Merge tag 'net-6.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
"Including fixes from wireless and netfilter.

The notable fixes here are the EEE fix which restores boot for many
embedded platforms (real and QEMU); WiFi warning suppression and the
ICE Kconfig cleanup.

Current release - regressions:

- phy: multiple fixes for EEE rework

- wifi: wext: warn about usage only once

- wifi: ath11k: allow system suspend to survive ath11k

Current release - new code bugs:

- mlx5: Fix memory leak in IPsec RoCE creation

- ibmvnic: assign XPS map to correct queue index

Previous releases - regressions:

- netfilter: ip6t_rpfilter: Fix regression with VRF interfaces

- netfilter: ctnetlink: make event listener tracking global

- nf_tables: allow to fetch set elements when table has an owner

- mlx5:
- fix skb leak while fifo resync and push
- fix possible ptp queue fifo use-after-free

Previous releases - always broken:

- sched: fix action bind logic

- ptp: vclock: use mutex to fix "sleep on atomic" bug if driver also
uses a mutex

- netfilter: conntrack: fix rmmod double-free race

- netfilter: xt_length: use skb len to match in length_mt6, avoid
issues with BIG TCP

Misc:

- ice: remove unnecessary CONFIG_ICE_GNSS

- mlx5e: remove hairpin write debugfs files

- sched: act_api: move TCA_EXT_WARN_MSG to the correct hierarchy"

* tag 'net-6.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (53 commits)
tcp: tcp_check_req() can be called from process context
net: phy: c45: fix network interface initialization failures on xtensa, arm:cubieboard
xen-netback: remove unused variables pending_idx and index
net/sched: act_api: move TCA_EXT_WARN_MSG to the correct hierarchy
net: dsa: ocelot_ext: remove unnecessary phylink.h include
net: mscc: ocelot: fix duplicate driver name error
net: dsa: felix: fix internal MDIO controller resource length
net: dsa: seville: ignore mscc-miim read errors from Lynx PCS
net/sched: act_sample: fix action bind logic
net/sched: act_mpls: fix action bind logic
net/sched: act_pedit: fix action bind logic
wifi: wext: warn about usage only once
wifi: mt76: usb: fix use-after-free in mt76u_free_rx_queue
qede: avoid uninitialized entries in coal_entry array
nfc: fix memory leak of se_io context in nfc_genl_se_io
ice: remove unnecessary CONFIG_ICE_GNSS
net/sched: cls_api: Move call to tcf_exts_miss_cookie_base_destroy()
ibmvnic: Assign XPS map to correct queue index
docs: net: fix inaccuracies in msg_zerocopy.rst
tools: net: add __pycache__ to gitignore
...

Documentation/netlink/specs/netdev.yaml

···
       -
         name: hw-offload
         doc:
-         This feature informs if netdev supports XDP hw oflloading.
+         This feature informs if netdev supports XDP hw offloading.
       -
         name: rx-sg
         doc:

Documentation/networking/msg_zerocopy.rst

···
 
 Copying large buffers between user process and kernel can be
 expensive. Linux supports various interfaces that eschew copying,
-such as sendpage and splice. The MSG_ZEROCOPY flag extends the
+such as sendfile and splice. The MSG_ZEROCOPY flag extends the
 underlying copy avoidance mechanism to common socket send calls.
 
 Copy avoidance is not a free lunch. As implemented, with page pinning,
···
 	ret = send(fd, buf, sizeof(buf), MSG_ZEROCOPY);
 
 A zerocopy failure will return -1 with errno ENOBUFS. This happens if
-the socket option was not set, the socket exceeds its optmem limit or
-the user exceeds its ulimit on locked pages.
+the socket exceeds its optmem limit or the user exceeds their ulimit on
+locked pages.
 
 
 Mixing copy avoidance and copying

drivers/mfd/ocelot-core.c

···
 		.num_resources = ARRAY_SIZE(vsc7512_miim1_resources),
 		.resources = vsc7512_miim1_resources,
 	}, {
-		.name = "ocelot-switch",
+		.name = "ocelot-ext-switch",
 		.of_compatible = "mscc,vsc7512-switch",
 		.num_resources = ARRAY_SIZE(vsc7512_switch_resources),
 		.resources = vsc7512_switch_resources,

drivers/net/dsa/ocelot/felix_vsc9959.c

···
  * SGMII/QSGMII MAC PCS can be found.
  */
 static const struct resource vsc9959_imdio_res =
-	DEFINE_RES_MEM_NAMED(0x8030, 0x8040, "imdio");
+	DEFINE_RES_MEM_NAMED(0x8030, 0x10, "imdio");
 
 static const struct reg_field vsc9959_regfields[REGFIELD_MAX] = {
 	[ANA_ADVLEARN_VLAN_CHK] = REG_FIELD(ANA_ADVLEARN, 6, 6),

drivers/net/dsa/ocelot/ocelot_ext.c

···
  */
 
 #include <linux/mfd/ocelot.h>
-#include <linux/phylink.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <soc/mscc/ocelot.h>
···
 
 static struct platform_driver ocelot_ext_switch_driver = {
 	.driver = {
-		.name = "ocelot-switch",
+		.name = "ocelot-ext-switch",
 		.of_match_table = of_match_ptr(ocelot_ext_switch_of_match),
 	},
 	.probe = ocelot_ext_probe,

drivers/net/dsa/ocelot/seville_vsc9953.c

···
 
 	rc = mscc_miim_setup(dev, &bus, "VSC9953 internal MDIO bus",
 			     ocelot->targets[GCB],
-			     ocelot->map[GCB][GCB_MIIM_MII_STATUS & REG_MASK]);
-
+			     ocelot->map[GCB][GCB_MIIM_MII_STATUS & REG_MASK],
+			     true);
 	if (rc) {
 		dev_err(dev, "failed to setup MDIO bus\n");
 		return rc;

drivers/net/ethernet/ibm/ibmvnic.c

···
 
 		rc = __netif_set_xps_queue(adapter->netdev,
 					   cpumask_bits(queue->affinity_mask),
-					   i, XPS_CPUS);
+					   i_txqs - 1, XPS_CPUS);
 		if (rc)
 			netdev_warn(adapter->netdev, "%s: Set XPS on queue %d failed, rc = %d.\n",
-				    __func__, i, rc);
+				    __func__, i_txqs - 1, rc);
 	}
 
 out:

drivers/net/ethernet/intel/Kconfig

···
 	default n
 	depends on PCI_MSI
 	depends on PTP_1588_CLOCK_OPTIONAL
+	depends on GNSS || GNSS = n
 	select AUXILIARY_BUS
 	select DIMLIB
 	select NET_DEVLINK
···
 	  with PCIe PTM support. The cross-timestamp is available through
 	  the PTP clock driver precise cross-timestamp ioctl
 	  (PTP_SYS_OFFSET_PRECISE).
-
-config ICE_GNSS
-	def_bool GNSS = y || GNSS = ICE
 
 config FM10K
 	tristate "Intel(R) FM10000 Ethernet Switch Host Interface Support"

drivers/net/ethernet/intel/ice/Makefile

···
 ice-$(CONFIG_RFS_ACCEL) += ice_arfs.o
 ice-$(CONFIG_XDP_SOCKETS) += ice_xsk.o
 ice-$(CONFIG_ICE_SWITCHDEV) += ice_eswitch.o
-ice-$(CONFIG_ICE_GNSS) += ice_gnss.o
+ice-$(CONFIG_GNSS) += ice_gnss.o

drivers/net/ethernet/intel/ice/ice_gnss.h

···
 	struct list_head queue;
 };
 
-#if IS_ENABLED(CONFIG_ICE_GNSS)
+#if IS_ENABLED(CONFIG_GNSS)
 void ice_gnss_init(struct ice_pf *pf);
 void ice_gnss_exit(struct ice_pf *pf);
 bool ice_gnss_is_gps_present(struct ice_hw *hw);
···
 {
 	return false;
 }
-#endif /* IS_ENABLED(CONFIG_ICE_GNSS) */
+#endif /* IS_ENABLED(CONFIG_GNSS) */
 #endif /* _ICE_GNSS_H_ */

drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c

···
 
 		/* NPC profile doesn't extract AH/ESP header fields */
 		if ((ah_esp_mask->spi & ah_esp_hdr->spi) ||
-		    (ah_esp_mask->tclass & ah_esp_mask->tclass))
+		    (ah_esp_mask->tclass & ah_esp_hdr->tclass))
 			return -EOPNOTSUPP;
 
 		if (flow_type == AH_V6_FLOW)

drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c

···
 #include <net/tso.h>
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
+#include <net/ip6_checksum.h>
 
 #include "otx2_reg.h"
 #include "otx2_common.h"
···
 
 static void otx2_sqe_add_mem(struct otx2_snd_queue *sq, int *offset,
 			     int alg, u64 iova, int ptp_offset,
-			     u64 base_ns, int udp_csum)
+			     u64 base_ns, bool udp_csum_crt)
 {
 	struct nix_sqe_mem_s *mem;
 
···
 
 	if (ptp_offset) {
 		mem->start_offset = ptp_offset;
-		mem->udp_csum_crt = udp_csum;
+		mem->udp_csum_crt = !!udp_csum_crt;
 		mem->base_ns = base_ns;
 		mem->step_type = 1;
 	}
···
 	return false;
 }
 
