Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Merge in the left-over fixes before the net-next pull-request.

Conflicts:

drivers/net/ethernet/mediatek/mtk_ppe.c
  ae3ed15da5 ("net: ethernet: mtk_eth_soc: fix state in __mtk_foe_entry_clear")
  9d8cb4c096 ("net: ethernet: mtk_eth_soc: add foe_entry_size to mtk_eth_soc")
https://lore.kernel.org/all/6cb6893b-4921-a068-4c30-1109795110bb@tessares.net/

kernel/bpf/helpers.c
  8addbfc7b3 ("bpf: Gate dynptr API behind CAP_BPF")
  5679ff2f13 ("bpf: Move bpf_loop and bpf_for_each_map_elem under CAP_BPF")
  8a67f2de9b ("bpf: expose bpf_strtol and bpf_strtoul to all program types")
https://lore.kernel.org/all/20221003201957.13149-1-daniel@iogearbox.net/

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

MAINTAINERS

@@ -3833,6 +3833,7 @@ F:	kernel/bpf/dispatcher.c
 F:	kernel/bpf/trampoline.c
 F:	include/linux/bpf*
 F:	include/linux/filter.h
+F:	include/linux/tnum.h
 
 BPF [BTF]
 M:	Martin KaFai Lau <martin.lau@linux.dev>

drivers/isdn/mISDN/l1oip.h

@@ -59,6 +59,7 @@ struct l1oip {
 	int			bundle;		/* bundle channels in one frm */
 	int			codec;		/* codec to use for transmis. */
 	int			limit;		/* limit number of bchannels */
+	bool			shutdown;	/* if card is released */
 
 	/* timer */
 	struct timer_list	keep_tl;

drivers/isdn/mISDN/l1oip_core.c

@@ -275,7 +275,7 @@ l1oip_socket_send(struct l1oip *hc, u8 localcodec, u8 channel, u32 chanmask,
 	p = frame;
 
 	/* restart timer */
-	if (time_before(hc->keep_tl.expires, jiffies + 5 * HZ))
+	if (time_before(hc->keep_tl.expires, jiffies + 5 * HZ) && !hc->shutdown)
 		mod_timer(&hc->keep_tl, jiffies + L1OIP_KEEPALIVE * HZ);
 	else
 		hc->keep_tl.expires = jiffies + L1OIP_KEEPALIVE * HZ;
@@ -601,7 +601,9 @@ multiframe:
 		goto multiframe;
 
 	/* restart timer */
-	if (time_before(hc->timeout_tl.expires, jiffies + 5 * HZ) || !hc->timeout_on) {
+	if ((time_before(hc->timeout_tl.expires, jiffies + 5 * HZ) ||
+	     !hc->timeout_on) &&
+	    !hc->shutdown) {
 		hc->timeout_on = 1;
 		mod_timer(&hc->timeout_tl, jiffies + L1OIP_TIMEOUT * HZ);
 	} else /* only adjust timer */
@@ -1232,11 +1234,10 @@ release_card(struct l1oip *hc)
 {
 	int	ch;
 
-	if (timer_pending(&hc->keep_tl))
+	hc->shutdown = true;
-		del_timer(&hc->keep_tl);
 
-	if (timer_pending(&hc->timeout_tl))
+	del_timer_sync(&hc->keep_tl);
-		del_timer(&hc->timeout_tl);
+	del_timer_sync(&hc->timeout_tl);
 
 	cancel_work_sync(&hc->workq);
 

drivers/net/ethernet/atheros/alx/main.c

@@ -1912,11 +1912,14 @@ static int alx_suspend(struct device *dev)
 
 	if (!netif_running(alx->dev))
 		return 0;
+
+	rtnl_lock();
 	netif_device_detach(alx->dev);
 
 	mutex_lock(&alx->mtx);
 	__alx_stop(alx);
 	mutex_unlock(&alx->mtx);
+	rtnl_unlock();
 
 	return 0;
 }
@@ -1927,6 +1930,7 @@ static int alx_resume(struct device *dev)
 	struct alx_hw *hw = &alx->hw;
 	int err;
 
+	rtnl_lock();
 	mutex_lock(&alx->mtx);
 	alx_reset_phy(hw);
 
@@ -1943,6 +1947,7 @@ static int alx_resume(struct device *dev)
 
 unlock:
 	mutex_unlock(&alx->mtx);
+	rtnl_unlock();
 	return err;
 }
 

drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c

@@ -787,6 +787,7 @@ static void bnx2x_tpa_stop(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 			BNX2X_ERR("skb_put is about to fail...  pad %d  len %d  rx_buf_size %d\n",
 				  pad, len, fp->rx_buf_size);
 			bnx2x_panic();
+			bnx2x_frag_free(fp, new_data);
 			return;
 		}
 #endif

drivers/net/ethernet/marvell/mvpp2/mvpp2.h

@@ -1530,6 +1530,7 @@ u32 mvpp2_read(struct mvpp2 *priv, u32 offset);
 void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name);
 
 void mvpp2_dbgfs_cleanup(struct mvpp2 *priv);
+void mvpp2_dbgfs_exit(void);
 
 void mvpp23_rx_fifo_fc_en(struct mvpp2 *priv, int port, bool en);
 

drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c

@@ -691,6 +691,13 @@ static int mvpp2_dbgfs_port_init(struct dentry *parent,
 	return 0;
 }
 
+static struct dentry *mvpp2_root;
+
+void mvpp2_dbgfs_exit(void)
+{
+	debugfs_remove(mvpp2_root);
+}
+
 void mvpp2_dbgfs_cleanup(struct mvpp2 *priv)
 {
 	debugfs_remove_recursive(priv->dbgfs_dir);
@@ -700,10 +707,9 @@ void mvpp2_dbgfs_cleanup(struct mvpp2 *priv)
 
 void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name)
 {
-	struct dentry *mvpp2_dir, *mvpp2_root;
+	struct dentry *mvpp2_dir;
 	int ret, i;
 
