From 0eaa1f245ac03ed0c6394159360532726f666811 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Fri, 29 May 2026 08:57:05 +0300 Subject: [PATCH 01/85] wifi: iwlwifi: mvm: don't support the reset handshake for old firmwares -77.ucode doesn't contain the fixes for this flow it seems. Don't use the firmware reset handshake even if the firmware claims support for it. Fixes: 906d4eb84408 ("iwlwifi: support firmware reset handshake") Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220600 Signed-off-by: Emmanuel Grumbach Reviewed-by: Johannes Berg Signed-off-by: Miri Korenblit Link: https://patch.msgid.link/20260529085453.9307b81d9b02.I21bba9e649f4cd0e35d3ea6cd97a03258be5832f@changeid --- drivers/net/wireless/intel/iwlwifi/mvm/ops.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index ae177477b201..384bed95835d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -1416,6 +1416,12 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_rf_cfg *cfg, fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_FW_RESET_HANDSHAKE); + /* Those firmware versions claim to support the fw_reset_handshake + * but they are buggy. + */ + if (IWL_UCODE_MAJOR(mvm->fw->ucode_ver) <= 77) + trans->conf.fw_reset_handshake = false; + trans->conf.queue_alloc_cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, WIDE_ID(DATA_PATH_GROUP, From 9bf1b409afc7c4a1f0340f3975846c4f3278643a Mon Sep 17 00:00:00 2001 From: Pagadala Yesu Anjaneyulu Date: Fri, 29 May 2026 08:57:06 +0300 Subject: [PATCH 02/85] wifi: iwlwifi: mld: send tx power constraints before link activation TX power constraints must be sent to the firmware before link activation. If not, the firmware will use default power values. Fix this by moving the iwl_mld_send_ap_tx_power_constraint_cmd() call from iwl_mld_start_ap_ibss() to iwl_mld_assign_vif_chanctx(), before iwl_mld_activate_link() for AP interfaces. Also update the guard in the function to allow it to run before link activation for AP interfaces. Signed-off-by: Pagadala Yesu Anjaneyulu Signed-off-by: Miri Korenblit Link: https://patch.msgid.link/20260529085453.06c94b01efd2.Id43bdfe5eb030061c23348779687ba71b5f58182@changeid --- drivers/net/wireless/intel/iwlwifi/mld/ap.c | 4 ---- drivers/net/wireless/intel/iwlwifi/mld/mac80211.c | 7 +++++++ drivers/net/wireless/intel/iwlwifi/mld/power.c | 2 +- 3 files changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mld/ap.c b/drivers/net/wireless/intel/iwlwifi/mld/ap.c index 5c59acc8c4c5..6598d9333333 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/ap.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/ap.c @@ -9,7 +9,6 @@ #include "ap.h" #include "hcmd.h" #include "tx.h" -#include "power.h" #include "key.h" #include "phy.h" #include "iwl-utils.h" @@ -273,9 +272,6 @@ int iwl_mld_start_ap_ibss(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx; int ret; - if (vif->type == NL80211_IFTYPE_AP) - iwl_mld_send_ap_tx_power_constraint_cmd(mld, vif, link); - ret = iwl_mld_update_beacon_template(mld, vif, link); if (ret) return ret; diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c index da6fd7471568..3c8daddc0bcb 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c @@ -1150,6 +1150,13 @@ int iwl_mld_assign_vif_chanctx(struct ieee80211_hw *hw, if (iwl_mld_can_activate_link(mld, vif, link)) { iwl_mld_tlc_update_phy(mld, vif, link); + /* FW requires AP_TX_POWER_CONSTRAINTS_CMD before link + * activation for AP and after link activation for STA, + * for an unknown reason. + */ + if (vif->type == NL80211_IFTYPE_AP) + iwl_mld_send_ap_tx_power_constraint_cmd(mld, vif, link); + ret = iwl_mld_activate_link(mld, link); if (ret) goto err; diff --git a/drivers/net/wireless/intel/iwlwifi/mld/power.c b/drivers/net/wireless/intel/iwlwifi/mld/power.c index 49b0d9f8f865..266fe16bb95d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/power.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/power.c @@ -366,7 +366,7 @@ iwl_mld_send_ap_tx_power_constraint_cmd(struct iwl_mld *mld, lockdep_assert_wiphy(mld->wiphy); - if (!mld_link->active) + if (!mld_link->active && vif->type != NL80211_IFTYPE_AP) return; if (link->chanreq.oper.chan->band != NL80211_BAND_6GHZ) From e0c121d545134af886b28c4c26d91abf5dd39c17 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Fri, 29 May 2026 08:57:07 +0300 Subject: [PATCH 03/85] wifi: iwlwifi: mvm: avoid oversized UATS command copy MCC_ALLOWED_AP_TYPE_CMD exceeds the fixed copied host-command buffer and triggers warnings in the gen2 enqueue path when command 0xc05 is sent. Use IWL_HCMD_DFL_NOCOPY as it was done before the offending commit. Fixes: 078df640ef05 ("wifi: iwlwifi: mld: add support for iwl_mcc_allowed_ap_type_cmd v2") Signed-off-by: Emmanuel Grumbach Signed-off-by: Miri Korenblit Link: https://patch.msgid.link/20260529085453.9af349ab459b.I348df3980764c15efce0099a35fe8a88fb2a6ee2@changeid --- drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 28 ++++++++++++++++----- 1 file changed, 22 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index f05df3a3300e..6e507d6dcdd2 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2025 Intel Corporation + * Copyright (C) 2012-2014, 2018-2026 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -459,9 +459,14 @@ static void iwl_mvm_phy_filter_init(struct iwl_mvm *mvm, static void iwl_mvm_uats_init(struct iwl_mvm *mvm) { + struct iwl_mcc_allowed_ap_type_cmd_v1 *cmd __free(kfree) = NULL; int cmd_id = WIDE_ID(REGULATORY_AND_NVM_GROUP, MCC_ALLOWED_AP_TYPE_CMD); - struct iwl_mcc_allowed_ap_type_cmd_v1 cmd = {}; + struct iwl_host_cmd hcmd = { + .id = cmd_id, + .len[0] = sizeof(*cmd), + .dataflags[0] = IWL_HCMD_DFL_NOCOPY, + }; u8 cmd_ver; int ret; @@ -485,14 +490,25 @@ static void iwl_mvm_uats_init(struct iwl_mvm *mvm) if (!mvm->fwrt.ap_type_cmd_valid) return; - BUILD_BUG_ON(sizeof(mvm->fwrt.ap_type_cmd.mcc_to_ap_type_map) != - sizeof(cmd.mcc_to_ap_type_map)); + /* Since we free the command immediately after iwl_mvm_send_cmd, we + * must send this command in SYNC mode. + */ + lockdep_assert_held(&mvm->mutex); - memcpy(cmd.mcc_to_ap_type_map, + cmd = kzalloc_obj(*cmd); + if (!cmd) + return; + + BUILD_BUG_ON(sizeof(mvm->fwrt.ap_type_cmd.mcc_to_ap_type_map) != + sizeof(cmd->mcc_to_ap_type_map)); + + memcpy(cmd->mcc_to_ap_type_map, mvm->fwrt.ap_type_cmd.mcc_to_ap_type_map, sizeof(mvm->fwrt.ap_type_cmd.mcc_to_ap_type_map)); - ret = iwl_mvm_send_cmd_pdu(mvm, cmd_id, 0, sizeof(cmd), &cmd); + hcmd.data[0] = cmd; + + ret = iwl_mvm_send_cmd(mvm, &hcmd); if (ret < 0) IWL_ERR(mvm, "failed to send MCC_ALLOWED_AP_TYPE_CMD (%d)\n", ret); From 093305d801fae6ff9b8bb531fd78b579794c4f80 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Sun, 31 May 2026 13:30:19 +0300 Subject: [PATCH 04/85] wifi: iwlwifi: pcie: simplify the resume flow if fast resume is not used In most distributions, NetworkManager shuts the device down before entering system suspend, so fast suspend is typically not used. On older devices, resume currently tries to grab NIC access to infer whether the device was powered off while suspended. That probe is only meaningful for the fast-suspend path where the device is expected to remain alive. Unfortunately, for unclear reasons, grabbing NIC access was harmful as reported in the bugzilla ticket below. Workaround this issue by simply not grabbing NIC access if fast suspend is not used. Cc: stable@vger.kernel.org Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221501 Assisted-by: GitHub Copilot:gpt-5.3-codex Signed-off-by: Emmanuel Grumbach Link: https://patch.msgid.link/20260531133005.e2ed9e0cd44f.If283625983a843933e0c01561a421daff184e9e9@changeid Signed-off-by: Miri Korenblit --- drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 56 +++++++++++-------- 1 file changed, 32 insertions(+), 24 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index dc99e7ac4726..eb3c5a6dd088 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -1225,33 +1225,41 @@ static int _iwl_pci_resume(struct device *device, bool restore) if (!trans->op_mode) return 0; - /* - * Scratch value was altered, this means the device was powered off, we - * need to reset it completely. - * Note: MAC (bits 0:7) will be cleared upon suspend even with wowlan, - * but not bits [15:8]. So if we have bits set in lower word, assume - * the device is alive. - * Alternatively, if the scratch value is 0xFFFFFFFF, then we no longer - * have access to the device and consider it powered off. - * For older devices, just try silently to grab the NIC. - */ - if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) { - u32 scratch = iwl_read32(trans, CSR_FUNC_SCRATCH); - - if (!(scratch & CSR_FUNC_SCRATCH_POWER_OFF_MASK) || - scratch == ~0U) - device_was_powered_off = true; - } else { + if (test_bit(STATUS_DEVICE_ENABLED, &trans->status)) { /* - * bh are re-enabled by iwl_trans_pcie_release_nic_access, - * so re-enable them if _iwl_trans_pcie_grab_nic_access fails. + * Scratch value was altered, this means the device was powered + * off, we need to reset it completely. + * Note: MAC (bits 0:7) will be cleared upon suspend even with + * wowlan, but not bits [15:8]. So if we have bits set in lower + * word, assume the device is alive. + * Alternatively, if the scratch value is 0xFFFFFFFF, then we + * no longer have access to the device and consider it powered + * off. + * For older devices, just try silently to grab the NIC. */ - local_bh_disable(); - if (_iwl_trans_pcie_grab_nic_access(trans, true)) { - iwl_trans_pcie_release_nic_access(trans); + if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) { + u32 scratch = iwl_read32(trans, CSR_FUNC_SCRATCH); + + if (!(scratch & CSR_FUNC_SCRATCH_POWER_OFF_MASK) || + scratch == ~0U) { + IWL_DEBUG_WOWLAN(trans, + "Scratch 0x%08x indicates device was powered off\n", + scratch); + device_was_powered_off = true; + } } else { - device_was_powered_off = true; - local_bh_enable(); + /* + * bh are re-enabled by iwl_trans_pcie_release_nic_access, + * so re-enable them if _iwl_trans_pcie_grab_nic_access + * fails. + */ + local_bh_disable(); + if (_iwl_trans_pcie_grab_nic_access(trans, true)) { + iwl_trans_pcie_release_nic_access(trans); + } else { + device_was_powered_off = true; + local_bh_enable(); + } } } From c6c5327dd18bec1e1bbf139b2cf5ae53608a9d30 Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Fri, 22 May 2026 12:47:17 +0200 Subject: [PATCH 05/85] netfilter: xt_NFQUEUE: prefer raw_smp_processor_id With PREEMPT_RCU this triggers a splat because smp_processor_id() can be preempted while inside a RCU critical section. If xt_NFQUEUE target is invoked via nft_compat_eval() path, we are inside a RCU critical section. Just use the raw version instead. Fixes: 0ca743a55991 ("netfilter: nf_tables: add compatibility layer for x_tables") Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_NFQUEUE.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c index 466da23e36ff..b32d153e3a18 100644 --- a/net/netfilter/xt_NFQUEUE.c +++ b/net/netfilter/xt_NFQUEUE.c @@ -91,7 +91,7 @@ nfqueue_tg_v3(struct sk_buff *skb, const struct xt_action_param *par) if (info->queues_total > 1) { if (info->flags & NFQ_FLAG_CPU_FANOUT) { - int cpu = smp_processor_id(); + int cpu = raw_smp_processor_id(); queue = info->queuenum + cpu % info->queues_total; } else { From 193989cc6d80dd8e0460fb3992e69fa03bf0ff9b Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Mon, 25 May 2026 07:07:44 +0300 Subject: [PATCH 06/85] ipvs: clear the svc scheduler ptr early on edit ip_vs_edit_service() while unbinding the old scheduler clears the svc->scheduler ptr after the scheduler module initiates RCU callbacks. This can cause packets to use the old scheduler at the time when svc->sched_data is already freed after RCU grace period. Fix it by clearing the ptr early in ip_vs_unbind_scheduler(), before the done_service method schedules any RCU callbacks. Also, if the new scheduler fails to initialize when replacing the old scheduler, try to restore the old scheduler while still returning the error code. Link: https://sashiko.dev/#/patchset/20260519015506.634185-1-rosenp%40gmail.com Fixes: 05f00505a89a ("ipvs: fix crash if scheduler is changed") Signed-off-by: Julian Anastasov Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 3 +-- net/netfilter/ipvs/ip_vs_ctl.c | 13 ++++++++----- net/netfilter/ipvs/ip_vs_sched.c | 14 +++++++------- 3 files changed, 16 insertions(+), 14 deletions(-) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index a02e569813d2..e517eaaa177b 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1824,8 +1824,7 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler); int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler); int ip_vs_bind_scheduler(struct ip_vs_service *svc, struct ip_vs_scheduler *scheduler); -void ip_vs_unbind_scheduler(struct ip_vs_service *svc, - struct ip_vs_scheduler *sched); +void ip_vs_unbind_scheduler(struct ip_vs_service *svc); struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name); void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler); struct ip_vs_conn * diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index bd9cae44d214..16daba8cac83 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1898,7 +1898,7 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, if (ret_hooks >= 0) ip_vs_unregister_hooks(ipvs, u->af); if (svc != NULL) { - ip_vs_unbind_scheduler(svc, sched); + ip_vs_unbind_scheduler(svc); ip_vs_service_free(svc); } ip_vs_scheduler_put(sched); @@ -1962,9 +1962,8 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) old_sched = rcu_dereference_protected(svc->scheduler, 1); if (sched != old_sched) { if (old_sched) { - ip_vs_unbind_scheduler(svc, old_sched); - RCU_INIT_POINTER(svc->scheduler, NULL); - /* Wait all svc->sched_data users */ + ip_vs_unbind_scheduler(svc); + /* Wait all svc->scheduler/sched_data users */ synchronize_rcu(); } /* Bind the new scheduler */ @@ -1972,6 +1971,10 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) ret = ip_vs_bind_scheduler(svc, sched); if (ret) { ip_vs_scheduler_put(sched); + /* Try to restore the old_sched */ + if (old_sched && + !ip_vs_bind_scheduler(svc, old_sched)) + old_sched = NULL; goto out; } } @@ -2027,7 +2030,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup) /* Unbind scheduler */ old_sched = rcu_dereference_protected(svc->scheduler, 1); - ip_vs_unbind_scheduler(svc, old_sched); + ip_vs_unbind_scheduler(svc); ip_vs_scheduler_put(old_sched); /* Unbind persistence engine, keep svc->pe */ diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c index c6e421c4e299..24adc38942a0 100644 --- a/net/netfilter/ipvs/ip_vs_sched.c +++ b/net/netfilter/ipvs/ip_vs_sched.c @@ -56,19 +56,19 @@ int ip_vs_bind_scheduler(struct ip_vs_service *svc, /* * Unbind a service with its scheduler */ -void ip_vs_unbind_scheduler(struct ip_vs_service *svc, - struct ip_vs_scheduler *sched) +void ip_vs_unbind_scheduler(struct ip_vs_service *svc) { - struct ip_vs_scheduler *cur_sched; + struct ip_vs_scheduler *sched; - cur_sched = rcu_dereference_protected(svc->scheduler, 1); - /* This check proves that old 'sched' was installed */ - if (!cur_sched) + sched = rcu_dereference_protected(svc->scheduler, 1); + if (!sched) return; + /* Reset the scheduler before initiating any RCU callbacks */ + rcu_assign_pointer(svc->scheduler, NULL); + smp_wmb(); /* paired with smp_rmb() in ip_vs_schedule() */ if (sched->done_service) sched->done_service(svc); - /* svc->scheduler can be set to NULL only by caller */ } From 36d29ceec32c8206a12dc2810cf65fd394e45baa Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Tue, 26 May 2026 10:02:27 +0800 Subject: [PATCH 07/85] netfilter: nft_fib_ipv6: bail out of sibling walk if rt got unlinked This was reported by Sashiko [1]. The RCU walk over rt->fib6_siblings can spin forever if rt is unlinked mid-iteration: rt->fib6_siblings.next still points into the old ring, so the loop never meets &rt->fib6_siblings as its terminator. fib6_purge_rt() always does WRITE_ONCE(rt->fib6_nsiblings, 0) before list_del_rcu(), so readers can use rt->fib6_nsiblings == 0 as the detach signal. The same pattern is used in fib6_info_uses_dev() and rt6_nlmsg_size(). [1]: https://sashiko.dev/#/patchset/20260520023411.391233-1-jiayuan.chen%40linux.dev Suggested-by: Florian Westphal Fixes: 1c32b24c234b ("netfilter: nft_fib_ipv6: switch to fib6_lookup") Signed-off-by: Jiayuan Chen Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/ipv6/netfilter/nft_fib_ipv6.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index c0a0075e2590..2dbe44715df3 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -191,6 +191,9 @@ static bool nft_fib6_info_nh_uses_dev(struct fib6_info *rt, if (nft_fib6_info_nh_dev_match(nh_dev, dev)) return true; + + if (!READ_ONCE(rt->fib6_nsiblings)) + return false; } return false; From 2fcba19caaeb2a33017459d3430f057967bb91b6 Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Tue, 26 May 2026 23:58:31 +0200 Subject: [PATCH 08/85] netfilter: synproxy: add mutex to guard hook reference counting As the synproxy infrastructure register netfilter hooks on-demand when a user adds the first iptables target or nftables expression, if done concurrently they can race each other. Introduce a mutex to serialize the refcount control blocks access from both frontends. While a per namespace mutex might be more efficient, it is not needed for target/expression like SYNPROXY. Fixes: ad49d86e07a4 ("netfilter: nf_tables: Add synproxy support") Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_synproxy_core.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 036c8586f49b..ed00114f65f3 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -22,6 +22,8 @@ #include #include +static DEFINE_MUTEX(synproxy_mutex); + unsigned int synproxy_net_id; EXPORT_SYMBOL_GPL(synproxy_net_id); @@ -769,26 +771,31 @@ static const struct nf_hook_ops ipv4_synproxy_ops[] = { int nf_synproxy_ipv4_init(struct synproxy_net *snet, struct net *net) { - int err; + int err = 0; + mutex_lock(&synproxy_mutex); if (snet->hook_ref4 == 0) { err = nf_register_net_hooks(net, ipv4_synproxy_ops, ARRAY_SIZE(ipv4_synproxy_ops)); if (err) - return err; + goto out; } snet->hook_ref4++; - return 0; +out: + mutex_unlock(&synproxy_mutex); + return err; } EXPORT_SYMBOL_GPL(nf_synproxy_ipv4_init); void nf_synproxy_ipv4_fini(struct synproxy_net *snet, struct net *net) { + mutex_lock(&synproxy_mutex); snet->hook_ref4--; if (snet->hook_ref4 == 0) nf_unregister_net_hooks(net, ipv4_synproxy_ops, ARRAY_SIZE(ipv4_synproxy_ops)); + mutex_unlock(&synproxy_mutex); } EXPORT_SYMBOL_GPL(nf_synproxy_ipv4_fini); @@ -1193,27 +1200,32 @@ static const struct nf_hook_ops ipv6_synproxy_ops[] = { int nf_synproxy_ipv6_init(struct synproxy_net *snet, struct net *net) { - int err; + int err = 0; + mutex_lock(&synproxy_mutex); if (snet->hook_ref6 == 0) { err = nf_register_net_hooks(net, ipv6_synproxy_ops, ARRAY_SIZE(ipv6_synproxy_ops)); if (err) - return err; + goto out; } snet->hook_ref6++; - return 0; +out: + mutex_unlock(&synproxy_mutex); + return err; } EXPORT_SYMBOL_GPL(nf_synproxy_ipv6_init); void nf_synproxy_ipv6_fini(struct synproxy_net *snet, struct net *net) { + mutex_lock(&synproxy_mutex); snet->hook_ref6--; if (snet->hook_ref6 == 0) nf_unregister_net_hooks(net, ipv6_synproxy_ops, ARRAY_SIZE(ipv6_synproxy_ops)); + mutex_unlock(&synproxy_mutex); } EXPORT_SYMBOL_GPL(nf_synproxy_ipv6_fini); #endif /* CONFIG_IPV6 */ From 66eba0ffce3b7e11449946b4cbbef8ea36112f56 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 27 May 2026 12:20:19 +0200 Subject: [PATCH 09/85] netfilter: conntrack_irc: fix possible out-of-bounds read When parsing fails after we've matched the command string we should bail out instead of trying to match a different command. This helper should be deprecated, given prevalence of TLS I doubt it has any relevance in 2026. Fixes: 869f37d8e48f ("[NETFILTER]: nf_conntrack/nf_nat: add IRC helper port") Closes: https://sashiko.dev/#/patchset/20260525182924.28456-1-fw%40strlen.de Signed-off-by: Florian Westphal Reviewed-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_irc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index 522183b9a604..2ebe4cb47cf6 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -203,7 +203,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, if (parse_dcc(data, data_limit, &dcc_ip, &dcc_port, &addr_beg_p, &addr_end_p)) { pr_debug("unable to parse dcc command\n"); - continue; + goto out; } pr_debug("DCC bound ip/port: %pI4:%u\n", @@ -217,7 +217,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, net_warn_ratelimited("Forged DCC command from %pI4: %pI4:%u\n", &tuple->src.u3.ip, &dcc_ip, dcc_port); - continue; + goto out; } exp = nf_ct_expect_alloc(ct); From c32b26aaa2f9216520a38b3f4bfeec846eb3eb8a Mon Sep 17 00:00:00 2001 From: Tristan Madani Date: Wed, 27 May 2026 13:57:50 +0000 Subject: [PATCH 10/85] netfilter: nft_tunnel: fix use-after-free on object destroy nft_tunnel_obj_destroy() calls metadata_dst_free() which directly kfree()s the metadata_dst, ignoring the dst_entry refcount. Packets that took a reference via dst_hold() in nft_tunnel_obj_eval() and are still queued (e.g. in a netem qdisc) are left with a dangling pointer. When these packets are eventually dequeued, dst_release() operates on freed memory. Replace metadata_dst_free() with dst_release() so the metadata_dst is freed only after all references are dropped. The dst subsystem already handles metadata_dst cleanup in dst_destroy() when DST_METADATA is set. Fixes: af308b94a2a4 ("netfilter: nf_tables: add tunnel support") Cc: stable@vger.kernel.org Signed-off-by: Tristan Madani Reviewed-by: Fernando Fernandez Mancera Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_tunnel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 0b987bc2132a..68f7cfbbee06 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -676,7 +676,7 @@ static void nft_tunnel_obj_destroy(const struct nft_ctx *ctx, { struct nft_tunnel_obj *priv = nft_obj_data(obj); - metadata_dst_free(priv->md); + dst_release(&priv->md->dst); } static struct nft_object_type nft_tunnel_obj_type; From 3027ecbdb5fdf9200251c21d4818e4c447ef78e1 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Thu, 28 May 2026 19:09:19 +0800 Subject: [PATCH 11/85] netfilter: nft_ct: bail out on template ct in get eval I noticed this issue while looking at a historic syzbot report [1]. A rule like the one below is enough to trigger the bug: table ip t { chain pre { type filter hook prerouting priority raw; ct zone set 1 ct original saddr 1.2.3.4 accept } } The first expression attaches a per-cpu template ct via nft_ct_set_zone_eval() (nf_ct_tmpl_alloc -> kzalloc, tuple is all zero, nf_ct_l3num(ct) == 0). The next expression then calls nft_ct_get_eval() on the same skb, treats the template as a real ct and hits the 16-byte memcpy path. With dreg at NFT_REG32_15 this overflows past struct nft_regs on the kernel stack; with smaller dreg values it silently clobbers adjacent registers. Reject template ct at the eval entry and in nft_ct_get_fast_eval(), mirroring the check nft_ct_set_eval() already has. Additionally, bound the address copy in NFT_CT_SRC / NFT_CT_DST by priv->len instead of by nf_ct_l3num(ct): nf_ct_get_tuple() zeroes the tuple before pkt_to_tuple() fills in only the protocol-relevant leading bytes, so the trailing bytes of tuple->{src,dst}.u3.all are well-defined zero. priv->len is validated at rule load, so the copy size is now bounded by the destination register rather than by an untrusted field on the conntrack. [1]: https://syzkaller.appspot.com/bug?id=389cf09cb72926114fce90dc85a2c3231dcb647c Fixes: 45d9bcda21f4 ("netfilter: nf_tables: validate len in nft_validate_data_load()") Suggested-by: Florian Westphal Signed-off-by: Jiayuan Chen Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_ct.c | 8 +++----- net/netfilter/nft_ct_fast.c | 2 +- 2 files changed, 4 insertions(+), 6 deletions(-) diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index fa2cc556331c..357513c6dcea 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -78,7 +78,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr, break; } - if (ct == NULL) + if (!ct || nf_ct_is_template(ct)) goto err; switch (priv->key) { @@ -180,12 +180,10 @@ static void nft_ct_get_eval(const struct nft_expr *expr, tuple = &ct->tuplehash[priv->dir].tuple; switch (priv->key) { case NFT_CT_SRC: - memcpy(dest, tuple->src.u3.all, - nf_ct_l3num(ct) == NFPROTO_IPV4 ? 4 : 16); + memcpy(dest, tuple->src.u3.all, priv->len); return; case NFT_CT_DST: - memcpy(dest, tuple->dst.u3.all, - nf_ct_l3num(ct) == NFPROTO_IPV4 ? 4 : 16); + memcpy(dest, tuple->dst.u3.all, priv->len); return; case NFT_CT_PROTO_SRC: nft_reg_store16(dest, (__force u16)tuple->src.u.all); diff --git a/net/netfilter/nft_ct_fast.c b/net/netfilter/nft_ct_fast.c index e684c8a91848..ecf7b3a404be 100644 --- a/net/netfilter/nft_ct_fast.c +++ b/net/netfilter/nft_ct_fast.c @@ -30,7 +30,7 @@ void nft_ct_get_fast_eval(const struct nft_expr *expr, break; } - if (!ct) { + if (!ct || nf_ct_is_template(ct)) { regs->verdict.code = NFT_BREAK; return; } From 67ba971ae02514d85818fe0c32549ab4bfa3bf49 Mon Sep 17 00:00:00 2001 From: Yiming Qian Date: Sat, 23 May 2026 12:29:10 +0000 Subject: [PATCH 12/85] netfilter: bridge: make ebt_snat ARP rewrite writable The ebtables SNAT target keeps the Ethernet source address rewrite behind skb_ensure_writable(skb, 0). This is intentional: at the bridge ebtables hooks the Ethernet header is addressed through skb_mac_header()/eth_hdr(), while skb->data points at the Ethernet payload. Asking skb_ensure_writable() for ETH_HLEN bytes would check the payload, not the Ethernet header, and would reintroduce the small packet regression fixed by commit 63137bc5882a. However, the optional ARP sender hardware address rewrite is different. It writes through skb_store_bits() at an offset relative to skb->data: skb_store_bits(skb, sizeof(struct arphdr), info->mac, ETH_ALEN) skb_header_pointer() only safely reads the ARP header; it does not make the later sender hardware address range writable. If that range is still held in a nonlinear skb fragment backed by a splice-imported file page, skb_store_bits() maps the frag page and copies the new MAC address directly into it. Ensure the ARP SHA range is writable before reading the ARP header and before calling skb_store_bits(). Fixes: 63137bc5882a ("netfilter: ebtables: Fixes dropping of small packets in bridge nat") Reported-by: Yiming Qian Signed-off-by: Yiming Qian Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/ebt_snat.