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;
if (!ff->reserved_req) {
kfree(ff);
ff = NULL;
+ } else {
+ INIT_LIST_HEAD(&ff->write_entry);
+ atomic_set(&ff->count, 0);
}
}
return 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);
+ fuse_put_request(fc, req);
+}
+
+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_mapping_pages(inode->i_mapping, 0, -1);
+ invalidate_inode_pages2(inode->i_mapping);
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)
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();
if (!ff)
return -ENOMEM;
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;
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)
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_path.mnt);
- req->dentry = dget(file->f_path.dentry);
- request_send_background(fc, req);
+ req->misc.release.vfsmount = mntget(file->f_path.mnt);
+ req->misc.release.dentry = dget(file->f_path.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 */
* 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;
return (u64) v0 + ((u64) v1 << 32);
}
+/*
+ * Check if page is under writeback
+ *
+ * This is currently done by walking the list of writepage requests
+ * for the inode, which can be pretty inefficient.
+ */
+static bool fuse_page_is_writeback(struct inode *inode, pgoff_t index)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_inode *fi = get_fuse_inode(inode);
+ struct fuse_req *req;
+ bool found = false;
+
+ spin_lock(&fc->lock);
+ list_for_each_entry(req, &fi->writepages, writepages_entry) {
+ pgoff_t curr_index;
+
+ BUG_ON(req->inode != inode);
+ curr_index = req->misc.write.in.offset >> PAGE_CACHE_SHIFT;
+ if (curr_index == index) {
+ found = true;
+ break;
+ }
+ }
+ spin_unlock(&fc->lock);
+
+ return found;
+}
+
+/*
+ * Wait for page writeback to be completed.
+ *
+ * Since fuse doesn't rely on the VM writeback tracking, this has to
+ * use some other means.
+ */
+static int fuse_wait_on_page_writeback(struct inode *inode, pgoff_t index)
+{
+ struct fuse_inode *fi = get_fuse_inode(inode);
+
+ wait_event(fi->page_waitq, !fuse_page_is_writeback(inode, index));
+ return 0;
+}
+
static int fuse_flush(struct file *file, fl_owner_t id)
{
struct inode *inode = file->f_path.dentry->d_inode;
return err;
}
+/*
+ * Wait for all pending writepages on the inode to finish.
+ *
+ * This is currently done by blocking further writes with FUSE_NOWRITE
+ * and waiting for all sent writes to complete.
+ *
+ * This must be called under i_mutex, otherwise the FUSE_NOWRITE usage
+ * could conflict with truncation.
+ */
+static void fuse_sync_writes(struct inode *inode)
+{
+ fuse_set_nowrite(inode);
+ fuse_release_nowrite(inode);
+}
+
int fuse_fsync_common(struct file *file, struct dentry *de, int datasync,
int isdir)
{
if ((!isdir && fc->no_fsync) || (isdir && fc->no_fsyncdir))
return 0;
+ /*
+ * Start writeback against all dirty pages of the inode, then
+ * wait for all outstanding writes, before sending the FSYNC
+ * request.
+ */
+ err = write_inode_now(inode, 0);
+ if (err)
+ return err;
+
+ fuse_sync_writes(inode);
+
req = fuse_get_req(fc);
if (IS_ERR(req))
return PTR_ERR(req);
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;
}
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;
if (is_bad_inode(inode))
goto out;
+ /*
+ * Page writeback can extend beyond the liftime of the
+ * page-cache page, so make sure we read a properly synced
+ * page.
