
+ if (c->change_supported) {
+ write64(p, c->before_change);
+ write64(p, c->after_change);
+ } else {
+ write32(p, c->before_ctime_sec);
+ write32(p, c->before_ctime_nsec);
+ write32(p, c->after_ctime_sec);
+ write32(p, c->after_ctime_nsec);
+ }
+}
#define RESERVE_SPACE(nbytes) do { \
p = resp->p; \
@@ -1874,16 +1855,9 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
WRITE32(NFS4_FH_PERSISTENT|NFS4_FH_VOL_RENAME);
}
if (bmval0 & FATTR4_WORD0_CHANGE) {
- /*
- * Note: This _must_ be consistent with the scheme for writing
- * change_info, so any changes made here must be reflected there
- * as well. (See xdr4.h:set_change_info() and the WRITECINFO()
- * macro above.)
- */
if ((buflen -= 8) < 0)
goto out_resource;
- WRITE32(stat.ctime.tv_sec);
- WRITE32(stat.ctime.tv_nsec);
+ write_change(&p, &stat, dentry->d_inode);
}
if (bmval0 & FATTR4_WORD0_SIZE) {
if ((buflen -= 8) < 0)
@@ -2348,7 +2322,7 @@ fail:
static void
nfsd4_encode_stateid(struct nfsd4_compoundres *resp, stateid_t *sid)
{
- ENCODE_HEAD;
+ __be32 *p;
RESERVE_SPACE(sizeof(stateid_t));
WRITE32(sid->si_generation);
@@ -2359,7 +2333,7 @@ nfsd4_encode_stateid(struct nfsd4_compoundres *resp, stateid_t *sid)
static __be32
nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_access *access)
{
- ENCODE_HEAD;
+ __be32 *p;
if (!nfserr) {
RESERVE_SPACE(8);
@@ -2386,7 +2360,7 @@ nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_c
static __be32
nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_commit *commit)
{
- ENCODE_HEAD;
+ __be32 *p;
if (!nfserr) {
RESERVE_SPACE(8);
@@ -2399,11 +2373,11 @@ nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
static __be32
nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_create *create)
{
- ENCODE_HEAD;
+ __be32 *p;
if (!nfserr) {
RESERVE_SPACE(32);
- WRITECINFO(create->cr_cinfo);
+ write_cinfo(&p, &create->cr_cinfo);
WRITE32(2);
WRITE32(create->cr_bmval[0]);
WRITE32(create->cr_bmval[1]);
@@ -2435,7 +2409,7 @@ nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh
{
struct svc_fh *fhp = *fhpp;
unsigned int len;
- ENCODE_HEAD;
+ __be32 *p;
if (!nfserr) {
len = fhp->fh_handle.fh_size;
@@ -2454,7 +2428,7 @@ nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh
static void
nfsd4_encode_lock_denied(struct nfsd4_compoundres *resp, struct nfsd4_lock_denied *ld)
{
- ENCODE_HEAD;
+ __be32 *p;
RESERVE_SPACE(32 + XDR_LEN(ld->ld_sop ? ld->ld_sop->so_owner.len : 0));
WRITE64(ld->ld_start);
@@ -2510,11 +2484,11 @@ nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l
static __be32
nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_link *link)
{
- ENCODE_HEAD;
+ __be32 *p;
if (!nfserr) {
RESERVE_SPACE(20);
- WRITECINFO(link->li_cinfo);
+ write_cinfo(&p, &link->li_cinfo);
ADJUST_ARGS();
}
return nfserr;
@@ -2524,7 +2498,7 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_li
static __be32
nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open *open)
{
- ENCODE_HEAD;
+ __be32 *p;
ENCODE_SEQID_OP_HEAD;
if (nfserr)
@@ -2532,7 +2506,7 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op
nfsd4_encode_stateid(resp, &open->op_stateid);
RESERVE_SPACE(40);
- WRITECINFO(open->op_cinfo);
+ write_cinfo(&p, &open->op_cinfo);
WRITE32(open->op_rflags);
WRITE32(2);
WRITE32(open->op_bmval[0]);
@@ -2619,7 +2593,7 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
int v, pn;
unsigned long maxcount;
long len;
- ENCODE_HEAD;
+ __be32 *p;
if (nfserr)
return nfserr;
@@ -2681,7 +2655,7 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd
{
int maxcount;
char *page;
- ENCODE_HEAD;
+ __be32 *p;
if (nfserr)
return nfserr;
@@ -2730,7 +2704,7 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
int maxcount;
loff_t offset;
__be32 *page, *savep, *tailbase;
- ENCODE_HEAD;
+ __be32 *p;
if (nfserr)
return nfserr;
@@ -2806,11 +2780,11 @@ err_no_verf:
static __be32
nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_remove *remove)
{
- ENCODE_HEAD;
+ __be32 *p;
if (!nfserr) {
RESERVE_SPACE(20);
- WRITECINFO(remove->rm_cinfo);
+ write_cinfo(&p, &remove->rm_cinfo);
ADJUST_ARGS();
}
return nfserr;
@@ -2819,12 +2793,12 @@ nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
static __be32
nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_rename *rename)
{
- ENCODE_HEAD;
+ __be32 *p;
if (!nfserr) {
RESERVE_SPACE(40);
- WRITECINFO(rename->rn_sinfo);
- WRITECINFO(rename->rn_tinfo);
+ write_cinfo(&p, &rename->rn_sinfo);
+ write_cinfo(&p, &rename->rn_tinfo);
ADJUST_ARGS();
}
return nfserr;
@@ -2839,7 +2813,7 @@ nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
u32 nflavs;
struct exp_flavor_info *flavs;
struct exp_flavor_info def_flavs[2];
- ENCODE_HEAD;
+ __be32 *p;
if (nfserr)
goto out;
@@ -2904,7 +2878,7 @@ out:
static __be32
nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setattr *setattr)
{
- ENCODE_HEAD;
+ __be32 *p;
RESERVE_SPACE(12);
if (nfserr) {
@@ -2924,7 +2898,7 @@ nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
static __be32
nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setclientid *scd)
{
- ENCODE_HEAD;
+ __be32 *p;
if (!nfserr) {
RESERVE_SPACE(8 + sizeof(nfs4_verifier));
@@ -2944,7 +2918,7 @@ nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct n
static __be32
nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_write *write)
{
- ENCODE_HEAD;
+ __be32 *p;
if (!nfserr) {
RESERVE_SPACE(16);
@@ -2960,7 +2934,7 @@ static __be32
nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, int nfserr,
struct nfsd4_exchange_id *exid)
{
- ENCODE_HEAD;
+ __be32 *p;
char *major_id;
char *server_scope;
int major_id_sz;
@@ -3015,7 +2989,7 @@ static __be32
nfsd4_encode_create_session(struct nfsd4_compoundres *resp, int nfserr,
struct nfsd4_create_session *sess)
{
- ENCODE_HEAD;
+ __be32 *p;
if (nfserr)
return nfserr;
@@ -3071,7 +3045,7 @@ __be32
nfsd4_encode_sequence(struct nfsd4_compoundres *resp, int nfserr,
struct nfsd4_sequence *seq)
{
- ENCODE_HEAD;
+ __be32 *p;
if (nfserr)
return nfserr;
@@ -3209,7 +3183,7 @@ static int nfsd4_check_drc_limit(struct nfsd4_compoundres *resp)
dprintk("%s length %u, xb->page_len %u tlen %u pad %u\n", __func__,
length, xb->page_len, tlen, pad);
- if (length <= session->se_fmaxresp_cached)
+ if (length <= session->se_fchannel.maxresp_cached)
return status;
else
return nfserr_rep_too_big_to_cache;
@@ -3219,7 +3193,7 @@ void
nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
{
__be32 *statp;
- ENCODE_HEAD;
+ __be32 *p;
RESERVE_SPACE(8);
WRITE32(op->opnum);
@@ -3253,7 +3227,7 @@ status:
void
nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
{
- ENCODE_HEAD;
+ __be32 *p;
struct nfs4_replay *rp = op->replay;
BUG_ON(!rp);
@@ -3268,10 +3242,6 @@ nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
ADJUST_ARGS();
}
-/*
- * END OF "GENERIC" ENCODE ROUTINES.
- */
-
int
nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy)
{
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 5bfc2ac60d5..4638635c5d8 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -29,15 +29,24 @@
*/
#define CACHESIZE 1024
#define HASHSIZE 64
-#define REQHASH(xid) (((((__force __u32)xid) >> 24) ^ ((__force __u32)xid)) & (HASHSIZE-1))
-static struct hlist_head * hash_list;
+static struct hlist_head * cache_hash;
static struct list_head lru_head;
static int cache_disabled = 1;
+/*
+ * Calculate the hash index from an XID.
+ */
+static inline u32 request_hash(u32 xid)
+{
+ u32 h = xid;
+ h ^= (xid >> 24);
+ return h & (HASHSIZE-1);
+}
+
static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec);
-/*
+/*
* locking for the reply cache:
* A cache entry is "single use" if c_state == RC_INPROG
* Otherwise, it when accessing _prev or _next, the lock must be held.
