diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2026-08-13 08:37:26 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2026-08-13 08:37:26 -0700 |
| commit | e14aacefb78d942d2308d9821fe52d75d21a824e (patch) | |
| tree | 1bad843db01ff93e3951865d1fdb7080e6ac2493 | |
| parent | 83a4f90e9835d3d61fe3dd39ffbbcac752467d09 (diff) | |
| parent | 9006c116dd111d457bf5d074990210f70a4ad2c8 (diff) | |
Merge tag 'net-7.2-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Paolo Abeni:
"Including fixes from netfilter.
There is a known WiFi/mt76 regression, waiting for a complete fix that
should land soonish.
Previous releases - regressions:
- tcp: fix icsk_ack.ato bitfield overflow
- af_unix: Unlink scc_entry in unix_del_edge()
- ipv4: fix use-after-free in fib_nhc_update_mtu()
- netfilter:
- ipset: fix refcount race between list:set GC and swap
- nf_tables_offload: suppress WARN_ON_ONCE for ENOMEM in abort
path
- sched: act_ct: fix sk_buff leak when the header checks reject a
packet
- sctp: clear new_transport when removing a peer
- dibs: correct freeing of dmb_clientid_arr
- ovpn: fix NULL dereference when killing missing key
- eth:
- veth: fix queue index used to wake the peer txq in veth_poll
- ngbe: fix NULL pointer dereference in non-MSI-X interrupt
enabling
- gve: fix zero-length skb frag with header-split
Previous releases - always broken:
- core: fix skb length accounting after generic XDP frag adjustment
- af_packet: don't send zero-byte data in tpacket_snd().
- eth:
- bnxt: avoid deadlock when canceling IRQ affinity notifier
- ipvlan: inherit needed_headroom and needed_tailroom from
phy_dev"
* tag 'net-7.2-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (55 commits)
l2tp: fix tunnel and session refcount leak on seq_file release
net/sched: cls_bpf: reject dev-bound programs bound to a different device
sctp: fix use-after-free of cached ASCONF chunk
net: ethernet: ti: am65-cpsw-nuss: Fix port_id extraction from SRC TAG
sctp: clear new_transport when removing a peer
net/dibs: Correct freeing of dmb_clientid_arr
net/sched: cls_u32: skip hash tables in u32_bind_class()
gve: fix NULL dereference due to missing ptp adjfine
gve: fix zero-length skb frag with header-split
net/sched: act_api: fix TOCTOU NULL deref on a->goto_chain
af_packet: Don't send zero-byte data in tpacket_snd().
tipc: read le->link under the node lock in tipc_node_link_down()
selftests: tls: cover splice after a failed decrypt
net/tls: Fail tls_sw_splice_read() after a failed async decrypt
net: ngbe: fix NULL pointer dereference in non-MSI-X interrupt enabling
net: tap: fix wrong transport_header when sending VLAN-tagged frame
net: packet: fix wrong transport_header when sending VLAN-tagged frame
vxlan: do not arm the ageing timer on a device that is down
ipv4: fix use-after-free in fib_nhc_update_mtu()
NTB: ntb_netdev: Preserve RX queue depth on allocation failure
...
76 files changed, 894 insertions, 327 deletions
@@ -212,6 +212,10 @@ Christophe Ricard <christophe.ricard@gmail.com> Christopher Obbard <christopher.obbard@linaro.org> <chris.obbard@collabora.com> Christoph Hellwig <hch@lst.de> Christoph Manszewski <c.manszewski@gmail.com> <christoph.manszewski@intel.com> +Christoph Paasch <cpaasch@openai.com> <christoph.paasch@gmail.com> +Christoph Paasch <cpaasch@openai.com> <christoph.paasch@student.uclouvain.be> +Christoph Paasch <cpaasch@openai.com> <christoph.paasch@uclouvain.be> +Christoph Paasch <cpaasch@openai.com> <cpaasch@apple.com> Chuck Lever <cel@kernel.org> <chuck.lever@oracle.com> Chuck Lever <cel@kernel.org> <cel@netapp.com> Chuck Lever <cel@kernel.org> <cel@citi.umich.edu> diff --git a/drivers/dibs/dibs_loopback.c b/drivers/dibs/dibs_loopback.c index fd5caf1e19a8..649e4e375be3 100644 --- a/drivers/dibs/dibs_loopback.c +++ b/drivers/dibs/dibs_loopback.c @@ -335,7 +335,6 @@ static int dibs_lo_dev_probe(void) return 0; err_reg: - kfree(dibs->dmb_clientid_arr); /* pairs with dibs_dev_alloc() */ put_device(&dibs->dev); kfree(ldev); diff --git a/drivers/dibs/dibs_main.c b/drivers/dibs/dibs_main.c index 4c26fd06973f..2b53a9d277dc 100644 --- a/drivers/dibs/dibs_main.c +++ b/drivers/dibs/dibs_main.c @@ -128,6 +128,7 @@ static void dibs_dev_release(struct device *dev) dibs = container_of(dev, struct dibs_dev, dev); + kfree(dibs->dmb_clientid_arr); kfree(dibs); } @@ -194,12 +195,13 @@ int dibs_dev_add(struct dibs_dev *dibs) ret = device_add(&dibs->dev); if (ret) - goto free_client_arr; + return ret; ret = sysfs_create_group(&dibs->dev.kobj, &dibs_dev_attr_group); if (ret) { dev_err(&dibs->dev, "sysfs_create_group failed for dibs_dev\n"); - goto err_device_del; + device_del(&dibs->dev); + return ret; } mutex_lock(&dibs_dev_list.mutex); mutex_lock(&clients_lock); @@ -214,13 +216,6 @@ int dibs_dev_add(struct dibs_dev *dibs) mutex_unlock(&dibs_dev_list.mutex); return 0; - -err_device_del: - device_del(&dibs->dev); -free_client_arr: - kfree(dibs->dmb_clientid_arr); - return ret; - } EXPORT_SYMBOL_GPL(dibs_dev_add); @@ -247,7 +242,6 @@ void dibs_dev_del(struct dibs_dev *dibs) mutex_unlock(&dibs_dev_list.mutex); device_del(&dibs->dev); - kfree(dibs->dmb_clientid_arr); } EXPORT_SYMBOL_GPL(dibs_dev_del); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 25099077fe4f..bc7b37cb74a7 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11789,10 +11789,21 @@ static void bnxt_irq_affinity_notify(struct irq_affinity_notify *notify, { struct bnxt_irq *irq; u16 tag; - int err; irq = container_of(notify, struct bnxt_irq, affinity_notify); +#ifdef CONFIG_RFS_ACCEL + if (irq->bp->dev->rx_cpu_rmap && irq->ring_nr < irq->bp->rx_nr_rings) { + int err; + + err = cpu_rmap_update(irq->bp->dev->rx_cpu_rmap, irq->ring_nr, + mask); + if (err) + netdev_warn(irq->bp->dev, + "aRFS rmap update failed: %d\n", err); + } +#endif + if (!irq->bp->tph_mode) return; @@ -11802,20 +11813,11 @@ static void bnxt_irq_affinity_notify(struct irq_affinity_notify *notify, return; if (pcie_tph_get_cpu_st(irq->bp->pdev, TPH_MEM_TYPE_VM, - cpumask_first(irq->cpu_mask), &tag)) + cpumask_first(mask), &tag)) return; - if (pcie_tph_set_st_entry(irq->bp->pdev, irq->msix_nr, tag)) - return; - - netdev_lock(irq->bp->dev); - if (netif_running(irq->bp->dev)) { - err = netdev_rx_queue_restart(irq->bp->dev, irq->ring_nr); - if (err) - netdev_err(irq->bp->dev, - "RX queue restart failed: err=%d\n", err); - } - netdev_unlock(irq->bp->dev); + WRITE_ONCE(irq->new_tag, tag); + bnxt_queue_sp_work(irq->bp, BNXT_TPH_UPDATE_SP_EVENT); } static void bnxt_irq_affinity_release(struct kref *ref) @@ -11866,10 +11868,6 @@ static void bnxt_free_irq(struct bnxt *bp) struct bnxt_irq *irq; int i; -#ifdef CONFIG_RFS_ACCEL - free_irq_cpu_rmap(bp->dev->rx_cpu_rmap); - bp->dev->rx_cpu_rmap = NULL; -#endif if (!bp->irq_tbl || !bp->bnapi) return; @@ -11878,27 +11876,35 @@ static void bnxt_free_irq(struct bnxt *bp) irq = &bp->irq_tbl[map_idx]; if (irq->requested) { + bnxt_release_irq_notifier(irq); + if (irq->have_cpumask) { irq_update_affinity_hint(irq->vector, NULL); free_cpumask_var(irq->cpu_mask); irq->have_cpumask = 0; } - bnxt_release_irq_notifier(irq); - free_irq(irq->vector, bp->bnapi[i]); } irq->requested = 0; + irq->tag = 0; + irq->new_tag = 0; } /* Disable TPH support */ pcie_disable_tph(bp->pdev); bp->tph_mode = 0; + +#ifdef CONFIG_RFS_ACCEL + free_irq_cpu_rmap(bp->dev->rx_cpu_rmap); + bp->dev->rx_cpu_rmap = NULL; +#endif } static int bnxt_request_irq(struct bnxt *bp) { + const int numa_node = dev_to_node(&bp->pdev->dev); struct cpu_rmap *rmap = NULL; int i, j, rc = 0; unsigned long flags = 0; @@ -11921,6 +11927,8 @@ static int bnxt_request_irq(struct bnxt *bp) for (i = 0, j = 0; i < bp->cp_nr_rings; i++) { int map_idx = bnxt_cp_num_to_irq_num(bp, i); struct bnxt_irq *irq = &bp->irq_tbl[map_idx]; + unsigned int cpu_num; + u16 tag; if (IS_ENABLED(CONFIG_RFS_ACCEL) && rmap && bp->bnapi[i]->rx_ring) { @@ -11939,32 +11947,31 @@ static int bnxt_request_irq(struct bnxt *bp) netif_napi_set_irq_locked(&bp->bnapi[i]->napi, irq->vector); irq->requested = 1; - if (zalloc_cpumask_var(&irq->cpu_mask, GFP_KERNEL)) { - int numa_node = dev_to_node(&bp->pdev->dev); - u16 tag; - - irq->have_cpumask = 1; - irq->msix_nr = map_idx; - irq->ring_nr = i; - cpumask_set_cpu(cpumask_local_spread(i, numa_node), - irq->cpu_mask); - rc = irq_update_affinity_hint(irq->vector, irq->cpu_mask); - if (rc) { - netdev_warn(bp->dev, - "Update affinity hint failed, IRQ = %d\n", - irq->vector); - break; - } + if (!zalloc_cpumask_var(&irq->cpu_mask, GFP_KERNEL)) + continue; - bnxt_register_irq_notifier(bp, irq); + irq->have_cpumask = 1; + irq->msix_nr = map_idx; + irq->ring_nr = i; + cpu_num = cpumask_local_spread(i, numa_node); + cpumask_set_cpu(cpu_num, irq->cpu_mask); + + /* Init ST table entry if we can get the mapping */ + if (!pcie_tph_get_cpu_st(bp->pdev, TPH_MEM_TYPE_VM, + cpu_num, &tag)) { + pcie_tph_set_st_entry(bp->pdev, irq->msix_nr, tag); + irq->tag = tag; + irq->new_tag = tag; + } - /* Init ST table entry */ - if (pcie_tph_get_cpu_st(irq->bp->pdev, TPH_MEM_TYPE_VM, - cpumask_first(irq->cpu_mask), - &tag)) - continue; + bnxt_register_irq_notifier(bp, irq); - pcie_tph_set_st_entry(irq->bp->pdev, irq->msix_nr, tag); + rc = irq_update_affinity_hint(irq->vector, irq->cpu_mask); + if (rc) { + netdev_warn(bp->dev, + "Update affinity hint failed, IRQ = %d\n", + irq->vector); + break; } } return rc; @@ -14468,6 +14475,43 @@ static void bnxt_rtnl_unlock_sp(struct bnxt *bp) rtnl_unlock(); } +static void bnxt_tph_update(struct bnxt *bp) +{ + struct net_device *dev = bp->dev; + int i; + + bnxt_lock_sp(bp); + if (!test_bit(BNXT_STATE_OPEN, &bp->state)) + goto unlock; + + for (i = 0; i < bp->rx_nr_rings; i++) { + struct bnxt_irq *irq; + int map_idx, err; + u16 tag; + + map_idx = bnxt_cp_num_to_irq_num(bp, i); + irq = &bp->irq_tbl[map_idx]; + tag = READ_ONCE(irq->new_tag); + if (irq->tag == tag) + continue; + + if (pcie_tph_set_st_entry(bp->pdev, irq->msix_nr, tag)) + continue; + + err = netdev_rx_queue_restart(dev, irq->ring_nr); + if (err) { + netdev_err(dev, "RX queue restart failed: err=%d\n", + err); + continue; + } + + irq->tag = tag; + } + +unlock: + bnxt_unlock_sp(bp); +} + /* Only called from bnxt_sp_task() */ static void bnxt_reset(struct bnxt *bp, bool silent) { @@ -14892,6 +14936,9 @@ static void bnxt_sp_task(struct work_struct *work) bnxt_devlink_health_fw_report(bp); } + if (test_and_clear_bit(BNXT_TPH_UPDATE_SP_EVENT, &bp->sp_event)) + bnxt_tph_update(bp); + smp_mb__before_atomic(); clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 44ea8fc7b766..dc8ec5e5733e 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1268,6 +1268,8 @@ struct bnxt_irq { struct bnxt *bp; int msix_nr; int ring_nr; + u16 tag; + u16 new_tag; struct irq_affinity_notify affinity_notify; }; @@ -2642,6 +2644,7 @@ struct bnxt { #define BNXT_RING_COAL_NOW_SP_EVENT 17 #define BNXT_FW_RESET_NOTIFY_SP_EVENT 18 #define BNXT_FW_EXCEPTION_SP_EVENT 19 +#define BNXT_TPH_UPDATE_SP_EVENT 20 #define BNXT_LINK_CFG_CHANGE_SP_EVENT 21 #define BNXT_THERMAL_THRESHOLD_SP_EVENT 22 #define BNXT_FW_ECHO_REQUEST_SP_EVENT 23 diff --git a/drivers/net/ethernet/google/gve/gve_ptp.c b/drivers/net/ethernet/google/gve/gve_ptp.c index 06b1cf4a5efc..1d6c59f4ead3 100644 --- a/drivers/net/ethernet/google/gve/gve_ptp.c +++ b/drivers/net/ethernet/google/gve/gve_ptp.c @@ -26,6 +26,11 @@ int gve_clock_nic_ts_read(struct gve_priv *priv) return 0; } +static int gve_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + return -EOPNOTSUPP; +} + static int gve_ptp_gettimex64(struct ptp_clock_info *info, struct timespec64 *ts, struct ptp_system_timestamp *sts) @@ -60,6 +65,7 @@ out: static const struct ptp_clock_info gve_ptp_caps = { .owner = THIS_MODULE, .name = "gve clock", + .adjfine = gve_ptp_adjfine, .gettimex64 = gve_ptp_gettimex64, .settime64 = gve_ptp_settime64, .do_aux_work = gve_ptp_do_aux_work, diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index 8271f731a91f..0ece2f6fdffb 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -886,6 +886,11 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, rx->rx_hsplit_unsplit_pkt += unsplit; rx->rx_hsplit_bytes += hdr_len; u64_stats_update_end(&rx->statss); + + if (!buf_len) { + gve_free_buffer(rx, buf_state); + return 0; + } } else if (!rx->ctx.skb_head && rx->dqo.page_pool && netmem_is_net_iov(buf_state->page_info.netmem)) { /* when header split is disabled, the header went to the packet diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 434a31080855..6330540979d7 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1310,6 +1310,8 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow, k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma); pkt_len = cppi5_hdesc_get_pktlen(desc_rx); cppi5_desc_get_tags_ids(&desc_rx->hdr, &port_id, NULL); + /* Port ID is contained in the lower 8-bits of the 16-bit Source Tag */ + port_id &= 0xFF; dev_dbg(dev, "%s rx port_id:%d\n", __func__, port_id); port = am65_common_get_port(common, port_id); ndev = port->ndev; diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c index a16221995909..cb653861aad8 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c @@ -180,8 +180,10 @@ static void ngbe_irq_enable(struct wx *wx, bool queues) /* mask interrupt */ if (queues) wx_intr_enable(wx, NGBE_INTR_ALL); - else + else if (wx->pdev->msix_enabled) wx_intr_enable(wx, NGBE_INTR_MISC(wx)); + else + wx_intr_enable(wx, BIT(0)); } /** diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index ed46439a9f4e..92d3d340281f 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -146,6 +146,8 @@ static int ipvlan_init(struct net_device *dev) dev->lltx = true; netif_inherit_tso_max(dev, phy_dev); dev->hard_header_len = phy_dev->hard_header_len; + dev->needed_headroom = phy_dev->needed_headroom; + dev->needed_tailroom = phy_dev->needed_tailroom; netdev_lockdep_set_classes(dev); @@ -773,6 +775,8 @@ static int ipvlan_device_event(struct notifier_block *unused, case NETDEV_FEAT_CHANGE: list_for_each_entry(ipvlan, &port->ipvlans, pnode) { netif_inherit_tso_max(ipvlan->dev, dev); + ipvlan->dev->needed_headroom = dev->needed_headroom; + ipvlan->dev->needed_tailroom = dev->needed_tailroom; netdev_update_features(ipvlan->dev); } break; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index c40fa331836b..ff2f4bb651b7 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -950,6 +950,8 @@ static int macvlan_init(struct net_device *dev) dev->lltx = true; netif_inherit_tso_max(dev, lowerdev); dev->hard_header_len = lowerdev->hard_header_len; + dev->needed_headroom = lowerdev->needed_headroom; + dev->needed_tailroom = lowerdev->needed_tailroom; macvlan_set_lockdep_class(dev); vlan->pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); @@ -1824,6 +1826,8 @@ static int macvlan_device_event(struct notifier_block *unused, case NETDEV_FEAT_CHANGE: list_for_each_entry(vlan, &port->vlans, list) { netif_inherit_tso_max(vlan->dev, dev); + vlan->dev->needed_headroom = dev->needed_headroom; + vlan->dev->needed_tailroom = dev->needed_tailroom; netdev_update_features(vlan->dev); } break; diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index c3a6ba96fc8a..029a4a532a10 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -127,8 +127,8 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data, { struct ntb_netdev_queue *q = qp_data; struct ntb_netdev *dev = q->ntdev; + struct sk_buff *skb, *new_skb; struct net_device *ndev; - struct sk_buff *skb; int rc; ndev = dev->ndev; @@ -144,6 +144,12 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data, goto enqueue_again; } + new_skb = netdev_alloc_skb(ndev, ndev->mtu + ETH_HLEN); + if (!new_skb) { + ndev->stats.rx_dropped++; + goto enqueue_again; + } + skb_put(skb, len); skb->protocol = eth_type_trans(skb, ndev); skb->ip_summed = CHECKSUM_NONE; @@ -157,12 +163,7 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data, ndev->stats.rx_bytes += len; } - skb = netdev_alloc_skb(ndev, ndev->mtu + ETH_HLEN); - if (!skb) { - ndev->stats.rx_errors++; - ndev->stats.rx_frame_errors++; - return; - } + skb = new_skb; enqueue_again: rc = ntb_transport_rx_enqueue(qp, skb, skb->data, ndev->mtu + ETH_HLEN); diff --git a/drivers/net/ovpn/crypto.c b/drivers/net/ovpn/crypto.c index 90580e32052f..7e545428900a 100644 --- a/drivers/net/ovpn/crypto.c +++ b/drivers/net/ovpn/crypto.c @@ -18,20 +18,12 @@ #include "crypto_aead.h" #include "crypto.h" -static void ovpn_ks_destroy_rcu(struct rcu_head *head) -{ - struct ovpn_crypto_key_slot *ks; - - ks = container_of(head, struct ovpn_crypto_key_slot, rcu); - ovpn_aead_crypto_key_slot_destroy(ks); -} - void ovpn_crypto_key_slot_release(struct kref *kref) { struct ovpn_crypto_key_slot *ks; ks = container_of(kref, struct ovpn_crypto_key_slot, refcount); - call_rcu(&ks->rcu, ovpn_ks_destroy_rcu); + queue_rcu_work(ovpn_wq, &ks->free_work); } /* can only be invoked when all peer references have been dropped (i.e. RCU @@ -58,15 +50,19 @@ void ovpn_crypto_state_release(struct ovpn_crypto_state *cs) bool ovpn_crypto_kill_key(struct ovpn_crypto_state *cs, u8 key_id) { struct ovpn_crypto_key_slot *ks = NULL; + struct ovpn_crypto_key_slot *tmp; + int slot = 0; spin_lock_bh(&cs->lock); - if (rcu_access_pointer(cs->slots[0])->key_id == key_id) { - ks = rcu_replace_pointer(cs->slots[0], NULL, - lockdep_is_held(&cs->lock)); - } else if (rcu_access_pointer(cs->slots[1])->key_id == key_id) { - ks = rcu_replace_pointer(cs->slots[1], NULL, - lockdep_is_held(&cs->lock)); + tmp = rcu_access_pointer(cs->slots[slot]); + if (!tmp || tmp->key_id != key_id) { + slot = 1; + tmp = rcu_access_pointer(cs->slots[slot]); } + + if (tmp && tmp->key_id == key_id) + ks = rcu_replace_pointer(cs->slots[slot], NULL, + lockdep_is_held(&cs->lock)); spin_unlock_bh(&cs->lock); if (ks) diff --git a/drivers/net/ovpn/crypto.h b/drivers/net/ovpn/crypto.h index 0e284fec3a75..e3feb16d5498 100644 --- a/drivers/net/ovpn/crypto.h +++ b/drivers/net/ovpn/crypto.h @@ -10,6 +10,8 @@ #ifndef _NET_OVPN_OVPNCRYPTO_H_ #define _NET_OVPN_OVPNCRYPTO_H_ +#include <linux/workqueue.h> + #include "pktid.h" #include "proto.h" @@ -45,8 +47,8 @@ struct ovpn_crypto_key_slot { struct ovpn_pktid_recv pid_recv ____cacheline_aligned_in_smp; struct ovpn_pktid_xmit pid_xmit ____cacheline_aligned_in_smp; + struct rcu_work free_work; struct kref refcount; - struct rcu_head rcu; }; struct ovpn_crypto_state { diff --git a/drivers/net/ovpn/crypto_aead.c b/drivers/net/ovpn/crypto_aead.c index 8f07c418622b..74eaf6fac2f5 100644 --- a/drivers/net/ovpn/crypto_aead.c +++ b/drivers/net/ovpn/crypto_aead.c @@ -9,6 +9,7 @@ #include <crypto/aead.h> #include <linux/skbuff.h> +#include <linux/workqueue.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/udp.h> @@ -380,13 +381,19 @@ error: return ERR_PTR(ret); } -void ovpn_aead_crypto_key_slot_destroy(struct ovpn_crypto_key_slot *ks) +static void ovpn_aead_crypto_key_slot_free(struct ovpn_crypto_key_slot *ks) { - if (!ks) - return; - crypto_free_aead(ks->encrypt); crypto_free_aead(ks->decrypt); +} + +static void ovpn_aead_crypto_key_slot_free_work(struct work_struct *work) +{ + struct ovpn_crypto_key_slot *ks; + + ks = container_of(to_rcu_work(work), struct ovpn_crypto_key_slot, + free_work); + ovpn_aead_crypto_key_slot_free(ks); kfree(ks); } @@ -420,6 +427,7 @@ ovpn_aead_crypto_key_slot_new(const struct ovpn_key_config *kc) ks->encrypt = NULL; ks->decrypt = NULL; + INIT_RCU_WORK(&ks->free_work, ovpn_aead_crypto_key_slot_free_work); kref_init(&ks->refcount); ks->key_id = kc->key_id; @@ -453,7 +461,8 @@ ovpn_aead_crypto_key_slot_new(const struct ovpn_key_config *kc) return ks; destroy_ks: - ovpn_aead_crypto_key_slot_destroy(ks); + ovpn_aead_crypto_key_slot_free(ks); + kfree(ks); return ERR_PTR(ret); } diff --git a/drivers/net/ovpn/crypto_aead.h b/drivers/net/ovpn/crypto_aead.h index 65a2ff307898..fae3b585a43b 100644 --- a/drivers/net/ovpn/crypto_aead.h +++ b/drivers/net/ovpn/crypto_aead.h @@ -22,7 +22,6 @@ int ovpn_aead_decrypt(struct ovpn_peer *peer, struct ovpn_crypto_key_slot *ks, struct ovpn_crypto_key_slot * ovpn_aead_crypto_key_slot_new(const struct ovpn_key_config *kc); -void ovpn_aead_crypto_key_slot_destroy(struct ovpn_crypto_key_slot *ks); enum ovpn_cipher_alg ovpn_aead_crypto_alg(struct ovpn_crypto_key_slot *ks); diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c index 9a66d693039a..9526f8096da6 100644 --- a/drivers/net/ovpn/io.c +++ b/drivers/net/ovpn/io.c @@ -204,10 +204,10 @@ drop: ovpn_dev_dstats_rx_dropped(peer->ovpn->dev); kfree_skb(skb); drop_nocount: - if (likely(peer)) - ovpn_peer_put(peer); if (likely(ks)) ovpn_crypto_key_slot_put(ks); + if (likely(peer)) + ovpn_peer_put(peer); } /* RX path entry point: decrypt packet and forward it to the device */ @@ -302,11 +302,11 @@ err_unlock: err: if (unlikely(skb)) ovpn_dev_dstats_tx_dropped(peer->ovpn->dev); - if (likely(peer)) - ovpn_peer_put(peer); + kfree_skb(skb); if (likely(ks)) ovpn_crypto_key_slot_put(ks); - kfree_skb(skb); + if (likely(peer)) + ovpn_peer_put(peer); } static bool ovpn_encrypt_one(struct ovpn_peer *peer, struct sk_buff *skb) diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c index 168cfe9b59a9..0708249e9607 100644 --- a/drivers/net/ovpn/main.c +++ b/drivers/net/ovpn/main.c @@ -12,6 +12,7 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> +#include <linux/workqueue.h> #include <net/gro_cells.h> #include <net/ip.h> #include <net/rtnetlink.h> @@ -26,6 +27,9 @@ #include "tcp.h" #include "udp.h" +/* module-owned workqueue on which all ovpn-specific work is queued */ +struct workqueue_struct *ovpn_wq; + static void ovpn_priv_free(struct net_device *net) { struct ovpn_priv *ovpn = netdev_priv(net); @@ -264,10 +268,16 @@ static int __init ovpn_init(void) ovpn_tcp_init(); + ovpn_wq = alloc_workqueue("ovpn", WQ_PERCPU, 0); + if (!ovpn_wq) { + pr_err("ovpn: cannot allocate workqueue\n"); + return -ENOMEM; + } + err = rtnl_link_register(&ovpn_link_ops); if (err) { pr_err("ovpn: can't register rtnl link ops: %d\n", err); - return err; + goto destroy_wq; } err = ovpn_nl_register(); @@ -280,6 +290,9 @@ static int __init ovpn_init(void) unreg_rtnl: rtnl_link_unregister(&ovpn_link_ops); +destroy_wq: + destroy_workqueue(ovpn_wq); + ovpn_wq = NULL; return err; } @@ -288,7 +301,11 @@ static __exit void ovpn_cleanup(void) ovpn_nl_unregister(); rtnl_link_unregister(&ovpn_link_ops); + flush_workqueue(ovpn_wq); rcu_barrier(); + + destroy_workqueue(ovpn_wq); + ovpn_wq = NULL; } module_init(ovpn_init); diff --git a/drivers/net/ovpn/ovpnpriv.h b/drivers/net/ovpn/ovpnpriv.h index 5898f6adada7..84499140e4bd 100644 --- a/drivers/net/ovpn/ovpnpriv.h +++ b/drivers/net/ovpn/ovpnpriv.h @@ -15,6 +15,10 @@ #include <uapi/linux/if_link.h> #include <uapi/linux/ovpn.h> +struct workqueue_struct; + +extern struct workqueue_struct *ovpn_wq; + /** * struct ovpn_peer_collection - container of peers for MultiPeer mode * @by_id: table of peers index by ID diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c index b0519f9840d8..c95656ca7c35 100644 --- a/drivers/net/ovpn/peer.c +++ b/drivers/net/ovpn/peer.c @@ -62,7 +62,7 @@ void ovpn_peer_keepalive_set(struct ovpn_peer *peer, u32 interval, u32 timeout) /* now that interval and timeout have been changed, kick * off the worker so that the next delay can be recomputed */ - mod_delayed_work(system_percpu_wq, &peer->ovpn->keepalive_work, 0); + mod_delayed_work(ovpn_wq, &peer->ovpn->keepalive_work, 0); } /** @@ -1371,7 +1371,7 @@ static time64_t ovpn_peer_keepalive_work_single(struct ovpn_peer *peer, peer->id); if (WARN_ON(!ovpn_peer_hold(peer))) return 0; - if (!schedule_work(&peer->keepalive_work)) + if (!queue_work(ovpn_wq, &peer->keepalive_work)) ovpn_peer_put(peer); } @@ -1463,8 +1463,8 @@ void ovpn_peer_keepalive_work(struct work_struct *work) netdev_dbg(ovpn->dev, "scheduling keepalive work: now=%llu next_run=%llu delta=%llu\n", next_run, now, next_run - now); - schedule_delayed_work(&ovpn->keepalive_work, - (next_run - now) * HZ); + queue_delayed_work(ovpn_wq, &ovpn->keepalive_work, + (next_run - now) * HZ); } unlock_ovpn(ovpn, &release_list); } diff --git a/drivers/net/ovpn/tcp.c b/drivers/net/ovpn/tcp.c index 0af14055c39a..8fe8a8e750a4 100644 --- a/drivers/net/ovpn/tcp.c +++ b/drivers/net/ovpn/tcp.c @@ -151,7 +151,7 @@ err: /* take reference for deferred peer deletion. should never fail */ if (WARN_ON(!ovpn_peer_hold(peer))) goto err_nopeer; - if (!schedule_work(&peer->tcp.defer_del_work)) + if (!queue_work(ovpn_wq, &peer->tcp.defer_del_work)) ovpn_peer_put(peer); ovpn_dev_dstats_rx_dropped(peer->ovpn->dev); err_nopeer: @@ -284,13 +284,12 @@ static void ovpn_tcp_send_sock(struct ovpn_peer *peer, struct sock *sk) * stream therefore we abort the connection */ ovpn_peer_hold(peer); - if (!schedule_work(&peer->tcp.defer_del_work)) + if (!queue_work(ovpn_wq, &peer->tcp.defer_del_work)) ovpn_peer_put(peer); /* we bail out immediately and keep tx_in_progress set * to true. This way we prevent more TX attempts - * which would lead to more invocations of - * schedule_work() + * which would lead to more invocations of queue_work() */ return; } @@ -487,7 +486,7 @@ static void ovpn_tcp_write_space(struct sock *sk) rcu_read_lock(); sock = rcu_dereference_sk_user_data(sk); if (likely(sock && sock->peer)) { - schedule_work(&sock->tcp_tx_work); + queue_work(ovpn_wq, &sock->tcp_tx_work); sock->peer->tcp.sk_cb.sk_write_space(sk); } rcu_read_unlock(); diff --git a/drivers/net/phy/realtek/realtek_main.c b/drivers/net/phy/realtek/realtek_main.c index b65d0f5fa1a0..0d2321bd18c8 100644 --- a/drivers/net/phy/realtek/realtek_main.c +++ b/drivers/net/phy/realtek/realtek_main.c @@ -1370,7 +1370,7 @@ static int rtlgen_write_mmd(struct phy_device *phydev, int devnum, u16 regnum, if (devnum == MDIO_MMD_VEND2) ret = rtlgen_write_vend2(phydev, regnum, val); else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV) - ret = rtlgen_write_vend2(phydev, regnum, RTL_MDIO_AN_EEE_ADV); + ret = rtlgen_write_vend2(phydev, RTL_MDIO_AN_EEE_ADV, val); else ret = -EOPNOTSUPP; diff --git a/drivers/net/tap.c b/drivers/net/tap.c index 5d2d34d24ce8..9b5af08cdd47 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -1091,12 +1091,13 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp) } } + skb_probe_transport_header(skb); + /* Move network header to the right position for VLAN tagged packets */ if (eth_type_vlan(skb->protocol) && vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); - skb_probe_transport_header(skb); dev_queue_xmit(skb); rcu_read_unlock(); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 00e34afd858e..6ab84c837a33 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -865,18 +865,24 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, skb_reset_mac_header(skb); - /* check if bpf_xdp_adjust_tail was used */ - off = xdp->data_end - orig_data_end; - if (off != 0) - __skb_put(skb, off); /* positive on grow, negative on shrink */ - /* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers - * (e.g. bpf_xdp_adjust_tail), we need to update data_len here. + * (e.g. bpf_xdp_adjust_tail). Remove the old fragment contribution + * from skb->len before updating data_len, then add the new one back. */ - if (xdp_buff_has_frags(xdp)) + skb->len -= skb->data_len; + if (xdp_buff_has_frags(xdp)) { skb->data_len = skb_shinfo(skb)->xdp_frags_size; - else + skb->len += skb->data_len; + } else { skb->data_len = 0; + } + + /* Synchronize the skb tail with XDP's updated linear area. */ + off = xdp->data_end - orig_data_end; + if (off != 0) { + skb_set_tail_pointer(skb, xdp->data_end - xdp->data); + skb->len += off; /* positive on grow, negative on shrink */ + } skb->protocol = eth_type_trans(skb, rq->dev); @@ -961,7 +967,7 @@ static int veth_poll(struct napi_struct *napi, int budget) struct veth_rq *rq = container_of(napi, struct veth_rq, xdp_napi); struct veth_priv *priv = netdev_priv(rq->dev); - int queue_idx = rq->xdp_rxq.queue_index; + int queue_idx = rq - priv->rq; struct netdev_queue *peer_txq; struct veth_stats stats = {}; struct net_device *peer_dev; diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 1ded27768a97..824144bb7774 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -4500,7 +4500,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], if (change_igmp && vxlan_addr_multicast(&dst->remote_ip)) err = vxlan_multicast_leave(vxlan); - if (conf.age_interval != vxlan->cfg.age_interval) + if (netif_running(dev) && conf.age_interval != vxlan->cfg.age_interval) mod_timer(&vxlan->age_timer, jiffies); netdev_adjacent_change_commit(dst->remote_dev, lowerdev, dev); diff --git a/include/net/act_api.h b/include/net/act_api.h index 20d9e55f8564..fd03f6319e88 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -270,6 +270,25 @@ int tcf_action_check_ctrlact(int action, struct tcf_proto *tp, struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action, struct tcf_chain *newchain); +/* Range check for a control action supplied by user space. + * + * This is the same test tcf_action_check_ctrlact() applies to the primary + * control action, factored out for the *fallback* control actions + * (act_gact's TCA_GACT_PROB.paction and act_police's TCA_POLICE_RESULT), + * which must not reach tcf_action_check_ctrlact() because they have no + * goto_chain to allocate. Without it, user space can store kernel-internal + * verdicts such as TC_ACT_CONSUMED, which is TC_ACT_VALUE_MAX + 1 and is + * deliberately not part of the UAPI value range. + */ +static inline bool tcf_action_valid(int action) +{ + int opcode = TC_ACT_EXT_OPCODE(action); + + if (!opcode) + return action <= TC_ACT_VALUE_MAX; + return opcode <= TC_ACT_EXT_OPCODE_MAX || action == TC_ACT_UNSPEC; +} + #ifdef CONFIG_INET DECLARE_STATIC_KEY_FALSE(tcf_frag_xmit_count); #endif diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index d2813eb795be..be3a6617adf4 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -36,6 +36,12 @@ #define IP_VS_HDR_INVERSE 1 #define IP_VS_HDR_ICMP 2 +/* Destination Server Flags */ +#define IP_VS_DEST_F_OVERLOAD 0x0002 /* server is overloaded */ + +/* Destination Server Config Flags */ +#define IP_VS_DEST_CF_AVAILABLE 0x0001 /* server is available */ + /* conn_tab limits (as per Kconfig) */ #define IP_VS_CONN_TAB_MIN_BITS 8 #if BITS_PER_LONG > 32 @@ -976,6 +982,7 @@ struct ip_vs_dest { volatile unsigned int flags; /* dest status flags */ atomic_t conn_flags; /* flags to copy to conn */ atomic_t weight; /* server weight */ + unsigned long cflags; /* config flags */ atomic_t last_weight; /* server latest weight */ __u16 tun_type; /* tunnel type */ __be16 tun_port; /* tunnel port */ @@ -987,10 +994,11 @@ struct ip_vs_dest { /* connection counters and thresholds */ atomic_t activeconns; /* active connections */ - atomic_t inactconns; /* inactive connections */ + atomic_t totalconns; /* total connections */ atomic_t persistconns; /* persistent connections */ __u32 u_threshold; /* upper threshold */ __u32 l_threshold; /* lower threshold */ + __u32 l_threshold_val;/* used lower threshold */ /* for destination cache */ spinlock_t dst_lock; /* lock of dst_cache */ @@ -1907,6 +1915,8 @@ static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest) kfree(dest); } +void ip_vs_dest_update_overload(struct ip_vs_dest *dest, int mode); + /* IPVS sync daemon data and function prototypes * (from ip_vs_sync.c) */ @@ -2058,7 +2068,7 @@ static inline bool ip_vs_conn_use_hash2(struct ip_vs_conn *cp) !(cp->flags & IP_VS_CONN_F_TEMPLATE); } -void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, +bool ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int dir, unsigned int toff, bool has_ports, struct ip_vs_iphdr *ciph); @@ -2220,14 +2230,21 @@ void ip_vs_unregister_hooks(struct netns_ipvs *ipvs, unsigned int af); static inline int ip_vs_dest_conn_overhead(struct ip_vs_dest *dest) { - /* We think the overhead of processing active connections is 256 + /* We think the overhead of processing active connections is 257 * times higher than that of inactive connections in average. (This - * 256 times might not be accurate, we will change it later) We + * 257 times might not be accurate, we will change it later) We * use the following formula to estimate the overhead now: - * dest->activeconns*256 + dest->inactconns + * dest->activeconns*256 + dest->totalconns */ return (atomic_read(&dest->activeconns) << 8) + - atomic_read(&dest->inactconns); + atomic_read(&dest->totalconns); +} + +static inline int +ip_vs_dest_inactconns(const struct ip_vs_dest *dest) +{ + return max(atomic_read(&dest->totalconns) - + atomic_read(&dest->activeconns), 0); } #ifdef CONFIG_IP_VS_PROTO_TCP diff --git a/include/net/route.h b/include/net/route.h index f90106f383c5..45290177a33c 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -276,6 +276,8 @@ int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fib_info *fi, int *fa_index, int fa_start, unsigned int flags); +void fnhe_update_pmtu(struct fib_nh_exception *fnhe, u32 new, u32 orig); + static inline void ip_rt_put(struct rtable *rt) { /* dst_release() accepts a NULL parameter. diff --git a/include/net/sctp/auth.h b/include/net/sctp/auth.h index 6f2cd562b1de..74b3790e2a3d 100644 --- a/include/net/sctp/auth.h +++ b/include/net/sctp/auth.h @@ -22,6 +22,7 @@ struct sctp_endpoint; struct sctp_association; struct sctp_authkey; struct sctp_hmacalgo; +struct sctp_cookie; /* Defines an HMAC algorithm supported by SCTP chunk authentication */ struct sctp_hmac { @@ -72,6 +73,8 @@ struct sctp_shared_key *sctp_auth_get_shkey( int sctp_auth_asoc_copy_shkeys(const struct sctp_endpoint *ep, struct sctp_association *asoc, gfp_t gfp); +bool sctp_auth_verify_cookie_params(const struct sctp_endpoint *ep, + const struct sctp_cookie *cookie); const struct sctp_hmac *sctp_auth_get_hmac(__u16 hmac_id); const struct sctp_hmac * sctp_auth_asoc_get_hmac(const struct sctp_association *asoc); diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h