#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 void nfs_zap_acl_cache(struct inode *);
-
static struct kmem_cache * nfs_inode_cachep;
static inline unsigned long
return nfs_fileid_to_ino_t(fattr->fileid);
}
+/**
+ * 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;
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))
}
}
-static void nfs_zap_acl_cache(struct inode *inode)
+void nfs_zap_acl_cache(struct inode *inode)
{
void (*clear_acl_cache)(struct inode *);
*/
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;
}
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;
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 */
if (S_ISREG(inode->i_mode)) {
filemap_write_and_wait(inode->i_mapping);
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 */
- if (S_ISREG(inode->i_mode))
+ /*
+ * 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);
if (!err) {
generic_fillattr(inode, stat);
- stat->ino = NFS_FILEID(inode);
+ stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
}
return err;
}
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;
}
-void put_nfs_open_context(struct nfs_open_context *ctx)
+static void __put_nfs_open_context(struct nfs_open_context *ctx, int wait)
{
- struct inode *inode = ctx->path.dentry->d_inode;
+ 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)
- nfs4_close_state(&ctx->path, ctx->state, ctx->mode);
+ 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);
- dput(ctx->path.dentry);
- mntput(ctx->path.mnt);
+ 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
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_path.mnt, filp->f_path.dentry, cred);
inode->i_sb->s_id, (long long)NFS_FILEID(inode));
nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE);
- lock_kernel();
if (is_bad_inode(inode))
goto out_nowait;
if (NFS_STALE(inode))
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;
+ /*
+ * 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 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.
- */
-void nfs_end_data_update(struct inode *inode)
-{
- /* Directories: invalidate page cache */
- if (S_ISDIR(inode->i_mode)) {
- spin_lock(&inode->i_lock);
- NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA;
- spin_unlock(&inode->i_lock);
- }
-}
-
static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
struct nfs_inode *nfsi = NFS_I(inode);
if (S_ISDIR(inode->i_mode))
nfsi->cache_validity |= NFS_INO_INVALID_DATA;
}
- if (inode->i_size == fattr->pre_size && nfsi->npages == 0)
- inode->i_size = fattr->size;
+ 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;
+ unsigned long invalid = 0;
/* Has the inode gone and changed behind our back? */
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;
{
struct nfs_inode *nfsi = NFS_I(inode);
- if (fattr->valid & NFS_ATTR_FATTR)
- return nfs_refresh_inode(inode, fattr);
-
spin_lock(&inode->i_lock);
- nfsi->cache_validity |= NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
+ 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 0;
+ return nfs_refresh_inode(inode, fattr);
}
/**
(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 = inode->i_size;
+ 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;
+ 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)
server = NFS_SERVER(inode);
/* Update the fsid? */
- if (S_ISDIR(inode->i_mode)
- && !nfs_fsid_equal(&server->fsid, &fattr->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 = now;
nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ATIME
| NFS_INO_REVAL_PAGECACHE);
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 = now;
+ 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))
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;
- nfsi->cache_change_attribute = now;
+ if (S_ISDIR(inode->i_mode))
+ nfs_force_lookup_revalidate(inode);
}
/* Check if our cached file size is stale */
/* Do we perhaps have any outstanding writes, or has
* the file grown beyond our last write? */
if (nfsi->npages == 0 || new_isize > cur_isize) {
- inode->i_size = new_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",
nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
nfsi->attrtimeo_timestamp = 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;
+ 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 */
* Big trouble! The inode has become a different object.
*/
printk(KERN_DEBUG "%s: inode %ld mode changed, %07o to %07o\n",
- __FUNCTION__, inode->i_ino, inode->i_mode, fattr->mode);
+ __func__, inode->i_ino, inode->i_mode, fattr->mode);
out_err:
/*
* No need to worry about unhashing the dentry, as the
void nfs4_clear_inode(struct inode *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);
}
#endif
}
-static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flags)
+static void init_once(void *foo)
{
struct nfs_inode *nfsi = (struct nfs_inode *) foo;
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);
}
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
*/
{
int err;
+ err = nfsiod_start();
+ if (err)
+ goto out6;
+
err = nfs_fs_proc_init();
if (err)
goto out5;
out4:
nfs_fs_proc_exit();
out5:
+ nfsiod_stop();
+out6:
return err;
}
#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)
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff