summaryrefslogtreecommitdiff
path: root/fs/nfsd/nfsctl.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfsd/nfsctl.c')
-rw-r--r--fs/nfsd/nfsctl.c944
1 files changed, 849 insertions, 95 deletions
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 887035b74467..dcaa31706394 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -15,8 +15,10 @@
#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/gss_api.h>
#include <linux/sunrpc/rpc_pipe_fs.h>
+#include <linux/sunrpc/svc.h>
#include <linux/module.h>
#include <linux/fsnotify.h>
+#include <linux/nfslocalio.h>
#include "idmap.h"
#include "nfsd.h"
@@ -26,6 +28,7 @@
#include "pnfs.h"
#include "filecache.h"
#include "trace.h"
+#include "netlink.h"
/*
* We have a single directory with several nodes in it.
@@ -47,16 +50,10 @@ enum {
NFSD_MaxBlkSize,
NFSD_MaxConnections,
NFSD_Filecache,
- /*
- * The below MUST come last. Otherwise we leave a hole in nfsd_files[]
- * with !CONFIG_NFSD_V4 and simple_fill_super() goes oops
- */
-#ifdef CONFIG_NFSD_V4
NFSD_Leasetime,
NFSD_Gracetime,
NFSD_RecoveryDir,
NFSD_V4EndGrace,
-#endif
NFSD_MaxReserved
};
@@ -75,7 +72,9 @@ 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
@@ -92,7 +91,9 @@ 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
};
@@ -174,11 +175,18 @@ static int export_features_show(struct seq_file *m, void *v)
DEFINE_SHOW_ATTRIBUTE(export_features);
+static int nfsd_pool_stats_open(struct inode *inode, struct file *file)
+{
+ struct nfsd_net *nn = net_generic(inode->i_sb->s_fs_info, nfsd_net_id);
+
+ return svc_pool_stats_open(&nn->nfsd_info, file);
+}
+
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);
@@ -280,6 +288,7 @@ static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size)
* 3. Is that directory the root of an exported file system?
*/
error = nlmsvc_unlock_all_by_sb(path.dentry->d_sb);
+ nfsd4_revoke_states(netns(file), path.dentry->d_sb);
path_put(&path);
return error;
@@ -404,7 +413,9 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
if (newthreads < 0)
return -EINVAL;
trace_nfsd_ctl_threads(net, newthreads);
- rv = nfsd_svc(newthreads, net, file->f_cred);
+ mutex_lock(&nfsd_mutex);
+ rv = nfsd_svc(1, &newthreads, net, file->f_cred, NULL);
+ mutex_unlock(&nfsd_mutex);
if (rv < 0)
return rv;
} else
@@ -478,6 +489,14 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size)
goto out_free;
trace_nfsd_ctl_pool_threads(net, i, nthreads[i]);
}
+
+ /*
+ * There must always be a thread in pool 0; the admin
+ * can't shut down NFS completely using pool_threads.
+ */
+ if (nthreads[0] == 0)
+ nthreads[0] = 1;
+
rv = nfsd_set_nrthreads(i, nthreads, net);
if (rv)
goto out_free;
@@ -706,12 +725,9 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred
serv = nn->nfsd_serv;
err = svc_addsock(serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred);
- if (err < 0 && !serv->sv_nrthreads && !nn->keep_active)
- nfsd_last_thread(net);
- else if (err >= 0 && !serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
- svc_get(serv);
+ if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
+ nfsd_destroy_serv(net);
- svc_put(serv);
return err;
}
@@ -749,10 +765,6 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr
if (err < 0 && err != -EAFNOSUPPORT)
goto out_close;
- if (!serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
- svc_get(serv);
-
- svc_put(serv);
return 0;
out_close:
xprt = svc_find_xprt(serv, transport, net, PF_INET, port);
@@ -761,10 +773,9 @@ out_close:
svc_xprt_put(xprt);
}
out_err:
- if (!serv->sv_nrthreads && !nn->keep_active)
- nfsd_last_thread(net);
+ if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
+ nfsd_destroy_serv(net);
- svc_put(serv);
return err;
}
@@ -1020,6 +1031,7 @@ 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)
{
@@ -1080,6 +1092,7 @@ 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
@@ -1140,7 +1153,7 @@ static struct inode *nfsd_get_inode(struct super_block *sb, umode_t mode)
/* Following advice from simple_fill_super documentation: */