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c index 7dfbcdfc30e5..c9e229af0366 100644 --- a/net/bridge/netfilter/ebt_snat.c +++ b/net/bridge/netfilter/ebt_snat.c @@ -31,6 +31,9 @@ ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par) const struct arphdr *ap; struct arphdr _ah; + if (skb_ensure_writable(skb, sizeof(_ah) + ETH_ALEN)) + return EBT_DROP; + ap = skb_header_pointer(skb, 0, sizeof(_ah), &_ah); if (ap == NULL) return EBT_DROP; From bb061d3de41707415269be75ebf700efb03ec212 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 12 May 2026 15:36:14 +0200 Subject: [PATCH 13/85] netfilter: nft_byteorder: remove multi-register support 64bit byteorder conversion is broken when several registers need to be converted because the source register array advances in steps for 4 bytes instead of 8: for (i = ... src64 = nft_reg_load64(&src[i]); ~~~~~ u32 *src nft_reg_store64(&dst64[i], Remove the multi-register support, it has other issues as well: Pablo points out that commit caf3ef7468f7 ("netfilter: nf_tables: prevent OOB access in nft_byteorder_eval") alters semantics: before the loop operated on registers, i.e. for ( ... ) dst32[i] = htons((u16)src32[i]) .. but after the patch it will operate on bytes, which makes this useless to convert e.g. concatenations, which store each compound in its own register. Multi-convert of u32 has one theoretical application: ct mark . meta mark . tcp dport @intervalset Because ct mark and meta mark are host byte order, use with intervals has to convert the byteorder for ct/meta mark value to network byte order (bigendian). nftables emits this: [ meta load mark => reg 1 ] [ byteorder reg 1 = hton(reg 1, 4, 4) ] [ ct load mark => reg 9 ] [ byteorder reg 9 = hton(reg 9, 4, 4) ] ... I.e. two separate calls. Theoretically it could be changed to do: [ meta load mark => reg 1 ] [ ct load mark => reg 9 ] [ byteorder reg 1 = htonl(reg 1, 4, 8) ] ... But then all it would take to change the set to meta mark . tcp dport . ct mark ... and we'd be back to two "byteorder" calls. IOW, support to convert a range of registers is both dysfunctional and dubious. Simplify this: remove the feature. Pablo Neira Ayuso points out that nftables before 1.1.0 can generate incorrect byteorder conversions, see 9fe58952c45a, "evaluate: skip byteorder conversion for selector smaller than 2 bytes" in nftables.git). Affected rulesets fail to load with this change and old userspace due to 'len != size' check. Fixes: c301f0981fdd ("netfilter: nf_tables: fix pointer math issue in nft_byteorder_eval()") Cc: # may break rule load with old nftables versions Reported-by: Michal Kubecek Link: https://lore.kernel.org/netfilter-devel/20240206104336.ctigqpkunom2ufmn@lion.mk-sys.cz/ Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_byteorder.c | 51 ++++++++++++++--------------------- 1 file changed, 20 insertions(+), 31 deletions(-) diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 2316c77f4228..dfd41fc8d9b8 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -19,7 +19,6 @@ struct nft_byteorder { u8 sreg; u8 dreg; enum nft_byteorder_ops op:8; - u8 len; u8 size; }; @@ -28,13 +27,8 @@ void nft_byteorder_eval(const struct nft_expr *expr, const struct nft_pktinfo *pkt) { const struct nft_byteorder *priv = nft_expr_priv(expr); - u32 *src = ®s->data[priv->sreg]; + const u32 *src = ®s->data[priv->sreg]; u32 *dst = ®s->data[priv->dreg]; - u16 *s16, *d16; - unsigned int i; - - s16 = (void *)src; - d16 = (void *)dst; switch (priv->size) { case 8: { @@ -43,18 +37,14 @@ void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->op) { case NFT_BYTEORDER_NTOH: - for (i = 0; i < priv->len / 8; i++) { - src64 = nft_reg_load64(&src[i]); - nft_reg_store64(&dst64[i], - be64_to_cpu((__force __be64)src64)); - } + src64 = nft_reg_load64(src); + + nft_reg_store64(dst64, be64_to_cpu((__force __be64)src64)); break; case NFT_BYTEORDER_HTON: - for (i = 0; i < priv->len / 8; i++) { - src64 = (__force __u64) - cpu_to_be64(nft_reg_load64(&src[i])); - nft_reg_store64(&dst64[i], src64); - } + src64 = (__force __u64)cpu_to_be64(nft_reg_load64(src)); + + nft_reg_store64(dst64, src64); break; } break; @@ -62,24 +52,20 @@ void nft_byteorder_eval(const struct nft_expr *expr, case 4: switch (priv->op) { case NFT_BYTEORDER_NTOH: - for (i = 0; i < priv->len / 4; i++) - dst[i] = ntohl((__force __be32)src[i]); + *dst = ntohl((__force __be32)*src); break; case NFT_BYTEORDER_HTON: - for (i = 0; i < priv->len / 4; i++) - dst[i] = (__force __u32)htonl(src[i]); + *dst = (__force __u32)htonl(*src); break; } break; case 2: switch (priv->op) { case NFT_BYTEORDER_NTOH: - for (i = 0; i < priv->len / 2; i++) - d16[i] = ntohs((__force __be16)s16[i]); + nft_reg_store16(dst, ntohs(nft_reg_load_be16(src))); break; case NFT_BYTEORDER_HTON: - for (i = 0; i < priv->len / 2; i++) - d16[i] = (__force __u16)htons(s16[i]); + nft_reg_store_be16(dst, htons(nft_reg_load16(src))); break; } break; @@ -137,20 +123,22 @@ static int nft_byteorder_init(const struct nft_ctx *ctx, if (err < 0) return err; - priv->len = len; + /* no longer support multi-reg conversions */ + if (len != size) + return -EOPNOTSUPP; err = nft_parse_register_load(ctx, tb[NFTA_BYTEORDER_SREG], &priv->sreg, - priv->len); + len); if (err < 0) return err; err = nft_parse_register_store(ctx, tb[NFTA_BYTEORDER_DREG], &priv->dreg, NULL, NFT_DATA_VALUE, - priv->len); + len); if (err < 0) return err; - if (nft_reg_overlap(priv->sreg, priv->dreg, priv->len)) + if (nft_reg_overlap(priv->sreg, priv->dreg, len)) return -EINVAL; return 0; @@ -167,10 +155,11 @@ static int nft_byteorder_dump(struct sk_buff *skb, goto nla_put_failure; if (nla_put_be32(skb, NFTA_BYTEORDER_OP, htonl(priv->op))) goto nla_put_failure; - if (nla_put_be32(skb, NFTA_BYTEORDER_LEN, htonl(priv->len))) - goto nla_put_failure; if (nla_put_be32(skb, NFTA_BYTEORDER_SIZE, htonl(priv->size))) goto nla_put_failure; + /* compatibility for old userspace which permitted size != len */ + if (nla_put_be32(skb, NFTA_BYTEORDER_LEN, htonl(priv->size))) + goto nla_put_failure; return 0; nla_put_failure: From 02896a7fa4cd3ec61d60ba30136841e4f04bdeac Mon Sep 17 00:00:00 2001 From: Nikolay Kuratov Date: Tue, 26 May 2026 19:29:32 +0300 Subject: [PATCH 14/85] net/mlx5: Reorder completion before putting command entry in cmd_work_handler Assuming callback != NULL && !page_queue, cmd_work_handler takes command entry with refcnt == 1 from mlx5_cmd_invoke. If either semaphore timeout or index allocation error happens, it does final cmd_ent_put(ent). To avoid access to freed memory, notify slotted completion before cmd_ent_put. This is theoretical issue found by Svace static analyser. Cc: stable@vger.kernel.org Fixes: 485d65e135712 ("net/mlx5: Add a timeout to acquire the command queue semaphore") Fixes: 0e2909c6bec90 ("net/mlx5: Fix variable not being completed when function returns") Signed-off-by: Nikolay Kuratov Reviewed-by: Md Haris Iqbal Reviewed-by: Moshe Shemesh Acked-by: Tariq Toukan Link: https://patch.msgid.link/20260526162932.501584-1-kniv@yandex-team.ru Signed-off-by: Paolo Abeni --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index c89417c1a1f9..e2895972cc82 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1002,12 +1002,13 @@ static void cmd_work_handler(struct work_struct *work) ent->callback(-EBUSY, ent->context); mlx5_free_cmd_msg(dev, ent->out); free_msg(dev, ent->in); + complete(&ent->slotted); cmd_ent_put(ent); } else { ent->ret = -EBUSY; complete(&ent->done); + complete(&ent->slotted); } - complete(&ent->slotted); return; } alloc_ret = cmd_alloc_index(cmd, ent); @@ -1017,13 +1018,14 @@ static void cmd_work_handler(struct work_struct *work) ent->callback(-EAGAIN, ent->context); mlx5_free_cmd_msg(dev, ent->out); free_msg(dev, ent->in); + complete(&ent->slotted); cmd_ent_put(ent); } else { ent->ret = -EAGAIN; complete(&ent->done); + complete(&ent->slotted); } up(&cmd->vars.sem); - complete(&ent->slotted); return; } } else { From 5057e1aca011e51ef51498c940ef96f3d3e8a305 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sun, 31 May 2026 12:08:12 -0400 Subject: [PATCH 15/85] net/sched: act_api: use RCU with deferred freeing for action lifecycle When NEWTFILTER and DELFILTER are run concurrently it is possible to create a race with an associated action. Let's illustrate with CPU0 running NEWTFILTER and CPU1 running DELFILTER: 0: mutex_lock() <-- holds the idr lock 0: rcu_read_lock() 0: p = idr_find(idr, index) <-- action p is valid (RCU protects IDR) 0: mutex_unlock() <-- releases the idr lock 1: refcount_dec_and_mutex_lock() <-- refcnt 1->0, mutex held 1: idr_remove(idr, index) <-- Action removed from IDR 1: mutex_unlock() <-- mutex released allowing us to delete the action 1: tcf_action_cleanup(p); kfree(p) <-- Kfrees p immediately, no deferral 0: refcount_inc_not_zero(&p->tcfa_refcnt) <-- ouch, UAF p points to freed memory This patch fixes the race condition between NEWTFILTER and DELFILTER by adding struct rcu_head to tc_action used in the deferral and introducing a call_rcu() in the delete path to defer the final kfree(). Note: this is a revert of commit d7fb60b9cafb ("net_sched: get rid of tcfa_rcu") but also modernization/simplification to directly use kfree_rcu(). Let's illustrate the new restored code path: 0: rcu_read_lock() 1: refcount_dec_and_mutex_lock() <-- refcnt 1->0, mutex held 1: idr_remove(idr, index) 1: mutex_unlock() 1: call_rcu(&p->tcfa_rcu, tcf_action_rcu_free) <-- defer kfree after grace period 0: p = idr_find(idr, index) 0: refcount_inc_not_zero(&p->tcfa_refcnt) <-- fails, refcnt already 0 1: rcu_read_unlock() <-- release so freeing can run after grace period After CPU1 calls idr_remove(), the object is no longer reachable through the IDR. CPU0's subsequent idr_find() will return NULL, and even if it still held a stale pointer, the immediate kfree() is now deferred until after the RCU grace period, so no UAF can occur. Fixes: d7fb60b9cafb ("net_sched: get rid of tcfa_rcu") Suggested-by: Jakub Kicinski Reported-by: Kyle Zeng Tested-by: Victor Nogueira Tested-by: syzbot@syzkaller.appspotmail.com Signed-off-by: Jamal Hadi Salim Tested-by: Kyle Zeng Reviewed-by: Pedro Tammela Reviewed-by: Eric Dumazet Reviewed-by: Victor Nogueira Link: https://patch.msgid.link/20260531160812.68020-1-jhs@mojatatu.com Signed-off-by: Jakub Kicinski --- include/net/act_api.h | 1 + net/sched/act_api.c | 7 +------ 2 files changed, 2 insertions(+), 6 deletions(-) diff --git a/include/net/act_api.h b/include/net/act_api.h index d11b79107930..fd2967ee08f7 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -45,6 +45,7 @@ struct tc_action { struct tc_cookie __rcu *user_cookie; struct tcf_chain __rcu *goto_chain; u32 tcfa_flags; + struct rcu_head tcfa_rcu; u8 hw_stats; u8 used_hw_stats; bool used_hw_stats_valid; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 332fd9695e54..04ea11c90e03 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -112,11 +112,6 @@ struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action, } EXPORT_SYMBOL(tcf_action_set_ctrlact); -/* XXX: For standalone actions, we don't need a RCU grace period either, because - * actions are always connected to filters and filters are already destroyed in - * RCU callbacks, so after a RCU grace period actions are already disconnected - * from filters. Readers later can not find us. - */ static void free_tcf(struct tc_action *p) { struct tcf_chain *chain = rcu_dereference_protected(p->goto_chain, 1); @@ -129,7 +124,7 @@ static void free_tcf(struct tc_action *p) if (chain) tcf_chain_put_by_act(chain); - kfree(p); + kfree_rcu(p, tcfa_rcu); } static void offload_action_hw_count_set(struct tc_action *act, From 2a58899d11009bffc7b4b32a571858f381121837 Mon Sep 17 00:00:00 2001 From: Yizhou Zhao Date: Wed, 27 May 2026 16:18:01 +0800 Subject: [PATCH 16/85] 6lowpan: fix off-by-one in multicast context address compression The second memcpy in lowpan_iphc_mcast_ctx_addr_compress() uses &data[1] as destination and &ipaddr->s6_addr[11] as source, but both should be offset by one: &data[2] and &ipaddr->s6_addr[12] respectively. This off-by-one has two consequences: 1. data[1] is overwritten with s6_addr[11], corrupting the RIID field in the compressed multicast address 2. data[5] is never written, so uninitialized kernel stack memory is transmitted over the network via lowpan_push_hc_data(), leaking kernel stack contents The correct inline data layout must match what the decompression function lowpan_uncompress_multicast_ctx_daddr() expects: data[0..1] = s6_addr[1..2] (flags/scope + RIID) data[2..5] = s6_addr[12..15] (group ID) Also zero-initialize the data array as a defensive measure against similar bugs in the future. Fixes: 5609c185f24d ("6lowpan: iphc: add support for stateful compression") Reported-by: Yizhou Zhao Reported-by: Yuxiang Yang Reported-by: Ao Wang Reported-by: Xuewei Feng Reported-by: Qi Li Reported-by: Ke Xu Signed-off-by: Yizhou Zhao Acked-by: Alexander Aring Link: https://patch.msgid.link/20260527081806.42747-1-zhaoyz24@mails.tsinghua.edu.cn Signed-off-by: Jakub Kicinski --- net/6lowpan/iphc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/6lowpan/iphc.c b/net/6lowpan/iphc.c index e116d308a8df..37eaff3f7b69 100644 --- a/net/6lowpan/iphc.c +++ b/net/6lowpan/iphc.c @@ -1086,12 +1086,12 @@ static u8 lowpan_iphc_mcast_ctx_addr_compress(u8 **hc_ptr, const struct lowpan_iphc_ctx *ctx, const struct in6_addr *ipaddr) { - u8 data[6]; + u8 data[6] = {}; /* flags/scope, reserved (RIID) */ memcpy(data, &ipaddr->s6_addr[1], 2); /* group ID */ - memcpy(&data[1], &ipaddr->s6_addr[11], 4); + memcpy(&data[2], &ipaddr->s6_addr[12], 4); lowpan_push_hc_data(hc_ptr, data, 6); return LOWPAN_IPHC_DAM_00; From a213a8950414c684999dcf03edeea6c46ede172e Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Wed, 27 May 2026 13:36:29 +0000 Subject: [PATCH 17/85] l2tp: pppol2tp: hold reference to session in pppol2tp_ioctl() pppol2tp_ioctl() read sock->sk->sk_user_data directly without any locks or reference counting. If a controllable sleep was induced during copy_from_user() (e.g. via a userfaultfd page fault sleep), a concurrent socket close could trigger pppol2tp_session_close() asynchronously. This frees the l2tp_session structure via the l2tp_session_del_work workqueue. Upon resuming, the ioctl thread dereferences the stale session pointer, resulting in a Use-After-Free (UAF). Fix this by securely fetching the session reference using the RCU-safe, refcounted helper pppol2tp_sock_to_session(sk) on entry. This locks the session's refcount across the sleep. We structured the function to exit via standard err breaks, guaranteeing that l2tp_session_put() is cleanly called on all return paths to drop the reference. To preserve existing behavior we validate the session and its magic signature only for the specific L2TP commands that require it. This ensures that generic/unknown ioctls called on an unconnected socket still return -ENOIOCTLCMD and correctly fall back to generic handlers (e.g. in sock_do_ioctl()). Signed-off-by: Lee Jones Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts") Link: https://patch.msgid.link/20260527133630.2120612-1-lee@kernel.org Signed-off-by: Jakub Kicinski --- net/l2tp/l2tp_ppp.c | 92 +++++++++++++++++++++++++++------------------ 1 file changed, 55 insertions(+), 37 deletions(-) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 99d6582f41de..e0b1915be1a6 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1045,64 +1045,76 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd, { struct pppol2tp_ioc_stats stats; struct l2tp_session *session; + int err = 0; + + session = pppol2tp_sock_to_session(sock->sk); + + /* Validate session presence and magic integrity ONLY for commands + * that belong to L2TP and require a valid session. + */ + switch (cmd) { + case PPPIOCGMRU: + case PPPIOCGFLAGS: + case PPPIOCSMRU: + case PPPIOCSFLAGS: + case PPPIOCGL2TPSTATS: + if (!session) + return -ENOTCONN; + + if (session->magic != L2TP_SESSION_MAGIC) { + l2tp_session_put(session); + return -EBADF; + } + break; + default: + break; + } switch (cmd) { case PPPIOCGMRU: case PPPIOCGFLAGS: - session = sock->sk->sk_user_data; - if (!session) - return -ENOTCONN; - - if (WARN_ON(session->magic != L2TP_SESSION_MAGIC)) - return -EBADF; - /* Not defined for tunnels */ - if (!session->session_id && !session->peer_session_id) - return -ENOSYS; + if (!session->session_id && !session->peer_session_id) { + err = -ENOSYS; + break; + } - if (put_user(0, (int __user *)arg)) - return -EFAULT; + if (put_user(0, (int __user *)arg)) { + err = -EFAULT; + break; + } break; case PPPIOCSMRU: case PPPIOCSFLAGS: - session = sock->sk->sk_user_data; - if (!session) - return -ENOTCONN; - - if (WARN_ON(session->magic != L2TP_SESSION_MAGIC)) - return -EBADF; - /* Not defined for tunnels */ - if (!session->session_id && !session->peer_session_id) - return -ENOSYS; + if (!session->session_id && !session->peer_session_id) { + err = -ENOSYS; + break; + } - if (!access_ok((int __user *)arg, sizeof(int))) - return -EFAULT; + if (!access_ok((int __user *)arg, sizeof(int))) { + err = -EFAULT; + break; + } break; case PPPIOCGL2TPSTATS: - session = sock->sk->sk_user_data; - if (!session) - return -ENOTCONN; - - if (WARN_ON(session->magic != L2TP_SESSION_MAGIC)) - return -EBADF; - /* Session 0 represents the parent tunnel */ if (!session->session_id && !session->peer_session_id) { u32 session_id; - int err; if (copy_from_user(&stats, (void __user *)arg, - sizeof(stats))) - return -EFAULT; + sizeof(stats))) { + err = -EFAULT; + break; + } session_id = stats.session_id; err = pppol2tp_tunnel_copy_stats(&stats, session->tunnel); if (err < 0) - return err; + break; stats.session_id = session_id; } else { @@ -1112,15 +1124,21 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd, stats.tunnel_id = session->tunnel->tunnel_id; stats.using_ipsec = l2tp_tunnel_uses_xfrm(session->tunnel); - if (copy_to_user((void __user *)arg, &stats, sizeof(stats))) - return -EFAULT; + if (copy_to_user((void __user *)arg, &stats, sizeof(stats))) { + err = -EFAULT; + break; + } break; default: - return -ENOIOCTLCMD; + err = -ENOIOCTLCMD; + break; } - return 0; + if (session) + l2tp_session_put(session); + + return err; } /***************************************************************************** From 3522b21fd7e1863d0734537737bd59f1b90d0190 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Thu, 28 May 2026 22:14:10 +0300 Subject: [PATCH 18/85] devlink: Release nested relation on devlink free devlink relation state is normally released from devl_unregister(), which calls devlink_rel_put(). This misses devlink instances that get a nested relation before registration and then fail probe before devl_register() is reached. That flow can happen for SFs. The child devlink gets linked to its parent before registration, then a later probe error calls devlink_free() directly. Since the instance was never registered, devl_unregister() is not called and devlink->rel is leaked. Release any pending relation from devlink_free() as well. The registered path is unchanged because devl_unregister() already clears devlink->rel before devlink_free() runs. Fixes: c137743bce02 ("devlink: introduce object and nested devlink relationship infra") Signed-off-by: Mark Bloch Reviewed-by: Jiri Pirko Link: https://patch.msgid.link/20260528191411.3270532-1-mbloch@nvidia.com Signed-off-by: Jakub Kicinski --- net/devlink/core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/devlink/core.c b/net/devlink/core.c index eeb6a71f5f56..fe9f6a0a67d5 100644 --- a/net/devlink/core.c +++ b/net/devlink/core.c @@ -518,6 +518,8 @@ void devlink_free(struct devlink *devlink) { ASSERT_DEVLINK_NOT_REGISTERED(devlink); + devlink_rel_put(devlink); + WARN_ON(!list_empty(&devlink->trap_policer_list)); WARN_ON(!list_empty(&devlink->trap_group_list)); WARN_ON(!list_empty(&devlink->trap_list)); From 4cd92957e8f8cc4ebfe8a5d4203c14c592fde6b1 Mon Sep 17 00:00:00 2001 From: Yuqi Xu Date: Fri, 29 May 2026 23:25:37 +0800 Subject: [PATCH 19/85] wifi: nl80211: reject oversized EMA RNR lists nl80211_parse_rnr_elems() stores the parsed element count in a u8-backed cfg80211_rnr_elems::cnt field and uses that count to size the flexible array allocation. Reject nested NL80211_ATTR_EMA_RNR_ELEMS input once the count reaches 255, before incrementing it again. This keeps the parser aligned with the data structure it fills and matches the existing bound check used by nl80211_parse_mbssid_elems(). Fixes: dbbb27e183b1 ("cfg80211: support RNR for EMA AP") Cc: stable@kernel.org Reported-by: Yuan Tan Reported-by: Zhengchuan Liang Reported-by: Xin Liu Assisted-by: Codex:gpt-5.4 Signed-off-by: Yuqi Xu Signed-off-by: Ren Wei Link: https://patch.msgid.link/20260529152542.1412734-1-n05ec@lzu.edu.cn Signed-off-by: Johannes Berg --- net/wireless/nl80211.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 7db9cd433801..dac2e8643c49 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -6366,6 +6366,9 @@ nl80211_parse_rnr_elems(struct wiphy *wiphy, struct nlattr *attrs, if (ret) return ERR_PTR(ret); + if (num_elems >= 255) + return ERR_PTR(-EINVAL); + num_elems++; } From 6c0cf89f36ac0c0fd8687a4ccdce2efb23a9c663 Mon Sep 17 00:00:00 2001 From: Deepanshu Kartikey Date: Sun, 31 May 2026 06:47:21 +0530 Subject: [PATCH 20/85] wifi: mac80211: limit injected antenna index in ieee80211_parse_tx_radiotap When parsing the radiotap header of an injected frame, ieee80211_parse_tx_radiotap() uses the IEEE80211_RADIOTAP_ANTENNA value directly as a shift count: info->control.antennas |= BIT(*iterator.this_arg); *iterator.this_arg is an 8-bit value taken straight from the frame supplied by userspace, so BIT() can be asked to shift by up to 255. That is undefined behaviour on the unsigned long and is reported by UBSAN: UBSAN: shift-out-of-bounds in net/mac80211/tx.c:2174:30 shift exponent 235 is too large for 64-bit type 'unsigned long' Call Trace: ieee80211_parse_tx_radiotap+0xadb/0x1950 net/mac80211/tx.c:2174 ieee80211_monitor_start_xmit+0xb1f/0x1250 net/mac80211/tx.c:2451 ... packet_sendmsg+0x3eb6/0x50f0 net/packet/af_packet.c:3109 info->control.antennas is a 2-bit bitmap (u8 antennas:2), so only antenna indices 0 and 1 can ever be represented. Ignore any larger value instead of shifting out of bounds. Reported-by: syzbot+8e0622f6d9446420271f@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=8e0622f6d9446420271f Fixes: ef246a1480cc ("wifi: mac80211: support antenna control in injection") Signed-off-by: Deepanshu Kartikey Link: https://patch.msgid.link/20260531011721.102941-1-kartikey406@gmail.com Signed-off-by: Johannes Berg --- net/mac80211/tx.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index b487d2330f25..ea7f63e1fc17 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2181,7 +2181,9 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, case IEEE80211_RADIOTAP_ANTENNA: /* this can appear multiple times, keep a bitmap */ - info->control.antennas |= BIT(*iterator.this_arg); + /* control.antennas is only a 2-bit bitmap */ + if (*iterator.this_arg < 2) + info->control.antennas |= BIT(*iterator.this_arg); break; case IEEE80211_RADIOTAP_DATA_RETRIES: From 73bf3cca7de6a73f53b6a52dc3b1c82ae5667a4d Mon Sep 17 00:00:00 2001 From: Oscar Maes Date: Thu, 28 May 2026 16:03:20 +0200 Subject: [PATCH 21/85] pcnet32: stop holding device spin lock during napi_complete_done napi_complete_done may call gro_flush_normal (though not currently, as GRO is unsupported at the moment), which may result in packet TX. This will eventually result in calling pcnet32_start_xmit - resulting in a deadlock while trying to re-acquire the already locked spin lock. It is safe to split the spinlock block into two, because the hardware registers are still protected from concurrent access, and the two blocks perform unrelated operations that don't need to happen atomically. Fixes: 5b2ec6f2be51 ("pcnet32: use napi_complete_done()") Reviewed-by: Andrew Lunn Signed-off-by: Oscar Maes Reviewed-by: Alexander Lobakin Link: https://patch.msgid.link/20260528140320.5556-1-oscmaes92@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amd/pcnet32.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index 911808ab13a7..4f3076d4ea34 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -1407,8 +1407,10 @@ static int pcnet32_poll(struct napi_struct *napi, int budget) pcnet32_restart(dev, CSR0_START); netif_wake_queue(dev); } + spin_unlock_irqrestore(&lp->lock, flags); if (work_done < budget && napi_complete_done(napi, work_done)) { + spin_lock_irqsave(&lp->lock, flags); /* clear interrupt masks */ val = lp->a->read_csr(ioaddr, CSR3); val &= 0x00ff; @@ -1416,9 +1418,9 @@ static int pcnet32_poll(struct napi_struct *napi, int budget) /* Set interrupt enable. */ lp->a->write_csr(ioaddr, CSR0, CSR0_INTEN); + spin_unlock_irqrestore(&lp->lock, flags); } - spin_unlock_irqrestore(&lp->lock, flags); return work_done; } From b748765019fe9e9234660327090fc1a9665cdbdd Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 29 May 2026 19:39:23 +0000 Subject: [PATCH 22/85] net: Annotate sk->sk_write_space() for UDP SOCKMAP. UDP TX skb->destructor() is sock_wfree(), and UDP holds lock_sock() only for UDP_CORK / MSG_MORE sendmsg(). Otherwise, sk->sk_write_space() may be read locklessly while SOCKMAP rewrites sk->sk_write_space(). Let's use WRITE_ONCE() and READ_ONCE() for sk->sk_write_space(). Note that the write side is annotated by commit 2ef2b20cf4e0 ("net: annotate data-races around sk->sk_{data_ready,write_space}"). Fixes: 7b98cd42b049 ("bpf: sockmap: Add UDP support") Signed-off-by: Kuniyuki Iwashima Reviewed-by: Jakub Sitnicki Link: https://patch.msgid.link/20260529193941.3897256-1-kuniyu@google.com Signed-off-by: Jakub Kicinski --- net/core/sock.