#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>
*/
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;
/*
* If we succeeded in removing the mapping, set LRU flag
* Raced with truncate or failed to remove page from current
* address space, unlock and return failure.
*/
+out_unlock:
unlock_page(page);
return 1;
}
do_wakeup = 0;
page_nr = 0;
- if (pipe->inode)
- mutex_lock(&pipe->inode->i_mutex);
+ pipe_lock(pipe);
for (;;) {
if (!pipe->readers) {
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)
break;
error = add_to_page_cache_lru(page, mapping, index,
- GFP_KERNEL);
+ mapping_gfp_mask(mapping));
if (unlikely(error)) {
page_cache_release(page);
if (error == -EEXIST)
* for an in-flight io page
*/
if (flags & SPLICE_F_NONBLOCK) {
- if (TestSetPageLocked(page))
+ 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);
- 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
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
{
- ssize_t spliced;
- int ret;
loff_t isize, left;
+ int ret;
isize = i_size_read(in->f_mapping->host);
if (unlikely(*ppos >= isize))
if (unlikely(left < len))
len = left;
- ret = 0;
- spliced = 0;
- while (len && !spliced) {
- ret = __generic_file_splice_read(in, ppos, pipe, len, flags);
-
- if (ret < 0)
- break;
- else if (!ret) {
- if (spliced)
- break;
- if (flags & SPLICE_F_NONBLOCK) {
- ret = -EAGAIN;
- break;
- }
- }
-
+ 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;
}
* 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;
- ret = __splice_from_pipe(pipe, &sd, pipe_to_file);
- if (ret > 0) {
- unsigned long nr_pages;
+ pipe_lock(pipe);
- *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;
- }
- balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
- }
+ splice_from_pipe_begin(&sd);
+ do {
+ ret = splice_from_pipe_next(pipe, &sd);
+ if (ret <= 0)
+ break;
- return ret;
-}
+ mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
+ ret = file_remove_suid(out);
+ if (!ret)
+ ret = splice_from_pipe_feed(pipe, &sd, pipe_to_file);
+ mutex_unlock(&inode->i_mutex);
+ } while (ret > 0);
+ splice_from_pipe_end(pipe, &sd);
-EXPORT_SYMBOL(generic_file_splice_write_nolock);
+ pipe_unlock(pipe);
-/**
- * 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)
-{
- struct address_space *mapping = out->f_mapping;
- struct inode *inode = mapping->host;
- int killsuid, killpriv;
- ssize_t ret;
- int err = 0;
-
- killpriv = security_inode_need_killpriv(out->f_path.dentry);
- killsuid = should_remove_suid(out->f_path.dentry);
- if (unlikely(killsuid || killpriv)) {
- mutex_lock(&inode->i_mutex);
- if (killpriv)
- err = security_inode_killpriv(out->f_path.dentry);
- if (!err && killsuid)
- err = __remove_suid(out->f_path.dentry, killsuid);
- mutex_unlock(&inode->i_mutex);
- if (err)
- return err;
- }
+ if (sd.num_spliced)
+ ret = sd.num_spliced;
- ret = splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_file);
if (ret > 0) {
unsigned long nr_pages;
* 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);
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;
while (len) {
size_t read_len;
- loff_t pos = sd->pos;
+ loff_t pos = sd->pos, prev_pos = pos;
ret = do_splice_to(in, &pos, pipe, len, flags);
if (unlikely(ret <= 0))
* could get stuck data in the internal pipe:
*/
ret = actor(pipe, sd);
- if (unlikely(ret <= 0))
+ if (unlikely(ret <= 0)) {
+ sd->pos = prev_pos;
goto out_release;
+ }
bytes += ret;
len -= ret;
sd->pos = pos;
- if (ret < read_len)
+ if (ret < read_len) {
+ sd->pos = prev_pos + ret;
goto out_release;
+ }
}
done:
ret = splice_direct_to_actor(in, &sd, direct_splice_actor);
if (ret > 0)
- *ppos += ret;
+ *ppos = sd.pos;
return ret;
}
}
/*
- * 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.
{
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;
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;
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;
* 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;
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;
}
return 0;
ret = 0;
- mutex_lock(&pipe->inode->i_mutex);
+ pipe_lock(pipe);
while (pipe->nrbufs >= PIPE_BUFFERS) {
if (!pipe->readers) {
pipe->waiting_writers--;
}
- mutex_unlock(&pipe->inode->i_mutex);
+ pipe_unlock(pipe);
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 (!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.
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;