linux-sg2042/fs/nfs/inode.c

1529 lines
43 KiB
C
Raw Normal View History

/*
* linux/fs/nfs/inode.c
*
* Copyright (C) 1992 Rick Sladkey
*
* nfs inode and superblock handling functions
*
* Modularised by Alan Cox <alan@lxorguk.ukuu.org.uk>, 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.
* J.S.Peatfield@damtp.cam.ac.uk
*
*/
#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 <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/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/nfs4_mount.h>
#include <linux/lockd/bind.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 <asm/system.h>
#include <asm/uaccess.h>
#include "nfs4_fs.h"
#include "callback.h"
#include "delegation.h"
#include "iostat.h"
#include "internal.h"
#include "fscache.h"
#define NFSDBG_FACILITY NFSDBG_VFS
#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 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);
}
2009-03-12 02:10:30 +08:00
/**
* nfs_wait_bit_killable - helper for functions that are sleeping on bit locks
* @word: long word containing the bit lock
*/
int nfs_wait_bit_killable(void *word)
{
if (fatal_signal_pending(current))
return -ERESTARTSYS;
schedule();
return 0;
}
/**
* 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.
*/
u64 nfs_compat_user_ino64(u64 fileid)
{
int ino;
if (enable_ino64)
return fileid;
ino = fileid;
if (sizeof(ino) < sizeof(fileid))
ino ^= fileid >> (sizeof(fileid)-sizeof(ino)) * 8;
return ino;
}
int nfs_write_inode(struct inode *inode, int sync)
{
int ret;
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;
}
void nfs_clear_inode(struct inode *inode)
{
/*
* The following should never happen...
*/
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_fscache_release_inode_cookie(inode);
}
/**
* nfs_sync_mapping - helper to flush all mmapped dirty data to disk
*/
int nfs_sync_mapping(struct address_space *mapping)
{
int ret;
if (mapping->nrpages == 0)
return 0;
unmap_mapping_range(mapping, 0, 0, 0);
ret = filemap_write_and_wait(mapping);
if (ret != 0)
goto out;
ret = nfs_wb_all(mapping->host);
out:
return ret;
}
/*
* Invalidate the local caches
*/
static void nfs_zap_caches_locked(struct inode *inode)
{
struct nfs_inode *nfsi = NFS_I(inode);
int mode = inode->i_mode;
nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
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))
nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE;
else
nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE;
}
void nfs_zap_caches(struct inode *inode)
{
spin_lock(&inode->i_lock);
nfs_zap_caches_locked(inode);
spin_unlock(&inode->i_lock);
}
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 *);
clear_acl_cache = NFS_PROTO(inode)->clear_acl_cache;
if (clear_acl_cache != NULL)
clear_acl_cache(inode);
spin_lock(&inode->i_lock);
NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_ACL;
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_I(inode)->flags);
nfs_zap_caches_locked(inode);
}
struct nfs_find_desc {
struct nfs_fh *fh;
struct nfs_fattr *fattr;
};
/*
* In NFSv3 we can have 64bit inode numbers. In order to support
* this, and re-exported directories (also seen in NFSv2)
* we are forced to allow 2 different inodes to have the same
* i_ino.
*/
static int
nfs_find_actor(struct inode *inode, void *opaque)
{
struct nfs_find_desc *desc = (struct nfs_find_desc *)opaque;
struct nfs_fh *fh = desc->fh;
struct nfs_fattr *fattr = desc->fattr;
if (NFS_FILEID(inode) != fattr->fileid)
return 0;
if (nfs_compare_fh(NFS_FH(inode), fh))
return 0;
if (is_bad_inode(inode) || NFS_STALE(inode))
return 0;
return 1;
}
static int
nfs_init_locked(struct inode *inode, void *opaque)
{
struct nfs_find_desc *desc = (struct nfs_find_desc *)opaque;
struct nfs_fattr *fattr = desc->fattr;
set_nfs_fileid(inode, fattr->fileid);
nfs_copy_fh(NFS_FH(inode), desc->fh);
return 0;
}
/* Don't use READDIRPLUS on directories that we believe are too large */
#define NFS_LIMIT_READDIRPLUS (8*PAGE_SIZE)
/*
* This is our front-end to iget that looks up inodes by file handle
* instead of inode number.
