* 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>
*
* 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, mapping_gfp_mask(mapping));
- 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.
+ */
+ 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)
+static int page_cache_pipe_buf_pin(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
{
struct page *page = buf->page;
int err;
}
/*
- * 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 = {
.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,
+ .pin = page_cache_pipe_buf_pin,
.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 = {
.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,
+ .pin = generic_pipe_buf_pin,
.release = page_cache_pipe_buf_release,
.steal = user_page_pipe_buf_steal,
- .get = page_cache_pipe_buf_get,
+ .get = generic_pipe_buf_get,
};
/*
buf->offset = spd->partial[page_nr].offset;
buf->len = spd->partial[page_nr].len;
buf->ops = spd->ops;
+ if (spd->flags & SPLICE_F_GIFT)
+ buf->flags |= PIPE_BUF_FLAG_GIFT;
+
pipe->nrbufs++;
page_nr++;
ret += buf->len;
*/
page = find_get_page(mapping, index);
if (!page) {
+ /*
+ * Make sure the read-ahead engine is notified
+ * about this failure.
+ */
+ handle_ra_miss(mapping, &in->f_ra, index);
+
/*
* page didn't exist, allocate one.
*/
mapping_gfp_mask(mapping));
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;
- 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);
-
- more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len;
+ ret = buf->ops->pin(pipe, buf);
+ if (!ret) {
+ 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;
}
* 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;
unsigned int offset, this_len;
struct page *page;
pgoff_t index;
- char *src;
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->pin(pipe, buf);
+ if (unlikely(ret))
+ return ret;
index = sd->pos >> PAGE_CACHE_SHIFT;
offset = sd->pos & ~PAGE_CACHE_MASK;
this_len = PAGE_CACHE_SIZE - offset;
/*
- * Reuse buf page, if SPLICE_F_MOVE is set.
+ * Reuse buf page, if SPLICE_F_MOVE is set and we are doing a full
+ * page.
*/
- if (sd->flags & SPLICE_F_MOVE) {
+ if ((sd->flags & SPLICE_F_MOVE) && this_len == PAGE_CACHE_SIZE) {
/*
- * 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 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))
+ if (buf->ops->steal(pipe, buf))
goto find_page;
page = buf->page;
goto find_page;
}
+ page_cache_get(page);
+
if (!(buf->flags & PIPE_BUF_FLAG_LRU))
lru_cache_add(page);
} else {
}
ret = mapping->a_ops->prepare_write(file, page, offset, offset+this_len);
- if (ret == AOP_TRUNCATED_PAGE) {
+ if (unlikely(ret)) {
+ loff_t isize = i_size_read(mapping->host);
+
+ if (ret != AOP_TRUNCATED_PAGE)
+ unlock_page(page);
page_cache_release(page);
- goto find_page;
- } else if (ret)
+ if (ret == AOP_TRUNCATED_PAGE)
+ goto find_page;
+
+ /*
+ * prepare_write() may have instantiated a few blocks
+ * outside i_size. Trim these off again.
+ */
+ if (sd->pos + this_len > isize)
+ vmtruncate(mapping->host, isize);
+
goto out;
+ }
- if (!(buf->flags & PIPE_BUF_FLAG_STOLEN)) {
- char *dst = kmap_atomic(page, KM_USER0);
+ if (buf->page != page) {
+ /*
+ * Careful, ->map() uses 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) {
+ if (!ret) {
+ /*
+ * Return the number of bytes written and mark page as
+ * accessed, we are now done!
+ */
+ 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;
- } else if (ret)
- goto out;
-
- /*
- * Return the number of bytes written.
- */
- ret = this_len;
- mark_page_accessed(page);
- balance_dirty_pages_ratelimited(mapping);
+ }
out:
- if (!(buf->flags & PIPE_BUF_FLAG_STOLEN))
- page_cache_release(page);
-
+ page_cache_release(page);
unlock_page(page);
out_nomem:
- buf->ops->unmap(info, buf);
return ret;
}
*/
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;
* 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;
* 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;
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 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
* 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);
+ mutex_lock_nested(&ipipe->inode->i_mutex, I_MUTEX_PARENT);
+ mutex_lock_nested(&opipe->inode->i_mutex, I_MUTEX_CHILD);
} else {
- mutex_lock(&opipe->inode->i_mutex);
- mutex_lock(&ipipe->inode->i_mutex);
+ mutex_lock_nested(&opipe->inode->i_mutex, I_MUTEX_PARENT);
+ mutex_lock_nested(&ipipe->inode->i_mutex, I_MUTEX_CHILD);
}
- 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);
- 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);
{
struct pipe_inode_info *ipipe = in->f_dentry->d_inode->i_pipe;
struct pipe_inode_info *opipe = out->f_dentry->d_inode->i_pipe;
+ 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)