aboutsummaryrefslogtreecommitdiff
path: root/fs/nfsd
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfsd')
-rw-r--r--fs/nfsd/Kconfig16
-rw-r--r--fs/nfsd/auth.c4
-rw-r--r--fs/nfsd/cache.h4
-rw-r--r--fs/nfsd/filecache.c6
-rw-r--r--fs/nfsd/netns.h11
-rw-r--r--fs/nfsd/nfs4callback.c123
-rw-r--r--fs/nfsd/nfs4proc.c7
-rw-r--r--fs/nfsd/nfs4recover.c97
-rw-r--r--fs/nfsd/nfs4state.c118
-rw-r--r--fs/nfsd/nfs4xdr.c20
-rw-r--r--fs/nfsd/nfscache.c93
-rw-r--r--fs/nfsd/nfsctl.c43
-rw-r--r--fs/nfsd/nfsd.h8
-rw-r--r--fs/nfsd/nfssvc.c84
-rw-r--r--fs/nfsd/state.h25
-rw-r--r--fs/nfsd/trace.h22
-rw-r--r--fs/nfsd/vfs.c66
-rw-r--r--fs/nfsd/vfs.h1
-rw-r--r--fs/nfsd/xdr4.h1
-rw-r--r--fs/nfsd/xdr4cb.h18
20 files changed, 276 insertions, 491 deletions
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 43b88eaf0673..272ab8d5c4d7 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -158,3 +158,19 @@ config NFSD_V4_SECURITY_LABEL
If you do not wish to enable fine-grained security labels SELinux or
Smack policies on NFSv4 files, say N.
+
+config NFSD_LEGACY_CLIENT_TRACKING
+ bool "Support legacy NFSv4 client tracking methods (DEPRECATED)"
+ depends on NFSD_V4
+ default n
+ help
+ The NFSv4 server needs to store a small amount of information on
+ stable storage in order to handle state recovery after reboot. Most
+ modern deployments upcall to a userland daemon for this (nfsdcld),
+ but older NFS servers may store information directly in a
+ recoverydir, or spawn a process directly using a usermodehelper
+ upcall.
+
+ These legacy client tracking methods have proven to be probelmatic
+ and will be removed in the future. Say Y here if you need support
+ for them in the interim.
diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c
index fdf2aad73470..e6beaaf4f170 100644
--- a/fs/nfsd/auth.c
+++ b/fs/nfsd/auth.c
@@ -26,8 +26,6 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
int i;
int flags = nfsexp_flags(rqstp, exp);
- validate_process_creds();
-
/* discard any old override before preparing the new set */
revert_creds(get_cred(current_real_cred()));
new = prepare_creds();
@@ -81,10 +79,8 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
else
new->cap_effective = cap_raise_nfsd_set(new->cap_effective,
new->cap_permitted);
- validate_process_creds();
put_cred(override_creds(new));
put_cred(new);
- validate_process_creds();
return 0;
oom:
diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h
index 929248c6ca84..4cbe0434cbb8 100644
--- a/fs/nfsd/cache.h
+++ b/fs/nfsd/cache.h
@@ -84,8 +84,8 @@ int nfsd_net_reply_cache_init(struct nfsd_net *nn);
void nfsd_net_reply_cache_destroy(struct nfsd_net *nn);
int nfsd_reply_cache_init(struct nfsd_net *);
void nfsd_reply_cache_shutdown(struct nfsd_net *);
-int nfsd_cache_lookup(struct svc_rqst *rqstp,
- struct nfsd_cacherep **cacherep);
+int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start,
+ unsigned int len, struct nfsd_cacherep **cacherep);
void nfsd_cache_update(struct svc_rqst *rqstp, struct nfsd_cacherep *rp,
int cachetype, __be32 *statp);
int nfsd_reply_cache_stats_show(struct seq_file *m, void *v);
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index ef063f93fde9..9cb7f0c33df5 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -322,7 +322,7 @@ nfsd_file_check_writeback(struct nfsd_file *nf)
static bool nfsd_file_lru_add(struct nfsd_file *nf)
{
set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags);
- if (list_lru_add(&nfsd_file_lru, &nf->nf_lru)) {
+ if (list_lru_add_obj(&nfsd_file_lru, &nf->nf_lru)) {
trace_nfsd_file_lru_add(nf);
return true;
}
@@ -331,7 +331,7 @@ static bool nfsd_file_lru_add(struct nfsd_file *nf)
static bool nfsd_file_lru_remove(struct nfsd_file *nf)
{
- if (list_lru_del(&nfsd_file_lru, &nf->nf_lru)) {
+ if (list_lru_del_obj(&nfsd_file_lru, &nf->nf_lru)) {
trace_nfsd_file_lru_del(nf);
return true;
}
@@ -717,7 +717,7 @@ nfsd_file_cache_init(void)
return ret;
ret = -ENOMEM;
- nfsd_filecache_wq = alloc_workqueue("nfsd_filecache", 0, 0);
+ nfsd_filecache_wq = alloc_workqueue("nfsd_filecache", WQ_UNBOUND, 0);
if (!nfsd_filecache_wq)
goto out;
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index ab303a8b77d5..74b4360779a1 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -123,14 +123,9 @@ struct nfsd_net {
u32 clientid_counter;
u32 clverifier_counter;
- struct svc_serv *nfsd_serv;
- /* When a listening socket is added to nfsd, keep_active is set
- * and this justifies a reference on nfsd_serv. This stops
- * nfsd_serv from being freed. When the number of threads is
- * set, keep_active is cleared and the reference is dropped. So
- * when the last thread exits, the service will be destroyed.
- */
- int keep_active;
+ struct svc_info nfsd_info;
+#define nfsd_serv nfsd_info.serv
+
/*
* clientid and stateid data for construction of net unique COPY
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 92bc109dabe6..926c29879c6a 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -31,6 +31,7 @@
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
+#include <linux/nfs4.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/xprt.h>
#include <linux/sunrpc/svc_xprt.h>
@@ -84,48 +85,9 @@ static void encode_uint32(struct xdr_stream *xdr, u32 n)
static void encode_bitmap4(struct xdr_stream *xdr, const __u32 *bitmap,
size_t len)
{
- xdr_stream_encode_uint32_array(xdr, bitmap, len);
+ WARN_ON_ONCE(xdr_stream_encode_uint32_array(xdr, bitmap, len) < 0);
}
-static int decode_cb_fattr4(struct xdr_stream *xdr, uint32_t *bitmap,
- struct nfs4_cb_fattr *fattr)
-{
- fattr->ncf_cb_change = 0;
- fattr->ncf_cb_fsize = 0;
- if (bitmap[0] & FATTR4_WORD0_CHANGE)
- if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_change) < 0)
- return -NFSERR_BAD_XDR;
- if (bitmap[0] & FATTR4_WORD0_SIZE)
- if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_fsize) < 0)
- return -NFSERR_BAD_XDR;
- return 0;
-}
-
-/*
- * nfs_cb_opnum4
- *
- * enum nfs_cb_opnum4 {
- * OP_CB_GETATTR = 3,
- * ...