inode->i_ino = iunique(sb, NFSD_MaxReserved);
inode->i_mode = mode;
- inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode);
+ simple_inode_init_ts(inode);
switch (mode & S_IFMT) {
case S_IFDIR:
inode->i_fop = &simple_dir_operations;
@@ -1243,63 +1256,34 @@ static inline void _nfsd_symlink(struct dentry *parent, const char *name,
#endif
-static void clear_ncl(struct inode *inode)
+static void clear_ncl(struct dentry *dentry)
{
+ struct inode *inode = d_inode(dentry);
struct nfsdfs_client *ncl = inode->i_private;
+ spin_lock(&inode->i_lock);
inode->i_private = NULL;
+ spin_unlock(&inode->i_lock);
kref_put(&ncl->cl_ref, ncl->cl_release);
}
-static struct nfsdfs_client *__get_nfsdfs_client(struct inode *inode)
-{
- struct nfsdfs_client *nc = inode->i_private;
-
- if (nc)
- kref_get(&nc->cl_ref);
- return nc;
-}
-
struct nfsdfs_client *get_nfsdfs_client(struct inode *inode)
{
struct nfsdfs_client *nc;
- inode_lock_shared(inode);
- nc = __get_nfsdfs_client(inode);
- inode_unlock_shared(inode);
+ spin_lock(&inode->i_lock);
+ nc = inode->i_private;
+ if (nc)
+ kref_get(&nc->cl_ref);
+ spin_unlock(&inode->i_lock);
return nc;
}
-/* from __rpc_unlink */
-static void nfsdfs_remove_file(struct inode *dir, struct dentry *dentry)
-{
- int ret;
-
- clear_ncl(d_inode(dentry));
- dget(dentry);
- ret = simple_unlink(dir, dentry);
- d_drop(dentry);
- fsnotify_unlink(dir, dentry);
- dput(dentry);
- WARN_ON_ONCE(ret);
-}
-
-static void nfsdfs_remove_files(struct dentry *root)
-{
- struct dentry *dentry, *tmp;
-
- list_for_each_entry_safe(dentry, tmp, &root->d_subdirs, d_child) {
- if (!simple_positive(dentry)) {
- WARN_ON_ONCE(1); /* I think this can't happen? */
- continue;
- }
- nfsdfs_remove_file(d_inode(root), dentry);
- }
-}
/* XXX: cut'n'paste from simple_fill_super; figure out if we could share
* code instead. */
static int nfsdfs_create_files(struct dentry *root,
const struct tree_descr *files,
+ struct nfsdfs_client *ncl,
struct dentry **fdentries)
{
struct inode *dir = d_inode(root);
@@ -1318,8 +1302,9 @@ static int nfsdfs_create_files(struct dentry *root,
dput(dentry);
goto out;
}
+ kref_get(&ncl->cl_ref);
inode->i_fop = files->ops;
- inode->i_private = __get_nfsdfs_client(dir);
+ inode->i_private = ncl;
d_add(dentry, inode);
fsnotify_create(dir, dentry);
if (fdentries)
@@ -1328,7 +1313,6 @@ static int nfsdfs_create_files(struct dentry *root,
inode_unlock(dir);
return 0;
out:
- nfsdfs_remove_files(root);
inode_unlock(dir);
return -ENOMEM;
}
@@ -1348,7 +1332,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
dentry = nfsd_mkdir(nn->nfsd_client_dir, ncl, name);
if (IS_ERR(dentry)) /* XXX: tossing errors? */
return NULL;
- ret = nfsdfs_create_files(dentry, files, fdentries);
+ ret = nfsdfs_create_files(dentry, files, ncl, fdentries);
if (ret) {
nfsd_client_rmdir(dentry);
return NULL;
@@ -1359,20 +1343,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
/* Taken from __rpc_rmdir: */
void nfsd_client_rmdir(struct dentry *dentry)
{
- struct inode *dir = d_inode(dentry->d_parent);
- struct inode *inode = d_inode(dentry);
- int ret;
-
- inode_lock(dir);
- nfsdfs_remove_files(dentry);
- clear_ncl(inode);
- dget(dentry);
- ret = simple_rmdir(dir, dentry);
- WARN_ON_ONCE(ret);
- d_drop(dentry);
- fsnotify_rmdir(dir, dentry);
- dput(dentry);
- inode_unlock(dir);
+ simple_recursive_removal(dentry, clear_ncl);
}
static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc)
@@ -1406,7 +1377,9 @@ static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc)
#ifdef CONFIG_NFSD_V4
[NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR},
[NFSD_Gracetime] = {"nfsv4gracetime", &transaction_ops, S_IWUSR|S_IRUSR},
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
[NFSD_RecoveryDir] = {"nfsv4recoverydir", &transaction_ops, S_IWUSR|S_IRUSR},
+#endif
[NFSD_V4EndGrace] = {"v4_end_grace", &transaction_ops, S_IWUSR|S_IRUGO},
#endif
/* last one */ {""}
@@ -1503,6 +1476,747 @@ static int create_proc_exports_entry(void)
unsigned int nfsd_net_id;