*/
struct inode *
nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
{
struct nfs_find_desc desc = {
.fh = fh,
.fattr = fattr
};
struct inode *inode = ERR_PTR(-ENOENT);
unsigned long hash;
if ((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0)
goto out_no_inode;
if ((fattr->valid & NFS_ATTR_FATTR_TYPE) == 0)
goto out_no_inode;
hash = nfs_fattr_to_ino_t(fattr);
inode = iget5_locked(sb, hash, nfs_find_actor, nfs_init_locked, &desc);
if (inode == NULL) {
inode = ERR_PTR(-ENOMEM);
goto out_no_inode;
}
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) */
inode->i_ino = hash;
/* We can't support update_atime(), since the server will reset it */
inode->i_flags |= S_NOATIME|S_NOCMTIME;
inode->i_mode = fattr->mode;
/* 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)->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)->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_I(inode)->flags);
/* Deal with crossing mountpoints */
if ((fattr->valid & NFS_ATTR_FATTR_FSID)
&& !nfs_fsid_equal(&NFS_SB(sb)->fsid, &fattr->fsid)) {
if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)
inode->i_op = &nfs_referral_inode_operations;
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;
else
init_special_inode(inode, inode->i_mode, fattr->rdev);
memset(&inode->i_atime, 0, sizeof(inode->i_atime));
memset(&inode->i_mtime, 0, sizeof(inode->i_mtime));
memset(&inode->i_ctime, 0, sizeof(inode->i_ctime));
nfsi->change_attr = 0;
inode->i_size = 0;
inode->i_nlink = 0;
inode->i_uid = -2;
inode->i_gid = -2;
inode->i_blocks = 0;
memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
nfsi->read_cache_jiffies = fattr->time_start;
nfsi->attr_gencount = fattr->gencount;
if (fattr->valid & NFS_ATTR_FATTR_ATIME)
inode->i_atime = fattr->atime;
if (fattr->valid & NFS_ATTR_FATTR_MTIME)
inode->i_mtime = fattr->mtime;
if (fattr->valid & NFS_ATTR_FATTR_CTIME)
inode->i_ctime = fattr->ctime;
if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
nfsi->change_attr = fattr->change_attr;
if (fattr->valid & NFS_ATTR_FATTR_SIZE)
inode->i_size = nfs_size_to_loff_t(fattr->size);
if (fattr->valid & NFS_ATTR_FATTR_NLINK)
inode->i_nlink = fattr->nlink;
if (fattr->valid & NFS_ATTR_FATTR_OWNER)
inode->i_uid = fattr->uid;
if (fattr->valid & NFS_ATTR_FATTR_GROUP)
inode->i_gid = fattr->gid;
if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
inode->i_blocks = fattr->du.nfs2.blocks;
if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
/*
* report the blocks in 512byte units
*/
inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
}
nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
nfsi->attrtimeo_timestamp = now;
nfsi->access_cache = RB_ROOT;
nfs_fscache_init_inode_cookie(inode);
unlock_new_inode(inode);
} else
nfs_refresh_inode(inode, fattr);
dprintk("NFS: nfs_fhget(%s/%Ld ct=%d)\n",
inode->i_sb->s_id,
(long long)NFS_FILEID(inode),
atomic_read(&inode->i_count));
out:
return inode;
out_no_inode:
dprintk("nfs_fhget: iget failed with error %ld\n", PTR_ERR(inode));
goto out;
}
#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)
{
struct inode *inode = dentry->d_inode;
struct nfs_fattr fattr;
int error;
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 & ~ATTR_FILE) == 0)
return 0;
/* Write all dirty data */
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
*/
if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0)
nfs_inode_return_delegation(inode);
error = NFS_PROTO(inode)->setattr(dentry, &fattr, attr);
if (error == 0)
nfs_refresh_inode(inode, &fattr);
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
*
* Note: we do this in the *proc.c in order to ensure that
* it works for things like exclusive creates too.