- * };
- */
-enum nfs_cb_opnum4 {
- OP_CB_GETATTR = 3,
- OP_CB_RECALL = 4,
- OP_CB_LAYOUTRECALL = 5,
- OP_CB_NOTIFY = 6,
- OP_CB_PUSH_DELEG = 7,
- OP_CB_RECALL_ANY = 8,
- OP_CB_RECALLABLE_OBJ_AVAIL = 9,
- OP_CB_RECALL_SLOT = 10,
- OP_CB_SEQUENCE = 11,
- OP_CB_WANTS_CANCELLED = 12,
- OP_CB_NOTIFY_LOCK = 13,
- OP_CB_NOTIFY_DEVICEID = 14,
- OP_CB_OFFLOAD = 15,
- OP_CB_ILLEGAL = 10044
-};
-
static void encode_nfs_cb_opnum4(struct xdr_stream *xdr, enum nfs_cb_opnum4 op)
{
__be32 *p;
@@ -372,30 +334,6 @@ encode_cb_recallany4args(struct xdr_stream *xdr,
}
/*
- * CB_GETATTR4args
- * struct CB_GETATTR4args {
- * nfs_fh4 fh;
- * bitmap4 attr_request;
- * };
- *
- * The size and change attributes are the only one
- * guaranteed to be serviced by the client.
- */
-static void
-encode_cb_getattr4args(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr,
- struct nfs4_cb_fattr *fattr)
-{
- struct nfs4_delegation *dp =
- container_of(fattr, struct nfs4_delegation, dl_cb_fattr);
- struct knfsd_fh *fh = &dp->dl_stid.sc_file->fi_fhandle;
-
- encode_nfs_cb_opnum4(xdr, OP_CB_GETATTR);
- encode_nfs_fh4(xdr, fh);
- encode_bitmap4(xdr, fattr->ncf_cb_bmap, ARRAY_SIZE(fattr->ncf_cb_bmap));
- hdr->nops++;
-}
-
-/*
* CB_SEQUENCE4args
*
* struct CB_SEQUENCE4args {
@@ -531,26 +469,6 @@ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr,
}
/*
- * 20.1. Operation 3: CB_GETATTR - Get Attributes
- */
-static void nfs4_xdr_enc_cb_getattr(struct rpc_rqst *req,
- struct xdr_stream *xdr, const void *data)
-{
- const struct nfsd4_callback *cb = data;
- struct nfs4_cb_fattr *ncf =
- container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
- struct nfs4_cb_compound_hdr hdr = {
- .ident = cb->cb_clp->cl_cb_ident,
- .minorversion = cb->cb_clp->cl_minorversion,
- };
-
- encode_cb_compound4args(xdr, &hdr);
- encode_cb_sequence4args(xdr, cb, &hdr);
- encode_cb_getattr4args(xdr, &hdr, ncf);
- encode_cb_nops(&hdr);
-}
-
-/*
* 20.2. Operation 4: CB_RECALL - Recall a Delegation
*/
static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr,
@@ -606,42 +524,6 @@ static int nfs4_xdr_dec_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr,
}
/*
- * 20.1. Operation 3: CB_GETATTR - Get Attributes
- */
-static int nfs4_xdr_dec_cb_getattr(struct rpc_rqst *rqstp,
- struct xdr_stream *xdr,
- void *data)
-{
- struct nfsd4_callback *cb = data;
- struct nfs4_cb_compound_hdr hdr;
- int status;
- u32 bitmap[3] = {0};
- u32 attrlen;
- struct nfs4_cb_fattr *ncf =
- container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
-
- status = decode_cb_compound4res(xdr, &hdr);
- if (unlikely(status))
- return status;
-
- status = decode_cb_sequence4res(xdr, cb);
- if (unlikely(status || cb->cb_seq_status))
- return status;
-
- status = decode_cb_op_status(xdr, OP_CB_GETATTR, &cb->cb_status);
- if (status)
- return status;
- if (xdr_stream_decode_uint32_array(xdr, bitmap, 3) < 0)
- return -NFSERR_BAD_XDR;
- if (xdr_stream_decode_u32(xdr, &attrlen) < 0)
- return -NFSERR_BAD_XDR;
- if (attrlen > (sizeof(ncf->ncf_cb_change) + sizeof(ncf->ncf_cb_fsize)))
- return -NFSERR_BAD_XDR;
- status = decode_cb_fattr4(xdr, bitmap, ncf);
- return status;
-}
-
-/*
* 20.2. Operation 4: CB_RECALL - Recall a Delegation
*/
static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp,
@@ -949,7 +831,6 @@ static const struct rpc_procinfo nfs4_cb_procedures[] = {
PROC(CB_NOTIFY_LOCK, COMPOUND, cb_notify_lock, cb_notify_lock),
PROC(CB_OFFLOAD, COMPOUND, cb_offload, cb_offload),
PROC(CB_RECALL_ANY, COMPOUND, cb_recall_any, cb_recall_any),
- PROC(CB_GETATTR, COMPOUND, cb_getattr, cb_getattr),
};
static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)];
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 6f2d4aa4970d..14712fa08f76 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -970,8 +970,11 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
* To ensure proper ordering, we therefore turn off zero copy if
* the client wants us to do more in this compound:
*/
- if (!nfsd4_last_compound_op(rqstp))
- clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+ if (!nfsd4_last_compound_op(rqstp)) {
+ struct nfsd4_compoundargs *argp = rqstp->rq_argp;
+
+ argp->splice_ok = false;
+ }
/* check stateid */
status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 3509e73abe1f..2c060e0b1604 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -66,6 +66,7 @@ struct nfsd4_client_tracking_ops {
static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops;
static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops_v2;
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
/* Globals */
static char user_recovery_dirname[PATH_MAX] = "/var/lib/nfs/v4recovery";
@@ -720,6 +721,7 @@ static const struct nfsd4_client_tracking_ops nfsd4_legacy_tracking_ops = {
.version = 1,
.msglen = 0,
};
+#endif /* CONFIG_NFSD_LEGACY_CLIENT_TRACKING */
/* Globals */
#define NFSD_PIPE_DIR "nfsd"
@@ -731,8 +733,10 @@ struct cld_net {
spinlock_t cn_lock;
struct list_head cn_list;
unsigned int cn_xid;
- bool cn_has_legacy;
struct crypto_shash *cn_tfm;
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
+ bool cn_has_legacy;
+#endif
};
struct cld_upcall {
@@ -793,7 +797,6 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg,
uint8_t cmd, princhashlen;
struct xdr_netobj name, princhash = { .len = 0, .data = NULL };
uint16_t namelen;
- struct cld_net *cn = nn->cld_net;
if (get_user(cmd, &cmsg->cm_cmd)) {
dprintk("%s: error when copying cmd from userspace", __func__);
@@ -833,11 +836,15 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg,
return PTR_ERR(name.data);
name.len = namelen;
}
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
if (name.len > 5 && memcmp(name.data, "hash:", 5) == 0) {
+ struct cld_net *cn = nn->cld_net;
+
name.len = name.len - 5;
memmove(name.data, name.data + 5, name.len);
cn->cn_has_legacy = true;
}
+#endif
if (!nfs4_client_to_reclaim(name, princhash, nn)) {
kfree(name.data);
kfree(princhash.data);
@@ -1010,7 +1017,9 @@ __nfsd4_init_cld_pipe(struct net *net)
}
cn->cn_pipe->dentry = dentry;
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
cn->cn_has_legacy = false;
+#endif
nn->cld_net = cn;
return 0;
@@ -1282,10 +1291,6 @@ nfsd4_cld_check(struct nfs4_client *clp)
{
struct nfs4_client_reclaim *crp;
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
- struct cld_net *cn = nn->cld_net;
- int status;
- char dname[HEXDIR_LEN];
- struct xdr_netobj name;
/* did we already find that this client is stable? */
if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
@@ -1296,7 +1301,12 @@ nfsd4_cld_check(struct nfs4_client *clp)
if (crp)
goto found;
- if (cn->cn_has_legacy) {
