nfsd: containerize NFSd filesystem

This patch makes NFSD file system superblock to be created per net.
This makes possible to get proper network namespace from superblock instead of
using hard-coded "init_net".

Note: NFSd fs super-block holds network namespace. This garantees, that
network namespace won't disappear from underneath of it.
This, obviously, means, that in case of kill of a container's "init" (which is not a mount
namespace, but network namespace creator) netowrk namespace won't be
destroyed.

Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>

2 files changed, 35 insertions, 16 deletions

diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 29c3f0d25469..f6d448e6eb28 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -220,6 +220,7 @@ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size)
         struct sockaddr *sap = (struct sockaddr *)&address;
         size_t salen = sizeof(address);
         char *fo_path;
+        struct net *net = file->f_dentry->d_sb->s_fs_info;
 
         /* sanity check */
         if (size == 0)
@@ -232,7 +233,7 @@ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size)
         if (qword_get(&buf, fo_path, size) < 0)
                 return -EINVAL;
 
-        if (rpc_pton(&init_net, fo_path, size, sap, salen) == 0)
+        if (rpc_pton(net, fo_path, size, sap, salen) == 0)
                 return -EINVAL;
 
         return nlmsvc_unlock_all_by_ip(sap);
@@ -317,6 +318,7 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
         int len;
         struct auth_domain *dom;
         struct knfsd_fh fh;
+        struct net *net = file->f_dentry->d_sb->s_fs_info;
 
         if (size == 0)
                 return -EINVAL;
@@ -352,7 +354,7 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
         if (!dom)
                 return -ENOMEM;
 
-        len = exp_rootfh(&init_net, dom, path, &fh,  maxsize);
+        len = exp_rootfh(net, dom, path, &fh,  maxsize);
         auth_domain_put(dom);
         if (len)
                 return len;
@@ -396,7 +398,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
 {
         char *mesg = buf;
         int rv;
-        struct net *net = &init_net;
+        struct net *net = file->f_dentry->d_sb->s_fs_info;
 
         if (size > 0) {
                 int newthreads;
@@ -447,7 +449,7 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size)
         int len;
         int npools;
         int *nthreads;
-        struct net *net = &init_net;
+        struct net *net = file->f_dentry->d_sb->s_fs_info;
 
         mutex_lock(&nfsd_mutex);
         npools = nfsd_nrpools(net);
@@ -510,7 +512,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
         unsigned minor;
         ssize_t tlen = 0;
         char *sep;
-        struct net *net = &init_net;
+        struct net *net = file->f_dentry->d_sb->s_fs_info;
         struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
         if (size>0) {
@@ -792,7 +794,7 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size,
 static ssize_t write_ports(struct file *file, char *buf, size_t size)
 {
         ssize_t rv;
-        struct net *net = &init_net;
+        struct net *net = file->f_dentry->d_sb->s_fs_info;
 
         mutex_lock(&nfsd_mutex);
         rv = __write_ports(file, buf, size, net);
@@ -827,7 +829,7 @@ int nfsd_max_blksize;
 static ssize_t write_maxblksize(struct file *file, char *buf, size_t size)
 {
         char *mesg = buf;
-        struct net *net = &init_net;
+        struct net *net = file->f_dentry->d_sb->s_fs_info;
         struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
         if (size > 0) {
@@ -923,7 +925,8 @@ static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size,
  */
 static ssize_t write_leasetime(struct file *file, char *buf, size_t size)
 {
-        struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+        struct net *net = file->f_dentry->d_sb->s_fs_info;
+        struct nfsd_net *nn = net_generic(net, nfsd_net_id);
         return nfsd4_write_time(file, buf, size, &nn->nfsd4_lease, nn);
 }
 
@@ -939,7 +942,8 @@ 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)
 {
-        struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+        struct net *net = file->f_dentry->d_sb->s_fs_info;
+        struct nfsd_net *nn = net_generic(net, nfsd_net_id);
         return nfsd4_write_time(file, buf, size, &nn->nfsd4_grace, nn);
 }
 
@@ -995,7 +999,8 @@ static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size,
 static ssize_t write_recoverydir(struct file *file, char *buf, size_t size)
 {
         ssize_t rv;
-        struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+        struct net *net = file->f_dentry->d_sb->s_fs_info;
+        struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
         mutex_lock(&nfsd_mutex);
         rv = __write_recoverydir(file, buf, size, nn);
@@ -1037,20 +1042,35 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
 #endif
                 /* last one */ {""}
         };
-        return simple_fill_super(sb, 0x6e667364, nfsd_files);
+        struct net *net = data;
+        int ret;
+
+        ret = simple_fill_super(sb, 0x6e667364, nfsd_files);
+        if (ret)
+                return ret;
+        sb->s_fs_info = get_net(net);
+        return 0;
 }
 
 static struct dentry *nfsd_mount(struct file_system_type *fs_type,
         int flags, const char *dev_name, void *data)
 {
-        return mount_single(fs_type, flags, data, nfsd_fill_super);
+        return mount_ns(fs_type, flags, current->nsproxy->net_ns, nfsd_fill_super);
+}
+
+static void nfsd_umount(struct super_block *sb)
+{
+        struct net *net = sb->s_fs_info;
+
+        kill_litter_super(sb);
+        put_net(net);
 }
 
 static struct file_system_type nfsd_fs_type = {
         .owner          = THIS_MODULE,
         .name           = "nfsd",
         .mount          = nfsd_mount,
-        .kill_sb        = kill_litter_super,
+        .kill_sb        = nfsd_umount,
 };
 
 #ifdef CONFIG_PROC_FS
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 40cb1cbaba4e..6cee5db72047 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -702,8 +702,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 int nfsd_pool_stats_open(struct inode *inode, struct file *file)
 {
         int ret;
-        struct net *net = &init_net;
-        struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+        struct nfsd_net *nn = net_generic(inode->i_sb->s_fs_info, nfsd_net_id);
 
         mutex_lock(&nfsd_mutex);
         if (nn->nfsd_serv == NULL) {
@@ -720,7 +719,7 @@ int nfsd_pool_stats_open(struct inode *inode, struct file *file)
 int nfsd_pool_stats_release(struct inode *inode, struct file *file)
 {
         int ret = seq_release(inode, file);
-        struct net *net = &init_net;
+        struct net *net = inode->i_sb->s_fs_info;
 
         mutex_lock(&nfsd_mutex);
         /* this function really, really should have been called svc_put() */