diff options
Diffstat (limited to 'fs/fuse')
| -rw-r--r-- | fs/fuse/Makefile | 7 | ||||
| -rw-r--r-- | fs/fuse/dev.c | 877 | ||||
| -rw-r--r-- | fs/fuse/dir.c | 982 | ||||
| -rw-r--r-- | fs/fuse/file.c | 555 | ||||
| -rw-r--r-- | fs/fuse/fuse_i.h | 451 | ||||
| -rw-r--r-- | fs/fuse/inode.c | 591 |
6 files changed, 3463 insertions, 0 deletions
diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile new file mode 100644 index 00000000000..c3e1f760cac --- /dev/null +++ b/fs/fuse/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the FUSE filesystem. +# + +obj-$(CONFIG_FUSE_FS) += fuse.o + +fuse-objs := dev.o dir.o file.o inode.o diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c new file mode 100644 index 00000000000..d4c869c6d01 --- /dev/null +++ b/fs/fuse/dev.c @@ -0,0 +1,877 @@ +/* + FUSE: Filesystem in Userspace + Copyright (C) 2001-2005 Miklos Szeredi <miklos@szeredi.hu> + + This program can be distributed under the terms of the GNU GPL. + See the file COPYING. +*/ + +#include "fuse_i.h" + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/poll.h> +#include <linux/uio.h> +#include <linux/miscdevice.h> +#include <linux/pagemap.h> +#include <linux/file.h> +#include <linux/slab.h> + +MODULE_ALIAS_MISCDEV(FUSE_MINOR); + +static kmem_cache_t *fuse_req_cachep; + +static inline struct fuse_conn *fuse_get_conn(struct file *file) +{ + struct fuse_conn *fc; + spin_lock(&fuse_lock); + fc = file->private_data; + if (fc && !fc->mounted) + fc = NULL; + spin_unlock(&fuse_lock); + return fc; +} + +static inline void fuse_request_init(struct fuse_req *req) +{ + memset(req, 0, sizeof(*req)); + INIT_LIST_HEAD(&req->list); + init_waitqueue_head(&req->waitq); + atomic_set(&req->count, 1); +} + +struct fuse_req *fuse_request_alloc(void) +{ + struct fuse_req *req = kmem_cache_alloc(fuse_req_cachep, SLAB_KERNEL); + if (req) + fuse_request_init(req); + return req; +} + +void fuse_request_free(struct fuse_req *req) +{ + kmem_cache_free(fuse_req_cachep, req); +} + +static inline void block_sigs(sigset_t *oldset) +{ + sigset_t mask; + + siginitsetinv(&mask, sigmask(SIGKILL)); + sigprocmask(SIG_BLOCK, &mask, oldset); +} + +static inline void restore_sigs(sigset_t *oldset) +{ + sigprocmask(SIG_SETMASK, oldset, NULL); +} + +void fuse_reset_request(struct fuse_req *req) +{ + int preallocated = req->preallocated; + BUG_ON(atomic_read(&req->count) != 1); + fuse_request_init(req); + req->preallocated = preallocated; +} + +static void __fuse_get_request(struct fuse_req *req) +{ + atomic_inc(&req->count); +} + +/* Must be called with > 1 refcount */ +static void __fuse_put_request(struct fuse_req *req) +{ + BUG_ON(atomic_read(&req->count) < 2); + atomic_dec(&req->count); +} + +static struct fuse_req *do_get_request(struct fuse_conn *fc) +{ + struct fuse_req *req; + + spin_lock(&fuse_lock); + BUG_ON(list_empty(&fc->unused_list)); + req = list_entry(fc->unused_list.next, struct fuse_req, list); + list_del_init(&req->list); + spin_unlock(&fuse_lock); + fuse_request_init(req); + req->preallocated = 1; + req->in.h.uid = current->fsuid; + req->in.h.gid = current->fsgid; + req->in.h.pid = current->pid; + return req; +} + +/* This can return NULL, but only in case it's interrupted by a SIGKILL */ +struct fuse_req *fuse_get_request(struct fuse_conn *fc) +{ + int intr; + sigset_t oldset; + + block_sigs(&oldset); + intr = down_interruptible(&fc->outstanding_sem); + restore_sigs(&oldset); + return intr ? NULL : do_get_request(fc); +} + +static void fuse_putback_request(struct fuse_conn *fc, struct fuse_req *req) +{ + spin_lock(&fuse_lock); + if (req->preallocated) + list_add(&req->list, &fc->unused_list); + else + fuse_request_free(req); + + /* If we are in debt decrease that first */ + if (fc->outstanding_debt) + fc->outstanding_debt--; + else + up(&fc->outstanding_sem); + spin_unlock(&fuse_lock); +} + +void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req) +{ + if (atomic_dec_and_test(&req->count)) + fuse_putback_request(fc, req); +} + +void fuse_release_background(struct fuse_req *req) +{ + iput(req->inode); + iput(req->inode2); + if (req->file) + fput(req->file); + spin_lock(&fuse_lock); + list_del(&req->bg_entry); + spin_unlock(&fuse_lock); +} + +/* + * This function is called when a request is finished. Either a reply + * has arrived or it was interrupted (and not yet sent) or some error + * occured during communication with userspace, or the device file was + * closed. It decreases the referece count for the request. In case + * of a background request the referece to the stored objects are + * released. The requester thread is woken up (if still waiting), and + * finally the request is either freed or put on the unused_list + * + * Called with fuse_lock, unlocks it + */ +static void request_end(struct fuse_conn *fc, struct fuse_req *req) +{ + int putback; + req->finished = 1; + putback = atomic_dec_and_test(&req->count); + spin_unlock(&fuse_lock); + if (req->background) { + down_read(&fc->sbput_sem); + if (fc->mounted) + fuse_release_background(req); + up_read(&fc->sbput_sem); + } + wake_up(&req->waitq); + if (req->in.h.opcode == FUSE_INIT) { + int i; + + if (req->misc.init_in_out.major != FUSE_KERNEL_VERSION) + fc->conn_error = 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); + } + if (putback) + fuse_putback_request(fc, req); +} + +/* + * Unfortunately request interruption not just solves the deadlock + * problem, it causes problems too. These stem from the fact, that an + * interrupted request is continued to be processed in userspace, + * while all the locks and object references (inode and file) held + * during the operation are released. + * + * To release the locks is exactly why there's a need to interrupt the + * request, so there's not a lot that can be done about this, except + * introduce additional locking in userspace. + * + * More important is to keep inode and file references until userspace + * has replied, otherwise FORGET and RELEASE could be sent while the + * inode/file is still used by the filesystem. + * + * For this reason the concept of "background" request is introduced. + * An interrupted request is backgrounded if it has been already sent + * to userspace. Backgrounding involves getting an extra reference to + * inode(s) or file used in the request, and adding the request to + * fc->background list. When a reply is received for a background + * request, the object references are released, and the request is + * removed from the list. If the filesystem is unmounted while there + * are still background requests, the list is walked and references + * are released as if a reply was received. + * + * There's one more use for a background request. The RELEASE message is + * always sent as background, since it doesn't return an error or + * data. + */ +static void background_request(struct fuse_conn *fc, struct fuse_req *req) +{ + req->background = 1; + list_add(&req->bg_entry, &fc->background); + if (req->inode) + req->inode = igrab(req->inode); + if (req->inode2) + req->inode2 = igrab(req->inode2); + if (req->file) + get_file(req->file); +} + +/* Called with fuse_lock held. Releases, and then reacquires it. */ +static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req) +{ + sigset_t oldset; + + spin_unlock(&fuse_lock); + block_sigs(&oldset); + wait_event_interruptible(req->waitq, req->finished); + restore_sigs(&oldset); + spin_lock(&fuse_lock); + if (req->finished) + return; + + req->out.h.error = -EINTR; + req->interrupted = 1; + if (req->locked) { + /* This is uninterruptible sleep, because data is + being copied to/from the buffers of req. During + locked state, there mustn't be any filesystem + operation (e.g. page fault), since that could lead + to deadlock */ + spin_unlock(&fuse_lock); + wait_event(req->waitq, !req->locked); + spin_lock(&fuse_lock); + } + if (!req->sent && !list_empty(&req->list)) { + list_del(&req->list); + __fuse_put_request(req); + } else if (!req->finished && req->sent) + background_request(fc, req); +} + +static unsigned len_args(unsigned numargs, struct fuse_arg *args) +{ + unsigned nbytes = 0; + unsigned i; + + for (i = 0; i < numargs; i++) + nbytes += args[i].size; + + return nbytes; +} + +static void queue_request(struct fuse_conn *fc, struct fuse_req *req) +{ + fc->reqctr++; + /* zero is special */ + if (fc->reqctr == 0) + fc->reqctr = 1; + req->in.h.unique = fc->reqctr; + req->in.h.len = sizeof(struct fuse_in_header) + + len_args(req->in.numargs, (struct fuse_arg *) req->in.args); + if (!req->preallocated) { + /* If request is not preallocated (either FORGET or + RELEASE), then still decrease outstanding_sem, so + user can't open infinite number of files while not + processing the RELEASE requests. However for + efficiency do it without blocking, so if down() + would block, just increase the debt instead */ + if (down_trylock(&fc->outstanding_sem)) + fc->outstanding_debt++; + } + list_add_tail(&req->list, &fc->pending); + wake_up(&fc->waitq); +} + +/* + * This can only be interrupted by a SIGKILL + */ +void request_send(struct fuse_conn *fc, struct fuse_req *req) +{ + req->isreply = 1; + spin_lock(&fuse_lock); + if (!fc->connected) + req->out.h.error = -ENOTCONN; + else if (fc->conn_error) + req->out.h.error = -ECONNREFUSED; + else { + queue_request(fc, req); + /* acquire extra reference, since request is still needed + after request_end() */ + __fuse_get_request(req); + + request_wait_answer(fc, req); + } + spin_unlock(&fuse_lock); +} + +static void request_send_nowait(struct fuse_conn *fc, struct fuse_req *req) +{ + spin_lock(&fuse_lock); + if (fc->connected) { + queue_request(fc, req); + spin_unlock(&fuse_lock); + } else { + req->out.h.error = -ENOTCONN; + request_end(fc, req); + } +} + +void request_send_noreply(struct fuse_conn *fc, struct fuse_req *req) +{ + req->isreply = 0; + request_send_nowait(fc, req); +} + +void request_send_background(struct fuse_conn *fc, struct fuse_req *req) +{ + req->isreply = 1; + spin_lock(&fuse_lock); + background_request(fc, req); + spin_unlock(&fuse_lock); + request_send_nowait(fc, req); +} + +void fuse_send_init(struct fuse_conn *fc) +{ + /* This is called from fuse_read_super() so there's guaranteed + to be a request available */ + struct fuse_req *req = do_get_request(fc); + struct fuse_init_in_out *arg = &req->misc.init_in_out; + arg->major = FUSE_KERNEL_VERSION; + arg->minor = FUSE_KERNEL_MINOR_VERSION; + req->in.h.opcode = FUSE_INIT; + req->in.numargs = 1; + req->in.args[0].size = sizeof(*arg); + req->in.args[0].value = arg; + req->out.numargs = 1; + req->out.args[0].size = sizeof(*arg); + req->out.args[0].value = arg; + request_send_background(fc, req); +} + +/* + * Lock the request. Up to the next unlock_request() there mustn't be + * anything