-static bool otx2_ptp_is_sync(struct sk_buff *skb, int *offset, int *udp_csum)
+static bool otx2_ptp_is_sync(struct sk_buff *skb, int *offset, bool *udp_csum_crt)
 {
 	struct ethhdr *eth = (struct ethhdr *)(skb->data);
 	u16 nix_offload_hlen = 0, inner_vhlen = 0;
+	bool udp_hdr_present = false, is_sync;
 	u8 *data = skb->data, *msgtype;
 	__be16 proto = eth->h_proto;
 	int network_depth = 0;
···
 		if (!otx2_validate_network_transport(skb))
 			return false;
 
-		*udp_csum = 1;
 		*offset = nix_offload_hlen + skb_transport_offset(skb) +
 			  sizeof(struct udphdr);
+		udp_hdr_present = true;
+
 	}
 
 	msgtype = data + *offset;
-
 	/* Check PTP messageId is SYNC or not */
-	return (*msgtype & 0xf) == 0;
+	is_sync = !(*msgtype & 0xf);
+	if (is_sync)
+		*udp_csum_crt = udp_hdr_present;
+	else
+		*offset = 0;
+
+	return is_sync;
 }
 
 static void otx2_set_txtstamp(struct otx2_nic *pfvf, struct sk_buff *skb,
 			      struct otx2_snd_queue *sq, int *offset)
 {
+	struct ethhdr	*eth = (struct ethhdr *)(skb->data);
 	struct ptpv2_tstamp *origin_tstamp;
-	int ptp_offset = 0, udp_csum = 0;
+	bool udp_csum_crt = false;
+	unsigned int udphoff;
 	struct timespec64 ts;
+	int ptp_offset = 0;
+	__wsum skb_csum;
 	u64 iova;
 
 	if (unlikely(!skb_shinfo(skb)->gso_size &&
 		     (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) {
-		if (unlikely(pfvf->flags & OTX2_FLAG_PTP_ONESTEP_SYNC)) {
-			if (otx2_ptp_is_sync(skb, &ptp_offset, &udp_csum)) {
-				origin_tstamp = (struct ptpv2_tstamp *)
-						((u8 *)skb->data + ptp_offset +
-						 PTP_SYNC_SEC_OFFSET);
-				ts = ns_to_timespec64(pfvf->ptp->tstamp);
-				origin_tstamp->seconds_msb = htons((ts.tv_sec >> 32) & 0xffff);
-				origin_tstamp->seconds_lsb = htonl(ts.tv_sec & 0xffffffff);
-				origin_tstamp->nanoseconds = htonl(ts.tv_nsec);
-				/* Point to correction field in PTP packet */
-				ptp_offset += 8;
+		if (unlikely(pfvf->flags & OTX2_FLAG_PTP_ONESTEP_SYNC &&
+			     otx2_ptp_is_sync(skb, &ptp_offset, &udp_csum_crt))) {
+			origin_tstamp = (struct ptpv2_tstamp *)
+					((u8 *)skb->data + ptp_offset +
+					 PTP_SYNC_SEC_OFFSET);
+			ts = ns_to_timespec64(pfvf->ptp->tstamp);
+			origin_tstamp->seconds_msb = htons((ts.tv_sec >> 32) & 0xffff);
+			origin_tstamp->seconds_lsb = htonl(ts.tv_sec & 0xffffffff);
+			origin_tstamp->nanoseconds = htonl(ts.tv_nsec);
+			/* Point to correction field in PTP packet */
+			ptp_offset += 8;
+
+			/* When user disables hw checksum, stack calculates the csum,
+			 * but it does not cover ptp timestamp which is added later.
+			 * Recalculate the checksum manually considering the timestamp.
+			 */
+			if (udp_csum_crt) {
+				struct udphdr *uh = udp_hdr(skb);
+
+				if (skb->ip_summed != CHECKSUM_PARTIAL && uh->check != 0) {
+					udphoff = skb_transport_offset(skb);
+					uh->check = 0;
+					skb_csum = skb_checksum(skb, udphoff, skb->len - udphoff,
+								0);
+					if (ntohs(eth->h_proto) == ETH_P_IPV6)
+						uh->check = csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+									    &ipv6_hdr(skb)->daddr,
+									    skb->len - udphoff,
+									    ipv6_hdr(skb)->nexthdr,
+									    skb_csum);
+					else
+						uh->check = csum_tcpudp_magic(ip_hdr(skb)->saddr,
+									      ip_hdr(skb)->daddr,
+									      skb->len - udphoff,
+									      IPPROTO_UDP,
+									      skb_csum);
+				}
 			}
 		} else {
 			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 		}
 		iova = sq->timestamps->iova + (sq->head * sizeof(u64));
 		otx2_sqe_add_mem(sq, offset, NIX_SENDMEMALG_E_SETTSTMP, iova,
-				 ptp_offset, pfvf->ptp->base_ns, udp_csum);
+				 ptp_offset, pfvf->ptp->base_ns, udp_csum_crt);
 	} else {
 		skb_tx_timestamp(skb);
 	}

drivers/net/ethernet/mellanox/mlx5/core/ecpf.c

···
 	err = mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_HOST_PF]);
 	if (err)
 		mlx5_core_warn(dev, "Timeout reclaiming external host PF pages err(%d)\n", err);
+
+	err = mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_VF]);
+	if (err)
+		mlx5_core_warn(dev, "Timeout reclaiming external host VFs pages err(%d)\n", err);
 }

drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c

···
 	return (ptpsq->ts_cqe_ctr_mask && (skb_cc != skb_id));
 }
 
-static void mlx5e_ptp_skb_fifo_ts_cqe_resync(struct mlx5e_ptpsq *ptpsq, u16 skb_cc, u16 skb_id)
+static bool mlx5e_ptp_ts_cqe_ooo(struct mlx5e_ptpsq *ptpsq, u16 skb_id)
+{
+	u16 skb_cc = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_cc);
+	u16 skb_pc = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_pc);
+
+	if (PTP_WQE_CTR2IDX(skb_id - skb_cc) >= PTP_WQE_CTR2IDX(skb_pc - skb_cc))
+		return true;
+
+	return false;
+}
+
+static void mlx5e_ptp_skb_fifo_ts_cqe_resync(struct mlx5e_ptpsq *ptpsq, u16 skb_cc,
+					     u16 skb_id, int budget)
 {
 	struct skb_shared_hwtstamps hwts = {};
 	struct sk_buff *skb;
···
 		hwts.hwtstamp = mlx5e_skb_cb_get_hwts(skb)->cqe_hwtstamp;
 		skb_tstamp_tx(skb, &hwts);
 		ptpsq->cq_stats->resync_cqe++;
+		napi_consume_skb(skb, budget);
 		skb_cc = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_cc);
 	}
 }
···
 		goto out;
 	}
 
-	if (mlx5e_ptp_ts_cqe_drop(ptpsq, skb_cc, skb_id))
-		mlx5e_ptp_skb_fifo_ts_cqe_resync(ptpsq, skb_cc, skb_id);
+	if (mlx5e_ptp_ts_cqe_drop(ptpsq, skb_cc, skb_id)) {
+		if (mlx5e_ptp_ts_cqe_ooo(ptpsq, skb_id)) {
+			/* already handled by a previous resync */
+			ptpsq->cq_stats->ooo_cqe_drop++;
+			return;
+		}
+		mlx5e_ptp_skb_fifo_ts_cqe_resync(ptpsq, skb_cc, skb_id, budget);
+	}
 
 	skb = mlx5e_skb_fifo_pop(&ptpsq->skb_fifo);
 	hwtstamp = mlx5e_cqe_ts_to_ns(sq->ptp_cyc2time, sq->clock, get_cqe_ts(cqe));

drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c

···
 	else
 		napi_gro_receive(rq->cq.napi, skb);
 
-	if (tc_priv.fwd_dev)
-		dev_put(tc_priv.fwd_dev);
+	dev_put(tc_priv.fwd_dev);
 
 	return;
 

drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c

···
 	int err;
 
 	handle = kvzalloc(sizeof(*handle), GFP_KERNEL);
-	if (IS_ERR(handle))
+	if (!handle)
 		return ERR_PTR(-ENOMEM);
 
 	err = rhashtable_init(&handle->ht, &act_counters_ht_params);

drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h

···
 static inline bool
 mlx5e_skb_fifo_has_room(struct mlx5e_skb_fifo *fifo)
 {
-	return (*fifo->pc - *fifo->cc) < fifo->mask;
+	return (u16)(*fifo->pc - *fifo->cc) < fifo->mask;
 }
 
 static inline bool
···
 static inline
 struct sk_buff *mlx5e_skb_fifo_pop(struct mlx5e_skb_fifo *fifo)
 {
+	WARN_ON_ONCE(*fifo->pc == *fifo->cc);
+
 	return *mlx5e_skb_fifo_get(fifo, (*fifo->cc)++);
 }
 

drivers/net/ethernet/mellanox/mlx5/core/en_stats.c

···
 	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, abort_abs_diff_ns) },
 	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, resync_cqe) },
 	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, resync_event) },
+	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, ooo_cqe_drop) },
 };
 
 static const struct counter_desc ptp_rq_stats_desc[] = {

drivers/net/ethernet/mellanox/mlx5/core/en_stats.h

···
 	u64 abort_abs_diff_ns;
 	u64 resync_cqe;
 	u64 resync_event;
+	u64 ooo_cqe_drop;
 };
 
 struct mlx5e_rep_stats {

drivers/net/ethernet/mellanox/mlx5/core/en_tc.c

···
 	return 0;
 }
 
-static int debugfs_hairpin_queues_set(void *data, u64 val)
-{
-	struct mlx5e_hairpin_params *hp = data;
-
-	if (!val) {
-		mlx5_core_err(hp->mdev,
-			      "Number of hairpin queues must be > 0\n");
-		return -EINVAL;
-	}
-
-	hp->num_queues = val;
-
-	return 0;
-}
-
-static int debugfs_hairpin_queues_get(void *data, u64 *val)
-{
-	struct mlx5e_hairpin_params *hp = data;
-
-	*val = hp->num_queues;
-
-	return 0;
-}
-DEFINE_DEBUGFS_ATTRIBUTE(fops_hairpin_queues, debugfs_hairpin_queues_get,
-			 debugfs_hairpin_queues_set, "%llu\n");
-
-static int debugfs_hairpin_queue_size_set(void *data, u64 val)
-{
-	struct mlx5e_hairpin_params *hp = data;
-
-	if (val > BIT(MLX5_CAP_GEN(hp->mdev, log_max_hairpin_num_packets))) {
-		mlx5_core_err(hp->mdev,
-			      "Invalid hairpin queue size, must be <= %lu\n",
-			      BIT(MLX5_CAP_GEN(hp->mdev,
-					       log_max_hairpin_num_packets)));
-		return -EINVAL;
-	}
-
-	hp->queue_size = roundup_pow_of_two(val);
-
-	return 0;
-}
-
-static int debugfs_hairpin_queue_size_get(void *data, u64 *val)
-{
-	struct mlx5e_hairpin_params *hp = data;
-
-	*val = hp->queue_size;
-
-	return 0;
-}
-DEFINE_DEBUGFS_ATTRIBUTE(fops_hairpin_queue_size,
-			 debugfs_hairpin_queue_size_get,
-			 debugfs_hairpin_queue_size_set, "%llu\n");
-
 static int debugfs_hairpin_num_active_get(void *data, u64 *val)
 {
 	struct mlx5e_tc_table *tc = data;
···
 
 	tc->dfs_root = debugfs_create_dir("tc", dfs_root);
 
-	debugfs_create_file("hairpin_num_queues", 0644, tc->dfs_root,
-			    &tc->hairpin_params, &fops_hairpin_queues);
-	debugfs_create_file("hairpin_queue_size", 0644, tc->dfs_root,
-			    &tc->hairpin_params, &fops_hairpin_queue_size);
 	debugfs_create_file("hairpin_num_active", 0444, tc->dfs_root, tc,
 			    &fops_hairpin_num_active);
 	debugfs_create_file("hairpin_table_dump", 0444, tc->dfs_root, tc,

drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c

···
 	dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 
-	if (rep->vport == MLX5_VPORT_UPLINK)
+	if (MLX5_CAP_ESW_FLOWTABLE(on_esw->dev, flow_source) &&
+	    rep->vport == MLX5_VPORT_UPLINK)
 		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT;
 
 	flow_rule = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(on_esw),

drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.c

···
 		geneve->opt_type = opt->type;
 		geneve->obj_id = res;
 		geneve->refcount++;
+		res = 0;
 	}
 
 unlock:

drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c

···
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		mlx5_core_err(mdev, "Fail to create RoCE IPsec tx ft err=%d\n", err);
-		return err;
+		goto free_in;
 	}
 
 	roce->ft = ft;
···
 	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
 		mlx5_core_err(mdev, "Fail to create RoCE IPsec tx group err=%d\n", err);
-		goto fail;
+		goto destroy_table;
 	}
 	roce->g = g;
 
 	err = ipsec_fs_roce_tx_rule_setup(mdev, roce, pol_ft);
 	if (err) {
 		mlx5_core_err(mdev, "Fail to create RoCE IPsec tx rules err=%d\n", err);
-		goto rule_fail;
+		goto destroy_group;
 	}
 
+	kvfree(in);
 	return 0;
 
-rule_fail:
+destroy_group:
 	mlx5_destroy_flow_group(roce->g);
-fail:
+destroy_table:
 	mlx5_destroy_flow_table(ft);
+free_in:
+	kvfree(in);
 	return err;
 }
 

drivers/net/ethernet/mellanox/mlx5/core/sriov.c

···
 
 	mlx5_eswitch_disable_sriov(dev->priv.eswitch, clear_vf);
 
+	/* For ECPFs, skip waiting for host VF pages until ECPF is destroyed */
+	if (mlx5_core_is_ecpf(dev))
+		return;
+
 	if (mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_VF]))
 		mlx5_core_warn(dev, "timeout reclaiming VFs pages\n");
 }

drivers/net/ethernet/qlogic/qede/qede_main.c

···
 {
 	u8 fp_combined, fp_rx = edev->fp_num_rx;
 	struct qede_fastpath *fp;
-	void *mem;
 	int i;
 
 	edev->fp_array = kcalloc(QEDE_QUEUE_CNT(edev),
···
 	}
 
 	if (!edev->coal_entry) {
-		mem = kcalloc(QEDE_MAX_RSS_CNT(edev),
-			      sizeof(*edev->coal_entry), GFP_KERNEL);
-	} else {
-		mem = krealloc(edev->coal_entry,
-			       QEDE_QUEUE_CNT(edev) * sizeof(*edev->coal_entry),
-			       GFP_KERNEL);
+		edev->coal_entry = kcalloc(QEDE_MAX_RSS_CNT(edev),
+					   sizeof(*edev->coal_entry),
+					   GFP_KERNEL);
+		if (!edev->coal_entry) {
+			DP_ERR(edev, "coalesce entry allocation failed\n");
+			goto err;
+		}
 	}
-
-	if (!mem) {
-		DP_ERR(edev, "coalesce entry allocation failed\n");
-		kfree(edev->coal_entry);
-		goto err;
-	}
-	edev->coal_entry = mem;
 
 	fp_combined = QEDE_QUEUE_CNT(edev) - fp_rx - edev->fp_num_tx;
 

drivers/net/ethernet/sun/sunhme.c

···
 		goto err_out_clear_quattro;
 	}
 
-	hpreg_res = devm_request_region(&pdev->dev, pci_resource_start(pdev, 0),
-					pci_resource_len(pdev, 0), DRV_NAME);
+	hpreg_res = devm_request_mem_region(&pdev->dev,
+					    pci_resource_start(pdev, 0),
+					    pci_resource_len(pdev, 0),
+					    DRV_NAME);
 	if (!hpreg_res) {
 		err = -EBUSY;
 		dev_err(&pdev->dev, "Cannot obtain PCI resources, aborting.\n");

drivers/net/mdio/mdio-mscc-miim.c

···
 struct mscc_miim_dev {
 	struct regmap *regs;
 	int mii_status_offset;
+	bool ignore_read_errors;
 	struct regmap *phy_regs;
 	const struct mscc_miim_info *info;
 	struct clk *clk;
···
 		goto out;
 	}
 
-	if (val & MSCC_MIIM_DATA_ERROR) {
+	if (!miim->ignore_read_errors && !!(val & MSCC_MIIM_DATA_ERROR)) {
 		ret = -EIO;
 		goto out;
 	}
···
 };
 
 int mscc_miim_setup(struct device *dev, struct mii_bus **pbus, const char *name,
-		    struct regmap *mii_regmap, int status_offset)
+		    struct regmap *mii_regmap, int status_offset,
+		    bool ignore_read_errors)
 {
 	struct mscc_miim_dev *miim;
 	struct mii_bus *bus;
···
 
 	miim->regs = mii_regmap;
 	miim->mii_status_offset = status_offset;
+	miim->ignore_read_errors = ignore_read_errors;
 
 	*pbus = bus;
 
···
 		return dev_err_probe(dev, PTR_ERR(phy_regmap),
 				     "Unable to create phy register regmap\n");
 
-	ret = mscc_miim_setup(dev, &bus, "mscc_miim", mii_regmap, 0);
+	ret = mscc_miim_setup(dev, &bus, "mscc_miim", mii_regmap, 0, false);
 	if (ret < 0) {
 		dev_err(dev, "Unable to setup the MDIO bus\n");
 		return ret;

drivers/net/phy/phy-c45.c

···
 	linkmode_and(phydev->advertising, phydev->advertising,
 		     phydev->supported);
 
-	ret = genphy_c45_write_eee_adv(phydev, phydev->supported_eee);
+	ret = genphy_c45_an_config_eee_aneg(phydev);
 	if (ret < 0)
 		return ret;
 	else if (ret)
···
  */
 int genphy_c45_write_eee_adv(struct phy_device *phydev, unsigned long *adv)
 {
-	int val, changed;
+	int val, changed = 0;
 
-	if (linkmode_intersects(phydev->supported, PHY_EEE_CAP1_FEATURES)) {
+	if (linkmode_intersects(phydev->supported_eee, PHY_EEE_CAP1_FEATURES)) {
 		val = linkmode_to_mii_eee_cap1_t(adv);
 
