#include <linux/file.h>
#include <linux/pagemap.h>
#include <linux/splice.h>
+#include <linux/memcontrol.h>
#include <linux/mm_inline.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/syscalls.h>
#include <linux/uio.h>
#include <linux/security.h>
+#include <linux/gfp.h>
/*
* Attempt to steal a page from a pipe buffer. This should perhaps go into
*/
wait_on_page_writeback(page);
- if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL))
+ if (page_has_private(page) &&
+ !try_to_release_page(page, GFP_KERNEL))
goto out_unlock;
/*
do_wakeup = 0;
page_nr = 0;
- if (pipe->inode)
- mutex_lock(&pipe->inode->i_mutex);
+ pipe_lock(pipe);
for (;;) {
if (!pipe->readers) {
break;
}
- if (pipe->nrbufs < PIPE_BUFFERS) {
- int newbuf = (pipe->curbuf + pipe->nrbufs) & (PIPE_BUFFERS - 1);
+ if (pipe->nrbufs < pipe->buffers) {
+ int newbuf = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1);
struct pipe_buffer *buf = pipe->bufs + newbuf;
buf->page = spd->pages[page_nr];
if (!--spd->nr_pages)
break;
- if (pipe->nrbufs < PIPE_BUFFERS)
+ if (pipe->nrbufs < pipe->buffers)
continue;
break;
pipe->waiting_writers--;
}
- if (pipe->inode) {
- mutex_unlock(&pipe->inode->i_mutex);
+ pipe_unlock(pipe);
- 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_pages)
page_cache_release(spd->pages[i]);
}
+/*
+ * Check if we need to grow the arrays holding pages and partial page
+ * descriptions.
+ */
+int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd)
+{
+ if (pipe->buffers <= PIPE_DEF_BUFFERS)
+ return 0;
+
+ spd->pages = kmalloc(pipe->buffers * sizeof(struct page *), GFP_KERNEL);
+ spd->partial = kmalloc(pipe->buffers * 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 pipe_inode_info *pipe,
+ struct splice_pipe_desc *spd)
+{
+ if (pipe->buffers <= PIPE_DEF_BUFFERS)
+ return;
+
+ kfree(spd->pages);
+ kfree(spd->partial);
+}
+
static int
__generic_file_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
{
struct address_space *mapping = in->f_mapping;
unsigned int loff, nr_pages, req_pages;
- struct page *pages[PIPE_BUFFERS];
- struct partial_page partial[PIPE_BUFFERS];
+ struct page *pages[PIPE_DEF_BUFFERS];
+ struct partial_page partial[PIPE_DEF_BUFFERS];
struct page *page;
pgoff_t index, end_index;
loff_t isize;
.spd_release = spd_release_page,
};
+ if (splice_grow_spd(pipe, &spd))
+ return -ENOMEM;
+
index = *ppos >> PAGE_CACHE_SHIFT;
loff = *ppos & ~PAGE_CACHE_MASK;
req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- nr_pages = min(req_pages, (unsigned)PIPE_BUFFERS);
+ nr_pages = min(req_pages, pipe->buffers);
/*
* Lookup the (hopefully) full range of pages we need.
*/
- spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, pages);
+ spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, spd.pages);
index += spd.nr_pages;
/*
unlock_page(page);
}
- pages[spd.nr_pages++] = page;
+ spd.pages[spd.nr_pages++] = page;
index++;
}
* 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];
+ page = spd.pages[page_nr];
if (PageReadahead(page))
page_cache_async_readahead(mapping, &in->f_ra, in,
* for an in-flight io page
*/
if (flags & SPLICE_F_NONBLOCK) {
- if (TestSetPageLocked(page)) {
+ if (!trylock_page(page)) {
error = -EAGAIN;
break;
}
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);
- break;
+ page = find_or_create_page(mapping, index,
+ mapping_gfp_mask(mapping));
+
+ if (!page) {
+ error = -ENOMEM;
+ break;
+ }
+ page_cache_release(spd.pages[page_nr]);
+ spd.pages[page_nr] = page;
}
/*
* page was already under io and is now done, great
len = this_len;
}
- partial[page_nr].offset = loff;
- partial[page_nr].len = this_len;
+ spd.partial[page_nr].offset = loff;
+ spd.partial[page_nr].len = this_len;
len -= this_len;
loff = 0;
spd.nr_pages++;
* we got, 'nr_pages' is how many pages are in the map.