that could cause a page-fault. If the request was already + * interrupted bail out. + */ +static inline int lock_request(struct fuse_req *req) +{ + int err = 0; + if (req) { + spin_lock(&fuse_lock); + if (req->interrupted) + err = -ENOENT; + else + req->locked = 1; + spin_unlock(&fuse_lock); + } + return err; +} + +/* + * Unlock request. If it was interrupted during being locked, the + * requester thread is currently waiting for it to be unlocked, so + * wake it up. + */ +static inline void unlock_request(struct fuse_req *req) +{ + if (req) { + spin_lock(&fuse_lock); + req->locked = 0; + if (req->interrupted) + wake_up(&req->waitq); + spin_unlock(&fuse_lock); + } +} + +struct fuse_copy_state { + int write; + struct fuse_req *req; + const struct iovec *iov; + unsigned long nr_segs; + unsigned long seglen; + unsigned long addr; + struct page *pg; + void *mapaddr; + void *buf; + unsigned len; +}; + +static void fuse_copy_init(struct fuse_copy_state *cs, int write, + struct fuse_req *req, const struct iovec *iov, + unsigned long nr_segs) +{ + memset(cs, 0, sizeof(*cs)); + cs->write = write; + cs->req = req; + cs->iov = iov; + cs->nr_segs = nr_segs; +} + +/* Unmap and put previous page of userspace buffer */ +static inline void fuse_copy_finish(struct fuse_copy_state *cs) +{ + if (cs->mapaddr) { + kunmap_atomic(cs->mapaddr, KM_USER0); + if (cs->write) { + flush_dcache_page(cs->pg); + set_page_dirty_lock(cs->pg); + } + put_page(cs->pg); + cs->mapaddr = NULL; + } +} + +/* + * Get another pagefull of userspace buffer, and map it to kernel + * address space, and lock request + */ +static int fuse_copy_fill(struct fuse_copy_state *cs) +{ + unsigned long offset; + int err; + + unlock_request(cs->req); + fuse_copy_finish(cs); + if (!cs->seglen) { + BUG_ON(!cs->nr_segs); + cs->seglen = cs->iov[0].iov_len; + cs->addr = (unsigned long) cs->iov[0].iov_base; + cs->iov ++; + cs->nr_segs --; + } + down_read(¤t->mm->mmap_sem); + err = get_user_pages(current, current->mm, cs->addr, 1, cs->write, 0, + &cs->pg, NULL); + up_read(¤t->mm->mmap_sem); + if (err < 0) + return err; + BUG_ON(err != 1); + offset = cs->addr % PAGE_SIZE; + cs->mapaddr = kmap_atomic(cs->pg, KM_USER0); + cs->buf = cs->mapaddr + offset; + cs->len = min(PAGE_SIZE - offset, cs->seglen); + cs->seglen -= cs->len; + cs->addr += cs->len; + + return lock_request(cs->req); +} + +/* Do as much copy to/from userspace buffer as we can */ +static inline int fuse_copy_do(struct fuse_copy_state *cs, void **val, + unsigned *size) +{ + unsigned ncpy = min(*size, cs->len); + if (val) { + if (cs->write) + memcpy(cs->buf, *val, ncpy); + else + memcpy(*val, cs->buf, ncpy); + *val += ncpy; + } + *size -= ncpy; + cs->len -= ncpy; + cs->buf += ncpy; + return ncpy; +} + +/* + * Copy a page in the request to/from the userspace buffer. Must be + * done atomically + */ +static inline int fuse_copy_page(struct fuse_copy_state *cs, struct page *page, + unsigned offset, unsigned count, int zeroing) +{ + if (page && zeroing && count < PAGE_SIZE) { + void *mapaddr = kmap_atomic(page, KM_USER1); + memset(mapaddr, 0, PAGE_SIZE); + kunmap_atomic(mapaddr, KM_USER1); + } + while (count) { + int err; + if (!cs->len && (err = fuse_copy_fill(cs))) + return err; + if (page) { + void *mapaddr = kmap_atomic(page, KM_USER1); + void *buf = mapaddr + offset; + offset += fuse_copy_do(cs, &buf, &count); + kunmap_atomic(mapaddr, KM_USER1); + } else + offset += fuse_copy_do(cs, NULL, &count); + } + if (page && !cs->write) + flush_dcache_page(page); + return 0; +} + +/* Copy pages in the request to/from userspace buffer */ +static int fuse_copy_pages(struct fuse_copy_state *cs, unsigned nbytes, + int zeroing) +{ + unsigned i; + struct fuse_req *req = cs->req; + unsigned offset = req->page_offset; + unsigned count = min(nbytes, (unsigned) PAGE_SIZE - offset); + + for (i = 0; i < req->num_pages && (nbytes || zeroing); i++) { + struct page *page = req->pages[i]; + int err = fuse_copy_page(cs, page, offset, count, zeroing); + if (err) + return err; + + nbytes -= count; + count = min(nbytes, (unsigned) PAGE_SIZE); + offset = 0; + } + return 0; +} + +/* Copy a single argument in the request to/from userspace buffer */ +static int fuse_copy_one(struct fuse_copy_state *cs, void *val, unsigned size) +{ + while (size) { + int err; + if (!cs->len && (err = fuse_copy_fill(cs))) + return err; + fuse_copy_do(cs, &val, &size); + } + return 0; +} + +/* Copy request arguments to/from userspace buffer */ +static int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs, + unsigned argpages, struct fuse_arg *args, + int zeroing) +{ + int err = 0; + unsigned i; + + for (i = 0; !err && i < numargs; i++) { + struct fuse_arg *arg = &args[i]; + if (i == numargs - 1 && argpages) + err = fuse_copy_pages(cs, arg->size, zeroing); + else + err = fuse_copy_one(cs, arg->value, arg->size); + } + return err; +} + +/* Wait until a request is available on the pending list */ +static void request_wait(struct fuse_conn *fc) +{ + DECLARE_WAITQUEUE(wait, current); + + add_wait_queue_exclusive(&fc->waitq, &wait); + while (fc->mounted && list_empty(&fc->pending)) { + set_current_state(TASK_INTERRUPTIBLE); + if (signal_pending(current)) + break; + + spin_unlock(&fuse_lock); + schedule(); + spin_lock(&fuse_lock); + } + set_current_state(TASK_RUNNING); + remove_wait_queue(&fc->waitq, &wait); +} + +/* + * Read a single request into the userspace filesystem's buffer. This + * function waits until a request is available, then removes it from + * the pending list and copies request data to userspace buffer. If + * no reply is needed (FORGET) or request has been interrupted or + * there was an error during the copying then it's finished by calling + * request_end(). Otherwise add it to the processing list, and set + * the 'sent' flag. + */ +static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov, + unsigned long nr_segs, loff_t *off) +{ + int err; + struct fuse_conn *fc; + struct fuse_req *req; + struct fuse_in *in; + struct fuse_copy_state cs; + unsigned reqsize; + + spin_lock(&fuse_lock); + fc = file->private_data; + err = -EPERM; + if (!fc) + goto err_unlock; + request_wait(fc); + err = -ENODEV; + if (!fc->mounted) + goto err_unlock; + err = -ERESTARTSYS; + if (list_empty(&fc->pending)) + goto err_unlock; + + req = list_entry(fc->pending.next, struct fuse_req, list); + list_del_init(&req->list); + spin_unlock(&fuse_lock); + + in = &req->in; + reqsize = req->in.h.len; + fuse_copy_init(&cs, 1, req, iov, nr_segs); + err = -EINVAL; + if (iov_length(iov, nr_segs) >= reqsize) { + err = fuse_copy_one(&cs, &in->h, sizeof(in->h)); + if (!err) + err = fuse_copy_args(&cs, in->numargs, in->argpages, + (struct fuse_arg *) in->args, 0); + } + fuse_copy_finish(&cs); + + spin_lock(&fuse_lock); + req->locked = 0; + if (!err && req->interrupted) + err = -ENOENT; + if (err) { + if (!req->interrupted) + req->out.h.error = -EIO; + request_end(fc, req); + return err; + } + if (!req->isreply) + request_end(fc, req); + else { + req->sent = 1; + list_add_tail(&req->list, &fc->processing); + spin_unlock(&fuse_lock); + } + return reqsize; + + err_unlock: + spin_unlock(&fuse_lock); + return err; +} + +static ssize_t fuse_dev_read(struct file *file, char __user *buf, + size_t nbytes, loff_t *off) +{ + struct iovec iov; + iov.iov_len = nbytes; + iov.iov_base = buf; + return fuse_dev_readv(file, &iov, 1, off); +} + +/* Look up request on processing list by unique ID */ +static struct fuse_req *request_find(struct fuse_conn *fc, u64 unique) +{ + struct list_head *entry; + + list_for_each(entry, &fc->processing) { + struct fuse_req *req; + req = list_entry(entry, struct fuse_req, list); + if (req->in.h.unique == unique) + return req; + } + return NULL; +} + +static int copy_out_args(struct fuse_copy_state *cs, struct fuse_out *out, + unsigned nbytes) +{ + unsigned reqsize = sizeof(struct fuse_out_header); + + if (out->h.error) + return nbytes != reqsize ? -EINVAL : 0; + + reqsize += len_args(out->numargs, out->args); + + if (reqsize < nbytes || (reqsize > nbytes && !out->argvar)) + return -EINVAL; + else if (reqsize > nbytes) { + struct fuse_arg *lastarg = &out->args[out->numargs-1]; + unsigned diffsize = reqsize - nbytes; + if (diffsize > lastarg->size) + return -EINVAL; + lastarg->size -= diffsize; + } + return fuse_copy_args(cs, out->numargs, out->argpages, out->args, + out->page_zeroing); +} + +/* + * Write a single reply to a request. First the header is copied from + * the write buffer. The request is then searched on the processing + * list by the unique ID found in the header. If found, then remove + * it from the list and copy the rest of the buffer to the request. + * The request is finished by calling request_end() + */ +static ssize_t fuse_dev_writev(struct file *file, const struct iovec *iov, + unsigned long nr_segs, loff_t *off) +{ + int err; + unsigned nbytes = iov_length(iov, nr_segs); + struct fuse_req *req; + struct fuse_out_header oh; + struct fuse_copy_state cs; + struct fuse_conn *fc = fuse_get_conn(file); + if (!fc) + return -ENODEV; + + fuse_copy_init(&cs, 0, NULL, iov, nr_segs); + if (nbytes < sizeof(struct fuse_out_header)) + return -EINVAL; + + err = fuse_copy_one(&cs, &oh, sizeof(oh)); + if (err) + goto err_finish; + err = -EINVAL; + if (!oh.unique || oh.error <= -1000 || oh.error > 0 || + oh.len != nbytes) + goto err_finish; + + spin_lock(&fuse_lock); + req = request_find(fc, oh.unique); + err = -EINVAL; + if (!req) + goto err_unlock; + + list_del_init(&req->list); + if (req->interrupted) { + request_end(fc, req); + fuse_copy_finish(&cs); + return -ENOENT; + } + req->out.h = oh; + req->locked = 1; + cs.req = req; + spin_unlock(&fuse_lock); + + err = copy_out_args(&cs, &req->out, nbytes); + fuse_copy_finish(&cs); + + spin_lock(&fuse_lock); + req->locked = 0; + if (!err) { + if (req->interrupted) + err = -ENOENT; + } else if (!req->interrupted) + req->out.h.error = -EIO; + request_end(fc, req); + + return err ? err : nbytes; + + err_unlock: + spin_unlock(&fuse_lock); + err_finish: + fuse_copy_finish(&cs); + return err; +} + +static ssize_t fuse_dev_write(struct file *file, const char __user *buf, + size_t nbytes, loff_t *off) +{ + struct iovec iov; + iov.iov_len = nbytes; + iov.iov_base = (char __user *) buf; + return fuse_dev_writev(file, &iov, 1, off); +} + +static unsigned fuse_dev_poll(struct file *file, poll_table *wait) +{ + struct fuse_conn *fc = fuse_get_conn(file); + unsigned mask = POLLOUT | POLLWRNORM; + + if (!fc) + return -ENODEV; + + poll_wait(file, &fc->waitq, wait); + + spin_lock(&fuse_lock); + if (!list_empty(&fc->pending)) + mask |= POLLIN | POLLRDNORM; + spin_unlock(&fuse_lock); + + return mask; +} + +/* Abort all requests on the given list (pending or processing) */ +static void end_requests(struct fuse_conn *fc, struct list_head *head) +{ + while (!list_empty(head)) { + struct fuse_req *req; + req = list_entry(head->next, struct fuse_req, list); + list_del_init(&req->list); + req->out.h.error = -ECONNABORTED; + request_end(fc, req); + spin_lock(&fuse_lock); + } +} + +static int fuse_dev_release(struct inode *inode, struct file *file) +{ + struct fuse_conn *fc; + + spin_lock(&fuse_lock); + fc = file->private_data; + if (fc) { + fc->connected = 0; + end_requests(fc, &fc->pending); + end_requests(fc, &fc->processing); + fuse_release_conn(fc); + } + spin_unlock(&fuse_lock); + return 0; +} + +struct file_operations fuse_dev_operations = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = fuse_dev_read, + .readv = fuse_dev_readv, + .write = fuse_dev_write, + .writev = fuse_dev_writev, + .poll = fuse_dev_poll, + .release = fuse_dev_release, +}; + +static struct miscdevice fuse_miscdevice = { + .minor = FUSE_MINOR, + .name = "fuse", + .fops = &fuse_dev_operations, +}; + +int __init fuse_dev_init(void) +{ + int err = -ENOMEM; + fuse_req_cachep = kmem_cache_create("fuse_request", + sizeof(struct fuse_req), + 0, 0, NULL, NULL); + if (!fuse_req_cachep) + goto out; + + err = misc_register(&fuse_miscdevice); + if (err) + goto out_cache_clean; + + return 0; + + out_cache_clean: + kmem_cache_destroy(fuse_req_cachep); + out: + return err; +} + +void fuse_dev_cleanup(void) +{ + misc_deregister(&fuse_miscdevice); + kmem_cache_destroy(fuse_req_cachep); +} diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c new file mode 100644 index 00000000000..e79e49b3eec --- /dev/null +++ b/fs/fuse/dir.c @@ -0,0 +1,982 @@ +/* + FUSE: Filesystem in Userspace + Copyright (C) 2001-2005 Miklos Szeredi <miklos@szeredi.hu> + + This program can be distributed under the terms of the GNU GPL. + See the file COPYING. +*/ + +#include "fuse_i.h" + +#include <linux/pagemap.h> +#include <linux/file.h> +#include <linux/gfp.h> +#include <linux/sched.h> +#include <linux/namei.h> + +static inline unsigned long time_to_jiffies(unsigned long sec, + unsigned long nsec) +{ + struct timespec ts = {sec, nsec}; + return jiffies + timespec_to_jiffies(&ts); +} + +static void fuse_lookup_init(struct fuse_req *req, struct inode *dir, + struct dentry *entry, + struct fuse_entry_out *outarg) +{ + req->in.h.opcode = FUSE_LOOKUP; + req->in.h.nodeid = get_node_id(dir); + req->inode = dir; + req->in.numargs = 1; + req->in.args[0].size = entry->d_name.len + 1; + req->in.args[0].value = entry->d_name.name; + req->out.numargs = 1; + req->out.args[0].size = sizeof(struct fuse_entry_out); + req->out.args[0].value = outarg; +} + +static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) +{ + if (!entry->d_inode || is_bad_inode(entry->d_inode)) + return 0; + else if (time_after(jiffies, entry->d_time)) { + int err; + struct fuse_entry_out outarg; + struct inode *inode = entry->d_inode; + struct fuse_inode *fi = get_fuse_inode(inode); + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_req *req = fuse_get_request(fc); + if (!req) + return 0; + + fuse_lookup_init(req, entry->d_parent->d_inode, entry, &outarg); + request_send(fc, req); + err = req->out.h.error; + if (!err) { + if (outarg.nodeid != get_node_id(inode)) { + fuse_send_forget(fc, req, outarg.nodeid, 1); + return 0; + } + fi->nlookup ++; + } + fuse_put_request(fc, req); + if (err || (outarg.attr.mode ^ inode->i_mode) & S_IFMT) + return 0; + + fuse_change_attributes(inode, &outarg.attr); + entry->d_time = time_to_jiffies(outarg.entry_valid, + outarg.entry_valid_nsec); + fi->i_time = time_to_jiffies(outarg.attr_valid, + outarg.attr_valid_nsec); + } + return 1; +} + +static struct dentry_operations fuse_dentry_operations = { + .d_revalidate = fuse_dentry_revalidate, +}; + +static int fuse_lookup_iget(struct inode *dir, struct dentry *entry, + struct inode **inodep) +{ + int err; + struct fuse_entry_out outarg; + struct inode *inode = NULL; + struct fuse_conn *fc = get_fuse_conn(dir); + struct fuse_req *req; + + if (entry->d_name.len > FUSE_NAME_MAX) + return -ENAMETOOLONG; + + req = fuse_get_request(fc); + if (!req) + return -EINTR; + + fuse_lookup_init(req, dir, entry, &outarg); + request_send(fc, req); + err = req->out.h.error; + if (!err) { + inode = fuse_iget(dir->i_sb, outarg.nodeid, outarg.generation, + &outarg.attr); + if (!inode) { + fuse_send_forget(fc, req, outarg.nodeid, 1); + return -ENOMEM; + } + } + fuse_put_request(fc, req); + if (err && err != -ENOENT) + return err; + + if (inode) { + struct fuse_inode *fi = get_fuse_inode(inode); + entry->d_time = time_to_jiffies(outarg.entry_valid, + outarg.entry_valid_nsec); + fi->i_time = time_to_jiffies(outarg.attr_valid, + outarg.attr_valid_nsec); + } + + entry->d_op = &fuse_dentry_operations; + *inodep = inode; + return 0; +} + +void fuse_invalidate_attr(struct inode *inode) +{ + get_fuse_inode(inode)->i_time = jiffies - 1; +} + +static void fuse_invalidate_entry(struct dentry *entry) +{ + d_invalidate(entry); + entry->d_time = jiffies - 1; +} + +static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req, + struct inode *dir, struct dentry *entry, + int mode) +{ + struct fuse_entry_out outarg; + struct inode *inode; + struct fuse_inode *fi; + int err; + + req->in.h.nodeid = get_node_id(dir); + req->inode = dir; + req->out.numargs = 1; + req->out.args[0].size = sizeof(outarg); + req->out.args[0].value = &outarg; + request_send(fc, req); + err = req->out.h.error; + if (err) { + fuse_put_request(fc, req); + return err; + } + inode = fuse_iget(dir->i_sb, outarg.nodeid, outarg.generation, + &outarg.attr); + if (!inode) { + fuse_send_forget(fc, req, outarg.nodeid, 1); + return -ENOMEM; + } + fuse_put_request(fc, req); + + /* Don't allow userspace to do really stupid things... */ + if ((inode->i_mode ^ mode) & S_IFMT) { + iput(inode); + return -EIO; + } + + entry->d_time = time_to_jiffies(outarg.entry_valid, + outarg.entry_valid_nsec); + + fi = get_fuse_inode(inode); + fi->i_time = time_to_jiffies(outarg.attr_valid, + outarg.attr_valid_nsec); + + d_instantiate(entry, inode); + fuse_invalidate_attr(dir); + return 0; +} + +static int fuse_mknod(struct inode *dir, struct dentry *entry, int mode, + dev_t rdev) +{ + struct fuse_mknod_in inarg; + struct fuse_conn *fc = get_fuse_conn(dir); + struct fuse_req *req = fuse_get_request(fc); + if (!req) + return -EINTR; + + memset(&inarg, 0, sizeof(inarg)); + inarg.mode = mode; + inarg.rdev = new_encode_dev(rdev); + req->in.h.opcode = FUSE_MKNOD; + req->in.numargs = 2; + req->in.args[0].size = sizeof(inarg); + req->in.args[0].value = &inarg; + req->in.args[1].size = entry->d_name.len + 1; + req->in.args[1].value = entry->d_name.name; + return create_new_entry(fc, req, dir, entry, mode); +} + +static int fuse_create(struct inode *dir, struct dentry *entry, int mode, + struct nameidata *nd) +{ + return fuse_mknod(dir, entry, mode, 0); +} + +static int fuse_mkdir(struct inode *dir, struct dentry *entry, int mode) +{ + struct fuse_mkdir_in inarg; + struct fuse_conn *fc = get_fuse_conn(dir); + struct fuse_req *req = fuse_get_request(fc); + if (!req) + return -EINTR; + + memset(&inarg, 0, sizeof(inarg)); + inarg.mode = mode; + req->in.h.opcode = FUSE_MKDIR; + req->in.numargs = 2; + req->in.args[0].size = sizeof(inarg); + req->in.args[0].value = &inarg; + req->in.args[1].size = entry->d_name.len + 1; + req->in.args[1].value = entry->d_name.name; + return create_new_entry(fc, req, dir, entry, S_IFDIR); +} + +static int fuse_symlink(struct inode *dir, struct dentry *entry, + const char *link) +{ + struct fuse_conn *fc = get_fuse_conn(dir); + unsigned len = strlen(link) + 1; + struct fuse_req *req; + + if (len > FUSE_SYMLINK_MAX) + return -ENAMETOOLONG; + + req = fuse_get_request(fc); + if (!req) + return -EINTR; + + req->in.h.opcode = FUSE_SYMLINK; + req->in.numargs = 2; + req->in.args[0].size = entry->d_name.len + 1; + req->in.args[0].value = entry->d_name.name; + req->in.args[1].size = len; + req->in.args[1].value = link; + return create_new_entry(fc, req, dir, entry, S_IFLNK); +} + +static int fuse_unlink(struct inode *dir, struct dentry *entry) +{ + int err; + struct fuse_conn *fc = get_fuse_conn(dir); + struct fuse_req *req = fuse_get_request(fc); + if (!req) + return -EINTR; + + req->in.h.opcode = FUSE_UNLINK; + req->in.h.nodeid = get_node_id(dir); + req->inode = dir; + req->in.numargs = 1; + req->in.args[0].size = entry->d_name.len + 1; + req->in.args[0].value = entry->d_name.name; + request_send(fc, req); + err = req->out.h.error; + fuse_put_request(fc, req); + if (!err) { + struct inode *inode = entry->d_inode; + + /* Set nlink to zero so the inode can be cleared, if + the inode does have more links this will be + discovered at the next lookup/getattr */ + inode->i_nlink = 0; + fuse_invalidate_attr(inode); + fuse_invalidate_attr(dir); + } else if (err == -EINTR) + fuse_invalidate_entry(entry); + return err; +} + +static int fuse_rmdir(struct inode *dir, struct dentry *entry) +{ + int err; + struct fuse_conn *fc = get_fuse_conn(dir); + struct fuse_req *req = fuse_get_request(fc); + if (!req) + return -EINTR; + + req->in.h.opcode = FUSE_RMDIR; + req->in.h.nodeid = get_node_id(dir); + req->inode = dir; + req->in.numargs = 1; + req->in.args[0].size = entry->d_name.len + 1; + req->in.args[0].value = entry->d_name.name; + request_send(fc, req); + err = req->out.h.error; + fuse_put_request(fc, req); + if (!err) { + entry->d_inode->i_nlink = 0; + fuse_invalidate_attr(dir); + } else if (err == -EINTR) + fuse_invalidate_entry(entry); + return err; +} + +static int fuse_rename(struct inode *olddir, struct dentry *oldent, + struct inode *newdir, struct dentry *newent) +{ + int err; + struct fuse_rename_in inarg; + struct fuse_conn *fc = get_fuse_conn(olddir); + struct fuse_req *req = fuse_get_request(fc); + if (!req) + return -EINTR; + + memset(&inarg, 0, sizeof(inarg)); + inarg.newdir = get_node_id(newdir); + req->in.h.opcode = FUSE_RENAME; + req->in.h.nodeid = get_node_id(olddir); + req->inode = olddir; + req->inode2 = newdir; + req->in.numargs = 3; + req->in.args[0].size = sizeof(inarg); + req->in.args[0].value = &inarg; + req->in.args[1].size = oldent->d_name.len + 1; + req->in.args[1].value = oldent->d_name.name; + req->in.args[2].size = newent->d_name.len + 1; + req->in.args[2].value = newent->d_name.name; + request_send(fc, req); + err = req->out.h.error; + fuse_put_request(fc, req); + if (!err) { + fuse_invalidate_attr(olddir); + if (olddir != newdir) + fuse_invalidate_attr(newdir); + } else if (err == -EINTR) { + /* If request was interrupted, DEITY only knows if the + rename actually took place. If the invalidation + fails (e.g. some process has CWD under the renamed + directory), then there can be inconsistency between + the dcache and the real filesystem. Tough luck. */ + fuse_invalidate_entry(oldent); + if (newent->d_inode) + fuse_invalidate_entry(newent); + } + + return err; +} + +static int fuse_link(struct dentry *entry, struct inode *newdir, + struct dentry *newent) +{ + int err; + struct fuse_link_in inarg; + struct inode *inode = entry->d_inode; + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_req *req = fuse_get_request(fc); + if (!req) + return -EINTR; + + memset(&inarg, 0, sizeof(inarg)); + inarg.oldnodeid = get_node_id(inode); + req->in.h.opcode = FUSE_LINK; + req->inode2 = inode; + req->in.numargs = 2; + req->in.args[0].size = sizeof(inarg); + req->in.args[0].value = &inarg; + req->in.args[1].size = newent->d_name.len + 1; + req->in.args[1].value = newent->d_name.name; + err = create_new_entry(fc, req, newdir, newent, inode->i_mode); + /* Contrary to "normal" filesystems it can happen that link + makes two "logical" inodes point to the same "physical" + inode. We invalidate the attributes of the old one, so it + will reflect changes in the backing inode (link count, + etc.) + */ + if (!err || err == -EINTR) + fuse_invalidate_attr(inode); + return err; +} + +int fuse_do_getattr(struct inode *inode) +{ + int err; + struct fuse_attr_out arg; + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_req *req = fuse_get_request(fc); + if (!req) + return -EINTR; + + req->in.h.opcode = FUSE_GETATTR; + req->in.h.nodeid = get_node_id(inode); + req->inode = inode; + req->out.numargs = 1; + req->out.args[0].size = sizeof(arg); + req->out.args[0].value = &arg; + request_send(fc, req); + err = req->out.h.error; + fuse_put_request(fc, req); + if (!err) { + if ((inode->i_mode ^ arg.attr.mode) & S_IFMT) { + make_bad_inode(inode); + err = -EIO; + } else { + struct fuse_inode *fi = get_fuse_inode(inode); + fuse_change_attributes(inode, &arg.attr); + fi->i_time = time_to_jiffies(arg.attr_valid, + arg.attr_valid_nsec); + } + } + return err; +} + +/* + * Calling into a user-controlled filesystem gives the filesystem + * daemon ptrace-like capabilities over the requester process. This + * means, that the filesystem daemon is able to record the exact + * filesystem operations performed, and can also control the behavior + * of the requester process in otherwise impossible ways. For example + * it can delay the operation for arbitrary length of time allowing + * DoS against the requester. + * + * For this reason only those processes can call into the filesystem, + * for which the owner of the mount has ptrace privilege. This + * excludes processes started by other users, suid or sgid processes. + */ +static int fuse_allow_task(struct fuse_conn *fc, struct task_struct *task) +{ + if (fc->flags & FUSE_ALLOW_OTHER) + return 1; + + if (task->euid == fc->user_id && + task->suid == fc->user_id && + task->uid == fc->user_id && + task->egid == fc->group_id && + task->sgid == fc->group_id && + task->gid == fc->group_id) + return 1; + + return 0; +} + +static int fuse_revalidate(struct dentry *entry) +{ + struct inode *inode = entry->d_inode; + struct fuse_inode *fi = get_fuse_inode(inode); + struct fuse_conn *fc = get_fuse_conn(inode); + + if (!fuse_allow_task(fc, current)) + return -EACCES; + if (get_node_id(inode) != FUSE_ROOT_ID && + time_before_eq(jiffies, fi->i_time)) + return 0; + + return fuse_do_getattr(inode); +} + +static int fuse_permission(struct inode *inode, int mask, struct nameidata *nd) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + + if (!fuse_allow_task(fc, current)) + return -EACCES; + else if (fc->flags & FUSE_DEFAULT_PERMISSIONS) { + int err = generic_permission(inode, mask, NULL); + + /* If permission is denied, try to refresh file + attributes. This is also needed, because the root + node will at first have no permissions */ + if (err == -EACCES) { + err = fuse_do_getattr(inode); + if (!err) + err = generic_permission(inode, mask, NULL); + } + + /* FIXME: Need some mechanism to revoke permissions: + currently if the filesystem suddenly changes the + file mode, we will not be informed about it, and + continue to allow access to the file/directory. + + This is actually not so grave, since the user can + simply keep access to the file/directory anyway by + keeping it open... */ + + return err; + } else { + int mode = inode->i_mode; + if ((mask & MAY_WRITE) && IS_RDONLY(inode) && + (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) + return -EROFS; + if ((mask & MAY_EXEC) && !S_ISDIR(mode) && !(mode & S_IXUGO)) + return -EACCES; + return 0; + } +} + +static int parse_dirfile(char *buf, size_t nbytes, struct file *file, + void *dstbuf, filldir_t filldir) +{ + while (nbytes >= FUSE_NAME_OFFSET) { + struct fuse_dirent *dirent = (struct fuse_dirent *) buf; + size_t reclen = FUSE_DIRENT_SIZE(dirent); + int over; + if (!dirent->namelen || dirent->namelen > FUSE_NAME_MAX) + return -EIO; + if (reclen > nbytes) + break; + + over = filldir(dstbuf, dirent->name, dirent->namelen, + file->f_pos, dirent->ino, dirent->type); + if (over) + break; + + buf += reclen; + nbytes -= reclen; + file->f_pos = dirent->off; + } + + return 0; +} + +static inline size_t fuse_send_readdir(struct fuse_req *req, struct file *file, + struct inode *inode, loff_t pos, + size_t count) +{ + return fuse_send_read_common(req, file, inode, pos, count, 1); +} + +static int fuse_readdir(struct file *file, void *dstbuf, filldir_t filldir) +{ + int err; + size_t nbytes; + struct page *page; + struct inode *inode = file->f_dentry->d_inode; + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_req *req = fuse_get_request(fc); + if (!req) + return -EINTR; + + page = alloc_page(GFP_KERNEL); + if (!page) { + fuse_put_request(fc, req); + return -ENOMEM; + } + req->num_pages = 1; + req->pages[0] = page; + nbytes = fuse_send_readdir(req, file, inode, file->f_pos, PAGE_SIZE); + err = req->out.h.error; + fuse_put_request(fc, req); + if (!err) + err = parse_dirfile(page_address(page), nbytes, file, dstbuf, + filldir); + + __free_page(page); + fuse_invalidate_attr(inode); /* atime changed */ + return err; +} + +static char *read_link(struct dentry *dentry) +{ + struct inode *inode = dentry->d_inode; + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_req *req = fuse_get_request(fc); + char *link; + + if (!req) + return ERR_PTR(-EINTR); + + link = (char *) __get_free_page(GFP_KERNEL); + if (!link) { + link = ERR_PTR(-ENOMEM); + goto out; + } + req->in.h.opcode = FUSE_READLINK; + req->in.h.nodeid = get_node_id(inode); + req->inode = inode; + req->out.argvar = 1; + req->out.numargs = 1; + req->out.args[0].size = PAGE_SIZE - 1; + req->out.args[0].value = link; + request_send(fc, req); + if (req->out.h.error) { + free_page((unsigned long) link); + link = ERR_PTR(req->out.h.error); + } else + link[req->out.args[0].size] = '\0'; + out: + fuse_put_request(fc, req); + fuse_invalidate_attr(inode); /* atime changed */ + return link; +} + +static void free_link(char *link) +{ + if (!IS_ERR(link)) + free_page((unsigned long) link); +} + +static void *fuse_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + nd_set_link(nd, read_link(dentry)); + return NULL; +} + +static void fuse_put_link(struct dentry *dentry, struct nameidata *nd, void *c) +{ + free_link(nd_get_link(nd)); +} + +static int fuse_dir_open(struct inode *inode, struct file *file) +{ + return fuse_open_common(inode, file, 1); +} + +static int fuse_dir_release(struct inode *inode, struct file *file) +{ + return fuse_release_common(inode, file, 1); +} + +static int fuse_dir_fsync(struct file *file, struct dentry *de, int datasync) +{ + /* nfsd can call this with no file */ + return file ? fuse_fsync_common(file, de, datasync, 1) : 0; +} + +static unsigned iattr_to_fattr(struct iattr *iattr, struct fuse_attr *fattr) +{ + unsigned ivalid = iattr->ia_valid; + unsigned fvalid = 0; + + memset(fattr, 0, sizeof(*fattr)); + + if (ivalid & ATTR_MODE) + fvalid |= FATTR_MODE, fattr->mode = iattr->ia_mode; + if (ivalid & ATTR_UID) + fvalid |= FATTR_UID, fattr->uid = iattr->ia_uid; + if (ivalid & ATTR_GID) + fvalid |= FATTR_GID, fattr->gid = iattr->ia_gid; + if (ivalid & ATTR_SIZE) + fvalid |= FATTR_SIZE, fattr->size = iattr->ia_size; + /* You can only _set_ these together (they may change by themselves) */ + if ((ivalid & (ATTR_ATIME | ATTR_MTIME)) == (ATTR_ATIME | ATTR_MTIME)) { + fvalid |= FATTR_ATIME | FATTR_MTIME; + fattr->atime = iattr->ia_atime.tv_sec; + fattr->mtime = iattr->ia_mtime.tv_sec; + } + + return fvalid; +} + +static int fuse_setattr(struct dentry *entry, struct iattr *attr) +{ + struct inode *inode = entry->d_inode; + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_inode *fi = get_fuse_inode(inode); + struct fuse_req *req; + struct fuse_setattr_in inarg; + struct fuse_attr_out outarg; + int err; + int is_truncate = 0; + + if (fc->flags & FUSE_DEFAULT_PERMISSIONS) { + err = inode_change_ok(inode, attr); + if (err) + return err; + } + + if (attr->ia_valid & ATTR_SIZE) { + unsigned long limit; + is_truncate = 1; + limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur; + if (limit != RLIM_INFINITY && attr->ia_size > (loff_t) limit) { + send_sig(SIGXFSZ, current, 0); + return -EFBIG; + } + } + + req = fuse_get_request(fc); + if (!req) + return -EINTR; + + memset(&inarg, 0, sizeof(inarg)); + inarg.valid = iattr_to_fattr(attr, &inarg.attr); + req->in.h.opcode = FUSE_SETATTR; + req->in.h.nodeid = get_node_id(inode); + req->inode = inode; + req->in.numargs = 1; + req->in.args[0].size = sizeof(inarg); + req->in.args[0].value = &inarg; + req->out.numargs = 1; + req->out.args[0].size = sizeof(outarg); + req->out.args[0].value = &outarg; + request_send(fc, req); + err = req->out.h.error; + fuse_put_request(fc, req); + if (!err) { + if ((inode->i_mode ^ outarg.attr.mode) & S_IFMT) { + make_bad_inode(inode); + err = -EIO; + } else { + if (is_truncate) { + loff_t origsize = i_size_read(inode); + i_size_write(inode, outarg.attr.size); + if (origsize > outarg.attr.size) + vmtruncate(inode, outarg.attr.size); + } + fuse_change_attributes(inode, &outarg.attr); + fi->i_time = time_to_jiffies(outarg.attr_valid, + outarg.attr_valid_nsec); + } + } else if (err == -EINTR) + fuse_invalidate_attr(inode); + + return err; +} + +static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry, + struct kstat *stat) +{ + struct inode *inode = entry->d_inode; + int err = fuse_revalidate(entry); + if (!err) + generic_fillattr(inode, stat); + + return err; +} + +static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, + struct nameidata *nd) +{ + struct inode *inode; + int err = fuse_lookup_iget(dir, entry, &inode); + if (err) + return ERR_PTR(err); + if (inode && S_ISDIR(inode->i_mode)) { + /* Don't allow creating an alias to a directory */ + struct dentry *alias = d_find_alias(inode); + if (alias && !