Merge branch 'netdev-expose-page-pool-order-via-netlink'

Dragos Tatulea says:

====================
netdev: expose page pool order via netlink

This small series exposes io_uring's high order page configuration
via the page_pool netlink interface and updates the appropriate
selftest to check this value.
====================

Link: https://patch.msgid.link/20260612211709.1456966-2-dtatulea@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Documentation/netlink/specs/netdev.yaml

@@ -127,7 +127,14 @@ attribute-sets:
         enum: xsk-flags
   -
     name: io-uring-provider-info
-    attributes: []
+    attributes:
+      -
+        name: rx-buf-len
+        type: uint
+        doc: |
+          RX buffer length in bytes for this io_uring memory provider.
+          Reflects the rx_buf_len passed at io_uring zerocopy rx
+          registration time.
   -
     name: page-pool
     attributes:

include/uapi/linux/netdev.h

@@ -97,6 +97,8 @@ enum {
 };
 
 enum {
+	NETDEV_A_IO_URING_PROVIDER_INFO_RX_BUF_LEN = 1,
+
 	__NETDEV_A_IO_URING_PROVIDER_INFO_MAX,
 	NETDEV_A_IO_URING_PROVIDER_INFO_MAX = (__NETDEV_A_IO_URING_PROVIDER_INFO_MAX - 1)
 };

io_uring/zcrx.c

@@ -1156,6 +1156,7 @@ static void io_pp_zc_destroy(struct page_pool *pp)
 static int io_pp_nl_fill(void *mp_priv, struct sk_buff *rsp,
 			 struct netdev_rx_queue *rxq)
 {
+	struct io_zcrx_ifq *ifq = mp_priv;
 	struct nlattr *nest;
 	int type;
 
@@ -1163,6 +1164,13 @@ static int io_pp_nl_fill(void *mp_priv, struct sk_buff *rsp,
 	nest = nla_nest_start(rsp, type);
 	if (!nest)
 		return -EMSGSIZE;
+
+	if (nla_put_uint(rsp, NETDEV_A_IO_URING_PROVIDER_INFO_RX_BUF_LEN,
+			 1ULL << ifq->niov_shift)) {
+		nla_nest_cancel(rsp, nest);
+		return -EMSGSIZE;
+	}
+
 	nla_nest_end(rsp, nest);
 
 	return 0;

tools/include/uapi/linux/netdev.h

@@ -97,6 +97,8 @@ enum {
 };
 
 enum {
+	NETDEV_A_IO_URING_PROVIDER_INFO_RX_BUF_LEN = 1,
+
 	__NETDEV_A_IO_URING_PROVIDER_INFO_MAX,
 	NETDEV_A_IO_URING_PROVIDER_INFO_MAX = (__NETDEV_A_IO_URING_PROVIDER_INFO_MAX - 1)
 };

tools/testing/selftests/drivers/net/hw/iou-zcrx.py

@@ -2,6 +2,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 import re
+import resource
 import time
 from os import path
 from lib.py import ksft_run, ksft_exit, KsftSkipEx, ksft_variants, KsftNamedVariant
@@ -41,6 +42,23 @@ def set_flow_rule_rss(cfg, rss_ctx_id):
     return int(values)
 
 
+def check_iou_rx_buf_len(cfg, expected_rx_buf_len):
+    """Check the io-uring memory provider exposes the expected rx_buf_len."""
+    q = cfg.netnl.queue_get({'ifindex': cfg.ifindex, 'type': 'rx', 'id': cfg.target})
+    napi_id = q['napi-id']
+    pools = cfg.netnl.page_pool_get({}, dump=True)
+    pools = [p for p in pools if p.get('napi-id') == napi_id
+             and 'io-uring' in p]
+    if len(pools) != 1:
+        raise Exception(f"Expected 1 io-uring page pool, found {len(pools)}")
+    rx_buf_len = pools[0]['io-uring'].get('rx-buf-len')
+    if rx_buf_len is None:
+        raise KsftSkipEx("io-uring 'rx-buf-len' attribute not supported")
+    if rx_buf_len != expected_rx_buf_len:
+        raise Exception(f'Expected io-uring rx-buf-len {expected_rx_buf_len}, '
+                        f'got {rx_buf_len}')
+
+
 def single(cfg):
     channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
     channels = channels['combined-count']
@@ -156,7 +174,10 @@ def test_zcrx_large_chunks(cfg) -> None:
             defer(lambda: open(hp_file, 'w', encoding='utf-8').write(str(nr_hugepages)))
 
     single(cfg)
-    rx_cmd = f"{cfg.bin_local} -s -p {cfg.port} -i {cfg.ifname} -q {cfg.target} -x 2"
+    page_size = resource.getpagesize()
+    nr_pages = 2
+    rx_buf_len = nr_pages * page_size
+    rx_cmd = f"{cfg.bin_local} -s -p {cfg.port} -i {cfg.ifname} -q {cfg.target} -x {nr_pages}"
     tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {cfg.port} -l 12840"
 
     probe = cmd(rx_cmd + " -d", fail=False)
@@ -166,6 +187,9 @@ def test_zcrx_large_chunks(cfg) -> None:
     mp_clear_wait(cfg)
     with bkg(rx_cmd, exit_wait=True):
         wait_port_listen(cfg.port, proto="tcp")
+
+        check_iou_rx_buf_len(cfg, rx_buf_len)
+
         cmd(tx_cmd, host=cfg.remote)