+ */
+ fuse_wait_on_page_writeback(inode, page->index);
+
req = fuse_get_req(fc);
err = PTR_ERR(req);
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);
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];
SetPageError(page);
unlock_page(page);
}
+ if (req->ff)
+ fuse_file_put(req->ff);
fuse_put_request(fc, req);
}
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 {
}
}
-struct fuse_readpages_data {
+struct fuse_fill_data {
struct fuse_req *req;
struct file *file;
struct inode *inode;
static int fuse_readpages_fill(void *_data, struct page *page)
{
- struct fuse_readpages_data *data = _data;
+ struct fuse_fill_data *data = _data;
struct fuse_req *req = data->req;
struct inode *inode = data->inode;
struct fuse_conn *fc = get_fuse_conn(inode);
+ fuse_wait_on_page_writeback(inode, page->index);
+
if (req->num_pages &&
(req->num_pages == FUSE_MAX_PAGES_PER_REQ ||
(req->num_pages + 1) * PAGE_CACHE_SIZE > fc->max_read ||
{
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;
return err;
}
-static size_t fuse_send_write(struct fuse_req *req, struct file *file,
- struct inode *inode, loff_t pos, size_t count)
+static ssize_t fuse_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
+{
+ struct inode *inode = iocb->ki_filp->f_mapping->host;
+
+ if (pos + iov_length(iov, nr_segs) > 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, iov, nr_segs, pos);
+}
+
+static void fuse_write_fill(struct fuse_req *req, struct file *file,
+ struct fuse_file *ff, 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 ? file->f_flags : 0;
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, file->private_data, 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(mapping, index);
+ 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))
return -EIO;
+ /*
+ * Make sure writepages on the same page are not mixed up with
+ * plain writes.
+ */
+ fuse_wait_on_page_writeback(inode, page->index);
+
req = fuse_get_req(fc);
if (IS_ERR(req))
return PTR_ERR(req);
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);
+ pos += nres;
+ fuse_write_update_size(inode, pos);
+ if (count == PAGE_CACHE_SIZE)
+ SetPageUptodate(page);
+ }
+ fuse_invalidate_attr(inode);
+ 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;
+}
- if (offset == 0 && to == PAGE_CACHE_SIZE)
+static size_t fuse_send_write_pages(struct fuse_req *req, struct file *file,
+ struct inode *inode, loff_t pos,
+ size_t count)
+{
+ size_t res;
+ unsigned offset;
+ unsigned i;
+
+ for (i = 0; i < req->num_pages; i++)
+ fuse_wait_on_page_writeback(inode, req->pages[i]->index);
+
+ res = fuse_send_write(req, file, inode, pos, count, NULL);
+
+ offset = req->page_offset;
+ count = res;
+ for (i = 0; i < req->num_pages; i++) {
+ struct page *page = req->pages[i];
+
+ if (!req->out.h.error && !offset && count >= PAGE_CACHE_SIZE)
SetPageUptodate(page);
+
+ if (count > PAGE_CACHE_SIZE - offset)
+ count -= PAGE_CACHE_SIZE - offset;
+ else
+ count = 0;
+ offset = 0;
+
+ unlock_page(page);
+ page_cache_release(page);
}
+
+ return res;
+}
+
+static ssize_t fuse_fill_write_pages(struct fuse_req *req,
+ struct address_space *mapping,
+ struct iov_iter *ii, loff_t pos)
+{
+ struct fuse_conn *fc = get_fuse_conn(mapping->host);
+ unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
+ size_t count = 0;
+ int err;
+
+ req->page_offset = offset;
+
+ do {
+ size_t tmp;
+ struct page *page;
+ pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+ size_t bytes = min_t(size_t, PAGE_CACHE_SIZE - offset,
+ iov_iter_count(ii));
+
+ bytes = min_t(size_t, bytes, fc->max_write - count);
+
+ again:
+ err = -EFAULT;
+ if (iov_iter_fault_in_readable(ii, bytes))
+ break;
+
+ err = -ENOMEM;
+ page = __grab_cache_page(mapping, index);
+ if (!page)
+ break;
+
+ pagefault_disable();
+ tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes);
+ pagefault_enable();
+ flush_dcache_page(page);
+
+ if (!tmp) {
+ unlock_page(page);
+ page_cache_release(page);
+ bytes = min(bytes, iov_iter_single_seg_count(ii));
+ goto again;
+ }
+
+ err = 0;
+ req->pages[req->num_pages] = page;
+ req->num_pages++;
+
+ iov_iter_advance(ii, tmp);
+ count += tmp;
+ pos += tmp;
+ offset += tmp;
+ if (offset == PAGE_CACHE_SIZE)
+ offset = 0;
+
