*
*/
-#include <linux/config.h>
#include <linux/module.h>
#include <linux/init.h>
-
+#include <linux/sched.h>
#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include "callback.h"
#include "delegation.h"
#include "iostat.h"
+#include "internal.h"
#define NFSDBG_FACILITY NFSDBG_VFS
-#define NFS_PARANOIA 1
-/* Maximum number of readahead requests
- * FIXME: this should really be a sysctl so that users may tune it to suit
- * their needs. People that do NFS over a slow network, might for
- * instance want to reduce it to something closer to 1 for improved
- * interactive response.
- */
-#define NFS_MAX_READAHEAD (RPC_DEF_SLOT_TABLE - 1)
+#define NFS_64_BIT_INODE_NUMBERS_ENABLED 1
+
+/* Default is to see 64-bit inode numbers */
+static int enable_ino64 = NFS_64_BIT_INODE_NUMBERS_ENABLED;
static void nfs_invalidate_inode(struct inode *);
static int nfs_update_inode(struct inode *, struct nfs_fattr *);
-static struct inode *nfs_alloc_inode(struct super_block *sb);
-static void nfs_destroy_inode(struct inode *);
-static int nfs_write_inode(struct inode *,int);
-static void nfs_clear_inode(struct inode *);
-static void nfs_umount_begin(struct vfsmount *, int);
-static int nfs_statfs(struct super_block *, struct kstatfs *);
-static int nfs_show_options(struct seq_file *, struct vfsmount *);
-static int nfs_show_stats(struct seq_file *, struct vfsmount *);
-static void nfs_zap_acl_cache(struct inode *);
-
-static struct rpc_program nfs_program;
-
-static 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,
-};
-
-/*
- * RPC cruft for NFS
- */
-static struct rpc_stat nfs_rpcstat = {
- .program = &nfs_program
-};
-static struct rpc_version * nfs_version[] = {
- NULL,
- NULL,
- &nfs_version2,
-#if defined(CONFIG_NFS_V3)
- &nfs_version3,
-#elif defined(CONFIG_NFS_V4)
- NULL,
-#endif
-#if defined(CONFIG_NFS_V4)
- &nfs_version4,
-#endif
-};
-
-static struct rpc_program nfs_program = {
- .name = "nfs",
- .number = NFS_PROGRAM,
- .nrvers = ARRAY_SIZE(nfs_version),
- .version = nfs_version,
- .stats = &nfs_rpcstat,
- .pipe_dir_name = "/nfs",
-};
-
-#ifdef CONFIG_NFS_V3_ACL
-static struct rpc_stat nfsacl_rpcstat = { &nfsacl_program };
-static struct rpc_version * nfsacl_version[] = {
- [3] = &nfsacl_version3,
-};
-
-struct rpc_program nfsacl_program = {
- .name = "nfsacl",
- .number = NFS_ACL_PROGRAM,
- .nrvers = ARRAY_SIZE(nfsacl_version),
- .version = nfsacl_version,
- .stats = &nfsacl_rpcstat,
-};
-#endif /* CONFIG_NFS_V3_ACL */
+static struct kmem_cache * nfs_inode_cachep;
static inline unsigned long
nfs_fattr_to_ino_t(struct nfs_fattr *fattr)
return nfs_fileid_to_ino_t(fattr->fileid);
}
-static int
-nfs_write_inode(struct inode *inode, int sync)
-{
- int flags = sync ? FLUSH_SYNC : 0;
- int ret;
-
- ret = nfs_commit_inode(inode, flags);
- if (ret < 0)
- return ret;
- return 0;
-}
-
-static void
-nfs_clear_inode(struct inode *inode)
-{
- struct nfs_inode *nfsi = NFS_I(inode);
- struct rpc_cred *cred;
-
- /*
- * The following should never happen...
- */
- BUG_ON(nfs_have_writebacks(inode));
- BUG_ON (!list_empty(&nfsi->open_files));
- nfs_zap_acl_cache(inode);
- cred = nfsi->cache_access.cred;
- if (cred)
- put_rpccred(cred);
- BUG_ON(atomic_read(&nfsi->data_updates) != 0);
-}
-
-static void nfs_umount_begin(struct vfsmount *vfsmnt, int flags)
-{
- struct nfs_server *server;
- struct rpc_clnt *rpc;
-
- shrink_submounts(vfsmnt, &nfs_automount_list);
- if (!(flags & MNT_FORCE))
- return;
- /* -EIO all pending I/O */
- server = NFS_SB(vfsmnt->mnt_sb);
- rpc = server->client;
- if (!IS_ERR(rpc))
- rpc_killall_tasks(rpc);
- rpc = server->client_acl;
- if (!IS_ERR(rpc))
- rpc_killall_tasks(rpc);
-}
-
-
-static inline unsigned long
-nfs_block_bits(unsigned long bsize, unsigned char *nrbitsp)
-{
- /* make sure blocksize is a power of two */
- if ((bsize & (bsize - 1)) || nrbitsp) {
- unsigned char nrbits;
-
- for (nrbits = 31; nrbits && !(bsize & (1 << nrbits)); nrbits--)
- ;
- bsize = 1 << nrbits;
- if (nrbitsp)
- *nrbitsp = nrbits;
- }
-
- return bsize;
-}
-
-/*
- * Calculate the number of 512byte blocks used.
- */
-static inline unsigned long
-nfs_calc_block_size(u64 tsize)
-{
- loff_t used = (tsize + 511) >> 9;
- return (used > ULONG_MAX) ? ULONG_MAX : used;
-}
-
-/*
- * Compute and set NFS server blocksize
- */
-static inline unsigned long
-nfs_block_size(unsigned long bsize, unsigned char *nrbitsp)
-{
- if (bsize < NFS_MIN_FILE_IO_SIZE)
- bsize = NFS_DEF_FILE_IO_SIZE;
- else if (bsize >= NFS_MAX_FILE_IO_SIZE)
- bsize = NFS_MAX_FILE_IO_SIZE;
-
- return nfs_block_bits(bsize, nrbitsp);
-}
-
-static inline void
-nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize)
-{
- sb->s_maxbytes = (loff_t)maxfilesize;
- if (sb->s_maxbytes > MAX_LFS_FILESIZE || sb->s_maxbytes <= 0)
- sb->s_maxbytes = MAX_LFS_FILESIZE;
-}
-
-/*
- * Obtain the root inode of the file system.
- */
-static struct inode *
-nfs_get_root(struct super_block *sb, struct nfs_fh *rootfh, struct nfs_fsinfo *fsinfo)
-{
- struct nfs_server *server = NFS_SB(sb);
- int error;
-
- error = server->rpc_ops->getroot(server, rootfh, fsinfo);
- if (error < 0) {
- dprintk("nfs_get_root: getattr error = %d\n", -error);
- return ERR_PTR(error);
- }
-
- server->fsid = fsinfo->fattr->fsid;
- return nfs_fhget(sb, rootfh, fsinfo->fattr);
-}
-
-/*
- * Do NFS version-independent mount processing, and sanity checking
- */
-static int
-nfs_sb_init(struct super_block *sb, rpc_authflavor_t authflavor)
-{
- struct nfs_server *server;
- struct inode *root_inode;
- struct nfs_fattr fattr;
- struct nfs_fsinfo fsinfo = {
- .fattr = &fattr,
- };
- struct nfs_pathconf pathinfo = {
- .fattr = &fattr,
- };
- int no_root_error = 0;
- unsigned long max_rpc_payload;
-
- /* We probably want something more informative here */
- snprintf(sb->s_id, sizeof(sb->s_id), "%x:%x", MAJOR(sb->s_dev), MINOR(sb->s_dev));
-
- server = NFS_SB(sb);
-
- sb->s_magic = NFS_SUPER_MAGIC;
-
- server->io_stats = nfs_alloc_iostats();
- if (server->io_stats == NULL)
- return -ENOMEM;
-
- root_inode = nfs_get_root(sb, &server->fh, &fsinfo);
- /* Did getting the root inode fail? */
- if (IS_ERR(root_inode)) {
- no_root_error = PTR_ERR(root_inode);
- goto out_no_root;
- }
- sb->s_root = d_alloc_root(root_inode);
- if (!sb->s_root) {
- no_root_error = -ENOMEM;
- goto out_no_root;
- }
- sb->s_root->d_op = server->rpc_ops->dentry_ops;
-
- /* mount time stamp, in seconds */
- server->mount_time = jiffies;
-
- /* Get some general file system info */
- if (server->namelen == 0 &&
- server->rpc_ops->pathconf(server, &server->fh, &pathinfo) >= 0)
- server->namelen = pathinfo.max_namelen;
- /* Work out a lot of parameters */
- if (server->rsize == 0)
- server->rsize = nfs_block_size(fsinfo.rtpref, NULL);
- if (server->wsize == 0)
- server->wsize = nfs_block_size(fsinfo.wtpref, NULL);
-
- if (fsinfo.rtmax >= 512 && server->rsize > fsinfo.rtmax)
- server->rsize = nfs_block_size(fsinfo.rtmax, NULL);
- if (fsinfo.wtmax >= 512 && server->wsize > fsinfo.wtmax)
- server->wsize = nfs_block_size(fsinfo.wtmax, NULL);
-
- max_rpc_payload = nfs_block_size(rpc_max_payload(server->client), NULL);
- if (server->rsize > max_rpc_payload)
- server->rsize = max_rpc_payload;
- if (server->rsize > NFS_MAX_FILE_IO_SIZE)
- server->rsize = NFS_MAX_FILE_IO_SIZE;
- server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-
- if (server->wsize > max_rpc_payload)
- server->wsize = max_rpc_payload;
- if (server->wsize > NFS_MAX_FILE_IO_SIZE)
- server->wsize = NFS_MAX_FILE_IO_SIZE;
- server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-
- if (sb->s_blocksize == 0)
- sb->s_blocksize = nfs_block_bits(server->wsize,
- &sb->s_blocksize_bits);
- server->wtmult = nfs_block_bits(fsinfo.wtmult, NULL);
-
- server->dtsize = nfs_block_size(fsinfo.dtpref, NULL);
- if (server->dtsize > PAGE_CACHE_SIZE)
- server->dtsize = PAGE_CACHE_SIZE;
- if (server->dtsize > server->rsize)
- server->dtsize = server->rsize;
-
- if (server->flags & NFS_MOUNT_NOAC) {
- server->acregmin = server->acregmax = 0;
- server->acdirmin = server->acdirmax = 0;
- sb->s_flags |= MS_SYNCHRONOUS;
- }
- server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD;
-
- nfs_super_set_maxbytes(sb, fsinfo.maxfilesize);
-
- server->client->cl_intr = (server->flags & NFS_MOUNT_INTR) ? 1 : 0;
- server->client->cl_softrtry = (server->flags & NFS_MOUNT_SOFT) ? 1 : 0;
-
- /* We're airborne Set socket buffersize */
- rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100);
- return 0;
- /* Yargs. It didn't work out. */
-out_no_root:
- dprintk("nfs_sb_init: get root inode failed: errno %d\n", -no_root_error);
- if (!IS_ERR(root_inode))
- iput(root_inode);
- return no_root_error;
-}
-
-static void nfs_init_timeout_values(struct rpc_timeout *to, int proto, unsigned int timeo, unsigned int retrans)
-{
- to->to_initval = timeo * HZ / 10;
- to->to_retries = retrans;
- if (!to->to_retries)
- to->to_retries = 2;
-
- switch (proto) {
- case IPPROTO_TCP:
- if (!to->to_initval)
- to->to_initval = 60 * HZ;
- if (to->to_initval > NFS_MAX_TCP_TIMEOUT)
- to->to_initval = NFS_MAX_TCP_TIMEOUT;
- to->to_increment = to->to_initval;
- to->to_maxval = to->to_initval + (to->to_increment * to->to_retries);
- to->to_exponential = 0;
- break;
- case IPPROTO_UDP:
- default:
- if (!to->to_initval)
- to->to_initval = 11 * HZ / 10;
- if (to->to_initval > NFS_MAX_UDP_TIMEOUT)
- to->to_initval = NFS_MAX_UDP_TIMEOUT;
- to->to_maxval = NFS_MAX_UDP_TIMEOUT;
- to->to_exponential = 1;
- break;
- }
-}
-
-/*
- * Create an RPC client handle.
