From: Josef Bacik <josef@redhat.com>
Date: Tue, 14 Apr 2009 10:46:42 -0400
Subject: [fs] fuse: update for RHEL-5.4
Message-id: 20090414144641.GE14446@unused.rdu.redhat.com
O-Subject: [PATCH][RHEL5.4] bring fuse uptodate with upstream
Bugzilla: 457975
RH-Acked-by: Eric Sandeen <sandeen@redhat.com>
Hello,
This is in reference to bz457975. Because this is only expected to be tech
preview, there are a few things that have been nuetered since they require much
more invasive patches. This includes poll support and writeable mmap support.
These are relatively new features to FUSE so they shouldn't be missed. I have
this patch broken up into individual patches that match the upstream commits.
Also comments 15-17 in the bz give a complete list of commit #'s that were taken
and commit #'s that were not taken, and the reason they were not taken.
This has been tested with the new AOP patches with dbench, fsx and fs_mark.
There is one slight gotcha where fsx will fail after a few days of running due
to detected corruption, but upon reading everything back again the files match,
so its some sort of weird read problem. This problem existed upstream until
2.6.28, and wasn't fixed by a FUSE patch, it was fixed somewhere else. I've
been running a bisect to figure out what fixed it, but it takes several days to
confirm that fsx isn't actually going to fail, so its slow going. The
corruption doesn't actually make it to the disk, as the information on disk is
correct, we just end up with stale data when we read back after writing, and
this is extremely hard to hit. Other than that, all of my testing has been
successfull. Thanks,
Josef
diff --git a/Documentation/filesystems/fuse.txt b/Documentation/filesystems/fuse.txt
index a584f05..e94e98b 100644
--- a/Documentation/filesystems/fuse.txt
+++ b/Documentation/filesystems/fuse.txt
@@ -51,6 +51,22 @@ homepage:
http://fuse.sourceforge.net/
+Filesystem type
+~~~~~~~~~~~~~~~
+
+The filesystem type given to mount(2) can be one of the following:
+
+'fuse'
+
+ This is the usual way to mount a FUSE filesystem. The first
+ argument of the mount system call may contain an arbitrary string,
+ which is not interpreted by the kernel.
+
+'fuseblk'
+
+ The filesystem is block device based. The first argument of the
+ mount system call is interpreted as the name of the device.
+
Mount options
~~~~~~~~~~~~~
@@ -94,6 +110,11 @@ Mount options
The default is infinite. Note that the size of read requests is
limited anyway to 32 pages (which is 128kbyte on i386).
+'blksize=N'
+
+ Set the block size for the filesystem. The default is 512. This
+ option is only valid for 'fuseblk' type mounts.
+
Control filesystem
~~~~~~~~~~~~~~~~~~
diff --git a/fs/fuse/control.c b/fs/fuse/control.c
index 79ec1f2..28eafc0 100644
--- a/fs/fuse/control.c
+++ b/fs/fuse/control.c
@@ -1,6 +1,6 @@
/*
FUSE: Filesystem in Userspace
- Copyright (C) 2001-2006 Miklos Szeredi <miklos@szeredi.hu>
+ Copyright (C) 2001-2008 Miklos Szeredi <miklos@szeredi.hu>
This program can be distributed under the terms of the GNU GPL.
See the file COPYING.
@@ -48,11 +48,13 @@ static ssize_t fuse_conn_waiting_read(struct file *file, char __user *buf,
size_t size;
if (!*ppos) {
+ long value;
struct fuse_conn *fc = fuse_ctl_file_conn_get(file);
if (!fc)
return 0;
- file->private_data=(void *)(long)atomic_read(&fc->num_waiting);
+ value = atomic_read(&fc->num_waiting);
+ file->private_data = (void *)value;
fuse_conn_put(fc);
}
size = sprintf(tmp, "%ld\n", (long)file->private_data);
@@ -116,7 +118,7 @@ int fuse_ctl_add_conn(struct fuse_conn *fc)
return 0;
parent = fuse_control_sb->s_root;
- parent->d_inode->i_nlink++;
+ inc_nlink(parent->d_inode);
sprintf(name, "%llu", (unsigned long long) fc->id);
parent = fuse_ctl_add_dentry(parent, fc, name, S_IFDIR | 0500, 2,
&simple_dir_inode_operations,
@@ -193,8 +195,12 @@ static int fuse_ctl_get_sb(struct file_system_type *fs_type, int flags,
static void fuse_ctl_kill_sb(struct super_block *sb)
{
+ struct fuse_conn *fc;
+
mutex_lock(&fuse_mutex);
fuse_control_sb = NULL;
+ list_for_each_entry(fc, &fuse_conn_list, entry)
+ fc->ctl_ndents = 0;
mutex_unlock(&fuse_mutex);
kill_litter_super(sb);
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 1e2006c..671d3df 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1,6 +1,6 @@
/*
FUSE: Filesystem in Userspace
- Copyright (C) 2001-2006 Miklos Szeredi <miklos@szeredi.hu>
+ Copyright (C) 2001-2008 Miklos Szeredi <miklos@szeredi.hu>
This program can be distributed under the terms of the GNU GPL.
See the file COPYING.
@@ -19,7 +19,7 @@
MODULE_ALIAS_MISCDEV(FUSE_MINOR);
-static kmem_cache_t *fuse_req_cachep;
+static struct kmem_cache *fuse_req_cachep;
static struct fuse_conn *fuse_get_conn(struct file *file)
{
@@ -41,7 +41,7 @@ static void fuse_request_init(struct fuse_req *req)
struct fuse_req *fuse_request_alloc(void)
{
- struct fuse_req *req = kmem_cache_alloc(fuse_req_cachep, SLAB_KERNEL);
+ struct fuse_req *req = kmem_cache_alloc(fuse_req_cachep, GFP_KERNEL);
if (req)
fuse_request_init(req);
return req;
@@ -129,7 +129,7 @@ static struct fuse_req *get_reserved_req(struct fuse_conn *fc,
struct fuse_file *ff = file->private_data;
do {
- wait_event(fc->blocked_waitq, ff->reserved_req);
+ wait_event(fc->reserved_req_waitq, ff->reserved_req);
spin_lock(&fc->lock);
if (ff->reserved_req) {
req = ff->reserved_req;
@@ -155,7 +155,7 @@ static void put_reserved_req(struct fuse_conn *fc, struct fuse_req *req)
fuse_request_init(req);
BUG_ON(ff->reserved_req);
ff->reserved_req = req;
- wake_up(&fc->blocked_waitq);
+ wake_up_all(&fc->reserved_req_waitq);
spin_unlock(&fc->lock);
fput(file);
}
@@ -201,6 +201,55 @@ void fuse_put_request(struct fuse_conn *fc, struct fuse_req *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 u64 fuse_get_unique(struct fuse_conn *fc)
+{
+ fc->reqctr++;
+ /* zero is special */
+ if (fc->reqctr == 0)
+ fc->reqctr = 1;
+
+ return fc->reqctr;
+}
+
+static void queue_request(struct fuse_conn *fc, struct fuse_req *req)
+{
+ req->in.h.unique = fuse_get_unique(fc);
+ req->in.h.len = sizeof(struct fuse_in_header) +
+ len_args(req->in.numargs, (struct fuse_arg *) req->in.args);
+ list_add_tail(&req->list, &fc->pending);
+ req->state = FUSE_REQ_PENDING;
+ if (!req->waiting) {
+ req->waiting = 1;
+ atomic_inc(&fc->num_waiting);
+ }
+ wake_up(&fc->waitq);
+ kill_fasync(&fc->fasync, SIGIO, POLL_IN);
+}
+
+static void flush_bg_queue(struct fuse_conn *fc)
+{
+ while (fc->active_background < FUSE_MAX_BACKGROUND &&
+ !list_empty(&fc->bg_queue)) {
+ struct fuse_req *req;
+
+ req = list_entry(fc->bg_queue.next, struct fuse_req, list);
+ list_del(&req->list);
+ fc->active_background++;
+ queue_request(fc, req);
+ }
+}
+
/*
* This function is called when a request is finished. Either a reply
* has arrived or it was aborted (and not yet sent) or some error
@@ -212,6 +261,7 @@ void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req)
* Called with fc->lock, unlocks it
*/
static void request_end(struct fuse_conn *fc, struct fuse_req *req)
+ __releases(fc->lock)
{
void (*end) (struct fuse_conn *, struct fuse_req *) = req->end;
req->end = NULL;
@@ -224,21 +274,19 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req)
wake_up_all(&fc->blocked_waitq);
}
fc->num_background--;
+ fc->active_background--;
+ flush_bg_queue(fc);
}
spin_unlock(&fc->lock);
- dput(req->dentry);
- mntput(req->vfsmount);
- if (req->file)
- fput(req->file);
wake_up(&req->waitq);
if (end)
end(fc, req);
- else
- fuse_put_request(fc, req);
+ fuse_put_request(fc, req);
}
static void wait_answer_interruptible(struct fuse_conn *fc,
struct fuse_req *req)
+ __releases(fc->lock) __acquires(fc->lock)
{
if (signal_pending(current))
return;
@@ -255,8 +303,8 @@ static void queue_interrupt(struct fuse_conn *fc, struct fuse_req *req)
kill_fasync(&fc->fasync, SIGIO, POLL_IN);
}
-/* Called with fc->lock held. Releases, and then reacquires it. */
static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req)
+ __releases(fc->lock) __acquires(fc->lock)
{
if (!fc->no_interrupt) {
/* Any signal may interrupt this */
@@ -272,28 +320,41 @@ static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req)
queue_interrupt(fc, req);
}
- if (req->force) {
- spin_unlock(&fc->lock);
- wait_event(req->waitq, req->state == FUSE_REQ_FINISHED);
- spin_lock(&fc->lock);
- } else {
+ if (!req->force) {
sigset_t oldset;
/* Only fatal signals may interrupt this */
block_sigs(&oldset);
wait_answer_interruptible(fc, req);
restore_sigs(&oldset);
+
+ if (req->aborted)
+ goto aborted;
+ if (req->state == FUSE_REQ_FINISHED)
+ return;
+
+ /* Request is not yet in userspace, bail out */
+ if (req->state == FUSE_REQ_PENDING) {
+ list_del(&req->list);
+ __fuse_put_request(req);
+ req->out.h.error = -EINTR;
+ return;
+ }
}
- if (req->aborted)
- goto aborted;
- if (req->state == FUSE_REQ_FINISHED)
- return;
+ /*
+ * Either request is already in userspace, or it was forced.
+ * Wait it out.
+ */
+ spin_unlock(&fc->lock);
+ wait_event(req->waitq, req->state == FUSE_REQ_FINISHED);
+ spin_lock(&fc->lock);
- req->out.h.error = -EINTR;
- req->aborted = 1;
+ if (!req->aborted)
+ return;
aborted:
+ BUG_ON(req->state != FUSE_REQ_FINISHED);
if (req->locked) {
/* This is uninterruptible sleep, because data is
being copied to/from the buffers of req. During
@@ -304,50 +365,6 @@ static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req)
wait_event(req->waitq, !req->locked);
spin_lock(&fc->lock);
}
- if (req->state == FUSE_REQ_PENDING) {
- list_del(&req->list);
- __fuse_put_request(req);
- } else if (req->state == FUSE_REQ_SENT) {
- spin_unlock(&fc->lock);
- wait_event(req->waitq, req->state == FUSE_REQ_FINISHED);
- spin_lock(&fc->lock);
- }
-}
-
-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 u64 fuse_get_unique(struct fuse_conn *fc)
- {
- fc->reqctr++;
- /* zero is special */
- if (fc->reqctr == 0)
- fc->reqctr = 1;
-
- return fc->reqctr;
-}
-
-static void queue_request(struct fuse_conn *fc, struct fuse_req *req)
-{
- req->in.h.unique = fuse_get_unique(fc);
- req->in.h.len = sizeof(struct fuse_in_header) +
- len_args(req->in.numargs, (struct fuse_arg *) req->in.args);
- list_add_tail(&req->list, &fc->pending);
- req->state = FUSE_REQ_PENDING;
- if (!req->waiting) {
- req->waiting = 1;
- atomic_inc(&fc->num_waiting);
- }
- wake_up(&fc->waitq);
- kill_fasync(&fc->fasync, SIGIO, POLL_IN);
}
void request_send(struct fuse_conn *fc, struct fuse_req *req)
@@ -369,16 +386,22 @@ void request_send(struct fuse_conn *fc, struct fuse_req *req)
spin_unlock(&fc->lock);
}
+static void request_send_nowait_locked(struct fuse_conn *fc,
+ struct fuse_req *req)
+{
+ req->background = 1;
+ fc->num_background++;
+ if (fc->num_background == FUSE_MAX_BACKGROUND)
+ fc->blocked = 1;
+ list_add_tail(&req->list, &fc->bg_queue);
+ flush_bg_queue(fc);
+}
+
static void request_send_nowait(struct fuse_conn *fc, struct fuse_req *req)
{
spin_lock(&fc->lock);
if (fc->connected) {
- req->background = 1;
- fc->num_background++;
- if (fc->num_background == FUSE_MAX_BACKGROUND)
- fc->blocked = 1;
-
- queue_request(fc, req);
+ request_send_nowait_locked(fc, req);
spin_unlock(&fc->lock);
} else {
req->out.h.error = -ENOTCONN;
@@ -488,8 +511,8 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
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 --;
+ cs->iov++;
+ cs->nr_segs--;
}
down_read(¤t->mm->mmap_sem);
err = get_user_pages(current, current->mm, cs->addr, 1, cs->write, 0,
@@ -538,9 +561,11 @@ static int fuse_copy_page(struct fuse_copy_state *cs, struct page *page,
kunmap_atomic(mapaddr, KM_USER1);
}
while (count) {
- int err;
- if (!cs->len && (err = fuse_copy_fill(cs)))
- return err;
+ if (!cs->len) {
+ int err = fuse_copy_fill(cs);
+ if (err)
+ return err;
+ }
if (page) {
void *mapaddr = kmap_atomic(page, KM_USER1);
void *buf = mapaddr + offset;
@@ -580,9 +605,11 @@ static int fuse_copy_pages(struct fuse_copy_state *cs, unsigned nbytes,
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;
+ if (!cs->len) {
+ int err = fuse_copy_fill(cs);
+ if (err)
+ return err;
+ }
fuse_copy_do(cs, &val, &size);
}
return 0;
@@ -640,6 +667,7 @@ static void request_wait(struct fuse_conn *fc)
*/
static int fuse_read_interrupt(struct fuse_conn *fc, struct fuse_req *req,
const struct iovec *iov, unsigned long nr_segs)
+ __releases(fc->lock)
{
struct fuse_copy_state cs;
struct fuse_in_header ih;
@@ -735,11 +763,12 @@ static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov,
fuse_copy_finish(&cs);
spin_lock(&fc->lock);
req->locked = 0;
- if (!err && req->aborted)
- err = -ENOENT;
+ if (req->aborted) {
+ request_end(fc, req);
+ return -ENODEV;
+ }
if (err) {
- if (!req->aborted)
- req->out.h.error = -EIO;
+ req->out.h.error = -EIO;
request_end(fc, req);
return err;
}
@@ -768,6 +797,15 @@ static ssize_t fuse_dev_read(struct file *file, char __user *buf,
return fuse_dev_readv(file, &iov, 1, off);
}
+static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
+ unsigned int size, struct fuse_copy_state *cs)
+{
+ switch (code) {
+ default:
+ return -EINVAL;
+ }
+}
+
/* Look up request on processing list by unique ID */
static struct fuse_req *request_find(struct fuse_conn *fc, u64 unique)
{
@@ -831,9 +869,23 @@ static ssize_t fuse_dev_writev(struct file *file, const struct iovec *iov,
err = fuse_copy_one(&cs, &oh, sizeof(oh));
if (err)
goto err_finish;
+
+ err = -EINVAL;
+ if (oh.len != nbytes)
+ goto err_finish;
+
+ /*
+ * Zero oh.unique indicates unsolicited notification message
+ * and error contains notification code.
+ */
+ if (!oh.unique) {
+ err = fuse_notify(fc, oh.error, nbytes - sizeof(oh), &cs);
+ fuse_copy_finish(&cs);
+ return err ? err : nbytes;
+ }
+
err = -EINVAL;
- if (!oh.unique || oh.error <= -1000 || oh.error > 0 ||
- oh.len != nbytes)
+ if (oh.error <= -1000 || oh.error > 0)
goto err_finish;
spin_lock(&fc->lock);
@@ -952,6 +1004,7 @@ static void end_requests(struct fuse_conn *fc, struct list_head *head)
* locked).
*/
static void end_io_requests(struct fuse_conn *fc)
+ __releases(fc->lock) __acquires(fc->lock)
{
while (!list_empty(&fc->io)) {
struct fuse_req *req =
@@ -965,11 +1018,11 @@ static void end_io_requests(struct fuse_conn *fc)
wake_up(&req->waitq);
if (end) {
req->end = NULL;
- /* The end function will consume this reference */
__fuse_get_request(req);
spin_unlock(&fc->lock);
wait_event(req->waitq, !req->locked);
end(fc, req);
+ fuse_put_request(fc, req);
spin_lock(&fc->lock);
}
}
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 5d7c726..a5d2dc5 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1,6 +1,6 @@
/*
FUSE: Filesystem in Userspace
- Copyright (C) 2001-2006 Miklos Szeredi <miklos@szeredi.hu>
+ Copyright (C) 2001-2008 Miklos Szeredi <miklos@szeredi.hu>
This program can be distributed under the terms of the GNU GPL.
See the file COPYING.
@@ -63,13 +63,21 @@ static u64 time_to_jiffies(unsigned long sec, unsigned long nsec)
* Set dentry and possibly attribute timeouts from the lookup/mk*
* replies
*/
-static void fuse_change_timeout(struct dentry *entry, struct fuse_entry_out *o)
+static void fuse_change_entry_timeout(struct dentry *entry,
+ struct fuse_entry_out *o)
{
fuse_dentry_settime(entry,
time_to_jiffies(o->entry_valid, o->entry_valid_nsec));
- if (entry->d_inode)
- get_fuse_inode(entry->d_inode)->i_time =
- time_to_jiffies(o->attr_valid, o->attr_valid_nsec);
+}
+
+static u64 attr_timeout(struct fuse_attr_out *o)
+{
+ return time_to_jiffies(o->attr_valid, o->attr_valid_nsec);
+}
+
+static u64 entry_attr_timeout(struct fuse_entry_out *o)
+{
+ return time_to_jiffies(o->attr_valid, o->attr_valid_nsec);
}
/*
@@ -104,20 +112,39 @@ static void fuse_invalidate_entry(struct dentry *entry)
fuse_invalidate_entry_cache(entry);
}
-static void fuse_lookup_init(struct fuse_req *req, struct inode *dir,
- struct dentry *entry,
+static void fuse_lookup_init(struct fuse_conn *fc, struct fuse_req *req,
+ u64 nodeid, struct qstr *name,
struct fuse_entry_out *outarg)
{
+ memset(outarg, 0, sizeof(struct fuse_entry_out));
req->in.h.opcode = FUSE_LOOKUP;
- req->in.h.nodeid = get_node_id(dir);
+ req->in.h.nodeid = nodeid;
req->in.numargs = 1;
- req->in.args[0].size = entry->d_name.len + 1;
- req->in.args[0].value = entry->d_name.name;
+ req->in.args[0].size = name->len + 1;
+ req->in.args[0].value = name->name;
req->out.numargs = 1;
- req->out.args[0].size = sizeof(struct fuse_entry_out);
+ if (fc->minor < 9)
+ req->out.args[0].size = FUSE_COMPAT_ENTRY_OUT_SIZE;
+ else
+ req->out.args[0].size = sizeof(struct fuse_entry_out);
req->out.args[0].value = outarg;
}
+u64 fuse_get_attr_version(struct fuse_conn *fc)
+{
+ u64 curr_version;
+
+ /*
+ * The spin lock isn't actually needed on 64bit archs, but we
+ * don't yet care too much about such optimizations.
+ */
+ spin_lock(&fc->lock);
+ curr_version = fc->attr_version;
+ spin_unlock(&fc->lock);
+
+ return curr_version;
+}
+
/*
* Check whether the dentry is still valid
*
@@ -138,9 +165,9 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
struct fuse_entry_out outarg;
struct fuse_conn *fc;
struct fuse_req *req;
-
- /* Doesn't hurt to "reset" the validity timeout */
- fuse_invalidate_entry_cache(entry);
+ struct fuse_req *forget_req;
+ struct dentry *parent;
+ u64 attr_version;
/* For negative dentries, always do a fresh lookup */
if (!inode)
@@ -151,46 +178,47 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
if (IS_ERR(req))
return 0;
- fuse_lookup_init(req, entry->d_parent->d_inode, entry, &outarg);
+ forget_req = fuse_get_req(fc);
+ if (IS_ERR(forget_req)) {
+ fuse_put_request(fc, req);
+ return 0;
+ }
+
+ attr_version = fuse_get_attr_version(fc);
+
+ parent = dget_parent(entry);
+ fuse_lookup_init(fc, req, get_node_id(parent->d_inode),
+ &entry->d_name, &outarg);
request_send(fc, req);
+ dput(parent);
err = req->out.h.error;
+ fuse_put_request(fc, req);
/* Zero nodeid is same as -ENOENT */
if (!err && !outarg.nodeid)
err = -ENOENT;
if (!err) {
struct fuse_inode *fi = get_fuse_inode(inode);
if (outarg.nodeid != get_node_id(inode)) {
- fuse_send_forget(fc, req, outarg.nodeid, 1);
+ fuse_send_forget(fc, forget_req,
+ outarg.nodeid, 1);
return 0;
}
- fi->nlookup ++;
+ spin_lock(&fc->lock);
+ fi->nlookup++;
+ spin_unlock(&fc->lock);
}
- fuse_put_request(fc, req);
+ fuse_put_request(fc, forget_req);
if (err || (outarg.attr.mode ^ inode->i_mode) & S_IFMT)
return 0;
- fuse_change_attributes(inode, &outarg.attr);
- fuse_change_timeout(entry, &outarg);
+ fuse_change_attributes(inode, &outarg.attr,
+ entry_attr_timeout(&outarg),
+ attr_version);
+ fuse_change_entry_timeout(entry, &outarg);
}
return 1;
}
-/*
- * Check if there's already a hashed alias of this directory inode.
- * If yes, then lookup and mkdir must not create a new alias.
- */
-static int dir_alias(struct inode *inode)
-{
- if (S_ISDIR(inode->i_mode)) {
- struct dentry *alias = d_find_alias(inode);
- if (alias) {
- dput(alias);
- return 1;
- }
- }
- return 0;
-}
-
static int invalid_nodeid(u64 nodeid)
{
return !nodeid || nodeid == FUSE_ROOT_ID;
@@ -200,58 +228,137 @@ static struct dentry_operations fuse_dentry_operations = {
.d_revalidate = fuse_dentry_revalidate,
};
-static int valid_mode(int m)
+int fuse_valid_type(int m)
{
return S_ISREG(m) || S_ISDIR(m) || S_ISLNK(m) || S_ISCHR(m) ||
S_ISBLK(m) || S_ISFIFO(m) || S_ISSOCK(m);
}
-static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
- struct nameidata *nd)
+/*
+ * Add a directory inode to a dentry, ensuring that no other dentry
+ * refers to this inode. Called with fc->inst_mutex.
