// SPDX-License-Identifier: GPL-2.0-only /* * "splice": joining two ropes together by interweaving their strands. * * This is the "extended pipe" functionality, where a pipe is used as * an arbitrary in-memory buffer. Think of a pipe as a small kernel * buffer that you can use to transfer data from one end to the other. * * The traditional unix read/write is extended with a "splice()" operation * that transfers data buffers to or from a pipe buffer. * * Named by Larry McVoy, original implementation from Linus, extended by * Jens to support splicing to files, network, direct splicing, etc and * fixing lots of bugs. * * Copyright (C) 2005-2006 Jens Axboe * Copyright (C) 2005-2006 Linus Torvalds * Copyright (C) 2006 Ingo Molnar * */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include "internal.h" /* * Attempt to steal a page from a pipe buffer. This should perhaps go into * a vm helper function, it's already simplified quite a bit by the * addition of remove_mapping(). If success is returned, the caller may * attempt to reuse this page for another destination. */ static int page_cache_pipe_buf_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; struct address_space *mapping; lock_page(page); mapping = page_mapping(page); if (mapping) { WARN_ON(!PageUptodate(page)); /* * At least for ext2 with nobh option, we need to wait on * writeback completing on this page, since we'll remove it * from the pagecache. Otherwise truncate wont wait on the * page, allowing the disk blocks to be reused by someone else * before we actually wrote our data to them. fs corruption * ensues. */ wait_on_page_writeback(page); if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) goto out_unlock; /* * If we succeeded in removing the mapping, set LRU flag * and return good. */ if (remove_mapping(mapping, page)) { buf->flags |= PIPE_BUF_FLAG_LRU; return 0; } } /* * Raced with truncate or failed to remove page from current * address space, unlock and return failure. */ out_unlock: unlock_page(page); return 1; } static void page_cache_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { put_page(buf->page); buf->flags &= ~PIPE_BUF_FLAG_LRU; } /* * Check whether the contents of buf is OK to access. Since the content * is a page cache page, IO may be in flight. */ static int page_cache_pipe_buf_confirm(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; int err; if (!PageUptodate(page)) { lock_page(page); /* * Page got truncated/unhashed. This will cause a 0-byte * splice, if this is the first page. */ if (!page->mapping) { err = -ENODATA; goto error; } /* * Uh oh, read-error from disk. */ if (!PageUptodate(page)) { err = -EIO; goto error; } /* * Page is ok afterall, we are done. */ unlock_page(page); } return 0; error: unlock_page(page); return err; } const struct pipe_buf_operations page_cache_pipe_buf_ops = { .confirm = page_cache_pipe_buf_confirm, .release = page_cache_pipe_buf_release, .steal = page_cache_pipe_buf_steal, .get = generic_pipe_buf_get, }; static int user_page_pipe_buf_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { if (!(buf->flags & PIPE_BUF_FLAG_GIFT)) return 1; buf->flags |= PIPE_BUF_FLAG_LRU; return generic_pipe_buf_steal(pipe, buf); } static const struct pipe_buf_operations user_page_pipe_buf_ops = { .confirm = generic_pipe_buf_confirm, .release = page_cache_pipe_buf_release, .steal = user_page_pipe_buf_steal, .get = generic_pipe_buf_get, }; static void wakeup_pipe_readers(struct pipe_inode_info *pipe) { smp_mb(); if (waitqueue_active(&pipe->wait)) wake_up_interruptible(&pipe->wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); } /** * splice_to_pipe - fill passed data into a pipe * @pipe: pipe to fill * @spd: data to fill * * Description: * @spd contains a map of pages and len/offset tuples, along with * the struct pipe_buf_operations associated with these pages. This * function will link that data to the pipe. * */ ssize_t splice_to_pipe(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) { unsigned int spd_pages = spd->nr_pages; unsigned int tail = pipe->tail; unsigned int head = pipe->head; unsigned int mask = pipe->ring_size - 1; int ret = 0, page_nr = 0; if (!spd_pages) return 0; if (unlikely(!pipe->readers)) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; goto out; } while (!pipe_full(head, tail, pipe->max_usage)) { struct pipe_buffer *buf = &pipe->bufs[head & mask]; buf->page = spd->pages[page_nr]; buf->offset = spd->partial[page_nr].offset; buf->len = spd->partial[page_nr].len; buf->private = spd->partial[page_nr].private; buf->ops = spd->ops; buf->flags = 0; head++; pipe->head = head; page_nr++; ret += buf->len; if (!