 		/* In eee_broken_modes are stored MDIO_AN_EEE_ADV specific raw
···
  * @phydev: target phy_device struct
  * @adv: the linkmode advertisement status
  */
-static int genphy_c45_read_eee_adv(struct phy_device *phydev,
-				   unsigned long *adv)
+int genphy_c45_read_eee_adv(struct phy_device *phydev, unsigned long *adv)
 {
 	int val;
 
-	if (linkmode_intersects(phydev->supported, PHY_EEE_CAP1_FEATURES)) {
+	if (linkmode_intersects(phydev->supported_eee, PHY_EEE_CAP1_FEATURES)) {
 		/* IEEE 802.3-2018 45.2.7.13 EEE advertisement 1
 		 * (Register 7.60)
 		 */
···
 {
 	int val;
 
-	if (linkmode_intersects(phydev->supported, PHY_EEE_CAP1_FEATURES)) {
+	if (linkmode_intersects(phydev->supported_eee, PHY_EEE_CAP1_FEATURES)) {
 		/* IEEE 802.3-2018 45.2.7.14 EEE link partner ability 1
 		 * (Register 7.61)
 		 */
···
 	return 0;
 }
 EXPORT_SYMBOL_GPL(genphy_c45_read_eee_abilities);
+
+/**
+ * genphy_c45_an_config_eee_aneg - configure EEE advertisement
+ * @phydev: target phy_device struct
+ */
+int genphy_c45_an_config_eee_aneg(struct phy_device *phydev)
+{
+	if (!phydev->eee_enabled) {
+		__ETHTOOL_DECLARE_LINK_MODE_MASK(adv) = {};
+
+		return genphy_c45_write_eee_adv(phydev, adv);
+	}
+
+	return genphy_c45_write_eee_adv(phydev, phydev->advertising_eee);
+}
 
 /**
  * genphy_c45_pma_read_abilities - read supported link modes from PMA
···
 int genphy_c45_ethtool_set_eee(struct phy_device *phydev,
 			       struct ethtool_eee *data)
 {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(adv) = {};
 	int ret;
 
 	if (data->eee_enabled) {
-		if (data->advertised)
-			adv[0] = data->advertised;
-		else
-			linkmode_copy(adv, phydev->supported_eee);
+		if (data->advertised) {
+			__ETHTOOL_DECLARE_LINK_MODE_MASK(adv);
+
+			ethtool_convert_legacy_u32_to_link_mode(adv,
+								data->advertised);
+			linkmode_andnot(adv, adv, phydev->supported_eee);
+			if (!linkmode_empty(adv)) {
+				phydev_warn(phydev, "At least some EEE link modes are not supported.\n");
+				return -EINVAL;
+			}
+
+			ethtool_convert_legacy_u32_to_link_mode(phydev->advertising_eee,
+								data->advertised);
+		} else {
+			linkmode_copy(phydev->advertising_eee,
+				      phydev->supported_eee);
+		}
+
+		phydev->eee_enabled = true;
+	} else {
+		phydev->eee_enabled = false;
 	}
 
-	ret = genphy_c45_write_eee_adv(phydev, adv);
+	ret = genphy_c45_an_config_eee_aneg(phydev);
 	if (ret < 0)
 		return ret;
 	if (ret > 0)

drivers/net/phy/phy_device.c

···
 {
 	int err;
 
-	err = genphy_c45_write_eee_adv(phydev, phydev->supported_eee);
+	err = genphy_c45_an_config_eee_aneg(phydev);
 	if (err < 0)
 		return err;
 	else if (err)
···
 
 	of_set_phy_supported(phydev);
 	phy_advertise_supported(phydev);
+
+	/* Get PHY default EEE advertising modes and handle them as potentially
+	 * safe initial configuration.
+	 */
+	err = genphy_c45_read_eee_adv(phydev, phydev->advertising_eee);
+	if (err)
+		return err;
+
+	/* There is no "enabled" flag. If PHY is advertising, assume it is
+	 * kind of enabled.
+	 */
+	phydev->eee_enabled = !linkmode_empty(phydev->advertising_eee);
+
+	/* Some PHYs may advertise, by default, not support EEE modes. So,
+	 * we need to clean them.
+	 */
+	if (phydev->eee_enabled)
+		linkmode_and(phydev->advertising_eee, phydev->supported_eee,
+			     phydev->advertising_eee);
 
 	/* Get the EEE modes we want to prohibit. We will ask
 	 * the PHY stop advertising these mode later on

drivers/net/wireless/ath/ath11k/pci.c

···
 	if (ret)
 		ath11k_warn(ab, "failed to suspend core: %d\n", ret);
 
-	return ret;
+	return 0;
 }
 
 static __maybe_unused int ath11k_pci_pm_resume(struct device *dev)

drivers/net/wireless/mediatek/mt76/usb.c

···
 		q->entry[i].urb = NULL;
 	}
 	page_pool_destroy(q->page_pool);
+	q->page_pool = NULL;
 }
 
 static void mt76u_free_rx(struct mt76_dev *dev)

drivers/net/xen-netback/netback.c

···
 		struct xen_netif_tx_request txfrags[XEN_NETBK_LEGACY_SLOTS_MAX];
 		struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX-1];
 		unsigned int extra_count;
-		u16 pending_idx;
 		RING_IDX idx;
 		int work_to_do;
 		unsigned int data_len;
-		pending_ring_idx_t index;
 
 		if (queue->tx.sring->req_prod - queue->tx.req_cons >
 		    XEN_NETIF_TX_RING_SIZE) {
···
 			xenvif_fatal_tx_err(queue->vif);
 			break;
 		}
-
-		index = pending_index(queue->pending_cons);
-		pending_idx = queue->pending_ring[index];
 
 		if (ret >= XEN_NETBK_LEGACY_SLOTS_MAX - 1 && data_len < txreq.size)
 			data_len = txreq.size;

drivers/nfc/st-nci/se.c

···
 					ST_NCI_EVT_TRANSMIT_DATA, apdu,
 					apdu_length);
 	default:
+		/* Need to free cb_context here as at the moment we can't
+		 * clearly indicate to the caller if the callback function
+		 * would be called (and free it) or not. In both cases a
+		 * negative value may be returned to the caller.
+		 */
+		kfree(cb_context);
 		return -ENODEV;
 	}
 }

drivers/nfc/st21nfca/se.c

···
 					ST21NFCA_EVT_TRANSMIT_DATA,
 					apdu, apdu_length);
 	default:
+		/* Need to free cb_context here as at the moment we can't
+		 * clearly indicate to the caller if the callback function
+		 * would be called (and free it) or not. In both cases a
+		 * negative value may be returned to the caller.
+		 */
+		kfree(cb_context);
 		return -ENODEV;
 	}
 }

drivers/ptp/ptp_private.h

···
 	struct hlist_node vclock_hash_node;
 	struct cyclecounter cc;
 	struct timecounter tc;
-	spinlock_t lock;	/* protects tc/cc */
+	struct mutex lock;	/* protects tc/cc */
 };
 
 /*

drivers/ptp/ptp_vclock.c

···
 static int ptp_vclock_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 {
 	struct ptp_vclock *vclock = info_to_vclock(ptp);
-	unsigned long flags;
 	s64 adj;
 
 	adj = (s64)scaled_ppm << PTP_VCLOCK_FADJ_SHIFT;
 	adj = div_s64(adj, PTP_VCLOCK_FADJ_DENOMINATOR);
 
-	spin_lock_irqsave(&vclock->lock, flags);
+	if (mutex_lock_interruptible(&vclock->lock))
+		return -EINTR;
 	timecounter_read(&vclock->tc);
 	vclock->cc.mult = PTP_VCLOCK_CC_MULT + adj;
-	spin_unlock_irqrestore(&vclock->lock, flags);
+	mutex_unlock(&vclock->lock);
 
 	return 0;
 }
···
 static int ptp_vclock_adjtime(struct ptp_clock_info *ptp, s64 delta)
 {
 	struct ptp_vclock *vclock = info_to_vclock(ptp);
-	unsigned long flags;
 
-	spin_lock_irqsave(&vclock->lock, flags);
+	if (mutex_lock_interruptible(&vclock->lock))
+		return -EINTR;
 	timecounter_adjtime(&vclock->tc, delta);
-	spin_unlock_irqrestore(&vclock->lock, flags);
+	mutex_unlock(&vclock->lock);
 
 	return 0;
 }
···
 			      struct timespec64 *ts)
 {
 	struct ptp_vclock *vclock = info_to_vclock(ptp);
-	unsigned long flags;
 	u64 ns;
 
-	spin_lock_irqsave(&vclock->lock, flags);
+	if (mutex_lock_interruptible(&vclock->lock))
+		return -EINTR;
 	ns = timecounter_read(&vclock->tc);
-	spin_unlock_irqrestore(&vclock->lock, flags);
+	mutex_unlock(&vclock->lock);
 	*ts = ns_to_timespec64(ns);
 
 	return 0;
···
 	struct ptp_vclock *vclock = info_to_vclock(ptp);
 	struct ptp_clock *pptp = vclock->pclock;
 	struct timespec64 pts;
-	unsigned long flags;
 	int err;
 	u64 ns;
 
···
 	if (err)
 		return err;
 
