Merge tag 'pipe-nonblock-2023-05-06' of git://git.kernel.dk/linux

Pull nonblocking pipe io_uring support from Jens Axboe:
 "Here's the revised edition of the FMODE_NOWAIT support for pipes, in
  which we just flag it as such supporting FMODE_NOWAIT unconditionally,
  but clear it if we ever end up using splice/vmsplice on the pipe.

  The pipe read/write side is perfectly fine for nonblocking IO, however
  splice and vmsplice can potentially wait for IO with the pipe lock
  held"

* tag 'pipe-nonblock-2023-05-06' of git://git.kernel.dk/linux:
  pipe: set FMODE_NOWAIT on pipes
  splice: clear FMODE_NOWAIT on file if splice/vmsplice is used

2 files changed, 33 insertions, 4 deletions

diff --git a/fs/pipe.c b/fs/pipe.c
index 42c7ff41c2dba2..ceb17d2dfa195a 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -976,6 +976,9 @@ static int __do_pipe_flags(int *fd, struct file **files, int flags)
 	audit_fd_pair(fdr, fdw);
 	fd[0] = fdr;
 	fd[1] = fdw;
+	/* pipe groks IOCB_NOWAIT */
+	files[0]->f_mode |= FMODE_NOWAIT;
+	files[1]->f_mode |= FMODE_NOWAIT;
 	return 0;
 
  err_fdr:
diff --git a/fs/splice.c b/fs/splice.c
index 0af8d150394f6a..3e06611d19ae55 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -39,6 +39,22 @@
 #include "internal.h"
 
 /*
+ * Splice doesn't support FMODE_NOWAIT. Since pipes may set this flag to
+ * indicate they support non-blocking reads or writes, we must clear it
+ * here if set to avoid blocking other users of this pipe if splice is
+ * being done on it.
+ */
+static noinline void noinline pipe_clear_nowait(struct file *file)
+{
+	fmode_t fmode = READ_ONCE(file->f_mode);
+
+	do {
+		if (!(fmode & FMODE_NOWAIT))
+			break;
+	} while (!try_cmpxchg(&file->f_mode, &fmode, fmode & ~FMODE_NOWAIT));
+}
+
+/*
  * Attempt to steal a page from a pipe buffer. This should perhaps go into
  * a vm helper function, it's already simplified quite a bit by the
  * addition of remove_mapping(). If success is returned, the caller may
@@ -1219,10 +1235,16 @@ static long __do_splice(struct file *in, loff_t __user *off_in,
 	ipipe = get_pipe_info(in, true);
 	opipe = get_pipe_info(out, true);
 
-	if (ipipe && off_in)
-		return -ESPIPE;
-	if (opipe && off_out)
-		return -ESPIPE;
+	if (ipipe) {
+		if (off_in)
+			return -ESPIPE;
+		pipe_clear_nowait(in);
+	}
+	if (opipe) {
+		if (off_out)
+			return -ESPIPE;
+		pipe_clear_nowait(out);
+	}
 
 	if (off_out) {
 		if (copy_from_user(&offset, off_out, sizeof(loff_t)))
@@ -1319,6 +1341,8 @@ static long vmsplice_to_user(struct file *file, struct iov_iter *iter,
 	if (!pipe)
 		return -EBADF;
 
+	pipe_clear_nowait(file);
+
 	if (sd.total_len) {
 		pipe_lock(pipe);
 		ret = __splice_from_pipe(pipe, &sd, pipe_to_user);
@@ -1347,6 +1371,8 @@ static long vmsplice_to_pipe(struct file *file, struct iov_iter *iter,
 	if (!pipe)
 		return -EBADF;
 
+	pipe_clear_nowait(file);
+
 	pipe_lock(pipe);
 	ret = wait_for_space(pipe, flags);
 	if (!ret)