*/
while (page_nr < nr_pages)
- page_cache_release(pages[page_nr++]);
+ page_cache_release(spd.pages[page_nr++]);
in->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;
if (spd.nr_pages)
- return splice_to_pipe(pipe, &spd);
+ error = splice_to_pipe(pipe, &spd);
+ splice_shrink_spd(pipe, &spd);
return error;
}
len = left;
ret = __generic_file_splice_read(in, ppos, pipe, len, flags);
- if (ret > 0)
+ if (ret > 0) {
*ppos += ret;
+ file_accessed(in);
+ }
return ret;
}
-
EXPORT_SYMBOL(generic_file_splice_read);
+static const struct pipe_buf_operations default_pipe_buf_ops = {
+ .can_merge = 0,
+ .map = generic_pipe_buf_map,
+ .unmap = generic_pipe_buf_unmap,
+ .confirm = generic_pipe_buf_confirm,
+ .release = generic_pipe_buf_release,
+ .steal = generic_pipe_buf_steal,
+ .get = generic_pipe_buf_get,
+};
+
+static ssize_t kernel_readv(struct file *file, const struct iovec *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(get_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);
+ set_fs(old_fs);
+
+ return res;
+}
+
+static ssize_t kernel_write(struct file *file, const char *buf, size_t count,
+ loff_t pos)
+{
+ mm_segment_t old_fs;
+ ssize_t res;
+
+ old_fs = get_fs();
+ set_fs(get_ds());
+ /* The cast to a user pointer is valid due to the set_fs() */
+ res = vfs_write(file, (const char __user *)buf, count, &pos);
+ set_fs(old_fs);
+
+ return res;
+}
+
+ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags)
+{
+ unsigned int nr_pages;
+ unsigned int nr_freed;
+ size_t offset;
+ struct page *pages[PIPE_DEF_BUFFERS];
+ struct partial_page partial[PIPE_DEF_BUFFERS];
+ struct iovec *vec, __vec[PIPE_DEF_BUFFERS];
+ pgoff_t index;
+ ssize_t res;
+ size_t this_len;
+ int error;
+ int i;
+ struct splice_pipe_desc spd = {
+ .pages = pages,
+ .partial = partial,
+ .flags = flags,
+ .ops = &default_pipe_buf_ops,
+ .spd_release = spd_release_page,
+ };
+
+ if (splice_grow_spd(pipe, &spd))
+ return -ENOMEM;
+
+ res = -ENOMEM;
+ vec = __vec;
+ if (pipe->buffers > PIPE_DEF_BUFFERS) {
+ vec = kmalloc(pipe->buffers * sizeof(struct iovec), GFP_KERNEL);
+ if (!vec)
+ goto shrink_ret;
+ }
+
+ index = *ppos >> PAGE_CACHE_SHIFT;
+ offset = *ppos & ~PAGE_CACHE_MASK;
+ nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+
+ for (i = 0; i < nr_pages && i < pipe->buffers && len; i++) {
+ struct page *page;
+
+ page = alloc_page(GFP_USER);
+ error = -ENOMEM;
+ if (!page)
+ goto err;
+
+ this_len = min_t(size_t, len, PAGE_CACHE_SIZE - offset);
+ vec[i].iov_base = (void __user *) page_address(page);
+ vec[i].iov_len = this_len;
+ spd.pages[i] = page;
+ spd.nr_pages++;
+ len -= this_len;
+ offset = 0;
+ }
+
+ res = kernel_readv(in, vec, spd.nr_pages, *ppos);
+ if (res < 0) {
+ error = res;
+ goto err;
+ }
+
+ error = 0;
+ if (!res)
+ goto err;
+
+ nr_freed = 0;
+ for (i = 0; i < spd.nr_pages; i++) {
+ this_len = min_t(size_t, vec[i].iov_len, res);
+ spd.partial[i].offset = 0;
+ spd.partial[i].len = this_len;
+ if (!this_len) {
+ __free_page(spd.pages[i]);
+ spd.pages[i] = NULL;
+ nr_freed++;
+ }
+ res -= this_len;
+ }
+ spd.nr_pages -= nr_freed;
+
+ res = splice_to_pipe(pipe, &spd);
+ if (res > 0)
+ *ppos += res;
+
+shrink_ret:
+ if (vec != __vec)
+ kfree(vec);
+ splice_shrink_spd(pipe, &spd);
+ return res;
+
+err:
+ for (i = 0; i < spd.nr_pages; i++)
+ __free_page(spd.pages[i]);
+
+ res = error;
+ goto shrink_ret;
+}
+EXPORT_SYMBOL(default_file_splice_read);
+
/*
* Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'
* using sendpage(). Return the number of bytes sent.