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index b37b664b6eb9..d097025c116a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2676,8 +2676,12 @@ void sock_wfree(struct sk_buff *skb) int old; if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) { + void (*sk_write_space)(struct sock *sk); + + sk_write_space = READ_ONCE(sk->sk_write_space); + if (sock_flag(sk, SOCK_RCU_FREE) && - sk->sk_write_space == sock_def_write_space) { + sk_write_space == sock_def_write_space) { rcu_read_lock(); free = __refcount_sub_and_test(len, &sk->sk_wmem_alloc, &old); @@ -2693,7 +2697,7 @@ void sock_wfree(struct sk_buff *skb) * after sk_write_space() call */ WARN_ON(refcount_sub_and_test(len - 1, &sk->sk_wmem_alloc)); - sk->sk_write_space(sk); + sk_write_space(sk); len = 1; } /* From e10902df24488ca722303133acfc82490f7d59ad Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 1 Jun 2026 18:20:55 +0000 Subject: [PATCH 23/85] tcp: Add preempt_{disable,enable}_nested() in reqsk_queue_hash_req(). syzbot reported a weird reqsk->rsk_refcnt underflow in __inet_csk_reqsk_queue_drop(). The captured reqsk_put() in __inet_csk_reqsk_queue_drop() is called only when it successfully removes reqsk from ehash. Moreover, reqsk_timer_handler() calls another reqsk_put() after that. This indicates that the reqsk was missing both refcnts for ehash and the timer itself. Since all the syzbot reports had PREEMPT_RT enabled, the only possible scenario is that reqsk_queue_hash_req() is preempted after mod_timer() and before refcount_set(), and then the timer triggered after 1s aborts the reqsk due to its listener's close(). Let's wrap mod_timer() and refcount_set() with preempt_disable_nested() and preempt_enable_nested(). Note that inet_ehash_insert() holds the normal spin_lock() (mutex in PREEMPT_RT), so it must be called outside of preempt_disable_nested(), but this is fine. The lookup path just ignores 0 sk_refcnt entries in ehash and tries to create another reqsk, but this will fail at inet_ehash_insert(). [0]: refcount_t: underflow; use-after-free. WARNING: lib/refcount.c:28 at refcount_warn_saturate+0xb2/0x110 lib/refcount.c:28, CPU#0: ktimers/0/16 Modules linked in: CPU: 0 UID: 0 PID: 16 Comm: ktimers/0 Tainted: G L syzkaller #0 PREEMPT_{RT,(full)} Tainted: [L]=SOFTLOCKUP Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/18/2026 RIP: 0010:refcount_warn_saturate+0xb2/0x110 lib/refcount.c:28 Code: e4 7d d1 0a 67 48 0f b9 3a eb 4a e8 38 3d 23 fd 48 8d 3d e1 7d d1 0a 67 48 0f b9 3a eb 37 e8 25 3d 23 fd 48 8d 3d de 7d d1 0a <67> 48 0f b9 3a eb 24 e8 12 3d 23 fd 48 8d 3d db 7d d1 0a 67 48 0f RSP: 0000:ffffc90000157948 EFLAGS: 00010246 RAX: ffffffff84a1301b RBX: 0000000000000003 RCX: ffff88801ca98000 RDX: 0000000000000100 RSI: 0000000000000000 RDI: ffffffff8f72ae00 RBP: ffffffff99ae3b01 R08: ffff88801ca98000 R09: 0000000000000005 R10: 0000000000000100 R11: 0000000000000004 R12: ffff8880425ef568 R13: ffff8880425ef4f8 R14: ffff8880425ef578 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff888126386000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f7b46710e9c CR3: 000000000dbb6000 CR4: 00000000003526f0 Call Trace: __refcount_sub_and_test include/linux/refcount.h:400 [inline] __refcount_dec_and_test include/linux/refcount.h:432 [inline] refcount_dec_and_test include/linux/refcount.h:450 [inline] reqsk_put include/net/request_sock.h:136 [inline] __inet_csk_reqsk_queue_drop+0x3ce/0x440 net/ipv4/inet_connection_sock.c:1007 reqsk_timer_handler+0x651/0xdf0 net/ipv4/inet_connection_sock.c:1137 call_timer_fn+0x192/0x5e0 kernel/time/timer.c:1748 expire_timers kernel/time/timer.c:1799 [inline] __run_timers kernel/time/timer.c:2374 [inline] __run_timer_base+0x6a3/0x9f0 kernel/time/timer.c:2386 run_timer_base kernel/time/timer.c:2395 [inline] run_timer_softirq+0x67/0x170 kernel/time/timer.c:2403 handle_softirqs+0x1de/0x6d0 kernel/softirq.c:622 __do_softirq kernel/softirq.c:656 [inline] run_ktimerd+0x69/0x100 kernel/softirq.c:1151 smpboot_thread_fn+0x541/0xa50 kernel/smpboot.c:160 kthread+0x388/0x470 kernel/kthread.c:436 ret_from_fork+0x514/0xb70 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245 Fixes: d2d6422f8bd1 ("x86: Allow to enable PREEMPT_RT.") Reported-by: syzbot+e809069bc15f26300526@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/6a1a7bcf.0a9e871e.332604.000b.GAE@google.com/ Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Reviewed-by: Sebastian Andrzej Siewior Link: https://patch.msgid.link/20260601182101.3183993-1-kuniyu@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/inet_connection_sock.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index dbcd37dfdc15..5b934ce8d98a 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1148,6 +1148,9 @@ static bool reqsk_queue_hash_req(struct request_sock *req) /* The timer needs to be setup after a successful insertion. */ req->timeout = tcp_timeout_init((struct sock *)req); timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED); + + preempt_disable_nested(); + mod_timer(&req->rsk_timer, jiffies + req->timeout); /* before letting lookups find us, make sure all req fields @@ -1155,6 +1158,9 @@ static bool reqsk_queue_hash_req(struct request_sock *req) */ smp_wmb(); refcount_set(&req->rsk_refcnt, 2 + 1); + + preempt_enable_nested(); + return true; } From afd0f17ca46258cec3a5cc48b8df9327fe772490 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Sat, 30 May 2026 06:42:58 +0000 Subject: [PATCH 24/85] hsr: Remove WARN_ONCE() in hsr_addr_is_self(). syzbot reported the warning [0] in hsr_addr_is_self(), whose assumption is simply wrong. hsr->self_node is cleared in hsr_del_self_node(), which is called from hsr_dellink(). Since dev->rtnl_link_ops->dellink() is called before unregister_netdevice_many(), there is a window when user can find the device but without hsr->self_node. Let's remove WARN_ONCE() in hsr_addr_is_self(). [0]: HSR: No self node WARNING: net/hsr/hsr_framereg.c:39 at hsr_addr_is_self+0x211/0x3f0 net/hsr/hsr_framereg.c:39, CPU#0: syz.4.16848/17220 Modules linked in: CPU: 0 UID: 0 PID: 17220 Comm: syz.4.16848 Tainted: G L syzkaller #0 PREEMPT_{RT,(full)} Tainted: [L]=SOFTLOCKUP Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/18/2026 RIP: 0010:hsr_addr_is_self+0x211/0x3f0 net/hsr/hsr_framereg.c:39 Code: 33 2f 41 0f b7 dd 89 ee 09 de 31 ff e8 c8 b4 c6 f6 09 dd 74 54 e8 0f b0 c6 f6 31 ed eb 53 e8 06 b0 c6 f6 48 8d 3d 2f 50 9c 04 <67> 48 0f b9 3a 31 ed eb 42 e8 c1 13 1f 00 89 c5 31 ff 89 c6 e8 96 RSP: 0018:ffffc900041c70e0 EFLAGS: 00010283 RAX: ffffffff8afdc6ca RBX: ffffffff8afdc4e6 RCX: 0000000000080000 RDX: ffffc90010493000 RSI: 0000000000000948 RDI: ffffffff8f9a1700 RBP: 0000000000000001 R08: 0000000000000000 R09: 0000000000000000 R10: ffffc900041c71e8 R11: fffff52000838e3f R12: dffffc0000000000 R13: ffff888041f9e3c0 R14: ffff888086ee3802 R15: 0000000000000000 FS: 00007f6fe985d6c0(0000) GS:ffff888126176000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f80bd437dac CR3: 0000000025096000 CR4: 00000000003526f0 DR0: ffffffffffffffff DR1: 00000000000001f8 DR2: 0000000000000002 DR3: ffffffffefffff15 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Call Trace: check_local_dest net/hsr/hsr_forward.c:592 [inline] fill_frame_info net/hsr/hsr_forward.c:728 [inline] hsr_forward_skb+0xa11/0x2a80 net/hsr/hsr_forward.c:739 hsr_dev_xmit+0x253/0x370 net/hsr/hsr_device.c:236 __netdev_start_xmit include/linux/netdevice.h:5368 [inline] netdev_start_xmit include/linux/netdevice.h:5377 [inline] xmit_one net/core/dev.c:3888 [inline] dev_hard_start_xmit+0x2df/0x860 net/core/dev.c:3904 __dev_queue_xmit+0x1428/0x3900 net/core/dev.c:4870 neigh_output include/net/neighbour.h:556 [inline] ip_finish_output2+0xcec/0x10b0 net/ipv4/ip_output.c:237 ip_send_skb net/ipv4/ip_output.c:1510 [inline] ip_push_pending_frames+0x8b/0x110 net/ipv4/ip_output.c:1530 raw_sendmsg+0x1547/0x1a50 net/ipv4/raw.c:659 sock_sendmsg_nosec net/socket.c:787 [inline] __sock_sendmsg net/socket.c:802 [inline] ____sys_sendmsg+0x7da/0x9c0 net/socket.c:2698 ___sys_sendmsg+0x2a5/0x360 net/socket.c:2752 __sys_sendmsg net/socket.c:2784 [inline] __do_sys_sendmsg net/socket.c:2789 [inline] __se_sys_sendmsg net/socket.c:2787 [inline] __x64_sys_sendmsg+0x1c3/0x2a0 net/socket.c:2787 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x15f/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f6feb62ce59 Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f6fe985d028 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f6feb8a6090 RCX: 00007f6feb62ce59 RDX: 0000000000000000 RSI: 0000200000000000 RDI: 0000000000000004 RBP: 00007f6feb6c2d6f R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007f6feb8a6128 R14: 00007f6feb8a6090 R15: 00007ffcf01cc488 Fixes: f266a683a480 ("net/hsr: Better frame dispatch") Reported-by: syzbot+652670cf249077eb498b@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/6a1a861e.b111c304.35cd64.0016.GAE@google.com/ Signed-off-by: Kuniyuki Iwashima Reviewed-by: Fernando Fernandez Mancera Link: https://patch.msgid.link/20260530064300.340793-1-kuniyu@google.com Signed-off-by: Jakub Kicinski --- net/hsr/hsr_framereg.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index b514e43766ef..a28dfd8490c5 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -35,10 +35,8 @@ bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr) rcu_read_lock(); sn = rcu_dereference(hsr->self_node); - if (!sn) { - WARN_ONCE(1, "HSR: No self node\n"); + if (!sn) goto out; - } if (ether_addr_equal(addr, sn->macaddress_A) || ether_addr_equal(addr, sn->macaddress_B)) From 16e408e607a94b646fb14a2a98422c6877ae4b3c Mon Sep 17 00:00:00 2001 From: Yizhou Zhao Date: Wed, 27 May 2026 16:31:58 +0800 Subject: [PATCH 25/85] net: garp: fix unsigned integer underflow in garp_pdu_parse_attr The receive-side GARP attribute parser computes dlen with reversed operands: dlen = sizeof(*ga) - ga->len; ga->len is the on-wire attribute length and includes the GARP attribute header. For normal attributes with data, ga->len is larger than sizeof(*ga), so the subtraction underflows in unsigned arithmetic. The resulting value is later passed to garp_attr_lookup(), whose length argument is u8. After truncation, the parsed data length usually no longer matches the length stored for locally registered attributes, so received Join/Leave events are ignored. This breaks the GARP receive path for common attributes, such as GVRP VLAN registration attributes. Compute the data length as the attribute length minus the header length. Fixes: eca9ebac651f ("net: Add GARP applicant-only participant") Reported-by: Yizhou Zhao Reported-by: Yuxiang Yang Reported-by: Ao Wang Reported-by: Xuewei Feng Reported-by: Qi Li Reported-by: Ke Xu Signed-off-by: Yizhou Zhao Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260527083200.42861-1-zhaoyz24@mails.tsinghua.edu.cn Signed-off-by: Jakub Kicinski --- net/802/garp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/802/garp.c b/net/802/garp.c index 6f563b6797d9..c7a39f298ad6 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -453,7 +453,7 @@ static int garp_pdu_parse_attr(struct garp_applicant *app, struct sk_buff *skb, if (!pskb_may_pull(skb, ga->len)) return -1; skb_pull(skb, ga->len); - dlen = sizeof(*ga) - ga->len; + dlen = ga->len - sizeof(*ga); if (attrtype > app->app->maxattr) return 0; From 20cf0fb715c41111469577e85e35d15f099473e0 Mon Sep 17 00:00:00 2001 From: Yuqi Xu Date: Fri, 29 May 2026 21:01:44 +0800 Subject: [PATCH 26/85] net: rds: clear i_sends on setup unwind The RDS IB connection teardown path is written so it can run during partial startup and on repeated shutdown attempts. It uses NULL pointers to distinguish resources that are still owned from resources that have already been released. When rds_ib_setup_qp() fails after allocating i_sends but before allocating i_recvs, the sends_out path frees i_sends without clearing the pointer. A later shutdown pass can still treat that stale pointer as a live send ring allocation. Clear i_sends after vfree() in the error unwind path so the existing shutdown logic continues to use the correct ownership state. Fixes: 3b12f73a5c29 ("rds: ib: add error handle") Cc: stable@kernel.org Reported-by: Yuan Tan Reported-by: Zhengchuan Liang Reported-by: Xin Liu Signed-off-by: Yuqi Xu Signed-off-by: Ren Wei Reviewed-by: Allison Henderson Link: https://patch.msgid.link/5a0f7624bb9845a7b67d26166a150b59e7f394ce.1779632468.git.xuyq21@lenovo.com Signed-off-by: Jakub Kicinski --- net/rds/ib_cm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index 0c64c504f79d..4001de0c4959 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -656,6 +656,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) sends_out: vfree(ic->i_sends); + ic->i_sends = NULL; ack_dma_out: rds_dma_hdr_free(rds_ibdev->dev, ic->i_ack, ic->i_ack_dma, From 8173d22b211f615015f7b35f48ab11a6dd78dc99 Mon Sep 17 00:00:00 2001 From: David Thompson Date: Fri, 29 May 2026 21:03:00 +0000 Subject: [PATCH 27/85] net: lan743x: permit VLAN-tagged packets up to configured MTU VLAN-tagged interfaces on lan743x devices were previously unreachable via SSH and failed to respond to large ping packets (e.g. "ping -s 1469" given MTU=1500). In these scenarios, "ethtool -S" reports non-zero "RX Oversize Frame Errors". According to Microchip AN2948, the MAC_RX FSE (VLAN field size enforcement) bit determines whether frames with VLAN tags exceeding the base MTU plus tag length are discarded. The driver must set the MAC_RX.FSE bit before setting MAC_RX.RXEN to allow VLAN-tagged frames up to the interface MTU, preventing them from being treated as oversized. As a result, both the base and VLAN-tagged interfaces can use the same MTU without receive errors. Fixes: 23f0703c125b ("lan743x: Add main source files for new lan743x driver") Signed-off-by: David Thompson Reviewed-by: Thangaraj Samynathan Reviewed-by: Nicolai Buchwitz Tested-by: Nicolai Buchwitz # lan7430 on arm64 (RevPi Link: https://patch.msgid.link/20260529210300.433135-1-davthompson@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/microchip/lan743x_main.c | 32 +++++++++++++++++++ drivers/net/ethernet/microchip/lan743x_main.h | 1 + 2 files changed, 33 insertions(+) diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index f3332417162e..ffac22883e49 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -1219,6 +1219,36 @@ static void lan743x_mac_set_address(struct lan743x_adapter *adapter, "MAC address set to %pM\n", addr); } +static void lan743x_mac_rx_enable_fse(struct lan743x_adapter *adapter) +{ + u32 mac_rx; + bool rxen; + + mac_rx = lan743x_csr_read(adapter, MAC_RX); + if (mac_rx & MAC_RX_FSE_) + return; + + rxen = mac_rx & MAC_RX_RXEN_; + if (rxen) { + mac_rx &= ~MAC_RX_RXEN_; + lan743x_csr_write(adapter, MAC_RX, mac_rx); + lan743x_csr_wait_for_bit(adapter, MAC_RX, MAC_RX_RXD_, + 1, 1000, 20000, 100); + } + + /* Per AN2948, hardware prevents modification of the FSE bit while the + * MAC receiver is enabled (RXEN bit set). Use separate register write + * to assert the FSE bit before enabling the RXEN bit in MAC_RX + */ + mac_rx |= MAC_RX_FSE_; + lan743x_csr_write(adapter, MAC_RX, mac_rx); + + if (rxen) { + mac_rx |= MAC_RX_RXEN_; + lan743x_csr_write(adapter, MAC_RX, mac_rx); + } +} + static int lan743x_mac_init(struct lan743x_adapter *adapter) { bool mac_address_valid = true; @@ -1258,6 +1288,8 @@ static int lan743x_mac_init(struct lan743x_adapter *adapter) lan743x_mac_set_address(adapter, adapter->mac_address); eth_hw_addr_set(netdev, adapter->mac_address); + lan743x_mac_rx_enable_fse(adapter); + return 0; } diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index 160d94a7cee6..1573c8f9c993 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -182,6 +182,7 @@ #define MAC_RX (0x104) #define MAC_RX_MAX_SIZE_SHIFT_ (16) #define MAC_RX_MAX_SIZE_MASK_ (0x3FFF0000) +#define MAC_RX_FSE_ BIT(2) #define MAC_RX_RXD_ BIT(1) #define MAC_RX_RXEN_ BIT(0) From b455410146bf723c7ebcb49ecd5becc0d6611482 Mon Sep 17 00:00:00 2001 From: Tapio Reijonen Date: Fri, 29 May 2026 06:18:57 +0000 Subject: [PATCH 28/85] net: fec: fix pinctrl default state restore order on resume In fec_resume(), fec_enet_clk_enable() is called before pinctrl_pm_select_default_state() in the non-WoL path, inverting the ordering used in fec_suspend() which correctly switches to the sleep pinctrl state before disabling clocks. For PHYs with the PHY_RST_AFTER_CLK_EN flag (e.g. TI DP83848 or SMSC LAN87xx), fec_enet_clk_enable() triggers a hardware reset pulse via the phy-reset GPIO. With the GPIO pin still in sleep pinctrl state at that point, the GPIO write has no physical effect and the PHY never receives the required reset after clock enable, leading to unreliable link establishment after system resume. Fix by restoring the default pinctrl state before enabling clocks, making resume the proper mirror of suspend. The call is made unconditionally: fec_suspend() only switches to the sleep pinctrl state on the non-WoL path and leaves the pins in the default state when WoL is enabled, so on a WoL resume the device is already in the default state and pinctrl_pm_select_default_state() is a no-op. Fixes: de40ed31b3c5 ("net: fec: add Wake-on-LAN support") Signed-off-by: Tapio Reijonen Reviewed-by: Wei Fang Link: https://patch.msgid.link/20260529-b4-fec-resume-pinctrl-order-v3-1-6eda0f592fca@vaisala.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/fec_main.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index f89aa94ce020..6ebde65d7f1b 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -5594,6 +5594,7 @@ static int fec_resume(struct device *dev) if (fep->rpm_active) pm_runtime_force_resume(dev); + pinctrl_pm_select_default_state(&fep->pdev->dev); ret = fec_enet_clk_enable(ndev, true); if (ret) { rtnl_unlock(); @@ -5610,8 +5611,6 @@ static int fec_resume(struct device *dev) val &= ~(FEC_ECR_MAGICEN | FEC_ECR_SLEEP); writel(val, fep->hwp + FEC_ECNTRL); fep->wol_flag &= ~FEC_WOL_FLAG_SLEEP_ON; - } else { - pinctrl_pm_select_default_state(&fep->pdev->dev); } fec_restart(ndev); netif_tx_lock_bh(ndev); From 5eba3e48d78edd7551b992cb7ba687019b3a78da Mon Sep 17 00:00:00 2001 From: Zhao Zhang Date: Sat, 30 May 2026 23:57:14 +0800 Subject: [PATCH 29/85] sctp: diag: reject stale associations in dump_one path The SCTP exact sock_diag lookup can hold a transport reference, block on lock_sock(sk), and then resume after sctp_association_free() has marked the association dead and freed its bind address list. When that happens, inet_assoc_attr_size() and inet_diag_msg_sctpasoc_fill() can still dereference association state that is no longer valid for reporting. In particular, inet_diag_msg_sctpasoc_fill() may read an empty bind-address list as a real sctp_sockaddr_entry and trigger an out-of-bounds read from unrelated association memory. Reject the association after taking the socket lock if it has been reaped or detached from the endpoint, and report the lookup as stale. This keeps the exact dump-one path from formatting torn association state. Fixes: 8f840e47f190 ("sctp: add the sctp_diag.c file") Cc: stable@kernel.org Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Zhengchuan Liang Reported-by: Xin Liu Signed-off-by: Zhao Zhang Signed-off-by: Ren Wei Acked-by: Xin Long Link: https://patch.msgid.link/fac6043fa20a2ff68e12958c431836f692c51268.1780113823.git.zzhan461@ucr.edu Signed-off-by: Jakub Kicinski --- net/sctp/diag.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 2afb376299fe..d758f5c3e06e 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -266,15 +266,15 @@ static int sctp_sock_dump_one(struct sctp_endpoint *ep, struct sctp_transport *t lock_sock(sk); - rep = nlmsg_new(inet_assoc_attr_size(sk, assoc), GFP_KERNEL); - if (!rep) { - release_sock(sk); - return -ENOMEM; + if (ep != assoc->ep || assoc->base.dead) { + err = -ESTALE; + goto out_unlock; } - if (ep != assoc->ep) { - err = -EAGAIN; - goto out; + rep = nlmsg_new(inet_assoc_attr_size(sk, assoc), GFP_KERNEL); + if (!rep) { + err = -ENOMEM; + goto out_unlock; } err = inet_sctp_diag_fill(sk, assoc, rep, req, sk_user_ns(NETLINK_CB(skb).sk), @@ -289,8 +289,9 @@ static int sctp_sock_dump_one(struct sctp_endpoint *ep, struct sctp_transport *t return nlmsg_unicast(sock_net(skb->sk)->diag_nlsk, rep, NETLINK_CB(skb).portid); out: - release_sock(sk); kfree_skb(rep); +out_unlock: + release_sock(sk); return err; } From f723ccaff2fb72b71ae8a9fd283f0dee4d9ae7a3 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Fri, 29 May 2026 23:22:18 +0800 Subject: [PATCH 30/85] ipv6: anycast: insert aca into global hash under idev->lock syzbot reported a splat [1]: a slab-use-after-free in ipv6_chk_acast_addr(), which walks the global inet6_acaddr_lst[] hash under RCU and dereferences a struct ifacaddr6 that has already been freed while still linked in the hash, so a later reader walks into a dangling node. In __ipv6_dev_ac_inc() the aca is allocated with refcount 1, then aca_get() bumps it to 2 to keep it alive across the unlocked region. It is published to idev->ac_list under idev->lock, but ipv6_add_acaddr_hash() runs after write_unlock_bh(). A concurrent teardown (ipv6_ac_destroy_dev() from addrconf_ifdown(), under RTNL) can slip into that window: CPU0 __ipv6_dev_ac_inc CPU1 ipv6_ac_destroy_dev (RTNL) ------------------------------ ------------------------------------ aca_alloc() refcnt 1 aca_get() refcnt 2 write_lock_bh(idev->lock) add aca to ac_list write_unlock_bh(idev->lock) write_lock_bh(idev->lock) pull aca off ac_list write_unlock_bh(idev->lock) ipv6_del_acaddr_hash(aca) hlist_del_init_rcu() is a no-op, aca is not in the hash yet aca_put() refcnt 2->1 ipv6_add_acaddr_hash(aca) aca now inserted into the hash aca_put() refcnt 1->0 call_rcu(aca_free_rcu) -> kfree(aca) The hash removal becomes a no-op because the insertion has not happened yet, so once CPU0 inserts and drops the last reference, the aca is freed while still linked in inet6_acaddr_lst[], and readers dereference freed memory after the slab slot is reused. This window opened once RTNL stopped serializing the join path against device teardown. Move ipv6_add_acaddr_hash() inside the idev->lock section so the ac_list and hash insertions are atomic with respect to teardown: a racing remover now either misses the aca entirely or finds it in both lists. acaddr_hash_lock is now nested under idev->lock, which is acquired in softirq context, so switch all acaddr_hash_lock sites to spin_lock_bh() to avoid the irq lock inversion reported in [2]. [1] https://syzkaller.appspot.com/bug?extid=a01df04303c131efbf3a [2] https://lore.kernel.org/netdev/6a194ef7.ba3b1513.1890b4.0000.GAE@google.com/ Reported-by: syzbot+819eb928d120d2bdad0e@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/6a191f87.ce022c6e.138e56.0003.GAE@google.com/T/ Reviewed-by: Kuniyuki Iwashima Fixes: eb1ac9ff6c4a ("ipv6: anycast: Don't hold RTNL for IPV6_JOIN_ANYCAST.") Signed-off-by: Jiayuan Chen Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260529152219.235475-1-jiayuan.chen@linux.dev Signed-off-by: Jakub Kicinski --- net/ipv6/anycast.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 67a42e01dfc3..be6dac8a8566 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -243,16 +243,16 @@ static void ipv6_add_acaddr_hash(struct net *net, struct ifacaddr6 *aca) { unsigned int hash = inet6_acaddr_hash(net, &aca->aca_addr); - spin_lock(&acaddr_hash_lock); + spin_lock_bh(&acaddr_hash_lock); hlist_add_head_rcu(&aca->aca_addr_lst, &inet6_acaddr_lst[hash]); - spin_unlock(&acaddr_hash_lock); + spin_unlock_bh(&acaddr_hash_lock); } static void ipv6_del_acaddr_hash(struct ifacaddr6 *aca) { - spin_lock(&acaddr_hash_lock); + spin_lock_bh(&acaddr_hash_lock); hlist_del_init_rcu(&aca->aca_addr_lst); - spin_unlock(&acaddr_hash_lock); + spin_unlock_bh(&acaddr_hash_lock); } static void aca_get(struct ifacaddr6 *aca) @@ -371,10 +371,10 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) aca->aca_next = idev->ac_list; rcu_assign_pointer(idev->ac_list, aca); - write_unlock_bh(&idev->lock); - ipv6_add_acaddr_hash(net, aca); + write_unlock_bh(&idev->lock); + ip6_ins_rt(net, f6i); addrconf_join_solict(idev->dev, &aca->aca_addr); @@ -649,8 +649,8 @@ void ipv6_anycast_cleanup(void) { int i; - spin_lock(&acaddr_hash_lock); + spin_lock_bh(&acaddr_hash_lock); for (i = 0; i < IN6_ADDR_HSIZE; i++) WARN_ON(!hlist_empty(&inet6_acaddr_lst[i])); - spin_unlock(&acaddr_hash_lock); + spin_unlock_bh(&acaddr_hash_lock); } From e8694f7cc29287e843648d1075177b9a2000d957 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Mon, 1 Jun 2026 12:41:56 +0300 Subject: [PATCH 31/85] wifi: fix leak if split 6 GHz scanning fails rdev->int_scan_req is leaked if cfg80211_scan() fails. Note that it's supposed to be released at ___cfg80211_scan_done() but this doesn't happen as rdev->scan_req is NULL at that point, too, leading to the early return from the freeing function. unreferenced object 0xffff8881161d0800 (size 512): comm "wpa_supplicant", pid 379, jiffies 4294749765 hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 f0 81 13 16 81 88 ff ff ................ backtrace (crc c867fdb6): kmemleak_alloc+0x89/0x90 __kmalloc_noprof+0x2fd/0x410 cfg80211_scan+0x133/0x730 nl80211_trigger_scan+0xc69/0x1cc0 genl_family_rcv_msg_doit+0x204/0x2f0 genl_rcv_msg+0x431/0x6b0 netlink_rcv_skb+0x143/0x3f0 genl_rcv+0x27/0x40 netlink_unicast+0x4f6/0x820 netlink_sendmsg+0x797/0xce0 __sock_sendmsg+0xc4/0x160 ____sys_sendmsg+0x5e4/0x890 ___sys_sendmsg+0xf8/0x180 __sys_sendmsg+0x136/0x1e0 __x64_sys_sendmsg+0x76/0xc0 x64_sys_call+0x13f0/0x17d0 Found by Linux Verification Center (linuxtesting.org). Fixes: c8cb5b854b40 ("nl80211/cfg80211: support 6 GHz scanning") Signed-off-by: Fedor Pchelkin Link: https://patch.msgid.link/20260601094157.92703-1-pchelkin@ispras.ru Signed-off-by: Johannes Berg --- net/wireless/scan.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 358cbc9e43d8..27a56ee2e8f0 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1071,6 +1071,7 @@ int cfg80211_scan(struct cfg80211_registered_device *rdev) struct cfg80211_scan_request_int *request; struct cfg80211_scan_request_int *rdev_req = rdev->scan_req; u32 n_channels = 0, idx, i; + int err; if (!(rdev->wiphy.flags & WIPHY_FLAG_SPLIT_SCAN_6GHZ)) { rdev_req->req.first_part = true; @@ -1100,8 +1101,14 @@ int cfg80211_scan(struct cfg80211_registered_device *rdev) rdev_req->req.scan_6ghz = false; rdev_req->req.first_part = true; + err = rdev_scan(rdev, request); + if (err) { + kfree(request); + return err; + } + rdev->int_scan_req = request; - return rdev_scan(rdev, request); + return 0; } void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, From cb9959ab5f99611d27a06586add84811fe8102dc Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 3 Jun 2026 11:18:11 +0200 Subject: [PATCH 32/85] wifi: cfg80211: enforce HE/EHT cap/oper consistency Xiang Mei reports that mac80211 could crash if eht_cap is set but eht_oper isn't. Rather than fixing that for the individual user(s), enforce that both HE/EHT have consistent elements. Reported-by: Xiang Mei Fixes: 22c64f37e1d4 ("wifi: mac80211: Update MCS15 support in link_conf") Link: https://patch.msgid.link/20260603091812.101894-2-johannes@sipsolutions.net Signed-off-by: Johannes Berg --- net/wireless/nl80211.