+static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb,
+ struct netlink_callback *cb,
+ struct nfsd_genl_rqstp *rqstp)
+{
+ void *hdr;
+ u32 i;
+
+ hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+ &nfsd_nl_family, 0, NFSD_CMD_RPC_STATUS_GET);
+ if (!hdr)
+ return -ENOBUFS;
+
+ if (nla_put_be32(skb, NFSD_A_RPC_STATUS_XID, rqstp->rq_xid) ||
+ nla_put_u32(skb, NFSD_A_RPC_STATUS_FLAGS, rqstp->rq_flags) ||
+ nla_put_u32(skb, NFSD_A_RPC_STATUS_PROG, rqstp->rq_prog) ||
+ nla_put_u32(skb, NFSD_A_RPC_STATUS_PROC, rqstp->rq_proc) ||
+ nla_put_u8(skb, NFSD_A_RPC_STATUS_VERSION, rqstp->rq_vers) ||
+ nla_put_s64(skb, NFSD_A_RPC_STATUS_SERVICE_TIME,
+ ktime_to_us(rqstp->rq_stime),
+ NFSD_A_RPC_STATUS_PAD))
+ return -ENOBUFS;
+
+ switch (rqstp->rq_saddr.sa_family) {
+ case AF_INET: {
+ const struct sockaddr_in *s_in, *d_in;
+
+ s_in = (const struct sockaddr_in *)&rqstp->rq_saddr;
+ d_in = (const struct sockaddr_in *)&rqstp->rq_daddr;
+ if (nla_put_in_addr(skb, NFSD_A_RPC_STATUS_SADDR4,
+ s_in->sin_addr.s_addr) ||
+ nla_put_in_addr(skb, NFSD_A_RPC_STATUS_DADDR4,
+ d_in->sin_addr.s_addr) ||
+ nla_put_be16(skb, NFSD_A_RPC_STATUS_SPORT,
+ s_in->sin_port) ||
+ nla_put_be16(skb, NFSD_A_RPC_STATUS_DPORT,
+ d_in->sin_port))
+ return -ENOBUFS;
+ break;
+ }
+ case AF_INET6: {
+ const struct sockaddr_in6 *s_in, *d_in;
+
+ s_in = (const struct sockaddr_in6 *)&rqstp->rq_saddr;
+ d_in = (const struct sockaddr_in6 *)&rqstp->rq_daddr;
+ if (nla_put_in6_addr(skb, NFSD_A_RPC_STATUS_SADDR6,
+ &s_in->sin6_addr) ||
+ nla_put_in6_addr(skb, NFSD_A_RPC_STATUS_DADDR6,
+ &d_in->sin6_addr) ||
+ nla_put_be16(skb, NFSD_A_RPC_STATUS_SPORT,
+ s_in->sin6_port) ||
+ nla_put_be16(skb, NFSD_A_RPC_STATUS_DPORT,
+ d_in->sin6_port))
+ return -ENOBUFS;
+ break;
+ }
+ }
+
+ for (i = 0; i < rqstp->rq_opcnt; i++)
+ if (nla_put_u32(skb, NFSD_A_RPC_STATUS_COMPOUND_OPS,
+ rqstp->rq_opnum[i]))
+ return -ENOBUFS;
+
+ genlmsg_end(skb, hdr);
+ return 0;
+}
+
+/**
+ * nfsd_nl_rpc_status_get_dumpit - Handle rpc_status_get dumpit
+ * @skb: reply buffer
+ * @cb: netlink metadata and command arguments
+ *
+ * Returns the size of the reply or a negative errno.
+ */
+int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ int i, ret, rqstp_index = 0;
+ struct nfsd_net *nn;
+
+ mutex_lock(&nfsd_mutex);
+
+ nn = net_generic(sock_net(skb->sk), nfsd_net_id);
+ if (!nn->nfsd_serv) {
+ ret = -ENODEV;
+ goto out_unlock;
+ }
+
+ rcu_read_lock();
+
+ for (i = 0; i < nn->nfsd_serv->sv_nrpools; i++) {
+ struct svc_rqst *rqstp;
+
+ if (i < cb->args[0]) /* already consumed */
+ continue;
+
+ rqstp_index = 0;
+ list_for_each_entry_rcu(rqstp,
+ &nn->nfsd_serv->sv_pools[i].sp_all_threads,
+ rq_all) {
+ struct nfsd_genl_rqstp genl_rqstp;
+ unsigned int status_counter;
+
+ if (rqstp_index++ < cb->args[1]) /* already consumed */
+ continue;
+ /*
+ * Acquire rq_status_counter before parsing the rqst
+ * fields. rq_status_counter is set to an odd value in
+ * order to notify the consumers the rqstp fields are
+ * meaningful.
+ */
+ status_counter =
+ smp_load_acquire(&rqstp->rq_status_counter);
+ if (!(status_counter & 1))
+ continue;
+
+ genl_rqstp.rq_xid = rqstp->rq_xid;
+ genl_rqstp.rq_flags = rqstp->rq_flags;
+ genl_rqstp.rq_vers = rqstp->rq_vers;
+ genl_rqstp.rq_prog = rqstp->rq_prog;
+ genl_rqstp.rq_proc = rqstp->rq_proc;
+ genl_rqstp.rq_stime = rqstp->rq_stime;
+ genl_rqstp.rq_opcnt = 0;
+ memcpy(&genl_rqstp.rq_daddr, svc_daddr(rqstp),
+ sizeof(struct sockaddr));
+ memcpy(&genl_rqstp.rq_saddr, svc_addr(rqstp),
+ sizeof(struct sockaddr));
+
+#ifdef CONFIG_NFSD_V4
+ if (rqstp->rq_vers == NFS4_VERSION &&
+ rqstp->rq_proc == NFSPROC4_COMPOUND) {
+ /* NFSv4 compound */
+ struct nfsd4_compoundargs *args;
+ int j;
+
+ args = rqstp->rq_argp;
+ genl_rqstp.rq_opcnt = args->opcnt;
+ for (j = 0; j < genl_rqstp.rq_opcnt; j++)
+ genl_rqstp.rq_opnum[j] =
+ args->ops[j].opnum;
+ }
+#endif /* CONFIG_NFSD_V4 */
+
+ /*
+ * Acquire rq_status_counter before reporting the rqst
+ * fields to the user.
