diff options
37 files changed, 276 insertions, 175 deletions
diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index a7d44e71019d..287b98708a40 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -39,7 +39,6 @@ Table : Subdirectories in /proc/sys/net 802 E802 protocol ax25 AX25 ethernet Ethernet protocol rose X.25 PLP layer ipv4 IP version 4 x25 X.25 protocol - ipx IPX token-ring IBM token ring bridge Bridging decnet DEC net ipv6 IP version 6 tipc TIPC ========= =================== = ========== ================== @@ -401,33 +400,7 @@ interface. (network) that the route leads to, the router (may be directly connected), the route flags, and the device the route is using. - -5. IPX ------- - -The IPX protocol has no tunable values in proc/sys/net. - -The IPX protocol does, however, provide proc/net/ipx. This lists each IPX -socket giving the local and remote addresses in Novell format (that is -network:node:port). In accordance with the strange Novell tradition, -everything but the port is in hex. Not_Connected is displayed for sockets that -are not tied to a specific remote address. The Tx and Rx queue sizes indicate -the number of bytes pending for transmission and reception. The state -indicates the state the socket is in and the uid is the owning uid of the -socket. - -The /proc/net/ipx_interface file lists all IPX interfaces. For each interface -it gives the network number, the node number, and indicates if the network is -the primary network. It also indicates which device it is bound to (or -Internal for internal networks) and the Frame Type if appropriate. Linux -supports 802.3, 802.2, 802.2 SNAP and DIX (Blue Book) ethernet framing for -IPX. - -The /proc/net/ipx_route table holds a list of IPX routes. For each route it -gives the destination network, the router node (or Directly) and the network -address of the router (or Connected) for internal networks. - -6. TIPC +5. TIPC ------- tipc_rmem diff --git a/Documentation/networking/tls-offload.rst b/Documentation/networking/tls-offload.rst index b70b70dc4524..0dd3f748239f 100644 --- a/Documentation/networking/tls-offload.rst +++ b/Documentation/networking/tls-offload.rst @@ -506,21 +506,3 @@ Drivers should ignore the changes to TLS the device feature flags. These flags will be acted upon accordingly by the core ``ktls`` code. TLS device feature flags only control adding of new TLS connection offloads, old connections will remain active after flags are cleared. - -Known bugs -========== - -skb_orphan() leaks clear text ------------------------------ - -Currently drivers depend on the :c:member:`sk` member of -:c:type:`struct sk_buff <sk_buff>` to identify segments requiring -encryption. Any operation which removes or does not preserve the socket -association such as :c:func:`skb_orphan` or :c:func:`skb_clone` -will cause the driver to miss the packets and lead to clear text leaks. - -Redirects leak clear text -------------------------- - -In the RX direction, if segment has already been decrypted by the device -and it gets redirected or mirrored - clear text will be transmitted out. diff --git a/Documentation/networking/tuntap.txt b/Documentation/networking/tuntap.txt index 949d5dcdd9a3..0104830d5075 100644 --- a/Documentation/networking/tuntap.txt +++ b/Documentation/networking/tuntap.txt @@ -204,8 +204,8 @@ Ethernet device, which instead of receiving packets from a physical media, receives them from user space program and instead of sending packets via physical media sends them to the user space program. -Let's say that you configured IPX on the tap0, then whenever -the kernel sends an IPX packet to tap0, it is passed to the application +Let's say that you configured IPv6 on the tap0, then whenever +the kernel sends an IPv6 packet to tap0, it is passed to the application (VTun for example). The application encrypts, compresses and sends it to the other side over TCP or UDP. The application on the other side decompresses and decrypts the data received and writes the packet to the TAP device, diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 02fd7822c14a..931d9d935686 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1126,6 +1126,8 @@ static void bond_compute_features(struct bonding *bond) done: bond_dev->vlan_features = vlan_features; bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX | NETIF_F_GSO_UDP_L4; bond_dev->mpls_features = mpls_features; bond_dev->gso_max_segs = gso_max_segs; diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index d073baffc20b..df976b259e43 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1223,12 +1223,8 @@ static int sja1105_fdb_dump(struct dsa_switch *ds, int port, { struct sja1105_private *priv = ds->priv; struct device *dev = ds->dev; - u16 rx_vid, tx_vid; int i; - rx_vid = dsa_8021q_rx_vid(ds, port); - tx_vid = dsa_8021q_tx_vid(ds, port); - for (i = 0; i < SJA1105_MAX_L2_LOOKUP_COUNT; i++) { struct sja1105_l2_lookup_entry l2_lookup = {0}; u8 