Merge tag 'io_uring-6.2-2022-12-29' of git://git.kernel.dk/linux

Pull io_uring fixes from Jens Axboe:

 - Two fixes for mutex grabbing when the task state is != TASK_RUNNING
   (me)

 - Check for invalid opcode in io_uring_register() a bit earlier, to
   avoid going through the quiesce machinery just to return -EINVAL
   later in the process (me)

 - Fix for the uapi io_uring header, skipping including time_types.h
   when necessary (Stefan)

* tag 'io_uring-6.2-2022-12-29' of git://git.kernel.dk/linux:
  uapi:io_uring.h: allow linux/time_types.h to be skipped
  io_uring: check for valid register opcode earlier
  io_uring/cancel: re-grab ctx mutex after finishing wait
  io_uring: finish waiting before flushing overflow entries

3 files changed, 31 insertions, 16 deletions

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 9d4c4078e8d0..2780bce62faf 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -10,7 +10,15 @@
 
 #include <linux/fs.h>
 #include <linux/types.h>
+/*
+ * this file is shared with liburing and that has to autodetect
+ * if linux/time_types.h is available or not, it can
+ * define UAPI_LINUX_IO_URING_H_SKIP_LINUX_TIME_TYPES_H
+ * if linux/time_types.h is not available
+ */
+#ifndef UAPI_LINUX_IO_URING_H_SKIP_LINUX_TIME_TYPES_H
 #include <linux/time_types.h>
+#endif
 
 #ifdef __cplusplus
 extern "C" {
diff --git a/io_uring/cancel.c b/io_uring/cancel.c
index 2291a53cdabd..b4f5dfacc0c3 100644
--- a/io_uring/cancel.c
+++ b/io_uring/cancel.c
@@ -288,24 +288,23 @@ int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg)
 
 		ret = __io_sync_cancel(current->io_uring, &cd, sc.fd);
 
+		mutex_unlock(&ctx->uring_lock);
 		if (ret != -EALREADY)
 			break;
 
-		mutex_unlock(&ctx->uring_lock);
 		ret = io_run_task_work_sig(ctx);
-		if (ret < 0) {
-			mutex_lock(&ctx->uring_lock);
+		if (ret < 0)
 			break;
-		}
 		ret = schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS);
-		mutex_lock(&ctx->uring_lock);
 		if (!ret) {
 			ret = -ETIME;
 			break;
 		}
+		mutex_lock(&ctx->uring_lock);
 	} while (1);
 
 	finish_wait(&ctx->cq_wait, &wait);
+	mutex_lock(&ctx->uring_lock);
 
 	if (ret == -ENOENT || ret > 0)
 		ret = 0;
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index ff2bbac1a10f..58ac13b69dc8 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -677,16 +677,20 @@ static void __io_cqring_overflow_flush(struct io_ring_ctx *ctx)
 	io_cq_unlock_post(ctx);
 }
 
+static void io_cqring_do_overflow_flush(struct io_ring_ctx *ctx)
+{
+	/* iopoll syncs against uring_lock, not completion_lock */
+	if (ctx->flags & IORING_SETUP_IOPOLL)
+		mutex_lock(&ctx->uring_lock);
+	__io_cqring_overflow_flush(ctx);
+	if (ctx->flags & IORING_SETUP_IOPOLL)
+		mutex_unlock(&ctx->uring_lock);
+}
+
 static void io_cqring_overflow_flush(struct io_ring_ctx *ctx)
 {
-	if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) {
-		/* iopoll syncs against uring_lock, not completion_lock */
-		if (ctx->flags & IORING_SETUP_IOPOLL)
-			mutex_lock(&ctx->uring_lock);
-		__io_cqring_overflow_flush(ctx);
-		if (ctx->flags & IORING_SETUP_IOPOLL)
-			mutex_unlock(&ctx->uring_lock);
-	}
+	if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq))
+		io_cqring_do_overflow_flush(ctx);
 }
 
 void __io_put_task(struct task_struct *task, int nr)
@@ -2549,7 +2553,10 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 
 	trace_io_uring_cqring_wait(ctx, min_events);
 	do {
-		io_cqring_overflow_flush(ctx);
+		if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) {
+			finish_wait(&ctx->cq_wait, &iowq.wq);
+			io_cqring_do_overflow_flush(ctx);
+		}
 		prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq,
 						TASK_INTERRUPTIBLE);
 		ret = io_cqring_wait_schedule(ctx, &iowq, timeout);
@@ -4013,8 +4020,6 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 		return -EEXIST;
 
 	if (ctx->restricted) {
-		if (opcode >= IORING_REGISTER_LAST)
-			return -EINVAL;
 		opcode = array_index_nospec(opcode, IORING_REGISTER_LAST);
 		if (!test_bit(opcode, ctx->restrictions.register_op))
 			return -EACCES;
@@ -4170,6 +4175,9 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
 	long ret = -EBADF;
 	struct fd f;
 
+	if (opcode >= IORING_REGISTER_LAST)
+		return -EINVAL;
+
 	f = fdget(fd);
 	if (!f.file)
 		return -EBADF;