-	mvpp2_root = debugfs_lookup(MVPP2_DRIVER_NAME, NULL);
 	if (!mvpp2_root)
 		mvpp2_root = debugfs_create_dir(MVPP2_DRIVER_NAME, NULL);
 

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

@@ -7704,7 +7704,18 @@ static struct platform_driver mvpp2_driver = {
 	},
 };
 
-module_platform_driver(mvpp2_driver);
+static int __init mvpp2_driver_init(void)
+{
+	return platform_driver_register(&mvpp2_driver);
+}
+module_init(mvpp2_driver_init);
+
+static void __exit mvpp2_driver_exit(void)
+{
+	platform_driver_unregister(&mvpp2_driver);
+	mvpp2_dbgfs_exit();
+}
+module_exit(mvpp2_driver_exit);
 
 MODULE_DESCRIPTION("Marvell PPv2 Ethernet Driver - www.marvell.com");
 MODULE_AUTHOR("Marcin Wojtas <mw@semihalf.com>");

drivers/net/ethernet/marvell/prestera/prestera_acl.c

@@ -185,10 +185,14 @@ err_rhashtable_init:
 	return ERR_PTR(err);
 }
 
-void prestera_acl_ruleset_keymask_set(struct prestera_acl_ruleset *ruleset,
+int prestera_acl_ruleset_keymask_set(struct prestera_acl_ruleset *ruleset,
-				      void *keymask)
+				     void *keymask)
 {
 	ruleset->keymask = kmemdup(keymask, ACL_KEYMASK_SIZE, GFP_KERNEL);
+	if (!ruleset->keymask)
+		return -ENOMEM;
+
+	return 0;
 }
 
 int prestera_acl_ruleset_offload(struct prestera_acl_ruleset *ruleset)

drivers/net/ethernet/marvell/prestera/prestera_acl.h

@@ -185,8 +185,8 @@ struct prestera_acl_ruleset *
 prestera_acl_ruleset_lookup(struct prestera_acl *acl,
 			    struct prestera_flow_block *block,
 			    u32 chain_index);
-void prestera_acl_ruleset_keymask_set(struct prestera_acl_ruleset *ruleset,
+int prestera_acl_ruleset_keymask_set(struct prestera_acl_ruleset *ruleset,
-				      void *keymask);
+				     void *keymask);
 bool prestera_acl_ruleset_is_offload(struct prestera_acl_ruleset *ruleset);
 int prestera_acl_ruleset_offload(struct prestera_acl_ruleset *ruleset);
 void prestera_acl_ruleset_put(struct prestera_acl_ruleset *ruleset);

drivers/net/ethernet/marvell/prestera/prestera_flower.c

@@ -500,7 +500,9 @@ int prestera_flower_tmplt_create(struct prestera_flow_block *block,
 	}
 
 	/* preserve keymask/template to this ruleset */
-	prestera_acl_ruleset_keymask_set(ruleset, rule.re_key.match.mask);
+	err = prestera_acl_ruleset_keymask_set(ruleset, rule.re_key.match.mask);
+	if (err)
+		goto err_ruleset_keymask_set;
 
 	/* skip error, as it is not possible to reject template operation,
 	 * so, keep the reference to the ruleset for rules to be added
@@ -516,6 +518,8 @@ int prestera_flower_tmplt_create(struct prestera_flow_block *block,
 	list_add_rcu(&template->list, &block->template_list);
 	return 0;
 
+err_ruleset_keymask_set:
+	prestera_acl_ruleset_put(ruleset);
 err_ruleset_get:
 	kfree(template);
 err_malloc:

drivers/net/ethernet/mediatek/mtk_ppe.c

@@ -442,7 +442,7 @@ __mtk_foe_entry_clear(struct mtk_ppe *ppe, struct mtk_flow_entry *entry)
 		struct mtk_foe_entry *hwe = mtk_foe_get_entry(ppe, entry->hash);
 
 		hwe->ib1 &= ~MTK_FOE_IB1_STATE;
-		hwe->ib1 |= FIELD_PREP(MTK_FOE_IB1_STATE, MTK_FOE_STATE_UNBIND);
+		hwe->ib1 |= FIELD_PREP(MTK_FOE_IB1_STATE, MTK_FOE_STATE_INVALID);
 		dma_wmb();
 	}
 	entry->hash = 0xffff;

drivers/net/ethernet/microchip/lan743x_ptp.c

@@ -1049,6 +1049,10 @@ static int lan743x_ptpci_verify_pin_config(struct ptp_clock_info *ptp,
 					   enum ptp_pin_function func,
 					   unsigned int chan)
 {
+	struct lan743x_ptp *lan_ptp =
+		container_of(ptp, struct lan743x_ptp, ptp_clock_info);
+	struct lan743x_adapter *adapter =
+		container_of(lan_ptp, struct lan743x_adapter, ptp);
 	int result = 0;
 
 	/* Confirm the requested function is supported. Parameter
@@ -1057,7 +1061,10 @@ static int lan743x_ptpci_verify_pin_config(struct ptp_clock_info *ptp,
 	switch (func) {
 	case PTP_PF_NONE:
 	case PTP_PF_PEROUT:
+		break;
 	case PTP_PF_EXTTS:
+		if (!adapter->is_pci11x1x)
+			result = -1;
 		break;
 	case PTP_PF_PHYSYNC:
 	default:

drivers/net/ethernet/microchip/sparx5/sparx5_main.h

@@ -305,7 +305,7 @@ struct frame_info {
 void sparx5_xtr_flush(struct sparx5 *sparx5, u8 grp);
 void sparx5_ifh_parse(u32 *ifh, struct frame_info *info);
 irqreturn_t sparx5_xtr_handler(int irq, void *_priv);
-int sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev);
+netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev);
 int sparx5_manual_injection_mode(struct sparx5 *sparx5);
 void sparx5_port_inj_timer_setup(struct sparx5_port *port);
 

drivers/net/ethernet/microchip/sparx5/sparx5_packet.c

@@ -222,13 +222,13 @@ static int sparx5_inject(struct sparx5 *sparx5,
 	return NETDEV_TX_OK;
 }
 
