From ccba9f6baa900e31ad1a4c36e6f3c176694f9eac Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 8 Aug 2025 17:12:04 -0700 Subject: net: update NAPI threaded config even for disabled NAPIs We have to make sure that all future NAPIs will have the right threaded state when the state is configured on the device level. We chose not to have an "unset" state for threaded, and not to wipe the NAPI config clean when channels are explicitly disabled. This means the persistent config structs "exist" even when their NAPIs are not instantiated. Differently put - the NAPI persistent state lives in the net_device (ncfg == struct napi_config): ,--- [napi 0] - [napi 1] [dev] | | `--- [ncfg 0] - [ncfg 1] so say we a device with 2 queues but only 1 enabled: ,--- [napi 0] [dev] | `--- [ncfg 0] - [ncfg 1] now we set the device to threaded=1: ,---------- [napi 0 (thr:1)] [dev(thr:1)] | `---------- [ncfg 0 (thr:1)] - [ncfg 1 (thr:?)] Since [ncfg 1] was not attached to a NAPI during configuration we skipped it. If we create a NAPI for it later it will have the old setting (presumably disabled). One could argue if this is right or not "in principle", but it's definitely not how things worked before per-NAPI config.. Fixes: 2677010e7793 ("Add support to set NAPI threaded for individual NAPI") Signed-off-by: Jakub Kicinski Reviewed-by: Joe Damato Link: https://patch.msgid.link/20250809001205.1147153-3-kuba@kernel.org Signed-off-by: Paolo Abeni --- net/core/dev.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 68dc47d7e700..f180746382a1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6999,7 +6999,7 @@ int netif_set_threaded(struct net_device *dev, enum netdev_napi_threaded threaded) { struct napi_struct *napi; - int err = 0; + int i, err = 0; netdev_assert_locked_or_invisible(dev); @@ -7021,6 +7021,10 @@ int netif_set_threaded(struct net_device *dev, list_for_each_entry(napi, &dev->napi_list, dev_list) WARN_ON_ONCE(napi_set_threaded(napi, threaded)); + /* Override the config for all NAPIs even if currently not listed */ + for (i = 0; i < dev->num_napi_configs; i++) + dev->napi_config[i].threaded = threaded; + return err; } @@ -11873,6 +11877,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, goto free_all; dev->cfg_pending = dev->cfg; + dev->num_napi_configs = maxqs; napi_config_sz = array_size(maxqs, sizeof(*dev->napi_config)); dev->napi_config = kvzalloc(napi_config_sz, GFP_KERNEL_ACCOUNT); if (!dev->napi_config) -- cgit From b3fc08ab9a565efb42fe08be046a0d203b82cdb8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 8 Aug 2025 17:12:05 -0700 Subject: net: prevent deadlocks when enabling NAPIs with mixed kthread config The following order of calls currently deadlocks if: - device has threaded=1; and - NAPI has persistent config with threaded=0. netif_napi_add_weight_config() dev->threaded == 1 napi_kthread_create() napi_enable() napi_restore_config() napi_set_threaded(0) napi_stop_kthread() while (NAPIF_STATE_SCHED) msleep(20) We deadlock because disabled NAPI has STATE_SCHED set. Creating a thread in netif_napi_add() just to destroy it in napi_disable() is fairly ugly in the first place. Let's read both the device config and the NAPI config in netif_napi_add(). Fixes: e6d76268813d ("net: Update threaded state in napi config in netif_set_threaded") Signed-off-by: Jakub Kicinski Reviewed-by: Joe Damato Link: https://patch.msgid.link/20250809001205.1147153-4-kuba@kernel.org Signed-off-by: Paolo Abeni --- net/core/dev.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index f180746382a1..5a3c0f40a93f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7357,8 +7357,9 @@ void netif_napi_add_weight_locked(struct net_device *dev, * Clear dev->threaded if kthread creation failed so that * threaded mode will not be enabled in napi_enable(). */ - if (dev->threaded && napi_kthread_create(napi)) - dev->threaded = NETDEV_NAPI_THREADED_DISABLED; + if (napi_get_threaded_config(dev, napi)) + if (napi_kthread_create(napi)) + dev->threaded = NETDEV_NAPI_THREADED_DISABLED; netif_napi_set_irq_locked(napi, -1); } EXPORT_SYMBOL(netif_napi_add_weight_locked); -- cgit From 