- */
-static struct rpc_clnt *
-nfs_create_client(struct nfs_server *server, const struct nfs_mount_data *data)
-{
- struct rpc_timeout timeparms;
- struct rpc_xprt *xprt = NULL;
- struct rpc_clnt *clnt = NULL;
- int proto = (data->flags & NFS_MOUNT_TCP) ? IPPROTO_TCP : IPPROTO_UDP;
-
- nfs_init_timeout_values(&timeparms, proto, data->timeo, data->retrans);
-
- server->retrans_timeo = timeparms.to_initval;
- server->retrans_count = timeparms.to_retries;
-
- /* create transport and client */
- xprt = xprt_create_proto(proto, &server->addr, &timeparms);
- if (IS_ERR(xprt)) {
- dprintk("%s: cannot create RPC transport. Error = %ld\n",
- __FUNCTION__, PTR_ERR(xprt));
- return (struct rpc_clnt *)xprt;
- }
- clnt = rpc_create_client(xprt, server->hostname, &nfs_program,
- server->rpc_ops->version, data->pseudoflavor);
- if (IS_ERR(clnt)) {
- dprintk("%s: cannot create RPC client. Error = %ld\n",
- __FUNCTION__, PTR_ERR(xprt));
- goto out_fail;
- }
-
- clnt->cl_intr = 1;
- clnt->cl_softrtry = 1;
-
- return clnt;
-
-out_fail:
- return clnt;
-}
-
-/*
- * The way this works is that the mount process passes a structure
- * in the data argument which contains the server's IP address
- * and the root file handle obtained from the server's mount
- * daemon. We stash these away in the private superblock fields.
+/**
+ * nfs_compat_user_ino64 - returns the user-visible inode number
+ * @fileid: 64-bit fileid
+ *
+ * This function returns a 32-bit inode number if the boot parameter
+ * nfs.enable_ino64 is zero.
*/
-static int
-nfs_fill_super(struct super_block *sb, struct nfs_mount_data *data, int silent)
-{
- struct nfs_server *server;
- rpc_authflavor_t authflavor;
-
- server = NFS_SB(sb);
- sb->s_blocksize_bits = 0;
- sb->s_blocksize = 0;
- if (data->bsize)
- sb->s_blocksize = nfs_block_size(data->bsize, &sb->s_blocksize_bits);
- if (data->rsize)
- server->rsize = nfs_block_size(data->rsize, NULL);
- if (data->wsize)
- server->wsize = nfs_block_size(data->wsize, NULL);
- server->flags = data->flags & NFS_MOUNT_FLAGMASK;
-
- server->acregmin = data->acregmin*HZ;
- server->acregmax = data->acregmax*HZ;
- server->acdirmin = data->acdirmin*HZ;
- server->acdirmax = data->acdirmax*HZ;
-
- /* Start lockd here, before we might error out */
- if (!(server->flags & NFS_MOUNT_NONLM))
- lockd_up();
-
- server->namelen = data->namlen;
- server->hostname = kmalloc(strlen(data->hostname) + 1, GFP_KERNEL);
- if (!server->hostname)
- return -ENOMEM;
- strcpy(server->hostname, data->hostname);
-
- /* Check NFS protocol revision and initialize RPC op vector
- * and file handle pool. */
-#ifdef CONFIG_NFS_V3
- if (server->flags & NFS_MOUNT_VER3) {
- server->rpc_ops = &nfs_v3_clientops;
- server->caps |= NFS_CAP_READDIRPLUS;
- } else {
- server->rpc_ops = &nfs_v2_clientops;
- }
-#else
- server->rpc_ops = &nfs_v2_clientops;
-#endif
-
- /* Fill in pseudoflavor for mount version < 5 */
- if (!(data->flags & NFS_MOUNT_SECFLAVOUR))
- data->pseudoflavor = RPC_AUTH_UNIX;
- authflavor = data->pseudoflavor; /* save for sb_init() */
- /* XXX maybe we want to add a server->pseudoflavor field */
-
- /* Create RPC client handles */
- server->client = nfs_create_client(server, data);
- if (IS_ERR(server->client))
- return PTR_ERR(server->client);
- /* RFC 2623, sec 2.3.2 */
- if (authflavor != RPC_AUTH_UNIX) {
- struct rpc_auth *auth;
-
- server->client_sys = rpc_clone_client(server->client);
- if (IS_ERR(server->client_sys))
- return PTR_ERR(server->client_sys);
- auth = rpcauth_create(RPC_AUTH_UNIX, server->client_sys);
- if (IS_ERR(auth))
- return PTR_ERR(auth);
- } else {
- atomic_inc(&server->client->cl_count);
- server->client_sys = server->client;
- }
- if (server->flags & NFS_MOUNT_VER3) {
-#ifdef CONFIG_NFS_V3_ACL
- if (!(server->flags & NFS_MOUNT_NOACL)) {
- server->client_acl = rpc_bind_new_program(server->client, &nfsacl_program, 3);
- /* No errors! Assume that Sun nfsacls are supported */
- if (!IS_ERR(server->client_acl))
- server->caps |= NFS_CAP_ACLS;
- }
-#else
- server->flags &= ~NFS_MOUNT_NOACL;
-#endif /* CONFIG_NFS_V3_ACL */
- /*
- * The VFS shouldn't apply the umask to mode bits. We will
- * do so ourselves when necessary.
- */
- sb->s_flags |= MS_POSIXACL;
- if (server->namelen == 0 || server->namelen > NFS3_MAXNAMLEN)
- server->namelen = NFS3_MAXNAMLEN;
- sb->s_time_gran = 1;
- } else {
- if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN)
- server->namelen = NFS2_MAXNAMLEN;
- }
-
- sb->s_op = &nfs_sops;
- return nfs_sb_init(sb, authflavor);
-}
-
-static int
-nfs_statfs(struct super_block *sb, struct kstatfs *buf)
+u64 nfs_compat_user_ino64(u64 fileid)
{
- struct nfs_server *server = NFS_SB(sb);
- unsigned char blockbits;
- unsigned long blockres;
- struct nfs_fh *rootfh = NFS_FH(sb->s_root->d_inode);
- struct nfs_fattr fattr;
- struct nfs_fsstat res = {
- .fattr = &fattr,
- };
- int error;
-
- lock_kernel();
-
- error = server->rpc_ops->statfs(server, rootfh, &res);
- buf->f_type = NFS_SUPER_MAGIC;
- if (error < 0)
- goto out_err;
-
- /*
- * 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 = 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 = sb->s_blocksize;
- blockbits = 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;
- out:
- unlock_kernel();
- return 0;
+ int ino;
- out_err:
- dprintk("%s: statfs error = %d\n", __FUNCTION__, -error);
- buf->f_bsize = buf->f_blocks = buf->f_bfree = buf->f_bavail = -1;
- goto out;
-
-}
-
-static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, int showdefaults)
-{
- static struct proc_nfs_info {
- int flag;
- char *str;
- char *nostr;
- } nfs_info[] = {
- { NFS_MOUNT_SOFT, ",soft", ",hard" },
- { NFS_MOUNT_INTR, ",intr", "" },
- { NFS_MOUNT_NOCTO, ",nocto", "" },
- { NFS_MOUNT_NOAC, ",noac", "" },
- { NFS_MOUNT_NONLM, ",nolock", "" },
- { NFS_MOUNT_NOACL, ",noacl", "" },
- { 0, NULL, NULL }
- };
- struct proc_nfs_info *nfs_infop;
- char buf[12];
- char *proto;
-
- seq_printf(m, ",vers=%d", nfss->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);
- }
- switch (nfss->client->cl_xprt->prot) {
- case IPPROTO_TCP:
- proto = "tcp";
- break;
- case IPPROTO_UDP:
- proto = "udp";
- break;
- default:
- snprintf(buf, sizeof(buf), "%u", nfss->client->cl_xprt->prot);
- proto = buf;
- }
- seq_printf(m, ",proto=%s", proto);
- seq_printf(m, ",timeo=%lu", 10U * nfss->retrans_timeo / HZ);
- seq_printf(m, ",retrans=%u", nfss->retrans_count);
+ if (enable_ino64)
+ return fileid;
+ ino = fileid;
+ if (sizeof(ino) < sizeof(fileid))
+ ino ^= fileid >> (sizeof(fileid)-sizeof(ino)) * 8;
+ return ino;
}
-static int nfs_show_options(struct seq_file *m, struct vfsmount *mnt)
+int nfs_write_inode(struct inode *inode, int sync)
{
- struct nfs_server *nfss = NFS_SB(mnt->mnt_sb);
-
- nfs_show_mount_options(m, nfss, 0);
-
- seq_puts(m, ",addr=");
- seq_escape(m, nfss->hostname, " \t\n\\");
+ int ret;
- return 0;
+ if (sync) {
+ ret = filemap_fdatawait(inode->i_mapping);
+ if (ret == 0)
+ ret = nfs_commit_inode(inode, FLUSH_SYNC);
+ } else
+ ret = nfs_commit_inode(inode, 0);
+ if (ret >= 0)
+ return 0;
+ __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+ return ret;
}
-static int nfs_show_stats(struct seq_file *m, struct vfsmount *mnt)
+void nfs_clear_inode(struct inode *inode)
{
- int i, cpu;
- struct nfs_server *nfss = NFS_SB(mnt->mnt_sb);
- struct rpc_auth *auth = nfss->client->cl_auth;
- struct nfs_iostats totals = { };
-
- seq_printf(m, "statvers=%s", NFS_IOSTAT_VERS);
-
- /*
- * Display all mount option settings
- */
- seq_printf(m, "\n\topts:\t");
- seq_puts(m, mnt->mnt_sb->s_flags & MS_RDONLY ? "ro" : "rw");
- seq_puts(m, mnt->mnt_sb->s_flags & MS_SYNCHRONOUS ? ",sync" : "");
- seq_puts(m, mnt->mnt_sb->s_flags & MS_NOATIME ? ",noatime" : "");
- seq_puts(m, mnt->mnt_sb->s_flags & MS_NODIRATIME ? ",nodiratime" : "");
- nfs_show_mount_options(m, nfss, 1);
-
- seq_printf(m, "\n\tage:\t%lu", (jiffies - nfss->mount_time) / HZ);
-
- seq_printf(m, "\n\tcaps:\t");
- seq_printf(m, "caps=0x%x", nfss->caps);
- seq_printf(m, ",wtmult=%d", nfss->wtmult);
- seq_printf(m, ",dtsize=%d", nfss->dtsize);
- seq_printf(m, ",bsize=%d", nfss->bsize);
- seq_printf(m, ",namelen=%d", nfss->namelen);
-
-#ifdef CONFIG_NFS_V4
- if (nfss->rpc_ops->version == 4) {
- seq_printf(m, "\n\tnfsv4:\t");
- seq_printf(m, "bm0=0x%x", nfss->attr_bitmask[0]);
- seq_printf(m, ",bm1=0x%x", nfss->attr_bitmask[1]);
- seq_printf(m, ",acl=0x%x", nfss->acl_bitmask);
- }
-#endif
-
/*
- * Display security flavor in effect for this mount
- */
- seq_printf(m, "\n\tsec:\tflavor=%d", auth->au_ops->au_flavor);
- if (auth->au_flavor)
- seq_printf(m, ",pseudoflavor=%d", auth->au_flavor);
-
- /*
- * Display superblock I/O counters
+ * The following should never happen...
*/
- for_each_possible_cpu(cpu) {
- struct nfs_iostats *stats;
-
- preempt_disable();
- stats = per_cpu_ptr(nfss->io_stats, cpu);
-
- for (i = 0; i < __NFSIOS_COUNTSMAX; i++)
- totals.events[i] += stats->events[i];
- for (i = 0; i < __NFSIOS_BYTESMAX; i++)
- totals.bytes[i] += stats->bytes[i];
-
- preempt_enable();
- }
-
- seq_printf(m, "\n\tevents:\t");
- for (i = 0; i < __NFSIOS_COUNTSMAX; i++)
- seq_printf(m, "%lu ", totals.events[i]);
- seq_printf(m, "\n\tbytes:\t");
- for (i = 0; i < __NFSIOS_BYTESMAX; i++)
- seq_printf(m, "%Lu ", totals.bytes[i]);
- seq_printf(m, "\n");
-
- rpc_print_iostats(m, nfss->client);
-
- return 0;
+ BUG_ON(nfs_have_writebacks(inode));
+ BUG_ON(!list_empty(&NFS_I(inode)->open_files));
+ nfs_zap_acl_cache(inode);
+ nfs_access_zap_cache(inode);
}
/**
nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
- NFS_ATTRTIMEO(inode) = NFS_MINATTRTIMEO(inode);
- NFS_ATTRTIMEO_UPDATE(inode) = jiffies;
+ nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
+ nfsi->attrtimeo_timestamp = jiffies;
memset(NFS_COOKIEVERF(inode), 0, sizeof(NFS_COOKIEVERF(inode)));
if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))
spin_unlock(&inode->i_lock);
}
-static void nfs_zap_acl_cache(struct inode *inode)
+void nfs_zap_mapping(struct inode *inode, struct address_space *mapping)
+{
+ if (mapping->nrpages != 0) {
+ spin_lock(&inode->i_lock);
+ NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA;
+ spin_unlock(&inode->i_lock);
+ }
+}
+
+void nfs_zap_acl_cache(struct inode *inode)
{
void (*clear_acl_cache)(struct inode *);
spin_unlock(&inode->i_lock);
}
+void nfs_invalidate_atime(struct inode *inode)
+{
+ spin_lock(&inode->i_lock);
+ NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATIME;
+ spin_unlock(&inode->i_lock);
+}
+
/*
* Invalidate, but do not unhash, the inode.
