+2006-01-16 Miklos Szeredi <miklos@szeredi.hu>
+
+ * Added (again) asynchronous readpages support
+
+ * Each connection now shows up under /sys/fs/fuse/connections
+
+ * Connection attributes exported to sysfs: 'waiting' number of
+ waiting requests; 'abort' abort the connection
+
+ * Connection may be aborted through either the sysfs interface or
+ with 'umount -f mountpoint'
+
+ *
+
2006-01-14 Miklos Szeredi <miklos@szeredi.hu>
* Released 2.5.0
* Clearing ->connected or ->mounted connection flags could race
with setting other bitfields not protected with a lock
-
+
2006-01-10 Miklos Szeredi <miklos@szeredi.hu>
* kernel: add necessary compile flags for 2.4.X/x86_64.
The default is infinite. Note that the size of read requests is
limited anyway to 32 pages (which is 128kbyte on i386).
+Sysfs
+~~~~~
+
+FUSE sets up the following hierarchy in sysfs:
+
+ /sys/fs/fuse/connections/N/
+
+where N is an increasing number allocated to each new connection.
+
+For each connection the following attributes are defined:
+
+ 'waiting'
+
+ The number of requests which are waiting to be transfered to
+ userspace or being processed by the filesystem daemon. If there is
+ no filesystem activity and 'waiting' is non-zero, then the
+ filesystem is hung or deadlocked.
+
+ 'abort'
+
+ Writing anything into this file will abort the filesystem
+ connection. This means that all waiting requests will be aborted an
+ error returned for all aborted and new requests.
+
+Only a privileged user may read or write these attributes.
+
+Aborting a filesystem connection
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+It is possible to get into certain situations where the filesystem is
+not responding. Reasons for this may be:
+
+ a) Broken userspace filesystem implementation
+
+ b) Network connection down
+
+ c) Accidental deadlock
+
+ d) Malicious deadlock
+
+(For more on c) and d) see later sections)
+
+In either of these cases it may be useful to abort the connection to
+the filesystem. There are several ways to do this:
+
+ - Kill the filesystem daemon. Works in case of a) and b)
+
+ - Kill the filesystem daemon and all users of the filesystem. Works
+ in all cases except some malicious deadlocks
+
+ - Use forced umount (umount -f). Works in all cases but only if
+ filesystem is still attached (it hasn't been lazy unmounted)
+
+ - Abort filesystem through the sysfs interface. Most powerful
+ method, always works.
+
How do non-privileged mounts work?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
when the copy is taking place, and interruption is delayed until
this flag is unset.
+Scenario 3 - Tricky deadlock with asynchronous read
+---------------------------------------------------
+
+The same situation as above, except thread-1 will wait on page lock
+and hence it will be uninterruptible as well. The solution is to
+abort the connection with forced umount (if mount is attached) or
+through the abort attribute in sysfs.
fi
if test "$checkmodule" = yes; then
AC_MSG_CHECKING([if FUSE module is from official kernel])
- if fgrep -q "fuse distribution version: " /lib/modules/${runver}/kernel/fs/fuse/fuse.ko 2> /dev/null; then
+ if test ! -f /lib/modules/${runver}/kernel/fs/fuse/fuse.ko; then
+ AC_MSG_RESULT([no])
+ elif fgrep -q "fuse distribution version: " /lib/modules/${runver}/kernel/fs/fuse/fuse.ko 2> /dev/null; then
AC_MSG_RESULT([no])
else
AC_MSG_RESULT([yes])
else
AC_MSG_RESULT([no])
fi
+ AC_MSG_CHECKING([if kernel defines kzalloc function])
+ if egrep -qw "kzalloc" $kernelsrc/include/linux/slab.h; then
+ AC_DEFINE(HAVE_KZALLOC, 1, [kzalloc() is defined])
+ AC_MSG_RESULT([yes])
+ else
+ AC_MSG_RESULT([no])
+ fi
+
+ AC_MSG_CHECKING([if kernel defines fs_subsys])
+ if egrep -qw "fs_subsys" $kernelsrc/include/linux/fs.h; then
+ AC_DEFINE(HAVE_FS_SUBSYS, 1, [fs_subsys is defined])
+ AC_MSG_RESULT([yes])
+ else
+ AC_MSG_RESULT([no])
+ fi
AC_MSG_CHECKING([whether lookup_instantiate_filp is defined])