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
+ if (nn->cld_net->cn_has_legacy) {
+ int status;
+ char dname[HEXDIR_LEN];
+ struct xdr_netobj name;
+
status = nfs4_make_rec_clidname(dname, &clp->cl_name);
if (status)
return -ENOENT;
@@ -1314,6 +1324,7 @@ nfsd4_cld_check(struct nfs4_client *clp)
goto found;
}
+#endif
return -ENOENT;
found:
crp->cr_clp = clp;
@@ -1327,8 +1338,6 @@ nfsd4_cld_check_v2(struct nfs4_client *clp)
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
struct cld_net *cn = nn->cld_net;
int status;
- char dname[HEXDIR_LEN];
- struct xdr_netobj name;
struct crypto_shash *tfm = cn->cn_tfm;
struct xdr_netobj cksum;
char *principal = NULL;
@@ -1342,7 +1351,11 @@ nfsd4_cld_check_v2(struct nfs4_client *clp)
if (crp)
goto found;
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
if (cn->cn_has_legacy) {
+ struct xdr_netobj name;
+ char dname[HEXDIR_LEN];
+
status = nfs4_make_rec_clidname(dname, &clp->cl_name);
if (status)
return -ENOENT;
@@ -1360,6 +1373,7 @@ nfsd4_cld_check_v2(struct nfs4_client *clp)
goto found;
}
+#endif
return -ENOENT;
found:
if (crp->cr_princhash.len) {
@@ -1663,6 +1677,7 @@ static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops_v2 = {
.msglen = sizeof(struct cld_msg_v2),
};
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
/* upcall via usermodehelper */
static char cltrack_prog[PATH_MAX] = "/sbin/nfsdcltrack";
module_param_string(cltrack_prog, cltrack_prog, sizeof(cltrack_prog),
@@ -2007,28 +2022,10 @@ static const struct nfsd4_client_tracking_ops nfsd4_umh_tracking_ops = {
.msglen = 0,
};
-int
-nfsd4_client_tracking_init(struct net *net)
+static inline int check_for_legacy_methods(int status, struct net *net)
{
- int status;
- struct path path;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
-
- /* just run the init if it the method is already decided */
- if (nn->client_tracking_ops)
- goto do_init;
-
- /* First, try to use nfsdcld */
- nn->client_tracking_ops = &nfsd4_cld_tracking_ops;
- status = nn->client_tracking_ops->init(net);
- if (!status)
- return status;
- if (status != -ETIMEDOUT) {
- nn->client_tracking_ops = &nfsd4_cld_tracking_ops_v0;
- status = nn->client_tracking_ops->init(net);
- if (!status)
- return status;
- }
+ struct path path;
/*
* Next, try the UMH upcall.
@@ -2045,14 +2042,46 @@ nfsd4_client_tracking_init(struct net *net)
nn->client_tracking_ops = &nfsd4_legacy_tracking_ops;
status = kern_path(nfs4_recoverydir(), LOOKUP_FOLLOW, &path);
if (!status) {
- status = d_is_dir(path.dentry);
+ status = !d_is_dir(path.dentry);
path_put(&path);
- if (!status) {
- status = -EINVAL;
- goto out;
- }
+ if (status)
+ return -ENOTDIR;
+ status = nn->client_tracking_ops->init(net);
+ }
+ return status;
+}
+#else
+static inline int check_for_legacy_methods(int status, struct net *net)
+{
+ return status;
+}
+#endif /* CONFIG_LEGACY_NFSD_CLIENT_TRACKING */
+
+int
+nfsd4_client_tracking_init(struct net *net)
+{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ int status;
+
+ /* just run the init if it the method is already decided */
+ if (nn->client_tracking_ops)
+ goto do_init;
+
+ /* First, try to use nfsdcld */
+ nn->client_tracking_ops = &nfsd4_cld_tracking_ops;
+ status = nn->client_tracking_ops->init(net);
+ if (!status)
+ return status;
+ if (status != -ETIMEDOUT) {
+ nn->client_tracking_ops = &nfsd4_cld_tracking_ops_v0;
+ status = nn->client_tracking_ops->init(net);
+ if (!status)
+ return status;
}
+ status = check_for_legacy_methods(status, net);
+ if (status)
+ goto out;
do_init:
status = nn->client_tracking_ops->init(net);
out:
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 4045c852a450..2fa54cfd4882 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -127,7 +127,6 @@ static void free_session(struct nfsd4_session *);
static const struct nfsd4_callback_ops nfsd4_cb_recall_ops;
static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops;
-static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops;
static struct workqueue_struct *laundry_wq;
@@ -1190,10 +1189,6 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
dp->dl_recalled = false;
nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client,
&nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL);
- nfsd4_init_cb(&dp->dl_cb_fattr.ncf_getattr, dp->dl_stid.sc_client,
- &nfsd4_cb_getattr_ops, NFSPROC4_CLNT_CB_GETATTR);
- dp->dl_cb_fattr.ncf_file_modified = false;
- dp->dl_cb_fattr.ncf_cb_bmap[0] = FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE;
get_nfs4_file(fp);
dp->dl_stid.sc_file = fp;
return dp;
@@ -2804,7 +2799,7 @@ static int client_opens_release(struct inode *inode, struct file *file)
/* XXX: alternatively, we could get/drop in seq start/stop */
drop_client(clp);
- return 0;
+ return seq_release(inode, file);
}
static const struct file_operations client_states_fops = {
@@ -2901,56 +2896,11 @@ nfsd4_cb_recall_any_release(struct nfsd4_callback *cb)
spin_unlock(&nn->client_lock);
}
-static int
-nfsd4_cb_getattr_done(struct nfsd4_callback *cb, struct rpc_task *task)
-{
- struct nfs4_cb_fattr *ncf =
- container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
-
- ncf->ncf_cb_status = task->tk_status;
- switch (task->tk_status) {
- case -NFS4ERR_DELAY:
- rpc_delay(task, 2 * HZ);
- return 0;
- default:
- return 1;
- }
-}
-
-static void
-nfsd4_cb_getattr_release(struct nfsd4_callback *cb)
-{
- struct nfs4_cb_fattr *ncf =
- container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
- struct nfs4_delegation *dp =
- container_of(ncf, struct nfs4_delegation, dl_cb_fattr);
-
- nfs4_put_stid(&dp->dl_stid);
- clear_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags);
- wake_up_bit(&ncf->ncf_cb_flags, CB_GETATTR_BUSY);
-}
-
static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = {
.done = nfsd4_cb_recall_any_done,
.release = nfsd4_cb_recall_any_release,
};
-static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops = {
- .done = nfsd4_cb_getattr_done,
- .release = nfsd4_cb_getattr_release,
-};
-
-void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf)
-{
- struct nfs4_delegation *dp =
- container_of(ncf, struct nfs4_delegation, dl_cb_fattr);
-
- if (test_and_set_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags))
- return;
- refcount_inc(&dp->dl_stid.sc_count);
- nfsd4_run_cb(&ncf->ncf_getattr);
-}
-
static struct nfs4_client *create_client(struct xdr_netobj name,
struct svc_rqst *rqstp, nfs4_verifier *verf)
{
@@ -5685,8 +5635,6 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
struct svc_fh *parent = NULL;
int cb_up;
int status = 0;
- struct kstat stat;
- struct path path;
cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client);
