Merge tag 'net-6.11-rc0' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from netfilter.

  Notably this includes fixes for a s390 build breakage.

  Current release - new code bugs:

   - eth: fbnic: fix s390 build

   - eth: airoha: fix NULL pointer dereference in
     airoha_qdma_cleanup_rx_queue()

  Previous releases - regressions:

   - flow_dissector: use DEBUG_NET_WARN_ON_ONCE

   - ipv4: fix incorrect TOS in route get reply

   - dsa: fix chip-wide frame size config in some drivers

  Previous releases - always broken:

   - netfilter: nf_set_pipapo: fix initial map fill

   - eth: gve: fix XDP TX completion handling when counters overflow"

* tag 'net-6.11-rc0' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net:
  eth: fbnic: don't build the driver when skb has more than 21 frags
  net: dsa: b53: Limit chip-wide jumbo frame config to CPU ports
  net: dsa: mv88e6xxx: Limit chip-wide frame size config to CPU ports
  net: airoha: Fix NULL pointer dereference in airoha_qdma_cleanup_rx_queue()
  net: wwan: t7xx: add support for Dell DW5933e
  ipv4: Fix incorrect TOS in fibmatch route get reply
  ipv4: Fix incorrect TOS in route get reply
  net: flow_dissector: use DEBUG_NET_WARN_ON_ONCE
  driver core: auxiliary bus: Fix documentation of auxiliary_device
  net: airoha: fix error branch in airoha_dev_xmit and airoha_set_gdm_ports
  gve: Fix XDP TX completion handling when counters overflow
  ipvs: properly dereference pe in ip_vs_add_service
  selftests: netfilter: add test case for recent mismatch bug
  netfilter: nf_set_pipapo: fix initial map fill
  netfilter: ctnetlink: use helper function to calculate expect ID
  eth: fbnic: fix s390 build.

drivers/net/dsa/b53/b53_common.c

@@ -2256,6 +2256,9 @@ static int b53_change_mtu(struct dsa_switch *ds, int port, int mtu)
 	if (is5325(dev) || is5365(dev))
 		return -EOPNOTSUPP;
 
+	if (!dsa_is_cpu_port(ds, port))
+		return 0;
+
 	enable_jumbo = (mtu >= JMS_MIN_SIZE);
 	allow_10_100 = (dev->chip_id == BCM583XX_DEVICE_ID);
 

drivers/net/dsa/mv88e6xxx/chip.c

@@ -3626,7 +3626,8 @@ static int mv88e6xxx_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
 	mv88e6xxx_reg_lock(chip);
 	if (chip->info->ops->port_set_jumbo_size)
 		ret = chip->info->ops->port_set_jumbo_size(chip, port, new_mtu);
-	else if (chip->info->ops->set_max_frame_size)
+	else if (chip->info->ops->set_max_frame_size &&
+		 dsa_is_cpu_port(ds, port))
 		ret = chip->info->ops->set_max_frame_size(chip, new_mtu);
 	mv88e6xxx_reg_unlock(chip);
 

drivers/net/ethernet/google/gve/gve_tx.c

@@ -158,15 +158,16 @@ static int gve_clean_xdp_done(struct gve_priv *priv, struct gve_tx_ring *tx,
 			      u32 to_do)
 {
 	struct gve_tx_buffer_state *info;
-	u32 clean_end = tx->done + to_do;
 	u64 pkts = 0, bytes = 0;
 	size_t space_freed = 0;
 	u32 xsk_complete = 0;
 	u32 idx;
+	int i;
 
-	for (; tx->done < clean_end; tx->done++) {
+	for (i = 0; i < to_do; i++) {
 		idx = tx->done & tx->mask;
 		info = &tx->info[idx];
+		tx->done++;
 
 		if (unlikely(!info->xdp.size))
 			continue;

drivers/net/ethernet/mediatek/airoha_eth.c

@@ -977,7 +977,7 @@ static int airoha_set_gdm_ports(struct airoha_eth *eth, bool enable)
 	return 0;
 
 error:
-	for (i--; i >= 0; i++)
+	for (i--; i >= 0; i--)
 		airoha_set_gdm_port(eth, port_list[i], false);
 
 	return err;
@@ -1585,7 +1585,6 @@ static int airoha_qdma_init_rx_queue(struct airoha_eth *eth,
 
 static void airoha_qdma_cleanup_rx_queue(struct airoha_queue *q)
 {
-	enum dma_data_direction dir = page_pool_get_dma_dir(q->page_pool);
 	struct airoha_eth *eth = q->eth;
 
 	while (q->queued) {
@@ -1593,7 +1592,7 @@ static void airoha_qdma_cleanup_rx_queue(struct airoha_queue *q)
 		struct page *page = virt_to_head_page(e->buf);
 
 		dma_sync_single_for_cpu(eth->dev, e->dma_addr, e->dma_len,
-					dir);
+					page_pool_get_dma_dir(q->page_pool));
 		page_pool_put_full_page(q->page_pool, page, false);
 		q->tail = (q->tail + 1) % q->ndesc;
 		q->queued--;
@@ -2431,9 +2430,11 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 
 error_unmap:
-	for (i--; i >= 0; i++)
-		dma_unmap_single(dev->dev.parent, q->entry[i].dma_addr,
-				 q->entry[i].dma_len, DMA_TO_DEVICE);
+	for (i--; i >= 0; i--) {
+		index = (q->head + i) % q->ndesc;
+		dma_unmap_single(dev->dev.parent, q->entry[index].dma_addr,
+				 q->entry[index].dma_len, DMA_TO_DEVICE);
+	}
 
 	spin_unlock_bh(&q->lock);
 error:

drivers/net/ethernet/meta/Kconfig

@@ -20,6 +20,8 @@ if NET_VENDOR_META
 config FBNIC
 	tristate "Meta Platforms Host Network Interface"
 	depends on X86_64 || COMPILE_TEST
+	depends on S390=n
+	depends on MAX_SKB_FRAGS < 22
 	depends on PCI_MSI
 	select PHYLINK
 	help

drivers/net/wwan/t7xx/t7xx_pci.c

@@ -852,6 +852,7 @@ static void t7xx_pci_remove(struct pci_dev *pdev)
 
 static const struct pci_device_id t7xx_pci_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x4d75) },
+	{ PCI_DEVICE(0x14c0, 0x4d75) }, // Dell DW5933e
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, t7xx_pci_table);

include/linux/auxiliary_bus.h

@@ -58,9 +58,10 @@
  *       in
  * @name: Match name found by the auxiliary device driver,
  * @id: unique identitier if multiple devices of the same name are exported,
- * @irqs: irqs xarray contains irq indices which are used by the device,
- * @lock: Synchronize irq sysfs creation,
- * @irq_dir_exists: whether "irqs" directory exists,
+ * @sysfs: embedded struct which hold all sysfs related fields,
+ * @sysfs.irqs: irqs xarray contains irq indices which are used by the device,
+ * @sysfs.lock: Synchronize irq sysfs creation,
+ * @sysfs.irq_dir_exists: whether "irqs" directory exists,
  *
  * An auxiliary_device represents a part of its parent device's functionality.
  * It is given a name that, combined with the registering drivers

include/net/ip_fib.h

@@ -173,6 +173,7 @@ struct fib_result {
 	unsigned char		type;
 	unsigned char		scope;
 	u32			tclassid;
+	dscp_t			dscp;
 	struct fib_nh_common	*nhc;
 	struct fib_info		*fi;
 	struct fib_table	*table;

net/core/flow_dissector.c

@@ -1117,7 +1117,7 @@ bool __skb_flow_dissect(const struct net *net,
 		}
 	}
 
-	WARN_ON_ONCE(!net);
+	DEBUG_NET_WARN_ON_ONCE(!net);
 	if (net) {
 		enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR;
 		struct bpf_prog_array *run_array;

net/ipv4/fib_trie.c

@@ -1629,6 +1629,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
 			res->nhc = nhc;
 			res->type = fa->fa_type;
 			res->scope = fi->fib_scope;
+			res->dscp = fa->fa_dscp;
 			res->fi = fi;
 			res->table = tb;
 			res->fa_head = &n->leaf;

net/ipv4/route.c

@@ -2867,9 +2867,9 @@ EXPORT_SYMBOL_GPL(ip_route_output_flow);
 