* NB: must be called with inode->i_lock held!
*/
static void nfs_invalidate_inode(struct inode *inode)
{
- set_bit(NFS_INO_STALE, &NFS_FLAGS(inode));
+ set_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
nfs_zap_caches_locked(inode);
}
struct nfs_find_desc *desc = (struct nfs_find_desc *)opaque;
struct nfs_fattr *fattr = desc->fattr;
- NFS_FILEID(inode) = fattr->fileid;
+ set_nfs_fileid(inode, fattr->fileid);
nfs_copy_fh(NFS_FH(inode), desc->fh);
return 0;
}
if (inode->i_state & I_NEW) {
struct nfs_inode *nfsi = NFS_I(inode);
+ unsigned long now = jiffies;
/* We set i_ino for the few things that still rely on it,
* such as stat(2) */
/* Why so? Because we want revalidate for devices/FIFOs, and
* that's precisely what we have in nfs_file_inode_operations.
*/
- inode->i_op = NFS_SB(sb)->rpc_ops->file_inode_ops;
+ inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->file_inode_ops;
if (S_ISREG(inode->i_mode)) {
inode->i_fop = &nfs_file_operations;
inode->i_data.a_ops = &nfs_file_aops;
inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info;
} else if (S_ISDIR(inode->i_mode)) {
- inode->i_op = NFS_SB(sb)->rpc_ops->dir_inode_ops;
+ inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops;
inode->i_fop = &nfs_dir_operations;
if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS)
&& fattr->size <= NFS_LIMIT_READDIRPLUS)
- set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_FLAGS(inode));
+ set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
/* Deal with crossing mountpoints */
if (!nfs_fsid_equal(&NFS_SB(sb)->fsid, &fattr->fsid)) {
if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)
else
inode->i_op = &nfs_mountpoint_inode_operations;
inode->i_fop = NULL;
+ set_bit(NFS_INO_MOUNTPOINT, &nfsi->flags);
}
} else if (S_ISLNK(inode->i_mode))
inode->i_op = &nfs_symlink_inode_operations;
init_special_inode(inode, inode->i_mode, fattr->rdev);
nfsi->read_cache_jiffies = fattr->time_start;
- nfsi->last_updated = jiffies;
+ nfsi->last_updated = now;
+ nfsi->cache_change_attribute = now;
inode->i_atime = fattr->atime;
inode->i_mtime = fattr->mtime;
inode->i_ctime = fattr->ctime;
* report the blocks in 512byte units
*/
inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
- inode->i_blksize = inode->i_sb->s_blocksize;
} else {
inode->i_blocks = fattr->du.nfs2.blocks;
- inode->i_blksize = fattr->du.nfs2.blocksize;
}
nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
- nfsi->attrtimeo_timestamp = jiffies;
+ nfsi->attrtimeo_timestamp = now;
memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
- nfsi->cache_access.cred = NULL;
+ nfsi->access_cache = RB_ROOT;
unlock_new_inode(inode);
} else
goto out;
}
-#define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET)
+#define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE)
int
nfs_setattr(struct dentry *dentry, struct iattr *attr)
nfs_inc_stats(inode, NFSIOS_VFSSETATTR);
+ /* skip mode change if it's just for clearing setuid/setgid */
+ if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
+ attr->ia_valid &= ~ATTR_MODE;
+
if (attr->ia_valid & ATTR_SIZE) {
if (!S_ISREG(inode->i_mode) || attr->ia_size == i_size_read(inode))
attr->ia_valid &= ~ATTR_SIZE;
/* Optimization: if the end result is no change, don't RPC */
attr->ia_valid &= NFS_VALID_ATTRS;
- if (attr->ia_valid == 0)
+ if ((attr->ia_valid & ~ATTR_FILE) == 0)
return 0;
- lock_kernel();
- nfs_begin_data_update(inode);
/* Write all dirty data */
- filemap_write_and_wait(inode->i_mapping);
- nfs_wb_all(inode);
+ if (S_ISREG(inode->i_mode)) {
+ filemap_write_and_wait(inode->i_mapping);
+ nfs_wb_all(inode);
+ }
/*
* Return any delegations if we're going to change ACLs
*/
error = NFS_PROTO(inode)->setattr(dentry, &fattr, attr);
if (error == 0)
nfs_refresh_inode(inode, &fattr);
- nfs_end_data_update(inode);
- unlock_kernel();
return error;
}
/**
+ * nfs_vmtruncate - unmap mappings "freed" by truncate() syscall
+ * @inode: inode of the file used
+ * @offset: file offset to start truncating
+ *
+ * This is a copy of the common vmtruncate, but with the locking
+ * corrected to take into account the fact that NFS requires
+ * inode->i_size to be updated under the inode->i_lock.
+ */
+static int nfs_vmtruncate(struct inode * inode, loff_t offset)
+{
+ if (i_size_read(inode) < offset) {
+ unsigned long limit;
+
+ limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
+ if (limit != RLIM_INFINITY && offset > limit)
+ goto out_sig;
+ if (offset > inode->i_sb->s_maxbytes)
+ goto out_big;
+ spin_lock(&inode->i_lock);
+ i_size_write(inode, offset);
+ spin_unlock(&inode->i_lock);
+ } else {
+ struct address_space *mapping = inode->i_mapping;
+
+ /*
+ * truncation of in-use swapfiles is disallowed - it would
+ * cause subsequent swapout to scribble on the now-freed
+ * blocks.
+ */
+ if (IS_SWAPFILE(inode))
+ return -ETXTBSY;
+ spin_lock(&inode->i_lock);
+ i_size_write(inode, offset);
+ spin_unlock(&inode->i_lock);
+
+ /*
+ * unmap_mapping_range is called twice, first simply for
+ * efficiency so that truncate_inode_pages does fewer
+ * single-page unmaps. However after this first call, and
+ * before truncate_inode_pages finishes, it is possible for
+ * private pages to be COWed, which remain after
+ * truncate_inode_pages finishes, hence the second
+ * unmap_mapping_range call must be made for correctness.
+ */
+ unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
+ truncate_inode_pages(mapping, offset);
+ unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
+ }
+ return 0;
+out_sig:
+ send_sig(SIGXFSZ, current, 0);
+out_big:
+ return -EFBIG;
+}
+
+/**
* nfs_setattr_update_inode - Update inode metadata after a setattr call.
* @inode: pointer to struct inode
* @attr: pointer to struct iattr
}
if ((attr->ia_valid & ATTR_SIZE) != 0) {
nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC);
- inode->i_size = attr->ia_size;
- vmtruncate(inode, attr->ia_size);
+ nfs_vmtruncate(inode, attr->ia_size);
}
}
*/
static int nfs_wait_on_inode(struct inode *inode)
{
- struct rpc_clnt *clnt = NFS_CLIENT(inode);
struct nfs_inode *nfsi = NFS_I(inode);
- sigset_t oldmask;
int error;
- rpc_clnt_sigmask(clnt, &oldmask);
error = wait_on_bit_lock(&nfsi->flags, NFS_INO_REVALIDATING,
- nfs_wait_schedule, TASK_INTERRUPTIBLE);
- rpc_clnt_sigunmask(clnt, &oldmask);
+ nfs_wait_schedule, TASK_KILLABLE);
return error;
}
int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
int err;
- /* Flush out writes to the server in order to update c/mtime */
- nfs_sync_inode_wait(inode, 0, 0, FLUSH_NOCOMMIT);
+ /*
+ * Flush out writes to the server in order to update c/mtime.
+ *
+ * Hold the i_mutex to suspend application writes temporarily;
+ * this prevents long-running writing applications from blocking
+ * nfs_wb_nocommit.
+ */
+ if (S_ISREG(inode->i_mode)) {
+ mutex_lock(&inode->i_mutex);
+ nfs_wb_nocommit(inode);
+ mutex_unlock(&inode->i_mutex);
+ }
/*
* We may force a getattr if the user cares about atime.
err = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
else
err = nfs_revalidate_inode(NFS_SERVER(inode), inode);
- if (!err)
+ if (!err) {
generic_fillattr(inode, stat);
+ stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
+ }
return err;
}
{
struct nfs_open_context *ctx;
- ctx = (struct nfs_open_context *)kmalloc(sizeof(*ctx), GFP_KERNEL);
+ ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
if (ctx != NULL) {
- atomic_set(&ctx->count, 1);
- ctx->dentry = dget(dentry);
- ctx->vfsmnt = mntget(mnt);
+ ctx->path.dentry = dget(dentry);
+ ctx->path.mnt = mntget(mnt);
ctx->cred = get_rpccred(cred);
ctx->state = NULL;
ctx->lockowner = current->files;
+ ctx->flags = 0;
ctx->error = 0;
ctx->dir_cookie = 0;
+ atomic_set(&ctx->count, 1);
}
return ctx;
}
return ctx;
}
-void put_nfs_open_context(struct nfs_open_context *ctx)
+static void __put_nfs_open_context(struct nfs_open_context *ctx, int wait)
{
- if (atomic_dec_and_test(&ctx->count)) {
- if (!list_empty(&ctx->list)) {
- struct inode *inode = ctx->dentry->d_inode;
- spin_lock(&inode->i_lock);
- list_del(&ctx->list);
- spin_unlock(&inode->i_lock);
- }
- if (ctx->state != NULL)
- nfs4_close_state(ctx->state, ctx->mode);
- if (ctx->cred != NULL)
- put_rpccred(ctx->cred);
- dput(ctx->dentry);
- mntput(ctx->vfsmnt);
- kfree(ctx);
+ struct inode *inode;
+
+ if (ctx == NULL)
+ return;
+
+ inode = ctx->path.dentry->d_inode;
+ if (!atomic_dec_and_lock(&ctx->count, &inode->i_lock))
+ return;
+ list_del(&ctx->list);
+ spin_unlock(&inode->i_lock);
+ if (ctx->state != NULL) {
+ if (wait)
+ nfs4_close_sync(&ctx->path, ctx->state, ctx->mode);
+ else
+ nfs4_close_state(&ctx->path, ctx->state, ctx->mode);
}
+ if (ctx->cred != NULL)
+ put_rpccred(ctx->cred);
+ path_put(&ctx->path);
+ kfree(ctx);
+}
+
+void put_nfs_open_context(struct nfs_open_context *ctx)
+{
+ __put_nfs_open_context(ctx, 0);
+}
+
+static void put_nfs_open_context_sync(struct nfs_open_context *ctx)
+{
+ __put_nfs_open_context(ctx, 1);
}
/*
*/
static void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx)
{
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = filp->f_path.dentry->d_inode;
struct nfs_inode *nfsi = NFS_I(inode);
filp->private_data = get_nfs_open_context(ctx);
static void nfs_file_clear_open_context(struct file *filp)
{
- struct inode *inode = filp->f_dentry->d_inode;
- struct nfs_open_context *ctx = (struct nfs_open_context *)filp->private_data;
+ struct inode *inode = filp->f_path.dentry->d_inode;
+ struct nfs_open_context *ctx = nfs_file_open_context(filp);
if (ctx) {
filp->private_data = NULL;
spin_lock(&inode->i_lock);
list_move_tail(&ctx->list, &NFS_I(inode)->open_files);
spin_unlock(&inode->i_lock);
- put_nfs_open_context(ctx);
+ put_nfs_open_context_sync(ctx);
}
}
struct nfs_open_context *ctx;
struct rpc_cred *cred;
- cred = rpcauth_lookupcred(NFS_CLIENT(inode)->cl_auth, 0);
+ cred = rpc_lookup_cred();
if (IS_ERR(cred))
return PTR_ERR(cred);
- ctx = alloc_nfs_open_context(filp->f_vfsmnt, filp->f_dentry, cred);
+ ctx = alloc_nfs_open_context(filp->f_path.mnt, filp->f_path.dentry, cred);
put_rpccred(cred);
if (ctx == NULL)
return -ENOMEM;
inode->i_sb->s_id, (long long)NFS_FILEID(inode));
nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE);
- lock_kernel();
- if (!inode || is_bad_inode(inode))
+ if (is_bad_inode(inode))
goto out_nowait;
if (NFS_STALE(inode))
goto out_nowait;
status = nfs_wait_on_inode(inode);
if (status < 0)
goto out;
- if (NFS_STALE(inode)) {
- status = -ESTALE;
- /* Do we trust the cached ESTALE? */
- if (NFS_ATTRTIMEO(inode) != 0) {
- if (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ATIME)) {
- /* no */
- } else
- goto out;
- }
- }
+
+ status = -ESTALE;
+ if (NFS_STALE(inode))
+ goto out;
status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), &fattr);
if (status != 0) {
if (status == -ESTALE) {
nfs_zap_caches(inode);
if (!S_ISDIR(inode->i_mode))
- set_bit(NFS_INO_STALE, &NFS_FLAGS(inode));
+ set_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
}
goto out;
}
nfs_wake_up_inode(inode);
out_nowait:
- unlock_kernel();
return status;
}
if (nfs_have_delegation(inode, FMODE_READ))
return 0;
- return time_after(jiffies, nfsi->read_cache_jiffies+nfsi->attrtimeo);
+ /*
+ * Special case: if the attribute timeout is set to 0, then always
+ * treat the cache as having expired (unless holding
+ * a delegation).
