Merge branch 'netdev-genl-add-an-xsk-attribute-to-queues'

Joe Damato says:

====================
netdev-genl: Add an xsk attribute to queues

This is an attempt to followup on something Jakub asked me about [1],
adding an xsk attribute to queues and more clearly documenting which
queues are linked to NAPIs...

After the RFC [2], Jakub suggested creating an empty nest for queues
which have a pool, so I've adjusted this version to work that way.

The nest can be extended in the future to express attributes about XSK
as needed. Queues which are not used for AF_XDP do not have the xsk
attribute present.

I've run the included test on:
  - my mlx5 machine (via NETIF=)
  - without setting NETIF

And the test seems to pass in both cases.

[1]: https://lore.kernel.org/netdev/20250113143109.60afa59a@kernel.org/
[2]: https://lore.kernel.org/netdev/20250129172431.65773-1-jdamato@fastly.com/
====================

Link: https://patch.msgid.link/20250214211255.14194-1-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Documentation/netlink/specs/netdev.yaml

@@ -276,6 +276,9 @@ attribute-sets:
         doc: The timeout, in nanoseconds, of how long to suspend irq
              processing, if event polling finds events
         type: uint
+  -
+    name: xsk-info
+    attributes: []
   -
     name: queue
     attributes:
@@ -294,6 +297,9 @@ attribute-sets:
       -
         name: type
         doc: Queue type as rx, tx. Each queue type defines a separate ID space.
+             XDP TX queues allocated in the kernel are not linked to NAPIs and
+             thus not listed. AF_XDP queues will have more information set in
+             the xsk attribute.
         type: u32
         enum: queue-type
       -
@@ -309,7 +315,11 @@ attribute-sets:
         doc: io_uring memory provider information.
         type: nest
         nested-attributes: io-uring-provider-info
-
+      -
+        name: xsk
+        doc: XSK information for this queue, if any.
+        type: nest
+        nested-attributes: xsk-info
   -
     name: qstats
     doc: |
@@ -652,6 +662,7 @@ operations:
             - ifindex
             - dmabuf
             - io-uring
+            - xsk
       dump:
         request:
           attributes:

include/net/netlink.h

@@ -118,6 +118,7 @@
  *   nla_nest_start(skb, type)		start a nested attribute
  *   nla_nest_end(skb, nla)		finalize a nested attribute
  *   nla_nest_cancel(skb, nla)		cancel nested attribute construction
+ *   nla_put_empty_nest(skb, type)	create an empty nest
  *
  * Attribute Length Calculations:
  *   nla_attr_size(payload)		length of attribute w/o padding
@@ -2240,6 +2241,20 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start)
 	nlmsg_trim(skb, start);
 }
 
+/**
+ * nla_put_empty_nest - Create an empty nest
+ * @skb: socket buffer the message is stored in
+ * @attrtype: attribute type of the container
+ *
+ * This function is a helper for creating empty nests.
+ *
+ * Returns: 0 when successful or -EMSGSIZE on failure.
+ */
+static inline int nla_put_empty_nest(struct sk_buff *skb, int attrtype)
+{
+	return nla_nest_start(skb, attrtype) ? 0 : -EMSGSIZE;
+}
+
 /**
  * __nla_validate_nested - Validate a stream of nested attributes
  * @start: container attribute

include/uapi/linux/netdev.h

@@ -136,13 +136,19 @@ enum {
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
 };
 
+enum {
+	__NETDEV_A_XSK_INFO_MAX,
+	NETDEV_A_XSK_INFO_MAX = (__NETDEV_A_XSK_INFO_MAX - 1)
+};
+
 enum {
 	NETDEV_A_QUEUE_ID = 1,
 	NETDEV_A_QUEUE_IFINDEX,
 	NETDEV_A_QUEUE_TYPE,
 	NETDEV_A_QUEUE_NAPI_ID,
 	NETDEV_A_QUEUE_DMABUF,
 	NETDEV_A_QUEUE_IO_URING,
+	NETDEV_A_QUEUE_XSK,
 