 /* called with rcu_read_lock held */
 static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
-			struct rtable *rt, u32 table_id, struct flowi4 *fl4,
-			struct sk_buff *skb, u32 portid, u32 seq,
-			unsigned int flags)
+			struct rtable *rt, u32 table_id, dscp_t dscp,
+			struct flowi4 *fl4, struct sk_buff *skb, u32 portid,
+			u32 seq, unsigned int flags)
 {
 	struct rtmsg *r;
 	struct nlmsghdr *nlh;
@@ -2885,7 +2885,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
 	r->rtm_family	 = AF_INET;
 	r->rtm_dst_len	= 32;
 	r->rtm_src_len	= 0;
-	r->rtm_tos	= fl4 ? fl4->flowi4_tos : 0;
+	r->rtm_tos	= inet_dscp_to_dsfield(dscp);
 	r->rtm_table	= table_id < 256 ? table_id : RT_TABLE_COMPAT;
 	if (nla_put_u32(skb, RTA_TABLE, table_id))
 		goto nla_put_failure;
@@ -3035,7 +3035,7 @@ static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb,
 				goto next;
 
 			err = rt_fill_info(net, fnhe->fnhe_daddr, 0, rt,
-					   table_id, NULL, skb,
+					   table_id, 0, NULL, skb,
 					   NETLINK_CB(cb->skb).portid,
 					   cb->nlh->nlmsg_seq, flags);
 			if (err)
@@ -3331,7 +3331,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		fri.tb_id = table_id;
 		fri.dst = res.prefix;
 		fri.dst_len = res.prefixlen;
-		fri.dscp = inet_dsfield_to_dscp(fl4.flowi4_tos);
+		fri.dscp = res.dscp;
 		fri.type = rt->rt_type;
 		fri.offload = 0;
 		fri.trap = 0;
@@ -3358,8 +3358,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		err = fib_dump_info(skb, NETLINK_CB(in_skb).portid,
 				    nlh->nlmsg_seq, RTM_NEWROUTE, &fri, 0);
 	} else {
-		err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb,
-				   NETLINK_CB(in_skb).portid,
+		err = rt_fill_info(net, dst, src, rt, table_id, res.dscp, &fl4,
+				   skb, NETLINK_CB(in_skb).portid,
 				   nlh->nlmsg_seq, 0);
 	}
 	if (err < 0)

net/netfilter/ipvs/ip_vs_ctl.c

@@ -1459,18 +1459,18 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u,
 	if (ret < 0)
 		goto out_err;
 
-	/* Bind the ct retriever */
-	RCU_INIT_POINTER(svc->pe, pe);
-	pe = NULL;
-
 	/* Update the virtual service counters */
 	if (svc->port == FTPPORT)
 		atomic_inc(&ipvs->ftpsvc_counter);
 	else if (svc->port == 0)
 		atomic_inc(&ipvs->nullsvc_counter);
-	if (svc->pe && svc->pe->conn_out)
+	if (pe && pe->conn_out)
 		atomic_inc(&ipvs->conn_out_counter);
 