+ } while (iov_iter_count(ii) && count < fc->max_write &&
+ req->num_pages < FUSE_MAX_PAGES_PER_REQ && offset == 0);
+
+ return count > 0 ? count : err;
+}
+
+static ssize_t fuse_perform_write(struct file *file,
+ struct address_space *mapping,
+ struct iov_iter *ii, loff_t pos)
+{
+ struct inode *inode = mapping->host;
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ int err = 0;
+ ssize_t res = 0;
+
+ if (is_bad_inode(inode))
+ return -EIO;
+
+ do {
+ struct fuse_req *req;
+ ssize_t count;
+
+ req = fuse_get_req(fc);
+ if (IS_ERR(req)) {
+ err = PTR_ERR(req);
+ break;
+ }
+
+ count = fuse_fill_write_pages(req, mapping, ii, pos);
+ if (count <= 0) {
+ err = count;
+ } else {
+ size_t num_written;
+
+ num_written = fuse_send_write_pages(req, file, inode,
+ pos, count);
+ err = req->out.h.error;
+ if (!err) {
+ res += num_written;
+ pos += num_written;
+
+ /* break out of the loop on short write */
+ if (num_written != count)
+ err = -EIO;
+ }
+ }
+ fuse_put_request(fc, req);
+ } while (!err && iov_iter_count(ii));
+
+ if (res > 0)
+ fuse_write_update_size(inode, pos);
+
fuse_invalidate_attr(inode);
- return err;
+
+ return res > 0 ? res : err;
+}
+
+static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
+{
+ struct file *file = iocb->ki_filp;
+ struct address_space *mapping = file->f_mapping;
+ size_t count = 0;
+ ssize_t written = 0;
+ struct inode *inode = mapping->host;
+ ssize_t err;
+ struct iov_iter i;
+
+ WARN_ON(iocb->ki_pos != pos);
+
+ err = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ);
+ if (err)
+ return err;
+
+ mutex_lock(&inode->i_mutex);
+ vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+
+ /* We can write back this queue in page reclaim */
+ current->backing_dev_info = mapping->backing_dev_info;
+
+ err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
+ if (err)
+ goto out;
+
+ if (count == 0)
+ goto out;
+
+ err = remove_suid(file->f_path.dentry);
+ if (err)
+ goto out;
+
+ file_update_time(file);
+
+ iov_iter_init(&i, iov, nr_segs, count, 0);
+ written = fuse_perform_write(file, mapping, &i, pos);
+ if (written >= 0)
+ iocb->ki_pos = pos + written;
+
+out:
+ current->backing_dev_info = NULL;
+ mutex_unlock(&inode->i_mutex);
+
+ return written ? written : err;
}
static void fuse_release_user_pages(struct fuse_req *req, int write)
nbytes = (req->num_pages << PAGE_SHIFT) - req->page_offset;
nbytes = min(count, 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)
}
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);
return res;
}
-static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
+static void fuse_writepage_free(struct fuse_conn *fc, struct fuse_req *req)
{
- if ((vma->vm_flags & VM_SHARED)) {
- if ((vma->vm_flags & VM_WRITE))
- return -ENODEV;
- else
- vma->vm_flags &= ~VM_MAYWRITE;
+ __free_page(req->pages[0]);
+ fuse_file_put(req->ff);
+ fuse_put_request(fc, req);
+}
+
+static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req)
+{
+ struct inode *inode = req->inode;
+ struct fuse_inode *fi = get_fuse_inode(inode);
+ struct backing_dev_info *bdi = inode->i_mapping->backing_dev_info;
+
+ list_del(&req->writepages_entry);
+ dec_bdi_stat(bdi, BDI_WRITEBACK);
+ dec_zone_page_state(req->pages[0], NR_WRITEBACK_TEMP);
+ bdi_writeout_inc(bdi);
+ wake_up(&fi->page_waitq);
+}
+
+/* Called under fc->lock, may release and reacquire it */
+static void fuse_send_writepage(struct fuse_conn *fc, struct fuse_req *req)
+{
+ struct fuse_inode *fi = get_fuse_inode(req->inode);
+ loff_t size = i_size_read(req->inode);
+ struct fuse_write_in *inarg = &req->misc.write.in;
+
+ if (!fc->connected)
+ goto out_free;
+
+ if (inarg->offset + PAGE_CACHE_SIZE <= size) {
+ inarg->size = PAGE_CACHE_SIZE;
+ } else if (inarg->offset < size) {
+ inarg->size = size & (PAGE_CACHE_SIZE - 1);
+ } else {
+ /* Got truncated off completely */
+ goto out_free;
+ }
+
+ req->in.args[1].size = inarg->size;
+ fi->writectr++;
+ request_send_background_locked(fc, req);
+ return;
+
+ out_free:
+ fuse_writepage_finish(fc, req);
+ spin_unlock(&fc->lock);
+ fuse_writepage_free(fc, req);
+ spin_lock(&fc->lock);
+}
+
+/*
+ * If fi->writectr is positive (no truncate or fsync going on) send
+ * all queued writepage requests.