+ */
+ if (smp_load_acquire(&rqstp->rq_status_counter) !=
+ status_counter)
+ continue;
+
+ ret = nfsd_genl_rpc_status_compose_msg(skb, cb,
+ &genl_rqstp);
+ if (ret)
+ goto out;
+ }
+ }
+
+ cb->args[0] = i;
+ cb->args[1] = rqstp_index;
+ ret = skb->len;
+out:
+ rcu_read_unlock();
+out_unlock:
+ mutex_unlock(&nfsd_mutex);
+
+ return ret;
+}
+
+/**
+ * nfsd_nl_threads_set_doit - set the number of running threads
+ * @skb: reply buffer
+ * @info: netlink metadata and command arguments
+ *
+ * Return 0 on success or a negative errno.
+ */
+int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info)
+{
+ int *nthreads, nrpools = 0, i, ret = -EOPNOTSUPP, rem;
+ struct net *net = genl_info_net(info);
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ const struct nlattr *attr;
+ const char *scope = NULL;
+
+ if (GENL_REQ_ATTR_CHECK(info, NFSD_A_SERVER_THREADS))
+ return -EINVAL;
+
+ /* count number of SERVER_THREADS values */
+ nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) {
+ if (nla_type(attr) == NFSD_A_SERVER_THREADS)
+ nrpools++;
+ }
+
+ mutex_lock(&nfsd_mutex);
+
+ nthreads = kcalloc(nrpools, sizeof(int), GFP_KERNEL);
+ if (!nthreads) {
+ ret = -ENOMEM;
+ goto out_unlock;
+ }
+
+ i = 0;
+ nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) {
+ if (nla_type(attr) == NFSD_A_SERVER_THREADS) {
+ nthreads[i++] = nla_get_u32(attr);
+ if (i >= nrpools)
+ break;
+ }
+ }
+
+ if (info->attrs[NFSD_A_SERVER_GRACETIME] ||
+ info->attrs[NFSD_A_SERVER_LEASETIME] ||
+ info->attrs[NFSD_A_SERVER_SCOPE]) {
+ ret = -EBUSY;
+ if (nn->nfsd_serv && nn->nfsd_serv->sv_nrthreads)
+ goto out_unlock;
+
+ ret = -EINVAL;
+ attr = info->attrs[NFSD_A_SERVER_GRACETIME];
+ if (attr) {
+ u32 gracetime = nla_get_u32(attr);
+
+ if (gracetime < 10 || gracetime > 3600)
+ goto out_unlock;
+
+ nn->nfsd4_grace = gracetime;
+ }
+
+ attr = info->attrs[NFSD_A_SERVER_LEASETIME];
+ if (attr) {
+ u32 leasetime = nla_get_u32(attr);
+
+ if (leasetime < 10 || leasetime > 3600)
+ goto out_unlock;
+
+ nn->nfsd4_lease = leasetime;
+ }
+
+ attr = info->attrs[NFSD_A_SERVER_SCOPE];
+ if (attr)
+ scope = nla_data(attr);
+ }
+
+ ret = nfsd_svc(nrpools, nthreads, net, get_current_cred(), scope);
+ if (ret > 0)
+ ret = 0;
+out_unlock:
+ mutex_unlock(&nfsd_mutex);
+ kfree(nthreads);
+ return ret;
+}
+
+/**
+ * nfsd_nl_threads_get_doit - get the number of running threads
+ * @skb: reply buffer
+ * @info: netlink metadata and command arguments
+ *
+ * Return 0 on success or a negative errno.
+ */
+int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net *net = genl_info_net(info);
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ void *hdr;
+ int err;
+
+ skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
+
+ hdr = genlmsg_iput(skb, info);
+ if (!hdr) {
+ err = -EMSGSIZE;
+ goto err_free_msg;
+ }
+
+ mutex_lock(&nfsd_mutex);
+
+ err = nla_put_u32(skb, NFSD_A_SERVER_GRACETIME,
+ nn->nfsd4_grace) ||
+ nla_put_u32(skb, NFSD_A_SERVER_LEASETIME,
+ nn->nfsd4_lease) ||
+ nla_put_string(skb, NFSD_A_SERVER_SCOPE,
+ nn->nfsd_name);
+ if (err)
+ goto err_unlock;
+
+ if (nn->nfsd_serv) {
+ int i;
+
+ for (i = 0; i < nfsd_nrpools(net); ++i) {
+ struct svc_pool *sp = &nn->nfsd_serv->sv_pools[i];
+
+ err = nla_put_u32(skb, NFSD_A_SERVER_THREADS,
+ sp->sp_nrthreads);
+ if (err)
+ goto err_unlock;
+ }
+ } else {
+ err = nla_put_u32(skb, NFSD_A_SERVER_THREADS, 0);
+ if (err)
+ goto err_unlock;
+ }
+
+ mutex_unlock(&nfsd_mutex);
+
+ genlmsg_end(skb, hdr);
+
+ return genlmsg_reply(skb, info);
+
+err_unlock:
+ mutex_unlock(&nfsd_mutex);
+err_free_msg:
+ nlmsg_free(skb);
+
+ return err;
+}
+
+/**
+ * nfsd_nl_version_set_doit - set the nfs enabled versions
+ * @skb: reply buffer
+ * @info: netlink metadata and command arguments
+ *
+ * Return 0 on success or a negative errno.
+ */
+int nfsd_nl_version_set_doit(struct sk_buff *skb, struct genl_info *info)
+{
+ const struct nlattr *attr;
+ struct nfsd_net *nn;
+ int i, rem;
+
+ if (GENL_REQ_ATTR_CHECK(info, NFSD_A_SERVER_PROTO_VERSION))
+ return -EINVAL;
+
+ mutex_lock(&nfsd_mutex);
+
+ nn = net_generic(genl_info_net(info), nfsd_net_id);
+ if (nn->nfsd_serv) {
+ mutex_unlock(&nfsd_mutex);
+ return -EBUSY;
+ }
+
+ /* clear current supported versions. */
+ nfsd_vers(nn, 2, NFSD_CLEAR);
+ nfsd_vers(nn, 3, NFSD_CLEAR);
+ for (i = 0; i <= NFSD_SUPPORTED_MINOR_VERSION; i++)
+ nfsd_minorversion(nn, i, NFSD_CLEAR);
+
+ nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) {
+ struct nlattr *tb[NFSD_A_VERSION_MAX + 1];
+ u32 major, minor = 0;
+ bool enabled;
+
+ if (nla_type(attr) != NFSD_A_SERVER_PROTO_VERSION)
+ continue;
+
+ if (nla_parse_nested(tb, NFSD_A_VERSION_MAX, attr,
+ nfsd_version_nl_policy, info->extack) < 0)
+ continue;
+
+ if (!tb[NFSD_A_VERSION_MAJOR])
+ continue;
+
+ major = nla_get_u32(tb[NFSD_A_VERSION_MAJOR]);
+ if (tb[NFSD_A_VERSION_MINOR])
+ minor = nla_get_u32(tb[NFSD_A_VERSION_MINOR]);
+
+ enabled = nla_get_flag(tb[NFSD_A_VERSION_ENABLED]);
+
+ switch (major) {
+ case 4:
+ nfsd_minorversion(nn, minor, enabled ? NFSD_SET : NFSD_CLEAR);
+ break;
+ case 3:
+ case 2:
+ if (!minor)
+ nfsd_vers(nn, major, enabled ? NFSD_SET : NFSD_CLEAR);
+ break;
+ default:
+ break;
+ }
+ }
+
+ mutex_unlock(&nfsd_mutex);
+
+ return 0;
+}
+
+/**
+ * nfsd_nl_version_get_doit - get the enabled status for all supported nfs versions
+ * @skb: reply buffer
+ * @info: netlink metadata and command arguments
+ *
+ * Return 0 on success or a negative errno.
+ */
+int nfsd_nl_version_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nfsd_net *nn;
+ int i, err;
+ void *hdr;
+
+ skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
+
+ hdr = genlmsg_iput(skb, info);
+ if (!hdr) {
+ err = -EMSGSIZE;
+ goto err_free_msg;
+ }
+
+ mutex_lock(&nfsd_mutex);
+ nn = net_generic(genl_info_net(info), nfsd_net_id);
+
+ for (i = 2; i <= 4; i++) {
+ int j;
+
+ for (j = 0; j <= NFSD_SUPPORTED_MINOR_VERSION; j++) {
+ struct nlattr *attr;
+
+ /* Don't record any versions the kernel doesn't have
+ * compiled in
+ */
+ if (!nfsd_support_version(i))
+ continue;
+
+ /* NFSv{2,3} does not support minor numbers */
+ if (i < 4 && j)
+ continue;
+
+ attr = nla_nest_start(skb,
+ NFSD_A_SERVER_PROTO_VERSION);
+ if (!attr) {
+ err = -EINVAL;
+ goto err_nfsd_unlock;
+ }
+
+ if (nla_put_u32(skb, NFSD_A_VERSION_MAJOR, i) ||
+ nla_put_u32(skb, NFSD_A_VERSION_MINOR, j)) {
+ err = -EINVAL;
+ goto err_nfsd_unlock;
+ }
+
+ /* Set the enabled flag if the version is enabled */
+ if (nfsd_vers(nn, i, NFSD_TEST) &&
+ (i < 4 || nfsd_minorversion(nn, j, NFSD_TEST)) &&
+ nla_put_flag(skb, NFSD_A_VERSION_ENABLED)) {
+ err = -EINVAL;
+ goto err_nfsd_unlock;
+ }
+
+ nla_nest_end(skb, attr);
+ }
+ }
+
+ mutex_unlock(&nfsd_mutex);
+ genlmsg_end(skb, hdr);
+
+ return genlmsg_reply(skb, info);
+
+err_nfsd_unlock:
+ mutex_unlock(&nfsd_mutex);
+err_free_msg:
+ nlmsg_free(skb);
+
+ return err;
+}
+
+/**
+ * nfsd_nl_listener_set_doit - set the nfs running sockets
+ * @skb: reply buffer
+ * @info: netlink metadata and command arguments
+ *
+ * Return 0 on success or a negative errno.