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index dac2e8643c49..76c537a6e8b5 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -6714,6 +6714,12 @@ static int nl80211_calculate_ap_params(struct cfg80211_ap_settings *params) return -EINVAL; } + if (!!params->he_cap != !!params->he_oper) + return -EINVAL; + + if (!!params->eht_cap != !!params->eht_oper) + return -EINVAL; + return 0; } From 43c441edacf953b39517a44f5e5e10a93618b226 Mon Sep 17 00:00:00 2001 From: Zhang Cen Date: Thu, 28 May 2026 15:56:41 +0800 Subject: [PATCH 33/85] Bluetooth: RFCOMM: hold listener socket in rfcomm_connect_ind() rfcomm_get_sock_by_channel() scans rfcomm_sk_list under the list lock, but returns the selected listener after dropping that lock without taking a reference. rfcomm_connect_ind() then locks the listener, queues a child socket on it, and may notify it after unlocking it. The buggy scenario involves two paths, with each column showing the order within that path: rfcomm_connect_ind(): listener close: 1. Find parent in 1. close() enters rfcomm_get_sock_by_channel() rfcomm_sock_release(). 2. Drop rfcomm_sk_list.lock 2. rfcomm_sock_shutdown() without pinning parent. closes the listener. 3. Call lock_sock(parent) and 3. rfcomm_sock_kill() bt_accept_enqueue(parent, unlinks and puts parent. sk, true). 4. Read parent flags and may 4. parent can be freed. call sk_state_change(). If close wins the race, parent can be freed before rfcomm_connect_ind() reaches lock_sock(), bt_accept_enqueue(), or the deferred-setup callback. Take a reference on the listener before leaving rfcomm_sk_list.lock. After lock_sock() succeeds, recheck that it is still in BT_LISTEN before queueing a child, cache the deferred-setup bit while the parent is locked, and drop the reference after the last parent use. KASAN reported a slab-use-after-free in lock_sock_nested() from rfcomm_connect_ind(), with the freeing stack going through rfcomm_sock_kill() and rfcomm_sock_release(). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Zhang Cen Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/rfcomm/sock.c | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-) diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index bd7d959c6e9e..805ed5d28ed6 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -122,7 +122,7 @@ static struct sock *__rfcomm_get_listen_sock_by_addr(u8 channel, bdaddr_t *src) } /* Find socket with channel and source bdaddr. - * Returns closest match. + * Returns closest match with an extra reference held. */ static struct sock *rfcomm_get_sock_by_channel(int state, u8 channel, bdaddr_t *src) { @@ -136,15 +136,25 @@ static struct sock *rfcomm_get_sock_by_channel(int state, u8 channel, bdaddr_t * if (rfcomm_pi(sk)->channel == channel) { /* Exact match. */ - if (!bacmp(&rfcomm_pi(sk)->src, src)) + if (!bacmp(&rfcomm_pi(sk)->src, src)) { + sock_hold(sk); break; + } /* Closest match */ - if (!bacmp(&rfcomm_pi(sk)->src, BDADDR_ANY)) + if (!bacmp(&rfcomm_pi(sk)->src, BDADDR_ANY)) { + if (sk1) + sock_put(sk1); + sk1 = sk; + sock_hold(sk1); + } } } + if (sk && sk1) + sock_put(sk1); + read_unlock(&rfcomm_sk_list.lock); return sk ? sk : sk1; @@ -941,6 +951,7 @@ int rfcomm_connect_ind(struct rfcomm_session *s, u8 channel, struct rfcomm_dlc * { struct sock *sk, *parent; bdaddr_t src, dst; + bool defer_setup = false; int result = 0; BT_DBG("session %p channel %d", s, channel); @@ -954,6 +965,11 @@ int rfcomm_connect_ind(struct rfcomm_session *s, u8 channel, struct rfcomm_dlc * lock_sock(parent); + if (parent->sk_state != BT_LISTEN) + goto done; + + defer_setup = test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags); + /* Check for backlog size */ if (sk_acceptq_is_full(parent)) { BT_DBG("backlog full %d", parent->sk_ack_backlog); @@ -981,9 +997,11 @@ int rfcomm_connect_ind(struct rfcomm_session *s, u8 channel, struct rfcomm_dlc * done: release_sock(parent); - if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) + if (defer_setup) parent->sk_state_change(parent); + sock_put(parent); + return result; } From de23fb62259aa01d294f77238ae3b835eb674413 Mon Sep 17 00:00:00 2001 From: Zhang Cen Date: Thu, 28 May 2026 17:45:06 +0800 Subject: [PATCH 34/85] Bluetooth: MGMT: validate advertising TLV before type checks tlv_data_is_valid() reads each advertising data field length from data[i], then inspects data[i + 1] for managed EIR types before checking that the current field still fits inside the supplied buffer. A malformed field whose length byte is the last byte of the buffer can therefore make the parser read one byte past the advertising data. KASAN reported the following when a malformed MGMT_OP_ADD_ADVERTISING request reached that path: BUG: KASAN: vmalloc-out-of-bounds in tlv_data_is_valid() Read of size 1 Call trace: tlv_data_is_valid() add_advertising() hci_mgmt_cmd() hci_sock_sendmsg() Move the existing element-length check before any type-octet inspection so each non-empty element is proven to contain its type byte before the parser looks at data[i + 1]. Fixes: 2bb36870e8cb ("Bluetooth: Unify advertising instance flags check") Reviewed-by: Paul Menzel Signed-off-by: Zhang Cen Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/mgmt.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index de5bd6b637b2..027b266ccc74 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -8638,6 +8638,12 @@ static bool tlv_data_is_valid(struct hci_dev *hdev, u32 adv_flags, u8 *data, if (!cur_len) continue; + /* If the current field length would exceed the total data + * length, then it's invalid. + */ + if (i + cur_len >= len) + return false; + if (data[i + 1] == EIR_FLAGS && (!is_adv_data || flags_managed(adv_flags))) return false; @@ -8654,12 +8660,6 @@ static bool tlv_data_is_valid(struct hci_dev *hdev, u32 adv_flags, u8 *data, if (data[i + 1] == EIR_APPEARANCE && appearance_managed(adv_flags)) return false; - - /* If the current field length would exceed the total data - * length, then it's invalid. - */ - if (i + cur_len >= len) - return false; } return true; From 23882b828c3c8c51d0c946446a396b10abb3b16b Mon Sep 17 00:00:00 2001 From: SeungJu Cheon Date: Mon, 25 May 2026 20:04:43 +0900 Subject: [PATCH 35/85] Bluetooth: RFCOMM: validate skb length in MCC handlers The RFCOMM MCC handlers cast skb->data to protocol-specific structs without validating skb->len first. A malicious remote device can send truncated MCC frames and trigger out-of-bounds reads in these handlers. Fix this by using skb_pull_data() to validate and access the required data before dereferencing it. rfcomm_recv_rpn() requires special handling since ETSI TS 07.10 allows 1-byte RPN requests. Handle this by validating only the DLCI byte first, and validating the full struct only when len > 1. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Suggested-by: Muhammad Bilal Signed-off-by: SeungJu Cheon Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/rfcomm/core.c | 69 +++++++++++++++++++++++++++---------- 1 file changed, 50 insertions(+), 19 deletions(-) diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index d11bd5337d57..364b9381c2dc 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1431,10 +1431,15 @@ static int rfcomm_apply_pn(struct rfcomm_dlc *d, int cr, struct rfcomm_pn *pn) static int rfcomm_recv_pn(struct rfcomm_session *s, int cr, struct sk_buff *skb) { - struct rfcomm_pn *pn = (void *) skb->data; + struct rfcomm_pn *pn; struct rfcomm_dlc *d; - u8 dlci = pn->dlci; + u8 dlci; + pn = skb_pull_data(skb, sizeof(*pn)); + if (!pn) + return -EILSEQ; + + dlci = pn->dlci; BT_DBG("session %p state %ld dlci %d", s, s->state, dlci); if (!dlci) @@ -1483,8 +1488,8 @@ static int rfcomm_recv_pn(struct rfcomm_session *s, int cr, struct sk_buff *skb) static int rfcomm_recv_rpn(struct rfcomm_session *s, int cr, int len, struct sk_buff *skb) { - struct rfcomm_rpn *rpn = (void *) skb->data; - u8 dlci = __get_dlci(rpn->dlci); + struct rfcomm_rpn *rpn; + u8 dlci; u8 bit_rate = 0; u8 data_bits = 0; @@ -1495,15 +1500,16 @@ static int rfcomm_recv_rpn(struct rfcomm_session *s, int cr, int len, struct sk_ u8 xoff_char = 0; u16 rpn_mask = RFCOMM_RPN_PM_ALL; - BT_DBG("dlci %d cr %d len 0x%x bitr 0x%x line 0x%x flow 0x%x xonc 0x%x xoffc 0x%x pm 0x%x", - dlci, cr, len, rpn->bit_rate, rpn->line_settings, rpn->flow_ctrl, - rpn->xon_char, rpn->xoff_char, rpn->param_mask); - - if (!cr) - return 0; - if (len == 1) { - /* This is a request, return default (according to ETSI TS 07.10) settings */ + rpn = skb_pull_data(skb, 1); + if (!rpn) + return -EILSEQ; + + dlci = __get_dlci(rpn->dlci); + + if (!cr) + return 0; + bit_rate = RFCOMM_RPN_BR_9600; data_bits = RFCOMM_RPN_DATA_8; stop_bits = RFCOMM_RPN_STOP_1; @@ -1514,6 +1520,19 @@ static int rfcomm_recv_rpn(struct rfcomm_session *s, int cr, int len, struct sk_ goto rpn_out; } + rpn = skb_pull_data(skb, sizeof(*rpn)); + if (!rpn) + return -EILSEQ; + + dlci = __get_dlci(rpn->dlci); + + BT_DBG("dlci %d cr %d len 0x%x bitr 0x%x line 0x%x flow 0x%x xonc 0x%x xoffc 0x%x pm 0x%x", + dlci, cr, len, rpn->bit_rate, rpn->line_settings, rpn->flow_ctrl, + rpn->xon_char, rpn->xoff_char, rpn->param_mask); + + if (!cr) + return 0; + /* Check for sane values, ignore/accept bit_rate, 8 bits, 1 stop bit, * no parity, no flow control lines, normal XON/XOFF chars */ @@ -1589,9 +1608,14 @@ static int rfcomm_recv_rpn(struct rfcomm_session *s, int cr, int len, struct sk_ static int rfcomm_recv_rls(struct rfcomm_session *s, int cr, struct sk_buff *skb) { - struct rfcomm_rls *rls = (void *) skb->data; - u8 dlci = __get_dlci(rls->dlci); + struct rfcomm_rls *rls; + u8 dlci; + rls = skb_pull_data(skb, sizeof(*rls)); + if (!rls) + return -EILSEQ; + + dlci = __get_dlci(rls->dlci); BT_DBG("dlci %d cr %d status 0x%x", dlci, cr, rls->status); if (!cr) @@ -1608,10 +1632,15 @@ static int rfcomm_recv_rls(struct rfcomm_session *s, int cr, struct sk_buff *skb static int rfcomm_recv_msc(struct rfcomm_session *s, int cr, struct sk_buff *skb) { - struct rfcomm_msc *msc = (void *) skb->data; + struct rfcomm_msc *msc; struct rfcomm_dlc *d; - u8 dlci = __get_dlci(msc->dlci); + u8 dlci; + msc = skb_pull_data(skb, sizeof(*msc)); + if (!msc) + return -EILSEQ; + + dlci = __get_dlci(msc->dlci); BT_DBG("dlci %d cr %d v24 0x%x", dlci, cr, msc->v24_sig); d = rfcomm_dlc_get(s, dlci); @@ -1644,17 +1673,19 @@ static int rfcomm_recv_msc(struct rfcomm_session *s, int cr, struct sk_buff *skb static int rfcomm_recv_mcc(struct rfcomm_session *s, struct sk_buff *skb) { - struct rfcomm_mcc *mcc = (void *) skb->data; + struct rfcomm_mcc *mcc; u8 type, cr, len; + mcc = skb_pull_data(skb, sizeof(*mcc)); + if (!mcc) + return -EILSEQ; + cr = __test_cr(mcc->type); type = __get_mcc_type(mcc->type); len = __get_mcc_len(mcc->len); BT_DBG("%p type 0x%x cr %d", s, type, cr); - skb_pull(skb, 2); - switch (type) { case RFCOMM_PN: rfcomm_recv_pn(s, cr, skb); From dd214733544427587a95f66dbf3adff072568990 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Thu, 21 May 2026 10:45:17 -0400 Subject: [PATCH 36/85] Bluetooth: L2CAP: reject BR/EDR signaling packets over MTUsig net/bluetooth/l2cap_core.c:l2cap_sig_channel() accepts BR/EDR signaling packets up to the channel MTU and dispatches each command without enforcing the signaling MTU (MTUsig). A Bluetooth BR/EDR peer within radio range can send a fixed-channel CID 0x0001 packet that is larger than MTUsig and contains many L2CAP_ECHO_REQ commands before pairing. In a real-radio stock-kernel run, one 681-byte signaling packet containing 168 zero-length ECHO_REQ commands made the target transmit 168 ECHO_RSP frames over about 220 ms. Impact: a Bluetooth BR/EDR peer within radio range, before pairing, can force 168 ECHO_RSP frames from one 681-byte fixed-channel signaling packet containing packed ECHO_REQ commands. Define Linux's BR/EDR signaling MTU as the spec minimum of 48 bytes and reject any larger signaling packet with one L2CAP_COMMAND_REJECT_RSP carrying L2CAP_REJ_MTU_EXCEEDED before any command is dispatched. The Bluetooth Core spec wording for MTUExceeded says the reject identifier shall match the first request command in the packet, and that packets containing only responses shall be silently discarded. Linux intentionally deviates from that prescription: silently discarding desynchronizes the peer because the remote stack never learns its responses were dropped, and locating the first request command requires walking command headers past MTUsig, i.e. processing bytes from a packet we have already decided is too large to process. We therefore always emit one reject and use the identifier from the first command header, a single fixed-offset byte read. The unrestricted BR/EDR signaling parser and ECHO_REQ response path both trace to the initial git import; no later introducing commit is available for a Fixes tag. Cc: stable@vger.kernel.org Suggested-by: Luiz Augusto von Dentz Link: https://lore.kernel.org/r/20260518002800.1361430-1-michael.bommarito@gmail.com Link: https://lore.kernel.org/r/20260520135034.1060859-1-michael.bommarito@gmail.com Link: https://lore.kernel.org/r/20260521000555.3712030-1-michael.bommarito@gmail.com Assisted-by: Claude:claude-opus-4-7 Assisted-by: Codex:gpt-5-5-xhigh Signed-off-by: Michael Bommarito Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/l2cap.h | 1 + net/bluetooth/l2cap_core.c | 46 +++++++++++++++++++++++++++++++++++ 2 files changed, 47 insertions(+) diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 5172afee5494..e0a1f2293679 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -33,6 +33,7 @@ /* L2CAP defaults */ #define L2CAP_DEFAULT_MTU 672 #define L2CAP_DEFAULT_MIN_MTU 48 +#define L2CAP_SIG_MTU 48 /* BR/EDR signaling MTU */ #define L2CAP_DEFAULT_FLUSH_TO 0xFFFF #define L2CAP_EFS_DEFAULT_FLUSH_TO 0xFFFFFFFF #define L2CAP_DEFAULT_TX_WINDOW 63 diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 45b175399e8d..c4ccfbda9d78 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -5643,6 +5643,15 @@ static inline void l2cap_sig_send_rej(struct l2cap_conn *conn, u16 ident) l2cap_send_cmd(conn, ident, L2CAP_COMMAND_REJ, sizeof(rej), &rej); } +static inline void l2cap_sig_send_mtu_rej(struct l2cap_conn *conn, u8 ident) +{ + struct l2cap_cmd_rej_mtu rej; + + rej.reason = cpu_to_le16(L2CAP_REJ_MTU_EXCEEDED); + rej.max_mtu = cpu_to_le16(L2CAP_SIG_MTU); + l2cap_send_cmd(conn, ident, L2CAP_COMMAND_REJ, sizeof(rej), &rej); +} + static inline void l2cap_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb) { @@ -5655,6 +5664,43 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn, if (hcon->type != ACL_LINK) goto drop; + /* + * Bluetooth Core v5.4, Vol 3, Part A, Section 4: the BR/EDR + * signaling channel has a fixed signaling MTU (MTUsig) whose + * minimum and default is 48 octets. Section 4.1 says that on + * an MTUExceeded command reject the identifier "shall match + * the first request command in the L2CAP packet" and that + * packets containing only response commands "shall be + * silently discarded". + * + * Linux intentionally deviates from that prescription: + * + * 1. Silently discarding desynchronizes the peer. The + * remote stack never learns its responses were dropped, + * so any state machine waiting on a paired response + * stalls until its own timer fires. + * + * 2. Locating "the first request command" requires walking + * command headers past MTUsig, i.e. processing bytes + * from a packet we have already decided is too large to + * process. + * + * Reject every over-MTUsig signaling packet with one + * L2CAP_REJ_MTU_EXCEEDED command reject. The reject's + * reason field is what tells the peer that the whole packet + * was discarded; the identifier value is informational, so + * we use the identifier from the first command header, a + * single fixed-offset byte read. + */ + if (skb->len > L2CAP_SIG_MTU) { + u8 ident = skb->data[1]; + + BT_DBG("signaling packet exceeds MTU: %u > %u", + skb->len, L2CAP_SIG_MTU); + l2cap_sig_send_mtu_rej(conn, ident); + goto drop; + } + while (skb->len >= L2CAP_CMD_HDR_SIZE) { u16 len; From 5c65b96b549ea2dcfde497436bf9e048deb87758 Mon Sep 17 00:00:00 2001 From: Yuqi Xu Date: Fri, 29 May 2026 16:54:23 +0800 Subject: [PATCH 37/85] Bluetooth: hci_sync: reject oversized Broadcast Announcement prepend Existing advertising instances can already hold the maximum extended advertising payload. When hci_adv_bcast_annoucement() prepends the Broadcast Announcement service data to that payload, the combined data may no longer fit in the temporary buffer used to rebuild the advertising data. Reject that case before copying the existing payload and report the failure through the device log. This keeps the existing advertising data intact and avoids overrunning the temporary buffer. Fixes: 5725bc608252 ("Bluetooth: hci_sync: Fix broadcast/PA when using an existing instance") Cc: stable@kernel.org Reported-by: Yuan Tan Reported-by: Zhengchuan Liang Reported-by: Xin Liu Assisted-by: Codex:GPT-5.4 Signed-off-by: Yuqi Xu Signed-off-by: Ren Wei Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/hci_sync.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index aeccd8084cba..df23245d6ccd 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -1725,6 +1725,11 @@ static int hci_adv_bcast_annoucement(struct hci_dev *hdev, struct adv_info *adv) /* Generate Broadcast ID */ get_random_bytes(bid, sizeof(bid)); len = eir_append_service_data(ad, 0, 0x1852, bid, sizeof(bid)); + if (adv->adv_data_len > sizeof(ad) - len) { + bt_dev_err(hdev, "No room for Broadcast Announcement"); + return -EINVAL; + } + memcpy(ad + len, adv->adv_data, adv->adv_data_len); hci_set_adv_instance_data(hdev, adv->instance, len + adv->adv_data_len, ad, 0, NULL); From 6770d3a8acdf9151769180cc3710346c4cfbe6f0 Mon Sep 17 00:00:00 2001 From: Zhang Cen Date: Fri, 29 May 2026 11:22:09 +0800 Subject: [PATCH 38/85] Bluetooth: bnep: reject short frames before parsing A BNEP peer can send a short BNEP SDU. bnep_rx_frame() reads the packet type byte immediately and, for control packets, reads the control opcode and setup UUID-size byte before proving that those bytes are present. bnep_rx_control() also dereferences the control opcode without rejecting an empty control payload. Use skb_pull_data() for the fixed fields in bnep_rx_frame() so a NULL return gates each dereference. Split the control handler so the frame path can pass an opcode that has already been pulled, and keep the byte-buffer wrapper for extension control payloads. For BNEP_SETUP_CONN_REQ, name the UUID-size byte before pulling the setup payload. struct bnep_setup_conn_req carries destination and source service UUIDs after that byte, each uuid_size bytes, so the parser now documents that tuple explicitly instead of leaving the pull length as an opaque multiplication. Validation reproduced this kernel report: KASAN slab-out-of-bounds in bnep_rx_frame.isra.0+0x130c/0x1790 The buggy address belongs to the object at ffff88800c0f7908 which belongs to the cache kmalloc-8 of size 8 The buggy address is located 0 bytes to the right of allocated 1-byte region [ffff88800c0f7908, ffff88800c0f7909) Read of size 1 Call trace: dump_stack_lvl+0xb3/0x140 (?:?) print_address_description+0x57/0x3a0 (?:?) bnep_rx_frame+0x130c/0x1790 (net/bluetooth/bnep/core.c:306) print_report+0xb9/0x2b0 (?:?) __virt_addr_valid+0x1ba/0x3a0 (?:?) srso_alias_return_thunk+0x5/0xfbef5 (?:?) kasan_addr_to_slab+0x21/0x60 (?:?) kasan_report+0xe0/0x110 (?:?) process_one_work+0xfce/0x17e0 (kernel/workqueue.c:3200) worker_thread+0x65c/0xe40 (?:?) __kthread_parkme+0x184/0x230 (?:?) kthread+0x35e/0x470 (?:?) _raw_spin_unlock_irq+0x28/0x50 (?:?) ret_from_fork+0x586/0x870 (?:?) __switch_to+0x74f/0xdc0 (?:?) ret_from_fork_asm+0x1a/0x30 (?:?) Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Assisted-by: Codex:gpt-5.5 Signed-off-by: Zhang Cen Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/bnep/core.c | 59 ++++++++++++++++++++++++--------------- 1 file changed, 37 insertions(+), 22 deletions(-) diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index 0de5df690bd0..5c5f53ff30e8 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -206,14 +206,11 @@ static int bnep_ctrl_set_mcfilter(struct bnep_session *s, u8 *data, int len) return 0; } -static int bnep_rx_control(struct bnep_session *s, void *data, int len) +static int bnep_rx_control_cmd(struct bnep_session *s, u8 cmd, void *data, + int len) { - u8 cmd = *(u8 *)data; int err = 0; - data++; - len--; - switch (cmd) { case BNEP_CMD_NOT_UNDERSTOOD: case BNEP_SETUP_CONN_RSP: @@ -254,6 +251,14 @@ static int bnep_rx_control(struct bnep_session *s, void *data, int len) return err; } +static int bnep_rx_control(struct bnep_session *s, void *data, int len) +{ + if (len < 1) + return -EILSEQ; + + return bnep_rx_control_cmd(s, *(u8 *)data, data + 1, len - 1); +} + static int bnep_rx_extension(struct bnep_session *s, struct sk_buff *skb) { struct bnep_ext_hdr *h; @@ -299,19 +304,26 @@ static int bnep_rx_frame(struct bnep_session *s, struct sk_buff *skb) { struct net_device *dev = s->dev; struct sk_buff *nskb; + u8 *data; u8 type, ctrl_type; dev->stats.rx_bytes += skb->len; - type = *(u8 *) skb->data; - skb_pull(skb, 1); - ctrl_type = *(u8 *)skb->data; + data = skb_pull_data(skb, sizeof(type)); + if (!data) + goto badframe; + type = *data; if ((type & BNEP_TYPE_MASK) >= sizeof(__bnep_rx_hlen)) goto badframe; if ((type & BNEP_TYPE_MASK) == BNEP_CONTROL) { - if (bnep_rx_control(s, skb->data, skb->len) < 0) { + data = skb_pull_data(skb, sizeof(ctrl_type)); + if (!data) + goto badframe; + ctrl_type = *data; + + if (bnep_rx_control_cmd(s, ctrl_type, skb->data, skb->len) < 0) { dev->stats.tx_errors++; kfree_skb(skb); return 0; @@ -324,24 +336,27 @@ static int bnep_rx_frame(struct bnep_session *s, struct sk_buff *skb) /* Verify and pull ctrl message since it's already processed */ switch (ctrl_type) { - case BNEP_SETUP_CONN_REQ: - /* Pull: ctrl type (1 b), len (1 b), data (len bytes) */ - if (!skb_pull(skb, 2 + *(u8 *)(skb->data + 1) * 2)) - goto badframe; - break; - case BNEP_FILTER_MULTI_ADDR_SET: - case BNEP_FILTER_NET_TYPE_SET: { - u8 *hdr; + case BNEP_SETUP_CONN_REQ: { + u8 uuid_size; - /* Pull ctrl type (1 b) + len (2 b) */ - hdr = skb_pull_data(skb, 3); - if (!hdr) + /* Pull uuid_size and the dst/src service UUIDs. */ + data = skb_pull_data(skb, sizeof(uuid_size)); + if (!data) goto badframe; - /* Pull data (len bytes); length is big-endian */ - if (!skb_pull(skb, get_unaligned_be16(&hdr[1]))) + uuid_size = *data; + if (!skb_pull(skb, uuid_size + uuid_size)) goto badframe; break; } + case BNEP_FILTER_MULTI_ADDR_SET: + case BNEP_FILTER_NET_TYPE_SET: + /* Pull: len (2 b), data (len bytes) */ + data = skb_pull_data(skb, sizeof(u16)); + if (!data) + goto badframe; + if (!skb_pull(skb, get_unaligned_be16(data))) + goto badframe; + break; default: kfree_skb(skb); return 0; From 37b3009bf5976e8ab77c8b9a9bc3bbd7ff49e37f Mon Sep 17 00:00:00 2001 From: Bharath Reddy Date: Mon, 1 Jun 2026 08:54:26 +0530 Subject: [PATCH 39/85] Bluetooth: fix memory leak in error path of hci_alloc_dev() Early failures in Bluetooth HCI UART configuration leak SRCU percpu memory. When device initialization fails before hci_register_dev() completes, the HCI_UNREGISTER flag is never set. As a result, when the device reference count reaches zero, bt_host_release() evaluates this flag as false and falls back to a direct kfree(hdev). Because hci_release_dev() is bypassed, the SRCU struct initialized early in hci_alloc_dev() is never cleaned up, resulting in a leak of percpu memory. Fix the leak by explicitly calling cleanup_srcu_struct() in the fallback (unregistered) branch of bt_host_release() before freeing the device. Reported-by: syzbot+535ecc844591e50588a5@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=535ecc844591e50588a5 Tested-by: syzbot+535ecc844591e50588a5@syzkaller.appspotmail.com Fixes: 1d6123102e9f ("Bluetooth: hci_core: Fix use-after-free in vhci_flush()") Signed-off-by: Bharath Reddy Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/hci_sysfs.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 041ce9adc378..8957ce7c21b7 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -83,10 +83,12 @@ static void bt_host_release(struct device *dev) { struct hci_dev *hdev = to_hci_dev(dev); - if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) + if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) { hci_release_dev(hdev); - else + } else { + cleanup_srcu_struct(&hdev->srcu); kfree(hdev); + } module_put(THIS_MODULE); } From 5cbf290b79351971f20c7a533247e8d58a3f970c Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 1 Jun 2026 14:45:42 -0400 Subject: [PATCH 40/85] Bluetooth: ISO: Fix not releasing hdev reference on iso_conn_big_sync hci_get_route() returns a reference-counted hci_dev pointer via hci_dev_hold(). The function exits normally or with an error without ever releasing it. Fixes: 07a9342b94a9 ("Bluetooth: ISO: Send BIG Create Sync via hci_sync") Reported-by: Sashiko Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/iso.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 876649556d3c..3d707c43bdc0 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -1595,6 +1595,7 @@ static void iso_conn_big_sync(struct sock *sk) release_sock(sk); hci_dev_unlock(hdev); + hci_dev_put(hdev); } static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg, From f50331f2a1441ec49988832c3a95f2edacc47322 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 1 Jun 2026 14:52:09 -0400 Subject: [PATCH 41/85] Bluetooth: ISO: Fix a use-after-free of the hci_conn pointer In iso_sock_rebind_bc(), the bis pointer is cached, then the socket lock is dropped: bis = iso_pi(sk)->conn->hcon; /* Release the socket before lookups since that requires hci_dev_lock * which shall not be acquired while holding sock_lock for proper * ordering. */ release_sock(sk); hci_dev_lock(bis->hdev); During the unlocked window, could a concurrent close() destroy the connection and free the bis structure, causing hci_dev_lock(bis->hdev) to access memory after it is freed, fix this by using the hdev reference which was safely acquired via iso_conn_get_hdev(). Fixes: d3413703d5f8 ("Bluetooth: ISO: Add support to bind to trigger PAST") Reported-by: Sashiko Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/iso.