open->op_recall = false;
@@ -5724,18 +5672,6 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) {
open->op_delegate_type = NFS4_OPEN_DELEGATE_WRITE;
trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid);
- path.mnt = currentfh->fh_export->ex_path.mnt;
- path.dentry = currentfh->fh_dentry;
- if (vfs_getattr(&path, &stat,
- (STATX_SIZE | STATX_CTIME | STATX_CHANGE_COOKIE),
- AT_STATX_SYNC_AS_STAT)) {
- nfs4_put_stid(&dp->dl_stid);
- destroy_delegation(dp);
- goto out_no_deleg;
- }
- dp->dl_cb_fattr.ncf_cur_fsize = stat.size;
- dp->dl_cb_fattr.ncf_initial_cinfo =
- nfsd4_change_attribute(&stat, d_inode(currentfh->fh_dentry));
} else {
open->op_delegate_type = NFS4_OPEN_DELEGATE_READ;
trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid);
@@ -6639,7 +6575,7 @@ unlock:
spin_unlock(&nn->s2s_cp_lock);
if (!state)
return nfserr_bad_stateid;
- if (!clp && state)
+ if (!clp)
*cps = state;
return 0;
}
@@ -8492,8 +8428,6 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate,
* nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict
* @rqstp: RPC transaction context
* @inode: file to be checked for a conflict
- * @modified: return true if file was modified
- * @size: new size of file if modified is true
*
* This function is called when there is a conflict between a write
* delegation and a change/size GETATTR from another client. The server
@@ -8502,23 +8436,21 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate,
* delegation before replying to the GETATTR. See RFC 8881 section
* 18.7.4.
*
+ * The current implementation does not support CB_GETATTR yet. However
+ * this can avoid recalling the delegation could be added in follow up
+ * work.
+ *
* Returns 0 if there is no conflict; otherwise an nfs_stat
* code is returned.
*/
__be32
-nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode,
- bool *modified, u64 *size)
+nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode)
{
+ __be32 status;
struct file_lock_context *ctx;
- struct nfs4_delegation *dp;
- struct nfs4_cb_fattr *ncf;
struct file_lock *fl;
- struct iattr attrs;
- __be32 status;
-
- might_sleep();
+ struct nfs4_delegation *dp;
- *modified = false;
ctx = locks_inode_context(inode);
if (!ctx)
return 0;
@@ -8545,34 +8477,10 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode,
break_lease:
spin_unlock(&ctx->flc_lock);
nfsd_stats_wdeleg_getattr_inc();
-
- dp = fl->fl_owner;
- ncf = &dp->dl_cb_fattr;
- nfs4_cb_getattr(&dp->dl_cb_fattr);
- wait_on_bit(&ncf->ncf_cb_flags, CB_GETATTR_BUSY, TASK_INTERRUPTIBLE);
- if (ncf->ncf_cb_status) {
- status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
- if (status != nfserr_jukebox ||
- !nfsd_wait_for_delegreturn(rqstp, inode))
- return status;
- }
- if (!ncf->ncf_file_modified &&
- (ncf->ncf_initial_cinfo != ncf->ncf_cb_change ||
- ncf->ncf_cur_fsize != ncf->ncf_cb_fsize))
- ncf->ncf_file_modified = true;
- if (ncf->ncf_file_modified) {
- /*
- * The server would not update the file's metadata
- * with the client's modified size.
- */
- attrs.ia_mtime = attrs.ia_ctime = current_time(inode);
- attrs.ia_valid = ATTR_MTIME | ATTR_CTIME;
- setattr_copy(&nop_mnt_idmap, inode, &attrs);
- mark_inode_dirty(inode);
- ncf->ncf_cur_fsize = ncf->ncf_cb_fsize;
- *size = ncf->ncf_cur_fsize;
- *modified = true;
- }
+ status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
+ if (status != nfserr_jukebox ||
+ !nfsd_wait_for_delegreturn(rqstp, inode))
+ return status;
return 0;
}
break;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index ec4ed6206df1..c719c475a068 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2524,8 +2524,9 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
svc_reserve(argp->rqstp, max_reply + readbytes);
argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE;
+ argp->splice_ok = nfsd_read_splice_ok(argp->rqstp);
if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack)
- clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags);
+ argp->splice_ok = false;
return true;
}
@@ -3505,9 +3506,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
u32 attrmask[3];
unsigned long mask[2];
} u;
- bool file_modified;
unsigned long bit;
- u64 size = 0;
WARN_ON_ONCE(bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1);
WARN_ON_ONCE(!nfsd_attrs_supported(minorversion, bmval));
@@ -3534,8 +3533,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
}
args.size = 0;
if (u.attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) {
- status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry),
- &file_modified, &size);
+ status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry));
if (status)
goto out;
}
@@ -3545,7 +3543,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
AT_STATX_SYNC_AS_STAT);
if (err)
goto out_nfserr;
- args.size = file_modified ? size : args.stat.size;
+ args.size = args.stat.size;
if (!(args.stat.result_mask & STATX_BTIME))
/* underlying FS does not offer btime so we can't share it */
@@ -4378,12 +4376,13 @@ static __be32
nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
union nfsd4_op_u *u)
{
+ struct nfsd4_compoundargs *argp = resp->rqstp->rq_argp;
struct nfsd4_read *read = &u->read;
- bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags);
- unsigned long maxcount;
struct xdr_stream *xdr = resp->xdr;
- struct file *file;
int starting_len = xdr->buf->len;
+ bool splice_ok = argp->splice_ok;
+ unsigned long maxcount;
+ struct file *file;
__be32 *p;
if (nfserr)
@@ -5204,9 +5203,10 @@ static __be32
nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp,
struct nfsd4_read *read)
{
- bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags);
+ struct nfsd4_compoundargs *argp = resp->rqstp->rq_argp;
struct file *file = read->rd_nf->nf_file;
struct xdr_stream *xdr = resp->xdr;
+ bool splice_ok = argp->splice_ok;
unsigned long maxcount;
__be32 nfserr, *p;
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index fd56a52aa5fb..5c1a4a0aa605 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -364,38 +364,55 @@ nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
if (freed > sc->nr_to_scan)
break;
}
-
- trace_nfsd_drc_gc(nn, freed);
return freed;
}
-/*
- * Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes
+/**
+ * nfsd_cache_csum - Checksum incoming NFS Call arguments
+ * @buf: buffer containing a whole RPC Call message
+ * @start: starting byte of the NFS Call header
+ * @remaining: size of the NFS Call header, in bytes
+ *
+ * Compute a weak checksum of the leading bytes of an NFS procedure
+ * call header to help verify that a retransmitted Call matches an
+ * entry in the duplicate reply cache.