+ */
+int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net *net = genl_info_net(info);
+ struct svc_xprt *xprt, *tmp;
+ const struct nlattr *attr;
+ struct svc_serv *serv;
+ LIST_HEAD(permsocks);
+ struct nfsd_net *nn;
+ bool delete = false;
+ int err, rem;
+
+ mutex_lock(&nfsd_mutex);
+
+ err = nfsd_create_serv(net);
+ if (err) {
+ mutex_unlock(&nfsd_mutex);
+ return err;
+ }
+
+ nn = net_generic(net, nfsd_net_id);
+ serv = nn->nfsd_serv;
+
+ spin_lock_bh(&serv->sv_lock);
+
+ /* Move all of the old listener sockets to a temp list */
+ list_splice_init(&serv->sv_permsocks, &permsocks);
+
+ /*
+ * Walk the list of server_socks from userland and move any that match
+ * back to sv_permsocks
+ */
+ nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) {
+ struct nlattr *tb[NFSD_A_SOCK_MAX + 1];
+ const char *xcl_name;
+ struct sockaddr *sa;
+
+ if (nla_type(attr) != NFSD_A_SERVER_SOCK_ADDR)
+ continue;
+
+ if (nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr,
+ nfsd_sock_nl_policy, info->extack) < 0)
+ continue;
+
+ if (!tb[NFSD_A_SOCK_ADDR] || !tb[NFSD_A_SOCK_TRANSPORT_NAME])
+ continue;
+
+ if (nla_len(tb[NFSD_A_SOCK_ADDR]) < sizeof(*sa))
+ continue;
+
+ xcl_name = nla_data(tb[NFSD_A_SOCK_TRANSPORT_NAME]);
+ sa = nla_data(tb[NFSD_A_SOCK_ADDR]);
+
+ /* Put back any matching sockets */
+ list_for_each_entry_safe(xprt, tmp, &permsocks, xpt_list) {
+ /* This shouldn't be possible */
+ if (WARN_ON_ONCE(xprt->xpt_net != net)) {
+ list_move(&xprt->xpt_list, &serv->sv_permsocks);
+ continue;
+ }
+
+ /* If everything matches, put it back */
+ if (!strcmp(xprt->xpt_class->xcl_name, xcl_name) &&
+ rpc_cmp_addr_port(sa, (struct sockaddr *)&xprt->xpt_local)) {
+ list_move(&xprt->xpt_list, &serv->sv_permsocks);
+ break;
+ }
+ }
+ }
+
+ /*
+ * If there are listener transports remaining on the permsocks list,
+ * it means we were asked to remove a listener.
+ */
+ if (!list_empty(&permsocks)) {
+ list_splice_init(&permsocks, &serv->sv_permsocks);
+ delete = true;
+ }
+ spin_unlock_bh(&serv->sv_lock);
+
+ /* Do not remove listeners while there are active threads. */
+ if (serv->sv_nrthreads) {
+ err = -EBUSY;
+ goto out_unlock_mtx;
+ }
+
+ /*
+ * Since we can't delete an arbitrary llist entry, destroy the
+ * remaining listeners and recreate the list.
+ */
+ if (delete)
+ svc_xprt_destroy_all(serv, net);
+
+ /* walk list of addrs again, open any that still don't exist */
+ nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) {
+ struct nlattr *tb[NFSD_A_SOCK_MAX + 1];
+ const char *xcl_name;
+ struct sockaddr *sa;
+ int ret;
+
+ if (nla_type(attr) != NFSD_A_SERVER_SOCK_ADDR)
+ continue;
+
+ if (nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr,
+ nfsd_sock_nl_policy, info->extack) < 0)
+ continue;
+
+ if (!tb[NFSD_A_SOCK_ADDR] || !tb[NFSD_A_SOCK_TRANSPORT_NAME])
+ continue;
+
+ if (nla_len(tb[NFSD_A_SOCK_ADDR]) < sizeof(*sa))
+ continue;
+
+ xcl_name = nla_data(tb[NFSD_A_SOCK_TRANSPORT_NAME]);
+ sa = nla_data(tb[NFSD_A_SOCK_ADDR]);
+
+ xprt = svc_find_listener(serv, xcl_name, net, sa);
+ if (xprt) {
+ if (delete)
+ WARN_ONCE(1, "Transport type=%s already exists\n",
+ xcl_name);
+ svc_xprt_put(xprt);
+ continue;
+ }
+
+ ret = svc_xprt_create_from_sa(serv, xcl_name, net, sa, 0,
+ get_current_cred());
+ /* always save the latest error */
+ if (ret < 0)
+ err = ret;
+ }
+
+ if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
+ nfsd_destroy_serv(net);
+
+out_unlock_mtx:
+ mutex_unlock(&nfsd_mutex);
+
+ return err;
+}
+
+/**
+ * nfsd_nl_listener_get_doit - get the nfs running listeners
+ * @skb: reply buffer
+ * @info: netlink metadata and command arguments
+ *
+ * Return 0 on success or a negative errno.