-	spin_lock_irqsave(&vclock->lock, flags);
+	if (mutex_lock_interruptible(&vclock->lock))
+		return -EINTR;
 	ns = timecounter_cyc2time(&vclock->tc, timespec64_to_ns(&pts));
-	spin_unlock_irqrestore(&vclock->lock, flags);
+	mutex_unlock(&vclock->lock);
 
 	*ts = ns_to_timespec64(ns);
 
···
 {
 	struct ptp_vclock *vclock = info_to_vclock(ptp);
 	u64 ns = timespec64_to_ns(ts);
-	unsigned long flags;
 
-	spin_lock_irqsave(&vclock->lock, flags);
+	if (mutex_lock_interruptible(&vclock->lock))
+		return -EINTR;
 	timecounter_init(&vclock->tc, &vclock->cc, ns);
-	spin_unlock_irqrestore(&vclock->lock, flags);
+	mutex_unlock(&vclock->lock);
 
 	return 0;
 }
···
 {
 	struct ptp_vclock *vclock = info_to_vclock(ptp);
 	struct ptp_clock *pptp = vclock->pclock;
-	unsigned long flags;
 	int err;
 	u64 ns;
 
···
 	if (err)
 		return err;
 
-	spin_lock_irqsave(&vclock->lock, flags);
+	if (mutex_lock_interruptible(&vclock->lock))
+		return -EINTR;
 	ns = timecounter_cyc2time(&vclock->tc, ktime_to_ns(xtstamp->device));
-	spin_unlock_irqrestore(&vclock->lock, flags);
+	mutex_unlock(&vclock->lock);
 
 	xtstamp->device = ns_to_ktime(ns);
 
···
 
 	INIT_HLIST_NODE(&vclock->vclock_hash_node);
 
-	spin_lock_init(&vclock->lock);
+	mutex_init(&vclock->lock);
 
 	vclock->clock = ptp_clock_register(&vclock->info, &pclock->dev);
 	if (IS_ERR_OR_NULL(vclock->clock)) {
···
 {
 	unsigned int hash = vclock_index % HASH_SIZE(vclock_hash);
 	struct ptp_vclock *vclock;
-	unsigned long flags;
 	u64 ns;
 	u64 vclock_ns = 0;
 
···
 		if (vclock->clock->index != vclock_index)
 			continue;
 
-		spin_lock_irqsave(&vclock->lock, flags);
+		if (mutex_lock_interruptible(&vclock->lock))
+			break;
 		vclock_ns = timecounter_cyc2time(&vclock->tc, ns);
-		spin_unlock_irqrestore(&vclock->lock, flags);
+		mutex_unlock(&vclock->lock);
 		break;
 	}
 

include/linux/mdio/mdio-mscc-miim.h

···
 
 int mscc_miim_setup(struct device *device, struct mii_bus **bus,
 		    const char *name, struct regmap *mii_regmap,
-		    int status_offset);
+		    int status_offset, bool ignore_read_errors);
 
 #endif

include/linux/netfilter.h

···
  */
 DECLARE_PER_CPU(bool, nf_skb_duplicated);
 
+/**
+ * Contains bitmask of ctnetlink event subscribers, if any.
+ * Can't be pernet due to NETLINK_LISTEN_ALL_NSID setsockopt flag.
+ */
+extern u8 nf_ctnetlink_has_listener;
 #endif /*__LINUX_NETFILTER_H*/

include/linux/phy.h

···
  * @advertising: Currently advertised linkmodes
  * @adv_old: Saved advertised while power saving for WoL
  * @supported_eee: supported PHY EEE linkmodes
+ * @advertising_eee: Currently advertised EEE linkmodes
+ * @eee_enabled: Flag indicating whether the EEE feature is enabled
  * @lp_advertising: Current link partner advertised linkmodes
  * @host_interfaces: PHY interface modes supported by host
  * @eee_broken_modes: Energy efficient ethernet modes which should be prohibited
···
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old);
 	/* used for eee validation */
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported_eee);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(advertising_eee);
+	bool eee_enabled;
 
 	/* Host supported PHY interface types. Should be ignored if empty. */
 	DECLARE_PHY_INTERFACE_MASK(host_interfaces);
···
 int genphy_c45_ethtool_set_eee(struct phy_device *phydev,
 			       struct ethtool_eee *data);
 int genphy_c45_write_eee_adv(struct phy_device *phydev, unsigned long *adv);
+int genphy_c45_an_config_eee_aneg(struct phy_device *phydev);
+int genphy_c45_read_eee_adv(struct phy_device *phydev, unsigned long *adv);
 
 /* Generic C45 PHY driver */
 extern struct phy_driver genphy_c45_driver;

include/net/netns/conntrack.h

···
 
 struct netns_ct {
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
-	u8 ctnetlink_has_listener;
 	bool ecache_dwork_pending;
 #endif
 	u8			sysctl_log_invalid; /* Log invalid packets */

include/net/sctp/structs.h

···
 	/* The next stream in line */
 	struct sctp_stream_out_ext *next;
 	__u16 prio;
+	__u16 users;
 };
 
 struct sctp_stream_out_ext {

include/uapi/linux/netdev.h

···
  * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP
  *   in zero copy mode.
  * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw
- *   oflloading.
+ *   offloading.
  * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear
  *   XDP buffer support in the driver napi callback.
  * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements

net/bridge/netfilter/ebtables.c

···
 
 	audit_log_nfcfg(repl->name, AF_BRIDGE, repl->nentries,
 			AUDIT_XT_OP_REPLACE, GFP_KERNEL);
-	return ret;
+	return 0;
 
 free_unlock:
 	mutex_unlock(&ebt_mutex);

net/core/dev.c

···
 {
 	if (in_hardirq() || irqs_disabled())
 		__dev_kfree_skb_irq(skb, reason);
+	else if (unlikely(reason == SKB_REASON_DROPPED))
+		kfree_skb(skb);
 	else
-		dev_kfree_skb(skb);
+		consume_skb(skb);
 }
 EXPORT_SYMBOL(__dev_kfree_skb_any);
 

net/ipv4/netfilter/arp_tables.c

···
 
 	new_table = xt_register_table(net, table, &bootstrap, newinfo);
 	if (IS_ERR(new_table)) {
+		struct arpt_entry *iter;
+
+		xt_entry_foreach(iter, loc_cpu_entry, newinfo->size)
+			cleanup_entry(iter, net);
 		xt_free_table_info(newinfo);
 		return PTR_ERR(new_table);
 	}

net/ipv4/netfilter/ip_tables.c

···
 	struct xt_counters *counters;
 	struct ipt_entry *iter;
 
-	ret = 0;
 	counters = xt_counters_alloc(num_counters);
 	if (!counters) {
 		ret = -ENOMEM;
···
 		net_warn_ratelimited("iptables: counters copy to user failed while replacing table\n");
 	}
 	vfree(counters);
-	return ret;
+	return 0;
 
  put_module:
 	module_put(t->me);
···
 
 	new_table = xt_register_table(net, table, &bootstrap, newinfo);
 	if (IS_ERR(new_table)) {
+		struct ipt_entry *iter;
+
+		xt_entry_foreach(iter, loc_cpu_entry, newinfo->size)
+			cleanup_entry(iter, net);
 		xt_free_table_info(newinfo);
 		return PTR_ERR(new_table);
 	}

net/ipv4/tcp_minisocks.c

···
  * validation and inside tcp_v4_reqsk_send_ack(). Can we do better?
  *
  * We don't need to initialize tmp_opt.sack_ok as we don't use the results
+ *
+ * Note: If @fastopen is true, this can be called from process context.
+ *       Otherwise, this is from BH context.
  */
 
 struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
···
 					  &tcp_rsk(req)->last_oow_ack_time))
 			req->rsk_ops->send_ack(sk, skb, req);
 		if (paws_reject)
-			__NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
 		return NULL;
 	}
 
···
 	 *	   "fourth, check the SYN bit"
 	 */
 	if (flg & (TCP_FLAG_RST|TCP_FLAG_SYN)) {
-		__TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS);
+		TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS);
 		goto embryonic_reset;
 	}
 

net/ipv6/netfilter/ip6_tables.c

···
 	struct xt_counters *counters;
 	struct ip6t_entry *iter;
 
-	ret = 0;
 	counters = xt_counters_alloc(num_counters);
 	if (!counters) {
 		ret = -ENOMEM;
···
 		net_warn_ratelimited("ip6tables: counters copy to user failed while replacing table\n");
 	}
 	vfree(counters);
-	return ret;
+	return 0;
 
  put_module:
 	module_put(t->me);
···
 
 	new_table = xt_register_table(net, table, &bootstrap, newinfo);
 	if (IS_ERR(new_table)) {
+		struct ip6t_entry *iter;
+
+		xt_entry_foreach(iter, loc_cpu_entry, newinfo->size)
+			cleanup_entry(iter, net);
 		xt_free_table_info(newinfo);
 		return PTR_ERR(new_table);
 	}

net/ipv6/netfilter/ip6t_rpfilter.c

···
 		goto out;
 	}
 
-	if (rt->rt6i_idev->dev == dev || (flags & XT_RPFILTER_LOOSE))
+	if (rt->rt6i_idev->dev == dev ||
+	    l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) == dev->ifindex ||
+	    (flags & XT_RPFILTER_LOOSE))
 		ret = true;
  out:
 	ip6_rt_put(rt);

net/ipv6/route.c

···
 		nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size,
 					 &nexthop_len);
 	} else {
+		struct fib6_info *sibling, *next_sibling;
 		struct fib6_nh *nh = f6i->fib6_nh;
 
 		nexthop_len = 0;
 		if (f6i->fib6_nsiblings) {
-			nexthop_len = nla_total_size(0)	 /* RTA_MULTIPATH */
-				    + NLA_ALIGN(sizeof(struct rtnexthop))
-				    + nla_total_size(16) /* RTA_GATEWAY */
-				    + lwtunnel_get_encap_size(nh->fib_nh_lws);
+			rt6_nh_nlmsg_size(nh, &nexthop_len);
 