*/
void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
{
if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) {
spin_lock(&inode->i_lock);
if ((attr->ia_valid & ATTR_MODE) != 0) {
int mode = attr->ia_mode & S_IALLUGO;
mode |= inode->i_mode & ~S_IALLUGO;
inode->i_mode = mode;
}
if ((attr->ia_valid & ATTR_UID) != 0)
inode->i_uid = attr->ia_uid;
if ((attr->ia_valid & ATTR_GID) != 0)
inode->i_gid = attr->ia_gid;
NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
spin_unlock(&inode->i_lock);
}
if ((attr->ia_valid & ATTR_SIZE) != 0) {
nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC);
nfs_vmtruncate(inode, attr->ia_size);
}
}
int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
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.
*
* 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.
*
* Note that we only have to check the vfsmount flags here:
* - NFS always sets S_NOATIME by so checking it would give a
* bogus result
* - NFS never sets MS_NOATIME or MS_NODIRATIME so there is
* no point in checking those.
*/
if ((mnt->mnt_flags & MNT_NOATIME) ||
((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)))
need_atime = 0;
if (need_atime)
err = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
else
err = nfs_revalidate_inode(NFS_SERVER(inode), inode);
if (!err) {
generic_fillattr(inode, stat);
stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
}
return err;
}
/**
* nfs_close_context - Common close_context() routine NFSv2/v3
* @ctx: pointer to context
* @is_sync: is this a synchronous close
*
* always ensure that the attributes are up to date if we're mounted
* with close-to-open semantics
*/
void nfs_close_context(struct nfs_open_context *ctx, int is_sync)
{
struct inode *inode;
struct nfs_server *server;
if (!(ctx->mode & FMODE_WRITE))
return;
if (!is_sync)
return;
inode = ctx->path.dentry->d_inode;
if (!list_empty(&NFS_I(inode)->open_files))
return;
server = NFS_SERVER(inode);
if (server->flags & NFS_MOUNT_NOCTO)
return;
nfs_revalidate_inode(server, inode);
}
static struct nfs_open_context *alloc_nfs_open_context(struct vfsmount *mnt, struct dentry *dentry, struct rpc_cred *cred)
{
struct nfs_open_context *ctx;
ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
if (ctx != NULL) {
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;
}
struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx)
{
if (ctx != NULL)
atomic_inc(&ctx->count);
return ctx;
}
static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
{
struct inode *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);
NFS_PROTO(inode)->close_context(ctx, is_sync);
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);
}
/*
* Ensure that mmap has a recent RPC credential for use when writing out
* shared pages
*/
static void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx)
{
struct inode *inode = filp->f_path.dentry->d_inode;
struct nfs_inode *nfsi = NFS_I(inode);
filp->private_data = get_nfs_open_context(ctx);
spin_lock(&inode->i_lock);
list_add(&ctx->list, &nfsi->open_files);
spin_unlock(&inode->i_lock);
}
/*
* Given an inode, search for an open context with the desired characteristics
*/
struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, fmode_t mode)
{
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_open_context *pos, *ctx = NULL;
spin_lock(&inode->i_lock);
list_for_each_entry(pos, &nfsi->open_files, list) {
if (cred != NULL && pos->cred != cred)
continue;
if ((pos->mode & mode) == mode) {
ctx = get_nfs_open_context(pos);
break;
}
}
spin_unlock(&inode->i_lock);
return ctx;
}
static void nfs_file_clear_open_context(struct file *filp)
{
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_sync(ctx);
}
}
/*
* These allocate and release file read/write context information.
*/
int nfs_open(struct inode *inode, struct file *filp)
{
struct nfs_open_context *ctx;
struct rpc_cred *cred;
cred = rpc_lookup_cred();
if (IS_ERR(cred))
return PTR_ERR(cred);
ctx = alloc_nfs_open_context(filp->f_path.mnt, filp->f_path.dentry, cred);
put_rpccred(cred);
if (ctx == NULL)
return -ENOMEM;
ctx->mode = filp->f_mode;
nfs_file_set_open_context(filp, ctx);
put_nfs_open_context(ctx);
nfs_fscache_set_inode_cookie(inode, filp);
return 0;
}
int nfs_release(struct inode *inode, struct file *filp)
{
nfs_file_clear_open_context(filp);
return 0;
}
/*
* This function is called whenever some part of NFS notices that
* the cached attributes have to be refreshed.