+ */
+int nfsd_nl_listener_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+ struct svc_xprt *xprt;
+ struct svc_serv *serv;
+ struct nfsd_net *nn;
+ void *hdr;
+ int err;
+
+ skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
+
+ hdr = genlmsg_iput(skb, info);
+ if (!hdr) {
+ err = -EMSGSIZE;
+ goto err_free_msg;
+ }
+
+ mutex_lock(&nfsd_mutex);
+ nn = net_generic(genl_info_net(info), nfsd_net_id);
+
+ /* no nfs server? Just send empty socket list */
+ if (!nn->nfsd_serv)
+ goto out_unlock_mtx;
+
+ serv = nn->nfsd_serv;
+ spin_lock_bh(&serv->sv_lock);
+ list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list) {
+ struct nlattr *attr;
+
+ attr = nla_nest_start(skb, NFSD_A_SERVER_SOCK_ADDR);
+ if (!attr) {
+ err = -EINVAL;
+ goto err_serv_unlock;
+ }
+
+ if (nla_put_string(skb, NFSD_A_SOCK_TRANSPORT_NAME,
+ xprt->xpt_class->xcl_name) ||
+ nla_put(skb, NFSD_A_SOCK_ADDR,
+ sizeof(struct sockaddr_storage),
+ &xprt->xpt_local)) {
+ err = -EINVAL;
+ goto err_serv_unlock;
+ }
+
+ nla_nest_end(skb, attr);
+ }
+ spin_unlock_bh(&serv->sv_lock);
+out_unlock_mtx:
+ mutex_unlock(&nfsd_mutex);
+ genlmsg_end(skb, hdr);
+
+ return genlmsg_reply(skb, info);
+
+err_serv_unlock:
+ spin_unlock_bh(&serv->sv_lock);
+ mutex_unlock(&nfsd_mutex);
+err_free_msg:
+ nlmsg_free(skb);
+
+ return err;
+}
+
+/**
+ * nfsd_nl_pool_mode_set_doit - set the number of running threads
+ * @skb: reply buffer
+ * @info: netlink metadata and command arguments
+ *
+ * Return 0 on success or a negative errno.
+ */
+int nfsd_nl_pool_mode_set_doit(struct sk_buff *skb, struct genl_info *info)
+{
+ const struct nlattr *attr;
+
+ if (GENL_REQ_ATTR_CHECK(info, NFSD_A_POOL_MODE_MODE))
+ return -EINVAL;
+
+ attr = info->attrs[NFSD_A_POOL_MODE_MODE];
+ return sunrpc_set_pool_mode(nla_data(attr));
+}
+
+/**
+ * nfsd_nl_pool_mode_get_doit - get info about pool_mode
+ * @skb: reply buffer
+ * @info: netlink metadata and command arguments
+ *
+ * Return 0 on success or a negative errno.
+ */
+int nfsd_nl_pool_mode_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net *net = genl_info_net(info);
+ char buf[16];
+ void *hdr;
+ int err;
+
+ if (sunrpc_get_pool_mode(buf, ARRAY_SIZE(buf)) >= ARRAY_SIZE(buf))
+ return -ERANGE;
+
+ skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
+
+ err = -EMSGSIZE;
+ hdr = genlmsg_iput(skb, info);
+ if (!hdr)
+ goto err_free_msg;
+
+ err = nla_put_string(skb, NFSD_A_POOL_MODE_MODE, buf) |
+ nla_put_u32(skb, NFSD_A_POOL_MODE_NPOOLS, nfsd_nrpools(net));
+ if (err)
+ goto err_free_msg;
+
+ genlmsg_end(skb, hdr);
+ return genlmsg_reply(skb, info);
+
+err_free_msg:
+ nlmsg_free(skb);
+ return err;
+}
+
/**
* nfsd_net_init - Prepare the nfsd_net portion of a new net namespace
* @net: a freshly-created network namespace
@@ -1515,8 +2229,9 @@ unsigned int nfsd_net_id;
*/
static __net_init int nfsd_net_init(struct net *net)
{
- int retval;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ int retval;
+ int i;
retval = nfsd_export_init(net);
if (retval)
@@ -1524,20 +2239,34 @@ static __net_init int nfsd_net_init(struct net *net)
retval = nfsd_idmap_init(net);
if (retval)
goto out_idmap_error;
- retval = nfsd_stat_counters_init(nn);
+ retval = percpu_counter_init_many(nn->counter, 0, GFP_KERNEL,
+ NFSD_STATS_COUNTERS_NUM);
if (retval)
goto out_repcache_error;
+
memset(&nn->nfsd_svcstats, 0, sizeof(nn->nfsd_svcstats));
- nn->nfsd_svcstats.program = &nfsd_program;
- nn->nfsd_versions = NULL;
- nn->nfsd4_minorversions = NULL;
+ nn->nfsd_svcstats.program = &nfsd_programs[0];
+ if (!nfsd_proc_stat_init(net)) {
+ retval = -ENOMEM;
+ goto out_proc_error;
+ }
+
