X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fsplice.c;h=4ed0ba44a966ce053cdf11475333f4bdb0bb73b4;hb=adc487204a9373d2b5a535412466326036147a72;hp=0b2c1f060cae772824f6107a1d9010b0bcb9e93c;hpb=912d35f86781e64d73be1ef358f703c08905ac37;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/splice.c b/fs/splice.c index 0b2c1f0..4ed0ba4 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -12,7 +12,7 @@ * 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 Jens Axboe * Copyright (C) 2005-2006 Linus Torvalds * Copyright (C) 2006 Ingo Molnar * @@ -20,7 +20,8 @@ #include #include #include -#include +#include +#include #include #include #include @@ -28,32 +29,7 @@ #include #include #include - -/* - * Passed to the actors - */ -struct splice_desc { - unsigned int len, total_len; /* current and remaining length */ - unsigned int flags; /* splice flags */ - struct file *file; /* file to read/write */ - loff_t pos; /* file position */ -}; - -struct partial_page { - unsigned int offset; - unsigned int len; -}; - -/* - * Passed to move_to_pipe - */ -struct splice_pipe_desc { - struct page **pages; /* page map */ - struct partial_page *partial; /* pages[] may not be contig */ - int nr_pages; /* number of pages in map */ - unsigned int flags; /* splice flags */ - struct pipe_buf_operations *ops;/* ops associated with output pipe */ -}; +#include /* * Attempt to steal a page from a pipe buffer. This should perhaps go into @@ -61,48 +37,63 @@ struct splice_pipe_desc { * 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 *info, +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 = page_mapping(page); + struct address_space *mapping; lock_page(page); - WARN_ON(!PageUptodate(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); + /* + * 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 (PagePrivate(page)) - try_to_release_page(page, mapping_gfp_mask(mapping)); + if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL)) + goto out_unlock; - if (!remove_mapping(mapping, page)) { - unlock_page(page); - return 1; + /* + * 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; + } } - buf->flags |= PIPE_BUF_FLAG_STOLEN | 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 *info, +static void page_cache_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { page_cache_release(buf->page); - buf->page = NULL; - buf->flags &= ~(PIPE_BUF_FLAG_STOLEN | PIPE_BUF_FLAG_LRU); + buf->flags &= ~PIPE_BUF_FLAG_LRU; } -static void *page_cache_pipe_buf_map(struct file *file, - struct pipe_inode_info *info, - struct pipe_buffer *buf) +/* + * 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; @@ -128,73 +119,62 @@ static void *page_cache_pipe_buf_map(struct file *file, } /* - * Page is ok afterall, fall through to mapping. + * Page is ok afterall, we are done. */ unlock_page(page); } - return kmap(page); + return 0; error: unlock_page(page); - return ERR_PTR(err); -} - -static void page_cache_pipe_buf_unmap(struct pipe_inode_info *info, - struct pipe_buffer *buf) -{ - kunmap(buf->page); -} - -static void *user_page_pipe_buf_map(struct file *file, - struct pipe_inode_info *pipe, - struct pipe_buffer *buf) -{ - return kmap(buf->page); -} - -static void user_page_pipe_buf_unmap(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) -{ - kunmap(buf->page); -} - -static void page_cache_pipe_buf_get(struct pipe_inode_info *info, - struct pipe_buffer *buf) -{ - page_cache_get(buf->page); + return err; } -static struct pipe_buf_operations page_cache_pipe_buf_ops = { +static const struct pipe_buf_operations page_cache_pipe_buf_ops = { .can_merge = 0, - .map = page_cache_pipe_buf_map, - .unmap = page_cache_pipe_buf_unmap, + .map = generic_pipe_buf_map, + .unmap = generic_pipe_buf_unmap, + .confirm = page_cache_pipe_buf_confirm, .release = page_cache_pipe_buf_release, .steal = page_cache_pipe_buf_steal, - .get = page_cache_pipe_buf_get, + .get = generic_pipe_buf_get, }; static int user_page_pipe_buf_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - return 1; + if (!(buf->flags & PIPE_BUF_FLAG_GIFT)) + return 1; + + buf->flags |= PIPE_BUF_FLAG_LRU; + return generic_pipe_buf_steal(pipe, buf); } -static struct pipe_buf_operations user_page_pipe_buf_ops = { +static const struct pipe_buf_operations user_page_pipe_buf_ops = { .can_merge = 0, - .map = user_page_pipe_buf_map, - .unmap = user_page_pipe_buf_unmap, + .map = generic_pipe_buf_map, + .unmap = generic_pipe_buf_unmap, + .confirm = generic_pipe_buf_confirm, .release = page_cache_pipe_buf_release, .steal = user_page_pipe_buf_steal, - .get = page_cache_pipe_buf_get, + .get = generic_pipe_buf_get, }; -/* - * Pipe output worker. This sets up our pipe format with the page cache - * pipe buffer operations. Otherwise very similar to the regular pipe_writev(). +/** + * 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. + * */ -static ssize_t move_to_pipe(struct pipe_inode_info *pipe, - struct splice_pipe_desc *spd) +ssize_t splice_to_pipe(struct pipe_inode_info *pipe, + struct splice_pipe_desc *spd) { + unsigned int spd_pages = spd->nr_pages; int ret, do_wakeup, page_nr; ret = 0; @@ -219,7 +199,11 @@ static ssize_t move_to_pipe(struct pipe_inode_info *pipe, 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; + if (spd->flags & SPLICE_F_GIFT) + buf->flags |= PIPE_BUF_FLAG_GIFT; + pipe->nrbufs++; page_nr++; ret += buf->len; @@ -260,81 +244,78 @@ static ssize_t move_to_pipe(struct pipe_inode_info *pipe, pipe->waiting_writers--; } - if (pipe->inode) + if (pipe->inode) { mutex_unlock(&pipe->inode->i_mutex); - if (do_wakeup) { - smp_mb(); - if (waitqueue_active(&pipe->wait)) - wake_up_interruptible(&pipe->wait); - kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); + if (do_wakeup) { + smp_mb(); + if (waitqueue_active(&pipe->wait)) + wake_up_interruptible(&pipe->wait); + kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); + } } - while (page_nr < spd->nr_pages) - page_cache_release(spd->pages[page_nr++]); + while (page_nr < spd_pages) + spd->spd_release(spd, page_nr++); return ret; } +static void spd_release_page(struct splice_pipe_desc *spd, unsigned int i) +{ + page_cache_release(spd->pages[i]); +} + 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; + unsigned int loff, nr_pages, req_pages; struct page *pages[PIPE_BUFFERS]; struct partial_page partial[PIPE_BUFFERS]; struct page *page; pgoff_t index, end_index; loff_t isize; - size_t total_len; - int error; + int error, page_nr; struct splice_pipe_desc spd = { .pages = pages, .partial = partial, .flags = flags, .ops = &page_cache_pipe_buf_ops, + .spd_release = spd_release_page, }; index = *ppos >> PAGE_CACHE_SHIFT; loff = *ppos & ~PAGE_CACHE_MASK; - nr_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - - if (nr_pages > PIPE_BUFFERS) - nr_pages = PIPE_BUFFERS; + req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + nr_pages = min(req_pages, (unsigned)PIPE_BUFFERS); /* - * Initiate read-ahead on this page range. however, don't call into - * read-ahead if this is a non-zero offset (we are likely doing small - * chunk splice and the page is already there) for a single page. + * Lookup the (hopefully) full range of pages we need. */ - if (!loff || spd.nr_pages > 1) - do_page_cache_readahead(mapping, in, index, spd.nr_pages); + spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, pages); + index += spd.nr_pages; /* - * Now fill in the holes: + * If find_get_pages_contig() returned fewer pages than we needed, + * readahead/allocate the rest and fill in the holes. */ - error = 0; - total_len = 0; - for (spd.nr_pages = 0; spd.nr_pages < nr_pages; spd.nr_pages++, index++) { - unsigned int this_len; + if (spd.nr_pages < nr_pages) + page_cache_sync_readahead(mapping, &in->f_ra, in, + index, req_pages - spd.nr_pages); - if (!len) - break; - - /* - * this_len is the max we'll use from this page - */ - this_len = min_t(unsigned long, len, PAGE_CACHE_SIZE - loff); -find_page: + error = 0; + while (spd.nr_pages < nr_pages) { /* - * lookup the page for this index + * 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 didn't exist, allocate one. */ page = page_cache_alloc_cold(mapping); if (!page) @@ -344,12 +325,44 @@ find_page: mapping_gfp_mask(mapping)); if (unlikely(error)) { page_cache_release(page); + if (error == -EEXIST) + continue; break; } - - goto readpage; + /* + * add_to_page_cache() locks the page, unlock it + * to avoid convoluting the logic below even more. + */ + unlock_page(page); } + 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_CACHE_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_CACHE_SIZE - loff); + page = 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 */ @@ -358,20 +371,31 @@ find_page: * If in nonblock mode then dont block on waiting * for an in-flight io page */ - if (flags & SPLICE_F_NONBLOCK) - break; - - lock_page(page); + if (flags & SPLICE_F_NONBLOCK) { + if (!trylock_page(page)) { + error = -EAGAIN; + break; + } + } else + lock_page(page); /* - * page was truncated, stop here. if this isn't the - * first page, we'll just complete what we already - * added + * 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); - page_cache_release(page); - break; + page = find_or_create_page(mapping, index, + mapping_gfp_mask(mapping)); + + if (!page) { + error = -ENOMEM; + break; + } + page_cache_release(pages[page_nr]); + pages[page_nr] = page; } /* * page was already under io and is now done, great @@ -381,58 +405,71 @@ find_page: goto fill_it; } -readpage: /* * need to read in the page */ error = mapping->a_ops->readpage(in, page); - if (unlikely(error)) { - page_cache_release(page); + /* + * We really should re-lookup the page here, + * but it complicates things a lot. Instead + * lets just do what we already stored, and + * we'll get it the next time we are called. + */ if (error == AOP_TRUNCATED_PAGE) - goto find_page; + error = 0; + break; } + } +fill_it: + /* + * i_size must be checked after PageUptodate. + */ + isize = i_size_read(mapping->host); + end_index = (isize - 1) >> PAGE_CACHE_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; /* - * i_size must be checked after ->readpage(). + * max good bytes in this page */ - isize = i_size_read(mapping->host); - end_index = (isize - 1) >> PAGE_CACHE_SHIFT; - if (unlikely(!isize || index > end_index)) { - page_cache_release(page); + plen = ((isize - 1) & ~PAGE_CACHE_MASK) + 1; + if (plen <= loff) break; - } /* - * if this is the last page, see if