+ */
+static struct dentry *fuse_d_add_directory(struct dentry *entry,
+ struct inode *inode)
{
- int err;
- struct fuse_entry_out outarg;
- struct inode *inode = NULL;
- struct fuse_conn *fc = get_fuse_conn(dir);
+ struct dentry *alias = d_find_alias(inode);
+ if (alias && !(alias->d_flags & DCACHE_DISCONNECTED)) {
+ /* This tries to shrink the subtree below alias */
+ fuse_invalidate_entry(alias);
+ dput(alias);
+ if (!list_empty(&inode->i_dentry))
+ return ERR_PTR(-EBUSY);
+ } else {
+ dput(alias);
+ }
+ return d_splice_alias(inode, entry);
+}
+
+int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name,
+ struct fuse_entry_out *outarg, struct inode **inode)
+ {
+ struct fuse_conn *fc = get_fuse_conn_super(sb);
struct fuse_req *req;
+ struct fuse_req *forget_req;
+ u64 attr_version;
+ int err;
- if (entry->d_name.len > FUSE_NAME_MAX)
- return ERR_PTR(-ENAMETOOLONG);
+ *inode = NULL;
+ err = -ENAMETOOLONG;
+ if (name->len > FUSE_NAME_MAX)
+ goto out;
req = fuse_get_req(fc);
+ err = PTR_ERR(req);
if (IS_ERR(req))
- return ERR_PTR(PTR_ERR(req));
+ goto out;
- fuse_lookup_init(req, dir, entry, &outarg);
+ forget_req = fuse_get_req(fc);
+ err = PTR_ERR(forget_req);
+ if (IS_ERR(forget_req)) {
+ fuse_put_request(fc, req);
+ goto out;
+ }
+
+ attr_version = fuse_get_attr_version(fc);
+
+ fuse_lookup_init(fc, req, nodeid, name, outarg);
request_send(fc, req);
err = req->out.h.error;
+ fuse_put_request(fc, req);
/* Zero nodeid is same as -ENOENT, but with valid timeout */
- if (!err && outarg.nodeid &&
- (invalid_nodeid(outarg.nodeid) || !valid_mode(outarg.attr.mode)))
- err = -EIO;
- if (!err && outarg.nodeid) {
- inode = fuse_iget(dir->i_sb, outarg.nodeid, outarg.generation,
- &outarg.attr);
- if (!inode) {
- fuse_send_forget(fc, req, outarg.nodeid, 1);
- return ERR_PTR(-ENOMEM);
- }
+ if (err || !outarg->nodeid)
+ goto out_put_forget;
+
+ err = -EIO;
+ if (!outarg->nodeid)
+ goto out_put_forget;
+ if (!fuse_valid_type(outarg->attr.mode))
+ goto out_put_forget;
+
+ *inode = fuse_iget(sb, outarg->nodeid, outarg->generation,
+ &outarg->attr, entry_attr_timeout(outarg),
+ attr_version);
+ err = -ENOMEM;
+ if (!*inode) {
+ fuse_send_forget(fc, forget_req, outarg->nodeid, 1);
+ goto out;
}
- fuse_put_request(fc, req);
- if (err && err != -ENOENT)
- return ERR_PTR(err);
+ err = 0;
+
+ out_put_forget:
+ fuse_put_request(fc, forget_req);
+ out:
+ return err;
+}
- if (inode && dir_alias(inode)) {
- iput(inode);
- return ERR_PTR(-EIO);
+static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
+ struct nameidata *nd)
+{
+ int err;
+ struct fuse_entry_out outarg;
+ struct inode *inode;
+ struct dentry *newent;
+ struct fuse_conn *fc = get_fuse_conn(dir);
+ bool outarg_valid = true;
+
+ err = fuse_lookup_name(dir->i_sb, get_node_id(dir), &entry->d_name,
+ &outarg, &inode);
+ if (err == -ENOENT) {
+ outarg_valid = false;
+ err = 0;
+ }
+ if (err)
+ goto out_err;
+
+ err = -EIO;
+ if (inode && get_node_id(inode) == FUSE_ROOT_ID)
+ goto out_iput;
+
+ if (inode && S_ISDIR(inode->i_mode)) {
+ mutex_lock(&fc->inst_mutex);
+ newent = fuse_d_add_directory(entry, inode);
+ mutex_unlock(&fc->inst_mutex);
+ err = PTR_ERR(newent);
+ if (IS_ERR(newent))
+ goto out_iput;
+ } else {
+ newent = d_splice_alias(inode, entry);
}
- d_add(entry, inode);
+
+ entry = newent ? newent : entry;
entry->d_op = &fuse_dentry_operations;
- if (!err)
- fuse_change_timeout(entry, &outarg);
+ if (outarg_valid)
+ fuse_change_entry_timeout(entry, &outarg);
else
fuse_invalidate_entry_cache(entry);
- return NULL;
+
+ return newent;
+
+ out_iput:
+ iput(inode);
+ out_err:
+ return ERR_PTR(err);
}
/*
@@ -260,12 +367,11 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
static void fuse_sync_release(struct fuse_conn *fc, struct fuse_file *ff,
u64 nodeid, int flags)
{
- struct fuse_req *req;
-
- req = fuse_release_fill(ff, nodeid, flags, FUSE_RELEASE);
- req->force = 1;
- request_send(fc, req);
- fuse_put_request(fc, req);
+ fuse_release_fill(ff, nodeid, flags, FUSE_RELEASE);
+ ff->reserved_req->force = 1;
+ request_send(fc, ff->reserved_req);
+ fuse_put_request(fc, ff->reserved_req);
+ kfree(ff);
}
/*
@@ -302,12 +408,13 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode,
goto out_put_forget_req;
err = -ENOMEM;
- ff = fuse_file_alloc();
+ ff = fuse_file_alloc(fc);
if (!ff)
goto out_put_request;
flags &= ~O_NOCTTY;
memset(&inarg, 0, sizeof(inarg));
+ memset(&outentry, 0, sizeof(outentry));
inarg.flags = flags;
inarg.mode = mode;
req->in.h.opcode = FUSE_CREATE;
@@ -318,7 +425,10 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode,
req->in.args[1].size = entry->d_name.len + 1;
req->in.args[1].value = entry->d_name.name;
req->out.numargs = 2;
- req->out.args[0].size = sizeof(outentry);
+ if (fc->minor < 9)
+ req->out.args[0].size = FUSE_COMPAT_ENTRY_OUT_SIZE;
+ else
+ req->out.args[0].size = sizeof(outentry);
req->out.args[0].value = &outentry;
req->out.args[1].size = sizeof(outopen);
req->out.args[1].value = &outopen;
@@ -336,7 +446,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode,
fuse_put_request(fc, req);
inode = fuse_iget(dir->i_sb, outentry.nodeid, outentry.generation,
- &outentry.attr);
+ &outentry.attr, entry_attr_timeout(&outentry), 0);
if (!inode) {
flags &= ~(O_CREAT | O_EXCL | O_TRUNC);
ff->fh = outopen.fh;
@@ -346,7 +456,8 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode,
}
fuse_put_request(fc, forget_req);
d_instantiate(entry, inode);
- fuse_change_timeout(entry, &outentry);
+ fuse_change_entry_timeout(entry, &outentry);
+ fuse_invalidate_attr(dir);
file = lookup_instantiate_filp(nd, entry, generic_file_open);
if (IS_ERR(file)) {
ff->fh = outopen.fh;
@@ -375,44 +486,65 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req,
struct fuse_entry_out outarg;
struct inode *inode;
int err;
+ struct fuse_req *forget_req;
+
+ forget_req = fuse_get_req(fc);
+ if (IS_ERR(forget_req)) {
+ fuse_put_request(fc, req);
+ return PTR_ERR(forget_req);
+ }
+ memset(&outarg, 0, sizeof(outarg));
req->in.h.nodeid = get_node_id(dir);
req->out.numargs = 1;
- req->out.args[0].size = sizeof(outarg);
+ if (fc->minor < 9)
+ req->out.args[0].size = FUSE_COMPAT_ENTRY_OUT_SIZE;
+ else
+ 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;
- }
+ fuse_put_request(fc, req);
+ if (err)
+ goto out_put_forget_req;
+
err = -EIO;
if (invalid_nodeid(outarg.nodeid))
- goto out_put_request;
+ goto out_put_forget_req;
if ((outarg.attr.mode ^ mode) & S_IFMT)
- goto out_put_request;
+ goto out_put_forget_req;
inode = fuse_iget(dir->i_sb, outarg.nodeid, outarg.generation,
- &outarg.attr);
+ &outarg.attr, entry_attr_timeout(&outarg), 0);
if (!inode) {
- fuse_send_forget(fc, req, outarg.nodeid, 1);
+ fuse_send_forget(fc, forget_req, outarg.nodeid, 1);
return -ENOMEM;
}
- fuse_put_request(fc, req);
+ fuse_put_request(fc, forget_req);
- if (dir_alias(inode)) {
- iput(inode);
- return -EIO;
- }
+ if (S_ISDIR(inode->i_mode)) {
+ struct dentry *alias;
+ mutex_lock(&fc->inst_mutex);
+ alias = d_find_alias(inode);
+ if (alias) {
+ /* New directory must have moved since mkdir */
+ mutex_unlock(&fc->inst_mutex);
+ dput(alias);
+ iput(inode);
+ return -EBUSY;
+ }
+ d_instantiate(entry, inode);
+ mutex_unlock(&fc->inst_mutex);
+ } else
+ d_instantiate(entry, inode);
- d_instantiate(entry, inode);
- fuse_change_timeout(entry, &outarg);
+ fuse_change_entry_timeout(entry, &outarg);
fuse_invalidate_attr(dir);
return 0;
- out_put_request:
- fuse_put_request(fc, req);
+ out_put_forget_req:
+ fuse_put_request(fc, forget_req);
return err;
}
@@ -440,7 +572,7 @@ static int fuse_mknod(struct inode *dir, struct dentry *entry, int mode,
static int fuse_create(struct inode *dir, struct dentry *entry, int mode,
struct nameidata *nd)
{
- if (nd && (nd->flags & LOOKUP_CREATE)) {
+ if (nd && (nd->flags & LOOKUP_OPEN)) {
int err = fuse_create_open(dir, entry, mode, nd);
if (err != -ENOSYS)
return err;
@@ -505,10 +637,12 @@ static int fuse_unlink(struct inode *dir, struct dentry *entry)
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;
+ /*
+ * 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.
+ */
+ clear_nlink(inode);
fuse_invalidate_attr(inode);
fuse_invalidate_attr(dir);
fuse_invalidate_entry_cache(entry);
@@ -534,7 +668,7 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry)
err = req->out.h.error;
fuse_put_request(fc, req);
if (!err) {
- entry->d_inode->i_nlink = 0;
+ clear_nlink(entry->d_inode);
fuse_invalidate_attr(dir);
fuse_invalidate_entry_cache(entry);
} else if (err == -EINTR)
@@ -567,6 +701,9 @@ static int fuse_rename(struct inode *olddir, struct dentry *oldent,
err = req->out.h.error;
fuse_put_request(fc, req);
if (!err) {
+ /* ctime changes */
+ fuse_invalidate_attr(oldent->d_inode);
+
fuse_invalidate_attr(olddir);
if (olddir != newdir)
fuse_invalidate_attr(newdir);
@@ -619,34 +756,103 @@ static int fuse_link(struct dentry *entry, struct inode *newdir,
return err;
}
-int fuse_do_getattr(struct inode *inode)
+static void fuse_fillattr(struct inode *inode, struct fuse_attr *attr,
+ struct kstat *stat)
+{
+ stat->dev = inode->i_sb->s_dev;
+ stat->ino = attr->ino;
+ stat->mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
+ stat->nlink = attr->nlink;
+ stat->uid = attr->uid;
+ stat->gid = attr->gid;
+ stat->rdev = inode->i_rdev;
+ stat->atime.tv_sec = attr->atime;
+ stat->atime.tv_nsec = attr->atimensec;
+ stat->mtime.tv_sec = attr->mtime;
+ stat->mtime.tv_nsec = attr->mtimensec;
+ stat->ctime.tv_sec = attr->ctime;
+ stat->ctime.tv_nsec = attr->ctimensec;
+ stat->size = attr->size;
+ stat->blocks = attr->blocks;
+ stat->blksize = (1 << inode->i_blkbits);
+}
+
+static int fuse_do_getattr(struct inode *inode, struct kstat *stat,
+ struct file *file)
{
int err;
- struct fuse_attr_out arg;
+ struct fuse_getattr_in inarg;
+ struct fuse_attr_out outarg;
struct fuse_conn *fc = get_fuse_conn(inode);
- struct fuse_req *req = fuse_get_req(fc);
+ struct fuse_req *req;
+ u64 attr_version;
+
+ req = fuse_get_req(fc);
if (IS_ERR(req))
return PTR_ERR(req);
+ attr_version = fuse_get_attr_version(fc);
+
+ memset(&inarg, 0, sizeof(inarg));
+ memset(&outarg, 0, sizeof(outarg));
+ /* Directories have separate file-handle space */
+ if (file && S_ISREG(inode->i_mode)) {
+ struct fuse_file *ff = file->private_data;
+
+ inarg.getattr_flags |= FUSE_GETATTR_FH;
+ inarg.fh = ff->fh;
+ }
req->in.h.opcode = FUSE_GETATTR;
req->in.h.nodeid = get_node_id(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(arg);
- req->out.args[0].value = &arg;
+ if (fc->minor < 9)
+ req->out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE;
+ else
+ 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 ^ arg.attr.mode) & S_IFMT) {
+ if ((inode->i_mode ^ outarg.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);
+ fuse_change_attributes(inode, &outarg.attr,
+ attr_timeout(&outarg),
+ attr_version);
+ if (stat)
+ fuse_fillattr(inode, &outarg.attr, stat);
+ }
+ }
+ return err;
+}
+
+int fuse_update_attributes(struct inode *inode, struct kstat *stat,
+ struct file *file, bool *refreshed)
+{
+ struct fuse_inode *fi = get_fuse_inode(inode);
+ int err;
+ bool r;
+
+ if (fi->i_time < get_jiffies_64()) {
+ r = true;
+ err = fuse_do_getattr(inode, stat, file);
+ } else {
+ r = false;
+ err = 0;
+ if (stat) {
+ generic_fillattr(inode, stat);
+ stat->mode = fi->orig_i_mode;
}
}
+
+ if (refreshed != NULL)
+ *refreshed = r;
+
return err;
}
@@ -663,7 +869,7 @@ int fuse_do_getattr(struct inode *inode)
* 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)
+int fuse_allow_task(struct fuse_conn *fc, struct task_struct *task)
{
if (fc->flags & FUSE_ALLOW_OTHER)
return 1;
@@ -679,30 +885,6 @@ static int fuse_allow_task(struct fuse_conn *fc, struct task_struct *task)
return 0;
}
-/*
- * Check whether the inode attributes are still valid
- *
- * If the attribute validity timeout has expired, then fetch the fresh
- * attributes with a 'getattr' request
- *
- * I'm not sure why cached attributes are never returned for the root
- * inode, this is probably being too cautious.