--spd->nr_pages) break; } if (!ret) ret = -EAGAIN; out: while (page_nr < spd_pages) spd->spd_release(spd, page_nr++); return ret; } EXPORT_SYMBOL_GPL(splice_to_pipe); ssize_t add_to_pipe(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { unsigned int head = pipe->head; unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; int ret; if (unlikely(!pipe->readers)) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; } else if (pipe_full(head, tail, pipe->max_usage)) { ret = -EAGAIN; } else { pipe->bufs[head & mask] = *buf; pipe->head = head + 1; return buf->len; } pipe_buf_release(pipe, buf); return ret; } EXPORT_SYMBOL(add_to_pipe); /* * Check if we need to grow the arrays holding pages and partial page * descriptions. */ int splice_grow_spd(const struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) { unsigned int max_usage = READ_ONCE(pipe->max_usage); spd->nr_pages_max = max_usage; if (max_usage <= PIPE_DEF_BUFFERS) return 0; spd->pages = kmalloc_array(max_usage, sizeof(struct page *), GFP_KERNEL); spd->partial = kmalloc_array(max_usage, sizeof(struct partial_page), GFP_KERNEL); if (spd->pages && spd->partial) return 0; kfree(spd->pages); kfree(spd->partial); return -ENOMEM; } void splice_shrink_spd(struct splice_pipe_desc *spd) { if (spd->nr_pages_max <= PIPE_DEF_BUFFERS) return; kfree(spd->pages); kfree(spd->partial); } /** * generic_file_splice_read - splice data from file to a pipe * @in: file to splice from * @ppos: position in @in * @pipe: pipe to splice to * @len: number of bytes to splice * @flags: splice modifier flags * * Description: * Will read pages from given file and fill them into a pipe. Can be * 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) { struct iov_iter to; struct kiocb kiocb; unsigned int i_head; int ret; iov_iter_pipe(&to, READ, pipe, len); i_head = to.head; init_sync_kiocb(&kiocb, in); kiocb.ki_pos = *ppos; ret = call_read_iter(in, &kiocb, &to); if (ret > 0) { *ppos = kiocb.ki_pos; file_accessed(in); } else if (ret < 0) { to.head = i_head; 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; } EXPORT_SYMBOL(generic_file_splice_read); const struct pipe_buf_operations default_pipe_buf_ops = { .confirm = generic_pipe_buf_confirm, .release = generic_pipe_buf_release, .steal = generic_pipe_buf_steal, .get = generic_pipe_buf_get, }; int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { return 1; } /* Pipe buffer operations for a socket and similar. */ const struct pipe_buf_operations nosteal_pipe_buf_ops = { .confirm = generic_pipe_buf_confirm, .release = generic_pipe_buf_release, .steal = generic_pipe_buf_nosteal, .get = generic_pipe_buf_get, }; EXPORT_SYMBOL(nosteal_pipe_buf_ops); static ssize_t kernel_readv(struct file *file, const struct kvec *vec, unsigned long vlen, loff_t offset) { mm_segment_t old_fs; loff_t pos = offset; ssize_t res; old_fs = get_fs(); set_fs(KERNEL_DS); /* The cast to a user pointer is valid due to the set_fs() */ res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0); set_fs(old_fs); return res; } 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 mask; size_t offset, base, copied = 0; ssize_t res; int i; if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) 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, READ, pipe, len + offset); res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &base); if (res <= 0) return -ENOMEM; nr_pages = DIV_ROUND_UP(res + base, PAGE_SIZE); vec = __vec; if (nr_pages > PIPE_DEF_BUFFERS) { vec = kmalloc_array(nr_pages, sizeof(struct kvec), GFP_KERNEL); if (unlikely(!vec)) { res = -ENOMEM; goto out; } } mask = pipe->ring_size - 1; pipe->bufs[to.head & mask].offset = offset; pipe->bufs[to.head & mask].len -= offset; 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; len -= this_len; offset = 0; } res = kernel_readv(in, vec, nr_pages, *ppos); if (res > 0) { copied = res; *ppos += res; } if (vec != __vec) kfree(vec); out: for (i = 0; i < nr_pages; i++) put_page(pages[i]); kvfree(pages); iov_iter_advance(&to, copied); /* truncates and discards */ return res; } /* * Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos' * using sendpage(). Return the number of bytes sent. */ static int pipe_to_sendpage(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct splice_desc *sd) { struct file *file = sd->u.file; loff_t pos = sd->pos; int more; if (!likely(file->f_op->sendpage)) return -EINVAL; more = (sd->flags & SPLICE_F_MORE) ? MSG_MORE : 0; if (sd->len < sd->total_len && pipe_occupancy(pipe->head, pipe->tail) > 1) more |= MSG_SENDPAGE_NOTLAST; return