ret = buf->ops->confirm(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);
+ if (file->f_op && file->f_op->sendpage)
+ ret = file->f_op->sendpage(file, buf->page, buf->offset,
+ sd->len, &pos, more);
+ else
+ ret = -EINVAL;
}
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 *pipe, struct pipe_buffer *buf,
- struct splice_desc *sd)
+int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
+ struct splice_desc *sd)
{
struct file *file = sd->u.file;
struct address_space *mapping = file->f_mapping;
out:
return ret;
}
+EXPORT_SYMBOL(pipe_to_file);
+
+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 - splice data from a pipe to given actor
+ * 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 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.
+ * 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.
*/
-ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd,
- splice_actor *actor)
+int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_desc *sd,
+ splice_actor *actor)
{
- int ret, do_wakeup, err;
-
- ret = 0;
- do_wakeup = 0;
-
- for (;;) {
- if (pipe->nrbufs) {
- struct pipe_buffer *buf = pipe->bufs + pipe->curbuf;
- const struct pipe_buf_operations *ops = buf->ops;
+ int ret;
- sd->len = buf->len;
- if (sd->len > sd->total_len)
- sd->len = sd->total_len;
+ while (pipe->nrbufs) {
+ struct pipe_buffer *buf = pipe->bufs + pipe->curbuf;
+ const struct pipe_buf_operations *ops = buf->ops;
- err = actor(pipe, buf, sd);
- if (err <= 0) {
- if (!ret && err != -ENODATA)
- ret = err;
+ sd->len = buf->len;
+ if (sd->len > sd->total_len)
+ sd->len = sd->total_len;
- break;
- }
+ ret = actor(pipe, buf, sd);
+ if (ret <= 0) {
+ if (ret == -ENODATA)
+ ret = 0;
+ return ret;
+ }
+ buf->offset += ret;
+ buf->len -= ret;
- ret += err;
- buf->offset += err;
- buf->len -= err;
+ sd->num_spliced += ret;
+ sd->len -= ret;
+ sd->pos += ret;
+ sd->total_len -= ret;
- sd->len -= err;
- sd->pos += err;
- sd->total_len -= err;
- if (sd->len)
- continue;
+ if (!buf->len) {
+ buf->ops = NULL;
+ ops->release(pipe, buf);
+ pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1);
+ pipe->nrbufs--;
+ if (pipe->inode)
+ sd->need_wakeup = true;
+ }
- if (!buf->len) {
- buf->ops = NULL;
- ops->release(pipe, buf);
- pipe->curbuf = (pipe->curbuf + 1) & (PIPE_BUFFERS - 1);
- pipe->nrbufs--;
- if (pipe->inode)
- do_wakeup = 1;
- }
+ if (!sd->total_len)
+ return 0;
+ }
- if (!sd->total_len)
- break;
- }
+ return 1;
+}
+EXPORT_SYMBOL(splice_from_pipe_feed);
- if (pipe->nrbufs)
- continue;
+/**
+ * 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.
+ */
+int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_desc *sd)
+{
+ while (!pipe->nrbufs) {
if (!pipe->writers)
- break;
- if (!pipe->waiting_writers) {
- if (ret)
- break;
- }
+ return 0;
- if (sd->flags & SPLICE_F_NONBLOCK) {
- if (!ret)
- ret = -EAGAIN;
- break;
- }
+ if (!pipe->waiting_writers && sd->num_spliced)
+ return 0;
- if (signal_pending(current)) {
- if (!ret)
- ret = -ERESTARTSYS;
- break;
- }
+ if (sd->flags & SPLICE_F_NONBLOCK)
+ return -EAGAIN;
- if (do_wakeup) {
- smp_mb();
- if (waitqueue_active(&pipe->wait))
- wake_up_interruptible_sync(&pipe->wait);
- kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
- do_wakeup = 0;
+ if (signal_pending(current))
+ return -ERESTARTSYS;
+
+ if (sd->need_wakeup) {
+ wakeup_pipe_writers(pipe);
+ sd->need_wakeup = false;
}
pipe_wait(pipe);
}
- if (do_wakeup) {
- smp_mb();
- if (waitqueue_active(&pipe->wait))
- wake_up_interruptible(&pipe->wait);
- kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
- }
+ return 1;
+}
+EXPORT_SYMBOL(splice_from_pipe_next);
- return ret;
+/**
+ * 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.