-			nexthop_len *= f6i->fib6_nsiblings;
+			list_for_each_entry_safe(sibling, next_sibling,
+						 &f6i->fib6_siblings, fib6_siblings) {
+				rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len);
+			}
 		}
 		nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
 	}

net/netfilter/core.c

···
 EXPORT_SYMBOL_GPL(nf_ct_hook);
 
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
+u8 nf_ctnetlink_has_listener;
+EXPORT_SYMBOL_GPL(nf_ctnetlink_has_listener);
+
 const struct nf_nat_hook __rcu *nf_nat_hook __read_mostly;
 EXPORT_SYMBOL_GPL(nf_nat_hook);
 

net/netfilter/nf_conntrack_bpf.c

···
 	struct nf_conn *nfct = (struct nf_conn *)nfct_i;
 	int err;
 
-	nfct->status |= IPS_CONFIRMED;
 	err = nf_conntrack_hash_check_insert(nfct);
 	if (err < 0) {
 		nf_conntrack_free(nfct);

net/netfilter/nf_conntrack_core.c

···
 
 	zone = nf_ct_zone(ct);
 
-	if (!nf_ct_ext_valid_pre(ct->ext)) {
-		NF_CT_STAT_INC_ATOMIC(net, insert_failed);
-		return -ETIMEDOUT;
-	}
+	if (!nf_ct_ext_valid_pre(ct->ext))
+		return -EAGAIN;
 
 	local_bh_disable();
 	do {
···
 			goto chaintoolong;
 	}
 
+	/* If genid has changed, we can't insert anymore because ct
+	 * extensions could have stale pointers and nf_ct_iterate_destroy
+	 * might have completed its table scan already.
+	 *
+	 * Increment of the ext genid right after this check is fine:
+	 * nf_ct_iterate_destroy blocks until locks are released.
+	 */
+	if (!nf_ct_ext_valid_post(ct->ext)) {
+		err = -EAGAIN;
+		goto out;
+	}
+
+	ct->status |= IPS_CONFIRMED;
 	smp_wmb();
 	/* The caller holds a reference to this object */
 	refcount_set(&ct->ct_general.use, 2);
···
 	nf_conntrack_double_unlock(hash, reply_hash);
 	NF_CT_STAT_INC(net, insert);
 	local_bh_enable();
-
-	if (!nf_ct_ext_valid_post(ct->ext)) {
-		nf_ct_kill(ct);
-		NF_CT_STAT_INC_ATOMIC(net, drop);
-		return -ETIMEDOUT;
-	}
 
 	return 0;
 chaintoolong:

net/netfilter/nf_conntrack_ecache.c

···
 			break;
 		return true;
 	case 2: /* autodetect: no event listener, don't allocate extension. */
-		if (!READ_ONCE(net->ct.ctnetlink_has_listener))
+		if (!READ_ONCE(nf_ctnetlink_has_listener))
 			return true;
 		fallthrough;
 	case 1:

net/netfilter/nf_conntrack_netlink.c

···
 	nfct_seqadj_ext_add(ct);
 	nfct_synproxy_ext_add(ct);
 
-	/* we must add conntrack extensions before confirmation. */
-	ct->status |= IPS_CONFIRMED;
-
 	if (cda[CTA_STATUS]) {
 		err = ctnetlink_change_status(ct, cda);
 		if (err < 0)
···
 
 	err = nf_conntrack_hash_check_insert(ct);
 	if (err < 0)
-		goto err2;
+		goto err3;
 
 	rcu_read_unlock();
 
 	return ct;
 
+err3:
+	if (ct->master)
+		nf_ct_put(ct->master);
 err2:
 	rcu_read_unlock();
 err1:

net/netfilter/nf_tables_api.c

···
 	int rem, err = 0;
 
 	table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family,
-				 genmask, NETLINK_CB(skb).portid);
+				 genmask, 0);
 	if (IS_ERR(table)) {
 		NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]);
 		return PTR_ERR(table);

net/netfilter/nfnetlink.c

···
 
 #include <net/netlink.h>
 #include <net/netns/generic.h>
+#include <linux/netfilter.h>
 #include <linux/netfilter/nfnetlink.h>
 
 MODULE_LICENSE("GPL");
···
 	group_bit = (1 << group);
 
 	spin_lock(&nfnl_grp_active_lock);
-	v = READ_ONCE(net->ct.ctnetlink_has_listener);
+	v = READ_ONCE(nf_ctnetlink_has_listener);
 	if ((v & group_bit) == 0) {
 		v |= group_bit;
 
 		/* read concurrently without nfnl_grp_active_lock held. */
-		WRITE_ONCE(net->ct.ctnetlink_has_listener, v);
+		WRITE_ONCE(nf_ctnetlink_has_listener, v);
 	}
 
 	spin_unlock(&nfnl_grp_active_lock);
···
 
 	spin_lock(&nfnl_grp_active_lock);
 	if (!nfnetlink_has_listeners(net, group)) {
-		u8 v = READ_ONCE(net->ct.ctnetlink_has_listener);
+		u8 v = READ_ONCE(nf_ctnetlink_has_listener);
 
 		v &= ~group_bit;
 
 		/* read concurrently without nfnl_grp_active_lock held. */
-		WRITE_ONCE(net->ct.ctnetlink_has_listener, v);
+		WRITE_ONCE(nf_ctnetlink_has_listener, v);
 	}
 	spin_unlock(&nfnl_grp_active_lock);
 #endif

net/netfilter/xt_length.c

···
 length_mt6(const struct sk_buff *skb, struct xt_action_param *par)
 {
 	const struct xt_length_info *info = par->matchinfo;
-	const u_int16_t pktlen = ntohs(ipv6_hdr(skb)->payload_len) +
-				 sizeof(struct ipv6hdr);
+	u32 pktlen = skb->len;
 
 	return (pktlen >= info->min && pktlen <= info->max) ^ info->invert;
 }

net/nfc/netlink.c

···
 	rc = dev->ops->se_io(dev, se_idx, apdu,
 			apdu_length, cb, cb_context);
 
+	device_unlock(&dev->dev);
+	return rc;
+
 error:
+	kfree(cb_context);
 	device_unlock(&dev->dev);
 	return rc;
 }

net/sched/act_api.c

···
 	if (tcf_action_dump(skb, actions, bind, ref, false) < 0)
 		goto out_nlmsg_trim;
 
-	nla_nest_end(skb, nest);
-
 	if (extack && extack->_msg &&
 	    nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg))
 		goto out_nlmsg_trim;
+
+	nla_nest_end(skb, nest);
 
 	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
 

net/sched/act_mpls.c

···
 	parm = nla_data(tb[TCA_MPLS_PARMS]);
 	index = parm->index;
 
