/*
FUSE: Filesystem in Userspace
- Copyright (C) 2001-2005 Miklos Szeredi <miklos@szeredi.hu>
+ Copyright (C) 2001-2006 Miklos Szeredi <miklos@szeredi.hu>
This program can be distributed under the terms of the GNU GPL.
See the file COPYING.
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/file.h>
-#include <linux/mount.h>
#include <linux/seq_file.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/parser.h>
#include <linux/statfs.h>
+#include <linux/random.h>
MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
MODULE_DESCRIPTION("Filesystem in Userspace");
MODULE_LICENSE("GPL");
-spinlock_t fuse_lock;
-static kmem_cache_t *fuse_inode_cachep;
-static struct subsystem connections_subsys;
-
-struct fuse_conn_attr {
- struct attribute attr;
- ssize_t (*show)(struct fuse_conn *, char *);
- ssize_t (*store)(struct fuse_conn *, const char *, size_t);
-};
+static struct kmem_cache *fuse_inode_cachep;
+struct list_head fuse_conn_list;
+DEFINE_MUTEX(fuse_mutex);
#define FUSE_SUPER_MAGIC 0x65735546
unsigned group_id_present : 1;
unsigned flags;
unsigned max_read;
+ unsigned blksize;
};
static struct inode *fuse_alloc_inode(struct super_block *sb)
struct inode *inode;
struct fuse_inode *fi;
- inode = kmem_cache_alloc(fuse_inode_cachep, SLAB_KERNEL);
+ inode = kmem_cache_alloc(fuse_inode_cachep, GFP_KERNEL);
if (!inode)
return NULL;
fi = get_fuse_inode(inode);
- fi->i_time = jiffies - 1;
+ fi->i_time = 0;
fi->nodeid = 0;
fi->nlookup = 0;
fi->forget_req = fuse_request_alloc();
}
}
+static int fuse_remount_fs(struct super_block *sb, int *flags, char *data)
+{
+ if (*flags & MS_MANDLOCK)
+ return -EINVAL;
+
+ return 0;
+}
+
void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr)
{
+ struct fuse_conn *fc = get_fuse_conn(inode);
if (S_ISREG(inode->i_mode) && i_size_read(inode) != attr->size)
invalidate_inode_pages(inode->i_mapping);
inode->i_nlink = attr->nlink;
inode->i_uid = attr->uid;
inode->i_gid = attr->gid;
- spin_lock(&fuse_lock);
+ spin_lock(&fc->lock);
i_size_write(inode, attr->size);
- spin_unlock(&fuse_lock);
- inode->i_blksize = PAGE_CACHE_SIZE;
+ spin_unlock(&fc->lock);
inode->i_blocks = attr->blocks;
inode->i_atime.tv_sec = attr->atime;
inode->i_atime.tv_nsec = attr->atimensec;
struct inode *inode;
struct fuse_inode *fi;
struct fuse_conn *fc = get_fuse_conn_super(sb);
- int retried = 0;
retry:
inode = iget5_locked(sb, nodeid, fuse_inode_eq, fuse_inode_set, &nodeid);
fuse_init_inode(inode, attr);
unlock_new_inode(inode);
} else if ((inode->i_mode ^ attr->mode) & S_IFMT) {
- BUG_ON(retried);
/* Inode has changed type, any I/O on the old should fail */
make_bad_inode(inode);
iput(inode);
- retried = 1;
goto retry;
}
fi = get_fuse_inode(inode);
+ spin_lock(&fc->lock);
fi->nlookup ++;
+ spin_unlock(&fc->lock);
fuse_change_attributes(inode, attr);
return inode;
}
-static void fuse_umount_begin(struct super_block *sb)
+static void fuse_umount_begin(struct vfsmount *vfsmnt, int flags)
+{
+ if (flags & MNT_FORCE)
+ fuse_abort_conn(get_fuse_conn_super(vfsmnt->mnt_sb));
+}
+
+static void fuse_send_destroy(struct fuse_conn *fc)
{
- fuse_abort_conn(get_fuse_conn_super(sb));
+ struct fuse_req *req = fc->destroy_req;
+ if (req && fc->conn_init) {
+ fc->destroy_req = NULL;
+ req->in.h.opcode = FUSE_DESTROY;
+ req->force = 1;
+ request_send(fc, req);
+ fuse_put_request(fc, req);
+ }
}
static void fuse_put_super(struct super_block *sb)
{
struct fuse_conn *fc = get_fuse_conn_super(sb);
- down_write(&fc->sbput_sem);
- while (!list_empty(&fc->background))
- fuse_release_background(list_entry(fc->background.next,
- struct fuse_req, bg_entry));
-
- spin_lock(&fuse_lock);
- fc->mounted = 0;
+ fuse_send_destroy(fc);
+ spin_lock(&fc->lock);
fc->connected = 0;
- spin_unlock(&fuse_lock);
- up_write(&fc->sbput_sem);
+ fc->blocked = 0;
+ spin_unlock(&fc->lock);
/* Flush all readers on this fs */
+ kill_fasync(&fc->fasync, SIGIO, POLL_IN);
wake_up_all(&fc->waitq);
- kobject_del(&fc->kobj);
- kobject_put(&fc->kobj);
+ wake_up_all(&fc->blocked_waitq);
+ mutex_lock(&fuse_mutex);
+ list_del(&fc->entry);
+ fuse_ctl_remove_conn(fc);
+ mutex_unlock(&fuse_mutex);
+ fuse_conn_put(fc);
}
static void convert_fuse_statfs(struct kstatfs *stbuf, struct fuse_kstatfs *attr)
/* fsid is left zero */
}
-static int fuse_statfs(struct super_block *sb, struct kstatfs *buf)
+static int fuse_statfs(struct dentry *dentry, struct kstatfs *buf)
{
+ struct super_block *sb = dentry->d_sb;
struct fuse_conn *fc = get_fuse_conn_super(sb);
struct fuse_req *req;
struct fuse_statfs_out outarg;
int err;
- req = fuse_get_request(fc);
- if (!req)
- return -EINTR;
+ req = fuse_get_req(fc);
+ if (IS_ERR(req))
+ return PTR_ERR(req);
memset(&outarg, 0, sizeof(outarg));
req->in.numargs = 0;
req->in.h.opcode = FUSE_STATFS;
+ req->in.h.nodeid = get_node_id(dentry->d_inode);
req->out.numargs = 1;
req->out.args[0].size =
fc->minor < 4 ? FUSE_COMPAT_STATFS_SIZE : sizeof(outarg);
OPT_DEFAULT_PERMISSIONS,
OPT_ALLOW_OTHER,
OPT_MAX_READ,
+ OPT_BLKSIZE,
OPT_ERR
};
{OPT_DEFAULT_PERMISSIONS, "default_permissions"},
{OPT_ALLOW_OTHER, "allow_other"},
{OPT_MAX_READ, "max_read=%u"},
+ {OPT_BLKSIZE, "blksize=%u"},
{OPT_ERR, NULL}
};
-static int parse_fuse_opt(char *opt, struct fuse_mount_data *d)
+static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
{
char *p;
memset(d, 0, sizeof(struct fuse_mount_data));
d->max_read = ~0;
+ d->blksize = 512;
while ((p = strsep(&opt, ",")) != NULL) {
int token;
d->max_read = value;
break;
+ case OPT_BLKSIZE:
+ if (!is_bdev || match_int(&args[0], &value))
+ return 0;
+ d->blksize = value;
+ break;
+
default:
return 0;
}
return 0;
}
-static void fuse_conn_release(struct kobject *kobj)
-{
- struct fuse_conn *fc = get_fuse_conn_kobj(kobj);
-
- while (!list_empty(&fc->unused_list)) {
- struct fuse_req *req;
- req = list_entry(fc->unused_list.next, struct fuse_req, list);
- list_del(&req->list);
- fuse_request_free(req);
- }
- kfree(fc);
-}
-
static struct fuse_conn *new_conn(void)
{
struct fuse_conn *fc;
fc = kzalloc(sizeof(*fc), GFP_KERNEL);
if (fc) {
- int i;
+ spin_lock_init(&fc->lock);
+ mutex_init(&fc->inst_mutex);
+ atomic_set(&fc->count, 1);
init_waitqueue_head(&fc->waitq);
+ init_waitqueue_head(&fc->blocked_waitq);
INIT_LIST_HEAD(&fc->pending);
INIT_LIST_HEAD(&fc->processing);
INIT_LIST_HEAD(&fc->io);
- INIT_LIST_HEAD(&fc->unused_list);
- INIT_LIST_HEAD(&fc->background);
- sema_init(&fc->outstanding_sem, 1); /* One for INIT */
- init_rwsem(&fc->sbput_sem);
- kobj_set_kset_s(fc, connections_subsys);
- kobject_init(&fc->kobj);
+ INIT_LIST_HEAD(&fc->interrupts);
atomic_set(&fc->num_waiting, 0);
- for (i = 0; i < FUSE_MAX_OUTSTANDING; i++) {