we need to shrink - * the length and stop + * force quit after adding this page */ - if (end_index == index) { - loff = PAGE_CACHE_SIZE - (isize & ~PAGE_CACHE_MASK); - if (total_len + loff > isize) { - page_cache_release(page); - break; - } - /* - * force quit after adding this page - */ - nr_pages = spd.nr_pages; - this_len = min(this_len, loff); - loff = 0; - } + this_len = min(this_len, plen - loff); + len = this_len; } -fill_it: - pages[spd.nr_pages] = page; - partial[spd.nr_pages].offset = loff; - partial[spd.nr_pages].len = this_len; + + partial[page_nr].offset = loff; + partial[page_nr].len = this_len; len -= this_len; - total_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) + page_cache_release(pages[page_nr++]); + in->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT; + if (spd.nr_pages) - return move_to_pipe(pipe, &spd); + return splice_to_pipe(pipe, &spd); return error; } @@ -440,43 +477,35 @@ fill_it: /** * 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 * - * Will read pages from given file and fill them into a pipe. + * 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. + * */ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { - ssize_t spliced; + loff_t isize, left; int ret; - ret = 0; - spliced = 0; - - while (len) { - ret = __generic_file_splice_read(in, ppos, pipe, len, flags); + isize = i_size_read(in->f_mapping->host); + if (unlikely(*ppos >= isize)) + return 0; - if (ret < 0) - break; - else if (!ret) { - if (spliced) - break; - if (flags & SPLICE_F_NONBLOCK) { - ret = -EAGAIN; - break; - } - } + left = isize - *ppos; + if (unlikely(left < len)) + len = left; + ret = __generic_file_splice_read(in, ppos, pipe, len, flags); + if (ret > 0) *ppos += ret; - len -= ret; - spliced += ret; - } - - if (spliced) - return spliced; return ret; } @@ -487,31 +516,21 @@ EXPORT_SYMBOL(generic_file_splice_read); * 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 *info, +static int pipe_to_sendpage(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct splice_desc *sd) { - struct file *file = sd->file; + struct file *file = sd->u.file; loff_t pos = sd->pos; - ssize_t ret; - void *ptr; - int more; + int ret, more; - /* - * Sub-optimal, but we are limited by the pipe ->map. We don't - * need a kmap'ed buffer here, we just want to make sure we - * have the page pinned if the pipe page originates from the - * page cache. - */ - ptr = buf->ops->map(file, info, buf); - if (IS_ERR(ptr)) - return PTR_ERR(ptr); + ret = buf->ops->confirm(pipe, buf); + if (!ret) { + more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len; - more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len; - - ret = file->f_op->sendpage(file, buf->page, buf->offset, sd->len, - &pos, more); + ret = file->f_op->sendpage(file, buf->page, buf->offset, + sd->len, &pos, more); + } - buf->ops->unmap(info, buf); return ret; } @@ -535,173 +554,83 @@ static int pipe_to_sendpage(struct pipe_inode_info *info, * SPLICE_F_MOVE isn't set, or we cannot move the page, we simply create * a new page in the output file page cache and fill/dirty that. */ -static int pipe_to_file(struct pipe_inode_info *info, struct pipe_buffer *buf, +static int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct splice_desc *sd) { - struct file *file = sd->file; + struct file *file = sd->u.file; struct address_space *mapping = file->f_mapping; - gfp_t gfp_mask = mapping_gfp_mask(mapping); unsigned int offset, this_len; struct page *page; - pgoff_t index; - char *src; + void *fsdata; int ret; /* * make sure the data in this buffer is uptodate */ - src = buf->ops->map(file, info, buf); - if (IS_ERR(src)) - return PTR_ERR(src); + ret = buf->ops->confirm(pipe, buf); + if (unlikely(ret)) + return ret; - index = sd->pos >> PAGE_CACHE_SHIFT; offset = sd->pos & ~PAGE_CACHE_MASK; this_len = sd->len; if (this_len + offset > PAGE_CACHE_SIZE) this_len = PAGE_CACHE_SIZE - offset; - /* - * Reuse buf page, if SPLICE_F_MOVE is set. - */ - if (sd->flags & SPLICE_F_MOVE) { - /* - * If steal succeeds, buf->page is now pruned from the vm - * side (LRU and page cache) and we can reuse it. The page - * will also be looked on successful return. - */ - if (buf->ops->steal(info, buf)) - goto find_page; - - page = buf->page; - if (add_to_page_cache(page, mapping, index, gfp_mask)) - goto find_page; - - if (!(buf->flags & PIPE_BUF_FLAG_LRU)) - lru_cache_add(page); - } else { -find_page: - page = find_lock_page(mapping, index); - if (!page) { - ret = -ENOMEM; - page = page_cache_alloc_cold(mapping); - if (unlikely(!page)) - goto out_nomem; - - /* - * This will also lock the page - */ - ret = add_to_page_cache_lru(page, mapping, index, - gfp_mask); - if (unlikely(ret)) - goto out; - } + ret = pagecache_write_begin(file, mapping, sd->pos, this_len, + AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata); + if (unlikely(ret)) + goto out; + if (buf->page != page) { /* - * We get here with the page locked. If the page is also - * uptodate, we don't need to do more. If it isn't, we - * may need to bring it in if we are not going to overwrite - * the full page. + * Careful, ->map() uses KM_USER0! */ - if (!PageUptodate(page)) { - if (this_len < PAGE_CACHE_SIZE) { - ret = mapping->a_ops->readpage(file, page); - if (unlikely(ret)) - goto out; - - lock_page(page); - - if (!PageUptodate(page)) { - /* - * Page got invalidated, repeat. - */ - if (!page->mapping) { - unlock_page(page); - page_cache_release(page); - goto find_page; - } - ret = -EIO; - goto out; - } - } else - SetPageUptodate(page); - } - } - - ret = mapping->a_ops->prepare_write(file, page, offset, offset+this_len); - if (ret == AOP_TRUNCATED_PAGE) { - page_cache_release(page); - goto find_page; - } else if (ret) - goto out; - - if (!