864e3396976ef41de6cc7bc366276bf4e084fff2 Mon Sep 17 00:00:00 2001 From: Jakub Ramaseuski Date: Thu, 14 Aug 2025 12:51:19 +0200 Subject: net: gso: Forbid IPv6 TSO with extensions on devices with only IPV6_CSUM When performing Generic Segmentation Offload (GSO) on an IPv6 packet that contains extension headers, the kernel incorrectly requests checksum offload if the egress device only advertises NETIF_F_IPV6_CSUM feature, which has a strict contract: it supports checksum offload only for plain TCP or UDP over IPv6 and explicitly does not support packets with extension headers. The current GSO logic violates this contract by failing to disable the feature for packets with extension headers, such as those used in GREoIPv6 tunnels. This violation results in the device being asked to perform an operation it cannot support, leading to a `skb_warn_bad_offload` warning and a collapse of network throughput. While device TSO/USO is correctly bypassed in favor of software GSO for these packets, the GSO stack must be explicitly told not to request checksum offload. Mask NETIF_F_IPV6_CSUM, NETIF_F_TSO6 and NETIF_F_GSO_UDP_L4 in gso_features_check if the IPv6 header contains extension headers to compute checksum in software. The exception is a BIG TCP extension, which, as stated in commit 68e068cabd2c6c53 ("net: reenable NETIF_F_IPV6_CSUM offload for BIG TCP packets"): "The feature is only enabled on devices that support BIG TCP TSO. The header is only present for PF_PACKET taps like tcpdump, and not transmitted by physical devices." kernel log output (truncated): WARNING: CPU: 1 PID: 5273 at net/core/dev.c:3535 skb_warn_bad_offload+0x81/0x140 ... Call Trace: skb_checksum_help+0x12a/0x1f0 validate_xmit_skb+0x1a3/0x2d0 validate_xmit_skb_list+0x4f/0x80 sch_direct_xmit+0x1a2/0x380 __dev_xmit_skb+0x242/0x670 __dev_queue_xmit+0x3fc/0x7f0 ip6_finish_output2+0x25e/0x5d0 ip6_finish_output+0x1fc/0x3f0 ip6_tnl_xmit+0x608/0xc00 [ip6_tunnel] ip6gre_tunnel_xmit+0x1c0/0x390 [ip6_gre] dev_hard_start_xmit+0x63/0x1c0 __dev_queue_xmit+0x6d0/0x7f0 ip6_finish_output2+0x214/0x5d0 ip6_finish_output+0x1fc/0x3f0 ip6_xmit+0x2ca/0x6f0 ip6_finish_output+0x1fc/0x3f0 ip6_xmit+0x2ca/0x6f0 inet6_csk_xmit+0xeb/0x150 __tcp_transmit_skb+0x555/0xa80 tcp_write_xmit+0x32a/0xe90 tcp_sendmsg_locked+0x437/0x1110 tcp_sendmsg+0x2f/0x50 ... skb linear: 00000000: e4 3d 1a 7d ec 30 e4 3d 1a 7e 5d 90 86 dd 60 0e skb linear: 00000010: 00 0a 1b 34 3c 40 20 11 00 00 00 00 00 00 00 00 skb linear: 00000020: 00 00 00 00 00 12 20 11 00 00 00 00 00 00 00 00 skb linear: 00000030: 00 00 00 00 00 11 2f 00 04 01 04 01 01 00 00 00 skb linear: 00000040: 86 dd 60 0e 00 0a 1b 00 06 40 20 23 00 00 00 00 skb linear: 00000050: 00 00 00 00 00 00 00 00 00 12 20 23 00 00 00 00 skb linear: 00000060: 00 00 00 00 00 00 00 00 00 11 bf 96 14 51 13 f9 skb linear: 00000070: ae 27 a0 a8 2b e3 80 18 00 40 5b 6f 00 00 01 01 skb linear: 00000080: 08 0a 42 d4 50 d5 4b 70 f8 1a Fixes: 04c20a9356f283da ("net: skip offload for NETIF_F_IPV6_CSUM if ipv6 header contains extension") Reported-by: Tianhao Zhao Suggested-by: Michal Schmidt Suggested-by: Willem de Bruijn Signed-off-by: Jakub Ramaseuski Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20250814105119.1525687-1-jramaseu@redhat.com Signed-off-by: Jakub Kicinski --- net/core/dev.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 5a3c0f40a93f..93a25d87b86b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3779,6 +3779,18 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb, features &= ~NETIF_F_TSO_MANGLEID; } + /* NETIF_F_IPV6_CSUM does not support IPv6 extension headers, + * so neither does TSO that depends on it. + */ + if (features & NETIF_F_IPV6_CSUM && + (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6 || + (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && + vlan_get_protocol(skb) == htons(ETH_P_IPV6))) && + skb_transport_header_was_set(skb) && + skb_network_header_len(skb) != sizeof(struct ipv6hdr) && + !ipv6_has_hopopt_jumbo(skb)) + features &= ~(NETIF_F_IPV6_CSUM | NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4); + return features; } -- cgit