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
+	if (err < 0)
+		return err;
+	exists = err;
+	if (exists && bind)
+		return 0;
+
+	if (!exists) {
+		ret = tcf_idr_create(tn, index, est, a, &act_mpls_ops, bind,
+				     true, flags);
+		if (ret) {
+			tcf_idr_cleanup(tn, index);
+			return ret;
+		}
+
+		ret = ACT_P_CREATED;
+	} else if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
+		tcf_idr_release(*a, bind);
+		return -EEXIST;
+	}
+
 	/* Verify parameters against action type. */
 	switch (parm->m_action) {
 	case TCA_MPLS_ACT_POP:
 		if (!tb[TCA_MPLS_PROTO]) {
 			NL_SET_ERR_MSG_MOD(extack, "Protocol must be set for MPLS pop");
-			return -EINVAL;
+			err = -EINVAL;
+			goto release_idr;
 		}
 		if (!eth_proto_is_802_3(nla_get_be16(tb[TCA_MPLS_PROTO]))) {
 			NL_SET_ERR_MSG_MOD(extack, "Invalid protocol type for MPLS pop");
-			return -EINVAL;
+			err = -EINVAL;
+			goto release_idr;
 		}
 		if (tb[TCA_MPLS_LABEL] || tb[TCA_MPLS_TTL] || tb[TCA_MPLS_TC] ||
 		    tb[TCA_MPLS_BOS]) {
 			NL_SET_ERR_MSG_MOD(extack, "Label, TTL, TC or BOS cannot be used with MPLS pop");
-			return -EINVAL;
+			err = -EINVAL;
+			goto release_idr;
 		}
 		break;
 	case TCA_MPLS_ACT_DEC_TTL:
 		if (tb[TCA_MPLS_PROTO] || tb[TCA_MPLS_LABEL] ||
 		    tb[TCA_MPLS_TTL] || tb[TCA_MPLS_TC] || tb[TCA_MPLS_BOS]) {
 			NL_SET_ERR_MSG_MOD(extack, "Label, TTL, TC, BOS or protocol cannot be used with MPLS dec_ttl");
-			return -EINVAL;
+			err = -EINVAL;
+			goto release_idr;
 		}
 		break;
 	case TCA_MPLS_ACT_PUSH:
 	case TCA_MPLS_ACT_MAC_PUSH:
 		if (!tb[TCA_MPLS_LABEL]) {
 			NL_SET_ERR_MSG_MOD(extack, "Label is required for MPLS push");
-			return -EINVAL;
+			err = -EINVAL;
+			goto release_idr;
 		}
 		if (tb[TCA_MPLS_PROTO] &&
 		    !eth_p_mpls(nla_get_be16(tb[TCA_MPLS_PROTO]))) {
 			NL_SET_ERR_MSG_MOD(extack, "Protocol must be an MPLS type for MPLS push");
-			return -EPROTONOSUPPORT;
+			err = -EPROTONOSUPPORT;
+			goto release_idr;
 		}
 		/* Push needs a TTL - if not specified, set a default value. */
 		if (!tb[TCA_MPLS_TTL]) {
···
 	case TCA_MPLS_ACT_MODIFY:
 		if (tb[TCA_MPLS_PROTO]) {
 			NL_SET_ERR_MSG_MOD(extack, "Protocol cannot be used with MPLS modify");
-			return -EINVAL;
+			err = -EINVAL;
+			goto release_idr;
 		}
 		break;
 	default:
 		NL_SET_ERR_MSG_MOD(extack, "Unknown MPLS action");
-		return -EINVAL;
-	}
-
-	err = tcf_idr_check_alloc(tn, &index, a, bind);
-	if (err < 0)
-		return err;
-	exists = err;
-	if (exists && bind)
-		return 0;
-
-	if (!exists) {
-		ret = tcf_idr_create(tn, index, est, a,
-				     &act_mpls_ops, bind, true, flags);
-		if (ret) {
-			tcf_idr_cleanup(tn, index);
-			return ret;
-		}
-
-		ret = ACT_P_CREATED;
-	} else if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
-		tcf_idr_release(*a, bind);
-		return -EEXIST;
+		err = -EINVAL;
+		goto release_idr;
 	}
 
 	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);

net/sched/act_pedit.c

···
 	}
 
 	parm = nla_data(pattr);
-	if (!parm->nkeys) {
-		NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed");
-		return -EINVAL;
-	}
-	ksize = parm->nkeys * sizeof(struct tc_pedit_key);
-	if (nla_len(pattr) < sizeof(*parm) + ksize) {
-		NL_SET_ERR_MSG_ATTR(extack, pattr, "Length of TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute is invalid");
-		return -EINVAL;
-	}
-
-	nparms = kzalloc(sizeof(*nparms), GFP_KERNEL);
-	if (!nparms)
-		return -ENOMEM;
-
-	nparms->tcfp_keys_ex =
-		tcf_pedit_keys_ex_parse(tb[TCA_PEDIT_KEYS_EX], parm->nkeys);
-	if (IS_ERR(nparms->tcfp_keys_ex)) {
-		ret = PTR_ERR(nparms->tcfp_keys_ex);
-		goto out_free;
-	}
 
 	index = parm->index;
 	err = tcf_idr_check_alloc(tn, &index, a, bind);
···
 						&act_pedit_ops, bind, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
-			goto out_free_ex;
+			return ret;
 		}
 		ret = ACT_P_CREATED;
 	} else if (err > 0) {
 		if (bind)
-			goto out_free;
+			return 0;
 		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
 			ret = -EEXIST;
 			goto out_release;
 		}
 	} else {
-		ret = err;
-		goto out_free_ex;
+		return err;
+	}
+
+	if (!parm->nkeys) {
+		NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed");
+		ret = -EINVAL;
+		goto out_release;
+	}
+	ksize = parm->nkeys * sizeof(struct tc_pedit_key);
+	if (nla_len(pattr) < sizeof(*parm) + ksize) {
+		NL_SET_ERR_MSG_ATTR(extack, pattr, "Length of TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute is invalid");
+		ret = -EINVAL;
+		goto out_release;
+	}
+
+	nparms = kzalloc(sizeof(*nparms), GFP_KERNEL);
+	if (!nparms) {
+		ret = -ENOMEM;
+		goto out_release;
+	}
+
+	nparms->tcfp_keys_ex =
+		tcf_pedit_keys_ex_parse(tb[TCA_PEDIT_KEYS_EX], parm->nkeys);
+	if (IS_ERR(nparms->tcfp_keys_ex)) {
+		ret = PTR_ERR(nparms->tcfp_keys_ex);
+		goto out_free;
 	}
 
 	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
 	if (err < 0) {
 		ret = err;
-		goto out_release;
+		goto out_free_ex;
 	}
 
 	nparms->tcfp_off_max_hint = 0;
···
 put_chain:
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
-out_release:
-	tcf_idr_release(*a, bind);
 out_free_ex:
 	kfree(nparms->tcfp_keys_ex);
 out_free:
 	kfree(nparms);
+out_release:
+	tcf_idr_release(*a, bind);
 	return ret;
 }
 

net/sched/act_sample.c

···
 					  sample_policy, NULL);
 	if (ret < 0)
 		return ret;
-	if (!tb[TCA_SAMPLE_PARMS] || !tb[TCA_SAMPLE_RATE] ||
-	    !tb[TCA_SAMPLE_PSAMPLE_GROUP])
+
+	if (!tb[TCA_SAMPLE_PARMS])
 		return -EINVAL;
 
 	parm = nla_data(tb[TCA_SAMPLE_PARMS]);
···
 		tcf_idr_release(*a, bind);
 		return -EEXIST;
 	}
+
+	if (!tb[TCA_SAMPLE_RATE] || !tb[TCA_SAMPLE_PSAMPLE_GROUP]) {
+		NL_SET_ERR_MSG(extack, "sample rate and group are required");
+		err = -EINVAL;
+		goto release_idr;
+	}
+
 	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
 	if (err < 0)
 		goto release_idr;

net/sched/cls_api.c

···
 
 void tcf_exts_destroy(struct tcf_exts *exts)
 {
-#ifdef CONFIG_NET_CLS_ACT
 	tcf_exts_miss_cookie_base_destroy(exts);
 
+#ifdef CONFIG_NET_CLS_ACT
 	if (exts->actions) {
 		tcf_action_destroy(exts->actions, TCA_ACT_UNBIND);
 		kfree(exts->actions);

net/sctp/stream_sched_prio.c

···
 
 static void sctp_sched_prio_unsched_all(struct sctp_stream *stream);
 
+static struct sctp_stream_priorities *sctp_sched_prio_head_get(struct sctp_stream_priorities *p)
+{
+	p->users++;
+	return p;
+}
+
+static void sctp_sched_prio_head_put(struct sctp_stream_priorities *p)
+{
+	if (p && --p->users == 0)
+		kfree(p);
+}
+
 static struct sctp_stream_priorities *sctp_sched_prio_new_head(
 			struct sctp_stream *stream, int prio, gfp_t gfp)
 {
···
 	INIT_LIST_HEAD(&p->active);
 	p->next = NULL;
 	p->prio = prio;
+	p->users = 1;
 
 	return p;
 }
···
 	 */
 	list_for_each_entry(p, &stream->prio_list, prio_sched) {
 		if (p->prio == prio)
-			return p;
+			return sctp_sched_prio_head_get(p);
 		if (p->prio > prio)
 			break;
 	}
···
 			 */
 			break;
 		if (p->prio == prio)
-			return p;
+			return sctp_sched_prio_head_get(p);
 	}
 
 	/* If not even there, allocate a new one. */
···
 	struct sctp_stream_out_ext *soute = sout->ext;
 	struct sctp_stream_priorities *prio_head, *old;
 	bool reschedule = false;
-	int i;
+
+	old = soute->prio_head;
+	if (old && old->prio == prio)
+		return 0;
 
 	prio_head = sctp_sched_prio_get_head(stream, prio, gfp);
 	if (!prio_head)
 		return -ENOMEM;
 
 	reschedule = sctp_sched_prio_unsched(soute);
-	old = soute->prio_head;
 	soute->prio_head = prio_head;
 	if (reschedule)
 		sctp_sched_prio_sched(stream, soute);
 
-	if (!old)
-		/* Happens when we set the priority for the first time */
-		return 0;
-
-	for (i = 0; i < stream->outcnt; i++) {
-		soute = SCTP_SO(stream, i)->ext;
-		if (soute && soute->prio_head == old)
-			/* It's still in use, nothing else to do here. */
-			return 0;
-	}
-
-	/* No hits, we are good to free it. */
-	kfree(old);
-
+	sctp_sched_prio_head_put(old);
 	return 0;
 }
 
···
 
 static void sctp_sched_prio_free_sid(struct sctp_stream *stream, __u16 sid)
 {
-	struct sctp_stream_priorities *prio = SCTP_SO(stream, sid)->ext->prio_head;
-	int i;
-
-	if (!prio)
-		return;
-
+	sctp_sched_prio_head_put(SCTP_SO(stream, sid)->ext->prio_head);
 	SCTP_SO(stream, sid)->ext->prio_head = NULL;
-	for (i = 0; i < stream->outcnt; i++) {
-		if (SCTP_SO(stream, i)->ext &&
-		    SCTP_SO(stream, i)->ext->prio_head == prio)
-			return;
-	}
-
-	kfree(prio);
 }
 
 static void sctp_sched_prio_enqueue(struct sctp_outq *q,

net/wireless/wext-core.c

···
 {
 	char name[sizeof(current->comm)];
 