file->f_op->sendpage(file, buf->page, buf->offset, sd->len, &pos, more); } static void wakeup_pipe_writers(struct pipe_inode_info *pipe) { smp_mb(); if (waitqueue_active(&pipe->wait)) wake_up_interruptible(&pipe->wait); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } /** * splice_from_pipe_feed - feed available data from a pipe to a file * @pipe: pipe to splice from * @sd: information to @actor * @actor: handler that splices the data * * Description: * This function loops over the pipe and calls @actor to do the * actual moving of a single struct pipe_buffer to the desired * destination. It returns when there's no more buffers left in * the pipe or if the requested number of bytes (@sd->total_len) * have been copied. It returns a positive number (one) if the * pipe needs to be filled with more data, zero if the required * number of bytes have been copied and -errno on error. * * This, together with splice_from_pipe_{begin,end,next}, may be * used to implement the functionality of __splice_from_pipe() when * locking is required around copying the pipe buffers to the * destination. */ static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_desc *sd, splice_actor *actor) { unsigned int head = pipe->head; unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; int ret; while (!pipe_empty(tail, head)) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; sd->len = buf->len; if (sd->len > sd->total_len) sd->len = sd->total_len; ret = pipe_buf_confirm(pipe, buf); if (unlikely(ret)) { if (ret == -ENODATA) ret = 0; return ret; } ret = actor(pipe, buf, sd); if (ret <= 0) return ret; buf->offset += ret; buf->len -= ret; sd->num_spliced += ret; sd->len -= ret; sd->pos += ret; sd->total_len -= ret; if (!buf->len) { pipe_buf_release(pipe, buf); tail++; pipe->tail = tail; if (pipe->files) sd->need_wakeup = true; } if (!sd->total_len) return 0; } return 1; } /** * splice_from_pipe_next - wait for some data to splice from * @pipe: pipe to splice from * @sd: information about the splice operation * * Description: * This function will wait for some data and return a positive * value (one) if pipe buffers are available. It will return zero * or -errno if no more data needs to be spliced. */ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_desc *sd) { /* * Check for signal early to make process killable when there are * always buffers available */ if (signal_pending(current)) return -ERESTARTSYS; while (pipe_empty(pipe->head, pipe->tail)) { if (!pipe->writers) return 0; if (!pipe->waiting_writers && sd->num_spliced) return 0; if (sd->flags & SPLICE_F_NONBLOCK) return -EAGAIN; if (signal_pending(current)) return -ERESTARTSYS; if (sd->need_wakeup) { wakeup_pipe_writers(pipe); sd->need_wakeup = false; } pipe_wait(pipe); } return 1; } /** * splice_from_pipe_begin - start splicing from pipe * @sd: information about the splice operation * * Description: * This function should be called before a loop containing * splice_from_pipe_next() and splice_from_pipe_feed() to * initialize the necessary fields of @sd. */ static void splice_from_pipe_begin(struct splice_desc *sd) { sd->num_spliced = 0; sd->need_wakeup = false; } /** * splice_from_pipe_end - finish splicing from pipe * @pipe: pipe to splice from * @sd: information about the splice operation * * Description: * This function will wake up pipe writers if necessary. It should * be called after a loop containing splice_from_pipe_next() and * splice_from_pipe_feed(). */ static void splice_from_pipe_end(struct pipe_inode_info *pipe, struct splice_desc *sd) { if (sd->need_wakeup) wakeup_pipe_writers(pipe); } /** * __splice_from_pipe - splice data from a pipe to given actor * @pipe: pipe to splice from * @sd: information to @actor * @actor: handler that splices the data * * Description: * This function does little more than loop over the pipe and call * @actor to do the actual moving of a single struct pipe_buffer to * the desired destination. See pipe_to_file, pipe_to_sendpage, or * pipe_to_user. * */ ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd, splice_actor *actor) { int ret; splice_from_pipe_begin(sd); do { cond_resched(); ret = splice_from_pipe_next(pipe, sd); if (ret > 0) ret = splice_from_pipe_feed(pipe, sd, actor); } while (ret > 0); splice_from_pipe_end(pipe, sd); return sd->num_spliced ? sd->num_spliced : ret; } EXPORT_SYMBOL(__splice_from_pipe); /** * splice_from_pipe - splice data from a pipe to a file * @pipe: pipe to splice from * @out: file to splice to * @ppos: position in @out * @len: how many bytes to splice * @flags: splice modifier flags * @actor: handler that splices the