+ */
+ if (nfsi->attrtimeo == 0)
+ return 1;
+ return !time_in_range(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo);
}
/**
return __nfs_revalidate_inode(server, inode);
}
-/**
- * nfs_revalidate_mapping - Revalidate the pagecache
- * @inode - pointer to host inode
- * @mapping - pointer to mapping
- */
-int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
+static int nfs_invalidate_mapping_nolock(struct inode *inode, struct address_space *mapping)
{
struct nfs_inode *nfsi = NFS_I(inode);
- int ret = 0;
-
- if (NFS_STALE(inode))
- ret = -ESTALE;
- if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
- || nfs_attribute_timeout(inode))
- ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
-
- if (nfsi->cache_validity & NFS_INO_INVALID_DATA) {
- nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
- if (S_ISREG(inode->i_mode))
- nfs_sync_mapping(mapping);
- invalidate_inode_pages2(mapping);
+
+ if (mapping->nrpages != 0) {
+ int ret = invalidate_inode_pages2(mapping);
+ if (ret < 0)
+ return ret;
+ }
+ spin_lock(&inode->i_lock);
+ nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
+ if (S_ISDIR(inode->i_mode))
+ memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
+ spin_unlock(&inode->i_lock);
+ nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
+ dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n",
+ inode->i_sb->s_id, (long long)NFS_FILEID(inode));
+ return 0;
+}
- spin_lock(&inode->i_lock);
- nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
- if (S_ISDIR(inode->i_mode)) {
- memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
- /* This ensures we revalidate child dentries */
- nfsi->cache_change_attribute = jiffies;
- }
- spin_unlock(&inode->i_lock);
+static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping)
+{
+ int ret = 0;
- dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n",
- inode->i_sb->s_id,
- (long long)NFS_FILEID(inode));
+ mutex_lock(&inode->i_mutex);
+ if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_DATA) {
+ ret = nfs_sync_mapping(mapping);
+ if (ret == 0)
+ ret = nfs_invalidate_mapping_nolock(inode, mapping);
}
+ mutex_unlock(&inode->i_mutex);
return ret;
}
/**
- * nfs_begin_data_update
- * @inode - pointer to inode
- * Declare that a set of operations will update file data on the server
+ * nfs_revalidate_mapping_nolock - Revalidate the pagecache
+ * @inode - pointer to host inode
+ * @mapping - pointer to mapping
*/
-void nfs_begin_data_update(struct inode *inode)
+int nfs_revalidate_mapping_nolock(struct inode *inode, struct address_space *mapping)
{
- atomic_inc(&NFS_I(inode)->data_updates);
+ struct nfs_inode *nfsi = NFS_I(inode);
+ int ret = 0;
+
+ if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
+ || nfs_attribute_timeout(inode) || NFS_STALE(inode)) {
+ ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
+ if (ret < 0)
+ goto out;
+ }
+ if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+ ret = nfs_invalidate_mapping_nolock(inode, mapping);
+out:
+ return ret;
}
/**
- * nfs_end_data_update
- * @inode - pointer to inode
- * Declare end of the operations that will update file data
- * This will mark the inode as immediately needing revalidation
- * of its attribute cache.
+ * nfs_revalidate_mapping - Revalidate the pagecache
+ * @inode - pointer to host inode
+ * @mapping - pointer to mapping
+ *
+ * This version of the function will take the inode->i_mutex and attempt to
+ * flush out all dirty data if it needs to invalidate the page cache.
*/
-void nfs_end_data_update(struct inode *inode)
+int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
{
struct nfs_inode *nfsi = NFS_I(inode);
+ int ret = 0;
- if (!nfs_have_delegation(inode, FMODE_READ)) {
- /* Directories and symlinks: invalidate page cache */
- if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) {
- spin_lock(&inode->i_lock);
- nfsi->cache_validity |= NFS_INO_INVALID_DATA;
- spin_unlock(&inode->i_lock);
- }
+ if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
+ || nfs_attribute_timeout(inode) || NFS_STALE(inode)) {
+ ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
+ if (ret < 0)
+ goto out;
}
- nfsi->cache_change_attribute = jiffies;
- atomic_dec(&nfsi->data_updates);
+ if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+ ret = nfs_invalidate_mapping(inode, mapping);
+out:
+ return ret;
}
static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
struct nfs_inode *nfsi = NFS_I(inode);
+ if ((fattr->valid & NFS_ATTR_WCC_V4) != 0 &&
+ nfsi->change_attr == fattr->pre_change_attr) {
+ nfsi->change_attr = fattr->change_attr;
+ if (S_ISDIR(inode->i_mode))
+ nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+ }
/* If we have atomic WCC data, we may update some attributes */
if ((fattr->valid & NFS_ATTR_WCC) != 0) {
- if (timespec_equal(&inode->i_ctime, &fattr->pre_ctime)) {
+ if (timespec_equal(&inode->i_ctime, &fattr->pre_ctime))
memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
- nfsi->cache_change_attribute = jiffies;
- }
if (timespec_equal(&inode->i_mtime, &fattr->pre_mtime)) {
memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
- nfsi->cache_change_attribute = jiffies;
- }
- if (inode->i_size == fattr->pre_size && nfsi->npages == 0) {
- inode->i_size = fattr->size;
- nfsi->cache_change_attribute = jiffies;
+ if (S_ISDIR(inode->i_mode))
+ nfsi->cache_validity |= NFS_INO_INVALID_DATA;
}
+ if (i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size) &&
+ nfsi->npages == 0)
+ i_size_write(inode, nfs_size_to_loff_t(fattr->size));
}
}
{
struct nfs_inode *nfsi = NFS_I(inode);
loff_t cur_size, new_isize;
- int data_unstable;
+ unsigned long invalid = 0;
/* Has the inode gone and changed behind our back? */
return -EIO;
}
- /* Are we in the process of updating data on the server? */
- data_unstable = nfs_caches_unstable(inode);
-
/* Do atomic weak cache consistency updates */
nfs_wcc_update_inode(inode, fattr);
if ((fattr->valid & NFS_ATTR_FATTR_V4) != 0 &&
nfsi->change_attr != fattr->change_attr)
- nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
+ invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
/* Verify a few of the more important attributes */
if (!timespec_equal(&inode->i_mtime, &fattr->mtime))
- nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
+ invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
cur_size = i_size_read(inode);
new_isize = nfs_size_to_loff_t(fattr->size);
if (cur_size != new_isize && nfsi->npages == 0)
- nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
+ invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
/* Have any file permissions changed? */
if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)
|| inode->i_uid != fattr->uid
|| inode->i_gid != fattr->gid)
- nfsi->cache_validity |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL;
+ invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL;
/* Has the link count changed? */
if (inode->i_nlink != fattr->nlink)
- nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
+ invalid |= NFS_INO_INVALID_ATTR;
if (!timespec_equal(&inode->i_atime, &fattr->atime))
- nfsi->cache_validity |= NFS_INO_INVALID_ATIME;
+ invalid |= NFS_INO_INVALID_ATIME;
+
+ if (invalid != 0)
+ nfsi->cache_validity |= invalid;
+ else
+ nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR
+ | NFS_INO_INVALID_ATIME
+ | NFS_INO_REVAL_PAGECACHE);
nfsi->read_cache_jiffies = fattr->time_start;
return 0;
*
* After an operation that has changed the inode metadata, mark the
* attribute cache as being invalid, then try to update it.
+ *
+ * NB: if the server didn't return any post op attributes, this
+ * function will force the retrieval of attributes before the next
+ * NFS request. Thus it should be used only for operations that
+ * are expected to change one or more attributes, to avoid
+ * unnecessary NFS requests and trips through nfs_update_inode().
*/
int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
struct nfs_inode *nfsi = NFS_I(inode);
- int status = 0;
spin_lock(&inode->i_lock);
- if (unlikely((fattr->valid & NFS_ATTR_FATTR) == 0)) {
- nfsi->cache_validity |= NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
- goto out;
- }
- status = nfs_update_inode(inode, fattr);
-out:
+ nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
+ if (S_ISDIR(inode->i_mode))
+ nfsi->cache_validity |= NFS_INO_INVALID_DATA;
spin_unlock(&inode->i_lock);
- return status;
+ return nfs_refresh_inode(inode, fattr);
+}
+
+/**
+ * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache
+ * @inode - pointer to inode
+ * @fattr - updated attributes
+ *
+ * After an operation that has changed the inode metadata, mark the
+ * attribute cache as being invalid, then try to update it. Fake up
+ * weak cache consistency data, if none exist.
+ *
+ * This function is mainly designed to be used by the ->write_done() functions.
+ */
+int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr)
+{
+ if ((fattr->valid & NFS_ATTR_FATTR_V4) != 0 &&
+ (fattr->valid & NFS_ATTR_WCC_V4) == 0) {
+ fattr->pre_change_attr = NFS_I(inode)->change_attr;
+ fattr->valid |= NFS_ATTR_WCC_V4;
+ }
+ if ((fattr->valid & NFS_ATTR_FATTR) != 0 &&
+ (fattr->valid & NFS_ATTR_WCC) == 0) {
+ memcpy(&fattr->pre_ctime, &inode->i_ctime, sizeof(fattr->pre_ctime));
+ memcpy(&fattr->pre_mtime, &inode->i_mtime, sizeof(fattr->pre_mtime));
+ fattr->pre_size = i_size_read(inode);
+ fattr->valid |= NFS_ATTR_WCC;
+ }
+ return nfs_post_op_update_inode(inode, fattr);
}
/*
struct nfs_server *server;
struct nfs_inode *nfsi = NFS_I(inode);
loff_t cur_isize, new_isize;
- unsigned int invalid = 0;
- int data_stable;
+ unsigned long invalid = 0;
+ unsigned long now = jiffies;
dfprintk(VFS, "NFS: %s(%s/%ld ct=%d info=0x%x)\n",
- __FUNCTION__, inode->i_sb->s_id, inode->i_ino,
+ __func__, inode->i_sb->s_id, inode->i_ino,
atomic_read(&inode->i_count), fattr->valid);
if (nfsi->fileid != fattr->fileid)
goto out_changed;
server = NFS_SERVER(inode);
- /* Update the fsid if and only if this is the root directory */
- if (inode == inode->i_sb->s_root->d_inode
- && !nfs_fsid_equal(&server->fsid, &fattr->fsid))
+ /* Update the fsid? */
+ if (S_ISDIR(inode->i_mode) &&
+ !nfs_fsid_equal(&server->fsid, &fattr->fsid) &&
+ !test_bit(NFS_INO_MOUNTPOINT, &nfsi->flags))
server->fsid = fattr->fsid;
/*
* Update the read time so we don't revalidate too often.