(buf->flags & PIPE_BUF_FLAG_STOLEN)) { - char *dst = kmap_atomic(page, KM_USER0); + char *src = buf->ops->map(pipe, buf, 1); + char *dst = kmap_atomic(page, KM_USER1); memcpy(dst + offset, src + buf->offset, this_len); flush_dcache_page(page); - kunmap_atomic(dst, KM_USER0); + kunmap_atomic(dst, KM_USER1); + buf->ops->unmap(pipe, buf, src); } - - ret = mapping->a_ops->commit_write(file, page, offset, offset+this_len); - if (ret == AOP_TRUNCATED_PAGE) { - page_cache_release(page); - goto find_page; - } else if (ret) - goto out; - - /* - * Return the number of bytes written. - */ - ret = this_len; - mark_page_accessed(page); - balance_dirty_pages_ratelimited(mapping); + ret = pagecache_write_end(file, mapping, sd->pos, this_len, this_len, + page, fsdata); out: - if (!(buf->flags & PIPE_BUF_FLAG_STOLEN)) - page_cache_release(page); - - unlock_page(page); -out_nomem: - buf->ops->unmap(info, buf); return ret; } -typedef int (splice_actor)(struct pipe_inode_info *, struct pipe_buffer *, - struct splice_desc *); - -/* - * Pipe input worker. Most of this logic works like a regular pipe, the - * key here is the 'actor' worker passed in that actually moves the data - * to the wanted destination. See pipe_to_file/pipe_to_sendpage above. +/** + * __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. + * */ -static ssize_t move_from_pipe(struct pipe_inode_info *pipe, struct file *out, - loff_t *ppos, size_t len, unsigned int flags, - splice_actor *actor) +ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd, + splice_actor *actor) { int ret, do_wakeup, err; - struct splice_desc sd; ret = 0; do_wakeup = 0; - sd.total_len = len; - sd.flags = flags; - sd.file = out; - sd.pos = *ppos; - - if (pipe->inode) - mutex_lock(&pipe->inode->i_mutex); - for (;;) { if (pipe->nrbufs) { struct pipe_buffer *buf = pipe->bufs + pipe->curbuf; - struct pipe_buf_operations *ops = buf->ops; + const struct pipe_buf_operations *ops = buf->ops; - sd.len = buf->len; - if (sd.len > sd.total_len) - sd.len = sd.total_len; + sd->len = buf->len; + if (sd->len > sd->total_len) + sd->len = sd->total_len; - err = actor(pipe, buf, &sd); + err = actor(pipe, buf, sd); if (err <= 0) { if (!ret && err != -ENODATA) ret = err; @@ -713,10 +642,10 @@ static ssize_t move_from_pipe(struct pipe_inode_info *pipe, struct file *out, buf->offset += err; buf->len -= err; - sd.len -= err; - sd.pos += err; - sd.total_len -= err; - if (sd.len) + sd->len -= err; + sd->pos += err; + sd->total_len -= err; + if (sd->len) continue; if (!buf->len) { @@ -728,7 +657,7 @@ static ssize_t move_from_pipe(struct pipe_inode_info *pipe, struct file *out, do_wakeup = 1; } - if (!sd.total_len) + if (!sd->total_len) break; } @@ -741,7 +670,7 @@ static ssize_t move_from_pipe(struct pipe_inode_info *pipe, struct file *out, break; } - if (flags & SPLICE_F_NONBLOCK) { + if (sd->flags & SPLICE_F_NONBLOCK) { if (!ret) ret = -EAGAIN; break; @@ -764,9 +693,6 @@ static ssize_t move_from_pipe(struct pipe_inode_info *pipe, struct file *out, pipe_wait(pipe); } - if (pipe->inode) - mutex_unlock(&pipe->inode->i_mutex); - if (do_wakeup) { smp_mb(); if (waitqueue_active(&pipe->wait)) @@ -776,78 +702,195 @@ static ssize_t move_from_pipe(struct pipe_inode_info *pipe, struct file *out, return ret; } +EXPORT_SYMBOL(__splice_from_pipe); /** - * generic_file_splice_write - splice data from a pipe to a file + * 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 input and output inodes, + * 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 inode *inode = out->f_mapping->host; + struct splice_desc sd = { + .total_len = len, + .flags = flags, + .pos = *ppos, + .u.file = out, + }; + + /* + * The actor worker might be calling ->write_begin and + * ->write_end. Most of the time, these expect i_mutex to + * be held. Since this may result in an ABBA deadlock with + * pipe->inode, we have to order lock acquiry here. + */ + inode_double_lock(inode, pipe->inode); + ret = __splice_from_pipe(pipe, &sd, actor); + inode_double_unlock(inode, pipe->inode); + + return ret; +} + +/** + * generic_file_splice_write_nolock - generic_file_splice_write without mutexes * @pipe: pipe info * @out: file to write to + * @ppos: position in @out * @len: number of bytes to splice * @flags: splice modifier flags * - * Will either move or copy pages (determined by @flags options) from - * the given pipe inode to the given file. + * Description: + * Will either move or copy pages (determined by @flags options) from + * the given pipe inode to the given file. The caller is responsible + * for acquiring i_mutex on both inodes. * */ ssize_t -generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out, - loff_t *ppos, size_t