@@ -62,8 +71,8 @@ int nfsd_reply_cache_init(void)
i--;
}
- hash_list = kcalloc (HASHSIZE, sizeof(struct hlist_head), GFP_KERNEL);
- if (!hash_list)
+ cache_hash = kcalloc (HASHSIZE, sizeof(struct hlist_head), GFP_KERNEL);
+ if (!cache_hash)
goto out_nomem;
cache_disabled = 0;
@@ -88,8 +97,8 @@ void nfsd_reply_cache_shutdown(void)
cache_disabled = 1;
- kfree (hash_list);
- hash_list = NULL;
+ kfree (cache_hash);
+ cache_hash = NULL;
}
/*
@@ -108,7 +117,7 @@ static void
hash_refile(struct svc_cacherep *rp)
{
hlist_del_init(&rp->c_hash);
- hlist_add_head(&rp->c_hash, hash_list + REQHASH(rp->c_xid));
+ hlist_add_head(&rp->c_hash, cache_hash + request_hash(rp->c_xid));
}
/*
@@ -138,7 +147,7 @@ nfsd_cache_lookup(struct svc_rqst *rqstp, int type)
spin_lock(&cache_lock);
rtn = RC_DOIT;
- rh = &hash_list[REQHASH(xid)];
+ rh = &cache_hash[request_hash(xid)];
hlist_for_each_entry(rp, hn, rh, c_hash) {
if (rp->c_state != RC_UNUSED &&
xid == rp->c_xid && proc == rp->c_proc &&
@@ -165,8 +174,8 @@ nfsd_cache_lookup(struct svc_rqst *rqstp, int type)
}
}
- /* This should not happen */
- if (rp == NULL) {
+ /* All entries on the LRU are in-progress. This should not happen */
+ if (&rp->c_lru == &lru_head) {
static int complaints;
printk(KERN_WARNING "nfsd: all repcache entries locked!\n");
@@ -264,7 +273,7 @@ nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp)
len = resv->iov_len - ((char*)statp - (char*)resv->iov_base);
len >>= 2;
-
+
/* Don't cache excessive amounts of data and XDR failures */
if (!statp || len > (256 >> 2)) {
rp->c_state = RC_UNUSED;
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index af16849d243..1250fb978ac 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -207,10 +207,14 @@ static struct file_operations pool_stats_operations = {
static ssize_t write_svc(struct file *file, char *buf, size_t size)
{
struct nfsctl_svc *data;
+ int err;
if (size < sizeof(*data))
return -EINVAL;
data = (struct nfsctl_svc*) buf;
- return nfsd_svc(data->svc_port, data->svc_nthreads);
+ err = nfsd_svc(data->svc_port, data->svc_nthreads);
+ if (err < 0)
+ return err;
+ return 0;
}
/**
@@ -692,11 +696,12 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
if (newthreads < 0)
return -EINVAL;
rv = nfsd_svc(NFS_PORT, newthreads);
- if (rv)
+ if (rv < 0)
return rv;
- }
- sprintf(buf, "%d\n", nfsd_nrthreads());
- return strlen(buf);
+ } else
+ rv = nfsd_nrthreads();
+
+ return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%d\n", rv);
}
/**
@@ -793,7 +798,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
{
char *mesg = buf;
char *vers, *minorp, sign;
- int len, num;
+ int len, num, remaining;
unsigned minor;
ssize_t tlen = 0;
char *sep;
@@ -840,32 +845,50 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
}
next:
vers += len + 1;
- tlen += len;
} while ((len = qword_get(&mesg, vers, size)) > 0);
/* If all get turned off, turn them back on, as
* having no versions is BAD
*/
nfsd_reset_versions();
}
+
/* Now write current state into reply buffer */
len = 0;
sep = "";
+ remaining = SIMPLE_TRANSACTION_LIMIT;
for (num=2 ; num <= 4 ; num++)
if (nfsd_vers(num, NFSD_AVAIL)) {
- len += sprintf(buf+len, "%s%c%d", sep,
+ len = snprintf(buf, remaining, "%s%c%d", sep,
nfsd_vers(num, NFSD_TEST)?'+':'-',
num);
sep = " ";
+
+ if (len > remaining)
+ break;
+ remaining -= len;
+ buf += len;
+ tlen += len;
}
if (nfsd_vers(4, NFSD_AVAIL))
- for (minor = 1; minor <= NFSD_SUPPORTED_MINOR_VERSION; minor++)
- len += sprintf(buf+len, " %c4.%u",
+ for (minor = 1; minor <= NFSD_SUPPORTED_MINOR_VERSION;
+ minor++) {
+ len = snprintf(buf, remaining, " %c4.%u",
(nfsd_vers(4, NFSD_TEST) &&
nfsd_minorversion(minor, NFSD_TEST)) ?
'+' : '-',
minor);
- len += sprintf(buf+len, "\n");
- return len;
+
+ if (len > remaining)
+ break;
+ remaining -= len;
+ buf += len;
+ tlen += len;
+ }
+
+ len = snprintf(buf, remaining, "\n");
+ if (len > remaining)
+ return -EINVAL;
+ return tlen + len;
}
/**
@@ -910,104 +933,143 @@ static ssize_t write_versions(struct file *file, char *buf, size_t size)
return rv;
}
-static ssize_t __write_ports(struct file *file, char *buf, size_t size)
+/*
+ * Zero-length write. Return a list of NFSD's current listener
+ * transports.
+ */
+static ssize_t __write_ports_names(char *buf)
{
- if (size == 0) {
- int len = 0;
+ if (nfsd_serv == NULL)
+ return 0;
+ return svc_xprt_names(nfsd_serv, buf, SIMPLE_TRANSACTION_LIMIT);
+}
- if (nfsd_serv)
- len = svc_xprt_names(nfsd_serv, buf, 0);
- return len;
- }
- /* Either a single 'fd' number is written, in which
- * case it must be for a socket of a supported family/protocol,
- * and we use it as an nfsd socket, or
- * A '-' followed by the 'name' of a socket in which case
- * we close the socket.
