summaryrefslogtreecommitdiff
path: root/fs/pipe.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/pipe.c')
-rw-r--r--fs/pipe.c32
1 files changed, 25 insertions, 7 deletions
diff --git a/fs/pipe.c b/fs/pipe.c
index bfd946a9ad01..678dee2a8228 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -32,6 +32,21 @@
#include "internal.h"
/*
+ * New pipe buffers will be restricted to this size while the user is exceeding
+ * their pipe buffer quota. The general pipe use case needs at least two
+ * buffers: one for data yet to be read, and one for new data. If this is less
+ * than two, then a write to a non-empty pipe may block even if the pipe is not
+ * full. This can occur with GNU make jobserver or similar uses of pipes as
+ * semaphores: multiple processes may be waiting to write tokens back to the
+ * pipe before reading tokens: https://lore.kernel.org/lkml/1628086770.5rn8p04n6j.none@localhost/.
+ *
+ * Users can reduce their pipe buffers with F_SETPIPE_SZ below this at their
+ * own risk, namely: pipe writes to non-full pipes may block until the pipe is
+ * emptied.
+ */
+#define PIPE_MIN_DEF_BUFFERS 2
+
+/*
* The max size that a non-root user is allowed to grow the pipe. Can
* be set by root in /proc/sys/fs/pipe-max-size
*/
@@ -429,14 +444,11 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
#endif
/*
- * Only wake up if the pipe started out empty, since
- * otherwise there should be no readers waiting.
- *
* If it wasn't empty we try to merge new data into
* the last buffer.
*
* That naturally merges small writes, but it also
- * page-aligs the rest of the writes for large writes
+ * page-aligns the rest of the writes for large writes
* spanning multiple pages.
*/
head = pipe->head;
@@ -575,8 +587,11 @@ out:
* This is particularly important for small writes, because of
* how (for example) the GNU make jobserver uses small writes to
* wake up pending jobs
+ *
+ * Epoll nonsensically wants a wakeup whether the pipe
+ * was already empty or not.
*/
- if (was_empty) {
+ if (was_empty || pipe->poll_usage) {
wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM);
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
}
@@ -639,6 +654,9 @@ pipe_poll(struct file *filp, poll_table *wait)
struct pipe_inode_info *pipe = filp->private_data;
unsigned int head, tail;
+ /* Epoll has some historical nasty semantics, this enables them */
+ pipe->poll_usage = 1;
+
/*
* Reading pipe state only -- no need for acquiring the semaphore.
*
@@ -781,8 +799,8 @@ struct pipe_inode_info *alloc_pipe_info(void)
user_bufs = account_pipe_buffers(user, 0, pipe_bufs);
if (too_many_pipe_buffers_soft(user_bufs) && pipe_is_unprivileged_user()) {
- user_bufs = account_pipe_buffers(user, pipe_bufs, 1);
- pipe_bufs = 1;
+ user_bufs = account_pipe_buffers(user, pipe_bufs, PIPE_MIN_DEF_BUFFERS);
+ pipe_bufs = PIPE_MIN_DEF_BUFFERS;
}
if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user())