(alias->d_flags & DCACHE_DISCONNECTED)) { + dput(alias); + iput(inode); + return ERR_PTR(-EIO); + } + } + return d_splice_alias(inode, entry); +} + +static int fuse_setxattr(struct dentry *entry, const char *name, + const void *value, size_t size, int flags) +{ + struct inode *inode = entry->d_inode; + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_req *req; + struct fuse_setxattr_in inarg; + int err; + + if (size > FUSE_XATTR_SIZE_MAX) + return -E2BIG; + + if (fc->no_setxattr) + return -EOPNOTSUPP; + + req = fuse_get_request(fc); + if (!req) + return -EINTR; + + memset(&inarg, 0, sizeof(inarg)); + inarg.size = size; + inarg.flags = flags; + req->in.h.opcode = FUSE_SETXATTR; + req->in.h.nodeid = get_node_id(inode); + req->inode = inode; + req->in.numargs = 3; + req->in.args[0].size = sizeof(inarg); + req->in.args[0].value = &inarg; + req->in.args[1].size = strlen(name) + 1; + req->in.args[1].value = name; + req->in.args[2].size = size; + req->in.args[2].value = value; + request_send(fc, req); + err = req->out.h.error; + fuse_put_request(fc, req); + if (err == -ENOSYS) { + fc->no_setxattr = 1; + err = -EOPNOTSUPP; + } + return err; +} + +static ssize_t fuse_getxattr(struct dentry *entry, const char *name, + void *value, size_t size) +{ + struct inode *inode = entry->d_inode; + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_req *req; + struct fuse_getxattr_in inarg; + struct fuse_getxattr_out outarg; + ssize_t ret; + + if (fc->no_getxattr) + return -EOPNOTSUPP; + + req = fuse_get_request(fc); + if (!req) + return -EINTR; + + memset(&inarg, 0, sizeof(inarg)); + inarg.size = size; + req->in.h.opcode = FUSE_GETXATTR; + req->in.h.nodeid = get_node_id(inode); + req->inode = inode; + req->in.numargs = 2; + req->in.args[0].size = sizeof(inarg); + req->in.args[0].value = &inarg; + req->in.args[1].size = strlen(name) + 1; + req->in.args[1].value = name; + /* This is really two different operations rolled into one */ + req->out.numargs = 1; + if (size) { + req->out.argvar = 1; + req->out.args[0].size = size; + req->out.args[0].value = value; + } else { + req->out.args[0].size = sizeof(outarg); + req->out.args[0].value = &outarg; + } + request_send(fc, req); + ret = req->out.h.error; + if (!ret) + ret = size ? req->out.args[0].size : outarg.size; + else { + if (ret == -ENOSYS) { + fc->no_getxattr = 1; + ret = -EOPNOTSUPP; + } + } + fuse_put_request(fc, req); + return ret; +} + +static ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size) +{ + struct inode *inode = entry->d_inode; + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_req *req; + struct fuse_getxattr_in inarg; + struct fuse_getxattr_out outarg; + ssize_t ret; + + if (fc->no_listxattr) + return -EOPNOTSUPP; + + req = fuse_get_request(fc); + if (!req) + return -EINTR; + + memset(&inarg, 0, sizeof(inarg)); + inarg.size = size; + req->in.h.opcode = FUSE_LISTXATTR; + req->in.h.nodeid = get_node_id(inode); + req->inode = inode; + req->in.numargs = 1; + req->in.args[0].size = sizeof(inarg); + req->in.args[0].value = &inarg; + /* This is really two different operations rolled into one */ + req->out.numargs = 1; + if (size) { + req->out.argvar = 1; + req->out.args[0].size = size; + req->out.args[0].value = list; + } else { + req->out.args[0].size = sizeof(outarg); + req->out.args[0].value = &outarg; + } + request_send(fc, req); + ret = req->out.h.error; + if (!ret) + ret = size ? req->out.args[0].size : outarg.size; + else { + if (ret == -ENOSYS) { + fc->no_listxattr = 1; + ret = -EOPNOTSUPP; + } + } + fuse_put_request(fc, req); + return ret; +} + +static int fuse_removexattr(struct dentry *entry, const char *name) +{ + struct inode *inode = entry->d_inode; + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_req *req; + int err; + + if (fc->no_removexattr) + return -EOPNOTSUPP; + + req = fuse_get_request(fc); + if (!req) + return -EINTR; + + req->in.h.opcode = FUSE_REMOVEXATTR; + req->in.h.nodeid = get_node_id(inode); + req->inode = inode; + req->in.numargs = 1; + req->in.args[0].size = strlen(name) + 1; + req->in.args[0].value = name; + request_send(fc, req); + err = req->out.h.error; + fuse_put_request(fc, req); + if (err == -ENOSYS) { + fc->no_removexattr = 1; + err = -EOPNOTSUPP; + } + return err; +} + +static struct inode_operations fuse_dir_inode_operations = { + .lookup = fuse_lookup, + .mkdir = fuse_mkdir, + .symlink = fuse_symlink, + .unlink = fuse_unlink, + .rmdir = fuse_rmdir, + .rename = fuse_rename, + .link = fuse_link, + .setattr = fuse_setattr, + .create = fuse_create, + .mknod = fuse_mknod, + .permission = fuse_permission, + .getattr = fuse_getattr, + .setxattr = fuse_setxattr, + .getxattr = fuse_getxattr, + .listxattr = fuse_listxattr, + .removexattr = fuse_removexattr, +}; + +static struct file_operations fuse_dir_operations = { + .llseek = generic_file_llseek, + .read = generic_read_dir, + .readdir = fuse_readdir, + .open = fuse_dir_open, + .release = fuse_dir_release, + .fsync = fuse_dir_fsync, +}; + +static struct inode_operations fuse_common_inode_operations = { + .setattr = fuse_setattr, + .permission = fuse_permission, + .getattr = fuse_getattr, + .setxattr = fuse_setxattr, + .getxattr = fuse_getxattr, + .listxattr = fuse_listxattr, + .removexattr = fuse_removexattr, +}; + +static struct inode_operations fuse_symlink_inode_operations = { + .setattr = fuse_setattr, + .follow_link = fuse_follow_link, + .put_link = fuse_put_link, + .readlink = generic_readlink, + .getattr = fuse_getattr, + .setxattr = fuse_setxattr, + .getxattr = fuse_getxattr, + .listxattr = fuse_listxattr, + .removexattr = fuse_removexattr, +}; + +void fuse_init_common(struct inode *inode) +{ + inode->i_op = &fuse_common_inode_operations; +} + +void fuse_init_dir(struct inode *inode) +{ + inode->i_op = &fuse_dir_inode_operations; + inode->i_fop = &fuse_dir_operations; +} + +void fuse_init_symlink(struct inode *inode) +{ + inode->i_op = &fuse_symlink_inode_operations; +} diff --git a/fs/fuse/file.c b/fs/fuse/file.c new file mode 100644 index 00000000000..6454022b053 --- /dev/null +++ b/fs/fuse/file.c @@ -0,0 +1,555 @@ +/* + FUSE: Filesystem in Userspace + Copyright (C) 2001-2005 Miklos Szeredi <miklos@szeredi.hu> + + This program can be distributed under the terms of the GNU GPL. + See the file COPYING. +*/ + +#include "fuse_i.h" + +#include <linux/pagemap.h> +#include <linux/slab.h> +#include <linux/kernel.h> + +static struct file_operations fuse_direct_io_file_operations; + +int fuse_open_common(struct inode *inode, struct file *file, int isdir) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_req *req; + struct fuse_open_in inarg; + struct fuse_open_out outarg; + struct fuse_file *ff; + int err; + + err = generic_file_open(inode, file); + if (err) + return err; + + /* If opening the root node, no lookup has been performed on + it, so the attributes must be refreshed */ + if (get_node_id(inode) == FUSE_ROOT_ID) { + int err = fuse_do_getattr(inode); + if (err) + return err; + } + + req = fuse_get_request(fc); + if (!req) + return -EINTR; + + err = -ENOMEM; + ff = kmalloc(sizeof(struct fuse_file), GFP_KERNEL); + if (!ff) + goto out_put_request; + + ff->release_req = fuse_request_alloc(); + if (!ff->release_req) { + kfree(ff); + goto out_put_request; + } + + memset(&inarg, 0, sizeof(inarg)); + inarg.flags = file->f_flags & ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); + req->in.h.opcode = isdir ? FUSE_OPENDIR : FUSE_OPEN; + req->in.h.nodeid = get_node_id(inode); + req->inode = inode; + req->in.numargs = 1; + req->in.args[0].size = sizeof(inarg); + req->in.args[0].value = &inarg; + req->out.numargs = 1; + req->out.args[0].size = sizeof(outarg); + req->out.args[0].value = &outarg; + request_send(fc, req); + err = req->out.h.error; + if (err) { + fuse_request_free(ff->release_req); + kfree(ff); + } else { + if (!isdir && (outarg.open_flags & FOPEN_DIRECT_IO)) + file->f_op = &fuse_direct_io_file_operations; + if (!(outarg.open_flags & FOPEN_KEEP_CACHE)) + invalidate_inode_pages(inode->i_mapping); + ff->fh = outarg.fh; + file->private_data = ff; + } + + out_put_request: + fuse_put_request(fc, req); + return err; +} + +int fuse_release_common(struct inode *inode, struct file *file, int isdir) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_file *ff = file->private_data; + struct fuse_req *req = ff->release_req; + struct fuse_release_in *inarg = &req->misc.release_in; + + inarg->fh = ff->fh; + inarg->flags = file->f_flags & ~O_EXCL; + req->in.h.opcode = isdir ? FUSE_RELEASEDIR : FUSE_RELEASE; + req->in.h.nodeid = get_node_id(inode); + req->inode = inode; + req->in.numargs = 1; + req->in.args[0].size = sizeof(struct fuse_release_in); + req->in.args[0].value = inarg; + request_send_background(fc, req); + kfree(ff); + + /* Return value is ignored by VFS */ + return 0; +} + +static int fuse_open(struct inode *inode, struct file *file) +{ + return fuse_open_common(inode, file, 0); +} + +static int fuse_release(struct inode *inode, struct file *file) +{ + return fuse_release_common(inode, file, 0); +} + +static int fuse_flush(struct file *file) +{ + struct inode *inode = file->f_dentry->d_inode; + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_file *ff = file->private_data; + struct fuse_req *req; + struct fuse_flush_in inarg; + int err; + + if (fc->no_flush) + return 0; + + req = fuse_get_request(fc); + if (!req) + return -EINTR; + + memset(&inarg, 0, sizeof(inarg)); + inarg.fh = ff->fh; + req->in.h.opcode = FUSE_FLUSH; + req->in.h.nodeid = get_node_id(inode); + req->inode = inode; + req->file = file; + req->in.numargs = 1; + req->in.args[0].size = sizeof(inarg); + req->in.args[0].value = &inarg; + request_send(fc, req); + err = req->out.h.error; + fuse_put_request(fc, req); + if (err == -ENOSYS) { + fc->no_flush = 1; + err = 0; + } + return err; +} + +int fuse_fsync_common(struct file *file, struct dentry *de, int datasync, + int isdir) +{ + struct inode *inode = de->d_inode; + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_file *ff = file->private_data; + struct fuse_req *req; + struct fuse_fsync_in inarg; + int err; + + if ((!isdir && fc->no_fsync) || (isdir && fc->no_fsyncdir)) + return 0; + + req = fuse_get_request(fc); + if (!req) + return -EINTR; + + memset(&inarg, 0, sizeof(inarg)); + inarg.fh = ff->fh; + inarg.fsync_flags = datasync ? 