data * * Description: * See __splice_from_pipe. This function locks the pipe inode, * otherwise it's identical to __splice_from_pipe(). * */ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags, splice_actor *actor) { ssize_t ret; struct splice_desc sd = { .total_len = len, .flags = flags, .pos = *ppos, .u.file = out, }; pipe_lock(pipe); ret = __splice_from_pipe(pipe, &sd, actor); pipe_unlock(pipe); return ret; } /** * iter_file_splice_write - splice data from a pipe to a file * @pipe: pipe info * @out: file to write to * @ppos: position in @out * @len: number of bytes to splice * @flags: splice modifier flags * * Description: * Will either move or copy pages (determined by @flags options) from * the given pipe inode to the given file. * This one is ->write_iter-based. * */ ssize_t iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { struct splice_desc sd = { .total_len = len, .flags = flags, .pos = *ppos, .u.file = out, }; int nbufs = pipe->max_usage; struct bio_vec *array = kcalloc(nbufs, sizeof(struct bio_vec), GFP_KERNEL); ssize_t ret; if (unlikely(!array)) return -ENOMEM; pipe_lock(pipe); splice_from_pipe_begin(&sd); while (sd.total_len) { struct iov_iter from; unsigned int head = pipe->head; unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; size_t left; int n; ret = splice_from_pipe_next(pipe, &sd); if (ret <= 0) break; if (unlikely(nbufs < pipe->max_usage)) { kfree(array); nbufs = pipe->max_usage; array = kcalloc(nbufs, sizeof(struct bio_vec), GFP_KERNEL); if (!array) { ret = -ENOMEM; break; } } /* build the vector */ left = sd.total_len; for (n = 0; !pipe_empty(head, tail) && left && n < nbufs; tail++, n++) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t this_len = buf->len; if (this_len > left) this_len = left; ret = pipe_buf_confirm(pipe, buf); if (unlikely(ret)) { if (ret == -ENODATA) ret = 0; goto done; } array[n].bv_page = buf->page; array[n].bv_len = this_len; array[n].bv_offset = buf->offset; left -= this_len; } iov_iter_bvec(&from, WRITE, array, n, sd.total_len - left); ret = vfs_iter_write(out, &from, &sd.pos, 0); if (ret <= 0) break; sd.num_spliced += ret; sd.total_len -= ret; *ppos = sd.pos; /* dismiss the fully eaten buffers, adjust the partial one */ tail = pipe->tail; while (ret) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; if (ret >= buf->len) { ret -= buf->len; buf->len = 0; pipe_buf_release(pipe, buf); tail++; pipe->tail = tail; if (pipe->files) sd.need_wakeup = true; } else { buf->offset += ret; buf->len -= ret; ret = 0; } } } done: kfree(array); splice_from_pipe_end(pipe, &sd); pipe_unlock(pipe); if (sd.num_spliced) ret = sd.num_spliced; return ret; } EXPORT_SYMBOL(iter_file_splice_write); static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct splice_desc *sd) { int ret; void *data; loff_t tmp = sd->pos; data = kmap(buf->page); ret = __kernel_write(sd->u.file, data + buf->offset, sd->len, &tmp); kunmap(buf->page); return ret; } static ssize_t default_file_splice_write(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { ssize_t ret; ret = splice_from_pipe(pipe, out, ppos, len, flags, write_pipe_buf); if (ret > 0) *ppos += ret; return ret; } /** * generic_splice_sendpage - splice data from a pipe to a socket * @pipe: pipe to splice from * @out: socket to write to * @ppos: position in @out * @len: number of bytes to splice * @flags: splice modifier flags * * Description: * Will send @len bytes from the pipe to a network socket. No data copying * is involved. * */ ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { return splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_sendpage); } EXPORT_SYMBOL(generic_splice_sendpage); /* * Attempt to initiate a splice from pipe to file. */ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); if (out->f_op->splice_write) splice_write = out->f_op->splice_write; else splice_write = default_file_splice_write; return splice_write(pipe, out, ppos, len, flags); } /* * Attempt to initiate a splice from a file to a pipe. */ static long do_splice_to(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); int ret; if (unlikely(!