+ *
+ * To avoid assumptions about how the RPC message is laid out in
+ * @buf and what else it might contain (eg, a GSS MIC suffix), the
+ * caller passes us the exact location and length of the NFS Call
+ * header.
+ *
+ * Returns a 32-bit checksum value, as defined in RFC 793.
*/
-static __wsum
-nfsd_cache_csum(struct svc_rqst *rqstp)
+static __wsum nfsd_cache_csum(struct xdr_buf *buf, unsigned int start,
+ unsigned int remaining)
{
+ unsigned int base, len;
+ struct xdr_buf subbuf;
+ __wsum csum = 0;
+ void *p;
int idx;
- unsigned int base;
- __wsum csum;
- struct xdr_buf *buf = &rqstp->rq_arg;
- const unsigned char *p = buf->head[0].iov_base;
- size_t csum_len = min_t(size_t, buf->head[0].iov_len + buf->page_len,
- RC_CSUMLEN);
- size_t len = min(buf->head[0].iov_len, csum_len);
+
+ if (remaining > RC_CSUMLEN)
+ remaining = RC_CSUMLEN;
+ if (xdr_buf_subsegment(buf, &subbuf, start, remaining))
+ return csum;
/* rq_arg.head first */
- csum = csum_partial(p, len, 0);
- csum_len -= len;
+ if (subbuf.head[0].iov_len) {
+ len = min_t(unsigned int, subbuf.head[0].iov_len, remaining);
+ csum = csum_partial(subbuf.head[0].iov_base, len, csum);
+ remaining -= len;
+ }
/* Continue into page array */
- idx = buf->page_base / PAGE_SIZE;
- base = buf->page_base & ~PAGE_MASK;
- while (csum_len) {
- p = page_address(buf->pages[idx]) + base;
- len = min_t(size_t, PAGE_SIZE - base, csum_len);
+ idx = subbuf.page_base / PAGE_SIZE;
+ base = subbuf.page_base & ~PAGE_MASK;
+ while (remaining) {
+ p = page_address(subbuf.pages[idx]) + base;
+ len = min_t(unsigned int, PAGE_SIZE - base, remaining);
csum = csum_partial(p, len, csum);
- csum_len -= len;
+ remaining -= len;
base = 0;
++idx;
}
@@ -466,6 +483,8 @@ out:
/**
* nfsd_cache_lookup - Find an entry in the duplicate reply cache
* @rqstp: Incoming Call to find
+ * @start: starting byte in @rqstp->rq_arg of the NFS Call header
+ * @len: size of the NFS Call header, in bytes
* @cacherep: OUT: DRC entry for this request
*
* Try to find an entry matching the current call in the cache. When none
@@ -479,14 +498,14 @@ out:
* %RC_REPLY: Reply from cache
* %RC_DROPIT: Do not process the request further
*/
-int nfsd_cache_lookup(struct svc_rqst *rqstp, struct nfsd_cacherep **cacherep)
+int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start,
+ unsigned int len, struct nfsd_cacherep **cacherep)
{
struct nfsd_net *nn;
struct nfsd_cacherep *rp, *found;
__wsum csum;
struct nfsd_drc_bucket *b;
int type = rqstp->rq_cachetype;
- unsigned long freed;
LIST_HEAD(dispose);
int rtn = RC_DOIT;
@@ -495,7 +514,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp, struct nfsd_cacherep **cacherep)
goto out;
}
- csum = nfsd_cache_csum(rqstp);
+ csum = nfsd_cache_csum(&rqstp->rq_arg, start, len);
/*
* Since the common case is a cache miss followed by an insert,
@@ -516,8 +535,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp, struct nfsd_cacherep **cacherep)
nfsd_prune_bucket_locked(nn, b, 3, &dispose);
spin_unlock(&b->cache_lock);
- freed = nfsd_cacherep_dispose(&dispose);
- trace_nfsd_drc_gc(nn, freed);
+ nfsd_cacherep_dispose(&dispose);
nfsd_stats_rc_misses_inc();
atomic_inc(&nn->num_drc_entries);
@@ -641,24 +659,17 @@ void nfsd_cache_update(struct svc_rqst *rqstp, struct nfsd_cacherep *rp,
return;
}
-/*
- * Copy cached reply to current reply buffer. Should always fit.
- * FIXME as reply is in a page, we should just attach the page, and
- * keep a refcount....
