eventfd: provide a eventfd_signal_mask() helper

This is identical to eventfd_signal(), but it allows the caller to pass
in a mask to be used for the poll wakeup key. The use case is avoiding
repeated multishot triggers if we have a dependency between eventfd and
io_uring.

If we setup an eventfd context and register that as the io_uring eventfd,
and at the same time queue a multishot poll request for the eventfd
context, then any CQE posted will repeatedly trigger the multishot request
until it terminates when the CQ ring overflows.

In preparation for io_uring detecting this circular dependency, add the
mentioned helper so that io_uring can pass in EPOLL_URING as part of the
poll wakeup key.

Cc: stable@vger.kernel.org # 6.0
[axboe: fold in !CONFIG_EVENTFD fix from Zhang Qilong]
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/fs/eventfd.c b/fs/eventfd.c
index c0ffee9..249ca6c 100644 (file)
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -43,21 +43,7 @@ struct eventfd_ctx {
        int id;
 };
 
-/**
- * eventfd_signal - Adds @n to the eventfd counter.
- * @ctx: [in] Pointer to the eventfd context.
- * @n: [in] Value of the counter to be added to the eventfd internal counter.
- *          The value cannot be negative.
- *
- * This function is supposed to be called by the kernel in paths that do not
- * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX
- * value, and we signal this as overflow condition by returning a EPOLLERR
- * to poll(2).
- *
- * Returns the amount by which the counter was incremented.  This will be less
- * than @n if the counter has overflowed.
- */
-__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
+__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, unsigned mask)
 {
        unsigned long flags;
 
@@ -78,12 +64,31 @@ __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
                n = ULLONG_MAX - ctx->count;
        ctx->count += n;
        if (waitqueue_active(&ctx->wqh))
-               wake_up_locked_poll(&ctx->wqh, EPOLLIN);
+               wake_up_locked_poll(&ctx->wqh, EPOLLIN | mask);
        current->in_eventfd = 0;
        spin_unlock_irqrestore(&ctx->wqh.lock, flags);
 
        return n;
 }
+
+/**
+ * eventfd_signal - Adds @n to the eventfd counter.
+ * @ctx: [in] Pointer to the eventfd context.
+ * @n: [in] Value of the counter to be added to the eventfd internal counter.
+ *          The value cannot be negative.
+ *
+ * This function is supposed to be called by the kernel in paths that do not
+ * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX
+ * value, and we signal this as overflow condition by returning a EPOLLERR
+ * to poll(2).
+ *
+ * Returns the amount by which the counter was incremented.  This will be less
+ * than @n if the counter has overflowed.
+ */
+__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
+{
+       return eventfd_signal_mask(ctx, n, 0);
+}
 EXPORT_SYMBOL_GPL(eventfd_signal);
 
 static void eventfd_free_ctx(struct eventfd_ctx *ctx)

diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index 30eb30d..786824f 100644 (file)
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -40,6 +40,7 @@ struct file *eventfd_fget(int fd);
 struct eventfd_ctx *eventfd_ctx_fdget(int fd);
 struct eventfd_ctx *eventfd_ctx_fileget(struct file *file);
 __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n);
+__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, unsigned mask);
 int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
                                  __u64 *cnt);
 void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt);
@@ -66,6 +67,12 @@ static inline int eventfd_signal(struct eventfd_ctx *ctx, int n)
        return -ENOSYS;
 }
 
+static inline int eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n,
+                                     unsigned mask)
+{
+       return -ENOSYS;
+}
+
 static inline void eventfd_ctx_put(struct eventfd_ctx *ctx)
 {