- */
-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 &&
- fi->i_time >= get_jiffies_64())
- return 0;
-
- return fuse_do_getattr(inode);
-}
-
static int fuse_access(struct inode *inode, int mask)
{
struct fuse_conn *fc = get_fuse_conn(inode);
@@ -750,17 +932,30 @@ static int fuse_access(struct inode *inode, int mask)
static int fuse_permission(struct inode *inode, int mask, struct nameidata *nd)
{
struct fuse_conn *fc = get_fuse_conn(inode);
+ bool refreshed = false;
+ int err = 0;
if (!fuse_allow_task(fc, current))
return -EACCES;
- else if (fc->flags & FUSE_DEFAULT_PERMISSIONS) {
- int err = generic_permission(inode, mask, NULL);
+
+ /*
+ * If attributes are needed, refresh them before proceeding
+ */
+ if ((fc->flags & FUSE_DEFAULT_PERMISSIONS) ||
+ ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))) {
+ err = fuse_update_attributes(inode, NULL, NULL, &refreshed);
+ if (err)
+ return err;
+ }
+
+ if (fc->flags & FUSE_DEFAULT_PERMISSIONS) {
+ 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 == -EACCES && !refreshed) {
+ err = fuse_do_getattr(inode, NULL, NULL);
if (!err)
err = generic_permission(inode, mask, NULL);
}
@@ -769,17 +964,19 @@ static int fuse_permission(struct inode *inode, int mask, struct nameidata *nd)
exist. So if permissions are revoked this won't be
noticed immediately, only after the attribute
timeout has expired */
-
- return err;
- } else {
- int mode = inode->i_mode;
- if ((mask & MAY_EXEC) && !S_ISDIR(mode) && !(mode & S_IXUGO))
- return -EACCES;
-
- if (nd && (nd->flags & LOOKUP_ACCESS))
- return fuse_access(inode, mask);
- return 0;
+ } else if (nd && (nd->flags & (LOOKUP_ACCESS | LOOKUP_CHDIR))) {
+ err = fuse_access(inode, mask);
+ } else if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode)) {
+ if (!(inode->i_mode & S_IXUGO)) {
+ if (refreshed)
+ return -EACCES;
+
+ err = fuse_do_getattr(inode, NULL, NULL);
+ if (!err && !(inode->i_mode & S_IXUGO))
+ return -EACCES;
+ }
}
+ return err;
}
static int parse_dirfile(char *buf, size_t nbytes, struct file *file,
@@ -910,6 +1107,20 @@ static int fuse_dir_fsync(struct file *file, struct dentry *de, int datasync)
return file ? fuse_fsync_common(file, de, datasync, 1) : 0;
}
+static bool update_mtime(unsigned ivalid)
+{
+ /* Always update if mtime is explicitly set */
+ if (ivalid & ATTR_MTIME_SET)
+ return true;
+
+ /* If it's an open(O_TRUNC) or an ftruncate(), don't update */
+ if ((ivalid & ATTR_SIZE) && (ivalid & ATTR_FILE))
+ return false;
+
+ /* In all other cases update */
+ return true;
+}
+
static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg)
{
unsigned ivalid = iattr->ia_valid;
@@ -922,33 +1133,19 @@ static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg)
arg->valid |= FATTR_GID, arg->gid = iattr->ia_gid;
if (ivalid & ATTR_SIZE)
arg->valid |= FATTR_SIZE, arg->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)) {
- arg->valid |= FATTR_ATIME | FATTR_MTIME;
+ if (ivalid & ATTR_ATIME) {
+ arg->valid |= FATTR_ATIME;
arg->atime = iattr->ia_atime.tv_sec;
- arg->mtime = iattr->ia_mtime.tv_sec;
+ arg->atimensec = iattr->ia_atime.tv_nsec;
+ if (!(ivalid & ATTR_ATIME_SET))
+ arg->valid |= FATTR_ATIME_NOW;
}
- if (ivalid & ATTR_FILE) {
- struct fuse_file *ff = iattr->ia_file->private_data;
- arg->valid |= FATTR_FH;
- arg->fh = ff->fh;
- }
-}
-
-static void fuse_vmtruncate(struct inode *inode, loff_t offset)
-{
- struct fuse_conn *fc = get_fuse_conn(inode);
- int need_trunc;
-
- spin_lock(&fc->lock);
- need_trunc = inode->i_size > offset;
- i_size_write(inode, offset);
- spin_unlock(&fc->lock);
-
- if (need_trunc) {
- struct address_space *mapping = inode->i_mapping;
- unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
- truncate_inode_pages(mapping, offset);
+ if ((ivalid & ATTR_MTIME) && update_mtime(ivalid)) {
+ arg->valid |= FATTR_MTIME;
+ arg->mtime = iattr->ia_mtime.tv_sec;
+ arg->mtimensec = iattr->ia_mtime.tv_nsec;
+ if (!(ivalid & ATTR_MTIME_SET))
+ arg->valid |= FATTR_MTIME_NOW;
}
}
@@ -960,16 +1157,18 @@ static void fuse_vmtruncate(struct inode *inode, loff_t offset)
* vmtruncate() doesn't allow for this case, so do the rlimit checking
* and the actual truncation by hand.
*/
-static int fuse_setattr(struct dentry *entry, struct iattr *attr)
+static int fuse_do_setattr(struct dentry *entry, struct iattr *attr,
+ struct file *file)
{
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 (!fuse_allow_task(fc, current))
+ return -EACCES;
if (fc->flags & FUSE_DEFAULT_PERMISSIONS) {
err = inode_change_ok(inode, attr);
@@ -977,9 +1176,13 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr)
return err;
}
+ if (fc->atomic_o_trunc)
+ return 0;
+
if (attr->ia_valid & ATTR_SIZE) {
unsigned long limit;
- is_truncate = 1;
+ if (IS_SWAPFILE(inode))
+ return -ETXTBSY;
limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
if (limit != RLIM_INFINITY && attr->ia_size > (loff_t) limit) {
send_sig(SIGXFSZ, current, 0);
@@ -992,44 +1195,65 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr)
return PTR_ERR(req);
memset(&inarg, 0, sizeof(inarg));
+ memset(&outarg, 0, sizeof(outarg));
iattr_to_fattr(attr, &inarg);
+ if (file) {
+ struct fuse_file *ff = file->private_data;
+ inarg.valid |= FATTR_FH;
+ inarg.fh = ff->fh;
+ }
+ if (attr->ia_valid & ATTR_SIZE) {
+ /* For mandatory locking in truncate */
+ inarg.valid |= FATTR_LOCKOWNER;
+ inarg.lock_owner = fuse_lock_owner_id(fc, current->files);
+ }
req->in.h.opcode = FUSE_SETATTR;
req->in.h.nodeid = get_node_id(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);
+ if (fc->minor < 9)
+ req->out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE;
+ else
+ 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)
- fuse_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);
+ if (err) {
+ if (err == -EINTR)
+ fuse_invalidate_attr(inode);
+ return err;
+ }
- return err;
+ if ((inode->i_mode ^ outarg.attr.mode) & S_IFMT) {
+ make_bad_inode(inode);
+ return -EIO;
+ }
+
+ fuse_change_attributes(inode, &outarg.attr, attr_timeout(&outarg), 0);
+ return 0;
+}
+
+static int fuse_setattr(struct dentry *entry, struct iattr *attr)
+{
+ if (attr->ia_valid & ATTR_FILE)
+ return fuse_do_setattr(entry, attr, attr->ia_file);
+ else
+ return fuse_do_setattr(entry, attr, NULL);
}
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);
+ struct fuse_conn *fc = get_fuse_conn(inode);
- return err;
+ if (!fuse_allow_task(fc, current))
+ return -EACCES;
+
+ return fuse_update_attributes(inode, stat, NULL, NULL);
}
static int fuse_setxattr(struct dentry *entry, const char *name,
@@ -1129,6 +1353,9 @@ static ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size)
struct fuse_getxattr_out outarg;
ssize_t ret;
+ if (!fuse_allow_task(fc, current))
+ return -EACCES;
+
if (fc->no_listxattr)
return -EOPNOTSUPP;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 51a6588..f9f06a5 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1,6 +1,6 @@
/*
FUSE: Filesystem in Userspace
- Copyright (C) 2001-2006 Miklos Szeredi <miklos@szeredi.hu>
+ Copyright (C) 2001-2008 Miklos Szeredi <miklos@szeredi.hu>
This program can be distributed under the terms of the GNU GPL.
See the file COPYING.
@@ -27,7 +27,9 @@ static int fuse_send_open(struct inode *inode, struct file *file, int isdir,
return PTR_ERR(req);
memset(&inarg, 0, sizeof(inarg));
- inarg.flags = file->f_flags & ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
+ inarg.flags = file->f_flags & ~(O_CREAT | O_EXCL | O_NOCTTY);
+ if (!fc->atomic_o_trunc)
+ inarg.flags &= ~O_TRUNC;
req->in.h.opcode = isdir ? FUSE_OPENDIR : FUSE_OPEN;
req->in.h.nodeid = get_node_id(inode);
req->in.numargs = 1;
@@ -43,7 +45,7 @@ static int fuse_send_open(struct inode *inode, struct file *file, int isdir,
return err;
}
-struct fuse_file *fuse_file_alloc(void)
+struct fuse_file *fuse_file_alloc(struct fuse_conn *fc)
{
struct fuse_file *ff;
ff = kmalloc(sizeof(struct fuse_file), GFP_KERNEL);
@@ -52,6 +54,12 @@ struct fuse_file *fuse_file_alloc(void)
if (!ff->reserved_req) {
kfree(ff);
ff = NULL;
+ } else {
+ INIT_LIST_HEAD(&ff->write_entry);
+ atomic_set(&ff->count, 0);
+ spin_lock(&fc->lock);
+ ff->kh = ++fc->khctr;
+ spin_unlock(&fc->lock);
}
}
return ff;
@@ -63,19 +71,46 @@ void fuse_file_free(struct fuse_file *ff)
kfree(ff);
}
+static struct fuse_file *fuse_file_get(struct fuse_file *ff)
+{
+ atomic_inc(&ff->count);
+ return ff;
+}
+
+static void fuse_release_end(struct fuse_conn *fc, struct fuse_req *req)
+{
+ dput(req->misc.release.dentry);
+ mntput(req->misc.release.vfsmount);
+}
+
+static void fuse_file_put(struct fuse_file *ff)
+{
+ if (atomic_dec_and_test(&ff->count)) {
+ struct fuse_req *req = ff->reserved_req;
+ struct inode *inode = req->misc.release.dentry->d_inode;
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ req->end = fuse_release_end;
+ request_send_background(fc, req);
+ kfree(ff);
+ }
+}
+
void fuse_finish_open(struct inode *inode, struct file *file,
struct fuse_file *ff, struct fuse_open_out *outarg)
{
if (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);
+ invalidate_inode_pages2(inode->i_mapping);
+ if (outarg->open_flags & FOPEN_NONSEEKABLE)
+ nonseekable_open(inode, file);
ff->fh = outarg->fh;
- file->private_data = ff;
+ file->private_data = fuse_file_get(ff);
}
int fuse_open_common(struct inode *inode, struct file *file, int isdir)
{
+ struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_open_out outarg;
struct fuse_file *ff;
int err;
@@ -88,15 +123,7 @@ int fuse_open_common(struct inode *inode, struct file *file, int isdir)
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) {
- err = fuse_do_getattr(inode);
- if (err)
- return err;
- }
-
- ff = fuse_file_alloc();
+ ff = fuse_file_alloc(fc);
if (!ff)
return -ENOMEM;
@@ -112,11 +139,10 @@ int fuse_open_common(struct inode *inode, struct file *file, int isdir)
return err;
}
-struct fuse_req *fuse_release_fill(struct fuse_file *ff, u64 nodeid, int flags,
- int opcode)
+void fuse_release_fill(struct fuse_file *ff, u64 nodeid, int flags, int opcode)
{
struct fuse_req *req = ff->reserved_req;
- struct fuse_release_in *inarg = &req->misc.release_in;
+ struct fuse_release_in *inarg = &req->misc.release.in;
inarg->fh = ff->fh;
inarg->flags = flags;
@@ -125,9 +151,6 @@ struct fuse_req *fuse_release_fill(struct fuse_file *ff, u64 nodeid, int flags,
req->in.numargs = 1;
req->in.args[0].size = sizeof(struct fuse_release_in);
req->in.args[0].value = inarg;
- kfree(ff);
-
- return req;
}
int fuse_release_common(struct inode *inode, struct file *file, int isdir)
@@ -135,15 +158,24 @@ int fuse_release_common(struct inode *inode, struct file *file, int isdir)
struct fuse_file *ff = file->private_data;
if (ff) {
struct fuse_conn *fc = get_fuse_conn(inode);
- struct fuse_req *req;
+ struct fuse_req *req = ff->reserved_req;
- req = fuse_release_fill(ff, get_node_id(inode), file->f_flags,
- isdir ? FUSE_RELEASEDIR : FUSE_RELEASE);
+ fuse_release_fill(ff, get_node_id(inode), file->f_flags,
+ isdir ? FUSE_RELEASEDIR : FUSE_RELEASE);
/* Hold vfsmount and dentry until release is finished */
- req->vfsmount = mntget(file->f_vfsmnt);
- req->dentry = dget(file->f_dentry);
- request_send_background(fc, req);
+ req->misc.release.vfsmount = mntget(file->f_vfsmnt);
+ req->misc.release.dentry = dget(file->f_dentry);
+
+ spin_lock(&fc->lock);
+ list_del(&ff->write_entry);
+ spin_unlock(&fc->lock);
+ /*
+ * Normally this will send the RELEASE request,
+ * however if some asynchronous READ or WRITE requests
+ * are outstanding, the sending will be delayed
+ */
+ fuse_file_put(ff);
}
/* Return value is ignored by VFS */
@@ -164,7 +196,7 @@ static int fuse_release(struct inode *inode, struct file *file)
* Scramble the ID space with XTEA, so that the value of the files_struct
* pointer is not exposed to userspace.