- */
static int
nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data)
{
- struct kvec *vec = &rqstp->rq_res.head[0];
-
- if (vec->iov_len + data->iov_len > PAGE_SIZE) {
- printk(KERN_WARNING "nfsd: cached reply too large (%zd).\n",
- data->iov_len);
- return 0;
- }
- memcpy((char*)vec->iov_base + vec->iov_len, data->iov_base, data->iov_len);
- vec->iov_len += data->iov_len;
- return 1;
+ __be32 *p;
+
+ p = xdr_reserve_space(&rqstp->rq_res_stream, data->iov_len);
+ if (unlikely(!p))
+ return false;
+ memcpy(p, data->iov_base, data->iov_len);
+ xdr_commit_encode(&rqstp->rq_res_stream);
+ return true;
}
/*
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 50df5e9d0069..c9f9590f056b 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -76,7 +76,9 @@ static ssize_t write_maxconn(struct file *file, char *buf, size_t size);
#ifdef CONFIG_NFSD_V4
static ssize_t write_leasetime(struct file *file, char *buf, size_t size);
static ssize_t write_gracetime(struct file *file, char *buf, size_t size);
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
static ssize_t write_recoverydir(struct file *file, char *buf, size_t size);
+#endif
static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size);
#endif
@@ -93,7 +95,9 @@ static ssize_t (*const write_op[])(struct file *, char *, size_t) = {
#ifdef CONFIG_NFSD_V4
[NFSD_Leasetime] = write_leasetime,
[NFSD_Gracetime] = write_gracetime,
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
[NFSD_RecoveryDir] = write_recoverydir,
+#endif
[NFSD_V4EndGrace] = write_v4_end_grace,
#endif
};
@@ -179,7 +183,7 @@ static const struct file_operations pool_stats_operations = {
.open = nfsd_pool_stats_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = nfsd_pool_stats_release,
+ .release = seq_release,
};
DEFINE_SHOW_ATTRIBUTE(nfsd_reply_cache_stats);
@@ -693,6 +697,7 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred
char *mesg = buf;
int fd, err;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct svc_serv *serv;
err = get_int(&mesg, &fd);
if (err != 0 || fd < 0)
@@ -703,13 +708,12 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred
if (err != 0)
return err;
- err = svc_addsock(nn->nfsd_serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred);
+ serv = nn->nfsd_serv;
+ err = svc_addsock(serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred);
- if (err >= 0 &&
- !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
- svc_get(nn->nfsd_serv);
+ if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
+ nfsd_destroy_serv(net);
- nfsd_put(net);
return err;
}
@@ -723,6 +727,7 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr
struct svc_xprt *xprt;
int port, err;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct svc_serv *serv;
if (sscanf(buf, "%15s %5u", transport, &port) != 2)
return -EINVAL;
@@ -735,29 +740,28 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr
if (err != 0)
return err;
- err = svc_xprt_create(nn->nfsd_serv, transport, net,
+ serv = nn->nfsd_serv;
+ err = svc_xprt_create(serv, transport, net,
PF_INET, port, SVC_SOCK_ANONYMOUS, cred);
if (err < 0)
goto out_err;
- err = svc_xprt_create(nn->nfsd_serv, transport, net,
+ err = svc_xprt_create(serv, transport, net,
PF_INET6, port, SVC_SOCK_ANONYMOUS, cred);
if (err < 0 && err != -EAFNOSUPPORT)
goto out_close;
- if (!nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
- svc_get(nn->nfsd_serv);
-
- nfsd_put(net);
return 0;
out_close:
- xprt = svc_find_xprt(nn->nfsd_serv, transport, net, PF_INET, port);
+ xprt = svc_find_xprt(serv, transport, net, PF_INET, port);
if (xprt != NULL) {
svc_xprt_close(xprt);
svc_xprt_put(xprt);
}
out_err:
- nfsd_put(net);
+ if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
+ nfsd_destroy_serv(net);
+
return err;
}
@@ -1013,6 +1017,7 @@ static ssize_t write_gracetime(struct file *file, char *buf, size_t size)
return nfsd4_write_time(file, buf, size, &nn->nfsd4_grace, nn);
}
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size,
struct nfsd_net *nn)
{
@@ -1073,6 +1078,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size)
mutex_unlock(&nfsd_mutex);
return rv;
}
+#endif
/*
* write_v4_end_grace - release grace period for nfsd's v4.x lock manager
@@ -1468,11 +1474,10 @@ int nfsd_nl_rpc_status_get_start(struct netlink_callback *cb)
int ret = -ENODEV;
mutex_lock(&nfsd_mutex);
- if (nn->nfsd_serv) {
- svc_get(nn->nfsd_serv);
+ if (nn->nfsd_serv)
ret = 0;
- }
- mutex_unlock(&nfsd_mutex);
+ else
+ mutex_unlock(&nfsd_mutex);
return ret;
}
@@ -1644,8 +1649,6 @@ out:
*/
int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb)
{
- mutex_lock(&nfsd_mutex);
- nfsd_put(sock_net(cb->skb->sk));
mutex_unlock(&nfsd_mutex);
return 0;
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index f5ff42f41ee7..304e9728b929 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -113,13 +113,6 @@ int nfsd_pool_stats_open(struct inode *, struct file *);
int nfsd_pool_stats_release(struct inode *, struct file *);
void nfsd_shutdown_threads(struct net *net);
-static inline void nfsd_put(struct net *net)
-{
- struct nfsd_net *nn = net_generic(net, nfsd_net_id);
-
- svc_put(nn->nfsd_serv);
-}
-
bool i_am_nfsd(void);
struct nfsdfs_client {
@@ -155,6 +148,7 @@ int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change);
int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change);
void nfsd_reset_versions(struct nfsd_net *nn);
int nfsd_create_serv(struct net *net);
+void nfsd_destroy_serv(struct net *net);
extern int nfsd_max_blksize;
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index d6122bb2d167..a667802e08e7 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -59,15 +59,6 @@ static __be32 nfsd_init_request(struct svc_rqst *,
* nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and some members
* of the svc_serv struct such as ->sv_temp_socks and ->sv_permsocks.
*
- * If (out side the lock) nn->nfsd_serv is non-NULL, then it must point to a
- * properly initialised 'struct svc_serv' with ->sv_nrthreads > 0 (unless
- * nn->keep_active is set). That number of nfsd threads must
- * exist and each must be listed in ->sp_all_threads in some entry of
- * ->sv_pools[].
- *
- * Each active thread holds a counted reference on nn->nfsd_serv, as does
- * the nn->keep_active flag and various transient calls to svc_get().
- *
* Finally, the nfsd_mutex also protects some of the global variables that are
* accessed when nfsd starts and that are settable via the write_* routines in
* nfsctl.c. In particular:
@@ -359,13 +350,12 @@ static bool nfsd_needs_lockd(struct nfsd_net *nn)
*/
void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn)
{
- int seq = 0;
+ unsigned int seq;
do {
- read_seqbegin_or_lock(&nn->writeverf_lock, &seq);
+ seq = read_seqbegin(&nn->writeverf_lock);
memcpy(verf, nn->writeverf, sizeof(nn->writeverf));
- } while (need_seqretry(&nn->writeverf_lock, seq));
- done_seqretry(&nn->writeverf_lock, seq);
+ } while (read_seqretry(&nn->writeverf_lock, seq));
}
static void nfsd_reset_write_verifier_locked(struct nfsd_net *nn)
@@ -542,7 +532,11 @@ static struct notifier_block nfsd_inet6addr_notifier = {
/* Only used under nfsd_mutex, so this atomic may be overkill: */
static atomic_t nfsd_notifier_refcount = ATOMIC_INIT(0);
-static void nfsd_last_thread(struct net *net)
+/**
+ * nfsd_destroy_serv - tear down NFSD's svc_serv for a namespace
+ * @net: network namespace the NFS service is associated with
+ */
+void nfsd_destroy_serv(struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
struct svc_serv *serv = nn->nfsd_serv;
@@ -564,7 +558,7 @@ static void nfsd_last_thread(struct net *net)
/*
* write_ports can create the server without actually starting
* any threads--if we get shut down before any threads are
- * started, then nfsd_last_thread will be run before any of this
+ * started, then nfsd_destroy_serv will be run before any of this
* other initialization has been done except the rpcb information.
