ublk: add segment parameter

IO split is usually bad in io_uring world, since -EAGAIN is caused and
IO handling may have to fallback to io-wq, this way does hurt performance.

ublk starts to support zero copy recently, for avoiding unnecessary IO
split, ublk driver's segment limit should be aligned with backend
device's segment limit.

Another reason is that io_buffer_register_bvec() needs to allocate bvecs,
which number is aligned with ublk request segment number, so that big
memory allocation can be avoided by setting reasonable max_segments limit.

So add segment parameter for providing ublk server chance to align
segment limit with backend, and keep it reasonable from implementation
viewpoint.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250327095123.179113-7-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: Ming Lei

drivers/block/ublk_drv.c

@@ -74,7 +74,7 @@
 #define UBLK_PARAM_TYPE_ALL                                \
 	(UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DISCARD | \
 	 UBLK_PARAM_TYPE_DEVT | UBLK_PARAM_TYPE_ZONED |    \
-	 UBLK_PARAM_TYPE_DMA_ALIGN)
+	 UBLK_PARAM_TYPE_DMA_ALIGN | UBLK_PARAM_TYPE_SEGMENT)
 
 struct ublk_rq_data {
 	struct kref ref;
@@ -580,6 +580,18 @@ static int ublk_validate_params(const struct ublk_device *ub)
 			return -EINVAL;
 	}
 
+	if (ub->params.types & UBLK_PARAM_TYPE_SEGMENT) {
+		const struct ublk_param_segment *p = &ub->params.seg;
+
+		if (!is_power_of_2(p->seg_boundary_mask + 1))
+			return -EINVAL;
+
+		if (p->seg_boundary_mask + 1 < UBLK_MIN_SEGMENT_SIZE)
+			return -EINVAL;
+		if (p->max_segment_size < UBLK_MIN_SEGMENT_SIZE)
+			return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -2370,6 +2382,12 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 	if (ub->params.types & UBLK_PARAM_TYPE_DMA_ALIGN)
 		lim.dma_alignment = ub->params.dma.alignment;
 
+	if (ub->params.types & UBLK_PARAM_TYPE_SEGMENT) {
+		lim.seg_boundary_mask = ub->params.seg.seg_boundary_mask;
+		lim.max_segment_size = ub->params.seg.max_segment_size;
+		lim.max_segments = ub->params.seg.max_segments;
+	}
+
 	if (wait_for_completion_interruptible(&ub->completion) != 0)
 		return -EINTR;
 

include/uapi/linux/ublk_cmd.h

@@ -410,6 +410,29 @@ struct ublk_param_dma_align {
 	__u8	pad[4];
 };
 
+#define UBLK_MIN_SEGMENT_SIZE   4096
+/*
+ * If any one of the three segment parameter is set as 0, the behavior is
+ * undefined.
+ */
+struct ublk_param_segment {
+	/*
+	 * seg_boundary_mask + 1 needs to be power_of_2(), and the sum has
+	 * to be >= UBLK_MIN_SEGMENT_SIZE(4096)
+	 */
+	__u64 	seg_boundary_mask;
+
+	/*
+	 * max_segment_size could be override by virt_boundary_mask, so be
+	 * careful when setting both.
+	 *
+	 * max_segment_size has to be >= UBLK_MIN_SEGMENT_SIZE(4096)
+	 */
+	__u32 	max_segment_size;
+	__u16 	max_segments;
+	__u8	pad[2];
+};
+
 struct ublk_params {
 	/*
 	 * Total length of parameters, userspace has to set 'len' for both
@@ -423,13 +446,15 @@ struct ublk_params {
 #define UBLK_PARAM_TYPE_DEVT            (1 << 2)
 #define UBLK_PARAM_TYPE_ZONED           (1 << 3)
 #define UBLK_PARAM_TYPE_DMA_ALIGN       (1 << 4)
+#define UBLK_PARAM_TYPE_SEGMENT         (1 << 5)
 	__u32	types;			/* types of parameter included */
 
 	struct ublk_param_basic		basic;
 	struct ublk_param_discard	discard;
 	struct ublk_param_devt		devt;
 	struct ublk_param_zoned	zoned;
 	struct ublk_param_dma_align	dma;
+	struct ublk_param_segment	seg;
 };
 
 #endif