 	__NETDEV_A_QUEUE_MAX,
 	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)

net/core/netdev-genl.c

@@ -400,11 +400,23 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 		if (params->mp_ops &&
 		    params->mp_ops->nl_fill(params->mp_priv, rsp, rxq))
 			goto nla_put_failure;
+#ifdef CONFIG_XDP_SOCKETS
+		if (rxq->pool)
+			if (nla_put_empty_nest(rsp, NETDEV_A_QUEUE_XSK))
+				goto nla_put_failure;
+#endif
+
 		break;
 	case NETDEV_QUEUE_TYPE_TX:
 		txq = netdev_get_tx_queue(netdev, q_idx);
 		if (nla_put_napi_id(rsp, txq->napi))
 			goto nla_put_failure;
+#ifdef CONFIG_XDP_SOCKETS
+		if (txq->pool)
+			if (nla_put_empty_nest(rsp, NETDEV_A_QUEUE_XSK))
+				goto nla_put_failure;
+#endif
+		break;
 	}
 
 	genlmsg_end(rsp, hdr);

tools/include/uapi/linux/netdev.h

@@ -136,13 +136,19 @@ enum {
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
 };
 
+enum {
+	__NETDEV_A_XSK_INFO_MAX,
+	NETDEV_A_XSK_INFO_MAX = (__NETDEV_A_XSK_INFO_MAX - 1)
+};
+
 enum {
 	NETDEV_A_QUEUE_ID = 1,
 	NETDEV_A_QUEUE_IFINDEX,
 	NETDEV_A_QUEUE_TYPE,
 	NETDEV_A_QUEUE_NAPI_ID,
 	NETDEV_A_QUEUE_DMABUF,
 	NETDEV_A_QUEUE_IO_URING,
+	NETDEV_A_QUEUE_XSK,
 
 	__NETDEV_A_QUEUE_MAX,
 	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)

tools/testing/selftests/drivers/net/.gitignore

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+xdp_helper

tools/testing/selftests/drivers/net/Makefile

@@ -1,10 +1,13 @@
 # SPDX-License-Identifier: GPL-2.0
+CFLAGS += $(KHDR_INCLUDES)
 
 TEST_INCLUDES := $(wildcard lib/py/*.py) \
 		 $(wildcard lib/sh/*.sh) \
 		 ../../net/net_helper.sh \
 		 ../../net/lib.sh \
 
+TEST_GEN_FILES := xdp_helper
+
 TEST_PROGS := \
 	netcons_basic.sh \
 	netcons_fragmented_msg.sh \

tools/testing/selftests/drivers/net/config

@@ -4,3 +4,4 @@ CONFIG_CONFIGFS_FS=y
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_NETCONSOLE_EXTENDED_LOG=y
+CONFIG_XDP_SOCKETS=y

tools/testing/selftests/drivers/net/queues.py

@@ -2,13 +2,16 @@
 # SPDX-License-Identifier: GPL-2.0
 
 from lib.py import ksft_disruptive, ksft_exit, ksft_run
-from lib.py import ksft_eq, ksft_raises, KsftSkipEx
+from lib.py import ksft_eq, ksft_raises, KsftSkipEx, KsftFailEx
 from lib.py import EthtoolFamily, NetdevFamily, NlError
 from lib.py import NetDrvEnv
 from lib.py import cmd, defer, ip
 import errno
 import glob
-
+import os
+import socket
+import struct
+import subprocess
 
 def sys_get_queues(ifname, qtype='rx') -> int:
     folders = glob.glob(f'/sys/class/net/{ifname}/queues/{qtype}-*')
@@ -21,6 +24,39 @@ def nl_get_queues(cfg, nl, qtype='rx'):
         return len([q for q in queues if q['type'] == qtype])
     return None
 
+def check_xdp(cfg, nl, xdp_queue_id=0) -> None:
+    test_dir = os.path.dirname(os.path.realpath(__file__))
+    xdp = subprocess.Popen([f"{test_dir}/xdp_helper", f"{cfg.ifindex}", f"{xdp_queue_id}"],
+                           stdin=subprocess.PIPE, stdout=subprocess.PIPE, bufsize=1,
+                           text=True)
+    defer(xdp.kill)
+
+    stdout, stderr = xdp.communicate(timeout=10)
+    rx = tx = False
+
+    if xdp.returncode == 255:
+        raise KsftSkipEx('AF_XDP unsupported')
+    elif xdp.returncode > 0:
+        raise KsftFailEx('unable to create AF_XDP socket')
+
+    queues = nl.queue_get({'ifindex': cfg.ifindex}, dump=True)
+    if not queues:
+        raise KsftSkipEx("Netlink reports no queues")
+
+    for q in queues:
+        if q['id'] == 0:
+            if q['type'] == 'rx':
+                rx = True
+            if q['type'] == 'tx':
+                tx = True
+
+            ksft_eq(q['xsk'], {})
+        else:
+            if 'xsk' in q:
+                _fail("Check failed: xsk attribute set.")
+
+    ksft_eq(rx, True)
+    ksft_eq(tx, True)
 