+ *
+ * Called with fc->lock
+ */
+void fuse_flush_writepages(struct inode *inode)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_inode *fi = get_fuse_inode(inode);
+ struct fuse_req *req;
+
+ while (fi->writectr >= 0 && !list_empty(&fi->queued_writes)) {
+ req = list_entry(fi->queued_writes.next, struct fuse_req, list);
+ list_del_init(&req->list);
+ fuse_send_writepage(fc, req);
+ }
+}
+
+static void fuse_writepage_end(struct fuse_conn *fc, struct fuse_req *req)
+{
+ struct inode *inode = req->inode;
+ struct fuse_inode *fi = get_fuse_inode(inode);
+
+ mapping_set_error(inode->i_mapping, req->out.h.error);
+ spin_lock(&fc->lock);
+ fi->writectr--;
+ fuse_writepage_finish(fc, req);
+ spin_unlock(&fc->lock);
+ fuse_writepage_free(fc, req);
+}
+
+static int fuse_writepage_locked(struct page *page)
+{
+ struct address_space *mapping = page->mapping;
+ struct inode *inode = mapping->host;
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_inode *fi = get_fuse_inode(inode);
+ struct fuse_req *req;
+ struct fuse_file *ff;
+ struct page *tmp_page;
+
+ set_page_writeback(page);
+
+ req = fuse_request_alloc_nofs();
+ if (!req)
+ goto err;
+
+ tmp_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+ if (!tmp_page)
+ goto err_free;
+
+ spin_lock(&fc->lock);
+ BUG_ON(list_empty(&fi->write_files));
+ ff = list_entry(fi->write_files.next, struct fuse_file, write_entry);
+ req->ff = fuse_file_get(ff);
+ spin_unlock(&fc->lock);
+
+ fuse_write_fill(req, NULL, ff, inode, page_offset(page), 0, 1);
+
+ copy_highpage(tmp_page, page);
+ req->num_pages = 1;
+ req->pages[0] = tmp_page;
+ req->page_offset = 0;
+ req->end = fuse_writepage_end;
+ req->inode = inode;
+
+ inc_bdi_stat(mapping->backing_dev_info, BDI_WRITEBACK);
+ inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
+ end_page_writeback(page);
+
+ spin_lock(&fc->lock);
+ list_add(&req->writepages_entry, &fi->writepages);
+ list_add_tail(&req->list, &fi->queued_writes);
+ fuse_flush_writepages(inode);
+ spin_unlock(&fc->lock);
+
+ return 0;
+
+err_free:
+ fuse_request_free(req);
+err:
+ end_page_writeback(page);
+ return -ENOMEM;
+}
+
+static int fuse_writepage(struct page *page, struct writeback_control *wbc)
+{
+ int err;
+
+ err = fuse_writepage_locked(page);
+ unlock_page(page);
+
+ return err;
+}
+
+static int fuse_launder_page(struct page *page)
+{
+ int err = 0;
+ if (clear_page_dirty_for_io(page)) {
+ struct inode *inode = page->mapping->host;
+ err = fuse_writepage_locked(page);
+ if (!err)
+ fuse_wait_on_page_writeback(inode, page->index);
}
- return generic_file_mmap(file, vma);
+ return err;
+}
+
+/*
+ * Write back dirty pages now, because there may not be any suitable
+ * open files later
+ */
+static void fuse_vma_close(struct vm_area_struct *vma)
+{
+ filemap_write_and_wait(vma->vm_file->f_mapping);
+}
+
+/*
+ * Wait for writeback against this page to complete before allowing it
+ * to be marked dirty again, and hence written back again, possibly
+ * before the previous writepage completed.
