diff options
98 files changed, 737 insertions, 440 deletions
diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst index 2d8d2fed7317..f41620439ef3 100644 --- a/Documentation/core-api/dma-api.rst +++ b/Documentation/core-api/dma-api.rst @@ -206,6 +206,14 @@ others should not be larger than the returned value. :: + bool + dma_need_sync(struct device *dev, dma_addr_t dma_addr); + +Returns %true if dma_sync_single_for_{device,cpu} calls are required to +transfer memory ownership. Returns %false if those calls can be skipped. + +:: + unsigned long dma_get_merge_boundary(struct device *dev); diff --git a/Documentation/networking/arcnet.rst b/Documentation/networking/arcnet.rst index e93d9820f0f1..82fce606c0f0 100644 --- a/Documentation/networking/arcnet.rst +++ b/Documentation/networking/arcnet.rst @@ -434,7 +434,7 @@ can set up your network then: ifconfig arc0 insight route add insight arc0 route add freedom arc0 /* I would use the subnet here (like I said - to to in "single protocol" above), + to in "single protocol" above), but the rest of the subnet unfortunately lies across the PPP link on freedom, which confuses diff --git a/Documentation/networking/ax25.rst b/Documentation/networking/ax25.rst index 824afd7002db..f060cfb1445a 100644 --- a/Documentation/networking/ax25.rst +++ b/Documentation/networking/ax25.rst @@ -6,7 +6,7 @@ AX.25 To use the amateur radio protocols within Linux you will need to get a suitable copy of the AX.25 Utilities. More detailed information about -AX.25, NET/ROM and ROSE, associated programs and and utilities can be +AX.25, NET/ROM and ROSE, associated programs and utilities can be found on http://www.linux-ax25.org. There is an active mailing list for discussing Linux amateur radio matters diff --git a/Documentation/networking/can_ucan_protocol.rst b/Documentation/networking/can_ucan_protocol.rst index 4cef88d24fc7..638ac1ee7914 100644 --- a/Documentation/networking/can_ucan_protocol.rst +++ b/Documentation/networking/can_ucan_protocol.rst @@ -144,7 +144,7 @@ UCAN_COMMAND_SET_BITTIMING *Host2Dev; mandatory* -Setup bittiming by sending the the structure +Setup bittiming by sending the structure ``ucan_ctl_payload_t.cmd_set_bittiming`` (see ``struct bittiming`` for details) @@ -232,7 +232,7 @@ UCAN_IN_TX_COMPLETE zero The CAN device has sent a message to the CAN bus. It answers with a -list of of tuples <echo-ids, flags>. +list of tuples <echo-ids, flags>. The echo-id identifies the frame from (echos the id from a previous UCAN_OUT_TX message). The flag indicates the result of the diff --git a/Documentation/networking/dsa/dsa.rst b/Documentation/networking/dsa/dsa.rst index 563d56c6a25c..a8d15dd2b42b 100644 --- a/Documentation/networking/dsa/dsa.rst +++ b/Documentation/networking/dsa/dsa.rst @@ -95,7 +95,7 @@ Ethernet switch. Networking stack hooks ---------------------- -When a master netdev is used with DSA, a small hook is placed in in the +When a master netdev is used with DSA, a small hook is placed in the networking stack is in order to have the DSA subsystem process the Ethernet switch specific tagging protocol. DSA accomplishes this by registering a specific (and fake) Ethernet type (later becoming ``skb->protocol``) with the diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index b72f89d5694c..837d51f9e1fa 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -741,7 +741,7 @@ tcp_fastopen - INTEGER Default: 0x1 - Note that that additional client or server features are only + Note that additional client or server features are only effective if the basic support (0x1 and 0x2) are enabled respectively. tcp_fastopen_blackhole_timeout_sec - INTEGER diff --git a/Documentation/networking/ipvs-sysctl.rst b/Documentation/networking/ipvs-sysctl.rst index be36c4600e8f..2afccc63856e 100644 --- a/Documentation/networking/ipvs-sysctl.rst +++ b/Documentation/networking/ipvs-sysctl.rst @@ -114,7 +114,7 @@ drop_entry - INTEGER modes (when there is no enough available memory, the strategy is enabled and the variable is automatically set to 2, otherwise the strategy is disabled and the variable is set to - 1), and 3 means that that the strategy is always enabled. + 1), and 3 means that the strategy is always enabled. drop_packet - INTEGER - 0 - disabled (default) diff --git a/Documentation/networking/rxrpc.rst b/Documentation/networking/rxrpc.rst index 68552b92dc44..39c2249c7aa7 100644 --- a/Documentation/networking/rxrpc.rst +++ b/Documentation/networking/rxrpc.rst @@ -186,7 +186,7 @@ About the AF_RXRPC driver: time [tunable] after the last connection using it discarded, in case a new connection is made that could use it. - (#) A client-side connection is only shared between calls if they have have + (#) A client-side connection is only shared between calls if they have the same key struct describing their security (and assuming the calls would otherwise share the connection). Non-secured calls would also be able to share connections with each other. diff --git a/MAINTAINERS b/MAINTAINERS index 63c4cc4a04d6..5f14938a5985 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2929,6 +2929,7 @@ F: include/uapi/linux/atm* ATMEL MACB ETHERNET DRIVER M: Nicolas Ferre <[email protected]> +M: Claudiu Beznea <[email protected]> S: Supported F: drivers/net/ethernet/cadence/ diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 47d65b77caf7..7c17b0f705ec 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -1268,6 +1268,9 @@ static int ksz8795_switch_init(struct ksz_device *dev) return -ENOMEM; } + /* set the real number of ports */ + dev->ds->num_ports = dev->port_cnt; + return 0; } diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 9a51b8a4de5d..8d15c3016024 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -1588,6 +1588,9 @@ static int ksz9477_switch_init(struct ksz_device *dev) return -ENOMEM; } + /* set the real number of ports */ + dev->ds->num_ports = dev->port_cnt; + return 0; } diff --git a/drivers/net/dsa/microchip/ksz9477_i2c.c b/drivers/net/dsa/microchip/ksz9477_i2c.c index 7d050fab0889..7951f52d860d 100644 --- a/drivers/net/dsa/microchip/ksz9477_i2c.c +++ b/drivers/net/dsa/microchip/ksz9477_i2c.c @@ -79,6 +79,7 @@ MODULE_DEVICE_TABLE(i2c, ksz9477_i2c_id); static const struct of_device_id ksz9477_dt_ids[] = { { .compatible = "microchip,ksz9477" }, { .compatible = "microchip,ksz9897" }, + { .compatible = "microchip,ksz9893" }, { .compatible = "microchip,ksz9567" }, {}, }; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 1aa6dc10dc0b..ad522f822cc2 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -3493,7 +3493,7 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info, drv_fw = &fw_info->fw_hdr; /* Read the header of the firmware on the card */ - ret = -t4_read_flash(adap, FLASH_FW_START, + ret = t4_read_flash(adap, FLASH_FW_START, sizeof(*card_fw) / sizeof(uint32_t), (uint32_t *)card_fw, 1); if (ret == 0) { @@ -3522,8 +3522,8 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info, should_install_fs_fw(adap, card_fw_usable, be32_to_cpu(fs_fw->fw_ver), be32_to_cpu(card_fw->fw_ver))) { - ret = -t4_fw_upgrade(adap, adap->mbox, fw_data, - fw_size, 0); + ret = t4_fw_upgrade(adap, adap->mbox, fw_data, + fw_size, 0); if (ret != 0) { dev_err(adap->pdev_dev, "failed to install firmware: %d\n", ret); @@ -3554,7 +3554,7 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info, FW_HDR_FW_VER_MICRO_G(c), FW_HDR_FW_VER_BUILD_G(c), FW_HDR_FW_VER_MAJOR_G(k), FW_HDR_FW_VER_MINOR_G(k), FW_HDR_FW_VER_MICRO_G(k), FW_HDR_FW_VER_BUILD_G(k)); - ret = EINVAL; + ret = -EINVAL; goto bye; } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c index 0245da02efbb..b735bc537508 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c @@ -814,6 +814,8 @@ err_aeqs_init: err_init_msix: err_pfhwdev_alloc: hinic_free_hwif(hwif); + if (err > 0) + err = -EIO; return ERR_PTR(err); } diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index c639e3a29302..7d5d9d34f4e4 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -3959,7 +3959,7 @@ static void mvneta_mac_config(struct phylink_config *config, unsigned int mode, /* When at 2.5G, the link partner can send frames with shortened * preambles. */ - if (state->speed == SPEED_2500) + if (state->interface == PHY_INTERFACE_MODE_2500BASEX) new_ctrl4 |= MVNETA_GMAC4_SHORT_PREAMBLE_ENABLE; if (pp->phy_interface != state->interface) { diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c index 55226b264e3c..ac7e5a04c8ac 100644 --- a/drivers/net/ipa/gsi.c +++ b/drivers/net/ipa/gsi.c @@ -500,6 +500,13 @@ static int gsi_channel_stop_command(struct gsi_channel *channel) int ret; state = gsi_channel_state(channel); + + /* Channel could have entered STOPPED state since last call + * if it timed out. If so, we're done. + */ + if (state == GSI_CHANNEL_STATE_STOPPED) + return 0; + if (state != GSI_CHANNEL_STATE_STARTED && state != GSI_CHANNEL_STATE_STOP_IN_PROC) return -EINVAL; @@ -789,20 +796,11 @@ int gsi_channel_start(struct gsi *gsi, u32 channel_id) int gsi_channel_stop(struct gsi *gsi, u32 channel_id) { struct gsi_channel *channel = &gsi->channel[channel_id]; - enum gsi_channel_state state; u32 retries; int ret; gsi_channel_freeze(channel); - /* Channel could have entered STOPPED state since last call if the - * STOP command timed out. We won't stop a channel if stopping it - * was successful previously (so we still want the freeze above). - */ - state = gsi_channel_state(channel); - if (state == GSI_CHANNEL_STATE_STOPPED) - return 0; - /* RX channels might require a little time to enter STOPPED state */ retries = channel->toward_ipa ? 0 : GSI_CHANNEL_STOP_RX_RETRIES; diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c index c9ab865e7290..d92dd3f09b73 100644 --- a/drivers/net/ipa/ipa_cmd.c +++ b/drivers/net/ipa/ipa_cmd.c @@ -586,6 +586,21 @@ u32 ipa_cmd_tag_process_count(void) return 4; } +void ipa_cmd_tag_process(struct ipa *ipa) +{ + u32 count = ipa_cmd_tag_process_count(); + struct gsi_trans *trans; + + trans = ipa_cmd_trans_alloc(ipa, count); + if (trans) { + ipa_cmd_tag_process_add(trans); + gsi_trans_commit_wait(trans); + } else { + dev_err(&ipa->pdev->dev, + "error allocating %u entry tag transaction\n", count); + } +} + static struct ipa_cmd_info * ipa_cmd_info_alloc(struct ipa_endpoint *endpoint, u32 tre_count) { diff --git a/drivers/net/ipa/ipa_cmd.h b/drivers/net/ipa/ipa_cmd.h index e440aa69c8b5..1a646e0264a0 100644 --- a/drivers/net/ipa/ipa_cmd.h +++ b/drivers/net/ipa/ipa_cmd.h @@ -172,6 +172,14 @@ void ipa_cmd_tag_process_add(struct gsi_trans *trans); u32 ipa_cmd_tag_process_count(void); /** + * ipa_cmd_tag_process() - Perform a tag process + * + * @Return: The number of elements to allocate in a transaction + * to hold tag process commands + */ +void ipa_cmd_tag_process(struct ipa *ipa); + +/** * ipa_cmd_trans_alloc() - Allocate a transaction for the command TX endpoint * @ipa: IPA pointer * @tre_count: Number of elements in the transaction diff --git a/drivers/net/ipa/ipa_data-sdm845.c b/drivers/net/ipa/ipa_data-sdm845.c index 52d4b84e0dac..de2768d71ab5 100644 --- a/drivers/net/ipa/ipa_data-sdm845.c +++ b/drivers/net/ipa/ipa_data-sdm845.c @@ -44,7 +44,6 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .endpoint = { .seq_type = IPA_SEQ_INVALID, .config = { - .checksum = true, .aggregation = true, .status_enable = true, .rx = { diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index 9f50d0d11704..9e58e495d373 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -1450,6 +1450,8 @@ void ipa_endpoint_suspend(struct ipa *ipa) if (ipa->modem_netdev) ipa_modem_suspend(ipa->modem_netdev); + ipa_cmd_tag_process(ipa); + ipa_endpoint_suspend_one(ipa->name_map[IPA_ENDPOINT_AP_LAN_RX]); ipa_endpoint_suspend_one(ipa->name_map[IPA_ENDPOINT_AP_COMMAND_TX]); } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 