if test -f $kernelsrc/include/linux/namei.h && egrep -q "lookup_instantiate_filp" $kernelsrc/include/linux/namei.h; then
static kmem_cache_t *fuse_req_cachep;
-static inline struct fuse_conn *fuse_get_conn(struct file *file)
+static 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)
+ if (fc && !fc->connected)
fc = NULL;
spin_unlock(&fuse_lock);
return fc;
}
-static inline void fuse_request_init(struct fuse_req *req)
+static void fuse_request_init(struct fuse_req *req)
{
memset(req, 0, sizeof(*req));
INIT_LIST_HEAD(&req->list);
}
#ifdef KERNEL_2_6
-static inline void block_sigs(sigset_t *oldset)
+static void block_sigs(sigset_t *oldset)
{
sigset_t mask;
sigprocmask(SIG_BLOCK, &mask, oldset);
}
-static inline void restore_sigs(sigset_t *oldset)
+static void restore_sigs(sigset_t *oldset)
{
sigprocmask(SIG_SETMASK, oldset, NULL);
}
#else
#ifdef HAVE_RECALC_SIGPENDING_TSK
-static inline void block_sigs(sigset_t *oldset)
+static void block_sigs(sigset_t *oldset)
{
spin_lock_irq(¤t->sighand->siglock);
*oldset = current->blocked;
spin_unlock_irq(¤t->sighand->siglock);
}
-static inline void restore_sigs(sigset_t *oldset)
+static void restore_sigs(sigset_t *oldset)
{
spin_lock_irq(¤t->sighand->siglock);
current->blocked = *oldset;
spin_unlock_irq(¤t->sighand->siglock);
}
#else
-static inline void block_sigs(sigset_t *oldset)
+static void block_sigs(sigset_t *oldset)
{
spin_lock_irq(¤t->sigmask_lock);
*oldset = current->blocked;
spin_unlock_irq(¤t->sigmask_lock);
}
-static inline void restore_sigs(sigset_t *oldset)
+static void restore_sigs(sigset_t *oldset)
{
spin_lock_irq(¤t->sigmask_lock);
current->blocked = *oldset;
int intr;
sigset_t oldset;
+ atomic_inc(&fc->num_waiting);
block_sigs(&oldset);
intr = down_interruptible(&fc->outstanding_sem);
restore_sigs(&oldset);
- return intr ? NULL : do_get_request(fc);
+ if (intr) {
+ atomic_dec(&fc->num_waiting);
+ return NULL;
+ }
+ return do_get_request(fc);
}
static void fuse_putback_request(struct fuse_conn *fc, struct fuse_req *req)
{
spin_lock(&fuse_lock);
- if (req->preallocated)
+ if (req->preallocated) {
+ atomic_dec(&fc->num_waiting);
list_add(&req->list, &fc->unused_list);
- else
+ } else
fuse_request_free(req);
/* If we are in debt decrease that first */
spin_unlock(&fuse_lock);
}
-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 (arg->major != FUSE_KERNEL_VERSION)
- fc->conn_error = 1;
- else {
- fc->minor = arg->minor;
- fc->max_write = arg->minor < 5 ? 4096 : arg->max_write;
- }
-
- /* 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);
-}
-
/*
* 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
- * occurred during communication with userspace, or the device file was
- * closed. It decreases the reference count for the request. In case
- * of a background request the reference 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
+ * occurred during communication with userspace, or the device file
+ * was closed. In case of a background request the reference to the
+ * stored objects are released. The requester thread is woken up (if
+ * still waiting), the 'end' callback is called if given, else the
+ * reference to the request is released
*
* Called with fuse_lock, unlocks it
*/
static void request_end(struct fuse_conn *fc, struct fuse_req *req)
{
- req->finished = 1;
+ void (*end) (struct fuse_conn *, struct fuse_req *) = req->end;
+ req->end = NULL;
+ list_del(&req->list);
+ req->state = FUSE_REQ_FINISHED;
spin_unlock(&fuse_lock);
if (req->background) {
down_read(&fc->sbput_sem);
up_read(&fc->sbput_sem);
}
wake_up(&req->waitq);
- if (req->in.h.opcode == FUSE_INIT)
- process_init_reply(fc, req);
- else if (req->in.h.opcode == FUSE_RELEASE && req->inode == NULL) {
- /* Special case for failed iget in CREATE */
- u64 nodeid = req->in.h.nodeid;
- fuse_reset_request(req);
- fuse_send_forget(fc, req, nodeid, 1);
- return;
- }
- fuse_put_request(fc, req);
+ if (end)
+ end(fc, req);
+ else
+ fuse_put_request(fc, req);
}
/*
spin_unlock(&fuse_lock);
block_sigs(&oldset);