(in->f_mode & FMODE_READ))) return -EBADF; ret = rw_verify_area(READ, in, ppos, len); if (unlikely(ret < 0)) return ret; if (unlikely(len > MAX_RW_COUNT)) len = MAX_RW_COUNT; if (in->f_op->splice_read) splice_read = in->f_op->splice_read; else splice_read = default_file_splice_read; return splice_read(in, ppos, pipe, len, flags); } /** * splice_direct_to_actor - splices data directly between two non-pipes * @in: file to splice from * @sd: actor information on where to splice to * @actor: handles the data splicing * * Description: * This is a special case helper to splice directly between two * points, without requiring an explicit pipe. Internally an allocated * pipe is cached in the process, and reused during the lifetime of * that process. * */ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, splice_direct_actor *actor) { struct pipe_inode_info *pipe; long ret, bytes; umode_t i_mode; size_t len; int i, flags, more; /* * We require the input being a regular file, as we don't want to * randomly drop data for eg socket -> socket splicing. Use the * piped splicing for that! */ i_mode = file_inode(in)->i_mode; if (unlikely(!S_ISREG(i_mode) && !S_ISBLK(i_mode))) return -EINVAL; /* * neither in nor out is a pipe, setup an internal pipe attached to * 'out' and transfer the wanted data from 'in' to 'out' through that */ pipe = current->splice_pipe; if (unlikely(!pipe)) { pipe = alloc_pipe_info(); if (!pipe) return -ENOMEM; /* * We don't have an immediate reader, but we'll read the stuff * out of the pipe right after the splice_to_pipe(). So set * PIPE_READERS appropriately. */ pipe->readers = 1; current->splice_pipe = pipe; } /* * Do the splice. */ ret = 0; bytes = 0; len = sd->total_len; flags = sd->flags; /* * Don't block on output, we have to drain the direct pipe. */ sd->flags &= ~SPLICE_F_NONBLOCK; more = sd->flags & SPLICE_F_MORE; WARN_ON_ONCE(!pipe_empty(pipe->head, pipe->tail)); while (len) { unsigned int p_space; size_t read_len; loff_t pos = sd->pos, prev_pos = pos; /* Don't try to read more the pipe has space for. */ p_space = pipe->max_usage - pipe_occupancy(pipe->head, pipe->tail); read_len = min_t(size_t, len, p_space << PAGE_SHIFT); ret = do_splice_to(in, &pos, pipe, read_len, flags); if (unlikely(ret <= 0)) goto out_release; read_len = ret; sd->total_len = read_len; /* * If more data is pending, set SPLICE_F_MORE * If this is the last data and SPLICE_F_MORE was not set * initially, clears it. */ if (read_len < len) sd->flags |= SPLICE_F_MORE; else if (!more) sd->flags &= ~SPLICE_F_MORE; /* * NOTE: nonblocking mode only applies to the input. We * must not do the output in nonblocking mode as then we * could get stuck data in the internal pipe: */ ret = actor(pipe, sd); if (unlikely(ret <= 0)) { sd->pos = prev_pos; goto out_release; } bytes += ret; len -= ret; sd->pos = pos; if (ret < read_len) { sd->pos = prev_pos + ret; goto out_release; } } done: pipe->tail = pipe->head = 0; file_accessed(in); return bytes; out_release: /* * If we did an incomplete transfer we must release * the pipe buffers in question: */ for (i = 0; i < pipe->ring_size; i++) { struct pipe_buffer *buf = &pipe->bufs[i]; if (buf->ops) pipe_buf_release(pipe, buf); } if (!bytes) bytes = ret; goto done; } EXPORT_SYMBOL(splice_direct_to_actor); static int direct_splice_actor(struct pipe_inode_info *pipe, struct splice_desc *sd) { struct file *file = sd->u.file; return do_splice_from(pipe, file, sd->opos, sd->total_len, sd->flags); } /** * do_splice_direct - splices data directly between two files * @in: file to splice from * @ppos: input file offset * @out: file to splice to * @opos: output file offset * @len: number of bytes to splice * @flags: splice modifier flags * * Description: * For use by do_sendfile(). splice can easily emulate sendfile, but * doing it in the application would incur an extra system call * (splice in + splice out, as compared to just sendfile()). So this helper * can splice directly through a process-private pipe. * */ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, loff_t *opos, size_t len, unsigned int flags) { struct splice_desc sd = { .len = len, .total_len = len, .flags = flags, .pos = *ppos, .u.file = out, .opos = opos, }; long ret; if (unlikely(!(out->f_mode & FMODE_WRITE))) return -EBADF; if (unlikely(out->f_flags & O_APPEND)) return -EINVAL; ret = rw_verify_area(WRITE, out, opos, len); if (unlikely(ret < 0)) return ret; ret = splice_direct_to_actor(in, &sd, direct_splice_actor); if (ret > 0) *ppos = sd.pos; return ret; } EXPORT_SYMBOL(do_splice_direct); static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags) { for (;;) { if (unlikely(!pipe->readers)) { send_sig(SIGPIPE, current, 0); return -EPIPE; } if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage)) return 0; if (flags & SPLICE_F_NONBLOCK) return -EAGAIN; if (signal_pending(current)) return -ERESTARTSYS; pipe->waiting_writers++; pipe_wait(pipe); pipe->waiting_writers--; } } static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, struct pipe_inode_info *opipe, size_t len, unsigned int flags); /* * Determine where to splice to/from. */ static long do_splice(struct file *in, loff_t __user *off_in, struct file *out, loff_t __user *off_out, size_t len, unsigned int flags) { struct pipe_inode_info *ipipe; struct pipe_inode_info *opipe; loff_t offset; long ret; ipipe = get_pipe_info(in); opipe = get_pipe_info(out); if (ipipe && opipe) { if (off_in || off_out) return -ESPIPE; if (!