super.c

linux 内核源代码

/*
 *  linux/fs/nfs/super.c
 *
 *  Copyright (C) 1992  Rick Sladkey
 *
 *  nfs superblock handling functions
 *
 *  Modularised by Alan Cox <[e-mail]>, while hacking some
 *  experimental NFS changes. Modularisation taken straight from SYS5 fs.
 *
 *  Change to nfs_read_super() to permit NFS mounts to multi-homed hosts.
 *  [e-mail]
 *
 *  Split from inode.c by David Howells <[e-mail]>
 *
 * - superblocks are indexed on server only - all inodes, dentries, etc. associated with a
 *   particular server are held in the same superblock
 * - NFS superblocks can have several effective roots to the dentry tree
 * - directory type roots are spliced into the tree when a path from one root reaches the root
 *   of another (see nfs_lookup())
 */

#include <linux/module.h>
#include <linux/init.h>

#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/errno.h>
#include <linux/unistd.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/metrics.h>
#include <linux/sunrpc/xprtsock.h>
#include <linux/sunrpc/xprtrdma.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/nfs4_mount.h>
#include <linux/lockd/bind.h>
#include <linux/smp_lock.h>
#include <linux/seq_file.h>
#include <linux/mount.h>
#include <linux/nfs_idmap.h>
#include <linux/vfs.h>
#include <linux/inet.h>
#include <linux/nfs_xdr.h>
#include <linux/magic.h>
#include <linux/parser.h>

#include <asm/system.h>
#include <asm/uaccess.h>

#include "nfs4_fs.h"
#include "callback.h"
#include "delegation.h"
#include "iostat.h"
#include "internal.h"

#define NFSDBG_FACILITY		NFSDBG_VFS

enum {
	/* Mount options that take no arguments */
	Opt_soft, Opt_hard,
	Opt_intr, Opt_nointr,
	Opt_posix, Opt_noposix,
	Opt_cto, Opt_nocto,
	Opt_ac, Opt_noac,
	Opt_lock, Opt_nolock,
	Opt_v2, Opt_v3,
	Opt_udp, Opt_tcp, Opt_rdma,
	Opt_acl, Opt_noacl,
	Opt_rdirplus, Opt_nordirplus,
	Opt_sharecache, Opt_nosharecache,

	/* Mount options that take integer arguments */
	Opt_port,
	Opt_rsize, Opt_wsize, Opt_bsize,
	Opt_timeo, Opt_retrans,
	Opt_acregmin, Opt_acregmax,
	Opt_acdirmin, Opt_acdirmax,
	Opt_actimeo,
	Opt_namelen,
	Opt_mountport,
	Opt_mountprog, Opt_mountvers,
	Opt_nfsprog, Opt_nfsvers,

	/* Mount options that take string arguments */
	Opt_sec, Opt_proto, Opt_mountproto,
	Opt_addr, Opt_mountaddr, Opt_clientaddr,

	/* Mount options that are ignored */
	Opt_userspace, Opt_deprecated,

	Opt_err
};

static match_table_t nfs_mount_option_tokens = {
	{ Opt_userspace, "bg" },
	{ Opt_userspace, "fg" },
	{ Opt_soft, "soft" },
	{ Opt_hard, "hard" },
	{ Opt_intr, "intr" },
	{ Opt_nointr, "nointr" },
	{ Opt_posix, "posix" },
	{ Opt_noposix, "noposix" },
	{ Opt_cto, "cto" },
	{ Opt_nocto, "nocto" },
	{ Opt_ac, "ac" },
	{ Opt_noac, "noac" },
	{ Opt_lock, "lock" },
	{ Opt_nolock, "nolock" },
	{ Opt_v2, "v2" },
	{ Opt_v3, "v3" },
	{ Opt_udp, "udp" },
	{ Opt_tcp, "tcp" },
	{ Opt_rdma, "rdma" },
	{ Opt_acl, "acl" },
	{ Opt_noacl, "noacl" },
	{ Opt_rdirplus, "rdirplus" },
	{ Opt_nordirplus, "nordirplus" },
	{ Opt_sharecache, "sharecache" },
	{ Opt_nosharecache, "nosharecache" },