- wait_event_interruptible(req->waitq, req->finished);
+ wait_event_interruptible(req->waitq, req->state == FUSE_REQ_FINISHED);
restore_sigs(&oldset);
spin_lock(&fuse_lock);
- if (req->finished)
+ if (req->state == FUSE_REQ_FINISHED && !req->interrupted)
return;
- req->out.h.error = -EINTR;
- req->interrupted = 1;
+ if (!req->interrupted) {
+ 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
wait_event(req->waitq, !req->locked);
spin_lock(&fuse_lock);
}
- if (!req->sent && !list_empty(&req->list)) {
+ if (req->state == FUSE_REQ_PENDING) {
list_del(&req->list);
__fuse_put_request(req);
- } else if (!req->finished && req->sent)
+ } else if (req->state == FUSE_REQ_SENT)
background_request(fc, req);
}
fc->outstanding_debt++;
}
list_add_tail(&req->list, &fc->pending);
+ req->state = FUSE_REQ_PENDING;
wake_up(&fc->waitq);
}
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 *arg = &req->misc.init_in;
- 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;
- /* Variable length arguement used for backward compatibility
- with interface version < 7.5. Rest of init_out is zeroed
- by do_get_request(), so a short reply is not a problem */
- req->out.argvar = 1;
- req->out.args[0].size = sizeof(struct fuse_init_out);
- req->out.args[0].value = &req->misc.init_out;
- 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)
+static int lock_request(struct fuse_req *req)
{
int err = 0;
if (req) {
* requester thread is currently waiting for it to be unlocked, so
* wake it up.
*/
-static inline void unlock_request(struct fuse_req *req)
+static void unlock_request(struct fuse_req *req)
{
if (req) {
spin_lock(&fuse_lock);
}
/* Unmap and put previous page of userspace buffer */
-static inline void fuse_copy_finish(struct fuse_copy_state *cs)
+static void fuse_copy_finish(struct fuse_copy_state *cs)
{
if (cs->mapaddr) {
kunmap_atomic(cs->mapaddr, KM_USER0);
}
/* 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)
+static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size)
{
unsigned ncpy = min(*size, cs->len);
if (val) {
* 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)
+static 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);
DECLARE_WAITQUEUE(wait, current);
add_wait_queue_exclusive(&fc->waitq, &wait);
- while (fc->mounted && list_empty(&fc->pending)) {
+ while (fc->connected && list_empty(&fc->pending)) {
set_current_state(TASK_INTERRUPTIBLE);
if (signal_pending(current))
break;
}
#ifndef KERNEL_2_6
-static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs)
+static size_t iov_length(const struct iovec *iov, unsigned long nr_segs)
{
unsigned long seg;
size_t ret = 0;
goto err_unlock;
request_wait(fc);
err = -ENODEV;
- if (!fc->mounted)
+ if (!fc->connected)
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);
+ req->state = FUSE_REQ_READING;
+ list_move(&req->list, &fc->io);
in = &req->in;
reqsize = in->h.len;
if (!req->isreply)
request_end(fc, req);
else {
- req->sent = 1;
- list_add_tail(&req->list, &fc->processing);
+ req->state = FUSE_REQ_SENT;
+ list_move_tail(&req->list, &fc->processing);
spin_unlock(&fuse_lock);
}
return reqsize;
goto err_finish;
spin_lock(&fuse_lock);
+ err = -ENOENT;
+ if (!fc->connected)
+ goto err_unlock;
+
req = request_find(fc, oh.unique);
err = -EINVAL;
if (!req)
goto err_unlock;
- list_del_init(&req->list);
if (req->interrupted) {
spin_unlock(&fuse_lock);
fuse_copy_finish(&cs);
request_end(fc, req);
return -ENOENT;
}
+ list_move(&req->list, &fc->io);
req->out.h = oh;
req->locked = 1;
cs.req = req;
return mask;
}
-/* Abort all requests on the given list (pending or processing) */
+/*
+ * Abort all requests on the given list (pending or processing)
+ *
+ * This function releases and reacquires fuse_lock
+ */
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);
}
}
+/*
+ * Abort requests under I/O
+ *
+ * The requests are set to interrupted and finished, and the request
+ * waiter is woken up. This will make request_wait_answer() wait
+ * until the request is unlocked and then return.