1 : 0; + req->in.h.opcode = isdir ? FUSE_FSYNCDIR : FUSE_FSYNC; + req->in.h.nodeid = get_node_id(inode); + req->inode = inode; + req->file = file; + req->in.numargs = 1; + req->in.args[0].size = sizeof(inarg); + req->in.args[0].value = &inarg; + request_send(fc, req); + err = req->out.h.error; + fuse_put_request(fc, req); + if (err == -ENOSYS) { + if (isdir) + fc->no_fsyncdir = 1; + else + fc->no_fsync = 1; + err = 0; + } + return err; +} + +static int fuse_fsync(struct file *file, struct dentry *de, int datasync) +{ + return fuse_fsync_common(file, de, datasync, 0); +} + +size_t fuse_send_read_common(struct fuse_req *req, struct file *file, + struct inode *inode, loff_t pos, size_t count, + int isdir) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_file *ff = file->private_data; + struct fuse_read_in inarg; + + memset(&inarg, 0, sizeof(struct fuse_read_in)); + inarg.fh = ff->fh; + inarg.offset = pos; + inarg.size = count; + req->in.h.opcode = isdir ? FUSE_READDIR : FUSE_READ; + req->in.h.nodeid = get_node_id(inode); + req->inode = inode; + req->file = file; + req->in.numargs = 1; + req->in.args[0].size = sizeof(struct fuse_read_in); + req->in.args[0].value = &inarg; + req->out.argpages = 1; + req->out.argvar = 1; + req->out.numargs = 1; + req->out.args[0].size = count; + request_send(fc, req); + return req->out.args[0].size; +} + +static inline size_t fuse_send_read(struct fuse_req *req, struct file *file, + struct inode *inode, loff_t pos, + size_t count) +{ + return fuse_send_read_common(req, file, inode, pos, count, 0); +} + +static int fuse_readpage(struct file *file, struct page *page) +{ + struct inode *inode = page->mapping->host; + struct fuse_conn *fc = get_fuse_conn(inode); + loff_t pos = (loff_t) page->index << PAGE_CACHE_SHIFT; + struct fuse_req *req = fuse_get_request(fc); + int err = -EINTR; + if (!req) + goto out; + + req->out.page_zeroing = 1; + req->num_pages = 1; + req->pages[0] = page; + fuse_send_read(req, file, inode, pos, PAGE_CACHE_SIZE); + err = req->out.h.error; + fuse_put_request(fc, req); + if (!err) + SetPageUptodate(page); + fuse_invalidate_attr(inode); /* atime changed */ + out: + unlock_page(page); + return err; +} + +static int fuse_send_readpages(struct fuse_req *req, struct file *file, + struct inode *inode) +{ + loff_t pos = (loff_t) req->pages[0]->index << PAGE_CACHE_SHIFT; + size_t count = req->num_pages << PAGE_CACHE_SHIFT; + unsigned i; + req->out.page_zeroing = 1; + fuse_send_read(req, file, inode, pos, count); + for (i = 0; i < req->num_pages; i++) { + struct page *page = req->pages[i]; + if (!req->out.h.error) + SetPageUptodate(page); + unlock_page(page); + } + return req->out.h.error; +} + +struct fuse_readpages_data { + struct fuse_req *req; + struct file *file; + struct inode *inode; +}; + +static int fuse_readpages_fill(void *_data, struct page *page) +{ + struct fuse_readpages_data *data = _data; + struct fuse_req *req = data->req; + struct inode *inode = data->inode; + struct fuse_conn *fc = get_fuse_conn(inode); + + if (req->num_pages && + (req->num_pages == FUSE_MAX_PAGES_PER_REQ || + (req->num_pages + 1) * PAGE_CACHE_SIZE > fc->max_read || + req->pages[req->num_pages - 1]->index + 1 != page->index)) { + int err = fuse_send_readpages(req, data->file, inode); + if (err) { + unlock_page(page); + return err; + } + fuse_reset_request(req); + } + req->pages[req->num_pages] = page; + req->num_pages ++; + return 0; +} + +static int fuse_readpages(struct file *file, struct address_space *mapping, + struct list_head *pages, unsigned nr_pages) +{ + struct inode *inode = mapping->host; + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_readpages_data data; + int err; + data.file = file; + data.inode = inode; + data.req = fuse_get_request(fc); + if (!data.req) + return -EINTR; + + err = read_cache_pages(mapping, pages, fuse_readpages_fill, &data); + if (!err && data.req->num_pages) + err = fuse_send_readpages(data.req, file, inode); + fuse_put_request(fc, data.req); + fuse_invalidate_attr(inode); /* atime changed */ + return err; +} + +static size_t fuse_send_write(struct fuse_req *req, struct file *file, + struct inode *inode, loff_t pos, size_t count) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_file *ff = file->private_data; + struct fuse_write_in inarg; + struct fuse_write_out outarg; + + memset(&inarg, 0, sizeof(struct fuse_write_in)); + inarg.fh = ff->fh; + inarg.offset = pos; + inarg.size = count; + req->in.h.opcode = FUSE_WRITE; + req->in.h.nodeid = get_node_id(inode); + req->inode = inode; + req->file = file; + req->in.argpages = 1; + req->in.numargs = 2; + req->in.args[0].size = sizeof(struct fuse_write_in); + req->in.args[0].value = &inarg; + req->in.args[1].size = count; + req->out.numargs = 1; + req->out.args[0].size = sizeof(struct fuse_write_out); + req->out.args[0].value = &outarg; + request_send(fc, req); + return outarg.size; +} + +static int fuse_prepare_write(struct file *file, struct page *page, + unsigned offset, unsigned to) +{ + /* No op */ + return 0; +} + +static int fuse_commit_write(struct file *file, struct page *page, + unsigned offset, unsigned to) +{ + int err; + size_t nres; + unsigned count = to - offset; + struct inode *inode = page->mapping->host; + struct fuse_conn *fc = get_fuse_conn(inode); + loff_t pos = ((loff_t) page->index << PAGE_CACHE_SHIFT) + offset; + struct fuse_req *req = fuse_get_request(fc); + if (!req) + return -EINTR; + + req->num_pages = 1; + req->pages[0] = page; + req->page_offset = offset; + nres = fuse_send_write(req, file, inode, pos, count); + err = req->out.h.error; + fuse_put_request(fc, req); + if (!err && nres != count) + err = -EIO; + if (!err) { + pos += count; + if (pos > i_size_read(inode)) + i_size_write(inode, pos); + + if (offset == 0 && to == PAGE_CACHE_SIZE) { + clear_page_dirty(page); + SetPageUptodate(page); + } + } + fuse_invalidate_attr(inode); + return err; +} + +static void fuse_release_user_pages(struct fuse_req *req, int write) +{ + unsigned i; + + for (i = 0; i < req->num_pages; i++) { + struct page *page = req->pages[i]; + if (write) + set_page_dirty_lock(page); + put_page(page); + } +} + +static int fuse_get_user_pages(struct fuse_req *req, const char __user *buf, + unsigned nbytes, int write) +{ + unsigned long user_addr = (unsigned long) buf; + unsigned offset = user_addr & ~PAGE_MASK; + int npages; + + /* This doesn't work with nfsd */ + if (!current->mm) + return -EPERM; + + nbytes = min(nbytes, (unsigned) FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT); + npages = (nbytes + offset + PAGE_SIZE - 1) >> PAGE_SHIFT; + npages = min(npages, FUSE_MAX_PAGES_PER_REQ); + down_read(¤t->mm->mmap_sem); + npages = get_user_pages(current, current->mm, user_addr, npages, write, + 0, req->pages, NULL); + up_read(¤t->mm->mmap_sem); + if (npages < 0) + return npages; + + req->num_pages = npages; + req->page_offset = offset; + return 0; +} + +static ssize_t fuse_direct_io(struct file *file, const char __user *buf, + size_t count, loff_t *ppos, int write) +{ + struct inode *inode = file->f_dentry->d_inode; + struct fuse_conn *fc = get_fuse_conn(inode); + size_t nmax = write ? fc->max_write : fc->max_read; + loff_t pos = *ppos; + ssize_t res = 0; + struct fuse_req *req = fuse_get_request(fc); + if (!req) + return -EINTR; + + while (count) { + size_t tmp; + size_t nres; + size_t nbytes = min(count, nmax); + int err = fuse_get_user_pages(req, buf, nbytes, !write); + if (err) { + res = err; + break; + } + tmp = (req->num_pages << PAGE_SHIFT) - req->page_offset; + nbytes = min(nbytes, tmp); + if (write) + nres = fuse_send_write(req, file, inode, pos, nbytes); + else + nres = fuse_send_read(req, file, inode, pos, nbytes); + fuse_release_user_pages(req, !write); + if (req->out.h.error) { + if (!res) + res = req->out.h.error; + break; + } else if (nres > nbytes) { + res = -EIO; + break; + } + count -= nres; + res += nres; + pos += nres; + buf += nres; + if (nres != nbytes) + break; + if (count) + fuse_reset_request(req); + } + fuse_put_request(fc, req); + if (res > 0) { + if (write && pos > i_size_read(inode)) + i_size_write(inode, pos); + *ppos = pos; + } + fuse_invalidate_attr(inode); + + return res; +} + +static ssize_t fuse_direct_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + return fuse_direct_io(file, buf, count, ppos, 0); +} + +static ssize_t fuse_direct_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct inode *inode = file->f_dentry->d_inode; + ssize_t res; + /* Don't allow parallel writes to the same file */ + down(&inode->i_sem); + res = fuse_direct_io(file, buf, count, ppos, 1); + up(&inode->i_sem); + return res; +} + +static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) +{ + if ((vma->vm_flags & VM_SHARED)) { + if ((vma->vm_flags & VM_WRITE)) + return -ENODEV; + else + vma->vm_flags &= ~VM_MAYWRITE; + } + return generic_file_mmap(file, vma); +} + +static int fuse_set_page_dirty(struct page *page) +{ + printk("fuse_set_page_dirty: should not happen\n"); + dump_stack(); + return 0; +} + +static struct file_operations fuse_file_operations = { + .llseek = generic_file_llseek, + .read = generic_file_read, + .write = generic_file_write, + .mmap = fuse_file_mmap, + .open = fuse_open, + .flush = fuse_flush, + .release = fuse_release, + .fsync = fuse_fsync, + .sendfile = generic_file_sendfile, +}; + +static struct file_operations fuse_direct_io_file_operations = { + .llseek = generic_file_llseek, + .read = fuse_direct_read, + .write = fuse_direct_write, + .open = fuse_open, + .flush = fuse_flush, + .release = fuse_release, + .fsync = fuse_fsync, + /* no mmap and sendfile */ +}; + +static struct address_space_operations fuse_file_aops = { + .readpage = fuse_readpage, + .prepare_write = fuse_prepare_write, + .commit_write = fuse_commit_write, + .readpages = fuse_readpages, + .set_page_dirty = fuse_set_page_dirty, +}; + +void fuse_init_file_inode(struct inode *inode) +{ + inode->i_fop = &fuse_file_operations; + inode->i_data.a_ops = &fuse_file_aops; +} diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h new file mode 100644 index 00000000000..24d761518d8 --- /dev/null +++ b/fs/fuse/fuse_i.h @@ -0,0 +1,451 @@ +/* + FUSE: Filesystem in Userspace + Copyright (C) 2001-2005 Miklos Szeredi <miklos@szeredi.hu> + + This program can be distributed under the terms of the GNU GPL. + See the file COPYING. +*/ + +#include <linux/fuse.h> +#include <linux/fs.h> +#include <linux/wait.h> +#include <linux/list.h> +#include <linux/spinlock.h> +#include <linux/mm.h> +#include <linux/backing-dev.h> +#include <asm/semaphore.h> + +/** Max number of pages that can be used in a single read request */ +#define FUSE_MAX_PAGES_PER_REQ 32 + +/** If more requests are outstanding, then the operation will block */ +#define FUSE_MAX_OUTSTANDING 10 + +/** If the FUSE_DEFAULT_PERMISSIONS flag is given, the filesystem + module will check permissions based on the file mode. Otherwise no + permission checking is done in the kernel */ +#define FUSE_DEFAULT_PERMISSIONS (1 << 0) + +/** If the FUSE_ALLOW_OTHER flag is given, then not only the user + doing the mount will be allowed to access the filesystem */ +#define