-int sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev)
+netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev)
 {
 	struct net_device_stats *stats = &dev->stats;
 	struct sparx5_port *port = netdev_priv(dev);
 	struct sparx5 *sparx5 = port->sparx5;
 	u32 ifh[IFH_LEN];
-	int ret;
+	netdev_tx_t ret;
 
 	memset(ifh, 0, IFH_LEN * 4);
 	sparx5_set_port_ifh(ifh, port->portno);

drivers/net/ethernet/sunplus/spl2sw_driver.c

@@ -249,8 +249,8 @@ static int spl2sw_nvmem_get_mac_address(struct device *dev, struct device_node *
 
 	/* Check if mac address is valid */
 	if (!is_valid_ether_addr(mac)) {
-		kfree(mac);
 		dev_info(dev, "Invalid mac address in nvmem (%pM)!\n", mac);
+		kfree(mac);
 		return -EINVAL;
 	}
 

drivers/net/usb/r8152.c

@@ -1875,7 +1875,9 @@ static void intr_callback(struct urb *urb)
 			   "Stop submitting intr, status %d\n", status);
 		return;
 	case -EOVERFLOW:
-		netif_info(tp, intr, tp->netdev, "intr status -EOVERFLOW\n");
+		if (net_ratelimit())
+			netif_info(tp, intr, tp->netdev,
+				   "intr status -EOVERFLOW\n");
 		goto resubmit;
 	/* -EPIPE:  should clear the halt */
 	default:

drivers/net/wwan/iosm/iosm_ipc_wwan.c

@@ -323,15 +323,16 @@ struct iosm_wwan *ipc_wwan_init(struct iosm_imem *ipc_imem, struct device *dev)
 	ipc_wwan->dev = dev;
 	ipc_wwan->ipc_imem = ipc_imem;
 
+	mutex_init(&ipc_wwan->if_mutex);
+
 	/* WWAN core will create a netdev for the default IP MUX channel */
 	if (wwan_register_ops(ipc_wwan->dev, &iosm_wwan_ops, ipc_wwan,
 			      IP_MUX_SESSION_DEFAULT)) {
+		mutex_destroy(&ipc_wwan->if_mutex);
 		kfree(ipc_wwan);
 		return NULL;
 	}
 
-	mutex_init(&ipc_wwan->if_mutex);
-
 	return ipc_wwan;
 }
 

drivers/vhost/vsock.c

@@ -393,7 +393,7 @@ vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq,
 		return NULL;
 	}
 
-	pkt->buf = kmalloc(pkt->len, GFP_KERNEL);
+	pkt->buf = kvmalloc(pkt->len, GFP_KERNEL);
 	if (!pkt->buf) {
 		kfree(pkt);
 		return NULL;

include/linux/tcp.h

@@ -295,7 +295,7 @@ struct tcp_sock {
 	u32	packets_out;	/* Packets which are "in flight"	*/
 	u32	retrans_out;	/* Retransmitted packets out		*/
 	u32	max_packets_out;  /* max packets_out in last window */
-	u32	max_packets_seq;  /* right edge of max_packets_out flight */
+	u32	cwnd_usage_seq;  /* right edge of cwnd usage tracking flight */
 
 	u16	urg_data;	/* Saved octet of OOB data and control flags */
 	u8	ecn_flags;	/* ECN status bits.			*/

include/net/tcp.h

@@ -1302,11 +1302,14 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 
+	if (tp->is_cwnd_limited)
+		return true;
+
 	/* If in slow start, ensure cwnd grows to twice what was ACKed. */
 	if (tcp_in_slow_start(tp))
 		return tcp_snd_cwnd(tp) < 2 * tp->max_packets_out;
 
-	return tp->is_cwnd_limited;
+	return false;
 }
 
 /* BBR congestion control needs pacing.

include/net/xsk_buff_pool.h

@@ -95,7 +95,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 						struct xdp_umem *umem);
 int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
 		  u16 queue_id, u16 flags);
-int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem,
+int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_sock *umem_xs,
 			 struct net_device *dev, u16 queue_id);
 int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs);
 void xp_destroy(struct xsk_buff_pool *pool);

include/uapi/linux/bpf.h

@@ -1259,7 +1259,7 @@ enum {
 
 /* Query effective (directly attached + inherited from ancestor cgroups)
  * programs that will be executed for events within a cgroup.
- * attach_flags with this flag are returned only for directly attached programs.
+ * attach_flags with this flag are always returned 0.
  */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
@@ -1458,7 +1458,10 @@ union bpf_attr {
 		__u32		attach_flags;
 		__aligned_u64	prog_ids;
 		__u32		prog_cnt;
-		__aligned_u64	prog_attach_flags; /* output: per-program attach_flags */
+		/* output: per-program attach_flags.
+		 * not allowed to be set during effective query.
+		 */
+		__aligned_u64	prog_attach_flags;
 	} query;
 
 	struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */

kernel/bpf/btf.c

@@ -3128,7 +3128,7 @@ static int btf_struct_resolve(struct btf_verifier_env *env,
 	if (v->next_member) {
 		const struct btf_type *last_member_type;
 		const struct btf_member *last_member;
-		u16 last_member_type_id;
+		u32 last_member_type_id;
 
 		last_member = btf_type_member(v->t) + v->next_member - 1;
 		last_member_type_id = last_member->type;

kernel/bpf/cgroup.c

@@ -1020,6 +1020,7 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 			      union bpf_attr __user *uattr)
 {
 	__u32 __user *prog_attach_flags = u64_to_user_ptr(attr->query.prog_attach_flags);
+	bool effective_query = attr->query.query_flags & BPF_F_QUERY_EFFECTIVE;
 	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
 	enum bpf_attach_type type = attr->query.attach_type;
 	enum cgroup_bpf_attach_type from_atype, to_atype;
@@ -1029,8 +1030,12 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 	int total_cnt = 0;
 	u32 flags;
 