*/
-static u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id)
+u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id)
{
u32 *k = fc->scramble_key;
u64 v = (unsigned long) id;
@@ -266,12 +298,13 @@ static int fuse_fsync(struct file *file, struct dentry *de, int datasync)
void fuse_read_fill(struct fuse_req *req, struct file *file,
struct inode *inode, loff_t pos, size_t count, int opcode)
{
+ struct fuse_read_in *inarg = &req->misc.read.in;
struct fuse_file *ff = file->private_data;
- struct fuse_read_in *inarg = &req->misc.read_in;
inarg->fh = ff->fh;
inarg->offset = pos;
inarg->size = count;
+ inarg->flags = file->f_flags;
req->in.h.opcode = opcode;
req->in.h.nodeid = get_node_id(inode);
req->in.numargs = 1;
@@ -284,19 +317,45 @@ void fuse_read_fill(struct fuse_req *req, struct file *file,
}
static size_t fuse_send_read(struct fuse_req *req, struct file *file,
- struct inode *inode, loff_t pos, size_t count)
+ struct inode *inode, loff_t pos, size_t count,
+ fl_owner_t owner)
{
struct fuse_conn *fc = get_fuse_conn(inode);
+
fuse_read_fill(req, file, inode, pos, count, FUSE_READ);
+ if (owner != NULL) {
+ struct fuse_read_in *inarg = &req->misc.read.in;
+
+ inarg->read_flags |= FUSE_READ_LOCKOWNER;
+ inarg->lock_owner = fuse_lock_owner_id(fc, owner);
+ }
request_send(fc, req);
return req->out.args[0].size;
}
+static void fuse_read_update_size(struct inode *inode, loff_t size,
+ u64 attr_ver)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_inode *fi = get_fuse_inode(inode);
+
+ spin_lock(&fc->lock);
+ if (attr_ver == fi->attr_version && size < inode->i_size) {
+ fi->attr_version = ++fc->attr_version;
+ i_size_write(inode, size);
+ }
+ spin_unlock(&fc->lock);
+}
+
static int fuse_readpage(struct file *file, struct page *page)
{
struct inode *inode = page->mapping->host;
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_req *req;
+ size_t num_read;
+ loff_t pos = page_offset(page);
+ size_t count = PAGE_CACHE_SIZE;
+ u64 attr_ver;
int err;
err = -EIO;
@@ -308,14 +367,25 @@ static int fuse_readpage(struct file *file, struct page *page)
if (IS_ERR(req))
goto out;
+ attr_ver = fuse_get_attr_version(fc);
+
req->out.page_zeroing = 1;
req->num_pages = 1;
req->pages[0] = page;
- fuse_send_read(req, file, inode, page_offset(page), PAGE_CACHE_SIZE);
+ num_read = fuse_send_read(req, file, inode, pos, count, NULL);
err = req->out.h.error;
fuse_put_request(fc, req);
- if (!err)
+
+ if (!err) {
+ /*
+ * Short read means EOF. If file size is larger, truncate it
+ */
+ if (num_read < count)
+ fuse_read_update_size(inode, pos + num_read, attr_ver);
+
SetPageUptodate(page);
+ }
+
fuse_invalidate_attr(inode); /* atime changed */
out:
unlock_page(page);
@@ -325,8 +395,19 @@ static int fuse_readpage(struct file *file, struct page *page)
static void fuse_readpages_end(struct fuse_conn *fc, struct fuse_req *req)
{
int i;
+ size_t count = req->misc.read.in.size;
+ size_t num_read = req->out.args[0].size;
+ struct inode *inode = req->pages[0]->mapping->host;
+
+ /*
+ * Short read means EOF. If file size is larger, truncate it
+ */
+ if (!req->out.h.error && num_read < count) {
+ loff_t pos = page_offset(req->pages[0]) + num_read;
+ fuse_read_update_size(inode, pos, req->misc.read.attr_ver);
+ }
- fuse_invalidate_attr(req->pages[0]->mapping->host); /* atime changed */
+ fuse_invalidate_attr(inode); /* atime changed */
for (i = 0; i < req->num_pages; i++) {
struct page *page = req->pages[i];
@@ -336,7 +417,8 @@ static void fuse_readpages_end(struct fuse_conn *fc, struct fuse_req *req)
SetPageError(page);
unlock_page(page);
}
- fuse_put_request(fc, req);
+ if (req->ff)
+ fuse_file_put(req->ff);
}
static void fuse_send_readpages(struct fuse_req *req, struct file *file,
@@ -347,18 +429,20 @@ static void fuse_send_readpages(struct fuse_req *req, struct file *file,
size_t count = req->num_pages << PAGE_CACHE_SHIFT;
req->out.page_zeroing = 1;
fuse_read_fill(req, file, inode, pos, count, FUSE_READ);
+ req->misc.read.attr_ver = fuse_get_attr_version(fc);
if (fc->async_read) {
- get_file(file);
- req->file = file;
+ struct fuse_file *ff = file->private_data;
+ req->ff = fuse_file_get(ff);
req->end = fuse_readpages_end;
request_send_background(fc, req);
} else {
request_send(fc, req);
fuse_readpages_end(fc, req);
+ fuse_put_request(fc, req);
}
}
-struct fuse_readpages_data {
+struct fuse_fill_data {
struct fuse_req *req;
struct file *file;
struct inode *inode;
@@ -366,7 +450,7 @@ struct fuse_readpages_data {
static int fuse_readpages_fill(void *_data, struct page *page)
{
- struct fuse_readpages_data *data = _data;
+ struct fuse_fill_data *data = _data;
struct fuse_req *req = data->req;
struct inode *inode = data->inode;
struct fuse_conn *fc = get_fuse_conn(inode);
@@ -383,7 +467,7 @@ static int fuse_readpages_fill(void *_data, struct page *page)
}
}
req->pages[req->num_pages] = page;
- req->num_pages ++;
+ req->num_pages++;
return 0;
}
@@ -392,19 +476,19 @@ static int fuse_readpages(struct file *file, struct address_space *mapping,
{
struct inode *inode = mapping->host;
struct fuse_conn *fc = get_fuse_conn(inode);
- struct fuse_readpages_data data;
+ struct fuse_fill_data data;
int err;
err = -EIO;
if (is_bad_inode(inode))
- goto clean_pages_up;
+ goto out;
data.file = file;
data.inode = inode;
data.req = fuse_get_req(fc);
err = PTR_ERR(data.req);
if (IS_ERR(data.req))
- goto clean_pages_up;
+ goto out;
err = read_cache_pages(mapping, pages, fuse_readpages_fill, &data);
if (!err) {
@@ -413,55 +497,105 @@ static int fuse_readpages(struct file *file, struct address_space *mapping,
else
fuse_put_request(fc, data.req);
}
+out:
return err;
+}
-clean_pages_up:
- put_pages_list(pages);
- return err;
+static ssize_t fuse_file_aio_read(struct kiocb *iocb, char __user *buf,
+ size_t count, loff_t pos)
+{
+ struct inode *inode = iocb->ki_filp->f_mapping->host;
+
+ if (pos + count > i_size_read(inode)) {
+ int err;
+ /*
+ * If trying to read past EOF, make sure the i_size
+ * attribute is up-to-date.
+ */
+ err = fuse_update_attributes(inode, NULL, iocb->ki_filp, NULL);
+ if (err)
+ return err;
+ }
+
+ return generic_file_aio_read(iocb, buf, count, pos);
}
-static size_t fuse_send_write(struct fuse_req *req, struct file *file,
- struct inode *inode, loff_t pos, size_t count)
+static void fuse_write_fill(struct fuse_req *req, struct file *file,
+ struct inode *inode, loff_t pos, size_t count,
+ int writepage)
{
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;
+ struct fuse_write_in *inarg = &req->misc.write.in;
+ struct fuse_write_out *outarg = &req->misc.write.out;
- memset(&inarg, 0, sizeof(struct fuse_write_in));
- inarg.fh = ff->fh;
- inarg.offset = pos;
- inarg.size = count;
+ memset(inarg, 0, sizeof(struct fuse_write_in));
+ inarg->fh = ff->fh;
+ inarg->offset = pos;
+ inarg->size = count;
+ inarg->write_flags = writepage ? FUSE_WRITE_CACHE : 0;
+ inarg->flags = file->f_flags;
req->in.h.opcode = FUSE_WRITE;
req->in.h.nodeid = get_node_id(inode);
req->in.argpages = 1;
req->in.numargs = 2;
- req->in.args[0].size = sizeof(struct fuse_write_in);
- req->in.args[0].value = &inarg;
+ if (fc->minor < 9)
+ req->in.args[0].size = FUSE_COMPAT_WRITE_IN_SIZE;
+ else
+ 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;
+ req->out.args[0].value = outarg;
+}
+
+static size_t fuse_send_write(struct fuse_req *req, struct file *file,
+ struct inode *inode, loff_t pos, size_t count,
+ fl_owner_t owner)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ fuse_write_fill(req, file, inode, pos, count, 0);
+ if (owner != NULL) {
+ struct fuse_write_in *inarg = &req->misc.write.in;
+ inarg->write_flags |= FUSE_WRITE_LOCKOWNER;
+ inarg->lock_owner = fuse_lock_owner_id(fc, owner);
+ }
request_send(fc, req);
- return outarg.size;
+ return req->misc.write.out.size;
}
-static int fuse_prepare_write(struct file *file, struct page *page,
- unsigned offset, unsigned to)
+static int fuse_write_begin(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned flags,
+ struct page **pagep, void **fsdata)
{
- /* No op */
+ pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+
+ *pagep = grab_cache_page_write_begin(mapping, index, flags);
+ if (!*pagep)
+ return -ENOMEM;
return 0;
}
-static int fuse_commit_write(struct file *file, struct page *page,
- unsigned offset, unsigned to)
+static void fuse_write_update_size(struct inode *inode, loff_t pos)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_inode *fi = get_fuse_inode(inode);
+
+ spin_lock(&fc->lock);
+ fi->attr_version = ++fc->attr_version;
+ if (pos > inode->i_size)
+ i_size_write(inode, pos);
+ spin_unlock(&fc->lock);
+}
+
+static int fuse_buffered_write(struct file *file, struct inode *inode,
+ loff_t pos, unsigned count, struct page *page)
{
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 = page_offset(page) + offset;
+ unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
struct fuse_req *req;
if (is_bad_inode(inode))
@@ -474,25 +608,34 @@ static int fuse_commit_write(struct file *file, struct page *page,
req->num_pages = 1;
req->pages[0] = page;
req->page_offset = offset;
- nres = fuse_send_write(req, file, inode, pos, count);
+ nres = fuse_send_write(req, file, inode, pos, count, NULL);
err = req->out.h.error;
fuse_put_request(fc, req);
- if (!err && nres != count)
+ if (!err && !nres)
err = -EIO;
if (!err) {
- pos += count;
- spin_lock(&fc->lock);
- if (pos > inode->i_size)
- i_size_write(inode, pos);
- spin_unlock(&fc->lock);
-
- if (offset == 0 && to == PAGE_CACHE_SIZE) {
- clear_page_dirty(page);
+ pos += nres;
+ fuse_write_update_size(inode, pos);
+ if (count == PAGE_CACHE_SIZE)
SetPageUptodate(page);
- }
}
fuse_invalidate_attr(inode);
- return err;
+ return err ? err : nres;
+}
+
+static int fuse_write_end(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
+{
+ struct inode *inode = mapping->host;
+ int res = 0;
+
+ if (copied)
+ res = fuse_buffered_write(file, inode, pos, copied, page);
+
+ unlock_page(page);
+ page_cache_release(page);
+ return res;
}
static void fuse_release_user_pages(struct fuse_req *req, int write)
@@ -520,7 +663,7 @@ static int fuse_get_user_pages(struct fuse_req *req, const char __user *buf,
nbytes = min(nbytes, (unsigned) FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT);
npages = (nbytes + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
- npages = min(max(npages, 1), FUSE_MAX_PAGES_PER_REQ);
+ npages = clamp(npages, 1, 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);
@@ -552,18 +695,21 @@ static ssize_t fuse_direct_io(struct file *file, const char __user *buf,
while (count) {
size_t nres;
- size_t nbytes = min(count, nmax);
- int err = fuse_get_user_pages(req, buf, nbytes, !write);
+ size_t nbytes_limit = min(count, nmax);
+ size_t nbytes;
+ int err = fuse_get_user_pages(req, buf, nbytes_limit, !write);
if (err) {
res = err;
break;
}
nbytes = (req->num_pages << PAGE_SHIFT) - req->page_offset;
- nbytes = min(count, nbytes);
+ nbytes = min(nbytes_limit, nbytes);
if (write)
- nres = fuse_send_write(req, file, inode, pos, nbytes);
+ nres = fuse_send_write(req, file, inode, pos, nbytes,
+ current->files);
else
- nres = fuse_send_read(req, file, inode, pos, nbytes);
+ nres = fuse_send_read(req, file, inode, pos, nbytes,
+ current->files);
fuse_release_user_pages(req, !write);
if (req->out.h.error) {
if (!res)
@@ -588,12 +734,8 @@ static ssize_t fuse_direct_io(struct file *file, const char __user *buf,
}
fuse_put_request(fc, req);
if (res > 0) {
- if (write) {
- spin_lock(&fc->lock);
- if (pos > inode->i_size)
- i_size_write(inode, pos);
- spin_unlock(&fc->lock);
- }
+ if (write)
+ fuse_write_update_size(inode, pos);
*ppos = pos;
}
fuse_invalidate_attr(inode);
@@ -614,7 +756,9 @@ static ssize_t fuse_direct_write(struct file *file, const char __user *buf,
ssize_t res;
/* Don't allow parallel writes to the same file */
mutex_lock(&inode->i_mutex);
- res = fuse_direct_io(file, buf, count, ppos, 1);
+ res = generic_write_checks(file, ppos, &count, 0);
+ if (!res)
+ res = fuse_direct_io(file, buf, count, ppos, 1);
mutex_unlock(&inode->i_mutex);
return res;
}
@@ -663,7 +807,8 @@ static int convert_fuse_file_lock(const struct fuse_file_lock *ffl,
}