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 3d707c43bdc0..c21ed2bb3cf8 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -1082,7 +1082,7 @@ static int iso_sock_rebind_bc(struct sock *sk, struct sockaddr_iso *sa, * ordering. */ release_sock(sk); - hci_dev_lock(bis->hdev); + hci_dev_lock(hdev); lock_sock(sk); if (!iso_pi(sk)->conn || iso_pi(sk)->conn->hcon != bis) { From 9ca7053d6215d89c33f28893bfd1625a32919d3f Mon Sep 17 00:00:00 2001 From: SeungJu Cheon Date: Mon, 1 Jun 2026 20:19:07 +0900 Subject: [PATCH 42/85] Bluetooth: ISO: Fix data-race on iso_pi fields in hci_get_route calls iso_connect_bis(), iso_connect_cis(), iso_listen_bis(), and iso_conn_big_sync() call hci_get_route() using iso_pi(sk)->dst, iso_pi(sk)->src, and iso_pi(sk)->src_type without holding lock_sock(). These fields may be modified concurrently by connect() or setsockopt() on the same socket, resulting in data-races reported by KCSAN. Fix this by snapshotting the required fields under lock_sock() before calling hci_get_route(). BUG: KCSAN: data-race in memcmp+0x45/0xb0 race at unknown origin, with read to 0xffff8880122135cf of 1 bytes by task 333 on cpu 1: memcmp+0x45/0xb0 hci_get_route+0x27e/0x490 iso_connect_cis+0x4c/0xa10 iso_sock_connect+0x60e/0xb30 __sys_connect_file+0xbd/0xe0 __sys_connect+0xe0/0x110 __x64_sys_connect+0x40/0x50 x64_sys_call+0xcad/0x1c60 do_syscall_64+0x133/0x590 entry_SYSCALL_64_after_hwframe+0x77/0x7f Fixes: 241f51931c35 ("Bluetooth: ISO: Avoid circular locking dependency") Signed-off-by: SeungJu Cheon Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/iso.c | 60 +++++++++++++++++++++++++++++++++------------ 1 file changed, 44 insertions(+), 16 deletions(-) diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index c21ed2bb3cf8..3abd8111dda8 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -337,12 +337,20 @@ static int iso_connect_bis(struct sock *sk) struct iso_conn *conn; struct hci_conn *hcon; struct hci_dev *hdev; + bdaddr_t src, dst; + u8 src_type, bc_sid; int err; - BT_DBG("%pMR (SID 0x%2.2x)", &iso_pi(sk)->src, iso_pi(sk)->bc_sid); + lock_sock(sk); + bacpy(&src, &iso_pi(sk)->src); + bacpy(&dst, &iso_pi(sk)->dst); + src_type = iso_pi(sk)->src_type; + bc_sid = iso_pi(sk)->bc_sid; + release_sock(sk); - hdev = hci_get_route(&iso_pi(sk)->dst, &iso_pi(sk)->src, - iso_pi(sk)->src_type); + BT_DBG("%pMR (SID 0x%2.2x)", &src, bc_sid); + + hdev = hci_get_route(&dst, &src, src_type); if (!hdev) return -EHOSTUNREACH; @@ -430,12 +438,19 @@ static int iso_connect_cis(struct sock *sk) struct iso_conn *conn; struct hci_conn *hcon; struct hci_dev *hdev; + bdaddr_t src, dst; + u8 src_type; int err; - BT_DBG("%pMR -> %pMR", &iso_pi(sk)->src, &iso_pi(sk)->dst); + lock_sock(sk); + bacpy(&src, &iso_pi(sk)->src); + bacpy(&dst, &iso_pi(sk)->dst); + src_type = iso_pi(sk)->src_type; + release_sock(sk); - hdev = hci_get_route(&iso_pi(sk)->dst, &iso_pi(sk)->src, - iso_pi(sk)->src_type); + BT_DBG("%pMR -> %pMR", &src, &dst); + + hdev = hci_get_route(&dst, &src, src_type); if (!hdev) return -EHOSTUNREACH; @@ -1212,18 +1227,25 @@ static int iso_sock_connect(struct socket *sock, struct sockaddr_unsized *addr, static int iso_listen_bis(struct sock *sk) { - struct hci_dev *hdev; - int err = 0; struct iso_conn *conn; struct hci_conn *hcon; + struct hci_dev *hdev; + bdaddr_t src, dst; + u8 src_type, bc_sid; + int err = 0; - BT_DBG("%pMR -> %pMR (SID 0x%2.2x)", &iso_pi(sk)->src, - &iso_pi(sk)->dst, iso_pi(sk)->bc_sid); + lock_sock(sk); + bacpy(&src, &iso_pi(sk)->src); + bacpy(&dst, &iso_pi(sk)->dst); + src_type = iso_pi(sk)->src_type; + bc_sid = iso_pi(sk)->bc_sid; + release_sock(sk); + + BT_DBG("%pMR -> %pMR (SID 0x%2.2x)", &src, &dst, bc_sid); write_lock(&iso_sk_list.lock); - if (__iso_get_sock_listen_by_sid(&iso_pi(sk)->src, &iso_pi(sk)->dst, - iso_pi(sk)->bc_sid)) + if (__iso_get_sock_listen_by_sid(&src, &dst, bc_sid)) err = -EADDRINUSE; write_unlock(&iso_sk_list.lock); @@ -1231,8 +1253,7 @@ static int iso_listen_bis(struct sock *sk) if (err) return err; - hdev = hci_get_route(&iso_pi(sk)->dst, &iso_pi(sk)->src, - iso_pi(sk)->src_type); + hdev = hci_get_route(&dst, &src, src_type); if (!hdev) return -EHOSTUNREACH; @@ -1568,9 +1589,16 @@ static void iso_conn_big_sync(struct sock *sk) { int err; struct hci_dev *hdev; + bdaddr_t src, dst; + u8 src_type; - hdev = hci_get_route(&iso_pi(sk)->dst, &iso_pi(sk)->src, - iso_pi(sk)->src_type); + lock_sock(sk); + bacpy(&src, &iso_pi(sk)->src); + bacpy(&dst, &iso_pi(sk)->dst); + src_type = iso_pi(sk)->src_type; + release_sock(sk); + + hdev = hci_get_route(&dst, &src, src_type); if (!hdev) return; From 4847c5bca22227100ae69e96af86618b6fd2671f Mon Sep 17 00:00:00 2001 From: SeungJu Cheon Date: Mon, 1 Jun 2026 20:19:08 +0900 Subject: [PATCH 43/85] Bluetooth: SCO: Fix data-race on sco_pi fields in sco_connect sco_sock_connect() copies the destination address into sco_pi(sk)->dst under lock_sock(), then releases the lock and calls sco_connect(), which reads dst, src, setting, and codec without holding lock_sock() in hci_get_route() and hci_connect_sco(). These fields may be modified concurrently by connect(), bind(), or setsockopt() on the same socket, resulting in data-races reported by KCSAN. Fix this by snapshotting dst, src, setting, and codec under lock_sock() at the start of sco_connect() before passing them to hci_get_route() and hci_connect_sco(). BUG: KCSAN: data-race in memcmp+0x45/0xb0 race at unknown origin, with read to 0xffff88800e6b0dd0 of 1 bytes by task 315 on cpu 0: memcmp+0x45/0xb0 hci_connect_acl+0x1b7/0x6b0 hci_connect_sco+0x4d/0xb30 sco_sock_connect+0x27b/0xd60 __sys_connect_file+0xbd/0xe0 __sys_connect+0xe0/0x110 __x64_sys_connect+0x40/0x50 x64_sys_call+0xcad/0x1c60 do_syscall_64+0x133/0x590 entry_SYSCALL_64_after_hwframe+0x77/0x7f Fixes: 9a8ec9e8ebb5 ("Bluetooth: SCO: Fix possible circular locking dependency on sco_connect_cfm") Signed-off-by: SeungJu Cheon Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/sco.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index f1799c6a6f87..140869e5b2df 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -312,11 +312,21 @@ static int sco_connect(struct sock *sk) struct sco_conn *conn; struct hci_conn *hcon; struct hci_dev *hdev; + bdaddr_t src, dst; + struct bt_codec codec; + __u16 setting; int err, type; - BT_DBG("%pMR -> %pMR", &sco_pi(sk)->src, &sco_pi(sk)->dst); + lock_sock(sk); + bacpy(&src, &sco_pi(sk)->src); + bacpy(&dst, &sco_pi(sk)->dst); + setting = sco_pi(sk)->setting; + codec = sco_pi(sk)->codec; + release_sock(sk); - hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); + BT_DBG("%pMR -> %pMR", &src, &dst); + + hdev = hci_get_route(&dst, &src, BDADDR_BREDR); if (!hdev) return -EHOSTUNREACH; @@ -327,7 +337,7 @@ static int sco_connect(struct sock *sk) else type = SCO_LINK; - switch (sco_pi(sk)->setting & SCO_AIRMODE_MASK) { + switch (setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_TRANSP: if (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev)) { err = -EOPNOTSUPP; @@ -336,8 +346,8 @@ static int sco_connect(struct sock *sk) break; } - hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst, - sco_pi(sk)->setting, &sco_pi(sk)->codec, + hcon = hci_connect_sco(hdev, type, &dst, + setting, &codec, READ_ONCE(sk->sk_sndtimeo)); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); From 149324fc762c2a7acef9c26790566f81f475e51f Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Tue, 2 Jun 2026 16:48:34 -0400 Subject: [PATCH 44/85] Bluetooth: MGMT: Fix backward compatibility with userspace bluetoothd has a bug with makes it send extra bytes as part of MGMT_OP_ADD_EXT_ADV_DATA which are now being checked to be the exact the expected length, relax this so only when the expected length is greater than the data length to cause an error since that would result in accessing invalid memory, otherwise just ignore the extra bytes. Link: https://lore.kernel.org/linux-bluetooth/20260602204749.210857-1-luiz.dentz@gmail.com/T/#u Fixes: d3f7d17960ed ("Bluetooth: MGMT: validate Add Extended Advertising Data length") Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/mgmt.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 027b266ccc74..f4aa814a0397 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -9114,8 +9114,9 @@ static int add_ext_adv_data(struct sock *sk, struct hci_dev *hdev, void *data, BT_DBG("%s", hdev->name); - expected_len = struct_size(cp, data, cp->adv_data_len + cp->scan_rsp_len); - if (expected_len != data_len) + expected_len = struct_size(cp, data, cp->adv_data_len + + cp->scan_rsp_len); + if (expected_len > data_len) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_EXT_ADV_DATA, MGMT_STATUS_INVALID_PARAMS); From 22ba97ea9cc1f63a0d0244fae38057ed452b6ac7 Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Sat, 30 May 2026 12:26:30 +0800 Subject: [PATCH 45/85] xsk: cache csum_start/csum_offset to fix TOCTOU in xsk_skb_metadata() The TX metadata area resides in the UMEM buffer which is memory-mapped and concurrently writable by userspace. In xsk_skb_metadata(), csum_start and csum_offset are read from shared memory for bounds validation, then read again for skb assignment. A malicious userspace application can race to overwrite these values between the two reads, bypassing the bounds check and causing out-of-bounds memory access during checksum computation in the transmit path. Fix this by reading csum_start and csum_offset into local variables once, then using the local copies for both validation and assignment. Note that other metadata fields (flags, launch_time) and the cached csum fields may be mutually inconsistent due to concurrent userspace writes, but this is benign: the only security-critical invariant is that each field's validated value is the same one used, which local caching guarantees. Closes: https://lore.kernel.org/all/20260503200927.73EA1C2BCB4@smtp.kernel.org/ Reviewed-by: Maciej Fijalkowski Signed-off-by: Jason Xing Acked-by: Stanislav Fomichev Fixes: 48eb03dd2630 ("xsk: Add TX timestamp and TX checksum offload support") Link: https://patch.msgid.link/20260530042630.80626-1-kerneljasonxing@gmail.com Signed-off-by: Jakub Kicinski --- net/xdp/xsk.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 5e5786cd9af5..f8c8a8c9dfba 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -802,6 +802,7 @@ static int xsk_skb_metadata(struct sk_buff *skb, void *buffer, u32 hr) { struct xsk_tx_metadata *meta = NULL; + u16 csum_start, csum_offset; if (unlikely(pool->tx_metadata_len == 0)) return -EINVAL; @@ -811,13 +812,15 @@ static int xsk_skb_metadata(struct sk_buff *skb, void *buffer, return -EINVAL; if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) { - if (unlikely(meta->request.csum_start + - meta->request.csum_offset + + csum_start = READ_ONCE(meta->request.csum_start); + csum_offset = READ_ONCE(meta->request.csum_offset); + + if (unlikely(csum_start + csum_offset + sizeof(__sum16) > desc->len)) return -EINVAL; - skb->csum_start = hr + meta->request.csum_start; - skb->csum_offset = meta->request.csum_offset; + skb->csum_start = hr + csum_start; + skb->csum_offset = csum_offset; skb->ip_summed = CHECKSUM_PARTIAL; if (unlikely(pool->tx_sw_csum)) { From 56d0885514491e5ed8f7593400879ab77c52504c Mon Sep 17 00:00:00 2001 From: Jonas Jelonek Date: Thu, 28 May 2026 20:52:40 +0000 Subject: [PATCH 46/85] net: sfp: initialize i2c_block_size at adapter configure time sfp->i2c_block_size is only assigned in sfp_sm_mod_probe(), which runs from the state machine timer after SFP_F_PRESENT has been set. Between those two points, sfp_module_eeprom() (the ethtool -m callback) gates only on SFP_F_PRESENT and can be entered with i2c_block_size still at its kzalloc'd value of 0. On a pure-I2C adapter, sfp_i2c_read() then issues an i2c_transfer() with msgs[1].len = 0 inside a loop that subtracts this_len from len each iteration; on adapters that succeed a zero-length read the loop never advances, spinning while holding rtnl_lock. This was previously addressed by initializing i2c_block_size in sfp_alloc() (commit 813c2dd78618), but the initialization was dropped when i2c_block_size was split from i2c_max_block_size. Initialize sfp->i2c_block_size from sfp->i2c_max_block_size in sfp_i2c_configure(), so the field is valid as soon as the adapter is known. sfp_sm_mod_probe() still reassigns it on each module insertion to recover from a per-module clamp to 1 (sfp_id_needs_byte_io). Fixes: 7662abf4db94 ("net: phy: sfp: Add support for SMBus module access") Cc: stable@vger.kernel.org Signed-off-by: Jonas Jelonek Link: https://patch.msgid.link/20260528205242.971410-2-jelonek.jonas@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/sfp.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index bd970f753beb..b94b9c433a21 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -822,6 +822,7 @@ static int sfp_i2c_configure(struct sfp *sfp, struct i2c_adapter *i2c) return -EINVAL; } + sfp->i2c_block_size = sfp->i2c_max_block_size; return 0; } From 2cdeaba5a1087f0f83e56729ea5c730b498639d9 Mon Sep 17 00:00:00 2001 From: Yizhou Zhao Date: Fri, 29 May 2026 18:50:16 +0800 Subject: [PATCH 47/85] appletalk: aarp: zero-initialize aarp_entry to prevent heap info leak aarp_alloc() allocates struct aarp_entry without zeroing it, but only initializes refcnt and packet_queue. When an unresolved AARP entry is created, hwaddr[ETH_ALEN] is left uninitialized. aarp_seq_show() later prints this field with %pM when users read /proc/net/atalk/arp. This can expose 6 bytes of stale heap data for each unresolved entry. Fix this by zero-initializing struct aarp_entry at allocation time. Reported-by: Yizhou Zhao Reported-by: Yuxiang Yang Reported-by: Ao Wang Reported-by: Xuewei Feng Reported-by: Qi Li Reported-by: Ke Xu Signed-off-by: Yizhou Zhao Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260529105017.81531-1-zhaoyz24@mails.tsinghua.edu.cn Signed-off-by: Jakub Kicinski --- net/appletalk/aarp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index 30493ea3c010..078fb7a6efa5 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -393,7 +393,7 @@ static void aarp_purge(void) */ static struct aarp_entry *aarp_alloc(void) { - struct aarp_entry *a = kmalloc_obj(*a, GFP_ATOMIC); + struct aarp_entry *a = kzalloc_obj(*a, GFP_ATOMIC); if (!a) return NULL; From a910fb8f7b9e4c566db363e6c2ec378dc7153995 Mon Sep 17 00:00:00 2001 From: Geetha sowjanya Date: Fri, 29 May 2026 17:07:57 +0530 Subject: [PATCH 48/85] octeontx2-pf: Fix NDC sync operation errors On system reboot "rvu_nicpf 0002:03:00.0: NDC sync operation failed" error messages are shown, even if the operations is successful. This is due to wrong if error check in ndc_syc() function. Fixes: 42c45ac1419c ("octeontx2-af: Sync NIX and NPA contexts from NDC to LLC/DRAM") Signed-off-by: Geetha sowjanya Signed-off-by: Subbaraya Sundeep Reviewed-by: Simon Horman Link: https://patch.msgid.link/1780054677-17249-1-git-send-email-sbhatta@marvell.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index ee623476e5ff..f9fbf0c17648 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -3473,7 +3473,7 @@ static void otx2_ndc_sync(struct otx2_nic *pf) req->nix_lf_rx_sync = 1; req->npa_lf_sync = 1; - if (!otx2_sync_mbox_msg(mbox)) + if (otx2_sync_mbox_msg(mbox)) dev_err(pf->dev, "NDC sync operation failed\n"); mutex_unlock(&mbox->lock); From 9a85ec3dc28b6df246801c19e4d9bae6297a25b0 Mon Sep 17 00:00:00 2001 From: Suman Ghosh Date: Fri, 29 May 2026 17:07:05 +0530 Subject: [PATCH 49/85] octeontx2-af: Fix initialization of mcam's entry2target_pffunc field NPC mcam entry stores a mapping between mcam entry and target pcifunc. During initialization of this field, API kmalloc_array has been used which caused some junk values to array. Whereas, the array is expected to be initialized by 0. This patch fixes the same by using kcalloc instead of kmalloc_array. Fixes: 55307fcb9258 ("octeontx2-af: Add mbox messages to install and delete MCAM rules") Signed-off-by: Suman Ghosh Signed-off-by: Subbaraya Sundeep Reviewed-by: Simon Horman Link: https://patch.msgid.link/1780054625-17090-1-git-send-email-sbhatta@marvell.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 607d0cf1a778..6bbda0593fcd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -2192,8 +2192,8 @@ int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr) goto free_entry_cntr_map; /* Alloc memory for saving target device of mcam rule */ - mcam->entry2target_pffunc = kmalloc_array(mcam->total_entries, - sizeof(u16), GFP_KERNEL); + mcam->entry2target_pffunc = kcalloc(mcam->total_entries, + sizeof(u16), GFP_KERNEL); if (!mcam->entry2target_pffunc) goto free_cntr_refcnt; From c1f07a7f2d47aeb9878301e7bb36bc1c2bc2be8e Mon Sep 17 00:00:00 2001 From: Jianyu Li Date: Mon, 1 Jun 2026 19:36:39 +0800 Subject: [PATCH 50/85] af_unix: Fix inq_len update problem in partial read Currently inq_len is updated only when the whole skb is consumed. If only part of the data is read, following SIOCINQ query would get value greater than what actually left. This change update inq_len timely in unix_stream_read_generic(), and adjust unix_stream_read_skb() accordingly to prevent repetitive update. Fixes: f4e1fb04c123 ("af_unix: Use cached value for SOCK_STREAM in unix_inq_len().") Signed-off-by: Jianyu Li Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260601113640.231897-2-jianyu.li@mediatek.com Signed-off-by: Jakub Kicinski --- net/unix/af_unix.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index dc71ed79be4a..0d9cd977c7b7 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2886,7 +2886,7 @@ static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor) return -EAGAIN; } - WRITE_ONCE(u->inq_len, u->inq_len - skb->len); + WRITE_ONCE(u->inq_len, u->inq_len - unix_skb_len(skb)); #if IS_ENABLED(CONFIG_AF_UNIX_OOB) if (skb == u->oob_skb) { @@ -3063,11 +3063,12 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, unix_detach_fds(&scm, skb); } - if (unix_skb_len(skb)) - break; - spin_lock(&sk->sk_receive_queue.lock); - WRITE_ONCE(u->inq_len, u->inq_len - skb->len); + WRITE_ONCE(u->inq_len, u->inq_len - chunk); + if (unix_skb_len(skb)) { + spin_unlock(&sk->sk_receive_queue.lock); + break; + } __skb_unlink(skb, &sk->sk_receive_queue); spin_unlock(&sk->sk_receive_queue.lock); From dd8975ad710ea1f3d7c7a36295072fd5ee59ca0a Mon Sep 17 00:00:00 2001 From: Jianyu Li Date: Mon, 1 Jun 2026 19:36:40 +0800 Subject: [PATCH 51/85] af_unix: Add test for SCM_INQ on partial read Add test to verify that when a skb is partially consumed, unix_inq_len() return correct remaining byte count. Before: # RUN scm_inq.stream.partial_read ... # scm_inq.c:165:partial_read:Expected remain (512) == *(int *)CMSG_DATA(cmsg) (768) # partial_read: Test terminated by assertion # FAIL scm_inq.stream.partial_read not ok 2 scm_inq.stream.partial_read After: # RUN scm_inq.stream.partial_read ... # OK scm_inq.stream.partial_read ok 2 scm_inq.stream.partial_read Signed-off-by: Jianyu Li Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260601113640.231897-3-jianyu.li@mediatek.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/af_unix/scm_inq.c | 54 ++++++++++++++++++- 1 file changed, 52 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/af_unix/scm_inq.c b/tools/testing/selftests/net/af_unix/scm_inq.c index 3a86be9bda17..6268b5bf50be 100644 --- a/tools/testing/selftests/net/af_unix/scm_inq.c +++ b/tools/testing/selftests/net/af_unix/scm_inq.c @@ -8,8 +8,9 @@ #include "kselftest_harness.h" -#define NR_CHUNKS 100 -#define MSG_LEN 256 +#define NR_CHUNKS 100 +#define MSG_LEN 256 +#define NR_PARTIAL_READS 3 FIXTURE(scm_inq) { @@ -120,4 +121,53 @@ TEST_F(scm_inq, basic) recv_chunks(_metadata, self); } +TEST_F(scm_inq, partial_read) +{ + char buf[MSG_LEN * NR_PARTIAL_READS] = {}; + char cmsg_buf[CMSG_SPACE(sizeof(int))]; + struct msghdr msg = {}; + struct iovec iov = {}; + struct cmsghdr *cmsg; + int err, inq, ret, i; + int remain; + + err = setsockopt(self->fd[1], SOL_SOCKET, SO_INQ, &(int){1}, sizeof(int)); + if (variant->type != SOCK_STREAM) { + ASSERT_EQ(-ENOPROTOOPT, -errno); + return; + } + ASSERT_EQ(0, err); + + ret = send(self->fd[0], buf, sizeof(buf), 0); + ASSERT_EQ(sizeof(buf), ret); + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = cmsg_buf; + msg.msg_controllen = sizeof(cmsg_buf); + + iov.iov_base = buf; + iov.iov_len = MSG_LEN; + + for (i = 0; i < NR_PARTIAL_READS; i++) { + remain = MSG_LEN * (NR_PARTIAL_READS - 1 - i); + + memset(buf, 0, MSG_LEN); + memset(cmsg_buf, 0, sizeof(cmsg_buf)); + ret = recvmsg(self->fd[1], &msg, 0); + ASSERT_EQ(MSG_LEN, ret); + + cmsg = CMSG_FIRSTHDR(&msg); + ASSERT_NE(NULL, cmsg); + ASSERT_EQ(CMSG_LEN(sizeof(int)), cmsg->cmsg_len); + ASSERT_EQ(SOL_SOCKET, cmsg->cmsg_level); + ASSERT_EQ(SCM_INQ, cmsg->cmsg_type); + ASSERT_EQ(remain, *(int *)CMSG_DATA(cmsg)); + + ret = ioctl(self->fd[1], SIOCINQ, &inq); + ASSERT_EQ(0, ret); + ASSERT_EQ(remain, inq); + } +} + TEST_HARNESS_MAIN From d3915a1f5a4bc0ac911032903c3c6ab8df9fcc7c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 2 Jun 2026 16:15:47 +0000 Subject: [PATCH 52/85] ipv4: restrict IPOPT_SSRR and IPOPT_LSRR options This patch restricts setting Loose Source and Record Route (LSRR) and Strict Source and Record Route (SSRR) IP options to users with CAP_NET_RAW capability. This prevents unprivileged applications from forcing packets to route through attacker-controlled nodes to leak TCP ISN and possibly other protocol information. While LSRR and SSRR are commonly filtered in many network environments, they may still be supported and forwarded along some network paths. RFC 7126 (Recommendations on Filtering of IPv4 Packets Containing IPv4 Options) recommend to drop these options in 4.3 and 4.4. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Tamir Shahar Reported-by: Amit Klein Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260602161547.2642155-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/ip_options.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index be8815ce3ac2..09d745112c15 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -530,6 +530,10 @@ int ip_options_get(struct net *net, struct ip_options_rcu **optp, kfree(opt); return -EINVAL; } + if (opt->opt.srr && !ns_capable(net->user_ns, CAP_NET_RAW)) { + kfree(opt); + return -EPERM; + } kfree(*optp); *optp = opt; return 0; From 672bd0519e27c357c43b7f8c0d653fce3817d06e Mon Sep 17 00:00:00 2001 From: Kurt Kanzenbach Date: Fri, 29 May 2026 19:11:47 +0200 Subject: [PATCH 53/85] ptp: vclock: Switch from RCU to SRCU The usage of PTP vClocks leads immediately to the following issues with ptp4l with LOCKDEP and DEBUG_ATOMIC_SLEEP enabled: "BUG: sleeping function called from invalid context". ptp_convert_timestamp() acquires a mutex_t within a RCU read section. This is illegal, because acquiring a mutex_t can result in voluntary scheduling request which is not allowed within a RCU read section. Replace the RCU usage with SRCU where sleeping is allowed. Reported-by: Florian Zeitz Closes: https://lore.kernel.org/all/00a8cce8-410e-4038-98af-49be6d93d7bd@schettke.com/ Fixes: 67d93ffc0f3c ("ptp: vclock: use mutex to fix "sleep on atomic" bug") Signed-off-by: Kurt Kanzenbach Reviewed-by: Sebastian Andrzej Siewior Link: https://patch.msgid.link/20260529-vclock_rcu-v2-1-02a5531fab92@linutronix.de Signed-off-by: Jakub Kicinski --- drivers/ptp/ptp_vclock.