- */
- if (isdigit(buf[0])) {
- char *mesg = buf;
- int fd;
- int err;
- err = get_int(&mesg, &fd);
- if (err)
- return -EINVAL;
- if (fd < 0)
- return -EINVAL;
- err = nfsd_create_serv();
- if (!err) {
- err = svc_addsock(nfsd_serv, fd, buf);
- if (err >= 0) {
- err = lockd_up();
- if (err < 0)
- svc_sock_names(buf+strlen(buf)+1, nfsd_serv, buf);
- }
- /* Decrease the count, but don't shutdown the
- * the service
- */
- nfsd_serv->sv_nrthreads--;
- }
- return err < 0 ? err : 0;
- }
- if (buf[0] == '-' && isdigit(buf[1])) {
- char *toclose = kstrdup(buf+1, GFP_KERNEL);
- int len = 0;
- if (!toclose)
- return -ENOMEM;
- if (nfsd_serv)
- len = svc_sock_names(buf, nfsd_serv, toclose);
- if (len >= 0)
- lockd_down();
- kfree(toclose);
- return len;
- }
- /*
- * Add a transport listener by writing it's transport name
- */
- if (isalpha(buf[0])) {
- int err;
- char transport[16];
- int port;
- if (sscanf(buf, "%15s %4d", transport, &port) == 2) {
- if (port < 1 || port > 65535)
- return -EINVAL;
- err = nfsd_create_serv();
- if (!err) {
- err = svc_create_xprt(nfsd_serv,
- transport, PF_INET, port,
- SVC_SOCK_ANONYMOUS);
- if (err == -ENOENT)
- /* Give a reasonable perror msg for
- * bad transport string */
- err = -EPROTONOSUPPORT;
- }
- return err < 0 ? err : 0;
- }
- }
- /*
- * Remove a transport by writing it's transport name and port number
- */
- if (buf[0] == '-' && isalpha(buf[1])) {
- struct svc_xprt *xprt;
- int err = -EINVAL;
- char transport[16];
- int port;
- if (sscanf(&buf[1], "%15s %4d", transport, &port) == 2) {
- if (port < 1 || port > 65535)
- return -EINVAL;
- if (nfsd_serv) {
- xprt = svc_find_xprt(nfsd_serv, transport,
- AF_UNSPEC, port);
- if (xprt) {
- svc_close_xprt(xprt);
- svc_xprt_put(xprt);
- err = 0;
- } else
- err = -ENOTCONN;
- }
- return err < 0 ? err : 0;
- }
+/*
+ * A single 'fd' number was written, in which case it must be for
+ * a socket of a supported family/protocol, and we use it as an
+ * nfsd listener.
+ */
+static ssize_t __write_ports_addfd(char *buf)
+{
+ char *mesg = buf;
+ int fd, err;
+
+ err = get_int(&mesg, &fd);
+ if (err != 0 || fd < 0)
+ return -EINVAL;
+
+ err = nfsd_create_serv();
+ if (err != 0)
+ return err;
+
+ err = lockd_up();
+ if (err != 0)
+ goto out;
+
+ err = svc_addsock(nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT);
+ if (err < 0)
+ lockd_down();
+
+out:
+ /* Decrease the count, but don't shut down the service */
+ nfsd_serv->sv_nrthreads--;
+ return err;
+}
+
+/*
+ * A '-' followed by the 'name' of a socket means we close the socket.
+ */
+static ssize_t __write_ports_delfd(char *buf)
+{
+ char *toclose;
+ int len = 0;
+
+ toclose = kstrdup(buf + 1, GFP_KERNEL);
+ if (toclose == NULL)
+ return -ENOMEM;
+
+ if (nfsd_serv != NULL)
+ len = svc_sock_names(nfsd_serv, buf,
+ SIMPLE_TRANSACTION_LIMIT, toclose);
+ if (len >= 0)
+ lockd_down();
+
+ kfree(toclose);
+ return len;
+}
+
+/*
+ * A transport listener is added by writing it's transport name and
+ * a port number.
+ */
+static ssize_t __write_ports_addxprt(char *buf)
+{
+ char transport[16];
+ int port, err;
+
+ if (sscanf(buf, "%15s %4u", transport, &port) != 2)
+ return -EINVAL;
+
+ if (port < 1 || port > USHORT_MAX)
+ return -EINVAL;
+
+ err = nfsd_create_serv();
+ if (err != 0)
+ return err;
+
+ err = svc_create_xprt(nfsd_serv, transport,
+ PF_INET, port, SVC_SOCK_ANONYMOUS);
+ if (err < 0) {
+ /* Give a reasonable perror msg for bad transport string */
+ if (err == -ENOENT)
+ err = -EPROTONOSUPPORT;
+ return err;
}
+ return 0;
+}
+
+/*
+ * A transport listener is removed by writing a "-", it's transport
+ * name, and it's port number.