index 1ed234e7f251..2c37c6ac7525 100644 --- a/include/uapi/linux/ip_vs.h +++ b/include/uapi/linux/ip_vs.h @@ -29,12 +29,6 @@ #define IP_VS_SVC_F_SCHED_SH_PORT IP_VS_SVC_F_SCHED2 /* SH use port */ /* - * Destination Server Flags - */ -#define IP_VS_DEST_F_AVAILABLE 0x0001 /* server is available */ -#define IP_VS_DEST_F_OVERLOAD 0x0002 /* server is overloaded */ - -/* * IPVS sync daemon states */ #define IP_VS_STATE_NONE 0x0000 /* daemon is stopped */ diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 58a33d0380b0..7ecb8a26bfa3 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -280,6 +280,7 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb, ret = nf_ct_br_defrag6(skb, &bridge_state); break; default: + nf_reset_ct(skb); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); return NF_ACCEPT; } diff --git a/net/core/dev.c b/net/core/dev.c index af260ff5462a..ece6700536d9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5517,12 +5517,16 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, } /* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers - * (e.g. bpf_xdp_adjust_tail), we need to update data_len here. + * (e.g. bpf_xdp_adjust_tail). Remove the old fragment contribution + * from skb->len before updating data_len, then add the new one back. */ - if (xdp_buff_has_frags(xdp)) + skb->len -= skb->data_len; + if (xdp_buff_has_frags(xdp)) { skb->data_len = skb_shinfo(skb)->xdp_frags_size; - else + skb->len += skb->data_len; + } else { skb->data_len = 0; + } /* check if XDP changed eth hdr such SKB needs update */ eth = (struct ethhdr *)xdp->data; diff --git a/net/core/netdev_queues.c b/net/core/netdev_queues.c index 4d6864bb4f6b..f5558b12877c 100644 --- a/net/core/netdev_queues.c +++ b/net/core/netdev_queues.c @@ -40,7 +40,7 @@ struct device *netdev_queue_get_dma_dev(struct net_device *dev, struct netdev_rx_queue *hw_rxq; struct device *dma_dev; - netdev_assert_locked_ops_compat(dev); + netdev_assert_locked(dev); /* Only RX side supports queue leasing today. */ if (type != NETDEV_QUEUE_TYPE_RX || !netif_rxq_is_leased(dev, idx)) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 78f84ae3ee12..0483519b7fb0 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1895,42 +1895,30 @@ static int call_fib_nh_notifiers(struct fib_nh *nh, return NOTIFY_DONE; } -/* Update the PMTU of exceptions when: - * - the new MTU of the first hop becomes smaller than the PMTU - * - the old MTU was the same as the PMTU, and it limited discovery of - * larger MTUs on the path. With that limit raised, we can now - * discover larger MTUs - * A special case is locked exceptions, for which the PMTU is smaller - * than the minimal accepted PMTU: - * - if the new MTU is greater than the PMTU, don't make any change - * - otherwise, unlock and set PMTU +/* Walk the exceptions of a nexthop after its first hop MTU changed. The + * chain is RCU protected here, while fnhe_update_pmtu() takes fnhe_lock + * for the update of each entry. */ void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig) { struct fnhe_hash_bucket *bucket; int i; - bucket = rcu_dereference_protected(nhc->nhc_exceptions, 1); + rcu_read_lock(); + bucket = rcu_dereference(nhc->nhc_exceptions); if (!bucket) - return; + goto out; for (i = 0; i < FNHE_HASH_SIZE; i++) { struct fib_nh_exception *fnhe; - for (fnhe = rcu_dereference_protected(bucket[i].chain, 1); + for (fnhe = rcu_dereference(bucket[i].chain); fnhe; - fnhe = rcu_dereference_protected(fnhe->fnhe_next, 1)) { - if (fnhe->fnhe_mtu_locked) { - if (new <= fnhe->fnhe_pmtu) { - fnhe->fnhe_pmtu = new; - fnhe->fnhe_mtu_locked = false; - } - } else if (new < fnhe->fnhe_pmtu || - orig == fnhe->fnhe_pmtu) { - fnhe->fnhe_pmtu = new; - } - } + fnhe = rcu_dereference(fnhe->fnhe_next)) + fnhe_update_pmtu(fnhe, new, orig); } +out: + rcu_read_unlock(); } void fib_sync_mtu(struct net_device *dev, u32 orig_mtu) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 152d8cb28f65..b82401a6baed 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -741,6 +741,35 @@ out_unlock: spin_unlock_bh(&fnhe_lock); } +/* Update the PMTU of an exception when: + * - the new MTU of the first hop becomes smaller than the PMTU + * - the old MTU was the same as the PMTU, and it limited discovery of + * larger MTUs on the path. With that limit raised, we can now + * discover larger MTUs + * A special case is locked exceptions, for which the PMTU is smaller + * than the minimal accepted PMTU: + * - if the new MTU is greater than the PMTU, don't make any change + * - otherwise, unlock and set PMTU + * + * fnhe_lock keeps fnhe_pmtu and fnhe_mtu_locked consistent against + * update_or_create_fnhe(), which sets both under the same lock. + */ +void fnhe_update_pmtu(struct fib_nh_exception *fnhe, u32 new, u32 orig) +{ + spin_lock_bh(&fnhe_lock); + + if (fnhe->fnhe_mtu_locked) { + if (new <= fnhe->fnhe_pmtu) { + fnhe->fnhe_pmtu = new; + fnhe->fnhe_mtu_locked = false; + } + } else if (new < fnhe->fnhe_pmtu || orig == fnhe->fnhe_pmtu) { + fnhe->fnhe_pmtu = new; + } + + spin_unlock_bh(&fnhe_lock); +} + static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4, bool kill_route) { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5b6378b94701..0f60a1dbf927 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1039,9 +1039,9 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb) /* The fastest case is the first. */ icsk->icsk_ack.ato = (icsk->icsk_ack.ato >> 1) + TCP_ATO_MIN / 2; } else if (m < icsk->icsk_ack.ato) { - icsk->icsk_ack.ato = (icsk->icsk_ack.ato >> 1) + m; - if (icsk->icsk_ack.ato > icsk->icsk_rto) - icsk->icsk_ack.ato = icsk->icsk_rto; + icsk->icsk_ack.ato = min3((icsk->icsk_ack.ato >> 1) + (u32)m, + icsk->icsk_rto, + (u32)TCP_DELACK_MAX); } else if (m > icsk->icsk_rto) { /* Too long gap. Apparently sender failed to * restart window, so that we send ACKs quickly. diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index bf171b5e1eb3..4df1c9745c5d 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -334,7 +334,9 @@ void tcp_delack_timer_handler(struct sock *sk) if (inet_csk_ack_scheduled(sk)) { if (!inet_csk_in_pingpong_mode(sk)) { /* Delayed ACK missed: inflate ATO. */ - icsk->icsk_ack.ato = min_t(u32, icsk->icsk_ack.ato << 1, icsk->icsk_rto); + icsk->icsk_ack.ato = min3((u32)icsk->icsk_ack.ato << 1, + icsk->icsk_rto, + (u32)TCP_DELACK_MAX); } else { /* Delayed ACK missed: leave pingpong mode and * deflate ATO. diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index b26986fda9d6..c12d5e1ee550 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -306,6 +306,10 @@ static int l2tp_dfs_seq_release(struct inode *inode, struct file *file) seq = file->private_data; pd = seq->private; + if (pd->session) + l2tp_session_put(pd->session); + if (pd->tunnel) + l2tp_tunnel_put(pd->tunnel); if (pd->net) put_net_track(pd->net, &pd->ns_tracker); kfree(pd); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index f8881699e1ca..ef8fdfaf051d 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1597,7 +1597,53 @@ static const struct seq_operations pppol2tp_seq_ops = { .stop = pppol2tp_seq_stop, .show = pppol2tp_seq_show, }; -#endif /* CONFIG_PROC_FS */ + +static int pppol2tp_proc_open(struct inode *inode, struct file *file) +{ + struct net *net = pde_data(inode); + struct pppol2tp_seq_data *pd; + + net = maybe_get_net(net); + if (!net) + return -ENXIO; + + pd = __seq_open_private(file, &pppol2tp_seq_ops, sizeof(*pd)); + if (!pd) { + put_net(net); + return -ENOMEM; + } + +#ifdef CONFIG_NET_NS + pd->p.net = net; + netns_tracker_alloc(net, &pd->p.ns_tracker, GFP_KERNEL); +#endif + return 0; +} + +static int pppol2tp_proc_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct pppol2tp_seq_data *pd = seq->private; + + if (pd->session) + l2tp_session_put(pd->session); + if (pd->tunnel) + l2tp_tunnel_put(pd->tunnel); + +#ifdef CONFIG_NET_NS + put_net_track(pd->p.net, &pd->p.ns_tracker); +#else + put_net(&init_net); +#endif + return seq_release_private(inode, file); +} + +static const struct proc_ops pppol2tp_proc_ops = { + .proc_open = pppol2tp_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = pppol2tp_proc_release, +}; /***************************************************************************** * Network namespace @@ -1608,8 +1654,8 @@ static __net_init int pppol2tp_init_net(struct net *net) struct proc_dir_entry *pde; int err = 0; - pde = proc_create_net("pppol2tp", 0444, net->proc_net, - &pppol2tp_seq_ops, sizeof(struct pppol2tp_seq_data)); + pde = proc_create_data("pppol2tp", 0444, net->proc_net, + &pppol2tp_proc_ops, net); if (!pde) { err = -ENOMEM; goto out; @@ -1624,9 +1670,13 @@ static __net_exit void pppol2tp_exit_net(struct net *net) remove_proc_entry("pppol2tp", net->proc_net); } +#endif /* CONFIG_PROC_FS */ + static struct pernet_operations pppol2tp_net_ops = { +#ifdef CONFIG_PROC_FS .init = pppol2tp_init_net, .exit = pppol2tp_exit_net, +#endif }; /***************************************************************************** diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 226fdf17b683..d6a7e6604542 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -77,7 +77,7 @@ mtype_flush(struct ip_set *set) mtype_ext_cleanup(set); bitmap_zero(map->members, map->elements); set->elements = 0; - atomic64_set(&set->ext_size, 0); + DEBUG_NET_WARN_ON_ONCE(atomic64_read(&set->ext_size) > 0); } /* Calculate the actual memory size of the set data */ diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 543851a923d0..0a86a170ba90 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -680,11 +680,18 @@ __ip_set_get(struct ip_set *set) } static void -__ip_set_put(struct ip_set *set) +__ip_set_put_locked(struct ip_set *set) { - write_lock_bh(&ip_set_ref_lock); + lockdep_assert_held(&ip_set_ref_lock); BUG_ON(set->ref == 0); set->ref--; +} + +static void +__ip_set_put(struct ip_set *set) +{ + write_lock_bh(&ip_set_ref_lock); + __ip_set_put_locked(set); write_unlock_bh(&ip_set_ref_lock); } @@ -855,11 +862,11 @@ __ip_set_put_byindex(struct ip_set_net *inst, ip_set_id_t index) { struct ip_set *set; - rcu_read_lock(); - set = rcu_dereference(inst->ip_set_list)[index]; + write_lock_bh(&ip_set_ref_lock); + set = ip_set(inst, index); if (set) - __ip_set_put(set); - rcu_read_unlock(); + __ip_set_put_locked(set); + write_unlock_bh(&ip_set_ref_lock); } void diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index ca3ef9479e83..f070088742d6 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -301,9 +301,12 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext, e->set = set; INIT_LIST_HEAD(&e->list); list_set_init_extensions(set, ext, e); - if (n) + if (n) { list_set_replace(set, e, n); - else if (next) + return 0; + } + + if (next) list_add_tail_rcu(&e->list, &next->list); else if (prev) list_add_rcu(&e->list, &prev->list); @@ -420,8 +423,7 @@ list_set_flush(struct ip_set *set) list_for_each_entry_safe(e, n, &map->members, list) list_set_del(set, e); - set->elements = 0; - atomic64_set(&set->ext_size, 0); + DEBUG_NET_WARN_ON_ONCE(set->elements > 0); } static void diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 36c5cba03f5b..6fa3e1dc534c 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1081,12 +1081,6 @@ static inline void ip_vs_bind_xmit_v6(struct ip_vs_conn *cp) #endif -static inline int ip_vs_dest_totalconns(struct ip_vs_dest *dest) -{ - return atomic_read(&dest->activeconns) - + atomic_read(&dest->inactconns); -} - /* * Bind a connection entry with a virtual service destination * Called just after a new connection entry is created. @@ -1147,23 +1141,22 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) /* Update the connection counters */ if (!