1 files changed, 173 insertions, 93 deletions

diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 348b535cd786..5a4d193da1a9 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * linux/fs/nfs/namespace.c
  *
@@ -18,6 +19,7 @@
 #include <linux/vfs.h>
 #include <linux/sunrpc/gss_api.h>
 #include "internal.h"
+#include "nfs.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
 
@@ -30,9 +32,9 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ;
 /*
  * nfs_path - reconstruct the path given an arbitrary dentry
  * @base - used to return pointer to the end of devname part of path
- * @dentry - pointer to dentry
+ * @dentry_in - pointer to dentry
  * @buffer - result buffer
- * @buflen - length of buffer
+ * @buflen_in - length of buffer
  * @flags - options (see below)
  *
  * Helper function for constructing the server pathname
@@ -47,15 +49,19 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ;
  *		       the original device (export) name
  *		       (if unset, the original name is returned verbatim)
  */
-char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen,
-	       unsigned flags)
+char *nfs_path(char **p, struct dentry *dentry_in, char *buffer,
+	       ssize_t buflen_in, unsigned flags)
 {
 	char *end;
 	int namelen;
 	unsigned seq;
 	const char *base;
+	struct dentry *dentry;
+	ssize_t buflen;
 
 rename_retry:
+	buflen = buflen_in;
+	dentry = dentry_in;
 	end = buffer+buflen;
 	*--end = '\0';
 	buflen--;
@@ -98,7 +104,7 @@ rename_retry:
 		return end;
 	}
 	namelen = strlen(base);
-	if (flags & NFS_PATH_CANONICAL) {
+	if (*end == '/') {
 		/* Strip off excess slashes in base string */
 		while (namelen > 0 && base[namelen - 1] == '/')
 			namelen--;
@@ -138,59 +144,87 @@ EXPORT_SYMBOL_GPL(nfs_path);
  */
 struct vfsmount *nfs_d_automount(struct path *path)
 {
-	struct vfsmount *mnt;
-	struct nfs_server *server = NFS_SERVER(path->dentry->d_inode);
-	struct nfs_fh *fh = NULL;
-	struct nfs_fattr *fattr = NULL;
-
-	dprintk("--> nfs_d_automount()\n");
+	struct nfs_fs_context *ctx;
+	struct fs_context *fc;
+	struct vfsmount *mnt = ERR_PTR(-ENOMEM);
+	struct nfs_server *server = NFS_SB(path->dentry->d_sb);
+	struct nfs_client *client = server->nfs_client;
+	int timeout = READ_ONCE(nfs_mountpoint_expiry_timeout);
+	int ret;
 
-	mnt = ERR_PTR(-ESTALE);
 	if (IS_ROOT(path->dentry))
-		goto out_nofree;
+		return ERR_PTR(-ESTALE);
+
+	/* Open a new filesystem context, transferring parameters from the
+	 * parent superblock, including the network namespace.
+	 */
+	fc = fs_context_for_submount(path->mnt->mnt_sb->s_type, path->dentry);
+	if (IS_ERR(fc))
+		return ERR_CAST(fc);
+
+	ctx = nfs_fc2context(fc);
+	ctx->clone_data.dentry	= path->dentry;
+	ctx->clone_data.sb	= path->dentry->d_sb;
+	ctx->clone_data.fattr	= nfs_alloc_fattr();
+	if (!ctx->clone_data.fattr)
+		goto out_fc;
+
+	if (fc->net_ns != client->cl_net) {
+		put_net(fc->net_ns);
+		fc->net_ns = get_net(client->cl_net);
+	}
+
+	/* for submounts we want the same server; referrals will reassign */
+	memcpy(&ctx->nfs_server._address, &client->cl_addr, client->cl_addrlen);
+	ctx->nfs_server.addrlen	= client->cl_addrlen;
+	ctx->nfs_server.port	= server->port;
 
-	mnt = ERR_PTR(-ENOMEM);
-	fh = nfs_alloc_fhandle();
-	fattr = nfs_alloc_fattr();
-	if (fh == NULL || fattr == NULL)
-		goto out;
+	ctx->version		= client->rpc_ops->version;
+	ctx->minorversion	= client->cl_minorversion;
+	ctx->nfs_mod		= client->cl_nfs_mod;
+	get_nfs_version(ctx->nfs_mod);
 
-	dprintk("%s: enter\n", __func__);
+	ret = client->rpc_ops->submount(fc, server);
+	if (ret < 0) {
+		mnt = ERR_PTR(ret);
+		goto out_fc;
+	}
 