+ */
+static ssize_t __write_ports_delxprt(char *buf)
+{
+ struct svc_xprt *xprt;
+ char transport[16];
+ int port;
+
+ if (sscanf(&buf[1], "%15s %4u", transport, &port) != 2)
+ return -EINVAL;
+
+ if (port < 1 || port > USHORT_MAX || nfsd_serv == NULL)
+ return -EINVAL;
+
+ xprt = svc_find_xprt(nfsd_serv, transport, AF_UNSPEC, port);
+ if (xprt == NULL)
+ return -ENOTCONN;
+
+ svc_close_xprt(xprt);
+ svc_xprt_put(xprt);
+ return 0;
+}
+
+static ssize_t __write_ports(struct file *file, char *buf, size_t size)
+{
+ if (size == 0)
+ return __write_ports_names(buf);
+
+ if (isdigit(buf[0]))
+ return __write_ports_addfd(buf);
+
+ if (buf[0] == '-' && isdigit(buf[1]))
+ return __write_ports_delfd(buf);
+
+ if (isalpha(buf[0]))
+ return __write_ports_addxprt(buf);
+
+ if (buf[0] == '-' && isalpha(buf[1]))
+ return __write_ports_delxprt(buf);
+
return -EINVAL;
}
@@ -1030,7 +1092,9 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size)
* buf: C string containing an unsigned
* integer value representing a bound
* but unconnected socket that is to be
- * used as an NFSD listener
+ * used as an NFSD listener; listen(3)
+ * must be called for a SOCK_STREAM
+ * socket, otherwise it is ignored
* size: non-zero length of C string in @buf
* Output:
* On success: NFS service is started;
@@ -1138,7 +1202,9 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size)
nfsd_max_blksize = bsize;
mutex_unlock(&nfsd_mutex);
}
- return sprintf(buf, "%d\n", nfsd_max_blksize);
+
+ return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%d\n",
+ nfsd_max_blksize);
}
#ifdef CONFIG_NFSD_V4
@@ -1162,8 +1228,9 @@ static ssize_t __write_leasetime(struct file *file, char *buf, size_t size)
return -EINVAL;
nfs4_reset_lease(lease);
}
- sprintf(buf, "%ld\n", nfs4_lease_time());
- return strlen(buf);
+
+ return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%ld\n",
+ nfs4_lease_time());
}
/**
@@ -1219,8 +1286,9 @@ static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size)
status = nfs4_reset_recoverydir(recdir);
}
- sprintf(buf, "%s\n", nfs4_recoverydir());
- return strlen(buf);
+
+ return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%s\n",
+ nfs4_recoverydir());
}
/**
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 9f1ca17293d..8847f3fbfc1 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -27,9 +27,6 @@
#define NFSDDBG_FACILITY NFSDDBG_FH
-static int nfsd_nr_verified;
-static int nfsd_nr_put;
-
/*
* our acceptability function.
* if NOSUBTREECHECK, accept anything
@@ -251,7 +248,6 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
fhp->fh_dentry = dentry;
fhp->fh_export = exp;
- nfsd_nr_verified++;
return 0;
out:
exp_put(exp);
@@ -552,7 +548,6 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
return nfserr_opnotsupp;
}
- nfsd_nr_verified++;
return 0;
}
@@ -609,7 +604,6 @@ fh_put(struct svc_fh *fhp)
fhp->fh_pre_saved = 0;
fhp->fh_post_saved = 0;
#endif
- nfsd_nr_put++;
}
if (exp) {
cache_put(&exp->h, &svc_export_cache);
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index e298e260b5f..0eb9c820b7a 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -533,45 +533,179 @@ nfsd_proc_statfs(struct svc_rqst * rqstp, struct nfsd_fhandle *argp,
* NFSv2 Server procedures.
* Only the results of non-idempotent operations are cached.