+	if (effective_query && prog_attach_flags)
+		return -EINVAL;
+
 	if (type == BPF_LSM_CGROUP) {
-		if (attr->query.prog_cnt && prog_ids && !prog_attach_flags)
+		if (!effective_query && attr->query.prog_cnt &&
+		    prog_ids && !prog_attach_flags)
 			return -EINVAL;
 
 		from_atype = CGROUP_LSM_START;
@@ -1045,7 +1050,7 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 	}
 
 	for (atype = from_atype; atype <= to_atype; atype++) {
-		if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) {
+		if (effective_query) {
 			effective = rcu_dereference_protected(cgrp->bpf.effective[atype],
 							      lockdep_is_held(&cgroup_mutex));
 			total_cnt += bpf_prog_array_length(effective);
@@ -1054,6 +1059,8 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 		}
 	}
 
+	/* always output uattr->query.attach_flags as 0 during effective query */
+	flags = effective_query ? 0 : flags;
 	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
 		return -EFAULT;
 	if (copy_to_user(&uattr->query.prog_cnt, &total_cnt, sizeof(total_cnt)))
@@ -1068,7 +1075,7 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 	}
 
 	for (atype = from_atype; atype <= to_atype && total_cnt; atype++) {
-		if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) {
+		if (effective_query) {
 			effective = rcu_dereference_protected(cgrp->bpf.effective[atype],
 							      lockdep_is_held(&cgroup_mutex));
 			cnt = min_t(int, bpf_prog_array_length(effective), total_cnt);
@@ -1090,15 +1097,16 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 				if (++i == cnt)
 					break;
 			}
-		}
 
-		if (prog_attach_flags) {
+			if (prog_attach_flags) {
-			flags = cgrp->bpf.flags[atype];
+				flags = cgrp->bpf.flags[atype];
 
-			for (i = 0; i < cnt; i++)
+				for (i = 0; i < cnt; i++)
-				if (copy_to_user(prog_attach_flags + i, &flags, sizeof(flags)))
+					if (copy_to_user(prog_attach_flags + i,
-					return -EFAULT;
+							 &flags, sizeof(flags)))
-			prog_attach_flags += cnt;
+						return -EFAULT;
+				prog_attach_flags += cnt;
+			}
 		}
 
 		prog_ids += cnt;

kernel/bpf/helpers.c

@@ -1609,26 +1609,12 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_ringbuf_discard_proto;
 	case BPF_FUNC_ringbuf_query:
 		return &bpf_ringbuf_query_proto;
-	case BPF_FUNC_ringbuf_reserve_dynptr:
-		return &bpf_ringbuf_reserve_dynptr_proto;
-	case BPF_FUNC_ringbuf_submit_dynptr:
-		return &bpf_ringbuf_submit_dynptr_proto;
-	case BPF_FUNC_ringbuf_discard_dynptr:
-		return &bpf_ringbuf_discard_dynptr_proto;
 	case BPF_FUNC_strncmp:
 		return &bpf_strncmp_proto;
 	case BPF_FUNC_strtol:
 		return &bpf_strtol_proto;
 	case BPF_FUNC_strtoul:
 		return &bpf_strtoul_proto;
-	case BPF_FUNC_dynptr_from_mem:
-		return &bpf_dynptr_from_mem_proto;
-	case BPF_FUNC_dynptr_read:
-		return &bpf_dynptr_read_proto;
-	case BPF_FUNC_dynptr_write:
-		return &bpf_dynptr_write_proto;
-	case BPF_FUNC_dynptr_data:
-		return &bpf_dynptr_data_proto;
 	default:
 		break;
 	}
@@ -1663,6 +1649,20 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_loop_proto;
 	case BPF_FUNC_user_ringbuf_drain:
 		return &bpf_user_ringbuf_drain_proto;
+	case BPF_FUNC_ringbuf_reserve_dynptr:
+		return &bpf_ringbuf_reserve_dynptr_proto;
+	case BPF_FUNC_ringbuf_submit_dynptr:
+		return &bpf_ringbuf_submit_dynptr_proto;
+	case BPF_FUNC_ringbuf_discard_dynptr:
+		return &bpf_ringbuf_discard_dynptr_proto;
+	case BPF_FUNC_dynptr_from_mem:
+		return &bpf_dynptr_from_mem_proto;
+	case BPF_FUNC_dynptr_read:
+		return &bpf_dynptr_read_proto;
+	case BPF_FUNC_dynptr_write:
+		return &bpf_dynptr_write_proto;
+	case BPF_FUNC_dynptr_data:
+		return &bpf_dynptr_data_proto;
 	default:
 		break;
 	}

kernel/bpf/syscall.c

@@ -4405,7 +4405,9 @@ static int bpf_task_fd_query(const union bpf_attr *attr,
 	if (attr->task_fd_query.flags != 0)
 		return -EINVAL;
 