+ */
+void splice_from_pipe_begin(struct splice_desc *sd)
+{
+ sd->num_spliced = 0;
+ sd->need_wakeup = false;
+}
+EXPORT_SYMBOL(splice_from_pipe_begin);
+
+/**
+ * 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().
+ */
+void splice_from_pipe_end(struct pipe_inode_info *pipe, struct splice_desc *sd)
+{
+ if (sd->need_wakeup)
+ wakeup_pipe_writers(pipe);
+}
+EXPORT_SYMBOL(splice_from_pipe_end);
+
+/**
+ * __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 {
+ 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);
* @actor: handler that splices the data
*
* Description:
- * See __splice_from_pipe. This function locks the input and output inodes,
+ * See __splice_from_pipe. This function locks the pipe inode,
* otherwise it's identical to __splice_from_pipe().
*
*/
splice_actor *actor)
{
ssize_t ret;
- struct inode *inode = out->f_mapping->host;
struct splice_desc sd = {
.total_len = len,
.flags = flags,
.u.file = out,
};
- /*
- * 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);
+ pipe_lock(pipe);
ret = __splice_from_pipe(pipe, &sd, actor);
- inode_double_unlock(inode, pipe->inode);
+ pipe_unlock(pipe);
return ret;
}
/**
- * generic_file_splice_write_nolock - generic_file_splice_write without mutexes
+ * generic_file_splice_write - splice data from a pipe to a file
* @pipe: pipe info
* @out: file to write to
* @ppos: position in @out
*
* 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.
+ * the given pipe inode to the given file.
*
*/
ssize_t
-generic_file_splice_write_nolock(struct pipe_inode_info *pipe, struct file *out,
- loff_t *ppos, size_t len, unsigned int flags)
+generic_file_splice_write(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;
.u.file = out,
};
ssize_t ret;
- int err;
- err = remove_suid(out->f_path.dentry);
- if (unlikely(err))
- return err;
+ pipe_lock(pipe);
+
+ splice_from_pipe_begin(&sd);
+ do {
+ ret = splice_from_pipe_next(pipe, &sd);
+ if (ret <= 0)
+ break;
+
+ mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
+ ret = file_remove_suid(out);
+ if (!ret) {
+ file_update_time(out);
+ ret = splice_from_pipe_feed(pipe, &sd, pipe_to_file);
+ }
+ mutex_unlock(&inode->i_mutex);
+ } while (ret > 0);
+ splice_from_pipe_end(pipe, &sd);
+
+ pipe_unlock(pipe);
+
+ if (sd.num_spliced)
+ ret = sd.num_spliced;
- ret = __splice_from_pipe(pipe, &sd, pipe_to_file);
if (ret > 0) {
unsigned long nr_pages;
+ int err;
- *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))) {
- err = generic_osync_inode(inode, mapping,
- OSYNC_METADATA|OSYNC_DATA);
-
- if (err)
- ret = err;
- }
+ err = generic_write_sync(out, *ppos, ret);
+ if (err)
+ ret = err;
+ else
+ *ppos += ret;
balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
}
return ret;
}
-EXPORT_SYMBOL(generic_file_splice_write_nolock);
+EXPORT_SYMBOL(generic_file_splice_write);
-/**
- * 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
- *
- * Description:
- * Will either move or copy pages (determined by @flags options) from
- * the given pipe inode to the given file.