*/
int
__nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
{
int status = -ESTALE;
struct nfs_fattr fattr;
struct nfs_inode *nfsi = NFS_I(inode);
dfprintk(PAGECACHE, "NFS: revalidating (%s/%Ld)\n",
inode->i_sb->s_id, (long long)NFS_FILEID(inode));
if (is_bad_inode(inode))
goto out;
if (NFS_STALE(inode))
goto out;
nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE);
status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), &fattr);
if (status != 0) {
dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Ld) getattr failed, error=%d\n",
inode->i_sb->s_id,
(long long)NFS_FILEID(inode), status);
if (status == -ESTALE) {
nfs_zap_caches(inode);
if (!S_ISDIR(inode->i_mode))
set_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
}
goto out;
}
status = nfs_refresh_inode(inode, &fattr);
if (status) {
dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Ld) refresh failed, error=%d\n",
inode->i_sb->s_id,
(long long)NFS_FILEID(inode), status);
goto out;
}
if (nfsi->cache_validity & NFS_INO_INVALID_ACL)
nfs_zap_acl_cache(inode);
dfprintk(PAGECACHE, "NFS: (%s/%Ld) revalidation complete\n",
inode->i_sb->s_id,
(long long)NFS_FILEID(inode));
out:
return status;
}
int nfs_attribute_timeout(struct inode *inode)
{
struct nfs_inode *nfsi = NFS_I(inode);
if (nfs_have_delegation(inode, FMODE_READ))
return 0;
return !time_in_range_open(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo);
}
/**
* nfs_revalidate_inode - Revalidate the inode attributes
* @server - pointer to nfs_server struct
* @inode - pointer to inode struct
*
* Updates inode attribute information by retrieving the data from the server.
*/
int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
{
if (!(NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATTR)
&& !nfs_attribute_timeout(inode))
return NFS_STALE(inode) ? -ESTALE : 0;
return __nfs_revalidate_inode(server, inode);
}
static int nfs_invalidate_mapping_nolock(struct inode *inode, struct address_space *mapping)
{
struct nfs_inode *nfsi = NFS_I(inode);
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);
nfs_fscache_reset_inode_cookie(inode);
dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n",
inode->i_sb->s_id, (long long)NFS_FILEID(inode));
return 0;
}
static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping)
{
int ret = 0;
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_revalidate_mapping_nolock - Revalidate the pagecache
* @inode - pointer to host inode
* @mapping - pointer to mapping
*/
int nfs_revalidate_mapping_nolock(struct inode *inode, struct address_space *mapping)
{
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_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.
*/
int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
{
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(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_FATTR_PRECHANGE)
&& (fattr->valid & NFS_ATTR_FATTR_CHANGE)
&& 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_FATTR_PRECTIME)
&& (fattr->valid & NFS_ATTR_FATTR_CTIME)
&& timespec_equal(&inode->i_ctime, &fattr->pre_ctime))
memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME)
&& (fattr->valid & NFS_ATTR_FATTR_MTIME)
&& timespec_equal(&inode->i_mtime, &fattr->pre_mtime)) {
memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
if (S_ISDIR(inode->i_mode))
nfsi->cache_validity |= NFS_INO_INVALID_DATA;
}
if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE)
&& (fattr->valid & NFS_ATTR_FATTR_SIZE)
&& 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));
}
/**
* nfs_check_inode_attributes - verify consistency of the inode attribute cache
* @inode - pointer to inode
* @fattr - updated attributes
*
* Verifies the attribute cache. If we have just changed the attributes,
* so that fattr carries weak cache consistency data, then it may
* also update the ctime/mtime/change_attribute.