(flags & IP_VS_CONN_F_TEMPLATE)) { + int tc; + /* It is a normal connection, so modify the counters * according to the flags, later the protocol can * update them on state change */ if (!(flags & IP_VS_CONN_F_INACTIVE)) atomic_inc(&dest->activeconns); - else - atomic_inc(&dest->inactconns); + tc = atomic_inc_return(&dest->totalconns); + if (tc == READ_ONCE(dest->u_threshold)) + ip_vs_dest_update_overload(dest, 1); } else { /* It is a persistent connection/template, so increase the persistent connection counter */ atomic_inc(&dest->persistconns); } - - if (dest->u_threshold != 0 && - ip_vs_dest_totalconns(dest) >= dest->u_threshold) - dest->flags |= IP_VS_DEST_F_OVERLOAD; } @@ -1244,30 +1237,20 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp) /* Update the connection counters */ if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) { - /* It is a normal connection, so decrease the inactconns - or activeconns counter */ - if (cp->flags & IP_VS_CONN_F_INACTIVE) { - atomic_dec(&dest->inactconns); - } else { + int tc; + + /* It is a normal connection, so decrease the counters */ + if (!(cp->flags & IP_VS_CONN_F_INACTIVE)) atomic_dec(&dest->activeconns); - } + tc = atomic_fetch_dec(&dest->totalconns); + if (tc == READ_ONCE(dest->l_threshold_val)) + ip_vs_dest_update_overload(dest, -1); } else { /* It is a persistent connection/template, so decrease the persistent connection counter */ atomic_dec(&dest->persistconns); } - if (dest->l_threshold != 0) { - if (ip_vs_dest_totalconns(dest) < dest->l_threshold) - dest->flags &= ~IP_VS_DEST_F_OVERLOAD; - } else if (dest->u_threshold != 0) { - if (ip_vs_dest_totalconns(dest) * 4 < dest->u_threshold * 3) - dest->flags &= ~IP_VS_DEST_F_OVERLOAD; - } else { - if (dest->flags & IP_VS_DEST_F_OVERLOAD) - dest->flags &= ~IP_VS_DEST_F_OVERLOAD; - } - ip_vs_dest_put(dest); } @@ -1296,7 +1279,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct, struct ip_vs_dest *cdest) * Checking the dest server status. */ if ((dest == NULL) || - !(dest->flags & IP_VS_DEST_F_AVAILABLE) || + !(dest->cflags & IP_VS_DEST_CF_AVAILABLE) || expire_quiescent_template(ipvs, dest) || (cdest && (dest != cdest))) { IP_VS_DBG_BUF(9, "check_template: dest not available for " @@ -2037,7 +2020,7 @@ repeat: cp = ip_vs_hn0_to_conn(hn); resched_score++; dest = cp->dest; - if (!dest || (dest->flags & IP_VS_DEST_F_AVAILABLE)) + if (!dest || (dest->cflags & IP_VS_DEST_CF_AVAILABLE)) continue; if (atomic_read(&cp->n_control)) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 0bdaeb4ed61e..eb806813292a 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -302,7 +302,7 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) struct ip_vs_dest *dest = cp->dest; struct netns_ipvs *ipvs = cp->ipvs; - if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { + if (dest && (dest->cflags & IP_VS_DEST_CF_AVAILABLE)) { struct ip_vs_cpu_stats *s; struct ip_vs_service *svc; @@ -338,7 +338,7 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) struct ip_vs_dest *dest = cp->dest; struct netns_ipvs *ipvs = cp->ipvs; - if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { + if (dest && (dest->cflags & IP_VS_DEST_CF_AVAILABLE)) { struct ip_vs_cpu_stats *s; struct ip_vs_service *svc; @@ -923,7 +923,7 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, * Packet has been made sufficiently writable in caller * - inout: 1=in->out, 0=out->in */ -void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, +bool ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int inout, unsigned int toff, bool has_ports, struct ip_vs_iphdr *ciph) { @@ -931,6 +931,11 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct icmphdr *icmph = (struct icmphdr *)(skb->data + toff); struct iphdr *cih = (struct iphdr *)(icmph + 1); + /* Before now we may used ihl from skb frag, revalidate it after + * copying it into skb head to prevent out-of-bounds access + */ + if (cih->ihl * 4 != ciph->len - ciph->off) + return false; if (inout) { iph->saddr = cp->vaddr.ip; ip_send_check(iph); @@ -964,6 +969,7 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, else IP_VS_DBG_PKT(11, AF_INET, pp, skb, ciph->off, "Forwarding altered incoming ICMP"); + return true; } #ifdef CONFIG_IP_VS_IPV6 @@ -1055,7 +1061,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb, ip_vs_nat_icmp_v6(skb, pp, cp, 1, toff, has_ports, ciph); else #endif - ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports, ciph); + if (!ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports, ciph)) + goto out; if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto out; @@ -1950,6 +1957,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (pskb_pull(skb, offset2) == NULL) goto ignore_tunnel; skb_reset_network_header(skb); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); /* Ensure the IP header is present in headroom */ if (!pskb_may_pull(skb, hlen_orig)) goto ignore_tunnel; @@ -2210,7 +2218,7 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state } /* Check the server status */ - if (cp && cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { + if (cp && cp->dest && !(cp->dest->cflags & IP_VS_DEST_CF_AVAILABLE)) { /* the destination server is not available */ if (sysctl_expire_nodest_conn(ipvs)) { bool old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index bcf40b8c41cf..8f9a8e491ad6 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1304,6 +1304,40 @@ void ip_vs_stats_free(struct ip_vs_stats *stats) } } +/* Update overload flag based on number of dest conns and lower/upper + * connection thresholds: + * - conns reach u_threshold and exceed it: set the flag + * - conns go below l_threshold (or 75% of u_threshold): clear the flag + */ +static void __ip_vs_dest_update_overload(struct ip_vs_dest *dest, int mode) +{ + int conns; + u32 l, u; + + lockdep_assert_held(&dest->dst_lock); + u = READ_ONCE(dest->u_threshold); + if (!u) + goto unset; + l = READ_ONCE(dest->l_threshold_val); + conns = atomic_read(&dest->totalconns); + if (conns >= (mode > 0 ? l : u)) { + dest->flags |= IP_VS_DEST_F_OVERLOAD; + return; + } + if (conns >= (mode < 0 ? u : l)) + return; + +unset: + dest->flags &= ~IP_VS_DEST_F_OVERLOAD; +} + +void ip_vs_dest_update_overload(struct ip_vs_dest *dest, int mode) +{ + spin_lock_bh(&dest->dst_lock); + __ip_vs_dest_update_overload(dest, mode); + spin_unlock_bh(&dest->dst_lock); +} + /* * Update a destination in the given service */ @@ -1368,12 +1402,21 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, } /* set the dest status flags */ - dest->flags |= IP_VS_DEST_F_AVAILABLE; + dest->cflags |= IP_VS_DEST_CF_AVAILABLE; - if (udest->u_threshold == 0 || udest->u_threshold > dest->u_threshold) - dest->flags &= ~IP_VS_DEST_F_OVERLOAD; - dest->u_threshold = udest->u_threshold; - dest->l_threshold = udest->l_threshold; + if (READ_ONCE(dest->u_threshold) != udest->u_threshold || + READ_ONCE(dest->l_threshold) != udest->l_threshold) { + spin_lock_bh(&dest->dst_lock); + WRITE_ONCE(dest->u_threshold, udest->u_threshold); + WRITE_ONCE(dest->l_threshold, udest->l_threshold); + /* Low threshold defaults to 75% of upper threshold */ + WRITE_ONCE(dest->l_threshold_val, + udest->l_threshold ? : + (udest->u_threshold - + (udest->u_threshold >> 2))); + __ip_vs_dest_update_overload(dest, 0); + spin_unlock_bh(&dest->dst_lock); + } dest->af = udest->af; @@ -1445,7 +1488,7 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) dest->port = udest->port; atomic_set(&dest->activeconns, 0); - atomic_set(&dest->inactconns, 0); + atomic_set(&dest->totalconns, 0); atomic_set(&dest->persistconns, 0); refcount_set(&dest->refcnt, 1); @@ -1486,6 +1529,9 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) return -ERANGE; } + if (udest->u_threshold > INT_MAX) + return -EINVAL; + if (udest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { if (udest->tun_port == 0) { pr_err("%s(): tunnel port is zero\n", __func__); @@ -1559,6 +1605,9 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) return -ERANGE; } + if (udest->u_threshold > INT_MAX) + return -EINVAL; + if (udest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { if (udest->tun_port == 0) { pr_err("%s(): tunnel port is zero\n", __func__); @@ -1613,7 +1662,7 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, int svcupd) { - dest->flags &= ~IP_VS_DEST_F_AVAILABLE; + dest->cflags &= ~IP_VS_DEST_CF_AVAILABLE; spin_lock_bh(&dest->dst_lock); __ip_vs_dst_cache_reset(dest); @@ -3031,7 +3080,7 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v) ip_vs_fwd_name(atomic_read(&dest->conn_flags)), atomic_read(&dest->weight), atomic_read(&dest->activeconns), - atomic_read(&dest->inactconns)); + ip_vs_dest_inactconns(dest)); else #endif seq_printf(seq, @@ -3042,7 +3091,7 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v) ip_vs_fwd_name(atomic_read(&dest->conn_flags)), atomic_read(&dest->weight), atomic_read(&dest->activeconns), - atomic_read(&dest->inactconns)); + ip_vs_dest_inactconns(dest)); } } @@ -3667,10 +3716,10 @@ __ip_vs_get_dest_entries(struct netns_ipvs *ipvs, const struct ip_vs_get_dests * entry.port = dest->port; entry.conn_flags = atomic_read(&dest->conn_flags); entry.weight = atomic_read(&dest->weight); - entry.u_threshold = dest->u_threshold; - entry.l_threshold = dest->l_threshold; + entry.u_threshold = READ_ONCE(dest->u_threshold); + entry.l_threshold = READ_ONCE(dest->l_threshold); entry.activeconns = atomic_read(&dest->activeconns); - entry.inactconns = atomic_read(&dest->inactconns); + entry.inactconns = ip_vs_dest_inactconns(dest); entry.persistconns = atomic_read(&dest->persistconns); ip_vs_copy_stats(&kstats, &dest->stats); ip_vs_export_stats_user(&entry.stats, &kstats); @@ -4277,12 +4326,14 @@ static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest) dest->tun_port) || nla_put_u16(skb, IPVS_DEST_ATTR_TUN_FLAGS, dest->tun_flags) || - nla_put_u32(skb, IPVS_DEST_ATTR_U_THRESH, dest->u_threshold) || - nla_put_u32(skb, IPVS_DEST_ATTR_L_THRESH, dest->l_threshold) || + nla_put_u32(skb, IPVS_DEST_ATTR_U_THRESH, + READ_ONCE(dest->u_threshold)) || + nla_put_u32(skb, IPVS_DEST_ATTR_L_THRESH, + READ_ONCE(dest->l_threshold)) || nla_put_u32(skb, IPVS_DEST_ATTR_ACTIVE_CONNS, atomic_read(&dest->activeconns)) || nla_put_u32(skb, IPVS_DEST_ATTR_INACT_CONNS, - atomic_read(&dest->inactconns)) || + ip_vs_dest_inactconns(dest)) || nla_put_u32(skb, IPVS_DEST_ATTR_PERSIST_CONNS, atomic_read(&dest->persistconns)) || nla_put_u16(skb, IPVS_DEST_ATTR_ADDR_FAMILY, dest->af)) diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c index e1f62f6b25e2..43abed7a26a6 100644 --- a/net/netfilter/ipvs/ip_vs_dh.c +++ b/net/netfilter/ipvs/ip_vs_dh.c @@ -219,8 +219,8 @@ ip_vs_dh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, s = (struct ip_vs_dh_state *) svc->sched_data; dest = ip_vs_dh_get(svc->af, s, &iph->daddr); - if (!dest - || !(dest->flags & IP_VS_DEST_F_AVAILABLE) + if (!dest || + !