X-Git-Url: http://git.cascardo.info/?p=cascardo%2Flinux.git;a=blobdiff_plain;f=fs%2Fsplice.c;h=153d4f3bd441febd7004b1862cd218afc0ee6252;hp=589a1d52bb98ecb3ba5fd3373a1585a213f685e9;hb=c3a690240423fc4eb8a0c3c7df025d13eadf140b;hpb=241699cd72a8489c9446ae3910ddd243e9b9061b diff --git a/fs/splice.c b/fs/splice.c index 589a1d52bb98..153d4f3bd441 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -238,8 +238,7 @@ ssize_t add_to_pipe(struct pipe_inode_info *pipe, struct pipe_buffer *buf) pipe->nrbufs++; return buf->len; } - buf->ops->release(pipe, buf); - buf->ops = NULL; + pipe_buf_release(pipe, buf); return ret; } EXPORT_SYMBOL(add_to_pipe); @@ -281,207 +280,6 @@ void splice_shrink_spd(struct splice_pipe_desc *spd) kfree(spd->partial); } -static int -__generic_file_splice_read(struct file *in, loff_t *ppos, - struct pipe_inode_info *pipe, size_t len, - unsigned int flags) -{ - struct address_space *mapping = in->f_mapping; - unsigned int loff, nr_pages, req_pages; - struct page *pages[PIPE_DEF_BUFFERS]; - struct partial_page partial[PIPE_DEF_BUFFERS]; - struct page *page; - pgoff_t index, end_index; - loff_t isize; - int error, page_nr; - struct splice_pipe_desc spd = { - .pages = pages, - .partial = partial, - .nr_pages_max = PIPE_DEF_BUFFERS, - .flags = flags, - .ops = &page_cache_pipe_buf_ops, - .spd_release = spd_release_page, - }; - - if (splice_grow_spd(pipe, &spd)) - return -ENOMEM; - - index = *ppos >> PAGE_SHIFT; - loff = *ppos & ~PAGE_MASK; - req_pages = (len + loff + PAGE_SIZE - 1) >> PAGE_SHIFT; - nr_pages = min(req_pages, spd.nr_pages_max); - - /* - * Lookup the (hopefully) full range of pages we need. - */ - spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, spd.pages); - index += spd.nr_pages; - - /* - * If find_get_pages_contig() returned fewer pages than we needed, - * readahead/allocate the rest and fill in the holes. - */ - if (spd.nr_pages < nr_pages) - page_cache_sync_readahead(mapping, &in->f_ra, in, - index, req_pages - spd.nr_pages); - - error = 0; - while (spd.nr_pages < nr_pages) { - /* - * Page could be there, find_get_pages_contig() breaks on - * the first hole. - */ - page = find_get_page(mapping, index); - if (!page) { - /* - * page didn't exist, allocate one. - */ - page = page_cache_alloc_cold(mapping); - if (!page) - break; - - error = add_to_page_cache_lru(page, mapping, index, - mapping_gfp_constraint(mapping, GFP_KERNEL)); - if (unlikely(error)) { - put_page(page); - if (error == -EEXIST) - continue; - break; - } - /* - * add_to_page_cache() locks the page, unlock it - * to avoid convoluting the logic below even more. - */ - unlock_page(page); - } - - spd.pages[spd.nr_pages++] = page; - index++; - } - - /* - * Now loop over the map and see if we need to start IO on any - * pages, fill in the partial map, etc. - */ - index = *ppos >> PAGE_SHIFT; - nr_pages = spd.nr_pages; - spd.nr_pages = 0; - for (page_nr = 0; page_nr < nr_pages; page_nr++) { - unsigned int this_len; - - if (!len) - break; - - /* - * this_len is the max we'll use from this page - */ - this_len = min_t(unsigned long, len, PAGE_SIZE - loff); - page = spd.pages[page_nr]; - - if (PageReadahead(page)) - page_cache_async_readahead(mapping, &in->f_ra, in, - page, index, req_pages - page_nr); - - /* - * If the page isn't uptodate, we may need to start io on it - */ - if (!PageUptodate(page)) { - lock_page(page); - - /* - * Page was truncated, or invalidated by the - * filesystem. Redo the find/create, but this time the - * page is kept locked, so there's no chance of another - * race with truncate/invalidate. - */ - if (!page->mapping) { - unlock_page(page); -retry_lookup: - page = find_or_create_page(mapping, index, - mapping_gfp_mask(mapping)); - - if (!page) { - error = -ENOMEM; - break; - } - put_page(spd.pages[page_nr]); - spd.pages[page_nr] = page; - } - /* - * page was already under io and is now done, great - */ - if (PageUptodate(page)) { - unlock_page(page); - goto fill_it; - } - - /* - * need to read in the page - */ - error = mapping->a_ops->readpage(in, page); - if (unlikely(error)) { - /* - * Re-lookup the page - */ - if (error == AOP_TRUNCATED_PAGE) - goto retry_lookup; - - break; - } - } -fill_it: - /* - * i_size must be checked after PageUptodate. - */ - isize = i_size_read(mapping->host); - end_index = (isize - 1) >> PAGE_SHIFT; - if (unlikely(!isize || index > end_index)) - break; - - /* - * if this is the last page, see if we need to shrink - * the length and stop - */ - if (end_index == index) { - unsigned int plen; - - /* - * max good bytes in this page - */ - plen = ((isize - 1) & ~PAGE_MASK) + 1; - if (plen <= loff) - break; - - /* - * force quit after adding this page - */ - this_len = min(this_len, plen - loff); - len = this_len; - } - - spd.partial[page_nr].offset = loff; - spd.partial[page_nr].len = this_len; - len -= this_len; - loff = 0; - spd.nr_pages++; - index++; - } - - /* - * Release any pages at the end, if we quit early. 'page_nr' is how far - * we got, 'nr_pages' is how many pages are in the map. - */ - while (page_nr < nr_pages) - put_page(spd.pages[page_nr++]); - in->f_ra.prev_pos = (loff_t)index << PAGE_SHIFT; - - if (spd.nr_pages) - error = splice_to_pipe(pipe, &spd); - - splice_shrink_spd(&spd); - return error; -} - /** * generic_file_splice_read - splice data from file to a pipe * @in: file to splice from @@ -492,32 +290,40 @@ fill_it: * * Description: * Will read pages from given file and fill them into a pipe. Can be - * used as long as the address_space operations for the source implements - * a readpage() hook. + * used as long as it has more or less sane ->read_iter(). * */ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { - loff_t isize, left; - int ret; - - if (IS_DAX(in->f_mapping->host)) - return default_file_splice_read(in, ppos, pipe, len, flags); + struct iov_iter to; + struct kiocb kiocb; + loff_t isize; + int idx, ret; isize = i_size_read(in->f_mapping->host); if (unlikely(*ppos >= isize)) return 0; - left = isize - *ppos; - if (unlikely(left < len)) - len = left; - - ret = __generic_file_splice_read(in, ppos, pipe, len, flags); + iov_iter_pipe(&to, ITER_PIPE | READ, pipe, len); + idx = to.idx; + init_sync_kiocb(&kiocb, in); + kiocb.ki_pos = *ppos; + ret = in->f_op->read_iter(&kiocb, &to); if (ret > 0) { - *ppos += ret; + *ppos = kiocb.ki_pos; file_accessed(in); + } else if (ret < 0) { + to.idx = idx; + to.iov_offset = 0; + iov_iter_advance(&to, 0); /* to free what was emitted */ + /* + * callers of ->splice_read() expect -EAGAIN on + * "can't put anything in there", rather than -EFAULT. + */ + if (ret == -EFAULT) + ret = -EAGAIN; } return ret; @@ -548,7 +354,7 @@ const struct pipe_buf_operations nosteal_pipe_buf_ops = { }; EXPORT_SYMBOL(nosteal_pipe_buf_ops); -static ssize_t kernel_readv(struct file *file, const struct iovec *vec, +static ssize_t kernel_readv(struct file *file, const struct kvec *vec, unsigned long vlen, loff_t offset) { mm_segment_t old_fs; @@ -580,102 +386,70 @@ ssize_t kernel_write(struct file *file, const char *buf, size_t count, } EXPORT_SYMBOL(kernel_write); -ssize_t default_file_splice_read(struct file *in, loff_t *ppos, +static ssize_t default_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { + struct kvec *vec, __vec[PIPE_DEF_BUFFERS]; + struct iov_iter to; + struct page **pages; unsigned int nr_pages; - unsigned int nr_freed; - size_t offset; - struct page *pages[PIPE_DEF_BUFFERS]; - struct partial_page partial[PIPE_DEF_BUFFERS]; - struct iovec *vec, __vec[PIPE_DEF_BUFFERS]; + size_t offset, dummy, copied = 0; ssize_t res; - size_t this_len; - int error; int i; - struct splice_pipe_desc spd = { - .pages = pages, - .partial = partial, - .nr_pages_max = PIPE_DEF_BUFFERS, - .flags = flags, - .ops = &default_pipe_buf_ops, - .spd_release = spd_release_page, - }; - if (splice_grow_spd(pipe, &spd)) + if (pipe->nrbufs == pipe->buffers) + return -EAGAIN; + + /* + * Try to keep page boundaries matching to source pagecache ones - + * it probably won't be much help, but... + */ + offset = *ppos & ~PAGE_MASK; + + iov_iter_pipe(&to, ITER_PIPE | READ, pipe, len + offset); + + res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &dummy); + if (res <= 0) return -ENOMEM; - res = -ENOMEM; + nr_pages = res / PAGE_SIZE; + vec = __vec; - if (spd.nr_pages_max > PIPE_DEF_BUFFERS) { - vec = kmalloc(spd.nr_pages_max * sizeof(struct iovec), GFP_KERNEL); - if (!vec) - goto shrink_ret; + if (nr_pages > PIPE_DEF_BUFFERS) { + vec = kmalloc(nr_pages * sizeof(struct kvec), GFP_KERNEL); + if (unlikely(!vec)) { + res = -ENOMEM; + goto out; + } } - offset = *ppos & ~PAGE_MASK; - nr_pages = (len + offset + PAGE_SIZE - 1) >> PAGE_SHIFT; - - for (i = 0; i < nr_pages && i < spd.nr_pages_max && len; i++) { - struct page *page; - - page = alloc_page(GFP_USER); - error = -ENOMEM; - if (!page) - goto err; + pipe->bufs[to.idx].offset = offset; + pipe->bufs[to.idx].len -= offset; - this_len = min_t(size_t, len, PAGE_SIZE - offset); - vec[i].iov_base = (void __user *) page_address(page); + for (i = 0; i < nr_pages; i++) { + size_t this_len = min_t(size_t, len, PAGE_SIZE - offset); + vec[i].iov_base = page_address(pages[i]) + offset; vec[i].iov_len = this_len; - spd.pages[i] = page; - spd.nr_pages++; len -= this_len; offset = 0; } - res = kernel_readv(in, vec, spd.nr_pages, *ppos); - if (res < 0) { - error = res; - goto err; - } - - error = 0; - if (!res) - goto err; - - nr_freed = 0; - for (i = 0; i < spd.nr_pages; i++) { - this_len = min_t(size_t, vec[i].iov_len, res); - spd.partial[i].offset = 0; - spd.partial[i].len = this_len; - if (!this_len) { - __free_page(spd.pages[i]); - spd.pages[i] = NULL; - nr_freed++; - } - res -= this_len; - } - spd.nr_pages -= nr_freed; - - res = splice_to_pipe(pipe, &spd); - if (res > 0) + res = kernel_readv(in, vec, nr_pages, *ppos); + if (res > 0) { + copied = res; *ppos += res; + } -shrink_ret: if (vec != __vec) kfree(vec); - splice_shrink_spd(&spd); +out: + for (i = 0; i < nr_pages; i++) + put_page(pages[i]); + kvfree(pages); + iov_iter_advance(&to, copied); /* truncates and discards */ return res; - -err: - for (i = 0; i < spd.nr_pages; i++) - __free_page(spd.pages[i]); - - res = error; - goto shrink_ret; } -EXPORT_SYMBOL(default_file_splice_read); /* * Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos' @@ -735,13 +509,12 @@ static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_des while (pipe->nrbufs) { struct pipe_buffer *buf = pipe->bufs + pipe->curbuf; - const struct pipe_buf_operations *ops = buf->ops; sd->len = buf->len; if (sd->len > sd->total_len) sd->len = sd->total_len; - ret = buf->ops->confirm(pipe, buf); + ret = pipe_buf_confirm(pipe, buf); if (unlikely(ret)) { if (ret == -ENODATA) ret = 0; @@ -761,8 +534,7 @@ static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_des sd->total_len -= ret; if (!buf->len) { - buf->ops = NULL; - ops->release(pipe, buf); + pipe_buf_release(pipe, buf); pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1); pipe->nrbufs--; if (pipe->files) @@ -981,7 +753,7 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, if (idx == pipe->buffers - 1) idx = -1; - ret = buf->ops->confirm(pipe, buf); + ret = pipe_buf_confirm(pipe, buf); if (unlikely(ret)) { if (ret == -ENODATA) ret = 0; @@ -1008,11 +780,9 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, while (ret) { struct pipe_buffer *buf = pipe->bufs + pipe->curbuf; if (ret >= buf->len) { - const struct pipe_buf_operations *ops = buf->ops; ret -= buf->len; buf->len = 0; - buf->ops = NULL; - ops->release(pipe, buf); + pipe_buf_release(pipe, buf); pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1); pipe->nrbufs--; if (pipe->files) @@ -1251,10 +1021,8 @@ out_release: for (i = 0; i < pipe->buffers; i++) { struct pipe_buffer *buf = pipe->bufs + i; - if (buf->ops) { - buf->ops->release(pipe, buf); - buf->ops = NULL; - } + if (buf->ops) + pipe_buf_release(pipe, buf); } if (!bytes) @@ -1815,7 +1583,7 @@ retry: * Get a reference to this pipe buffer, * so we can copy the contents over. */ - ibuf->ops->get(ipipe, ibuf); + pipe_buf_get(ipipe, ibuf); *obuf = *ibuf; /* @@ -1887,7 +1655,7 @@ static int link_pipe(struct pipe_inode_info *ipipe, * Get a reference to this pipe buffer, * so we can copy the contents over. */ - ibuf->ops->get(ipipe, ibuf); + pipe_buf_get(ipipe, ibuf); obuf = opipe->bufs + nbuf; *obuf = *ibuf;