*/
static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fattr)
{
struct nfs_inode *nfsi = NFS_I(inode);
loff_t cur_size, new_isize;
unsigned long invalid = 0;
/* Has the inode gone and changed behind our back? */
if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
return -EIO;
if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
return -EIO;
if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 &&
nfsi->change_attr != fattr->change_attr)
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
/* Verify a few of the more important attributes */
if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&inode->i_mtime, &fattr->mtime))
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
cur_size = i_size_read(inode);
new_isize = nfs_size_to_loff_t(fattr->size);
if (cur_size != new_isize && nfsi->npages == 0)
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
}
/* Have any file permissions changed? */
if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO))
invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL;
if ((fattr->valid & NFS_ATTR_FATTR_OWNER) && inode->i_uid != fattr->uid)
invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL;
if ((fattr->valid & NFS_ATTR_FATTR_GROUP) && inode->i_gid != fattr->gid)
invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL;
/* Has the link count changed? */
if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink)
invalid |= NFS_INO_INVALID_ATTR;
if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec_equal(&inode->i_atime, &fattr->atime))
invalid |= NFS_INO_INVALID_ATIME;
if (invalid != 0)
nfsi->cache_validity |= invalid;
nfsi->read_cache_jiffies = fattr->time_start;
return 0;
}
static int nfs_ctime_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
{
if (!(fattr->valid & NFS_ATTR_FATTR_CTIME))
return 0;
return timespec_compare(&fattr->ctime, &inode->i_ctime) > 0;
}
static int nfs_size_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
{
if (!(fattr->valid & NFS_ATTR_FATTR_SIZE))
return 0;
return nfs_size_to_loff_t(fattr->size) > i_size_read(inode);
}
static atomic_long_t nfs_attr_generation_counter;
static unsigned long nfs_read_attr_generation_counter(void)
{
return atomic_long_read(&nfs_attr_generation_counter);
}
unsigned long nfs_inc_attr_generation_counter(void)
{
return atomic_long_inc_return(&nfs_attr_generation_counter);
}
void nfs_fattr_init(struct nfs_fattr *fattr)
{
fattr->valid = 0;
fattr->time_start = jiffies;
fattr->gencount = nfs_inc_attr_generation_counter();
}
/**
* nfs_inode_attrs_need_update - check if the inode attributes need updating
* @inode - pointer to inode
* @fattr - attributes
*
* Attempt to divine whether or not an RPC call reply carrying stale
* attributes got scheduled after another call carrying updated ones.
*
* To do so, the function first assumes that a more recent ctime means
* that the attributes in fattr are newer, however it also attempt to
* catch the case where ctime either didn't change, or went backwards
* (if someone reset the clock on the server) by looking at whether
* or not this RPC call was started after the inode was last updated.
* Note also the check for wraparound of 'attr_gencount'
*
* The function returns 'true' if it thinks the attributes in 'fattr' are
* more recent than the ones cached in the inode.
*
*/
static int nfs_inode_attrs_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
{
const struct nfs_inode *nfsi = NFS_I(inode);
return ((long)fattr->gencount - (long)nfsi->attr_gencount) > 0 ||
nfs_ctime_need_update(inode, fattr) ||
nfs_size_need_update(inode, fattr) ||
((long)nfsi->attr_gencount - (long)nfs_read_attr_generation_counter() > 0);
}
static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
{
if (nfs_inode_attrs_need_update(inode, fattr))
return nfs_update_inode(inode, fattr);
return nfs_check_inode_attributes(inode, fattr);
}
/**
* nfs_refresh_inode - try to update the inode attribute cache
* @inode - pointer to inode
* @fattr - updated attributes
*
* Check that an RPC call that returned attributes has not overlapped with
* other recent updates of the inode metadata, then decide whether it is
* safe to do a full update of the inode attributes, or whether just to
* call nfs_check_inode_attributes.
*/
int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
{
int status;
if ((fattr->valid & NFS_ATTR_FATTR) == 0)
return 0;
spin_lock(&inode->i_lock);
status = nfs_refresh_inode_locked(inode, fattr);
spin_unlock(&inode->i_lock);
return status;
}
static int nfs_post_op_update_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
{
struct nfs_inode *nfsi = NFS_I(inode);
nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
if (S_ISDIR(inode->i_mode))
nfsi->cache_validity |= NFS_INO_INVALID_DATA;
if ((fattr->valid & NFS_ATTR_FATTR) == 0)
return 0;
return nfs_refresh_inode_locked(inode, fattr);
}
/**
* nfs_post_op_update_inode - 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.