+	/* Bind the ct retriever */
+	RCU_INIT_POINTER(svc->pe, pe);
+	pe = NULL;
+
 	/* Count only IPv4 services for old get/setsockopt interface */
 	if (svc->af == AF_INET)
 		ipvs->num_services++;

net/netfilter/nf_conntrack_netlink.c

@@ -3420,7 +3420,8 @@ static int ctnetlink_del_expect(struct sk_buff *skb,
 
 		if (cda[CTA_EXPECT_ID]) {
 			__be32 id = nla_get_be32(cda[CTA_EXPECT_ID]);
-			if (ntohl(id) != (u32)(unsigned long)exp) {
+
+			if (id != nf_expect_get_id(exp)) {
 				nf_ct_expect_put(exp);
 				return -ENOENT;
 			}

net/netfilter/nft_set_pipapo.c

@@ -434,7 +434,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 	res_map  = scratch->map + (map_index ? m->bsize_max : 0);
 	fill_map = scratch->map + (map_index ? 0 : m->bsize_max);
 
-	memset(res_map, 0xff, m->bsize_max * sizeof(*res_map));
+	pipapo_resmap_init(m, res_map);
 
 	nft_pipapo_for_each_field(f, i, m) {
 		bool last = i == m->field_count - 1;
@@ -542,7 +542,7 @@ static struct nft_pipapo_elem *pipapo_get(const struct net *net,
 		goto out;
 	}
 
-	memset(res_map, 0xff, m->bsize_max * sizeof(*res_map));
+	pipapo_resmap_init(m, res_map);
 
 	nft_pipapo_for_each_field(f, i, m) {
 		bool last = i == m->field_count - 1;

net/netfilter/nft_set_pipapo.h

@@ -278,4 +278,25 @@ static u64 pipapo_estimate_size(const struct nft_set_desc *desc)
 	return size;
 }
 
+/**
+ * pipapo_resmap_init() - Initialise result map before first use
+ * @m:		Matching data, including mapping table
+ * @res_map:	Result map
+ *
+ * Initialize all bits covered by the first field to one, so that after
+ * the first step, only the matching bits of the first bit group remain.
+ *
+ * If other fields have a large bitmap, set remainder of res_map to 0.
+ */
+static inline void pipapo_resmap_init(const struct nft_pipapo_match *m, unsigned long *res_map)
+{
+	const struct nft_pipapo_field *f = m->f;
+	int i;
+
+	for (i = 0; i < f->bsize; i++)
+		res_map[i] = ULONG_MAX;
+
+	for (i = f->bsize; i < m->bsize_max; i++)
+		res_map[i] = 0ul;
+}
 #endif /* _NFT_SET_PIPAPO_H */

net/netfilter/nft_set_pipapo_avx2.c

@@ -1036,6 +1036,7 @@ static int nft_pipapo_avx2_lookup_8b_16(unsigned long *map, unsigned long *fill,
 
 /**
  * nft_pipapo_avx2_lookup_slow() - Fallback function for uncommon field sizes
+ * @mdata:	Matching data, including mapping table
  * @map:	Previous match result, used as initial bitmap
  * @fill:	Destination bitmap to be filled with current match result
  * @f:		Field, containing lookup and mapping tables
@@ -1051,7 +1052,8 @@ static int nft_pipapo_avx2_lookup_8b_16(unsigned long *map, unsigned long *fill,
  * Return: -1 on no match, rule index of match if @last, otherwise first long
  * word index to be checked next (i.e. first filled word).
  */
-static int nft_pipapo_avx2_lookup_slow(unsigned long *map, unsigned long *fill,
+static int nft_pipapo_avx2_lookup_slow(const struct nft_pipapo_match *mdata,
+					unsigned long *map, unsigned long *fill,
 					const struct nft_pipapo_field *f,
 					int offset, const u8 *pkt,
 					bool first, bool last)
@@ -1060,7 +1062,7 @@ static int nft_pipapo_avx2_lookup_slow(unsigned long *map, unsigned long *fill,
 	int i, ret = -1, b;
 
 	if (first)
-		memset(map, 0xff, bsize * sizeof(*map));
+		pipapo_resmap_init(mdata, map);
 