-	pr_warn_ratelimited("warning: `%s' uses wireless extensions that are deprecated for modern drivers; use nl80211\n",
-			    get_task_comm(name, current));
+	pr_warn_once("warning: `%s' uses wireless extensions which will stop working for Wi-Fi 7 hardware; use nl80211\n",
+		     get_task_comm(name, current));
 }
 #endif
 

tools/include/uapi/linux/netdev.h

···
  * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP
  *   in zero copy mode.
  * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw
- *   oflloading.
+ *   offloading.
  * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear
  *   XDP buffer support in the driver napi callback.
  * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements

tools/net/ynl/lib/.gitignore

···
+__pycache__/

tools/net/ynl/lib/nlspec.py

···
 import collections
 import importlib
 import os
-import traceback
 import yaml
 
 
···
                 resolved.append(elem)
 
             if len(resolved) == 0:
-                traceback.print_exception(last_exception)
-                raise Exception("Could not resolve any spec element, infinite loop?")
+                raise last_exception
 
     def new_attr_set(self, elem):
         return SpecAttrSet(self, elem)

tools/net/ynl/ynl-gen-c.py

···
         max_val = 0
         self.attr_max_val = None
         for name, attr in self.attr_list:
-            if attr.value > max_val:
+            if attr.value >= max_val:
                 max_val = attr.value
                 self.attr_max_val = attr
             self.attrs[name] = attr

tools/testing/selftests/net/fib_tests.sh

···
 ksft_skip=4
 
 # all tests in this script. Can be overridden with -t option
-TESTS="unregister down carrier nexthop suppress ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh"
+TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh"
 
 VERBOSE=0
 PAUSE_ON_FAIL=no
···
 	$IP link del red
 	) 2>/dev/null
 	cleanup
+}
+
+fib6_notify_test()
+{
+	setup
+
+	echo
+	echo "Fib6 info length calculation in route notify test"
+	set -e
+
+	for i in 10 20 30 40 50 60 70;
+	do
+		$IP link add dummy_$i type dummy
+		$IP link set dev dummy_$i up
+		$IP -6 address add 2001:$i::1/64 dev dummy_$i
+	done
+
+	$NS_EXEC ip monitor route &> errors.txt &
+	sleep 2
+
+	$IP -6 route add 2001::/64 \
+                nexthop via 2001:10::2 dev dummy_10 \
+                nexthop encap ip6 dst 2002::20 via 2001:20::2 dev dummy_20 \
+                nexthop encap ip6 dst 2002::30 via 2001:30::2 dev dummy_30 \
+                nexthop encap ip6 dst 2002::40 via 2001:40::2 dev dummy_40 \
+                nexthop encap ip6 dst 2002::50 via 2001:50::2 dev dummy_50 \
+                nexthop encap ip6 dst 2002::60 via 2001:60::2 dev dummy_60 \
+                nexthop encap ip6 dst 2002::70 via 2001:70::2 dev dummy_70
+
+	set +e
+
+	err=`cat errors.txt |grep "Message too long"`
+	if [ -z "$err" ];then
+		ret=0
+	else
+		ret=1
+	fi
+
+	log_test $ret 0 "ipv6 route add notify"
+
+	{ kill %% && wait %%; } 2>/dev/null
+
+	#rm errors.txt
+
+	cleanup &> /dev/null
+}
+
+
+fib_notify_test()
+{
+	setup
+
+	echo
+	echo "Fib4 info length calculation in route notify test"
+
+	set -e
+
+	for i in 10 20 30 40 50 60 70;
+	do
+		$IP link add dummy_$i type dummy
+		$IP link set dev dummy_$i up
+		$IP address add 20.20.$i.2/24 dev dummy_$i
+	done
+
+	$NS_EXEC ip monitor route &> errors.txt &
+	sleep 2
+
+        $IP route add 10.0.0.0/24 \
+                nexthop via 20.20.10.1 dev dummy_10 \
+                nexthop encap ip dst 192.168.10.20 via 20.20.20.1 dev dummy_20 \
+                nexthop encap ip dst 192.168.10.30 via 20.20.30.1 dev dummy_30 \
+                nexthop encap ip dst 192.168.10.40 via 20.20.40.1 dev dummy_40 \
+                nexthop encap ip dst 192.168.10.50 via 20.20.50.1 dev dummy_50 \
+                nexthop encap ip dst 192.168.10.60 via 20.20.60.1 dev dummy_60 \
+                nexthop encap ip dst 192.168.10.70 via 20.20.70.1 dev dummy_70
+
+	set +e
+
+	err=`cat errors.txt |grep "Message too long"`
+	if [ -z "$err" ];then
+		ret=0
+	else
+		ret=1
+	fi
+
+	log_test $ret 0 "ipv4 route add notify"
+
+	{ kill %% && wait %%; } 2>/dev/null
+
+	rm  errors.txt
+
+	cleanup &> /dev/null
 }
 
 fib_suppress_test()
···
 	fib_carrier_test|carrier)	fib_carrier_test;;
 	fib_rp_filter_test|rp_filter)	fib_rp_filter_test;;
 	fib_nexthop_test|nexthop)	fib_nexthop_test;;
+	fib_notify_test|ipv4_notify)	fib_notify_test;;
+	fib6_notify_test|ipv6_notify)	fib6_notify_test;;
 	fib_suppress_test|suppress)	fib_suppress_test;;
 	ipv6_route_test|ipv6_rt)	ipv6_route_test;;
 	ipv4_route_test|ipv4_rt)	ipv4_route_test;;

tools/testing/selftests/netfilter/rpath.sh

···
 ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad
 
 # firewall matches to test
-[ -n "$iptables" ] && ip netns exec "$ns2" \
-	"$iptables" -t raw -A PREROUTING -s 192.168.0.0/16 -m rpfilter
-[ -n "$ip6tables" ] && ip netns exec "$ns2" \
-	"$ip6tables" -t raw -A PREROUTING -s fec0::/16 -m rpfilter
+[ -n "$iptables" ] && {
+	common='-t raw -A PREROUTING -s 192.168.0.0/16'
+	ip netns exec "$ns2" "$iptables" $common -m rpfilter
+	ip netns exec "$ns2" "$iptables" $common -m rpfilter --invert
+}
+[ -n "$ip6tables" ] && {
+	common='-t raw -A PREROUTING -s fec0::/16'
+	ip netns exec "$ns2" "$ip6tables" $common -m rpfilter
+	ip netns exec "$ns2" "$ip6tables" $common -m rpfilter --invert
+}
 [ -n "$nft" ] && ip netns exec "$ns2" $nft -f - <<EOF
 table inet t {
 	chain c {
···
 	[ -n "$1" ] || return 0
 	ip netns exec "$ns2" "$1" -t raw -vS | grep -q -- "-m rpfilter -c 0 0"
 }
+ipt_zero_reverse_rule() { # (command)
+	[ -n "$1" ] || return 0
+	ip netns exec "$ns2" "$1" -t raw -vS | \
+		grep -q -- "-m rpfilter --invert -c 0 0"
+}
 nft_zero_rule() { # (family)
 	[ -n "$nft" ] || return 0
 	ip netns exec "$ns2" "$nft" list chain inet t c | \
···
 	ip netns exec "$netns" ping -q -c 1 -W 1 "$@" >/dev/null
 }
 
-testrun() {
-	# clear counters first
+clear_counters() {
 	[ -n "$iptables" ] && ip netns exec "$ns2" "$iptables" -t raw -Z
 	[ -n "$ip6tables" ] && ip netns exec "$ns2" "$ip6tables" -t raw -Z
 	if [ -n "$nft" ]; then
···
 			ip netns exec "$ns2" $nft -s list table inet t;
 		) | ip netns exec "$ns2" $nft -f -
 	fi
+}
+
+testrun() {
+	clear_counters
 
 	# test 1: martian traffic should fail rpfilter matches
 	netns_ping "$ns1" -I v0 192.168.42.1 && \
···
 
 	ipt_zero_rule "$iptables" || die "iptables matched martian"
 	ipt_zero_rule "$ip6tables" || die "ip6tables matched martian"
+	ipt_zero_reverse_rule "$iptables" && die "iptables not matched martian"
+	ipt_zero_reverse_rule "$ip6tables" && die "ip6tables not matched martian"
 	nft_zero_rule ip || die "nft IPv4 matched martian"
 	nft_zero_rule ip6 || die "nft IPv6 matched martian"
+
+	clear_counters
 
 	# test 2: rpfilter match should pass for regular traffic
 	netns_ping "$ns1" 192.168.23.1 || \
···
 
 	ipt_zero_rule "$iptables" && die "iptables match not effective"
 	ipt_zero_rule "$ip6tables" && die "ip6tables match not effective"
+	ipt_zero_reverse_rule "$iptables" || die "iptables match over-effective"
+	ipt_zero_reverse_rule "$ip6tables" || die "ip6tables match over-effective"
 	nft_zero_rule ip && die "nft IPv4 match not effective"
 	nft_zero_rule ip6 && die "nft IPv6 match not effective"