(in->f_mode & FMODE_READ)) return -EBADF; if (!(out->f_mode & FMODE_WRITE)) return -EBADF; /* Splicing to self would be fun, but... */ if (ipipe == opipe) return -EINVAL; if ((in->f_flags | out->f_flags) & O_NONBLOCK) flags |= SPLICE_F_NONBLOCK; return splice_pipe_to_pipe(ipipe, opipe, len, flags); } if (ipipe) { if (off_in) return -ESPIPE; if (off_out) { if (!(out->f_mode & FMODE_PWRITE)) return -EINVAL; if (copy_from_user(&offset, off_out, sizeof(loff_t))) return -EFAULT; } else { offset = out->f_pos; } if (unlikely(!(out->f_mode & FMODE_WRITE))) return -EBADF; if (unlikely(out->f_flags & O_APPEND)) return -EINVAL; ret = rw_verify_area(WRITE, out, &offset, len); if (unlikely(ret < 0)) return ret; if (in->f_flags & O_NONBLOCK) flags |= SPLICE_F_NONBLOCK; file_start_write(out); ret = do_splice_from(ipipe, out, &offset, len, flags); file_end_write(out); if (!off_out) out->f_pos = offset; else if (copy_to_user(off_out, &offset, sizeof(loff_t))) ret = -EFAULT; return ret; } if (opipe) { if (off_out) return -ESPIPE; if (off_in) { if (!(in->f_mode & FMODE_PREAD)) return -EINVAL; if (copy_from_user(&offset, off_in, sizeof(loff_t))) return -EFAULT; } else { offset = in->f_pos; } if (out->f_flags & O_NONBLOCK) flags |= SPLICE_F_NONBLOCK; pipe_lock(opipe); ret = wait_for_space(opipe, flags); if (!ret) ret = do_splice_to(in, &offset, opipe, len, flags); pipe_unlock(opipe); if (ret > 0) wakeup_pipe_readers(opipe); if (!off_in) in->f_pos = offset; else if (copy_to_user(off_in, &offset, sizeof(loff_t))) ret = -EFAULT; return ret; } return -EINVAL; } static int iter_to_pipe(struct iov_iter *from, struct pipe_inode_info *pipe, unsigned flags) { struct pipe_buffer buf = { .ops = &user_page_pipe_buf_ops, .flags = flags }; size_t total = 0; int ret = 0; bool failed = false; while (iov_iter_count(from) && !failed) { struct page *pages[16]; ssize_t copied; size_t start; int n; copied = iov_iter_get_pages(from, pages, ~0UL, 16, &start); if (copied <= 0) { ret = copied; break; } for (n = 0; copied; n++, start = 0) { int size = min_t(int, copied, PAGE_SIZE - start); if (!failed) { buf.page = pages[n]; buf.offset = start; buf.len = size; ret = add_to_pipe(pipe, &buf); if (unlikely(ret < 0)) { failed = true; } else { iov_iter_advance(from, ret); total += ret; } } else { put_page(pages[n]); } copied -= size; } } return total ? total : ret; } static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct splice_desc *sd) { int n = copy_page_to_iter(buf->page, buf->offset, sd->len, sd->u.data); return n == sd->len ? n : -EFAULT; } /* * For lack of a better implementation, implement vmsplice() to userspace * as a simple copy of the pipes pages to the user iov. */ static long vmsplice_to_user(struct file *file, struct iov_iter *iter, unsigned int flags) { struct pipe_inode_info *pipe = get_pipe_info(file); struct splice_desc sd = { .total_len = iov_iter_count(iter), .flags = flags, .u.data = iter }; long ret = 0; if (!pipe) return -EBADF; if (sd.total_len) { pipe_lock(pipe); ret = __splice_from_pipe(pipe, &sd, pipe_to_user); pipe_unlock(pipe); } return ret; } /* * vmsplice splices a user address range into a pipe. It can be thought of * as splice-from-memory, where the regular splice is splice-from-file (or * to file). In both cases the output is a pipe, naturally. */ static long vmsplice_to_pipe(struct file *file, struct iov_iter *iter, unsigned int flags) { struct pipe_inode_info *pipe; long ret = 0; unsigned buf_flag = 0; if (flags & SPLICE_F_GIFT) buf_flag = PIPE_BUF_FLAG_GIFT; pipe = get_pipe_info(file); if (!pipe) return -EBADF; pipe_lock(pipe); ret = wait_for_space(pipe, flags); if (!ret) ret = iter_to_pipe(iter, pipe, buf_flag); pipe_unlock(pipe); if (ret > 0) wakeup_pipe_readers(pipe); return ret; } static int vmsplice_type(struct fd f, int *type) { if (!f.file) return -EBADF; if (f.file->f_mode & FMODE_WRITE) { *type = WRITE; } else if (f.file->f_mode & FMODE_READ) { *type = READ; } else { fdput(f); return -EBADF; } return 0; } /* * Note that vmsplice only really supports true splicing _from_ user memory * to a pipe, not the other way around. Splicing from user memory is a simple * operation that can be supported without any funky alignment restrictions * or nasty vm tricks. We simply