Commit aadd06e5 authored by Jens Axboe's avatar Jens Axboe

[PATCH] splice: fix problems with sys_tee()

Several issues noticed/fixed:

- We cannot reliably block in link_pipe() while holding both input and output
  mutexes. So do preparatory checks before locking down both mutexes and doing
  the link.

- The ipipe->nrbufs vs i check was bad, because we could have dropped the
  ipipe lock in-between. This causes us to potentially look at unknown
  buffers if we were racing with someone else reading this pipe.
Signed-off-by: default avatarJens Axboe <axboe@suse.de>
parent b3cf2576
...@@ -1306,6 +1306,85 @@ asmlinkage long sys_splice(int fd_in, loff_t __user *off_in, ...@@ -1306,6 +1306,85 @@ asmlinkage long sys_splice(int fd_in, loff_t __user *off_in,
return error; 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. * Link contents of ipipe to opipe.
*/ */
...@@ -1314,9 +1393,7 @@ static int link_pipe(struct pipe_inode_info *ipipe, ...@@ -1314,9 +1393,7 @@ static int link_pipe(struct pipe_inode_info *ipipe,
size_t len, unsigned int flags) size_t len, unsigned int flags)
{ {
struct pipe_buffer *ibuf, *obuf; struct pipe_buffer *ibuf, *obuf;
int ret, do_wakeup, i, ipipe_first; int ret = 0, i = 0, nbuf;
ret = do_wakeup = ipipe_first = 0;
/* /*
* Potential ABBA deadlock, work around it by ordering lock * Potential ABBA deadlock, work around it by ordering lock
...@@ -1324,29 +1401,30 @@ static int link_pipe(struct pipe_inode_info *ipipe, ...@@ -1324,29 +1401,30 @@ static int link_pipe(struct pipe_inode_info *ipipe,
* could deadlock (one doing tee from A -> B, the other from B -> A). * could deadlock (one doing tee from A -> B, the other from B -> A).
*/ */
if (ipipe->inode < opipe->inode) { if (ipipe->inode < opipe->inode) {
ipipe_first = 1; mutex_lock_nested(&ipipe->inode->i_mutex, I_MUTEX_PARENT);
mutex_lock(&ipipe->inode->i_mutex); mutex_lock_nested(&opipe->inode->i_mutex, I_MUTEX_CHILD);
mutex_lock(&opipe->inode->i_mutex);
} else { } else {
mutex_lock(&opipe->inode->i_mutex); mutex_lock_nested(&opipe->inode->i_mutex, I_MUTEX_PARENT);
mutex_lock(&ipipe->inode->i_mutex); mutex_lock_nested(&ipipe->inode->i_mutex, I_MUTEX_CHILD);
} }
for (i = 0;; i++) { do {
if (!opipe->readers) { if (!opipe->readers) {
send_sig(SIGPIPE, current, 0); send_sig(SIGPIPE, current, 0);
if (!ret) if (!ret)
ret = -EPIPE; ret = -EPIPE;
break; break;
} }
if (ipipe->nrbufs - i) {
ibuf = ipipe->bufs + ((ipipe->curbuf + i) & (PIPE_BUFFERS - 1));
/* /*
* If we have room, fill this buffer * If we have iterated all input buffers or ran out of
* output room, break.
*/ */
if (opipe->nrbufs < PIPE_BUFFERS) { if (i >= ipipe->nrbufs || opipe->nrbufs >= PIPE_BUFFERS)
int nbuf = (opipe->curbuf + opipe->nrbufs) & (PIPE_BUFFERS - 1); break;
ibuf = ipipe->bufs + ((ipipe->curbuf + i) & (PIPE_BUFFERS - 1));
nbuf = (opipe->curbuf + opipe->nrbufs) & (PIPE_BUFFERS - 1);
/* /*
* Get a reference to this pipe buffer, * Get a reference to this pipe buffer,
...@@ -1367,83 +1445,18 @@ static int link_pipe(struct pipe_inode_info *ipipe, ...@@ -1367,83 +1445,18 @@ static int link_pipe(struct pipe_inode_info *ipipe,
obuf->len = len; obuf->len = len;
opipe->nrbufs++; opipe->nrbufs++;
do_wakeup = 1;
ret += obuf->len; ret += obuf->len;
len -= obuf->len; len -= obuf->len;
i++;
if (!len) } while (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;
}
opipe->waiting_writers++;
pipe_wait(opipe);
opipe->waiting_writers--;
continue;
}
/*
* No input buffers, do the usual checks for available
* writers and blocking and wait if necessary
*/
if (!ipipe->writers)
break;
if (!ipipe->waiting_writers) {
if (ret)
break;
}
/*
* 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.
*/
if ((flags & SPLICE_F_NONBLOCK) || ipipe_first) {
if (!ret)
ret = -EAGAIN;
break;
}
if (signal_pending(current)) {
if (!ret)
ret = -ERESTARTSYS;
break;
}
if (waitqueue_active(&ipipe->wait))
wake_up_interruptible_sync(&ipipe->wait);
kill_fasync(&ipipe->fasync_writers, SIGIO, POLL_OUT);
pipe_wait(ipipe);
}
mutex_unlock(&ipipe->inode->i_mutex); mutex_unlock(&ipipe->inode->i_mutex);
mutex_unlock(&opipe->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(); smp_mb();
if (waitqueue_active(&opipe->wait)) if (waitqueue_active(&opipe->wait))
wake_up_interruptible(&opipe->wait); wake_up_interruptible(&opipe->wait);
...@@ -1464,14 +1477,29 @@ static long do_tee(struct file *in, struct file *out, size_t len, ...@@ -1464,14 +1477,29 @@ static long do_tee(struct file *in, struct file *out, size_t len,
{ {
struct pipe_inode_info *ipipe = in->f_dentry->d_inode->i_pipe; 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 *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 && ipipe != opipe) {
/*
* Keep going, unless we encounter an error. The ipipe/opipe
* ordering doesn't really matter.
*/ */
if (ipipe && opipe) ret = link_ipipe_prep(ipipe, flags);
return link_pipe(ipipe, opipe, len, 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) asmlinkage long sys_tee(int fdin, int fdout, size_t len, unsigned int flags)
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment