tgupdate: merge t/DO-NOT-MERGE-mptcp-enabled-by-default into t/upstream base

Author: matttbe

drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c

@@ -2967,7 +2967,7 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf,
 			dev_err(&pf->pdev->dev,
 				"Cannot add more MAC addresses: VF reached its maximum allowed limit (%d)\n",
 				mac_add_max);
-				return -EPERM;
+			return -EPERM;
 		}
 		if (!vf_trusted) {
 			dev_err(&pf->pdev->dev,

drivers/net/ethernet/marvell/mvneta.c

@@ -5012,17 +5012,9 @@ static u32 mvneta_ethtool_get_rxfh_indir_size(struct net_device *dev)
 	return MVNETA_RSS_LU_TABLE_SIZE;
 }
 
-static int mvneta_ethtool_get_rxnfc(struct net_device *dev,
-				    struct ethtool_rxnfc *info,
-				    u32 *rules __always_unused)
+static u32 mvneta_ethtool_get_rx_ring_count(struct net_device *dev)
 {
-	switch (info->cmd) {
-	case ETHTOOL_GRXRINGS:
-		info->data =  rxq_number;
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
+	return rxq_number;
 }
 
 static int  mvneta_config_rss(struct mvneta_port *pp)
@@ -5356,7 +5348,7 @@ static const struct ethtool_ops mvneta_eth_tool_ops = {
 	.get_ethtool_stats = mvneta_ethtool_get_stats,
 	.get_sset_count	= mvneta_ethtool_get_sset_count,
 	.get_rxfh_indir_size = mvneta_ethtool_get_rxfh_indir_size,
-	.get_rxnfc	= mvneta_ethtool_get_rxnfc,
+	.get_rx_ring_count = mvneta_ethtool_get_rx_ring_count,
 	.get_rxfh	= mvneta_ethtool_get_rxfh,
 	.set_rxfh	= mvneta_ethtool_set_rxfh,
 	.get_link_ksettings = mvneta_ethtool_get_link_ksettings,

drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c

@@ -5580,6 +5580,13 @@ static int mvpp2_ethtool_set_link_ksettings(struct net_device *dev,
 	return phylink_ethtool_ksettings_set(port->phylink, cmd);
 }
 
+static u32 mvpp2_ethtool_get_rx_ring_count(struct net_device *dev)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+
+	return port->nrxqs;
+}
+
 static int mvpp2_ethtool_get_rxnfc(struct net_device *dev,
 				   struct ethtool_rxnfc *info, u32 *rules)
 {
@@ -5590,9 +5597,6 @@ static int mvpp2_ethtool_get_rxnfc(struct net_device *dev,
 		return -EOPNOTSUPP;
 
 	switch (info->cmd) {
-	case ETHTOOL_GRXRINGS:
-		info->data = port->nrxqs;
-		break;
 	case ETHTOOL_GRXCLSRLCNT:
 		info->rule_cnt = port->n_rfs_rules;
 		break;
@@ -5827,6 +5831,7 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = {
 	.set_pauseparam		= mvpp2_ethtool_set_pause_param,
 	.get_link_ksettings	= mvpp2_ethtool_get_link_ksettings,
 	.set_link_ksettings	= mvpp2_ethtool_set_link_ksettings,
+	.get_rx_ring_count	= mvpp2_ethtool_get_rx_ring_count,
 	.get_rxnfc		= mvpp2_ethtool_get_rxnfc,
 	.set_rxnfc		= mvpp2_ethtool_set_rxnfc,
 	.get_rxfh_indir_size	= mvpp2_ethtool_get_rxfh_indir_size,

drivers/net/hyperv/netvsc_drv.c

@@ -1624,22 +1624,15 @@ netvsc_get_rxfh_fields(struct net_device *ndev,
 	return 0;
 }
 