 	for (i = offset; i < bsize; i++) {
 		if (f->bb == 8)
@@ -1186,7 +1188,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 			} else if (f->groups == 16) {
 				NFT_SET_PIPAPO_AVX2_LOOKUP(8, 16);
 			} else {
-				ret = nft_pipapo_avx2_lookup_slow(res, fill, f,
+				ret = nft_pipapo_avx2_lookup_slow(m, res, fill, f,
 								  ret, rp,
 								  first, last);
 			}
@@ -1202,7 +1204,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 			} else if (f->groups == 32) {
 				NFT_SET_PIPAPO_AVX2_LOOKUP(4, 32);
 			} else {
-				ret = nft_pipapo_avx2_lookup_slow(res, fill, f,
+				ret = nft_pipapo_avx2_lookup_slow(m, res, fill, f,
 								  ret, rp,
 								  first, last);
 			}

tools/testing/selftests/net/fib_tests.sh

@@ -1737,53 +1737,53 @@ ipv4_rt_dsfield()
 
 	# DSCP 0x10 should match the specific route, no matter the ECN bits
 	$IP route get fibmatch 172.16.102.1 dsfield 0x10 | \
-		grep -q "via 172.16.103.2"
+		grep -q "172.16.102.0/24 tos 0x10 via 172.16.103.2"
 	log_test $? 0 "IPv4 route with DSCP and ECN:Not-ECT"
 
 	$IP route get fibmatch 172.16.102.1 dsfield 0x11 | \
-		grep -q "via 172.16.103.2"
+		grep -q "172.16.102.0/24 tos 0x10 via 172.16.103.2"
 	log_test $? 0 "IPv4 route with DSCP and ECN:ECT(1)"
 
 	$IP route get fibmatch 172.16.102.1 dsfield 0x12 | \
-		grep -q "via 172.16.103.2"
+		grep -q "172.16.102.0/24 tos 0x10 via 172.16.103.2"
 	log_test $? 0 "IPv4 route with DSCP and ECN:ECT(0)"
 
 	$IP route get fibmatch 172.16.102.1 dsfield 0x13 | \
-		grep -q "via 172.16.103.2"
+		grep -q "172.16.102.0/24 tos 0x10 via 172.16.103.2"
 	log_test $? 0 "IPv4 route with DSCP and ECN:CE"
 
 	# Unknown DSCP should match the generic route, no matter the ECN bits
 	$IP route get fibmatch 172.16.102.1 dsfield 0x14 | \
-		grep -q "via 172.16.101.2"
+		grep -q "172.16.102.0/24 via 172.16.101.2"
 	log_test $? 0 "IPv4 route with unknown DSCP and ECN:Not-ECT"
 
 	$IP route get fibmatch 172.16.102.1 dsfield 0x15 | \
-		grep -q "via 172.16.101.2"
+		grep -q "172.16.102.0/24 via 172.16.101.2"
 	log_test $? 0 "IPv4 route with unknown DSCP and ECN:ECT(1)"
 
 	$IP route get fibmatch 172.16.102.1 dsfield 0x16 | \
-		grep -q "via 172.16.101.2"
+		grep -q "172.16.102.0/24 via 172.16.101.2"
 	log_test $? 0 "IPv4 route with unknown DSCP and ECN:ECT(0)"
 
 	$IP route get fibmatch 172.16.102.1 dsfield 0x17 | \
-		grep -q "via 172.16.101.2"
+		grep -q "172.16.102.0/24 via 172.16.101.2"
 	log_test $? 0 "IPv4 route with unknown DSCP and ECN:CE"
 
 	# Null DSCP should match the generic route, no matter the ECN bits
 	$IP route get fibmatch 172.16.102.1 dsfield 0x00 | \
-		grep -q "via 172.16.101.2"
+		grep -q "172.16.102.0/24 via 172.16.101.2"
 	log_test $? 0 "IPv4 route with no DSCP and ECN:Not-ECT"
 
 	$IP route get fibmatch 172.16.102.1 dsfield 0x01 | \
-		grep -q "via 172.16.101.2"
+		grep -q "172.16.102.0/24 via 172.16.101.2"
 	log_test $? 0 "IPv4 route with no DSCP and ECN:ECT(1)"
 