map in the user memory and fill them into * a pipe. The reverse isn't quite as easy, though. There are two possible * solutions for that: * * - memcpy() the data internally, at which point we might as well just * do a regular read() on the buffer anyway. * - Lots of nasty vm tricks, that are neither fast nor flexible (it * has restriction limitations on both ends of the pipe). * * Currently we punt and implement it as a normal copy, see pipe_to_user(). * */ static long do_vmsplice(struct file *f, struct iov_iter *iter, unsigned int flags) { if (unlikely(flags & ~SPLICE_F_ALL)) return -EINVAL; if (!iov_iter_count(iter)) return 0; if (iov_iter_rw(iter) == WRITE) return vmsplice_to_pipe(f, iter, flags); else return vmsplice_to_user(f, iter, flags); } SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov, unsigned long, nr_segs, unsigned int, flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; ssize_t error; struct fd f; int type; f = fdget(fd); error = vmsplice_type(f, &type); if (error) return error; error = import_iovec(type, uiov, nr_segs, ARRAY_SIZE(iovstack), &iov, &iter); if (error >= 0) { error = do_vmsplice(f.file, &iter, flags); kfree(iov); } fdput(f); return error; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(vmsplice, int, fd, const struct compat_iovec __user *, iov32, unsigned int, nr_segs, unsigned int, flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; ssize_t error; struct fd f; int type; f = fdget(fd); error = vmsplice_type(f, &type); if (error) return error; error = compat_import_iovec(type, iov32, nr_segs, ARRAY_SIZE(iovstack), &iov, &iter); if (error >= 0) { error = do_vmsplice(f.file, &iter, flags); kfree(iov); } fdput(f); return error; } #endif SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags) { struct fd in, out; long error; if (unlikely(!len)) return 0; if (unlikely(flags & ~SPLICE_F_ALL)) return -EINVAL; error = -EBADF; in = fdget(fd_in); if (in.file) { if (in.file->f_mode & FMODE_READ) { out = fdget(fd_out); if (out.file) { if (out.file->f_mode & FMODE_WRITE) error = do_splice(in.file, off_in, out.file, off_out, len, flags); fdput(out); } } fdput(in); } return error; } /* * Make sure there's data to read. Wait for input if we can, otherwise * return an appropriate error. */ static int ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags) { int ret; /* * Check the pipe occupancy without the inode lock first. This function * is speculative anyways, so missing one is ok. */ if (!pipe_empty(pipe->head, pipe->tail)) return 0; ret = 0; pipe_lock(pipe); while (pipe_empty(pipe->head, pipe->tail)) { if (signal_pending(current)) { ret = -ERESTARTSYS; break; } if (!pipe->writers) break; if (!pipe->waiting_writers) { if (flags & SPLICE_F_NONBLOCK) { ret = -EAGAIN; break; } } pipe_wait(pipe); } pipe_unlock(pipe); return ret; } /* * Make sure there's writeable room. Wait for room if we can, otherwise * return an appropriate error. */ static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags) { int ret; /* * Check pipe occupancy without the inode lock first. This function * is speculative anyways, so missing one is ok. */ if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) return 0; ret = 0; pipe_lock(pipe); while (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) { if (!pipe->readers) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; break; } if (flags & SPLICE_F_NONBLOCK) { ret = -EAGAIN; break; } if (signal_pending(current)) { ret = -ERESTARTSYS; break; } pipe->waiting_writers++; pipe_wait(pipe); pipe->waiting_writers--; } pipe_unlock(pipe); return ret; } /* * Splice contents of ipipe to opipe. */ static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, struct pipe_inode_info *opipe, size_t len, unsigned int flags) { struct pipe_buffer *ibuf, *obuf; unsigned int i_head, o_head; unsigned int i_tail, o_tail; unsigned int i_mask, o_mask; int ret = 0; bool input_wakeup = false; retry: ret = ipipe_prep(ipipe, flags); if (ret) return ret; ret = opipe_prep(opipe, flags); if (ret) return ret; /* * Potential ABBA deadlock, work around it by ordering lock * grabbing by pipe info address. Otherwise two different processes * could deadlock (one doing tee from A -> B, the other from B -> A). */ pipe_double_lock(ipipe, opipe); i_tail = ipipe->tail; i_mask = ipipe->ring_size - 1; o_head = opipe->head; o_mask = opipe->ring_size - 1; do { size_t o_len; if (!opipe->readers) { send_sig(SIGPIPE, current, 0); if (!ret) ret = -EPIPE; break; } i_head = ipipe->head; o_tail = opipe->tail; if (pipe_empty(i_head, i_tail) && !ipipe->writers) break; /* * Cannot make any progress, because