(dest->cflags & IP_VS_DEST_CF_AVAILABLE) || atomic_read(&dest->weight) <= 0 || is_overloaded(dest)) { ip_vs_scheduler_err(svc, "no destination available"); diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 15ccb2b2fa1f..693bcc82ccb7 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -502,7 +502,7 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, */ dest = en->dest; - if ((dest->flags & IP_VS_DEST_F_AVAILABLE) && + if ((dest->cflags & IP_VS_DEST_CF_AVAILABLE) && atomic_read(&dest->weight) > 0 && !is_overloaded(dest, svc)) goto out; } diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index c90ea897c3f7..f53f05ceea36 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -169,8 +169,8 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) if (least->flags & IP_VS_DEST_F_OVERLOAD) continue; - if ((atomic_read(&least->weight) > 0) - && (least->flags & IP_VS_DEST_F_AVAILABLE)) { + if ((atomic_read(&least->weight) > 0) && + (least->cflags & IP_VS_DEST_CF_AVAILABLE)) { loh = ip_vs_dest_conn_overhead(least); goto nextstage; } @@ -186,8 +186,8 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) doh = ip_vs_dest_conn_overhead(dest); if (((__s64)loh * atomic_read(&dest->weight) > - (__s64)doh * atomic_read(&least->weight)) - && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { + (__s64)doh * atomic_read(&least->weight)) && + (dest->cflags & IP_VS_DEST_CF_AVAILABLE)) { least = dest; loh = doh; } diff --git a/net/netfilter/ipvs/ip_vs_lc.c b/net/netfilter/ipvs/ip_vs_lc.c index 38cc38c5d8bb..18b976a7c4d2 100644 --- a/net/netfilter/ipvs/ip_vs_lc.c +++ b/net/netfilter/ipvs/ip_vs_lc.c @@ -30,7 +30,7 @@ ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, /* * Simply select the server with the least number of - * (activeconns<<5) + inactconns + * (activeconns*256) + totalconns * Except whose weight is equal to zero. * If the weight is equal to zero, it means that the server is * quiesced, the existing connections to the server still get @@ -56,7 +56,7 @@ ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), - atomic_read(&least->inactconns)); + ip_vs_dest_inactconns(least)); return least; } diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index c80567c73469..fb8af6b15a39 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -446,12 +446,10 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && (next_state != IP_VS_SCTP_S_ESTABLISHED)) { atomic_dec(&dest->activeconns); - atomic_inc(&dest->inactconns); cp->flags |= IP_VS_CONN_F_INACTIVE; } else if ((cp->flags & IP_VS_CONN_F_INACTIVE) && (next_state == IP_VS_SCTP_S_ESTABLISHED)) { atomic_inc(&dest->activeconns); - atomic_dec(&dest->inactconns); cp->flags &= ~IP_VS_CONN_F_INACTIVE; } } diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 99a286fdc90c..fec0e8b47b71 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -526,12 +526,10 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && !tcp_state_active(new_state)) { atomic_dec(&dest->activeconns); - atomic_inc(&dest->inactconns); cp->flags |= IP_VS_CONN_F_INACTIVE; } else if ((cp->flags & IP_VS_CONN_F_INACTIVE) && tcp_state_active(new_state)) { atomic_inc(&dest->activeconns); - atomic_dec(&dest->inactconns); cp->flags &= ~IP_VS_CONN_F_INACTIVE; } } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 93038abbf5e0..ea5fdd4f4ce7 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -878,13 +878,10 @@ static void ip_vs_proc_conn(struct netns_ipvs *ipvs, struct ip_vs_conn_param *pa spin_lock_bh(&cp->lock); if ((cp->flags ^ flags) & IP_VS_CONN_F_INACTIVE && !(flags & IP_VS_CONN_F_TEMPLATE) && dest) { - if (flags & IP_VS_CONN_F_INACTIVE) { + if (flags & IP_VS_CONN_F_INACTIVE) atomic_dec(&dest->activeconns); - atomic_inc(&dest->inactconns); - } else { + else atomic_inc(&dest->activeconns); - atomic_dec(&dest->inactconns); - } } flags &= IP_VS_CONN_F_BACKUP_UPD_MASK; flags |= cp->flags & ~IP_VS_CONN_F_BACKUP_UPD_MASK; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index c4508f3f43dd..04450a48f01a 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -351,7 +351,7 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, * stored in dest_trash. */ if (!rt_dev_is_down(dst_dev_rcu(&rt->dst)) && - dest->flags & IP_VS_DEST_F_AVAILABLE) + dest->cflags & IP_VS_DEST_CF_AVAILABLE) __ip_vs_dst_set(dest, dest_dst, &rt->dst, 0); else noref = 0; @@ -530,7 +530,7 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, * stored in dest_trash. */ if (!rt_dev_is_down(dst_dev_rcu(&rt->dst)) && - dest->flags & IP_VS_DEST_F_AVAILABLE) + dest->cflags & IP_VS_DEST_CF_AVAILABLE) __ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie); else noref = 0; @@ -1580,7 +1580,8 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error; - ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports, ciph); + if (!ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports, ciph)) + goto tx_error; /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index ad96896516b6..7a40e4e0e33e 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -79,6 +79,12 @@ void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, struct net *net; va_list args; + /* nfnetlink_log may re-enter conntrack attribute dumping and try to + * take ct->lock again via helpers such as tcp_to_nlattr(), so invalid + * conntrack logs must only be emitted after dropping ct->lock. + */ + lockdep_assert_not_held(&ct->lock); + net = nf_ct_net(ct); if (likely(net->ct.sysctl_log_invalid == 0)) return; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 7e10fa65cbdd..71cc920f6856 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -336,10 +336,12 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, struct sctphdr _sctph; const struct sctp_chunkhdr *sch; struct sctp_chunkhdr _sch; + bool log_invalid = false; u_int32_t offset, count; unsigned int *timeouts; unsigned long map[256 / sizeof(unsigned long)] = { 0 }; bool ignore = false; + u8 invalid_type = 0; if (sctp_error(skb, dataoff, state)) return -NF_ACCEPT; @@ -451,10 +453,8 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, /* Invalid */ if (new_state == SCTP_CONNTRACK_MAX) { - nf_ct_l4proto_log_invalid(skb, ct, state, - "Invalid, old_state %d, dir %d, type %d", - old_state, dir, sch->type); - + log_invalid = true; + invalid_type = sch->type; goto out_unlock; } @@ -529,6 +529,10 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, out_unlock: spin_unlock_bh(&ct->lock); + if (log_invalid) + nf_ct_l4proto_log_invalid(skb, ct, state, + "Invalid, old_state %d, dir %d, type %d", + old_state, dir, invalid_type); out: return -NF_ACCEPT; } diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index ceeed3d7fe52..30b970e2ade5 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -480,37 +480,81 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender, } } -__printf(6, 7) -static enum nf_ct_tcp_action nf_tcp_log_invalid(const struct sk_buff *skb, - const struct nf_conn *ct, - const struct nf_hook_state *state, - const struct ip_ct_tcp_state *sender, - enum nf_ct_tcp_action ret, - const char *fmt, ...) +enum nf_tcp_invalid_log_type { + NF_TCP_LOG_NONE, + NF_TCP_LOG_OVERSHOT, + NF_TCP_LOG_SEQ_OVER, + NF_TCP_LOG_ACK_OVER, + NF_TCP_LOG_SEQ_UNDER, + NF_TCP_LOG_ACK_UNDER, +}; + +struct nf_tcp_invalid_log { + enum nf_tcp_invalid_log_type type; + u32 value; +}; + +static enum nf_ct_tcp_action +nf_tcp_store_invalid(const struct nf_conn *ct, + const struct ip_ct_tcp_state *sender, + struct nf_tcp_invalid_log *log, + enum nf_ct_tcp_action ret, + enum nf_tcp_invalid_log_type type, + u32 value) { const struct nf_tcp_net *tn = nf_tcp_pernet(nf_ct_net(ct)); - struct va_format vaf; - va_list args; bool be_liberal; be_liberal = sender->flags & IP_CT_TCP_FLAG_BE_LIBERAL || tn->tcp_be_liberal; if (be_liberal) return NFCT_TCP_ACCEPT; - va_start(args, fmt); - vaf.fmt = fmt; - vaf.va = &args; - nf_ct_l4proto_log_invalid(skb, ct, state, "%pV", &vaf); - va_end(args); - + log->type = type; + log->value = value; return ret; } +static void nf_tcp_log_invalid(const struct sk_buff *skb, + const struct nf_conn *ct, + const struct nf_hook_state *state, + const struct nf_tcp_invalid_log *log) +{ + switch (log->type) { + case NF_TCP_LOG_OVERSHOT: + nf_ct_l4proto_log_invalid(skb, ct, state, + "%u bytes more than expected", + log->value); + break; + case NF_TCP_LOG_SEQ_OVER: + nf_ct_l4proto_log_invalid(skb, ct, state, + "SEQ is over upper bound %u (over the window of the receiver)", + log->value); + break; + case NF_TCP_LOG_ACK_OVER: + nf_ct_l4proto_log_invalid(skb, ct, state, + "ACK is over upper bound %u (ACKed data not seen yet)", + log->value); + break; + case NF_TCP_LOG_SEQ_UNDER: + nf_ct_l4proto_log_invalid(skb, ct, state, + "SEQ is under lower bound %u (already ACKed data retransmitted)", + log->value); + break; + case NF_TCP_LOG_ACK_UNDER: + nf_ct_l4proto_log_invalid(skb, ct, state, + "ignored ACK under lower bound %u (possible overly delayed)", + log->value); + break; + case NF_TCP_LOG_NONE: + break; + } +} + static enum nf_ct_tcp_action tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, unsigned int index, const struct sk_buff *skb, unsigned int dataoff, const struct tcphdr *tcph, - const struct nf_hook_state *hook_state) + struct nf_tcp_invalid_log *log) { struct ip_ct_tcp *state = &ct->proto.tcp; struct ip_ct_tcp_state *sender = &state->seen[dir]; @@ -640,31 +684,29 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, sender->td_end = end; sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED; - return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_IGNORE, - "%u bytes more than expected", overshot); + return nf_tcp_store_invalid(ct, sender, log, NFCT_TCP_IGNORE, + NF_TCP_LOG_OVERSHOT, overshot); } - return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_INVALID, - "SEQ is over upper bound %u (over the window of the receiver)", - sender->td_maxend + 1); + return nf_tcp_store_invalid(ct, sender, log, NFCT_TCP_INVALID, + NF_TCP_LOG_SEQ_OVER, sender->td_maxend + 1); } if (!before(sack, receiver->td_end + 1)) - return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_INVALID, - "ACK is over upper bound %u (ACKed data not seen yet)", - receiver->td_end + 1); + return nf_tcp_store_invalid(ct, sender, log, NFCT_TCP_INVALID, + NF_TCP_LOG_ACK_OVER, receiver->td_end + 1); /* Is the ending sequence in the receive window (if available)? */ in_recv_win = !receiver->td_maxwin || after(end, sender->td_end - receiver->td_maxwin - 1); if (!in_recv_win) - return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_IGNORE, - "SEQ is under lower bound %u (already ACKed data retransmitted)", - sender->td_end - receiver->td_maxwin - 1); + return nf_tcp_store_invalid(ct, sender, log, NFCT_TCP_IGNORE, + NF_TCP_LOG_SEQ_UNDER, + sender->td_end - receiver->td_maxwin - 1); if (!after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1)) - return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_IGNORE, - "ignored ACK under lower bound %u (possible overly delayed)", - receiver->td_end - MAXACKWINDOW(sender) - 1); + return nf_tcp_store_invalid(ct, sender, log, NFCT_TCP_IGNORE, + NF_TCP_LOG_ACK_UNDER, + receiver->td_end - MAXACKWINDOW(sender) - 1); /* Take into account window scaling (RFC 1323). */ if (!tcph->syn) @@ -719,11 +761,8 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, return