+ *
+ * If the request is asynchronous, then the end function needs to be
+ * called after waiting for the request to be unlocked (if it was
+ * locked).
+ */
+static void end_io_requests(struct fuse_conn *fc)
+{
+ while (!list_empty(&fc->io)) {
+ struct fuse_req *req =
+ list_entry(fc->io.next, struct fuse_req, list);
+ void (*end) (struct fuse_conn *, struct fuse_req *) = req->end;
+
+ req->interrupted = 1;
+ req->out.h.error = -ECONNABORTED;
+ req->state = FUSE_REQ_FINISHED;
+ list_del_init(&req->list);
+ wake_up(&req->waitq);
+ if (end) {
+ req->end = NULL;
+ /* The end function will consume this reference */
+ __fuse_get_request(req);
+ spin_unlock(&fuse_lock);
+ wait_event(req->waitq, !req->locked);
+ end(fc, req);
+ spin_lock(&fuse_lock);
+ }
+ }
+}
+
+/*
+ * Abort all requests.
+ *
+ * Emergency exit in case of a malicious or accidental deadlock, or
+ * just a hung filesystem.
+ *
+ * The same effect is usually achievable through killing the
+ * filesystem daemon and all users of the filesystem. The exception
+ * is the combination of an asynchronous request and the tricky
+ * deadlock (see Documentation/filesystems/fuse.txt).
+ *
+ * During the aborting, progression of requests from the pending and
+ * processing lists onto the io list, and progression of new requests
+ * onto the pending list is prevented by req->connected being false.
+ *
+ * Progression of requests under I/O to the processing list is
+ * prevented by the req->interrupted flag being true for these
+ * requests. For this reason requests on the io list must be aborted
+ * first.
+ */
+void fuse_abort_conn(struct fuse_conn *fc)
+{
+ spin_lock(&fuse_lock);
+ if (fc->connected) {
+ fc->connected = 0;
+ end_io_requests(fc);
+ end_requests(fc, &fc->pending);
+ end_requests(fc, &fc->processing);
+ wake_up_all(&fc->waitq);
+ }
+ spin_unlock(&fuse_lock);
+}
+
static int fuse_dev_release(struct inode *inode, struct file *file)
{
struct fuse_conn *fc;
fc->connected = 0;
end_requests(fc, &fc->pending);
end_requests(fc, &fc->processing);
- fuse_release_conn(fc);
}
spin_unlock(&fuse_lock);
+ if (fc)
+ kobject_put(&fc->kobj);
+
return 0;
}
*/
/*
- * Calcualte the time in jiffies until a dentry/attributes are valid
+ * Calculate the time in jiffies until a dentry/attributes are valid
*/
-static inline unsigned long time_to_jiffies(unsigned long sec,
- unsigned long nsec)
+static unsigned long time_to_jiffies(unsigned long sec, unsigned long nsec)
{
struct timespec ts = {sec, nsec};
return jiffies + timespec_to_jiffies(&ts);
return 0;
}
-static inline int invalid_nodeid(u64 nodeid)
+static int invalid_nodeid(u64 nodeid)
{
return !nodeid || nodeid == FUSE_ROOT_ID;
}
#endif
};
-static inline int valid_mode(int m)
+static int valid_mode(int m)
{
return S_ISREG(m) || S_ISDIR(m) || S_ISLNK(m) || S_ISCHR(m) ||
S_ISBLK(m) || S_ISFIFO(m) || S_ISSOCK(m);
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;
}
req->num_pages = 1;
req->pages[0] = page;
- nbytes = fuse_send_readdir(req, file, inode, file->f_pos, PAGE_SIZE);
+ fuse_read_fill(req, file, inode, file->f_pos, PAGE_SIZE, FUSE_READDIR);
+ request_send(fc, req);
+ nbytes = req->out.args[0].size;
err = req->out.h.error;
fuse_put_request(fc, req);
if (!err)
return err;
}
+/* Special case for failed iget in CREATE */
+static void fuse_release_end(struct fuse_conn *fc, struct fuse_req *req)
+{
+ u64 nodeid = req->in.h.nodeid;
+ fuse_reset_request(req);
+ fuse_send_forget(fc, req, nodeid, 1);
+}
+
void fuse_send_release(struct fuse_conn *fc, struct fuse_file *ff,
u64 nodeid, struct inode *inode, int flags, int isdir)
{
req->in.args[0].size = sizeof(struct fuse_release_in);
req->in.args[0].value = inarg;
request_send_background(fc, req);
+ if (!inode)
+ req->end = fuse_release_end;
kfree(ff);
}
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)
+void fuse_read_fill(struct fuse_req *req, struct file *file,
+ struct inode *inode, loff_t pos, size_t count, int opcode)
{
- struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_file *ff = file->private_data;
- struct fuse_read_in inarg;
+ struct fuse_read_in *inarg = &req->misc.read_in;
- 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;
+ inarg->fh = ff->fh;
+ inarg->offset = pos;
+ inarg->size = count;
+ req->in.h.opcode = opcode;