+	rcu_read_lock();
 	task = get_pid_task(find_vpid(pid), PIDTYPE_PID);
+	rcu_read_unlock();
 	if (!task)
 		return -ENOENT;
 

net/ieee802154/socket.c

@@ -251,6 +251,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 		return -EOPNOTSUPP;
 	}
 
+	if (!size)
+		return -EINVAL;
+
 	lock_sock(sk);
 	if (!sk->sk_bound_dev_if)
 		dev = dev_getfirstbyhwtype(sock_net(sk), ARPHRD_IEEE802154);

net/ipv4/esp4_offload.c

@@ -110,7 +110,10 @@ static struct sk_buff *xfrm4_tunnel_gso_segment(struct xfrm_state *x,
 						struct sk_buff *skb,
 						netdev_features_t features)
 {
-	return skb_eth_gso_segment(skb, features, htons(ETH_P_IP));
+	__be16 type = x->inner_mode.family == AF_INET6 ? htons(ETH_P_IPV6)
+						       : htons(ETH_P_IP);
+
+	return skb_eth_gso_segment(skb, features, type);
 }
 
 static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x,

net/ipv4/tcp.c

@@ -3136,6 +3136,8 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
 	tcp_snd_cwnd_set(tp, TCP_INIT_CWND);
 	tp->snd_cwnd_cnt = 0;
+	tp->is_cwnd_limited = 0;
+	tp->max_packets_out = 0;
 	tp->window_clamp = 0;
 	tp->delivered = 0;
 	tp->delivered_ce = 0;

net/ipv4/tcp_output.c

@@ -1875,15 +1875,20 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited)
 	const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	/* Track the maximum number of outstanding packets in each
+	/* Track the strongest available signal of the degree to which the cwnd
-	 * window, and remember whether we were cwnd-limited then.
+	 * is fully utilized. If cwnd-limited then remember that fact for the
+	 * current window. If not cwnd-limited then track the maximum number of
+	 * outstanding packets in the current window. (If cwnd-limited then we
+	 * chose to not update tp->max_packets_out to avoid an extra else
+	 * clause with no functional impact.)
 	 */
-	if (!before(tp->snd_una, tp->max_packets_seq) ||
+	if (!before(tp->snd_una, tp->cwnd_usage_seq) ||
-	    tp->packets_out > tp->max_packets_out ||
+	    is_cwnd_limited ||
-	    is_cwnd_limited) {
+	    (!tp->is_cwnd_limited &&
-		tp->max_packets_out = tp->packets_out;
+	     tp->packets_out > tp->max_packets_out)) {
-		tp->max_packets_seq = tp->snd_nxt;
 		tp->is_cwnd_limited = is_cwnd_limited;
+		tp->max_packets_out = tp->packets_out;
+		tp->cwnd_usage_seq = tp->snd_nxt;
 	}
 
 	if (tcp_is_cwnd_limited(sk)) {

net/ipv6/esp6_offload.c

@@ -145,7 +145,10 @@ static struct sk_buff *xfrm6_tunnel_gso_segment(struct xfrm_state *x,
 						struct sk_buff *skb,
 						netdev_features_t features)
 {
-	return skb_eth_gso_segment(skb, features, htons(ETH_P_IPV6));
+	__be16 type = x->inner_mode.family == AF_INET ? htons(ETH_P_IP)
+						      : htons(ETH_P_IPV6);
+
+	return skb_eth_gso_segment(skb, features, type);
 }
 
 static struct sk_buff *xfrm6_transport_gso_segment(struct xfrm_state *x,

net/rds/tcp.c

@@ -166,10 +166,10 @@ void rds_tcp_reset_callbacks(struct socket *sock,
 	 */
 	atomic_set(&cp->cp_state, RDS_CONN_RESETTING);
 	wait_event(cp->cp_waitq, !test_bit(RDS_IN_XMIT, &cp->cp_flags));
-	lock_sock(osock->sk);
 	/* reset receive side state for rds_tcp_data_recv() for osock  */
 	cancel_delayed_work_sync(&cp->cp_send_w);
 	cancel_delayed_work_sync(&cp->cp_recv_w);
+	lock_sock(osock->sk);
 	if (tc->t_tinc) {
 		rds_inc_put(&tc->t_tinc->ti_inc);
 		tc->t_tinc = NULL;

net/sctp/auth.c

@@ -863,12 +863,17 @@ int sctp_auth_set_key(struct sctp_endpoint *ep,
 	}
 
 	list_del_init(&shkey->key_list);
-	sctp_auth_shkey_release(shkey);
 	list_add(&cur_key->key_list, sh_keys);
 
-	if (asoc && asoc->active_key_id == auth_key->sca_keynumber)
+	if (asoc && asoc->active_key_id == auth_key->sca_keynumber &&
-		sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL);
+	    sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL)) {
+		list_del_init(&cur_key->key_list);
+		sctp_auth_shkey_release(cur_key);
+		list_add(&shkey->key_list, sh_keys);
+		return -ENOMEM;
+	}
 
+	sctp_auth_shkey_release(shkey);
 	return 0;
 }
 
@@ -902,8 +907,13 @@ int sctp_auth_set_active_key(struct sctp_endpoint *ep,
 		return -EINVAL;
 
 	if (asoc) {
+		__u16  active_key_id = asoc->active_key_id;
+
 		asoc->active_key_id = key_id;
-		sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL);
+		if (sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL)) {
+			asoc->active_key_id = active_key_id;
+			return -ENOMEM;
+		}
 	} else
 		ep->active_key_id = key_id;
 

net/unix/af_unix.c

@@ -569,12 +569,6 @@ static void unix_sock_destructor(struct sock *sk)
 
 	skb_queue_purge(&sk->sk_receive_queue);
 