-static int
-netvsc_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
-		 u32 *rules)
+static u32 netvsc_get_rx_ring_count(struct net_device *dev)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
 	struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev);
 
 	if (!nvdev)
-		return -ENODEV;
-
-	switch (info->cmd) {
-	case ETHTOOL_GRXRINGS:
-		info->data = nvdev->num_chn;
 		return 0;
-	}
-	return -EOPNOTSUPP;
+
+	return nvdev->num_chn;
 }
 
 static int
@@ -1969,7 +1962,7 @@ static const struct ethtool_ops ethtool_ops = {
 	.get_channels   = netvsc_get_channels,
 	.set_channels   = netvsc_set_channels,
 	.get_ts_info	= ethtool_op_get_ts_info,
-	.get_rxnfc	= netvsc_get_rxnfc,
+	.get_rx_ring_count = netvsc_get_rx_ring_count,
 	.get_rxfh_key_size = netvsc_get_rxfh_key_size,
 	.get_rxfh_indir_size = netvsc_rss_indir_size,
 	.get_rxfh	= netvsc_get_rxfh,

drivers/net/ipvlan/ipvlan_core.c

@@ -52,8 +52,8 @@ static u8 ipvlan_get_v4_hash(const void *iaddr)
 {
 	const struct in_addr *ip4_addr = iaddr;
 
-	return jhash_1word(ip4_addr->s_addr, ipvlan_jhash_secret) &
-	       IPVLAN_HASH_MASK;
+	return jhash_1word((__force u32)ip4_addr->s_addr, ipvlan_jhash_secret) &
+			   IPVLAN_HASH_MASK;
 }
 
 static bool addr_equal(bool is_v6, struct ipvl_addr *addr, const void *iaddr)

net/ethernet/eth.c

@@ -154,9 +154,9 @@ EXPORT_SYMBOL(eth_get_headlen);
  */
 __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
 {
-	unsigned short _service_access_point;
 	const unsigned short *sap;
 	const struct ethhdr *eth;
+	__be16 res;
 
 	skb->dev = dev;
 	skb_reset_mac_header(skb);
@@ -181,15 +181,15 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
 	 *      the protocol design and runs IPX over 802.3 without an 802.2 LLC
 	 *      layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This
 	 *      won't work for fault tolerant netware but does for the rest.
+	 *	We use skb->dev as temporary storage to not hit
+	 *	CONFIG_STACKPROTECTOR_STRONG=y costs on some platforms.
 	 */
-	sap = skb_header_pointer(skb, 0, sizeof(*sap), &_service_access_point);
-	if (sap && *sap == 0xFFFF)
-		return htons(ETH_P_802_3);
+	sap = skb_header_pointer(skb, 0, sizeof(*sap), &skb->dev);
+	res = (sap && *sap == 0xFFFF) ? htons(ETH_P_802_3) : htons(ETH_P_802_2);
 
-	/*
-	 *      Real 802.2 LLC
-	 */
-	return htons(ETH_P_802_2);
+	/* restore skb->dev in case it was mangled by skb_header_pointer(). */
+	skb->dev = dev;
+	return res;
 }
 EXPORT_SYMBOL(eth_type_trans);
 

net/mptcp/protocol.c

@@ -2518,6 +2518,13 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 		subflow->lent_mem_frag = 0;
 	}
 
+	/* Do not pass RX data to the msk, even if the subflow socket is not
+	 * going to be freed (i.e. even for the first subflow on graceful
+	 * subflow close.
+	 */
+	lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
+	subflow->closing = 1;
+
 	/* If the first subflow moved to a close state before accept, e.g. due
 	 * to an incoming reset or listener shutdown, the subflow socket is
 	 * already deleted by inet_child_forget() and the mptcp socket can't

tools/testing/selftests/drivers/net/hw/Makefile

@@ -1,8 +1,20 @@
 # SPDX-License-Identifier: GPL-2.0+ OR MIT
 
+# Check if io_uring supports zero-copy receive
+HAS_IOURING_ZCRX := $(shell \
+	echo -e '#include <liburing.h>\n' \
+	     'void *func = (void *)io_uring_register_ifq;\n' \
+	     'int main() {return 0;}' | \
+	$(CC) -luring -x c - -o /dev/null 2>&1 && echo y)
+
+ifeq ($(HAS_IOURING_ZCRX),y)
+COND_GEN_FILES += iou-zcrx
+else
+$(warning excluding iouring tests, liburing not installed or too old)
+endif
+
 TEST_GEN_FILES := \
-	iou-zcrx \
-	toeplitz \
+	$(COND_GEN_FILES) \
 # end of TEST_GEN_FILES
 