 def get_queues(cfg, nl) -> None:
     snl = NetdevFamily(recv_size=4096)
@@ -81,7 +117,7 @@ def check_down(cfg, nl) -> None:
 
 def main() -> None:
     with NetDrvEnv(__file__, queue_count=100) as cfg:
-        ksft_run([get_queues, addremove_queues, check_down], args=(cfg, NetdevFamily()))
+        ksft_run([get_queues, addremove_queues, check_down, check_xdp], args=(cfg, NetdevFamily()))
     ksft_exit()
 
 

tools/testing/selftests/drivers/net/xdp_helper.c

@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <sys/socket.h>
+#include <linux/if_xdp.h>
+#include <linux/if_link.h>
+#include <net/if.h>
+#include <inttypes.h>
+
+#define UMEM_SZ (1U << 16)
+#define NUM_DESC (UMEM_SZ / 2048)
+
+/* this is a simple helper program that creates an XDP socket and does the
+ * minimum necessary to get bind() to succeed.
+ *
+ * this test program is not intended to actually process packets, but could be
+ * extended in the future if that is actually needed.
+ *
+ * it is used by queues.py to ensure the xsk netlinux attribute is set
+ * correctly.
+ */
+int main(int argc, char **argv)
+{
+	struct xdp_umem_reg umem_reg = { 0 };
+	struct sockaddr_xdp sxdp = { 0 };
+	int num_desc = NUM_DESC;
+	void *umem_area;
+	int ifindex;
+	int sock_fd;
+	int queue;
+	char byte;
+
+	if (argc != 3) {
+		fprintf(stderr, "Usage: %s ifindex queue_id", argv[0]);
+		return 1;
+	}
+
+	sock_fd = socket(AF_XDP, SOCK_RAW, 0);
+	if (sock_fd < 0) {
+		perror("socket creation failed");
+		/* if the kernel doesn't support AF_XDP, let the test program
+		 * know with -1. All other error paths return 1.
+		 */
+		if (errno == EAFNOSUPPORT)
+			return -1;
+		return 1;
+	}
+
+	ifindex = atoi(argv[1]);
+	queue = atoi(argv[2]);
+
+	umem_area = mmap(NULL, UMEM_SZ, PROT_READ | PROT_WRITE, MAP_PRIVATE |
+			MAP_ANONYMOUS, -1, 0);
+	if (umem_area == MAP_FAILED) {
+		perror("mmap failed");
+		return 1;
+	}
+
+	umem_reg.addr = (uintptr_t)umem_area;
+	umem_reg.len = UMEM_SZ;
+	umem_reg.chunk_size = 2048;
+	umem_reg.headroom = 0;
+
+	setsockopt(sock_fd, SOL_XDP, XDP_UMEM_REG, &umem_reg,
+		   sizeof(umem_reg));
+	setsockopt(sock_fd, SOL_XDP, XDP_UMEM_FILL_RING, &num_desc,
+		   sizeof(num_desc));
+	setsockopt(sock_fd, SOL_XDP, XDP_UMEM_COMPLETION_RING, &num_desc,
+		   sizeof(num_desc));
+	setsockopt(sock_fd, SOL_XDP, XDP_RX_RING, &num_desc, sizeof(num_desc));
+
+	sxdp.sxdp_family = AF_XDP;
+	sxdp.sxdp_ifindex = ifindex;
+	sxdp.sxdp_queue_id = queue;
+	sxdp.sxdp_flags = 0;
+
+	if (bind(sock_fd, (struct sockaddr *)&sxdp, sizeof(sxdp)) != 0) {
+		munmap(umem_area, UMEM_SZ);
+		perror("bind failed");
+		close(sock_fd);
+		return 1;
+	}
+
+	/* give the parent program some data when the socket is ready*/
+	fprintf(stdout, "%d\n", sock_fd);
+
+	/* parent program will write a byte to stdin when its ready for this
+	 * helper to exit
+	 */
+	read(STDIN_FILENO, &byte, 1);
+
+	close(sock_fd);
+	return 0;
+}