diff options
Diffstat (limited to 'net')
86 files changed, 3543 insertions, 471 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 2a7f1b15714a..407b2335f091 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -702,20 +702,7 @@ static int vlan_ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) { const struct vlan_dev_priv *vlan = vlan_dev_priv(dev); - const struct ethtool_ops *ops = vlan->real_dev->ethtool_ops; - struct phy_device *phydev = vlan->real_dev->phydev; - - if (phy_has_tsinfo(phydev)) { - return phy_ts_info(phydev, info); - } else if (ops->get_ts_info) { - return ops->get_ts_info(vlan->real_dev, info); - } else { - info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE | - SOF_TIMESTAMPING_SOFTWARE; - info->phc_index = -1; - } - - return 0; + return ethtool_get_ts_info_by_layer(vlan->real_dev, info); } static void vlan_dev_get_stats64(struct net_device *dev, diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index 3bd0760c76a2..b51d8b071b56 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -20,6 +20,7 @@ batman-adv-y += hash.o batman-adv-$(CONFIG_BATMAN_ADV_DEBUG) += log.o batman-adv-y += main.o batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast.o +batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast_forw.o batman-adv-y += netlink.o batman-adv-$(CONFIG_BATMAN_ADV_NC) += network-coding.o batman-adv-y += originator.o diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 37ce6cfb3520..5f46ca3d4bb8 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -20,7 +20,6 @@ #include <linux/if_vlan.h> #include <linux/jhash.h> #include <linux/jiffies.h> -#include <linux/kernel.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/lockdep.h> @@ -31,6 +30,7 @@ #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> +#include <linux/sprintf.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/workqueue.h> diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index c120c7c6d25f..757c084ac2d1 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -25,7 +25,6 @@ #include "hard-interface.h" #include "originator.h" -#include "routing.h" #include "send.h" /** @@ -351,18 +350,14 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb, struct batadv_orig_node *orig_node_src) { struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); - struct batadv_orig_node *orig_node_dst; struct batadv_neigh_node *neigh_node = NULL; struct batadv_frag_packet *packet; u16 total_size; bool ret = false; packet = (struct batadv_frag_packet *)skb->data; - orig_node_dst = batadv_orig_hash_find(bat_priv, packet->dest); - if (!orig_node_dst) - goto out; - neigh_node = batadv_find_router(bat_priv, orig_node_dst, recv_if); + neigh_node = batadv_orig_to_router(bat_priv, packet->dest, recv_if); if (!neigh_node) goto out; @@ -381,7 +376,6 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb, } out: - batadv_orig_node_put(orig_node_dst); batadv_neigh_node_put(neigh_node); return ret; } diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index d26124bc27e1..0ddd8b4b3f4c 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -18,7 +18,6 @@ #include <linux/in.h> #include <linux/ip.h> #include <linux/ipv6.h> -#include <linux/kernel.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/lockdep.h> @@ -29,6 +28,7 @@ #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> +#include <linux/sprintf.h> #include <linux/stddef.h> #include <linux/udp.h> #include <net/sock.h> diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index e8a449915566..5fc754b0b3f7 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -6,6 +6,7 @@ #include "main.h" +#include <linux/array_size.h> #include <linux/atomic.h> #include <linux/build_bug.h> #include <linux/byteorder/generic.h> @@ -20,7 +21,6 @@ #include <linux/init.h> #include <linux/ip.h> #include <linux/ipv6.h> -#include <linux/kernel.h> #include <linux/kobject.h> #include <linux/kref.h> #include <linux/list.h> @@ -33,6 +33,7 @@ #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> +#include <linux/sprintf.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/workqueue.h> @@ -532,6 +533,8 @@ static void batadv_recv_handler_init(void) /* broadcast packet */ batadv_rx_handler[BATADV_BCAST] = batadv_recv_bcast_packet; + /* multicast packet */ + batadv_rx_handler[BATADV_MCAST] = batadv_recv_mcast_packet; /* unicast packets ... */ /* unicast with 4 addresses packet */ diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 10007c5894a1..870dcd7f1786 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -13,7 +13,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2023.3" +#define BATADV_SOURCE_VERSION "2024.0" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 315394f12c55..d982daea8329 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -25,7 +25,6 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/jiffies.h> -#include <linux/kernel.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/netdevice.h> @@ -36,6 +35,7 @@ #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> +#include <linux/sprintf.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/types.h> @@ -236,6 +236,37 @@ static u8 batadv_mcast_mla_rtr_flags_get(struct batadv_priv *bat_priv, } /** + * batadv_mcast_mla_forw_flags_get() - get multicast forwarding flags + * @bat_priv: the bat priv with all the soft interface information + * + * Checks if all active hard interfaces have an MTU larger or equal to 1280 + * bytes (IPv6 minimum MTU). + * + * Return: BATADV_MCAST_HAVE_MC_PTYPE_CAPA if yes, BATADV_NO_FLAGS otherwise. + */ +static u8 batadv_mcast_mla_forw_flags_get(struct batadv_priv *bat_priv) +{ + const struct batadv_hard_iface *hard_iface; + + rcu_read_lock(); + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->if_status != BATADV_IF_ACTIVE) + continue; + + if (hard_iface->soft_iface != bat_priv->soft_iface) + continue; + + if (hard_iface->net_dev->mtu < IPV6_MIN_MTU) { + rcu_read_unlock(); + return BATADV_NO_FLAGS; + } + } + rcu_read_unlock(); + + return BATADV_MCAST_HAVE_MC_PTYPE_CAPA; +} + +/** * batadv_mcast_mla_flags_get() - get the new multicast flags * @bat_priv: the bat priv with all the soft interface information * @@ -256,6 +287,7 @@ batadv_mcast_mla_flags_get(struct batadv_priv *bat_priv) mla_flags.enabled = 1; mla_flags.tvlv_flags |= batadv_mcast_mla_rtr_flags_get(bat_priv, bridge); + mla_flags.tvlv_flags |= batadv_mcast_mla_forw_flags_get(bat_priv); if (!bridge) return mla_flags; @@ -806,23 +838,25 @@ static void batadv_mcast_flags_log(struct batadv_priv *bat_priv, u8 flags) { bool old_enabled = bat_priv->mcast.mla_flags.enabled; u8 old_flags = bat_priv->mcast.mla_flags.tvlv_flags; - char str_old_flags[] = "[.... . ]"; + char str_old_flags[] = "[.... . .]"; - sprintf(str_old_flags, "[%c%c%c%s%s]", + sprintf(str_old_flags, "[%c%c%c%s%s%c]", (old_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.', (old_flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.', (old_flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.', !(old_flags & BATADV_MCAST_WANT_NO_RTR4) ? "R4" : ". ", - !(old_flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". "); + !(old_flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". ", + !(old_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA) ? 'P' : '.'); batadv_dbg(BATADV_DBG_MCAST, bat_priv, - "Changing multicast flags from '%s' to '[%c%c%c%s%s]'\n", + "Changing multicast flags from '%s' to '[%c%c%c%s%s%c]'\n", old_enabled ? str_old_flags : "<undefined>", (flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.', (flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.', (flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.', !(flags & BATADV_MCAST_WANT_NO_RTR4) ? "R4" : ". ", - !(flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". "); + !(flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". ", + !(flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA) ? 'P' : '.'); } /** @@ -1136,16 +1170,61 @@ static int batadv_mcast_forw_rtr_count(struct batadv_priv *bat_priv, } /** + * batadv_mcast_forw_mode_by_count() - get forwarding mode by count + * @bat_priv: the bat priv with all the soft interface information + * @skb: the multicast packet to check + * @vid: the vlan identifier + * @is_routable: stores whether the destination is routable + * @count: the number of originators the multicast packet need to be sent to + * + * For a multicast packet with multiple destination originators, checks which + * mode to use. For BATADV_FORW_MCAST it also encapsulates the packet with a + * complete batman-adv multicast header. + * + * Return: + * BATADV_FORW_MCAST: If all nodes have multicast packet routing + * capabilities and an MTU >= 1280 on all hard interfaces (including us) + * and the encapsulated multicast packet with all destination addresses + * would still fit into an 1280 bytes batman-adv multicast packet + * (excluding the outer ethernet frame) and we could successfully push + * the full batman-adv multicast packet header. + * BATADV_FORW_UCASTS: If the packet cannot be sent in a batman-adv + * multicast packet and the amount of batman-adv unicast packets needed + * is smaller or equal to the configured multicast fanout. + * BATADV_FORW_BCAST: Otherwise. + */ +static enum batadv_forw_mode +batadv_mcast_forw_mode_by_count(struct batadv_priv *bat_priv, + struct sk_buff *skb, unsigned short vid, + int is_routable, int count) +{ + unsigned int mcast_hdrlen = batadv_mcast_forw_packet_hdrlen(count); + u8 own_tvlv_flags = bat_priv->mcast.mla_flags.tvlv_flags; + + if (!atomic_read(&bat_priv->mcast.num_no_mc_ptype_capa) && + own_tvlv_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA && + skb->len + mcast_hdrlen <= IPV6_MIN_MTU && + batadv_mcast_forw_push(bat_priv, skb, vid, is_routable, count)) + return BATADV_FORW_MCAST; + + if (count <= atomic_read(&bat_priv->multicast_fanout)) + return BATADV_FORW_UCASTS; + + return BATADV_FORW_BCAST; +} + +/** * batadv_mcast_forw_mode() - check on how to forward a multicast packet * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to check + * @vid: the vlan identifier * @is_routable: stores whether the destination is routable * * Return: The forwarding mode as enum batadv_forw_mode. */ enum batadv_forw_mode batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, - int *is_routable) + unsigned short vid, int *is_routable) { int ret, tt_count, ip_count, unsnoop_count, total_count; bool is_unsnoopable = false; @@ -1175,10 +1254,8 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, else if (unsnoop_count) return BATADV_FORW_BCAST; - if (total_count <= atomic_read(&bat_priv->multicast_fanout)) - return BATADV_FORW_UCASTS; - - return BATADV_FORW_BCAST; + return batadv_mcast_forw_mode_by_count(bat_priv, skb, vid, *is_routable, + total_count); } /** @@ -1739,6 +1816,31 @@ static void batadv_mcast_want_rtr6_update(struct batadv_priv *bat_priv, } /** + * batadv_mcast_have_mc_ptype_update() - update multicast packet type counter + * @bat_priv: the bat priv with all the soft interface information + * @orig: the orig_node which multicast state might have changed of + * @mcast_flags: flags indicating the new multicast state + * + * If the BATADV_MCAST_HAVE_MC_PTYPE_CAPA flag of this originator, orig, has + * toggled then this method updates the counter accordingly. + */ +static void batadv_mcast_have_mc_ptype_update(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig, + u8 mcast_flags) +{ + lockdep_assert_held(&orig->mcast_handler_lock); + + /* switched from flag set to unset */ + if (!(mcast_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA) && + orig->mcast_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA) + atomic_inc(&bat_priv->mcast.num_no_mc_ptype_capa); + /* switched from flag unset to set */ + else if (mcast_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA && + !(orig->mcast_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA)) + atomic_dec(&bat_priv->mcast.num_no_mc_ptype_capa); +} + +/** * batadv_mcast_tvlv_flags_get() - get multicast flags from an OGM TVLV * @enabled: whether the originator has multicast TVLV support enabled * @tvlv_value: tvlv buffer containing the multicast flags @@ -1806,6 +1908,7 @@ static void batadv_mcast_tvlv_ogm_handler(struct batadv_priv *bat_priv, batadv_mcast_want_ipv6_update(bat_priv, orig, mcast_flags); batadv_mcast_want_rtr4_update(bat_priv, orig, mcast_flags); batadv_mcast_want_rtr6_update(bat_priv, orig, mcast_flags); + batadv_mcast_have_mc_ptype_update(bat_priv, orig, mcast_flags); orig->mcast_flags = mcast_flags; spin_unlock_bh(&orig->mcast_handler_lock); @@ -1820,6 +1923,10 @@ void batadv_mcast_init(struct batadv_priv *bat_priv) batadv_tvlv_handler_register(bat_priv, batadv_mcast_tvlv_ogm_handler, NULL, NULL, BATADV_TVLV_MCAST, 2, BATADV_TVLV_HANDLER_OGM_CIFNOTFND); + batadv_tvlv_handler_register(bat_priv, NULL, NULL, + batadv_mcast_forw_tracker_tvlv_handler, + BATADV_TVLV_MCAST_TRACKER, 1, + BATADV_TVLV_HANDLER_OGM_CIFNOTFND); INIT_DELAYED_WORK(&bat_priv->mcast.work, batadv_mcast_mla_update); batadv_mcast_start_timer(bat_priv); diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index a9770d8d6d36..d97ee51d26f2 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -11,6 +11,7 @@ #include <linux/netlink.h> #include <linux/skbuff.h> +#include <linux/types.h> /** * enum batadv_forw_mode - the way a packet should be forwarded as @@ -28,6 +29,12 @@ enum batadv_forw_mode { */ BATADV_FORW_UCASTS, + /** + * @BATADV_FORW_MCAST: forward the packet to some nodes via a + * batman-adv multicast packet + */ + BATADV_FORW_MCAST, + /** @BATADV_FORW_NONE: don't forward, drop it */ BATADV_FORW_NONE, }; @@ -36,7 +43,7 @@ enum batadv_forw_mode { enum batadv_forw_mode batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, - int *is_routable); + unsigned short vid, int *is_routable); int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid, int is_routable); @@ -52,11 +59,23 @@ void batadv_mcast_free(struct batadv_priv *bat_priv); void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node); +/* multicast_forw.c */ + +int batadv_mcast_forw_tracker_tvlv_handler(struct batadv_priv *bat_priv, + struct sk_buff *skb); + +unsigned int batadv_mcast_forw_packet_hdrlen(unsigned int num_dests); + +bool batadv_mcast_forw_push(struct batadv_priv *bat_priv, struct sk_buff *skb, + unsigned short vid, int is_routable, int count); + +int batadv_mcast_forw_mcsend(struct batadv_priv *bat_priv, struct sk_buff *skb); + #else static inline enum batadv_forw_mode batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, - int *is_routable) + unsigned short vid, int *is_routable) { return BATADV_FORW_BCAST; } @@ -94,6 +113,13 @@ static inline void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node) { } +static inline int batadv_mcast_forw_mcsend(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + kfree_skb(skb); + return NET_XMIT_DROP; +} + #endif /* CONFIG_BATMAN_ADV_MCAST */ #endif /* _NET_BATMAN_ADV_MULTICAST_H_ */ diff --git a/net/batman-adv/multicast_forw.c b/net/batman-adv/multicast_forw.c new file mode 100644 index 000000000000..fafd6ba8c056 --- /dev/null +++ b/net/batman-adv/multicast_forw.c @@ -0,0 +1,1178 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) B.A.T.M.A.N. contributors: + * + * Linus Lüssing + */ + +#include "multicast.h" +#include "main.h" + +#include <linux/bug.h> +#include <linux/build_bug.h> +#include <linux/byteorder/generic.h> +#include <linux/compiler.h> +#include <linux/errno.h> +#include <linux/etherdevice.h> +#include <linux/gfp.h> +#include <linux/if_ether.h> +#include <linux/if_vlan.h> +#include <linux/ipv6.h> +#include <linux/limits.h> +#include <linux/netdevice.h> +#include <linux/rculist.h> +#include <linux/rcupdate.h> +#include <linux/skbuff.h> +#include <linux/stddef.h> +#include <linux/string.h> +#include <linux/types.h> +#include <uapi/linux/batadv_packet.h> + +#include "bridge_loop_avoidance.h" +#include "originator.h" +#include "send.h" +#include "translation-table.h" + +#define batadv_mcast_forw_tracker_for_each_dest(dest, num_dests) \ + for (; num_dests; num_dests--, (dest) += ETH_ALEN) + +#define batadv_mcast_forw_tracker_for_each_dest2(dest1, dest2, num_dests) \ + for (; num_dests; num_dests--, (dest1) += ETH_ALEN, (dest2) += ETH_ALEN) + +/** + * batadv_mcast_forw_skb_push() - skb_push and memorize amount of pushed bytes + * @skb: the skb to push onto + * @size: the amount of bytes to push + * @len: stores the total amount of bytes pushed + * + * Performs an skb_push() onto the given skb and adds the amount of pushed bytes + * to the given len pointer. + * + * Return: the return value of the skb_push() call. + */ +static void *batadv_mcast_forw_skb_push(struct sk_buff *skb, size_t size, + unsigned short *len) +{ + *len += size; + return skb_push(skb, size); +} + +/** + * batadv_mcast_forw_push_padding() - push 2 padding bytes to skb's front + * @skb: the skb to push onto + * @tvlv_len: stores the amount of currently pushed TVLV bytes + * + * Pushes two padding bytes to the front of the given skb. + * + * Return: On success a pointer to the first byte of the two pushed padding + * bytes within the skb. NULL otherwise. + */ +static char * +batadv_mcast_forw_push_padding(struct sk_buff *skb, unsigned short *tvlv_len) +{ + const int pad_len = 2; + char *padding; + + if (skb_headroom(skb) < pad_len) + return NULL; + + padding = batadv_mcast_forw_skb_push(skb, pad_len, tvlv_len); + memset(padding, 0, pad_len); + + return padding; +} + +/** + * batadv_mcast_forw_push_est_padding() - push padding bytes if necessary + * @skb: the skb to potentially push the padding onto + * @count: the (estimated) number of originators the multicast packet needs to + * be sent to + * @tvlv_len: stores the amount of currently pushed TVLV bytes + * + * If the number of destination entries is even then this adds two + * padding bytes to the end of the tracker TVLV. + * + * Return: true on success or if no padding is needed, false otherwise. + */ +static bool +batadv_mcast_forw_push_est_padding(struct sk_buff *skb, int count, + unsigned short *tvlv_len) +{ + if (!(count % 2) && !batadv_mcast_forw_push_padding(skb, tvlv_len)) + return false; + + return true; +} + +/** + * batadv_mcast_forw_orig_entry() - get orig_node from an hlist node + * @node: the hlist node to get the orig_node from + * @entry_offset: the offset of the hlist node within the orig_node struct + * + * Return: The orig_node containing the hlist node on success, NULL on error. + */ +static struct batadv_orig_node * +batadv_mcast_forw_orig_entry(struct hlist_node *node, + size_t entry_offset) +{ + /* sanity check */ + switch (entry_offset) { + case offsetof(struct batadv_orig_node, mcast_want_all_ipv4_node): + case offsetof(struct batadv_orig_node, mcast_want_all_ipv6_node): + case offsetof(struct batadv_orig_node, mcast_want_all_rtr4_node): + case offsetof(struct batadv_orig_node, mcast_want_all_rtr6_node): + break; + default: + WARN_ON(1); + return NULL; + } + + return (struct batadv_orig_node *)((void *)node - entry_offset); +} + +/** + * batadv_mcast_forw_push_dest() - push an originator MAC address onto an skb + * @bat_priv: the bat priv with all the soft interface information + * @skb: the skb to push the destination address onto + * @vid: the vlan identifier + * @orig_node: the originator node to get the MAC address from + * @num_dests: a pointer to store the number of pushed addresses in + * @tvlv_len: stores the amount of currently pushed TVLV bytes + * + * If the orig_node is a BLA backbone gateway, if there is not enough skb + * headroom available or if num_dests is already at its maximum (65535) then + * neither the skb nor num_dests is changed. Otherwise the originator's MAC + * address is pushed onto the given skb and num_dests incremented by one. + * + * Return: true if the orig_node is a backbone gateway or if an orig address + * was pushed successfully, false otherwise. + */ +static bool batadv_mcast_forw_push_dest(struct batadv_priv *bat_priv, + struct sk_buff *skb, unsigned short vid, + struct batadv_orig_node *orig_node, + unsigned short *num_dests, + unsigned short *tvlv_len) +{ + BUILD_BUG_ON(sizeof_field(struct batadv_tvlv_mcast_tracker, num_dests) + != sizeof(__be16)); + + /* Avoid sending to other BLA gateways - they already got the frame from + * the LAN side we share with them. + * TODO: Refactor to take BLA into account earlier in mode check. + */ + if (batadv_bla_is_backbone_gw_orig(bat_priv, orig_node->orig, vid)) + return true; + + if (skb_headroom(skb) < ETH_ALEN || *num_dests == U16_MAX) + return false; + + batadv_mcast_forw_skb_push(skb, ETH_ALEN, tvlv_len); + ether_addr_copy(skb->data, orig_node->orig); + (*num_dests)++; + + return true; +} + +/** + * batadv_mcast_forw_push_dests_list() - push originators from list onto an skb + * @bat_priv: the bat priv with all the soft interface information + * @skb: the skb to push the destination addresses onto + * @vid: the vlan identifier + * @head: the list to gather originators from + * @entry_offset: offset of an hlist node in an orig_node structure + * @num_dests: a pointer to store the number of pushed addresses in + * @tvlv_len: stores the amount of currently pushed TVLV bytes + * + * Push the MAC addresses of all originators in the given list onto the given + * skb. + * + * Return: true on success, false otherwise. + */ +static int batadv_mcast_forw_push_dests_list(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + struct hlist_head *head, + size_t entry_offset, + unsigned short *num_dests, + unsigned short *tvlv_len) +{ + struct hlist_node *node; + struct batadv_orig_node *orig_node; + + rcu_read_lock(); + __hlist_for_each_rcu(node, head) { + orig_node = batadv_mcast_forw_orig_entry(node, entry_offset); + if (!orig_node || + !batadv_mcast_forw_push_dest(bat_priv, skb, vid, orig_node, + num_dests, tvlv_len)) { + rcu_read_unlock(); + return false; + } + } + rcu_read_unlock(); + + return true; +} + +/** + * batadv_mcast_forw_push_tt() - push originators with interest through TT + * @bat_priv: the bat priv with all the soft interface information + * @skb: the skb to push the destination addresses onto + * @vid: the vlan identifier + * @num_dests: a pointer to store the number of pushed addresses in + * @tvlv_len: stores the amount of currently pushed TVLV bytes + * + * Push the MAC addresses of all originators which have indicated interest in + * this multicast packet through the translation table onto the given skb. + * + * Return: true on success, false otherwise. + */ +static bool +batadv_mcast_forw_push_tt(struct batadv_priv *bat_priv, struct sk_buff *skb, + unsigned short vid, unsigned short *num_dests, + unsigned short *tvlv_len) +{ + struct batadv_tt_orig_list_entry *orig_entry; + + struct batadv_tt_global_entry *tt_global; + const u8 *addr = eth_hdr(skb)->h_dest; + + /* ok */ + int ret = true; + + tt_global = batadv_tt_global_hash_find(bat_priv, addr, vid); + if (!tt_global) + goto out; + + rcu_read_lock(); + hlist_for_each_entry_rcu(orig_entry, &tt_global->orig_list, list) { + if (!batadv_mcast_forw_push_dest(bat_priv, skb, vid, + orig_entry->orig_node, + num_dests, tvlv_len)) { + ret = false; + break; + } + } + rcu_read_unlock(); + + batadv_tt_global_entry_put(tt_global); + +out: + return ret; +} + +/** + * batadv_mcast_forw_push_want_all() - push originators with want-all flag + * @bat_priv: the bat priv with all the soft interface information + * @skb: the skb to push the destination addresses onto + * @vid: the vlan identifier + * @num_dests: a pointer to store the number of pushed addresses in + * @tvlv_len: stores the amount of currently pushed TVLV bytes + * + * Push the MAC addresses of all originators which have indicated interest in + * this multicast packet through the want-all flag onto the given skb. + * + * Return: true on success, false otherwise. + */ +static bool batadv_mcast_forw_push_want_all(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + unsigned short *num_dests, + unsigned short *tvlv_len) +{ + struct hlist_head *head = NULL; + size_t offset; + int ret; + + switch (eth_hdr(skb)->h_proto) { + case htons(ETH_P_IP): + head = &bat_priv->mcast.want_all_ipv4_list; + offset = offsetof(struct batadv_orig_node, + mcast_want_all_ipv4_node); + break; + case htons(ETH_P_IPV6): + head = &bat_priv->mcast.want_all_ipv6_list; + offset = offsetof(struct batadv_orig_node, + mcast_want_all_ipv6_node); + break; + default: + return false; + } + + ret = batadv_mcast_forw_push_dests_list(bat_priv, skb, vid, head, + offset, num_dests, tvlv_len); + if (!ret) + return false; + + return true; +} + +/** + * batadv_mcast_forw_push_want_rtr() - push originators with want-router flag + * @bat_priv: the bat priv with all the soft interface information + * @skb: the skb to push the destination addresses onto + * @vid: the vlan identifier + * @num_dests: a pointer to store the number of pushed addresses in + * @tvlv_len: stores the amount of currently pushed TVLV bytes + * + * Push the MAC addresses of all originators which have indicated interest in + * this multicast packet through the want-all-rtr flag onto the given skb. + * + * Return: true on success, false otherwise. + */ +static bool batadv_mcast_forw_push_want_rtr(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + unsigned short *num_dests, + unsigned short *tvlv_len) +{ + struct hlist_head *head = NULL; + size_t offset; + int ret; + + switch (eth_hdr(skb)->h_proto) { + case htons(ETH_P_IP): + head = &bat_priv->mcast.want_all_rtr4_list; + offset = offsetof(struct batadv_orig_node, + mcast_want_all_rtr4_node); + break; + case htons(ETH_P_IPV6): + head = &bat_priv->mcast.want_all_rtr6_list; + offset = offsetof(struct batadv_orig_node, + mcast_want_all_rtr6_node); + break; + default: + return false; + } + + ret = batadv_mcast_forw_push_dests_list(bat_priv, skb, vid, head, + offset, num_dests, tvlv_len); + if (!ret) + return false; + + return true; +} + +/** + * batadv_mcast_forw_scrape() - remove bytes within skb data + * @skb: the skb to remove bytes from + * @offset: the offset from the skb data from which to scrape + * @len: the amount of bytes to scrape starting from the offset + * + * Scrapes/removes len bytes from the given skb at the given offset from the + * skb data. + * + * Caller needs to ensure that the region from the skb data's start up + * to/including the to be removed bytes are linearized. + */ +static void batadv_mcast_forw_scrape(struct sk_buff *skb, + unsigned short offset, + unsigned short len) +{ + char *to, *from; + + SKB_LINEAR_ASSERT(skb); + + to = skb_pull(skb, len); + from = to - len; + + memmove(to, from, offset); +} + +/** + * batadv_mcast_forw_push_scrape_padding() - remove TVLV padding + * @skb: the skb to potentially adjust the TVLV's padding on + * @tvlv_len: stores the amount of currently pushed TVLV bytes + * + * Remove two padding bytes from the end of the multicast tracker TVLV, + * from before the payload data. + * + * Caller needs to ensure that the TVLV bytes are linearized. + */ +static void batadv_mcast_forw_push_scrape_padding(struct sk_buff *skb, + unsigned short *tvlv_len) +{ + const int pad_len = 2; + + batadv_mcast_forw_scrape(skb, *tvlv_len - pad_len, pad_len); + *tvlv_len -= pad_len; +} + +/** + * batadv_mcast_forw_push_insert_padding() - insert TVLV padding + * @skb: the skb to potentially adjust the TVLV's padding on + * @tvlv_len: stores the amount of currently pushed TVLV bytes + * + * Inserts two padding bytes at the end of the multicast tracker TVLV, + * before the payload data in the given skb. + * + * Return: true on success, false otherwise. + */ +static bool batadv_mcast_forw_push_insert_padding(struct sk_buff *skb, + unsigned short *tvlv_len) +{ + unsigned short offset = *tvlv_len; + char *to, *from = skb->data; + + to = batadv_mcast_forw_push_padding(skb, tvlv_len); + if (!to) + return false; + + memmove(to, from, offset); + memset(to + offset, 0, *tvlv_len - offset); + return true; +} + +/** + * batadv_mcast_forw_push_adjust_padding() - adjust padding if necessary + * @skb: the skb to potentially adjust the TVLV's padding on + * @count: the estimated number of originators the multicast packet needs to + * be sent to + * @num_dests_pushed: the number of originators that were actually added to the + * multicast packet's tracker TVLV + * @tvlv_len: stores the amount of currently pushed TVLV bytes + * + * Adjusts the padding in the multicast packet's tracker TVLV depending on the + * initially estimated amount of destinations versus the amount of destinations + * that were actually added to the tracker TVLV. + * + * If the initial estimate was correct or at least the oddness was the same then + * no padding adjustment is performed. + * If the initially estimated number was even, so padding was initially added, + * but it turned out to be odd then padding is removed. + * If the initially estimated number was odd, so no padding was initially added, + * but it turned out to be even then padding is added. + * + * Return: true if no padding adjustment is needed or the adjustment was + * successful, false otherwise. + */ +static bool +batadv_mcast_forw_push_adjust_padding(struct sk_buff *skb, int *count, + unsigned short num_dests_pushed, + unsigned short *tvlv_len) +{ + int ret = true; + + if (likely((num_dests_pushed % 2) == (*count % 2))) + goto out; + + /** + * estimated even number of destinations, but turned out to be odd + * -> remove padding + */ + if (!(*count % 2) && (num_dests_pushed % 2)) + batadv_mcast_forw_push_scrape_padding(skb, tvlv_len); + /** + * estimated odd number of destinations, but turned out to be even + * -> add padding + */ + else if ((*count % 2) && (!(num_dests_pushed % 2))) + ret = batadv_mcast_forw_push_insert_padding(skb, tvlv_len); + +out: + *count = num_dests_pushed; + return ret; +} + +/** + * batadv_mcast_forw_push_dests() - push originator addresses onto an skb + * @bat_priv: the bat priv with all the soft interface information + * @skb: the skb to push the destination addresses onto + * @vid: the vlan identifier + * @is_routable: indicates whether the destination is routable + * @count: the number of originators the multicast packet needs to be sent to + * @tvlv_len: stores the amount of currently pushed TVLV bytes + * + * Push the MAC addresses of all originators which have indicated interest in + * this multicast packet onto the given skb. + * + * Return: -ENOMEM if there is not enough skb headroom available. Otherwise, on + * success 0. + */ +static int +batadv_mcast_forw_push_dests(struct batadv_priv *bat_priv, struct sk_buff *skb, + unsigned short vid, int is_routable, int *count, + unsigned short *tvlv_len) +{ + unsigned short num_dests = 0; + + if (!batadv_mcast_forw_push_est_padding(skb, *count, tvlv_len)) + goto err; + + if (!batadv_mcast_forw_push_tt(bat_priv, skb, vid, &num_dests, + tvlv_len)) + goto err; + + if (!batadv_mcast_forw_push_want_all(bat_priv, skb, vid, &num_dests, + tvlv_len)) + goto err; + + if (is_routable && + !batadv_mcast_forw_push_want_rtr(bat_priv, skb, vid, &num_dests, + tvlv_len)) + goto err; + + if (!batadv_mcast_forw_push_adjust_padding(skb, count, num_dests, + tvlv_len)) + goto err; + + return 0; +err: + return -ENOMEM; +} + +/** + * batadv_mcast_forw_push_tracker() - push a multicast tracker TVLV header + * @skb: the skb to push the tracker TVLV onto + * @num_dests: the number of destination addresses to set in the header + * @tvlv_len: stores the amount of currently pushed TVLV bytes + * + * Pushes a multicast tracker TVLV header onto the given skb, including the + * generic TVLV header but excluding the destination MAC addresses. + * + * The provided num_dests value is taken into consideration to set the + * num_dests field in the tracker header and to set the appropriate TVLV length + * value fields. + * + * Return: -ENOMEM if there is not enough skb headroom available. Otherwise, on + * success 0. + */ +static int batadv_mcast_forw_push_tracker(struct sk_buff *skb, int num_dests, + unsigned short *tvlv_len) +{ + struct batadv_tvlv_mcast_tracker *mcast_tracker; + struct batadv_tvlv_hdr *tvlv_hdr; + unsigned int tvlv_value_len; + + if (skb_headroom(skb) < sizeof(*mcast_tracker) + sizeof(*tvlv_hdr)) + return -ENOMEM; + + tvlv_value_len = sizeof(*mcast_tracker) + *tvlv_len; + if (tvlv_value_len + sizeof(*tvlv_hdr) > U16_MAX) + return -ENOMEM; + + batadv_mcast_forw_skb_push(skb, sizeof(*mcast_tracker), tvlv_len); + mcast_tracker = (struct batadv_tvlv_mcast_tracker *)skb->data; + mcast_tracker->num_dests = htons(num_dests); + + skb_reset_network_header(skb); + + batadv_mcast_forw_skb_push(skb, sizeof(*tvlv_hdr), tvlv_len); + tvlv_hdr = (struct batadv_tvlv_hdr *)skb->data; + tvlv_hdr->type = BATADV_TVLV_MCAST_TRACKER; + tvlv_hdr->version = 1; + tvlv_hdr->len = htons(tvlv_value_len); + + return 0; +} + +/** + * batadv_mcast_forw_push_tvlvs() - push a multicast tracker TVLV onto an skb + * @bat_priv: the bat priv with all the soft interface information + * @skb: the skb to push the tracker TVLV onto + * @vid: the vlan identifier + * @is_routable: indicates whether the destination is routable + * @count: the number of originators the multicast packet needs to be sent to + * @tvlv_len: stores the amount of currently pushed TVLV bytes + * + * Pushes a multicast tracker TVLV onto the given skb, including the collected + * destination MAC addresses and the generic TVLV header. + * + * Return: -ENOMEM if there is not enough skb headroom available. Otherwise, on + * success 0. + */ +static int +batadv_mcast_forw_push_tvlvs(struct batadv_priv *bat_priv, struct sk_buff *skb, + unsigned short vid, int is_routable, int count, + unsigned short *tvlv_len) +{ + int ret; + + ret = batadv_mcast_forw_push_dests(bat_priv, skb, vid, is_routable, + &count, tvlv_len); + if (ret < 0) + return ret; + + ret = batadv_mcast_forw_push_tracker(skb, count, tvlv_len); + if (ret < 0) + return ret; + + return 0; +} + +/** + * batadv_mcast_forw_push_hdr() - push a multicast packet header onto an skb + * @skb: the skb to push the header onto + * @tvlv_len: the total TVLV length value to set in the header + * + * Pushes a batman-adv multicast packet header onto the given skb and sets + * the provided total TVLV length value in it. + * + * Caller needs to ensure enough skb headroom is available. + * + * Return: -ENOMEM if there is not enough skb headroom available. Otherwise, on + * success 0. + */ +static int +batadv_mcast_forw_push_hdr(struct sk_buff *skb, unsigned short tvlv_len) +{ + struct batadv_mcast_packet *mcast_packet; + + if (skb_headroom(skb) < sizeof(*mcast_packet)) + return -ENOMEM; + + skb_push(skb, sizeof(*mcast_packet)); + + mcast_packet = (struct batadv_mcast_packet *)skb->data; + mcast_packet->version = BATADV_COMPAT_VERSION; + mcast_packet->ttl = BATADV_TTL; + mcast_packet->packet_type = BATADV_MCAST; + mcast_packet->reserved = 0; + mcast_packet->tvlv_len = htons(tvlv_len); + + return 0; +} + +/** + * batadv_mcast_forw_scrub_dests() - scrub destinations in a tracker TVLV + * @bat_priv: the bat priv with all the soft interface information + * @comp_neigh: next hop neighbor to scrub+collect destinations for + * @dest: start MAC entry in original skb's tracker TVLV + * @next_dest: start MAC entry in to be sent skb's tracker TVLV + * @num_dests: number of remaining destination MAC entries to iterate over + * + * This sorts destination entries into either the original batman-adv + * multicast packet or the skb (copy) that is going to be sent to comp_neigh + * next. + * + * In preparation for the next, to be (unicast) transmitted batman-adv multicast + * packet skb to be sent to the given neighbor node, tries to collect all + * originator MAC addresses that have the given neighbor node as their next hop + * in the to be transmitted skb (copy), which next_dest points into. That is we + * zero all destination entries in next_dest which do not have comp_neigh as + * their next hop. And zero all destination entries in the original skb that + * would have comp_neigh as their next hop (to avoid redundant transmissions and + * duplicated payload later). + */ +static void +batadv_mcast_forw_scrub_dests(struct batadv_priv *bat_priv, + struct batadv_neigh_node *comp_neigh, u8 *dest, + u8 *next_dest, u16 num_dests) +{ + struct batadv_neigh_node *next_neigh; + + /* skip first entry, this is what we are comparing with */ + eth_zero_addr(dest); + dest += ETH_ALEN; + next_dest += ETH_ALEN; + num_dests--; + + batadv_mcast_forw_tracker_for_each_dest2(dest, next_dest, num_dests) { + if (is_zero_ether_addr(next_dest)) + continue; + + /* sanity check, we expect unicast destinations */ + if (is_multicast_ether_addr(next_dest)) { + eth_zero_addr(dest); + eth_zero_addr(next_dest); + continue; + } + + next_neigh = batadv_orig_to_router(bat_priv, next_dest, NULL); + if (!next_neigh) { + eth_zero_addr(next_dest); + continue; + } + + if (!batadv_compare_eth(next_neigh->addr, comp_neigh->addr)) { + eth_zero_addr(next_dest); + batadv_neigh_node_put(next_neigh); + continue; + } + + /* found an entry for our next packet to transmit, so remove it + * from the original packet + */ + eth_zero_addr(dest); + batadv_neigh_node_put(next_neigh); + } +} + +/** + * batadv_mcast_forw_shrink_fill() - swap slot with next non-zero destination + * @slot: the to be filled zero-MAC destination entry in a tracker TVLV + * @num_dests_slot: remaining entries in tracker TVLV from/including slot + * + * Searches for the next non-zero-MAC destination entry in a tracker TVLV after + * the given slot pointer. And if found, swaps it with the zero-MAC destination + * entry which the slot points to. + * + * Return: true if slot was swapped/filled successfully, false otherwise. + */ +static bool batadv_mcast_forw_shrink_fill(u8 *slot, u16 num_dests_slot) +{ + u16 num_dests_filler; + u8 *filler; + + /* sanity check, should not happen */ + if (!num_dests_slot) + return false; + + num_dests_filler = num_dests_slot - 1; + filler = slot + ETH_ALEN; + + /* find a candidate to fill the empty slot */ + batadv_mcast_forw_tracker_for_each_dest(filler, num_dests_filler) { + if (is_zero_ether_addr(filler)) + continue; + + ether_addr_copy(slot, filler); + eth_zero_addr(filler); + return true; + } + + return false; +} + +/** + * batadv_mcast_forw_shrink_pack_dests() - pack destinations of a tracker TVLV + * @skb: the batman-adv multicast packet to compact destinations in + * + * Compacts the originator destination MAC addresses in the multicast tracker + * TVLV of the given multicast packet. This is done by moving all non-zero + * MAC addresses in direction of the skb head and all zero MAC addresses in skb + * tail direction, within the multicast tracker TVLV. + * + * Return: The number of consecutive zero MAC address destinations which are + * now at the end of the multicast tracker TVLV. + */ +static int batadv_mcast_forw_shrink_pack_dests(struct sk_buff *skb) +{ + struct batadv_tvlv_mcast_tracker *mcast_tracker; + unsigned char *skb_net_hdr; + u16 num_dests_slot; + u8 *slot; + + skb_net_hdr = skb_network_header(skb); + mcast_tracker = (struct batadv_tvlv_mcast_tracker *)skb_net_hdr; + num_dests_slot = ntohs(mcast_tracker->num_dests); + + slot = (u8 *)mcast_tracker + sizeof(*mcast_tracker); + + batadv_mcast_forw_tracker_for_each_dest(slot, num_dests_slot) { + /* find an empty slot */ + if (!is_zero_ether_addr(slot)) + continue; + + if (!batadv_mcast_forw_shrink_fill(slot, num_dests_slot)) + /* could not find a filler, so we successfully packed + * and can stop - and must not reduce num_dests_slot! + */ + break; + } + + /* num_dests_slot is now the amount of reduced, zeroed + * destinations at the end of the tracker TVLV + */ + return num_dests_slot; +} + +/** + * batadv_mcast_forw_shrink_align_offset() - get new alignment offset + * @num_dests_old: the old, to be updated amount of destination nodes + * @num_dests_reduce: the number of destinations that were removed + * + * Calculates the amount of potential extra alignment offset that is needed to + * adjust the TVLV padding after the change in destination nodes. + * + * Return: + * 0: If no change to padding is needed. + * 2: If padding needs to be removed. + * -2: If padding needs to be added. + */ +static short +batadv_mcast_forw_shrink_align_offset(unsigned int num_dests_old, + unsigned int num_dests_reduce) +{ + /* even amount of removed destinations -> no alignment change */ + if (!(num_dests_reduce % 2)) + return 0; + + /* even to odd amount of destinations -> remove padding */ + if (!(num_dests_old % 2)) + return 2; + + /* odd to even amount of destinations -> add padding */ + return -2; +} + +/** + * batadv_mcast_forw_shrink_update_headers() - update shrunk mc packet headers + * @skb: the batman-adv multicast packet to update headers of + * @num_dests_reduce: the number of destinations that were removed + * + * This updates any fields of a batman-adv multicast packet that are affected + * by the reduced number of destinations in the multicast tracket TVLV. In + * particular this updates: + * + * The num_dest field of the multicast tracker TVLV. + * The TVLV length field of the according generic TVLV header. + * The batman-adv multicast packet's total TVLV length field. + * + * Return: The offset in skb's tail direction at which the new batman-adv + * multicast packet header needs to start. + */ +static unsigned int +batadv_mcast_forw_shrink_update_headers(struct sk_buff *skb, + unsigned int num_dests_reduce) +{ + struct batadv_tvlv_mcast_tracker *mcast_tracker; + struct batadv_mcast_packet *mcast_packet; + struct batadv_tvlv_hdr *tvlv_hdr; + unsigned char *skb_net_hdr; + unsigned int offset; + short align_offset; + u16 num_dests; + + skb_net_hdr = skb_network_header(skb); + mcast_tracker = (struct batadv_tvlv_mcast_tracker *)skb_net_hdr; + num_dests = ntohs(mcast_tracker->num_dests); + + align_offset = batadv_mcast_forw_shrink_align_offset(num_dests, + num_dests_reduce); + offset = ETH_ALEN * num_dests_reduce + align_offset; + num_dests -= num_dests_reduce; + + /* update tracker header */ + mcast_tracker->num_dests = htons(num_dests); + + /* update tracker's tvlv header's length field */ + tvlv_hdr = (struct batadv_tvlv_hdr *)(skb_network_header(skb) - + sizeof(*tvlv_hdr)); + tvlv_hdr->len = htons(ntohs(tvlv_hdr->len) - offset); + + /* update multicast packet header's tvlv length field */ + mcast_packet = (struct batadv_mcast_packet *)skb->data; + mcast_packet->tvlv_len = htons(ntohs(mcast_packet->tvlv_len) - offset); + + return offset; +} + +/** + * batadv_mcast_forw_shrink_move_headers() - move multicast headers by offset + * @skb: the batman-adv multicast packet to move headers for + * @offset: a non-negative offset to move headers by, towards the skb tail + * + * Moves the batman-adv multicast packet header, its multicast tracker TVLV and + * any TVLVs in between by the given offset in direction towards the tail. + */ +static void +batadv_mcast_forw_shrink_move_headers(struct sk_buff *skb, unsigned int offset) +{ + struct batadv_tvlv_mcast_tracker *mcast_tracker; + unsigned char *skb_net_hdr; + unsigned int len; + u16 num_dests; + + skb_net_hdr = skb_network_header(skb); + mcast_tracker = (struct batadv_tvlv_mcast_tracker *)skb_net_hdr; + num_dests = ntohs(mcast_tracker->num_dests); + len = skb_network_offset(skb) + sizeof(*mcast_tracker); + len += num_dests * ETH_ALEN; + + batadv_mcast_forw_scrape(skb, len, offset); +} + +/** + * batadv_mcast_forw_shrink_tracker() - remove zero addresses in a tracker tvlv + * @skb: the batman-adv multicast packet to (potentially) shrink + * + * Removes all destinations with a zero MAC addresses (00:00:00:00:00:00) from + * the given batman-adv multicast packet's tracker TVLV and updates headers + * accordingly to maintain a valid batman-adv multicast packet. + */ +static void batadv_mcast_forw_shrink_tracker(struct sk_buff *skb) +{ + unsigned int offset; + u16 dests_reduced; + + dests_reduced = batadv_mcast_forw_shrink_pack_dests(skb); + if (!dests_reduced) + return; + + offset = batadv_mcast_forw_shrink_update_headers(skb, dests_reduced); + batadv_mcast_forw_shrink_move_headers(skb, offset); +} + +/** + * batadv_mcast_forw_packet() - forward a batman-adv multicast packet + * @bat_priv: the bat priv with all the soft interface information + * @skb: the received or locally generated batman-adv multicast packet + * @local_xmit: indicates that the packet was locally generated and not received + * + * Parses the tracker TVLV of a batman-adv multicast packet and forwards the + * packet as indicated in this TVLV. + * + * Caller needs to set the skb network header to the start of the multicast + * tracker TVLV (excluding the generic TVLV header) and the skb transport header + * to the next byte after this multicast tracker TVLV. + * + * Caller needs to free the skb. + * + * Return: NET_RX_SUCCESS or NET_RX_DROP on success or a negative error + * code on failure. NET_RX_SUCCESS if the received packet is supposed to be + * decapsulated and forwarded to the own soft interface, NET_RX_DROP otherwise. + */ +static int batadv_mcast_forw_packet(struct batadv_priv *bat_priv, + struct sk_buff *skb, bool local_xmit) +{ + struct batadv_tvlv_mcast_tracker *mcast_tracker; + struct batadv_neigh_node *neigh_node; + unsigned long offset, num_dests_off; + struct sk_buff *nexthop_skb; + unsigned char *skb_net_hdr; + bool local_recv = false; + unsigned int tvlv_len; + bool xmitted = false; + u8 *dest, *next_dest; + u16 num_dests; + int ret; + + /* (at least) TVLV part needs to be linearized */ + SKB_LINEAR_ASSERT(skb); + + /* check if num_dests is within skb length */ + num_dests_off = offsetof(struct batadv_tvlv_mcast_tracker, num_dests); + if (num_dests_off > skb_network_header_len(skb)) + return -EINVAL; + + skb_net_hdr = skb_network_header(skb); + mcast_tracker = (struct batadv_tvlv_mcast_tracker *)skb_net_hdr; + num_dests = ntohs(mcast_tracker->num_dests); + + dest = (u8 *)mcast_tracker + sizeof(*mcast_tracker); + + /* check if full tracker tvlv is within skb length */ + tvlv_len = sizeof(*mcast_tracker) + ETH_ALEN * num_dests; + if (tvlv_len > skb_network_header_len(skb)) + return -EINVAL; + + /* invalidate checksum: */ + skb->ip_summed = CHECKSUM_NONE; + + batadv_mcast_forw_tracker_for_each_dest(dest, num_dests) { + if (is_zero_ether_addr(dest)) + continue; + + /* only unicast originator addresses supported */ + if (is_multicast_ether_addr(dest)) { + eth_zero_addr(dest); + continue; + } + + if (batadv_is_my_mac(bat_priv, dest)) { + eth_zero_addr(dest); + local_recv = true; + continue; + } + + neigh_node = batadv_orig_to_router(bat_priv, dest, NULL); + if (!neigh_node) { + eth_zero_addr(dest); + continue; + } + + nexthop_skb = skb_copy(skb, GFP_ATOMIC); + if (!nexthop_skb) { + batadv_neigh_node_put(neigh_node); + return -ENOMEM; + } + + offset = dest - skb->data; + next_dest = nexthop_skb->data + offset; + + batadv_mcast_forw_scrub_dests(bat_priv, neigh_node, dest, + next_dest, num_dests); + batadv_mcast_forw_shrink_tracker(nexthop_skb); + + batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_TX); + batadv_add_counter(bat_priv, BATADV_CNT_MCAST_TX_BYTES, + nexthop_skb->len + ETH_HLEN); + xmitted = true; + ret = batadv_send_unicast_skb(nexthop_skb, neigh_node); + + batadv_neigh_node_put(neigh_node); + + if (ret < 0) + return ret; + } + + if (xmitted) { + if (local_xmit) { + batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_TX_LOCAL); + batadv_add_counter(bat_priv, + BATADV_CNT_MCAST_TX_LOCAL_BYTES, + skb->len - + skb_transport_offset(skb)); + } else { + batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_FWD); + batadv_add_counter(bat_priv, BATADV_CNT_MCAST_FWD_BYTES, + skb->len + ETH_HLEN); + } + } + + if (local_recv) + return NET_RX_SUCCESS; + else + return NET_RX_DROP; +} + +/** + * batadv_mcast_forw_tracker_tvlv_handler() - handle an mcast tracker tvlv + * @bat_priv: the bat priv with all the soft interface information + * @skb: the received batman-adv multicast packet + * + * Parses the tracker TVLV of an incoming batman-adv multicast packet and + * forwards the packet as indicated in this TVLV. + * + * Caller needs to set the skb network header to the start of the multicast + * tracker TVLV (excluding the generic TVLV header) and the skb transport header + * to the next byte after this multicast tracker TVLV. + * + * Caller needs to free the skb. + * + * Return: NET_RX_SUCCESS or NET_RX_DROP on success or a negative error + * code on failure. NET_RX_SUCCESS if the received packet is supposed to be + * decapsulated and forwarded to the own soft interface, NET_RX_DROP otherwise. + */ +int batadv_mcast_forw_tracker_tvlv_handler(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + return batadv_mcast_forw_packet(bat_priv, skb, false); +} + +/** + * batadv_mcast_forw_packet_hdrlen() - multicast packet header length + * @num_dests: number of destination nodes + * + * Calculates the total batman-adv multicast packet header length for a given + * number of destination nodes (excluding the outer ethernet frame). + * + * Return: The calculated total batman-adv multicast packet header length. + */ +unsigned int batadv_mcast_forw_packet_hdrlen(unsigned int num_dests) +{ + /** + * If the number of destination entries is even then we need to add + * two byte padding to the tracker TVLV. + */ + int padding = (!