858b012074bd..7adeb91bd368 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -62,6 +62,7 @@ #include <net/rtnetlink.h> #include <net/sock.h> #include <net/xdp.h> +#include <net/ip_tunnels.h> #include <linux/seq_file.h> #include <linux/uio.h> #include <linux/skb_array.h> @@ -1351,6 +1352,7 @@ static void tun_net_init(struct net_device *dev) switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: dev->netdev_ops = &tun_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; /* Point-to-Point TUN Device */ dev->hard_header_len = 0; diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index a8f151b1b5fa..c9f65e96ccb0 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -262,6 +262,7 @@ static void wg_setup(struct net_device *dev) max(sizeof(struct ipv6hdr), sizeof(struct iphdr)); dev->netdev_ops = &netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->hard_header_len = 0; dev->addr_len = 0; dev->needed_headroom = DATA_PACKET_HEAD_ROOM; diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h index c58df439dbbe..dfb674e03076 100644 --- a/drivers/net/wireguard/queueing.h +++ b/drivers/net/wireguard/queueing.h @@ -11,6 +11,7 @@ #include <linux/skbuff.h> #include <linux/ip.h> #include <linux/ipv6.h> +#include <net/ip_tunnels.h> struct wg_device; struct wg_peer; @@ -65,25 +66,9 @@ struct packet_cb { #define PACKET_CB(skb) ((struct packet_cb *)((skb)->cb)) #define PACKET_PEER(skb) (PACKET_CB(skb)->keypair->entry.peer) -/* Returns either the correct skb->protocol value, or 0 if invalid. */ -static inline __be16 wg_examine_packet_protocol(struct sk_buff *skb) -{ - if (skb_network_header(skb) >= skb->head && - (skb_network_header(skb) + sizeof(struct iphdr)) <= - skb_tail_pointer(skb) && - ip_hdr(skb)->version == 4) - return htons(ETH_P_IP); - if (skb_network_header(skb) >= skb->head && - (skb_network_header(skb) + sizeof(struct ipv6hdr)) <= - skb_tail_pointer(skb) && - ipv6_hdr(skb)->version == 6) - return htons(ETH_P_IPV6); - return 0; -} - static inline bool wg_check_packet_protocol(struct sk_buff *skb) { - __be16 real_protocol = wg_examine_packet_protocol(skb); + __be16 real_protocol = ip_tunnel_parse_protocol(skb); return real_protocol && skb->protocol == real_protocol; } diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index 9b2ab6fc91cd..2c9551ea6dc7 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -387,7 +387,7 @@ static void wg_packet_consume_data_done(struct wg_peer *peer, */ skb->ip_summed = CHECKSUM_UNNECESSARY; skb->csum_level = ~0; /* All levels */ - skb->protocol = wg_examine_packet_protocol(skb); + skb->protocol = ip_tunnel_parse_protocol(skb); if (skb->protocol == htons(ETH_P_IP)) { len = ntohs(ip_hdr(skb)->tot_len); if (unlikely(len < sizeof(struct iphdr))) diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h index 4052d649f36d..47d5b0c708c9 100644 --- a/include/linux/bpf-netns.h +++ b/include/linux/bpf-netns.h @@ -33,7 +33,7 @@ int netns_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); -int netns_bpf_prog_detach(const union bpf_attr *attr); +int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int netns_bpf_link_create(const union bpf_attr *attr, struct bpf_prog *prog); #else @@ -49,7 +49,8 @@ static inline int netns_bpf_prog_attach(const union bpf_attr *attr, return -EOPNOTSUPP; } -static inline int netns_bpf_prog_detach(const union bpf_attr *attr) +static inline int netns_bpf_prog_detach(const union bpf_attr *attr, + enum bpf_prog_type ptype) { return -EOPNOTSUPP; } diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 07052d44bca1..9750a1902ee5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1543,13 +1543,16 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map) #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #if defined(CONFIG_BPF_STREAM_PARSER) -int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which); +int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, + struct bpf_prog *old, u32 which); int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); +int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); void sock_map_unhash(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else static inline int sock_map_prog_update(struct bpf_map *map, - struct bpf_prog *prog, u32 which) + struct bpf_prog *prog, + struct bpf_prog *old, u32 which) { return -EOPNOTSUPP; } @@ -1559,6 +1562,12 @@ static inline int sock_map_get_from_fd(const union bpf_attr *attr, { return -EINVAL; } + +static inline int sock_map_prog_detach(const union bpf_attr *attr, + enum bpf_prog_type ptype) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_BPF_STREAM_PARSER */ #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) diff --git a/include/linux/btf.h b/include/linux/btf.h index 5c1ea99b480f..8b81fbb4497c 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -82,6 +82,11 @@ static inline bool btf_type_is_int(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_INT; } +static inline bool btf_type_is_small_int(const struct btf_type *t) +{ + return btf_type_is_int(t) && t->size <= sizeof(u64); +} + static inline bool btf_type_is_enum(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 136f984df0d9..8b006730687b 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -87,4 +87,5 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); int dma_direct_supported(struct device *dev, u64 mask); +bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr); #endif /* _LINUX_DMA_DIRECT_H */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 78f677cf45ab..a33ed3954ed4 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -461,6 +461,7 @@ int dma_set_mask(struct device *dev, u64 mask); int dma_set_coherent_mask(struct device *dev, u64 mask); u64 dma_get_required_mask(struct device *dev); size_t dma_max_mapping_size(struct device *dev); +bool dma_need_sync(struct device *dev, dma_addr_t dma_addr); unsigned long dma_get_merge_boundary(struct device *dev); #else /* CONFIG_HAS_DMA */ static inline dma_addr_t dma_map_page_attrs(struct device *dev, @@ -571,6 +572,10 @@ static inline size_t dma_max_mapping_size(struct device *dev) { return 0; } +static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + return false; +} static inline unsigned long dma_get_merge_boundary(struct device *dev) { return 0; diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index b05e855f1ddd..427a5b8597c2 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -308,6 +308,34 @@ static inline bool eth_type_vlan(__be16 ethertype) } } +/* A getter for the SKB protocol field which will handle VLAN tags consistently + * whether VLAN acceleration is enabled or not. + */ +static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan) +{ + unsigned int offset = skb_mac_offset(skb) + sizeof(struct ethhdr); + __be16 proto = skb->protocol; + + if (!skip_vlan) + /* VLAN acceleration strips the VLAN header from the skb and + * moves it to skb->vlan_proto + */ + return skb_vlan_tag_present(skb) ? skb->vlan_proto : proto; + + while (eth_type_vlan(proto)) { + struct vlan_hdr vhdr, *vh; + + vh = skb_header_pointer(skb, offset, sizeof(vhdr), &vhdr); + if (!vh) + break; + + proto = vh->h_vlan_encapsulated_proto; + offset += sizeof(vhdr); + } + + return proto; +} + static inline bool vlan_hw_offload_capable(netdev_features_t features, __be16 proto) { diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 08674cd14d5a..1e9ed840b9fc 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -430,6 +430,19 @@ static inline void psock_set_prog(struct bpf_prog **pprog, bpf_prog_put(prog); } +static inline int psock_replace_prog(struct bpf_prog **pprog, + struct bpf_prog *prog, + struct bpf_prog *old) +{ + if (cmpxchg(pprog, old, prog) != old) + return -ENOENT; + + if (old) + bpf_prog_put(old); + + return 0; +} + static inline void psock_progs_drop(struct sk_psock_progs *progs) { psock_set_prog(&progs->msg_parser, NULL); diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index a7eba43fe4e4..4b6e36288ddd 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -372,7 +372,8 @@ flow_dissector_init_keys(struct flow_dissector_key_control *key_control, } #ifdef CONFIG_BPF_SYSCALL -int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog); +int flow_dissector_bpf_prog_attach_check(struct net *net, + struct bpf_prog *prog); #endif /* CONFIG_BPF_SYSCALL */ #endif diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 74950663bb00..6e5f1e1aa822 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -35,13 +35,6 @@ struct genl_info; * do additional, common, filtering and return an error * @post_doit: called after an operation's doit callback, it may * undo operations done by pre_doit, for example release locks - * @mcast_bind: a socket bound to the given multicast group (which - * is given as the offset into the groups array) - * @mcast_unbind: a socket was unbound from the given multicast group. - * Note that unbind() will not be called symmetrically if the - * generic netlink family is removed while there are still open - * sockets. - * @attrbuf: buffer to store parsed attributes (private) * @mcgrps: multicast groups used by this family * @n_mcgrps: number of multicast groups * @mcgrp_offset: starting number of multicast group IDs in this family @@ -64,9 +57,6 @@ struct genl_family { void (*post_doit)(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info); - int (*mcast_bind)(struct net *net, int group); - void (*mcast_unbind)(struct net *net, int group); - struct nlattr ** attrbuf; /* private */ const struct genl_ops * ops; const struct genl_multicast_group *mcgrps; unsigned int n_ops; diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index 0f0d1efe06dd..e1eaf1780288 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -4,6 +4,7 @@ #include <linux/ip.h> #include <linux/skbuff.h> +#include <linux/if_vlan.h> #include <net/inet_sock.h> #include <net/dsfield.h> @@ -172,7 +173,7 @@ static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner) static inline int INET_ECN_set_ce(struct sk_buff *skb) { - switch (skb->protocol) { + switch (skb_protocol(skb, true)) { case cpu_to_be16(ETH_P_IP): if (skb_network_header(skb) + sizeof(struct iphdr) <= skb_tail_pointer(skb)) @@ -191,7 +192,7 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb) static inline int INET_ECN_set_ect1(struct sk_buff *skb) { - switch (skb->protocol) { + switch (skb_protocol(skb, true)) { case cpu_to_be16(ETH_P_IP): if (skb_network_header(skb) + sizeof(struct iphdr) <= skb_tail_pointer(skb)) @@ -272,12 +273,16 @@ static inline int IP_ECN_decapsulate(const struct iphdr *oiph, { __u8 inner; - if (skb->protocol == htons(ETH_P_IP)) + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): inner = ip_hdr(skb)->tos; - else if (skb->protocol == htons(ETH_P_IPV6)) + break; + case htons(ETH_P_IPV6): inner = ipv6_get_dsfield(ipv6_hdr(skb)); - else + break; + default: return 0; + } return INET_ECN_decapsulate(skb, oiph->tos, inner); } @@ -287,12 +292,16 @@ static inline int IP6_ECN_decapsulate(const struct ipv6hdr *oipv6h, { __u8 inner; - if (skb->protocol == htons(ETH_P_IP)) + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): inner = ip_hdr(skb)->tos; - else if (skb->protocol == htons(ETH_P_IPV6)) + break; + case htons(ETH_P_IPV6): inner = ipv6_get_dsfield(ipv6_hdr(skb)); - else + break; + default: return 0; + } return INET_ECN_decapsulate(skb, ipv6_get_dsfield(oipv6h), inner); } diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 076e5d7db7d3..36025dea7612 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -290,6 +290,9 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p, __u32 fwmark); void ip_tunnel_setup(struct net_device *dev, unsigned int net_id); +extern const struct header_ops ip_tunnel_header_ops; +__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb); + struct ip_tunnel_encap_ops { size_t (*encap_hlen)(struct ip_tunnel_encap *e); int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e, diff --git a/include/net/netns/bpf.h b/include/net/netns/bpf.h index a8dce2a380c8..0ca6a1b87185 100644 --- a/include/net/netns/bpf.h +++ b/include/net/netns/bpf.h @@ -9,10 +9,13 @@ #include <linux/bpf-netns.h> struct bpf_prog; +struct bpf_prog_array; struct netns_bpf { - struct bpf_prog __rcu *progs[MAX_NETNS_BPF_ATTACH_TYPE]; - struct bpf_link *links[MAX_NETNS_BPF_ATTACH_TYPE]; + /* Array of programs to run compiled from progs or links */ + struct bpf_prog_array __rcu *run_array[MAX_NETNS_BPF_ATTACH_TYPE]; + struct bpf_prog *progs[MAX_NETNS_BPF_ATTACH_TYPE]; + struct list_head links[MAX_NETNS_BPF_ATTACH_TYPE]; }; #endif /* __NETNS_BPF_H__ */ diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 9092e697059e..ac8c890a2657 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -136,17 +136,6 @@ static inline void qdisc_run(struct Qdisc *q) } } -static inline __be16 tc_skb_protocol(const struct sk_buff *skb) -{ - /* We need to take extra care in case the skb came via - * vlan accelerated path. In that case, use skb->vlan_proto - * as the original vlan header was already stripped. - */ - if (skb_vlan_tag_present(skb)) - return skb->vlan_proto; - return skb->protocol; -} - /* Calculate maximal size of packet seen by hard_start_xmit routine of this device. */ diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index a4ff226505c9..6842990e2712 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -40,7 +40,7 @@ struct xsk_buff_pool { u32 headroom; u32 chunk_size; u32 frame_len; - bool cheap_dma; + bool dma_need_sync; bool unaligned; void *addrs; struct device *dev; @@ -80,7 +80,7 @@ static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb) void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb); static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb) { - if (xskb->pool->cheap_dma) + if (!xskb->pool->dma_need_sync) return; xp_dma_sync_for_cpu_slow(xskb); @@ -91,7 +91,7 @@ void xp_dma_sync_for_device_slow(struct xsk_buff_pool *pool, dma_addr_t dma, static inline void xp_dma_sync_for_device(struct xsk_buff_pool *pool, dma_addr_t dma, size_t size) { - if (pool->cheap_dma) + if (!pool->dma_need_sync) return; xp_dma_sync_for_device_slow(pool, dma, size); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 974a71342aea..8bd33050b7bb 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3171,13 +3171,12 @@ union bpf_attr { * int bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) * Description * Copy *size* bytes from *data* into a ring buffer *ringbuf*. - * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of - * new data availability is sent. - * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of - * new data availability is sent unconditionally. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. * Return - * 0, on success; - * < 0, on error. + * 0 on success, or a negative error in case of failure. * * void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags) * Description @@ -3189,20 +3188,20 @@ union bpf_attr { * void bpf_ringbuf_submit(void *data, u64 flags) * Description * Submit reserved ring buffer sample, pointed to by *data*. - * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of - * new data availability is sent. - * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of - * new data availability is sent unconditionally. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. * Return * Nothing. Always succeeds. * * void bpf_ringbuf_discard(void *data, u64 flags) * Description * Discard reserved ring buffer sample, pointed to by *data*. - * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of - * new data availability is sent. - * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of - * new data availability is sent unconditionally. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. * Return * Nothing. Always succeeds. * @@ -3210,16 +3209,18 @@ union bpf_attr { * Description * Query various characteristics of provided ring buffer. What * exactly is queries is determined by *flags*: - * - BPF_RB_AVAIL_DATA - amount of data not yet consumed; - * - BPF_RB_RING_SIZE - the size of ring buffer; - * - BPF_RB_CONS_POS - consumer position (can wrap around); - * - BPF_RB_PROD_POS - producer(s) position (can wrap around); - * Data returned is just a momentary snapshots of actual values + * + * * **BPF_RB_AVAIL_DATA**: Amount of data not yet consumed. + * * **BPF_RB_RING_SIZE**: The size of ring buffer. + * * **BPF_RB_CONS_POS**: Consumer position (can wrap around). + * * **BPF_RB_PROD_POS**: Producer(s) position (can wrap around). + * + * Data returned is just a momentary snapshot of actual values * and could be inaccurate, so this facility should be used to * power heuristics and for reporting, not to make 100% correct * calculation. * Return - * Requested value, or 0, if flags are not recognized. + * Requested value, or 0, if *flags* are not recognized. * * int bpf_csum_level(struct sk_buff *skb, u64 level) * Description diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 58c9af1d4808..9a1a98dd9e97 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3746,7 +3746,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, return false; t = btf_type_skip_modifiers(btf, t->type, NULL); - if (!btf_type_is_int(t)) { + if (!btf_type_is_small_int(t)) { bpf_log(log, "ret type %s not allowed for fmod_ret\n", btf_kind_str[BTF_INFO_KIND(t->info)]); @@ -3768,7 +3768,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, /* skip modifiers */ while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); - if (btf_type_is_int(t) || btf_type_is_enum(t)) + if (btf_type_is_small_int(t) || btf_type_is_enum(t)) /* accessing a scalar */ return true; if (!btf_type_is_ptr(t)) { diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c index 78cf061f8179..310241ca7991 100644 --- a/kernel/bpf/net_namespace.c +++ b/kernel/bpf/net_namespace.c @@ -19,18 +19,21 @@ struct bpf_netns_link { * with netns_bpf_mutex held. */ struct net *net; + struct list_head node; /* node in list of links attached to net */ }; /* Protects updates to netns_bpf */ DEFINE_MUTEX(netns_bpf_mutex); /* Must be called with netns_bpf_mutex held. */ -static void __net_exit bpf_netns_link_auto_detach(struct bpf_link *link) +static void netns_bpf_run_array_detach(struct net *net, + enum netns_bpf_attach_type type) { - struct bpf_netns_link *net_link = - container_of(link, struct bpf_netns_link, link); + struct bpf_prog_array *run_array; - net_link->net = NULL; + run_array = rcu_replace_pointer(net->bpf.run_array[type], NULL, + lockdep_is_held(&netns_bpf_mutex)); + bpf_prog_array_free(run_array); } static void bpf_netns_link_release(struct bpf_link *link) @@ -40,22 +43,18 @@ static void bpf_netns_link_release(struct bpf_link *link) enum netns_bpf_attach_type type = net_link->netns_type; struct net *net; - /* Link auto-detached by dying netns. */ - if (!net_link->net) - return; - mutex_lock(&netns_bpf_mutex); - /* Recheck after potential sleep. We can race with cleanup_net - * here, but if we see a non-NULL struct net pointer pre_exit - * has not happened yet and will block on netns_bpf_mutex. + /* We can race with cleanup_net, but if we see a non-NULL + * struct net pointer, pre_exit has not run yet and wait for + * netns_bpf_mutex. */ net = net_link->net; if (!net) goto out_unlock; - net->bpf.links[type] = NULL; - RCU_INIT_POINTER(net->bpf.progs[type], NULL); + netns_bpf_run_array_detach(net, type); + list_del(&net_link->node); out_unlock: mutex_unlock(&netns_bpf_mutex); @@ -76,6 +75,7 @@ static int bpf_netns_link_update_prog(struct bpf_link *link, struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); enum netns_bpf_attach_type type = net_link->netns_type; + struct bpf_prog_array *run_array; struct net *net; int ret = 0; @@ -93,8 +93,11 @@ static int bpf_netns_link_update_prog(struct bpf_link *link, goto out_unlock; } + run_array = rcu_dereference_protected(net->bpf.run_array[type], + lockdep_is_held(&netns_bpf_mutex)); + WRITE_ONCE(run_array->items[0].prog, new_prog); + old_prog = xchg(&link->prog, new_prog); - rcu_assign_pointer(net->bpf.progs[type], new_prog); bpf_prog_put(old_prog); out_unlock: @@ -142,14 +145,38 @@ static const struct bpf_link_ops bpf_netns_link_ops = { .show_fdinfo = bpf_netns_link_show_fdinfo, }; +/* Must be called with netns_bpf_mutex held. */ +static int __netns_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr, + struct net *net, + enum netns_bpf_attach_type type) +{ + __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); + struct bpf_prog_array *run_array; + u32 prog_cnt = 0, flags = 0; + + run_array = rcu_dereference_protected(net->bpf.run_array[type], + lockdep_is_held(&netns_bpf_mutex)); + if (run_array) + prog_cnt = bpf_prog_array_length(run_array); + + if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) + return -EFAULT; + if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) + return -EFAULT; + if (!attr->query.prog_cnt || !prog_ids || !prog_cnt) + return 0; + + return bpf_prog_array_copy_to_user(run_array, prog_ids, + attr->query.prog_cnt); +} + int netns_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { - __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); - u32 prog_id, prog_cnt = 0, flags = 0; enum netns_bpf_attach_type type; - struct bpf_prog *attached; struct net *net; + int ret; if (attr->query.query_flags) return -EINVAL; @@ -162,36 +189,25 @@ int netns_bpf_prog_query(const union bpf_attr *attr, if (IS_ERR(net)) return PTR_ERR(net); - rcu_read_lock(); - attached = rcu_dereference(net->bpf.progs[type]); - if (attached) { - prog_cnt = 1; - prog_id = attached->aux->id; - } - rcu_read_unlock(); + mutex_lock(&netns_bpf_mutex); + ret = __netns_bpf_prog_query(attr, uattr, net, type); + mutex_unlock(&netns_bpf_mutex); put_net(net); - - if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) - return -EFAULT; - if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) - return -EFAULT; - - if (!attr->query.prog_cnt || !prog_ids || !prog_cnt) - return 0; - - if (copy_to_user(prog_ids, &prog_id, sizeof(u32))) - return -EFAULT; - - return 0; + return ret; } int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { + struct bpf_prog_array *run_array; enum netns_bpf_attach_type type; + struct bpf_prog *attached; struct net *net; int ret; + if (attr->target_fd || attr->attach_flags || attr->replace_bpf_fd) + return -EINVAL; + type = to_netns_bpf_attach_type(attr->attach_type); if (type < 0) return -EINVAL; @@ -200,19 +216,47 @@ int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) mutex_lock(&netns_bpf_mutex); /* Attaching prog directly is not compatible with links */ - if (net->bpf.links[type]) { + if (!list_empty(&net->bpf.links[type])) { ret = -EEXIST; goto out_unlock; } switch (type) { case NETNS_BPF_FLOW_DISSECTOR: - ret = flow_dissector_bpf_prog_attach(net, prog); + ret = flow_dissector_bpf_prog_attach_check(net, prog); break; default: ret = -EINVAL; break; } + if (ret) + goto out_unlock; + + attached = net->bpf.progs[type]; + if (attached == prog) { + /* The same program cannot be attached twice */ + ret = -EINVAL; + goto out_unlock; + } + + run_array = rcu_dereference_protected(net->bpf.run_array[type], + lockdep_is_held(&netns_bpf_mutex)); + if (run_array) { + WRITE_ONCE(run_array->items[0].prog, prog); + } else { + run_array = bpf_prog_array_alloc(1, GFP_KERNEL); + if (!run_array) { + ret = -ENOMEM; + goto out_unlock; + } + run_array->items[0].prog = prog; + rcu_assign_pointer(net->bpf.run_array[type], run_array); + } + + net->bpf.progs[type] = prog; + if (attached) + bpf_prog_put(attached); + out_unlock: mutex_unlock(&netns_bpf_mutex); @@ -221,63 +265,74 @@ out_unlock: /* Must be called with netns_bpf_mutex held. */ static int __netns_bpf_prog_detach(struct net *net, - enum netns_bpf_attach_type type) + enum netns_bpf_attach_type type, + struct bpf_prog *old) { struct bpf_prog *attached; /* Progs attached via links cannot be detached */ - if (net->bpf.links[type]) + if (!list_empty(&net->bpf.links[type])) return -EINVAL; - attached = rcu_dereference_protected(net->bpf.progs[type], - lockdep_is_held(&netns_bpf_mutex)); - if (!attached) + attached = net->bpf.progs[type]; + if (!attached || attached != old) return -ENOENT; - RCU_INIT_POINTER(net->bpf.progs[type], NULL); + netns_bpf_run_array_detach(net, type); + net->bpf.progs[type] = NULL; bpf_prog_put(attached); return 0; } -int netns_bpf_prog_detach(const union bpf_attr *attr) +int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { enum netns_bpf_attach_type type; + struct bpf_prog *prog; int ret; + if (attr->target_fd) + return -EINVAL; + type = to_netns_bpf_attach_type(attr->attach_type); if (type < 0) return -EINVAL; + prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); + if (IS_ERR(prog)) + return PTR_ERR(prog); + mutex_lock(&netns_bpf_mutex); - ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type); + ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type, prog); mutex_unlock(&netns_bpf_mutex); + bpf_prog_put(prog); + return ret; } static int netns_bpf_link_attach(struct net *net, struct bpf_link *link, enum netns_bpf_attach_type type) { - struct bpf_prog *prog; + struct bpf_netns_link *net_link = + container_of(link, struct bpf_netns_link, link); + struct bpf_prog_array *run_array; int err; mutex_lock(&netns_bpf_mutex); /* Allow attaching only one prog or link for now */ - if (net->bpf.links[type]) { + if (!list_empty(&net->bpf.links[type])) { err = -E2BIG; goto out_unlock; } /* Links are not compatible with attaching prog directly */ - prog = rcu_dereference_protected(net->bpf.progs[type], - lockdep_is_held(&netns_bpf_mutex)); - if (prog) { + if (net->bpf.progs[type]) { err = -EEXIST; goto out_unlock; } switch (type) { case NETNS_BPF_FLOW_DISSECTOR: - err = flow_dissector_bpf_prog_attach(net, link->prog); + err = flow_dissector_bpf_prog_attach_check(net, link->prog); break; default: err = -EINVAL; @@ -286,7 +341,15 @@ static int netns_bpf_link_attach(struct net *net, struct bpf_link *link, if (err) goto out_unlock; - net->bpf.links[type] = link; + run_array = bpf_prog_array_alloc(1, GFP_KERNEL); + if (!run_array) { + err = -ENOMEM; + goto out_unlock; + } + run_array->items[0].prog = link->prog; + rcu_assign_pointer(net->bpf.run_array[type], run_array); + + list_add_tail(&net_link->node, &net->bpf.links[type]); out_unlock: mutex_unlock(&netns_bpf_mutex); @@ -345,23 +408,34 @@ out_put_net: return err; } +static int __net_init netns_bpf_pernet_init(struct net *net) +{ + int type; + + for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) + INIT_LIST_HEAD(&net->bpf.links[type]); + + return 0; +} + static void __net_exit netns_bpf_pernet_pre_exit(struct net *net) { enum netns_bpf_attach_type type; - struct bpf_link *link; + struct bpf_netns_link *net_link; mutex_lock(&netns_bpf_mutex); for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) { - link = net->bpf.links[type]; - if (link) - bpf_netns_link_auto_detach(link); - else - __netns_bpf_prog_detach(net, type); + netns_bpf_run_array_detach(net, type); + list_for_each_entry(net_link, &net->bpf.links[type], node) + net_link->net = NULL; /* auto-detach link */ + if (net->bpf.progs[type]) + bpf_prog_put(net->bpf.progs[type]); } mutex_unlock(&netns_bpf_mutex); } static struct pernet_operations netns_bpf_pernet_ops __net_initdata = { + .init = netns_bpf_pernet_init, .pre_exit = netns_bpf_pernet_pre_exit, }; diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 180414bb0d3e..0af88bbc1c15 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -132,15 +132,6 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) { struct bpf_ringbuf *rb; - if (!data_sz || !PAGE_ALIGNED(data_sz)) - return ERR_PTR(-EINVAL); - -#ifdef CONFIG_64BIT - /* on 32-bit arch, it's impossible to overflow record's hdr->pgoff */ - if (data_sz > RINGBUF_MAX_DATA_SZ) - return ERR_PTR(-E2BIG); -#endif - rb = bpf_ringbuf_area_alloc(data_sz, numa_node); if (!rb) return ERR_PTR(-ENOMEM); @@ -166,9 +157,16 @@ static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr) return ERR_PTR(-EINVAL); if (attr->key_size || attr->value_size || - attr->max_entries == 0 || !PAGE_ALIGNED(attr->max_entries)) + !is_power_of_2(attr->max_entries) || + !PAGE_ALIGNED(attr->max_entries)) return ERR_PTR(-EINVAL); +#ifdef CONFIG_64BIT + /* on 32-bit arch, it's impossible to overflow record's hdr->pgoff */ + if (attr->max_entries > RINGBUF_MAX_DATA_SZ) + return ERR_PTR(-E2BIG); +#endif + rb_map = kzalloc(sizeof(*rb_map), GFP_USER); if (!rb_map) return ERR_PTR(-ENOMEM); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 8da159936bab..a74fce8ce043 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2121,7 +2121,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) !bpf_capable()) return -EPERM; - if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN)) + if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN) && !capable(CAP_SYS_ADMIN)) return -EPERM; if (is_perfmon_prog_type(type) && !perfmon_capable()) return -EPERM; @@ -2893,13 +2893,11 @@ static int bpf_prog_detach(const union bpf_attr *attr) switch (ptype) { case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_SK_SKB: - return sock_map_get_from_fd(attr, NULL); + return sock_map_prog_detach(attr, ptype); case BPF_PROG_TYPE_LIRC_MODE2: return lirc_prog_detach(attr); case BPF_PROG_TYPE_FLOW_DISSECTOR: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - return netns_bpf_prog_detach(attr); + return netns_bpf_prog_detach(attr, ptype); case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 34cde841ab68..94cead5a43e5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -399,8 +399,7 @@ static bool reg_type_not_null(enum bpf_reg_type type) return type == PTR_TO_SOCKET || type == PTR_TO_TCP_SOCK || type == PTR_TO_MAP_VALUE || - type == PTR_TO_SOCK_COMMON || - type == PTR_TO_BTF_ID; + type == PTR_TO_SOCK_COMMON; } static bool reg_type_may_be_null(enum bpf_reg_type type) @@ -9801,7 +9800,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) int i, j, subprog_start, subprog_end = 0, len, subprog; struct bpf_insn *insn; void *old_bpf_func; - int err; + int err, num_exentries; if (env->subprog_cnt <= 1) return 0; @@ -9876,6 +9875,14 @@ static int jit_subprogs(struct bpf_verifier_env *env) func[i]->aux->nr_linfo = prog->aux->nr_linfo; func[i]->aux->jited_linfo = prog->aux->jited_linfo; func[i]->aux->linfo_idx = env->subprog_info[i].linfo_idx; + num_exentries = 0; + insn = func[i]->insnsi; + for (j = 0; j < func[i]->len; j++, insn++) { + if (BPF_CLASS(insn->code) == BPF_LDX && + BPF_MODE(insn->code) == BPF_PROBE_MEM) + num_exentries++; + } + func[i]->aux->num_exentries = num_exentries; func[i] = bpf_int_jit_compile(func[i]); if (!func[i]->jited) { err = -ENOTSUPP; diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 0a4881e59aa7..ecb922a0bfa0 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -530,3 +530,9 @@ size_t dma_direct_max_mapping_size(struct device *dev) return swiotlb_max_mapping_size(dev); return SIZE_MAX; } + +bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + return !dev_is_dma_coherent(dev) || + is_swiotlb_buffer(dma_to_phys(dev, dma_addr)); +} diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 98e3d873792e..a8c18c9a796f 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -397,6 +397,16 @@ size_t dma_max_mapping_size(struct device *dev) } EXPORT_SYMBOL_GPL(dma_max_mapping_size); +bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (dma_is_direct(ops)) + return dma_direct_need_sync(dev, dma_addr); + return ops->sync_single_for_cpu || ops->sync_single_for_device; +} +EXPORT_SYMBOL_GPL(dma_need_sync); + unsigned long dma_get_merge_boundary(struct device *dev) { const struct dma_map_ops *ops = get_dma_ops(dev); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index bfd4ccd80847..b03c469cd01f 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -147,6 +147,20 @@ int noinline bpf_fentry_test6(u64 a, void *b, short c, int d, void *e, u64 f) return a + (long)b + c + d + (long)e + f; } +struct bpf_fentry_test_t { + struct bpf_fentry_test_t *a; +}; + +int noinline bpf_fentry_test7(struct bpf_fentry_test_t *arg) +{ + return (long)arg; +} + +int noinline bpf_fentry_test8(struct bpf_fentry_test_t *arg) +{ + return (long)arg->a; +} + int noinline bpf_modify_return_test(int a, int *b) { *b += 1; @@ -185,6 +199,7 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { + struct bpf_fentry_test_t arg = {}; u16 side_effect = 0, ret = 0; int b = 2, err = -EFAULT; u32 retval = 0; @@ -197,7 +212,9 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog, bpf_fentry_test3(4, 5, 6) != 15 || bpf_fentry_test4((void *)7, 8, 9, 10) != 34 || bpf_fentry_test5(11, (void *)12, 13, 14, 15) != 65 || - bpf_fentry_test6(16, (void *)17, 18, 19, (void *)20, 21) != 111) + bpf_fentry_test6(16, (void *)17, 18, 19, (void *)20, 21) != 111 || + bpf_fentry_test7((struct bpf_fentry_test_t *)0) != 0 || + bpf_fentry_test8(&arg) != 0) goto out; break; case BPF_MODIFY_RETURN: diff --git a/net/core/filter.c b/net/core/filter.c index 73395384afe2..82e1b5b06167 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5853,12 +5853,16 @@ BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb) { unsigned int iphdr_len; - if (skb->protocol == cpu_to_be16(ETH_P_IP)) + switch (skb_protocol(skb, true)) { + case cpu_to_be16(ETH_P_IP): iphdr_len = sizeof(struct iphdr); - else if (skb->protocol == cpu_to_be16(ETH_P_IPV6)) + break; + case cpu_to_be16(ETH_P_IPV6): iphdr_len = sizeof(struct ipv6hdr); - else + break; + default: return 0; + } if (skb_headlen(skb) < iphdr_len) return 0; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index d02df0b6d0d9..142a8824f0a8 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -70,10 +70,10 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, EXPORT_SYMBOL(skb_flow_dissector_init); #ifdef CONFIG_BPF_SYSCALL -int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog) +int flow_dissector_bpf_prog_attach_check(struct net *net, + struct bpf_prog *prog) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; - struct bpf_prog *attached; if (net == &init_net) { /* BPF flow dissector in the root namespace overrides @@ -86,26 +86,17 @@ int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog) for_each_net(ns) { if (ns == &init_net) continue; - if (rcu_access_pointer(ns->bpf.progs[type])) + if (rcu_access_pointer(ns->bpf.run_array[type])) return -EEXIST; } } else { /* Make sure root flow dissector is not attached * when attaching to the non-root namespace. */ - if (rcu_access_pointer(init_net.bpf.progs[type])) + if (rcu_access_pointer(init_net.bpf.run_array[type])) return -EEXIST; } - attached = rcu_dereference_protected(net->bpf.progs[type], - lockdep_is_held(&netns_bpf_mutex)); - if (attached == prog) - /* The same program cannot be attached twice */ - return -EINVAL; - - rcu_assign_pointer(net->bpf.progs[type], prog); - if (attached) - bpf_prog_put(attached); return 0; } #endif /* CONFIG_BPF_SYSCALL */ @@ -903,7 +894,6 @@ bool __skb_flow_dissect(const struct net *net, struct flow_dissector_key_addrs *key_addrs; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; - struct bpf_prog *attached = NULL; enum flow_dissect_ret fdret; enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX; bool mpls_el = false; @@ -960,14 +950,14 @@ bool __skb_flow_dissect(const struct net *net, WARN_ON_ONCE(!net); if (net) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; + struct bpf_prog_array *run_array; rcu_read_lock(); - attached = rcu_dereference(init_net.bpf.progs[type]); - - if (!attached) - attached = rcu_dereference(net->bpf.progs[type]); + run_array = rcu_dereference(init_net.bpf.run_array[type]); + if (!run_array) + run_array = rcu_dereference(net->bpf.run_array[type]); - if (attached) { + if (run_array) { struct bpf_flow_keys flow_keys; struct bpf_flow_dissector ctx = { .flow_keys = &flow_keys, @@ -975,6 +965,7 @@ bool __skb_flow_dissect(const struct net *net, .data_end = data + hlen, }; __be16 n_proto = proto; + struct bpf_prog *prog; if (skb) { ctx.skb = skb; @@ -985,7 +976,8 @@ bool __skb_flow_dissect(const struct net *net, n_proto = skb->protocol; } - ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff, + prog = READ_ONCE(run_array->items[0].prog); + ret = bpf_flow_dissect(prog, &ctx, n_proto, nhoff, hlen, flags); __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 351afbf6bfba..6a32a1fd34f8 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -683,7 +683,7 @@ static struct sk_psock *sk_psock_from_strp(struct strparser *strp) return container_of(parser, struct sk_psock, parser); } -static void sk_psock_skb_redirect(struct sk_psock *psock, struct sk_buff *skb) +static void sk_psock_skb_redirect(struct sk_buff *skb) { struct sk_psock *psock_other; struct sock *sk_other; @@ -715,12 +715,11 @@ static void sk_psock_skb_redirect(struct sk_psock *psock, struct sk_buff *skb) } } -static void sk_psock_tls_verdict_apply(struct sk_psock *psock, - struct sk_buff *skb, int verdict) +static void sk_psock_tls_verdict_apply(struct sk_buff *skb, int verdict) { switch (verdict) { case __SK_REDIRECT: - sk_psock_skb_redirect(psock, skb); + sk_psock_skb_redirect(skb); break; case __SK_PASS: case __SK_DROP: @@ -741,8 +740,8 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb) ret = sk_psock_bpf_run(psock, prog, skb); ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); } + sk_psock_tls_verdict_apply(skb, ret); rcu_read_unlock(); - sk_psock_tls_verdict_apply(psock, skb, ret); return ret; } EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read); @@ -770,7 +769,7 @@ static void sk_psock_verdict_apply(struct sk_psock *psock, } goto out_free; case __SK_REDIRECT: - sk_psock_skb_redirect(psock, skb); + sk_psock_skb_redirect(skb); break; case __SK_DROP: /* fall-through */ @@ -782,11 +781,18 @@ out_free: static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) { - struct sk_psock *psock = sk_psock_from_strp(strp); + struct sk_psock *psock; struct bpf_prog *prog; int ret = __SK_DROP; + struct sock *sk; rcu_read_lock(); + sk = strp->sk; + psock = sk_psock(sk); + if (unlikely(!psock)) { + kfree_skb(skb); + goto out; + } prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { skb_orphan(skb); @@ -794,8 +800,9 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) ret = sk_psock_bpf_run(psock, prog, skb); ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); } - rcu_read_unlock(); sk_psock_verdict_apply(psock, skb, ret); +out: + rcu_read_unlock(); } static int sk_psock_strp_read_done(struct strparser *strp, int err) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 4059f94e9bb5..0971f17e8e54 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -70,11 +70,49 @@ int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) struct fd f; int ret; + if (attr->attach_flags || attr->replace_bpf_fd) + return -EINVAL; + f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - ret = sock_map_prog_update(map, prog, attr->attach_type); + ret = sock_map_prog_update(map, prog, NULL, attr->attach_type); + fdput(f); + return ret; +} + +int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) +{ + u32 ufd = attr->target_fd; + struct bpf_prog *prog; + struct bpf_map *map; + struct fd f; + int ret; + + if (attr->attach_flags || attr->replace_bpf_fd) + return -EINVAL; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + prog = bpf_prog_get(attr->attach_bpf_fd); + if (IS_ERR(prog)) { + ret = PTR_ERR(prog); + goto put_map; + } + + if (prog->type != ptype) { + ret = -EINVAL; + goto put_prog; + } + + ret = sock_map_prog_update(map, NULL, prog, attr->attach_type); +put_prog: + bpf_prog_put(prog); +put_map: fdput(f); return ret; } @@ -1203,27 +1241,32 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map) } int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, - u32 which) + struct bpf_prog *old, u32 which) { struct sk_psock_progs *progs = sock_map_progs(map); + struct bpf_prog **pprog; if (!progs) return -EOPNOTSUPP; switch (which) { case BPF_SK_MSG_VERDICT: - psock_set_prog(&progs->msg_parser, prog); + pprog = &progs->msg_parser; break; case BPF_SK_SKB_STREAM_PARSER: - psock_set_prog(&progs->skb_parser, prog); + pprog = &progs->skb_parser; break; case BPF_SK_SKB_STREAM_VERDICT: - psock_set_prog(&progs->skb_verdict, prog); + pprog = &progs->skb_verdict; break; default: return -EOPNOTSUPP; } + if (old) + return psock_replace_prog(pprog, prog, old); + + psock_set_prog(pprog, prog); return 0; } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 956a806649f7..e30515f89802 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -427,7 +427,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) ipcm_init(&ipc); inet->tos = ip_hdr(skb)->tos; - sk->sk_mark = mark; + ipc.sockc.mark = mark; daddr = ipc.addr = ip_hdr(skb)->saddr; saddr = fib_compute_spec_dst(skb); @@ -710,10 +710,10 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, icmp_param.skb = skb_in; icmp_param.offset = skb_network_offset(skb_in); inet_sk(sk)->tos = tos; - sk->sk_mark = mark; ipcm_init(&ipc); ipc.addr = iph->saddr; ipc.opt = &icmp_param.replyopts.opt; + ipc.sockc.mark = mark; rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark, type, code, &icmp_param); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 090d3097ee15..17206677d503 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1702,7 +1702,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; sk->sk_sndbuf = sysctl_wmem_default; - sk->sk_mark = fl4.flowi4_mark; + ipc.sockc.mark = fl4.flowi4_mark; err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); if (unlikely(err)) { diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 181b7a2a0247..f8b419e2475c 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -844,3 +844,21 @@ void ip_tunnel_unneed_metadata(void) static_branch_dec(&ip_tunnel_metadata_cnt); } EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata); + +/* Returns either the correct skb->protocol value, or 0 if invalid. */ +__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb) +{ + if (skb_network_header(skb) >= skb->head && + (skb_network_header(skb) + sizeof(struct iphdr)) <= skb_tail_pointer(skb) && + ip_hdr(skb)->version == 4) + return htons(ETH_P_IP); + if (skb_network_header(skb) >= skb->head && + (skb_network_header(skb) + sizeof(struct ipv6hdr)) <= skb_tail_pointer(skb) && + ipv6_hdr(skb)->version == 6) + return htons(ETH_P_IPV6); + return 0; +} +EXPORT_SYMBOL(ip_tunnel_parse_protocol); + +const struct header_ops ip_tunnel_header_ops = { .parse_protocol = ip_tunnel_parse_protocol }; +EXPORT_SYMBOL(ip_tunnel_header_ops); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 1d9c8cff5ac3..460ca1099e8a 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -441,6 +441,7 @@ static const struct net_device_ops vti_netdev_ops = { static void vti_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &vti_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->type = ARPHRD_TUNNEL; ip_tunnel_setup(dev, vti_net_id); } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 40fea52c8277..75d35e76bec2 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -361,6 +361,7 @@ static const struct net_device_ops ipip_netdev_ops = { static void ipip_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipip_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->type = ARPHRD_TUNNEL; dev->flags = IFF_NOARP; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 810cc164f795..861fbd84c9cf 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3246,10 +3246,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: case TCP_MD5SIG_EXT: - if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) - err = tp->af_specific->md5_parse(sk, optname, optval, optlen); - else - err = -EINVAL; + err = tp->af_specific->md5_parse(sk, optname, optval, optlen); break; #endif case TCP_USER_TIMEOUT: @@ -4033,11 +4030,14 @@ EXPORT_SYMBOL(tcp_md5_hash_skb_data); int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key) { + u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */ struct scatterlist sg; - sg_init_one(&sg, key->key, key->keylen); - ahash_request_set_crypt(hp->md5_req, &sg, NULL, key->keylen); - return crypto_ahash_update(hp->md5_req); + sg_init_one(&sg, key->key, keylen); + ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen); + + /* We use data_race() because tcp_md5_do_add() might change key->key under us */ + return data_race(crypto_ahash_update(hp->md5_req)); } EXPORT_SYMBOL(tcp_md5_hash_key); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index f3a0eb139b76..9615e72656d1 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4582,6 +4582,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP); + sk->sk_data_ready(sk); tcp_drop(sk, skb); return; } @@ -4828,6 +4829,7 @@ queue_and_out: sk_forced_mem_schedule(sk, skb->truesize); else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); + sk->sk_data_ready(sk); goto drop; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ad6435ba6d72..04bfcbbfee83 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1111,9 +1111,21 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index); if (key) { - /* Pre-existing entry - just update that one. */ - memcpy(key->key, newkey, newkeylen); - key->keylen = newkeylen; + /* Pre-existing entry - just update that one. + * Note that the key might be used concurrently. + * data_race() is telling kcsan that we do not care of + * key mismatches, since changing MD5 key on live flows + * can lead to packet drops. + */ + data_race(memcpy(key->key, newkey, newkeylen)); + + /* Pairs with READ_ONCE() in tcp_md5_hash_key(). + * Also note that a reader could catch new key->keylen value + * but old key->key[], this is the reason we use __GFP_ZERO + * at sock_kmalloc() time below these lines. + */ + WRITE_ONCE(key->keylen, newkeylen); + return 0; } @@ -1129,7 +1141,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, rcu_assign_pointer(tp->md5sig_info, md5sig); } - key = sock_kmalloc(sk, sizeof(*key), gfp); + key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO); if (!key) return -ENOMEM; if (!tcp_alloc_md5sig_pool()) { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index a50e1990a845..5f5b2f0b0e60 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -700,7 +700,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, const struct tcp_md5sig_key *md5, - struct tcp_fastopen_cookie *foc) + struct tcp_fastopen_cookie *foc, + enum tcp_synack_type synack_type) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; @@ -715,7 +716,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, * rather than TS in order to fit in better with old, * buggy kernels, but that was deemed to be unnecessary. */ - ireq->tstamp_ok &= !ireq->sack_ok; + if (synack_type != TCP_SYNACK_COOKIE) + ireq->tstamp_ok &= !ireq->sack_ok; } #endif @@ -3394,7 +3396,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, #endif skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, - foc) + sizeof(*th); + foc, synack_type) + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index fc5000370030..9df8737ae0d3 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -566,7 +566,6 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, NULL); security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); - sk->sk_mark = mark; np = inet6_sk(sk); if (!icmpv6_xrlim_allow(sk, type, &fl6)) @@ -583,6 +582,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, fl6.flowi6_oif = np->ucast_oif; ipcm6_init_sk(&ipc6, np); + ipc6.sockc.mark = mark; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = icmpv6_route_lookup(net, skb, sk, &fl6); @@ -751,7 +751,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb) sk = icmpv6_xmit_lock(net); if (!sk) goto out_bh_enable; - sk->sk_mark = mark; np = inet6_sk(sk); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) @@ -779,6 +778,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) ipcm6_init_sk(&ipc6, np); ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb)); + ipc6.sockc.mark = mark; if (ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 821d96c720b9..a18c378ca5f4 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1846,6 +1846,7 @@ static const struct net_device_ops ip6_tnl_netdev_ops = { static void ip6_tnl_dev_setup(struct net_device *dev) { dev->netdev_ops = &ip6_tnl_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; dev->priv_destructor = ip6_dev_free; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 1147f647b9a0..0d964160a9dd 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -905,6 +905,7 @@ static const struct net_device_ops vti6_netdev_ops = { static void vti6_dev_setup(struct net_device *dev) { dev->netdev_ops = &vti6_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; dev->priv_destructor = vti6_dev_free; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 1fbb4dfbb191..5e2c34c0ac97 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1421,6 +1421,7 @@ static void ipip6_tunnel_setup(struct net_device *dev) int t_hlen = tunnel->hlen + sizeof(struct iphdr); dev->netdev_ops = &ipip6_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; dev->priv_destructor = ipip6_dev_free; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 55ee680e9db1..9395ee8a868d 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -351,22 +351,11 @@ int genl_register_family(struct genl_family *family) start = end = GENL_ID_VFS_DQUOT; } - if (family->maxattr && !family->parallel_ops) { - family->attrbuf = kmalloc_array(family->maxattr + 1, - sizeof(struct nlattr *), - GFP_KERNEL); - if (family->attrbuf == NULL) { - err = -ENOMEM; - goto errout_locked; - } - } else - family->attrbuf = NULL; - family->id = idr_alloc_cyclic(&genl_fam_idr, family, start, end + 1, GFP_KERNEL); if (family->id < 0) { err = family->id; - goto errout_free; + goto errout_locked; } err = genl_validate_assign_mc_groups(family); @@ -385,8 +374,6 @@ int genl_register_family(struct genl_family *family) errout_remove: idr_remove(&genl_fam_idr, family->id); -errout_free: - kfree(family->attrbuf); errout_locked: genl_unlock_all(); return err; @@ -419,8 +406,6 @@ int genl_unregister_family(const struct genl_family *family) atomic_read(&genl_sk_destructing_cnt) == 0); genl_unlock(); - kfree(family->attrbuf); - genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0); return 0; @@ -485,30 +470,23 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family, if (!family->maxattr) return NULL; - if (family->parallel_ops) { - attrbuf = kmalloc_array(family->maxattr + 1, - sizeof(struct nlattr *), GFP_KERNEL); - if (!attrbuf) - return ERR_PTR(-ENOMEM); - } else { - attrbuf = family->attrbuf; - } + attrbuf = kmalloc_array(family->maxattr + 1, + sizeof(struct nlattr *), GFP_KERNEL); + if (!attrbuf) + return ERR_PTR(-ENOMEM); err = __nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr, family->policy, validate, extack); if (err) { - if (family->parallel_ops) - kfree(attrbuf); + kfree(attrbuf); return ERR_PTR(err); } return attrbuf; } -static void genl_family_rcv_msg_attrs_free(const struct genl_family *family, - struct nlattr **attrbuf) +static void genl_family_rcv_msg_attrs_free(struct nlattr **attrbuf) { - if (family->parallel_ops) - kfree(attrbuf); + kfree(attrbuf); } struct genl_start_context { @@ -542,7 +520,7 @@ static int genl_start(struct netlink_callback *cb) no_attrs: info = genl_dumpit_info_alloc(); if (!info) { - genl_family_rcv_msg_attrs_free(ctx->family, attrs); + genl_family_rcv_msg_attrs_free(attrs); return -ENOMEM; } info->family = ctx->family; @@ -559,7 +537,7 @@ no_attrs: } if (rc) { - genl_family_rcv_msg_attrs_free(info->family, info->attrs); + genl_family_rcv_msg_attrs_free(info->attrs); genl_dumpit_info_free(info); cb->data = NULL; } @@ -588,7 +566,7 @@ static int genl_lock_done(struct netlink_callback *cb) rc = ops->done(cb); genl_unlock(); } - genl_family_rcv_msg_attrs_free(info->family, info->attrs); + genl_family_rcv_msg_attrs_free(info->attrs); genl_dumpit_info_free(info); return rc; } @@ -601,7 +579,7 @@ static int genl_parallel_done(struct netlink_callback *cb) if (ops->done) rc = ops->done(cb); - genl_family_rcv_msg_attrs_free(info->family, info->attrs); + genl_family_rcv_msg_attrs_free(info->attrs); genl_dumpit_info_free(info); return rc; } @@ -694,7 +672,7 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family, family->post_doit(ops, skb, &info); out: - genl_family_rcv_msg_attrs_free(family, attrbuf); + genl_family_rcv_msg_attrs_free(attrbuf); return err; } @@ -1166,60 +1144,11 @@ static struct genl_family genl_ctrl __ro_after_init = { .netnsok = true, }; -static int genl_bind(struct net *net, int group) -{ - struct genl_family *f; - int err = -ENOENT; - unsigned int id; - - down_read(&cb_lock); - - idr_for_each_entry(&genl_fam_idr, f, id) { - if (group >= f->mcgrp_offset && - group < f->mcgrp_offset + f->n_mcgrps) { - int fam_grp = group - f->mcgrp_offset; - - if (!f->netnsok && net != &init_net) - err = -ENOENT; - else if (f->mcast_bind) - err = f->mcast_bind(net, fam_grp); - else - err = 0; - break; - } - } - up_read(&cb_lock); - - return err; -} - -static void genl_unbind(struct net *net, int group) -{ - struct genl_family *f; - unsigned int id; - - down_read(&cb_lock); - - idr_for_each_entry(&genl_fam_idr, f, id) { - if (group >= f->mcgrp_offset && - group < f->mcgrp_offset + f->n_mcgrps) { - int fam_grp = group - f->mcgrp_offset; - - if (f->mcast_unbind) - f->mcast_unbind(net, fam_grp); - break; - } - } - up_read(&cb_lock); -} - static int __net_init genl_pernet_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = genl_rcv, .flags = NL_CFG_F_NONROOT_RECV, - .bind = genl_bind, - .unbind = genl_unbind, }; /* we'll bump the group number right afterwards */ diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 2d8d6131bc5f..24a8c3c6da0d 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -166,6 +166,7 @@ static void __qrtr_node_release(struct kref *kref) { struct qrtr_node *node = container_of(kref, struct qrtr_node, ref); struct radix_tree_iter iter; + struct qrtr_tx_flow *flow; unsigned long flags; void __rcu **slot; @@ -181,8 +182,9 @@ static void __qrtr_node_release(struct kref *kref) /* Free tx flow counters */ radix_tree_for_each_slot(slot, &node->qrtr_tx_flow, &iter, 0) { + flow = *slot; radix_tree_iter_delete(&node->qrtr_tx_flow, &iter, slot); - kfree(*slot); + kfree(flow); } kfree(node); } @@ -427,7 +429,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) unsigned int ver; size_t hdrlen; - if (len & 3) + if (len == 0 || len & 3) return -EINVAL; skb = netdev_alloc_skb(NULL, len); @@ -441,6 +443,8 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) switch (ver) { case QRTR_PROTO_VER_1: + if (len < sizeof(*v1)) + goto err; v1 = data; hdrlen = sizeof(*v1); @@ -454,6 +458,8 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) size = le32_to_cpu(v1->size); break; case QRTR_PROTO_VER_2: + if (len < sizeof(*v2)) + goto err; v2 = data; hdrlen = sizeof(*v2) + v2->optlen; diff --git a/net/rds/connection.c b/net/rds/connection.c index ed7f2133acc2..f2fcab182095 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -905,6 +905,17 @@ void rds_conn_path_connect_if_down(struct rds_conn_path *cp) } EXPORT_SYMBOL_GPL(rds_conn_path_connect_if_down); +/* Check connectivity of all paths + */ +void rds_check_all_paths(struct rds_connection *conn) +{ + int i = 0; + + do { + rds_conn_path_connect_if_down(&conn->c_path[i]); + } while (++i < conn->c_npaths); +} + void rds_conn_connect_if_down(struct rds_connection *conn) { WARN_ON(conn->c_trans->t_mp_capable); diff --git a/net/rds/rds.h b/net/rds/rds.h index 6019b0c004a9..106e862996b9 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -778,6 +778,7 @@ void rds_conn_drop(struct rds_connection *conn); void rds_conn_path_drop(struct rds_conn_path *cpath, bool destroy); void rds_conn_connect_if_down(struct rds_connection *conn); void rds_conn_path_connect_if_down(struct rds_conn_path *cp); +void rds_check_all_paths(struct rds_connection *conn); void rds_for_each_conn_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens, @@ -823,6 +824,12 @@ rds_conn_path_up(struct rds_conn_path *cp) } static inline int +rds_conn_path_down(struct rds_conn_path *cp) +{ + return atomic_read(&cp->cp_state) == RDS_CONN_DOWN; +} + +static inline int rds_conn_up(struct rds_connection *conn) { WARN_ON(conn->c_trans->t_mp_capable); diff --git a/net/rds/send.c b/net/rds/send.c index 68e2bdb08fd0..9a529a01cdc6 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1340,7 +1340,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) goto out; } - rds_conn_path_connect_if_down(cpath); + if (rds_conn_path_down(cpath)) + rds_check_all_paths(conn); ret = rds_cong_wait(conn->c_fcong, dport, nonblock, rs); if (ret) { diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 43a243081e7d..f901421b0634 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -43,17 +43,20 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&ca->tcf_tm); bstats_update(&ca->tcf_bstats, skb); - if (skb->protocol == htons(ETH_P_IP)) { + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): if (skb->len < sizeof(struct iphdr)) goto out; proto = NFPROTO_IPV4; - } else if (skb->protocol == htons(ETH_P_IPV6)) { + break; + case htons(ETH_P_IPV6): if (skb->len < sizeof(struct ipv6hdr)) goto out; proto = NFPROTO_IPV6; - } else { + break; + default: goto out; } diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index cb8608f0a77a..c60674cf25c4 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -587,7 +587,7 @@ static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a, goto drop; update_flags = params->update_flags; - protocol = tc_skb_protocol(skb); + protocol = skb_protocol(skb, false); again: switch (protocol) { case cpu_to_be16(ETH_P_IP): diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index e9f3576cbf71..86ed02487467 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -624,7 +624,7 @@ static u8 tcf_ct_skb_nf_family(struct sk_buff *skb) { u8 family = NFPROTO_UNSPEC; - switch (skb->protocol) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): family = NFPROTO_IPV4; break; @@ -748,6 +748,7 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype) { + __be16 proto = skb_protocol(skb, true); int hooknum, err = NF_ACCEPT; /* See HOOK2MANIP(). */ @@ -759,14 +760,13 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, switch (ctinfo) { case IP_CT_RELATED: case IP_CT_RELATED_REPLY: - if (skb->protocol == htons(ETH_P_IP) && + if (proto == htons(ETH_P_IP) && ip_hdr(skb)->protocol == IPPROTO_ICMP) { if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, hooknum)) err = NF_DROP; goto out; - } else if (IS_ENABLED(CONFIG_IPV6) && - skb->protocol == htons(ETH_P_IPV6)) { + } else if (IS_ENABLED(CONFIG_IPV6) && proto == htons(ETH_P_IPV6)) { __be16 frag_off; u8 nexthdr = ipv6_hdr(skb)->nexthdr; int hdrlen = ipv6_skip_exthdr(skb, @@ -1550,4 +1550,3 @@ MODULE_AUTHOR("Yossi Kuperman <[email protected]>"); MODULE_AUTHOR("Marcelo Ricardo Leitner <[email protected]>"); MODULE_DESCRIPTION("Connection tracking action"); MODULE_LICENSE("GPL v2"); - diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 