len, unsigned int flags) +generic_file_splice_write_nolock(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags) { struct address_space *mapping = out->f_mapping; + struct inode *inode = mapping->host; + struct splice_desc sd = { + .total_len = len, + .flags = flags, + .pos = *ppos, + .u.file = out, + }; ssize_t ret; + int err; + + err = file_remove_suid(out); + if (unlikely(err)) + return err; - ret = move_from_pipe(pipe, out, ppos, len, flags, pipe_to_file); + ret = __splice_from_pipe(pipe, &sd, pipe_to_file); if (ret > 0) { - struct inode *inode = mapping->host; + unsigned long nr_pages; *ppos += ret; + nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; /* * If file or inode is SYNC and we actually wrote some data, * sync it. */ if (unlikely((out->f_flags & O_SYNC) || IS_SYNC(inode))) { - int err; - - mutex_lock(&inode->i_mutex); err = generic_osync_inode(inode, mapping, OSYNC_METADATA|OSYNC_DATA); - mutex_unlock(&inode->i_mutex); if (err) ret = err; } + balance_dirty_pages_ratelimited_nr(mapping, nr_pages); } return ret; } -EXPORT_SYMBOL(generic_file_splice_write); +EXPORT_SYMBOL(generic_file_splice_write_nolock); /** - * generic_splice_sendpage - splice data from a pipe to a socket - * @inode: pipe inode - * @out: socket to write to + * generic_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 * - * Will send @len bytes from the pipe to a network socket. No data copying - * is involved. + * Description: + * Will either move or copy pages (determined by @flags options) from + * the given pipe inode to the given file. * */ -ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out, - loff_t *ppos, size_t len, unsigned int flags) +ssize_t +generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags) { - return move_from_pipe(pipe, out, ppos, len, flags, pipe_to_sendpage); -} + struct address_space *mapping = out->f_mapping; + struct inode *inode = mapping->host; + struct splice_desc sd = { + .total_len = len, + .flags = flags, + .pos = *ppos, + .u.file = out, + }; + ssize_t ret; -EXPORT_SYMBOL(generic_splice_sendpage); + inode_double_lock(inode, pipe->inode); + ret = file_remove_suid(out); + if (likely(!ret)) + ret = __splice_from_pipe(pipe, &sd, pipe_to_file); + inode_double_unlock(inode, pipe->inode); + if (ret > 0) { + unsigned long nr_pages; -/* - * 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) -{ + *ppos += ret; + nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + + /* + * If file or inode is SYNC and we actually wrote some data, + * sync it. + */ + if (unlikely((out->f_flags & O_SYNC) || IS_SYNC(inode))) { + int err; + + mutex_lock(&inode->i_mutex); + err = generic_osync_inode(inode, mapping, + OSYNC_METADATA|OSYNC_DATA); + mutex_unlock(&inode->i_mutex); + + if (err) + ret = err; + } + balance_dirty_pages_ratelimited_nr(mapping, nr_pages); + } + + return ret; +} + +EXPORT_SYMBOL(generic_file_splice_write); + +/** + * 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) +{ int ret; if (unlikely(!out->f_op || !out->f_op->splice_write)) @@ -856,6 +899,9 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, if (unlikely(!(out->f_mode & FMODE_WRITE))) return -EBADF; + if (unlikely(out->f_flags & O_APPEND)) + return -EINVAL; + ret = rw_verify_area(WRITE, out, ppos, len); if (unlikely(ret < 0)) return ret; @@ -870,7 +916,6 @@ static long do_splice_to(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { - loff_t isize, left; int ret; if (unlikely(!in->f_op || !in->f_op->splice_read)) @@ -883,32 +928,37 @@ static long do_splice_to(struct file *in, loff_t *ppos, if (unlikely(ret < 0)) return ret; - isize = i_size_read(in->f_mapping->host); - if (unlikely(*ppos >= isize)) - return 0; - - left = isize - *ppos; - if (unlikely(left < len)) - len = left; - return in->f_op->splice_read(in, ppos, pipe, len, flags); } -long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, - size_t len, unsigned int 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; - loff_t out_off; umode_t i_mode; - int i; + size_t len; + int i, flags; /* * 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 = in->f_dentry->d_inode->i_mode; + i_mode = in->f_path.dentry->d_inode->i_mode; if (unlikely(!S_ISREG(i_mode) && !S_ISBLK(i_mode))) return -EINVAL; @@ -924,7 +974,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, /* * We don't have an immediate reader, but we'll read the stuff - * out of the pipe right after the move_to_pipe(). So set + * out of the pipe right after the splice_to_pipe(). So set * PIPE_READERS appropriately. */ pipe->readers = 1; @@ -937,49 +987,49 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, */ ret = 0; bytes = 0; - out_off = 0; + len = sd->total_len; + flags = sd->flags; - while (len) { - size_t read_len, max_read_len; + /* + * Don't block on output, we have to drain the direct pipe. + */ + sd->flags &= ~SPLICE_F_NONBLOCK; - /* - * Do at most PIPE_BUFFERS pages worth of transfer: - */ - max_read_len = min(len, (size_t)(PIPE_BUFFERS*PAGE_SIZE)); + while (len) { + size_t read_len; + loff_t pos = sd->pos, prev_pos = pos; - ret = do_splice_to(in, ppos, pipe, max_read_len, flags); - if (unlikely(ret < 0)) + ret = do_splice_to(in, &pos, pipe, len, flags); + if (unlikely(ret <= 0)) goto