(num_dests % 2)) ? 2 : 0; + + return padding + num_dests * ETH_ALEN + + sizeof(struct batadv_tvlv_mcast_tracker) + + sizeof(struct batadv_tvlv_hdr) + + sizeof(struct batadv_mcast_packet); +} + +/** + * batadv_mcast_forw_expand_head() - expand headroom for an mcast packet + * @bat_priv: the bat priv with all the soft interface information + * @skb: the multicast packet to send + * + * Tries to expand an skb's headroom so that its head to tail is 1298 + * bytes (minimum IPv6 MTU + vlan ethernet header size) large. + * + * Return: -EINVAL if the given skb's length is too large or -ENOMEM on memory + * allocation failure. Otherwise, on success, zero is returned. + */ +static int batadv_mcast_forw_expand_head(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + int hdr_size = VLAN_ETH_HLEN + IPV6_MIN_MTU - skb->len; + + /* TODO: Could be tightened to actual number of destination nodes? + * But it's tricky, number of destinations might have increased since + * we last checked. + */ + if (hdr_size < 0) { + /* batadv_mcast_forw_mode_check_count() should ensure we do not + * end up here + */ + WARN_ON(1); + return -EINVAL; + } + + if (skb_headroom(skb) < hdr_size && + pskb_expand_head(skb, hdr_size, 0, GFP_ATOMIC) < 0) + return -ENOMEM; + + return 0; +} + +/** + * batadv_mcast_forw_push() - encapsulate skb in a batman-adv multicast packet + * @bat_priv: the bat priv with all the soft interface information + * @skb: the multicast packet to encapsulate and send + * @vid: the vlan identifier + * @is_routable: indicates whether the destination is routable + * @count: the number of originators the multicast packet needs to be sent to + * + * Encapsulates the given multicast packet in a batman-adv multicast packet. + * A multicast tracker TVLV with destination originator addresses for any node + * that signaled interest in it, that is either via the translation table or the + * according want-all flags, is attached accordingly. + * + * Return: true on success, false otherwise. + */ +bool batadv_mcast_forw_push(struct batadv_priv *bat_priv, struct sk_buff *skb, + unsigned short vid, int is_routable, int count) +{ + unsigned short tvlv_len = 0; + int ret; + + if (batadv_mcast_forw_expand_head(bat_priv, skb) < 0) + goto err; + + skb_reset_transport_header(skb); + + ret = batadv_mcast_forw_push_tvlvs(bat_priv, skb, vid, is_routable, + count, &tvlv_len); + if (ret < 0) + goto err; + + ret = batadv_mcast_forw_push_hdr(skb, tvlv_len); + if (ret < 0) + goto err; + + return true; + +err: + if (tvlv_len) + skb_pull(skb, tvlv_len); + + return false; +} + +/** + * batadv_mcast_forw_mcsend() - send a self prepared batman-adv multicast packet + * @bat_priv: the bat priv with all the soft interface information + * @skb: the multicast packet to encapsulate and send + * + * Transmits a batman-adv multicast packet that was locally prepared and + * consumes/frees it. + * + * Return: NET_XMIT_DROP on memory allocation failure. NET_XMIT_SUCCESS + * otherwise. + */ +int batadv_mcast_forw_mcsend(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + int ret = batadv_mcast_forw_packet(bat_priv, skb, true); + + if (ret < 0) { + kfree_skb(skb); + return NET_XMIT_DROP; + } + + consume_skb(skb); + return NET_XMIT_SUCCESS; +} diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 0c64d81a7761..1f7ed9d4f6fd 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -7,6 +7,7 @@ #include "netlink.h" #include "main.h" +#include <linux/array_size.h> #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/bug.h> @@ -20,7 +21,6 @@ #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <linux/init.h> -#include <linux/kernel.h> #include <linux/limits.h> #include <linux/list.h> #include <linux/minmax.h> diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 34903df4fe93..71c143d4b6d0 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -312,6 +312,33 @@ batadv_orig_router_get(struct batadv_orig_node *orig_node, } /** + * batadv_orig_to_router() - get next hop neighbor to an orig address + * @bat_priv: the bat priv with all the soft interface information + * @orig_addr: the originator MAC address to search the best next hop router for + * @if_outgoing: the interface where the payload packet has been received or + * the OGM should be sent to + * + * Return: A neighbor node which is the best router towards the given originator + * address. + */ +struct batadv_neigh_node * +batadv_orig_to_router(struct batadv_priv *bat_priv, u8 *orig_addr, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_neigh_node *neigh_node; + struct batadv_orig_node *orig_node; + + orig_node = batadv_orig_hash_find(bat_priv, orig_addr); + if (!orig_node) + return NULL; + + neigh_node = batadv_find_router(bat_priv, orig_node, if_outgoing); + batadv_orig_node_put(orig_node); + + return neigh_node; +} + +/** * batadv_orig_ifinfo_get() - find the ifinfo from an orig_node * @orig_node: the orig node to be queried * @if_outgoing: the interface for which the ifinfo should be acquired @@ -942,6 +969,7 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, #ifdef CONFIG_BATMAN_ADV_MCAST orig_node->mcast_flags = BATADV_MCAST_WANT_NO_RTR4; orig_node->mcast_flags |= BATADV_MCAST_WANT_NO_RTR6; + orig_node->mcast_flags |= BATADV_MCAST_HAVE_MC_PTYPE_CAPA; INIT_HLIST_NODE(&orig_node->mcast_want_all_unsnoopables_node); INIT_HLIST_NODE(&orig_node->mcast_want_all_ipv4_node); INIT_HLIST_NODE(&orig_node->mcast_want_all_ipv6_node); diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index ea3d69e4e670..db0c55128170 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -36,6 +36,9 @@ void batadv_neigh_node_release(struct kref *ref); struct batadv_neigh_node * batadv_orig_router_get(struct batadv_orig_node *orig_node, const struct batadv_hard_iface *if_outgoing); +struct batadv_neigh_node * +batadv_orig_to_router(struct batadv_priv *bat_priv, u8 *orig_addr, + struct batadv_hard_iface *if_outgoing); struct batadv_neigh_ifinfo * batadv_neigh_ifinfo_new(struct batadv_neigh_node *neigh, struct batadv_hard_iface *if_outgoing); diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 163cd43c4821..f1061985149f 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1270,3 +1270,73 @@ out: batadv_orig_node_put(orig_node); return ret; } + +#ifdef CONFIG_BATMAN_ADV_MCAST +/** + * batadv_recv_mcast_packet() - process received batman-adv multicast packet + * @skb: the received batman-adv multicast packet + * @recv_if: interface that the skb is received on + * + * Parses the given, received batman-adv multicast packet. Depending on the + * contents of its TVLV forwards it and/or decapsulates it to hand it to the + * soft interface. + * + * Return: NET_RX_DROP if the skb is not consumed, NET_RX_SUCCESS otherwise. + */ +int batadv_recv_mcast_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if) +{ + struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); + struct batadv_mcast_packet *mcast_packet; + int hdr_size = sizeof(*mcast_packet); + unsigned char *tvlv_buff; + int ret = NET_RX_DROP; + u16 tvlv_buff_len; + + if (batadv_check_unicast_packet(bat_priv, skb, hdr_size) < 0) + goto free_skb; + + /* create a copy of the skb, if needed, to modify it. */ + if (skb_cow(skb, ETH_HLEN) < 0) + goto free_skb; + + /* packet needs to be linearized to access the tvlv content */ + if (skb_linearize(skb) < 0) + goto free_skb; + + mcast_packet = (struct batadv_mcast_packet *)skb->data; + if (mcast_packet->ttl-- < 2) + goto free_skb; + + tvlv_buff = (unsigned char *)(skb->data + hdr_size); + tvlv_buff_len = ntohs(mcast_packet->tvlv_len); + + if (tvlv_buff_len > skb->len - hdr_size) + goto free_skb; + + ret = batadv_tvlv_containers_process(bat_priv, BATADV_MCAST, NULL, skb, + tvlv_buff, tvlv_buff_len); + if (ret >= 0) { + batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_RX); + batadv_add_counter(bat_priv, BATADV_CNT_MCAST_RX_BYTES, + skb->len + ETH_HLEN); + } + + hdr_size += tvlv_buff_len; + + if (ret == NET_RX_SUCCESS && (skb->len - hdr_size >= ETH_HLEN)) { + batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_RX_LOCAL); + batadv_add_counter(bat_priv, BATADV_CNT_MCAST_RX_LOCAL_BYTES, + skb->len - hdr_size); + + batadv_interface_rx(bat_priv->soft_iface, skb, hdr_size, NULL); + /* skb was consumed */ + skb = NULL; + } + +free_skb: + kfree_skb(skb); + + return ret; +} +#endif /* CONFIG_BATMAN_ADV_MCAST */ diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index afd15b3879f1..e9849f032a24 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -27,6 +27,17 @@ int batadv_recv_frag_packet(struct sk_buff *skb, struct batadv_hard_iface *iface); int batadv_recv_bcast_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if); +#ifdef CONFIG_BATMAN_ADV_MCAST +int batadv_recv_mcast_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if); +#else +static inline int batadv_recv_mcast_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if) +{ + kfree_skb(skb); + return NET_RX_DROP; +} +#endif int batadv_recv_unicast_tvlv(struct sk_buff *skb, struct batadv_hard_iface *recv_if); int batadv_recv_unhandled_unicast_packet(struct sk_buff *skb, diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 1bf1232a4f75..89c51b3cf430 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -301,12 +301,13 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, send: if (do_bcast && !is_broadcast_ether_addr(ethhdr->h_dest)) { - forw_mode = batadv_mcast_forw_mode(bat_priv, skb, + forw_mode = batadv_mcast_forw_mode(bat_priv, skb, vid, &mcast_is_routable); switch (forw_mode) { case BATADV_FORW_BCAST: break; case BATADV_FORW_UCASTS: + case BATADV_FORW_MCAST: do_bcast = false; break; case BATADV_FORW_NONE: @@ -365,6 +366,8 @@ send: } else if (forw_mode == BATADV_FORW_UCASTS) { ret = batadv_mcast_forw_send(bat_priv, skb, vid, mcast_is_routable); + } else if (forw_mode == BATADV_FORW_MCAST) { + ret = batadv_mcast_forw_mcsend(bat_priv, skb); } else { if (batadv_dat_snoop_outgoing_arp_request(bat_priv, skb)) @@ -762,6 +765,7 @@ static int batadv_softif_init_late(struct net_device *dev) atomic_set(&bat_priv->mcast.num_want_all_unsnoopables, 0); atomic_set(&bat_priv->mcast.num_want_all_ipv4, 0); atomic_set(&bat_priv->mcast.num_want_all_ipv6, 0); + atomic_set(&bat_priv->mcast.num_no_mc_ptype_capa, 0); #endif atomic_set(&bat_priv->gw.mode, BATADV_GW_MODE_OFF); atomic_set(&bat_priv->gw.bandwidth_down, 100); @@ -925,6 +929,18 @@ static const struct { { "tt_response_rx" }, { "tt_roam_adv_tx" }, { "tt_roam_adv_rx" }, +#ifdef CONFIG_BATMAN_ADV_MCAST + { "mcast_tx" }, + { "mcast_tx_bytes" }, + { "mcast_tx_local" }, + { "mcast_tx_local_bytes" }, + { "mcast_rx" }, + { "mcast_rx_bytes" }, + { "mcast_rx_local" }, + { "mcast_rx_local_bytes" }, + { "mcast_fwd" }, + { "mcast_fwd_bytes" }, +#endif #ifdef CONFIG_BATMAN_ADV_DAT { "dat_get_tx" }, { "dat_get_rx" }, diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 17d5ea1d8e84..00840d5784fe 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -862,6 +862,70 @@ enum batadv_counters { */ BATADV_CNT_TT_ROAM_ADV_RX, +#ifdef CONFIG_BATMAN_ADV_MCAST + /** + * @BATADV_CNT_MCAST_TX: transmitted batman-adv multicast packets + * counter + */ + BATADV_CNT_MCAST_TX, + + /** + * @BATADV_CNT_MCAST_TX_BYTES: transmitted batman-adv multicast packets + * bytes counter + */ + BATADV_CNT_MCAST_TX_BYTES, + + /** + * @BATADV_CNT_MCAST_TX_LOCAL: counter for multicast packets which + * were locally encapsulated and transmitted as batman-adv multicast + * packets + */ + BATADV_CNT_MCAST_TX_LOCAL, + + /** + * @BATADV_CNT_MCAST_TX_LOCAL_BYTES: bytes counter for multicast packets + * which were locally encapsulated and transmitted as batman-adv + * multicast packets + */ + BATADV_CNT_MCAST_TX_LOCAL_BYTES, + + /** + * @BATADV_CNT_MCAST_RX: received batman-adv multicast packet counter + */ + BATADV_CNT_MCAST_RX, + + /** + * @BATADV_CNT_MCAST_RX_BYTES: received batman-adv multicast packet + * bytes counter + */ + BATADV_CNT_MCAST_RX_BYTES, + + /** + * @BATADV_CNT_MCAST_RX_LOCAL: counter for received batman-adv multicast + * packets which were forwarded to the local soft interface + */ + BATADV_CNT_MCAST_RX_LOCAL, + + /** + * @BATADV_CNT_MCAST_RX_LOCAL_BYTES: bytes counter for received + * batman-adv multicast packets which were forwarded to the local soft + * interface + */ + BATADV_CNT_MCAST_RX_LOCAL_BYTES, + + /** + * @BATADV_CNT_MCAST_FWD: counter for received batman-adv multicast + * packets which were forwarded to other, neighboring nodes + */ + BATADV_CNT_MCAST_FWD, + + /** + * @BATADV_CNT_MCAST_FWD_BYTES: bytes counter for received batman-adv + * multicast packets which were forwarded to other, neighboring nodes + */ + BATADV_CNT_MCAST_FWD_BYTES, +#endif + #ifdef CONFIG_BATMAN_ADV_DAT /** * @BATADV_CNT_DAT_GET_TX: transmitted dht GET traffic packet counter @@ -1279,6 +1343,12 @@ struct batadv_priv_mcast { atomic_t num_want_all_rtr6; /** + * @num_no_mc_ptype_capa: counter for number of nodes without the + * BATADV_MCAST_HAVE_MC_PTYPE_CAPA flag + */ + atomic_t num_no_mc_ptype_capa; + + /** * @want_lists_lock: lock for protecting modifications to mcasts * want_all_{unsnoopables,ipv4,ipv6}_list (traversals are rcu-locked) */ diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index c9fdcc5cdce1..711cf5d59816 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -542,7 +542,7 @@ struct bpf_fentry_test_t { int noinline bpf_fentry_test7(struct bpf_fentry_test_t *arg) { - asm volatile (""); + asm volatile ("": "+r"(arg)); return (long)arg; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 6b7f36769d03..051ea81864ac 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -186,6 +186,7 @@ enum { * struct net_bridge_vlan - per-vlan entry * * @vnode: rhashtable member + * @tnode: rhashtable member * @vid: VLAN id * @flags: bridge vlan flags * @priv_flags: private (in-kernel) bridge vlan flags @@ -196,6 +197,7 @@ enum { * @refcnt: if MASTER flag set, this is bumped for each port referencing it * @brvlan: if MASTER flag unset, this points to the global per-VLAN context * for this VLAN entry + * @tinfo: bridge tunnel info * @br_mcast_ctx: if MASTER flag set, this is the global vlan multicast context * @port_mcast_ctx: if MASTER flag unset, this is the per-port/vlan multicast * context diff --git a/net/core/Makefile b/net/core/Makefile index 0cb734cbc24b..821aec06abf1 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -18,7 +18,7 @@ obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o obj-y += net-sysfs.o -obj-$(CONFIG_PAGE_POOL) += page_pool.o +obj-$(CONFIG_PAGE_POOL) += page_pool.o page_pool_user.o obj-$(CONFIG_PROC_FS) += net-procfs.o obj-$(CONFIG_NET_PKTGEN) += pktgen.o obj-$(CONFIG_NETPOLL) += netpoll.o diff --git a/net/core/dev.c b/net/core/dev.c index c879246be48d..0432b04cf9b0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -165,7 +165,6 @@ static int netif_rx_internal(struct sk_buff *skb); static int call_netdevice_notifiers_extack(unsigned long val, struct net_device *dev, struct netlink_ext_ack *extack); -static struct napi_struct *napi_by_id(unsigned int napi_id); /* * The @dev_base_head list is protected by @dev_base_lock and the rtnl @@ -6139,7 +6138,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done) EXPORT_SYMBOL(napi_complete_done); /* must be called under rcu_read_lock(), as we dont take a reference */ -static struct napi_struct *napi_by_id(unsigned int napi_id) +struct napi_struct *napi_by_id(unsigned int napi_id) { unsigned int hash = napi_id % HASH_SIZE(napi_hash); struct napi_struct *napi; @@ -6400,6 +6399,43 @@ int dev_set_threaded(struct net_device *dev, bool threaded) } EXPORT_SYMBOL(dev_set_threaded); +/** + * netif_queue_set_napi - Associate queue with the napi + * @dev: device to which NAPI and queue belong + * @queue_index: Index of queue + * @type: queue type as RX or TX + * @napi: NAPI context, pass NULL to clear previously set NAPI + * + * Set queue with its corresponding napi context. This should be done after + * registering the NAPI handler for the queue-vector and the queues have been + * mapped to the corresponding interrupt vector. + */ +void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index, + enum netdev_queue_type type, struct napi_struct *napi) +{ + struct netdev_rx_queue *rxq; + struct netdev_queue *txq; + + if (WARN_ON_ONCE(napi && !napi->dev)) + return; + if (dev->reg_state >= NETREG_REGISTERED) + ASSERT_RTNL(); + + switch (type) { + case NETDEV_QUEUE_TYPE_RX: + rxq = __netif_get_rx_queue(dev, queue_index); + rxq->napi = napi; + return; + case NETDEV_QUEUE_TYPE_TX: + txq = netdev_get_tx_queue(dev, queue_index); + txq->napi = napi; + return; + default: + return; + } +} +EXPORT_SYMBOL(netif_queue_set_napi); + void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { @@ -6435,6 +6471,7 @@ void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, */ if (dev->threaded && napi_kthread_create(napi)) dev->threaded = 0; + netif_napi_set_irq(napi, -1); } EXPORT_SYMBOL(netif_napi_add_weight); @@ -10511,7 +10548,7 @@ void netdev_run_todo(void) write_lock(&dev_base_lock); dev->reg_state = NETREG_UNREGISTERED; write_unlock(&dev_base_lock); - linkwatch_forget_dev(dev); + linkwatch_sync_dev(dev); } while (!list_empty(&list)) { @@ -11236,17 +11273,19 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, dev_net_set(dev, net); dev->ifindex = new_ifindex; - /* Send a netdev-add uevent to the new namespace */ - kobject_uevent(&dev->dev.kobj, KOBJ_ADD); - netdev_adjacent_add_links(dev); - if (new_name[0]) /* Rename the netdev to prepared name */ strscpy(dev->name, new_name, IFNAMSIZ); /* Fixup kobjects */ + dev_set_uevent_suppress(&dev->dev, 1); err = device_rename(&dev->dev, dev->name); + dev_set_uevent_suppress(&dev->dev, 0); WARN_ON(err); + /* Send a netdev-add uevent to the new namespace */ + kobject_uevent(&dev->dev.kobj, KOBJ_ADD); + netdev_adjacent_add_links(dev); + /* Adapt owner in case owning user namespace of target network * namespace is different from the original one. */ @@ -11570,6 +11609,60 @@ static struct pernet_operations __net_initdata default_device_ops = { .exit_batch = default_device_exit_batch, }; +static void __init net_dev_struct_check(void) +{ + /* TX read-mostly hotpath */ + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, priv_flags); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, netdev_ops); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, header_ops); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, _tx); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, real_num_tx_queues); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_size); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_ipv4_max_size); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_segs); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, num_tc); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, mtu); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, needed_headroom); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tc_to_txq); +#ifdef CONFIG_XPS + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, xps_maps); +#endif +#ifdef CONFIG_NETFILTER_EGRESS + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, nf_hooks_egress); +#endif +#ifdef CONFIG_NET_XGRESS + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tcx_egress); +#endif + CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 152); + + /* TXRX read-mostly hotpath */ + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr); + CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 30); + + /* RX read-mostly hotpath */ + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ifindex); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, real_num_rx_queues); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, _rx); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_flush_timeout); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, napi_defer_hard_irqs); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_max_size); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_ipv4_max_size); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler_data); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, nd_net); +#ifdef CONFIG_NETPOLL + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, npinfo); +#endif +#ifdef CONFIG_NET_XGRESS + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, tcx_ingress); +#endif + CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_rx, 96); +} + /* * Initialize the DEV module. At boot time this walks the device list and * unhooks any devices that fail to initialise (normally hardware not @@ -11587,6 +11680,8 @@ static int __init net_dev_init(void) BUG_ON(!dev_boot_phase); + net_dev_struct_check(); + if (dev_proc_init()) goto out; diff --git a/net/core/dev.h b/net/core/dev.h index 5aa45f0fd4ae..cf93e188785b 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -30,7 +30,6 @@ int __init dev_proc_init(void); #endif void linkwatch_init_dev(struct net_device *dev); -void linkwatch_forget_dev(struct net_device *dev); void linkwatch_run_queue(void); void dev_addr_flush(struct net_device *dev); @@ -145,4 +144,6 @@ void xdp_do_check_flushed(struct napi_struct *napi); #else static inline void xdp_do_check_flushed(struct napi_struct *napi) { } #endif + +struct napi_struct *napi_by_id(unsigned int napi_id); #endif diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index feeddf95f450..9a66cf5015f2 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -322,9 +322,9 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr) * frames and not forward them), it must set IFF_SEE_ALL_HWTSTAMP_REQUESTS in * dev->priv_flags. */ -static int dev_set_hwtstamp_phylib(struct net_device *dev, - struct kernel_hwtstamp_config *cfg, - struct netlink_ext_ack *extack) +int dev_set_hwtstamp_phylib(struct net_device *dev, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; bool phy_ts = phy_has_hwtstamp(dev->phydev); @@ -363,6 +363,7 @@ static int dev_set_hwtstamp_phylib(struct net_device *dev, return 0; } +EXPORT_SYMBOL_GPL(dev_set_hwtstamp_phylib); static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr) { diff --git a/net/core/filter.c b/net/core/filter.c index 1737884be52f..eedb33f3e998 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7257,7 +7257,6 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len struct tcphdr *, th, u32, th_len) { #ifdef CONFIG_SYN_COOKIES - u32 cookie; int ret; if (unlikely(!sk || th_len < sizeof(*th))) @@ -7279,8 +7278,6 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len if (tcp_synq_no_recent_overflow(sk)) return -ENOENT; - cookie = ntohl(th->ack_seq) - 1; - /* Both struct iphdr and struct ipv6hdr have the version field at the * same offset so we can cast to the shorter header (struct iphdr). */ @@ -7289,7 +7286,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk)) return -EINVAL; - ret = __cookie_v4_check((struct iphdr *)iph, th, cookie); + ret = __cookie_v4_check((struct iphdr *)iph, th); break; #if IS_BUILTIN(CONFIG_IPV6) @@ -7300,7 +7297,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len if (sk->sk_family != AF_INET6) return -EINVAL; - ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie); + ret = __cookie_v6_check((struct ipv6hdr *)iph, th); break; #endif /* CONFIG_IPV6 */ @@ -7753,9 +7750,7 @@ static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv6_proto = { BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv4, struct iphdr *, iph, struct tcphdr *, th) { - u32 cookie = ntohl(th->ack_seq) - 1; - - if (__cookie_v4_check(iph, th, cookie) > 0) + if (__cookie_v4_check(iph, th) > 0) return 0; return -EACCES; @@ -7776,9 +7771,7 @@ BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv6, struct ipv6hdr *, iph, struct tcphdr *, th) { #if IS_BUILTIN(CONFIG_IPV6) - u32 cookie = ntohl(th->ack_seq) - 1; - - if (__cookie_v6_check(iph, th, cookie) > 0) + if (__cookie_v6_check(iph, th) > 0) return 0; return -EACCES; diff --git a/net/core/link_watch.c b/net/core/link_watch.c index c469d1c4db5d..7be5b3ab32bd 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -192,8 +192,6 @@ static void __linkwatch_run_queue(int urgent_only) #define MAX_DO_DEV_PER_LOOP 100 int do_dev = MAX_DO_DEV_PER_LOOP; - struct net_device *dev; - LIST_HEAD(wrk); /* Give urgent case more budget */ if (urgent_only) @@ -215,11 +213,11 @@ static void __linkwatch_run_queue(int urgent_only) clear_bit(LW_URGENT, &linkwatch_flags); spin_lock_irq(&lweventlist_lock); - list_splice_init(&lweventlist, &wrk); + while (!list_empty(&lweventlist) && do_dev > 0) { + struct net_device *dev; - while (!list_empty(&wrk) && do_dev > 0) { - - dev = list_first_entry(&wrk, struct net_device, link_watch_list); + dev = list_first_entry(&lweventlist, struct net_device, + link_watch_list); list_del_init(&dev->link_watch_list); if (!netif_device_present(dev) || @@ -237,15 +235,12 @@ static void __linkwatch_run_queue(int urgent_only) spin_lock_irq(&lweventlist_lock); } - /* Add the remaining work back to lweventlist */ - list_splice_init(&wrk, &lweventlist); - if (!list_empty(&lweventlist)) linkwatch_schedule_work(0); spin_unlock_irq(&lweventlist_lock); } -void linkwatch_forget_dev(struct net_device *dev) +void linkwatch_sync_dev(struct net_device *dev) { unsigned long flags; int clean = 0; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index fccaa5bac0ed..d9b33e923b18 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -194,8 +194,14 @@ static ssize_t carrier_show(struct device *dev, { struct net_device *netdev = to_net_dev(dev); - if (netif_running(netdev)) + if (netif_running(netdev)) { + /* Synchronize carrier state with link watch, + * see also rtnl_getlink(). + */ + linkwatch_sync_dev(netdev); + return sysfs_emit(buf, fmt_dec, !!netif_carrier_ok(netdev)); + } return -EINVAL; } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index f4183c4c1ec8..cb8bcbff9e83 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -1099,11 +1099,56 @@ out: rtnl_set_sk_err(net, RTNLGRP_NSID, err); } +#ifdef CONFIG_NET_NS +static void __init netns_ipv4_struct_check(void) +{ + /* TX readonly hotpath cache lines */ + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_tcp_early_retrans); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_tcp_tso_win_divisor); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_tcp_tso_rtt_log); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_tcp_autocorking); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_tcp_min_snd_mss); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_tcp_notsent_lowat); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_tcp_limit_output_bytes); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_tcp_min_rtt_wlen); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_tcp_wmem); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_ip_fwd_use_pmtu); + CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_tx, 33); + + /* TXRX readonly hotpath cache lines */ + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_txrx, + sysctl_tcp_moderate_rcvbuf); + CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_txrx, 1); + + /* RX readonly hotpath cache line */ + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, + sysctl_ip_early_demux); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, + sysctl_tcp_early_demux); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, + sysctl_tcp_reordering); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, + sysctl_tcp_rmem); + CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_rx, 18); +} +#endif + void __init net_ns_init(void) { struct net_generic *ng; #ifdef CONFIG_NET_NS + netns_ipv4_struct_check(); net_cachep = kmem_cache_create("net_namespace", sizeof(struct net), SMP_CACHE_BYTES, SLAB_PANIC|SLAB_ACCOUNT, NULL); diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index ea9231378aa6..be7f2ebd61b2 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -10,11 +10,64 @@ #include <uapi/linux/netdev.h> +/* Integer value ranges */ +static const struct netlink_range_validation netdev_a_page_pool_id_range = { + .min = 1ULL, + .max = 4294967295ULL, +}; + +static const struct netlink_range_validation netdev_a_page_pool_ifindex_range = { + .min = 1ULL, + .max = 2147483647ULL, +}; + +/* Common nested types */ +const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1] = { + [NETDEV_A_PAGE_POOL_ID] = NLA_POLICY_FULL_RANGE(NLA_UINT, &netdev_a_page_pool_id_range), + [NETDEV_A_PAGE_POOL_IFINDEX] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_page_pool_ifindex_range), +}; + /* NETDEV_CMD_DEV_GET - do */ static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = { [NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), }; +/* NETDEV_CMD_PAGE_POOL_GET - do */ +#ifdef CONFIG_PAGE_POOL +static const struct nla_policy netdev_page_pool_get_nl_policy[NETDEV_A_PAGE_POOL_ID + 1] = { + [NETDEV_A_PAGE_POOL_ID] = NLA_POLICY_FULL_RANGE(NLA_UINT, &netdev_a_page_pool_id_range), +}; +#endif /* CONFIG_PAGE_POOL */ + +/* NETDEV_CMD_PAGE_POOL_STATS_GET - do */ +#ifdef CONFIG_PAGE_POOL_STATS +static const struct nla_policy netdev_page_pool_stats_get_nl_policy[NETDEV_A_PAGE_POOL_STATS_INFO + 1] = { + [NETDEV_A_PAGE_POOL_STATS_INFO] = NLA_POLICY_NESTED(netdev_page_pool_info_nl_policy), +}; +#endif /* CONFIG_PAGE_POOL_STATS */ + +/* NETDEV_CMD_QUEUE_GET - do */ +static const struct nla_policy netdev_queue_get_do_nl_policy[NETDEV_A_QUEUE_TYPE + 1] = { + [NETDEV_A_QUEUE_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), + [NETDEV_A_QUEUE_TYPE] = NLA_POLICY_MAX(NLA_U32, 1), + [NETDEV_A_QUEUE_ID] = { .type = NLA_U32, }, +}; + +/* NETDEV_CMD_QUEUE_GET - dump */ +static const struct nla_policy netdev_queue_get_dump_nl_policy[NETDEV_A_QUEUE_IFINDEX + 1] = { + [NETDEV_A_QUEUE_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), +}; + +/* NETDEV_CMD_NAPI_GET - do */ +static const struct nla_policy netdev_napi_get_do_nl_policy[NETDEV_A_NAPI_ID + 1] = { + [NETDEV_A_NAPI_ID] = { .type = NLA_U32, }, +}; + +/* NETDEV_CMD_NAPI_GET - dump */ +static const struct nla_policy netdev_napi_get_dump_nl_policy[NETDEV_A_NAPI_IFINDEX + 1] = { + [NETDEV_A_NAPI_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), +}; + /* Ops table for netdev */ static const struct genl_split_ops netdev_nl_ops[] = { { @@ -29,10 +82,67 @@ static const struct genl_split_ops netdev_nl_ops[] = { .dumpit = netdev_nl_dev_get_dumpit, .flags = GENL_CMD_CAP_DUMP, }, +#ifdef CONFIG_PAGE_POOL + { + .cmd = NETDEV_CMD_PAGE_POOL_GET, + .doit = netdev_nl_page_pool_get_doit, + .policy = netdev_page_pool_get_nl_policy, + .maxattr = NETDEV_A_PAGE_POOL_ID, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = NETDEV_CMD_PAGE_POOL_GET, + .dumpit = netdev_nl_page_pool_get_dumpit, + .flags = GENL_CMD_CAP_DUMP, + }, +#endif /* CONFIG_PAGE_POOL */ +#ifdef CONFIG_PAGE_POOL_STATS + { + .cmd = NETDEV_CMD_PAGE_POOL_STATS_GET, + .doit = netdev_nl_page_pool_stats_get_doit, + .policy = netdev_page_pool_stats_get_nl_policy, + .maxattr = NETDEV_A_PAGE_POOL_STATS_INFO, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = NETDEV_CMD_PAGE_POOL_STATS_GET, + .dumpit = netdev_nl_page_pool_stats_get_dumpit, + .flags = GENL_CMD_CAP_DUMP, + }, +#endif /* CONFIG_PAGE_POOL_STATS */ + { + .cmd = NETDEV_CMD_QUEUE_GET, + .doit = netdev_nl_queue_get_doit, + .policy = netdev_queue_get_do_nl_policy, + .maxattr = NETDEV_A_QUEUE_TYPE, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = NETDEV_CMD_QUEUE_GET, + .dumpit = netdev_nl_queue_get_dumpit, + .policy = netdev_queue_get_dump_nl_policy, + .maxattr = NETDEV_A_QUEUE_IFINDEX, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = NETDEV_CMD_NAPI_GET, + .doit = netdev_nl_napi_get_doit, + .policy = netdev_napi_get_do_nl_policy, + .maxattr = NETDEV_A_NAPI_ID, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = NETDEV_CMD_NAPI_GET, + .dumpit = netdev_nl_napi_get_dumpit, + .policy = netdev_napi_get_dump_nl_policy, + .maxattr = NETDEV_A_NAPI_IFINDEX, + .flags = GENL_CMD_CAP_DUMP, + }, }; static const struct genl_multicast_group netdev_nl_mcgrps[] = { [NETDEV_NLGRP_MGMT] = { "mgmt", }, + [NETDEV_NLGRP_PAGE_POOL] = { "page-pool", }, }; struct genl_family netdev_nl_family __ro_after_init = { diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index 7b370c073e7d..a47f2bcbe4fa 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -11,11 +11,27 @@ #include <uapi/linux/netdev.h> +/* Common nested types */ +extern const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1]; + int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info); +int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int netdev_nl_page_pool_stats_get_doit(struct sk_buff *skb, + struct genl_info *info); +int netdev_nl_page_pool_stats_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info); +int netdev_nl_queue_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info); +int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); enum { NETDEV_NLGRP_MGMT, + NETDEV_NLGRP_PAGE_POOL, }; extern struct genl_family netdev_nl_family; diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index fe61f85bcf33..fd98936da3ae 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -6,13 +6,32 @@ #include <net/net_namespace.h> #include <net/sock.h> #include <net/xdp.h> +#include <net/xdp_sock.h> +#include <net/netdev_rx_queue.h> +#include <net/busy_poll.h> #include "netdev-genl-gen.h" +#include "dev.h" + +struct netdev_nl_dump_ctx { + unsigned long ifindex; + unsigned int rxq_idx; + unsigned int txq_idx; + unsigned int napi_id; +}; + +static struct netdev_nl_dump_ctx *netdev_dump_ctx(struct netlink_callback *cb) +{ + NL_ASSERT_DUMP_CTX_FITS(struct netdev_nl_dump_ctx); + + return (struct netdev_nl_dump_ctx *)cb->ctx; +} static int netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp, const struct genl_info *info) { + u64 xsk_features = 0; u64 xdp_rx_meta = 0; void *hdr; @@ -26,11 +45,20 @@ netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp, XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC + if (netdev->xsk_tx_metadata_ops) { + if (netdev->xsk_tx_metadata_ops->tmo_fill_timestamp) + xsk_features |= NETDEV_XSK_FLAGS_TX_TIMESTAMP; + if (netdev->xsk_tx_metadata_ops->tmo_request_checksum) + xsk_features |= NETDEV_XSK_FLAGS_TX_CHECKSUM; + } + if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) || nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_FEATURES, netdev->xdp_features, NETDEV_A_DEV_PAD) || nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_RX_METADATA_FEATURES, - xdp_rx_meta, NETDEV_A_DEV_PAD)) { + xdp_rx_meta, NETDEV_A_DEV_PAD) || + nla_put_u64_64bit(rsp, NETDEV_A_DEV_XSK_FEATURES, + xsk_features, NETDEV_A_DEV_PAD)) { genlmsg_cancel(rsp, hdr); return -EINVAL; } @@ -111,12 +139,13 @@ err_free_msg: int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { + struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb); struct net *net = sock_net(skb->sk); struct net_device *netdev; int err = 0; rtnl_lock(); - for_each_netdev_dump(net, netdev, cb->args[0]) { + for_each_netdev_dump(net, netdev, ctx->ifindex) { err = netdev_nl_dev_fill(netdev, skb, genl_info_dump(cb)); if (err < 0) break; @@ -129,6 +158,317 @@ int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } +static int +netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi, + const struct genl_info *info) +{ + void *hdr; + pid_t pid; + + if (WARN_ON_ONCE(!napi->dev)) + return -EINVAL; + if (!(napi->dev->flags & IFF_UP)) + return 0; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + + if (napi->napi_id >= MIN_NAPI_ID && + nla_put_u32(rsp, NETDEV_A_NAPI_ID, napi->napi_id)) + goto nla_put_failure; + + if (nla_put_u32(rsp, NETDEV_A_NAPI_IFINDEX, napi->dev->ifindex)) + goto nla_put_failure; + + if (napi->irq >= 0 && nla_put_u32(rsp, NETDEV_A_NAPI_IRQ, napi->irq)) + goto nla_put_failure; + + if (napi->thread) { + pid = task_pid_nr(napi->thread); + if (nla_put_u32(rsp, NETDEV_A_NAPI_PID, pid)) + goto nla_put_failure; + } + + genlmsg_end(rsp, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +} + +int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct napi_struct *napi; + struct sk_buff *rsp; + u32 napi_id; + int err; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_NAPI_ID)) + return -EINVAL; + + napi_id = nla_get_u32(info->attrs[NETDEV_A_NAPI_ID]); + + rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!rsp) + return -ENOMEM; + + rtnl_lock(); + + napi = napi_by_id(napi_id); + if (napi) + err = netdev_nl_napi_fill_one(rsp, napi, info); + else + err = -EINVAL; + + rtnl_unlock(); + + if (err) + goto err_free_msg; + + return genlmsg_reply(rsp, info); + +err_free_msg: + nlmsg_free(rsp); + return err; +} + +static int +netdev_nl_napi_dump_one(struct net_device *netdev, struct sk_buff *rsp, + const struct genl_info *info, + struct netdev_nl_dump_ctx *ctx) +{ + struct napi_struct *napi; + int err = 0; + + if (!(netdev->flags & IFF_UP)) + return err; + + list_for_each_entry(napi, &netdev->napi_list, dev_list) { + if (ctx->napi_id && napi->napi_id >= ctx->napi_id) + continue; + + err = netdev_nl_napi_fill_one(rsp, napi, info); + if (err) + return err; + ctx->napi_id = napi->napi_id; + } + return err; +} + +int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb); + const struct genl_info *info = genl_info_dump(cb); + struct net *net = sock_net(skb->sk); + struct net_device *netdev; + u32 ifindex = 0; + int err = 0; + + if (info->attrs[NETDEV_A_NAPI_IFINDEX]) + ifindex = nla_get_u32(info->attrs[NETDEV_A_NAPI_IFINDEX]); + + rtnl_lock(); + if (ifindex) { + netdev = __dev_get_by_index(net, ifindex); + if (netdev) + err = netdev_nl_napi_dump_one(netdev, skb, info, ctx); + else + err = -ENODEV; + } else { + for_each_netdev_dump(net, netdev, ctx->ifindex) { + err = netdev_nl_napi_dump_one(netdev, skb, info, ctx); + if (err < 0) + break; + ctx->napi_id = 0; + } + } + rtnl_unlock(); + + if (err != -EMSGSIZE) + return err; + + return skb->len; +} + +static int +netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, + u32 q_idx, u32 q_type, const struct genl_info *info) +{ + struct netdev_rx_queue *rxq; + struct netdev_queue *txq; + void *hdr; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_u32(rsp, NETDEV_A_QUEUE_ID, q_idx) || + nla_put_u32(rsp, NETDEV_A_QUEUE_TYPE, q_type) || + nla_put_u32(rsp, NETDEV_A_QUEUE_IFINDEX, netdev->ifindex)) + goto nla_put_failure; + + switch (q_type) { + case NETDEV_QUEUE_TYPE_RX: + rxq = __netif_get_rx_queue(netdev, q_idx); + if (rxq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID, + rxq->napi->napi_id)) + goto nla_put_failure; + break; + case NETDEV_QUEUE_TYPE_TX: + txq = netdev_get_tx_queue(netdev, q_idx); + if (txq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID, + txq->napi->napi_id)) + goto nla_put_failure; + } + + genlmsg_end(rsp, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +} + +static int netdev_nl_queue_validate(struct net_device *netdev, u32 q_id, + u32 q_type) +{ + switch (q_type) { + case NETDEV_QUEUE_TYPE_RX: + if (q_id >= netdev->real_num_rx_queues) + return -EINVAL; + return 0; + case NETDEV_QUEUE_TYPE_TX: + if (q_id >= netdev->real_num_tx_queues) + return -EINVAL; + } + return 0; +} + +static int +netdev_nl_queue_fill(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx, + u32 q_type, const struct genl_info *info) +{ + int err = 0; + + if (!(netdev->flags & IFF_UP)) + return err; + + err = netdev_nl_queue_validate(netdev, q_idx, q_type); + if (err) + return err; + + return netdev_nl_queue_fill_one(rsp, netdev, q_idx, q_type, info); +} + +int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + u32 q_id, q_type, ifindex; + struct net_device *netdev; + struct sk_buff *rsp; + int err; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_ID) || + GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_TYPE) || + GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_IFINDEX)) + return -EINVAL; + + q_id = nla_get_u32(info->attrs[NETDEV_A_QUEUE_ID]); + q_type = nla_get_u32(info->attrs[NETDEV_A_QUEUE_TYPE]); + ifindex = nla_get_u32(info->attrs[NETDEV_A_QUEUE_IFINDEX]); + + rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!rsp) + return -ENOMEM; + + rtnl_lock(); + + netdev = __dev_get_by_index(genl_info_net(info), ifindex); + if (netdev) + err = netdev_nl_queue_fill(rsp, netdev, q_id, q_type, info); + else + err = -ENODEV; + + rtnl_unlock(); + + if (err) + goto err_free_msg; + + return genlmsg_reply(rsp, info); + +err_free_msg: + nlmsg_free(rsp); + return err; +} + +static int +netdev_nl_queue_dump_one(struct net_device *netdev, struct sk_buff *rsp, + const struct genl_info *info, + struct netdev_nl_dump_ctx *ctx) +{ + int err = 0; + int i; + + if (!(netdev->flags & IFF_UP)) + return err; + + for (i = ctx->rxq_idx; i < netdev->real_num_rx_queues;) { + err = netdev_nl_queue_fill_one(rsp, netdev, i, + NETDEV_QUEUE_TYPE_RX, info); + if (err) + return err; + ctx->rxq_idx = i++; + } + for (i = ctx->txq_idx; i < netdev->real_num_tx_queues;) { + err = netdev_nl_queue_fill_one(rsp, netdev, i, + NETDEV_QUEUE_TYPE_TX, info); + if (err) + return err; + ctx->txq_idx = i++; + } + + return err; +} + +int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb); + const struct genl_info *info = genl_info_dump(cb); + struct net *net = sock_net(skb->sk); + struct net_device *netdev; + u32 ifindex = 0; + int err = 0; + + if (info->attrs[NETDEV_A_QUEUE_IFINDEX]) + ifindex = nla_get_u32(info->attrs[NETDEV_A_QUEUE_IFINDEX]); + + rtnl_lock(); + if (ifindex) { + netdev = __dev_get_by_index(net, ifindex); + if (netdev) + err = netdev_nl_queue_dump_one(netdev, skb, info, ctx); + else + err = -ENODEV; + } else { + for_each_netdev_dump(net, netdev, ctx->ifindex) { + err = netdev_nl_queue_dump_one(netdev, skb, info, ctx); + if (err < 0) + break; + ctx->rxq_idx = 0; + ctx->txq_idx = 0; + } + } + rtnl_unlock(); + + if (err != -EMSGSIZE) + return err; + + return skb->len; +} + static int netdev_genl_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { diff --git a/net/core/page_pool.c b/net/core/page_pool.c index dec544337236..c2e7c9a6efbe 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -23,6 +23,8 @@ #include <trace/events/page_pool.h> +#include "page_pool_priv.h" + #define DEFER_TIME (msecs_to_jiffies(1000)) #define DEFER_WARN_INTERVAL (60 * HZ) @@ -69,7 +71,7 @@ static const char pp_stats[][ETH_GSTRING_LEN] = { * is passed to this API which is filled in. The caller can then report * those stats to the user (perhaps via ethtool, debugfs, etc.). */ -bool page_pool_get_stats(struct page_pool *pool, +bool page_pool_get_stats(const struct page_pool *pool, struct page_pool_stats *stats) { int cpu = 0; @@ -173,7 +175,8 @@ static int page_pool_init(struct page_pool *pool, { unsigned int ring_qsize = 1024; /* Default */ - memcpy(&pool->p, params, sizeof(pool->p)); + memcpy(&pool->p, ¶ms->fast, sizeof(pool->p)); + memcpy(&pool->slow, ¶ms->slow, sizeof(pool->slow)); /* Validate only known flags were used */ if (pool->p.flags & ~(PP_FLAG_ALL)) @@ -211,6 +214,8 @@ static int page_pool_init(struct page_pool *pool, */ } + pool->has_init_callback = !!pool->slow.init_callback; + #ifdef CONFIG_PAGE_POOL_STATS pool->recycle_stats = alloc_percpu(struct page_pool_recycle_stats); if (!pool->recycle_stats) @@ -235,6 +240,18 @@ static int page_pool_init(struct page_pool *pool, return 0; } +static void page_pool_uninit(struct page_pool *pool) +{ + ptr_ring_cleanup(&pool->ring, NULL); + + if (pool->p.flags & PP_FLAG_DMA_MAP) + put_device(pool->p.dev); + +#ifdef CONFIG_PAGE_POOL_STATS + free_percpu(pool->recycle_stats); +#endif +} + /** * page_pool_create() - create a page pool. * @params: parameters, see struct page_pool_params @@ -249,13 +266,21 @@ struct page_pool *page_pool_create(const struct page_pool_params *params) return ERR_PTR(-ENOMEM); err = page_pool_init(pool, params); - if (err < 0) { - pr_warn("%s() gave up with errno %d\n", __func__, err); - kfree(pool); - return ERR_PTR(err); - } + if (err < 0) + goto err_free; + + err = page_pool_list(pool); + if (err) + goto err_uninit; return pool; + +err_uninit: + page_pool_uninit(pool); +err_free: + pr_warn("%s() gave up with errno %d\n", __func__, err); + kfree(pool); + return ERR_PTR(err); } EXPORT_SYMBOL(page_pool_create); @@ -388,8 +413,8 @@ static void page_pool_set_pp_info(struct page_pool *pool, * the overhead is negligible. */ page_pool_fragment_page(page, 1); - if (pool->p.init_callback) - pool->p.init_callback(page, pool->p.init_arg); + if (pool->has_init_callback) + pool->slow.init_callback(page, pool->slow.init_arg); } static void page_pool_clear_pp_info(struct page *page) @@ -504,7 +529,7 @@ EXPORT_SYMBOL(page_pool_alloc_pages); */ #define _distance(a, b) (s32)((a) - (b)) -static s32 page_pool_inflight(struct page_pool *pool) +s32 page_pool_inflight(const struct page_pool *pool, bool strict) { u32 release_cnt = atomic_read(&pool->pages_state_release_cnt); u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt); @@ -512,8 +537,13 @@ static s32 page_pool_inflight(struct page_pool *pool) inflight = _distance(hold_cnt, release_cnt); - trace_page_pool_release(pool, inflight, hold_cnt, release_cnt); - WARN(inflight < 0, "Negative(%d) inflight packet-pages", inflight); + if (strict) { + trace_page_pool_release(pool, inflight, hold_cnt, release_cnt); + WARN(inflight < 0, "Negative(%d) inflight packet-pages", + inflight); + } else { + inflight = max(0, inflight); + } return inflight; } @@ -818,14 +848,8 @@ static void __page_pool_destroy(struct page_pool *pool) if (pool->disconnect) pool->disconnect(pool); - ptr_ring_cleanup(&pool->ring, NULL); - - if (pool->p.flags & PP_FLAG_DMA_MAP) - put_device(pool->p.dev); - -#ifdef CONFIG_PAGE_POOL_STATS - free_percpu(pool->recycle_stats); -#endif + page_pool_unlist(pool); + page_pool_uninit(pool); kfree(pool); } @@ -862,7 +886,7 @@ static int page_pool_release(struct page_pool *pool) int inflight; page_pool_scrub(pool); - inflight = page_pool_inflight(pool); + inflight = page_pool_inflight(pool, true); if (!inflight) __page_pool_destroy(pool); @@ -873,18 +897,21 @@ static void page_pool_release_retry(struct work_struct *wq) { struct delayed_work *dwq = to_delayed_work(wq); struct page_pool *pool = container_of(dwq, typeof(*pool), release_dw); + void *netdev; int inflight; inflight = page_pool_release(pool); if (!inflight) return; - /* Periodic warning */ - if (time_after_eq(jiffies, pool->defer_warn)) { + /* Periodic warning for page pools the user can't see */ + netdev = READ_ONCE(pool->slow.netdev); + if (time_after_eq(jiffies, pool->defer_warn) && + (!netdev || netdev == NET_PTR_POISON)) { int sec = (s32)((u32)jiffies - (u32)pool->defer_start) / HZ; - pr_warn("%s() stalled pool shutdown %d inflight %d sec\n", - __func__, inflight, sec); + pr_warn("%s() stalled pool shutdown: id %u, %d inflight %d sec\n", + __func__, pool->user.id, inflight, sec); pool->defer_warn = jiffies + DEFER_WARN_INTERVAL; } @@ -929,6 +956,7 @@ void page_pool_destroy(struct page_pool *pool) if (!page_pool_release(pool)) return; + page_pool_detached(pool); pool->defer_start = jiffies; pool->defer_warn = jiffies + DEFER_WARN_INTERVAL; diff --git a/net/core/page_pool_priv.h b/net/core/page_pool_priv.h new file mode 100644 index 000000000000..90665d40f1eb --- /dev/null +++ b/net/core/page_pool_priv.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __PAGE_POOL_PRIV_H +#define __PAGE_POOL_PRIV_H + +s32 page_pool_inflight(const struct page_pool *pool, bool strict); + +int page_pool_list(struct page_pool *pool); +void page_pool_detached(struct page_pool *pool); +void page_pool_unlist(struct page_pool *pool); + +#endif diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c new file mode 100644 index 000000000000..ffe5244e5597 --- /dev/null +++ b/net/core/page_pool_user.c @@ -0,0 +1,410 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/mutex.h> +#include <linux/netdevice.h> +#include <linux/xarray.h> +#include <net/net_debug.h> +#include <net/page_pool/types.h> +#include <net/page_pool/helpers.h> +#include <net/sock.h> + +#include "page_pool_priv.h" +#include "netdev-genl-gen.h" + +static DEFINE_XARRAY_FLAGS(page_pools, XA_FLAGS_ALLOC1); +/* Protects: page_pools, netdevice->page_pools, pool->slow.netdev, pool->user. + * Ordering: inside rtnl_lock + */ +static DEFINE_MUTEX(page_pools_lock); + +/* Page pools are only reachable from user space (via netlink) if they are + * linked to a netdev at creation time. Following page pool "visibility" + * states are possible: + * - normal + * - user.list: linked to real netdev, netdev: real netdev + * - orphaned - real netdev has disappeared + * - user.list: linked to lo, netdev: lo + * - invisible - either (a) created without netdev linking, (b) unlisted due + * to error, or (c) the entire namespace which owned this pool disappeared + * - user.list: unhashed, netdev: unknown + */ + +typedef int (*pp_nl_fill_cb)(struct sk_buff *rsp, const struct page_pool *pool, + const struct genl_info *info); + +static int +netdev_nl_page_pool_get_do(struct genl_info *info, u32 id, pp_nl_fill_cb fill) +{ + struct page_pool *pool; + struct sk_buff *rsp; + int err; + + mutex_lock(&page_pools_lock); + pool = xa_load(&page_pools, id); + if (!pool || hlist_unhashed(&pool->user.list) || + !net_eq(dev_net(pool->slow.netdev), genl_info_net(info))) { + err = -ENOENT; + goto err_unlock; + } + + rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!rsp) { + err = -ENOMEM; + goto err_unlock; + } + + err = fill(rsp, pool, info); + if (err) + goto err_free_msg; + + mutex_unlock(&page_pools_lock); + + return genlmsg_reply(rsp, info); + +err_free_msg: + nlmsg_free(rsp); +err_unlock: + mutex_unlock(&page_pools_lock); + return err; +} + +struct page_pool_dump_cb { + unsigned long ifindex; + u32 pp_id; +}; + +static int +netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb, + pp_nl_fill_cb fill) +{ + struct page_pool_dump_cb *state = (void *)cb->ctx; + const struct genl_info *info = genl_info_dump(cb); + struct net *net = sock_net(skb->sk); + struct net_device *netdev; + struct page_pool *pool; + int err = 0; + + rtnl_lock(); + mutex_lock(&page_pools_lock); + for_each_netdev_dump(net, netdev, state->ifindex) { + hlist_for_each_entry(pool, &netdev->page_pools, user.list) { + if (state->pp_id && state->pp_id < pool->user.id) + continue; + + state->pp_id = pool->user.id; + err = fill(skb, pool, info); + if (err) + break; + } + + state->pp_id = 0; + } + mutex_unlock(&page_pools_lock); + rtnl_unlock(); + + if (skb->len && err == -EMSGSIZE) + return skb->len; + return err; +} + +static int +page_pool_nl_stats_fill(struct sk_buff *rsp, const struct page_pool *pool, + const struct genl_info *info) +{ +#ifdef CONFIG_PAGE_POOL_STATS + struct page_pool_stats stats = {}; + struct nlattr *nest; + void *hdr; + + if (!page_pool_get_stats(pool, &stats)) + return 0; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + + nest = nla_nest_start(rsp, NETDEV_A_PAGE_POOL_STATS_INFO); + + if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_ID, pool->user.id) || + (pool->slow.netdev->ifindex != LOOPBACK_IFINDEX && + nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX, + pool->slow.netdev->ifindex))) + goto err_cancel_nest; + + nla_nest_end(rsp, nest); + + if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST, + stats.alloc_stats.fast) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW, + stats.alloc_stats.slow) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER, + stats.alloc_stats.slow_high_order) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY, + stats.alloc_stats.empty) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL, + stats.alloc_stats.refill) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE, + stats.alloc_stats.waive) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED, + stats.recycle_stats.cached) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL, + stats.recycle_stats.cache_full) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING, + stats.recycle_stats.ring) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL, + stats.recycle_stats.ring_full) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT, + stats.recycle_stats.released_refcnt)) + goto err_cancel_msg; + + genlmsg_end(rsp, hdr); + + return 0; +err_cancel_nest: + nla_nest_cancel(rsp, nest); +err_cancel_msg: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +#else + GENL_SET_ERR_MSG(info, "kernel built without CONFIG_PAGE_POOL_STATS"); + return -EOPNOTSUPP; +#endif +} + +int netdev_nl_page_pool_stats_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct nlattr *tb[ARRAY_SIZE(netdev_page_pool_info_nl_policy)]; + struct nlattr *nest; + int err; + u32 id; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_PAGE_POOL_STATS_INFO)) + return -EINVAL; + + nest = info->attrs[NETDEV_A_PAGE_POOL_STATS_INFO]; + err = nla_parse_nested(tb, ARRAY_SIZE(tb) - 1, nest, + netdev_page_pool_info_nl_policy, + info->extack); + if (err) + return err; + + if (NL_REQ_ATTR_CHECK(info->extack, nest, tb, NETDEV_A_PAGE_POOL_ID)) + return -EINVAL; + if (tb[NETDEV_A_PAGE_POOL_IFINDEX]) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[NETDEV_A_PAGE_POOL_IFINDEX], + "selecting by ifindex not supported"); + return -EINVAL; + } + + id = nla_get_uint(tb[NETDEV_A_PAGE_POOL_ID]); + + return netdev_nl_page_pool_get_do(info, id, page_pool_nl_stats_fill); +} + +int netdev_nl_page_pool_stats_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return netdev_nl_page_pool_get_dump(skb, cb, page_pool_nl_stats_fill); +} + +static int +page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, + const struct genl_info *info) +{ + size_t inflight, refsz; + void *hdr; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_ID, pool->user.id)) + goto err_cancel; + + if (pool->slow.netdev->ifindex != LOOPBACK_IFINDEX && + nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX, + pool->slow.netdev->ifindex)) + goto err_cancel; + if (pool->user.napi_id && + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, pool->user.napi_id)) + goto err_cancel; + + inflight = page_pool_inflight(pool, false); + refsz = PAGE_SIZE << pool->p.order; + if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT, inflight) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT_MEM, + inflight * refsz)) + goto err_cancel; + if (pool->user.detach_time && + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_DETACH_TIME, + pool->user.detach_time)) + goto err_cancel; + + genlmsg_end(rsp, hdr); + + return 0; +err_cancel: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +} + +static void netdev_nl_page_pool_event(const struct page_pool *pool, u32 cmd) +{ + struct genl_info info; + struct sk_buff *ntf; + struct net *net; + + lockdep_assert_held(&page_pools_lock); + + /* 'invisible' page pools don't matter */ + if (hlist_unhashed(&pool->user.list)) + return; + net = dev_net(pool->slow.netdev); + + if (!genl_has_listeners(&netdev_nl_family, net, NETDEV_NLGRP_PAGE_POOL)) + return; + + genl_info_init_ntf(&info, &netdev_nl_family, cmd); + + ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!ntf) + return; + + if (page_pool_nl_fill(ntf, pool, &info)) { + nlmsg_free(ntf); + return; + } + + genlmsg_multicast_netns(&netdev_nl_family, net, ntf, + 0, NETDEV_NLGRP_PAGE_POOL, GFP_KERNEL); +} + +int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + u32 id; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_PAGE_POOL_ID)) + return -EINVAL; + + id = nla_get_uint(info->attrs[NETDEV_A_PAGE_POOL_ID]); + + return netdev_nl_page_pool_get_do(info, id, page_pool_nl_fill); +} + +int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return netdev_nl_page_pool_get_dump(skb, cb, page_pool_nl_fill); +} + +int page_pool_list(struct page_pool *pool) +{ + static u32 id_alloc_next; + int err; + + mutex_lock(&page_pools_lock); + err = xa_alloc_cyclic(&page_pools, &pool->user.id, pool, xa_limit_32b, + &id_alloc_next, GFP_KERNEL); + if (err < 0) + goto err_unlock; + + INIT_HLIST_NODE(&pool->user.list); + if (pool->slow.netdev) { + hlist_add_head(&pool->user.list, + &pool->slow.netdev->page_pools); + pool->user.napi_id = pool->p.napi ? pool->p.napi->napi_id : 0; + + netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_ADD_NTF); + } + + mutex_unlock(&page_pools_lock); + return 0; + +err_unlock: + mutex_unlock(&page_pools_lock); + return err; +} + +void page_pool_detached(struct page_pool *pool) +{ + mutex_lock(&page_pools_lock); + pool->user.detach_time = ktime_get_boottime_seconds(); + netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_CHANGE_NTF); + mutex_unlock(&page_pools_lock); +} + +void page_pool_unlist(struct page_pool *pool) +{ + mutex_lock(&page_pools_lock); + netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_DEL_NTF); + xa_erase(&page_pools, pool->user.id); + if (!hlist_unhashed(&pool->user.list)) + hlist_del(&pool->user.list); + mutex_unlock(&page_pools_lock); +} + +static void page_pool_unreg_netdev_wipe(struct net_device *netdev) +{ + struct page_pool *pool; + struct hlist_node *n; + + mutex_lock(&page_pools_lock); + hlist_for_each_entry_safe(pool, n, &netdev->page_pools, user.list) { + hlist_del_init(&pool->user.list); + pool->slow.netdev = NET_PTR_POISON; + } + mutex_unlock(&page_pools_lock); +} + +static void page_pool_unreg_netdev(struct net_device *netdev) +{ + struct page_pool *pool, *last; + struct net_device *lo; + + lo = dev_net(netdev)->loopback_dev; + + mutex_lock(&page_pools_lock); + last = NULL; + hlist_for_each_entry(pool, &netdev->page_pools, user.list) { + pool->slow.netdev = lo; + netdev_nl_page_pool_event(pool, + NETDEV_CMD_PAGE_POOL_CHANGE_NTF); + last = pool; + } + if (last) + hlist_splice_init(&netdev->page_pools, &last->user.list, + &lo->page_pools); + mutex_unlock(&page_pools_lock); +} + +static int +page_pool_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + + if (event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + + if (hlist_empty(&netdev->page_pools)) + return NOTIFY_OK; + + if (netdev->ifindex != LOOPBACK_IFINDEX) + page_pool_unreg_netdev(netdev); + else + page_pool_unreg_netdev_wipe(netdev); + return NOTIFY_OK; +} + +static struct notifier_block page_pool_netdevice_nb = { + .notifier_call = page_pool_netdevice_event, +}; + +static int __init page_pool_user_init(void) +{ + return register_netdevice_notifier(&page_pool_netdevice_nb); +} + +subsys_initcall(page_pool_user_init); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e8431c6c8490..5e0ab4c08f72 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3849,10 +3849,18 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, goto out; err = -ENOBUFS; - nskb = nlmsg_new(if_nlmsg_size(dev, ext_filter_mask), GFP_KERNEL); + nskb = nlmsg_new_large(if_nlmsg_size(dev, ext_filter_mask)); if (nskb == NULL) goto out; + /* Synchronize the carrier state so we don't report a state + * that we're not actually going to honour immediately; if + * the driver just did a carrier off->on transition, we can + * only TX if link watch work has run, but without this we'd + * already report carrier on, even if it doesn't work yet. + */ + linkwatch_sync_dev(dev); + err = rtnl_fill_ifinfo(nskb, dev, net, RTM_NEWLINK, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, 0, ext_filter_mask, diff --git a/net/devlink/core.c b/net/devlink/core.c index 6984877e9f10..4275a2bc6d8e 100644 --- a/net/devlink/core.c +++ b/net/devlink/core.c @@ -503,14 +503,14 @@ static void __net_exit devlink_pernet_pre_exit(struct net *net) * all devlink instances from this namespace into init_net. */ devlinks_xa_for_each_registered_get(net, index, devlink) { - devl_lock(devlink); + devl_dev_lock(devlink, true); err = 0; if (devl_is_registered(devlink)) err = devlink_reload(devlink, &init_net, DEVLINK_RELOAD_ACTION_DRIVER_REINIT, DEVLINK_RELOAD_LIMIT_UNSPEC, &actions_performed, NULL); - devl_unlock(devlink); + devl_dev_unlock(devlink, true); devlink_put(devlink); if (err && err != -EOPNOTSUPP) pr_warn("Failed to reload devlink instance into init_net\n"); diff --git a/net/devlink/dev.c b/net/devlink/dev.c index 4fc7adb32663..918a0395b03e 100644 --- a/net/devlink/dev.c +++ b/net/devlink/dev.c @@ -4,6 +4,7 @@ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> */ +#include <linux/device.h> #include <net/genetlink.h> #include <net/sock.h> #include "devl_internal.h" @@ -424,6 +425,18 @@ static void devlink_reload_netns_change(struct devlink *devlink, devlink_rel_nested_in_notify(devlink); } +static void devlink_reload_reinit_sanity_check(struct devlink *devlink) +{ + WARN_ON(!list_empty(&devlink->trap_policer_list)); + WARN_ON(!list_empty(&devlink->trap_group_list)); + WARN_ON(!list_empty(&devlink->trap_list)); + WARN_ON(!list_empty(&devlink->dpipe_table_list)); + WARN_ON(!list_empty(&devlink->sb_list)); + WARN_ON(!list_empty(&devlink->rate_list)); + WARN_ON(!list_empty(&devlink->linecard_list)); + WARN_ON(!xa_empty(&devlink->ports)); +} + int devlink_reload(struct devlink *devlink, struct net *dest_net, enum devlink_reload_action action, enum devlink_reload_limit limit, @@ -433,6 +446,13 @@ int devlink_reload(struct devlink *devlink, struct net *dest_net, struct net *curr_net; int err; + /* Make sure the reload operations are invoked with the device lock + * held to allow drivers to trigger functionality that expects it + * (e.g., PCI reset) and to close possible races between these + * operations and probe/remove. + */ + device_lock_assert(devlink->dev); + memcpy(remote_reload_stats, devlink->stats.remote_reload_stats, sizeof(remote_reload_stats)); @@ -444,8 +464,10 @@ int devlink_reload(struct devlink *devlink, struct net *dest_net, if (dest_net && !net_eq(dest_net, curr_net)) devlink_reload_netns_change(devlink, curr_net, dest_net); - if (action == DEVLINK_RELOAD_ACTION_DRIVER_REINIT) + if (action == DEVLINK_RELOAD_ACTION_DRIVER_REINIT) { devlink_params_driverinit_load_new(devlink); + devlink_reload_reinit_sanity_check(devlink); + } err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack); devlink_reload_failed_set(devlink, !!err); diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h index 183dbe3807ab..5ea2e2012e93 100644 --- a/net/devlink/devl_internal.h +++ b/net/devlink/devl_internal.h @@ -3,6 +3,7 @@ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> */ +#include <linux/device.h> #include <linux/etherdevice.h> #include <linux/mutex.h> #include <linux/netdevice.h> @@ -96,6 +97,20 @@ static inline bool devl_is_registered(struct devlink *devlink) return xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); } +static inline void devl_dev_lock(struct devlink *devlink, bool dev_lock) +{ + if (dev_lock) + device_lock(devlink->dev); + devl_lock(devlink); +} + +static inline void devl_dev_unlock(struct devlink *devlink, bool dev_lock) +{ + devl_unlock(devlink); + if (dev_lock) + device_unlock(devlink->dev); +} + typedef void devlink_rel_notify_cb_t(struct devlink *devlink, u32 obj_index); typedef void devlink_rel_cleanup_cb_t(struct devlink *devlink, u32 obj_index, u32 rel_index); @@ -111,9 +126,6 @@ int devlink_rel_devlink_handle_put(struct sk_buff *msg, struct devlink *devlink, bool *msg_updated); /* Netlink */ -#define DEVLINK_NL_FLAG_NEED_PORT BIT(0) -#define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT BIT(1) - enum devlink_multicast_groups { DEVLINK_MCGRP_CONFIG, }; @@ -140,7 +152,8 @@ typedef int devlink_nl_dump_one_func_t(struct sk_buff *msg, int flags); struct devlink * -devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs); +devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs, + bool dev_lock); int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb, devlink_nl_dump_one_func_t *dump_one); diff --git a/net/devlink/health.c b/net/devlink/health.c index 695df61f8ac2..71ae121dc739 100644 --- a/net/devlink/health.c +++ b/net/devlink/health.c @@ -1151,7 +1151,8 @@ devlink_health_reporter_get_from_cb_lock(struct netlink_callback *cb) struct nlattr **attrs = info->attrs; struct devlink *devlink; - devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs); + devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs, + false); if (IS_ERR(devlink)) return NULL; diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c index d0b90ebc8b15..fa9afe3e6d9b 100644 --- a/net/devlink/netlink.c +++ b/net/devlink/netlink.c @@ -9,6 +9,10 @@ #include "devl_internal.h" +#define DEVLINK_NL_FLAG_NEED_PORT BIT(0) +#define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT BIT(1) +#define DEVLINK_NL_FLAG_NEED_DEV_LOCK BIT(2) + static const struct genl_multicast_group devlink_nl_mcgrps[] = { [DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME }, }; @@ -61,7 +65,8 @@ int devlink_nl_msg_reply_and_new(struct sk_buff **msg, struct genl_info *info) } struct devlink * -devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs) +devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs, + bool dev_lock) { struct devlink *devlink; unsigned long index; @@ -75,12 +80,12 @@ devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs) devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]); devlinks_xa_for_each_registered_get(net, index, devlink) { - devl_lock(devlink); + devl_dev_lock(devlink, dev_lock); if (devl_is_registered(devlink) && strcmp(devlink->dev->bus->name, busname) == 0 && strcmp(dev_name(devlink->dev), devname) == 0) return devlink; - devl_unlock(devlink); + devl_dev_unlock(devlink, dev_lock); devlink_put(devlink); } @@ -90,11 +95,13 @@ devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs) static int __devlink_nl_pre_doit(struct sk_buff *skb, struct genl_info *info, u8 flags) { + bool dev_lock = flags & DEVLINK_NL_FLAG_NEED_DEV_LOCK; struct devlink_port *devlink_port; struct devlink *devlink; int err; - devlink = devlink_get_from_attrs_lock(genl_info_net(info), info->attrs); + devlink = devlink_get_from_attrs_lock(genl_info_net(info), info->attrs, + dev_lock); if (IS_ERR(devlink)) return PTR_ERR(devlink); @@ -114,7 +121,7 @@ static int __devlink_nl_pre_doit(struct sk_buff *skb, struct genl_info *info, return 0; unlock: - devl_unlock(devlink); + devl_dev_unlock(devlink, dev_lock); devlink_put(devlink); return err; } @@ -131,6 +138,12 @@ int devlink_nl_pre_doit_port(const struct genl_split_ops *ops, return __devlink_nl_pre_doit(skb, info, DEVLINK_NL_FLAG_NEED_PORT); } +int devlink_nl_pre_doit_dev_lock(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + return __devlink_nl_pre_doit(skb, info, DEVLINK_NL_FLAG_NEED_DEV_LOCK); +} + int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) @@ -138,16 +151,30 @@ int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops, return __devlink_nl_pre_doit(skb, info, DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT); } -void devlink_nl_post_doit(const struct genl_split_ops *ops, - struct sk_buff *skb, struct genl_info *info) +static void __devlink_nl_post_doit(struct sk_buff *skb, struct genl_info *info, + u8 flags) { + bool dev_lock = flags & DEVLINK_NL_FLAG_NEED_DEV_LOCK; struct devlink *devlink; devlink = info->user_ptr[0]; - devl_unlock(devlink); + devl_dev_unlock(devlink, dev_lock); devlink_put(devlink); } +void devlink_nl_post_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + __devlink_nl_post_doit(skb, info, 0); +} + +void +devlink_nl_post_doit_dev_lock(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + __devlink_nl_post_doit(skb, info, DEVLINK_NL_FLAG_NEED_DEV_LOCK); +} + static int devlink_nl_inst_single_dumpit(struct sk_buff *msg, struct netlink_callback *cb, int flags, devlink_nl_dump_one_func_t *dump_one, @@ -156,7 +183,7 @@ static int devlink_nl_inst_single_dumpit(struct sk_buff *msg, struct devlink *devlink; int err; - devlink = devlink_get_from_attrs_lock(sock_net(msg->sk), attrs); + devlink = devlink_get_from_attrs_lock(sock_net(msg->sk), attrs, false); if (IS_ERR(devlink)) return PTR_ERR(devlink); err = dump_one(msg, devlink, cb, flags | NLM_F_DUMP_FILTERED); diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c index 788dfdc498a9..95f9b4350ab7 100644 --- a/net/devlink/netlink_gen.c +++ b/net/devlink/netlink_gen.c @@ -846,9 +846,9 @@ const struct genl_split_ops devlink_nl_ops[73] = { { .cmd = DEVLINK_CMD_RELOAD, .validate = GENL_DONT_VALIDATE_STRICT, - .pre_doit = devlink_nl_pre_doit, + .pre_doit = devlink_nl_pre_doit_dev_lock, .doit = devlink_nl_reload_doit, - .post_doit = devlink_nl_post_doit, + .post_doit = devlink_nl_post_doit_dev_lock, .policy = devlink_reload_nl_policy, .maxattr = DEVLINK_ATTR_RELOAD_LIMITS, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h index 0e9e89c31c31..02f3c0bfae0e 100644 --- a/net/devlink/netlink_gen.h +++ b/net/devlink/netlink_gen.h @@ -22,12 +22,17 @@ int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); int devlink_nl_pre_doit_port(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); +int devlink_nl_pre_doit_dev_lock(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info); int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); void devlink_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); +void +devlink_nl_post_doit_dev_lock(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info); int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); diff --git a/net/devlink/region.c b/net/devlink/region.c index 0aab7b82d678..e3bab458db94 100644 --- a/net/devlink/region.c +++ b/net/devlink/region.c @@ -883,7 +883,8 @@ int devlink_nl_region_read_dumpit(struct sk_buff *skb, start_offset = state->start_offset; - devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs); + devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs, + false); if (IS_ERR(devlink)) return PTR_ERR(devlink); diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c index 4da5bad1a7aa..a019226ec6d2 100644 --- a/net/dsa/tag_rtl4_a.c +++ b/net/dsa/tag_rtl4_a.c @@ -23,7 +23,6 @@ #define RTL4_A_NAME "rtl4a" #define RTL4_A_HDR_LEN 4 -#define RTL4_A_ETHERTYPE 0x8899 #define RTL4_A_PROTOCOL_SHIFT 12 /* * 0x1 = Realtek Remote Control protocol (RRCP) @@ -54,7 +53,7 @@ static struct sk_buff *rtl4a_tag_xmit(struct sk_buff *skb, /* Set Ethertype */ p = (__be16 *)tag; - *p = htons(RTL4_A_ETHERTYPE); + *p = htons(ETH_P_REALTEK); out = (RTL4_A_PROTOCOL_RTL8366RB << RTL4_A_PROTOCOL_SHIFT); /* The lower bits indicate the port number */ @@ -82,7 +81,7 @@ static struct sk_buff *rtl4a_tag_rcv(struct sk_buff *skb, tag = dsa_etype_header_pos_rx(skb); p = (__be16 *)tag; etype = ntohs(*p); - if (etype != RTL4_A_ETHERTYPE) { + if (etype != ETH_P_REALTEK) { /* Not custom, just pass through */ netdev_dbg(dev, "non-realtek ethertype 0x%04x\n", etype); return skb; diff --git a/net/ethtool/common.c b/net/ethtool/common.c index b4419fb6df6a..11d8797f63f6 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -661,6 +661,12 @@ int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index) } EXPORT_SYMBOL(ethtool_get_phc_vclocks); +int ethtool_get_ts_info_by_layer(struct net_device *dev, struct ethtool_ts_info *info) +{ + return __ethtool_get_ts_info(dev, info); +} +EXPORT_SYMBOL(ethtool_get_ts_info_by_layer); + const struct ethtool_phy_ops *ethtool_phy_ops; void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops) diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 0b0ce4f81c01..a977f8903467 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -58,6 +58,9 @@ static struct devlink *netdev_to_devlink_get(struct net_device *dev) u32 ethtool_op_get_link(struct net_device *dev) { + /* Synchronize carrier state with link watch, see also rtnl_getlink() */ + linkwatch_sync_dev(dev); + return netif_carrier_ok(dev) ? 1 : 0; } EXPORT_SYMBOL(ethtool_op_get_link); diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 306f942c3b28..7ceb9ac6e730 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -173,7 +173,24 @@ static int hsr_dev_open(struct net_device *dev) static int hsr_dev_close(struct net_device *dev) { - /* Nothing to do here. */ + struct hsr_port *port; + struct hsr_priv *hsr; + + hsr = netdev_priv(dev); + hsr_for_each_port(hsr, port) { + if (port->type == HSR_PT_MASTER) + continue; + switch (port->type) { + case HSR_PT_SLAVE_A: + case HSR_PT_SLAVE_B: + dev_uc_unsync(port->dev, dev); + dev_mc_unsync(port->dev, dev); + break; + default: + break; + } + } + return 0; } @@ -404,12 +421,60 @@ void hsr_del_ports(struct hsr_priv *hsr) hsr_del_port(port); } +static void hsr_set_rx_mode(struct net_device *dev) +{ + struct hsr_port *port; + struct hsr_priv *hsr; + + hsr = netdev_priv(dev); + + hsr_for_each_port(hsr, port) { + if (port->type == HSR_PT_MASTER) + continue; + switch (port->type) { + case HSR_PT_SLAVE_A: + case HSR_PT_SLAVE_B: + dev_mc_sync_multiple(port->dev, dev); + dev_uc_sync_multiple(port->dev, dev); + break; + default: + break; + } + } +} + +static void hsr_change_rx_flags(struct net_device *dev, int change) +{ + struct hsr_port *port; + struct hsr_priv *hsr; + + hsr = netdev_priv(dev); + + hsr_for_each_port(hsr, port) { + if (port->type == HSR_PT_MASTER) + continue; + switch (port->type) { + case HSR_PT_SLAVE_A: + case HSR_PT_SLAVE_B: + if (change & IFF_ALLMULTI) + dev_set_allmulti(port->dev, + dev->flags & + IFF_ALLMULTI ? 1 : -1); + break; + default: + break; + } + } +} + static const struct net_device_ops hsr_device_ops = { .ndo_change_mtu = hsr_dev_change_mtu, .ndo_open = hsr_dev_open, .ndo_stop = hsr_dev_close, .ndo_start_xmit = hsr_dev_xmit, + .ndo_change_rx_flags = hsr_change_rx_flags, .ndo_fix_features = hsr_fix_features, + .ndo_set_rx_mode = hsr_set_rx_mode, }; static struct device_type hsr_type = { diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 7d0e7aaa71e0..46b13962ad02 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -1077,10 +1077,94 @@ skip_listen_ht: s_i = num = s_num = 0; } +/* Process a maximum of SKARR_SZ sockets at a time when walking hash buckets + * with bh disabled. + */ +#define SKARR_SZ 16 + + /* Dump bound but inactive (not listening, connecting, etc.) sockets */ + if (cb->args[0] == 1) { + if (!(idiag_states & TCPF_BOUND_INACTIVE)) + goto skip_bind_ht; + + for (i = s_i; i < hashinfo->bhash_size; i++) { + struct inet_bind_hashbucket *ibb; + struct inet_bind2_bucket *tb2; + struct sock *sk_arr[SKARR_SZ]; + int num_arr[SKARR_SZ]; + int idx, accum, res; + +resume_bind_walk: + num = 0; + accum = 0; + ibb = &hashinfo->bhash2[i]; + + spin_lock_bh(&ibb->lock); + inet_bind_bucket_for_each(tb2, &ibb->chain) { + if (!net_eq(ib2_net(tb2), net)) + continue; + + sk_for_each_bound_bhash2(sk, &tb2->owners) { + struct inet_sock *inet = inet_sk(sk); + + if (num < s_num) + goto next_bind; + + if (sk->sk_state != TCP_CLOSE || + !inet->inet_num) + goto next_bind; + + if (r->sdiag_family != AF_UNSPEC && + r->sdiag_family != sk->sk_family) + goto next_bind; + + if (!inet_diag_bc_sk(bc, sk)) + goto next_bind; + + sock_hold(sk); + num_arr[accum] = num; + sk_arr[accum] = sk; + if (++accum == SKARR_SZ) + goto pause_bind_walk; +next_bind: + num++; + } + } +pause_bind_walk: + spin_unlock_bh(&ibb->lock); + + res = 0; + for (idx = 0; idx < accum; idx++) { + if (res >= 0) { + res = inet_sk_diag_fill(sk_arr[idx], + NULL, skb, cb, + r, NLM_F_MULTI, + net_admin); + if (res < 0) + num = num_arr[idx]; + } + sock_put(sk_arr[idx]); + } + if (res < 0) + goto done; + + cond_resched(); + + if (accum == SKARR_SZ) { + s_num = num + 1; + goto resume_bind_walk; + } + + s_num = 0; + } +skip_bind_ht: + cb->args[0] = 2; + s_i = num = s_num = 0; + } + if (!(idiag_states & ~TCPF_LISTEN)) goto out; -#define SKARR_SZ 16 for (i = s_i; i <= hashinfo->ehash_mask; i++) { struct inet_ehash_bucket *head = &hashinfo->ehash[i]; spinlock_t *lock = inet_ehash_lockp(hashinfo, i); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index d37282c06e3d..61f1c96cfe63 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -189,12 +189,14 @@ __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mssp) * Check if a ack sequence number is a valid syncookie. * Return the decoded mss if it is, or 0 if not. */ -int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, - u32 cookie) +int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th) { + __u32 cookie = ntohl(th->ack_seq) - 1; __u32 seq = ntohl(th->seq) - 1; - __u32 mssind = check_tcp_syn_cookie(cookie, iph->saddr, iph->daddr, - th->source, th->dest, seq); + __u32 mssind; + + mssind = check_tcp_syn_cookie(cookie, iph->saddr, iph->daddr, + th->source, th->dest, seq); return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0; } @@ -202,7 +204,7 @@ EXPORT_SYMBOL_GPL(__cookie_v4_check); struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, - struct dst_entry *dst, u32 tsoff) + struct dst_entry *dst) { struct inet_connection_sock *icsk = inet_csk(sk); struct sock *child; @@ -212,7 +214,6 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, NULL, &own_req); if (child) { refcount_set(&req->rsk_refcnt, 1); - tcp_sk(child)->tsoffset = tsoff; sock_rps_save_rxhash(child, skb); if (rsk_drop_req(req)) { @@ -269,26 +270,46 @@ bool cookie_timestamp_decode(const struct net *net, } EXPORT_SYMBOL(cookie_timestamp_decode); -bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt, - const struct net *net, const struct dst_entry *dst) +static int cookie_tcp_reqsk_init(struct sock *sk, struct sk_buff *skb, + struct request_sock *req) { - bool ecn_ok = tcp_opt->rcv_tsecr & TS_OPT_ECN; + struct inet_request_sock *ireq = inet_rsk(req); + struct tcp_request_sock *treq = tcp_rsk(req); + const struct tcphdr *th = tcp_hdr(skb); - if (!ecn_ok) - return false; + req->num_retrans = 0; - if (READ_ONCE(net->ipv4.sysctl_tcp_ecn)) - return true; + ireq->ir_num = ntohs(th->dest); + ireq->ir_rmt_port = th->source; + ireq->ir_iif = inet_request_bound_dev_if(sk, skb); + ireq->ir_mark = inet_request_mark(sk, skb); + + if (IS_ENABLED(CONFIG_SMC)) + ireq->smc_ok = 0; - return dst_feature(dst, RTAX_FEATURE_ECN); + treq->snt_synack = 0; + treq->tfo_listener = false; + treq->txhash = net_tx_rndhash(); + treq->rcv_isn = ntohl(th->seq) - 1; + treq->snt_isn = ntohl(th->ack_seq) - 1; + treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; + treq->req_usec_ts = false; + +#if IS_ENABLED(CONFIG_MPTCP) + treq->is_mptcp = sk_is_mptcp(sk); + if (treq->is_mptcp) + return mptcp_subflow_init_cookie_req(req, sk, skb); +#endif + + return 0; } -EXPORT_SYMBOL(cookie_ecn_ok); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, - const struct tcp_request_sock_ops *af_ops, - struct sock *sk, - struct sk_buff *skb) + struct sock *sk, struct sk_buff *skb, + struct tcp_options_received *tcp_opt, + int mss, u32 tsoff) { + struct inet_request_sock *ireq; struct tcp_request_sock *treq; struct request_sock *req; @@ -300,126 +321,109 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, if (!req) return NULL; - treq = tcp_rsk(req); + if (cookie_tcp_reqsk_init(sk, skb, req)) { + reqsk_free(req); + return NULL; + } - /* treq->af_specific might be used to perform TCP_MD5 lookup */ - treq->af_specific = af_ops; + ireq = inet_rsk(req); + treq = tcp_rsk(req); - treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; - treq->req_usec_ts = false; + req->mss = mss; + req->ts_recent = tcp_opt->saw_tstamp ? tcp_opt->rcv_tsval : 0; -#if IS_ENABLED(CONFIG_MPTCP) - treq->is_mptcp = sk_is_mptcp(sk); - if (treq->is_mptcp) { - int err = mptcp_subflow_init_cookie_req(req, sk, skb); + ireq->snd_wscale = tcp_opt->snd_wscale; + ireq->tstamp_ok = tcp_opt->saw_tstamp; + ireq->sack_ok = tcp_opt->sack_ok; + ireq->wscale_ok = tcp_opt->wscale_ok; + ireq->ecn_ok = !!(tcp_opt->rcv_tsecr & TS_OPT_ECN); - if (err) { - reqsk_free(req); - return NULL; - } - } -#endif + treq->ts_off = tsoff; return req; } EXPORT_SYMBOL_GPL(cookie_tcp_reqsk_alloc); -/* On input, sk is a listener. - * Output is listener if incoming packet would not create a child - * NULL if memory could not be allocated. - */ -struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) +static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk, + struct sk_buff *skb) { - struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt; struct tcp_options_received tcp_opt; - struct inet_request_sock *ireq; - struct tcp_request_sock *treq; - struct tcp_sock *tp = tcp_sk(sk); - const struct tcphdr *th = tcp_hdr(skb); - __u32 cookie = ntohl(th->ack_seq) - 1; - struct sock *ret = sk; - struct request_sock *req; - int full_space, mss; - struct rtable *rt; - __u8 rcv_wscale; - struct flowi4 fl4; u32 tsoff = 0; - int l3index; - - if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) || - !th->ack || th->rst) - goto out; + int mss; if (tcp_synq_no_recent_overflow(sk)) goto out; - mss = __cookie_v4_check(ip_hdr(skb), th, cookie); - if (mss == 0) { - __NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESFAILED); + mss = __cookie_v4_check(ip_hdr(skb), tcp_hdr(skb)); + if (!mss) { + __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESFAILED); goto out; } - __NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV); + __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESRECV); /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(sock_net(sk), skb, &tcp_opt, 0, NULL); + tcp_parse_options(net, skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { - tsoff = secure_tcp_ts_off(sock_net(sk), + tsoff = secure_tcp_ts_off(net, ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); tcp_opt.rcv_tsecr -= tsoff; } - if (!cookie_timestamp_decode(sock_net(sk), &tcp_opt)) + if (!cookie_timestamp_decode(net, &tcp_opt)) goto out; - ret = NULL; - req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, - &tcp_request_sock_ipv4_ops, sk, skb); - if (!req) + return cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, sk, skb, + &tcp_opt, mss, tsoff); +out: + return ERR_PTR(-EINVAL); +} + +/* On input, sk is a listener. + * Output is listener if incoming packet would not create a child + * NULL if memory could not be allocated. + */ +struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) +{ + struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt; + const struct tcphdr *th = tcp_hdr(skb); + struct tcp_sock *tp = tcp_sk(sk); + struct inet_request_sock *ireq; + struct net *net = sock_net(sk); + struct request_sock *req; + struct sock *ret = sk; + struct flowi4 fl4; + struct rtable *rt; + __u8 rcv_wscale; + int full_space; + + if (!READ_ONCE(net->ipv4.sysctl_tcp_syncookies) || + !th->ack || th->rst) goto out; + req = cookie_tcp_check(net, sk, skb); + if (IS_ERR(req)) + goto out; + if (!req) + goto out_drop; + ireq = inet_rsk(req); - treq = tcp_rsk(req); - treq->rcv_isn = ntohl(th->seq) - 1; - treq->snt_isn = cookie; - treq->ts_off = 0; - treq->txhash = net_tx_rndhash(); - req->mss = mss; - ireq->ir_num = ntohs(th->dest); - ireq->ir_rmt_port = th->source; + sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); - ireq->ir_mark = inet_request_mark(sk, skb); - ireq->snd_wscale = tcp_opt.snd_wscale; - ireq->sack_ok = tcp_opt.sack_ok; - ireq->wscale_ok = tcp_opt.wscale_ok; - ireq->tstamp_ok = tcp_opt.saw_tstamp; - req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - treq->snt_synack = 0; - treq->tfo_listener = false; - - if (IS_ENABLED(CONFIG_SMC)) - ireq->smc_ok = 0; - - ireq->ir_iif = inet_request_bound_dev_if(sk, skb); - - l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif); - tcp_ao_syncookie(sk, skb, treq, AF_INET, l3index); /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) */ - RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(sock_net(sk), skb)); + RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb)); - if (security_inet_conn_request(sk, skb, req)) { - reqsk_free(req); - goto out; - } + if (security_inet_conn_request(sk, skb, req)) + goto out_free; - req->num_retrans = 0; + tcp_ao_syncookie(sk, skb, req, AF_INET); /* * We need to lookup the route here to get at the correct @@ -433,11 +437,9 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) opt->srr ? opt->faddr : ireq->ir_rmt_addr, ireq->ir_loc_addr, th->source, th->dest, sk->sk_uid); security_req_classify_flow(req, flowi4_to_flowi_common(&fl4)); - rt = ip_route_output_key(sock_net(sk), &fl4); - if (IS_ERR(rt)) { - reqsk_free(req); - goto out; - } + rt = ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) + goto out_free; /* Try to redo what tcp_v4_send_synack did. */ req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW); @@ -453,13 +455,18 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) dst_metric(&rt->dst, RTAX_INITRWND)); ireq->rcv_wscale = rcv_wscale; - ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), &rt->dst); + ireq->ecn_ok &= cookie_ecn_ok(net, &rt->dst); - ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst, tsoff); + ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst); /* ip_queue_xmit() depends on our flow being setup * Normal sockets get it right from inet_csk_route_child_sock() */ if (ret) inet_sk(ret)->cork.fl.u.ip4 = fl4; -out: return ret; +out: + return ret; +out_free: + reqsk_free(req); +out_drop: + return NULL; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index ff6838ca2e58..1d6b80145efb 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2605,6 +2605,7 @@ void tcp_set_state(struct sock *sk, int state) BUILD_BUG_ON((int)BPF_TCP_LISTEN != (int)TCP_LISTEN); BUILD_BUG_ON((int)BPF_TCP_CLOSING != (int)TCP_CLOSING); BUILD_BUG_ON((int)BPF_TCP_NEW_SYN_RECV != (int)TCP_NEW_SYN_RECV); + BUILD_BUG_ON((int)BPF_TCP_BOUND_INACTIVE != (int)TCP_BOUND_INACTIVE); BUILD_BUG_ON((int)BPF_TCP_MAX_STATES != (int)TCP_MAX_STATES); /* bpf uapi header bpf.h defines an anonymous enum with values @@ -4585,6 +4586,97 @@ static void __init tcp_init_mem(void) sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2; /* 9.37 % */ } +static void __init tcp_struct_check(void) +{ + /* TX read-mostly hotpath cache lines */ + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, max_window); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, rcv_ssthresh); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, reordering); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, notsent_lowat); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, gso_segs); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, lost_skb_hint); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, retransmit_skb_hint); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_tx, 40); + + /* TXRX read-mostly hotpath cache lines */ + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, tsoffset); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, snd_wnd); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, mss_cache); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, snd_cwnd); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, prr_out); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, lost_out); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, sacked_out); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 31); + + /* RX read-mostly hotpath cache lines */ + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, copied_seq); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rcv_tstamp); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_wl1); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, tlp_high_seq); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rttvar_us); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, retrans_out); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, advmss); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, urg_data); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, lost); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rtt_min); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, out_of_order_queue); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_ssthresh); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_rx, 69); + + /* TX read-write hotpath cache lines */ + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, segs_out); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, data_segs_out); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, bytes_sent); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, snd_sml); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, chrono_start); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, chrono_stat); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, write_seq); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, pushed_seq); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, lsndtime); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, mdev_us); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_wstamp_ns); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_clock_cache); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_mstamp); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, rtt_seq); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tsorted_sent_queue); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, highest_sack); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, ecn_flags); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 113); + + /* TXRX read-write hotpath cache lines */ + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pred_flags); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_nxt); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_nxt); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_una); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, window_clamp); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, srtt_us); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, packets_out); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_up); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered_ce); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, app_limited); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_wnd); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rx_opt); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 76); + + /* RX read-write hotpath cache lines */ + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_received); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, segs_in); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, data_segs_in); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_wup); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, max_packets_out); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, cwnd_usage_seq); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_delivered); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_interval_us); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_last_tsecr); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, first_tx_mstamp); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_mstamp); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_acked); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_est); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcvq_space); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_rx, 99); +} + void __init tcp_init(void) { int max_rshare, max_wshare, cnt; @@ -4595,6 +4687,8 @@ void __init tcp_init(void) BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof_field(struct sk_buff, cb)); + tcp_struct_check(); + percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); timer_setup(&tcp_orphan_timer, tcp_orphan_update, TIMER_DEFERRABLE); diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index f8308d3f565e..87db432c6bb4 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -844,18 +844,30 @@ static struct tcp_ao_key *tcp_ao_inbound_lookup(unsigned short int family, } void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb, - struct tcp_request_sock *treq, - unsigned short int family, int l3index) + struct request_sock *req, unsigned short int family) { + struct tcp_request_sock *treq = tcp_rsk(req); const struct tcphdr *th = tcp_hdr(skb); const struct tcp_ao_hdr *aoh; struct tcp_ao_key *key; + int l3index; + + /* treq->af_specific is used to perform TCP_AO lookup + * in tcp_create_openreq_child(). + */ +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6) + treq->af_specific = &tcp_request_sock_ipv6_ops; + else +#endif + treq->af_specific = &tcp_request_sock_ipv4_ops; treq->used_tcp_ao = false; if (tcp_parse_auth_options(th, NULL, &aoh) || !aoh) return; + l3index = l3mdev_master_ifindex_by_index(sock_net(sk), inet_rsk(req)->ir_iif); key = tcp_ao_inbound_lookup(family, sk, skb, -1, aoh->keyid, l3index); if (!key) /* Key not found, continue without TCP-AO */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 90de838a2745..7990f4939e8d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -202,23 +202,17 @@ static void bpf_skops_established(struct sock *sk, int bpf_op, } #endif -static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb, - unsigned int len) +static __cold void tcp_gro_dev_warn(const struct sock *sk, const struct sk_buff *skb, + unsigned int len) { - static bool __once __read_mostly; + struct net_device *dev; - if (!__once) { - struct net_device *dev; - - __once = true; - - rcu_read_lock(); - dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif); - if (!dev || len >= dev->mtu) - pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n", - dev ? dev->name : "Unknown driver"); - rcu_read_unlock(); - } + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif); + if (!dev || len >= READ_ONCE(dev->mtu)) + pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n", + dev ? dev->name : "Unknown driver"); + rcu_read_unlock(); } /* Adapt the MSS value used to make delayed ack decision to the @@ -250,9 +244,8 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); /* Account for possibly-removed options */ - if (unlikely(len > icsk->icsk_ack.rcv_mss + - MAX_TCP_OPTION_SPACE)) - tcp_gro_dev_warn(sk, skb, len); + DO_ONCE_LITE_IF(len > icsk->icsk_ack.rcv_mss + MAX_TCP_OPTION_SPACE, + tcp_gro_dev_warn, sk, skb, len); /* If the skb has a len of exactly 1*MSS and has the PSH bit * set then it is likely the end of an application write. So * more data may not be arriving soon, and yet the data sender diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 0c50c5a32b84..4bac6e319aca 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -482,6 +482,7 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) const int code = icmp_hdr(skb)->code; struct sock *sk; struct request_sock *fastopen; + bool harderr = false; u32 seq, snd_una; int err; struct net *net = dev_net(skb->dev); @@ -555,6 +556,7 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) goto out; case ICMP_PARAMETERPROB: err = EPROTO; + harderr = true; break; case ICMP_DEST_UNREACH: if (code > NR_ICMP_UNREACH) @@ -579,6 +581,7 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) } err = icmp_err_convert[code].errno; + harderr = icmp_err_convert[code].fatal; /* check if this ICMP message allows revert of backoff. * (see RFC 6069) */ @@ -604,6 +607,9 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) ip_icmp_error(sk, skb, err, th->dest, info, (u8 *)th); + if (!harderr) + break; + if (!sock_owned_by_user(sk)) { WRITE_ONCE(sk->sk_err, err); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 1f9f6c1c196b..d1ad20ce1c8c 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -626,7 +626,6 @@ void tcp_retransmit_timer(struct sock *sk) * implemented ftp to mars will work nicely. We will have to fix * the 120 second clamps though! */ - icsk->icsk_backoff++; out_reset_timer: /* If stream is thin, use linear timeouts. Since 'icsk_backoff' is @@ -647,11 +646,12 @@ out_reset_timer: tcp_rto_min(sk), TCP_RTO_MAX); } else if (sk->sk_state != TCP_SYN_SENT || - icsk->icsk_backoff > + tp->total_rto > READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts)) { /* Use normal (exponential) backoff unless linear timeouts are * activated. */ + icsk->icsk_backoff++; icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 12eedc6ca2cc..c8d2ca27220c 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -114,76 +114,82 @@ __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mssp) return __cookie_v6_init_sequence(iph, th, mssp); } -int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th, - __u32 cookie) +int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th) { + __u32 cookie = ntohl(th->ack_seq) - 1; __u32 seq = ntohl(th->seq) - 1; - __u32 mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr, - th->source, th->dest, seq); + __u32 mssind; + + mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr, + th->source, th->dest, seq); return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0; } EXPORT_SYMBOL_GPL(__cookie_v6_check); -struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) +static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk, + struct sk_buff *skb) { struct tcp_options_received tcp_opt; - struct inet_request_sock *ireq; - struct tcp_request_sock *treq; - struct ipv6_pinfo *np = inet6_sk(sk); - struct tcp_sock *tp = tcp_sk(sk); - const struct tcphdr *th = tcp_hdr(skb); - __u32 cookie = ntohl(th->ack_seq) - 1; - struct sock *ret = sk; - struct request_sock *req; - int full_space, mss; - struct dst_entry *dst; - __u8 rcv_wscale; u32 tsoff = 0; - int l3index; - - if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) || - !th->ack || th->rst) - goto out; + int mss; if (tcp_synq_no_recent_overflow(sk)) goto out; - mss = __cookie_v6_check(ipv6_hdr(skb), th, cookie); - if (mss == 0) { - __NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESFAILED); + mss = __cookie_v6_check(ipv6_hdr(skb), tcp_hdr(skb)); + if (!mss) { + __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESFAILED); goto out; } - __NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV); + __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESRECV); /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(sock_net(sk), skb, &tcp_opt, 0, NULL); + tcp_parse_options(net, skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { - tsoff = secure_tcpv6_ts_off(sock_net(sk), + tsoff = secure_tcpv6_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32); tcp_opt.rcv_tsecr -= tsoff; } - if (!cookie_timestamp_decode(sock_net(sk), &tcp_opt)) + if (!cookie_timestamp_decode(net, &tcp_opt)) goto out; - ret = NULL; - req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, - &tcp_request_sock_ipv6_ops, sk, skb); - if (!req) + return cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, sk, skb, + &tcp_opt, mss, tsoff); +out: + return ERR_PTR(-EINVAL); +} + +struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) +{ + const struct tcphdr *th = tcp_hdr(skb); + struct ipv6_pinfo *np = inet6_sk(sk); + struct tcp_sock *tp = tcp_sk(sk); + struct inet_request_sock *ireq; + struct net *net = sock_net(sk); + struct request_sock *req; + struct dst_entry *dst; + struct sock *ret = sk; + __u8 rcv_wscale; + int full_space; + + if (!READ_ONCE(net->ipv4.sysctl_tcp_syncookies) || + !th->ack || th->rst) goto out; + req = cookie_tcp_check(net, sk, skb); + if (IS_ERR(req)) + goto out; + if (!req) + goto out_drop; + ireq = inet_rsk(req); - treq = tcp_rsk(req); - treq->tfo_listener = false; - req->mss = mss; - ireq->ir_rmt_port = th->source; - ireq->ir_num = ntohs(th->dest); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; @@ -197,31 +203,12 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->pktopts = skb; } - ireq->ir_iif = inet_request_bound_dev_if(sk, skb); /* So that link locals have meaning */ if (!sk->sk_bound_dev_if && ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) ireq->ir_iif = tcp_v6_iif(skb); - ireq->ir_mark = inet_request_mark(sk, skb); - - req->num_retrans = 0; - ireq->snd_wscale = tcp_opt.snd_wscale; - ireq->sack_ok = tcp_opt.sack_ok; - ireq->wscale_ok = tcp_opt.wscale_ok; - ireq->tstamp_ok = tcp_opt.saw_tstamp; - req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - treq->snt_synack = 0; - treq->rcv_isn = ntohl(th->seq) - 1; - treq->snt_isn = cookie; - treq->ts_off = 0; - treq->txhash = net_tx_rndhash(); - - l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif); - tcp_ao_syncookie(sk, skb, treq, AF_INET6, l3index); - - if (IS_ENABLED(CONFIG_SMC)) - ireq->smc_ok = 0; + tcp_ao_syncookie(sk, skb, req, AF_INET6); /* * We need to lookup the dst_entry to get the correct window size. @@ -243,7 +230,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) fl6.flowi6_uid = sk->sk_uid; security_req_classify_flow(req, flowi6_to_flowi_common(&fl6)); - dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(net, sk, &fl6, final_p); if (IS_ERR(dst)) goto out_free; } @@ -261,12 +248,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) dst_metric(dst, RTAX_INITRWND)); ireq->rcv_wscale = rcv_wscale; - ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), dst); + ireq->ecn_ok &= cookie_ecn_ok(net, dst); - ret = tcp_get_cookie_sock(sk, skb, req, dst, tsoff); + ret = tcp_get_cookie_sock(sk, skb, req, dst); out: return ret; out_free: reqsk_free(req); +out_drop: return NULL; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 8c6623496dd7..06a19fe2afd1 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -381,7 +381,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct tcp_sock *tp; __u32 seq, snd_una; struct sock *sk; - bool fatal; + bool harderr; int err; sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, @@ -402,9 +402,9 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return 0; } seq = ntohl(th->seq); - fatal = icmpv6_err_convert(type, code, &err); + harderr = icmpv6_err_convert(type, code, &err); if (sk->sk_state == TCP_NEW_SYN_RECV) { - tcp_req_err(sk, seq, fatal); + tcp_req_err(sk, seq, harderr); return 0; } @@ -489,6 +489,9 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, ipv6_icmp_error(sk, skb, err, th->dest, ntohl(info), (u8 *)th); + if (!harderr) + break; + if (!sock_owned_by_user(sk)) { WRITE_ONCE(sk->sk_err, err); sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */ diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 24fa06105378..1d98877647d8 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -194,11 +194,32 @@ ieee80211_bss_info_update(struct ieee80211_local *local, if (scan_sdata && scan_sdata->vif.type == NL80211_IFTYPE_STATION && scan_sdata->vif.cfg.assoc && ieee80211_have_rx_timestamp(rx_status)) { - bss_meta.parent_tsf = - ieee80211_calculate_rx_timestamp(local, rx_status, - len + FCS_LEN, 24); - ether_addr_copy(bss_meta.parent_bssid, - scan_sdata->vif.bss_conf.bssid); + struct ieee80211_bss_conf *link_conf = NULL; + + /* for an MLO connection, set the TSF data only in case we have + * an indication on which of the links the frame was received + */ + if (ieee80211_vif_is_mld(&scan_sdata->vif)) { + if (rx_status->link_valid) { + s8 link_id = rx_status->link_id; + + link_conf = + rcu_dereference(scan_sdata->vif.link_conf[link_id]); + } + } else { + link_conf = &scan_sdata->vif.bss_conf; + } + + if (link_conf) { + bss_meta.parent_tsf = + ieee80211_calculate_rx_timestamp(local, + rx_status, + len + FCS_LEN, + 24); + + ether_addr_copy(bss_meta.parent_bssid, + link_conf->bssid); + } } rcu_read_unlock(); @@ -666,6 +687,21 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, if (local->scan_req) return -EBUSY; + /* For an MLO connection, if a link ID was specified, validate that it + * is indeed active. If no link ID was specified, select one of the + * active links. + */ + if (ieee80211_vif_is_mld(&sdata->vif)) { + if (req->tsf_report_link_id >= 0) { + if (!(sdata->vif.active_links & + BIT(req->tsf_report_link_id))) + return -EINVAL; + } else { + req->tsf_report_link_id = + __ffs(sdata->vif.active_links); + } + } + if (!__ieee80211_can_leave_ch(sdata)) return -EBUSY; @@ -714,6 +750,8 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, local->hw_scan_req->req.duration = req->duration; local->hw_scan_req->req.duration_mandatory = req->duration_mandatory; + local->hw_scan_req->req.tsf_report_link_id = + req->tsf_report_link_id; local->hw_scan_band = 0; local->hw_scan_req->req.n_6ghz_params = req->n_6ghz_params; diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 5c01b9bc619a..efecbe3cf415 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -276,12 +276,12 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info) if (!mptcp_pm_is_userspace(msk)) { GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); - goto remove_err; + goto out; } if (id_val == 0) { err = mptcp_userspace_pm_remove_id_zero_address(msk, info); - goto remove_err; + goto out; } lock_sock(sk); @@ -296,7 +296,7 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info) if (!match) { GENL_SET_ERR_MSG(info, "address with specified id not found"); release_sock(sk); - goto remove_err; + goto out; } list_move(&match->list, &free_list); @@ -310,7 +310,7 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info) } err = 0; - remove_err: +out: sock_put(sk); return err; } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index fe6f2d399ee8..458a2d7bb0dd 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -1072,6 +1072,15 @@ static inline void __mptcp_do_fallback(struct mptcp_sock *msk) set_bit(MPTCP_FALLBACK_DONE, &msk->flags); } +static inline bool __mptcp_has_initial_subflow(const struct mptcp_sock *msk) +{ + struct sock *ssk = READ_ONCE(msk->first); + + return ssk && ((1 << inet_sk_state_load(ssk)) & + (TCPF_ESTABLISHED | TCPF_SYN_SENT | + TCPF_SYN_RECV | TCPF_LISTEN)); +} + static inline void mptcp_do_fallback(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 353680733700..cabe856b2a45 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -938,6 +938,8 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) info->mptcpi_bytes_sent = msk->bytes_sent; info->mptcpi_bytes_received = msk->bytes_received; info->mptcpi_bytes_retrans = msk->bytes_retrans; + info->mptcpi_subflows_total = info->mptcpi_subflows + + __mptcp_has_initial_subflow(msk); unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(mptcp_diag_fill_info); diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index 03757e76bb6b..374412ed780b 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -105,8 +105,11 @@ enum { struct ncsi_channel_version { - u32 version; /* Supported BCD encoded NCSI version */ - u32 alpha2; /* Supported BCD encoded NCSI version */ + u8 major; /* NCSI version major */ + u8 minor; /* NCSI version minor */ + u8 update; /* NCSI version update */ + char alpha1; /* NCSI version alpha1 */ + char alpha2; /* NCSI version alpha2 */ u8 fw_name[12]; /* Firmware name string */ u32 fw_version; /* Firmware version */ u16 pci_ids[4]; /* PCI identification */ diff --git a/net/ncsi/ncsi-cmd.c b/net/ncsi/ncsi-cmd.c index fd2236ee9a79..b3ff37a181d7 100644 --- a/net/ncsi/ncsi-cmd.c +++ b/net/ncsi/ncsi-cmd.c @@ -270,7 +270,8 @@ static struct ncsi_cmd_handler { { NCSI_PKT_CMD_GPS, 0, ncsi_cmd_handler_default }, { NCSI_PKT_CMD_OEM, -1, ncsi_cmd_handler_oem }, { NCSI_PKT_CMD_PLDM, 0, NULL }, - { NCSI_PKT_CMD_GPUUID, 0, ncsi_cmd_handler_default } + { NCSI_PKT_CMD_GPUUID, 0, ncsi_cmd_handler_default }, + { NCSI_PKT_CMD_GMCMA, 0, ncsi_cmd_handler_default } }; static struct ncsi_request *ncsi_alloc_command(struct ncsi_cmd_arg *nca) diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index d9da942ad53d..745c788f1d1d 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -689,8 +689,6 @@ static int set_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, return 0; } -#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY) - static int ncsi_oem_keep_phy_intel(struct ncsi_cmd_arg *nca) { unsigned char data[NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN]; @@ -716,10 +714,6 @@ static int ncsi_oem_keep_phy_intel(struct ncsi_cmd_arg *nca) return ret; } -#endif - -#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC) - /* NCSI OEM Command APIs */ static int ncsi_oem_gma_handler_bcm(struct ncsi_cmd_arg *nca) { @@ -856,8 +850,6 @@ static int ncsi_gma_handler(struct ncsi_cmd_arg *nca, unsigned int mf_id) return nch->handler(nca); } -#endif /* CONFIG_NCSI_OEM_CMD_GET_MAC */ - /* Determine if a given channel from the channel_queue should be used for Tx */ static bool ncsi_channel_is_tx(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc) @@ -1039,20 +1031,23 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) goto error; } - nd->state = ncsi_dev_state_config_oem_gma; + nd->state = IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC) + ? ncsi_dev_state_config_oem_gma + : ncsi_dev_state_config_clear_vids; break; case ncsi_dev_state_config_oem_gma: nd->state = ncsi_dev_state_config_clear_vids; - ret = -1; -#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC) - nca.type = NCSI_PKT_CMD_OEM; nca.package = np->id; nca.channel = nc->id; ndp->pending_req_num = 1; - ret = ncsi_gma_handler(&nca, nc->version.mf_id); -#endif /* CONFIG_NCSI_OEM_CMD_GET_MAC */ - + if (nc->version.major >= 1 && nc->version.minor >= 2) { + nca.type = NCSI_PKT_CMD_GMCMA; + ret = ncsi_xmit_cmd(&nca); + } else { + nca.type = NCSI_PKT_CMD_OEM; + ret = ncsi_gma_handler(&nca, nc->version.mf_id); + } if (ret < 0) schedule_work(&ndp->work); @@ -1404,7 +1399,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) schedule_work(&ndp->work); break; -#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC) case ncsi_dev_state_probe_mlx_gma: ndp->pending_req_num = 1; @@ -1429,7 +1423,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) nd->state = ncsi_dev_state_probe_cis; break; -#endif /* CONFIG_NCSI_OEM_CMD_GET_MAC */ case ncsi_dev_state_probe_cis: ndp->pending_req_num = NCSI_RESERVED_CHANNEL; @@ -1447,7 +1440,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY)) nd->state = ncsi_dev_state_probe_keep_phy; break; -#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY) case ncsi_dev_state_probe_keep_phy: ndp->pending_req_num = 1; @@ -1460,7 +1452,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) nd->state = ncsi_dev_state_probe_gvi; break; -#endif /* CONFIG_NCSI_OEM_CMD_KEEP_PHY */ case ncsi_dev_state_probe_gvi: case ncsi_dev_state_probe_gc: case ncsi_dev_state_probe_gls: diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index a3a6753a1db7..2f872d064396 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -71,8 +71,8 @@ static int ncsi_write_channel_info(struct sk_buff *skb, if (nc == nc->package->preferred_channel) nla_put_flag(skb, NCSI_CHANNEL_ATTR_FORCED); - nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MAJOR, nc->version.version); - nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MINOR, nc->version.alpha2); + nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MAJOR, nc->version.major); + nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MINOR, nc->version.minor); nla_put_string(skb, NCSI_CHANNEL_ATTR_VERSION_STR, nc->version.fw_name); vid_nest = nla_nest_start_noflag(skb, NCSI_CHANNEL_ATTR_VLAN_LIST); diff --git a/net/ncsi/ncsi-pkt.h b/net/ncsi/ncsi-pkt.h index ba66c7dc3a21..f2f3b5c1b941 100644 --- a/net/ncsi/ncsi-pkt.h +++ b/net/ncsi/ncsi-pkt.h @@ -197,9 +197,12 @@ struct ncsi_rsp_gls_pkt { /* Get Version ID */ struct ncsi_rsp_gvi_pkt { struct ncsi_rsp_pkt_hdr rsp; /* Response header */ - __be32 ncsi_version; /* NCSI version */ + unsigned char major; /* NCSI version major */ + unsigned char minor; /* NCSI version minor */ + unsigned char update; /* NCSI version update */ + unsigned char alpha1; /* NCSI version alpha1 */ unsigned char reserved[3]; /* Reserved */ - unsigned char alpha2; /* NCSI version */ + unsigned char alpha2; /* NCSI version alpha2 */ unsigned char fw_name[12]; /* f/w name string */ __be32 fw_version; /* f/w version */ __be16 pci_ids[4]; /* PCI IDs */ @@ -335,6 +338,14 @@ struct ncsi_rsp_gpuuid_pkt { __be32 checksum; }; +/* Get MC MAC Address */ +struct ncsi_rsp_gmcma_pkt { + struct ncsi_rsp_pkt_hdr rsp; + unsigned char address_count; + unsigned char reserved[3]; + unsigned char addresses[][ETH_ALEN]; +}; + /* AEN: Link State Change */ struct ncsi_aen_lsc_pkt { struct ncsi_aen_pkt_hdr aen; /* AEN header */ @@ -395,6 +406,7 @@ struct ncsi_aen_hncdsc_pkt { #define NCSI_PKT_CMD_GPUUID 0x52 /* Get package UUID */ #define NCSI_PKT_CMD_QPNPR 0x56 /* Query Pending NC PLDM request */ #define NCSI_PKT_CMD_SNPR 0x57 /* Send NC PLDM Reply */ +#define NCSI_PKT_CMD_GMCMA 0x58 /* Get MC MAC Address */ /* NCSI packet responses */ @@ -430,6 +442,7 @@ struct ncsi_aen_hncdsc_pkt { #define NCSI_PKT_RSP_GPUUID (NCSI_PKT_CMD_GPUUID + 0x80) #define NCSI_PKT_RSP_QPNPR (NCSI_PKT_CMD_QPNPR + 0x80) #define NCSI_PKT_RSP_SNPR (NCSI_PKT_CMD_SNPR + 0x80) +#define NCSI_PKT_RSP_GMCMA (NCSI_PKT_CMD_GMCMA + 0x80) /* NCSI response code/reason */ #define NCSI_PKT_RSP_C_COMPLETED 0x0000 /* Command Completed */ diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 069c2659074b..bee290d0f48b 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -19,6 +19,19 @@ #include "ncsi-pkt.h" #include "ncsi-netlink.h" +/* Nibbles within [0xA, 0xF] add zero "0" to the returned value. + * Optional fields (encoded as 0xFF) will default to zero. + */ +static u8 decode_bcd_u8(u8 x) +{ + int lo = x & 0xF; + int hi = x >> 4; + + lo = lo < 0xA ? lo : 0; + hi = hi < 0xA ? hi : 0; + return lo + hi * 10; +} + static int ncsi_validate_rsp_pkt(struct ncsi_request *nr, unsigned short payload) { @@ -755,9 +768,18 @@ static int ncsi_rsp_handler_gvi(struct ncsi_request *nr) if (!nc) return -ENODEV; - /* Update to channel's version info */ + /* Update channel's version info + * + * Major, minor, and update fields are supposed to be + * unsigned integers encoded as packed BCD. + * + * Alpha1 and alpha2 are ISO/IEC 8859-1 characters. + */ ncv = &nc->version; - ncv->version = ntohl(rsp->ncsi_version); + ncv->major = decode_bcd_u8(rsp->major); + ncv->minor = decode_bcd_u8(rsp->minor); + ncv->update = decode_bcd_u8(rsp->update); + ncv->alpha1 = rsp->alpha1; ncv->alpha2 = rsp->alpha2; memcpy(ncv->fw_name, rsp->fw_name, 12); ncv->fw_version = ntohl(rsp->fw_version); @@ -1069,6 +1091,44 @@ static int ncsi_rsp_handler_netlink(struct ncsi_request *nr) return ret; } +static int ncsi_rsp_handler_gmcma(struct ncsi_request *nr) +{ + struct ncsi_dev_priv *ndp = nr->ndp; + struct net_device *ndev = ndp->ndev.dev; + struct ncsi_rsp_gmcma_pkt *rsp; + struct sockaddr saddr; + int ret = -1; + int i; + + rsp = (struct ncsi_rsp_gmcma_pkt *)skb_network_header(nr->rsp); + saddr.sa_family = ndev->type; + ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + + netdev_info(ndev, "NCSI: Received %d provisioned MAC addresses\n", + rsp->address_count); + for (i = 0; i < rsp->address_count; i++) { + netdev_info(ndev, "NCSI: MAC address %d: %02x:%02x:%02x:%02x:%02x:%02x\n", + i, rsp->addresses[i][0], rsp->addresses[i][1], + rsp->addresses[i][2], rsp->addresses[i][3], + rsp->addresses[i][4], rsp->addresses[i][5]); + } + + for (i = 0; i < rsp->address_count; i++) { + memcpy(saddr.sa_data, &rsp->addresses[i], ETH_ALEN); + ret = ndev->netdev_ops->ndo_set_mac_address(ndev, &saddr); + if (ret < 0) { + netdev_warn(ndev, "NCSI: Unable to assign %pM to device\n", + saddr.sa_data); + continue; + } + netdev_warn(ndev, "NCSI: Set MAC address to %pM\n", saddr.sa_data); + break; + } + + ndp->gma_flag = ret == 0; + return ret; +} + static struct ncsi_rsp_handler { unsigned char type; int payload; @@ -1105,7 +1165,8 @@ static struct ncsi_rsp_handler { { NCSI_PKT_RSP_PLDM, -1, ncsi_rsp_handler_pldm }, { NCSI_PKT_RSP_GPUUID, 20, ncsi_rsp_handler_gpuuid }, { NCSI_PKT_RSP_QPNPR, -1, ncsi_rsp_handler_pldm }, - { NCSI_PKT_RSP_SNPR, -1, ncsi_rsp_handler_pldm } + { NCSI_PKT_RSP_SNPR, -1, ncsi_rsp_handler_pldm }, + { NCSI_PKT_RSP_GMCMA, -1, ncsi_rsp_handler_gmcma }, }; int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev, diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 467671f2d42f..fbbc4fd37349 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -617,7 +617,7 @@ synproxy_recv_client_ack(struct net *net, struct synproxy_net *snet = synproxy_pernet(net); int mss; - mss = __cookie_v4_check(ip_hdr(skb), th, ntohl(th->ack_seq) - 1); + mss = __cookie_v4_check(ip_hdr(skb), th); if (mss == 0) { this_cpu_inc(snet->stats->cookie_invalid); return false; @@ -1034,7 +1034,7 @@ synproxy_recv_client_ack_ipv6(struct net *net, struct synproxy_net *snet = synproxy_pernet(net); int mss; - mss = nf_cookie_v6_check(ipv6_hdr(skb), th, ntohl(th->ack_seq) - 1); + mss = nf_cookie_v6_check(ipv6_hdr(skb), th); if (mss == 0) { this_cpu_inc(snet->stats->cookie_invalid); return false; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index eb086b06d60d..177126fb0484 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1204,8 +1204,7 @@ struct sock *netlink_getsockbyfilp(struct file *filp) return sock; } -static struct sk_buff *netlink_alloc_large_skb(unsigned int size, - int broadcast) +struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast) { struct sk_buff *skb; void *data; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 7adf48549a3b..5f1757a32842 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2121,13 +2121,13 @@ static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb, static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { + enum skb_drop_reason drop_reason = SKB_CONSUMED; struct sock *sk; struct sockaddr_ll *sll; struct packet_sock *po; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; - bool is_drop_n_account = false; if (skb->pkt_type == PACKET_LOOPBACK) goto drop; @@ -2217,9 +2217,9 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, return 0; drop_n_acct: - is_drop_n_account = true; atomic_inc(&po->tp_drops); atomic_inc(&sk->sk_drops); + drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { @@ -2227,16 +2227,14 @@ drop_n_restore: skb->len = skb_len; } drop: - if (!is_drop_n_account) - consume_skb(skb); - else - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); return 0; } static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { + enum skb_drop_reason drop_reason = SKB_CONSUMED; struct sock *sk; struct packet_sock *po; struct sockaddr_ll *sll; @@ -2250,7 +2248,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct sk_buff *copy_skb = NULL; struct timespec64 ts; __u32 ts_status; - bool is_drop_n_account = false; unsigned int slot_id = 0; int vnet_hdr_sz = 0; @@ -2498,19 +2495,16 @@ drop_n_restore: skb->len = skb_len; } drop: - if (!is_drop_n_account) - consume_skb(skb); - else - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); return 0; drop_n_account: spin_unlock(&sk->sk_receive_queue.lock); atomic_inc(&po->tp_drops); - is_drop_n_account = true; + drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; sk->sk_data_ready(sk); - kfree_skb(copy_skb); + kfree_skb_reason(copy_skb, drop_reason); goto drop_n_restore; } diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 14cc8fe8584b..c3feb4f49d09 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1351,11 +1351,11 @@ static long rfkill_fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct rfkill_data *data = file->private_data; - int ret = -ENOSYS; + int ret = -ENOTTY; u32 size; if (_IOC_TYPE(cmd) != RFKILL_IOC_MAGIC) - return -ENOSYS; + return -ENOTTY; mutex_lock(&data->mtx); switch (_IOC_NR(cmd)) { diff --git a/net/sched/act_api.c b/net/sched/act_api.c index c39252d61ebb..abec5c45b5a4 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1118,8 +1118,7 @@ int tcf_action_destroy(struct tc_action *actions[], int bind) struct tc_action *a; int ret = 0, i; - for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { - a = actions[i]; + tcf_act_for_each_action(i, a, actions) { actions[i] = NULL; ops = a->ops; ret = __tcf_idr_release(a, bind, true); @@ -1136,18 +1135,29 @@ static int tcf_action_put(struct tc_action *p) return __tcf_action_put(p, false); } -/* Put all actions in this array, skip those NULL's. */ static void tcf_action_put_many(struct tc_action *actions[]) { + struct tc_action *a; + int i; + + tcf_act_for_each_action(i, a, actions) { + const struct tc_action_ops *ops = a->ops; + if (tcf_action_put(a)) + module_put(ops->owner); + } +} + +static void tca_put_bound_many(struct tc_action *actions[], int init_res[]) +{ + struct tc_action *a; int i; - for (i = 0; i < TCA_ACT_MAX_PRIO; i++) { - struct tc_action *a = actions[i]; - const struct tc_action_ops *ops; + tcf_act_for_each_action(i, a, actions) { + const struct tc_action_ops *ops = a->ops; - if (!a) + if (init_res[i] == ACT_P_CREATED) continue; - ops = a->ops; + if (tcf_action_put(a)) module_put(ops->owner); } @@ -1211,8 +1221,7 @@ int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int err = -EINVAL, i; struct nlattr *nest; - for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { - a = actions[i]; + tcf_act_for_each_action(i, a, actions) { nest = nla_nest_start_noflag(skb, i + 1); if (nest == NULL) goto nla_put_failure; @@ -1276,14 +1285,12 @@ static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = { void tcf_idr_insert_many(struct tc_action *actions[]) { + struct tc_action *a; int i; - for (i = 0; i < TCA_ACT_MAX_PRIO; i++) { - struct tc_action *a = actions[i]; + tcf_act_for_each_action(i, a, actions) { struct tcf_idrinfo *idrinfo; - if (!a) - continue; idrinfo = a->idrinfo; mutex_lock(&idrinfo->lock); /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc if @@ -1497,10 +1504,8 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, err: tcf_action_destroy(actions, flags & TCA_ACT_FLAGS_BIND); err_mod: - for (i = 0; i < TCA_ACT_MAX_PRIO; i++) { - if (ops[i]) - module_put(ops[i]->owner); - } + for (i = 0; i < TCA_ACT_MAX_PRIO && ops[i]; i++) + module_put(ops[i]->owner); return err; } @@ -1753,10 +1758,10 @@ err_out: static int tcf_action_delete(struct net *net, struct tc_action *actions[]) { + struct tc_action *a; int i; - for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { - struct tc_action *a = actions[i]; + tcf_act_for_each_action(i, a, actions) { const struct tc_action_ops *ops = a->ops; /* Actions can be deleted concurrently so we must save their * type and id to search again after reference is released. @@ -1768,7 +1773,7 @@ static int tcf_action_delete(struct net *net, struct tc_action *actions[]) if (tcf_action_put(a)) { /* last reference, action was deleted concurrently */ module_put(ops->owner); - } else { + } else { int ret; /* now do the delete */ @@ -1977,7 +1982,7 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { size_t attr_size = 0; - int loop, ret, i; + int loop, ret; struct tc_action *actions[TCA_ACT_MAX_PRIO] = {}; int init_res[TCA_ACT_MAX_PRIO] = {}; @@ -1990,13 +1995,11 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, if (ret < 0) return ret; + ret = tcf_add_notify(net, n, actions, portid, attr_size, extack); - /* only put existing actions */ - for (i = 0; i < TCA_ACT_MAX_PRIO; i++) - if (init_res[i] == ACT_P_CREATED) - actions[i] = NULL; - tcf_action_put_many(actions); + /* only put bound actions */ + tca_put_bound_many(actions, init_res); return ret; } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index d5bdfd4a7655..289e1755c26b 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -71,7 +71,7 @@ struct tc_u_hnode { struct tc_u_hnode __rcu *next; u32 handle; u32 prio; - int refcnt; + refcount_t refcnt; unsigned int divisor; struct idr handle_idr; bool is_root; @@ -86,7 +86,7 @@ struct tc_u_hnode { struct tc_u_common { struct tc_u_hnode __rcu *hlist; void *ptr; - int refcnt; + refcount_t refcnt; struct idr handle_idr; struct hlist_node hnode; long knodes; @@ -359,7 +359,7 @@ static int u32_init(struct tcf_proto *tp) if (root_ht == NULL) return -ENOBUFS; - root_ht->refcnt++; + refcount_set(&root_ht->refcnt, 1); root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : 0x80000000; root_ht->prio = tp->prio; root_ht->is_root = true; @@ -371,18 +371,20 @@ static int u32_init(struct tcf_proto *tp) kfree(root_ht); return -ENOBUFS; } + refcount_set(&tp_c->refcnt, 1); tp_c->ptr = key; INIT_HLIST_NODE(&tp_c->hnode); idr_init(&tp_c->handle_idr); hlist_add_head(&tp_c->hnode, tc_u_hash(key)); + } else { + refcount_inc(&tp_c->refcnt); } - tp_c->refcnt++; RCU_INIT_POINTER(root_ht->next, tp_c->hlist); rcu_assign_pointer(tp_c->hlist, root_ht); - root_ht->refcnt++; + /* root_ht must be destroyed when tcf_proto is destroyed */ rcu_assign_pointer(tp->root, root_ht); tp->data = tp_c; return 0; @@ -393,7 +395,7 @@ static void __u32_destroy_key(struct tc_u_knode *n) struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); tcf_exts_destroy(&n->exts); - if (ht && --ht->refcnt == 0) + if (ht && refcount_dec_and_test(&ht->refcnt)) kfree(ht); kfree(n); } @@ -601,8 +603,6 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, struct tc_u_hnode __rcu **hn; struct tc_u_hnode *phn; - WARN_ON(--ht->refcnt); - u32_clear_hnode(tp, ht, extack); hn = &tp_c->hlist; @@ -630,10 +630,10 @@ static void u32_destroy(struct tcf_proto *tp, bool rtnl_held, WARN_ON(root_ht == NULL); - if (root_ht && --root_ht->refcnt == 1) + if (root_ht && refcount_dec_and_test(&root_ht->refcnt)) u32_destroy_hnode(tp, root_ht, extack); - if (--tp_c->refcnt == 0) { + if (refcount_dec_and_test(&tp_c->refcnt)) { struct tc_u_hnode *ht; hlist_del(&tp_c->hnode); @@ -645,7 +645,7 @@ static void u32_destroy(struct tcf_proto *tp, bool rtnl_held, /* u32_destroy_key() will later free ht for us, if it's * still referenced by some knode */ - if (--ht->refcnt == 0) + if (refcount_dec_and_test(&ht->refcnt)) kfree_rcu(ht, rcu); } @@ -674,7 +674,7 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, return -EINVAL; } - if (ht->refcnt == 1) { + if (refcount_dec_if_one(&ht->refcnt)) { u32_destroy_hnode(tp, ht, extack); } else { NL_SET_ERR_MSG_MOD(extack, "Can not delete in-use filter"); @@ -682,7 +682,7 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, } out: - *last = tp_c->refcnt == 1 && tp_c->knodes == 0; + *last = refcount_read(&tp_c->refcnt) == 1 && tp_c->knodes == 0; return ret; } @@ -766,14 +766,14 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, NL_SET_ERR_MSG_MOD(extack, "Not linking to root node"); return -EINVAL; } - ht_down->refcnt++; + refcount_inc(&ht_down->refcnt); } ht_old = rtnl_dereference(n->ht_down); rcu_assign_pointer(n->ht_down, ht_down); if (ht_old) - ht_old->refcnt--; + refcount_dec(&ht_old->refcnt); } if (ifindex >= 0) @@ -852,7 +852,7 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, /* bump reference count as long as we hold pointer to structure */ if (ht) - ht->refcnt++; + refcount_inc(&ht->refcnt); return new; } @@ -932,7 +932,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, ht_old = rtnl_dereference(n->ht_down); if (ht_old) - ht_old->refcnt++; + refcount_inc(&ht_old->refcnt); } __u32_destroy_key(new); return err; @@ -980,7 +980,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return err; } } - ht->refcnt = 1; + refcount_set(&ht->refcnt, 1); ht->divisor = divisor; ht->handle = handle; ht->prio = tp->prio; diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index 9a0b85190a2c..beece8e82c23 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -57,6 +57,8 @@ #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> +#include <linux/units.h> + #include <net/netevent.h> #include <net/netlink.h> #include <net/sch_generic.h> @@ -65,8 +67,6 @@ static LIST_HEAD(cbs_list); static DEFINE_SPINLOCK(cbs_list_lock); -#define BYTES_PER_KBIT (1000LL / 8) - struct cbs_sched_data { bool offload; int queue; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 4195a4bc26ca..8dd0e5925342 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -522,8 +522,9 @@ static void dev_watchdog(struct timer_list *t) if (unlikely(timedout_ms)) { trace_net_dev_xmit_timeout(dev, i); - WARN_ONCE(1, "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out %u ms\n", - dev->name, netdev_drivername(dev), i, timedout_ms); + netdev_crit(dev, "NETDEV WATCHDOG: CPU: %d: transmit queue %u timed out %u ms\n", + raw_smp_processor_id(), + i, timedout_ms); netif_freeze_queues(dev); dev->netdev_ops->ndo_tx_timeout(dev, i); netif_unfreeze_queues(dev); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 73eebddbbf41..7fc2f3c6d248 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2461,7 +2461,7 @@ static void smc_listen_work(struct work_struct *work) if (rc) goto out_decl; - rc = smc_clc_srv_v2x_features_validate(pclc, ini); + rc = smc_clc_srv_v2x_features_validate(new_smc, pclc, ini); if (rc) goto out_decl; diff --git a/net/smc/smc.h b/net/smc/smc.h index e377980b8414..cd51261b7d9e 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -196,7 +196,6 @@ struct smc_connection { * - dec on polled tx cqe */ wait_queue_head_t cdc_pend_tx_wq; /* wakeup on no cdc_pend_tx_wr*/ - atomic_t tx_pushing; /* nr_threads trying tx push */ struct delayed_work tx_work; /* retry of smc_cdc_msg_send */ u32 tx_off; /* base offset in peer rmb */ diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 72f4d81a3f41..95e19aa3e769 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -824,6 +824,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) struct smc_clc_smcd_gid_chid *gidchids; struct smc_clc_msg_proposal_area *pclc; struct smc_clc_ipv6_prefix *ipv6_prfx; + struct net *net = sock_net(&smc->sk); struct smc_clc_v2_extension *v2_ext; struct smc_clc_msg_smcd *pclc_smcd; struct smc_clc_msg_trail *trl; @@ -943,8 +944,8 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) } if (smcr_indicated(ini->smc_type_v2)) { memcpy(v2_ext->roce, ini->smcrv2.ib_gid_v2, SMC_GID_SIZE); - v2_ext->max_conns = SMC_CONN_PER_LGR_PREFER; - v2_ext->max_links = SMC_LINKS_PER_LGR_MAX_PREFER; + v2_ext->max_conns = net->smc.sysctl_max_conns_per_lgr; + v2_ext->max_links = net->smc.sysctl_max_links_per_lgr; } pclc_base->hdr.length = htons(plen); @@ -1170,10 +1171,12 @@ int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact, return len > 0 ? 0 : len; } -int smc_clc_srv_v2x_features_validate(struct smc_clc_msg_proposal *pclc, +int smc_clc_srv_v2x_features_validate(struct smc_sock *smc, + struct smc_clc_msg_proposal *pclc, struct smc_init_info *ini) { struct smc_clc_v2_extension *pclc_v2_ext; + struct net *net = sock_net(&smc->sk); ini->max_conns = SMC_CONN_PER_LGR_MAX; ini->max_links = SMC_LINKS_ADD_LNK_MAX; @@ -1187,11 +1190,13 @@ int smc_clc_srv_v2x_features_validate(struct smc_clc_msg_proposal *pclc, return SMC_CLC_DECL_NOV2EXT; if (ini->smcr_version & SMC_V2) { - ini->max_conns = min_t(u8, pclc_v2_ext->max_conns, SMC_CONN_PER_LGR_PREFER); + ini->max_conns = min_t(u8, pclc_v2_ext->max_conns, + net->smc.sysctl_max_conns_per_lgr); if (ini->max_conns < SMC_CONN_PER_LGR_MIN) return SMC_CLC_DECL_MAXCONNERR; - ini->max_links = min_t(u8, pclc_v2_ext->max_links, SMC_LINKS_PER_LGR_MAX_PREFER); + ini->max_links = min_t(u8, pclc_v2_ext->max_links, + net->smc.sysctl_max_links_per_lgr); if (ini->max_links < SMC_LINKS_ADD_LNK_MIN) return SMC_CLC_DECL_MAXLINKERR; } diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 08155a96a02a..1697b84d85be 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -422,7 +422,8 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, u8 version, u8 *eid, struct smc_init_info *ini); int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact, u8 version, u8 *negotiated_eid, struct smc_init_info *ini); -int smc_clc_srv_v2x_features_validate(struct smc_clc_msg_proposal *pclc, +int smc_clc_srv_v2x_features_validate(struct smc_sock *smc, + struct smc_clc_msg_proposal *pclc, struct smc_init_info *ini); int smc_clc_clnt_v2x_features_validate(struct smc_clc_first_contact_ext *fce, struct smc_init_info *ini); diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c index 5cbc18c6e62b..a5946d1b9d60 100644 --- a/net/smc/smc_sysctl.c +++ b/net/smc/smc_sysctl.c @@ -25,6 +25,10 @@ static int max_sndbuf = INT_MAX / 2; static int max_rcvbuf = INT_MAX / 2; static const int net_smc_wmem_init = (64 * 1024); static const int net_smc_rmem_init = (64 * 1024); +static int links_per_lgr_min = SMC_LINKS_ADD_LNK_MIN; +static int links_per_lgr_max = SMC_LINKS_ADD_LNK_MAX; +static int conns_per_lgr_min = SMC_CONN_PER_LGR_MIN; +static int conns_per_lgr_max = SMC_CONN_PER_LGR_MAX; static struct ctl_table smc_table[] = { { @@ -68,6 +72,24 @@ static struct ctl_table smc_table[] = { .extra1 = &min_rcvbuf, .extra2 = &max_rcvbuf, }, + { + .procname = "smcr_max_links_per_lgr", + .data = &init_net.smc.sysctl_max_links_per_lgr, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &links_per_lgr_min, + .extra2 = &links_per_lgr_max, + }, + { + .procname = "smcr_max_conns_per_lgr", + .data = &init_net.smc.sysctl_max_conns_per_lgr, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &conns_per_lgr_min, + .extra2 = &conns_per_lgr_max, + }, { } }; @@ -97,6 +119,8 @@ int __net_init smc_sysctl_net_init(struct net *net) net->smc.sysctl_smcr_testlink_time = SMC_LLC_TESTLINK_DEFAULT_TIME; WRITE_ONCE(net->smc.sysctl_wmem, net_smc_wmem_init); WRITE_ONCE(net->smc.sysctl_rmem, net_smc_rmem_init); + net->smc.sysctl_max_links_per_lgr = SMC_LINKS_PER_LGR_MAX_PREFER; + net->smc.sysctl_max_conns_per_lgr = SMC_CONN_PER_LGR_PREFER; return 0; diff --git a/net/smc/smc_sysctl.h b/net/smc/smc_sysctl.h index 0becc11bd2f4..eb2465ae1e15 100644 --- a/net/smc/smc_sysctl.h +++ b/net/smc/smc_sysctl.h @@ -23,6 +23,8 @@ void __net_exit smc_sysctl_net_exit(struct net *net); static inline int smc_sysctl_net_init(struct net *net) { net->smc.sysctl_autocorking_size = SMC_AUTOCORKING_DEFAULT_SIZE; + net->smc.sysctl_max_links_per_lgr = SMC_LINKS_PER_LGR_MAX_PREFER; + net->smc.sysctl_max_conns_per_lgr = SMC_CONN_PER_LGR_PREFER; return 0; } diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 3b0ff3b589c7..214ac3cbcf9a 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -621,7 +621,7 @@ static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn) return rc; } -static int __smc_tx_sndbuf_nonempty(struct smc_connection *conn) +int smc_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); int rc = 0; @@ -655,34 +655,6 @@ out: return rc; } -int smc_tx_sndbuf_nonempty(struct smc_connection *conn) -{ - int rc; - - /* This make sure only one can send simultaneously to prevent wasting - * of CPU and CDC slot. - * Record whether someone has tried to push while we are pushing. - */ - if (atomic_inc_return(&conn->tx_pushing) > 1) - return 0; - -again: - atomic_set(&conn->tx_pushing, 1); - smp_wmb(); /* Make sure tx_pushing is 1 before real send */ - rc = __smc_tx_sndbuf_nonempty(conn); - - /* We need to check whether someone else have added some data into - * the send queue and tried to push but failed after the atomic_set() - * when we are pushing. - * If so, we need to push again to prevent those data hang in the send - * queue. - */ - if (unlikely(!atomic_dec_and_test(&conn->tx_pushing))) - goto again; - - return rc; -} - /* Wakeup sndbuf consumers from process context * since there is more data to transmit. The caller * must hold sock lock. diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index c763008a8adb..079aebb16ed8 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -168,7 +168,7 @@ static struct sk_buff *tipc_get_err_tlv(char *str) int str_len = strlen(str) + 1; struct sk_buff *buf; - buf = tipc_tlv_alloc(TLV_SPACE(str_len)); + buf = tipc_tlv_alloc(str_len); if (buf) tipc_add_tlv(buf, TIPC_TLV_ERROR_STRING, str, str_len); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 1cbbb11ea503..d0f499227c29 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -9342,6 +9342,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) else eth_broadcast_addr(request->bssid); + request->tsf_report_link_id = nl80211_link_id_or_invalid(info->attrs); request->wdev = wdev; request->wiphy = &rdev->wiphy; request->scan_start = jiffies; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 06cead2b8e34..caa340134b0e 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -148,6 +148,11 @@ static int xdp_umem_account_pages(struct xdp_umem *umem) return 0; } +#define XDP_UMEM_FLAGS_VALID ( \ + XDP_UMEM_UNALIGNED_CHUNK_FLAG | \ + XDP_UMEM_TX_SW_CSUM | \ + 0) + static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) { bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG; @@ -167,7 +172,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) return -EINVAL; } - if (mr->flags & ~XDP_UMEM_UNALIGNED_CHUNK_FLAG) + if (mr->flags & ~XDP_UMEM_FLAGS_VALID) return -EINVAL; if (!unaligned_chunks && !is_power_of_2(chunk_size)) @@ -199,6 +204,9 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (headroom >= chunk_size - XDP_PACKET_HEADROOM) return -EINVAL; + if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8) + return -EINVAL; + umem->size = size; umem->headroom = headroom; umem->chunk_size = chunk_size; @@ -207,6 +215,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->pgs = NULL; umem->user = NULL; umem->flags = mr->flags; + umem->tx_metadata_len = mr->tx_metadata_len; INIT_LIST_HEAD(&umem->xsk_dma_list); refcount_set(&umem->users, 1); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 3da0b52f308d..9f13aa3353e3 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -571,6 +571,13 @@ static u32 xsk_get_num_desc(struct sk_buff *skb) static void xsk_destruct_skb(struct sk_buff *skb) { + struct xsk_tx_metadata_compl *compl = &skb_shinfo(skb)->xsk_meta; + + if (compl->tx_timestamp) { + /* sw completion timestamp, not a real one */ + *compl->tx_timestamp = ktime_get_tai_fast_ns(); + } + xsk_cq_submit_locked(xdp_sk(skb->sk), xsk_get_num_desc(skb)); sock_wfree(skb); } @@ -655,8 +662,10 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs, static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, struct xdp_desc *desc) { + struct xsk_tx_metadata *meta = NULL; struct net_device *dev = xs->dev; struct sk_buff *skb = xs->skb; + bool first_frag = false; int err; if (dev->priv_flags & IFF_TX_SKB_NO_LINEAR) { @@ -687,6 +696,8 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, kfree_skb(skb); goto free_err; } + + first_frag = true; } else { int nr_frags = skb_shinfo(skb)->nr_frags; struct page *page; @@ -709,12 +720,45 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, skb_add_rx_frag(skb, nr_frags, page, 0, len, 0); } + + if (first_frag && desc->options & XDP_TX_METADATA) { + if (unlikely(xs->pool->tx_metadata_len == 0)) { + err = -EINVAL; + goto free_err; + } + + meta = buffer - xs->pool->tx_metadata_len; + if (unlikely(!xsk_buff_valid_tx_metadata(meta))) { + err = -EINVAL; + goto free_err; + } + + if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) { + if (unlikely(meta->request.csum_start + + meta->request.csum_offset + + sizeof(__sum16) > len)) { + err = -EINVAL; + goto free_err; + } + + skb->csum_start = hr + meta->request.csum_start; + skb->csum_offset = meta->request.csum_offset; + skb->ip_summed = CHECKSUM_PARTIAL; + + if (unlikely(xs->pool->tx_sw_csum)) { + err = skb_checksum_help(skb); + if (err) + goto free_err; + } + } + } } skb->dev = dev; skb->priority = READ_ONCE(xs->sk.sk_priority); skb->mark = READ_ONCE(xs->sk.sk_mark); skb->destructor = xsk_destruct_skb; + xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta); xsk_set_destructor_arg(skb); return skb; @@ -1282,6 +1326,14 @@ struct xdp_umem_reg_v1 { __u32 headroom; }; +struct xdp_umem_reg_v2 { + __u64 addr; /* Start of packet data area */ + __u64 len; /* Length of packet data area */ + __u32 chunk_size; + __u32 headroom; + __u32 flags; +}; + static int xsk_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { @@ -1325,8 +1377,10 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, if (optlen < sizeof(struct xdp_umem_reg_v1)) return -EINVAL; - else if (optlen < sizeof(mr)) + else if (optlen < sizeof(struct xdp_umem_reg_v2)) mr_size = sizeof(struct xdp_umem_reg_v1); + else if (optlen < sizeof(mr)) + mr_size = sizeof(struct xdp_umem_reg_v2); if (copy_from_sockptr(&mr, optval, mr_size)) return -EFAULT; diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 49cb9f9a09be..4f6f538a5462 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -85,6 +85,8 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, XDP_PACKET_HEADROOM; pool->umem = umem; pool->addrs = umem->addrs; + pool->tx_metadata_len = umem->tx_metadata_len; + pool->tx_sw_csum = umem->flags & XDP_UMEM_TX_SW_CSUM; INIT_LIST_HEAD(&pool->free_list); INIT_LIST_HEAD(&pool->xskb_list); INIT_LIST_HEAD(&pool->xsk_tx_list); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 13354a1e4280..6f2d1621c992 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -137,21 +137,23 @@ static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr) static inline bool xp_unused_options_set(u32 options) { - return options & ~XDP_PKT_CONTD; + return options & ~(XDP_PKT_CONTD | XDP_TX_METADATA); } static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { - u64 offset = desc->addr & (pool->chunk_size - 1); + u64 addr = desc->addr - pool->tx_metadata_len; + u64 len = desc->len + pool->tx_metadata_len; + u64 offset = addr & (pool->chunk_size - 1); if (!desc->len) return false; - if (offset + desc->len > pool->chunk_size) + if (offset + len > pool->chunk_size) return false; - if (desc->addr >= pool->addrs_cnt) + if (addr >= pool->addrs_cnt) return false; if (xp_unused_options_set(desc->options)) @@ -162,16 +164,17 @@ static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool, static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { - u64 addr = xp_unaligned_add_offset_to_addr(desc->addr); + u64 addr = xp_unaligned_add_offset_to_addr(desc->addr) - pool->tx_metadata_len; + u64 len = desc->len + pool->tx_metadata_len; if (!desc->len) return false; - if (desc->len > pool->chunk_size) + if (len > pool->chunk_size) return false; - if (addr >= pool->addrs_cnt || addr + desc->len > pool->addrs_cnt || - xp_desc_crosses_non_contig_pg(pool, addr, desc->len)) + if (addr >= pool->addrs_cnt || addr + len > pool->addrs_cnt || + xp_desc_crosses_non_contig_pg(pool, addr, len)) return false; if (xp_unused_options_set(desc->options)) |