diff options
Diffstat (limited to 'fs/fuse')
| -rw-r--r-- | fs/fuse/control.c | 2 | ||||
| -rw-r--r-- | fs/fuse/dev.c | 23 | ||||
| -rw-r--r-- | fs/fuse/dir.c | 86 | ||||
| -rw-r--r-- | fs/fuse/file.c | 633 | ||||
| -rw-r--r-- | fs/fuse/fuse_i.h | 52 | ||||
| -rw-r--r-- | fs/fuse/inode.c | 90 |
6 files changed, 803 insertions, 83 deletions
diff --git a/fs/fuse/control.c b/fs/fuse/control.c index 105d4a271e07..4f3cab321415 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -117,7 +117,7 @@ int fuse_ctl_add_conn(struct fuse_conn *fc) parent = fuse_control_sb->s_root; inc_nlink(parent->d_inode); - sprintf(name, "%llu", (unsigned long long) fc->id); + sprintf(name, "%u", fc->dev); parent = fuse_ctl_add_dentry(parent, fc, name, S_IFDIR | 0500, 2, &simple_dir_inode_operations, &simple_dir_operations); diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index af639807524e..87250b6a8682 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -47,6 +47,14 @@ struct fuse_req *fuse_request_alloc(void) return req; } +struct fuse_req *fuse_request_alloc_nofs(void) +{ + struct fuse_req *req = kmem_cache_alloc(fuse_req_cachep, GFP_NOFS); + if (req) + fuse_request_init(req); + return req; +} + void fuse_request_free(struct fuse_req *req) { kmem_cache_free(fuse_req_cachep, req); @@ -291,6 +299,7 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *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; @@ -307,8 +316,8 @@ 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 */ @@ -430,6 +439,17 @@ void request_send_background(struct fuse_conn *fc, struct fuse_req *req) } /* + * Called under fc->lock + * + * fc->connected must have been checked previously + */ +void request_send_background_locked(struct fuse_conn *fc, struct fuse_req *req) +{ + req->isreply = 1; + request_send_nowait_locked(fc, req); +} + +/* * Lock the request. Up to the next unlock_request() there mustn't be * anything that could cause a page-fault. If the request was already * aborted bail out. @@ -968,6 +988,7 @@ 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 = diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index c4807b3fc8a3..2060bf06b906 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -132,7 +132,7 @@ static void fuse_lookup_init(struct fuse_req *req, struct inode *dir, req->out.args[0].value = outarg; } -static u64 fuse_get_attr_version(struct fuse_conn *fc) +u64 fuse_get_attr_version(struct fuse_conn *fc) { u64 curr_version; @@ -1107,6 +1107,50 @@ static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg) } /* + * Prevent concurrent writepages on inode + * + * This is done by adding a negative bias to the inode write counter + * and waiting for all pending writes to finish. + */ +void fuse_set_nowrite(struct inode *inode) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_inode *fi = get_fuse_inode(inode); + + BUG_ON(!mutex_is_locked(&inode->i_mutex)); + + spin_lock(&fc->lock); + BUG_ON(fi->writectr < 0); + fi->writectr += FUSE_NOWRITE; + spin_unlock(&fc->lock); + wait_event(fi->page_waitq, fi->writectr == FUSE_NOWRITE); +} + +/* + * Allow writepages on inode + * + * Remove the bias from the writecounter and send any queued + * writepages. + */ +static void __fuse_release_nowrite(struct inode *inode) +{ + struct fuse_inode *fi = get_fuse_inode(inode); + + BUG_ON(fi->writectr != FUSE_NOWRITE); + fi->writectr = 0; + fuse_flush_writepages(inode); +} + +void fuse_release_nowrite(struct inode *inode) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + + spin_lock(&fc->lock); + __fuse_release_nowrite(inode); + spin_unlock(&fc->lock); +} + +/* * Set attributes, and at the same time refresh them. * * Truncation is slightly complicated, because the 'truncate' request @@ -1122,6 +1166,8 @@ static int fuse_do_setattr(struct dentry *entry, struct iattr *attr, struct fuse_req *req; struct fuse_setattr_in inarg; struct fuse_attr_out outarg; + bool is_truncate = false; + loff_t oldsize; int err; if (!fuse_allow_task(fc, current)) @@ -1145,12 +1191,16 @@ static int fuse_do_setattr(struct dentry *entry, struct iattr *attr, send_sig(SIGXFSZ, current, 0); return -EFBIG; } + is_truncate = true; } req = fuse_get_req(fc); if (IS_ERR(req)) return PTR_ERR(req); + if (is_truncate) + fuse_set_nowrite(inode); + memset(&inarg, 0, sizeof(inarg)); memset(&outarg, 0, sizeof(outarg)); iattr_to_fattr(attr, &inarg); @@ -1181,16 +1231,44 @@ static int fuse_do_setattr(struct dentry *entry, struct iattr *attr, if (err) { if (err == -EINTR) fuse_invalidate_attr(inode); - return err; + goto error; } if ((inode->i_mode ^ outarg.attr.mode) & S_IFMT) { make_bad_inode(inode); - return -EIO; + err = -EIO; + goto error; + } + + spin_lock(&fc->lock); + fuse_change_attributes_common(inode, &outarg.attr, + attr_timeout(&outarg)); + oldsize = inode->i_size; + i_size_write(inode, outarg.attr.size); + + if (is_truncate) { + /* NOTE: this may release/reacquire fc->lock */ + __fuse_release_nowrite(inode); + } + spin_unlock(&fc->lock); + + /* + * Only call invalidate_inode_pages2() after removing + * FUSE_NOWRITE, otherwise fuse_launder_page() would deadlock. + */ + if (S_ISREG(inode->i_mode) && oldsize != outarg.attr.size) { + if (outarg.attr.size < oldsize) + fuse_truncate(inode->i_mapping, outarg.attr.size); + invalidate_inode_pages2(inode->i_mapping); } - fuse_change_attributes(inode, &outarg.attr, attr_timeout(&outarg), 0); return 0; + +error: + if (is_truncate) + fuse_release_nowrite(inode); + + return err; } static int fuse_setattr(struct dentry *entry, struct iattr *attr) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 676b0bc8a86d..f28cf8b46f80 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -210,6 +210,49 @@ u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t 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; @@ -245,6 +288,21 @@ static int fuse_flush(struct file *file, fl_owner_t id) 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) { @@ -261,6 +319,17 @@ int fuse_fsync_common(struct file *file, struct dentry *de, int datasync, 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); @@ -294,7 +363,7 @@ 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_read_in *inarg = &req->misc.read.in; struct fuse_file *ff = file->private_data; inarg->fh = ff->fh; @@ -320,7 +389,7 @@ static size_t fuse_send_read(struct fuse_req *req, struct file *file, fuse_read_fill(req, file, inode, pos, count, FUSE_READ); if (owner != NULL) { - struct fuse_read_in *inarg = &req->misc.read_in; + struct fuse_read_in *inarg = &req->misc.read.in; inarg->read_flags |= FUSE_READ_LOCKOWNER; inarg->lock_owner = fuse_lock_owner_id(fc, owner); @@ -329,31 +398,66 @@ static size_t fuse_send_read(struct fuse_req *req, struct file *file, 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, - NULL); + 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); @@ -363,8 +467,19 @@ 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]; @@ -387,6 +502,7 @@ 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) { struct fuse_file *ff = file->private_data; req->ff = fuse_file_get(ff); @@ -411,6 +527,8 @@ static int fuse_readpages_fill(void *_data, struct page *page) 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 || @@ -477,11 +595,10 @@ static ssize_t fuse_file_aio_read(struct kiocb *iocb, const struct iovec *iov, } 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_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 = &req->misc.write.in; struct fuse_write_out *outarg = &req->misc.write.out; @@ -490,7 +607,7 @@ static void fuse_write_fill(struct fuse_req *req, struct file *file, inarg->offset = pos; inarg->size = count; inarg->write_flags = writepage ? FUSE_WRITE_CACHE : 0; - inarg->flags = file->f_flags; + 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; @@ -511,7 +628,7 @@ static size_t fuse_send_write(struct fuse_req *req, struct file *file, fl_owner_t owner) { struct fuse_conn *fc = get_fuse_conn(inode); - fuse_write_fill(req, file, inode, pos, count, 0); + 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; @@ -533,19 +650,36 @@ static int fuse_write_begin(struct file *file, struct address_space *mapping, return 0; } +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; struct fuse_conn *fc = get_fuse_conn(inode); - struct fuse_inode *fi = get_fuse_inode(inode); 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); @@ -560,12 +694,7 @@ static int fuse_buffered_write(struct file *file, struct inode *inode, err = -EIO; if (!err) { pos += nres; - spin_lock(&fc->lock); - fi->attr_version = ++fc->attr_version; - if (pos > inode->i_size) - i_size_write(inode, pos); - spin_unlock(&fc->lock); - + fuse_write_update_size(inode, pos); if (count == PAGE_CACHE_SIZE) SetPageUptodate(page); } @@ -588,6 +717,198 @@ static int fuse_write_end(struct file *file, struct address_space *mapping, return res; } +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 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) { unsigned i; @@ -613,7 +934,7 @@ 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); @@ -645,14 +966,15 @@ 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, current->files); @@ -683,12 +1005,8 @@ 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); @@ -716,21 +1034,225 @@ static ssize_t fuse_direct_write(struct