FUSE_ALLOW_OTHER (1 << 1) + + +/** FUSE inode */ +struct fuse_inode { + /** Inode data */ + struct inode inode; + + /** Unique ID, which identifies the inode between userspace + * and kernel */ + u64 nodeid; + + /** Number of lookups on this inode */ + u64 nlookup; + + /** The request used for sending the FORGET message */ + struct fuse_req *forget_req; + + /** Time in jiffies until the file attributes are valid */ + unsigned long i_time; +}; + +/** FUSE specific file data */ +struct fuse_file { + /** Request reserved for flush and release */ + struct fuse_req *release_req; + + /** File handle used by userspace */ + u64 fh; +}; + +/** One input argument of a request */ +struct fuse_in_arg { + unsigned size; + const void *value; +}; + +/** The request input */ +struct fuse_in { + /** The request header */ + struct fuse_in_header h; + + /** True if the data for the last argument is in req->pages */ + unsigned argpages:1; + + /** Number of arguments */ + unsigned numargs; + + /** Array of arguments */ + struct fuse_in_arg args[3]; +}; + +/** One output argument of a request */ +struct fuse_arg { + unsigned size; + void *value; +}; + +/** The request output */ +struct fuse_out { + /** Header returned from userspace */ + struct fuse_out_header h; + + /** Last argument is variable length (can be shorter than + arg->size) */ + unsigned argvar:1; + + /** Last argument is a list of pages to copy data to */ + unsigned argpages:1; + + /** Zero partially or not copied pages */ + unsigned page_zeroing:1; + + /** Number or arguments */ + unsigned numargs; + + /** Array of arguments */ + struct fuse_arg args[3]; +}; + +struct fuse_req; +struct fuse_conn; + +/** + * A request to the client + */ +struct fuse_req { + /** This can be on either unused_list, pending or processing + lists in fuse_conn */ + struct list_head list; + + /** Entry on the background list */ + struct list_head bg_entry; + + /** refcount */ + atomic_t count; + + /** True if the request has reply */ + unsigned isreply:1; + + /** The request is preallocated */ + unsigned preallocated:1; + + /** The request was interrupted */ + unsigned interrupted:1; + + /** Request is sent in the background */ + unsigned background:1; + + /** Data is being copied to/from the request */ + unsigned locked:1; + + /** Request has been sent to userspace */ + unsigned sent:1; + + /** The request is finished */ + unsigned finished:1; + + /** The request input */ + struct fuse_in in; + + /** The request output */ + struct fuse_out out; + + /** Used to wake up the task waiting for completion of request*/ + wait_queue_head_t waitq; + + /** Data for asynchronous requests */ + union { + struct fuse_forget_in forget_in; + struct fuse_release_in release_in; + struct fuse_init_in_out init_in_out; + } misc; + + /** page vector */ + struct page *pages[FUSE_MAX_PAGES_PER_REQ]; + + /** number of pages in vector */ + unsigned num_pages; + + /** offset of data on first page */ + unsigned page_offset; + + /** Inode used in the request */ + struct inode *inode; + + /** Second inode used in the request (or NULL) */ + struct inode *inode2; + + /** File used in the request (or NULL) */ + struct file *file; +}; + +/** + * A Fuse connection. + * + * This structure is created, when the filesystem is mounted, and is + * destroyed, when the client device is closed and the filesystem is + * unmounted. + */ +struct fuse_conn { + /** Reference count */ + int count; + + /** The user id for this mount */ + uid_t user_id; + + /** The group id for this mount */ + gid_t group_id; + + /** The fuse mount flags for this mount */ + unsigned flags; + + /** Maximum read size */ + unsigned max_read; + + /** Maximum write size */ + unsigned max_write; + + /** Readers of the connection are waiting on this */ + wait_queue_head_t waitq; + + /** The list of pending requests */ + struct list_head pending; + + /** The list of requests being processed */ + struct list_head processing; + + /** Requests put in the background (RELEASE or any other + interrupted request) */ + struct list_head background; + + /** Controls the maximum number of outstanding requests */ + struct semaphore outstanding_sem; + + /** This counts the number of outstanding requests if + outstanding_sem would go negative */ + unsigned outstanding_debt; + + /** RW semaphore for exclusion with fuse_put_super() */ + struct rw_semaphore sbput_sem; + + /** The list of unused requests */ + struct list_head unused_list; + + /** The next unique request id */ + u64 reqctr; + + /** Mount is active */ + unsigned mounted : 1; + + /** Connection established */ + unsigned connected : 1; + + /** Connection failed (version mismatch) */ + unsigned conn_error : 1; + + /** Is fsync not implemented by fs? */ + unsigned no_fsync : 1; + + /** Is fsyncdir not implemented by fs? */ + unsigned no_fsyncdir : 1; + + /** Is flush not implemented by fs? */ + unsigned no_flush : 1; + + /** Is setxattr not implemented by fs? */ + unsigned no_setxattr : 1; + + /** Is getxattr not implemented by fs? */ + unsigned no_getxattr : 1; + + /** Is listxattr not implemented by fs? */ + unsigned no_listxattr : 1; + + /** Is removexattr not implemented by fs? */ + unsigned no_removexattr : 1; + + /** Backing dev info */ + struct backing_dev_info bdi; +}; + +static inline struct fuse_conn **get_fuse_conn_super_p(struct super_block *sb) +{ + return (struct fuse_conn **) &sb->s_fs_info; +} + +static inline struct fuse_conn *get_fuse_conn_super(struct super_block *sb) +{ + return *get_fuse_conn_super_p(sb); +} + +static inline struct fuse_conn *get_fuse_conn(struct inode *inode) +{ + return get_fuse_conn_super(inode->i_sb); +} + +static inline struct fuse_inode *get_fuse_inode(struct inode *inode) +{ + return container_of(inode, struct fuse_inode, inode); +} + +static inline u64 get_node_id(struct inode *inode) +{ + return get_fuse_inode(inode)->nodeid; +} + +/** Device operations */ +extern struct file_operations fuse_dev_operations; + +/** + * This is the single global spinlock which protects FUSE's structures + * + * The following data is protected by this lock: + * + * - the private_data field of the device file + * - the s_fs_info field of the super block + * - unused_list, pending, processing lists in fuse_conn + * - background list in fuse_conn + * - the unique request ID counter reqctr in fuse_conn + * - the sb (super_block) field in fuse_conn + * - the file (device file) field in fuse_conn + */ +extern spinlock_t fuse_lock; + +/** + * Get a filled in inode + */ +struct inode *fuse_iget(struct super_block *sb, unsigned long nodeid, + int generation, struct fuse_attr *attr); + +/** + * Send FORGET command + */ +void fuse_send_forget(struct fuse_conn *fc, struct fuse_req *req, + unsigned long nodeid, u64 nlookup); + +/** + * Send READ or READDIR request + */ +size_t fuse_send_read_common(struct fuse_req *req, struct file *file, + struct inode *inode, loff_t pos, size_t count, + int isdir); + +/** + * Send OPEN or OPENDIR request + */ +int fuse_open_common(struct inode *inode, struct file *file, int isdir); + +/** + * Send RELEASE or RELEASEDIR request + */ +int fuse_release_common(struct inode *inode, struct file *file, int isdir); + +/** + * Send FSYNC or FSYNCDIR request + */ +int fuse_fsync_common(struct file *file, struct dentry *de, int datasync, + int isdir); + +/** + * Initialise file operations on a regular file + */ +void fuse_init_file_inode(struct inode *inode); + +/** + * Initialise inode operations on regular files and special files + */ +void fuse_init_common(struct inode *inode); + +/** + * Initialise inode and file operations on a directory + */ +void fuse_init_dir(struct inode *inode); + +/** + * Initialise inode operations on a symlink + */ +void fuse_init_symlink(struct inode *inode); + +/** + * Change attributes of an inode + */ +void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr); + +/** + * Check if the connection can be released, and if yes, then free the + * connection structure + */ +void fuse_release_conn(struct fuse_conn *fc); + +/** + * Initialize the client device + */ +int fuse_dev_init(void); + +/** + * Cleanup the client device + */ +void fuse_dev_cleanup(void); + +/** + * Allocate a request + */ +struct fuse_req *fuse_request_alloc(void); + +/** + * Free a request + */ +void fuse_request_free(struct fuse_req *req); + +/** + * Reinitialize a request, the preallocated flag is left unmodified + */ +void fuse_reset_request(struct fuse_req *req); + +/** + * Reserve a preallocated request + */ +struct fuse_req *fuse_get_request(struct fuse_conn *fc); + +/** + * Decrement reference count of a request. If count goes to zero put + * on unused list (preallocated) or free reqest (not preallocated). + */ +void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req); + +/** + * Send a request (synchronous) + */ +void request_send(struct fuse_conn *fc, struct fuse_req *req); + +/** + * Send a request with no reply + */ +void request_send_noreply(struct fuse_conn *fc, struct fuse_req *req); + +/** + * Send a request in the background + */ +void request_send_background(struct fuse_conn *fc, struct fuse_req *req); + +/** + * Release inodes and file assiciated with background request + */ +void fuse_release_background(struct fuse_req *req); + +/** + * Get the attributes of a file + */ +int fuse_do_getattr(struct inode *inode); + +/** + * Invalidate inode attributes + */ +void fuse_invalidate_attr(struct inode *inode); + +/** + * Send the INIT message + */ +void fuse_send_init(struct fuse_conn *fc); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c new file mode 100644 index 00000000000..e69a546844d --- /dev/null +++ b/fs/fuse/inode.c @@ -0,0 +1,591 @@ +/* + FUSE: Filesystem in Userspace + Copyright (C) 2001-2005 Miklos Szeredi <miklos@szeredi.hu> + + This program can be distributed under the terms of the GNU GPL. + See the file COPYING. +*/ + +#include "fuse_i.h" + +#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> + +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; + +#define FUSE_SUPER_MAGIC 0x65735546 + +struct fuse_mount_data { + int fd; + unsigned rootmode; + unsigned user_id; + unsigned group_id; + unsigned fd_present : 1; + unsigned rootmode_present : 1; + unsigned user_id_present : 1; + unsigned group_id_present : 1; + unsigned flags; + unsigned max_read; +}; + +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); + if (!inode) + return NULL; + + fi = get_fuse_inode(inode); + fi->i_time = jiffies - 1; + fi->nodeid = 0; + fi->nlookup = 0; + fi->forget_req = fuse_request_alloc(); + if (!fi->forget_req) { + kmem_cache_free(fuse_inode_cachep, inode); + return NULL; + } + + return inode; +} + +static void fuse_destroy_inode(struct inode *inode) +{ + struct fuse_inode *fi = get_fuse_inode(inode); + if (fi->forget_req) + fuse_request_free(fi->forget_req); + kmem_cache_free(fuse_inode_cachep, inode); +} + +static void fuse_read_inode(struct inode *inode) +{ + /* No op */ +} + +void fuse_send_forget(struct fuse_conn *fc, struct fuse_req *req, + unsigned long nodeid, u64 nlookup) +{ + struct fuse_forget_in *inarg = &req->misc.forget_in; + inarg->nlookup = nlookup; + req->in.h.opcode = FUSE_FORGET; + req->in.h.nodeid = nodeid; + req->in.numargs = 1; + req->in.args[0].size = sizeof(struct fuse_forget_in); + req->in.args[0].value = inarg; + request_send_noreply(fc, req); +} + +static void fuse_clear_inode(struct inode *inode) +{ + if (inode->i_sb->s_flags & MS_ACTIVE) { + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_inode *fi = get_fuse_inode(inode); + fuse_send_forget(fc, fi->forget_req, fi->nodeid, fi->nlookup); + fi->forget_req = NULL; + } +} + +void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr) +{ + if (S_ISREG(inode->i_mode) && i_size_read(inode) != attr->size) + invalidate_inode_pages(inode->i_mapping); + + inode->i_ino = attr->ino; + inode->i_mode = (inode->i_mode & S_IFMT) + (attr->mode & 07777); + inode->i_nlink = attr->nlink; + inode->i_uid = attr->uid; + inode->i_gid = attr->gid; + i_size_write(inode, attr->size); + inode->i_blksize = PAGE_CACHE_SIZE; + inode->i_blocks = attr->blocks; + inode->i_atime.tv_sec = attr->atime; + inode->i_atime.tv_nsec = attr->atimensec; + inode->i_mtime.tv_sec = attr->mtime; + inode->i_mtime.tv_nsec = attr->mtimensec; + inode->i_ctime.tv_sec = attr->ctime; + inode->i_ctime.tv_nsec = attr->ctimensec; +} + +static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr) +{ + inode->i_mode = attr->mode & S_IFMT; + i_size_write(inode, attr->size); + if (S_ISREG(inode->i_mode)) { + fuse_init_common(inode); + fuse_init_file_inode(inode); + } else if (S_ISDIR(inode->i_mode)) + fuse_init_dir(inode); + else if (S_ISLNK(inode->i_mode)) + fuse_init_symlink(inode); + else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || + S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { + fuse_init_common(inode); + init_special_inode(inode, inode->i_mode, + new_decode_dev(attr->rdev)); + } else { + /* Don't let user create weird files */ + inode->i_mode = S_IFREG; + fuse_init_common(inode); + fuse_init_file_inode(inode); + } +} + +static int fuse_inode_eq(struct inode *inode, void *_nodeidp) +{ + unsigned long nodeid = *(unsigned long *) _nodeidp; + if (get_node_id(inode) == nodeid) + return 1; + else + return 0; +} + +static int fuse_inode_set(struct inode *inode, void *_nodeidp) +{ + unsigned long nodeid = *(unsigned long *) _nodeidp; + get_fuse_inode(inode)->nodeid = nodeid; + return 0; +} + +struct inode *fuse_iget(struct super_block *sb, unsigned long nodeid, + int generation, struct fuse_attr *attr) +{ + 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); + if (!inode) + return NULL; + + if ((inode->i_state & I_NEW)) { + inode->i_flags |= S_NOATIME|S_NOCMTIME; + inode->i_generation = generation; + inode->i_data.backing_dev_info = &fc->bdi; + 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); + fi->nlookup ++; + fuse_change_attributes(inode, attr); + return inode; +} + +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; + fc->user_id = 0; + fc->group_id = 0; + fc->flags = 0; + /* Flush all readers on this fs */ + wake_up_all(&fc->waitq); + up_write(&fc->sbput_sem); + fuse_release_conn(fc); + spin_unlock(&fuse_lock); +} + +static void convert_fuse_statfs(struct kstatfs *stbuf, struct fuse_kstatfs *attr) +{ + stbuf->f_type = FUSE_SUPER_MAGIC; + stbuf->f_bsize = attr->bsize; + stbuf->f_blocks = attr->blocks; + stbuf->f_bfree = attr->bfree; + stbuf->f_bavail = attr->bavail; + stbuf->f_files = attr->files; + stbuf->f_ffree = attr->ffree; + stbuf->f_namelen = attr->namelen; + /* fsid is left zero */ +} + +static int fuse_statfs(struct super_block *sb, struct kstatfs *buf) +{ + 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->in.numargs = 0; + req->in.h.opcode = FUSE_STATFS; + req->out.numargs = 1; + req->out.args[0].size = sizeof(outarg); + req->out.args[0].value = &outarg; + request_send(fc, req); + err = req->out.h.error; + if (!err) + convert_fuse_statfs(buf, &outarg.st); + fuse_put_request(fc, req); + return err; +} + +enum { + OPT_FD, + OPT_ROOTMODE, + OPT_USER_ID, + OPT_GROUP_ID, + OPT_DEFAULT_PERMISSIONS, + OPT_ALLOW_OTHER, + OPT_MAX_READ, + OPT_ERR +}; + +static match_table_t tokens = { + {OPT_FD, "fd=%u"}, + {OPT_ROOTMODE, "rootmode=%o"}, + {OPT_USER_ID, "user_id=%u"}, + {OPT_GROUP_ID, "group_id=%u"}, + {OPT_DEFAULT_PERMISSIONS, "default_permissions"}, + {OPT_ALLOW_OTHER, "allow_other"}, + {OPT_MAX_READ, "max_read=%u"}, + {OPT_ERR, NULL} +}; + +static int parse_fuse_opt(char *opt, struct fuse_mount_data *d) +{ + char *p; + memset(d, 0, sizeof(struct fuse_mount_data)); + d->max_read = ~0; + + while ((p = strsep(&opt, ",")) != NULL) { + int token; + int value; + substring_t args[MAX_OPT_ARGS]; + if (!*p) + continue; + + token = match_token(p, tokens, args); + switch (token) { + case OPT_FD: + if (match_int(&args[0], &value)) + return 0; + d->fd = value; + d->fd_present = 1; + break; + + case OPT_ROOTMODE: + if (match_octal(&args[0], &value)) + return 0; + d->rootmode = value; + d->rootmode_present = 1; + break; + + case OPT_USER_ID: + if (match_int(&args[0], &value)) + return 0; + d->user_id = value; + d->user_id_present = 1; + break; + + case OPT_GROUP_ID: + if (match_int(&args[0], &value)) + return 0; + d->group_id = value; + d->group_id_present = 1; + break; + + case OPT_DEFAULT_PERMISSIONS: + d->flags |= FUSE_DEFAULT_PERMISSIONS; + break; + + case OPT_ALLOW_OTHER: + d->flags |= FUSE_ALLOW_OTHER; + break; + + case OPT_MAX_READ: + if (match_int(&args[0], &value)) + return 0; + d->max_read = value; + break; + + default: + return 0; + } + } + + if (!d->fd_present || !d->rootmode_present || + !d->user_id_present || !d->group_id_present) + return 0; + + return 1; +} + +static int fuse_show_options(struct seq_file *m, struct vfsmount *mnt) +{ + struct fuse_conn *fc = get_fuse_conn_super(mnt->mnt_sb); + + seq_printf(m, ",user_id=%u", fc->user_id); + seq_printf(m, ",group_id=%u", fc->group_id); + if (fc->flags & FUSE_DEFAULT_PERMISSIONS) + seq_puts(m, ",default_permissions"); + if (fc->flags & FUSE_ALLOW_OTHER) + seq_puts(m, ",allow_other"); + if (fc->max_read != ~0) + seq_printf(m, ",max_read=%u", fc->max_read); + return 0; +} + +static void free_conn(struct fuse_conn *fc) +{ + 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); +} + +/* Must be called with the fuse lock held */ +void fuse_release_conn(struct fuse_conn *fc) +{ + fc->count--; + if (!fc->count) + free_conn(fc); +} + +static struct fuse_conn *new_conn(void) +{ + struct fuse_conn *fc; + + fc = kmalloc(sizeof(*fc), GFP_KERNEL); + if (fc != NULL) { + int i; + memset(fc, 0, sizeof(*fc)); + init_waitqueue_head(&fc->waitq); + INIT_LIST_HEAD(&fc->pending); + INIT_LIST_HEAD(&fc->processing); + INIT_LIST_HEAD(&fc->unused_list); + INIT_LIST_HEAD(&fc->background); + sema_init(&fc->outstanding_sem, 0); + init_rwsem(&fc->sbput_sem); + for (i = 0; i < FUSE_MAX_OUTSTANDING; i++) { + struct fuse_req *req = fuse_request_alloc(); + if (!req) { + free_conn(fc); + 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; + } + return fc; +} + +static struct fuse_conn *get_conn(struct file *file, struct super_block *sb) +{ + struct fuse_conn *fc; + + if (file->f_op != &fuse_dev_operations) + return ERR_PTR(-EINVAL); + fc = new_conn(); + if (fc == NULL) + return ERR_PTR(-ENOMEM); + spin_lock(&fuse_lock); + if (file->private_data) { + free_conn(fc); + fc = ERR_PTR(-EINVAL); + } else { + file->private_data = fc; + *get_fuse_conn_super_p(sb) = fc; + fc->mounted = 1; + fc->connected = 1; + fc->count = 2; + } + spin_unlock(&fuse_lock); + return fc; +} + +static struct inode *get_root_inode(struct super_block *sb, unsigned mode) +{ + struct fuse_attr attr; + memset(&attr, 0, sizeof(attr)); + + attr.mode = mode; + attr.ino = FUSE_ROOT_ID; + return fuse_iget(sb, 1, 0, &attr); +} + +static struct super_operations fuse_super_operations = { + .alloc_inode = fuse_alloc_inode, + .destroy_inode = fuse_destroy_inode, + .read_inode = fuse_read_inode, + .clear_inode = fuse_clear_inode, + .put_super = fuse_put_super, + .statfs = fuse_statfs, + .show_options = fuse_show_options, +}; + +static int fuse_fill_super(struct super_block *sb, void *data, int silent) +{ + struct fuse_conn *fc; + struct inode *root; + struct fuse_mount_data d; + struct file *file; + int err; + + if (!parse_fuse_opt((char *) data, &d)) + return -EINVAL; + + 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; + + file = fget(d.fd); + if (!file) + return -EINVAL; + + fc = get_conn(file, sb); + fput(file); + if (IS_ERR(fc)) + return PTR_ERR(fc); + + fc->flags = d.flags; + fc->user_id = d.user_id; + fc->group_id = d.group_id; + fc->max_read = d.max_read; + if (fc->max_read / PAGE_CACHE_SIZE < fc->bdi.ra_pages) + fc->bdi.ra_pages = fc->max_read / PAGE_CACHE_SIZE; + fc->max_write = FUSE_MAX_IN / 2; + + err = -ENOMEM; + root = get_root_inode(sb, d.rootmode); + if (root == NULL) + goto err; + + sb->s_root = d_alloc_root(root); + if (!sb->s_root) { + iput(root); + goto err; + } + fuse_send_init(fc); + return 0; + + err: + spin_lock(&fuse_lock); + fuse_release_conn(fc); + spin_unlock(&fuse_lock); + return err; +} + +static struct super_block *fuse_get_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, + void *raw_data) +{ + return get_sb_nodev(fs_type, flags, raw_data, fuse_fill_super); +} + +static struct file_system_type fuse_fs_type = { + .owner = THIS_MODULE, + .name = "fuse", + .get_sb = fuse_get_sb, + .kill_sb = kill_anon_super, +}; + +static void fuse_inode_init_once(void *foo, kmem_cache_t *cachep, + unsigned long flags) +{ + struct inode * inode = foo; + + if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) == + SLAB_CTOR_CONSTRUCTOR) + inode_init_once(inode); +} + +static int __init fuse_fs_init(void) +{ + int err; + + 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; + } + } + + return err; +} + +static void fuse_fs_cleanup(void) +{ + unregister_filesystem(&fuse_fs_type); + kmem_cache_destroy(fuse_inode_cachep); +} + +static int __init fuse_init(void) +{ + int res; + + printk("fuse init (API version %i.%i)\n", + FUSE_KERNEL_VERSION, FUSE_KERNEL_MINOR_VERSION); + + spin_lock_init(&fuse_lock); + res = fuse_fs_init(); + if (res) + goto err; + + res = fuse_dev_init(); + if (res) + goto err_fs_cleanup; + + return 0; + + err_fs_cleanup: + fuse_fs_cleanup(); + err: + return res; +} + +static void __exit fuse_exit(void) +{ + printk(KERN_DEBUG "fuse exit\n"); + + fuse_fs_cleanup(); + fuse_dev_cleanup(); +} + +module_init(fuse_init); +module_exit(fuse_exit); |