out_release; read_len = ret; + sd->total_len = read_len; /* * 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 = do_splice_from(pipe, out, &out_off, read_len, - flags & ~SPLICE_F_NONBLOCK); - if (unlikely(ret < 0)) + ret = actor(pipe, sd); + if (unlikely(ret <= 0)) { + sd->pos = prev_pos; goto out_release; + } bytes += ret; len -= ret; + sd->pos = pos; - /* - * In nonblocking mode, if we got back a short read then - * that was due to either an IO error or due to the - * pagecache entry not being there. In the IO error case - * the _next_ splice attempt will produce a clean IO error - * return value (not a short read), so in both cases it's - * correct to break out of the loop here: - */ - if ((flags & SPLICE_F_NONBLOCK) && (read_len < max_read_len)) - break; + if (ret < read_len) { + sd->pos = prev_pos + ret; + goto out_release; + } } +done: pipe->nrbufs = pipe->curbuf = 0; - + file_accessed(in); return bytes; out_release: @@ -995,18 +1045,68 @@ out_release: buf->ops = NULL; } } - pipe->nrbufs = pipe->curbuf = 0; - /* - * If we transferred some data, return the number of bytes: - */ - if (bytes > 0) - return bytes; + 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->pos, 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 + * @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, + size_t len, unsigned int flags) +{ + struct splice_desc sd = { + .len = len, + .total_len = len, + .flags = flags, + .pos = *ppos, + .u.file = out, + }; + long ret; + + ret = splice_direct_to_actor(in, &sd, direct_splice_actor); + if (ret > 0) + *ppos = sd.pos; return ret; } -EXPORT_SYMBOL(do_splice_direct); +/* + * After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same + * location, so checking ->i_pipe is not enough to verify that this is a + * pipe. + */ +static inline struct pipe_inode_info *pipe_info(struct inode *inode) +{ + if (S_ISFIFO(inode->i_mode)) + return inode->i_pipe; + + return NULL; +} /* * Determine where to splice to/from. @@ -1019,7 +1119,7 @@ static long do_splice(struct file *in, loff_t __user *off_in, loff_t offset, *off; long ret; - pipe = in->f_dentry->d_inode->i_pipe; + pipe = pipe_info(in->f_path.dentry->d_inode); if (pipe) { if (off_in) return -ESPIPE; @@ -1040,7 +1140,7 @@ static long do_splice(struct file *in, loff_t __user *off_in, return ret; } - pipe = out->f_dentry->d_inode->i_pipe; + pipe = pipe_info(out->f_path.dentry->d_inode); if (pipe) { if (off_out) return -ESPIPE; @@ -1073,39 +1173,32 @@ static long do_splice(struct file *in, loff_t __user *off_in, */ static int get_iovec_page_array(const struct iovec __user *iov, unsigned int nr_vecs, struct page **pages, - struct partial_page *partial) + struct partial_page *partial, int aligned) { int buffers = 0, error = 0; - /* - * It's ok to take the mmap_sem for reading, even - * across a "get_user()". - */ - down_read(¤t->mm->mmap_sem); - while (nr_vecs) { unsigned long off, npages; + struct iovec entry; void __user *base; size_t len; int i; - /* - * Get user address base and length for this iovec. - */ - error = get_user(base, &iov->iov_base); - if (unlikely(error)) - break; - error = get_user(len, &iov->iov_len); - if (unlikely(error)) + error = -EFAULT; + if (copy_from_user(&entry, iov, sizeof(entry))) break; + base = entry.iov_base; + len = entry.iov_len; + /* * Sanity check this iovec. 0 read succeeds. */ + error = 0; if (unlikely(!len)) break; error = -EFAULT; - if (unlikely(!base)) + if (!access_ok(VERIFY_READ, base, len)) break; /* @@ -1113,13 +1206,21 @@ static int get_iovec_page_array(const struct iovec __user *iov, * in the user pages. */ off = (unsigned long) base & ~PAGE_MASK; + + /* + * If asked for alignment, the offset must be zero and the + * length a multiple of the PAGE_SIZE. + */ + error = -EINVAL; + if (aligned && (off || len & ~PAGE_MASK)) + break; + npages = (off + len + PAGE_SIZE - 1) >> PAGE_SHIFT; if (npages > PIPE_BUFFERS - buffers) npages = PIPE_BUFFERS - buffers; - error = get_user_pages(current, current->mm, - (unsigned long) base, npages, 0, 0, - &pages[buffers], NULL); + error = get_user_pages_fast((unsigned long)base, npages, + 0, &pages[buffers]); if (unlikely(error <= 0)) break; @@ -1128,7 +1229,7 @@ static int get_iovec_page_array(const struct iovec __user *iov, * Fill this contiguous range into the partial page map. */ for (i = 0; i < error; i++) { - const int plen = min_t(size_t, len, PAGE_SIZE) - off; + const int plen = min_t(size_t, len, PAGE_SIZE - off); partial[buffers].offset = off; partial[buffers].len = plen; @@ -1158,38 +1259,144 @@ static int get_iovec_page_array(const struct iovec __user *iov, iov++; } - up_read(¤t->mm->mmap_sem); - if (buffers) return buffers; return error; } +static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf, + struct splice_desc *sd) +{ + char *src; + int ret; + + ret = buf->ops->confirm(pipe, buf); + if (unlikely(ret)) + return ret; + + /* + * See if we can use the atomic maps, by prefaulting in the + * pages and doing an atomic copy + */ + if (!fault_in_pages_writeable(sd->u.userptr, sd->len)) { + src = buf->ops->map(pipe, buf, 1); + ret = __copy_to_user_inatomic(sd->u.userptr, src + buf->offset, + sd->len); + buf->ops->unmap(pipe, buf, src); + if (!ret) { + ret = sd->len; + goto out; + } + } + + /* + * No dice, use slow non-atomic map and copy + */ + src = buf->ops->map(pipe, buf, 0); + + ret = sd->len; + if (copy_to_user(sd->u.userptr, src + buf->offset, sd->len)) + ret = -EFAULT; + + buf->ops->unmap(pipe, buf, src); +out: + if (ret > 0) + sd->u.userptr += ret; + return ret; +} + +/* + * 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, const struct iovec __user *iov, + unsigned long nr_segs, unsigned int flags) +{ + struct pipe_inode_info *pipe; + struct splice_desc sd; + ssize_t size; + int error; + long ret; + + pipe = pipe_info(file->f_path.dentry->d_inode); + if (!pipe) + return -EBADF; + + if (pipe->inode) + mutex_lock(&pipe->inode->i_mutex); + + error = ret = 0; + while (nr_segs) { + void __user *base; + size_t len; + + /* + * Get user address base and length for this iovec. + */ + error = get_user(base, &iov->iov_base); + if (unlikely(error)) + break; + error = get_user(len, &iov->iov_len); + if (unlikely(error)) + break; + + /* + * Sanity check this iovec. 0 read succeeds. + */ + if (unlikely(!len)) + break; + if (unlikely(!base)) { + error = -EFAULT; + break; + } + + if (unlikely(!access_ok(VERIFY_WRITE, base, len))) { + error = -EFAULT; + break; + } + + sd.len = 0; + sd.total_len = len; + sd.flags = flags; + sd.u.userptr = base; + sd.pos = 0; + + size = __splice_from_pipe(pipe, &sd, pipe_to_user); + if (size < 0) { + if (!ret) + ret = size; + + break; + } + + ret += size; + + if (size < len) + break; + + nr_segs--; + iov++; + } + + if (pipe->inode) + mutex_unlock(&pipe->inode->i_mutex); + + if (!ret) + ret = error; + + 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. - * - * Note that vmsplice only supports 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). - * - * Alas, it isn't here. - * */ -static long do_vmsplice(struct file *file, const struct iovec __user *iov, - unsigned long nr_segs, unsigned int flags) +static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov, + unsigned long nr_segs, unsigned int flags) { - struct pipe_inode_info *pipe = file->f_dentry->d_inode->i_pipe; + struct pipe_inode_info *pipe; struct page *pages[PIPE_BUFFERS]; struct partial_page partial[PIPE_BUFFERS]; struct splice_pipe_desc spd = { @@ -1197,34 +1404,56 @@ static long do_vmsplice(struct file *file, const struct iovec __user *iov, .partial = partial, .flags = flags, .ops = &user_page_pipe_buf_ops, + .spd_release = spd_release_page, }; - if (unlikely(!pipe)) + pipe = pipe_info(file->f_path.dentry->d_inode); + if (!pipe) return -EBADF; - if (unlikely(nr_segs > UIO_MAXIOV)) - return -EINVAL; - else if (unlikely(!nr_segs)) - return 0; - spd.nr_pages = get_iovec_page_array(iov, nr_segs, pages, partial); + spd.nr_pages = get_iovec_page_array(iov, nr_segs, pages, partial, + flags & SPLICE_F_GIFT); if (spd.nr_pages <= 0) return spd.nr_pages; - return move_to_pipe(pipe, &spd); + return splice_to_pipe(pipe, &spd); } -asmlinkage long sys_vmsplice(int fd, const struct iovec __user *iov, - unsigned long nr_segs, unsigned int flags) +/* + * 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(). + * + */ +SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, iov, + unsigned long, nr_segs, unsigned int, flags) { struct file *file; long error; int fput; + if (unlikely(nr_segs > UIO_MAXIOV)) + return -EINVAL; + else if (unlikely(!nr_segs)) + return 0; + error = -EBADF; file = fget_light(fd, &fput); if (file) { if (file->f_mode & FMODE_WRITE) - error = do_vmsplice(file, iov, nr_segs, flags); + error = vmsplice_to_pipe(file, iov, nr_segs, flags); + else if (file->f_mode & FMODE_READ) + error = vmsplice_to_user(file, iov, nr_segs, flags); fput_light(file, fput); } @@ -1232,9 +1461,9 @@ asmlinkage long sys_vmsplice(int fd, const struct iovec __user *iov, return error; } -asmlinkage long sys_splice(int fd_in, loff_t __user *off_in, - int fd_out, loff_t __user *off_out, - size_t len, unsigned int flags) +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) { long error; struct file *in, *out; @@ -1264,6 +1493,85 @@ asmlinkage long sys_splice(int fd_in, loff_t __user *off_in, } /* + * Make sure there's data to read. Wait for input if we can, otherwise + * return an appropriate error. + */ +static int link_ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags) +{ + int ret; + + /* + * Check ->nrbufs without the inode lock first. This function + * is speculative anyways, so missing one is ok. + */ + if (pipe->nrbufs) + return 0; + + ret = 0; + mutex_lock(&pipe->inode->i_mutex); + + while (!pipe->nrbufs) { + 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); + } + + mutex_unlock(&pipe->inode->i_mutex); + return ret; +} + +/* + * Make sure there's writeable room. Wait for room if we can, otherwise + * return an appropriate error. + */ +static int link_opipe_prep(struct pipe_inode_info *pipe, unsigned int flags) +{ + int ret; + + /* + * Check ->nrbufs without the inode lock first. This function + * is speculative anyways, so missing one is ok. + */ + if (pipe->nrbufs < PIPE_BUFFERS) + return 0; + + ret = 0; + mutex_lock(&pipe->inode->i_mutex); + + while (pipe->nrbufs >= PIPE_BUFFERS) { + 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--; + } + + mutex_unlock(&pipe->inode->i_mutex); + return