-#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
-	if (u->oob_skb) {
-		kfree_skb(u->oob_skb);
-		u->oob_skb = NULL;
-	}
-#endif
 	DEBUG_NET_WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc));
 	DEBUG_NET_WARN_ON_ONCE(!sk_unhashed(sk));
 	DEBUG_NET_WARN_ON_ONCE(sk->sk_socket);
@@ -620,6 +614,13 @@ static void unix_release_sock(struct sock *sk, int embrion)
 
 	unix_state_unlock(sk);
 
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+	if (u->oob_skb) {
+		kfree_skb(u->oob_skb);
+		u->oob_skb = NULL;
+	}
+#endif
+
 	wake_up_interruptible_all(&u->peer_wait);
 
 	if (skpair != NULL) {

net/vmw_vsock/virtio_transport_common.c

@@ -1339,7 +1339,7 @@ EXPORT_SYMBOL_GPL(virtio_transport_recv_pkt);
 
 void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt)
 {
-	kfree(pkt->buf);
+	kvfree(pkt->buf);
 	kfree(pkt);
 }
 EXPORT_SYMBOL_GPL(virtio_transport_free_pkt);

net/xdp/xsk.c

@@ -355,16 +355,15 @@ static u32 xsk_tx_peek_release_fallback(struct xsk_buff_pool *pool, u32 max_entr
 	return nb_pkts;
 }
 
-u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max_entries)
+u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 nb_pkts)
 {
 	struct xdp_sock *xs;
-	u32 nb_pkts;
 
 	rcu_read_lock();
 	if (!list_is_singular(&pool->xsk_tx_list)) {
 		/* Fallback to the non-batched version */
 		rcu_read_unlock();
-		return xsk_tx_peek_release_fallback(pool, max_entries);
+		return xsk_tx_peek_release_fallback(pool, nb_pkts);
 	}
 
 	xs = list_first_or_null_rcu(&pool->xsk_tx_list, struct xdp_sock, tx_list);
@@ -373,12 +372,7 @@ u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max_entries)
 		goto out;
 	}
 
-	max_entries = xskq_cons_nb_entries(xs->tx, max_entries);
+	nb_pkts = xskq_cons_nb_entries(xs->tx, nb_pkts);
-	nb_pkts = xskq_cons_read_desc_batch(xs->tx, pool, max_entries);
-	if (!nb_pkts) {
-		xs->tx->queue_empty_descs++;
-		goto out;
-	}
 
 	/* This is the backpressure mechanism for the Tx path. Try to
 	 * reserve space in the completion queue for all packets, but
@@ -386,12 +380,18 @@ u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max_entries)
 	 * packets. This avoids having to implement any buffering in
 	 * the Tx path.
 	 */
-	nb_pkts = xskq_prod_reserve_addr_batch(pool->cq, pool->tx_descs, nb_pkts);
+	nb_pkts = xskq_prod_nb_free(pool->cq, nb_pkts);
 	if (!nb_pkts)
 		goto out;
 
-	xskq_cons_release_n(xs->tx, max_entries);
+	nb_pkts = xskq_cons_read_desc_batch(xs->tx, pool, nb_pkts);
+	if (!nb_pkts) {
+		xs->tx->queue_empty_descs++;
+		goto out;
+	}
+
 	__xskq_cons_release(xs->tx);
+	xskq_prod_write_addr_batch(pool->cq, pool->tx_descs, nb_pkts);
 	xs->sk.sk_write_space(&xs->sk);
 
 out:
@@ -954,8 +954,8 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 				goto out_unlock;
 			}
 
-			err = xp_assign_dev_shared(xs->pool, umem_xs->umem,
+			err = xp_assign_dev_shared(xs->pool, umem_xs, dev,
-						   dev, qid);
+						   qid);
 			if (err) {
 				xp_destroy(xs->pool);
 				xs->pool = NULL;

net/xdp/xsk_buff_pool.c

@@ -212,17 +212,18 @@ err_unreg_pool:
 	return err;
 }
 
-int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem,
+int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_sock *umem_xs,
 			 struct net_device *dev, u16 queue_id)
 {
 	u16 flags;
+	struct xdp_umem *umem = umem_xs->umem;
 
 	/* One fill and completion ring required for each queue id. */
 	if (!pool->fq || !pool->cq)
 		return -EINVAL;
 
 	flags = umem->zc ? XDP_ZEROCOPY : XDP_COPY;
-	if (pool->uses_need_wakeup)
+	if (umem_xs->pool->uses_need_wakeup)
 		flags |= XDP_USE_NEED_WAKEUP;
 
 	return xp_assign_dev(pool, dev, queue_id, flags);

net/xdp/xsk_queue.h

@@ -205,6 +205,11 @@ static inline bool xskq_cons_read_desc(struct xsk_queue *q,
 	return false;
 }
 
+static inline void xskq_cons_release_n(struct xsk_queue *q, u32 cnt)
+{
+	q->cached_cons += cnt;
+}
+
 static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q, struct xsk_buff_pool *pool,
 					    u32 max)
 {
@@ -226,6 +231,8 @@ static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q, struct xsk_buff
 		cached_cons++;
 	}
 
+	/* Release valid plus any invalid entries */
+	xskq_cons_release_n(q, cached_cons - q->cached_cons);
 	return nb_entries;
 }
 
@@ -291,11 +298,6 @@ static inline void xskq_cons_release(struct xsk_queue *q)
 	q->cached_cons++;
 }
 
-static inline void xskq_cons_release_n(struct xsk_queue *q, u32 cnt)
-{
-	q->cached_cons += cnt;
-}
-
 static inline u32 xskq_cons_present_entries(struct xsk_queue *q)
 {
 	/* No barriers needed since data is not accessed */
@@ -350,21 +352,17 @@ static inline int xskq_prod_reserve_addr(struct xsk_queue *q, u64 addr)
 	return 0;
 }
 