*
* 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)
{
int status;
spin_lock(&inode->i_lock);
status = nfs_post_op_update_inode_locked(inode, fattr);
spin_unlock(&inode->i_lock);
return status;
}
/**
* 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)
{
int status;
spin_lock(&inode->i_lock);
/* Don't do a WCC update if these attributes are already stale */
if ((fattr->valid & NFS_ATTR_FATTR) == 0 ||
!nfs_inode_attrs_need_update(inode, fattr)) {
fattr->valid &= ~(NFS_ATTR_FATTR_PRECHANGE
| NFS_ATTR_FATTR_PRESIZE
| NFS_ATTR_FATTR_PREMTIME
| NFS_ATTR_FATTR_PRECTIME);
goto out_noforce;
}
if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 &&
(fattr->valid & NFS_ATTR_FATTR_PRECHANGE) == 0) {
fattr->pre_change_attr = NFS_I(inode)->change_attr;
fattr->valid |= NFS_ATTR_FATTR_PRECHANGE;
}
if ((fattr->valid & NFS_ATTR_FATTR_CTIME) != 0 &&
(fattr->valid & NFS_ATTR_FATTR_PRECTIME) == 0) {
memcpy(&fattr->pre_ctime, &inode->i_ctime, sizeof(fattr->pre_ctime));
fattr->valid |= NFS_ATTR_FATTR_PRECTIME;
}
if ((fattr->valid & NFS_ATTR_FATTR_MTIME) != 0 &&
(fattr->valid & NFS_ATTR_FATTR_PREMTIME) == 0) {
memcpy(&fattr->pre_mtime, &inode->i_mtime, sizeof(fattr->pre_mtime));
fattr->valid |= NFS_ATTR_FATTR_PREMTIME;
}
if ((fattr->valid & NFS_ATTR_FATTR_SIZE) != 0 &&
(fattr->valid & NFS_ATTR_FATTR_PRESIZE) == 0) {
fattr->pre_size = i_size_read(inode);
fattr->valid |= NFS_ATTR_FATTR_PRESIZE;
}
out_noforce:
status = nfs_post_op_update_inode_locked(inode, fattr);
spin_unlock(&inode->i_lock);
return status;
}
/*
* Many nfs protocol calls return the new file attributes after
* an operation. Here we update the inode to reflect the state
* of the server's inode.
*
* This is a bit tricky because we have to make sure all dirty pages
* have been sent off to the server before calling invalidate_inode_pages.
* To make sure no other process adds more write requests while we try
* our best to flush them, we make them sleep during the attribute refresh.
*
* A very similar scenario holds for the dir cache.
*/
static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
struct nfs_server *server;
struct nfs_inode *nfsi = NFS_I(inode);
loff_t cur_isize, new_isize;
unsigned long invalid = 0;
unsigned long now = jiffies;
dfprintk(VFS, "NFS: %s(%s/%ld ct=%d info=0x%x)\n",
__func__, inode->i_sb->s_id, inode->i_ino,
atomic_read(&inode->i_count), fattr->valid);
if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
goto out_fileid;
/*
* Make sure the inode's type hasn't changed.
*/
if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
goto out_changed;
server = NFS_SERVER(inode);
/* Update the fsid? */
if (S_ISDIR(inode->i_mode) && (fattr->valid & NFS_ATTR_FATTR_FSID) &&
!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;
if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) || (fattr->valid & (NFS_ATTR_FATTR_MTIME|NFS_ATTR_FATTR_CTIME)))
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_CHANGE) {
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);
nfsi->change_attr = fattr->change_attr;
}
}
if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
/* 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);
memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
}
}
if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
/* If ctime has changed we should definitely clear access+acl caches */
if (!timespec_equal(&inode->i_ctime, &fattr->ctime)) {
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
/* and probably clear data for a directory too as utimes can cause
* havoc with our cache.