static void fuse_lk_fill(struct fuse_req *req, struct file *file,
- const struct file_lock *fl, int opcode, pid_t pid)
+ const struct file_lock *fl, int opcode, pid_t pid,
+ int flock)
{
struct inode *inode = file->f_dentry->d_inode;
struct fuse_conn *fc = get_fuse_conn(inode);
@@ -676,6 +821,8 @@ static void fuse_lk_fill(struct fuse_req *req, struct file *file,
arg->lk.end = fl->fl_end;
arg->lk.type = fl->fl_type;
arg->lk.pid = pid;
+ if (flock)
+ arg->lk_flags |= FUSE_LK_FLOCK;
req->in.h.opcode = opcode;
req->in.h.nodeid = get_node_id(inode);
req->in.numargs = 1;
@@ -695,7 +842,7 @@ static int fuse_getlk(struct file *file, struct file_lock *fl)
if (IS_ERR(req))
return PTR_ERR(req);
- fuse_lk_fill(req, file, fl, FUSE_GETLK, 0);
+ fuse_lk_fill(req, file, fl, FUSE_GETLK, 0, 0);
req->out.numargs = 1;
req->out.args[0].size = sizeof(outarg);
req->out.args[0].value = &outarg;
@@ -708,7 +855,7 @@ static int fuse_getlk(struct file *file, struct file_lock *fl)
return err;
}
-static int fuse_setlk(struct file *file, struct file_lock *fl)
+static int fuse_setlk(struct file *file, struct file_lock *fl, int flock)
{
struct inode *inode = file->f_dentry->d_inode;
struct fuse_conn *fc = get_fuse_conn(inode);
@@ -725,7 +872,7 @@ static int fuse_setlk(struct file *file, struct file_lock *fl)
if (IS_ERR(req))
return PTR_ERR(req);
- fuse_lk_fill(req, file, fl, opcode, pid);
+ fuse_lk_fill(req, file, fl, opcode, pid, flock);
request_send(fc, req);
err = req->out.h.error;
/* locking is restartable */
@@ -751,14 +898,96 @@ static int fuse_file_lock(struct file *file, int cmd, struct file_lock *fl)
if (fc->no_lock)
err = posix_lock_file_wait(file, fl);
else
- err = fuse_setlk(file, fl);
+ err = fuse_setlk(file, fl, 0);
}
return err;
}
+static int fuse_file_flock(struct file *file, int cmd, struct file_lock *fl)
+{
+ struct inode *inode = file->f_dentry->d_inode;
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ int err;
+
+ if (fc->no_lock) {
+ err = flock_lock_file_wait(file, fl);
+ } else {
+ /* emulate flock with POSIX locks */
+ fl->fl_owner = (fl_owner_t) file;
+ err = fuse_setlk(file, fl, 1);
+ }
+
+ return err;
+}
+
+static sector_t fuse_bmap(struct address_space *mapping, sector_t block)
+{
+ struct inode *inode = mapping->host;
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_req *req;
+ struct fuse_bmap_in inarg;
+ struct fuse_bmap_out outarg;
+ int err;
+
+ if (!inode->i_sb->s_bdev || fc->no_bmap)
+ return 0;
+
+ req = fuse_get_req(fc);
+ if (IS_ERR(req))
+ return 0;
+
+ memset(&inarg, 0, sizeof(inarg));
+ inarg.block = block;
+ inarg.blocksize = inode->i_sb->s_blocksize;
+ req->in.h.opcode = FUSE_BMAP;
+ req->in.h.nodeid = get_node_id(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 == -ENOSYS)
+ fc->no_bmap = 1;
+
+ return err ? 0 : outarg.block;
+}
+
+static loff_t fuse_file_llseek(struct file *file, loff_t offset, int origin)
+{
+ loff_t retval;
+ struct inode *inode = file->f_dentry->d_inode;
+
+ mutex_lock(&inode->i_mutex);
+ switch (origin) {
+ case SEEK_END:
+ retval = fuse_update_attributes(inode, NULL, file, NULL);
+ if (retval)
+ return retval;
+ offset += i_size_read(inode);
+ break;
+ case SEEK_CUR:
+ offset += file->f_pos;
+ }
+ retval = -EINVAL;
+ if (offset >= 0 && offset <= inode->i_sb->s_maxbytes) {
+ if (offset != file->f_pos) {
+ file->f_pos = offset;
+ file->f_version = 0;
+ }
+ retval = offset;
+ }
+ mutex_unlock(&inode->i_mutex);
+ return retval;
+}
+
static const struct file_operations fuse_file_operations = {
- .llseek = generic_file_llseek,
+ .llseek = fuse_file_llseek,
.read = generic_file_read,
+ .aio_read = fuse_file_aio_read,
.write = generic_file_write,
.mmap = fuse_file_mmap,
.open = fuse_open,
@@ -766,11 +995,12 @@ static const struct file_operations fuse_file_operations = {
.release = fuse_release,
.fsync = fuse_fsync,
.lock = fuse_file_lock,
+ .flock = fuse_file_flock,
.sendfile = generic_file_sendfile,
};
static const struct file_operations fuse_direct_io_file_operations = {
- .llseek = generic_file_llseek,
+ .llseek = fuse_file_llseek,
.read = fuse_direct_read,
.write = fuse_direct_write,
.open = fuse_open,
@@ -778,19 +1008,21 @@ static const struct file_operations fuse_direct_io_file_operations = {
.release = fuse_release,
.fsync = fuse_fsync,
.lock = fuse_file_lock,
+ .flock = fuse_file_flock,
/* no mmap and sendfile */
};
-static const 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,
+static const struct address_space_operations_ext fuse_file_aops = {
+ .orig_aops.readpage = fuse_readpage,
+ .write_begin = fuse_write_begin,
+ .write_end = fuse_write_end,
+ .orig_aops.readpages = fuse_readpages,
+ .orig_aops.set_page_dirty = fuse_set_page_dirty,
+ .orig_aops.bmap = fuse_bmap,
};
void fuse_init_file_inode(struct inode *inode)
{
inode->i_fop = &fuse_file_operations;
- inode->i_data.a_ops = &fuse_file_aops;
+ inode->i_data.a_ops = (struct address_space_operations *)&fuse_file_aops;
}
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 69c7750..08dd7f5 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -1,11 +1,14 @@
/*
FUSE: Filesystem in Userspace
- Copyright (C) 2001-2006 Miklos Szeredi <miklos@szeredi.hu>
+ Copyright (C) 2001-2008 Miklos Szeredi <miklos@szeredi.hu>
This program can be distributed under the terms of the GNU GPL.
See the file COPYING.
*/
+#ifndef _FS_FUSE_I_H
+#define _FS_FUSE_I_H
+
#include <linux/fuse.h>
#include <linux/fs.h>
#include <linux/mount.h>
@@ -60,6 +63,16 @@ struct fuse_inode {
/** Time in jiffies until the file attributes are valid */
u64 i_time;
+
+ /** The sticky bit in inode->i_mode may have been removed, so
+ preserve the original mode */
+ mode_t orig_i_mode;
+
+ /** Version of last attribute change */
+ u64 attr_version;
+
+ /** Files usable in writepage. Protected by fc->lock */
+ struct list_head write_files;
};
/** FUSE specific file data */
@@ -67,8 +80,17 @@ struct fuse_file {
/** Request reserved for flush and release */
struct fuse_req *reserved_req;
+ /** Kernel file handle guaranteed to be unique */
+ u64 kh;
+
/** File handle used by userspace */
u64 fh;
+
+ /** Refcount */
+ atomic_t count;
+
+ /** Entry on inode's write_files list */
+ struct list_head write_entry;
};
/** One input argument of a request */
@@ -196,10 +218,21 @@ struct fuse_req {
/** Data for asynchronous requests */
union {
struct fuse_forget_in forget_in;
- struct fuse_release_in release_in;
+ struct {
+ struct fuse_release_in in;
+ struct vfsmount *vfsmount;
+ struct dentry *dentry;
+ } release;
struct fuse_init_in init_in;
struct fuse_init_out init_out;
- struct fuse_read_in read_in;
+ struct {
+ struct fuse_read_in in;
+ u64 attr_ver;
+ } read;
+ struct {
+ struct fuse_write_in in;
+ struct fuse_write_out out;
+ } write;
struct fuse_lk_in lk_in;
} misc;
@@ -213,13 +246,7 @@ struct fuse_req {
unsigned page_offset;
/** File used in the request (or NULL) */
- struct file *file;
-
- /** vfsmount used in release */
- struct vfsmount *vfsmount;
-
- /** dentry used in release */
- struct dentry *dentry;
+ struct fuse_file *ff;
/** Request completion callback */
void (*end)(struct fuse_conn *, struct fuse_req *);
@@ -239,6 +266,9 @@ struct fuse_conn {
/** Lock protecting accessess to members of this structure */
spinlock_t lock;
+ /** Mutex protecting against directory alias creation */
+ struct mutex inst_mutex;
+
/** Refcount */
atomic_t count;
@@ -269,9 +299,18 @@ struct fuse_conn {
/** The list of requests under I/O */
struct list_head io;
+ /** The next unique kernel file handle */
+ u64 khctr;
+
/** Number of requests currently in the background */
unsigned num_background;
+ /** Number of background requests currently queued for userspace */
+ unsigned active_background;
+
+ /** The list of background requests set aside for later queuing */
+ struct list_head bg_queue;
+
/** Pending interrupts */
struct list_head interrupts;
@@ -283,6 +322,9 @@ struct fuse_conn {
/** waitq for blocked connection */
wait_queue_head_t blocked_waitq;
+ /** waitq for reserved requests */
+ wait_queue_head_t reserved_req_waitq;
+
/** The next unique request id */
u64 reqctr;
@@ -293,10 +335,16 @@ struct fuse_conn {
/** 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;
+ unsigned conn_error:1;
+
+ /** Connection successful. Only set in INIT */
+ unsigned conn_init:1;
/** Do readpages asynchronously? Only set in INIT */
- unsigned async_read : 1;
+ unsigned async_read:1;
+
+ /** Do not send separate SETATTR request before open(O_TRUNC) */
+ unsigned atomic_o_trunc:1;
/*
* The following bitfields are only for optimization purposes
@@ -304,37 +352,40 @@ struct fuse_conn {
*/
/** Is fsync not implemented by fs? */
- unsigned no_fsync : 1;
+ unsigned no_fsync:1;
/** Is fsyncdir not implemented by fs? */
- unsigned no_fsyncdir : 1;
+ unsigned no_fsyncdir:1;
/** Is flush not implemented by fs? */
- unsigned no_flush : 1;
+ unsigned no_flush:1;
/** Is setxattr not implemented by fs? */
- unsigned no_setxattr : 1;
+ unsigned no_setxattr:1;
/** Is getxattr not implemented by fs? */
- unsigned no_getxattr : 1;
+ unsigned no_getxattr:1;
/** Is listxattr not implemented by fs? */
- unsigned no_listxattr : 1;
+ unsigned no_listxattr:1;
/** Is removexattr not implemented by fs? */
- unsigned no_removexattr : 1;
+ unsigned no_removexattr:1;
/** Are file locking primitives not implemented by fs? */
- unsigned no_lock : 1;
+ unsigned no_lock:1;
/** Is access not implemented by fs? */
- unsigned no_access : 1;
+ unsigned no_access:1;
/** Is create not implemented by fs? */
- unsigned no_create : 1;
+ unsigned no_create:1;
/** Is interrupt not implemented by fs? */
- unsigned no_interrupt : 1;
+ unsigned no_interrupt:1;
+
+ /** Is bmap not implemented by fs? */
+ unsigned no_bmap:1;
/** The number of requests waiting for completion */
atomic_t num_waiting;
@@ -362,6 +413,12 @@ struct fuse_conn {
/** Key for lock owner ID scrambling */
u32 scramble_key[4];
+
+ /** Reserved request for the DESTROY message */
+ struct fuse_req *destroy_req;
+
+ /** Version counter for attribute changes */
+ u64 attr_version;
};
static inline struct fuse_conn *get_fuse_conn_super(struct super_block *sb)
@@ -390,14 +447,15 @@ extern const struct file_operations fuse_dev_operations;
/**
* Get a filled in inode
*/
-struct inode *fuse_iget(struct super_block *sb, unsigned long nodeid,
- int generation, struct fuse_attr *attr);
+struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
+ int generation, struct fuse_attr *attr,
+ u64 attr_valid, u64 attr_version);
/**
* Send FORGET command
*/
void fuse_send_forget(struct fuse_conn *fc, struct fuse_req *req,
- unsigned long nodeid, u64 nlookup);
+ u64 nodeid, u64 nlookup);
/**
* Initialize READ or READDIR request
@@ -410,14 +468,14 @@ void fuse_read_fill(struct fuse_req *req, struct file *file,
*/
int fuse_open_common(struct inode *inode, struct file *file, int isdir);
-struct fuse_file *fuse_file_alloc(void);
+struct fuse_file *fuse_file_alloc(struct fuse_conn *fc);
void fuse_file_free(struct fuse_file *ff);
void fuse_finish_open(struct inode *inode, struct file *file,
struct fuse_file *ff, struct fuse_open_out *outarg);
-/** */
-struct fuse_req *fuse_release_fill(struct fuse_file *ff, u64 nodeid, int flags,
- int opcode);
+/** Fill in ff->reserved_req with a RELEASE request */
+void fuse_release_fill(struct fuse_file *ff, u64 nodeid, int flags, int opcode);
+
/**
* Send RELEASE or RELEASEDIR request
*/
@@ -452,7 +510,8 @@ void fuse_init_symlink(struct inode *inode);
/**
* Change attributes of an inode
*/
-void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr);
+void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
+ u64 attr_valid, u64 attr_version);
/**
* Initialize the client device
@@ -512,11 +571,6 @@ void request_send_background(struct fuse_conn *fc, struct fuse_req *req);
void fuse_abort_conn(struct fuse_conn *fc);
/**
- * Get the attributes of a file
- */
-int fuse_do_getattr(struct inode *inode);
-
-/**
* Invalidate inode attributes
*/
void fuse_invalidate_attr(struct inode *inode);
@@ -540,3 +594,23 @@ int fuse_ctl_add_conn(struct fuse_conn *fc);
* Remove connection from control filesystem
*/
void fuse_ctl_remove_conn(struct fuse_conn *fc);
+
+/**
+ * Is file type valid?