*/
svc_rpcb_cleanup(serv, net);
@@ -573,6 +567,7 @@ static void nfsd_last_thread(struct net *net)
nfsd_shutdown_net(net);
nfsd_export_flush(net);
+ svc_destroy(&serv);
}
void nfsd_reset_versions(struct nfsd_net *nn)
@@ -647,11 +642,9 @@ void nfsd_shutdown_threads(struct net *net)
return;
}
- svc_get(serv);
/* Kill outstanding nfsd threads */
svc_set_num_threads(serv, NULL, 0);
- nfsd_last_thread(net);
- svc_put(serv);
+ nfsd_destroy_serv(net);
mutex_unlock(&nfsd_mutex);
}
@@ -667,10 +660,9 @@ int nfsd_create_serv(struct net *net)
struct svc_serv *serv;
WARN_ON(!mutex_is_locked(&nfsd_mutex));
- if (nn->nfsd_serv) {
- svc_get(nn->nfsd_serv);
+ if (nn->nfsd_serv)
return 0;
- }
+
if (nfsd_max_blksize == 0)
nfsd_max_blksize = nfsd_get_default_max_blksize();
nfsd_reset_versions(nn);
@@ -681,10 +673,11 @@ int nfsd_create_serv(struct net *net)
serv->sv_maxconn = nn->max_connections;
error = svc_bind(serv, net);
if (error < 0) {
- svc_put(serv);
+ svc_destroy(&serv);
return error;
}
spin_lock(&nfsd_notifier_lock);
+ nn->nfsd_info.mutex = &nfsd_mutex;
nn->nfsd_serv = serv;
spin_unlock(&nfsd_notifier_lock);
@@ -764,7 +757,6 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
nthreads[0] = 1;
/* apply the new numbers */
- svc_get(nn->nfsd_serv);
for (i = 0; i < n; i++) {
err = svc_set_num_threads(nn->nfsd_serv,
&nn->nfsd_serv->sv_pools[i],
@@ -772,7 +764,6 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
if (err)
break;
}
- svc_put(nn->nfsd_serv);
return err;
}
@@ -814,13 +805,8 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred)
goto out_put;
error = serv->sv_nrthreads;
out_put:
- /* Threads now hold service active */
- if (xchg(&nn->keep_active, 0))
- svc_put(serv);
-
if (serv->sv_nrthreads == 0)
- nfsd_last_thread(net);
- svc_put(serv);
+ nfsd_destroy_serv(net);
out:
mutex_unlock(&nfsd_mutex);
return error;
@@ -955,7 +941,6 @@ nfsd(void *vrqstp)
rqstp->rq_server->sv_maxconn = nn->max_connections;
svc_recv(rqstp);
- validate_process_creds();
}
atomic_dec(&nfsdstats.th_cnt);
@@ -981,6 +966,8 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
const struct svc_procedure *proc = rqstp->rq_procinfo;
__be32 *statp = rqstp->rq_accept_statp;
struct nfsd_cacherep *rp;
+ unsigned int start, len;
+ __be32 *nfs_reply;
/*
* Give the xdr decoder a chance to change this if it wants
@@ -988,6 +975,13 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
*/
rqstp->rq_cachetype = proc->pc_cachetype;
+ /*
+ * ->pc_decode advances the argument stream past the NFS
+ * Call header, so grab the header's starting location and
+ * size now for the call to nfsd_cache_lookup().
+ */
+ start = xdr_stream_pos(&rqstp->rq_arg_stream);
+ len = xdr_stream_remaining(&rqstp->rq_arg_stream);
if (!proc->pc_decode(rqstp, &rqstp->rq_arg_stream))
goto out_decode_err;
@@ -1001,7 +995,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter | 1);
rp = NULL;
- switch (nfsd_cache_lookup(rqstp, &rp)) {
+ switch (nfsd_cache_lookup(rqstp, start, len, &rp)) {
case RC_DOIT:
break;
case RC_REPLY:
@@ -1010,6 +1004,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
goto out_dropit;
}
+ nfs_reply = xdr_inline_decode(&rqstp->rq_res_stream, 0);
*statp = proc->pc_func(rqstp);
if (test_bit(RQ_DROPME, &rqstp->rq_flags))
goto out_update_drop;
@@ -1023,7 +1018,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
*/
smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter + 1);
- nfsd_cache_update(rqstp, rp, rqstp->rq_cachetype, statp + 1);
+ nfsd_cache_update(rqstp, rp, rqstp->rq_cachetype, nfs_reply);
out_cached_reply:
return 1;
@@ -1074,28 +1069,7 @@ bool nfssvc_encode_voidres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
int nfsd_pool_stats_open(struct inode *inode, struct file *file)
{
- int ret;
struct nfsd_net *nn = net_generic(inode->i_sb->s_fs_info, nfsd_net_id);
- mutex_lock(&nfsd_mutex);
- if (nn->nfsd_serv == NULL) {
- mutex_unlock(&nfsd_mutex);
- return -ENODEV;
- }
- svc_get(nn->nfsd_serv);
- ret = svc_pool_stats_open(nn->nfsd_serv, file);
- mutex_unlock(&nfsd_mutex);
- return ret;
-}
-
-int nfsd_pool_stats_release(struct inode *inode, struct file *file)
-{
- struct seq_file *seq = file->private_data;
- struct svc_serv *serv = seq->private;
- int ret = seq_release(inode, file);
-
- mutex_lock(&nfsd_mutex);
- svc_put(serv);
- mutex_unlock(&nfsd_mutex);
- return ret;
+ return svc_pool_stats_open(&nn->nfsd_info, file);
}
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index f96eaa8e9413..41bdc913fa71 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -117,24 +117,6 @@ struct nfs4_cpntf_state {
time64_t cpntf_time; /* last time stateid used */
};
-struct nfs4_cb_fattr {
- struct nfsd4_callback ncf_getattr;
- u32 ncf_cb_status;
- u32 ncf_cb_bmap[1];
-
- /* from CB_GETATTR reply */
- u64 ncf_cb_change;
- u64 ncf_cb_fsize;
-
- unsigned long ncf_cb_flags;
- bool ncf_file_modified;
- u64 ncf_initial_cinfo;
- u64 ncf_cur_fsize;
-};
-
-/* bits for ncf_cb_flags */
-#define CB_GETATTR_BUSY 0
-
/*
* Represents a delegation stateid. The nfs4_client holds references to these
* and they are put when it is being destroyed or when the delegation is
@@ -168,9 +150,6 @@ struct nfs4_delegation {
int dl_retries;
struct nfsd4_callback dl_recall;
bool dl_recalled;
-
- /* for CB_GETATTR */
- struct nfs4_cb_fattr dl_cb_fattr;
};
#define cb_to_delegation(cb) \
@@ -661,7 +640,6 @@ enum nfsd4_cb_op {
NFSPROC4_CLNT_CB_SEQUENCE,
NFSPROC4_CLNT_CB_NOTIFY_LOCK,
NFSPROC4_CLNT_CB_RECALL_ANY,
- NFSPROC4_CLNT_CB_GETATTR,
};
/* Returns true iff a is later than b: */
@@ -754,6 +732,5 @@ static inline bool try_to_expire_client(struct nfs4_client *clp)
}
extern __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp,
- struct inode *inode, bool *file_modified, u64 *size);
-extern void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf);
+ struct inode *inode);
#endif /* NFSD4_STATE_H */
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index fbc0ccb40424..d1e8cf079b0f 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -1262,28 +1262,6 @@ TRACE_EVENT(nfsd_drc_mismatch,
__entry->ingress)
);
-TRACE_EVENT_CONDITION(nfsd_drc_gc,
- TP_PROTO(