macaddr[ETH_ALEN]; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index cbaf712d6529..7882148abb43 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7897,11 +7897,8 @@ static void ixgbe_service_task(struct work_struct *work) return; } if (ixgbe_check_fw_error(adapter)) { - if (!test_bit(__IXGBE_DOWN, &adapter->state)) { - rtnl_lock(); + if (!test_bit(__IXGBE_DOWN, &adapter->state)) unregister_netdev(adapter->netdev); - rtnl_unlock(); - } ixgbe_service_event_complete(adapter); return; } diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c index 78a7de3fb622..c62f474b6d08 100644 --- a/drivers/net/ethernet/tundra/tsi108_eth.c +++ b/drivers/net/ethernet/tundra/tsi108_eth.c @@ -371,9 +371,10 @@ tsi108_stat_carry_one(int carry, int carry_bit, int carry_shift, static void tsi108_stat_carry(struct net_device *dev) { struct tsi108_prv_data *data = netdev_priv(dev); + unsigned long flags; u32 carry1, carry2; - spin_lock_irq(&data->misclock); + spin_lock_irqsave(&data->misclock, flags); carry1 = TSI_READ(TSI108_STAT_CARRY1); carry2 = TSI_READ(TSI108_STAT_CARRY2); @@ -441,7 +442,7 @@ static void tsi108_stat_carry(struct net_device *dev) TSI108_STAT_TXPAUSEDROP_CARRY, &data->tx_pause_drop); - spin_unlock_irq(&data->misclock); + spin_unlock_irqrestore(&data->misclock, flags); } /* Read a stat counter atomically with respect to carries. diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index abfa0da9bbd2..e8089def5a46 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1004,6 +1004,8 @@ static void __team_compute_features(struct team *team) team->dev->vlan_features = vlan_features; team->dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX | NETIF_F_GSO_UDP_L4; team->dev->hard_header_len = max_hard_header_len; diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 1d9940d4e8c7..c9262ffeefe4 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -925,6 +925,7 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, skb_shinfo(skb)->nr_frags = MAX_SKB_FRAGS; nskb = xenvif_alloc_skb(0); if (unlikely(nskb == NULL)) { + skb_shinfo(skb)->nr_frags = 0; kfree_skb(skb); xenvif_tx_err(queue, &txreq, extra_count, idx); if (net_ratelimit()) @@ -940,6 +941,7 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, if (xenvif_set_skb_gso(queue->vif, skb, gso)) { /* Failure in xenvif_set_skb_gso is fatal. */ + skb_shinfo(skb)->nr_frags = 0; kfree_skb(skb); kfree_skb(nskb); break; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d8af86d995d6..ba5583522d24 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1374,6 +1374,14 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) to->l4_hash = from->l4_hash; }; +static inline void skb_copy_decrypted(struct sk_buff *to, + const struct sk_buff *from) +{ +#ifdef CONFIG_TLS_DEVICE + to->decrypted = from->decrypted; +#endif +} + #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { diff --git a/include/linux/socket.h b/include/linux/socket.h index 97523818cb14..fc0bed59fc84 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -292,6 +292,9 @@ struct ucred { #define MSG_BATCH 0x40000 /* sendmmsg(): more messages coming */ #define MSG_EOF MSG_FIN #define MSG_NO_SHARED_FRAGS 0x80000 /* sendpage() internal : page frags are not shared */ +#define MSG_SENDPAGE_DECRYPTED 0x100000 /* sendpage() internal : page may carry + * plain text and require encryption + */ #define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 010f26b31c89..bac79e817776 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -171,7 +171,7 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, struct sk_buff *parent); void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, - void *reasm_data); + void *reasm_data, bool try_coalesce); struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q); #endif diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 4a9da951a794..cb668bc2692d 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -61,7 +61,6 @@ struct net { spinlock_t rules_mod_lock; u32 hash_mix; - atomic64_t cookie_gen; struct list_head list; /* list of network namespaces */ struct list_head exit_list; /* To linked to call pernet exit diff --git a/include/net/sock.h b/include/net/sock.h index 228db3998e46..2c53f1a1d905 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2482,6 +2482,7 @@ static inline bool sk_fullsock(const struct sock *sk) /* Checks if this SKB belongs to an HW offloaded socket * and whether any SW fallbacks are required based on dev. + * Check decrypted mark in case skb_orphan() cleared socket. */ static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb, struct net_device *dev) @@ -2489,8 +2490,15 @@ static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb, #ifdef CONFIG_SOCK_VALIDATE_XMIT struct sock *sk = skb->sk; - if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb) + if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb) { skb = sk->sk_validate_xmit_skb(sk, dev, skb); +#ifdef CONFIG_TLS_DEVICE + } else if (unlikely(skb->decrypted)) { + pr_warn_ratelimited("unencrypted skb with no associated socket - dropping\n"); + kfree_skb(skb); + skb = NULL; +#endif + } #endif return skb; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index fa1c753dcdbc..a5aa7d3ac6a1 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1466,8 +1466,8 @@ union bpf_attr { * If no cookie has been set yet, generate a new cookie. Once * generated, the socket cookie remains stable for the life of the * socket. This helper can be useful for monitoring per socket - * networking traffic statistics as it provides a unique socket - * identifier per namespace. + * networking traffic statistics as it provides a global socket + * identifier that can be assumed unique. * Return * A 8-byte long non-decreasing number on success, or 0 if the * socket field is missing inside *skb*. diff --git a/net/core/sock.c b/net/core/sock.c index d57b0cc995a0..6d08553f885c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1992,6 +1992,19 @@ void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) } EXPORT_SYMBOL(skb_set_owner_w); +static bool can_skb_orphan_partial(const struct sk_buff *skb) +{ +#ifdef CONFIG_TLS_DEVICE + /* Drivers depend on in-order delivery for crypto offload, + * partial orphan breaks out-of-order-OK logic. + */ + if (skb->decrypted) + return false; +#endif + return (skb->destructor == sock_wfree || + (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree)); +} + /* This helper is used by netem, as it can hold packets in its * delay queue. We want to allow the owner socket to send more * packets, as if they were already TX completed by a typical driver. @@ -2003,11 +2016,7 @@ void skb_orphan_partial(struct sk_buff *skb) if (skb_is_tcp_pure_ack(skb)) return; - if (skb->destructor == sock_wfree -#ifdef CONFIG_INET - || skb->destructor == tcp_wfree -#endif - ) { + if (can_skb_orphan_partial(skb)) { struct sock *sk = skb->sk; if (refcount_inc_not_zero(&sk->sk_refcnt)) { diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 3312a5849a97..c13ffbd33d8d 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -19,6 +19,7 @@ static const struct sock_diag_handler *sock_diag_handlers[AF_MAX]; static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh); static DEFINE_MUTEX(sock_diag_table_mutex); static struct workqueue_struct *broadcast_wq; +static atomic64_t cookie_gen; u64 sock_gen_cookie(struct sock *sk) { @@ -27,7 +28,7 @@ u64 sock_gen_cookie(struct sock *sk) if (res) return res; - res = atomic64_inc_return(&sock_net(sk)->cookie_gen); + res = atomic64_inc_return(&cookie_gen); atomic64_cmpxchg(&sk->sk_cookie, 0, res); } } diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index e4aba5d485be..bbe9b3b2d395 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -170,7 +170,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *skb, reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); if (!reasm_data) goto out_oom; - inet_frag_reasm_finish(&fq->q, skb, reasm_data); + inet_frag_reasm_finish(&fq->q, skb, reasm_data, false); skb->dev = ldev; skb->tstamp = fq->q.stamp; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index a999451345f9..10d31733297d 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -475,11 +475,12 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, EXPORT_SYMBOL(inet_frag_reasm_prepare); void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, - void *reasm_data) + void *reasm_data, bool try_coalesce) { struct sk_buff **nextp = (struct sk_buff **)reasm_data; struct rb_node *rbn; struct sk_buff *fp; + int sum_truesize; skb_push(head, head->data - skb_network_header(head)); @@ -487,25 +488,41 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, fp = FRAG_CB(head)->next_frag; rbn = rb_next(&head->rbnode); rb_erase(&head->rbnode, &q->rb_fragments); + + sum_truesize = head->truesize; while (rbn || fp) { /* fp points to the next sk_buff in the current run; * rbn points to the next run. */ /* Go through the current run. */ while (fp) { - *nextp = fp; - nextp = &fp->next; - fp->prev = NULL; - memset(&fp->rbnode, 0, sizeof(fp->rbnode)); - fp->sk = NULL; - head->data_len += fp->len; - head->len += fp->len; + struct sk_buff *next_frag = FRAG_CB(fp)->next_frag; + bool stolen; + int delta; + + sum_truesize += fp->truesize; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); - head->truesize += fp->truesize; - fp = FRAG_CB(fp)->next_frag; + + if (try_coalesce && skb_try_coalesce(head, fp, &stolen, + &delta)) { + kfree_skb_partial(fp, stolen); + } else { + fp->prev = NULL; + memset(&fp->rbnode, 0, sizeof(fp->rbnode)); + fp->sk = NULL; + + head->data_len += fp->len; + head->len += fp->len; + head->truesize += fp->truesize; + + *nextp = fp; + nextp = &fp->next; + } + + fp = next_frag; } /* Move to the next run. */ if (rbn) { @@ -516,7 +533,7 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, rbn = rbnext; } } - sub_frag_mem_limit(q->fqdir, head->truesize); + sub_frag_mem_limit(q->fqdir, sum_truesize); *nextp = NULL; skb_mark_not_on_list(head); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 4385eb9e781f..cfeb8890f94e 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -393,6 +393,11 @@ err: return err; } +static bool ip_frag_coalesce_ok(const struct ipq *qp) +{ + return qp->q.key.v4.user == IP_DEFRAG_LOCAL_DELIVER; +} + /* Build a new IP datagram from all its fragments. */ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *dev) @@ -421,7 +426,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, if (len > 65535) goto out_oversize; - inet_frag_reasm_finish(&qp->q, skb, reasm_data); + inet_frag_reasm_finish(&qp->q, skb, reasm_data, + ip_frag_coalesce_ok(qp)); skb->dev = dev; IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 776905899ac0..77b485d60b9d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -984,6 +984,9 @@ new_segment: if (!skb) goto wait_for_memory; +#ifdef CONFIG_TLS_DEVICE + skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED); +#endif skb_entail(sk, skb); copy = size_goal; } diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 3d1e15401384..8a56e09cfb0e 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -398,10 +398,14 @@ more_data: static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { struct sk_msg tmp, *msg_tx = NULL; - int flags = msg->msg_flags | MSG_NO_SHARED_FRAGS; int copied = 0, err = 0; struct sk_psock *psock; long timeo; + int flags; + + /* Don't let internal do_tcp_sendpages() flags through */ + flags = (msg->msg_flags & ~MSG_SENDPAGE_DECRYPTED); + flags |= MSG_NO_SHARED_FRAGS; psock = sk_psock_get(sk); if (unlikely(!psock)) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6e4afc48d7bb..979520e46e33 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1320,6 +1320,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, buff = sk_stream_alloc_skb(sk, nsize, gfp, true); if (!buff) return -ENOMEM; /* We'll just try again later. */ + skb_copy_decrypted(buff, skb); sk->sk_wmem_queued += buff->truesize; sk_mem_charge(sk, buff->truesize); @@ -1874,6 +1875,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, buff = sk_stream_alloc_skb(sk, 0, gfp, true); if (unlikely(!buff)) return -ENOMEM; + skb_copy_decrypted(buff, skb); sk->sk_wmem_queued += buff->truesize; sk_mem_charge(sk, buff->truesize); @@ -2143,6 +2145,7 @@ static int tcp_mtu_probe(struct sock *sk) sk_mem_charge(sk, nskb->truesize); skb = tcp_send_head(sk); + skb_copy_decrypted(nskb, skb); TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq; TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 0f82c150543b..fed9666a2f7d 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -348,7 +348,7 @@ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, skb_reset_transport_header(skb); - inet_frag_reasm_finish(&fq->q, skb, reasm_data); + inet_frag_reasm_finish(&fq->q, skb, reasm_data, false); skb->ignore_df = 1; skb->dev = dev; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index ca05b16f1bb9..1f5d4d196dcc 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -282,7 +282,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, skb_reset_transport_header(skb); - inet_frag_reasm_finish(&fq->q, skb, reasm_data); + inet_frag_reasm_finish(&fq->q, skb, reasm_data, true); skb->dev = dev; ipv6_hdr(skb)->payload_len = htons(payload_len); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index d09eaf153544..0dbbfd1b6487 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -193,7 +193,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) service_in_use: write_unlock(&local->services_lock); - rxrpc_put_local(local); + rxrpc_unuse_local(local); ret = -EADDRINUSE; error_unlock: release_sock(&rx->sk); @@ -402,7 +402,7 @@ EXPORT_SYMBOL(rxrpc_kernel_check_life); */ void rxrpc_kernel_probe_life(struct socket *sock, struct rxrpc_call *call) { - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false, rxrpc_propose_ack_ping_for_check_life); rxrpc_send_ack_packet(call, true, NULL); } @@ -901,7 +901,7 @@ static int rxrpc_release_sock(struct sock *sk) rxrpc_queue_work(&rxnet->service_conn_reaper); rxrpc_queue_work(&rxnet->client_conn_reaper); - rxrpc_put_local(rx->local); + rxrpc_unuse_local(rx->local); rx->local = NULL; key_put(rx->key); rx->key = NULL; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 822f45386e31..145335611af6 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -254,7 +254,8 @@ struct rxrpc_security { */ struct rxrpc_local { struct rcu_head rcu; - atomic_t usage; + atomic_t active_users; /* Number of users of the local endpoint */ + atomic_t usage; /* Number of references to the structure */ struct rxrpc_net *rxnet; /* The network ns in which this resides */ struct list_head link; struct socket *socket; /* my UDP socket */ @@ -649,7 +650,6 @@ struct rxrpc_call { /* receive-phase ACK management */ u8 ackr_reason; /* reason to ACK */ - u16 ackr_skew; /* skew on packet being ACK'd */ rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */ rxrpc_serial_t ackr_first_seq; /* first sequence number received */ rxrpc_seq_t ackr_prev_seq; /* previous sequence number received */ @@ -743,7 +743,7 @@ int rxrpc_reject_call(struct rxrpc_sock *); /* * call_event.c */ -void rxrpc_propose_ACK(struct rxrpc_call *, u8, u16, u32, bool, bool, +void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool, bool, enum rxrpc_propose_ack_trace); void rxrpc_process_call(struct work_struct *); @@ -1002,6 +1002,8 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *, const struct sockaddr_rxrpc struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *); struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *); void rxrpc_put_local(struct rxrpc_local *); +struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *); +void rxrpc_unuse_local(struct rxrpc_local *); void rxrpc_queue_local(struct rxrpc_local *); void rxrpc_destroy_all_locals(struct rxrpc_net *); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index bc2adeb3acb9..c767679bfa5d 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -43,8 +43,7 @@ static void rxrpc_propose_ping(struct rxrpc_call *call, * propose an ACK be sent */ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u16 skew, u32 serial, bool immediate, - bool background, + u32 serial, bool immediate, bool background, enum rxrpc_propose_ack_trace why) { enum rxrpc_propose_ack_outcome outcome = rxrpc_propose_ack_use; @@ -69,14 +68,12 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, if (RXRPC_ACK_UPDATEABLE & (1 << ack_reason)) { outcome = rxrpc_propose_ack_update; call->ackr_serial = serial; - call->ackr_skew = skew; } if (!immediate) goto trace; } else if (prior > rxrpc_ack_priority[call->ackr_reason]) { call->ackr_reason = ack_reason; call->ackr_serial = serial; - call->ackr_skew = skew; } else { outcome = rxrpc_propose_ack_subsume; } @@ -137,11 +134,11 @@ trace: * propose an ACK be sent, locking the call structure */ void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u16 skew, u32 serial, bool immediate, bool background, + u32 serial, bool immediate, bool background, enum rxrpc_propose_ack_trace why) { spin_lock_bh(&call->lock); - __rxrpc_propose_ACK(call, ack_reason, skew, serial, + __rxrpc_propose_ACK(call, ack_reason, serial, immediate, background, why); spin_unlock_bh(&call->lock); } @@ -239,7 +236,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) ack_ts = ktime_sub(now, call->acks_latest_ts); if (ktime_to_ns(ack_ts) < call->peer->rtt) goto out; - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false, rxrpc_propose_ack_ping_for_lost_ack); rxrpc_send_ack_packet(call, true, NULL); goto out; @@ -372,7 +369,7 @@ recheck_state: if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_keepalive, now); cmpxchg(&call->keepalive_at, t, now + MAX_JIFFY_OFFSET); - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, true, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, true, rxrpc_propose_ack_ping_for_keepalive); set_bit(RXRPC_CALL_EV_PING, &call->events); } @@ -407,7 +404,7 @@ recheck_state: send_ack = NULL; if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) { call->acks_lost_top = call->tx_top; - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false, rxrpc_propose_ack_ping_for_lost_ack); send_ack = &call->acks_lost_ping; } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 5bd6f1546e5c..dd47d465d1d3 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -196,15 +196,14 @@ send_extra_data: * Ping the other end to fill our RTT cache and to retrieve the rwind * and MTU parameters. */ -static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb, - int skew) +static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); ktime_t now = skb->tstamp; if (call->peer->rtt_usage < 3 || ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, skew, sp->hdr.serial, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, true, true, rxrpc_propose_ack_ping_for_params); } @@ -419,8 +418,7 @@ static void rxrpc_input_dup_data(struct rxrpc_call *call, rxrpc_seq_t seq, /* * Process a DATA packet, adding the packet to the Rx ring. */ -static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb, - u16 skew) +static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); enum rxrpc_call_state state; @@ -600,11 +598,11 @@ skip: ack: if (ack) - rxrpc_propose_ACK(call, ack, skew, ack_serial, + rxrpc_propose_ACK(call, ack, ack_serial, immediate_ack, true, rxrpc_propose_ack_input_data); else - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, skew, serial, + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, false, true, rxrpc_propose_ack_input_data); @@ -822,8 +820,7 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks, * soft-ACK means that the packet may be discarded and retransmission * requested. A phase is complete when all packets are hard-ACK'd. */ -static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, - u16 skew) +static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_ack_summary summary = { 0 }; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -867,11 +864,11 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, if (buf.ack.reason == RXRPC_ACK_PING) { _proto("Rx ACK %%%u PING Request", sp->hdr.serial); rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE, - skew, sp->hdr.serial, true, true, + sp->hdr.serial, true, true, rxrpc_propose_ack_respond_to_ping); } else if (sp->hdr.flags & RXRPC_REQUEST_ACK) { rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, - skew, sp->hdr.serial, true, true, + sp->hdr.serial, true, true, rxrpc_propose_ack_respond_to_ack); } @@ -948,7 +945,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, RXRPC_TX_ANNO_LAST && summary.nr_acks == call->tx_top - hard_ack && rxrpc_is_client_call(call)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, skew, sp->hdr.serial, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, false, true, rxrpc_propose_ack_ping_for_lost_reply); @@ -1004,7 +1001,7 @@ static void rxrpc_input_abort(struct rxrpc_call *call, struct sk_buff *skb) * Process an incoming call packet. */ static void rxrpc_input_call_packet(struct rxrpc_call *call, - struct sk_buff *skb, u16 skew) + struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned long timo; @@ -1023,11 +1020,11 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_DATA: - rxrpc_input_data(call, skb, skew); + rxrpc_input_data(call, skb); break; case RXRPC_PACKET_TYPE_ACK: - rxrpc_input_ack(call, skb, skew); + rxrpc_input_ack(call, skb); break; case RXRPC_PACKET_TYPE_BUSY: @@ -1108,8 +1105,12 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, { _enter("%p,%p", local, skb); - skb_queue_tail(&local->event_queue, skb); - rxrpc_queue_local(local); + if (rxrpc_get_local_maybe(local)) { + skb_queue_tail(&local->event_queue, skb); + rxrpc_queue_local(local); + } else { + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + } } /* @@ -1119,8 +1120,12 @@ static void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) { CHECK_SLAB_OKAY(&local->usage); - skb_queue_tail(&local->reject_queue, skb); - rxrpc_queue_local(local); + if (rxrpc_get_local_maybe(local)) { + skb_queue_tail(&local->reject_queue, skb); + rxrpc_queue_local(local); + } else { + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + } } /* @@ -1173,7 +1178,6 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) struct rxrpc_peer *peer = NULL; struct rxrpc_sock *rx = NULL; unsigned int channel; - int skew = 0; _enter("%p", udp_sk); @@ -1301,15 +1305,8 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) goto out; } - /* Note the serial number skew here */ - skew = (int)sp->hdr.serial - (int)conn->hi_serial; - if (skew >= 0) { - if (skew > 0) - conn->hi_serial = sp->hdr.serial; - } else { - skew = -skew; - skew = min(skew, 65535); - } + if ((int)sp->hdr.serial - (int)conn->hi_serial > 0) + conn->hi_serial = sp->hdr.serial; /* Call-bound packets are routed by connection channel. */ channel = sp->hdr.cid & RXRPC_CHANNELMASK; @@ -1372,11 +1369,11 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) call = rxrpc_new_incoming_call(local, rx, skb); if (!call) goto reject_packet; - rxrpc_send_ping(call, skb, skew); + rxrpc_send_ping(call, skb); mutex_unlock(&call->user_mutex); } - rxrpc_input_call_packet(call, skb, skew); + rxrpc_input_call_packet(call, skb); goto discard; discard: diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index b1c71bad510b..9798159ee65f 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -79,6 +79,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL); if (local) { atomic_set(&local->usage, 1); + atomic_set(&local->active_users, 1); local->rxnet = rxnet; INIT_LIST_HEAD(&local->link); INIT_WORK(&local->processor, rxrpc_local_processor); @@ -266,11 +267,8 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net, * bind the transport socket may still fail if we're attempting * to use a local address that the dying object is still using. */ - if (!rxrpc_get_local_maybe(local)) { - cursor = cursor->next; - list_del_init(&local->link); + if (!rxrpc_use_local(local)) break; - } age = "old"; goto found; @@ -284,7 +282,10 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net, if (ret < 0) goto sock_error; - list_add_tail(&local->link, cursor); + if (cursor != &rxnet->local_endpoints) + list_replace(cursor, &local->link); + else + list_add_tail(&local->link, cursor); age = "new"; found: @@ -342,7 +343,8 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local) } /* - * Queue a local endpoint. + * Queue a local endpoint unless it has become unreferenced and pass the + * caller's reference to the work item. */ void rxrpc_queue_local(struct rxrpc_local *local) { @@ -351,15 +353,8 @@ void rxrpc_queue_local(struct rxrpc_local *local) if (rxrpc_queue_work(&local->processor)) trace_rxrpc_local(local, rxrpc_local_queued, atomic_read(&local->usage), here); -} - -/* - * A local endpoint reached its end of life. - */ -static void __rxrpc_put_local(struct rxrpc_local *local) -{ - _enter("%d", local->debug_id); - rxrpc_queue_work(&local->processor); + else + rxrpc_put_local(local); } /* @@ -375,11 +370,46 @@ void rxrpc_put_local(struct rxrpc_local *local) trace_rxrpc_local(local, rxrpc_local_put, n, here); if (n == 0) - __rxrpc_put_local(local); + call_rcu(&local->rcu, rxrpc_local_rcu); } } /* + * Start using a local endpoint. + */ +struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local) +{ + unsigned int au; + + local = rxrpc_get_local_maybe(local); + if (!local) + return NULL; + + au = atomic_fetch_add_unless(&local->active_users, 1, 0); + if (au == 0) { + rxrpc_put_local(local); + return NULL; + } + + return local; +} + +/* + * Cease using a local endpoint. Once the number of active users reaches 0, we + * start the closure of the transport in the work processor. + */ +void rxrpc_unuse_local(struct rxrpc_local *local) +{ + unsigned int au; + + au = atomic_dec_return(&local->active_users); + if (au == 0) + rxrpc_queue_local(local); + else + rxrpc_put_local(local); +} + +/* * Destroy a local endpoint's socket and then hand the record to RCU to dispose * of. * @@ -393,16 +423,6 @@ static void rxrpc_local_destroyer(struct rxrpc_local *local) _enter("%d", local->debug_id); - /* We can get a race between an incoming call packet queueing the - * processor again and the work processor starting the destruction - * process which will shut down the UDP socket. - */ - if (local->dead) { - _leave(" [already dead]"); - return; - } - local->dead = true; - mutex_lock(&rxnet->local_mutex); list_del_init(&local->link); mutex_unlock(&rxnet->local_mutex); @@ -422,13 +442,11 @@ static void rxrpc_local_destroyer(struct rxrpc_local *local) */ rxrpc_purge_queue(&local->reject_queue); rxrpc_purge_queue(&local->event_queue); - - _debug("rcu local %d", local->debug_id); - call_rcu(&local->rcu, rxrpc_local_rcu); } /* - * Process events on an endpoint + * Process events on an endpoint. The work item carries a ref which + * we must release. */ static void rxrpc_local_processor(struct work_struct *work) { @@ -441,8 +459,10 @@ static void rxrpc_local_processor(struct work_struct *work) do { again = false; - if (atomic_read(&local->usage) == 0) - return rxrpc_local_destroyer(local); + if (atomic_read(&local->active_users) == 0) { + rxrpc_local_destroyer(local); + break; + } if (!skb_queue_empty(&local->reject_queue)) { rxrpc_reject_packets(local); @@ -454,6 +474,8 @@ static void rxrpc_local_processor(struct work_struct *work) again = true; } } while (again); + + rxrpc_put_local(local); } /* diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 948e3fe249ec..369e516c4bdf 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -87,7 +87,7 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, *_top = top; pkt->ack.bufferSpace = htons(8); - pkt->ack.maxSkew = htons(call->ackr_skew); + pkt->ack.maxSkew = htons(0); pkt->ack.firstPacket = htonl(hard_ack + 1); pkt->ack.previousPacket = htonl(call->ackr_prev_seq); pkt->ack.serial = htonl(serial); @@ -228,7 +228,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, if (ping) clear_bit(RXRPC_CALL_PINGING, &call->flags); rxrpc_propose_ACK(call, pkt->ack.reason, - ntohs(pkt->ack.maxSkew), ntohl(pkt->ack.serial), false, true, rxrpc_propose_ack_retry_tx); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 5abf46cf9e6c..9a7e1bc9791d 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -141,7 +141,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) ASSERTCMP(call->rx_hard_ack, ==, call->rx_top); if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) { - rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, false, true, + rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial, false, true, rxrpc_propose_ack_terminal_ack); //rxrpc_send_ack_packet(call, false, NULL); } @@ -159,7 +159,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) call->state = RXRPC_CALL_SERVER_ACK_REQUEST; call->expect_req_by = jiffies + MAX_JIFFY_OFFSET; write_unlock_bh(&call->state_lock); - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial, false, true, + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, false, true, rxrpc_propose_ack_processing_op); break; default: @@ -212,7 +212,7 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) if (after_eq(hard_ack, call->ackr_consumed + 2) || after_eq(top, call->ackr_seen + 2) || (hard_ack == top && after(hard_ack, call->ackr_consumed))) - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial, + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, true, true, rxrpc_propose_ack_rotate_rx); if (call->ackr_reason && call->ackr_reason != RXRPC_ACK_DELAY) diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index b100870f02a6..37dced00b63d 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -307,6 +307,17 @@ static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index) return tcf_idr_search(tn, a, index); } +static size_t