	{ Opt_port, "port=%u" },
	{ Opt_rsize, "rsize=%u" },
	{ Opt_wsize, "wsize=%u" },
	{ Opt_bsize, "bsize=%u" },
	{ Opt_timeo, "timeo=%u" },
	{ Opt_retrans, "retrans=%u" },
	{ Opt_acregmin, "acregmin=%u" },
	{ Opt_acregmax, "acregmax=%u" },
	{ Opt_acdirmin, "acdirmin=%u" },
	{ Opt_acdirmax, "acdirmax=%u" },
	{ Opt_actimeo, "actimeo=%u" },
	{ Opt_userspace, "retry=%u" },
	{ Opt_namelen, "namlen=%u" },
	{ Opt_mountport, "mountport=%u" },
	{ Opt_mountprog, "mountprog=%u" },
	{ Opt_mountvers, "mountvers=%u" },
	{ Opt_nfsprog, "nfsprog=%u" },
	{ Opt_nfsvers, "nfsvers=%u" },
	{ Opt_nfsvers, "vers=%u" },

	{ Opt_sec, "sec=%s" },
	{ Opt_proto, "proto=%s" },
	{ Opt_mountproto, "mountproto=%s" },
	{ Opt_addr, "addr=%s" },
	{ Opt_clientaddr, "clientaddr=%s" },
	{ Opt_userspace, "mounthost=%s" },
	{ Opt_mountaddr, "mountaddr=%s" },

	{ Opt_err, NULL }
};

enum {
	Opt_xprt_udp, Opt_xprt_tcp, Opt_xprt_rdma,

	Opt_xprt_err
};

static match_table_t nfs_xprt_protocol_tokens = {
	{ Opt_xprt_udp, "udp" },
	{ Opt_xprt_tcp, "tcp" },
	{ Opt_xprt_rdma, "rdma" },

	{ Opt_xprt_err, NULL }
};

enum {
	Opt_sec_none, Opt_sec_sys,
	Opt_sec_krb5, Opt_sec_krb5i, Opt_sec_krb5p,
	Opt_sec_lkey, Opt_sec_lkeyi, Opt_sec_lkeyp,
	Opt_sec_spkm, Opt_sec_spkmi, Opt_sec_spkmp,

	Opt_sec_err
};

static match_table_t nfs_secflavor_tokens = {
	{ Opt_sec_none, "none" },
	{ Opt_sec_none, "null" },
	{ Opt_sec_sys, "sys" },

	{ Opt_sec_krb5, "krb5" },
	{ Opt_sec_krb5i, "krb5i" },
	{ Opt_sec_krb5p, "krb5p" },

	{ Opt_sec_lkey, "lkey" },
	{ Opt_sec_lkeyi, "lkeyi" },
	{ Opt_sec_lkeyp, "lkeyp" },

	{ Opt_sec_err, NULL }
};


static void nfs_umount_begin(struct vfsmount *, int);
static int  nfs_statfs(struct dentry *, struct kstatfs *);
static int  nfs_show_options(struct seq_file *, struct vfsmount *);
static int  nfs_show_stats(struct seq_file *, struct vfsmount *);
static int nfs_get_sb(struct file_system_type *, int, const char *, void *, struct vfsmount *);
static int nfs_xdev_get_sb(struct file_system_type *fs_type,
		int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
static void nfs_kill_super(struct super_block *);

static struct file_system_type nfs_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "nfs",
	.get_sb		= nfs_get_sb,
	.kill_sb	= nfs_kill_super,
	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
};

struct file_system_type nfs_xdev_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "nfs",
	.get_sb		= nfs_xdev_get_sb,
	.kill_sb	= nfs_kill_super,
	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
};

static const struct super_operations nfs_sops = {
	.alloc_inode	= nfs_alloc_inode,
	.destroy_inode	= nfs_destroy_inode,
	.write_inode	= nfs_write_inode,
	.statfs		= nfs_statfs,
	.clear_inode	= nfs_clear_inode,
	.umount_begin	= nfs_umount_begin,
	.show_options	= nfs_show_options,
	.show_stats	= nfs_show_stats,
};