*/
nfsi->read_cache_jiffies = fattr->time_start;
- nfsi->last_updated = jiffies;
- /* Are we racing with known updates of the metadata on the server? */
- data_stable = nfs_verify_change_attribute(inode, fattr->time_start);
- if (data_stable)
- nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_ATIME);
+ nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ATIME
+ | NFS_INO_REVAL_PAGECACHE);
/* Do atomic weak cache consistency updates */
nfs_wcc_update_inode(inode, fattr);
+ /* More cache consistency checks */
+ if (!(fattr->valid & NFS_ATTR_FATTR_V4)) {
+ /* NFSv2/v3: Check if the mtime agrees */
+ if (!timespec_equal(&inode->i_mtime, &fattr->mtime)) {
+ dprintk("NFS: mtime change on server for file %s/%ld\n",
+ inode->i_sb->s_id, inode->i_ino);
+ invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
+ if (S_ISDIR(inode->i_mode))
+ nfs_force_lookup_revalidate(inode);
+ }
+ /* If ctime has changed we should definitely clear access+acl caches */
+ if (!timespec_equal(&inode->i_ctime, &fattr->ctime))
+ invalid |= NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
+ } else if (nfsi->change_attr != fattr->change_attr) {
+ dprintk("NFS: change_attr change on server for file %s/%ld\n",
+ inode->i_sb->s_id, inode->i_ino);
+ invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
+ if (S_ISDIR(inode->i_mode))
+ nfs_force_lookup_revalidate(inode);
+ }
+
/* Check if our cached file size is stale */
new_isize = nfs_size_to_loff_t(fattr->size);
cur_isize = i_size_read(inode);
if (new_isize != cur_isize) {
- /* Do we perhaps have any outstanding writes? */
- if (nfsi->npages == 0) {
- /* No, but did we race with nfs_end_data_update()? */
- if (data_stable) {
- inode->i_size = new_isize;
- invalid |= NFS_INO_INVALID_DATA;
- }
- invalid |= NFS_INO_INVALID_ATTR;
- } else if (new_isize > cur_isize) {
- inode->i_size = new_isize;
+ /* Do we perhaps have any outstanding writes, or has
+ * the file grown beyond our last write? */
+ if (nfsi->npages == 0 || new_isize > cur_isize) {
+ i_size_write(inode, new_isize);
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
}
- nfsi->cache_change_attribute = jiffies;
dprintk("NFS: isize change on server for file %s/%ld\n",
inode->i_sb->s_id, inode->i_ino);
}
- /* Check if the mtime agrees */
- if (!timespec_equal(&inode->i_mtime, &fattr->mtime)) {
- memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
- dprintk("NFS: mtime change on server for file %s/%ld\n",
- inode->i_sb->s_id, inode->i_ino);
- invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
- nfsi->cache_change_attribute = jiffies;
- }
- /* If ctime has changed we should definitely clear access+acl caches */
- if (!timespec_equal(&inode->i_ctime, &fattr->ctime)) {
- invalid |= NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
- memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
- nfsi->cache_change_attribute = jiffies;
- }
+ memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
+ memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));
+ nfsi->change_attr = fattr->change_attr;
if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO) ||
inode->i_uid != fattr->uid ||
* report the blocks in 512byte units
*/
inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
- inode->i_blksize = inode->i_sb->s_blocksize;
} else {
inode->i_blocks = fattr->du.nfs2.blocks;
- inode->i_blksize = fattr->du.nfs2.blocksize;
}
- if ((fattr->valid & NFS_ATTR_FATTR_V4) != 0 &&
- nfsi->change_attr != fattr->change_attr) {
- dprintk("NFS: change_attr change on server for file %s/%ld\n",
- inode->i_sb->s_id, inode->i_ino);
- nfsi->change_attr = fattr->change_attr;
- invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
- nfsi->cache_change_attribute = jiffies;
- }
-
/* Update attrtimeo value if we're out of the unstable period */
if (invalid & NFS_INO_INVALID_ATTR) {
nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
- nfsi->attrtimeo_timestamp = jiffies;
- } else if (time_after(jiffies, nfsi->attrtimeo_timestamp+nfsi->attrtimeo)) {
- if ((nfsi->attrtimeo <<= 1) > NFS_MAXATTRTIMEO(inode))
- nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode);
- nfsi->attrtimeo_timestamp = jiffies;
+ nfsi->attrtimeo_timestamp = now;
+ nfsi->last_updated = now;
+ } else {
+ if (!time_in_range(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) {
+ if ((nfsi->attrtimeo <<= 1) > NFS_MAXATTRTIMEO(inode))
+ nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode);
+ nfsi->attrtimeo_timestamp = now;
+ }
+ /*
+ * Avoid jiffy wraparound issues with nfsi->last_updated
+ */
+ if (!time_in_range(nfsi->last_updated, nfsi->read_cache_jiffies, now))
+ nfsi->last_updated = nfsi->read_cache_jiffies;
}
+ invalid &= ~NFS_INO_INVALID_ATTR;
/* Don't invalidate the data if we were to blame */
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
|| S_ISLNK(inode->i_mode)))
invalid &= ~NFS_INO_INVALID_DATA;
- if (data_stable)
- invalid &= ~(NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ATIME|NFS_INO_REVAL_PAGECACHE);
- if (!nfs_have_delegation(inode, FMODE_READ))
+ if (!nfs_have_delegation(inode, FMODE_READ) ||
+ (nfsi->cache_validity & NFS_INO_REVAL_FORCED))
nfsi->cache_validity |= invalid;
+ nfsi->cache_validity &= ~NFS_INO_REVAL_FORCED;
return 0;
out_changed:
/*
* Big trouble! The inode has become a different object.
*/
-#ifdef NFS_PARANOIA
printk(KERN_DEBUG "%s: inode %ld mode changed, %07o to %07o\n",
- __FUNCTION__, inode->i_ino, inode->i_mode, fattr->mode);
-#endif
+ __func__, inode->i_ino, inode->i_mode, fattr->mode);
out_err:
/*
* No need to worry about unhashing the dentry, as the
out_fileid:
printk(KERN_ERR "NFS: server %s error: fileid changed\n"
"fsid %s: expected fileid 0x%Lx, got 0x%Lx\n",
- NFS_SERVER(inode)->hostname, inode->i_sb->s_id,
+ NFS_SERVER(inode)->nfs_client->cl_hostname, inode->i_sb->s_id,
(long long)nfsi->fileid, (long long)fattr->fileid);
goto out_err;
}
-/*
- * File system information
- */
-
-/*
- * nfs_path - reconstruct the path given an arbitrary dentry
- * @base - arbitrary string to prepend to the path
- * @dentry - pointer to dentry
- * @buffer - result buffer
- * @buflen - length of buffer
- *
- * Helper function for constructing the path from the
- * root dentry to an arbitrary hashed dentry.
- *
- * This is mainly for use in figuring out the path on the
- * server side when automounting on top of an existing partition.
- */
-static char *nfs_path(const char *base, const struct dentry *dentry,
- char *buffer, ssize_t buflen)
-{
- char *end = buffer+buflen;
- int namelen;
-
- *--end = '\0';
- buflen--;
- spin_lock(&dcache_lock);
- while (!IS_ROOT(dentry)) {
- namelen = dentry->d_name.len;
- buflen -= namelen + 1;
- if (buflen < 0)
- goto Elong;
- end -= namelen;
- memcpy(end, dentry->d_name.name, namelen);
- *--end = '/';
- dentry = dentry->d_parent;
- }
- spin_unlock(&dcache_lock);
- namelen = strlen(base);
- /* Strip off excess slashes in base string */
- while (namelen > 0 && base[namelen - 1] == '/')
- namelen--;
- buflen -= namelen;
- if (buflen < 0)
- goto Elong;
- end -= namelen;
- memcpy(end, base, namelen);
- return end;
-Elong:
- return ERR_PTR(-ENAMETOOLONG);
-}
-
-struct nfs_clone_mount {
- const struct super_block *sb;
- const struct dentry *dentry;
- struct nfs_fh *fh;
- struct nfs_fattr *fattr;
- char *hostname;
- char *mnt_path;
- struct sockaddr_in *addr;
- rpc_authflavor_t authflavor;
-};
-
-static struct super_block *nfs_clone_generic_sb(struct nfs_clone_mount *data,
- struct super_block *(*fill_sb)(struct nfs_server *, struct nfs_clone_mount *),
- struct nfs_server *(*fill_server)(struct super_block *, struct nfs_clone_mount *))
-{
- struct nfs_server *server;
- struct nfs_server *parent = NFS_SB(data->sb);
- struct super_block *sb = ERR_PTR(-EINVAL);
- void *err = ERR_PTR(-ENOMEM);
- char *hostname;
- int len;
-
- server = kmalloc(sizeof(struct nfs_server), GFP_KERNEL);
- if (server == NULL)
- goto out_err;
- memcpy(server, parent, sizeof(*server));
- hostname = (data->hostname != NULL) ? data->hostname : parent->hostname;
- len = strlen(hostname) + 1;
- server->hostname = kmalloc(len, GFP_KERNEL);
- if (server->hostname == NULL)
- goto free_server;
- memcpy(server->hostname, hostname, len);
- if (rpciod_up() != 0)
- goto free_hostname;
-
- sb = fill_sb(server, data);
- if (IS_ERR((err = sb)) || sb->s_root)
- goto kill_rpciod;
-
- server = fill_server(sb, data);
- if (IS_ERR((err = server)))
- goto out_deactivate;
- return sb;
-out_deactivate:
- up_write(&sb->s_umount);
- deactivate_super(sb);
- return (struct super_block *)err;
-kill_rpciod:
- rpciod_down();
-free_hostname:
- kfree(server->hostname);
-free_server:
- kfree(server);
-out_err:
- return (struct super_block *)err;
-}
-
-static int nfs_set_super(struct super_block *s, void *data)
-{
- s->s_fs_info = data;
- return set_anon_super(s, data);
-}
-
-static int nfs_compare_super(struct super_block *sb, void *data)
-{
- struct nfs_server *server = data;
- struct nfs_server *old = NFS_SB(sb);
-
- if (old->addr.sin_addr.s_addr != server->addr.sin_addr.s_addr)
- return 0;
- if (old->addr.sin_port != server->addr.sin_port)
- return 0;
- return !nfs_compare_fh(&old->fh, &server->fh);
-}
-
-static struct super_block *nfs_get_sb(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *raw_data)
-{
- int error;
- struct nfs_server *server = NULL;
- struct super_block *s;
- struct nfs_fh *root;
- struct nfs_mount_data *data = raw_data;
-
- s = ERR_PTR(-EINVAL);
- if (data == NULL) {
- dprintk("%s: missing data argument\n", __FUNCTION__);
- goto out_err;
- }
- if (data->version <= 0 || data->version > NFS_MOUNT_VERSION) {
- dprintk("%s: bad mount version\n", __FUNCTION__);
- goto out_err;
- }
- switch (data->version) {
- case 1:
- data->namlen = 0;
- case 2:
- data->bsize = 0;
- case 3:
- if (data->flags & NFS_MOUNT_VER3) {
- dprintk("%s: mount structure version %d does not support NFSv3\n",
- __FUNCTION__,
- data->version);
- goto out_err;
- }
- data->root.size = NFS2_FHSIZE;
- memcpy(data->root.data, data->old_root.data, NFS2_FHSIZE);
