io_uring/zcrx: implement large rx buffer support

There are network cards that support receive buffers larger than 4K, and
that can be vastly beneficial for performance, and benchmarks for this
patch showed up to 30% CPU util improvement for 32K vs 4K buffers.

Allows zcrx users to specify the size in struct
io_uring_zcrx_ifq_reg::rx_buf_len. If set to zero, zcrx will use a
default value. zcrx will check and fail if the memory backing the area
can't be split into physically contiguous chunks of the required size.
It's more restrictive as it only needs dma addresses to be contig, but
that's beyond this series.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
[axboe: kill duplicate netdev_queues.h include]
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: isilence

include/uapi/linux/io_uring.h

@@ -1082,7 +1082,7 @@ struct io_uring_zcrx_ifq_reg {
 
 	struct io_uring_zcrx_offsets offsets;
 	__u32	zcrx_id;
-	__u32	__resv2;
+	__u32	rx_buf_len;
 	__u64	__resv[3];
 };
 

io_uring/zcrx.c

@@ -55,6 +55,18 @@ static inline struct page *io_zcrx_iov_page(const struct net_iov *niov)
 	return area->mem.pages[net_iov_idx(niov) << niov_pages_shift];
 }
 
+static int io_area_max_shift(struct io_zcrx_mem *mem)
+{
+	struct sg_table *sgt = mem->sgt;
+	struct scatterlist *sg;
+	unsigned shift = -1U;
+	unsigned i;
+
+	for_each_sgtable_dma_sg(sgt, sg, i)
+		shift = min(shift, __ffs(sg->length));
+	return shift;
+}
+
 static int io_populate_area_dma(struct io_zcrx_ifq *ifq,
 				struct io_zcrx_area *area)
 {
@@ -416,12 +428,21 @@ static int io_zcrx_append_area(struct io_zcrx_ifq *ifq,
 }
 
 static int io_zcrx_create_area(struct io_zcrx_ifq *ifq,
-			       struct io_uring_zcrx_area_reg *area_reg)
+			       struct io_uring_zcrx_area_reg *area_reg,
+			       struct io_uring_zcrx_ifq_reg *reg)
 {
+	int buf_size_shift = PAGE_SHIFT;
 	struct io_zcrx_area *area;
 	unsigned nr_iovs;
 	int i, ret;
 
+	if (reg->rx_buf_len) {
+		if (!is_power_of_2(reg->rx_buf_len) ||
+		     reg->rx_buf_len < PAGE_SIZE)
+			return -EINVAL;
+		buf_size_shift = ilog2(reg->rx_buf_len);
+	}
+
 	ret = -ENOMEM;
 	area = kzalloc(sizeof(*area), GFP_KERNEL);
 	if (!area)
@@ -432,7 +453,12 @@ static int io_zcrx_create_area(struct io_zcrx_ifq *ifq,
 	if (ret)
 		goto err;
 
-	ifq->niov_shift = PAGE_SHIFT;
+	if (buf_size_shift > io_area_max_shift(&area->mem)) {
+		ret = -ERANGE;
+		goto err;
+	}
+
+	ifq->niov_shift = buf_size_shift;
 	nr_iovs = area->mem.size >> ifq->niov_shift;
 	area->nia.num_niovs = nr_iovs;
 
@@ -742,8 +768,7 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 		return -EINVAL;
 	if (copy_from_user(&reg, arg, sizeof(reg)))
 		return -EFAULT;
-	if (!mem_is_zero(&reg.__resv, sizeof(reg.__resv)) ||
-	    reg.__resv2 || reg.zcrx_id)
+	if (!mem_is_zero(&reg.__resv, sizeof(reg.__resv)) || reg.zcrx_id)
 		return -EINVAL;
 	if (reg.flags & ZCRX_REG_IMPORT)
 		return import_zcrx(ctx, arg, &reg);
@@ -800,10 +825,11 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 	}
 	get_device(ifq->dev);
 
-	ret = io_zcrx_create_area(ifq, &area);
+	ret = io_zcrx_create_area(ifq, &area, &reg);
 	if (ret)
 		goto netdev_put_unlock;
 
+	mp_param.rx_page_size = 1U << ifq->niov_shift;
 	mp_param.mp_ops = &io_uring_pp_zc_ops;
 	mp_param.mp_priv = ifq;
 	ret = __net_mp_open_rxq(ifq->netdev, reg.if_rxq, &mp_param, NULL);
@@ -821,6 +847,8 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 			goto err;
 	}
 
+	reg.rx_buf_len = 1U << ifq->niov_shift;
+
 	if (copy_to_user(arg, &reg, sizeof(reg)) ||
 	    copy_to_user(u64_to_user_ptr(reg.region_ptr), &rd, sizeof(rd)) ||
 	    copy_to_user(u64_to_user_ptr(reg.area_ptr), &area, sizeof(area))) {