*/
-#define nfsd_proc_none NULL
-#define nfssvc_release_none NULL
struct nfsd_void { int dummy; };
-#define PROC(name, argt, rest, relt, cache, respsize) \
- { (svc_procfunc) nfsd_proc_##name, \
- (kxdrproc_t) nfssvc_decode_##argt, \
- (kxdrproc_t) nfssvc_encode_##rest, \
- (kxdrproc_t) nfssvc_release_##relt, \
- sizeof(struct nfsd_##argt), \
- sizeof(struct nfsd_##rest), \
- 0, \
- cache, \
- respsize, \
- }
-
#define ST 1 /* status */
#define FH 8 /* filehandle */
#define AT 18 /* attributes */
static struct svc_procedure nfsd_procedures2[18] = {
- PROC(null, void, void, none, RC_NOCACHE, ST),
- PROC(getattr, fhandle, attrstat, fhandle, RC_NOCACHE, ST+AT),
- PROC(setattr, sattrargs, attrstat, fhandle, RC_REPLBUFF, ST+AT),
- PROC(none, void, void, none, RC_NOCACHE, ST),
- PROC(lookup, diropargs, diropres, fhandle, RC_NOCACHE, ST+FH+AT),
- PROC(readlink, readlinkargs, readlinkres, none, RC_NOCACHE, ST+1+NFS_MAXPATHLEN/4),
- PROC(read, readargs, readres, fhandle, RC_NOCACHE, ST+AT+1+NFSSVC_MAXBLKSIZE_V2/4),
- PROC(none, void, void, none, RC_NOCACHE, ST),
- PROC(write, writeargs, attrstat, fhandle, RC_REPLBUFF, ST+AT),
- PROC(create, createargs, diropres, fhandle, RC_REPLBUFF, ST+FH+AT),
- PROC(remove, diropargs, void, none, RC_REPLSTAT, ST),
- PROC(rename, renameargs, void, none, RC_REPLSTAT, ST),
- PROC(link, linkargs, void, none, RC_REPLSTAT, ST),
- PROC(symlink, symlinkargs, void, none, RC_REPLSTAT, ST),
- PROC(mkdir, createargs, diropres, fhandle, RC_REPLBUFF, ST+FH+AT),
- PROC(rmdir, diropargs, void, none, RC_REPLSTAT, ST),
- PROC(readdir, readdirargs, readdirres, none, RC_NOCACHE, 0),
- PROC(statfs, fhandle, statfsres, none, RC_NOCACHE, ST+5),
+ [NFSPROC_NULL] = {
+ .pc_func = (svc_procfunc) nfsd_proc_null,
+ .pc_decode = (kxdrproc_t) nfssvc_decode_void,
+ .pc_encode = (kxdrproc_t) nfssvc_encode_void,
+ .pc_argsize = sizeof(struct nfsd_void),
+ .pc_ressize = sizeof(struct nfsd_void),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = ST,
+ },
+ [NFSPROC_GETATTR] = {
+ .pc_func = (svc_procfunc) nfsd_proc_getattr,
+ .pc_decode = (kxdrproc_t) nfssvc_decode_fhandle,
+ .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
+ .pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+ .pc_argsize = sizeof(struct nfsd_fhandle),
+ .pc_ressize = sizeof(struct nfsd_attrstat),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = ST+AT,
+ },
+ [NFSPROC_SETATTR] = {
+ .pc_func = (svc_procfunc) nfsd_proc_setattr,
+ .pc_decode = (kxdrproc_t) nfssvc_decode_sattrargs,
+ .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
+ .pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+ .pc_argsize = sizeof(struct nfsd_sattrargs),
+ .pc_ressize = sizeof(struct nfsd_attrstat),
+ .pc_cachetype = RC_REPLBUFF,
+ .pc_xdrressize = ST+AT,
+ },
+ [NFSPROC_ROOT] = {
+ .pc_decode = (kxdrproc_t) nfssvc_decode_void,
+ .pc_encode = (kxdrproc_t) nfssvc_encode_void,
+ .pc_argsize = sizeof(struct nfsd_void),
+ .pc_ressize = sizeof(struct nfsd_void),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = ST,
+ },
+ [NFSPROC_LOOKUP] = {
+ .pc_func = (svc_procfunc) nfsd_proc_lookup,
+ .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
+ .pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
+ .pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+ .pc_argsize = sizeof(struct nfsd_diropargs),
+ .pc_ressize = sizeof(struct nfsd_diropres),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = ST+FH+AT,
+ },
+ [NFSPROC_READLINK] = {
+ .pc_func = (svc_procfunc) nfsd_proc_readlink,
+ .pc_decode = (kxdrproc_t) nfssvc_decode_readlinkargs,
+ .pc_encode = (kxdrproc_t) nfssvc_encode_readlinkres,
+ .pc_argsize = sizeof(struct nfsd_readlinkargs),
+ .pc_ressize = sizeof(struct nfsd_readlinkres),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = ST+1+NFS_MAXPATHLEN/4,
+ },
+ [NFSPROC_READ] = {
+ .pc_func = (svc_procfunc) nfsd_proc_read,
+ .pc_decode = (kxdrproc_t) nfssvc_decode_readargs,
+ .pc_encode = (kxdrproc_t) nfssvc_encode_readres,
+ .pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+ .pc_argsize = sizeof(struct nfsd_readargs),
+ .pc_ressize = sizeof(struct nfsd_readres),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = ST+AT+1+NFSSVC_MAXBLKSIZE_V2/4,
+ },
+ [NFSPROC_WRITECACHE] = {
+ .pc_decode = (kxdrproc_t) nfssvc_decode_void,
+ .pc_encode = (kxdrproc_t) nfssvc_encode_void,
+ .pc_argsize = sizeof(struct nfsd_void),
+ .pc_ressize = sizeof(struct nfsd_void),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = ST,
+ },
+ [NFSPROC_WRITE] = {
+ .pc_func = (svc_procfunc) nfsd_proc_write,
+ .pc_decode = (kxdrproc_t) nfssvc_decode_writeargs,
+ .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