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->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)
+static 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);
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ fuse_read_fill(req, file, inode, pos, count, FUSE_READ);
+ request_send(fc, req);
+ return req->out.args[0].size;
}
static int fuse_readpage(struct file *file, struct page *page)
}
#ifdef KERNEL_2_6
-static int fuse_send_readpages(struct fuse_req *req, struct file *file,
- struct inode *inode)
+static void fuse_readpages_end(struct fuse_conn *fc, struct fuse_req *req)
{
- loff_t pos = page_offset(req->pages[0]);
- size_t count = req->num_pages << PAGE_CACHE_SHIFT;
- unsigned i;
- req->out.page_zeroing = 1;
- fuse_send_read(req, file, inode, pos, count);
+ int i;
+
+ fuse_invalidate_attr(req->pages[0]->mapping->host); /* atime changed */
+
for (i = 0; i < req->num_pages; i++) {
struct page *page = req->pages[i];
if (!req->out.h.error)
SetPageUptodate(page);
+ else
+ SetPageError(page);
unlock_page(page);
}
- return req->out.h.error;
+ fuse_put_request(fc, req);
+}
+
+static void fuse_send_readpages(struct fuse_req *req, struct file *file,
+ struct inode *inode)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ loff_t pos = page_offset(req->pages[0]);
+ size_t count = req->num_pages << PAGE_CACHE_SHIFT;
+ req->out.page_zeroing = 1;
+ req->end = fuse_readpages_end;
+ fuse_read_fill(req, file, inode, pos, count, FUSE_READ);
+ request_send_background(fc, req);
}
struct fuse_readpages_data {
(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) {
+ fuse_send_readpages(req, data->file, inode);
+ data->req = req = fuse_get_request(fc);
+ if (!req) {
unlock_page(page);
- return err;
+ return -EINTR;
}
- fuse_reset_request(req);
}
req->pages[req->num_pages] = page;
req->num_pages ++;
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 */
+ if (!err)
+ fuse_send_readpages(data.req, file, inode);
return err;
}
#else /* KERNEL_2_6 */
static struct file_operations fuse_file_operations = {
.llseek = generic_file_llseek,
#ifdef KERNEL_2_6
- .read = do_sync_read,
- .write = do_sync_write,
- .readv = generic_file_readv,
- .writev = generic_file_writev,
- .aio_read = generic_file_aio_read,
- .aio_write = generic_file_aio_write,
+ .read = generic_file_read,
+ .write = generic_file_write,
#else
.read = fuse_file_read,
.write = generic_file_write,
# endif
# define new_decode_dev(x) (x)
# define new_encode_dev(x) (x)
+# define s_fs_info u.generic_sbp
#endif /* KERNEL_2_6 */
#endif /* FUSE_MAINLINE */
#include <linux/fs.h>
set_page_dirty(page);
unlock_page(page);
}
+
+struct kobject {
+ atomic_t count;
+ void (*release) (struct kobject *);
+};
+
+static inline void kobject_get(struct kobject *kobj)
+{
+ atomic_inc(&kobj->count);
+}
+
+static inline void kobject_put(struct kobject *kobj)
+{
+ if (atomic_dec_and_test(&kobj->count))
+ kobj->release(kobj);
+}
#endif
/** Max number of pages that can be used in a single read request */
#define FUSE_MAX_PAGES_PER_REQ 32
/** Header returned from userspace */
struct fuse_out_header h;
+ /*
+ * The following bitfields are not changed during the request
+ * processing
+ */
+
/** Last argument is variable length (can be shorter than
arg->size) */
unsigned argvar:1;
struct fuse_arg args[3];
};
+/** The request state */
+enum fuse_req_state {
+ FUSE_REQ_INIT = 0,
+ FUSE_REQ_PENDING,
+ FUSE_REQ_READING,
+ FUSE_REQ_SENT,
+ FUSE_REQ_FINISHED
+};
+
+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 */
+ /** This can be on either unused_list, pending processing or
+ io lists in fuse_conn */
struct list_head list;
/** Entry on the background list */
/** refcount */
atomic_t count;
+ /*
+ * The following bitfields are either set once before the
+ * request is queued or setting/clearing them is protected by
+ * fuse_lock
+ */
+
/** True if the request has reply */
unsigned isreply: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;
+ /** State of the request */
+ enum fuse_req_state state;
/** The request input */
struct fuse_in in;
struct fuse_release_in release_in;
struct fuse_init_in init_in;
struct fuse_init_out init_out;
+ struct fuse_read_in read_in;
} misc;
/** page vector */
/** File used in the request (or NULL) */
struct file *file;
+
+ /** Request completion callback */
+ void (*end)(struct fuse_conn *, struct fuse_req *);
};
/**
* unmounted.
*/
struct fuse_conn {
- /** Reference count */
- int count;
-
/** The user id for this mount */
uid_t user_id;
/** The list of requests being processed */
struct list_head processing;
+ /** The list of requests under I/O */
+ struct list_head io;
+
/** Requests put in the background (RELEASE or any other
interrupted request) */
struct list_head background;
/** Mount is active */
unsigned mounted;
- /** Connection established */
+ /** Connection established, cleared on umount, connection
+ abort and device release */
unsigned connected;
- /** Connection failed (version mismatch) */
+ /** Connection failed (version mismatch). Cannot race with
+ setting other bitfields since it is only set once in INIT
+ reply, before any other request, and never cleared */
unsigned conn_error : 1;
+ /*
+ * The following bitfields are only for optimization purposes
+ * and hence races in setting them will not cause malfunction
+ */
+
/** Is fsync not implemented by fs? */
unsigned no_fsync : 1;
/** Is create not implemented by fs? */
unsigned no_create : 1;
+ /** The number of requests waiting for completion */
+ atomic_t num_waiting;
+
/** Negotiated minor version */
unsigned minor;
/** Backing dev info */
struct backing_dev_info bdi;
#endif
-};
-static inline struct fuse_conn **get_fuse_conn_super_p(struct super_block *sb)
-{
-#ifdef KERNEL_2_6
- return (struct fuse_conn **) &sb->s_fs_info;
-#else
- return (struct fuse_conn **) &sb->u.generic_sbp;
-#endif
-}
+ /** kobject */
+ struct kobject kobj;
+};
static inline struct fuse_conn *get_fuse_conn_super(struct super_block *sb)
{
- return *get_fuse_conn_super_p(sb);
+ return sb->s_fs_info;
}
static inline struct fuse_conn *get_fuse_conn(struct inode *inode)
return get_fuse_conn_super(inode->i_sb);
}
+static inline struct fuse_conn *get_fuse_conn_kobj(struct kobject *obj)
+{
+ return container_of(obj, struct fuse_conn, kobj);
+}
+
static inline struct fuse_inode *get_fuse_inode(struct inode *inode)
{
return container_of(inode, struct fuse_inode, inode);
unsigned long nodeid, u64 nlookup);
/**
- * Send READ or READDIR request
+ * Initialize 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);
+void fuse_read_fill(struct fuse_req *req, struct file *file,
+ struct inode *inode, loff_t pos, size_t count, int opcode);
/**
* Send OPEN or OPENDIR request
*/
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
*/
*/
void fuse_release_background(struct fuse_req *req);
+/* Abort all requests */
+void fuse_abort_conn(struct fuse_conn *fc);
+
/**
* Get the attributes of a file
*/
* Invalidate inode attributes
*/
void fuse_invalidate_attr(struct inode *inode);
-
-/**
- * Send the INIT message
- */
-void fuse_send_init(struct fuse_conn *fc);
spinlock_t fuse_lock;
static kmem_cache_t *fuse_inode_cachep;
+#ifdef KERNEL_2_6
+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);
+};
+#endif
#define FUSE_SUPER_MAGIC 0x65735546
}
#endif
+static void fuse_umount_begin(struct super_block *sb)
+{
+ fuse_abort_conn(get_fuse_conn_super(sb));
+}
+
static void fuse_put_super(struct super_block *sb)
{
struct fuse_conn *fc = get_fuse_conn_super(sb);
spin_lock(&fuse_lock);
fc->mounted = 0;
- fc->user_id = 0;
- fc->group_id = 0;
- fc->flags = 0;
+ fc->connected = 0;
+ spin_unlock(&fuse_lock);
+ up_write(&fc->sbput_sem);
/* Flush all readers on this fs */
wake_up_all(&fc->waitq);
- up_write(&fc->sbput_sem);
- fuse_release_conn(fc);
