Merge branch 'netdev-fix-repeated-netlink-messages-in-queue-dumps'

Jakub Kicinski says:

====================
netdev: fix repeated netlink messages in queue dumps

Fix dump continuation for queues and queue stats in the netdev family.
Because we used post-increment when saving id of dumped queue next
skb would re-dump the already dumped queue.
====================

Link: https://patch.msgid.link/20241213152244.3080955-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

net/core/netdev-genl.c

@@ -488,24 +488,21 @@ netdev_nl_queue_dump_one(struct net_device *netdev, struct sk_buff *rsp,
 			 struct netdev_nl_dump_ctx *ctx)
 {
 	int err = 0;
-	int i;
 
 	if (!(netdev->flags & IFF_UP))
 		return err;
 
-	for (i = ctx->rxq_idx; i < netdev->real_num_rx_queues;) {
+	for (; ctx->rxq_idx < netdev->real_num_rx_queues; ctx->rxq_idx++) {
-		err = netdev_nl_queue_fill_one(rsp, netdev, i,
+		err = netdev_nl_queue_fill_one(rsp, netdev, ctx->rxq_idx,
 					       NETDEV_QUEUE_TYPE_RX, info);
 		if (err)
 			return err;
-		ctx->rxq_idx = i++;
 	}
-	for (i = ctx->txq_idx; i < netdev->real_num_tx_queues;) {
+	for (; ctx->txq_idx < netdev->real_num_tx_queues; ctx->txq_idx++) {
-		err = netdev_nl_queue_fill_one(rsp, netdev, i,
+		err = netdev_nl_queue_fill_one(rsp, netdev, ctx->txq_idx,
 					       NETDEV_QUEUE_TYPE_TX, info);
 		if (err)
 			return err;
-		ctx->txq_idx = i++;
 	}
 
 	return err;
@@ -671,7 +668,7 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp,
 					    i, info);
 		if (err)
 			return err;
-		ctx->rxq_idx = i++;
+		ctx->rxq_idx = ++i;
 	}
 	i = ctx->txq_idx;
 	while (ops->get_queue_stats_tx && i < netdev->real_num_tx_queues) {
@@ -679,7 +676,7 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp,
 					    i, info);
 		if (err)
 			return err;
-		ctx->txq_idx = i++;
+		ctx->txq_idx = ++i;
 	}
 
 	ctx->rxq_idx = 0;

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

@@ -8,25 +8,28 @@ from lib.py import cmd
 import glob
 
 
-def sys_get_queues(ifname) -> int:
+def sys_get_queues(ifname, qtype='rx') -> int:
-    folders = glob.glob(f'/sys/class/net/{ifname}/queues/rx-*')
+    folders = glob.glob(f'/sys/class/net/{ifname}/queues/{qtype}-*')
     return len(folders)
 
 
-def nl_get_queues(cfg, nl):
+def nl_get_queues(cfg, nl, qtype='rx'):
     queues = nl.queue_get({'ifindex': cfg.ifindex}, dump=True)
     if queues:
-        return len([q for q in queues if q['type'] == 'rx'])
+        return len([q for q in queues if q['type'] == qtype])
     return None
 
 
 def get_queues(cfg, nl) -> None:
-    queues = nl_get_queues(cfg, nl)
+    snl = NetdevFamily(recv_size=4096)
-    if not queues:
-        raise KsftSkipEx('queue-get not supported by device')
 
-    expected = sys_get_queues(cfg.dev['ifname'])
+    for qtype in ['rx', 'tx']:
-    ksft_eq(queues, expected)
+        queues = nl_get_queues(cfg, snl, qtype)
+        if not queues:
+            raise KsftSkipEx('queue-get not supported by device')
+
+        expected = sys_get_queues(cfg.dev['ifname'], qtype)
+        ksft_eq(queues, expected)
 
 
 def addremove_queues(cfg, nl) -> None:
@@ -57,7 +60,7 @@ def addremove_queues(cfg, nl) -> None:
 
 
 def main() -> None:
-    with NetDrvEnv(__file__, queue_count=3) as cfg:
+    with NetDrvEnv(__file__, queue_count=100) as cfg:
         ksft_run([get_queues, addremove_queues], args=(cfg, NetdevFamily()))
     ksft_exit()
 

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

@@ -110,6 +110,23 @@ def qstat_by_ifindex(cfg) -> None:
             ksft_ge(triple[1][key], triple[0][key], comment="bad key: " + key)
             ksft_ge(triple[2][key], triple[1][key], comment="bad key: " + key)
 
+    # Sanity check the dumps
+    queues = NetdevFamily(recv_size=4096).qstats_get({"scope": "queue"}, dump=True)
+    # Reformat the output into {ifindex: {rx: [id, id, ...], tx: [id, id, ...]}}
+    parsed = {}
+    for entry in queues:
+        ifindex = entry["ifindex"]
+        if ifindex not in parsed:
+            parsed[ifindex] = {"rx":[], "tx": []}
+        parsed[ifindex][entry["queue-type"]].append(entry['queue-id'])
+    # Now, validate
+    for ifindex, queues in parsed.items():
+        for qtype in ['rx', 'tx']:
+            ksft_eq(len(queues[qtype]), len(set(queues[qtype])),
+                    comment="repeated queue keys")
+            ksft_eq(len(queues[qtype]), max(queues[qtype]) + 1,
+                    comment="missing queue keys")
+
     # Test invalid dumps
     # 0 is invalid
     with ksft_raises(NlError) as cm:
@@ -158,7 +175,7 @@ def check_down(cfg) -> None:
 
 
 def main() -> None:
-    with NetDrvEnv(__file__) as cfg:
+    with NetDrvEnv(__file__, queue_count=100) as cfg:
         ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex,
                   check_down],
                  args=(cfg, ))

tools/testing/selftests/net/lib/py/ynl.py

@@ -32,23 +32,23 @@ except ModuleNotFoundError as e:
 # Set schema='' to avoid jsonschema validation, it's slow
 #
 class EthtoolFamily(YnlFamily):
-    def __init__(self):
+    def __init__(self, recv_size=0):
         super().__init__((SPEC_PATH / Path('ethtool.yaml')).as_posix(),
-                         schema='')
+                         schema='', recv_size=recv_size)
 
 
 class RtnlFamily(YnlFamily):
-    def __init__(self):
+    def __init__(self, recv_size=0):
         super().__init__((SPEC_PATH / Path('rt_link.yaml')).as_posix(),
-                         schema='')
+                         schema='', recv_size=recv_size)
 
 
 class NetdevFamily(YnlFamily):
-    def __init__(self):
+    def __init__(self, recv_size=0):
         super().__init__((SPEC_PATH / Path('netdev.yaml')).as_posix(),
-                         schema='')
+                         schema='', recv_size=recv_size)
 
 class NetshaperFamily(YnlFamily):
-    def __init__(self):
+    def __init__(self, recv_size=0):
         super().__init__((SPEC_PATH / Path('net_shaper.yaml')).as_posix(),
-                         schema='')
+                         schema='', recv_size=recv_size)