*/
if (S_ISDIR(inode->i_mode)) {
invalid |= NFS_INO_INVALID_DATA;
nfs_force_lookup_revalidate(inode);
}
memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
}
}
/* Check if our cached file size is stale */
if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
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, 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;
}
dprintk("NFS: isize change on server for file %s/%ld\n",
inode->i_sb->s_id, inode->i_ino);
}
}
if (fattr->valid & NFS_ATTR_FATTR_ATIME)
memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));
if (fattr->valid & NFS_ATTR_FATTR_MODE) {
if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) {
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
inode->i_mode = fattr->mode;
}
}
if (fattr->valid & NFS_ATTR_FATTR_OWNER) {
if (inode->i_uid != fattr->uid) {
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
inode->i_uid = fattr->uid;
}
}
if (fattr->valid & NFS_ATTR_FATTR_GROUP) {
if (inode->i_gid != fattr->gid) {
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
inode->i_gid = fattr->gid;
}
}
if (fattr->valid & NFS_ATTR_FATTR_NLINK) {
if (inode->i_nlink != fattr->nlink) {
invalid |= NFS_INO_INVALID_ATTR;
if (S_ISDIR(inode->i_mode))
invalid |= NFS_INO_INVALID_DATA;
inode->i_nlink = fattr->nlink;
}
}
if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
/*
* report the blocks in 512byte units
*/
inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
}
if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
inode->i_blocks = fattr->du.nfs2.blocks;
/* 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 = now;
nfsi->attr_gencount = nfs_inc_attr_generation_counter();
} else {
if (!time_in_range_open(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;
}
}
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 (!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.
*/
printk(KERN_DEBUG "%s: inode %ld mode changed, %07o to %07o\n",
__func__, inode->i_ino, inode->i_mode, fattr->mode);
out_err:
/*
* No need to worry about unhashing the dentry, as the
* lookup validation will know that the inode is bad.
* (But we fall through to invalidate the caches.)
*/
nfs_invalidate_inode(inode);
return -ESTALE;
out_fileid:
printk(KERN_ERR "NFS: server %s error: fileid changed\n"
"fsid %s: expected fileid 0x%Lx, got 0x%Lx\n",
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
NFS_SERVER(inode)->nfs_client->cl_hostname, inode->i_sb->s_id,
(long long)nfsi->fileid, (long long)fattr->fileid);
goto out_err;
}
#ifdef CONFIG_NFS_V4
/*
* 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().
*/
void nfs4_clear_inode(struct inode *inode)
{
/* If we are holding a delegation, return it! */
nfs_inode_return_delegation_noreclaim(inode);
/* First call standard NFS clear_inode() code */
nfs_clear_inode(inode);
}
#endif
struct inode *nfs_alloc_inode(struct super_block *sb)
{
struct nfs_inode *nfsi;
nfsi = (struct nfs_inode *)kmem_cache_alloc(nfs_inode_cachep, GFP_KERNEL);
if (!nfsi)
return NULL;
nfsi->flags = 0UL;
nfsi->cache_validity = 0UL;
#ifdef CONFIG_NFS_V3_ACL
nfsi->acl_access = ERR_PTR(-EAGAIN);
nfsi->acl_default = ERR_PTR(-EAGAIN);
#endif
#ifdef CONFIG_NFS_V4
nfsi->nfs4_acl = NULL;
#endif /* CONFIG_NFS_V4 */
return &nfsi->vfs_inode;
}
void nfs_destroy_inode(struct inode *inode)
{
kmem_cache_free(nfs_inode_cachep, NFS_I(inode));
}
git-nfs-build-fixes Fix various problems with nfs4 disabled. And various other things. In file included from fs/nfs/inode.c:50: fs/nfs/internal.h:24: error: static declaration of 'nfs_do_refmount' follows non-static declaration include/linux/nfs_fs.h:320: error: previous declaration of 'nfs_do_refmount' was here fs/nfs/internal.h:65: warning: 'struct nfs4_fs_locations' declared inside parameter list fs/nfs/internal.h:65: warning: its scope is only this definition or declaration, which is probably not what you want fs/nfs/internal.h: In function 'nfs4_path': fs/nfs/internal.h:97: error: 'struct nfs_server' has no member named 'mnt_path' fs/nfs/inode.c: In function 'init_once': fs/nfs/inode.c:1116: error: 'struct nfs_inode' has no member named 'open_states' fs/nfs/inode.c:1116: error: 'struct nfs_inode' has no member named 'delegation' fs/nfs/inode.c:1116: error: 'struct nfs_inode' has no member named 'delegation_state' fs/nfs/inode.c:1116: error: 'struct nfs_inode' has no member named 'rwsem' distcc[26452] ERROR: compile fs/nfs/inode.c on g5/64 failed make[1]: *** [fs/nfs/inode.o] Error 1 make: *** [fs/nfs/inode.o] Error 2 make: *** Waiting for unfinished jobs.... In file included from fs/nfs/nfs3xdr.c:26: fs/nfs/internal.h:24: error: static declaration of 'nfs_do_refmount' follows non-static declaration include/linux/nfs_fs.h:320: error: previous declaration of 'nfs_do_refmount' was here fs/nfs/internal.h:65: warning: 'struct nfs4_fs_locations' declared inside parameter list fs/nfs/internal.h:65: warning: its scope is only this definition or declaration, which is probably not what you want fs/nfs/internal.h: In function 'nfs4_path': fs/nfs/internal.h:97: error: 'struct nfs_server' has no member named 'mnt_path' distcc[26486] ERROR: compile fs/nfs/nfs3xdr.c on g5/64 failed make[1]: *** [fs/nfs/nfs3xdr.o] Error 1 make: *** [fs/nfs/nfs3xdr.o] Error 2 In file included from fs/nfs/nfs3proc.c:24: fs/nfs/internal.h:24: error: static declaration of 'nfs_do_refmount' follows non-static declaration include/linux/nfs_fs.h:320: error: previous declaration of 'nfs_do_refmount' was here fs/nfs/internal.h:65: warning: 'struct nfs4_fs_locations' declared inside parameter list fs/nfs/internal.h:65: warning: its scope is only this definition or declaration, which is probably not what you want fs/nfs/internal.h: In function 'nfs4_path': fs/nfs/internal.h:97: error: 'struct nfs_server' has no member named 'mnt_path' distcc[26469] ERROR: compile fs/nfs/nfs3proc.c on bix/32 failed make[1]: *** [fs/nfs/nfs3proc.o] Error 1 make: *** [fs/nfs/nfs3proc.o] Error 2 **FAILED** Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andreas Gruenbacher <agruen@suse.de> Cc: Andy Adamson <andros@citi.umich.edu> Cc: Chuck Lever <cel@netapp.com> Cc: David Howells <dhowells@redhat.com> Cc: J. Bruce Fields <bfields@fieldses.org> Cc: Manoj Naik <manoj@almaden.ibm.com> Cc: Marc Eshel <eshel@almaden.ibm.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-06-25 17:41:26 +08:00
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(void *foo)
{
struct nfs_inode *nfsi = (struct nfs_inode *) foo;
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->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 __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);
if (nfs_inode_cachep == NULL)
return -ENOMEM;
return 0;
}
static void nfs_destroy_inodecache(void)
{
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);
}
/*
* Initialize NFS
*/
static int __init init_nfs_fs(void)
{
int err;
err = nfs_fscache_register();
if (err < 0)
goto out7;
err = nfsiod_start();
if (err)
goto out6;
err = nfs_fs_proc_init();
if (err)
goto out5;
err = nfs_init_nfspagecache();
if (err)
goto out4;
err = nfs_init_inodecache();
if (err)
goto out3;
err = nfs_init_readpagecache();
if (err)
goto out2;
err = nfs_init_writepagecache();
if (err)
goto out1;
err = nfs_init_directcache();
if (err)
goto out0;
#ifdef CONFIG_PROC_FS
rpc_proc_register(&nfs_rpcstat);
#endif
if ((err = register_nfs_fs()) != 0)
goto out;
return 0;
out:
#ifdef CONFIG_PROC_FS
rpc_proc_unregister("nfs");
#endif
nfs_destroy_directcache();
out0:
nfs_destroy_writepagecache();
out1:
nfs_destroy_readpagecache();
out2:
nfs_destroy_inodecache();
out3:
nfs_destroy_nfspagecache();
out4:
nfs_fs_proc_exit();
out5:
nfsiod_stop();
out6:
nfs_fscache_unregister();
out7:
return err;
}
static void __exit exit_nfs_fs(void)
{
nfs_destroy_directcache();
nfs_destroy_writepagecache();
nfs_destroy_readpagecache();
nfs_destroy_inodecache();
nfs_destroy_nfspagecache();
nfs_fscache_unregister();
#ifdef CONFIG_PROC_FS
rpc_proc_unregister("nfs");
#endif
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)