- const struct nfsd_net *nn,
- unsigned long freed
- ),
- TP_ARGS(nn, freed),
- TP_CONDITION(freed > 0),
- TP_STRUCT__entry(
- __field(unsigned long long, boot_time)
- __field(unsigned long, freed)
- __field(int, total)
- ),
- TP_fast_assign(
- __entry->boot_time = nn->boot_time;
- __entry->freed = freed;
- __entry->total = atomic_read(&nn->num_drc_entries);
- ),
- TP_printk("boot_time=%16llx total=%d freed=%lu",
- __entry->boot_time, __entry->total, __entry->freed
- )
-);
-
TRACE_EVENT(nfsd_cb_args,
TP_PROTO(
const struct nfs4_client *clp,
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index fbbea7498f02..b7c7a9273ea0 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -901,7 +901,6 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
int host_err;
bool retried = false;
- validate_process_creds();
/*
* If we get here, then the client has already done an "open",
* and (hopefully) checked permission - so allow OWNER_OVERRIDE
@@ -926,7 +925,6 @@ retry:
}
err = nfserrno(host_err);
}
- validate_process_creds();
return err;
}
@@ -943,12 +941,7 @@ int
nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, int may_flags,
struct file **filp)
{
- int err;
-
- validate_process_creds();
- err = __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp);
- validate_process_creds();
- return err;
+ return __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp);
}
/*
@@ -1046,7 +1039,10 @@ __be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
ssize_t host_err;
trace_nfsd_read_splice(rqstp, fhp, offset, *count);
- host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor);
+ host_err = rw_verify_area(READ, file, &offset, *count);
+ if (!host_err)
+ host_err = splice_direct_to_actor(file, &sd,
+ nfsd_direct_splice_actor);
return nfsd_finish_read(rqstp, fhp, file, offset, count, eof, host_err);
}
@@ -1183,9 +1179,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
since = READ_ONCE(file->f_wb_err);
if (verf)
nfsd_copy_write_verifier(verf, nn);
- file_start_write(file);
host_err = vfs_iter_write(file, &iter, &pos, flags);
- file_end_write(file);
if (host_err < 0) {
commit_reset_write_verifier(nn, rqstp, host_err);
goto out_nfserr;
@@ -1217,6 +1211,30 @@ out_nfserr:
}
/**
+ * nfsd_read_splice_ok - check if spliced reading is supported
+ * @rqstp: RPC transaction context
+ *
+ * Return values:
+ * %true: nfsd_splice_read() may be used
+ * %false: nfsd_splice_read() must not be used
+ *
+ * NFS READ normally uses splice to send data in-place. However the
+ * data in cache can change after the reply's MIC is computed but
+ * before the RPC reply is sent. To prevent the client from
+ * rejecting the server-computed MIC in this somewhat rare case, do
+ * not use splice with the GSS integrity and privacy services.
+ */
+bool nfsd_read_splice_ok(struct svc_rqst *rqstp)
+{
+ switch (svc_auth_flavor(rqstp)) {
+ case RPC_AUTH_GSS_KRB5I:
+ case RPC_AUTH_GSS_KRB5P:
+ return false;
+ }
+ return true;
+}
+
+/**
* nfsd_read - Read data from a file
* @rqstp: RPC transaction context
* @fhp: file handle of file to be read
@@ -1245,7 +1263,7 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
return err;
file = nf->nf_file;
- if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &rqstp->rq_flags))
+ if (file->f_op->splice_read && nfsd_read_splice_ok(rqstp))
err = nfsd_splice_read(rqstp, fhp, file, offset, count, eof);
else
err = nfsd_iter_read(rqstp, fhp, file, offset, count, 0, eof);
@@ -1813,6 +1831,10 @@ retry:
}
trap = lock_rename(tdentry, fdentry);
+ if (IS_ERR(trap)) {
+ err = (rqstp->rq_vers == 2) ? nfserr_acces : nfserr_xdev;
+ goto out;
+ }
err = fh_fill_pre_attrs(ffhp);
if (err != nfs_ok)
goto out_unlock;
@@ -2109,9 +2131,23 @@ static __be32 nfsd_buffered_readdir(struct file *file, struct svc_fh *fhp,
return cdp->err;
}
-/*
- * Read entries from a directory.
- * The NFSv3/4 verifier we ignore for now.
+/**
+ * nfsd_readdir - Read entries from a directory
+ * @rqstp: RPC transaction context
+ * @fhp: NFS file handle of directory to be read
+ * @offsetp: OUT: seek offset of final entry that was read
+ * @cdp: OUT: an eof error value
+ * @func: entry filler actor
+ *
+ * This implementation ignores the NFSv3/4 verifier cookie.
+ *
+ * NB: normal system calls hold file->f_pos_lock when calling
+ * ->iterate_shared and ->llseek, but nfsd_readdir() does not.
+ * Because the struct file acquired here is not visible to other
+ * threads, it's internal state does not need mutex protection.
+ *
+ * Returns nfs_ok on success, otherwise an nfsstat code is
+ * returned.
*/
__be32
nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp,
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index e3c29596f4df..702fbc4483bf 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -114,6 +114,7 @@ __be32 nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
struct file *file, loff_t offset,
unsigned long *count, unsigned int base,
u32 *eof);
+bool nfsd_read_splice_ok(struct svc_rqst *rqstp);
__be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
loff_t offset, unsigned long *count,
u32 *eof);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 80e859dc84d8..415516c1b27e 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -840,6 +840,7 @@ struct nfsd4_compoundargs {
u32 minorversion;
u32 client_opcnt;
u32 opcnt;
+ bool splice_ok;
struct nfsd4_op *ops;
struct nfsd4_op iops[8];
};
diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h
index e8b00309c449..0d39af1b00a0 100644
--- a/fs/nfsd/xdr4cb.h
+++ b/fs/nfsd/xdr4cb.h
@@ -54,21 +54,3 @@
#define NFS4_dec_cb_recall_any_sz (cb_compound_dec_hdr_sz + \
cb_sequence_dec_sz + \
op_dec_sz)
-
-/*
- * 1: CB_GETATTR opcode (32-bit)
- * N: file_handle
- * 1: number of entry in attribute array (32-bit)
- * 1: entry 0 in attribute array (32-bit)
- */
-#define NFS4_enc_cb_getattr_sz (cb_compound_enc_hdr_sz + \
- cb_sequence_enc_sz + \
- 1 + enc_nfs4_fh_sz + 1 + 1)
-/*
- * 4: fattr_bitmap_maxsz
- * 1: attribute array len
- * 2: change attr (64-bit)
- * 2: size (64-bit)
- */
-#define NFS4_dec_cb_getattr_sz (cb_compound_dec_hdr_sz + \
- cb_sequence_dec_sz + 4 + 1 + 2 + 2 + op_dec_sz)