file *file, const char __user *buf, 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; } -static int fuse_set_page_dirty(struct page *page) +/* + * 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) { - printk("fuse_set_page_dirty: should not happen\n"); - dump_stack(); + 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 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) +{ + 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; } @@ -909,12 +1431,37 @@ static sector_t fuse_bmap(struct address_space *mapping, sector_t block) 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_path.dentry->d_inode; + + mutex_lock(&inode->i_mutex); + switch (origin) { + case SEEK_END: + 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 = do_sync_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, @@ -926,7 +1473,7 @@ static const struct file_operations fuse_file_operations = { }; 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, @@ -940,10 +1487,12 @@ static const struct file_operations fuse_direct_io_file_operations = { static const struct address_space_operations fuse_file_aops = { .readpage = fuse_readpage, + .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, }; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 67aaf6ee38ea..dadffa21a206 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -15,6 +15,7 @@ #include <linux/mm.h> #include <linux/backing-dev.h> #include <linux/mutex.h> +#include <linux/rwsem.h> /** Max number of pages that can be used in a single read request */ #define FUSE_MAX_PAGES_PER_REQ 32 @@ -25,6 +26,9 @@ /** Congestion starts at 75% of maximum */ #define FUSE_CONGESTION_THRESHOLD (FUSE_MAX_BACKGROUND * 75 / 100) +/** Bias for fi->writectr, meaning new writepages must not be sent */ +#define FUSE_NOWRITE INT_MIN + /** It could be as large as PATH_MAX, but would that have any uses? */ #define FUSE_NAME_MAX 1024 @@ -73,6 +77,19 @@ struct fuse_inode { /** Files usable in writepage. Protected by fc->lock */ struct list_head write_files; + + /** Writepages pending on truncate or fsync */ + struct list_head queued_writes; + + /** Number of sent writes, a negative bias (FUSE_NOWRITE) + * means more writes are blocked */ + int writectr; + + /** Waitq for writepage completion */ + wait_queue_head_t page_waitq; + + /** List of writepage requestst (pending or sent) */ + struct list_head writepages; }; /** FUSE specific file data */ @@ -222,7 +239,10 @@ struct fuse_req { } 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; @@ -242,6 +262,12 @@ struct fuse_req { /** File used in the request (or NULL) */ struct fuse_file *ff; + /** Inode used in the request or NULL */ + struct inode *inode; + + /** Link on fi->writepages */ + struct list_head writepages_entry; + /** Request completion callback */ void (*end)(struct fuse_conn *, struct fuse_req *); @@ -390,8 +416,8 @@ struct fuse_conn { /** Entry on the fuse_conn_list */ struct list_head entry; - /** Unique ID */ - u64 id; + /** Device ID from super block */ + dev_t dev; /** Dentries in the control filesystem */ struct dentry *ctl_dentry[FUSE_CTL_NUM_DENTRIES]; @@ -438,7 +464,7 @@ extern const struct file_operations fuse_dev_operations; /** * Get a filled in inode */ -struct inode *fuse_iget(struct super_block *sb, unsigned long nodeid, +struct inode *fuse_iget(struct super_block *sb, u64 nodeid, int generation, struct fuse_attr *attr, u64 attr_valid, u64 attr_version); @@ -446,7 +472,7 @@ struct inode *fuse_iget(struct super_block *sb, unsigned long nodeid, * 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 @@ -504,6 +530,11 @@ void fuse_init_symlink(struct inode *inode); void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, u64 attr_valid, u64 attr_version); +void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, + u64 attr_valid); + +void fuse_truncate(struct address_space *mapping, loff_t offset); + /** * Initialize the client device */ @@ -522,6 +553,8 @@ void fuse_ctl_cleanup(void); */ struct fuse_req *fuse_request_alloc(void); +struct fuse_req *fuse_request_alloc_nofs(void); + /** * Free a request */ @@ -558,6 +591,8 @@ void request_send_noreply(struct fuse_conn *fc, struct fuse_req *req); */ void request_send_background(struct fuse_conn *fc, struct fuse_req *req); +void request_send_background_locked(struct fuse_conn *fc, struct fuse_req *req); + /* Abort all requests */ void fuse_abort_conn(struct fuse_conn *fc); @@ -600,3 +635,10 @@ 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); + +void fuse_flush_writepages(struct inode *inode); + +void fuse_set_nowrite(struct inode *inode); +void fuse_release_nowrite(struct inode *inode); + +u64 fuse_get_attr_version(struct fuse_conn *fc); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 4df34da2284a..79b615873838 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -59,7 +59,11 @@ static struct inode *fuse_alloc_inode(struct super_block *sb) fi->nodeid = 0; fi->nlookup = 0; fi->attr_version = 0; + fi->writectr = 0; INIT_LIST_HEAD(&fi->write_files); + INIT_LIST_HEAD(&fi->queued_writes); + INIT_LIST_HEAD(&fi->writepages); + init_waitqueue_head(&fi->page_waitq); fi->forget_req = fuse_request_alloc(); if (!fi->forget_req) { kmem_cache_free(fuse_inode_cachep, inode); @@ -73,13 +77,14 @@ static void fuse_destroy_inode(struct inode *inode) { struct fuse_inode *fi = get_fuse_inode(inode); BUG_ON(!list_empty(&fi->write_files)); + BUG_ON(!list_empty(&fi->queued_writes)); if (fi->forget_req) fuse_request_free(fi->forget_req); kmem_cache_free(fuse_inode_cachep, inode); } 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; @@ -109,7 +114,7 @@ static int fuse_remount_fs(struct super_block *sb, int *flags, char *data) return 0; } -static void fuse_truncate(struct address_space *mapping, loff_t offset) +void fuse_truncate(struct address_space *mapping, loff_t offset) { /* See vmtruncate() */ unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1); @@ -117,19 +122,12 @@ static void fuse_truncate(struct address_space *mapping, loff_t 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) +void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, + u64 attr_valid) { struct fuse_conn *fc = get_fuse_conn(inode); 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; @@ -159,6 +157,22 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, fi->orig_i_mode = inode->i_mode; if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS)) inode->i_mode &= ~S_ISVTX; +} + +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); + 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; + } + + fuse_change_attributes_common(inode, attr, attr_valid); oldsize = inode->i_size; i_size_write(inode, attr->size); @@ -193,7 +207,7 @@ 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 @@ -202,12 +216,12 @@ 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, +struct inode *fuse_iget(struct super_block *sb, u64 nodeid, int generation, struct fuse_attr *attr, u64 attr_valid, u64 attr_version) { @@ -447,7 +461,7 @@ static int fuse_show_options(struct seq_file *m, struct vfsmount *mnt) return 0; } -static struct fuse_conn *new_conn(void) +static struct fuse_conn *new_conn(struct super_block *sb) { struct fuse_conn *fc; int err; @@ -468,19 +482,41 @@ static struct fuse_conn *new_conn(void) 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; + /* fuse does it's own writeback accounting */ + fc->bdi.capabilities = BDI_CAP_NO_ACCT_WB; + fc->dev = sb->s_dev; err = bdi_init(&fc->bdi); - if (err) { - kfree(fc); - fc = NULL; - goto out; - } + if (err) + goto error_kfree; + err = bdi_register_dev(&fc->bdi, fc->dev); + if (err) + goto error_bdi_destroy; + /* + * For a single fuse filesystem use max 1% of dirty + + * writeback threshold. + * + * This gives about 1M of write buffer for memory maps on a + * machine with 1G and 10% dirty_ratio, which should be more + * than enough. + * + * Privileged users can raise it by writing to + * + * /sys/class/bdi/<bdi>/max_ratio + */ + bdi_set_max_ratio(&fc->bdi, 1); fc->reqctr = 0; fc->blocked = 1; fc->attr_version = 1; get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key)); } -out: return fc; + +error_bdi_destroy: + bdi_destroy(&fc->bdi); +error_kfree: + mutex_destroy(&fc->inst_mutex); + kfree(fc); + return NULL; } void fuse_conn_put(struct fuse_conn *fc) @@ -548,6 +584,7 @@ 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 = min_t(unsigned, 4096, fc->max_write); fc->conn_init = 1; } fuse_put_request(fc, req); @@ -578,12 +615,6 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) request_send_background(fc, req); } -static u64 conn_id(void) -{ - static u64 ctr = 1; - return ctr++; -} - static int fuse_fill_super(struct super_block *sb, void *data, int silent) { struct fuse_conn *fc; @@ -621,14 +652,14 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) if (file->f_op != &fuse_dev_operations) return -EINVAL; - fc = new_conn(); + fc = new_conn(sb); if (!fc) return -ENOMEM; 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 = min_t(unsigned, 4096, d.max_read); /* Used by get_root_inode() */ sb->s_fs_info = fc; @@ -659,7 +690,6 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) if (file->private_data) goto err_unlock; - fc->id = conn_id(); err = fuse_ctl_add_conn(fc); if (err) goto err_unlock; |