ret; +} + +/* * Link contents of ipipe to opipe. */ static int link_pipe(struct pipe_inode_info *ipipe, @@ -1271,130 +1579,70 @@ static int link_pipe(struct pipe_inode_info *ipipe, size_t len, unsigned int flags) { struct pipe_buffer *ibuf, *obuf; - int ret, do_wakeup, i, ipipe_first; - - ret = do_wakeup = ipipe_first = 0; + int ret = 0, i = 0, nbuf; /* * Potential ABBA deadlock, work around it by ordering lock * grabbing by inode address. Otherwise two different processes * could deadlock (one doing tee from A -> B, the other from B -> A). */ - if (ipipe->inode < opipe->inode) { - ipipe_first = 1; - mutex_lock(&ipipe->inode->i_mutex); - mutex_lock(&opipe->inode->i_mutex); - } else { - mutex_lock(&opipe->inode->i_mutex); - mutex_lock(&ipipe->inode->i_mutex); - } + inode_double_lock(ipipe->inode, opipe->inode); - for (i = 0;; i++) { + do { if (!opipe->readers) { send_sig(SIGPIPE, current, 0); if (!ret) ret = -EPIPE; break; } - if (ipipe->nrbufs - i) { - ibuf = ipipe->bufs + ((ipipe->curbuf + i) & (PIPE_BUFFERS - 1)); - - /* - * If we have room, fill this buffer - */ - if (opipe->nrbufs < PIPE_BUFFERS) { - int nbuf = (opipe->curbuf + opipe->nrbufs) & (PIPE_BUFFERS - 1); - - /* - * Get a reference to this pipe buffer, - * so we can copy the contents over. - */ - ibuf->ops->get(ipipe, ibuf); - - obuf = opipe->bufs + nbuf; - *obuf = *ibuf; - - if (obuf->len > len) - obuf->len = len; - - opipe->nrbufs++; - do_wakeup = 1; - ret += obuf->len; - len -= obuf->len; - - if (!len) - break; - if (opipe->nrbufs < PIPE_BUFFERS) - continue; - } - /* - * We have input available, but no output room. - * If we already copied data, return that. If we - * need to drop the opipe lock, it must be ordered - * last to avoid deadlocks. - */ - if ((flags & SPLICE_F_NONBLOCK) || !ipipe_first) { - if (!ret) - ret = -EAGAIN; - break; - } - if (signal_pending(current)) { - if (!ret) - ret = -ERESTARTSYS; - break; - } - if (do_wakeup) { - smp_mb(); - if (waitqueue_active(&opipe->wait)) - wake_up_interruptible(&opipe->wait); - kill_fasync(&opipe->fasync_readers, SIGIO, POLL_IN); - do_wakeup = 0; - } + /* + * If we have iterated all input buffers or ran out of + * output room, break. + */ + if (i >= ipipe->nrbufs || opipe->nrbufs >= PIPE_BUFFERS) + break; - opipe->waiting_writers++; - pipe_wait(opipe); - opipe->waiting_writers--; - continue; - } + ibuf = ipipe->bufs + ((ipipe->curbuf + i) & (PIPE_BUFFERS - 1)); + nbuf = (opipe->curbuf + opipe->nrbufs) & (PIPE_BUFFERS - 1); /* - * No input buffers, do the usual checks for available - * writers and blocking and wait if necessary + * Get a reference to this pipe buffer, + * so we can copy the contents over. */ - if (!ipipe->writers) - break; - if (!ipipe->waiting_writers) { - if (ret) - break; - } + ibuf->ops->get(ipipe, ibuf); + + obuf = opipe->bufs + nbuf; + *obuf = *ibuf; + /* - * pipe_wait() drops the ipipe mutex. To avoid deadlocks - * with another process, we can only safely do that if - * the ipipe lock is ordered last. + * Don't inherit the gift flag, we need to + * prevent multiple steals of this page. */ - if ((flags & SPLICE_F_NONBLOCK) || ipipe_first) { - if (!ret) - ret = -EAGAIN; - break; - } - if (signal_pending(current)) { - if (!ret) - ret = -ERESTARTSYS; - break; - } + obuf->flags &= ~PIPE_BUF_FLAG_GIFT; - if (waitqueue_active(&ipipe->wait)) - wake_up_interruptible_sync(&ipipe->wait); - kill_fasync(&ipipe->fasync_writers, SIGIO, POLL_OUT); + if (obuf->len > len) + obuf->len = len; - pipe_wait(ipipe); - } + opipe->nrbufs++; + ret += obuf->len; + len -= obuf->len; + i++; + } while (len); - mutex_unlock(&ipipe->inode->i_mutex); - mutex_unlock(&opipe->inode->i_mutex); + /* + * 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; - if (do_wakeup) { + inode_double_unlock(ipipe->inode, opipe->inode); + + /* + * If we put data in the output pipe, wakeup any potential readers. + */ + if (ret > 0) { smp_mb(); if (waitqueue_active(&opipe->wait)) wake_up_interruptible(&opipe->wait); @@ -1413,19 +1661,31 @@ static int link_pipe(struct pipe_inode_info *ipipe, static long do_tee(struct file *in, struct file *out, size_t len, unsigned int flags) { - struct pipe_inode_info *ipipe = in->f_dentry->d_inode->i_pipe; - struct pipe_inode_info *opipe = out->f_dentry->d_inode->i_pipe; + struct pipe_inode_info *ipipe = pipe_info(in->f_path.dentry->d_inode); + struct pipe_inode_info *opipe = pipe_info(out->f_path.dentry->d_inode); + int ret = -EINVAL; /* - * Link ipipe to the two output pipes, consuming as we go along. + * Duplicate the contents of ipipe to opipe without actually + * copying the data. */ - if (ipipe && opipe) - return link_pipe(ipipe, opipe, len, flags); + if (ipipe && opipe && ipipe != opipe) { + /* + * Keep going, unless we encounter an error. The ipipe/opipe + * ordering doesn't really matter. + */ + ret = link_ipipe_prep(ipipe, flags); + if (!ret) { + ret = link_opipe_prep(opipe, flags); + if (!ret) + ret = link_pipe(ipipe, opipe, len, flags); + } + } - return -EINVAL; + return ret; } -asmlinkage long sys_tee(int fdin, int fdout, size_t len, unsigned int flags) +SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags) { struct file *in; int error, fput_in;