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c index 915a4f6defc9..84cb527f59cc 100644 --- a/drivers/ptp/ptp_vclock.c +++ b/drivers/ptp/ptp_vclock.c @@ -19,6 +19,8 @@ static DEFINE_SPINLOCK(vclock_hash_lock); static DEFINE_READ_MOSTLY_HASHTABLE(vclock_hash, 8); +DEFINE_STATIC_SRCU(vclock_srcu); + static void ptp_vclock_hash_add(struct ptp_vclock *vclock) { spin_lock(&vclock_hash_lock); @@ -37,7 +39,7 @@ static void ptp_vclock_hash_del(struct ptp_vclock *vclock) spin_unlock(&vclock_hash_lock); - synchronize_rcu(); + synchronize_srcu(&vclock_srcu); } static int ptp_vclock_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) @@ -276,14 +278,16 @@ ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, int vclock_index) { unsigned int hash = vclock_index % HASH_SIZE(vclock_hash); struct ptp_vclock *vclock; - u64 ns; u64 vclock_ns = 0; + int srcu_idx; + u64 ns; ns = ktime_to_ns(*hwtstamp); - rcu_read_lock(); + srcu_idx = srcu_read_lock(&vclock_srcu); - hlist_for_each_entry_rcu(vclock, &vclock_hash[hash], vclock_hash_node) { + hlist_for_each_entry_srcu(vclock, &vclock_hash[hash], vclock_hash_node, + srcu_read_lock_held(&vclock_srcu)) { if (vclock->clock->index != vclock_index) continue; @@ -294,7 +298,7 @@ ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, int vclock_index) break; } - rcu_read_unlock(); + srcu_read_unlock(&vclock_srcu, srcu_idx); return ns_to_ktime(vclock_ns); } From 9d8d28738f24b75616d6ca7a27cb4aed88520343 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 2 Jun 2026 22:14:08 +1000 Subject: [PATCH 54/85] mptcp: fix missing wakeups in edge scenarios The mptcp_recvmsg() can fill MPTCP socket receive queue via mptcp_move_skbs(), but currently does not try to wakeup any listener, because the same process is going to check the receive queue soon. When multiple threads are reading from the same fd, the above can cause stall. Add the missing wakeup. Fixes: 6771bfd9ee24 ("mptcp: update mptcp ack sequence from work queue") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-1-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a72a6ad6ee8b..5a20ab2789ae 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2276,6 +2276,10 @@ static bool mptcp_move_skbs(struct sock *sk) mptcp_backlog_spooled(sk, moved, &skbs); } mptcp_data_unlock(sk); + + if (enqueued && mptcp_epollin_ready(sk)) + sk->sk_data_ready(sk); + return enqueued; } From d1918b36edcaed0ec4ef6888b2358c6b1ddcff47 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 2 Jun 2026 22:14:09 +1000 Subject: [PATCH 55/85] mptcp: fix retransmission loop when csum is enabled Sashiko noted that retransmission with csum enabled can actually transmit new data, but currently the relevant code does not update accordingly snd_nxt. The may cause incoming ack drop and an endless retransmission loop. Address the issue incrementing snd_nxt as needed. Fixes: 4e14867d5e91 ("mptcp: tune re-injections for csum enabled mode") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-2-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 5a20ab2789ae..7fac5fac2097 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2869,6 +2869,10 @@ static void __mptcp_retrans(struct sock *sk) msk->bytes_retrans += len; dfrag->already_sent = max(dfrag->already_sent, len); + /* With csum enabled retransmission can send new data. */ + if (after64(dfrag->already_sent + dfrag->data_seq, msk->snd_nxt)) + WRITE_ONCE(msk->snd_nxt, dfrag->already_sent + dfrag->data_seq); + reset_timer: mptcp_check_and_set_pending(sk); From 8ab24fdebc369c0dfb90f82c1650b1e66662bb45 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 2 Jun 2026 22:14:10 +1000 Subject: [PATCH 56/85] mptcp: close TOCTOU race while computing rcv_wnd The MPTCP output path access locklessly the MPTCP-level ack_seq in multiple times, using possibly different values for the data_ack in the DSS option and to compute the announced rcv wnd for the same packet. Refactor the cote to avoid inconsistencies which may confuse the peer. Also ensure that the MPTCP level rcv wnd is updated only when the egress packet actually contains a DSS ack. Fixes: fa3fe2b15031 ("mptcp: track window announced to peer") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-3-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/options.c | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 8a1c5698983c..2d25f319f328 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -570,7 +570,6 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, struct mptcp_ext *mpext; unsigned int ack_size; bool ret = false; - u64 ack_seq; opts->csum_reqd = READ_ONCE(msk->csum_enabled); mpext = skb ? mptcp_get_ext(skb) : NULL; @@ -601,14 +600,11 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, return ret; } - ack_seq = READ_ONCE(msk->ack_seq); if (READ_ONCE(msk->use_64bit_ack)) { ack_size = TCPOLEN_MPTCP_DSS_ACK64; - opts->ext_copy.data_ack = ack_seq; opts->ext_copy.ack64 = 1; } else { ack_size = TCPOLEN_MPTCP_DSS_ACK32; - opts->ext_copy.data_ack32 = (uint32_t)ack_seq; opts->ext_copy.ack64 = 0; } opts->ext_copy.use_ack = 1; @@ -1297,19 +1293,14 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) return true; } -static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th) +static u64 mptcp_set_rwin(struct mptcp_sock *msk, struct tcp_sock *tp, + struct tcphdr *th, u64 ack_seq) { const struct sock *ssk = (const struct sock *)tp; - struct mptcp_subflow_context *subflow; - u64 ack_seq, rcv_wnd_old, rcv_wnd_new; - struct mptcp_sock *msk; + u64 rcv_wnd_old, rcv_wnd_new; u32 new_win; u64 win; - subflow = mptcp_subflow_ctx(ssk); - msk = mptcp_sk(subflow->conn); - - ack_seq = READ_ONCE(msk->ack_seq); rcv_wnd_new = ack_seq + tp->rcv_wnd; rcv_wnd_old = atomic64_read(&msk->rcv_wnd_sent); @@ -1362,7 +1353,7 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th) update_wspace: WRITE_ONCE(msk->old_wspace, tp->rcv_wnd); - subflow->rcv_wnd_sent = rcv_wnd_new; + return rcv_wnd_new; } static void mptcp_track_rwin(struct tcp_sock *tp) @@ -1474,13 +1465,25 @@ void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp, *ptr++ = mptcp_option(MPTCPOPT_DSS, len, 0, flags); if (mpext->use_ack) { + struct mptcp_sock *msk; + u64 ack_seq; + + /* DSS option is set only by mptcp_established_options, + * the caller is __tcp_transmit_skb() and ssk is always + * not NULL. + */ + subflow = mptcp_subflow_ctx(ssk); + msk = mptcp_sk(subflow->conn); + ack_seq = READ_ONCE(msk->ack_seq); if (mpext->ack64) { - put_unaligned_be64(mpext->data_ack, ptr); + put_unaligned_be64(ack_seq, ptr); ptr += 2; } else { - put_unaligned_be32(mpext->data_ack32, ptr); + put_unaligned_be32(ack_seq, ptr); ptr += 1; } + subflow->rcv_wnd_sent = mptcp_set_rwin(msk, tp, th, + ack_seq); } if (mpext->use_map) { @@ -1708,9 +1711,6 @@ void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp, i += 4; } } - - if (tp) - mptcp_set_rwin(tp, th); } __be32 mptcp_get_reset_option(const struct sk_buff *skb) From da23be77e1292cd611e736c3aa17da633d7ddce7 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 2 Jun 2026 22:14:11 +1000 Subject: [PATCH 57/85] mptcp: allow subflow rcv wnd to shrink In MPTCP connection, the `window` field in the TCP header refers to the MPTCP-level rcv_nxt and it's right edge should not move backward. Such constraint is enforced at DSS option generation time. At the same time, the TCP stack ensures independently that the TCP-level rcv wnd right's edge does not move backward. That in turn causes artificial inflating of the MPTCP rcv window when the incoming data is acked at the TCP level and is OoO in the MPTCP sequence space (or lands in the backlog). As a consequence, the incoming traffic can exceed the receiver rcvbuf size even when the sender is not misbehaving. Prevent such scenario forcibly allowing the TCP subflow to shrink the TCP-level rcv wnd regardless of the current netns setting. Fixes: f3589be0c420 ("mptcp: never shrink offered window") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-4-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/options.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 2d25f319f328..51ca334678b4 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -566,6 +566,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); + struct tcp_sock *tp = tcp_sk(sk); unsigned int dss_size = 0; struct mptcp_ext *mpext; unsigned int ack_size; @@ -614,6 +615,12 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, if (dss_size == 0) ack_size += TCPOLEN_MPTCP_DSS_BASE; + /* The caller is __tcp_transmit_skb(), and will compute the new rcv + * wnd soon: ensure that the window can shrink. + */ + if (skb) + tp->rcv_wnd = tp->rcv_nxt - tp->rcv_wup; + dss_size += ack_size; *size = ALIGN(dss_size, 4); From 14e9fea30b68fc75b2b3d97396a7e6adb544bd2a Mon Sep 17 00:00:00 2001 From: Tao Cui Date: Tue, 2 Jun 2026 22:14:12 +1000 Subject: [PATCH 58/85] mptcp: pm: fix extra_subflows underflow on userspace PM subflow creation The userspace PM increments extra_subflows after __mptcp_subflow_connect() succeeds, but __mptcp_subflow_connect() calls mptcp_pm_close_subflow() on failure to roll back the pre-increment done by the kernel PM's fill_*() helpers. Because the userspace PM hasn't incremented yet at that point, this decrement is spurious and causes extra_subflows to underflow. Fix it by aligning the userspace PM with the kernel PM: increment extra_subflows before calling __mptcp_subflow_connect(), so the existing error path in subflow.c correctly rolls it back on failure. Also simplify the error handling by taking pm.lock only when needed for cleanup. Fixes: 77e4b94a3de6 ("mptcp: update userspace pm infos") Cc: stable@vger.kernel.org Signed-off-by: Tao Cui Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-5-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_userspace.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 8cbc1920afb4..0d3a95e676f1 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -408,19 +408,21 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) local.flags = entry.flags; local.ifindex = entry.ifindex; + spin_lock_bh(&msk->pm.lock); + msk->pm.extra_subflows++; + spin_unlock_bh(&msk->pm.lock); + lock_sock(sk); err = __mptcp_subflow_connect(sk, &local, &addr_r); release_sock(sk); - if (err) + if (err) { GENL_SET_ERR_MSG_FMT(info, "connect error: %d", err); - spin_lock_bh(&msk->pm.lock); - if (err) + spin_lock_bh(&msk->pm.lock); mptcp_userspace_pm_delete_local_addr(msk, &entry); - else - msk->pm.extra_subflows++; - spin_unlock_bh(&msk->pm.lock); + spin_unlock_bh(&msk->pm.lock); + } create_err: sock_put(sk); From 06fd2bec7aebf393288e4b78924482fe170caabc Mon Sep 17 00:00:00 2001 From: Tao Cui Date: Tue, 2 Jun 2026 22:14:13 +1000 Subject: [PATCH 59/85] selftests: mptcp: add test for extra_subflows underflow on userspace PM Add a test to verify that when userspace PM fails to create a subflow (e.g. using an unreachable address), the extra_subflows counter is not decremented below zero. Fixes: 77e4b94a3de6 ("mptcp: update userspace pm infos") Cc: stable@vger.kernel.org Signed-off-by: Tao Cui Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-6-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 5acd12021e6e..4b3f71e66609 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -4100,6 +4100,10 @@ userspace_tests() chk_rm_nr 0 1 chk_mptcp_info subflows 0 subflows 0 chk_subflows_total 1 1 + # check counters are not affected by errors at creation time + userspace_pm_add_sf $ns2 10.0.12.2 10 2>/dev/null + chk_mptcp_info subflows 0 subflows 0 + chk_subflows_total 1 1 kill_events_pids mptcp_lib_kill_group_wait $tests_pid fi From 57132affbc89c02e1bf73fdf5724311bdc9a29da Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Tue, 2 Jun 2026 22:14:14 +1000 Subject: [PATCH 60/85] mptcp: sockopt: check timestamping ret value sock_set_timestamping() can fail for different reasons. The returned value should then be checked. If sock_set_timestamping() fails for at least one subflow, the first error is now reported to the userspace, similar to what is done with other socket options. Fixes: 9061f24bf82e ("mptcp: sockopt: propagate timestamp request to subflows") Cc: stable@vger.kernel.org Reported-by: Willem de Bruijn Closes: https://lore.kernel.org/willemdebruijn.kernel.178a41a53d041@gmail.com Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-7-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/sockopt.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 87b5796d0135..91aa57f1d0fd 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -241,15 +241,19 @@ static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk, mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + int err; lock_sock(ssk); - sock_set_timestamping(ssk, optname, timestamping); + err = sock_set_timestamping(ssk, optname, timestamping); release_sock(ssk); + + if (err < 0 && ret == 0) + ret = err; } release_sock(sk); - return 0; + return ret; } static int mptcp_setsockopt_sol_socket_linger(struct mptcp_sock *msk, sockptr_t optval, From 7690137e70ab0fb1f8b5a30e6f087f8ee908b680 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Tue, 2 Jun 2026 22:14:15 +1000 Subject: [PATCH 61/85] mptcp: sockopt: set sockopt on all subflows The mptcp_setsockopt_all_sf(), currently used only with TCP_MAXSEG, stopped when one subflow returned an error. Even if it is not wrong, this is different from the other helpers trying to set the option on all subflows, and then returning an error if at least one of them had an issue. Follow this behaviour, for a question of uniformity. Fixes: 51c5fd09e1b4 ("mptcp: add TCP_MAXSEG sockopt support") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-8-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/sockopt.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 91aa57f1d0fd..fcf6feb2a9eb 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -817,10 +817,11 @@ static int mptcp_setsockopt_all_sf(struct mptcp_sock *msk, int level, mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + int err; - ret = tcp_setsockopt(ssk, level, optname, optval, optlen); - if (ret) - break; + err = tcp_setsockopt(ssk, level, optname, optval, optlen); + if (err < 0 && ret == 0) + ret = err; } if (!ret) From c378b1a6f8dd3e02eb08661f4d5d50f236eead03 Mon Sep 17 00:00:00 2001 From: Gang Yan Date: Tue, 2 Jun 2026 22:14:16 +1000 Subject: [PATCH 62/85] mptcp: check desc->count in read_sock __tcp_read_sock() checks desc->count after each skb is consumed and breaks the loop when it reaches 0. The MPTCP variant lacks this check. This is a functional bug, other subsystems also rely on this check: TLS strparser sets desc->count to 0 once a full TLS record is assembled and depends on this break to stop reading. Add the same desc->count check to __mptcp_read_sock(), mirroring __tcp_read_sock(). Fixes: 250d9766a984 ("mptcp: implement .read_sock") Cc: stable@vger.kernel.org Co-developed-by: Geliang Tang Signed-off-by: Geliang Tang Signed-off-by: Gang Yan Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-9-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 7fac5fac2097..cb9515f505aa 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -4428,6 +4428,8 @@ static int __mptcp_read_sock(struct sock *sk, read_descriptor_t *desc, } mptcp_eat_recv_skb(sk, skb); + if (!desc->count) + break; } if (noack) From 5e939544f9d2b4d5c052a07cfcde97de44263946 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 2 Jun 2026 22:14:17 +1000 Subject: [PATCH 63/85] mptcp: fix uninit-value in mptcp_established_options syzbot reported the following uninit splat: BUG: KMSAN: uninit-value in mptcp_write_data_fin net/mptcp/options.c:542 [inline] BUG: KMSAN: uninit-value in mptcp_established_options_dss net/mptcp/options.c:590 [inline] BUG: KMSAN: uninit-value in mptcp_established_options+0x112f/0x3530 net/mptcp/options.c:874 mptcp_write_data_fin net/mptcp/options.c:542 [inline] mptcp_established_options_dss net/mptcp/options.c:590 [inline] mptcp_established_options+0x112f/0x3530 net/mptcp/options.c:874 tcp_established_options+0x312/0xcc0 net/ipv4/tcp_output.c:1192 __tcp_transmit_skb+0x5dc/0x5fe0 net/ipv4/tcp_output.c:1575 __tcp_send_ack+0x967/0xad0 net/ipv4/tcp_output.c:4499 tcp_send_ack+0x3d/0x60 net/ipv4/tcp_output.c:4505 mptcp_subflow_shutdown+0x164/0x690 net/mptcp/protocol.c:3137 mptcp_check_send_data_fin+0x31b/0x3d0 net/mptcp/protocol.c:3218 __mptcp_wr_shutdown net/mptcp/protocol.c:3234 [inline] __mptcp_close+0x860/0x1360 net/mptcp/protocol.c:3313 mptcp_close+0x42/0x260 net/mptcp/protocol.c:3367 inet_release+0x1ee/0x2a0 net/ipv4/af_inet.c:442 __sock_release net/socket.c:722 [inline] sock_close+0xd6/0x2f0 net/socket.c:1514 __fput+0x60e/0x1010 fs/file_table.c:510 ____fput+0x25/0x30 fs/file_table.c:538 task_work_run+0x208/0x2b0 kernel/task_work.c:233 resume_user_mode_work include/linux/resume_user_mode.h:50 [inline] __exit_to_user_mode_loop kernel/entry/common.c:67 [inline] exit_to_user_mode_loop+0x306/0x1b60 kernel/entry/common.c:98 __exit_to_user_mode_prepare include/linux/irq-entry-common.h:207 [inline] syscall_exit_to_user_mode_prepare include/linux/irq-entry-common.h:238 [inline] syscall_exit_to_user_mode include/linux/entry-common.h:318 [inline] __do_fast_syscall_32+0x2c7/0x460 arch/x86/entry/syscall_32.c:310 do_fast_syscall_32+0x37/0x80 arch/x86/entry/syscall_32.c:332 do_SYSENTER_32+0x1f/0x30 arch/x86/entry/syscall_32.c:370 entry_SYSENTER_compat_after_hwframe+0x84/0x8e Local variable opts created at: __tcp_transmit_skb+0x4d/0x5fe0 net/ipv4/tcp_output.c:1536 __tcp_send_ack+0x967/0xad0 net/ipv4/tcp_output.c:4499 The output path currently omits initializing the mptcp extension `use_map` flag in a few corner cases. Address the issue always zeroing all the extensions flags before eventually initializing the individual bits. To that extent, introduce and use a struct_group to avoid multiple bitwise operations. Fixes: cfcceb7a39fc ("tcp: shrink per-packet memset in __tcp_transmit_skb()") Cc: stable@vger.kernel.org Reported-by: syzbot+ff020673c5e3d94d9478@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=ff020673c5e3d94d9478 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-10-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- include/net/mptcp.h | 7 +++++-- net/mptcp/options.c | 6 +++++- 2 files changed, 10 insertions(+), 3 deletions(-) diff --git a/include/net/mptcp.h b/include/net/mptcp.h index f7263fe2a2e4..ee70f597a4de 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -27,7 +27,9 @@ struct mptcp_ext { u32 subflow_seq; u16 data_len; __sum16 csum; - u8 use_map:1, + + struct_group(flags, + u8 use_map:1, dsn64:1, data_fin:1, use_ack:1, @@ -35,9 +37,10 @@ struct mptcp_ext { mpc_map:1, frozen:1, reset_transient:1; - u8 reset_reason:4, + u8 reset_reason:4, csum_reqd:1, infinite_map:1; + ); /* end of flags group */ }; #define MPTCPOPT_HMAC_LEN 20 diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 51ca334678b4..f9f587203c35 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -572,6 +572,11 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, unsigned int ack_size; bool ret = false; + /* Zero `use_ack` and `use_map` flags with one shot. */ + BUILD_BUG_ON(sizeof_field(struct mptcp_ext, flags) != sizeof(u16)); + BUILD_BUG_ON(!IS_ALIGNED(offsetof(struct mptcp_ext, flags), + sizeof(u16))); + *(u16 *)&opts->ext_copy.flags = 0; opts->csum_reqd = READ_ONCE(msk->csum_enabled); mpext = skb ? mptcp_get_ext(skb) : NULL; @@ -595,7 +600,6 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, /* passive sockets msk will set the 'can_ack' after accept(), even * if the first subflow may have the already the remote key handy */ - opts->ext_copy.use_ack = 0; if (!READ_ONCE(msk->can_ack)) { *size = ALIGN(dss_size, 4); return ret; From bd34fa0257261b76964df1c98f44b3cb4ee14620 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Tue, 2 Jun 2026 22:14:18 +1000 Subject: [PATCH 64/85] mptcp: add-addr: always drop other suboptions When an ADD_ADDR needs to be sent, it could be prepared if there is enough remaining space and even if the packet is not a pure ACK. But it would be dropped soon after. Indeed, in mptcp_pm_add_addr_signal(), there is enough space to fit a DSS of 20 octets and an ADD_ADDR echo containing an IPv4 address on 8 octets for example. In this case, the packet would be prepared, the MPTCP_ADD_ADDR_ECHO bit would be removed from pm->addr_signal, but the option would be silently dropped in mptcp_established_options_add_addr() not to override DSS info in the union from 'struct mptcp_out_options', and also because mptcp_write_options() will enforce mutually exclusion with DSS. Instead, don't even try to send an ADD_ADDR if it is not a pure ACK. Retry for each new packet until a pure-ACK is emitted. That's fine to do that, because each time an ADD_ADDR (echo) is scheduled, a pure ACK is queued. This also simplifies the code, and the skb checks can be done earlier, before the lock. Note: also, since commit 6d0060f600ad ("mptcp: Write MPTCP DSS headers to outgoing data packets"), opts->ahmac would not have been set to 0 when other suboptions were not dropped, and when sending an ADD_ADDR echo. That would have resulted in sending an ADD_ADDR using garbage info, where there was not enough space, instead of an echo one without the ADD_ADDR HMAC. Fixes: 1bff1e43a30e ("mptcp: optimize out option generation") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260602-net-mptcp-misc-fixes-7-1-rc7-v2-11-856831229976@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/options.c | 30 +++++++----------------------- net/mptcp/pm.c | 15 ++++----------- net/mptcp/protocol.h | 7 +++---- 3 files changed, 14 insertions(+), 38 deletions(-) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index f9f587203c35..b3ea7854818f 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -665,7 +665,6 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); - bool drop_other_suboptions = false; unsigned int opt_size = *size; struct mptcp_addr_info addr; bool echo; @@ -676,36 +675,20 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * */ if (!mptcp_pm_should_add_signal(msk) || (opts->suboptions & (OPTION_MPTCP_MPJ_ACK | OPTION_MPTCP_MPC_ACK)) || - !mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, &addr, - &echo, &drop_other_suboptions)) + !skb || !skb_is_tcp_pure_ack(skb) || + !mptcp_pm_add_addr_signal(msk, opt_size, remaining, &addr, &echo)) return false; - /* - * Later on, mptcp_write_options() will enforce mutually exclusion with - * DSS, bail out if such option is set and we can't drop it. - */ - if (drop_other_suboptions) - remaining += opt_size; - else if (opts->suboptions & OPTION_MPTCP_DSS) - return false; + remaining += opt_size; len = mptcp_add_addr_len(addr.family, echo, !!addr.port); if (remaining < len) return false; *size = len; - if (drop_other_suboptions) { - pr_debug("drop other suboptions\n"); - opts->suboptions = 0; - - /* note that e.g. DSS could have written into the memory - * aliased by ahmac, we must reset the field here - * to avoid appending the hmac even for ADD_ADDR echo - * options - */ - opts->ahmac = 0; - *size -= opt_size; - } + pr_debug("drop other suboptions\n"); + opts->suboptions = 0; + *size -= opt_size; opts->addr = addr; opts->suboptions |= OPTION_MPTCP_ADD_ADDR; if (!echo) { @@ -715,6 +698,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * &opts->addr); } else { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADDTX); + opts->ahmac = 0; } pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d\n", opts->addr.id, opts->ahmac, echo, ntohs(opts->addr.port)); diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 3e770c7407e1..470501470fe5 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -887,10 +887,9 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq) } } -bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb, - unsigned int opt_size, unsigned int remaining, - struct mptcp_addr_info *addr, bool *echo, - bool *drop_other_suboptions) +bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int opt_size, + unsigned int remaining, + struct mptcp_addr_info *addr, bool *echo) { bool skip_add_addr = false; int ret = false; @@ -908,10 +907,7 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb, * plain dup-ack from TCP perspective. The other MPTCP-relevant info, * if any, will be carried by the 'original' TCP ack */ - if (skb && skb_is_tcp_pure_ack(skb)) { - remaining += opt_size; - *drop_other_suboptions = true; - } + remaining += opt_size; *echo = mptcp_pm_should_add_signal_echo(msk); if (*echo) { @@ -929,9 +925,6 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb, if (remaining < mptcp_add_addr_len(family, *echo, port)) { struct net *net = sock_net((struct sock *)msk); - if (!*drop_other_suboptions) - goto out_unlock; - if (*echo) { MPTCP_INC_STATS(net, MPTCP_MIB_ECHOADDTXDROP); } else { diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index e4f5aba24da7..b93b878478d2 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -1229,10 +1229,9 @@ static inline int mptcp_rm_addr_len(const struct mptcp_rm_list *rm_list) return TCPOLEN_MPTCP_RM_ADDR_BASE + roundup(rm_list->nr - 1, 4) + 1; } -bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb, - unsigned int opt_size, unsigned int remaining, - struct mptcp_addr_info *addr, bool *echo, - bool *drop_other_suboptions); +bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int opt_size, + unsigned int remaining, + struct mptcp_addr_info *addr, bool *echo); bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, struct mptcp_rm_list *rm_list); int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); From b38cae85d1c45ff189d7ecb6ac36f41cdc3d84d0 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 2 Jun 2026 11:21:04 +0200 Subject: [PATCH 65/85] net: airoha: Fix use-after-free in metadata dst teardown airoha_metadata_dst_free() runs metadata_dst_free() which frees the metadata_dst with kfree() immediately, bypassing the RCU grace period. In the RX path, skb_dst_set_noref() sets a non-refcounted pointer from the skb to the metadata_dst. This function requires RCU read-side protection and the dst must remain valid until all RCU readers complete. Since metadata_dst_free() calls kfree() directly, an use-after-free can occur if any skb still holds a noref pointer to the dst when the driver tears it down. Replace metadata_dst_free() with dst_release() which properly goes through the refcount path: when the refcount drops to zero, it schedules the actual free via call_rcu_hurry(), ensuring all RCU readers have completed before the memory is freed. Fixes: af3cf757d5c9 ("net: airoha: Move DSA tag in DMA descriptor") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260602-airoha-mtk-metadata-uaf-fix-v1-1-3aaa99d83351@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/airoha/airoha_eth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index cecd66251dba..eab6a98d62b9 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -2936,7 +2936,7 @@ static void airoha_metadata_dst_free(struct airoha_gdm_port *port) if (!port->dsa_meta[i]) continue; - metadata_dst_free(port->dsa_meta[i]); + dst_release(&port->dsa_meta[i]->dst); } } From 80df409e1a483676826a6c66e693dba6ac507751 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 2 Jun 2026 11:21:05 +0200 Subject: [PATCH 66/85] net: ethernet: mtk_eth_soc: Fix use-after-free in metadata dst teardown mtk_free_dev() calls metadata_dst_free() which frees the metadata_dst with kfree() immediately, bypassing the RCU grace period. In the RX path, skb_dst_set_noref() sets a non-refcounted pointer from the skb to the metadata_dst. This function requires RCU read-side protection and the dst must remain valid until all RCU readers complete. Since metadata_dst_free() calls kfree() directly, a use-after-free can occur if any skb still holds a noref pointer to the dst when the driver tears it down. Replace metadata_dst_free() with dst_release() which properly goes through the refcount path: when the refcount drops to zero, it schedules the actual free via call_rcu_hurry(), ensuring all RCU readers have completed before the memory is freed. Fixes: 2d7605a72906 ("net: ethernet: mtk_eth_soc: enable hardware DSA untagging") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260602-airoha-mtk-metadata-uaf-fix-v1-2-3aaa99d83351@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 8d225bc9f063..7d771168b990 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -4491,7 +4491,7 @@ static int mtk_free_dev(struct mtk_eth *eth) for (i = 0; i < ARRAY_SIZE(eth->dsa_meta); i++) { if (!eth->dsa_meta[i]) break; - metadata_dst_free(eth->dsa_meta[i]); + dst_release(ð->dsa_meta[i]->dst); } return 0; From 1231623fd3b5aa6b41cce799ffb0d82e10914be4 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Fri, 29 May 2026 16:47:00 +0200 Subject: [PATCH 67/85] geneve: fix length used in GRO hint UDP checksum adjustment In geneve_post_decap_hint the length used for adjusting the UDP checksum should be 'skb->len - gro_hint->nested_tp_offset' (UDP length) instead of 'skb->len - gro_hint->nested_nh_offset' (IP length). Fixes: fd0dd796576e ("geneve: use GRO hint option in the RX path") Cc: Paolo Abeni Reported-by: Sashiko Closes: https://sashiko.dev/#/patchset/20260521131436.748832-1-jhs%40mojatatu.com Signed-off-by: Antoine Tenart Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260529144713.780938-1-atenart@kernel.org Signed-off-by: Paolo Abeni --- drivers/net/geneve.