tcf_skbedit_get_fill_size(const struct tc_action *act) +{ + return nla_total_size(sizeof(struct tc_skbedit)) + + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_PRIORITY */ + + nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING */ + + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MARK */ + + nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_PTYPE */ + + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MASK */ + + nla_total_size_64bit(sizeof(u64)); /* TCA_SKBEDIT_FLAGS */ +} + static struct tc_action_ops act_skbedit_ops = { .kind = "skbedit", .id = TCA_ID_SKBEDIT, @@ -316,6 +327,7 @@ static struct tc_action_ops act_skbedit_ops = { .init = tcf_skbedit_init, .cleanup = tcf_skbedit_cleanup, .walk = tcf_skbedit_walker, + .get_fill_size = tcf_skbedit_get_fill_size, .lookup = tcf_skbedit_search, .size = sizeof(struct tcf_skbedit), }; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index c39db507ba3f..e25d414ae12f 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1195,7 +1195,8 @@ unlock: spin_unlock_bh(qdisc_lock(sch)); free_sched: - kfree(new_admin); + if (new_admin) + call_rcu(&new_admin->rcu, taprio_free_sched_cb); return err; } diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 7c0b2b778703..43922d86e510 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -373,9 +373,9 @@ static int tls_push_data(struct sock *sk, struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_prot_info *prot = &tls_ctx->prot_info; struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); - int tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST; int more = flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE); struct tls_record_info *record = ctx->open_record; + int tls_push_record_flags; struct page_frag *pfrag; size_t orig_size = size; u32 max_open_record_len; @@ -390,6 +390,9 @@ static int tls_push_data(struct sock *sk, if (sk->sk_err) return -sk->sk_err; + flags |= MSG_SENDPAGE_DECRYPTED; + tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST; + timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); if (tls_is_partially_sent_record(tls_ctx)) { rc = tls_push_partial_record(sk, tls_ctx, flags); @@ -576,7 +579,9 @@ void tls_device_write_space(struct sock *sk, struct tls_context *ctx) gfp_t sk_allocation = sk->sk_allocation; sk->sk_allocation = GFP_ATOMIC; - tls_push_partial_record(sk, ctx, MSG_DONTWAIT | MSG_NOSIGNAL); + tls_push_partial_record(sk, ctx, + MSG_DONTWAIT | MSG_NOSIGNAL | + MSG_SENDPAGE_DECRYPTED); sk->sk_allocation = sk_allocation; } } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 4e455018da65..a5aa7d3ac6a1 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1466,8 +1466,8 @@ union bpf_attr { * If no cookie has been set yet, generate a new cookie. Once * generated, the socket cookie remains stable for the life of the * socket. This helper can be useful for monitoring per socket - * networking traffic statistics as it provides a unique socket - * identifier per namespace. + * networking traffic statistics as it provides a global socket + * identifier that can be assumed unique. * Return * A 8-byte long non-decreasing number on success, or 0 if the * socket field is missing inside *skb*. @@ -1571,8 +1571,11 @@ union bpf_attr { * but this is only implemented for native XDP (with driver * support) as of this writing). * - * All values for *flags* are reserved for future usage, and must - * be left at zero. + * The lower two bits of *flags* are used as the return code if + * the map lookup fails. This is so that the return value can be + * one of the XDP program return codes up to XDP_TX, as chosen by + * the caller. Any higher bits in the *flags* argument must be + * unset. * * When used to redirect packets to net devices, this helper * provides a high performance increase over **bpf_redirect**\ (). diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json index bf5ebf59c2d4..9cdd2e31ac2c 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json @@ -670,5 +670,52 @@ "teardown": [ "$TC actions flush action skbedit" ] + }, + { + "id": "630c", + "name": "Add batch of 32 skbedit actions with all parameters and cookie", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action skbedit queue_mapping 2 priority 10 mark 7/0xaabbccdd ptype host inheritdsfield index \\$i cookie aabbccddeeff112233445566778800a1 \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "32", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "706d", + "name": "Delete batch of 32 skbedit actions with all parameters", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ], + "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action skbedit queue_mapping 2 priority 10 mark 7/0xaabbccdd ptype host inheritdsfield index \\$i \\\"; args=\\\"\\$args\\$cmd\\\"; done && $TC actions add \\$args\"" + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action skbedit index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "0", + "teardown": [] } ] |