- spin_unlock(&fuse_lock);
+#ifdef KERNEL_2_6
+ kobject_del(&fc->kobj);
+#endif
+ kobject_put(&fc->kobj);
}
static void convert_fuse_statfs(struct kstatfs *stbuf, struct fuse_kstatfs *attr)
return 0;
}
-static void free_conn(struct fuse_conn *fc)
+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);
kfree(fc);
}
-/* Must be called with the fuse lock held */
-void fuse_release_conn(struct fuse_conn *fc)
+#ifndef HAVE_KZALLOC
+static void *kzalloc(size_t size, int flags)
{
- fc->count--;
- if (!fc->count)
- free_conn(fc);
+ void *ret = kmalloc(size, flags);
+ if (ret)
+ memset(ret, 0, size);
+ return ret;
}
-
+#endif
static struct fuse_conn *new_conn(void)
{
struct fuse_conn *fc;
- fc = kmalloc(sizeof(*fc), GFP_KERNEL);
- if (fc != NULL) {
+ fc = kzalloc(sizeof(*fc), GFP_KERNEL);
+ if (fc) {
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->io);
INIT_LIST_HEAD(&fc->unused_list);
INIT_LIST_HEAD(&fc->background);
- sema_init(&fc->outstanding_sem, 0);
+ sema_init(&fc->outstanding_sem, 1); /* One for INIT */
init_rwsem(&fc->sbput_sem);
+#ifdef KERNEL_2_6
+ kobj_set_kset_s(fc, connections_subsys);
+ kobject_init(&fc->kobj);
+#else
+ atomic_set(&fc->kobj.count, 1);
+ fc->kobj.release = fuse_conn_release;
+#endif
+ atomic_set(&fc->num_waiting, 0);
for (i = 0; i < FUSE_MAX_OUTSTANDING; i++) {
struct fuse_req *req = fuse_request_alloc();
if (!req) {
- free_conn(fc);
+ kobject_put(&fc->kobj);
return NULL;
}
list_add(&req->list, &fc->unused_list);
static struct fuse_conn *get_conn(struct file *file, struct super_block *sb)
{
struct fuse_conn *fc;
+ int err;
+ err = -EINVAL;
if (file->f_op != &fuse_dev_operations)
- return ERR_PTR(-EINVAL);
+ goto out_err;
+
+ err = -ENOMEM;
fc = new_conn();
- if (fc == NULL)
- return ERR_PTR(-ENOMEM);
+ if (!fc)
+ goto out_err;
+
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;
- }
+ err = -EINVAL;
+ if (file->private_data)
+ goto out_unlock;
+
+ kobject_get(&fc->kobj);
+ file->private_data = fc;
spin_unlock(&fuse_lock);
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)
.read_inode = fuse_read_inode,
.clear_inode = fuse_clear_inode,
.put_super = fuse_put_super,
+ .umount_begin = fuse_umount_begin,
.statfs = fuse_statfs,
.show_options = fuse_show_options,
};
+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)
+ fc->conn_error = 1;
+ else {
+ fc->minor = arg->minor;
+ fc->max_write = arg->minor < 5 ? 4096 : arg->max_write;
+ }
+
+ /* 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);
+}
+
+static void fuse_send_init(struct fuse_conn *fc)
+{
+ /* 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;
+ 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;
+ /* Variable length arguement used for backward compatibility
+ with interface version < 7.5. Rest of init_out is zeroed
+ by do_get_request(), so a short reply is not a problem */
+ req->out.argvar = 1;
+ req->out.args[0].size = sizeof(struct fuse_init_out);
+ req->out.args[0].value = &req->misc.init_out;
+ req->end = process_init_reply;
+ request_send_background(fc, req);
+}
+
+#ifdef KERNEL_2_6
+static unsigned long long 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;
+}
+#endif
+
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;
+ struct dentry *root_dentry;
int err;
if (!parse_fuse_opt((char *) data, &d))
fc->bdi.ra_pages = fc->max_read / PAGE_CACHE_SIZE;
#endif
+ /* Used by get_root_inode() */
+ sb->s_fs_info = fc;
+
err = -ENOMEM;