+ for (i = 0; i < sizeof(nn->nfsd_versions); i++)
+ nn->nfsd_versions[i] = nfsd_support_version(i);
+ for (i = 0; i < sizeof(nn->nfsd4_minorversions); i++)
+ nn->nfsd4_minorversions[i] = nfsd_support_version(4);
+ nn->nfsd_info.mutex = &nfsd_mutex;
+ nn->nfsd_serv = NULL;
nfsd4_init_leases_net(nn);
get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key));
seqlock_init(&nn->writeverf_lock);
- nfsd_proc_stat_init(net);
-
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+ INIT_LIST_HEAD(&nn->local_clients);
+#endif
return 0;
+out_proc_error:
+ percpu_counter_destroy_many(nn->counter, NFSD_STATS_COUNTERS_NUM);
out_repcache_error:
nfsd_idmap_shutdown(net);
out_idmap_error:
@@ -1546,6 +2275,22 @@ out_export_error:
return retval;
}
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+/**
+ * nfsd_net_pre_exit - Disconnect localio clients from net namespace
+ * @net: a network namespace that is about to be destroyed
+ *
+ * This invalidated ->net pointers held by localio clients
+ * while they can still safely access nn->counter.
+ */
+static __net_exit void nfsd_net_pre_exit(struct net *net)
+{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+ nfs_uuid_invalidate_clients(&nn->local_clients);
+}
+#endif
+
/**
* nfsd_net_exit - Release the nfsd_net portion of a net namespace
* @net: a network namespace that is about to be destroyed
@@ -1556,14 +2301,16 @@ static __net_exit void nfsd_net_exit(struct net *net)
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
nfsd_proc_stat_shutdown(net);
- nfsd_stat_counters_destroy(nn);
+ percpu_counter_destroy_many(nn->counter, NFSD_STATS_COUNTERS_NUM);
nfsd_idmap_shutdown(net);
nfsd_export_shutdown(net);
- nfsd_netns_free_versions(nn);
}
static struct pernet_operations nfsd_net_ops = {
.init = nfsd_net_init,
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+ .pre_exit = nfsd_net_pre_exit,
+#endif
.exit = nfsd_net_exit,
.id = &nfsd_net_id,
.size = sizeof(struct nfsd_net),
@@ -1583,12 +2330,9 @@ static int __init init_nfsd(void)
if (retval)
goto out_free_pnfs;
nfsd_lockd_init(); /* lockd->nfsd callbacks */
- retval = create_proc_exports_entry();
- if (retval)
- goto out_free_lockd;
retval = register_pernet_subsys(&nfsd_net_ops);
if (retval < 0)
- goto out_free_exports;
+ goto out_free_lockd;
retval = register_cld_notifier();
if (retval)
goto out_free_subsys;
@@ -1597,17 +2341,26 @@ static int __init init_nfsd(void)
goto out_free_cld;
retval = register_filesystem(&nfsd_fs_type);
if (retval)
+ goto out_free_nfsd4;
+ retval = genl_register_family(&nfsd_nl_family);
+ if (retval)
+ goto out_free_filesystem;
+ retval = create_proc_exports_entry();
+ if (retval)
goto out_free_all;
+ nfsd_localio_ops_init();
+
return 0;
out_free_all:
+ genl_unregister_family(&nfsd_nl_family);
+out_free_filesystem:
+ unregister_filesystem(&nfsd_fs_type);
+out_free_nfsd4:
nfsd4_destroy_laundry_wq();
out_free_cld:
unregister_cld_notifier();
out_free_subsys:
unregister_pernet_subsys(&nfsd_net_ops);
-out_free_exports:
- remove_proc_entry("fs/nfs/exports", NULL);
- remove_proc_entry("fs/nfs", NULL);
out_free_lockd:
nfsd_lockd_shutdown();
nfsd_drc_slab_free();
@@ -1620,13 +2373,14 @@ out_free_slabs:
static void __exit exit_nfsd(void)
{
+ remove_proc_entry("fs/nfs/exports", NULL);
+ remove_proc_entry("fs/nfs", NULL);
+ genl_unregister_family(&nfsd_nl_family);
unregister_filesystem(&nfsd_fs_type);
nfsd4_destroy_laundry_wq();
unregister_cld_notifier();
unregister_pernet_subsys(&nfsd_net_ops);
nfsd_drc_slab_free();
- remove_proc_entry("fs/nfs/exports", NULL);
- remove_proc_entry("fs/nfs", NULL);
nfsd_lockd_shutdown();
nfsd4_free_slabs();
nfsd4_exit_pnfs();