NFCT_TCP_ACCEPT; } -static void __cold nf_tcp_handle_invalid(struct nf_conn *ct, - enum ip_conntrack_dir dir, - int index, - const struct sk_buff *skb, - const struct nf_hook_state *hook_state) +static bool __cold +nf_tcp_handle_invalid(struct nf_conn *ct, enum ip_conntrack_dir dir, int index) { const unsigned int *timeouts; const struct nf_tcp_net *tn; @@ -732,7 +771,7 @@ static void __cold nf_tcp_handle_invalid(struct nf_conn *ct, if (!test_bit(IPS_ASSURED_BIT, &ct->status) || test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status)) - return; + return false; /* We don't want to have connections hanging around in ESTABLISHED * state for long time 'just because' conntrack deemed a FIN/RST @@ -747,7 +786,7 @@ static void __cold nf_tcp_handle_invalid(struct nf_conn *ct, case TCP_FIN_SET: break; default: - return; + return false; } if (ct->proto.tcp.last_dir != dir && @@ -755,7 +794,7 @@ static void __cold nf_tcp_handle_invalid(struct nf_conn *ct, ct->proto.tcp.last_index == TCP_RST_SET)) { expires = nf_ct_expires(ct); if (expires < 120 * HZ) - return; + return false; tn = nf_tcp_pernet(nf_ct_net(ct)); timeouts = nf_ct_timeout_lookup(ct); @@ -764,16 +803,15 @@ static void __cold nf_tcp_handle_invalid(struct nf_conn *ct, timeout = READ_ONCE(timeouts[TCP_CONNTRACK_UNACK]); if (expires > timeout) { - nf_ct_l4proto_log_invalid(skb, ct, hook_state, - "packet (index %d, dir %d) response for index %d lower timeout to %u", - index, dir, ct->proto.tcp.last_index, timeout); - WRITE_ONCE(ct->timeout, timeout + nfct_time_stamp); + return true; } } else { ct->proto.tcp.last_index = index; ct->proto.tcp.last_dir = dir; } + + return false; } /* table of valid flag combinations - PUSH, ECE and CWR are always valid */ @@ -969,7 +1007,9 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, struct net *net = nf_ct_net(ct); struct nf_tcp_net *tn = nf_tcp_pernet(net); enum tcp_conntrack new_state, old_state; + struct nf_tcp_invalid_log log = {}; unsigned int index, *timeouts; + bool lowered_timeout = false; enum nf_ct_tcp_action res; enum ip_conntrack_dir dir; const struct tcphdr *th; @@ -1252,14 +1292,18 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, } res = tcp_in_window(ct, dir, index, - skb, dataoff, th, state); + skb, dataoff, th, &log); switch (res) { case NFCT_TCP_IGNORE: spin_unlock_bh(&ct->lock); + nf_tcp_log_invalid(skb, ct, state, &log); return NF_ACCEPT; case NFCT_TCP_INVALID: - nf_tcp_handle_invalid(ct, dir, index, skb, state); + lowered_timeout = nf_tcp_handle_invalid(ct, dir, index); spin_unlock_bh(&ct->lock); + nf_tcp_log_invalid(skb, ct, state, &log); + if (lowered_timeout) + nf_ct_l4proto_log_invalid(skb, ct, state, "lowered timeout to UNACK"); return -NF_ACCEPT; case NFCT_TCP_ACCEPT: break; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index b66e65439341..8b1165f2b5a4 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -332,17 +332,18 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); err = rhashtable_insert_fast(&flow_table->rhashtable, - &flow->tuplehash[0].node, + &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node, nf_flow_offload_rhash_params); if (err < 0) return err; + /* GC only iterates original-direction entries; publish original last. */ err = rhashtable_insert_fast(&flow_table->rhashtable, - &flow->tuplehash[1].node, + &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node, nf_flow_offload_rhash_params); if (err < 0) { rhashtable_remove_fast(&flow_table->rhashtable, - &flow->tuplehash[0].node, + &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node, nf_flow_offload_rhash_params); return err; } diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c index e37b09b3203b..5ffde27d450a 100644 --- a/net/netfilter/nf_log_syslog.c +++ b/net/netfilter/nf_log_syslog.c @@ -1014,7 +1014,7 @@ err1: return ret; } -static void __net_exit nf_log_syslog_net_exit(struct net *net) +static void __net_exit nf_log_syslog_net_pre_exit(struct net *net) { nf_log_unset(net, &nf_ip_logger); nf_log_unset(net, &nf_arp_logger); @@ -1025,7 +1025,7 @@ static void __net_exit nf_log_syslog_net_exit(struct net *net) static struct pernet_operations nf_log_syslog_net_ops = { .init = nf_log_syslog_net_init, - .exit = nf_log_syslog_net_exit, + .pre_exit = nf_log_syslog_net_pre_exit, }; static int __init nf_log_syslog_init(void) diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 8998a24651ff..0ac3c26dfb3d 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -558,7 +558,7 @@ static void nft_flow_rule_offload_abort(struct net *net, break; } - if (WARN_ON_ONCE(err)) + if (WARN_ON_ONCE(err && err != -ENOMEM)) break; } } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 5fee61b3813c..6c7fa2ed34f5 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -1170,21 +1170,26 @@ static int __net_init nfnl_log_net_init(struct net *net) return 0; } -static void __net_exit nfnl_log_net_exit(struct net *net) +static void __net_exit nfnl_log_net_pre_exit(struct net *net) { - struct nfnl_log_net *log = nfnl_log_pernet(net); - unsigned int i; - #ifdef CONFIG_PROC_FS remove_proc_entry("nfnetlink_log", net->nf.proc_netfilter); #endif nf_log_unset(net, &nfulnl_logger); +} + +static void __net_exit nfnl_log_net_exit(struct net *net) +{ + struct nfnl_log_net *log = nfnl_log_pernet(net); + unsigned int i; + for (i = 0; i < INSTANCE_BUCKETS; i++) WARN_ON_ONCE(!hlist_empty(&log->instance_table[i])); } static struct pernet_operations nfnl_log_net_ops = { .init = nfnl_log_net_init, + .pre_exit = nfnl_log_net_pre_exit, .exit = nfnl_log_net_exit, .id = &nfnl_log_net_id, .size = sizeof(struct nfnl_log_net), diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 435756877aba..1168bd6b09cd 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1943,13 +1943,13 @@ static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) sock->type == SOCK_RAW) skb->protocol = dev_parse_header_protocol(skb); + skb_probe_transport_header(skb); + /* Move network header to the right position for VLAN tagged packets */ if (likely(skb->dev->type == ARPHRD_ETHER) && eth_type_vlan(skb->protocol) && vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); - - skb_probe_transport_header(skb); } /* @@ -2660,6 +2660,9 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, len = ((to_write > len_max) ? len_max : to_write); } + if (unlikely(!skb->len)) + return -EINVAL; + packet_parse_headers(skb, sock); return tp_len; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index f141634df214..600b7804befd 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -41,11 +41,9 @@ int tcf_dev_queue_xmit(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb)) } EXPORT_SYMBOL_GPL(tcf_dev_queue_xmit); -static void tcf_action_goto_chain_exec(const struct tc_action *a, +static void tcf_action_goto_chain_exec(const struct tcf_chain *chain, struct tcf_result *res) { - const struct tcf_chain *chain = rcu_dereference_bh(a->goto_chain); - res->goto_tp = rcu_dereference_bh(chain->filter_chain); } @@ -1170,12 +1168,14 @@ repeat: return TC_ACT_OK; } } else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) { - if (unlikely(!rcu_access_pointer(a->goto_chain))) { + struct tcf_chain *chain = rcu_dereference_bh(a->goto_chain); + + if (unlikely(!chain)) { tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_CHAIN_NOTFOUND); return TC_ACT_SHOT; } - tcf_action_goto_chain_exec(a, res); + tcf_action_goto_chain_exec(chain, res); } if (ret != TC_ACT_PIPE) diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index be535a261fa0..e250969c84ac 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -840,8 +840,15 @@ static int tcf_ct_ipv6_is_fragment(struct sk_buff *skb, bool *frag) return 0; } +/* On error, tells the caller whether it still owns @skb and must free it + * itself. @skb is ours only when the header checks below reject the packet + * before it is handed to the defragmentation engine; once nf_ct_handle_ + * fragments() has been called the skb is either queued (-EINPROGRESS) or has + * already been freed by it. + */ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, - u8 family, u16 zone, bool *defrag) + u8 family, u16 zone, bool *defrag, + bool *skb_is_ours) { enum ip_conntrack_info ctinfo; struct tc_skb_cb cb; @@ -859,8 +866,12 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, err = tcf_ct_ipv4_is_fragment(skb, &frag); else err = tcf_ct_ipv6_is_fragment(skb, &frag); - if (err || !frag) + if (err) { + *skb_is_ours = true; return err; + } + if (!frag) + return 0; cb = *tc_skb_cb(skb); err = nf_ct_handle_fragments(net, skb, zone, family, &proto, &cb.mru); @@ -977,6 +988,7 @@ TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, int nh_ofs, err, retval; struct tcf_ct_params *p; bool add_helper = false; + bool skb_is_ours = false; bool skip_add = false; bool defrag = false; struct nf_conn *ct; @@ -1012,9 +1024,18 @@ TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, */ nh_ofs = skb_network_offset(skb); skb_pull_rcsum(skb, nh_ofs); - err = tcf_ct_handle_fragments(net, skb, family, p->zone, &defrag); - if (err) + err = tcf_ct_handle_fragments(net, skb, family, p->zone, &defrag, + &skb_is_ours); + if (err) { + /* The skb is still ours only when the header checks rejected + * it; returning TC_ACT_CONSUMED for such a packet would leak + * it, since no caller frees an skb it was told it no longer + * owns. + */ + if (skb_is_ours) + goto drop; goto out_frag; + } err = nf_ct_skb_network_trim(skb, family); if (err) diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index e949280eb800..565860cccba6 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -89,6 +89,11 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, p_parm = nla_data(tb[TCA_GACT_PROB]); if (p_parm->ptype >= MAX_RAND) return -EINVAL; + if (!tcf_action_valid(p_parm->paction)) { + NL_SET_ERR_MSG(extack, + "invalid fallback control action"); + return -EINVAL; + } if (TC_ACT_EXT_CMP(p_parm->paction, TC_ACT_GOTO_CHAIN)) { NL_SET_ERR_MSG(extack, "goto chain not allowed on fallback"); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index b16468a98c55..ce08f6840ef7 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -128,6 +128,12 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, if (tb[TCA_POLICE_RESULT]) { tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]); + if (!tcf_action_valid(tcfp_result)) { + NL_SET_ERR_MSG(extack, + "invalid fallback control action"); + err = -EINVAL; + goto failure; + } if (TC_ACT_EXT_CMP(tcfp_result, TC_ACT_GOTO_CHAIN)) { NL_SET_ERR_MSG(extack, "goto chain not allowed on fallback"); diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 001d8c4ebfed..6d19155becc8 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -374,7 +374,8 @@ static int cls_bpf_prog_from_ops(struct nlattr **tb, struct cls_bpf_prog *prog) } static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, - u32 gen_flags, const struct tcf_proto *tp) + u32 gen_flags, const struct tcf_proto *tp, + struct netlink_ext_ack *extack) { struct bpf_prog *fp; char *name = NULL; @@ -388,6 +389,19 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, if (IS_ERR(fp)) return PTR_ERR(fp); + if (bpf_prog_is_dev_bound(fp->aux)) { + struct tcf_block *block = tp->chain->block; + struct net_device *dev; + + dev = block->q ? qdisc_dev(block->q) : NULL; + if (!dev || !bpf_offload_dev_match(fp, dev)) { + NL_SET_ERR_MSG(extack, + "Program is bound to a different device"); + bpf_prog_put(fp); + return -EINVAL; + } + } + if (tb[TCA_BPF_NAME]) { name = nla_memdup(tb[TCA_BPF_NAME], GFP_KERNEL); if (!name) { @@ -492,7 +506,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, prog->gen_flags = gen_flags; ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : - cls_bpf_prog_from_efd(tb, prog, gen_flags, tp); + cls_bpf_prog_from_efd(tb, prog, gen_flags, tp, extack); if (ret < 0) goto errout_idr; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index ac98b1c2144a..c297d7dbcf91 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -1346,6 +1346,9 @@ static void u32_bind_class(void *fh, u32 classid, unsigned long cl, void *q, { struct tc_u_knode *n = fh; + if (TC_U32_KEY(n->handle) == 0) + return; + tc_cls_bind_class(classid, cl, q, &n->res, base); } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 5b0ae616e1ff..5be0bed2685e 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -543,6 +543,9 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc, asoc->addip_last_asconf->transport == peer) asoc->addip_last_asconf->transport = NULL; + if (asoc->new_transport == peer) + asoc->new_transport = NULL; + /* If we have something on the transmitted list, we have to * save it off. The best place is the active path. */ @@ -1713,6 +1716,8 @@ void sctp_asconf_queue_teardown(struct sctp_association *asoc) sctp_assoc_free_asconf_queue(asoc); /* Free any cached ASCONF chunk. */ - if (asoc->addip_last_asconf) + if (asoc->addip_last_asconf) { sctp_chunk_free(asoc->addip_last_asconf); + asoc->addip_last_asconf = NULL; + } } diff --git a/net/sctp/auth.c b/net/sctp/auth.c index c901d373af80..cc4229ee116d 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -377,6 +377,81 @@ nomem: return -ENOMEM; } +static bool sctp_auth_chunk_id_forbidden(__u8 chunk_id) +{ + switch (chunk_id) { + case SCTP_CID_INIT: + case SCTP_CID_INIT_ACK: + case SCTP_CID_SHUTDOWN_COMPLETE: + case SCTP_CID_AUTH: + return true; + default: + return false; + } +} + +/* Verify AUTH parameters copied from a state cookie before they are restored + * into an association. When cookie authentication is disabled these fields + * are peer-controlled, so they must satisfy the same constraints as locally + * generated AUTH parameters. + */ +bool sctp_auth_verify_cookie_params(const struct sctp_endpoint *ep, + const struct sctp_cookie *cookie) +{ + const struct sctp_paramhdr *random; + const struct sctp_hmac_algo_param *hmacs; + const struct sctp_chunks_param *chunks; + u16 hmacs_len, chunks_len; + u16 n_hmacs, n_chunks, i; + bool has_sha1 = false; + + if (sctp_sk(ep->base.sk)->cookie_auth_enable || !ep->auth_enable) + return true; + + random = (const struct sctp_paramhdr *)cookie->auth_random; + if (random->type != SCTP_PARAM_RANDOM || + ntohs(random->length) != sizeof(*random) + SCTP_AUTH_RANDOM_LENGTH) + return false; + + hmacs = (const struct sctp_hmac_algo_param *)cookie->auth_hmacs; + hmacs_len = ntohs(hmacs->param_hdr.length); + if (hmacs->param_hdr.type != SCTP_PARAM_HMAC_ALGO || + hmacs_len < sizeof(struct sctp_paramhdr) + + sizeof(hmacs->hmac_ids[0]) || + hmacs_len > sizeof(cookie->auth_hmacs) || + (hmacs_len - sizeof(struct sctp_paramhdr)) % + sizeof(hmacs->hmac_ids[0])) + return false; + + n_hmacs = (hmacs_len - sizeof(struct sctp_paramhdr)) / + sizeof(hmacs->hmac_ids[0]); + for (i = 0; i < n_hmacs; i++) { + u16 hmac_id = ntohs(hmacs->hmac_ids[i]); + + if (!sctp_hmac_supported(hmac_id)) + return false; + if (hmac_id == SCTP_AUTH_HMAC_ID_SHA1) + has_sha1 = true; + } + if (!has_sha1) + return false; + + chunks = (const struct sctp_chunks_param *)cookie->auth_chunks; + chunks_len = ntohs(chunks->param_hdr.length); + if (chunks->param_hdr.type != SCTP_PARAM_CHUNKS || + chunks_len < sizeof(struct sctp_paramhdr) || + chunks_len > sizeof(cookie->auth_chunks)) + return false; + + n_chunks = chunks_len - sizeof(struct sctp_paramhdr); + for (i = 0; i < n_chunks; i++) { + if (sctp_auth_chunk_id_forbidden(chunks->chunks[i])) + return false; + } + + return true; +} + /* Public interface to create the association shared key. * See code above for the algorithm. diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index e25612e9d082..236e25abc7a4 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1852,6 +1852,9 @@ struct sctp_association *sctp_unpack_cookie( /* Set up our peer's port number. */ retval->peer.port = ntohs(chunk->sctp_hdr->source); + if (!sctp_auth_verify_cookie_params(ep, bear_cookie)) + goto malformed; + /* Populate the association from the cookie. */ memcpy(&retval->c, bear_cookie, sizeof(*bear_cookie)); diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 708fa07d5fff..3a8e16b29660 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -6145,8 +6145,12 @@ enum sctp_disposition sctp_sf_t4_timer_expire( struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = asoc->addip_last_asconf; - struct sctp_transport *transport = chunk->transport; + struct sctp_transport *transport; + + if (!chunk) + return SCTP_DISPOSITION_CONSUME; + transport = chunk->transport; SCTP_INC_STATS(net, SCTP_MIB_T4_RTO_EXPIREDS); /* ADDIP 4.1 B1) Increment the error counters and perform path failure diff --git a/net/tipc/node.c b/net/tipc/node.c index 8e4ef2630ae4..683a136e53ef 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1061,18 +1061,23 @@ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id, static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete) { - struct tipc_link_entry *le = &n->links[bearer_id]; struct tipc_media_addr *maddr = NULL; - struct tipc_link *l = le->link; int old_bearer_id = bearer_id; + struct tipc_link_entry *le; struct sk_buff_head xmitq; - - if (!l) - return; + struct tipc_link *l; __skb_queue_head_init(&xmitq); + /* Synchronize the link lookup with bearer teardown. */ tipc_node_write_lock(n); + le = &n->links[bearer_id]; + l = le->link; + if (!l) { + tipc_node_write_unlock_fast(n); + return; + } + if (!tipc_link_is_establishing(l)) { __tipc_node_link_down(n, &bearer_id, &xmitq, &maddr); } else { diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 62d46736e24b..d1ad31986cf2 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2014,6 +2014,11 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, if (err < 0) return err; + /* If crypto failed the connection is broken */ + err = ctx->async_wait.err; + if (err) + goto splice_read_end; + if (!skb_queue_empty(&ctx->rx_list)) { skb = __skb_dequeue(&ctx->rx_list); } else { diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 0783555e2526..9fcaaf55cba5 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -186,6 +186,7 @@ static void unix_del_edge(struct scm_fp_list *fpl, struct unix_edge *edge) if (!vertex->out_degree) { edge->predecessor->vertex = NULL; list_move_tail(&vertex->entry, &fpl->vertices); + list_del(&vertex->scc_entry); } } diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index a0e72e402748..9d3cd4fff062 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -24,6 +24,7 @@ #include "kselftest_harness.h" #define TLS_PAYLOAD_MAX_LEN 16384 +#define TLS_HDR_LEN 5 #define SOL_TLS 282 static int fips_enabled; @@ -2732,28 +2733,83 @@ TEST_F(tls_err, bad_rec) EXPECT_EQ(errno, EAGAIN); } +/* cfd carries a byte stream, so one recv() can return part of a + * record. Take the fragment length from the record header and wait + * for the remainder. + */ +static void tls_send_bad_auth(struct __test_metadata *_metadata, + int fd, int cfd, int fd2) +{ + char buf[128]; + int len; + + memrnd(buf, sizeof(buf) / 2); + ASSERT_EQ(send(fd, buf, sizeof(buf) / 2, 0), sizeof(buf) / 2); + + ASSERT_EQ(recv(cfd, buf, TLS_HDR_LEN, MSG_WAITALL), TLS_HDR_LEN); + + len = ((unsigned char)buf[3] << 8) | (unsigned char)buf[4]; + ASSERT_GT(len, 0); + ASSERT_LE(len, (int)sizeof(buf) - TLS_HDR_LEN); + + ASSERT_EQ(recv(cfd, buf + TLS_HDR_LEN, len, MSG_WAITALL), len); + + buf[TLS_HDR_LEN + len - 1]++; + + ASSERT_EQ(send(fd2, buf, TLS_HDR_LEN + len, 0), TLS_HDR_LEN + len); +} + TEST_F(tls_err, bad_auth) { char buf[128]; - int n; if (self->notls) SKIP(return, "no TLS support"); - memrnd(buf, sizeof(buf) / 2); - EXPECT_EQ(send(self->fd, buf, sizeof(buf) / 2, 0), sizeof(buf) / 2); - n = recv(self->cfd, buf, sizeof(buf), 0); - EXPECT_GT(n, sizeof(buf) / 2); + tls_send_bad_auth(_metadata, self->fd, self->cfd, self->fd2); - buf[n - 1]++; - - EXPECT_EQ(send(self->fd2, buf, n, 0), n); EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); EXPECT_EQ(errno, EBADMSG); EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); EXPECT_EQ(errno, EBADMSG); } +/* A record that did not authenticate breaks the connection for every + * reader, splice included. + * + * The two decrypt paths reach that result differently. A synchronous + * decrypt leaves the record parsed, so the splice re-runs the decrypt + * and fails on the record itself; the ctx->async_wait.err check in + * tls_sw_splice_read() is not what stops it. Only an asynchronous + * decrypt, which needs a TLS 1.2 socket and an AEAD advertising + * CRYPTO_ALG_ASYNC, consumes the record before the failure is + * recorded, leaving that check the sole reason the splice fails. + */ +TEST_F(tls_err, bad_auth_splice) +{ + char buf[128]; + ssize_t ret; + int p[2]; + + if (self->notls) + SKIP(return, "no TLS support"); + + tls_send_bad_auth(_metadata, self->fd, self->cfd, self->fd2); + + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); + + ASSERT_GE(pipe(p), 0); + + ret = splice(self->cfd2, NULL, p[1], NULL, sizeof(buf), + SPLICE_F_NONBLOCK); + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno, EBADMSG); + + close(p[0]); + close(p[1]); +} + TEST_F(tls_err, bad_in_large_read) { char txt[3][64]; @@ -3009,7 +3065,6 @@ static size_t parse_tls_records(struct __test_metadata *_metadata, { const __u8 *rec = rx_buf; size_t total_plaintext_rx = 0; - const __u8 rec_header_len = 5; while (rec < rx_buf + rx_len) { __u16 record_payload_len; @@ -3029,7 +3084,7 @@ static size_t parse_tls_records(struct __test_metadata *_metadata, /* Plaintext must not exceed the specified limit */ ASSERT_LE(plaintext_len, max_payload_len); - rec += rec_header_len + record_payload_len; + rec += TLS_HDR_LEN + record_payload_len; } return total_plaintext_rx; diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json index da65f838bd52..8ab48def89b6 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json @@ -702,5 +702,45 @@ "$TC qdisc del dev $DUMMY clsact", "$TC qdisc del dev $DUMMY root handle 1:" ] + }, + { + "id": "c7a3", + "name": "Verify act_ct drops a packet whose header checks fail", + "category": [ + "actions", + "ct", + "scapy" + ], + "plugins": { + "requires": [ + "nsPlugin", + "scapyPlugin" + ] + }, + "setup": [ + [ + "$TC qdisc del dev $DEV1 clsact", + 0, + 1, + 2, + 255 + ], + "$TC qdisc add dev $DEV1 clsact" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 ingress protocol all prio 1 matchall action ct", + "scapy": [ + { + "iface": "$DEV0", + "count": 10, + "packet": "Ether(type=0x86dd)/IPv6(nh=0, plen=0, src='::1', dst='::2')" + } + ], + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DEV1 clsact", + "matchPattern": "dropped 10", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 clsact" + ] } ] |