+ .pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+ .pc_argsize = sizeof(struct nfsd_writeargs),
+ .pc_ressize = sizeof(struct nfsd_attrstat),
+ .pc_cachetype = RC_REPLBUFF,
+ .pc_xdrressize = ST+AT,
+ },
+ [NFSPROC_CREATE] = {
+ .pc_func = (svc_procfunc) nfsd_proc_create,
+ .pc_decode = (kxdrproc_t) nfssvc_decode_createargs,
+ .pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
+ .pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+ .pc_argsize = sizeof(struct nfsd_createargs),
+ .pc_ressize = sizeof(struct nfsd_diropres),
+ .pc_cachetype = RC_REPLBUFF,
+ .pc_xdrressize = ST+FH+AT,
+ },
+ [NFSPROC_REMOVE] = {
+ .pc_func = (svc_procfunc) nfsd_proc_remove,
+ .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
+ .pc_encode = (kxdrproc_t) nfssvc_encode_void,
+ .pc_argsize = sizeof(struct nfsd_diropargs),
+ .pc_ressize = sizeof(struct nfsd_void),
+ .pc_cachetype = RC_REPLSTAT,
+ .pc_xdrressize = ST,
+ },
+ [NFSPROC_RENAME] = {
+ .pc_func = (svc_procfunc) nfsd_proc_rename,
+ .pc_decode = (kxdrproc_t) nfssvc_decode_renameargs,
+ .pc_encode = (kxdrproc_t) nfssvc_encode_void,
+ .pc_argsize = sizeof(struct nfsd_renameargs),
+ .pc_ressize = sizeof(struct nfsd_void),
+ .pc_cachetype = RC_REPLSTAT,
+ .pc_xdrressize = ST,
+ },
+ [NFSPROC_LINK] = {
+ .pc_func = (svc_procfunc) nfsd_proc_link,
+ .pc_decode = (kxdrproc_t) nfssvc_decode_linkargs,
+ .pc_encode = (kxdrproc_t) nfssvc_encode_void,
+ .pc_argsize = sizeof(struct nfsd_linkargs),
+ .pc_ressize = sizeof(struct nfsd_void),
+ .pc_cachetype = RC_REPLSTAT,
+ .pc_xdrressize = ST,
+ },
+ [NFSPROC_SYMLINK] = {
+ .pc_func = (svc_procfunc) nfsd_proc_symlink,
+ .pc_decode = (kxdrproc_t) nfssvc_decode_symlinkargs,
+ .pc_encode = (kxdrproc_t) nfssvc_encode_void,
+ .pc_argsize = sizeof(struct nfsd_symlinkargs),
+ .pc_ressize = sizeof(struct nfsd_void),
+ .pc_cachetype = RC_REPLSTAT,
+ .pc_xdrressize = ST,
+ },
+ [NFSPROC_MKDIR] = {
+ .pc_func = (svc_procfunc) nfsd_proc_mkdir,
+ .pc_decode = (kxdrproc_t) nfssvc_decode_createargs,
+ .pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
+ .pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+ .pc_argsize = sizeof(struct nfsd_createargs),
+ .pc_ressize = sizeof(struct nfsd_diropres),
+ .pc_cachetype = RC_REPLBUFF,
+ .pc_xdrressize = ST+FH+AT,
+ },
+ [NFSPROC_RMDIR] = {
+ .pc_func = (svc_procfunc) nfsd_proc_rmdir,
+ .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
+ .pc_encode = (kxdrproc_t) nfssvc_encode_void,
+ .pc_argsize = sizeof(struct nfsd_diropargs),
+ .pc_ressize = sizeof(struct nfsd_void),
+ .pc_cachetype = RC_REPLSTAT,
+ .pc_xdrressize = ST,
+ },
+ [NFSPROC_READDIR] = {
+ .pc_func = (svc_procfunc) nfsd_proc_readdir,
+ .pc_decode = (kxdrproc_t) nfssvc_decode_readdirargs,
+ .pc_encode = (kxdrproc_t) nfssvc_encode_readdirres,
+ .pc_argsize = sizeof(struct nfsd_readdirargs),
+ .pc_ressize = sizeof(struct nfsd_readdirres),
+ .pc_cachetype = RC_NOCACHE,
+ },
+ [NFSPROC_STATFS] = {
+ .pc_func = (svc_procfunc) nfsd_proc_statfs,
+ .pc_decode = (kxdrproc_t) nfssvc_decode_fhandle,
+ .pc_encode = (kxdrproc_t) nfssvc_encode_statfsres,
+ .pc_argsize = sizeof(struct nfsd_fhandle),
+ .pc_ressize = sizeof(struct nfsd_statfsres),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = ST+5,
+ },
};
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index cbba4a93578..d4c9884cd54 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -390,12 +390,14 @@ nfsd_svc(unsigned short port, int nrservs)
mutex_lock(&nfsd_mutex);
dprintk("nfsd: creating service\n");
- error = -EINVAL;
if (nrservs <= 0)
nrservs = 0;
if (nrservs > NFSD_MAXSERVS)
nrservs = NFSD_MAXSERVS;
-
+ error = 0;
+ if (nrservs == 0 && nfsd_serv == NULL)
+ goto out;
+
/* Readahead param cache - will no-op if it already exists */
error = nfsd_racache_init(2*nrservs);
if (error<0)
@@ -413,6 +415,12 @@ nfsd_svc(unsigned short port, int nrservs)
goto failure;
error = svc_set_num_threads(nfsd_serv, NULL, nrservs);
+ if (error == 0)
+ /* We are holding a reference to nfsd_serv which
+ * we don't want to count in the return value,
+ * so subtract 1
+ */
+ error = nfsd_serv->sv_nrthreads - 1;
failure:
svc_destroy(nfsd_serv); /* Release server */
out:
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 99f83575359..4145083dcf8 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -966,6 +966,43 @@ static void kill_suid(struct dentry *dentry)
mutex_unlock(&dentry->d_inode->i_mutex);
}
+/*
+ * Gathered writes: If another process is currently writing to the file,
+ * there's a high chance this is another nfsd (triggered by a bulk write
+ * from a client's biod). Rather than syncing the file with each write
+ * request, we sleep for 10 msec.
