*
* nfs inode and superblock handling functions
*
- * Modularised by Alan Cox <Alan.Cox@linux.org>, while hacking some
+ * 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.
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
}
}
-static void nfs_zap_acl_cache(struct inode *inode)
+void nfs_zap_acl_cache(struct inode *inode)
{
void (*clear_acl_cache)(struct inode *);
init_special_inode(inode, inode->i_mode, fattr->rdev);
nfsi->read_cache_jiffies = fattr->time_start;
- nfsi->last_updated = now;
- nfsi->cache_change_attribute = now;
+ nfsi->attr_gencount = fattr->gencount;
inode->i_atime = fattr->atime;
inode->i_mtime = fattr->mtime;
inode->i_ctime = fattr->ctime;
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)
/* 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();
/* 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);
- 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
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_uid = attr->ia_uid;
if ((attr->ia_valid & ATTR_GID) != 0)
inode->i_gid = attr->ia_gid;
- spin_lock(&inode->i_lock);
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);
- inode->i_size = attr->ia_size;
- vmtruncate(inode, attr->ia_size);
+ nfs_vmtruncate(inode, attr->ia_size);
}
}
-static int nfs_wait_schedule(void *word)
-{
- if (signal_pending(current))
- return -ERESTARTSYS;
- schedule();
- return 0;
-}
-
-/*
- * Wait for the inode to get unlocked.
- */
-static int nfs_wait_on_inode(struct inode *inode)
-{
- struct nfs_inode *nfsi = NFS_I(inode);
- int error;
-
- error = wait_on_bit_lock(&nfsi->flags, NFS_INO_REVALIDATING,
- nfs_wait_schedule, TASK_KILLABLE);
-
- return error;
-}
-
-static void nfs_wake_up_inode(struct inode *inode)
-{
- struct nfs_inode *nfsi = NFS_I(inode);
-
- clear_bit(NFS_INO_REVALIDATING, &nfsi->flags);
- smp_mb__after_clear_bit();
- wake_up_bit(&nfsi->flags, NFS_INO_REVALIDATING);
-}
-
int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
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);
}
if (ctx->cred != NULL)
put_rpccred(ctx->cred);
- dput(ctx->path.dentry);
- mntput(ctx->path.mnt);
+ path_put(&ctx->path);
kfree(ctx);
}
/*
* 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, int mode)
+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;
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);
dfprintk(PAGECACHE, "NFS: revalidating (%s/%Ld)\n",
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;
+ goto out;
if (NFS_STALE(inode))
- goto out_nowait;
-
- status = nfs_wait_on_inode(inode);
- if (status < 0)
goto out;
- status = -ESTALE;
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",
goto out;
}
- spin_lock(&inode->i_lock);
- status = nfs_update_inode(inode, &fattr);
+ status = nfs_refresh_inode(inode, &fattr);
if (status) {
- spin_unlock(&inode->i_lock);
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;
}
- spin_unlock(&inode->i_lock);
if (nfsi->cache_validity & NFS_INO_INVALID_ACL)
nfs_zap_acl_cache(inode);
(long long)NFS_FILEID(inode));
out:
- nfs_wake_up_inode(inode);
-
- out_nowait:
- unlock_kernel();
return status;
}
if (nfs_have_delegation(inode, FMODE_READ))
return 0;
- return !time_in_range(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo);
+ return !time_in_range_open(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo);
}
/**
if (S_ISDIR(inode->i_mode))
nfsi->cache_validity |= NFS_INO_INVALID_DATA;
}
- if (inode->i_size == nfs_size_to_loff_t(fattr->pre_size) &&
+ if (i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size) &&
nfsi->npages == 0)
- inode->i_size = nfs_size_to_loff_t(fattr->size);
+ i_size_write(inode, nfs_size_to_loff_t(fattr->size));
}
}
return -EIO;
}
- /* 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)
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
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;
}
+static int nfs_ctime_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
+{
+ return timespec_compare(&fattr->ctime, &inode->i_ctime) > 0;
+}
+
+static int nfs_size_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
+{
+ 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
*/
int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
{
- struct nfs_inode *nfsi = NFS_I(inode);
int status;
if ((fattr->valid & NFS_ATTR_FATTR) == 0)
return 0;
spin_lock(&inode->i_lock);
- if (time_after(fattr->time_start, nfsi->last_updated))
- status = nfs_update_inode(inode, fattr);
- else
- status = nfs_check_inode_attributes(inode, fattr);
-
+ 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
*/
int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
- struct nfs_inode *nfsi = NFS_I(inode);
+ int status;
spin_lock(&inode->i_lock);
- nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
- if (S_ISDIR(inode->i_mode))
- nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+ status = nfs_post_op_update_inode_locked(inode, fattr);
spin_unlock(&inode->i_lock);
- return nfs_refresh_inode(inode, fattr);
+ return status;
}
/**
*/
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_WCC_V4|NFS_ATTR_WCC);
+ goto out_noforce;
+ }
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) == 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);
+out_noforce:
+ status = nfs_post_op_update_inode_locked(inode, fattr);
+ spin_unlock(&inode->i_lock);
+ return status;
}
/*
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)
}
/* 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;
+ invalid |= NFS_INO_INVALID_ATTR|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);
/* 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",
inode->i_gid != fattr->gid)
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
+ if (inode->i_nlink != fattr->nlink)
+ invalid |= NFS_INO_INVALID_ATTR;
+
inode->i_mode = fattr->mode;
inode->i_nlink = fattr->nlink;
inode->i_uid = fattr->uid;
nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
nfsi->attrtimeo_timestamp = now;
- nfsi->last_updated = now;
+ nfsi->attr_gencount = nfs_inc_attr_generation_counter();
} else {
- if (!time_in_range(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) {
+ 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;
}
- /*
- * 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
#endif
}
-static void init_once(struct kmem_cache * cachep, void *foo)
+static void init_once(void *foo)
{
struct nfs_inode *nfsi = (struct nfs_inode *) foo;
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 */