- case 4:
- if (data->flags & NFS_MOUNT_SECFLAVOUR) {
- dprintk("%s: mount structure version %d does not support strong security\n",
- __FUNCTION__,
- data->version);
- goto out_err;
- }
- case 5:
- memset(data->context, 0, sizeof(data->context));
- }
-#ifndef CONFIG_NFS_V3
- /* If NFSv3 is not compiled in, return -EPROTONOSUPPORT */
- s = ERR_PTR(-EPROTONOSUPPORT);
- if (data->flags & NFS_MOUNT_VER3) {
- dprintk("%s: NFSv3 not compiled into kernel\n", __FUNCTION__);
- goto out_err;
- }
-#endif /* CONFIG_NFS_V3 */
-
- s = ERR_PTR(-ENOMEM);
- server = kzalloc(sizeof(struct nfs_server), GFP_KERNEL);
- if (!server)
- goto out_err;
- /* Zero out the NFS state stuff */
- init_nfsv4_state(server);
- server->client = server->client_sys = server->client_acl = ERR_PTR(-EINVAL);
-
- root = &server->fh;
- if (data->flags & NFS_MOUNT_VER3)
- root->size = data->root.size;
- else
- root->size = NFS2_FHSIZE;
- s = ERR_PTR(-EINVAL);
- if (root->size > sizeof(root->data)) {
- dprintk("%s: invalid root filehandle\n", __FUNCTION__);
- goto out_err;
- }
- memcpy(root->data, data->root.data, root->size);
-
- /* We now require that the mount process passes the remote address */
- memcpy(&server->addr, &data->addr, sizeof(server->addr));
- if (server->addr.sin_addr.s_addr == INADDR_ANY) {
- dprintk("%s: mount program didn't pass remote address!\n",
- __FUNCTION__);
- goto out_err;
- }
-
- /* Fire up rpciod if not yet running */
- s = ERR_PTR(rpciod_up());
- if (IS_ERR(s)) {
- dprintk("%s: couldn't start rpciod! Error = %ld\n",
- __FUNCTION__, PTR_ERR(s));
- goto out_err;
- }
-
- s = sget(fs_type, nfs_compare_super, nfs_set_super, server);
- if (IS_ERR(s) || s->s_root)
- goto out_rpciod_down;
-
- s->s_flags = flags;
-
- error = nfs_fill_super(s, data, flags & MS_SILENT ? 1 : 0);
- if (error) {
- up_write(&s->s_umount);
- deactivate_super(s);
- return ERR_PTR(error);
- }
- s->s_flags |= MS_ACTIVE;
- return s;
-out_rpciod_down:
- rpciod_down();
-out_err:
- kfree(server);
- return s;
-}
-
-static void nfs_kill_super(struct super_block *s)
-{
- struct nfs_server *server = NFS_SB(s);
-
- kill_anon_super(s);
-
- if (!IS_ERR(server->client))
- rpc_shutdown_client(server->client);
- if (!IS_ERR(server->client_sys))
- rpc_shutdown_client(server->client_sys);
- if (!IS_ERR(server->client_acl))
- rpc_shutdown_client(server->client_acl);
-
- if (!(server->flags & NFS_MOUNT_NONLM))
- lockd_down(); /* release rpc.lockd */
-
- rpciod_down(); /* release rpciod */
-
- nfs_free_iostats(server->io_stats);
- kfree(server->hostname);
- kfree(server);
- nfs_release_automount_timer();
-}
-
-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_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
-
-static struct super_block *nfs_clone_sb(struct nfs_server *server, struct nfs_clone_mount *data)
-{
- struct super_block *sb;
-
- server->fsid = data->fattr->fsid;
- nfs_copy_fh(&server->fh, data->fh);
- sb = sget(&nfs_fs_type, nfs_compare_super, nfs_set_super, server);
- if (!IS_ERR(sb) && sb->s_root == NULL && !(server->flags & NFS_MOUNT_NONLM))
- lockd_up();
- return sb;
-}
-
-static struct nfs_server *nfs_clone_server(struct super_block *sb, struct nfs_clone_mount *data)
-{
- struct nfs_server *server = NFS_SB(sb);
- struct nfs_server *parent = NFS_SB(data->sb);
- struct inode *root_inode;
- struct nfs_fsinfo fsinfo;
- void *err = ERR_PTR(-ENOMEM);
-
- sb->s_op = data->sb->s_op;
- sb->s_blocksize = data->sb->s_blocksize;
- sb->s_blocksize_bits = data->sb->s_blocksize_bits;
- sb->s_maxbytes = data->sb->s_maxbytes;
-
- server->client_sys = server->client_acl = ERR_PTR(-EINVAL);
- server->io_stats = nfs_alloc_iostats();
- if (server->io_stats == NULL)
- goto out;
-
- server->client = rpc_clone_client(parent->client);
- if (IS_ERR((err = server->client)))
- goto out;
-
- if (!IS_ERR(parent->client_sys)) {
- server->client_sys = rpc_clone_client(parent->client_sys);
- if (IS_ERR((err = server->client_sys)))
- goto out;
- }
- if (!IS_ERR(parent->client_acl)) {
- server->client_acl = rpc_clone_client(parent->client_acl);
- if (IS_ERR((err = server->client_acl)))
- goto out;
- }
- root_inode = nfs_fhget(sb, data->fh, data->fattr);
- if (!root_inode)
- goto out;
- sb->s_root = d_alloc_root(root_inode);
- if (!sb->s_root)
- goto out_put_root;
- fsinfo.fattr = data->fattr;
- if (NFS_PROTO(root_inode)->fsinfo(server, data->fh, &fsinfo) == 0)
- nfs_super_set_maxbytes(sb, fsinfo.maxfilesize);
- sb->s_root->d_op = server->rpc_ops->dentry_ops;
- sb->s_flags |= MS_ACTIVE;
- return server;
-out_put_root:
- iput(root_inode);
-out:
- return err;
-}
-
-static struct super_block *nfs_clone_nfs_sb(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *raw_data)
-{
- struct nfs_clone_mount *data = raw_data;
- return nfs_clone_generic_sb(data, nfs_clone_sb, nfs_clone_server);
-}
-
-static struct file_system_type clone_nfs_fs_type = {
- .owner = THIS_MODULE,
- .name = "nfs",
- .get_sb = nfs_clone_nfs_sb,
- .kill_sb = nfs_kill_super,
- .fs_flags = FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
#ifdef CONFIG_NFS_V4
-static void nfs4_clear_inode(struct inode *);
-
-
-static 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,
-};
-
/*
* Clean out any remaining NFSv4 state that might be left over due
* to open() calls that passed nfs_atomic_lookup, but failed to call
* nfs_open().
*/
-static void nfs4_clear_inode(struct inode *inode)
+void nfs4_clear_inode(struct inode *inode)
{
- struct nfs_inode *nfsi = NFS_I(inode);
-
/* If we are holding a delegation, return it! */
- nfs_inode_return_delegation(inode);
+ nfs_inode_return_delegation_noreclaim(inode);
/* First call standard NFS clear_inode() code */
nfs_clear_inode(inode);
- /* Now clear out any remaining state */
- while (!list_empty(&nfsi->open_states)) {
- struct nfs4_state *state;
-
- state = list_entry(nfsi->open_states.next,
- struct nfs4_state,
- inode_states);
- dprintk("%s(%s/%Ld): found unclaimed NFSv4 state %p\n",
- __FUNCTION__,
- inode->i_sb->s_id,
- (long long)NFS_FILEID(inode),
- state);
- BUG_ON(atomic_read(&state->count) != 1);
- nfs4_close_state(state, state->state);
- }
-}
-
-
-static struct rpc_clnt *nfs4_create_client(struct nfs_server *server,
- struct rpc_timeout *timeparms, int proto, rpc_authflavor_t flavor)
-{
- struct nfs4_client *clp;
- struct rpc_xprt *xprt = NULL;
- struct rpc_clnt *clnt = NULL;
- int err = -EIO;
-
- clp = nfs4_get_client(&server->addr.sin_addr);
- if (!clp) {
- dprintk("%s: failed to create NFS4 client.\n", __FUNCTION__);
- return ERR_PTR(err);
- }
-
- /* Now create transport and client */
- down_write(&clp->cl_sem);
- if (IS_ERR(clp->cl_rpcclient)) {
- xprt = xprt_create_proto(proto, &server->addr, timeparms);
- if (IS_ERR(xprt)) {
- up_write(&clp->cl_sem);
- err = PTR_ERR(xprt);
- dprintk("%s: cannot create RPC transport. Error = %d\n",
- __FUNCTION__, err);
- goto out_fail;
- }
- clnt = rpc_create_client(xprt, server->hostname, &nfs_program,
- server->rpc_ops->version, flavor);
- if (IS_ERR(clnt)) {
- up_write(&clp->cl_sem);
- err = PTR_ERR(clnt);
- dprintk("%s: cannot create RPC client. Error = %d\n",
- __FUNCTION__, err);
- goto out_fail;
- }
- clnt->cl_intr = 1;
- clnt->cl_softrtry = 1;
- clp->cl_rpcclient = clnt;
- memcpy(clp->cl_ipaddr, server->ip_addr, sizeof(clp->cl_ipaddr));
- nfs_idmap_new(clp);
- }
- list_add_tail(&server->nfs4_siblings, &clp->cl_superblocks);
- clnt = rpc_clone_client(clp->cl_rpcclient);
- if (!IS_ERR(clnt))
- server->nfs4_state = clp;
- up_write(&clp->cl_sem);
- clp = NULL;
-
- if (IS_ERR(clnt)) {
- dprintk("%s: cannot create RPC client. Error = %d\n",
- __FUNCTION__, err);
- return clnt;
- }
-
- if (server->nfs4_state->cl_idmap == NULL) {
- dprintk("%s: failed to create idmapper.\n", __FUNCTION__);
- return ERR_PTR(-ENOMEM);
- }
-
- if (clnt->cl_auth->au_flavor != flavor) {
- struct rpc_auth *auth;
-
- auth = rpcauth_create(flavor, clnt);
- if (IS_ERR(auth)) {
- dprintk("%s: couldn't create credcache!\n", __FUNCTION__);
- return (struct rpc_clnt *)auth;
- }
- }
- return clnt;
-
- out_fail:
- if (clp)
- nfs4_put_client(clp);
- return ERR_PTR(err);
-}
-
-static int nfs4_fill_super(struct super_block *sb, struct nfs4_mount_data *data, int silent)
-{
- struct nfs_server *server;
- struct rpc_timeout timeparms;
- rpc_authflavor_t authflavour;
- int err = -EIO;
-
- sb->s_blocksize_bits = 0;
- sb->s_blocksize = 0;
- server = NFS_SB(sb);
- if (data->rsize != 0)
- server->rsize = nfs_block_size(data->rsize, NULL);
- if (data->wsize != 0)
- server->wsize = nfs_block_size(data->wsize, NULL);
- server->flags = data->flags & NFS_MOUNT_FLAGMASK;
- server->caps = NFS_CAP_ATOMIC_OPEN;
-
- server->acregmin = data->acregmin*HZ;
- server->acregmax = data->acregmax*HZ;
- server->acdirmin = data->acdirmin*HZ;
- server->acdirmax = data->acdirmax*HZ;
-
- server->rpc_ops = &nfs_v4_clientops;
-
- nfs_init_timeout_values(&timeparms, data->proto, data->timeo, data->retrans);
-
- server->retrans_timeo = timeparms.to_initval;
- server->retrans_count = timeparms.to_retries;
-
- /* Now create transport and client */
- authflavour = RPC_AUTH_UNIX;
- if (data->auth_flavourlen != 0) {
- if (data->auth_flavourlen != 1) {
- dprintk("%s: Invalid number of RPC auth flavours %d.\n",
- __FUNCTION__, data->auth_flavourlen);
- err = -EINVAL;
- goto out_fail;
- }
- if (copy_from_user(&authflavour, data->auth_flavours, sizeof(authflavour))) {
- err = -EFAULT;
- goto out_fail;
- }
- }
-
- server->client = nfs4_create_client(server, &timeparms, data->proto, authflavour);
- if (IS_ERR(server->client)) {
- err = PTR_ERR(server->client);
- dprintk("%s: cannot create RPC client. Error = %d\n",
- __FUNCTION__, err);
- goto out_fail;
- }
-
- sb->s_time_gran = 1;
-
- sb->s_op = &nfs4_sops;
- err = nfs_sb_init(sb, authflavour);
-
- out_fail:
- return err;
-}
-
-static int nfs4_compare_super(struct super_block *sb, void *data)
-{
- struct nfs_server *server = data;
- struct nfs_server *old = NFS_SB(sb);
-
- if (strcmp(server->hostname, old->hostname) != 0)
- return 0;
- if (strcmp(server->mnt_path, old->mnt_path) != 0)
- return 0;
- return 1;
-}
-
-static void *
-nfs_copy_user_string(char *dst, struct nfs_string *src, int maxlen)
-{
- void *p = NULL;
-
- if (!src->len)
- return ERR_PTR(-EINVAL);
- if (src->len < maxlen)
- maxlen = src->len;
- if (dst == NULL) {
- p = dst = kmalloc(maxlen + 1, GFP_KERNEL);
- if (p == NULL)
- return ERR_PTR(-ENOMEM);
- }
- if (copy_from_user(dst, src->data, maxlen)) {
- kfree(p);
- return ERR_PTR(-EFAULT);
- }
- dst[maxlen] = '\0';
- return dst;
-}
-
-static struct super_block *nfs4_get_sb(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *raw_data)
-{
- int error;
- struct nfs_server *server;
- struct super_block *s;
- struct nfs4_mount_data *data = raw_data;
- void *p;
-
- if (data == NULL) {
- dprintk("%s: missing data argument\n", __FUNCTION__);
- return ERR_PTR(-EINVAL);
- }
- if (data->version <= 0 || data->version > NFS4_MOUNT_VERSION) {
- dprintk("%s: bad mount version\n", __FUNCTION__);
- return ERR_PTR(-EINVAL);
- }
-
- server = kzalloc(sizeof(struct nfs_server), GFP_KERNEL);
- if (!server)
- return ERR_PTR(-ENOMEM);
- /* Zero out the NFS state stuff */
- init_nfsv4_state(server);
- server->client = server->client_sys = server->client_acl = ERR_PTR(-EINVAL);
-
- p = nfs_copy_user_string(NULL, &data->hostname, 256);
- if (IS_ERR(p))
- goto out_err;
- server->hostname = p;
-
- p = nfs_copy_user_string(NULL, &data->mnt_path, 1024);
- if (IS_ERR(p))
- goto out_err;
- server->mnt_path = p;
-
- p = nfs_copy_user_string(server->ip_addr, &data->client_addr,
- sizeof(server->ip_addr) - 1);
- if (IS_ERR(p))
- goto out_err;
-
- /* We now require that the mount process passes the remote address */
- if (data->host_addrlen != sizeof(server->addr)) {
- s = ERR_PTR(-EINVAL);
- goto out_free;
- }
- if (copy_from_user(&server->addr, data->host_addr, sizeof(server->addr))) {
- s = ERR_PTR(-EFAULT);
- goto out_free;
- }
- if (server->addr.sin_family != AF_INET ||
- server->addr.sin_addr.s_addr == INADDR_ANY) {
- dprintk("%s: mount program didn't pass remote IP address!\n",
- __FUNCTION__);
- s = ERR_PTR(-EINVAL);
- goto out_free;
- }
-
- /* Fire up rpciod if not yet running */
- s = ERR_PTR(rpciod_up());
- if (IS_ERR(s)) {
- dprintk("%s: couldn't start rpciod! Error = %ld\n",
- __FUNCTION__, PTR_ERR(s));
- goto out_free;
- }
-
- s = sget(fs_type, nfs4_compare_super, nfs_set_super, server);
-
- if (IS_ERR(s) || s->s_root)
- goto out_free;
-
- s->s_flags = flags;
-
- error = nfs4_fill_super(s, data, flags & MS_SILENT ? 1 : 0);
- if (error) {
- up_write(&s->s_umount);
- deactivate_super(s);
- return ERR_PTR(error);
- }
- s->s_flags |= MS_ACTIVE;
- return s;
-out_err:
- s = (struct super_block *)p;
-out_free:
- kfree(server->mnt_path);
- kfree(server->hostname);
- kfree(server);
- return s;
-}
-
-static void nfs4_kill_super(struct super_block *sb)
-{
- struct nfs_server *server = NFS_SB(sb);
-
- nfs_return_all_delegations(sb);
- kill_anon_super(sb);
-
- nfs4_renewd_prepare_shutdown(server);
-
- if (server->client != NULL && !IS_ERR(server->client))
- rpc_shutdown_client(server->client);
-
- destroy_nfsv4_state(server);
-
- rpciod_down();
-
- nfs_free_iostats(server->io_stats);
- kfree(server->hostname);
- kfree(server);
- nfs_release_automount_timer();
-}
-
-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_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
-
-static const int nfs_set_port_min = 0;
-static const int nfs_set_port_max = 65535;
-static int param_set_port(const char *val, struct kernel_param *kp)
-{
- char *endp;
- int num = simple_strtol(val, &endp, 0);
- if (endp == val || *endp || num < nfs_set_port_min || num > nfs_set_port_max)
- return -EINVAL;
- *((int *)kp->arg) = num;
- return 0;
-}
-
-module_param_call(callback_tcpport, param_set_port, param_get_int,
- &nfs_callback_set_tcpport, 0644);
-
-static int param_set_idmap_timeout(const char *val, struct kernel_param *kp)
-{
- char *endp;
- int num = simple_strtol(val, &endp, 0);
- int jif = num * HZ;
- if (endp == val || *endp || num < 0 || jif < num)
- return -EINVAL;
- *((int *)kp->arg) = jif;
- return 0;
-}
-
-module_param_call(idmap_cache_timeout, param_set_idmap_timeout, param_get_int,
- &nfs_idmap_cache_timeout, 0644);
-
-/* Constructs the SERVER-side path */
-static inline char *nfs4_path(const struct dentry *dentry, char *buffer, ssize_t buflen)
-{
- return nfs_path(NFS_SB(dentry->d_sb)->mnt_path, dentry, buffer, buflen);
-}
-
-static inline char *nfs4_dup_path(const struct dentry *dentry)
-{
- char *page = (char *) __get_free_page(GFP_USER);
- char *path;
-
- path = nfs4_path(dentry, page, PAGE_SIZE);
- if (!IS_ERR(path)) {
- int len = PAGE_SIZE + page - path;
- char *tmp = path;
-
- path = kmalloc(len, GFP_KERNEL);
- if (path)
- memcpy(path, tmp, len);
- else
- path = ERR_PTR(-ENOMEM);
- }
- free_page((unsigned long)page);
- return path;
-}
-
-static struct super_block *nfs4_clone_sb(struct nfs_server *server, struct nfs_clone_mount *data)
-{
- const struct dentry *dentry = data->dentry;
- struct nfs4_client *clp = server->nfs4_state;
- struct super_block *sb;
-
- server->fsid = data->fattr->fsid;
- nfs_copy_fh(&server->fh, data->fh);
- server->mnt_path = nfs4_dup_path(dentry);
- if (IS_ERR(server->mnt_path)) {
- sb = (struct super_block *)server->mnt_path;
- goto err;
- }
- sb = sget(&nfs4_fs_type, nfs4_compare_super, nfs_set_super, server);
- if (IS_ERR(sb) || sb->s_root)
- goto free_path;
- nfs4_server_capabilities(server, &server->fh);
-
- down_write(&clp->cl_sem);
- atomic_inc(&clp->cl_count);
- list_add_tail(&server->nfs4_siblings, &clp->cl_superblocks);
- up_write(&clp->cl_sem);
- return sb;
-free_path:
- kfree(server->mnt_path);
-err:
- server->mnt_path = NULL;
- return sb;
-}
-
-static struct super_block *nfs_clone_nfs4_sb(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *raw_data)
-{
- struct nfs_clone_mount *data = raw_data;
- return nfs_clone_generic_sb(data, nfs4_clone_sb, nfs_clone_server);
-}
-
-static struct file_system_type clone_nfs4_fs_type = {
- .owner = THIS_MODULE,
- .name = "nfs4",
- .get_sb = nfs_clone_nfs4_sb,
- .kill_sb = nfs4_kill_super,
- .fs_flags = FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
-
-#define nfs4_init_once(nfsi) \
- do { \
- INIT_LIST_HEAD(&(nfsi)->open_states); \
- nfsi->delegation = NULL; \
- nfsi->delegation_state = 0; \
- init_rwsem(&nfsi->rwsem); \
- } while(0)
-
-static inline int register_nfs4fs(void)
-{
- int ret;
-
- ret = nfs_register_sysctl();
- if (ret != 0)
- return ret;
- ret = register_filesystem(&nfs4_fs_type);
- if (ret != 0)
- nfs_unregister_sysctl();
- return ret;
-}
-
-static inline void unregister_nfs4fs(void)
-{
- unregister_filesystem(&nfs4_fs_type);
- nfs_unregister_sysctl();
-}
-#else
-#define nfs4_fill_sb(a,b) ERR_PTR(-EINVAL)
-#define nfs4_fill_super(a,b) ERR_PTR(-EINVAL)
-#define nfs4_init_once(nfsi) \
- do { } while (0)
-#define register_nfs4fs() (0)
-#define unregister_nfs4fs()
-#endif
-
-static inline char *nfs_devname(const struct vfsmount *mnt_parent,
- const struct dentry *dentry,
- char *buffer, ssize_t buflen)
-{
- return nfs_path(mnt_parent->mnt_devname, dentry, buffer, buflen);
-}
-
-/**
- * nfs_do_submount - set up mountpoint when crossing a filesystem boundary
- * @mnt_parent - mountpoint of parent directory
- * @dentry - parent directory
- * @fh - filehandle for new root dentry
- * @fattr - attributes for new root inode
- *
- */
-struct vfsmount *nfs_do_submount(const struct vfsmount *mnt_parent,
- const struct dentry *dentry, struct nfs_fh *fh,
- struct nfs_fattr *fattr)
-{
- struct nfs_clone_mount mountdata = {
- .sb = mnt_parent->mnt_sb,
- .dentry = dentry,
- .fh = fh,
- .fattr = fattr,
- };
- struct vfsmount *mnt = ERR_PTR(-ENOMEM);
- char *page = (char *) __get_free_page(GFP_USER);
- char *devname;
-
- dprintk("%s: submounting on %s/%s\n", __FUNCTION__,
- dentry->d_parent->d_name.name,
- dentry->d_name.name);
- if (page == NULL)
- goto out;
- devname = nfs_devname(mnt_parent, dentry, page, PAGE_SIZE);
- mnt = (struct vfsmount *)devname;
- if (IS_ERR(devname))
- goto free_page;
- switch (NFS_SB(mnt_parent->mnt_sb)->rpc_ops->version) {
- case 2:
- case 3:
- mnt = vfs_kern_mount(&clone_nfs_fs_type, 0, devname, &mountdata);
- break;
- case 4:
- mnt = vfs_kern_mount(&clone_nfs4_fs_type, 0, devname, &mountdata);
- break;
- default:
- BUG();
- }
-free_page:
- free_page((unsigned long)page);
-out:
- dprintk("%s: done\n", __FUNCTION__);
- return mnt;
}
-
-/* Check if fs_root is valid */
-static inline char *nfs4_pathname_string(struct nfs4_pathname *pathname, char *buffer, ssize_t buflen)
-{
- char *end = buffer + buflen;
- int n;
-
- *--end = '\0';
- buflen--;
-
- n = pathname->ncomponents;
- while (--n >= 0) {
- struct nfs4_string *component = &pathname->components[n];
- buflen -= component->len + 1;
- if (buflen < 0)
- goto Elong;
- end -= component->len;
- memcpy(end, component->data, component->len);
- *--end = '/';
- }
- return end;
-Elong:
- return ERR_PTR(-ENAMETOOLONG);
-}
-
-/* Check if the string represents a "valid" IPv4 address */
-static inline int valid_ipaddr4(const char *buf)
-{
- int rc, count, in[4];
-
- rc = sscanf(buf, "%d.%d.%d.%d", &in[0], &in[1], &in[2], &in[3]);
- if (rc != 4)
- return -EINVAL;
- for (count = 0; count < 4; count++) {
- if (in[count] > 255)
- return -EINVAL;
- }
- return 0;
-}
-
-static struct super_block *nfs4_referral_sb(struct nfs_server *server, struct nfs_clone_mount *data)
-{
- struct super_block *sb = ERR_PTR(-ENOMEM);
- int len;
-
- len = strlen(data->mnt_path) + 1;
- server->mnt_path = kmalloc(len, GFP_KERNEL);
- if (server->mnt_path == NULL)
- goto err;
- memcpy(server->mnt_path, data->mnt_path, len);
- memcpy(&server->addr, data->addr, sizeof(struct sockaddr_in));
-
- sb = sget(&nfs4_fs_type, nfs4_compare_super, nfs_set_super, server);
- if (IS_ERR(sb) || sb->s_root)
- goto free_path;
- return sb;
-free_path:
- kfree(server->mnt_path);
-err:
- server->mnt_path = NULL;
- return sb;
-}
-
-static struct nfs_server *nfs4_referral_server(struct super_block *sb, struct nfs_clone_mount *data)