+ */
+int fuse_valid_type(int m);
+
+/**
+ * Is task allowed to perform filesystem operation?
+ */
+int fuse_allow_task(struct fuse_conn *fc, struct task_struct *task);
+
+u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id);
+
+int fuse_update_attributes(struct inode *inode, struct kstat *stat,
+ struct file *file, bool *refreshed);
+
+u64 fuse_get_attr_version(struct fuse_conn *fc);
+
+#endif /* _FS_FUSE_I_H */
+
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 3407d2e..eb335f6 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1,6 +1,6 @@
/*
FUSE: Filesystem in Userspace
- Copyright (C) 2001-2006 Miklos Szeredi <miklos@szeredi.hu>
+ Copyright (C) 2001-2008 Miklos Szeredi <miklos@szeredi.hu>
This program can be distributed under the terms of the GNU GPL.
See the file COPYING.
@@ -22,23 +22,26 @@ MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
MODULE_DESCRIPTION("Filesystem in Userspace");
MODULE_LICENSE("GPL");
-static kmem_cache_t *fuse_inode_cachep;
+static struct kmem_cache *fuse_inode_cachep;
struct list_head fuse_conn_list;
DEFINE_MUTEX(fuse_mutex);
#define FUSE_SUPER_MAGIC 0x65735546
+#define FUSE_DEFAULT_BLKSIZE 512
+
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 fd_present:1;
+ unsigned rootmode_present:1;
+ unsigned user_id_present:1;
+ unsigned group_id_present:1;
unsigned flags;
unsigned max_read;
+ unsigned blksize;
};
static struct inode *fuse_alloc_inode(struct super_block *sb)
@@ -46,7 +49,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
struct inode *inode;
struct fuse_inode *fi;
- inode = kmem_cache_alloc(fuse_inode_cachep, SLAB_KERNEL);
+ inode = kmem_cache_alloc(fuse_inode_cachep, GFP_KERNEL);
if (!inode)
return NULL;
@@ -54,6 +57,8 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
fi->i_time = 0;
fi->nodeid = 0;
fi->nlookup = 0;
+ fi->attr_version = 0;
+ INIT_LIST_HEAD(&fi->write_files);
fi->forget_req = fuse_request_alloc();
if (!fi->forget_req) {
kmem_cache_free(fuse_inode_cachep, inode);
@@ -66,18 +71,14 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
static void fuse_destroy_inode(struct inode *inode)
{
struct fuse_inode *fi = get_fuse_inode(inode);
+ BUG_ON(!list_empty(&fi->write_files));
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)
+ u64 nodeid, u64 nlookup)
{
struct fuse_forget_in *inarg = &req->misc.forget_in;
inarg->nlookup = nlookup;
@@ -107,20 +108,35 @@ static int fuse_remount_fs(struct super_block *sb, int *flags, char *data)
return 0;
}
-void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr)
+static void fuse_truncate(struct address_space *mapping, loff_t offset)
+{
+ /* See vmtruncate() */
+ unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
+ truncate_inode_pages(mapping, offset);
+ unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
+}
+
+
+void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
+ u64 attr_valid, u64 attr_version)
{
struct fuse_conn *fc = get_fuse_conn(inode);
- if (S_ISREG(inode->i_mode) && i_size_read(inode) != attr->size)
- invalidate_inode_pages(inode->i_mapping);
+ struct fuse_inode *fi = get_fuse_inode(inode);
+ loff_t oldsize;
+
+ spin_lock(&fc->lock);
+ if (attr_version != 0 && fi->attr_version > attr_version) {
+ spin_unlock(&fc->lock);
+ return;
+ }
+ fi->attr_version = ++fc->attr_version;
+ fi->i_time = attr_valid;
inode->i_ino = attr->ino;
- inode->i_mode = (inode->i_mode & S_IFMT) + (attr->mode & 07777);
+ 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;
- spin_lock(&fc->lock);
- i_size_write(inode, attr->size);
- spin_unlock(&fc->lock);
inode->i_blocks = attr->blocks;
inode->i_atime.tv_sec = attr->atime;
inode->i_atime.tv_nsec = attr->atimensec;
@@ -128,6 +144,30 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr)
inode->i_mtime.tv_nsec = attr->mtimensec;
inode->i_ctime.tv_sec = attr->ctime;
inode->i_ctime.tv_nsec = attr->ctimensec;
+
+ if (attr->blksize != 0)
+ inode->i_blkbits = ilog2(attr->blksize);
+ else
+ inode->i_blkbits = inode->i_sb->s_blocksize_bits;
+
+ /*
+ * Don't set the sticky bit in i_mode, unless we want the VFS
+ * to check permissions. This prevents failures due to the
+ * check in may_delete().
+ */
+ fi->orig_i_mode = inode->i_mode;
+ if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS))
+ inode->i_mode &= ~S_ISVTX;
+
+ oldsize = inode->i_size;
+ i_size_write(inode, attr->size);
+ spin_unlock(&fc->lock);
+
+ if (S_ISREG(inode->i_mode) && oldsize != attr->size) {
+ if (attr->size < oldsize)
+ fuse_truncate(inode->i_mapping, attr->size);
+ invalidate_inode_pages2(inode->i_mapping);
+ }
}
static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr)
@@ -152,7 +192,7 @@ static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr)
static int fuse_inode_eq(struct inode *inode, void *_nodeidp)
{
- unsigned long nodeid = *(unsigned long *) _nodeidp;
+ u64 nodeid = *(u64 *) _nodeidp;
if (get_node_id(inode) == nodeid)
return 1;
else
@@ -161,18 +201,18 @@ static int fuse_inode_eq(struct inode *inode, void *_nodeidp)
static int fuse_inode_set(struct inode *inode, void *_nodeidp)
{
- unsigned long nodeid = *(unsigned long *) _nodeidp;
+ u64 nodeid = *(u64 *) _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 *fuse_iget(struct super_block *sb, u64 nodeid,
+ int generation, struct fuse_attr *attr,
+ u64 attr_valid, u64 attr_version)
{
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);
@@ -186,17 +226,18 @@ struct inode *fuse_iget(struct super_block *sb, unsigned long nodeid,
fuse_init_inode(inode, attr);
unlock_new_inode(inode);
} else if ((inode->i_mode ^ attr->mode) & S_IFMT) {
- BUG_ON(retried);
/* Inode has changed type, any I/O on the old should fail */
make_bad_inode(inode);
iput(inode);
- retried = 1;
goto retry;
}
fi = get_fuse_inode(inode);
- fi->nlookup ++;
- fuse_change_attributes(inode, attr);
+ spin_lock(&fc->lock);
+ fi->nlookup++;
+ spin_unlock(&fc->lock);
+ fuse_change_attributes(inode, attr, attr_valid, attr_version);
+
return inode;
}
@@ -206,10 +247,23 @@ static void fuse_umount_begin(struct vfsmount *vfsmnt, int flags)
fuse_abort_conn(get_fuse_conn_super(vfsmnt->mnt_sb));
}
+static void fuse_send_destroy(struct fuse_conn *fc)
+{
+ struct fuse_req *req = fc->destroy_req;
+ if (req && fc->conn_init) {
+ fc->destroy_req = NULL;
+ req->in.h.opcode = FUSE_DESTROY;
+ req->force = 1;
+ request_send(fc, req);
+ fuse_put_request(fc, req);
+ }
+}
+
static void fuse_put_super(struct super_block *sb)
{
struct fuse_conn *fc = get_fuse_conn_super(sb);
+ fuse_send_destroy(fc);
spin_lock(&fc->lock);
fc->connected = 0;
fc->blocked = 0;
@@ -218,6 +272,7 @@ static void fuse_put_super(struct super_block *sb)
kill_fasync(&fc->fasync, SIGIO, POLL_IN);
wake_up_all(&fc->waitq);
wake_up_all(&fc->blocked_waitq);
+ wake_up_all(&fc->reserved_req_waitq);
mutex_lock(&fuse_mutex);
list_del(&fc->entry);
fuse_ctl_remove_conn(fc);
@@ -247,6 +302,11 @@ static int fuse_statfs(struct dentry *dentry, struct kstatfs *buf)
struct fuse_statfs_out outarg;
int err;
+ if (!fuse_allow_task(fc, current)) {
+ buf->f_type = FUSE_SUPER_MAGIC;
+ return 0;
+ }
+
req = fuse_get_req(fc);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -254,6 +314,7 @@ static int fuse_statfs(struct dentry *dentry, struct kstatfs *buf)
memset(&outarg, 0, sizeof(outarg));
req->in.numargs = 0;
req->in.h.opcode = FUSE_STATFS;
+ req->in.h.nodeid = get_node_id(dentry->d_inode);
req->out.numargs = 1;
req->out.args[0].size =
fc->minor < 4 ? FUSE_COMPAT_STATFS_SIZE : sizeof(outarg);
@@ -274,6 +335,7 @@ enum {
OPT_DEFAULT_PERMISSIONS,
OPT_ALLOW_OTHER,
OPT_MAX_READ,
+ OPT_BLKSIZE,
OPT_ERR
};
@@ -285,14 +347,16 @@ static match_table_t tokens = {
{OPT_DEFAULT_PERMISSIONS, "default_permissions"},
{OPT_ALLOW_OTHER, "allow_other"},
{OPT_MAX_READ, "max_read=%u"},
+ {OPT_BLKSIZE, "blksize=%u"},
{OPT_ERR, NULL}
};
-static int parse_fuse_opt(char *opt, struct fuse_mount_data *d)
+static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
{
char *p;
memset(d, 0, sizeof(struct fuse_mount_data));
d->max_read = ~0;
+ d->blksize = FUSE_DEFAULT_BLKSIZE;
while ((p = strsep(&opt, ",")) != NULL) {
int token;
@@ -313,6 +377,8 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d)
case OPT_ROOTMODE:
if (match_octal(&args[0], &value))
return 0;
+ if (!fuse_valid_type(value))
+ return 0;
d->rootmode = value;
d->rootmode_present = 1;
break;
@@ -345,6 +411,12 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d)
d->max_read = value;
break;
+ case OPT_BLKSIZE:
+ if (!is_bdev || match_int(&args[0], &value))
+ return 0;
+ d->blksize = value;
+ break;
+
default:
return 0;
}
@@ -369,6 +441,9 @@ static int fuse_show_options(struct seq_file *m, struct vfsmount *mnt)
seq_puts(m, ",allow_other");
if (fc->max_read != ~0)
seq_printf(m, ",max_read=%u", fc->max_read);
+ if (mnt->mnt_sb->s_bdev &&
+ mnt->mnt_sb->s_blocksize != FUSE_DEFAULT_BLKSIZE)
+ seq_printf(m, ",blksize=%lu", mnt->mnt_sb->s_blocksize);
return 0;
}
@@ -379,18 +454,23 @@ static struct fuse_conn *new_conn(void)
fc = kzalloc(sizeof(*fc), GFP_KERNEL);
if (fc) {
spin_lock_init(&fc->lock);
+ mutex_init(&fc->inst_mutex);
atomic_set(&fc->count, 1);
init_waitqueue_head(&fc->waitq);
init_waitqueue_head(&fc->blocked_waitq);
+ init_waitqueue_head(&fc->reserved_req_waitq);
INIT_LIST_HEAD(&fc->pending);
INIT_LIST_HEAD(&fc->processing);
INIT_LIST_HEAD(&fc->io);
INIT_LIST_HEAD(&fc->interrupts);
+ INIT_LIST_HEAD(&fc->bg_queue);
atomic_set(&fc->num_waiting, 0);
fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
fc->bdi.unplug_io_fn = default_unplug_io_fn;
+ fc->khctr = 0;
fc->reqctr = 0;
fc->blocked = 1;
+ fc->attr_version = 1;
get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
}
return fc;
@@ -398,8 +478,12 @@ static struct fuse_conn *new_conn(void)
void fuse_conn_put(struct fuse_conn *fc)
{
- if (atomic_dec_and_test(&fc->count))
+ if (atomic_dec_and_test(&fc->count)) {
+ if (fc->destroy_req)
+ fuse_request_free(fc->destroy_req);
+ mutex_destroy(&fc->inst_mutex);
kfree(fc);
+ }
}
struct fuse_conn *fuse_conn_get(struct fuse_conn *fc)