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index c6563367d382..715180c3a1b3 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -632,7 +632,7 @@ static int geneve_post_decap_hint(const struct sock *sk, struct sk_buff *skb, uh = udp_hdr(skb); uh->len = htons(skb->len - gro_hint->nested_tp_offset); if (uh->check) { - len = skb->len - gro_hint->nested_nh_offset; + len = skb->len - gro_hint->nested_tp_offset; skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM; if (gro_hint->nested_is_v6) uh->check = ~udp_v6_check(len, &ipv6h->saddr, From a764b0e8317a863006e05732e1aefe821b9d8c2d Mon Sep 17 00:00:00 2001 From: ZhaoJinming Date: Mon, 1 Jun 2026 16:56:49 +0800 Subject: [PATCH 68/85] net: bonding: fix NULL pointer dereference in bond_do_ioctl() In bond_do_ioctl(), slave_dev is obtained via __dev_get_by_name() which can return NULL if the requested interface name does not exist. However, the subsequent slave_dbg() call is placed before the NULL check: slave_dev = __dev_get_by_name(net, ifr->ifr_slave); slave_dbg(bond_dev, slave_dev, "slave_dev=%p:\n", slave_dev); //here if (!slave_dev) return -ENODEV; The slave_dbg() macro expands to netdev_dbg(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ...) which unconditionally dereferences slave_dev->name before the NULL check is performed. This results in a NULL pointer dereference kernel oops when a user calls bonding ioctl (e.g. SIOCBONDENSLAVE, SIOCBONDRELEASE, etc.) with a non-existent slave interface name. This is reachable from userspace via the bonding ioctl interface with CAP_NET_ADMIN capability, making it a potential local denial-of-service vector. Fix by moving the slave_dbg() call after the NULL check. Fixes: e2a7420df2e0 ("bonding/main: convert to using slave printk macros") Cc: stable@vger.kernel.org # v5.2+ Signed-off-by: ZhaoJinming Link: https://patch.msgid.link/20260601085649.4029067-1-zhaojinming@uniontech.com Signed-off-by: Paolo Abeni --- drivers/net/bonding/bond_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 82e779f7916b..8e75453ce0ef 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4621,11 +4621,11 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd slave_dev = __dev_get_by_name(net, ifr->ifr_slave); - slave_dbg(bond_dev, slave_dev, "slave_dev=%p:\n", slave_dev); - if (!slave_dev) return -ENODEV; + slave_dbg(bond_dev, slave_dev, "slave_dev=%p:\n", slave_dev); + switch (cmd) { case SIOCBONDENSLAVE: res = bond_enslave(bond_dev, slave_dev, NULL); From c05fa14db43ebef3bd862ca9d073981c0358b3f0 Mon Sep 17 00:00:00 2001 From: Raf Dickson Date: Tue, 26 May 2026 10:43:56 +0000 Subject: [PATCH 69/85] vsock/vmci: fix sk_ack_backlog leak on failed handshake When vmci_transport_recv_connecting_server() returns an error, vmci_transport_recv_listen() calls vsock_remove_pending() but never calls sk_acceptq_removed(). This leaves sk_ack_backlog incremented permanently. Repeated handshake failures (malformed packets, queue pair alloc failure, event subscribe failure) cause sk_ack_backlog to climb toward sk_max_ack_backlog. Once it reaches the limit the listener permanently refuses all new connections with -ECONNREFUSED, a silent denial of service requiring a process restart to recover. The two existing sk_acceptq_removed() calls in af_vsock.c do not cover this path: line 764 checks vsock_is_pending() which returns false after vsock_remove_pending(), and line 1889 is only reached on successful accept(). Fix by balancing sk_acceptq_added() with sk_acceptq_removed() on the error path. Fixes: d021c344051a ("VSOCK: Introduce VM Sockets") Cc: stable@vger.kernel.org Signed-off-by: Raf Dickson Acked-by: Stefano Garzarella Link: https://patch.msgid.link/20260526104356.469928-1-rafdog35@gmail.com Signed-off-by: Paolo Abeni --- net/vmw_vsock/vmci_transport.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 5c1ecd5bfdbc..91516488a742 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -980,8 +980,10 @@ static int vmci_transport_recv_listen(struct sock *sk, err = -EINVAL; } - if (err < 0) + if (err < 0) { vsock_remove_pending(sk, pending); + sk_acceptq_removed(sk); + } release_sock(pending); vmci_transport_release_pending(pending); From 899ee91156e57784090c5565e4f31bd7dbffbc5a Mon Sep 17 00:00:00 2001 From: Rajat Gupta Date: Sun, 31 May 2026 08:32:21 -0400 Subject: [PATCH 70/85] net/sched: fix pedit partial COW leading to page cache corruption MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit tcf_pedit_act() computes the COW range for skb_ensure_writable() once before the key loop using tcfp_off_max_hint, but the hint does not account for the runtime header offset added by typed keys. This can leave part of the write region un-COW'd. Fix by moving skb_ensure_writable() inside the per-key loop where the actual write offset is known, and add overflow checking on the offset arithmetic. For negative offsets (e.g. Ethernet header edits at ingress), use skb_cow() to COW the headroom instead. Guard offset_valid() against INT_MIN, where negation is undefined. Fixes: 8b796475fd78 ("net/sched: act_pedit: really ensure the skb is writable") Reported-by: Yiming Qian Reported-by: Keenan Dong Reported-by: Han Guidong <2045gemini@gmail.com> Reported-by: Zhang Cen Reviewed-by: Han Guidong <2045gemini@gmail.com> Tested-by: Han Guidong <2045gemini@gmail.com> Reviewed-by: Davide Caratti Tested-by: Davide Caratti Reviewed-by: Toke Høiland-Jørgensen Tested-by: Toke Høiland-Jørgensen Reviewed-by: Victor Nogueira Tested-by: Victor Nogueira Acked-by: Jamal Hadi Salim Signed-off-by: Rajat Gupta Link: https://patch.msgid.link/20260531123221.48732-1-jhs@mojatatu.com Signed-off-by: Jakub Kicinski --- include/net/tc_act/tc_pedit.h | 1 - net/sched/act_pedit.c | 77 +++++++++++++++++++---------------- 2 files changed, 41 insertions(+), 37 deletions(-) diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h index f58ee15cd858..cb7b82f2cbc7 100644 --- a/include/net/tc_act/tc_pedit.h +++ b/include/net/tc_act/tc_pedit.h @@ -15,7 +15,6 @@ struct tcf_pedit_parms { struct tc_pedit_key *tcfp_keys; struct tcf_pedit_key_ex *tcfp_keys_ex; int action; - u32 tcfp_off_max_hint; unsigned char tcfp_nkeys; unsigned char tcfp_flags; struct rcu_head rcu; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index bc20f08a2789..bd3b1da3cd63 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -16,6 +16,8 @@ #include #include #include +#include +#include #include #include #include @@ -242,7 +244,6 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, goto out_free_ex; } - nparms->tcfp_off_max_hint = 0; nparms->tcfp_flags = parm->flags; nparms->tcfp_nkeys = parm->nkeys; @@ -268,14 +269,6 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, BITS_PER_TYPE(int) - 1, nparms->tcfp_keys[i].shift); - /* The AT option can read a single byte, we can bound the actual - * value with uchar max. - */ - cur += (0xff & offmask) >> nparms->tcfp_keys[i].shift; - - /* Each key touches 4 bytes starting from the computed offset */ - nparms->tcfp_off_max_hint = - max(nparms->tcfp_off_max_hint, cur + 4); } p = to_pedit(*a); @@ -318,15 +311,12 @@ static void tcf_pedit_cleanup(struct tc_action *a) call_rcu(&parms->rcu, tcf_pedit_cleanup_rcu); } -static bool offset_valid(struct sk_buff *skb, int offset) +static bool offset_valid(struct sk_buff *skb, int offset, int len) { - if (offset > 0 && offset > skb->len) + if (offset < -(int)skb_headroom(skb)) return false; - if (offset < 0 && -offset > skb_headroom(skb)) - return false; - - return true; + return offset <= (int)skb->len - len; } static int pedit_l4_skb_offset(struct sk_buff *skb, int *hoffset, const int header_type) @@ -393,18 +383,10 @@ TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb, struct tcf_pedit_key_ex *tkey_ex; struct tcf_pedit_parms *parms; struct tc_pedit_key *tkey; - u32 max_offset; int i; parms = rcu_dereference_bh(p->parms); - max_offset = (skb_transport_header_was_set(skb) ? - skb_transport_offset(skb) : - skb_network_offset(skb)) + - parms->tcfp_off_max_hint; - if (skb_ensure_writable(skb, min(skb->len, max_offset))) - goto done; - tcf_lastuse_update(&p->tcf_tm); tcf_action_update_bstats(&p->common, skb); @@ -412,10 +394,11 @@ TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb, tkey_ex = parms->tcfp_keys_ex; for (i = parms->tcfp_nkeys; i > 0; i--, tkey++) { + int write_offset, write_len; int offset = tkey->off; int hoffset = 0; - u32 *ptr, hdata; - u32 val; + u32 cur_val, val; + u32 *ptr; int rc; if (tkey_ex) { @@ -433,13 +416,15 @@ TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb, if (tkey->offmask) { u8 *d, _d; + int at_offset; - if (!offset_valid(skb, hoffset + tkey->at)) { + if (check_add_overflow(hoffset, (int)tkey->at, &at_offset) || + !offset_valid(skb, at_offset, sizeof(_d))) { pr_info_ratelimited("tc action pedit 'at' offset %d out of bounds\n", hoffset + tkey->at); goto bad; } - d = skb_header_pointer(skb, hoffset + tkey->at, + d = skb_header_pointer(skb, at_offset, sizeof(_d), &_d); if (!d) goto bad; @@ -451,31 +436,51 @@ TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb, } } - if (!offset_valid(skb, hoffset + offset)) { - pr_info_ratelimited("tc action pedit offset %d out of bounds\n", hoffset + offset); + if (check_add_overflow(hoffset, offset, &write_offset)) { + pr_info_ratelimited("tc action pedit offset overflow\n"); goto bad; } - ptr = skb_header_pointer(skb, hoffset + offset, - sizeof(hdata), &hdata); - if (!ptr) + if (!offset_valid(skb, write_offset, sizeof(*ptr))) { + pr_info_ratelimited("tc action pedit offset %d out of bounds\n", + write_offset); goto bad; + } + + if (write_offset < 0) { + if (skb_cow(skb, -write_offset)) + goto bad; + if (write_offset + (int)sizeof(*ptr) > 0) { + if (skb_ensure_writable(skb, + min_t(int, skb->len, + write_offset + (int)sizeof(*ptr)))) + goto bad; + } + } else { + if (check_add_overflow(write_offset, (int)sizeof(*ptr), + &write_len)) + goto bad; + if (skb_ensure_writable(skb, min_t(int, skb->len, + write_len))) + goto bad; + } + + ptr = (u32 *)(skb->data + write_offset); + cur_val = get_unaligned(ptr); /* just do it, baby */ switch (cmd) { case TCA_PEDIT_KEY_EX_CMD_SET: val = tkey->val; break; case TCA_PEDIT_KEY_EX_CMD_ADD: - val = (*ptr + tkey->val) & ~tkey->mask; + val = (cur_val + tkey->val) & ~tkey->mask; break; default: pr_info_ratelimited("tc action pedit bad command (%d)\n", cmd); goto bad; } - *ptr = ((*ptr & tkey->mask) ^ val); - if (ptr == &hdata) - skb_store_bits(skb, hoffset + offset, ptr, 4); + put_unaligned((cur_val & tkey->mask) ^ val, ptr); } goto done; From 0861615c28de668669d748ef4eb913ea9262d13b Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 1 Jun 2026 21:06:06 -0400 Subject: [PATCH 71/85] sctp: validate cached peer INIT chunk length in COOKIE_ECHO processing When a listening SCTP server processes a COOKIE_ECHO chunk, the cached peer INIT chunk embedded after the cookie is parsed and its parameters are later walked by sctp_process_init() using sctp_walk_params(). However, the chunk header length of this cached INIT chunk was not validated against the remaining buffer in the COOKIE_ECHO payload. If the length field is inflated, the parameter walk can run beyond the actual received data, leading to out-of-bounds reads and potential memory corruption during later parameter handling (e.g. STATE_COOKIE processing and kmemdup() copies). Add a bounds check in sctp_unpack_cookie() to ensure the cached INIT chunk length does not exceed the available data in the COOKIE_ECHO buffer before it is used. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Brian Geffon Signed-off-by: Xin Long Link: https://patch.msgid.link/eb60825fa22d6f9e663c7d4dbb69f397b5d34d42.1780362366.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski --- net/sctp/sm_make_chunk.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index de86ac088289..85264862fb6b 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1730,6 +1730,7 @@ struct sctp_association *sctp_unpack_cookie( struct sctp_signed_cookie *cookie; struct sk_buff *skb = chunk->skb; struct sctp_cookie *bear_cookie; + struct sctp_chunkhdr *ch; enum sctp_scope scope; unsigned int len; ktime_t kt; @@ -1759,6 +1760,10 @@ struct sctp_association *sctp_unpack_cookie( cookie = chunk->subh.cookie_hdr; bear_cookie = &cookie->c; + ch = (struct sctp_chunkhdr *)(bear_cookie + 1); + if (ntohs(ch->length) > len - fixed_size) + goto malformed; + /* Verify the cookie's MAC, if cookie authentication is enabled. */ if (sctp_sk(ep->base.sk)->cookie_auth_enable) { u8 mac[SHA256_DIGEST_SIZE]; From 1232b3104b4b2c0267f31608fe0f8a8758428f28 Mon Sep 17 00:00:00 2001 From: Zhi Li Date: Tue, 2 Jun 2026 09:45:28 +0800 Subject: [PATCH 72/85] dt-bindings: ethernet: eswin: fix hsp-sp-csr backward compatibility Commit c36069c6f46c ("dt-bindings: ethernet: eswin: add optional TXD and RXD delay register offsets") added two optional cells to eswin,hsp-sp-csr but omitted minItems: 4. As a result, dt-schema implicitly required all 6 cells, which broke backward compatibility with existing 4-cell device trees. Add minItems: 4 to preserve backward compatibility. Fixes: c36069c6f46c ("dt-bindings: ethernet: eswin: add optional TXD and RXD delay register offsets") Reported-by: Sashiko AI Closes: https://lore.kernel.org/all/20260519022334.35742C2BCB7@smtp.kernel.org/ Reviewed-by: Krzysztof Kozlowski Signed-off-by: Zhi Li Link: https://patch.msgid.link/20260602014528.2076-1-lizhi2@eswincomputing.com Signed-off-by: Jakub Kicinski --- Documentation/devicetree/bindings/net/eswin,eic7700-eth.yaml | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/net/eswin,eic7700-eth.yaml b/Documentation/devicetree/bindings/net/eswin,eic7700-eth.yaml index b66ae6300faf..65882ff79d8d 100644 --- a/Documentation/devicetree/bindings/net/eswin,eic7700-eth.yaml +++ b/Documentation/devicetree/bindings/net/eswin,eic7700-eth.yaml @@ -84,7 +84,8 @@ properties: This reference is provided for background information only. $ref: /schemas/types.yaml#/definitions/phandle-array items: - - items: + - minItems: 4 + items: - description: Phandle to HSP(High-Speed Peripheral) device - description: Offset of phy control register for internal or external clock selection From 1d31eb27e570daa04f5373345f9ac98c95863be9 Mon Sep 17 00:00:00 2001 From: Nithin Dabilpuram Date: Tue, 2 Jun 2026 10:28:53 +0530 Subject: [PATCH 73/85] octeontx2-af: npc: Fix CPT channel mask in npc_install_flow Use the CPT-aware NIX channel mask in the npc_install_flow path so that when the host PF installs steering rules in kernel for a VF used from userspace (e.g. DPDK), MCAM entries see the same channel mask semantics as other RX paths. Fixes: 56bcef528bd8 ("octeontx2-af: Use npc_install_flow API for promisc and broadcast entries") Cc: Naveen Mamindlapalli Signed-off-by: Nithin Dabilpuram Signed-off-by: Ratheesh Kannoth Link: https://patch.msgid.link/20260602045853.1558530-1-rkannoth@marvell.com Signed-off-by: Jakub Kicinski --- .../net/ethernet/marvell/octeontx2/af/rvu.h | 1 + .../ethernet/marvell/octeontx2/af/rvu_npc.c | 32 +++++++++---------- .../marvell/octeontx2/af/rvu_npc_fs.c | 2 +- 3 files changed, 18 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index de3fbd3d15d6..65397daae4c2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -1145,6 +1145,7 @@ int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf, int slot); int rvu_cpt_ctx_flush(struct rvu *rvu, u16 pcifunc); int rvu_cpt_init(struct rvu *rvu); +u32 rvu_get_cpt_chan_mask(struct rvu *rvu); #define NDC_AF_BANK_MASK GENMASK_ULL(7, 0) #define NDC_AF_BANK_LINE_MASK GENMASK_ULL(31, 16) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 6bbda0593fcd..d301a3f0f87a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -701,6 +701,19 @@ void npc_set_mcam_action(struct rvu *rvu, struct npc_mcam *mcam, return rvu_write64(rvu, blkaddr, reg, cfg); } +u32 rvu_get_cpt_chan_mask(struct rvu *rvu) +{ + /* For cn10k the upper two bits of the channel number are + * cpt channel number. with masking out these bits in the + * mcam entry, same entry used for NIX will allow packets + * received from cpt for parsing. + */ + if (!is_rvu_otx2(rvu)) + return NIX_CHAN_CPT_X2P_MASK; + else + return 0xFFFu; +} + void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc, int nixlf, u64 chan, u8 *mac_addr) { @@ -750,7 +763,7 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc, eth_broadcast_addr((u8 *)&req.mask.dmac); req.features = BIT_ULL(NPC_DMAC); req.channel = chan; - req.chan_mask = 0xFFFU; + req.chan_mask = rvu_get_cpt_chan_mask(rvu); req.intf = pfvf->nix_rx_intf; req.op = action.op; req.hdr.pcifunc = 0; /* AF is requester */ @@ -845,11 +858,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, * mcam entry, same entry used for NIX will allow packets * received from cpt for parsing. */ - if (!is_rvu_otx2(rvu)) { - req.chan_mask = NIX_CHAN_CPT_X2P_MASK; - } else { - req.chan_mask = 0xFFFU; - } + req.chan_mask = rvu_get_cpt_chan_mask(rvu); if (chan_cnt > 1) { if (!is_power_of_2(chan_cnt)) { @@ -1053,16 +1062,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, ether_addr_copy(req.mask.dmac, mac_addr); req.features = BIT_ULL(NPC_DMAC); - /* For cn10k the upper two bits of the channel number are - * cpt channel number. with masking out these bits in the - * mcam entry, same entry used for NIX will allow packets - * received from cpt for parsing. - */ - if (!is_rvu_otx2(rvu)) - req.chan_mask = NIX_CHAN_CPT_X2P_MASK; - else - req.chan_mask = 0xFFFU; - + req.chan_mask = rvu_get_cpt_chan_mask(rvu); req.channel = chan; req.intf = pfvf->nix_rx_intf; req.entry = index; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c index 6ae9cdcb608b..34f1e066707b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c @@ -1820,7 +1820,7 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu, /* ignore chan_mask in case pf func is not AF, revisit later */ if (!is_pffunc_af(req->hdr.pcifunc)) - req->chan_mask = 0xFFF; + req->chan_mask = rvu_get_cpt_chan_mask(rvu); err = npc_check_unsupported_flows(rvu, req->features, req->intf); if (err) { From ab1ecaabe74b7d86c38ab2ab44bd56cdcc33645a Mon Sep 17 00:00:00 2001 From: Justin Lai Date: Tue, 2 Jun 2026 19:46:59 +0800 Subject: [PATCH 74/85] rtase: Reset TX subqueue when clearing TX ring rtase_tx_clear() clears the TX ring and resets the ring indexes. However, the TX queue state and BQL accounting are not reset at the same time. This may leave __QUEUE_STATE_STACK_XOFF asserted after rtase_sw_reset(), preventing new TX packets from being scheduled. Reset the TX subqueue when clearing the TX ring so the TX queue state and BQL accounting are restored together. Fixes: 5a2a2f15244c ("rtase: Implement the rtase_down function") Cc: stable@vger.kernel.org Signed-off-by: Justin Lai Reviewed-by: Alexander Lobakin Link: https://patch.msgid.link/20260602114659.12335-1-justinlai0215@realtek.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/realtek/rtase/rtase_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c index ef13109c49cf..6ccbefb5acf2 100644 --- a/drivers/net/ethernet/realtek/rtase/rtase_main.c +++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c @@ -239,6 +239,8 @@ static void rtase_tx_clear(struct rtase_private *tp) rtase_tx_clear_range(ring, ring->dirty_idx, RTASE_NUM_DESC); ring->cur_idx = 0; ring->dirty_idx = 0; + + netdev_tx_reset_subqueue(tp->dev, i); } } From aa6ca1c5c338907817374b59f7551fd855a88754 Mon Sep 17 00:00:00 2001 From: Andy Roulin Date: Tue, 2 Jun 2026 11:51:36 -0700 Subject: [PATCH 75/85] vxlan: vnifilter: send notification on VNI add When a new VNI is added to a vxlan device with vnifilter enabled, no RTM_NEWTUNNEL notification is sent to userspace. This means 'bridge monitor vni' never shows VNI add events, even though VNI delete events are reported correctly. The bug is in vxlan_vni_add(), where the notification is guarded by 'if (changed)'. The 'changed' flag is set by vxlan_vni_update_group() only when the multicast group or remote IP is modified, but for a new VNI added without a group (e.g. in L3 VxLAN interface scenarios), the function returns early without setting changed=true. Since this is a new VNI, the notification should be sent unconditionally. The notification is not guarded by the return value of vxlan_vni_update_group() because, at this point, the VNI has already been inserted into the hash table and list with no rollback on error. The VNI will be visible in 'bridge vni show' regardless, so userspace should be informed. This is consistent with vxlan_vni_del() which also notifies unconditionally. The 'if (changed)' guard remains correct in vxlan_vni_update(), which handles the case where a VNI already exists and is being re-added -- there, we only want to notify if the group/remote actually changed. Reproducer: # ip link add vxlan100 type vxlan dstport 4789 local 10.0.0.1 \ nolearning external vnifilter # ip link set vxlan100 up # bridge monitor vni & # bridge vni add vni 1000 dev vxlan100 # no notification # bridge vni delete vni 1000 dev vxlan100 # notification received Fixes: f9c4bb0b245c ("vxlan: vni filtering support on collect metadata device") Reported-by: Chirag Shah Signed-off-by: Andy Roulin Reviewed-by: Petr Machata Link: https://patch.msgid.link/20260602185138.253265-2-aroulin@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/vxlan/vxlan_vnifilter.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c index 2042369379ff..f2a202d46892 100644 --- a/drivers/net/vxlan/vxlan_vnifilter.c +++ b/drivers/net/vxlan/vxlan_vnifilter.c @@ -759,8 +759,7 @@ static int vxlan_vni_add(struct vxlan_dev *vxlan, err = vxlan_vni_update_group(vxlan, vninode, group, true, &changed, extack); - if (changed) - vxlan_vnifilter_notify(vxlan, vninode, RTM_NEWTUNNEL); + vxlan_vnifilter_notify(vxlan, vninode, RTM_NEWTUNNEL); return err; } From 84683b5b60c7274e2c8f7f413d39d78d3db5540f Mon Sep 17 00:00:00 2001 From: Andy Roulin Date: Tue, 2 Jun 2026 11:51:37 -0700 Subject: [PATCH 76/85] vxlan: vnifilter: fix spurious notification on VNI update When a VNI is re-added with the same attributes (e.g. same group or no group), vxlan_vni_update() sends a spurious RTM_NEWTUNNEL notification even though nothing changed. The bug is that 'if (changed)' tests whether the pointer is non-NULL, not the bool value it points to. Since every caller passes a valid pointer, the condition is always true and the notification fires unconditionally. Fix by dereferencing the pointer: 'if (*changed)'. Reproducer: # ip link add vxlan100 type vxlan dstport 4789 local 10.0.0.1 \ nolearning external vnifilter # ip link set vxlan100 up # bridge monitor vni & # bridge vni add vni 1000 dev vxlan100 # bridge vni add vni 1000 dev vxlan100 # spurious notification Fixes: f9c4bb0b245c ("vxlan: vni filtering support on collect metadata device") Signed-off-by: Andy Roulin Reviewed-by: Petr Machata Link: https://patch.msgid.link/20260602185138.253265-3-aroulin@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/vxlan/vxlan_vnifilter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c index f2a202d46892..3e76f4e21094 100644 --- a/drivers/net/vxlan/vxlan_vnifilter.c +++ b/drivers/net/vxlan/vxlan_vnifilter.c @@ -661,7 +661,7 @@ static int vxlan_vni_update(struct vxlan_dev *vxlan, if (ret) return ret; - if (changed) + if (*changed) vxlan_vnifilter_notify(vxlan, vninode, RTM_NEWTUNNEL); return 0; From 8df1c84e7272a5e24b563df7e50111dc81014d4a Mon Sep 17 00:00:00 2001 From: Andy Roulin Date: Tue, 2 Jun 2026 11:51:38 -0700 Subject: [PATCH 77/85] selftests: net: add vxlan vnifilter notification test Add a selftest for VXLAN vnifilter netlink notifications that verifies RTM_NEWTUNNEL and RTM_DELTUNNEL are sent correctly when VNIs are added, deleted, or updated, and that no spurious notifications are sent when a VNI is re-added with the same attributes. Signed-off-by: Andy Roulin Acked-by: Petr Machata Link: https://patch.msgid.link/20260602185138.253265-4-aroulin@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/Makefile | 1 + .../net/test_vxlan_vnifilter_notify.sh | 184 ++++++++++++++++++ 2 files changed, 185 insertions(+) create mode 100755 tools/testing/selftests/net/test_vxlan_vnifilter_notify.sh diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index f3da38c54d27..2ed7d803eb54 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -109,6 +109,7 @@ TEST_PROGS := \ test_vxlan_nh.sh \ test_vxlan_nolocalbypass.sh \ test_vxlan_under_vrf.sh \ + test_vxlan_vnifilter_notify.sh \ test_vxlan_vnifiltering.sh \ tfo_passive.sh \ traceroute.sh \ diff --git a/tools/testing/selftests/net/test_vxlan_vnifilter_notify.sh b/tools/testing/selftests/net/test_vxlan_vnifilter_notify.sh new file mode 100755 index 000000000000..9d51a9e02ae0 --- /dev/null +++ b/tools/testing/selftests/net/test_vxlan_vnifilter_notify.sh @@ -0,0 +1,184 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# shellcheck disable=SC2034,SC2154,SC2317,SC2329 +# +# Test for VXLAN vnifilter netlink notifications (RTM_NEWTUNNEL / +# RTM_DELTUNNEL). +# +# Verifies that: +# - Adding a new VNI sends a notification +# - Adding a new VNI with a remote sends a notification +# - Deleting a VNI sends a notification +# - Re-adding an existing VNI with the same attributes does not send +# a spurious notification +# - Updating an existing VNI's remote sends a notification +# - Deleting a non-existent VNI does not send a notification + +source lib.sh + +require_command bridge + +VXLAN_DEV=vxlan100 + +ALL_TESTS=" + test_vni_add_notify + test_vni_add_remote_notify + test_vni_del_notify + test_vni_readd_no_notify + test_vni_update_remote_notify + test_vni_del_nonexistent_no_notify +" + +setup_prepare() +{ + setup_ns NS1 + defer cleanup_all_ns + + ip -n "$NS1" link add $VXLAN_DEV type vxlan dstport 4789 \ + local 10.0.0.1 nolearning external vnifilter + ip -n "$NS1" link set $VXLAN_DEV up +} + +# Run bridge monitor in the background, execute a command, then count +# the notification lines. +# Usage: vni_notify_check [args...] +# Sets: NOTIFY_COUNT with the number of notifications observed. +vni_notify_check() +{ + local tmpf cmd_ret monitor_pid + + tmpf=$(mktemp) + defer rm "$tmpf" + + defer_scope_push + ip netns exec "$NS1" bridge monitor vni > "$tmpf" 2>/dev/null & + monitor_pid=$! + defer kill_process "$monitor_pid" + + sleep 0.5 + if [ ! -e "/proc/$monitor_pid" ]; then + RET=$ksft_skip + log_test "iproute2 'bridge monitor vni' not supported" + return "$RET" + fi + + "$@" + cmd_ret=$? + sleep 0.2 + defer_scope_pop + + NOTIFY_COUNT=$(grep -c "$VXLAN_DEV" "$tmpf") + NOTIFY_COUNT=${NOTIFY_COUNT:-0} + return "$cmd_ret" +} + +# Adding a brand new VNI should produce a notification. +test_vni_add_notify() +{ + RET=0 + + vni_notify_check \ + bridge -n "$NS1" vni add vni 1000 dev "$VXLAN_DEV" + check_err $? "Failed to add VNI" + + [ "$NOTIFY_COUNT" -eq 1 ] + check_err $? "Expected 1 notification for VNI add, got $NOTIFY_COUNT" + + bridge -n "$NS1" vni delete vni 1000 dev "$VXLAN_DEV" 2>/dev/null + + log_test "VNI add sends notification" +} + +# Adding a VNI with a remote should produce a notification. +test_vni_add_remote_notify() +{ + RET=0 + + vni_notify_check \ + bridge -n "$NS1" vni add vni 4000 remote 10.0.0.2 dev "$VXLAN_DEV" + check_err $? "Failed to add VNI with remote" + + [ "$NOTIFY_COUNT" -eq 1 ] + check_err $? "Expected 1 notification for VNI add with remote, got $NOTIFY_COUNT" + + bridge -n "$NS1" vni delete vni 4000 dev "$VXLAN_DEV" + + log_test "VNI add with remote sends notification" +} + +# Deleting a VNI should produce a notification. +test_vni_del_notify() +{ + RET=0 + + bridge -n "$NS1" vni add vni 2000 dev "$VXLAN_DEV" + + vni_notify_check \ + bridge -n "$NS1" vni delete vni 2000 dev "$VXLAN_DEV" + check_err $? "Failed to delete VNI" + + [ "$NOTIFY_COUNT" -eq 1 ] + check_err $? "Expected 1 notification for VNI del, got $NOTIFY_COUNT" + + log_test "VNI delete sends notification" +} + +# Re-adding an existing VNI with the same attributes should not produce +# a notification. +test_vni_readd_no_notify() +{ + RET=0 + + bridge -n "$NS1" vni add vni 3000 dev "$VXLAN_DEV" + + vni_notify_check \ + bridge -n "$NS1" vni add vni 3000 dev "$VXLAN_DEV" + check_err $? "Failed to re-add VNI" + + [ "$NOTIFY_COUNT" -eq 0 ] + check_err $? "Expected 0 notifications for VNI re-add, got $NOTIFY_COUNT" + + bridge -n "$NS1" vni delete vni 3000 dev "$VXLAN_DEV" + + log_test "VNI re-add does not send spurious notification" +} + +# Updating an existing VNI's remote should produce a notification. +test_vni_update_remote_notify() +{ + RET=0 + + bridge -n "$NS1" vni add vni 5000 remote 10.0.0.2 dev "$VXLAN_DEV" + + vni_notify_check \ + bridge -n "$NS1" vni add vni 5000 remote 10.0.0.3 dev "$VXLAN_DEV" + check_err $? "Failed to update VNI remote" + + [ "$NOTIFY_COUNT" -eq 1 ] + check_err $? "Expected 1 notification for VNI remote update, got $NOTIFY_COUNT" + + bridge -n "$NS1" vni delete vni 5000 dev "$VXLAN_DEV" + + log_test "VNI remote update sends notification" +} + +# Deleting a non-existent VNI should not produce a notification. +test_vni_del_nonexistent_no_notify() +{ + RET=0 + + vni_notify_check \ + bridge -n "$NS1" vni delete vni 9999 dev "$VXLAN_DEV" 2>/dev/null + + [ "$NOTIFY_COUNT" -eq 0 ] + check_err $? "Expected 0 notifications for non-existent VNI del, got $NOTIFY_COUNT" + + log_test "Non-existent VNI delete does not send notification" +} + +trap defer_scopes_cleanup EXIT + +setup_prepare +tests_run + +exit "$EXIT_STATUS" From 791c91dc7a9dfb2457d5e29b8216a6484b9c4b40 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 3 Jun 2026 13:18:11 +0300 Subject: [PATCH 78/85] ipv6: mcast: Fix use-after-free when processing MLD queries When processing an MLD query, a pointer to the multicast group address is retrieved when initially parsing the packet. This pointer is later dereferenced without being reloaded despite the fact that the skb header might have been reallocated following the pskb_may_pull() calls, leading to a use-after-free [1]. Fix by copying the multicast group address when the packet is initially parsed. [1] BUG: KASAN: slab-use-after-free in __mld_query_work (net/ipv6/mcast.c:1512) Read of size 8 at addr ffff8881154b8e90 by task kworker/4:1/118 Workqueue: mld mld_query_work Call Trace: dump_stack_lvl (lib/dump_stack.c:94 lib/dump_stack.c:120) print_address_description.constprop.0 (mm/kasan/report.c:378) print_report (mm/kasan/report.c:482) kasan_report (mm/kasan/report.c:595) __mld_query_work (net/ipv6/mcast.c:1512) mld_query_work (net/ipv6/mcast.c:1563) process_one_work (kernel/workqueue.c:3314) worker_thread (kernel/workqueue.c:3397 kernel/workqueue.c:3478) kthread (kernel/kthread.c:436) ret_from_fork (arch/x86/kernel/process.c:158) ret_from_fork_asm (arch/x86/entry/entry_64.S:245) [...] Freed by task 118: kasan_save_stack (mm/kasan/common.c:57) kasan_save_track (mm/kasan/common.c:78) kasan_save_free_info (mm/kasan/generic.c:584) __kasan_slab_free (mm/kasan/common.c:253 mm/kasan/common.c:285) kfree (./include/linux/kasan.h:235 mm/slub.c:2689 mm/slub.c:6251 mm/slub.c:6566) pskb_expand_head (net/core/skbuff.c:2335) __pskb_pull_tail (net/core/skbuff.c:2878 (discriminator 4)) __mld_query_work (net/ipv6/mcast.c:1495 (discriminator 1)) mld_query_work (net/ipv6/mcast.c:1563) process_one_work (kernel/workqueue.c:3314) worker_thread (kernel/workqueue.c:3397 kernel/workqueue.c:3478) kthread (kernel/kthread.c:436) ret_from_fork (arch/x86/kernel/process.c:158) ret_from_fork_asm (arch/x86/entry/entry_64.S:245) Fixes: 97300b5fdfe2 ("[MCAST] IPv6: Check packet size when process Multicast") Reported-by: Leo Lin Reviewed-by: David Ahern Signed-off-by: Ido Schimmel Reviewed-by: Eric Dumazet Reviewed-by: Jiayuan Chen Link: https://patch.msgid.link/20260603101811.612594-1-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv6/mcast.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 3330adcf26db..d9b855d5191b 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1424,9 +1424,9 @@ void igmp6_event_query(struct sk_buff *skb) static void __mld_query_work(struct sk_buff *skb) { struct mld2_query *mlh2 = NULL; - const struct in6_addr *group; unsigned long max_delay; struct inet6_dev *idev; + struct in6_addr group; struct ifmcaddr6 *ma; struct mld_msg *mld; int group_type; @@ -1458,8 +1458,8 @@ static void __mld_query_work(struct sk_buff *skb) goto kfree_skb; mld = (struct mld_msg *)icmp6_hdr(skb); - group = &mld->mld_mca; - group_type = ipv6_addr_type(group); + group = mld->mld_mca; + group_type = ipv6_addr_type(&group); if (group_type != IPV6_ADDR_ANY && !(group_type&IPV6_ADDR_MULTICAST)) @@ -1509,7 +1509,7 @@ static void __mld_query_work(struct sk_buff *skb) } } else { for_each_mc_mclock(idev, ma) { - if (!ipv6_addr_equal(group, &ma->mca_addr)) + if (!ipv6_addr_equal(&group, &ma->mca_addr)) continue; if (ma->mca_flags & MAF_TIMER_RUNNING) { /* gsquery <- gsquery && mark */ From 3a5f3f7aff18bcc36a57839cf50cf0cc8de707f3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 3 Jun 2026 07:29:55 +0000 Subject: [PATCH 79/85] ieee802154: 6lowpan: only accept IPv6 packets in lowpan_xmit() The aoe driver (or similar) generates a non-IPv6 packet (e.g., ETH_P_AOE) and queues it for transmission via dev_queue_xmit() on a 6LoWPAN interface (configured by the user or test case). Since the packet is not IPv6, the 6LoWPAN header_ops->create function (lowpan_header_create or header_create) returns early without initializing the lowpan_addr_info structure in the skb headroom. In the transmit function (lowpan_xmit), the driver calls lowpan_header (or setup_header) which unconditionally copies and uses the lowpan_addr_info from the headroom, which contains uninitialized data. Fix this by dropping non IPv6 packets. A similar fix is needed in net/bluetooth/6lowpan.c bt_xmit(). Fixes: 4dc315e267fe ("ieee802154: 6lowpan: move transmit functionality") Reported-by: syzbot+f13c19f75e1097abd116@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/6a1fd763.278b5b03.2bcf39.0049.GAE@google.com/T/#u Signed-off-by: Eric Dumazet Reviewed-by: Miquel Raynal Link: https://patch.msgid.link/20260603072955.4032221-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ieee802154/6lowpan/tx.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c index 0c07662b44c0..4df76ff50699 100644 --- a/net/ieee802154/6lowpan/tx.c +++ b/net/ieee802154/6lowpan/tx.c @@ -255,6 +255,11 @@ netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *ldev) pr_debug("package xmit\n"); + if (skb->protocol != htons(ETH_P_IPV6)) { + kfree_skb(skb); + return NET_XMIT_DROP; + } + WARN_ON_ONCE(skb->len > IPV6_MIN_MTU); /* We must take a copy of the skb before we modify/replace the ipv6 From 9fc237f8d49f06d05f0f8e80361047b718894e81 Mon Sep 17 00:00:00 2001 From: Justin Lai Date: Wed, 3 Jun 2026 14:18:16 +0800 Subject: [PATCH 80/85] rtase: Avoid sleeping in get_stats64() The .ndo_get_stats64 callback must not sleep because it can be called when reading /proc/net/dev. rtase_get_stats64() calls rtase_dump_tally_counter(), which polls the tally counter dump bit with read_poll_timeout(). This may sleep while waiting for the hardware counter dump to complete. Use read_poll_timeout_atomic() instead to avoid sleeping in the get_stats64() path. Fixes: 079600489960 ("rtase: Implement net_device_ops") Cc: stable@vger.kernel.org Signed-off-by: Justin Lai Link: https://patch.msgid.link/20260603061816.31356-1-justinlai0215@realtek.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/realtek/rtase/rtase_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c index 6ccbefb5acf2..55105d34bc79 100644 --- a/drivers/net/ethernet/realtek/rtase/rtase_main.c +++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c @@ -1565,8 +1565,9 @@ static void rtase_dump_tally_counter(const struct rtase_private *tp) rtase_w32(tp, RTASE_DTCCR0, cmd); rtase_w32(tp, RTASE_DTCCR0, cmd | RTASE_COUNTER_DUMP); - err = read_poll_timeout(rtase_r32, val, !(val & RTASE_COUNTER_DUMP), - 10, 250, false, tp, RTASE_DTCCR0); + err = read_poll_timeout_atomic(rtase_r32, val, + !(val & RTASE_COUNTER_DUMP), + 10, 250, false, tp, RTASE_DTCCR0); if (err == -ETIMEDOUT) netdev_err(tp->dev, "error occurred in dump tally counter\n"); From 7561c7fbc694308da73300f036719e63e42bf0b4 Mon Sep 17 00:00:00 2001 From: Yizhou Zhao Date: Wed, 3 Jun 2026 14:00:13 +0800 Subject: [PATCH 81/85] net/802/mrp: fix vector attribute parsing in mrp_pdu_parse_vecattr In mrp_pdu_parse_vecattr(), vector attribute events are encoded three per byte and valen tracks the number of events left to process. The parser decrements valen after processing the first and second events from each event byte, but not after processing the third one. When valen is exactly a multiple of three, the loop continues after the last valid event and consumes the next byte as a new event byte, applying a spurious event to the MRP applicant state. Additionally, when valen is zero the parser unconditionally consumes attrlen bytes as FirstValue and advances the offset, even though per IEEE 802.1ak a VectorAttribute with only a LeaveAllEvent has valen of zero and no FirstValue or Vector fields. This corrupts the offset for subsequent PDU parsing. Also, when valen exceeds three the loop crosses byte boundaries but the attribute value is not incremented between the last event of one byte and the first event of the next. This causes the first event of the next byte to use the same attribute value as the third event rather than the next consecutive value. Decrement valen after processing the third event, skip FirstValue consumption when valen is zero, and increment the attribute value at the end of each loop iteration. Fixes: febf018d2234 ("net/802: Implement Multiple Registration Protocol (MRP)") Reported-by: Yizhou Zhao Reported-by: Yuxiang Yang Reported-by: Ao Wang Reported-by: Xuewei Feng Reported-by: Qi Li Reported-by: Ke Xu Signed-off-by: Yizhou Zhao Link: https://patch.msgid.link/20260603060016.21522-1-zhaoyz24@mails.tsinghua.edu.cn Signed-off-by: Jakub Kicinski --- net/802/mrp.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/net/802/mrp.c b/net/802/mrp.c index ff0e80574e6b..160a3b14569c 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -703,6 +703,12 @@ static int mrp_pdu_parse_vecattr(struct mrp_applicant *app, valen = be16_to_cpu(get_unaligned(&mrp_cb(skb)->vah->lenflags) & MRP_VECATTR_HDR_LEN_MASK); + /* If valen is 0, only a LeaveAllEvent is present; FirstValue and + * Vector fields are absent per IEEE 802.1ak. + */ + if (valen == 0) + return 0; + /* The VectorAttribute structure in a PDU carries event information * about one or more attributes having consecutive values. Only the * value for the first attribute is contained in the structure. So @@ -753,6 +759,9 @@ static int mrp_pdu_parse_vecattr(struct mrp_applicant *app, vaevents %= __MRP_VECATTR_EVENT_MAX; vaevent = vaevents; mrp_pdu_parse_vecattr_event(app, skb, vaevent); + valen--; + mrp_attrvalue_inc(mrp_cb(skb)->attrvalue, + mrp_cb(skb)->mh->attrlen); } return 0; } From b47ff80f280e18ad2310f44293cc057d9b64ff11 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 3 Jun 2026 12:35:14 +0000 Subject: [PATCH 82/85] bonding: annotate data-races arcound churn variables These fields are updated asynchronously by the bonding state machine in ad_churn_machine() while holding bond->mode_lock. bond_info_show_slave() and bond_fill_slave_info() read them without bond->mode_lock being held, we need to add READ_ONCE() and WRITE_ONCE() annotations. Note that AD_CHURN_MONITOR, AD_CHURN, and AD_NO_CHURN are defined exclusively in (kernel private) include/net/bond_3ad.h header. They should be moved to include/uapi/linux/if_bonding.h or userspace tools will have to hardcode their values. Fixes: 4916f2e2f3fc ("bonding: print churn state via netlink") Fixes: 14c9551a32eb ("bonding: Implement port churn-machine (AD standard 43.4.17).") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260603123514.388226-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- drivers/net/bonding/bond_3ad.c | 18 ++++++++++-------- drivers/net/bonding/bond_netlink.c | 4 ++-- drivers/net/bonding/bond_procfs.c | 8 ++++---- 3 files changed, 16 insertions(+), 14 deletions(-) diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index f0aa7d2f2171..985ef66dc333 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -1386,8 +1386,8 @@ static void ad_churn_machine(struct port *port) { if (port->sm_vars & AD_PORT_CHURNED) { port->sm_vars &= ~AD_PORT_CHURNED; - port->sm_churn_actor_state = AD_CHURN_MONITOR; - port->sm_churn_partner_state = AD_CHURN_MONITOR; + WRITE_ONCE(port->sm_churn_actor_state, AD_CHURN_MONITOR); + WRITE_ONCE(port->sm_churn_partner_state, AD_CHURN_MONITOR); port->sm_churn_actor_timer_counter = __ad_timer_to_ticks(AD_ACTOR_CHURN_TIMER, 0); port->sm_churn_partner_timer_counter = @@ -1398,20 +1398,22 @@ static void ad_churn_machine(struct port *port) !(--port->sm_churn_actor_timer_counter) && port->sm_churn_actor_state == AD_CHURN_MONITOR) { if (port->actor_oper_port_state & LACP_STATE_SYNCHRONIZATION) { - port->sm_churn_actor_state = AD_NO_CHURN; + WRITE_ONCE(port->sm_churn_actor_state, AD_NO_CHURN); } else { - port->churn_actor_count++; - port->sm_churn_actor_state = AD_CHURN; + WRITE_ONCE(port->churn_actor_count, + port->churn_actor_count + 1); + WRITE_ONCE(port->sm_churn_actor_state, AD_CHURN); } } if (port->sm_churn_partner_timer_counter && !(--port->sm_churn_partner_timer_counter) && port->sm_churn_partner_state == AD_CHURN_MONITOR) { if (port->partner_oper.port_state & LACP_STATE_SYNCHRONIZATION) { - port->sm_churn_partner_state = AD_NO_CHURN; + WRITE_ONCE(port->sm_churn_partner_state, AD_NO_CHURN); } else { - port->churn_partner_count++; - port->sm_churn_partner_state = AD_CHURN; + WRITE_ONCE(port->churn_partner_count, + port->churn_partner_count + 1); + WRITE_ONCE(port->sm_churn_partner_state, AD_CHURN); } } } diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index c7d3e0602c83..90365d3f7ebf 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -82,10 +82,10 @@ static int bond_fill_slave_info(struct sk_buff *skb, goto nla_put_failure_rcu; if (nla_put_u8(skb, IFLA_BOND_SLAVE_AD_CHURN_ACTOR_STATE, - ad_port->sm_churn_actor_state)) + READ_ONCE(ad_port->sm_churn_actor_state))) goto nla_put_failure_rcu; if (nla_put_u8(skb, IFLA_BOND_SLAVE_AD_CHURN_PARTNER_STATE, - ad_port->sm_churn_partner_state)) + READ_ONCE(ad_port->sm_churn_partner_state))) goto nla_put_failure_rcu; } rcu_read_unlock(); diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index 3714aab1a3d9..3607b62f9b63 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -221,13 +221,13 @@ static void bond_info_show_slave(struct seq_file *seq, seq_printf(seq, "Aggregator ID: %d\n", agg->aggregator_identifier); seq_printf(seq, "Actor Churn State: %s\n", - bond_3ad_churn_desc(port->sm_churn_actor_state)); + bond_3ad_churn_desc(READ_ONCE(port->sm_churn_actor_state))); seq_printf(seq, "Partner Churn State: %s\n", - bond_3ad_churn_desc(port->sm_churn_partner_state)); + bond_3ad_churn_desc(READ_ONCE(port->sm_churn_partner_state))); seq_printf(seq, "Actor Churned Count: %d\n", - port->churn_actor_count); + READ_ONCE(port->churn_actor_count)); seq_printf(seq, "Partner Churned Count: %d\n", - port->churn_partner_count); + READ_ONCE(port->churn_partner_count)); if (capable(CAP_NET_ADMIN)) { seq_puts(seq, "details actor lacp pdu:\n"); From e374b22e9b07b72a25909621464ff74096151bfb Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 3 Jun 2026 14:11:44 -0400 Subject: [PATCH 83/85] sctp: purge outqueue on stale COOKIE-ECHO handling sctp_stream_update() is only invoked when the association is moved into COOKIE_WAIT during association setup/reconfiguration. In this path, the outbound stream scheduler state (stream->out_curr) is expected to be clean, since no user data should have been transmitted yet unless the state machine has already partially progressed. However, a corner case exists in sctp_sf_do_5_2_6_stale(): when a Stale Cookie ERROR is received, the association is rolled back from COOKIE_ECHOED to COOKIE_WAIT. In this scenario, user data may already have been queued and even bundled with the COOKIE-ECHO chunk. During the rollback, sctp_stream_update() frees the old stream table and installs a new one, but it does not invalidate stream->out_curr. As a result, out_curr may still point to a freed sctp_stream_out entry from the previous stream state. Later, SCTP scheduler dequeue paths (FCFS, RR, PRIO, etc.) rely on stream->out_curr->ext, which can lead to use-after-free once the old stream state has been released via sctp_stream_free(). This results in crashes such as (reported by Yuqi): BUG: KASAN: slab-use-after-free in sctp_sched_fcfs_dequeue+0x13a/0x140 Read of size 8 at addr ff1100004d4d3208 by task mini_poc/9312 CPU: 1 UID: 1001 PID: 9312 Comm: mini_poc Not tainted 7.1.0-rc1-00305-gbd3a4795d574 #5 PREEMPT(full) sctp_sched_fcfs_dequeue+0x13a/0x140 sctp_outq_flush+0x1603/0x33e0 sctp_do_sm+0x31c9/0x5d30 sctp_assoc_bh_rcv+0x392/0x6f0 sctp_inq_push+0x1db/0x270 sctp_rcv+0x138d/0x3c10 Fix this by fully purging the association outqueue when handling the Stale Cookie case. This ensures all pending transmit and retransmit state is dropped, and any scheduler cached pointers are invalidated, making it safe to rebuild stream state during COOKIE_WAIT restart. Updating only stream->out_curr would be insufficient, since queued and retransmittable data would still reference the old stream state and trigger later use-after-free in dequeue paths. Fixes: 5bbbbe32a431 ("sctp: introduce stream scheduler foundations") Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Zhengchuan Liang Reported-by: Xin Liu Reported-by: Yuqi Xu Reported-by: Ren Wei Signed-off-by: Xin Long Link: https://patch.msgid.link/94318159b9052907a6cbb7256aee8b5f8dfbfccb.1780510304.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski --- net/sctp/sm_statefuns.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 8e89a870780c..9b23c11cbb9e 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -2598,11 +2598,7 @@ static enum sctp_disposition sctp_sf_do_5_2_6_stale( */ sctp_add_cmd_sf(commands, SCTP_CMD_DEL_NON_PRIMARY, SCTP_NULL()); - /* If we've sent any data bundled with COOKIE-ECHO we will need to - * resend - */ - sctp_add_cmd_sf(commands, SCTP_CMD_T1_RETRAN, - SCTP_TRANSPORT(asoc->peer.primary_path)); + sctp_add_cmd_sf(commands, SCTP_CMD_PURGE_OUTQUEUE, SCTP_NULL()); /* Cast away the const modifier, as we want to just * rerun it through as a sideffect. From 3c94f241f776562c489876ff506f366224565c21 Mon Sep 17 00:00:00 2001 From: Sechang Lim Date: Wed, 3 Jun 2026 16:27:33 +0000 Subject: [PATCH 84/85] udp: clear skb->dev before running a sockmap verdict On the UDP receive path skb->dev is repurposed as dev_scratch (the truesize/state cache set by udp_set_dev_scratch()), through the union { struct net_device *dev; unsigned long dev_scratch; } in sk_buff. When a UDP socket is in a sockmap, sk_data_ready is sk_psock_verdict_data_ready(), which calls udp_read_skb() -> recv_actor() (sk_psock_verdict_recv) to run the attached SK_SKB verdict program in softirq. If that program calls a socket-lookup helper (bpf_sk_lookup_tcp/udp, bpf_skc_lookup_tcp), bpf_skc_lookup() does: if (skb->dev) caller_net = dev_net(skb->dev); skb->dev still holds the dev_scratch value (a non-NULL integer), so dev_net() dereferences it as a struct net_device * and the kernel takes a general protection fault on a non-canonical address in softirq: Oops: general protection fault, probably for non-canonical address 0x1010000800004a0 CPU: 1 UID: 0 PID: 1406 Comm: syz.2.19 Not tainted 7.1.0-rc6 #1 PREEMPT(full) RIP: 0010:bpf_skc_lookup net/core/filter.c:7033 [inline] RIP: 0010:bpf_sk_lookup+0x45/0x160 net/core/filter.c:7047 Call Trace: bpf_prog_4675cb904b7071f8+0x12e/0x14e bpf_prog_run_pin_on_cpu+0xc6/0x1f0 sk_psock_verdict_recv+0x1ba/0x350 udp_read_skb+0x31a/0x370 sk_psock_verdict_data_ready+0x2e3/0x600 __udp_enqueue_schedule_skb+0x4c8/0x650 udpv6_queue_rcv_one_skb+0x3ec/0x740 udp6_unicast_rcv_skb+0x11d/0x140 ip6_protocol_deliver_rcu+0x61e/0x950 ip6_input_finish+0xa9/0x150 NF_HOOK+0x286/0x2f0 ip6_input+0x117/0x220 NF_HOOK+0x286/0x2f0 __netif_receive_skb+0x85/0x200 process_backlog+0x374/0x9a0 __napi_poll+0x4f/0x1c0 net_rx_action+0x3b0/0x770 handle_softirqs+0x15a/0x460 do_softirq+0x57/0x80 The rmem charge that dev_scratch accounted for is released by skb_recv_udp() on dequeue, just above, so the scratch is dead by the time recv_actor() runs. Clear skb->dev so bpf_skc_lookup() falls back to sock_net(skb->sk), which skb_set_owner_sk_safe() set just above. Fixes: 965b57b469a5 ("net: Introduce a new proto_ops ->read_skb()") Cc: stable@vger.kernel.org Signed-off-by: Sechang Lim Reviewed-by: Jiayuan Chen Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260603162737.697215-1-rhkrqnwk98@gmail.com Signed-off-by: Jakub Kicinski --- net/ipv4/udp.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 0ac2bf4f8759..70f6cbd4ef73 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2011,6 +2011,14 @@ int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) } WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); + + /* + * skb->dev still aliases the UDP rx dev_scratch (its charge was freed + * on dequeue above); a sockmap verdict program may deref it via + * bpf_sk_lookup_*(), so clear it -> bpf_skc_lookup() uses skb->sk + */ + skb->dev = NULL; + return recv_actor(sk, skb); } From b6197b386677ae5268d4702e23849d9ad53051ad Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 3 Jun 2026 12:58:45 -0700 Subject: [PATCH 85/85] Reapply "bnxt_en: bring back rtnl_lock() in the bnxt_open() path" This reverts commit 850d9248d2eac662f869c766a598c877690c74e5. This reapplies commit 325eb217e41f ("bnxt_en: bring back rtnl_lock() in the bnxt_open() path"). Breno reports a lockdep warning in bnxt. During FW reset the driver may end up calling netif_set_real_num_tx_queues() (if queue count changes), so calls to bnxt_open() still require rtnl_lock. net/sched/sch_generic.c:1416 suspicious rcu_dereference_protected() usage! dev_qdisc_change_real_num_tx+0x54/0xe0 netif_set_real_num_tx_queues+0x4ed/0xa80 __bnxt_open_nic+0x9cb/0x3490 bnxt_open+0x1cb/0x370 bnxt_fw_reset_task+0x80d/0x1e80 process_scheduled_works+0x9c1/0x13b0 The reverted commit was just an optimization / experiment so let's go back to taking the lock. Reported-by: Breno Leitao Link: https://lore.kernel.org/ah726OtFX-Qw3U-R@gmail.com Fixes: 850d9248d2ea ("Revert "bnxt_en: bring back rtnl_lock() in the bnxt_open() path"") Acked-by: Stanislav Fomichev Reviewed-by: Michael Chan Reviewed-by: Breno Leitao Link: https://patch.msgid.link/20260603195845.2574426-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 36 ++++++++++++++++++----- 1 file changed, 29 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 008c34cff7b4..35e1f8f663c7 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -14388,13 +14388,28 @@ static void bnxt_unlock_sp(struct bnxt *bp) netdev_unlock(bp->dev); } +/* Same as bnxt_lock_sp() with additional rtnl_lock */ +static void bnxt_rtnl_lock_sp(struct bnxt *bp) +{ + clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state); + rtnl_lock(); + netdev_lock(bp->dev); +} + +static void bnxt_rtnl_unlock_sp(struct bnxt *bp) +{ + set_bit(BNXT_STATE_IN_SP_TASK, &bp->state); + netdev_unlock(bp->dev); + rtnl_unlock(); +} + /* Only called from bnxt_sp_task() */ static void bnxt_reset(struct bnxt *bp, bool silent) { - bnxt_lock_sp(bp); + bnxt_rtnl_lock_sp(bp); if (test_bit(BNXT_STATE_OPEN, &bp->state)) bnxt_reset_task(bp, silent); - bnxt_unlock_sp(bp); + bnxt_rtnl_unlock_sp(bp); } /* Only called from bnxt_sp_task() */ @@ -14402,9 +14417,9 @@ static void bnxt_rx_ring_reset(struct bnxt *bp) { int i; - bnxt_lock_sp(bp); + bnxt_rtnl_lock_sp(bp); if (!test_bit(BNXT_STATE_OPEN, &bp->state)) { - bnxt_unlock_sp(bp); + bnxt_rtnl_unlock_sp(bp); return; } /* Disable and flush TPA before resetting the RX ring */ @@ -14443,7 +14458,7 @@ static void bnxt_rx_ring_reset(struct bnxt *bp) } if (bp->flags & BNXT_FLAG_TPA) bnxt_set_tpa(bp, true); - bnxt_unlock_sp(bp); + bnxt_rtnl_unlock_sp(bp); } static void bnxt_fw_fatal_close(struct bnxt *bp) @@ -15358,15 +15373,17 @@ static void bnxt_fw_reset_task(struct work_struct *work) bp->fw_reset_state = BNXT_FW_RESET_STATE_OPENING; fallthrough; case BNXT_FW_RESET_STATE_OPENING: - while (!netdev_trylock(bp->dev)) { + while (!rtnl_trylock()) { bnxt_queue_fw_reset_work(bp, HZ / 10); return; } + netdev_lock(bp->dev); rc = bnxt_open(bp->dev); if (rc) { netdev_err(bp->dev, "bnxt_open() failed during FW reset\n"); bnxt_fw_reset_abort(bp, rc); netdev_unlock(bp->dev); + rtnl_unlock(); goto ulp_start; } @@ -15386,6 +15403,7 @@ static void bnxt_fw_reset_task(struct work_struct *work) bnxt_dl_health_fw_status_update(bp, true); } netdev_unlock(bp->dev); + rtnl_unlock(); bnxt_ulp_start(bp); bnxt_reenable_sriov(bp); netdev_lock(bp->dev); @@ -16379,7 +16397,7 @@ static int bnxt_queue_start(struct net_device *dev, rc); napi_enable_locked(&bnapi->napi); bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons); - bnxt_reset_task(bp, true); + netif_close(dev); return rc; } @@ -17230,6 +17248,7 @@ static int bnxt_resume(struct device *device) struct bnxt *bp = netdev_priv(dev); int rc = 0; + rtnl_lock(); netdev_lock(dev); rc = pci_enable_device(bp->pdev); if (rc) { @@ -17274,6 +17293,7 @@ static int bnxt_resume(struct device *device) resume_exit: netdev_unlock(bp->dev); + rtnl_unlock(); if (!rc) { bnxt_ulp_start(bp); bnxt_reenable_sriov(bp); @@ -17445,6 +17465,7 @@ static void bnxt_io_resume(struct pci_dev *pdev) int err; netdev_info(bp->dev, "PCI Slot Resume\n"); + rtnl_lock(); netdev_lock(netdev); err = bnxt_hwrm_func_qcaps(bp); @@ -17462,6 +17483,7 @@ static void bnxt_io_resume(struct pci_dev *pdev) netif_device_attach(netdev); netdev_unlock(netdev); + rtnl_unlock(); if (!err) { bnxt_ulp_start(bp); bnxt_reenable_sriov(bp);