root = get_root_inode(sb, d.rootmode);
- if (root == NULL)
+ if (!root)
goto err;
- sb->s_root = d_alloc_root(root);
- if (!sb->s_root) {
+ root_dentry = d_alloc_root(root);
+ if (!root_dentry) {
iput(root);
goto err;
}
+
+#ifdef KERNEL_2_6
+ err = kobject_set_name(&fc->kobj, "%llu", conn_id());
+ if (err)
+ goto err_put_root;
+
+ err = kobject_add(&fc->kobj);
+ if (err)
+ goto err_put_root;
+#endif
+
+ sb->s_root = root_dentry;
+ spin_lock(&fuse_lock);
+ fc->mounted = 1;
+ fc->connected = 1;
+ spin_unlock(&fuse_lock);
+
fuse_send_init(fc);
+
return 0;
+#ifdef KERNEL_2_6
+ err_put_root:
+ dput(root_dentry);
+#endif
err:
- spin_lock(&fuse_lock);
- fuse_release_conn(fc);
- spin_unlock(&fuse_lock);
+ kobject_put(&fc->kobj);
return err;
}
static DECLARE_FSTYPE(fuse_fs_type, "fuse", fuse_read_super_compat, 0);
#endif
+#ifdef KERNEL_2_6
+static ssize_t fuse_conn_waiting_show(struct fuse_conn *fc, char *page)
+{
+ return sprintf(page, "%i\n", atomic_read(&fc->num_waiting));
+}
+
+static ssize_t fuse_conn_abort_store(struct fuse_conn *fc, const char *page,
+ size_t count)
+{
+ fuse_abort_conn(fc);
+ return count;
+}
+
+#ifndef __ATTR
+#define __ATTR(_name,_mode,_show,_store) { \
+ .attr = {.name = __stringify(_name), .mode = _mode, .owner = THIS_MODULE }, \
+ .show = _show, \
+ .store = _store, \
+}
+#endif
+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 ssize_t fuse_conn_attr_show(struct kobject *kobj,
+ struct attribute *attr,
+ char *page)
+{
+ 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;
+}
+
+static ssize_t fuse_conn_attr_store(struct kobject *kobj,
+ struct attribute *attr,
+ const char *page, size_t count)
+{
+ 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;
+}
+
+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,
+};
+
+#ifndef HAVE_FS_SUBSYS
+static decl_subsys(fs, NULL, NULL);
+#endif
+static decl_subsys(fuse, NULL, NULL);
+static decl_subsys(connections, &ktype_fuse_conn, NULL);
+#endif /* KERNEL_2_6 */
+
static void fuse_inode_init_once(void *foo, kmem_cache_t *cachep,
unsigned long flags)
{
kmem_cache_destroy(fuse_inode_cachep);
}
+#ifdef KERNEL_2_6
+static int fuse_sysfs_init(void)
+{
+ int err;
+
+#ifndef HAVE_FS_SUBSYS
+ err = subsystem_register(&fs_subsys);
+ if (err)
+ return err;
+#endif
+ kset_set_kset_s(&fuse_subsys, fs_subsys);
+ err = subsystem_register(&fuse_subsys);
+ if (err)
+ goto out_err;
+
+ kset_set_kset_s(&connections_subsys, fuse_subsys);
+ err = subsystem_register(&connections_subsys);
+ if (err)
+ goto out_fuse_unregister;
+
+ return 0;
+
+ out_fuse_unregister:
+ subsystem_unregister(&fuse_subsys);
+ out_err:
+#ifndef HAVE_FS_SUBSYS
+ subsystem_unregister(&fs_subsys);
+#endif
+ return err;
+}
+
+static void fuse_sysfs_cleanup(void)
+{
+ subsystem_unregister(&connections_subsys);
+ subsystem_unregister(&fuse_subsys);
+#ifndef HAVE_FS_SUBSYS
+ subsystem_unregister(&fs_subsys);
+#endif
+}
+#else /* KERNEL_2_6 */
+static int fuse_sysfs_init(void)
+{
+ return 0;
+}
+static void fuse_sysfs_cleanup(void)
+{
+}
+#endif /* KERNEL_2_6 */
+
static int __init fuse_init(void)
{
int res;
if (res)
goto err_fs_cleanup;
+ res = fuse_sysfs_init();
+ if (res)
+ goto err_dev_cleanup;
+
return 0;
+ err_dev_cleanup:
+ fuse_dev_cleanup();
err_fs_cleanup:
fuse_fs_cleanup();
err:
{
printk(KERN_DEBUG "fuse exit\n");
+ fuse_sysfs_cleanup();
fuse_fs_cleanup();
fuse_dev_cleanup();
}
projects / qemu-gpiodev / libfuse.git / commitdiff