@@ -415,14 +499,15 @@ static struct inode *get_root_inode(struct super_block *sb, unsigned mode)
attr.mode = mode;
attr.ino = FUSE_ROOT_ID;
- return fuse_iget(sb, 1, 0, &attr);
+ attr.nlink = 1;
+ return fuse_iget(sb, 1, 0, &attr, 0, 0);
}
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,
+ .drop_inode = generic_delete_inode,
.remount_fs = fuse_remount_fs,
.put_super = fuse_put_super,
.umount_begin = fuse_umount_begin,
@@ -445,6 +530,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
fc->async_read = 1;
if (!(arg->flags & FUSE_POSIX_LOCKS))
fc->no_lock = 1;
+ if (arg->flags & FUSE_ATOMIC_O_TRUNC)
+ fc->atomic_o_trunc = 1;
} else {
ra_pages = fc->max_read / PAGE_CACHE_SIZE;
fc->no_lock = 1;
@@ -453,8 +540,9 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
fc->bdi.ra_pages = min(fc->bdi.ra_pages, ra_pages);
fc->minor = arg->minor;
fc->max_write = arg->minor < 5 ? 4096 : arg->max_write;
+ fc->max_write = max_t(unsigned, 4096, fc->max_write);
+ fc->conn_init = 1;
}
- fuse_put_request(fc, req);
fc->blocked = 0;
wake_up_all(&fc->blocked_waitq);
}
@@ -466,7 +554,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
arg->major = FUSE_KERNEL_VERSION;
arg->minor = FUSE_KERNEL_MINOR_VERSION;
arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE;
- arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS;
+ arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC;
req->in.h.opcode = FUSE_INIT;
req->in.numargs = 1;
req->in.args[0].size = sizeof(*arg);
@@ -497,18 +585,25 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
struct dentry *root_dentry;
struct fuse_req *init_req;
int err;
+ int is_bdev = sb->s_bdev != NULL;
if (sb->s_flags & MS_MANDLOCK)
return -EINVAL;
- if (!parse_fuse_opt((char *) data, &d))
+ if (!parse_fuse_opt((char *) data, &d, is_bdev))
return -EINVAL;
- sb->s_blocksize = PAGE_CACHE_SIZE;
- sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+ if (is_bdev) {
+ if (!sb_set_blocksize(sb, d.blksize))
+ return -EINVAL;
+ } else {
+ sb->s_blocksize = PAGE_CACHE_SIZE;
+ sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+ }
sb->s_magic = FUSE_SUPER_MAGIC;
sb->s_op = &fuse_super_operations;
sb->s_maxbytes = MAX_LFS_FILESIZE;
+ sb->s_flags |= MS_HAS_NEW_AOPS;
file = fget(d.fd);
if (!file)
@@ -524,7 +619,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
fc->flags = d.flags;
fc->user_id = d.user_id;
fc->group_id = d.group_id;
- fc->max_read = d.max_read;
+ fc->max_read = max_t(unsigned, 4096, d.max_read);
/* Used by get_root_inode() */
sb->s_fs_info = fc;
@@ -544,6 +639,12 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
if (!init_req)
goto err_put_root;
+ if (is_bdev) {
+ fc->destroy_req = fuse_request_alloc();
+ if (!fc->destroy_req)
+ goto err_free_init_req;
+ }
+
mutex_lock(&fuse_mutex);
err = -EINVAL;
if (file->private_data)
@@ -572,6 +673,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
err_unlock:
mutex_unlock(&fuse_mutex);
+ err_free_init_req:
fuse_request_free(init_req);
err_put_root:
dput(root_dentry);
@@ -588,6 +690,14 @@ static int fuse_get_sb(struct file_system_type *fs_type,
return get_sb_nodev(fs_type, flags, raw_data, fuse_fill_super, mnt);
}
+static int fuse_get_sb_blk(struct file_system_type *fs_type,
+ int flags, const char *dev_name,
+ void *raw_data, struct vfsmount *mnt)
+{
+ return get_sb_bdev(fs_type, flags, dev_name, raw_data, fuse_fill_super,
+ mnt);
+}
+
static struct file_system_type fuse_fs_type = {
.owner = THIS_MODULE,
.name = "fuse",
@@ -595,13 +705,21 @@ static struct file_system_type fuse_fs_type = {
.kill_sb = kill_anon_super,
};
+static struct file_system_type fuseblk_fs_type = {
+ .owner = THIS_MODULE,
+ .name = "fuseblk",
+ .get_sb = fuse_get_sb_blk,
+ .kill_sb = kill_block_super,
+ .fs_flags = FS_REQUIRES_DEV,
+};
+
static decl_subsys(fuse, NULL, NULL);
static decl_subsys(connections, NULL, NULL);
-static void fuse_inode_init_once(void *foo, kmem_cache_t *cachep,
+static void fuse_inode_init_once(void *foo, struct kmem_cache *cachep,
unsigned long flags)
{
- struct inode * inode = foo;
+ struct inode *inode = foo;
if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
SLAB_CTOR_CONSTRUCTOR)
@@ -614,24 +732,34 @@ static int __init fuse_fs_init(void)
err = register_filesystem(&fuse_fs_type);
if (err)
- printk("fuse: failed to register filesystem\n");
- else {
- fuse_inode_cachep = kmem_cache_create("fuse_inode",
- sizeof(struct fuse_inode),
- 0, SLAB_HWCACHE_ALIGN,
- fuse_inode_init_once, NULL);
- if (!fuse_inode_cachep) {
- unregister_filesystem(&fuse_fs_type);
- err = -ENOMEM;
- }
- }
+ goto out;
+ err = register_filesystem(&fuseblk_fs_type);
+ if (err)
+ goto out_unreg;
+
+ fuse_inode_cachep = kmem_cache_create("fuse_inode",
+ sizeof(struct fuse_inode),
+ 0, SLAB_HWCACHE_ALIGN,
+ fuse_inode_init_once, NULL);
+ err = -ENOMEM;
+ if (!fuse_inode_cachep)
+ goto out_unreg2;
+
+ return 0;
+
+ out_unreg2:
+ unregister_filesystem(&fuseblk_fs_type);
+ out_unreg:
+ unregister_filesystem(&fuse_fs_type);
+ out:
return err;
}
static void fuse_fs_cleanup(void)
{
unregister_filesystem(&fuse_fs_type);
+ unregister_filesystem(&fuseblk_fs_type);
kmem_cache_destroy(fuse_inode_cachep);
}
@@ -667,7 +795,7 @@ static int __init fuse_init(void)
{
int res;
- printk("fuse init (API version %i.%i)\n",
+ printk(KERN_INFO "fuse init (API version %i.%i)\n",
FUSE_KERNEL_VERSION, FUSE_KERNEL_MINOR_VERSION);
INIT_LIST_HEAD(&fuse_conn_list);
diff --git a/include/linux/fuse.h b/include/linux/fuse.h
index 9fc48a6..939a1ba 100644
--- a/include/linux/fuse.h
+++ b/include/linux/fuse.h
@@ -6,7 +6,24 @@
See the file COPYING.
*/
-/* This file defines the kernel interface of FUSE */
+/*
+ * This file defines the kernel interface of FUSE
+ *
+ * Protocol changelog:
+ *
+ * 7.9:
+ * - new fuse_getattr_in input argument of GETATTR
+ * - add lk_flags in fuse_lk_in
+ * - add lock_owner field to fuse_setattr_in, fuse_read_in and fuse_write_in
+ * - add blksize field to fuse_attr
+ * - add file flags field to fuse_read_in and fuse_write_in
+ *
+ * 7.10
+ * - add nonseekable open flag
+ */
+
+#ifndef _LINUX_FUSE_H
+#define _LINUX_FUSE_H
#include <asm/types.h>
#include <linux/major.h>
@@ -15,7 +32,7 @@
#define FUSE_KERNEL_VERSION 7
/** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 7
+#define FUSE_KERNEL_MINOR_VERSION 10
/** The node ID of the root inode */
#define FUSE_ROOT_ID 1
@@ -44,6 +61,8 @@ struct fuse_attr {
__u32 uid;
__u32 gid;
__u32 rdev;
+ __u32 blksize;
+ __u32 padding;
};
struct fuse_kstatfs {
@@ -76,21 +95,57 @@ struct fuse_file_lock {
#define FATTR_ATIME (1 << 4)
#define FATTR_MTIME (1 << 5)
#define FATTR_FH (1 << 6)
+#define FATTR_ATIME_NOW (1 << 7)
+#define FATTR_MTIME_NOW (1 << 8)
+#define FATTR_LOCKOWNER (1 << 9)
/**
* Flags returned by the OPEN request
*
* FOPEN_DIRECT_IO: bypass page cache for this open file
* FOPEN_KEEP_CACHE: don't invalidate the data cache on open
+ * FOPEN_NONSEEKABLE: the file is not seekable
*/
#define FOPEN_DIRECT_IO (1 << 0)
#define FOPEN_KEEP_CACHE (1 << 1)
+#define FOPEN_NONSEEKABLE (1 << 2)
/**
* INIT request/reply flags
*/
#define FUSE_ASYNC_READ (1 << 0)
#define FUSE_POSIX_LOCKS (1 << 1)
+#define FUSE_FILE_OPS (1 << 2)
+#define FUSE_ATOMIC_O_TRUNC (1 << 3)
+
+/**
+ * Release flags
+ */
+#define FUSE_RELEASE_FLUSH (1 << 0)
+
+/**
+ * Getattr flags
+ */
+#define FUSE_GETATTR_FH (1 << 0)
+
+/**
+ * Lock flags
+ */
+#define FUSE_LK_FLOCK (1 << 0)
+
+/**
+ * WRITE flags
+ *
+ * FUSE_WRITE_CACHE: delayed write from page cache, file handle is guessed
+ * FUSE_WRITE_LOCKOWNER: lock_owner field is valid
+ */
+#define FUSE_WRITE_CACHE (1 << 0)
+#define FUSE_WRITE_LOCKOWNER (1 << 1)
+
+/**
+ * Read flags
+ */
+#define FUSE_READ_LOCKOWNER (1 << 1)
enum fuse_opcode {
FUSE_LOOKUP = 1,
@@ -127,11 +182,19 @@ enum fuse_opcode {
FUSE_ACCESS = 34,
FUSE_CREATE = 35,
FUSE_INTERRUPT = 36,
+ FUSE_BMAP = 37,
+ FUSE_DESTROY = 38,
+};
+
+enum fuse_notify_code {
+ FUSE_NOTIFY_CODE_MAX,
};
/* The read buffer is required to be at least 8k, but may be much larger */
#define FUSE_MIN_READ_BUFFER 8192
+#define FUSE_COMPAT_ENTRY_OUT_SIZE 120
+
struct fuse_entry_out {
__u64 nodeid; /* Inode ID */
__u64 generation; /* Inode generation: nodeid:gen must
@@ -147,6 +210,14 @@ struct fuse_forget_in {
__u64 nlookup;
};
+struct fuse_getattr_in {
+ __u32 getattr_flags;
+ __u32 dummy;
+ __u64 fh;
+};
+
+#define FUSE_COMPAT_ATTR_OUT_SIZE 96
+
struct fuse_attr_out {
__u64 attr_valid; /* Cache timeout for the attributes */
__u32 attr_valid_nsec;
@@ -177,7 +248,7 @@ struct fuse_setattr_in {
__u32 padding;
__u64 fh;
__u64 size;
- __u64 unused1;
+ __u64 lock_owner;
__u64 atime;
__u64 mtime;
__u64 unused2;
@@ -205,12 +276,13 @@ struct fuse_open_out {
struct fuse_release_in {
__u64 fh;
__u32 flags;
- __u32 padding;
+ __u32 release_flags;
+ __u64 lock_owner;
};
struct fuse_flush_in {
__u64 fh;
- __u32 flush_flags;
+ __u32 unused;
__u32 padding;
__u64 lock_owner;
};
@@ -219,14 +291,22 @@ struct fuse_read_in {
__u64 fh;
__u64 offset;
__u32 size;
+ __u32 read_flags;
+ __u64 lock_owner;
+ __u32 flags;
__u32 padding;
};
+#define FUSE_COMPAT_WRITE_IN_SIZE 24
+
struct fuse_write_in {
__u64 fh;
__u64 offset;
__u32 size;
__u32 write_flags;
+ __u64 lock_owner;
+ __u32 flags;
+ __u32 padding;
};
struct fuse_write_out {
@@ -265,6 +345,8 @@ struct fuse_lk_in {
__u64 fh;
__u64 owner;
struct fuse_file_lock lk;
+ __u32 lk_flags;
+ __u32 padding;
};
struct fuse_lk_out {
@@ -296,6 +378,16 @@ struct fuse_interrupt_in {
__u64 unique;
};
+struct fuse_bmap_in {
+ __u64 block;
+ __u32 blocksize;
+ __u32 padding;
+};
+
+struct fuse_bmap_out {
+ __u64 block;
+};
+
struct fuse_in_header {
__u32 len;
__u32 opcode;
@@ -325,3 +417,5 @@ struct fuse_dirent {
#define FUSE_DIRENT_ALIGN(x) (((x) + sizeof(__u64) - 1) & ~(sizeof(__u64) - 1))
#define FUSE_DIRENT_SIZE(d) \
FUSE_DIRENT_ALIGN(FUSE_NAME_OFFSET + (d)->namelen)
+
+#endif /* _LINUX_FUSE_H */
distrib
>
Scientific%20Linux
>
5x
>
x86_64
>
by-pkgid
>
27922b4260f65d317aabda37e42bbbff
>
files
>
1051