 TEST_PROGS = \
@@ -42,7 +54,10 @@ TEST_INCLUDES := \
 	#
 
 # YNL files, must be before "include ..lib.mk"
-YNL_GEN_FILES := ncdevmem
+YNL_GEN_FILES := \
+	ncdevmem \
+	toeplitz \
+# end of YNL_GEN_FILES
 TEST_GEN_FILES += $(YNL_GEN_FILES)
 TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c))
 
@@ -58,4 +73,6 @@ include ../../../net/ynl.mk
 
 include ../../../net/bpf.mk
 
+ifeq ($(HAS_IOURING_ZCRX),y)
 $(OUTPUT)/iou-zcrx: LDLIBS += -luring
+endif

tools/testing/selftests/drivers/net/hw/toeplitz.c

@@ -52,6 +52,9 @@
 #include <sys/types.h>
 #include <unistd.h>
 
+#include <ynl.h>
+#include "ethtool-user.h"
+
 #include "../../../kselftest.h"
 #include "../../../net/lib/ksft.h"
 
@@ -65,6 +68,7 @@
 #define FOUR_TUPLE_MAX_LEN	((sizeof(struct in6_addr) * 2) + (sizeof(uint16_t) * 2))
 
 #define RSS_MAX_CPUS (1 << 16)	/* real constraint is PACKET_FANOUT_MAX */
+#define RSS_MAX_INDIR	(1 << 16)
 
 #define RPS_MAX_CPUS 16UL	/* must be a power of 2 */
 
@@ -102,6 +106,8 @@ struct ring_state {
 static unsigned int rx_irq_cpus[RSS_MAX_CPUS];	/* map from rxq to cpu */
 static int rps_silo_to_cpu[RPS_MAX_CPUS];
 static unsigned char toeplitz_key[TOEPLITZ_KEY_MAX_LEN];
+static unsigned int rss_indir_tbl[RSS_MAX_INDIR];
+static unsigned int rss_indir_tbl_size;
 static struct ring_state rings[RSS_MAX_CPUS];
 
 static inline uint32_t toeplitz(const unsigned char *four_tuple,
@@ -130,7 +136,12 @@ static inline uint32_t toeplitz(const unsigned char *four_tuple,
 /* Compare computed cpu with arrival cpu from packet_fanout_cpu */
 static void verify_rss(uint32_t rx_hash, int cpu)
 {
-	int queue = rx_hash % cfg_num_queues;
+	int queue;
+
+	if (rss_indir_tbl_size)
+		queue = rss_indir_tbl[rx_hash % rss_indir_tbl_size];
+	else
+		queue = rx_hash % cfg_num_queues;
 
 	log_verbose(" rxq %d (cpu %d)", queue, rx_irq_cpus[queue]);
 	if (rx_irq_cpus[queue] != cpu) {
@@ -483,6 +494,56 @@ static void parse_rps_bitmap(const char *arg)
 			rps_silo_to_cpu[cfg_num_rps_cpus++] = i;
 }
 