+ *
+ * I don't know if this roughly approximates C. Juszak's idea of
+ * gathered writes, but it's a nice and simple solution (IMHO), and it
+ * seems to work:-)
+ *
+ * Note: we do this only in the NFSv2 case, since v3 and higher have a
+ * better tool (separate unstable writes and commits) for solving this
+ * problem.
+ */
+static int wait_for_concurrent_writes(struct file *file)
+{
+ struct inode *inode = file->f_path.dentry->d_inode;
+ static ino_t last_ino;
+ static dev_t last_dev;
+ int err = 0;
+
+ if (atomic_read(&inode->i_writecount) > 1
+ || (last_ino == inode->i_ino && last_dev == inode->i_sb->s_dev)) {
+ dprintk("nfsd: write defer %d\n", task_pid_nr(current));
+ msleep(10);
+ dprintk("nfsd: write resume %d\n", task_pid_nr(current));
+ }
+
+ if (inode->i_state & I_DIRTY) {
+ dprintk("nfsd: write sync %d\n", task_pid_nr(current));
+ err = nfsd_sync(file);
+ }
+ last_ino = inode->i_ino;
+ last_dev = inode->i_sb->s_dev;
+ return err;
+}
+
static __be32
nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
loff_t offset, struct kvec *vec, int vlen,
@@ -978,6 +1015,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
__be32 err = 0;
int host_err;
int stable = *stablep;
+ int use_wgather;
#ifdef MSNFS
err = nfserr_perm;
@@ -996,9 +1034,10 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
* - the sync export option has been set, or
* - the client requested O_SYNC behavior (NFSv3 feature).
* - The file system doesn't support fsync().
- * When gathered writes have been configured for this volume,
+ * When NFSv2 gathered writes have been configured for this volume,
* flushing the data to disk is handled separately below.
*/
+ use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp);
if (!file->f_op->fsync) {/* COMMIT3 cannot work */
stable = 2;
@@ -1007,7 +1046,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
if (!EX_ISSYNC(exp))
stable = 0;
- if (stable && !EX_WGATHER(exp)) {
+ if (stable && !use_wgather) {
spin_lock(&file->f_lock);
file->f_flags |= O_SYNC;
spin_unlock(&file->f_lock);
@@ -1017,52 +1056,20 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
oldfs = get_fs(); set_fs(KERNEL_DS);
host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &offset);
set_fs(oldfs);
- if (host_err >= 0) {
- *cnt = host_err;
- nfsdstats.io_write += host_err;
- fsnotify_modify(file->f_path.dentry);
- }
+ if (host_err < 0)
+ goto out_nfserr;
+ *cnt = host_err;
+ nfsdstats.io_write += host_err;
+ fsnotify_modify(file->f_path.dentry);
/* clear setuid/setgid flag after write */
- if (host_err >= 0 && (inode->i_mode & (S_ISUID | S_ISGID)))
+ if (inode->i_mode & (S_ISUID | S_ISGID))
kill_suid(dentry);
- if (host_err >= 0 && stable) {
- static ino_t last_ino;
- static dev_t last_dev;
-
- /*
- * Gathered writes: If another process is currently
- * writing to the file, there's a high chance
- * this is another nfsd (triggered by a bulk write
- * from a client's biod). Rather than syncing the
- * file with each write request, we sleep for 10 msec.
- *
- * I don't know if this roughly approximates
- * C. Juszak's idea of gathered writes, but it's a
- * nice and simple solution (IMHO), and it seems to
- * work:-)
- */
- if (EX_WGATHER(exp)) {
- if (atomic_read(&inode->i_writecount) > 1
- || (last_ino == inode->i_ino && last_dev == inode->i_sb->s_dev)) {
- dprintk("nfsd: write defer %d\n", task_pid_nr(current));
- msleep(10);
- dprintk("nfsd: write resume %d\n", task_pid_nr(current));
- }
-
- if (inode->i_state & I_DIRTY) {
- dprintk("nfsd: write sync %d\n", task_pid_nr(current));
- host_err=nfsd_sync(file);
- }
-#if 0
- wake_up(&inode->i_wait);
-#endif
- }
- last_ino = inode->i_ino;
- last_dev = inode->i_sb->s_dev;
- }
+ if (stable && use_wgather)
+ host_err = wait_for_concurrent_writes(file);
+out_nfserr:
dprintk("nfsd: write complete host_err=%d\n", host_err);
if (host_err >= 0)
err = 0;