-static inline u32 xskq_prod_reserve_addr_batch(struct xsk_queue *q, struct xdp_desc *descs,
+static inline void xskq_prod_write_addr_batch(struct xsk_queue *q, struct xdp_desc *descs,
-					       u32 max)
+					      u32 nb_entries)
 {
 	struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
-	u32 nb_entries, i, cached_prod;
+	u32 i, cached_prod;
-
-	nb_entries = xskq_prod_nb_free(q, max);
 
 	/* A, matches D */
 	cached_prod = q->cached_prod;
 	for (i = 0; i < nb_entries; i++)
 		ring->desc[cached_prod++ & q->ring_mask] = descs[i].addr;
 	q->cached_prod = cached_prod;
-
-	return nb_entries;
 }
 
 static inline int xskq_prod_reserve_desc(struct xsk_queue *q,

net/xfrm/xfrm_input.c

@@ -25,7 +25,8 @@
 #include "xfrm_inout.h"
 
 struct xfrm_trans_tasklet {
-	struct tasklet_struct tasklet;
+	struct work_struct work;
+	spinlock_t queue_lock;
 	struct sk_buff_head queue;
 };
 
@@ -763,18 +764,22 @@ int xfrm_input_resume(struct sk_buff *skb, int nexthdr)
 }
 EXPORT_SYMBOL(xfrm_input_resume);
 
-static void xfrm_trans_reinject(struct tasklet_struct *t)
+static void xfrm_trans_reinject(struct work_struct *work)
 {
-	struct xfrm_trans_tasklet *trans = from_tasklet(trans, t, tasklet);
+	struct xfrm_trans_tasklet *trans = container_of(work, struct xfrm_trans_tasklet, work);
 	struct sk_buff_head queue;
 	struct sk_buff *skb;
 
 	__skb_queue_head_init(&queue);
+	spin_lock_bh(&trans->queue_lock);
 	skb_queue_splice_init(&trans->queue, &queue);
+	spin_unlock_bh(&trans->queue_lock);
 
+	local_bh_disable();
 	while ((skb = __skb_dequeue(&queue)))
 		XFRM_TRANS_SKB_CB(skb)->finish(XFRM_TRANS_SKB_CB(skb)->net,
 					       NULL, skb);
+	local_bh_enable();
 }
 
 int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
@@ -792,8 +797,10 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
 
 	XFRM_TRANS_SKB_CB(skb)->finish = finish;
 	XFRM_TRANS_SKB_CB(skb)->net = net;
+	spin_lock_bh(&trans->queue_lock);
 	__skb_queue_tail(&trans->queue, skb);
-	tasklet_schedule(&trans->tasklet);
+	spin_unlock_bh(&trans->queue_lock);
+	schedule_work(&trans->work);
 	return 0;
 }
 EXPORT_SYMBOL(xfrm_trans_queue_net);
@@ -820,7 +827,8 @@ void __init xfrm_input_init(void)
 		struct xfrm_trans_tasklet *trans;
 
 		trans = &per_cpu(xfrm_trans_tasklet, i);
+		spin_lock_init(&trans->queue_lock);
 		__skb_queue_head_init(&trans->queue);
-		tasklet_setup(&trans->tasklet, xfrm_trans_reinject);
+		INIT_WORK(&trans->work, xfrm_trans_reinject);
 	}
 }

net/xfrm/xfrm_ipcomp.c

@@ -203,6 +203,7 @@ static void ipcomp_free_scratches(void)
 		vfree(*per_cpu_ptr(scratches, i));
 
 	free_percpu(scratches);
+	ipcomp_scratches = NULL;
 }
 
 static void * __percpu *ipcomp_alloc_scratches(void)

tools/bpf/bpftool/cgroup.c

@@ -136,8 +136,8 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type,
 			jsonw_string_field(json_wtr, "attach_type", attach_type_str);
 		else
 			jsonw_uint_field(json_wtr, "attach_type", attach_type);
-		jsonw_string_field(json_wtr, "attach_flags",
+		if (!(query_flags & BPF_F_QUERY_EFFECTIVE))
-				   attach_flags_str);
+			jsonw_string_field(json_wtr, "attach_flags", attach_flags_str);
 		jsonw_string_field(json_wtr, "name", prog_name);
 		if (attach_btf_name)
 			jsonw_string_field(json_wtr, "attach_btf_name", attach_btf_name);
@@ -150,7 +150,10 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type,
 			printf("%-15s", attach_type_str);
 		else
 			printf("type %-10u", attach_type);
-		printf(" %-15s %-15s", attach_flags_str, prog_name);
+		if (query_flags & BPF_F_QUERY_EFFECTIVE)
+			printf(" %-15s", prog_name);
+		else
+			printf(" %-15s %-15s", attach_flags_str, prog_name);
 		if (attach_btf_name)
 			printf(" %-15s", attach_btf_name);
 		else if (info.attach_btf_id)
@@ -195,6 +198,32 @@ static int cgroup_has_attached_progs(int cgroup_fd)
 
 	return no_prog ? 0 : 1;
 }
+
+static int show_effective_bpf_progs(int cgroup_fd, enum bpf_attach_type type,
+				    int level)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, p);
+	__u32 prog_ids[1024] = {0};
+	__u32 iter;
+	int ret;
+
+	p.query_flags = query_flags;
+	p.prog_cnt = ARRAY_SIZE(prog_ids);
+	p.prog_ids = prog_ids;
+
+	ret = bpf_prog_query_opts(cgroup_fd, type, &p);
+	if (ret)
+		return ret;
+
+	if (p.prog_cnt == 0)
+		return 0;
+
+	for (iter = 0; iter < p.prog_cnt; iter++)
+		show_bpf_prog(prog_ids[iter], type, NULL, level);
+
+	return 0;
+}
+
 static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type,
 				   int level)
 {
@@ -245,6 +274,14 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type,
 	return 0;
 }
 