-{
- struct nfs_server *server = NFS_SB(sb);
- struct rpc_timeout timeparms;
- int proto, timeo, retrans;
- void *err;
-
- proto = IPPROTO_TCP;
- /* Since we are following a referral and there may be alternatives,
- set the timeouts and retries to low values */
- timeo = 2;
- retrans = 1;
- nfs_init_timeout_values(&timeparms, proto, timeo, retrans);
-
- server->client = nfs4_create_client(server, &timeparms, proto, data->authflavor);
- if (IS_ERR((err = server->client)))
- goto out_err;
-
- sb->s_time_gran = 1;
- sb->s_op = &nfs4_sops;
- err = ERR_PTR(nfs_sb_init(sb, data->authflavor));
- if (!IS_ERR(err))
- return server;
-out_err:
- return (struct nfs_server *)err;
-}
-
-static struct super_block *nfs_referral_nfs4_sb(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *raw_data)
-{
- struct nfs_clone_mount *data = raw_data;
- return nfs_clone_generic_sb(data, nfs4_referral_sb, nfs4_referral_server);
-}
-
-static struct file_system_type nfs_referral_nfs4_fs_type = {
- .owner = THIS_MODULE,
- .name = "nfs4",
- .get_sb = nfs_referral_nfs4_sb,
- .kill_sb = nfs4_kill_super,
- .fs_flags = FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
-
-/**
- * nfs_follow_referral - set up mountpoint when hitting a referral on moved error
- * @mnt_parent - mountpoint of parent directory
- * @dentry - parent directory
- * @fspath - fs path returned in fs_locations
- * @mntpath - mount path to new server
- * @hostname - hostname of new server
- * @addr - host addr of new server
- *
- */
-struct vfsmount *nfs_follow_referral(const struct vfsmount *mnt_parent,
- const struct dentry *dentry, struct nfs4_fs_locations *locations)
-{
- struct vfsmount *mnt = ERR_PTR(-ENOENT);
- struct nfs_clone_mount mountdata = {
- .sb = mnt_parent->mnt_sb,
- .dentry = dentry,
- .authflavor = NFS_SB(mnt_parent->mnt_sb)->client->cl_auth->au_flavor,
- };
- char *page, *page2;
- char *path, *fs_path;
- char *devname;
- int loc, s;
-
- if (locations == NULL || locations->nlocations <= 0)
- goto out;
-
- dprintk("%s: referral at %s/%s\n", __FUNCTION__,
- dentry->d_parent->d_name.name, dentry->d_name.name);
-
- /* Ensure fs path is a prefix of current dentry path */
- page = (char *) __get_free_page(GFP_USER);
- if (page == NULL)
- goto out;
- page2 = (char *) __get_free_page(GFP_USER);
- if (page2 == NULL)
- goto out;
-
- path = nfs4_path(dentry, page, PAGE_SIZE);
- if (IS_ERR(path))
- goto out_free;
-
- fs_path = nfs4_pathname_string(&locations->fs_path, page2, PAGE_SIZE);
- if (IS_ERR(fs_path))
- goto out_free;
-
- if (strncmp(path, fs_path, strlen(fs_path)) != 0) {
- dprintk("%s: path %s does not begin with fsroot %s\n", __FUNCTION__, path, fs_path);
- goto out_free;
- }
-
- devname = nfs_devname(mnt_parent, dentry, page, PAGE_SIZE);
- if (IS_ERR(devname)) {
- mnt = (struct vfsmount *)devname;
- goto out_free;
- }
-
- loc = 0;
- while (loc < locations->nlocations && IS_ERR(mnt)) {
- struct nfs4_fs_location *location = &locations->locations[loc];
- char *mnt_path;
-
- if (location == NULL || location->nservers <= 0 ||
- location->rootpath.ncomponents == 0) {
- loc++;
- continue;
- }
-
- mnt_path = nfs4_pathname_string(&location->rootpath, page2, PAGE_SIZE);
- if (IS_ERR(mnt_path)) {
- loc++;
- continue;
- }
- mountdata.mnt_path = mnt_path;
-
- s = 0;
- while (s < location->nservers) {
- struct sockaddr_in addr = {};
-
- if (location->servers[s].len <= 0 ||
- valid_ipaddr4(location->servers[s].data) < 0) {
- s++;
- continue;
- }
-
- mountdata.hostname = location->servers[s].data;
- addr.sin_addr.s_addr = in_aton(mountdata.hostname);
- addr.sin_family = AF_INET;
- addr.sin_port = htons(NFS_PORT);
- mountdata.addr = &addr;
-
- mnt = vfs_kern_mount(&nfs_referral_nfs4_fs_type, 0, devname, &mountdata);
- if (!IS_ERR(mnt)) {
- break;
- }
- s++;
- }
- loc++;
- }
-
-out_free:
- free_page((unsigned long)page);
- free_page((unsigned long)page2);
-out:
- dprintk("%s: done\n", __FUNCTION__);
- return mnt;
-}
-
-/*
- * nfs_do_refmount - handle crossing a referral on server
- * @dentry - dentry of referral
- * @nd - nameidata info
- *
- */
-struct vfsmount *nfs_do_refmount(const struct vfsmount *mnt_parent, struct dentry *dentry)
-{
- struct vfsmount *mnt = ERR_PTR(-ENOENT);
- struct dentry *parent;
- struct nfs4_fs_locations *fs_locations = NULL;
- struct page *page;
- int err;
-
- /* BUG_ON(IS_ROOT(dentry)); */
- dprintk("%s: enter\n", __FUNCTION__);
-
- page = alloc_page(GFP_KERNEL);
- if (page == NULL)
- goto out;
-
- fs_locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL);
- if (fs_locations == NULL)
- goto out_free;
-
- /* Get locations */
- parent = dget_parent(dentry);
- dprintk("%s: getting locations for %s/%s\n", __FUNCTION__, parent->d_name.name, dentry->d_name.name);
- err = nfs4_proc_fs_locations(parent->d_inode, dentry, fs_locations, page);
- dput(parent);
- if (err != 0 || fs_locations->nlocations <= 0 ||
- fs_locations->fs_path.ncomponents <= 0)
- goto out_free;
-
- mnt = nfs_follow_referral(mnt_parent, dentry, fs_locations);
-out_free:
- __free_page(page);
- kfree(fs_locations);
-out:
- dprintk("%s: done\n", __FUNCTION__);
- return mnt;
-}
-
-extern int nfs_init_nfspagecache(void);
-extern void nfs_destroy_nfspagecache(void);
-extern int nfs_init_readpagecache(void);
-extern void nfs_destroy_readpagecache(void);
-extern int nfs_init_writepagecache(void);
-extern void nfs_destroy_writepagecache(void);
-#ifdef CONFIG_NFS_DIRECTIO
-extern int nfs_init_directcache(void);
-extern void nfs_destroy_directcache(void);
#endif
-static kmem_cache_t * nfs_inode_cachep;
-
-static struct inode *nfs_alloc_inode(struct super_block *sb)
+struct inode *nfs_alloc_inode(struct super_block *sb)
{
struct nfs_inode *nfsi;
- nfsi = (struct nfs_inode *)kmem_cache_alloc(nfs_inode_cachep, SLAB_KERNEL);
+ nfsi = (struct nfs_inode *)kmem_cache_alloc(nfs_inode_cachep, GFP_KERNEL);
if (!nfsi)
return NULL;
nfsi->flags = 0UL;
nfsi->cache_validity = 0UL;
- nfsi->cache_change_attribute = jiffies;
#ifdef CONFIG_NFS_V3_ACL
nfsi->acl_access = ERR_PTR(-EAGAIN);
nfsi->acl_default = ERR_PTR(-EAGAIN);
return &nfsi->vfs_inode;
}
-static void nfs_destroy_inode(struct inode *inode)
+void nfs_destroy_inode(struct inode *inode)
{
kmem_cache_free(nfs_inode_cachep, NFS_I(inode));
}
-static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
+static inline void nfs4_init_once(struct nfs_inode *nfsi)
+{
+#ifdef CONFIG_NFS_V4
+ INIT_LIST_HEAD(&nfsi->open_states);
+ nfsi->delegation = NULL;
+ nfsi->delegation_state = 0;
+ init_rwsem(&nfsi->rwsem);
+#endif
+}
+
+static void init_once(struct kmem_cache * cachep, void *foo)
{
struct nfs_inode *nfsi = (struct nfs_inode *) foo;
- if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
- SLAB_CTOR_CONSTRUCTOR) {
- inode_init_once(&nfsi->vfs_inode);
- spin_lock_init(&nfsi->req_lock);
- INIT_LIST_HEAD(&nfsi->dirty);
- INIT_LIST_HEAD(&nfsi->commit);
- INIT_LIST_HEAD(&nfsi->open_files);
- INIT_RADIX_TREE(&nfsi->nfs_page_tree, GFP_ATOMIC);
- atomic_set(&nfsi->data_updates, 0);
- nfsi->ndirty = 0;
- nfsi->ncommit = 0;
- nfsi->npages = 0;
- nfs4_init_once(nfsi);
- }
+ inode_init_once(&nfsi->vfs_inode);
+ INIT_LIST_HEAD(&nfsi->open_files);
+ INIT_LIST_HEAD(&nfsi->access_cache_entry_lru);
+ INIT_LIST_HEAD(&nfsi->access_cache_inode_lru);
+ INIT_RADIX_TREE(&nfsi->nfs_page_tree, GFP_ATOMIC);
+ nfsi->ncommit = 0;
+ nfsi->npages = 0;
+ atomic_set(&nfsi->silly_count, 1);
+ INIT_HLIST_HEAD(&nfsi->silly_list);
+ init_waitqueue_head(&nfsi->waitqueue);
+ nfs4_init_once(nfsi);
}
-
-static int nfs_init_inodecache(void)
+
+static int __init nfs_init_inodecache(void)
{
nfs_inode_cachep = kmem_cache_create("nfs_inode_cache",
sizeof(struct nfs_inode),
0, (SLAB_RECLAIM_ACCOUNT|
SLAB_MEM_SPREAD),
- init_once, NULL);
+ init_once);
if (nfs_inode_cachep == NULL)
return -ENOMEM;
static void nfs_destroy_inodecache(void)
{
- if (kmem_cache_destroy(nfs_inode_cachep))
- printk(KERN_INFO "nfs_inode_cache: not all structures were freed\n");
+ kmem_cache_destroy(nfs_inode_cachep);
+}
+
+struct workqueue_struct *nfsiod_workqueue;
+
+/*
+ * start up the nfsiod workqueue
+ */
+static int nfsiod_start(void)
+{
+ struct workqueue_struct *wq;
+ dprintk("RPC: creating workqueue nfsiod\n");
+ wq = create_singlethread_workqueue("nfsiod");
+ if (wq == NULL)
+ return -ENOMEM;
+ nfsiod_workqueue = wq;
+ return 0;
+}
+
+/*
+ * Destroy the nfsiod workqueue
+ */
+static void nfsiod_stop(void)
+{
+ struct workqueue_struct *wq;
+
+ wq = nfsiod_workqueue;
+ if (wq == NULL)
+ return;
+ nfsiod_workqueue = NULL;
+ destroy_workqueue(wq);
}
/*
{
int err;
+ err = nfsiod_start();
+ if (err)
+ goto out6;
+
+ err = nfs_fs_proc_init();
+ if (err)
+ goto out5;
+
err = nfs_init_nfspagecache();
if (err)
goto out4;
if (err)
goto out1;
-#ifdef CONFIG_NFS_DIRECTIO
err = nfs_init_directcache();
if (err)
goto out0;
-#endif
#ifdef CONFIG_PROC_FS
rpc_proc_register(&nfs_rpcstat);
#endif
- err = register_filesystem(&nfs_fs_type);
- if (err)
- goto out;
- if ((err = register_nfs4fs()) != 0)
+ if ((err = register_nfs_fs()) != 0)
goto out;
return 0;
out:
#ifdef CONFIG_PROC_FS
rpc_proc_unregister("nfs");
#endif
-#ifdef CONFIG_NFS_DIRECTIO
nfs_destroy_directcache();
out0:
-#endif
nfs_destroy_writepagecache();
out1:
nfs_destroy_readpagecache();
out3:
nfs_destroy_nfspagecache();
out4:
+ nfs_fs_proc_exit();
+out5:
+ nfsiod_stop();
+out6:
return err;
}
static void __exit exit_nfs_fs(void)
{
-#ifdef CONFIG_NFS_DIRECTIO
nfs_destroy_directcache();
-#endif
nfs_destroy_writepagecache();
nfs_destroy_readpagecache();
nfs_destroy_inodecache();
#ifdef CONFIG_PROC_FS
rpc_proc_unregister("nfs");
#endif
- unregister_filesystem(&nfs_fs_type);
- unregister_nfs4fs();
+ unregister_nfs_fs();
+ nfs_fs_proc_exit();
+ nfsiod_stop();
}
/* Not quite true; I just maintain it */
MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>");
MODULE_LICENSE("GPL");
+module_param(enable_ino64, bool, 0644);
module_init(init_nfs_fs)
module_exit(exit_nfs_fs)
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff