From 28098defc79fe7d29e6bfe4eb6312991f6bdc3d3 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Fri, 17 Oct 2025 03:41:52 +0000 Subject: net: add a common function to compute features for upper devices Some high level software drivers need to compute features from lower devices. But each has their own implementations and may lost some feature compute. Let's use one common function to compute features for kinds of these devices. The new helper uses the current bond implementation as the reference one, as the latter already handles all the relevant aspects: netdev features, TSO limits and dst retention. Suggested-by: Paolo Abeni Signed-off-by: Hangbin Liu Reviewed-by: Sabrina Dubroca Reviewed-by: Jiri Pirko Link: https://patch.msgid.link/20251017034155.61990-2-liuhangbin@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d1a687444b27..7f5aad5cc9a1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -5304,6 +5304,7 @@ static inline netdev_features_t netdev_add_tso_features(netdev_features_t featur int __netdev_update_features(struct net_device *dev); void netdev_update_features(struct net_device *dev); void netdev_change_features(struct net_device *dev); +void netdev_compute_master_upper_features(struct net_device *dev, bool update_header); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); -- cgit v1.2.3 From c72568c21b97dbc48d02b769f4eec6667ad13d5a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 24 Oct 2025 09:12:40 +0000 Subject: net: rps: softnet_data reorg to make enqueue_to_backlog() fast enqueue_to_backlog() is showing up in kernel profiles on hosts with many cores, when RFS/RPS is used. The following softnet_data fields need to be updated: - input_queue_tail - input_pkt_queue (next, prev, qlen, lock) - backlog.state (if input_pkt_queue was empty) Unfortunately they are currenly using two cache lines: /* --- cacheline 3 boundary (192 bytes) --- */ call_single_data_t csd __attribute__((__aligned__(64))); /* 0xc0 0x20 */ struct softnet_data * rps_ipi_next; /* 0xe0 0x8 */ unsigned int cpu; /* 0xe8 0x4 */ unsigned int input_queue_tail; /* 0xec 0x4 */ struct sk_buff_head input_pkt_queue; /* 0xf0 0x18 */ /* --- cacheline 4 boundary (256 bytes) was 8 bytes ago --- */ struct napi_struct backlog __attribute__((__aligned__(8))); /* 0x108 0x1f0 */ Add one ____cacheline_aligned_in_smp to make sure they now are using a single cache line. Also, because napi_struct has written fields, make @state its first field. We want to make sure that cpus adding packets to sd->input_pkt_queue are not slowing down cpus processing their backlog because of false sharing. After this patch new layout is: /* --- cacheline 5 boundary (320 bytes) --- */ long int pad[3] __attribute__((__aligned__(64))); /* 0x140 0x18 */ unsigned int input_queue_tail; /* 0x158 0x4 */ /* XXX 4 bytes hole, try to pack */ struct sk_buff_head input_pkt_queue; /* 0x160 0x18 */ struct napi_struct backlog __attribute__((__aligned__(8))); /* 0x178 0x1f0 */ Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20251024091240.3292546-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7f5aad5cc9a1..9c1e5042c5e7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -377,6 +377,8 @@ struct napi_config { * Structure for NAPI scheduling similar to tasklet but with weighting */ struct napi_struct { + /* This field should be first or softnet_data.backlog needs tweaks. */ + unsigned long state; /* The poll_list must only be managed by the entity which * changes the state of the NAPI_STATE_SCHED bit. This means * whoever atomically sets that bit can add this napi_struct @@ -385,7 +387,6 @@ struct napi_struct { */ struct list_head poll_list; - unsigned long state; int weight; u32 defer_hard_irqs_count; int (*poll)(struct napi_struct *, int); @@ -3529,9 +3530,17 @@ struct softnet_data { call_single_data_t csd ____cacheline_aligned_in_smp; struct softnet_data *rps_ipi_next; unsigned int cpu; + + /* We force a cacheline alignment from here, to hold together + * input_queue_tail, input_pkt_queue and backlog.state. + * We add holes so that backlog.state is the last field + * of this cache line. + */ + long pad[3] ____cacheline_aligned_in_smp; unsigned int input_queue_tail; #endif struct sk_buff_head input_pkt_queue; + struct napi_struct backlog; struct numa_drop_counters drop_counters; -- cgit v1.2.3 From c18d4b190a46651726c9a952667c74d2deb33c28 Mon Sep 17 00:00:00 2001 From: Samiullah Khawaja Date: Tue, 28 Oct 2025 20:30:05 +0000 Subject: net: Extend NAPI threaded polling to allow kthread based busy polling Add a new state NAPI_STATE_THREADED_BUSY_POLL to the NAPI state enum to enable and disable threaded busy polling. When threaded busy polling is enabled for a NAPI, enable NAPI_STATE_THREADED also. When the threaded NAPI is scheduled, set NAPI_STATE_IN_BUSY_POLL to signal napi_complete_done not to rearm interrupts. Whenever NAPI_STATE_THREADED_BUSY_POLL is unset, the NAPI_STATE_IN_BUSY_POLL will be unset, napi_complete_done unsets the NAPI_STATE_SCHED_THREADED bit also, which in turn will make the kthread go to sleep. Signed-off-by: Samiullah Khawaja Reviewed-by: Willem de Bruijn Acked-by: Martin Karsten Tested-by: Martin Karsten Link: https://patch.msgid.link/20251028203007.575686-2-skhawaja@google.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9c1e5042c5e7..e808071dbb7d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -423,11 +423,12 @@ enum { NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ NAPI_STATE_LISTED, /* NAPI added to system lists */ NAPI_STATE_NO_BUSY_POLL, /* Do not add in napi_hash, no busy polling */ - NAPI_STATE_IN_BUSY_POLL, /* sk_busy_loop() owns this NAPI */ + NAPI_STATE_IN_BUSY_POLL, /* Do not rearm NAPI interrupt */ NAPI_STATE_PREFER_BUSY_POLL, /* prefer busy-polling over softirq processing*/ NAPI_STATE_THREADED, /* The poll is performed inside its own thread*/ NAPI_STATE_SCHED_THREADED, /* Napi is currently scheduled in threaded mode */ NAPI_STATE_HAS_NOTIFIER, /* Napi has an IRQ notifier */ + NAPI_STATE_THREADED_BUSY_POLL, /* The threaded NAPI poller will busy poll */ }; enum { @@ -442,6 +443,7 @@ enum { NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED), NAPIF_STATE_SCHED_THREADED = BIT(NAPI_STATE_SCHED_THREADED), NAPIF_STATE_HAS_NOTIFIER = BIT(NAPI_STATE_HAS_NOTIFIER), + NAPIF_STATE_THREADED_BUSY_POLL = BIT(NAPI_STATE_THREADED_BUSY_POLL), }; enum gro_result { -- cgit v1.2.3 From c07a491c1b735e0c27454ea5c27a446d43401b1e Mon Sep 17 00:00:00 2001 From: David Wei Date: Fri, 31 Oct 2025 19:24:48 -0700 Subject: net: export netdev_get_by_index_lock() Need to call netdev_get_by_index_lock() from io_uring/zcrx.c, but it is currently private to net. Export the function in linux/netdevice.h. Signed-off-by: David Wei Acked-by: Jakub Kicinski Signed-off-by: Jens Axboe --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d1a687444b27..77c46a2823ec 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3401,6 +3401,7 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *netdev_get_by_index(struct net *net, int ifindex, netdevice_tracker *tracker, gfp_t gfp); +struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex); struct net_device *netdev_get_by_name(struct net *net, const char *name, netdevice_tracker *tracker, gfp_t gfp); struct net_device *netdev_get_by_flags_rcu(struct net *net, netdevice_tracker *tracker, -- cgit v1.2.3 From ab427db17885814069bae891834f20842f0ac3a4 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 7 Nov 2025 12:14:46 +0100 Subject: netfilter: flowtable: Add IPIP rx sw acceleration Introduce sw acceleration for rx path of IPIP tunnels relying on the netfilter flowtable infrastructure. Subsequent patches will add sw acceleration for IPIP tunnels tx path. This series introduces basic infrastructure to accelerate other tunnel types (e.g. IP6IP6). IPIP rx sw acceleration can be tested running the following scenario where the traffic is forwarded between two NICs (eth0 and eth1) and an IPIP tunnel is used to access a remote site (using eth1 as the underlay device): ETH0 -- TUN0 <==> ETH1 -- [IP network] -- TUN1 (192.168.100.2) $ip addr show 6: eth0: mtu 1500 qdisc noqueue state UP group default qlen 1000 link/ether 00:00:22:33:11:55 brd ff:ff:ff:ff:ff:ff inet 192.168.0.2/24 scope global eth0 valid_lft forever preferred_lft forever 7: eth1: mtu 1500 qdisc noqueue state UP group default qlen 1000 link/ether 00:11:22:33:11:55 brd ff:ff:ff:ff:ff:ff inet 192.168.1.1/24 scope global eth1 valid_lft forever preferred_lft forever 8: tun0@NONE: mtu 1480 qdisc noqueue state UNKNOWN group default qlen 1000 link/ipip 192.168.1.1 peer 192.168.1.2 inet 192.168.100.1/24 scope global tun0 valid_lft forever preferred_lft forever $ip route show default via 192.168.100.2 dev tun0 192.168.0.0/24 dev eth0 proto kernel scope link src 192.168.0.2 192.168.1.0/24 dev eth1 proto kernel scope link src 192.168.1.1 192.168.100.0/24 dev tun0 proto kernel scope link src 192.168.100.1 $nft list ruleset table inet filter { flowtable ft { hook ingress priority filter devices = { eth0, eth1 } } chain forward { type filter hook forward priority filter; policy accept; meta l4proto { tcp, udp } flow add @ft } } Reproducing the scenario described above using veths I got the following results: - TCP stream received from the IPIP tunnel: - net-next: (baseline) ~ 71Gbps - net-next + IPIP flowtbale support: ~101Gbps Signed-off-by: Lorenzo Bianconi Signed-off-by: Pablo Neira Ayuso --- include/linux/netdevice.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e808071dbb7d..bf99fe8622da 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -877,6 +877,7 @@ enum net_device_path_type { DEV_PATH_PPPOE, DEV_PATH_DSA, DEV_PATH_MTK_WDMA, + DEV_PATH_TUN, }; struct net_device_path { @@ -888,6 +889,18 @@ struct net_device_path { __be16 proto; u8 h_dest[ETH_ALEN]; } encap; + struct { + union { + struct in_addr src_v4; + struct in6_addr src_v6; + }; + union { + struct in_addr dst_v4; + struct in6_addr dst_v6; + }; + + u8 l3_proto; + } tun; struct { enum { DEV_PATH_BR_VLAN_KEEP, -- cgit v1.2.3