-	mnt = server->nfs_client->rpc_ops->submount(server, path->dentry, fh, fattr);
+	up_write(&fc->root->d_sb->s_umount);
+	mnt = vfs_create_mount(fc);
 	if (IS_ERR(mnt))
-		goto out;
+		goto out_fc;
+
+	if (timeout <= 0)
+		goto out_fc;
 
-	dprintk("%s: done, success\n", __func__);
-	mntget(mnt); /* prevent immediate expiration */
 	mnt_set_expiry(mnt, &nfs_automount_list);
-	schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout);
+	schedule_delayed_work(&nfs_automount_task, timeout);
 
-out:
-	nfs_free_fattr(fattr);
-	nfs_free_fhandle(fh);
-out_nofree:
-	if (IS_ERR(mnt))
-		dprintk("<-- %s(): error %ld\n", __func__, PTR_ERR(mnt));
-	else
-		dprintk("<-- %s() = %p\n", __func__, mnt);
+out_fc:
+	put_fs_context(fc);
 	return mnt;
 }
 
 static int
-nfs_namespace_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+nfs_namespace_getattr(struct mnt_idmap *idmap,
+		      const struct path *path, struct kstat *stat,
+		      u32 request_mask, unsigned int query_flags)
 {
-	if (NFS_FH(dentry->d_inode)->size != 0)
-		return nfs_getattr(mnt, dentry, stat);
-	generic_fillattr(dentry->d_inode, stat);
+	if (NFS_FH(d_inode(path->dentry))->size != 0)
+		return nfs_getattr(idmap, path, stat, request_mask,
+				   query_flags);
+	generic_fillattr(&nop_mnt_idmap, request_mask, d_inode(path->dentry),
+			 stat);
 	return 0;
 }
 
 static int
-nfs_namespace_setattr(struct dentry *dentry, struct iattr *attr)
+nfs_namespace_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+		      struct iattr *attr)
 {
-	if (NFS_FH(dentry->d_inode)->size != 0)
-		return nfs_setattr(dentry, attr);
+	if (NFS_FH(d_inode(dentry))->size != 0)
+		return nfs_setattr(idmap, dentry, attr);
 	return -EACCES;
 }
 
@@ -207,10 +241,11 @@ const struct inode_operations nfs_referral_inode_operations = {
 static void nfs_expire_automounts(struct work_struct *work)
 {
 	struct list_head *list = &nfs_automount_list;
+	int timeout = READ_ONCE(nfs_mountpoint_expiry_timeout);
 
 	mark_mounts_for_expiry(list);
-	if (!list_empty(list))
-		schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout);
+	if (!list_empty(list) && timeout > 0)
+		schedule_delayed_work(&nfs_automount_task, timeout);
 }
 
 void nfs_release_automount_timer(void)
@@ -219,72 +254,117 @@ void nfs_release_automount_timer(void)
 		cancel_delayed_work(&nfs_automount_task);
 }
 
-/*
- * Clone a mountpoint of the appropriate type
- */
-static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server,
-					   const char *devname,
-					   struct nfs_clone_mount *mountdata)
-{
-	return vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata);
-}
-
 /**
  * nfs_do_submount - set up mountpoint when crossing a filesystem boundary
- * @dentry - parent directory
- * @fh - filehandle for new root dentry
- * @fattr - attributes for new root inode
- * @authflavor - security flavor to use when performing the mount
+ * @fc: pointer to struct nfs_fs_context
  *
  */
-struct vfsmount *nfs_do_submount(struct dentry *dentry, struct nfs_fh *fh,
-				 struct nfs_fattr *fattr, rpc_authflavor_t authflavor)
+int nfs_do_submount(struct fs_context *fc)
 {
-	struct nfs_clone_mount mountdata = {
-		.sb = dentry->d_sb,
-		.dentry = dentry,
-		.fh = fh,
-		.fattr = fattr,
-		.authflavor = authflavor,
-	};
-	struct vfsmount *mnt = ERR_PTR(-ENOMEM);
-	char *page = (char *) __get_free_page(GFP_USER);
-	char *devname;
-
-	dprintk("--> nfs_do_submount()\n");
-
-	dprintk("%s: submounting on %s/%s\n", __func__,
-			dentry->d_parent->d_name.name,
-			dentry->d_name.name);
-	if (page == NULL)
-		goto out;
-	devname = nfs_devname(dentry, page, PAGE_SIZE);
-	mnt = (struct vfsmount *)devname;
-	if (IS_ERR(devname))
-		goto free_page;
-	mnt = nfs_do_clone_mount(NFS_SB(dentry->d_sb), devname, &mountdata);
-free_page:
-	free_page((unsigned long)page);
-out:
-	dprintk("%s: done\n", __func__);
-
-	dprintk("<-- nfs_do_submount() = %p\n", mnt);
-	return mnt;
+	struct nfs_fs_context *ctx = nfs_fc2context(fc);
+	struct dentry *dentry = ctx->clone_data.dentry;
+	struct nfs_server *server;
+	char *buffer, *p;
+	int ret;
+
+	/* create a new volume representation */
+	server = ctx->nfs_mod->rpc_ops->clone_server(NFS_SB(ctx->clone_data.sb),
+						     ctx->mntfh,
+						     ctx->clone_data.fattr,
+						     ctx->selected_flavor);
+
+	if (IS_ERR(server))
+		return PTR_ERR(server);
+
+	ctx->server = server;
+
+	buffer = kmalloc(4096, GFP_USER);
+	if (!buffer)
+		return -ENOMEM;
+
+	ctx->internal		= true;
+	ctx->clone_data.inherited_bsize = ctx->clone_data.sb->s_blocksize_bits;
+
+	p = nfs_devname(dentry, buffer, 4096);
+	if (IS_ERR(p)) {
+		nfs_errorf(fc, "NFS: Couldn't determine submount pathname");
+		ret = PTR_ERR(p);
+	} else {
+		ret = vfs_parse_fs_qstr(fc, "source",
+					&QSTR_LEN(p, buffer + 4096 - p));
+		if (!ret)
+			ret = vfs_get_tree(fc);
+	}
+	kfree(buffer);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(nfs_do_submount);
 