19649623493b..b5042f3ea079 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -96,19 +96,22 @@ static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, action = READ_ONCE(ca->tcf_action); wlen = skb_network_offset(skb); - if (tc_skb_protocol(skb) == htons(ETH_P_IP)) { + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen)) goto out; proto = NFPROTO_IPV4; - } else if (tc_skb_protocol(skb) == htons(ETH_P_IPV6)) { + break; + case htons(ETH_P_IPV6): wlen += sizeof(struct ipv6hdr); if (!pskb_may_pull(skb, wlen)) goto out; proto = NFPROTO_IPV6; - } else { + break; + default: goto out; } diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index be3f215cd027..8118e2640979 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -82,7 +82,7 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, goto drop; break; case TCA_MPLS_ACT_PUSH: - new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol)); + new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb_protocol(skb, true))); if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len, skb->dev && skb->dev->type == ARPHRD_ETHER)) goto drop; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index b125b2be4467..b2b3faa57294 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -41,7 +41,7 @@ static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a, if (params->flags & SKBEDIT_F_INHERITDSFIELD) { int wlen = skb_network_offset(skb); - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen)) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index faa78b7dd962..e62beec0d844 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1538,7 +1538,7 @@ static inline int __tcf_classify(struct sk_buff *skb, reclassify: #endif for (; tp; tp = rcu_dereference_bh(tp->next)) { - __be16 protocol = tc_skb_protocol(skb); + __be16 protocol = skb_protocol(skb, false); int err; if (tp->protocol != protocol && diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 80ae7b9fa90a..ab53a93b2f2b 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -80,7 +80,7 @@ static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow) if (dst) return ntohl(dst); - return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); + return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true); } static u32 flow_get_proto(const struct sk_buff *skb, @@ -104,7 +104,7 @@ static u32 flow_get_proto_dst(const struct sk_buff *skb, if (flow->ports.ports) return ntohs(flow->ports.dst); - return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); + return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true); } static u32 flow_get_iif(const struct sk_buff *skb) @@ -151,7 +151,7 @@ static u32 flow_get_nfct(const struct sk_buff *skb) static u32 flow_get_nfct_src(const struct sk_buff *skb, const struct flow_keys *flow) { - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): return ntohl(CTTUPLE(skb, src.u3.ip)); case htons(ETH_P_IPV6): @@ -164,7 +164,7 @@ fallback: static u32 flow_get_nfct_dst(const struct sk_buff *skb, const struct flow_keys *flow) { - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): return ntohl(CTTUPLE(skb, dst.u3.ip)); case htons(ETH_P_IPV6): diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index b2da37286082..e30bd969fc48 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -313,7 +313,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, /* skb_flow_dissect() does not set n_proto in case an unknown * protocol, so do it rather here. */ - skb_key.basic.n_proto = skb->protocol; + skb_key.basic.n_proto = skb_protocol(skb, false); skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key); skb_flow_dissect_ct(skb, &mask->dissector, &skb_key, fl_ct_info_to_flower_map, diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c index df00566d327d..c95cf86fb431 100644 --- a/net/sched/em_ipset.c +++ b/net/sched/em_ipset.c @@ -59,7 +59,7 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em, }; int ret, network_offset; - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): state.pf = NFPROTO_IPV4; if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) diff --git a/net/sched/em_ipt.c b/net/sched/em_ipt.c index 18755d29fd15..3650117da47f 100644 --- a/net/sched/em_ipt.c +++ b/net/sched/em_ipt.c @@ -212,7 +212,7 @@ static int em_ipt_match(struct sk_buff *skb, struct tcf_ematch *em, struct nf_hook_state state; int ret; - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) return 0; diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index d99966a55c84..46254968d390 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -195,7 +195,7 @@ META_COLLECTOR(int_priority) META_COLLECTOR(int_protocol) { /* Let userspace take care of the byte ordering */ - dst->value = tc_skb_protocol(skb); + dst->value = skb_protocol(skb, false); } META_COLLECTOR(int_pkttype) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index ca813697728e..ebaeec1e5c82 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -592,7 +592,7 @@ static bool cake_update_flowkeys(struct flow_keys *keys, bool rev = !skb->_nfct, upd = false; __be32 ip; - if (tc_skb_protocol(skb) != htons(ETH_P_IP)) + if (skb_protocol(skb, true) != htons(ETH_P_IP)) return false; if (!nf_ct_get_tuple_skb(&tuple, skb)) @@ -1557,7 +1557,7 @@ static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash) u16 *buf, buf_; u8 dscp; - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); if (unlikely(!buf)) diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 05605b30bef3..2b88710994d7 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -210,7 +210,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (p->set_tc_index) { int wlen = skb_network_offset(skb); - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen) || @@ -303,7 +303,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) index = skb->tc_index & (p->indices - 1); pr_debug("index %d->%d\n", skb->tc_index, index); - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask, p->mv[index].value); @@ -320,7 +320,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) */ if (p->mv[index].mask != 0xff || p->mv[index].value) pr_warn("%s: unsupported protocol %d\n", - __func__, ntohs(tc_skb_protocol(skb))); + __func__, ntohs(skb_protocol(skb, true))); break; } diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 689ef6f3ded8..2f1f0a378408 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -239,7 +239,7 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, char haddr[MAX_ADDR_LEN]; neigh_ha_snapshot(haddr, n, dev); - err = dev_hard_header(skb, dev, ntohs(tc_skb_protocol(skb)), + err = dev_hard_header(skb, dev, ntohs(skb_protocol(skb, false)), haddr, NULL, skb->len); if (err < 0) diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 540ed75e4482..08b80669f649 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -2,9 +2,6 @@ #include <net/xsk_buff_pool.h> #include <net/xdp_sock.h> -#include <linux/dma-direct.h> -#include <linux/dma-noncoherent.h> -#include <linux/swiotlb.h> #include "xsk_queue.h" @@ -55,7 +52,6 @@ struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks, pool->free_heads_cnt = chunks; pool->headroom = headroom; pool->chunk_size = chunk_size; - pool->cheap_dma = true; pool->unaligned = unaligned; pool->frame_len = chunk_size - headroom - XDP_PACKET_HEADROOM; INIT_LIST_HEAD(&pool->free_list); @@ -125,48 +121,6 @@ static void xp_check_dma_contiguity(struct xsk_buff_pool *pool) } } -static bool __maybe_unused xp_check_swiotlb_dma(struct xsk_buff_pool *pool) -{ -#if defined(CONFIG_SWIOTLB) - phys_addr_t paddr; - u32 i; - - for (i = 0; i < pool->dma_pages_cnt; i++) { - paddr = dma_to_phys(pool->dev, pool->dma_pages[i]); - if (is_swiotlb_buffer(paddr)) - return false; - } -#endif - return true; -} - -static bool xp_check_cheap_dma(struct xsk_buff_pool *pool) -{ -#if defined(CONFIG_HAS_DMA) - const struct dma_map_ops *ops = get_dma_ops(pool->dev); - - if (ops) { - return !ops->sync_single_for_cpu && - !ops->sync_single_for_device; - } - - if (!dma_is_direct(ops)) - return false; - - if (!xp_check_swiotlb_dma(pool)) - return false; - - if (!dev_is_dma_coherent(pool->dev)) { -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) - return false; -#endif - } -#endif - return true; -} - int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, unsigned long attrs, struct page **pages, u32 nr_pages) { @@ -180,6 +134,7 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, pool->dev = dev; pool->dma_pages_cnt = nr_pages; + pool->dma_need_sync = false; for (i = 0; i < pool->dma_pages_cnt; i++) { dma = dma_map_page_attrs(dev, pages[i], 0, PAGE_SIZE, @@ -188,14 +143,13 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, xp_dma_unmap(pool, attrs); return -ENOMEM; } + if (dma_need_sync(dev, dma)) + pool->dma_need_sync = true; pool->dma_pages[i] = dma; } if (pool->unaligned) xp_check_dma_contiguity(pool); - - pool->dev = dev; - pool->cheap_dma = xp_check_cheap_dma(pool); return 0; } EXPORT_SYMBOL(xp_dma_map); @@ -280,7 +234,7 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool) xskb->xdp.data = xskb->xdp.data_hard_start + XDP_PACKET_HEADROOM; xskb->xdp.data_meta = xskb->xdp.data; - if (!pool->cheap_dma) { + if (pool->dma_need_sync) { dma_sync_single_range_for_device(pool->dev, xskb->dma, 0, pool->frame_len, DMA_BIDIRECTIONAL); diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index c407ecbc5d46..b615729812e5 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -37,6 +37,7 @@ #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_route.h> +#include <net/ip_tunnels.h> #include <net/addrconf.h> #include <net/xfrm.h> #include <net/net_namespace.h> @@ -581,6 +582,7 @@ static const struct net_device_ops xfrmi_netdev_ops = { static void xfrmi_dev_setup(struct net_device *dev) { dev->netdev_ops = &xfrmi_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->type = ARPHRD_NONE; dev->mtu = ETH_DATA_LEN; dev->min_mtu = ETH_MIN_MTU; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 974a71342aea..8bd33050b7bb 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3171,13 +3171,12 @@ union bpf_attr { * int bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) * Description * Copy *size* bytes from *data* into a ring buffer *ringbuf*. - * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of - * new data availability is sent. - * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of - * new data availability is sent unconditionally. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. * Return - * 0, on success; - * < 0, on error. + * 0 on success, or a negative error in case of failure. * * void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags) * Description @@ -3189,20 +3188,20 @@ union bpf_attr { * void bpf_ringbuf_submit(void *data, u64 flags) * Description * Submit reserved ring buffer sample, pointed to by *data*. - * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of - * new data availability is sent. - * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of - * new data availability is sent unconditionally. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. * Return * Nothing. Always succeeds. * * void bpf_ringbuf_discard(void *data, u64 flags) * Description * Discard reserved ring buffer sample, pointed to by *data*. - * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of - * new data availability is sent. - * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of - * new data availability is sent unconditionally. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. * Return * Nothing. Always succeeds. * @@ -3210,16 +3209,18 @@ union bpf_attr { * Description * Query various characteristics of provided ring buffer. What * exactly is queries is determined by *flags*: - * - BPF_RB_AVAIL_DATA - amount of data not yet consumed; - * - BPF_RB_RING_SIZE - the size of ring buffer; - * - BPF_RB_CONS_POS - consumer position (can wrap around); - * - BPF_RB_PROD_POS - producer(s) position (can wrap around); - * Data returned is just a momentary snapshots of actual values + * + * * **BPF_RB_AVAIL_DATA**: Amount of data not yet consumed. + * * **BPF_RB_RING_SIZE**: The size of ring buffer. + * * **BPF_RB_CONS_POS**: Consumer position (can wrap around). + * * **BPF_RB_PROD_POS**: Producer(s) position (can wrap around). + * + * Data returned is just a momentary snapshot of actual values * and could be inaccurate, so this facility should be used to * power heuristics and for reporting, not to make 100% correct * calculation. * Return - * Requested value, or 0, if flags are not recognized. + * Requested value, or 0, if *flags* are not recognized. * * int bpf_csum_level(struct sk_buff *skb, u64 level) * Description diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 1b6015b21ba8..dbef24ebcfcb 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -233,6 +233,8 @@ LIBBPF_API int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset, __u64 *probe_addr); + +enum bpf_stats_type; /* defined in up-to-date linux/bpf.h */ LIBBPF_API int bpf_enable_stats(enum bpf_stats_type type); #ifdef __cplusplus diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 477c679ed945..11e4725b8b1c 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -4818,7 +4818,13 @@ bpf_core_reloc_fields(struct bpf_object *obj, const char *targ_btf_path) err = -EINVAL; goto out; } - prog = bpf_object__find_program_by_title(obj, sec_name); + prog = NULL; + for (i = 0; i < obj->nr_programs; i++) { + if (!strcmp(obj->programs[i].section_name, sec_name)) { + prog = &obj->programs[i]; + break; + } + } if (!prog) { pr_warn("failed to find program '%s' for CO-RE offset relocation\n", sec_name); @@ -6653,7 +6659,7 @@ static const struct bpf_sec_def section_defs[] = { .expected_attach_type = BPF_TRACE_ITER, .is_attach_btf = true, .attach_fn = attach_iter), - BPF_EAPROG_SEC("xdp_devmap", BPF_PROG_TYPE_XDP, + BPF_EAPROG_SEC("xdp_devmap/", BPF_PROG_TYPE_XDP, BPF_XDP_DEVMAP), BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c index 83493bd5745c..109d0345a2be 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c @@ -36,7 +36,7 @@ void test_fentry_fexit(void) fentry_res = (__u64 *)fentry_skel->bss; fexit_res = (__u64 *)fexit_skel->bss; printf("%lld\n", fentry_skel->bss->test1_result); - for (i = 0; i < 6; i++) { + for (i = 0; i < 8; i++) { CHECK(fentry_res[i] != 1, "result", "fentry_test%d failed err %lld\n", i + 1, fentry_res[i]); CHECK(fexit_res[i] != 1, "result", diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index ea14e3ece812..f11f187990e9 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -527,8 +527,8 @@ static void test_skb_less_prog_attach(struct bpf_flow *skel, int tap_fd) run_tests_skb_less(tap_fd, skel->maps.last_dissection); - err = bpf_prog_detach(prog_fd, BPF_FLOW_DISSECTOR); - CHECK(err, "bpf_prog_detach", "err %d errno %d\n", err, errno); + err = bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR); + CHECK(err, "bpf_prog_detach2", "err %d errno %d\n", err, errno); } static void test_skb_less_link_create(struct bpf_flow *skel, int tap_fd) diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c index 15cb554a66d8..172c586b6996 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c @@ -1,9 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Test that the flow_dissector program can be updated with a single - * syscall by attaching a new program that replaces the existing one. - * - * Corner case - the same program cannot be attached twice. + * Tests for attaching, detaching, and replacing flow_dissector BPF program. */ #define _GNU_SOURCE @@ -116,7 +113,7 @@ static void test_prog_attach_prog_attach(int netns, int prog1, int prog2) CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog2)); out_detach: - err = bpf_prog_detach(0, BPF_FLOW_DISSECTOR); + err = bpf_prog_detach2(prog2, 0, BPF_FLOW_DISSECTOR); if (CHECK_FAIL(err)) perror("bpf_prog_detach"); CHECK_FAIL(prog_is_attached(netns)); @@ -152,7 +149,7 @@ static void test_prog_attach_link_create(int netns, int prog1, int prog2) DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts); int err, link; - err = bpf_prog_attach(prog1, -1, BPF_FLOW_DISSECTOR, 0); + err = bpf_prog_attach(prog1, 0, BPF_FLOW_DISSECTOR, 0); if (CHECK_FAIL(err)) { perror("bpf_prog_attach(prog1)"); return; @@ -168,7 +165,7 @@ static void test_prog_attach_link_create(int netns, int prog1, int prog2) close(link); CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); - err = bpf_prog_detach(-1, BPF_FLOW_DISSECTOR); + err = bpf_prog_detach2(prog1, 0, BPF_FLOW_DISSECTOR); if (CHECK_FAIL(err)) perror("bpf_prog_detach"); CHECK_FAIL(prog_is_attached(netns)); @@ -188,7 +185,7 @@ static void test_link_create_prog_attach(int netns, int prog1, int prog2) /* Expect failure attaching prog when link exists */ errno = 0; - err = bpf_prog_attach(prog2, -1, BPF_FLOW_DISSECTOR, 0); + err = bpf_prog_attach(prog2, 0, BPF_FLOW_DISSECTOR, 0); if (CHECK_FAIL(!err || errno != EEXIST)) perror("bpf_prog_attach(prog2) expected EEXIST"); CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); @@ -211,7 +208,7 @@ static void test_link_create_prog_detach(int netns, int prog1, int prog2) /* Expect failure detaching prog when link exists */ errno = 0; - err = bpf_prog_detach(-1, BPF_FLOW_DISSECTOR); + err = bpf_prog_detach2(prog1, 0, BPF_FLOW_DISSECTOR); if (CHECK_FAIL(!err || errno != EINVAL)) perror("bpf_prog_detach expected EINVAL"); CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); @@ -231,7 +228,7 @@ static void test_prog_attach_detach_query(int netns, int prog1, int prog2) } CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); - err = bpf_prog_detach(0, BPF_FLOW_DISSECTOR); + err = bpf_prog_detach2(prog1, 0, BPF_FLOW_DISSECTOR); if (CHECK_FAIL(err)) { perror("bpf_prog_detach"); return; @@ -308,6 +305,31 @@ static void test_link_update_replace_old_prog(int netns, int prog1, int prog2) CHECK_FAIL(prog_is_attached(netns)); } +static void test_link_update_same_prog(int netns, int prog1, int prog2) +{ + DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts); + DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts); + int err, link; + + link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts); + if (CHECK_FAIL(link < 0)) { + perror("bpf_link_create(prog1)"); + return; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + /* Expect success updating the prog with the same one */ + update_opts.flags = 0; + update_opts.old_prog_fd = 0; + err = bpf_link_update(link, prog1, &update_opts); + if (CHECK_FAIL(err)) + perror("bpf_link_update"); + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + close(link); + CHECK_FAIL(prog_is_attached(netns)); +} + static void test_link_update_invalid_opts(int netns, int prog1, int prog2) { DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts); @@ -571,6 +593,8 @@ static void run_tests(int netns) test_link_update_no_old_prog }, { "link update with replace old prog", test_link_update_replace_old_prog }, + { "link update with same prog", + test_link_update_same_prog }, { "link update invalid opts", test_link_update_invalid_opts }, { "link update invalid prog", diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c index e7b8753eac0b..75ecf956a2df 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c @@ -25,7 +25,7 @@ struct bpf_iter__netlink { struct netlink_sock *sk; } __attribute__((preserve_access_index)); -static inline struct inode *SOCK_INODE(struct socket *socket) +static __attribute__((noinline)) struct inode *SOCK_INODE(struct socket *socket) { return &container_of(socket, struct socket_alloc, socket)->vfs_inode; } diff --git a/tools/testing/selftests/bpf/progs/fentry_test.c b/tools/testing/selftests/bpf/progs/fentry_test.c index 9365b686f84b..5f645fdaba6f 100644 --- a/tools/testing/selftests/bpf/progs/fentry_test.c +++ b/tools/testing/selftests/bpf/progs/fentry_test.c @@ -55,3 +55,25 @@ int BPF_PROG(test6, __u64 a, void *b, short c, int d, void * e, __u64 f) e == (void *)20 && f == 21; return 0; } + +struct bpf_fentry_test_t { + struct bpf_fentry_test_t *a; +}; + +__u64 test7_result = 0; +SEC("fentry/bpf_fentry_test7") +int BPF_PROG(test7, struct bpf_fentry_test_t *arg) +{ + if (arg == 0) + test7_result = 1; + return 0; +} + +__u64 test8_result = 0; +SEC("fentry/bpf_fentry_test8") +int BPF_PROG(test8, struct bpf_fentry_test_t *arg) +{ + if (arg->a == 0) + test8_result = 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/fexit_test.c b/tools/testing/selftests/bpf/progs/fexit_test.c index bd1e17d8024c..0952affb22a6 100644 --- a/tools/testing/selftests/bpf/progs/fexit_test.c +++ b/tools/testing/selftests/bpf/progs/fexit_test.c @@ -56,3 +56,25 @@ int BPF_PROG(test6, __u64 a, void *b, short c, int d, void *e, __u64 f, int ret) e == (void *)20 && f == 21 && ret == 111; return 0; } + +struct bpf_fentry_test_t { + struct bpf_fentry_test *a; +}; + +__u64 test7_result = 0; +SEC("fexit/bpf_fentry_test7") +int BPF_PROG(test7, struct bpf_fentry_test_t *arg) +{ + if (arg == 0) + test7_result = 1; + return 0; +} + +__u64 test8_result = 0; +SEC("fexit/bpf_fentry_test8") +int BPF_PROG(test8, struct bpf_fentry_test_t *arg) +{ + if (arg->a == 0) + test8_result = 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h index 057036ca1111..3dca4c2e2418 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h +++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h @@ -79,7 +79,7 @@ struct { struct { __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 2); + __uint(max_entries, 3); __type(key, int); __type(value, int); } sock_skb_opts SEC(".maps"); @@ -94,6 +94,12 @@ struct { SEC("sk_skb1") int bpf_prog1(struct __sk_buff *skb) { + int *f, two = 2; + + f = bpf_map_lookup_elem(&sock_skb_opts, &two); + if (f && *f) { + return *f; + } return skb->len; } diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c index 330811260123..0ac086497722 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c @@ -27,7 +27,7 @@ int xdp_dummy_prog(struct xdp_md *ctx) /* valid program on DEVMAP entry via SEC name; * has access to egress and ingress ifindex */ -SEC("xdp_devmap") +SEC("xdp_devmap/map_prog") int xdp_dummy_dm(struct xdp_md *ctx) { char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n"; diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 37695fc8096a..78789b27e573 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -85,6 +85,7 @@ int txmsg_ktls_skb_drop; int txmsg_ktls_skb_redir; int ktls; int peek_flag; +int skb_use_parser; static const struct option long_options[] = { {"help", no_argument, NULL, 'h' }, @@ -174,6 +175,7 @@ static void test_reset(void) txmsg_apply = txmsg_cork = 0; txmsg_ingress = txmsg_redir_skb = 0; txmsg_ktls_skb = txmsg_ktls_skb_drop = txmsg_ktls_skb_redir = 0; + skb_use_parser = 0; } static int test_start_subtest(const struct _test *t, struct sockmap_options *o) @@ -1211,6 +1213,11 @@ run: } } + if (skb_use_parser) { + i = 2; + err = bpf_map_update_elem(map_fd[7], &i, &skb_use_parser, BPF_ANY); + } + if (txmsg_drop) options->drop_expected = true; @@ -1650,6 +1657,16 @@ static void test_txmsg_cork(int cgrp, struct sockmap_options *opt) test_send(opt, cgrp); } +static void test_txmsg_ingress_parser(int cgrp, struct sockmap_options *opt) +{ + txmsg_pass = 1; + skb_use_parser = 512; + opt->iov_length = 256; + opt->iov_count = 1; + opt->rate = 2; + test_exec(cgrp, opt); +} + char *map_names[] = { "sock_map", "sock_map_txmsg", @@ -1748,6 +1765,7 @@ struct _test test[] = { {"txmsg test pull-data", test_txmsg_pull}, {"txmsg test pop-data", test_txmsg_pop}, {"txmsg test push/pop data", test_txmsg_push_pop}, + {"txmsg text ingress parser", test_txmsg_ingress_parser}, }; static int check_whitelist(struct _test *t, struct sockmap_options *opt) |