 	$IP route get fibmatch 172.16.102.1 dsfield 0x02 | \
-		grep -q "via 172.16.101.2"
+		grep -q "172.16.102.0/24 via 172.16.101.2"
 	log_test $? 0 "IPv4 route with no DSCP and ECN:ECT(0)"
 
 	$IP route get fibmatch 172.16.102.1 dsfield 0x03 | \
-		grep -q "via 172.16.101.2"
+		grep -q "172.16.102.0/24 via 172.16.101.2"
 	log_test $? 0 "IPv4 route with no DSCP and ECN:CE"
 }
 

tools/testing/selftests/net/netfilter/nft_concat_range.sh

@@ -27,7 +27,7 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto
        net6_port_net6_port net_port_mac_proto_net"
 
 # Reported bugs, also described by TYPE_ variables below
-BUGS="flush_remove_add reload"
+BUGS="flush_remove_add reload net_port_proto_match"
 
 # List of possible paths to pktgen script from kernel tree for performance tests
 PKTGEN_SCRIPT_PATHS="
@@ -371,6 +371,22 @@ race_repeat	0
 perf_duration	0
 "
 
+TYPE_net_port_proto_match="
+display		net,port,proto
+type_spec	ipv4_addr . inet_service . inet_proto
+chain_spec	ip daddr . udp dport . meta l4proto
+dst		addr4 port proto
+src
+start		1
+count		9
+src_delta	9
+tools		sendip bash
+proto		udp
+
+race_repeat	0
+
+perf_duration	0
+"
 # Set template for all tests, types and rules are filled in depending on test
 set_template='
 flush ruleset
@@ -1555,6 +1571,64 @@ test_bug_reload() {
 	nft flush ruleset
 }
 
+# - add ranged element, check that packets match it
+# - delete element again, check it is gone
+test_bug_net_port_proto_match() {
+	setup veth send_"${proto}" set || return ${ksft_skip}
+	rstart=${start}
+
+	range_size=1
+	for i in $(seq 1 10); do
+		for j in $(seq 1 20) ; do
+			elem=$(printf "10.%d.%d.0/24 . %d1-%d0 . 6-17 " ${i} ${j} ${i} "$((i+1))")
+
+			nft "add element inet filter test { $elem }" || return 1
+			nft "get element inet filter test { $elem }" | grep -q "$elem"
+			if [ $? -ne 0 ];then
+				local got=$(nft "get element inet filter test { $elem }")
+				err "post-add: should have returned $elem but got $got"
+				return 1
+			fi
+		done
+	done
+
+	# recheck after set was filled
+	for i in $(seq 1 10); do
+		for j in $(seq 1 20) ; do
+			elem=$(printf "10.%d.%d.0/24 . %d1-%d0 . 6-17 " ${i} ${j} ${i} "$((i+1))")
+
+			nft "get element inet filter test { $elem }" | grep -q "$elem"
+			if [ $? -ne 0 ];then
+				local got=$(nft "get element inet filter test { $elem }")
+				err "post-fill: should have returned $elem but got $got"
+				return 1
+			fi
+		done
+	done
+
+	# random del and re-fetch
+	for i in $(seq 1 10); do
+		for j in $(seq 1 20) ; do
+			local rnd=$((RANDOM%10))
+			local got=""
+
+			elem=$(printf "10.%d.%d.0/24 . %d1-%d0 . 6-17 " ${i} ${j} ${i} "$((i+1))")
+			if [ $rnd -gt 0 ];then
+				continue
+			fi
+
+			nft "delete element inet filter test { $elem }"
+			got=$(nft "get element inet filter test { $elem }" 2>/dev/null)
+			if [ $? -eq 0 ];then
+				err "post-delete: query for $elem returned $got instead of error."
+				return 1
+			fi
+		done
+	done
+
+	nft flush ruleset
+}
+
 test_reported_issues() {
 	eval test_bug_"${subtest}"
 }