-struct vfsmount *nfs_submount(struct nfs_server *server, struct dentry *dentry,
-			      struct nfs_fh *fh, struct nfs_fattr *fattr)
+int nfs_submount(struct fs_context *fc, struct nfs_server *server)
 {
-	int err;
+	struct nfs_fs_context *ctx = nfs_fc2context(fc);
+	struct dentry *dentry = ctx->clone_data.dentry;
 	struct dentry *parent = dget_parent(dentry);
+	int err;
 
 	/* Look it up again to get its attributes */
-	err = server->nfs_client->rpc_ops->lookup(parent->d_inode, &dentry->d_name, fh, fattr, NULL);
+	err = server->nfs_client->rpc_ops->lookup(d_inode(parent), dentry, &dentry->d_name,
+						  ctx->mntfh, ctx->clone_data.fattr);
 	dput(parent);
 	if (err != 0)
-		return ERR_PTR(err);
+		return err;
 
-	return nfs_do_submount(dentry, fh, fattr, server->client->cl_auth->au_flavor);
+	ctx->selected_flavor = server->client->cl_auth->au_flavor;
+	return nfs_do_submount(fc);
 }
 EXPORT_SYMBOL_GPL(nfs_submount);
+
+static int param_set_nfs_timeout(const char *val, const struct kernel_param *kp)
+{
+	long num;
+	int ret;
+
+	if (!val)
+		return -EINVAL;
+	ret = kstrtol(val, 0, &num);
+	if (ret)
+		return -EINVAL;
+	if (num > 0) {
+		if (num >= INT_MAX / HZ)
+			num = INT_MAX;
+		else
+			num *= HZ;
+		*((int *)kp->arg) = num;
+		if (!list_empty(&nfs_automount_list))
+			mod_delayed_work(system_percpu_wq, &nfs_automount_task, num);
+	} else {
+		*((int *)kp->arg) = -1*HZ;
+		cancel_delayed_work(&nfs_automount_task);
+	}
+	return 0;
+}
+
+static int param_get_nfs_timeout(char *buffer, const struct kernel_param *kp)
+{
+	long num = *((int *)kp->arg);
+
+	if (num > 0) {
+		if (num >= INT_MAX - (HZ - 1))
+			num = INT_MAX / HZ;
+		else
+			num = (num + (HZ - 1)) / HZ;
+	} else
+		num = -1;
+	return sysfs_emit(buffer, "%li\n", num);
+}
+
+static const struct kernel_param_ops param_ops_nfs_timeout = {
+	.set = param_set_nfs_timeout,
+	.get = param_get_nfs_timeout,
+};
+#define param_check_nfs_timeout(name, p) __param_check(name, p, int)
+
+module_param(nfs_mountpoint_expiry_timeout, nfs_timeout, 0644);
+MODULE_PARM_DESC(nfs_mountpoint_expiry_timeout,
+		"Set the NFS automounted mountpoint timeout value (seconds)."
+		"Values <= 0 turn expiration off.");