#ifdef CONFIG_NFS_V4
static int nfs4_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
static int nfs4_xdev_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
static int nfs4_referral_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
static void nfs4_kill_super(struct super_block *sb);

static struct file_system_type nfs4_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "nfs4",
	.get_sb		= nfs4_get_sb,
	.kill_sb	= nfs4_kill_super,
	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
};

struct file_system_type nfs4_xdev_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "nfs4",
	.get_sb		= nfs4_xdev_get_sb,
	.kill_sb	= nfs4_kill_super,
	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
};

struct file_system_type nfs4_referral_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "nfs4",
	.get_sb		= nfs4_referral_get_sb,
	.kill_sb	= nfs4_kill_super,
	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
};

static const struct super_operations nfs4_sops = {
	.alloc_inode	= nfs_alloc_inode,
	.destroy_inode	= nfs_destroy_inode,
	.write_inode	= nfs_write_inode,
	.statfs		= nfs_statfs,
	.clear_inode	= nfs4_clear_inode,
	.umount_begin	= nfs_umount_begin,
	.show_options	= nfs_show_options,
	.show_stats	= nfs_show_stats,
};
#endif

static struct shrinker acl_shrinker = {
	.shrink		= nfs_access_cache_shrinker,
	.seeks		= DEFAULT_SEEKS,
};

/*
 * Register the NFS filesystems
 */
int __init register_nfs_fs(void)
{
	int ret;

        ret = register_filesystem(&nfs_fs_type);
	if (ret < 0)
		goto error_0;

	ret = nfs_register_sysctl();
	if (ret < 0)
		goto error_1;
#ifdef CONFIG_NFS_V4
	ret = register_filesystem(&nfs4_fs_type);
	if (ret < 0)
		goto error_2;
#endif
	register_shrinker(&acl_shrinker);
	return 0;

#ifdef CONFIG_NFS_V4
error_2:
	nfs_unregister_sysctl();
#endif
error_1:
	unregister_filesystem(&nfs_fs_type);
error_0:
	return ret;
}

/*
 * Unregister the NFS filesystems
 */
void __exit unregister_nfs_fs(void)
{
	unregister_shrinker(&acl_shrinker);
#ifdef CONFIG_NFS_V4
	unregister_filesystem(&nfs4_fs_type);
#endif
	nfs_unregister_sysctl();
	unregister_filesystem(&nfs_fs_type);
}

/*
 * Deliver file system statistics to userspace
 */
static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct nfs_server *server = NFS_SB(dentry->d_sb);
	unsigned char blockbits;
	unsigned long blockres;
	struct nfs_fh *fh = NFS_FH(dentry->d_inode);
	struct nfs_fattr fattr;
	struct nfs_fsstat res = {
			.fattr = &fattr,
	};
	int error;

	lock_kernel();

	error = server->nfs_client->rpc_ops->statfs(server, fh, &res);
	if (error < 0)
		goto out_err;
	buf->f_type = NFS_SUPER_MAGIC;

	/*
	 * Current versions of glibc do not correctly handle the
	 * case where f_frsize != f_bsize.  Eventually we want to
	 * report the value of wtmult in this field.
	 */
	buf->f_frsize = dentry->d_sb->s_blocksize;

	/*
	 * On most *nix systems, f_blocks, f_bfree, and f_bavail
	 * are reported in units of f_frsize.  Linux hasn't had
	 * an f_frsize field in its statfs struct until recently,
	 * thus historically Linux's sys_statfs reports these
	 * fields in units of f_bsize.
	 */
	buf->f_bsize = dentry->d_sb->s_blocksize;
	blockbits = dentry->d_sb->s_blocksize_bits;
	blockres = (1 << blockbits) - 1;
	buf->f_blocks = (res.tbytes + blockres) >> blockbits;
	buf->f_bfree = (res.fbytes + blockres) >> blockbits;
	buf->f_bavail = (res.abytes + blockres) >> blockbits;

	buf->f_files = res.tfiles;
	buf->f_ffree = res.afiles;

	buf->f_namelen = server->namelen;

	unlock_kernel();
	return 0;

 out_err:
	dprintk("%s: statfs error = %d\n", __FUNCTION__, -error);
	unlock_kernel();
	return error;
}