+static void read_rss_dev_info_ynl(void)
+{
+	struct ethtool_rss_get_req *req;
+	struct ethtool_rss_get_rsp *rsp;
+	struct ynl_sock *ys;
+
+	ys = ynl_sock_create(&ynl_ethtool_family, NULL);
+	if (!ys)
+		error(1, errno, "ynl_sock_create failed");
+
+	req = ethtool_rss_get_req_alloc();
+	if (!req)
+		error(1, errno, "ethtool_rss_get_req_alloc failed");
+
+	ethtool_rss_get_req_set_header_dev_name(req, cfg_ifname);
+
+	rsp = ethtool_rss_get(ys, req);
+	if (!rsp)
+		error(1, ys->err.code, "YNL: %s", ys->err.msg);
+
+	if (!rsp->_len.hkey)
+		error(1, 0, "RSS key not available for %s", cfg_ifname);
+
+	if (rsp->_len.hkey < TOEPLITZ_KEY_MIN_LEN ||
+	    rsp->_len.hkey > TOEPLITZ_KEY_MAX_LEN)
+		error(1, 0, "RSS key length %u out of bounds [%u, %u]",
+		      rsp->_len.hkey, TOEPLITZ_KEY_MIN_LEN,
+		      TOEPLITZ_KEY_MAX_LEN);
+
+	memcpy(toeplitz_key, rsp->hkey, rsp->_len.hkey);
+
+	if (rsp->_count.indir > RSS_MAX_INDIR)
+		error(1, 0, "RSS indirection table too large (%u > %u)",
+		      rsp->_count.indir, RSS_MAX_INDIR);
+
+	/* If indir table not available we'll fallback to simple modulo math */
+	if (rsp->_count.indir) {
+		memcpy(rss_indir_tbl, rsp->indir,
+		       rsp->_count.indir * sizeof(rss_indir_tbl[0]));
+		rss_indir_tbl_size = rsp->_count.indir;
+
+		log_verbose("RSS indirection table size: %u\n",
+			    rss_indir_tbl_size);
+	}
+
+	ethtool_rss_get_rsp_free(rsp);
+	ethtool_rss_get_req_free(req);
+	ynl_sock_destroy(ys);
+}
+
 static void parse_opts(int argc, char **argv)
 {
 	static struct option long_options[] = {
@@ -551,7 +612,7 @@ static void parse_opts(int argc, char **argv)
 	}
 
 	if (!have_toeplitz)
-		error(1, 0, "Must supply rss key ('-k')");
+		read_rss_dev_info_ynl();
 
 	num_cpus = get_nprocs();
 	if (num_cpus > RSS_MAX_CPUS)

tools/testing/selftests/drivers/net/hw/toeplitz.py

@@ -17,6 +17,9 @@
 from lib.py import ksft_in
 from lib.py import ksft_variants, KsftNamedVariant, KsftSkipEx, KsftFailEx
 
+# "define" for the ID of the Toeplitz hash function
+ETH_RSS_HASH_TOP = 1
+
 
 def _check_rps_and_rfs_not_configured(cfg):
     """Verify that RPS is not already configured."""
@@ -34,16 +37,6 @@ def _check_rps_and_rfs_not_configured(cfg):
             raise KsftSkipEx(f"RFS already configured {rfs_file}: {val}")
 
 
-def _get_rss_key(cfg):
-    """
-    Read the RSS key from the device.
-    Return a string in the traditional %02x:%02x:%02x:.. format.
-    """
-
-    rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
-    return ':'.join(f'{b:02x}' for b in rss["hkey"])
-
-
 def _get_cpu_for_irq(irq):
     with open(f"/proc/irq/{irq}/smp_affinity_list", "r",
               encoding="utf-8") as fp:
@@ -153,8 +146,18 @@ def test(cfg, proto_flag, ipver, grp):
     # Check that rxhash is enabled
     ksft_in("receive-hashing: on", cmd(f"ethtool -k {cfg.ifname}").stdout)
 
+    rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    # Make sure NIC is configured to use Toeplitz hash, and no key xfrm.
+    if rss.get('hfunc') != ETH_RSS_HASH_TOP or rss.get('input-xfrm'):
+        cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                           "hfunc": ETH_RSS_HASH_TOP,
+                           "input-xfrm": {}})
+        defer(cfg.ethnl.rss_set, {"header": {"dev-index": cfg.ifindex},
+                                  "hfunc": rss.get('hfunc'),
+                                  "input-xfrm": rss.get('input-xfrm', {})
+                                  })
+
     port = rand_port(socket.SOCK_DGRAM)
-    key = _get_rss_key(cfg)
 
     toeplitz_path = cfg.test_dir / "toeplitz"
     rx_cmd = [
@@ -163,8 +166,7 @@ def test(cfg, proto_flag, ipver, grp):
         proto_flag,
         "-d", str(port),
         "-i", cfg.ifname,
-        "-k", key,
-        "-T", "1000",
+        "-T", "4000",
         "-s",
         "-v"
     ]