+static int show_bpf_progs(int cgroup_fd, enum bpf_attach_type type,
+			  int level)
+{
+	return query_flags & BPF_F_QUERY_EFFECTIVE ?
+	       show_effective_bpf_progs(cgroup_fd, type, level) :
+	       show_attached_bpf_progs(cgroup_fd, type, level);
+}
+
 static int do_show(int argc, char **argv)
 {
 	enum bpf_attach_type type;
@@ -292,6 +329,8 @@ static int do_show(int argc, char **argv)
 
 	if (json_output)
 		jsonw_start_array(json_wtr);
+	else if (query_flags & BPF_F_QUERY_EFFECTIVE)
+		printf("%-8s %-15s %-15s\n", "ID", "AttachType", "Name");
 	else
 		printf("%-8s %-15s %-15s %-15s\n", "ID", "AttachType",
 		       "AttachFlags", "Name");
@@ -304,7 +343,7 @@ static int do_show(int argc, char **argv)
 		 * If we were able to get the show for at least one
 		 * attach type, let's return 0.
 		 */
-		if (show_attached_bpf_progs(cgroup_fd, type, 0) == 0)
+		if (show_bpf_progs(cgroup_fd, type, 0) == 0)
 			ret = 0;
 	}
 
@@ -362,7 +401,7 @@ static int do_show_tree_fn(const char *fpath, const struct stat *sb,
 
 	btf_vmlinux = libbpf_find_kernel_btf();
 	for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++)
-		show_attached_bpf_progs(cgroup_fd, type, ftw->level);
+		show_bpf_progs(cgroup_fd, type, ftw->level);
 
 	if (errno == EINVAL)
 		/* Last attach type does not support query.
@@ -436,6 +475,11 @@ static int do_show_tree(int argc, char **argv)
 
 	if (json_output)
 		jsonw_start_array(json_wtr);
+	else if (query_flags & BPF_F_QUERY_EFFECTIVE)
+		printf("%s\n"
+		       "%-8s %-15s %-15s\n",
+		       "CgroupPath",
+		       "ID", "AttachType", "Name");
 	else
 		printf("%s\n"
 		       "%-8s %-15s %-15s %-15s\n",

tools/include/uapi/linux/bpf.h

@@ -1259,7 +1259,7 @@ enum {
 
 /* Query effective (directly attached + inherited from ancestor cgroups)
  * programs that will be executed for events within a cgroup.
- * attach_flags with this flag are returned only for directly attached programs.
+ * attach_flags with this flag are always returned 0.
  */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
@@ -1458,7 +1458,10 @@ union bpf_attr {
 		__u32		attach_flags;
 		__aligned_u64	prog_ids;
 		__u32		prog_cnt;
-		__aligned_u64	prog_attach_flags; /* output: per-program attach_flags */
+		/* output: per-program attach_flags.
+		 * not allowed to be set during effective query.
+		 */
+		__aligned_u64	prog_attach_flags;
 	} query;
 
 	struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */

tools/testing/selftests/bpf/prog_tests/cgroup_link.c

@@ -71,10 +71,9 @@ void serial_test_cgroup_link(void)
 
 	ping_and_check(cg_nr, 0);
 
-	/* query the number of effective progs and attach flags in root cg */
+	/* query the number of attached progs and attach flags in root cg */
 	err = bpf_prog_query(cgs[0].fd, BPF_CGROUP_INET_EGRESS,
-			     BPF_F_QUERY_EFFECTIVE, &attach_flags, NULL,
+			     0, &attach_flags, NULL, &prog_cnt);
-			     &prog_cnt);
 	CHECK_FAIL(err);
 	CHECK_FAIL(attach_flags != BPF_F_ALLOW_MULTI);
 	if (CHECK(prog_cnt != 1, "effect_cnt", "exp %d, got %d\n", 1, prog_cnt))
@@ -85,17 +84,15 @@ void serial_test_cgroup_link(void)
 			     BPF_F_QUERY_EFFECTIVE, NULL, NULL,
 			     &prog_cnt);
 	CHECK_FAIL(err);
-	CHECK_FAIL(attach_flags != BPF_F_ALLOW_MULTI);
 	if (CHECK(prog_cnt != cg_nr, "effect_cnt", "exp %d, got %d\n",
 		  cg_nr, prog_cnt))
 		goto cleanup;
 
 	/* query the effective prog IDs in last cg */
 	err = bpf_prog_query(cgs[last_cg].fd, BPF_CGROUP_INET_EGRESS,
-			     BPF_F_QUERY_EFFECTIVE, &attach_flags,
+			     BPF_F_QUERY_EFFECTIVE, NULL, prog_ids,
-			     prog_ids, &prog_cnt);
+			     &prog_cnt);
 	CHECK_FAIL(err);
-	CHECK_FAIL(attach_flags != BPF_F_ALLOW_MULTI);
 	if (CHECK(prog_cnt != cg_nr, "effect_cnt", "exp %d, got %d\n",
 		  cg_nr, prog_cnt))
 		goto cleanup;

tools/testing/selftests/bpf/xskxceiver.c

@@ -1842,6 +1842,8 @@ static struct ifobject *ifobject_create(void)
 	if (!ifobj->umem)
 		goto out_umem;
 
+	ifobj->ns_fd = -1;
+
 	return ifobj;
 
 out_umem:
@@ -1853,6 +1855,8 @@ out_xsk_arr:
 
 static void ifobject_delete(struct ifobject *ifobj)
 {
+	if (ifobj->ns_fd != -1)
+		close(ifobj->ns_fd);
 	free(ifobj->umem);
 	free(ifobj->xsk_arr);
 	free(ifobj);