either the input * pipe is empty or the output pipe is full. */ if (pipe_empty(i_head, i_tail) || pipe_full(o_head, o_tail, opipe->max_usage)) { /* Already processed some buffers, break */ if (ret) break; if (flags & SPLICE_F_NONBLOCK) { ret = -EAGAIN; break; } /* * We raced with another reader/writer and haven't * managed to process any buffers. A zero return * value means EOF, so retry instead. */ pipe_unlock(ipipe); pipe_unlock(opipe); goto retry; } ibuf = &ipipe->bufs[i_tail & i_mask]; obuf = &opipe->bufs[o_head & o_mask]; if (len >= ibuf->len) { /* * Simply move the whole buffer from ipipe to opipe */ *obuf = *ibuf; ibuf->ops = NULL; i_tail++; ipipe->tail = i_tail; input_wakeup = true; o_len = obuf->len; o_head++; opipe->head = o_head; } else { /* * Get a reference to this pipe buffer, * so we can copy the contents over. */ if (!pipe_buf_get(ipipe, ibuf)) { if (ret == 0) ret = -EFAULT; break; } *obuf = *ibuf; /* * Don't inherit the gift flag, we need to * prevent multiple steals of this page. */ obuf->flags &= ~PIPE_BUF_FLAG_GIFT; pipe_buf_mark_unmergeable(obuf); obuf->len = len; ibuf->offset += len; ibuf->len -= len; o_len = len; o_head++; opipe->head = o_head; } ret += o_len; len -= o_len; } while (len); pipe_unlock(ipipe); pipe_unlock(opipe); /* * If we put data in the output pipe, wakeup any potential readers. */ if (ret > 0) wakeup_pipe_readers(opipe); if (input_wakeup) wakeup_pipe_writers(ipipe); return ret; } /* * Link contents of ipipe to opipe. */ static int link_pipe(struct pipe_inode_info *ipipe, struct pipe_inode_info *opipe, size_t len, unsigned int flags) { struct pipe_buffer *ibuf, *obuf; unsigned int i_head, o_head; unsigned int i_tail, o_tail; unsigned int i_mask, o_mask; int ret = 0; /* * Potential ABBA deadlock, work around it by ordering lock * grabbing by pipe info address. Otherwise two different processes * could deadlock (one doing tee from A -> B, the other from B -> A). */ pipe_double_lock(ipipe, opipe); i_tail = ipipe->tail; i_mask = ipipe->ring_size - 1; o_head = opipe->head; o_mask = opipe->ring_size - 1; do { if (!opipe->readers) { send_sig(SIGPIPE, current, 0); if (!ret) ret = -EPIPE; break; } i_head = ipipe->head; o_tail = opipe->tail; /* * If we have iterated all input buffers or run out of * output room, break. */ if (pipe_empty(i_head, i_tail) || pipe_full(o_head, o_tail, opipe->max_usage)) break; ibuf = &ipipe->bufs[i_tail & i_mask]; obuf = &opipe->bufs[o_head & o_mask]; /* * Get a reference to this pipe buffer, * so we can copy the contents over. */ if (!pipe_buf_get(ipipe, ibuf)) { if (ret == 0) ret = -EFAULT; break; } *obuf = *ibuf; /* * Don't inherit the gift flag, we need to * prevent multiple steals of this page. */ obuf->flags &= ~PIPE_BUF_FLAG_GIFT; pipe_buf_mark_unmergeable(obuf); if (obuf->len > len) obuf->len = len; ret += obuf->len; len -= obuf->len; o_head++; opipe->head = o_head; i_tail++; } while (len); /* * return EAGAIN if we have the potential of some data in the * future, otherwise just return 0 */ if (!ret && ipipe->waiting_writers && (flags & SPLICE_F_NONBLOCK)) ret = -EAGAIN; pipe_unlock(ipipe); pipe_unlock(opipe); /* * If we put data in the output pipe, wakeup any potential readers. */ if (ret > 0) wakeup_pipe_readers(opipe); return ret; } /* * This is a tee(1) implementation that works on pipes. It doesn't copy * any data, it simply references the 'in' pages on the 'out' pipe. * The 'flags' used are the SPLICE_F_* variants, currently the only * applicable one is SPLICE_F_NONBLOCK. */ static long do_tee(struct file *in, struct file *out, size_t len, unsigned int flags) { struct pipe_inode_info *ipipe = get_pipe_info(in); struct pipe_inode_info *opipe = get_pipe_info(out); int ret = -EINVAL; /* * Duplicate the contents of ipipe to opipe without actually * copying the data. */ if (ipipe && opipe && ipipe != opipe) { if ((in->f_flags | out->f_flags) & O_NONBLOCK) flags |= SPLICE_F_NONBLOCK; /* * Keep going, unless we encounter an error. The ipipe/opipe * ordering doesn't really matter. */ ret = ipipe_prep(ipipe, flags); if (!ret) { ret = opipe_prep(opipe, flags); if (!ret) ret = link_pipe(ipipe, opipe, len, flags); } } return ret; } SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags) { struct fd in; int error; if (unlikely(flags & ~SPLICE_F_ALL)) return -EINVAL; if (unlikely(!len)) return 0; error = -EBADF; in = fdget(fdin); if (in.file) { if (in.file->f_mode & FMODE_READ) { struct fd out = fdget(fdout); if (out.file) { if (out.file->f_mode & FMODE_WRITE) error = do_tee(in.file, out.file, len, flags); fdput(out); } } fdput(in); } return error; }