- struct fuse_req *req = fuse_request_alloc();
- if (!req) {
- kobject_put(&fc->kobj);
- return NULL;
- }
- list_add(&req->list, &fc->unused_list);
- }
fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
fc->bdi.unplug_io_fn = default_unplug_io_fn;
fc->reqctr = 0;
+ fc->blocked = 1;
+ get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
}
return fc;
}
-static struct fuse_conn *get_conn(struct file *file, struct super_block *sb)
+void fuse_conn_put(struct fuse_conn *fc)
{
- struct fuse_conn *fc;
- int err;
-
- err = -EINVAL;
- if (file->f_op != &fuse_dev_operations)
- goto out_err;
-
- err = -ENOMEM;
- fc = new_conn();
- if (!fc)
- goto out_err;
-
- spin_lock(&fuse_lock);
- err = -EINVAL;
- if (file->private_data)
- goto out_unlock;
+ if (atomic_dec_and_test(&fc->count)) {
+ if (fc->destroy_req)
+ fuse_request_free(fc->destroy_req);
+ mutex_destroy(&fc->inst_mutex);
+ kfree(fc);
+ }
+}
- kobject_get(&fc->kobj);
- file->private_data = fc;
- spin_unlock(&fuse_lock);
+struct fuse_conn *fuse_conn_get(struct fuse_conn *fc)
+{
+ atomic_inc(&fc->count);
return fc;
-
- out_unlock:
- spin_unlock(&fuse_lock);
- kobject_put(&fc->kobj);
- out_err:
- return ERR_PTR(err);
}
static struct inode *get_root_inode(struct super_block *sb, unsigned mode)
.destroy_inode = fuse_destroy_inode,
.read_inode = fuse_read_inode,
.clear_inode = fuse_clear_inode,
+ .remount_fs = fuse_remount_fs,
.put_super = fuse_put_super,
.umount_begin = fuse_umount_begin,
.statfs = fuse_statfs,
static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
{
- int i;
struct fuse_init_out *arg = &req->misc.init_out;
if (req->out.h.error || arg->major != FUSE_KERNEL_VERSION)
ra_pages = arg->max_readahead / PAGE_CACHE_SIZE;
if (arg->flags & FUSE_ASYNC_READ)
fc->async_read = 1;
- } else
+ if (!(arg->flags & FUSE_POSIX_LOCKS))
+ fc->no_lock = 1;
+ } else {
ra_pages = fc->max_read / PAGE_CACHE_SIZE;
+ fc->no_lock = 1;
+ }
fc->bdi.ra_pages = min(fc->bdi.ra_pages, ra_pages);
fc->minor = arg->minor;
fc->max_write = arg->minor < 5 ? 4096 : arg->max_write;
+ fc->conn_init = 1;
}
-
- /* After INIT reply is received other requests can go
- out. So do (FUSE_MAX_OUTSTANDING - 1) number of
- up()s on outstanding_sem. The last up() is done in
- fuse_putback_request() */
- for (i = 1; i < FUSE_MAX_OUTSTANDING; i++)
- up(&fc->outstanding_sem);
-
fuse_put_request(fc, req);
+ fc->blocked = 0;
+ wake_up_all(&fc->blocked_waitq);
}
-static void fuse_send_init(struct fuse_conn *fc)
+static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
{
- /* This is called from fuse_read_super() so there's guaranteed
- to be exactly one request available */
- struct fuse_req *req = fuse_get_request(fc);
struct fuse_init_in *arg = &req->misc.init_in;
arg->major = FUSE_KERNEL_VERSION;
arg->minor = FUSE_KERNEL_MINOR_VERSION;
arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE;
- arg->flags |= FUSE_ASYNC_READ;
+ arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS;
req->in.h.opcode = FUSE_INIT;
req->in.numargs = 1;
req->in.args[0].size = sizeof(*arg);
request_send_background(fc, req);
}
-static unsigned long long conn_id(void)
+static u64 conn_id(void)
{
- static unsigned long long ctr = 1;
- unsigned long long val;
- spin_lock(&fuse_lock);
- val = ctr++;
- spin_unlock(&fuse_lock);
- return val;
+ static u64 ctr = 1;
