+static inline void
+filemap_set_next_kvec(const struct kvec **iovp, size_t *basep, size_t bytes)
+{
+ const struct kvec *iov = *iovp;
+ size_t base = *basep;
+
+ while (bytes) {
+ int copy = min(bytes, iov->iov_len - base);
+
+ bytes -= copy;
+ base += copy;
+ if (iov->iov_len == base) {
+ iov++;
+ base = 0;
+ }
+ }
+ *iovp = iov;
+ *basep = base;
+}
+
+/*
+ * TODO:
+ * This largely tries to copy generic_file_aio_write_nolock(), although it
+ * doesn't have to be nearly as generic. A real cleanup should either
+ * merge this into generic_file_aio_write_nolock() as well or keep it special
+ * and remove as much code as possible.
+ */
+static ssize_t
+generic_kernel_file_aio_write_nolock(struct kiocb *iocb, const struct kvec*iov,
+ unsigned long nr_segs, loff_t *ppos)
+{
+ struct file *file = iocb->ki_filp;
+ struct address_space * mapping = file->f_mapping;
+ const struct address_space_operations *a_ops = mapping->a_ops;
+ size_t ocount; /* original count */
+ size_t count; /* after file limit checks */
+ struct inode *inode = mapping->host;
+ long status = 0;
+ loff_t pos;
+ struct page *page;
+ struct page *cached_page = NULL;
+ const int isblk = S_ISBLK(inode->i_mode);
+ ssize_t written;
+ ssize_t err;
+ size_t bytes;
+ struct pagevec lru_pvec;
+ const struct kvec *cur_iov = iov; /* current kvec */
+ size_t iov_base = 0; /* offset in the current kvec */
+ unsigned long seg;
+ char *buf;
+
+ ocount = 0;
+ for (seg = 0; seg < nr_segs; seg++) {
+ const struct kvec *iv = &iov[seg];
+
+ /*
+ * If any segment has a negative length, or the cumulative
+ * length ever wraps negative then return -EINVAL.
+ */
+ ocount += iv->iov_len;
+ if (unlikely((ssize_t)(ocount|iv->iov_len) < 0))
+ return -EINVAL;
+ }
+
+ count = ocount;
+ pos = *ppos;
+ pagevec_init(&lru_pvec, 0);
+
+ /* We can write back this queue in page reclaim */
+ current->backing_dev_info = mapping->backing_dev_info;
+ written = 0;
+
+ err = generic_write_checks(file, &pos, &count, isblk);
+ if (err)
+ goto out;
+
+
+ if (count == 0)
+ goto out;
+
+ remove_suid(file->f_dentry);
+ file_update_time(file);
+
+ /* There is no sane reason to use O_DIRECT */
+ BUG_ON(file->f_flags & O_DIRECT);
+
+ buf = iov->iov_base;
+ do {
+ unsigned long index;
+ unsigned long offset;
+ size_t copied;
+
+ offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
+ index = pos >> PAGE_CACHE_SHIFT;
+ bytes = PAGE_CACHE_SIZE - offset;
+ if (bytes > count)
+ bytes = count;
+
+ page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
+ if (!page) {
+ status = -ENOMEM;
+ break;
+ }
+
+ status = a_ops->prepare_write(file, page, offset, offset+bytes);
+ if (unlikely(status)) {
+ loff_t isize = i_size_read(inode);
+ /*
+ * prepare_write() may have instantiated a few blocks
+ * outside i_size. Trim these off again.
+ */
+ unlock_page(page);
+ page_cache_release(page);
+ if (pos + bytes > isize)
+ vmtruncate(inode, isize);
+ break;
+ }
+
+ BUG_ON(nr_segs != 1);
+ copied = filemap_copy_from_kernel(page, offset, buf, bytes);
+
+ flush_dcache_page(page);
+ status = a_ops->commit_write(file, page, offset, offset+bytes);
+ if (likely(copied > 0)) {
+ if (!status)
+ status = copied;
+
+ if (status >= 0) {
+ written += status;
+ count -= status;
+ pos += status;
+ buf += status;
+ if (unlikely(nr_segs > 1))
+ filemap_set_next_kvec(&cur_iov,
+ &iov_base, status);
+ }
+ }
+ if (unlikely(copied != bytes))
+ if (status >= 0)
+ status = -EFAULT;
+ unlock_page(page);
+ mark_page_accessed(page);
+ page_cache_release(page);
+ if (status < 0)
+ break;
+ balance_dirty_pages_ratelimited(mapping);
+ cond_resched();
+ } while (count);
+ *ppos = pos;
+
+ if (cached_page)
+ page_cache_release(cached_page);
+
+ /*
+ * For now, when the user asks for O_SYNC, we'll actually give O_DSYNC
+ */
+ if (status >= 0) {
+ if ((file->f_flags & O_SYNC) || IS_SYNC(inode))
+ status = generic_osync_inode(inode, mapping,
+ OSYNC_METADATA|OSYNC_DATA);
+ }
+
+ err = written ? written : status;
+out:
+ pagevec_lru_add(&lru_pvec);
+ current->backing_dev_info = 0;
+ return err;
+}
+