iomap: support IOCB_DIO_CALLER_COMP

If IOCB_DIO_CALLER_COMP is set, utilize that to set kiocb->dio_complete
handler and data for that callback. Rather than punt the completion to a
workqueue, we pass back the handler and data to the issuer and will get
a callback from a safe task context.

Using the following fio job to randomly dio write 4k blocks at
queue depths of 1..16:

fio --name=dio-write --filename=/data1/file --time_based=1 \
--runtime=10 --bs=4096 --rw=randwrite --norandommap --buffered=0 \
--cpus_allowed=4 --ioengine=io_uring --iodepth=$depth

shows the following results before and after this patch:

	Stock	Patched		Diff
=======================================
QD1	155K	162K		+ 4.5%
QD2	290K	313K		+ 7.9%
QD4	533K	597K		+12.0%
QD8	604K	827K		+36.9%
QD16	615K	845K		+37.4%

which shows nice wins all around. If we factored in per-IOP efficiency,
the wins look even nicer. This becomes apparent as queue depth rises,
as the offloaded workqueue completions runs out of steam.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

fs/iomap/direct-io.c

@@ -20,6 +20,7 @@
  * Private flags for iomap_dio, must not overlap with the public ones in
  * iomap.h:
  */
+#define IOMAP_DIO_CALLER_COMP	(1U << 26)
 #define IOMAP_DIO_INLINE_COMP	(1U << 27)
 #define IOMAP_DIO_WRITE_THROUGH	(1U << 28)
 #define IOMAP_DIO_NEED_SYNC	(1U << 29)
@@ -132,6 +133,11 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 }
 EXPORT_SYMBOL_GPL(iomap_dio_complete);
 
+static ssize_t iomap_dio_deferred_complete(void *data)
+{
+	return iomap_dio_complete(data);
+}
+
 static void iomap_dio_complete_work(struct work_struct *work)
 {
 	struct iomap_dio *dio = container_of(work, struct iomap_dio, aio.work);
@@ -182,6 +188,31 @@ void iomap_dio_bio_end_io(struct bio *bio)
 		goto release_bio;
 	}
 
+	/*
+	 * If this dio is flagged with IOMAP_DIO_CALLER_COMP, then schedule
+	 * our completion that way to avoid an async punt to a workqueue.
+	 */
+	if (dio->flags & IOMAP_DIO_CALLER_COMP) {
+		/* only polled IO cares about private cleared */
+		iocb->private = dio;
+		iocb->dio_complete = iomap_dio_deferred_complete;
+
+		/*
+		 * Invoke ->ki_complete() directly. We've assigned our
+		 * dio_complete callback handler, and since the issuer set
+		 * IOCB_DIO_CALLER_COMP, we know their ki_complete handler will
+		 * notice ->dio_complete being set and will defer calling that
+		 * handler until it can be done from a safe task context.
+		 *
+		 * Note that the 'res' being passed in here is not important
+		 * for this case. The actual completion value of the request
+		 * will be gotten from dio_complete when that is run by the
+		 * issuer.
+		 */
+		iocb->ki_complete(iocb, 0);
+		goto release_bio;
+	}
+
 	/*
 	 * Async DIO completion that requires filesystem level completion work
 	 * gets punted to a work queue to complete as the operation may require
@@ -278,12 +309,17 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 		 * after IO completion such as unwritten extent conversion) and
 		 * the underlying device either supports FUA or doesn't have
 		 * a volatile write cache. This allows us to avoid cache flushes
-		 * on IO completion.
+		 * on IO completion. If we can't use writethrough and need to
+		 * sync, disable in-task completions as dio completion will
+		 * need to call generic_write_sync() which will do a blocking
+		 * fsync / cache flush call.
 		 */
 		if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) &&
 		    (dio->flags & IOMAP_DIO_WRITE_THROUGH) &&
 		    (bdev_fua(iomap->bdev) || !bdev_write_cache(iomap->bdev)))
 			use_fua = true;
+		else if (dio->flags & IOMAP_DIO_NEED_SYNC)
+			dio->flags &= ~IOMAP_DIO_CALLER_COMP;
 	}
 
 	/*
@@ -298,10 +334,23 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 		goto out;
 
 	/*
-	 * We can only poll for single bio I/Os.
+	 * We can only do deferred completion for pure overwrites that
+	 * don't require additional IO at completion. This rules out
+	 * writes that need zeroing or extent conversion, extend
+	 * the file size, or issue journal IO or cache flushes
+	 * during completion processing.
 	 */
 	if (need_zeroout ||
+	    ((dio->flags & IOMAP_DIO_NEED_SYNC) && !use_fua) ||
 	    ((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode)))
+		dio->flags &= ~IOMAP_DIO_CALLER_COMP;
+
+	/*
+	 * The rules for polled IO completions follow the guidelines as the
+	 * ones we set for inline and deferred completions. If none of those
+	 * are available for this IO, clear the polled flag.
+	 */
+	if (!(dio->flags & (IOMAP_DIO_INLINE_COMP|IOMAP_DIO_CALLER_COMP)))
 		dio->iocb->ki_flags &= ~IOCB_HIPRI;
 
 	if (need_zeroout) {
@@ -547,6 +596,15 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		iomi.flags |= IOMAP_WRITE;
 		dio->flags |= IOMAP_DIO_WRITE;
 
+		/*
+		 * Flag as supporting deferred completions, if the issuer
+		 * groks it. This can avoid a workqueue punt for writes.
+		 * We may later clear this flag if we need to do other IO
+		 * as part of this IO completion.
+		 */
+		if (iocb->ki_flags & IOCB_DIO_CALLER_COMP)
+			dio->flags |= IOMAP_DIO_CALLER_COMP;
+
 		if (dio_flags & IOMAP_DIO_OVERWRITE_ONLY) {
 			ret = -EAGAIN;
 			if (iomi.pos >= dio->i_size ||