+ return ctr++;
}
static int fuse_fill_super(struct super_block *sb, void *data, int silent)
struct fuse_mount_data d;
struct file *file;
struct dentry *root_dentry;
+ struct fuse_req *init_req;
int err;
+ int is_bdev = sb->s_bdev != NULL;
+
+ if (sb->s_flags & MS_MANDLOCK)
+ return -EINVAL;
- if (!parse_fuse_opt((char *) data, &d))
+ if (!parse_fuse_opt((char *) data, &d, is_bdev))
return -EINVAL;
- sb->s_blocksize = PAGE_CACHE_SIZE;
- sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+ if (is_bdev) {
+#ifdef CONFIG_BLOCK
+ if (!sb_set_blocksize(sb, d.blksize))
+ return -EINVAL;
+#endif
+ } else {
+ sb->s_blocksize = PAGE_CACHE_SIZE;
+ sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+ }
sb->s_magic = FUSE_SUPER_MAGIC;
sb->s_op = &fuse_super_operations;
sb->s_maxbytes = MAX_LFS_FILESIZE;
if (!file)
return -EINVAL;
- fc = get_conn(file, sb);
- fput(file);
- if (IS_ERR(fc))
- return PTR_ERR(fc);
+ if (file->f_op != &fuse_dev_operations)
+ return -EINVAL;
+
+ fc = new_conn();
+ if (!fc)
+ return -ENOMEM;
fc->flags = d.flags;
fc->user_id = d.user_id;
goto err;
}
- err = kobject_set_name(&fc->kobj, "%llu", conn_id());
- if (err)
+ init_req = fuse_request_alloc();
+ if (!init_req)
goto err_put_root;
- err = kobject_add(&fc->kobj);
+ if (is_bdev) {
+ fc->destroy_req = fuse_request_alloc();
+ if (!fc->destroy_req)
+ goto err_put_root;
+ }
+
+ mutex_lock(&fuse_mutex);
+ err = -EINVAL;
+ if (file->private_data)
+ goto err_unlock;
+
+ fc->id = conn_id();
+ err = fuse_ctl_add_conn(fc);
if (err)
- goto err_put_root;
+ goto err_unlock;
+ list_add_tail(&fc->entry, &fuse_conn_list);
sb->s_root = root_dentry;
- spin_lock(&fuse_lock);
- fc->mounted = 1;
fc->connected = 1;
- spin_unlock(&fuse_lock);
+ file->private_data = fuse_conn_get(fc);
+ mutex_unlock(&fuse_mutex);
+ /*
+ * atomic_dec_and_test() in fput() provides the necessary
+ * memory barrier for file->private_data to be visible on all
+ * CPUs after this
+ */
+ fput(file);
- fuse_send_init(fc);
+ fuse_send_init(fc, init_req);
return 0;
+ err_unlock:
+ mutex_unlock(&fuse_mutex);
+ fuse_request_free(init_req);
err_put_root:
dput(root_dentry);
err:
- kobject_put(&fc->kobj);
+ fput(file);
+ fuse_conn_put(fc);
return err;
}
-static struct super_block *fuse_get_sb(struct file_system_type *fs_type,
- int flags, const char *dev_name,
- void *raw_data)
+static int fuse_get_sb(struct file_system_type *fs_type,
+ int flags, const char *dev_name,
+ void *raw_data, struct vfsmount *mnt)
{
- return get_sb_nodev(fs_type, flags, raw_data, fuse_fill_super);
+ return get_sb_nodev(fs_type, flags, raw_data, fuse_fill_super, mnt);
}
static struct file_system_type fuse_fs_type = {
.kill_sb = kill_anon_super,
};
-static ssize_t fuse_conn_waiting_show(struct fuse_conn *fc, char *page)
+#ifdef CONFIG_BLOCK
+static int fuse_get_sb_blk(struct file_system_type *fs_type,
+ int flags, const char *dev_name,
+ void *raw_data, struct vfsmount *mnt)
{
- return sprintf(page, "%i\n", atomic_read(&fc->num_waiting));
+ return get_sb_bdev(fs_type, flags, dev_name, raw_data, fuse_fill_super,
+ mnt);
}
-static ssize_t fuse_conn_abort_store(struct fuse_conn *fc, const char *page,
- size_t count)
-{
- fuse_abort_conn(fc);
- return count;
-}
-
-static struct fuse_conn_attr fuse_conn_waiting =
- __ATTR(waiting, 0400, fuse_conn_waiting_show, NULL);
-static struct fuse_conn_attr fuse_conn_abort =
- __ATTR(abort, 0600, NULL, fuse_conn_abort_store);
-
-static struct attribute *fuse_conn_attrs[] = {
- &fuse_conn_waiting.attr,
- &fuse_conn_abort.attr,
- NULL,
+static struct file_system_type fuseblk_fs_type = {
+ .owner = THIS_MODULE,
+ .name = "fuseblk",
+ .get_sb = fuse_get_sb_blk,
+ .kill_sb = kill_block_super,
+ .fs_flags = FS_REQUIRES_DEV,
};
-static ssize_t fuse_conn_attr_show(struct kobject *kobj,
- struct attribute *attr,
- char *page)
+static inline int register_fuseblk(void)
{
- struct fuse_conn_attr *fca =
- container_of(attr, struct fuse_conn_attr, attr);
-
- if (fca->show)
- return fca->show(get_fuse_conn_kobj(kobj), page);
- else
- return -EACCES;
+ return register_filesystem(&fuseblk_fs_type);
}
-static ssize_t fuse_conn_attr_store(struct kobject *kobj,
- struct attribute *attr,
- const char *page, size_t count)
+static inline void unregister_fuseblk(void)
{
- struct fuse_conn_attr *fca =
- container_of(attr, struct fuse_conn_attr, attr);
-
- if (fca->store)
- return fca->store(get_fuse_conn_kobj(kobj), page, count);
- else
- return -EACCES;
+ unregister_filesystem(&fuseblk_fs_type);
+}
+#else
+static inline int register_fuseblk(void)
+{
+ return 0;
}
-static struct sysfs_ops fuse_conn_sysfs_ops = {
- .show = &fuse_conn_attr_show,
- .store = &fuse_conn_attr_store,
-};
-
-static struct kobj_type ktype_fuse_conn = {
- .release = fuse_conn_release,
- .sysfs_ops = &fuse_conn_sysfs_ops,
- .default_attrs = fuse_conn_attrs,
-};
+static inline void unregister_fuseblk(void)
+{
+}
+#endif
static decl_subsys(fuse, NULL, NULL);
-static decl_subsys(connections, &ktype_fuse_conn, NULL);
+static decl_subsys(connections, NULL, NULL);
-static void fuse_inode_init_once(void *foo, kmem_cache_t *cachep,
+static void fuse_inode_init_once(void *foo, struct kmem_cache *cachep,
unsigned long flags)
{
struct inode * inode = foo;
err = register_filesystem(&fuse_fs_type);
if (err)
- printk("fuse: failed to register filesystem\n");
- else {
- fuse_inode_cachep = kmem_cache_create("fuse_inode",
- sizeof(struct fuse_inode),
- 0, SLAB_HWCACHE_ALIGN,
- fuse_inode_init_once, NULL);
- if (!fuse_inode_cachep) {
- unregister_filesystem(&fuse_fs_type);
- err = -ENOMEM;
- }
- }
+ goto out;
+
+ err = register_fuseblk();
+ if (err)
+ goto out_unreg;
+ fuse_inode_cachep = kmem_cache_create("fuse_inode",
+ sizeof(struct fuse_inode),
+ 0, SLAB_HWCACHE_ALIGN,
+ fuse_inode_init_once, NULL);
+ err = -ENOMEM;
+ if (!fuse_inode_cachep)
+ goto out_unreg2;
+
+ return 0;
+
+ out_unreg2:
+ unregister_fuseblk();
+ out_unreg:
+ unregister_filesystem(&fuse_fs_type);
+ out:
return err;
}
static void fuse_fs_cleanup(void)
{
unregister_filesystem(&fuse_fs_type);
+ unregister_fuseblk();
kmem_cache_destroy(fuse_inode_cachep);
}
printk("fuse init (API version %i.%i)\n",
FUSE_KERNEL_VERSION, FUSE_KERNEL_MINOR_VERSION);
- spin_lock_init(&fuse_lock);
+ INIT_LIST_HEAD(&fuse_conn_list);
res = fuse_fs_init();
if (res)
goto err;
if (res)
goto err_dev_cleanup;
+ res = fuse_ctl_init();
+ if (res)
+ goto err_sysfs_cleanup;
+
return 0;
+ err_sysfs_cleanup:
+ fuse_sysfs_cleanup();
err_dev_cleanup:
fuse_dev_cleanup();
err_fs_cleanup:
{
printk(KERN_DEBUG "fuse exit\n");
+ fuse_ctl_cleanup();
fuse_sysfs_cleanup();
fuse_fs_cleanup();
fuse_dev_cleanup();