io_uring: add absolute mode wait timeouts

In addition to current relative timeouts for the waiting loop, where the
timespec argument specifies the maximum time it can wait for, add
support for the absolute mode, with the value carrying a CLOCK_MONOTONIC
absolute time until which we should return control back to the user.

Suggested-by: Lewis Baker <[email protected]>
Signed-off-by: Pavel Begunkov <[email protected]>
Link: https://lore.kernel.org/r/4d5b74d67ada882590b2e42aa3aa7117bbf6b55f.1723039801.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <[email protected]>

Author: isilence

include/uapi/linux/io_uring.h

@@ -507,6 +507,7 @@ struct io_cqring_offsets {
 #define IORING_ENTER_SQ_WAIT		(1U << 2)
 #define IORING_ENTER_EXT_ARG		(1U << 3)
 #define IORING_ENTER_REGISTERED_RING	(1U << 4)
+#define IORING_ENTER_ABS_TIMER		(1U << 5)
 
 /*
  * Passed in for io_uring_setup(2). Copied back with updated info on success

io_uring/io_uring.c

@@ -2387,7 +2387,7 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
  * Wait until events become available, if we don't already have some. The
  * application must reap them itself, as they reside on the shared cq ring.
  */
-static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
+static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags,
 			  const sigset_t __user *sig, size_t sigsz,
 			  struct __kernel_timespec __user *uts)
 {
@@ -2416,13 +2416,13 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 
 	if (uts) {
 		struct timespec64 ts;
-		ktime_t dt;
 
 		if (get_timespec64(&ts, uts))
 			return -EFAULT;
 
-		dt = timespec64_to_ktime(ts);
-		iowq.timeout = ktime_add(dt, ktime_get());
+		iowq.timeout = timespec64_to_ktime(ts);
+		if (!(flags & IORING_ENTER_ABS_TIMER))
+			iowq.timeout = ktime_add(iowq.timeout, ktime_get());
 	}
 
 	if (sig) {
@@ -3153,7 +3153,8 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 
 	if (unlikely(flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP |
 			       IORING_ENTER_SQ_WAIT | IORING_ENTER_EXT_ARG |
-			       IORING_ENTER_REGISTERED_RING)))
+			       IORING_ENTER_REGISTERED_RING |
+			       IORING_ENTER_ABS_TIMER)))
 		return -EINVAL;
 
 	/*
@@ -3251,8 +3252,8 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 			if (likely(!ret2)) {
 				min_complete = min(min_complete,
 						   ctx->cq_entries);
-				ret2 = io_cqring_wait(ctx, min_complete, sig,
-						      argsz, ts);
+				ret2 = io_cqring_wait(ctx, min_complete, flags,
+						      sig, argsz, ts);
 			}
 		}