- *
- */
-ssize_t
-generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
- loff_t *ppos, size_t len, unsigned int flags)
+static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
+ struct splice_desc *sd)
{
- 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 ret;
+ void *data;
- inode_double_lock(inode, pipe->inode);
- ret = remove_suid(out->f_path.dentry);
- 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;
+ ret = buf->ops->confirm(pipe, buf);
+ if (ret)
+ return ret;
- *ppos += ret;
- nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ data = buf->ops->map(pipe, buf, 0);
+ ret = kernel_write(sd->u.file, data + buf->offset, sd->len, sd->pos);
+ buf->ops->unmap(pipe, buf, data);
- /*
- * 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;
+ return ret;
+}
- mutex_lock(&inode->i_mutex);
- err = generic_osync_inode(inode, mapping,
- OSYNC_METADATA|OSYNC_DATA);
- mutex_unlock(&inode->i_mutex);
+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;
- if (err)
- ret = err;
- }
- balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
- }
+ ret = splice_from_pipe(pipe, out, ppos, len, flags, write_pipe_buf);
+ if (ret > 0)
+ *ppos += ret;
return ret;
}
-EXPORT_SYMBOL(generic_file_splice_write);
-
/**
* generic_splice_sendpage - splice data from a pipe to a socket
* @pipe: pipe to splice from
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);
int ret;
- if (unlikely(!out->f_op || !out->f_op->splice_write))
- return -EINVAL;
-
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;
- return out->f_op->splice_write(pipe, out, ppos, len, flags);
+ if (out->f_op && 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);
}
/*
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_op || !in->f_op->splice_read))
- return -EINVAL;
-
if (unlikely(!(in->f_mode & FMODE_READ)))
return -EBADF;
if (unlikely(ret < 0))
return ret;
- return in->f_op->splice_read(in, ppos, pipe, len, flags);
+ if (in->f_op && 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);
}
/**
* If we did an incomplete transfer we must release
* the pipe buffers in question:
*/
- for (i = 0; i < PIPE_BUFFERS; i++) {
+ for (i = 0; i < pipe->buffers; i++) {
struct pipe_buffer *buf = pipe->bufs + i;
if (buf->ops) {
return ret;
}
+static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
+ struct pipe_inode_info *opipe,
+ size_t len, unsigned int flags);
/*
* 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
struct file *out, loff_t __user *off_out,
size_t len, unsigned int flags)
{
- struct pipe_inode_info *pipe;
+ struct pipe_inode_info *ipipe;
+ struct pipe_inode_info *opipe;
loff_t offset, *off;
long ret;
- pipe = pipe_info(in->f_path.dentry->d_inode);
- if (pipe) {
+ ipipe = pipe_info(in->f_path.dentry->d_inode);
+ opipe = pipe_info(out->f_path.dentry->d_inode);
+
+ 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;
+
+ return splice_pipe_to_pipe(ipipe, opipe, len, flags);
+ }
+
+ if (ipipe) {
if (off_in)
return -ESPIPE;
if (off_out) {
- if (out->f_op->llseek == no_llseek)
+ if (!out->f_op || !out->f_op->llseek ||
+ out->f_op->llseek == no_llseek)
return -EINVAL;
if (copy_from_user(&offset, off_out, sizeof(loff_t)))
return -EFAULT;
} else
off = &out->f_pos;
- ret = do_splice_from(pipe, out, off, len, flags);
+ ret = do_splice_from(ipipe, out, off, len, flags);
if (off_out && copy_to_user(off_out, off, sizeof(loff_t)))
ret = -EFAULT;
return ret;
}
- pipe = pipe_info(out->f_path.dentry->d_inode);
- if (pipe) {
+ if (opipe) {
if (off_out)
return -ESPIPE;
if (off_in) {
- if (in->f_op->llseek == no_llseek)
+ if (!in->f_op || !in->f_op->llseek ||
+ in->f_op->llseek == no_llseek)
return -EINVAL;
if (copy_from_user(&offset, off_in, sizeof(loff_t)))
return -EFAULT;
} else
off = &in->f_pos;
- ret = do_splice_to(in, off, pipe, len, flags);
+ ret = do_splice_to(in, off, opipe, len, flags);
if (off_in && copy_to_user(off_in, off, sizeof(loff_t)))
ret = -EFAULT;
}
/*
- * Do a copy-from-user while holding the mmap_semaphore for reading, in a
- * manner safe from deadlocking with simultaneous mmap() (grabbing mmap_sem
- * for writing) and page faulting on the user memory pointed to by src.
- * This assumes that we will very rarely hit the partial != 0 path, or this
- * will not be a win.
- */
-static int copy_from_user_mmap_sem(void *dst, const void __user *src, size_t n)
-{
- int partial;
-
- if (!access_ok(VERIFY_READ, src, n))
- return -EFAULT;
-
- pagefault_disable();
- partial = __copy_from_user_inatomic(dst, src, n);
- pagefault_enable();
-
- /*
- * Didn't copy everything, drop the mmap_sem and do a faulting copy
- */
- if (unlikely(partial)) {
- up_read(¤t->mm->mmap_sem);
- partial = copy_from_user(dst, src, n);
- down_read(¤t->mm->mmap_sem);
- }
-
- return partial;
-}
-
-/*
* Map an iov into an array of pages and offset/length tupples. With the
* partial_page structure, we can map several non-contiguous ranges into
* our ones pages[] map instead of splitting that operation into pieces.
*/
static int get_iovec_page_array(const struct iovec __user *iov,
unsigned int nr_vecs, struct page **pages,
- struct partial_page *partial, int aligned)
+ struct partial_page *partial, int aligned,
+ unsigned int pipe_buffers)
{
int buffers = 0, error = 0;
- down_read(¤t->mm->mmap_sem);
-
while (nr_vecs) {
unsigned long off, npages;
struct iovec entry;
int i;
error = -EFAULT;
- if (copy_from_user_mmap_sem(&entry, iov, sizeof(entry)))
+ if (copy_from_user(&entry, iov, sizeof(entry)))
break;
base = entry.iov_base;
break;
npages = (off + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
- if (npages > PIPE_BUFFERS - buffers)
- npages = PIPE_BUFFERS - buffers;
+ 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;
* or if we mapped the max number of pages that we have
* room for.
*/
- if (error < npages || buffers == PIPE_BUFFERS)
+ if (error < npages || buffers == pipe_buffers)
break;
nr_vecs--;
iov++;
}
- up_read(¤t->mm->mmap_sem);
-
if (buffers)
return buffers;
if (!pipe)
return -EBADF;
- if (pipe->inode)
- mutex_lock(&pipe->inode->i_mutex);
+ pipe_lock(pipe);
error = ret = 0;
while (nr_segs) {
iov++;
}
- if (pipe->inode)
- mutex_unlock(&pipe->inode->i_mutex);
+ pipe_unlock(pipe);
if (!ret)
ret = error;
unsigned long nr_segs, unsigned int flags)
{
struct pipe_inode_info *pipe;
- struct page *pages[PIPE_BUFFERS];
- struct partial_page partial[PIPE_BUFFERS];
+ struct page *pages[PIPE_DEF_BUFFERS];
+ struct partial_page partial[PIPE_DEF_BUFFERS];
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
.ops = &user_page_pipe_buf_ops,
.spd_release = spd_release_page,
};
+ long ret;
pipe = pipe_info(file->f_path.dentry->d_inode);
if (!pipe)
return -EBADF;
- spd.nr_pages = get_iovec_page_array(iov, nr_segs, pages, partial,
- flags & SPLICE_F_GIFT);
+ if (splice_grow_spd(pipe, &spd))
+ return -ENOMEM;
+
+ spd.nr_pages = get_iovec_page_array(iov, nr_segs, spd.pages,
+ spd.partial, flags & SPLICE_F_GIFT,
+ pipe->buffers);
if (spd.nr_pages <= 0)
- return spd.nr_pages;
+ ret = spd.nr_pages;
+ else
+ ret = splice_to_pipe(pipe, &spd);
- return splice_to_pipe(pipe, &spd);
+ splice_shrink_spd(pipe, &spd);
+ return ret;
}
/*
* Currently we punt and implement it as a normal copy, see pipe_to_user().
*
*/
-asmlinkage long sys_vmsplice(int fd, const struct iovec __user *iov,
- unsigned long nr_segs, unsigned int flags)
+SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, iov,
+ unsigned long, nr_segs, unsigned int, flags)
{
struct file *file;
long error;
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;
* 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)
+static int ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
{
int ret;
return 0;
ret = 0;
- mutex_lock(&pipe->inode->i_mutex);
+ pipe_lock(pipe);
while (!pipe->nrbufs) {
if (signal_pending(current)) {
pipe_wait(pipe);
}
- mutex_unlock(&pipe->inode->i_mutex);
+ pipe_unlock(pipe);
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)
+static int 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)
+ if (pipe->nrbufs < pipe->buffers)
return 0;
ret = 0;
- mutex_lock(&pipe->inode->i_mutex);
+ pipe_lock(pipe);
- while (pipe->nrbufs >= PIPE_BUFFERS) {
+ while (pipe->nrbufs >= pipe->buffers) {
if (!pipe->readers) {
send_sig(SIGPIPE, current, 0);
ret = -EPIPE;
pipe->waiting_writers--;
}
- mutex_unlock(&pipe->inode->i_mutex);
+ 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;
+ int ret = 0, nbuf;
+ 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);
+
+ do {
+ if (!opipe->readers) {
+ send_sig(SIGPIPE, current, 0);
+ if (!ret)
+ ret = -EPIPE;
+ break;
+ }
+
+ if (!ipipe->nrbufs && !ipipe->writers)
+ break;
+
+ /*
+ * Cannot make any progress, because either the input
+ * pipe is empty or the output pipe is full.
+ */
+ if (!ipipe->nrbufs || opipe->nrbufs >= opipe->buffers) {
+ /* 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 + ipipe->curbuf;
+ nbuf = (opipe->curbuf + opipe->nrbufs) & (opipe->buffers - 1);
+ obuf = opipe->bufs + nbuf;
+
+ if (len >= ibuf->len) {
+ /*
+ * Simply move the whole buffer from ipipe to opipe
+ */
+ *obuf = *ibuf;
+ ibuf->ops = NULL;
+ opipe->nrbufs++;
+ ipipe->curbuf = (ipipe->curbuf + 1) & (ipipe->buffers - 1);
+ ipipe->nrbufs--;
+ input_wakeup = true;
+ } else {
+ /*
+ * Get a reference to this pipe buffer,
+ * so we can copy the contents over.
+ */
+ ibuf->ops->get(ipipe, ibuf);
+ *obuf = *ibuf;
+
+ /*
+ * Don't inherit the gift flag, we need to
+ * prevent multiple steals of this page.
+ */
+ obuf->flags &= ~PIPE_BUF_FLAG_GIFT;
+
+ obuf->len = len;
+ opipe->nrbufs++;
+ ibuf->offset += obuf->len;
+ ibuf->len -= obuf->len;
+ }
+ ret += obuf->len;
+ len -= obuf->len;
+ } while (len);
+
+ pipe_unlock(ipipe);
+ pipe_unlock(opipe);
+
+ /*
+ * 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);
+ kill_fasync(&opipe->fasync_readers, SIGIO, POLL_IN);
+ }
+ if (input_wakeup)
+ wakeup_pipe_writers(ipipe);
+
return ret;
}
/*
* Potential ABBA deadlock, work around it by ordering lock
- * grabbing by inode address. Otherwise two different processes
+ * grabbing by pipe info address. Otherwise two different processes
* could deadlock (one doing tee from A -> B, the other from B -> A).
*/
- inode_double_lock(ipipe->inode, opipe->inode);
+ pipe_double_lock(ipipe, opipe);
do {
if (!opipe->readers) {
* If we have iterated all input buffers or ran out of
* output room, break.
*/
- if (i >= ipipe->nrbufs || opipe->nrbufs >= PIPE_BUFFERS)
+ if (i >= ipipe->nrbufs || opipe->nrbufs >= opipe->buffers)
break;
- ibuf = ipipe->bufs + ((ipipe->curbuf + i) & (PIPE_BUFFERS - 1));
- nbuf = (opipe->curbuf + opipe->nrbufs) & (PIPE_BUFFERS - 1);
+ ibuf = ipipe->bufs + ((ipipe->curbuf + i) & (ipipe->buffers-1));
+ nbuf = (opipe->curbuf + opipe->nrbufs) & (opipe->buffers - 1);
/*
* Get a reference to this pipe buffer,
if (!ret && ipipe->waiting_writers && (flags & SPLICE_F_NONBLOCK))
ret = -EAGAIN;
- inode_double_unlock(ipipe->inode, opipe->inode);
+ pipe_unlock(ipipe);
+ pipe_unlock(opipe);
/*
* If we put data in the output pipe, wakeup any potential readers.
* Keep going, unless we encounter an error. The ipipe/opipe
* ordering doesn't really matter.
*/
- ret = link_ipipe_prep(ipipe, flags);
+ ret = ipipe_prep(ipipe, flags);
if (!ret) {
- ret = link_opipe_prep(opipe, flags);
+ ret = opipe_prep(opipe, flags);
if (!ret)
ret = link_pipe(ipipe, opipe, len, flags);
}
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;