+ *
+ * Block here, instead of in ->writepage(), so that the userspace fs
+ * can only block processes actually operating on the filesystem.
+ *
+ * Otherwise unprivileged userspace fs would be able to block
+ * unrelated:
+ *
+ * - page migration
+ * - sync(2)
+ * - try_to_free_pages() with order > PAGE_ALLOC_COSTLY_ORDER
+ */
+static int fuse_page_mkwrite(struct vm_area_struct *vma, struct page *page)
+{
+ /*
+ * Don't use page->mapping as it may become NULL from a
+ * concurrent truncate.
+ */
+ struct inode *inode = vma->vm_file->f_mapping->host;
+
+ fuse_wait_on_page_writeback(inode, page->index);
+ return 0;
}
-static int fuse_set_page_dirty(struct page *page)
+static struct vm_operations_struct fuse_file_vm_ops = {
+ .close = fuse_vma_close,
+ .fault = filemap_fault,
+ .page_mkwrite = fuse_page_mkwrite,
+};
+
+static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
{
- printk("fuse_set_page_dirty: should not happen\n");
- dump_stack();
+ if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) {
+ struct inode *inode = file->f_dentry->d_inode;
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_inode *fi = get_fuse_inode(inode);
+ struct fuse_file *ff = file->private_data;
+ /*
+ * file may be written through mmap, so chain it onto the
+ * inodes's write_file list
+ */
+ spin_lock(&fc->lock);
+ if (list_empty(&ff->write_entry))
+ list_add(&ff->write_entry, &fi->write_files);
+ spin_unlock(&fc->lock);
+ }
+ file_accessed(file);
+ vma->vm_ops = &fuse_file_vm_ops;
return 0;
}
}
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_path.dentry->d_inode;
struct fuse_conn *fc = get_fuse_conn(inode);
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;
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;
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_path.dentry->d_inode;
struct fuse_conn *fc = get_fuse_conn(inode);
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 */
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_path.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 const struct file_operations fuse_file_operations = {
.llseek = generic_file_llseek,
.read = do_sync_read,
- .aio_read = generic_file_aio_read,
+ .aio_read = fuse_file_aio_read,
.write = do_sync_write,
- .aio_write = generic_file_aio_write,
+ .aio_write = fuse_file_aio_write,
.mmap = fuse_file_mmap,
.open = fuse_open,
.flush = fuse_flush,
.release = fuse_release,
.fsync = fuse_fsync,
.lock = fuse_file_lock,
- .sendfile = generic_file_sendfile,
+ .flock = fuse_file_flock,
+ .splice_read = generic_file_splice_read,
};
static const struct file_operations fuse_direct_io_file_operations = {
.release = fuse_release,
.fsync = fuse_fsync,
.lock = fuse_file_lock,
- /* no mmap and sendfile */
+ .flock = fuse_file_flock,
+ /* no mmap and splice_read */
};
static const struct address_space_operations fuse_file_aops = {
.readpage = fuse_readpage,
- .prepare_write = fuse_prepare_write,
- .commit_write = fuse_commit_write,
+ .writepage = fuse_writepage,
+ .launder_page = fuse_launder_page,
+ .write_begin = fuse_write_begin,
+ .write_end = fuse_write_end,
.readpages = fuse_readpages,
- .set_page_dirty = fuse_set_page_dirty,
+ .set_page_dirty = __set_page_dirty_nobuffers,
.bmap = fuse_bmap,
};
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff