* Jens to support splicing to files, network, direct splicing, etc and
* fixing lots of bugs.
*
- * Copyright (C) 2005-2006 Jens Axboe <axboe@suse.de>
+ * Copyright (C) 2005-2006 Jens Axboe <axboe@kernel.dk>
* Copyright (C) 2005-2006 Linus Torvalds <torvalds@osdl.org>
* Copyright (C) 2006 Ingo Molnar <mingo@elte.hu>
*
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 */
+ const struct pipe_buf_operations *ops;/* ops associated with output pipe */
};
/*
* 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);
- 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_LRU;
- return 0;
+ /*
+ * Raced with truncate or failed to remove page from current
+ * address space, unlock and return failure.
+ */
+ 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->flags &= ~PIPE_BUF_FLAG_LRU;
}
-static int page_cache_pipe_buf_pin(struct pipe_inode_info *info,
+static int page_cache_pipe_buf_pin(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
struct page *page = 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 = generic_pipe_buf_map,
.unmap = generic_pipe_buf_unmap,
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 = generic_pipe_buf_map,
.unmap = generic_pipe_buf_unmap,
break;
error = add_to_page_cache_lru(page, mapping, index,
- mapping_gfp_mask(mapping));
+ GFP_KERNEL);
if (unlikely(error)) {
page_cache_release(page);
+ if (error == -EEXIST)
+ continue;
break;
}
/*
* 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;
loff_t pos = sd->pos;
int ret, more;
- ret = buf->ops->pin(info, buf);
+ ret = buf->ops->pin(pipe, buf);
if (!ret) {
more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len;
* 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 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;
/*
* make sure the data in this buffer is uptodate
*/
- ret = buf->ops->pin(info, buf);
+ ret = buf->ops->pin(pipe, buf);
if (unlikely(ret))
return ret;
if (this_len + offset > PAGE_CACHE_SIZE)
this_len = PAGE_CACHE_SIZE - offset;
- /*
- * Reuse buf page, if SPLICE_F_MOVE is set and we are doing a full
- * page.
- */
- if ((sd->flags & SPLICE_F_MOVE) && this_len == PAGE_CACHE_SIZE) {
- /*
- * If steal succeeds, buf->page is now pruned from the
- * pagecache and we can reuse it. The page will also be
- * locked 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)) {
- unlock_page(page);
- goto find_page;
- }
-
- page_cache_get(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;
- }
+ page = find_lock_page(mapping, index);
+ if (!page) {
+ ret = -ENOMEM;
+ page = page_cache_alloc_cold(mapping);
+ if (unlikely(!page))
+ goto out_ret;
/*
- * 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.
+ * This will also lock the page
*/
- 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 = add_to_page_cache_lru(page, mapping, index,
+ GFP_KERNEL);
+ if (unlikely(ret))
+ goto out;
}
ret = mapping->a_ops->prepare_write(file, page, offset, offset+this_len);
if (sd->pos + this_len > isize)
vmtruncate(mapping->host, isize);
- goto out;
+ goto out_ret;
}
if (buf->page != page) {
/*
* Careful, ->map() uses KM_USER0!
*/
- char *src = buf->ops->map(info, buf, 1);
+ 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_USER1);
- buf->ops->unmap(info, buf, src);
+ buf->ops->unmap(pipe, buf, src);
}
ret = mapping->a_ops->commit_write(file, page, offset, offset+this_len);
- if (!ret) {
+ if (ret) {
+ if (ret == AOP_TRUNCATED_PAGE) {
+ page_cache_release(page);
+ goto find_page;
+ }
+ if (ret < 0)
+ goto out;
/*
- * Return the number of bytes written and mark page as
- * accessed, we are now done!
+ * Partial write has happened, so 'ret' already initialized by
+ * number of bytes written, Where is nothing we have to do here.
*/
+ } else
ret = this_len;
- mark_page_accessed(page);
- balance_dirty_pages_ratelimited(mapping);
- } else if (ret == AOP_TRUNCATED_PAGE) {
- page_cache_release(page);
- goto find_page;
- }
+ /*
+ * Return the number of bytes written and mark page as
+ * accessed, we are now done!
+ */
+ mark_page_accessed(page);
+ balance_dirty_pages_ratelimited(mapping);
out:
page_cache_release(page);
unlock_page(page);
-out_nomem:
+out_ret:
return ret;
}
* 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.
*/
-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 __splice_from_pipe(struct pipe_inode_info *pipe,
+ struct file *out, loff_t *ppos, size_t len,
+ unsigned int flags, splice_actor *actor)
{
int ret, do_wakeup, err;
struct splice_desc sd;
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)
pipe_wait(pipe);
}
- if (pipe->inode)
- mutex_unlock(&pipe->inode->i_mutex);
-
if (do_wakeup) {
smp_mb();
if (waitqueue_active(&pipe->wait))
return ret;
}
+EXPORT_SYMBOL(__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;
+
+ /*
+ * The actor worker might be calling ->prepare_write and
+ * ->commit_write. 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, out, ppos, len, flags, 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
+ * @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. The caller is responsible
+ * for acquiring i_mutex on both inodes.
+ *
+ */
+ssize_t
+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;
+ ssize_t ret;
+ int err;
+
+ err = remove_suid(out->f_path.dentry);
+ if (unlikely(err))
+ return err;
+
+ ret = __splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_file);
+ if (ret > 0) {
+ *ppos += ret;
+
+ /*
+ * If file or inode is SYNC and we actually wrote some data,
+ * sync it.
+ */
+ if (unlikely((out->f_flags & O_SYNC) || IS_SYNC(inode))) {
+ err = generic_osync_inode(inode, mapping,
+ OSYNC_METADATA|OSYNC_DATA);
+
+ if (err)
+ ret = err;
+ }
+ }
+
+ return ret;
+}
+
+EXPORT_SYMBOL(generic_file_splice_write_nolock);
/**
* generic_file_splice_write - splice data from a pipe to a file
loff_t *ppos, size_t len, unsigned int flags)
{
struct address_space *mapping = out->f_mapping;
+ struct inode *inode = mapping->host;
ssize_t ret;
+ int err;
+
+ err = should_remove_suid(out->f_path.dentry);
+ if (unlikely(err)) {
+ mutex_lock(&inode->i_mutex);
+ err = __remove_suid(out->f_path.dentry, err);
+ mutex_unlock(&inode->i_mutex);
+ if (err)
+ return err;
+ }
ret = splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_file);
if (ret > 0) {
- struct inode *inode = mapping->host;
-
*ppos += ret;
/*
* 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);
* 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;
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.
*/
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;
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;
static long do_vmsplice(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 = {
.ops = &user_page_pipe_buf_ops,
};
- if (unlikely(!pipe))
+ pipe = pipe_info(file->f_path.dentry->d_inode);
+ if (!pipe)
return -EBADF;
if (unlikely(nr_segs > UIO_MAXIOV))
return -EINVAL;
return error;
}
+/*
+ * 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.
*/
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;
- /*
- * Don't inherit the gift flag, we need to
- * prevent multiple steals of this page.
- */
- obuf->flags &= ~PIPE_BUF_FLAG_GIFT;
-
- 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);
+ inode_double_unlock(ipipe->inode, opipe->inode);
- if (do_wakeup) {
+ /*
+ * 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);
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);
+ if (!ret && (flags & SPLICE_F_NONBLOCK))
+ ret = -EAGAIN;
+ }
+ }
+ }
- return -EINVAL;
+ return ret;
}
asmlinkage long sys_tee(int fdin, int fdout, size_t len, unsigned int flags)