/*
 * Map the security flavour number to a name
 */
static const char *nfs_pseudoflavour_to_name(rpc_authflavor_t flavour)
{
	static const struct {
		rpc_authflavor_t flavour;
		const char *str;
	} sec_flavours[] = {
		{ RPC_AUTH_NULL, "null" },
		{ RPC_AUTH_UNIX, "sys" },
		{ RPC_AUTH_GSS_KRB5, "krb5" },
		{ RPC_AUTH_GSS_KRB5I, "krb5i" },
		{ RPC_AUTH_GSS_KRB5P, "krb5p" },
		{ RPC_AUTH_GSS_LKEY, "lkey" },
		{ RPC_AUTH_GSS_LKEYI, "lkeyi" },
		{ RPC_AUTH_GSS_LKEYP, "lkeyp" },
		{ RPC_AUTH_GSS_SPKM, "spkm" },
		{ RPC_AUTH_GSS_SPKMI, "spkmi" },
		{ RPC_AUTH_GSS_SPKMP, "spkmp" },
		{ UINT_MAX, "unknown" }
	};
	int i;

	for (i = 0; sec_flavours[i].flavour != UINT_MAX; i++) {
		if (sec_flavours[i].flavour == flavour)
			break;
	}
	return sec_flavours[i].str;
}

/*
 * Describe the mount options in force on this server representation
 */
static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, int showdefaults)
{
	static const struct proc_nfs_info {
		int flag;
		const char *str;
		const char *nostr;
	} nfs_info[] = {
		{ NFS_MOUNT_SOFT, ",soft", ",hard" },
		{ NFS_MOUNT_INTR, ",intr", ",nointr" },
		{ NFS_MOUNT_NOCTO, ",nocto", "" },
		{ NFS_MOUNT_NOAC, ",noac", "" },
		{ NFS_MOUNT_NONLM, ",nolock", "" },
		{ NFS_MOUNT_NOACL, ",noacl", "" },
		{ NFS_MOUNT_NORDIRPLUS, ",nordirplus", "" },
		{ NFS_MOUNT_UNSHARED, ",nosharecache", ""},
		{ 0, NULL, NULL }
	};
	const struct proc_nfs_info *nfs_infop;
	struct nfs_client *clp = nfss->nfs_client;

	seq_printf(m, ",vers=%d", clp->rpc_ops->version);
	seq_printf(m, ",rsize=%d", nfss->rsize);
	seq_printf(m, ",wsize=%d", nfss->wsize);
	if (nfss->acregmin != 3*HZ || showdefaults)
		seq_printf(m, ",acregmin=%d", nfss->acregmin/HZ);
	if (nfss->acregmax != 60*HZ || showdefaults)
		seq_printf(m, ",acregmax=%d", nfss->acregmax/HZ);
	if (nfss->acdirmin != 30*HZ || showdefaults)
		seq_printf(m, ",acdirmin=%d", nfss->acdirmin/HZ);
	if (nfss->acdirmax != 60*HZ || showdefaults)
		seq_printf(m, ",acdirmax=%d", nfss->acdirmax/HZ);
	for (nfs_infop = nfs_info; nfs_infop->flag; nfs_infop++) {
		if (nfss->flags & nfs_infop->flag)
			seq_puts(m, nfs_infop->str);
		else
			seq_puts(m, nfs_infop->nostr);
	}
	seq_printf(m, ",proto=%s",
		   rpc_peeraddr2str(nfss->client, RPC_DISPLAY_PROTO));
	seq_printf(m, ",timeo=%lu", 10U * clp->retrans_timeo / HZ);
	seq_printf(m, ",retrans=%u", clp->retrans_count);
	seq_printf(m, ",sec=%s", nfs_pseudoflavour_to_name(nfss->client->cl_auth->au_flavor));
}

/*
 * Describe the mount options on this VFS mountpoint
 */
static int nfs_show_options(struct seq_file *m, struct vfsmount *mnt)
{
	struct nfs_server *nfss = NFS_SB(mnt->mnt_sb);

	nfs_show_mount_options(m, nfss, 0);

	seq_printf(m, ",addr="NIPQUAD_FMT,
		NIPQUAD(nfss->nfs_client->cl_addr.sin_addr));

	return 0;
}

/*
 * Present statistical information for this VFS mountpoint
 */
static int nfs_show_stats(struct seq_file *m, struct vfsmount *mnt)
{
	int i, cpu;
	struct nfs_server *nfss = NFS_SB(mnt->mnt_sb);